Async IO threads (#13665)

## Introduction
Redis introduced IO Thread in 6.0, allowing IO threads to handle client
request reading, command parsing and reply writing, thereby improving
performance. The current IO thread implementation has a few drawbacks.
- The main thread is blocked during IO thread read/write operations and
must wait for all IO threads to complete their current tasks before it
can continue execution. In other words, the entire process is
synchronous. This prevents the efficient utilization of multi-core CPUs
for parallel processing.

- When the number of clients and requests increases moderately, it
causes all IO threads to reach full CPU utilization due to the busy wait
mechanism used by the IO threads. This makes it challenging for us to
determine which part of Redis has reached its bottleneck.

- When IO threads are enabled with TLS and io-threads-do-reads, a
disconnection of a connection with pending data may result in it being
assigned to multiple IO threads simultaneously. This can cause race
conditions and trigger assertion failures. Related issue:
https://github.com/redis/redis/issues/12540

Therefore, we designed an asynchronous IO threads solution. The IO
threads adopt an event-driven model, with the main thread dedicated to
command processing, meanwhile, the IO threads handle client read and
write operations in parallel.

## Implementation
### Overall
As before, we did not change the fact that all client commands must be
executed on the main thread, because Redis was originally designed to be
single-threaded, and processing commands in a multi-threaded manner
would inevitably introduce numerous race and synchronization issues. But
now each IO thread has independent event loop, therefore, IO threads can
use a multiplexing approach to handle client read and write operations,
eliminating the CPU overhead caused by busy-waiting.

the execution process can be briefly described as follows:
the main thread assigns clients to IO threads after accepting
connections, IO threads will notify the main thread when clients
finish reading and parsing queries, then the main thread processes
queries from IO threads and generates replies, IO threads handle
writing reply to clients after receiving clients list from main thread,
and then continue to handle client read and write events.

### Each IO thread has independent event loop
We now assign each IO thread its own event loop. This approach
eliminates the need for the main thread to perform the costly
`epoll_wait` operation for handling connections (except for specific
ones). Instead, the main thread processes requests from the IO threads
and hands them back once completed, fully offloading read and write
events to the IO threads.

Additionally, all TLS operations, including handling pending data, have
been moved entirely to the IO threads. This resolves the issue where
io-threads-do-reads could not be used with TLS.

### Event-notified client queue
To facilitate communication between the IO threads and the main thread,
we designed an event-notified client queue. Each IO thread and the main
thread have two such queues to store clients waiting to be processed.
These queues are also integrated with the event loop to enable handling.
We use pthread_mutex to ensure the safety of queue operations, as well
as data visibility and ordering, and race conditions are minimized, as
each IO thread and the main thread operate on independent queues,
avoiding thread suspension due to lock contention. And we implemented an
event notifier based on `eventfd` or `pipe` to support event-driven
handling.

### Thread safety
Since the main thread and IO threads can execute in parallel, we must
handle data race issues carefully.

**client->flags**
The primary tasks of IO threads are reading and writing, i.e.
`readQueryFromClient` and `writeToClient`. However, IO threads and the
main thread may concurrently modify or access `client->flags`, leading
to potential race conditions. To address this, we introduced an io-flags
variable to record operations performed by IO threads, thereby avoiding
race conditions on `client->flags`.

**Pause IO thread**
In the main thread, we may want to operate data of IO threads, maybe
uninstall event handler, access or operate query/output buffer or resize
event loop, we need a clean and safe context to do that. We pause IO
thread in `IOThreadBeforeSleep`, do some jobs and then resume it. To
avoid thread suspended, we use busy waiting to confirm the target
status. Besides we use atomic variable to make sure memory visibility
and ordering. We introduce these functions to pause/resume IO Threads as
below.
```
pauseIOThread, resumeIOThread
pauseAllIOThreads, resumeAllIOThreads
pauseIOThreadsRange, resumeIOThreadsRange
```
Testing has shown that `pauseIOThread` is highly efficient, allowing the
main thread to execute nearly 200,000 operations per second during
stress tests. Similarly, `pauseAllIOThreads` with 8 IO threads can
handle up to nearly 56,000 operations per second. But operations
performed between pausing and resuming IO threads must be quick;
otherwise, they could cause the IO threads to reach full CPU
utilization.

**freeClient and freeClientAsync**
The main thread may need to terminate a client currently running on an
IO thread, for example, due to ACL rule changes, reaching the output
buffer limit, or evicting a client. In such cases, we need to pause the
IO thread to safely operate on the client.

**maxclients and maxmemory-clients updating**
When adjusting `maxclients`, we need to resize the event loop for all IO
threads. Similarly, when modifying `maxmemory-clients`, we need to
traverse all clients to calculate their memory usage. To ensure safe
operations, we pause all IO threads during these adjustments.

**Client info reading**
The main thread may need to read a client’s fields to generate a
descriptive string, such as for the `CLIENT LIST` command or logging
purposes. In such cases, we need to pause the IO thread handling that
client. If information for all clients needs to be displayed, all IO
threads must be paused.

**Tracking redirect**
Redis supports the tracking feature and can even send invalidation
messages to a connection with a specified ID. But the target client may
be running on IO thread, directly manipulating the client’s output
buffer is not thread-safe, and the IO thread may not be aware that the
client requires a response. In such cases, we pause the IO thread
handling the client, modify the output buffer, and install a write event
handler to ensure proper handling.

**clientsCron**
In the `clientsCron` function, the main thread needs to traverse all
clients to perform operations such as timeout checks, verifying whether
they have reached the soft output buffer limit, resizing the
output/query buffer, or updating memory usage. To safely operate on a
client, the IO thread handling that client must be paused.
If we were to pause the IO thread for each client individually, the
efficiency would be very low. Conversely, pausing all IO threads
simultaneously would be costly, especially when there are many IO
threads, as clientsCron is invoked relatively frequently.
To address this, we adopted a batched approach for pausing IO threads.
At most, 8 IO threads are paused at a time. The operations mentioned
above are only performed on clients running in the paused IO threads,
significantly reducing overhead while maintaining safety.

### Observability
In the current design, the main thread always assigns clients to the IO
thread with the least clients. To clearly observe the number of clients
handled by each IO thread, we added the new section in INFO output. The
`INFO THREADS` section can show the client count for each IO thread.
```
# Threads
io_thread_0:clients=0
io_thread_1:clients=2
io_thread_2:clients=2
```

Additionally, in the `CLIENT LIST` output, we also added a field to
indicate the thread to which each client is assigned.

`id=244 addr=127.0.0.1:41870 laddr=127.0.0.1:6379 ... resp=2 lib-name=
lib-ver= io-thread=1`

## Trade-off
### Special Clients
For certain special types of clients, keeping them running on IO threads
would result in severe race issues that are difficult to resolve.
Therefore, we chose not to offload these clients to the IO threads.

For replica, monitor, subscribe, and tracking clients, main thread may
directly write them a reply when conditions are met. Race issues are
difficult to resolve, so we have them processed in the main thread. This
includes the Lua debug clients as well, since we may operate connection
directly.

For blocking client, after the IO thread reads and parses a command and
hands it over to the main thread, if the client is identified as a
blocking type, it will be remained in the main thread. Once the blocking
operation completes and the reply is generated, the client is
transferred back to the IO thread to send the reply and wait for event
triggers.

### Clients Eviction
To support client eviction, it is necessary to update each client’s
memory usage promptly during operations such as read, write, or command
execution. However, when a client operates on an IO thread, it is not
feasible to update the memory usage immediately due to the risk of data
races. As a result, memory usage can only be updated either in the main
thread while processing commands or in the `ClientsCron` periodically.
The downside of this approach is that updates might experience a delay
of up to one second, which could impact the precision of memory
management for eviction.

To avoid incorrectly evicting clients. We adopted a best-effort
compensation solution, when we decide to eviction a client, we update
its memory usage again before evicting, if the memory used by the client
does not decrease or memory usage bucket is not changed, then we will
evict it, otherwise, not evict it.

However, we have not completely solved this problem. Due to the delay in
memory usage updates, it may lead us to make incorrect decisions about
the need to evict clients.

### Defragment
In the majority of cases we do NOT use the data from argv directly in
the db.
1. key names
We store a copy that we allocate in the main thread, see `sdsdup()` in
`dbAdd()`.
2. hash key and value
We store key as hfield and store value as sds, see `hfieldNew()` and
`sdsdup()` in `hashTypeSet()`.
3. other datatypes
   They don't even use SDS, so there is no reference issues.

But in some cases client the data from argv may be retain by the main
thread.
As a result, during fragmentation cleanup, we need to move allocations
from the IO thread’s arena to the main thread’s arena. We always
allocate new memory in the main thread’s arena, but the memory released
by IO threads may not yet have been reclaimed. This ultimately causes
the fragmentation rate to be higher compared to creating and allocating
entirely within a single thread.
The following cases below will lead to memory allocated by the IO thread
being kept by the main thread.
1. string related command: `append`, `getset`, `mset` and `set`.
If `tryObjectEncoding()` does not change argv, we will keep it directly
in the main thread, see the code in `tryObjectEncoding()`(specifically
`trimStringObjectIfNeeded()`)
2. block related command.
    the key names will be kept in `c->db->blocking_keys`.
3. watch command
    the key names will be kept in `c->db->watched_keys`.
4. [s]subscribe command
    channel name will be kept in `serverPubSubChannels`.
5. script load command
    script will be kept in `server.lua_scripts`.
7. some module API: `RM_RetainString`, `RM_HoldString`

Those issues will be handled in other PRs.

## Testing
### Functional Testing
The commit with enabling IO Threads has passed all TCL tests, but we did
some changes:
**Client query buffer**: In the original code, when using a reusable
query buffer, ownership of the query buffer would be released after the
command was processed. However, with IO threads enabled, the client
transitions from an IO thread to the main thread for processing. This
causes the ownership release to occur earlier than the command
execution. As a result, when IO threads are enabled, the client's
information will never indicate that a shared query buffer is in use.
Therefore, we skip the corresponding query buffer tests in this case.
**Defragment**: Add a new defragmentation test to verify the effect of
io threads on defragmentation.
**Command delay**: For deferred clients in TCL tests, due to clients
being assigned to different threads for execution, delays may occur. To
address this, we introduced conditional waiting: the process proceeds to
the next step only when the `client list` contains the corresponding
commands.

### Sanitizer Testing
The commit passed all TCL tests and reported no errors when compiled
with the `fsanitizer=thread` and `fsanitizer=address` options enabled.
But we made the following modifications: we suppressed the sanitizer
warnings for clients with watched keys when updating `client->flags`, we
think IO threads read `client->flags`, but never modify it or read the
`CLIENT_DIRTY_CAS` bit, main thread just only modifies this bit, so
there is no actual data race.

## Others
### IO thread number
In the new multi-threaded design, the main thread is primarily focused
on command processing to improve performance. Typically, the main thread
does not handle regular client I/O operations but is responsible for
clients such as replication and tracking clients. To avoid breaking
changes, we still consider the main thread as the first IO thread.

When the io-threads configuration is set to a low value (e.g., 2),
performance does not show a significant improvement compared to a
single-threaded setup for simple commands (such as SET or GET), as the
main thread does not consume much CPU for these simple operations. This
results in underutilized multi-core capacity. However, for more complex
commands, having a low number of IO threads may still be beneficial.
Therefore, it’s important to adjust the `io-threads` based on your own
performance tests.

Additionally, you can clearly monitor the CPU utilization of the main
thread and IO threads using `top -H -p $redis_pid`. This allows you to
easily identify where the bottleneck is. If the IO thread is the
bottleneck, increasing the `io-threads` will improve performance. If the
main thread is the bottleneck, the overall performance can only be
scaled by increasing the number of shards or replicas.

---------

Co-authored-by: debing.sun <debing.sun@redis.com>
Co-authored-by: oranagra <oran@redislabs.com>

.github/workflows/ci.yml

@@ -2,16 +2,12 @@ name: CI
 
 on: [push, pull_request]
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
 
   test-ubuntu-latest:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       # Fail build if there are warnings
       # build with TLS just for compilation coverage
@@ -20,6 +16,8 @@ jobs:
       run: |
         sudo apt-get install tcl8.6 tclx
         ./runtest --verbose --tags -slow --dump-logs
+    - name: module api test
+      run: CFLAGS='-Werror' ./runtest-moduleapi --verbose --dump-logs
     - name: validate commands.def up to date
       run: |
         touch src/commands/ping.json
@@ -30,49 +28,47 @@ jobs:
   test-sanitizer-address:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: make
         # build with TLS module just for compilation coverage
-        run: make SANITIZER=address REDIS_CFLAGS='-Werror -DDEBUG_ASSERTIONS -DREDIS_TEST' BUILD_TLS=module
+        run: make SANITIZER=address REDIS_CFLAGS='-Werror -DDEBUG_ASSERTIONS' BUILD_TLS=module
       - name: testprep
         run: sudo apt-get install tcl8.6 tclx -y
       - name: test
         run: ./runtest --verbose --tags -slow --dump-logs
+      - name: module api test
+        run: CFLAGS='-Werror' ./runtest-moduleapi --verbose --dump-logs
 
   build-debian-old:
     runs-on: ubuntu-latest
     container: debian:buster
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       run: |
-        sed -i 's|http://deb.debian.org/debian|http://archive.debian.org/debian|g' /etc/apt/sources.list
-        sed -i 's|http://security.debian.org|http://archive.debian.org/debian-security|g' /etc/apt/sources.list
         apt-get update && apt-get install -y build-essential
         make REDIS_CFLAGS='-Werror'
 
   build-macos-latest:
     runs-on: macos-latest
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
-      # Fail build if there are warnings
-      # build with TLS just for compilation coverage
-      run: make REDIS_CFLAGS='-Werror' BUILD_TLS=yes
+      run: make REDIS_CFLAGS='-Werror'
 
   build-32bit:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       run: |
-        sudo apt-get update && sudo apt-get install libc6-dev-i386 gcc-multilib
+        sudo apt-get update && sudo apt-get install libc6-dev-i386 gcc-multilib g++-multilib
         make REDIS_CFLAGS='-Werror' 32bit
 
   build-libc-malloc:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       run: make REDIS_CFLAGS='-Werror' MALLOC=libc
 
@@ -80,26 +76,27 @@ jobs:
     runs-on: ubuntu-latest
     container: quay.io/centos/centos:stream9
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       run: |
-        dnf -y install which gcc make
+        dnf -y install which gcc gcc-c++ make
         make REDIS_CFLAGS='-Werror'
 
   build-old-chain-jemalloc:
     runs-on: ubuntu-latest
     container: ubuntu:20.04
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: make
       run: |
         apt-get update
         apt-get install -y gnupg2
-        echo "deb http://archive.ubuntu.com/ubuntu/ xenial main" >> /etc/apt/sources.list
-        echo "deb http://archive.ubuntu.com/ubuntu/ xenial universe" >> /etc/apt/sources.list
+        echo "deb http://dk.archive.ubuntu.com/ubuntu/ xenial main" >> /etc/apt/sources.list
+        echo "deb http://dk.archive.ubuntu.com/ubuntu/ xenial universe" >> /etc/apt/sources.list
         apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 40976EAF437D05B5
         apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 3B4FE6ACC0B21F32
         apt-get update
-        apt-get install -y make gcc-4.8
+        apt-get install -y make gcc-4.8 g++-4.8
         update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-4.8 100
+        update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-4.8 100
         make CC=gcc REDIS_CFLAGS='-Werror'

.github/workflows/codecov.yml

@@ -1,36 +0,0 @@
-name: "Codecov"
-
-# Enabling on each push is to display the coverage changes in every PR, 
-# where each PR needs to be compared against the coverage of the head commit
-on: [push, pull_request]
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  code-coverage:
-    if: ${{ github.repository == 'redis/redis' }}
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v6
-
-    - name: Install lcov and run test
-      run: |
-        sudo apt-get install lcov
-        make lcov
-
-    - name: Upload coverage reports to Codecov
-      uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6
-      env:
-        CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-      with:
-        files: ./src/redis.info
-        disable_search: true
-        fail_ci_if_error: true
-

.github/workflows/codeql-analysis.yml

@@ -6,10 +6,6 @@ on:
     # run weekly new vulnerability was added to the database
     - cron: '0 0 * * 0'
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   analyze:
     name: Analyze
@@ -23,15 +19,15 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v6
+      uses: actions/checkout@v4
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v4
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
 
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v4
+      uses: github/codeql-action/autobuild@v3
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v4
+      uses: github/codeql-action/analyze@v3

.github/workflows/coverity.yml

@@ -6,24 +6,17 @@ on:
   - cron: '0 0 * * *'
   # Support manual execution
   workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   coverity:
     if: github.repository == 'redis/redis'
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@main
     - name: Download and extract the Coverity Build Tool
       run: |
-          wget -q https://scan.coverity.com/download/cxx/linux64 --post-data "token=${COVERITY_SCAN_TOKEN}&project=redis-unstable" -O cov-analysis-linux64.tar.gz
+          wget -q https://scan.coverity.com/download/cxx/linux64 --post-data "token=${{ secrets.COVERITY_SCAN_TOKEN }}&project=redis-unstable" -O cov-analysis-linux64.tar.gz
           mkdir cov-analysis-linux64
           tar xzf cov-analysis-linux64.tar.gz --strip 1 -C cov-analysis-linux64
-      env:
-        COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}
     - name: Install Redis dependencies
       run: sudo apt install -y gcc tcl8.6 tclx procps libssl-dev
     - name: Build with cov-build
@@ -33,10 +26,7 @@ jobs:
           tar czvf cov-int.tgz cov-int
           curl \
             --form project=redis-unstable \
-            --form email="${COVERITY_SCAN_EMAIL}" \
-            --form token="${COVERITY_SCAN_TOKEN}" \
+            --form email=${{ secrets.COVERITY_SCAN_EMAIL }} \
+            --form token=${{ secrets.COVERITY_SCAN_TOKEN }} \
             --form file=@cov-int.tgz \
             https://scan.coverity.com/builds
-      env:
-        COVERITY_SCAN_EMAIL: ${{ secrets.COVERITY_SCAN_EMAIL }}
-        COVERITY_SCAN_TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}

.github/workflows/deploy.yml

@@ -1,16 +0,0 @@
-name: Docker
-on:
-  workflow_dispatch:
-  push:
-    branches: [main, dev, test, unstable]
-    tags: ['v*']
-permissions:
-  contents: read
-  packages: write
-  id-token: write
-jobs:
-  docker:
-    uses: hanzoai/.github/.github/workflows/docker-build.yml@main
-    with:
-      image: ghcr.io/hanzoai/memory
-    secrets: inherit

.github/workflows/external.yml

@@ -6,17 +6,13 @@ on:
     schedule:
       - cron: '0 0 * * *'
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   test-external-standalone:
     runs-on: ubuntu-latest
     if: github.event_name != 'schedule' || github.repository == 'redis/redis'
-    timeout-minutes: 360
+    timeout-minutes: 14400
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: Build
       run: make REDIS_CFLAGS=-Werror
     - name: Start redis-server
@@ -31,7 +27,7 @@ jobs:
             --tags -slow
     - name: Archive redis log
       if: ${{ failure() }}
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v3
       with:
         name: test-external-redis-log
         path: external-redis.log
@@ -39,9 +35,9 @@ jobs:
   test-external-cluster:
     runs-on: ubuntu-latest
     if: github.event_name != 'schedule' || github.repository == 'redis/redis'
-    timeout-minutes: 360
+    timeout-minutes: 14400
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
     - name: Build
       run: make REDIS_CFLAGS=-Werror
     - name: Start redis-server
@@ -59,7 +55,7 @@ jobs:
             --tags -slow
     - name: Archive redis log
       if: ${{ failure() }}
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v3
       with:
         name: test-external-cluster-log
         path: external-redis-cluster.log
@@ -67,9 +63,9 @@ jobs:
   test-external-nodebug:
     runs-on: ubuntu-latest
     if: github.event_name != 'schedule' || github.repository == 'redis/redis'
-    timeout-minutes: 360
+    timeout-minutes: 14400
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Build
         run: make REDIS_CFLAGS=-Werror
       - name: Start redis-server
@@ -83,7 +79,7 @@ jobs:
             --tags "-slow -needs:debug"
       - name: Archive redis log
         if: ${{ failure() }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v3
         with:
           name: test-external-redis-nodebug-log
           path: external-redis-nodebug.log

.github/workflows/redis_docs_sync.yaml

@@ -11,7 +11,7 @@ jobs:
     steps:
       - name: Generate a token
         id: generate-token
-        uses: actions/create-github-app-token@v3
+        uses: actions/create-github-app-token@v1
         with:
           app-id: ${{ secrets.DOCS_APP_ID }}
           private-key: ${{ secrets.DOCS_APP_PRIVATE_KEY }}

.github/workflows/reply-schemas-linter.yml

@@ -8,17 +8,13 @@ on:
     paths:
       - 'src/commands/*.json'
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   reply-schemas-linter:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup nodejs
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
       - name: Install packages
         run: npm install ajv
       - name: linter

.github/workflows/spell-check.yml

@@ -9,10 +9,6 @@ on:
   push:
   pull_request:
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.head_ref || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   build:
     name: Spellcheck
@@ -20,10 +16,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: pip cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
         with:
           path: ~/.cache/pip
           key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}

.github/workflows/workflow-sanity.yml

@@ -1,7 +0,0 @@
-name: Workflow Sanity
-on:
-  pull_request:
-    paths: ['.github/workflows/**']
-jobs:
-  sanity:
-    uses: hanzoai/.github/.github/workflows/workflow-sanity.yml@main

.gitignore

@@ -30,7 +30,7 @@ deps/lua/src/luac
 deps/lua/src/liblua.a
 deps/hdr_histogram/libhdrhistogram.a
 deps/fpconv/libfpconv.a
-deps/tre/libtre.a
+deps/fast_float/libfast_float.a
 tests/tls/*
 .make-*
 .prerequisites

AGENTS.md

@@ -1 +0,0 @@
-LLM.md

CLAUDE.md

@@ -1 +0,0 @@
-LLM.md

CONTRIBUTING.md

@@ -1,7 +1,7 @@
 By contributing code to the Redis project in any form you agree to the Redis Software Grant and
 Contributor License Agreement attached below. Only contributions made under the Redis Software Grant
 and Contributor License Agreement may be accepted by Redis, and any contribution is subject to the
-terms of the Redis tri-license under RSALv2/SSPLv1/AGPLv3 as described in the LICENSE.txt file included in
+terms of the Redis dual-license under RSALv2/SSPLv1 as described in the LICENSE.txt file included in
 the Redis source distribution.
 
 # REDIS SOFTWARE GRANT AND CONTRIBUTOR LICENSE AGREEMENT
@@ -9,7 +9,7 @@ the Redis source distribution.
 To specify the intellectual property license granted in any Contribution, Redis Ltd., ("**Redis**")
 requires a Software Grant and Contributor License Agreement ("**Agreement**"). This Agreement is for
 your protection as a contributor as well as the protection of Redis and its users; it does not
-change your rights to use your own Contribution for any other purpose permitted by this Agreement.
+change your rights to use your own Contribution for any other purpose.
 
 By making any Contribution, You accept and agree to the following terms and conditions for the
 Contribution. Except for the license granted in this Agreement to Redis and the recipients of the
@@ -115,4 +115,4 @@ view, and so forth. This helps.
 
 4. For minor fixes - open a pull request on GitHub.
 
-Additional information on the RSALv2/SSPLv1/AGPLv3 tri-license is also found in the LICENSE.txt file.
+Additional information on the RSALv2/SSPLv1 dual-license is also found in the LICENSE.txt file.

Dockerfile

@@ -1,37 +0,0 @@
-FROM --platform=$TARGETPLATFORM alpine:latest AS builder
-
-RUN apk add --no-cache gcc g++ make musl-dev linux-headers
-
-WORKDIR /src
-COPY . /src
-
-RUN make -j$(nproc) BUILD_TLS=no MALLOC=libc
-
-FROM --platform=$TARGETPLATFORM alpine:latest
-
-LABEL maintainer="dev@hanzo.ai"
-LABEL org.opencontainers.image.title="Hanzo Memory"
-LABEL org.opencontainers.image.description="Redis-compatible in-memory store — Hanzo Memory"
-LABEL org.opencontainers.image.vendor="Hanzo AI"
-LABEL org.opencontainers.image.source="https://github.com/hanzoai/redis"
-
-RUN addgroup -S memory && adduser -S memory -G memory
-
-COPY --from=builder /src/src/redis-server    /usr/local/bin/redis-server
-COPY --from=builder /src/src/redis-cli       /usr/local/bin/redis-cli
-COPY --from=builder /src/src/redis-sentinel  /usr/local/bin/redis-sentinel
-COPY --from=builder /src/src/redis-benchmark /usr/local/bin/redis-benchmark
-
-RUN mkdir -p /data && chown memory:memory /data
-VOLUME /data
-WORKDIR /data
-
-EXPOSE 6379
-
-USER memory
-
-HEALTHCHECK --interval=15s --timeout=3s --start-period=10s --retries=3 \
-    CMD redis-cli ping | grep -q PONG || exit 1
-
-ENTRYPOINT ["redis-server"]
-CMD ["--bind", "0.0.0.0", "--dir", "/data", "--maxmemory-policy", "allkeys-lru", "--protected-mode", "no"]

LICENSE.txt

@@ -1,11 +1,8 @@
-Starting with Redis 8, Redis Open Source is moving to a tri-licensing model with all new Redis code
-contributions governed by the updated Redis Software Grant and Contributor License Agreement.
-After this release, contributions are subject to your choice of: (a) the Redis Source Available License v2
-(RSALv2);or (b) the Server Side Public License v1 (SSPLv1); or (c) the GNU Affero General Public License v3 (AGPLv3).
-Redis Open Source 7.2 and prior releases remain subject to the BSDv3 clause license as referenced
-in the REDISCONTRIBUTIONS.txt file.
-
-The licensing structure for Redis 8.0 and subsequent releases is as follows:
+Starting on March 20th, 2024, Redis follows a dual-licensing model with all Redis project code
+contributions under version 7.4 and subsequent releases governed by the Redis Software Grant and
+Contributor License Agreement. After this date, contributions are subject to the user's choice of
+the Redis Source Available License v2 (RSALv2) or the Server Side Public License v1 (SSPLv1), as
+follows:
 
 
 1. Redis Source Available License 2.0 (RSALv2) Agreement
@@ -734,666 +731,3 @@ exclusive jurisdiction for all purposes relating to this Agreement.
   return for a fee.
 
                         END OF TERMS AND CONDITIONS
-
-
-3. GNU AFFERO GENERAL PUBLIC LICENSE, Version 3, 19 Nov 2007
-========================================================
-
- Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The GNU Affero General Public License is a free, copyleft license for
-software and other kinds of works, specifically designed to ensure
-cooperation with the community in the case of network server software.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-our General Public Licenses are intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-them if you wish), that you receive source code or can get it if you
-want it, that you can change the software or use pieces of it in new
-free programs, and that you know you can do these things.
-
-  Developers that use our General Public Licenses protect your rights
-with two steps: (1) assert copyright on the software, and (2) offer
-you this License which gives you legal permission to copy, distribute
-and/or modify the software.
-
-  A secondary benefit of defending all users' freedom is that
-improvements made in alternate versions of the program, if they
-receive widespread use, become available for other developers to
-incorporate.  Many developers of free software are heartened and
-encouraged by the resulting cooperation.  However, in the case of
-software used on network servers, this result may fail to come about.
-The GNU General Public License permits making a modified version and
-letting the public access it on a server without ever releasing its
-source code to the public.
-
-  The GNU Affero General Public License is designed specifically to
-ensure that, in such cases, the modified source code becomes available
-to the community.  It requires the operator of a network server to
-provide the source code of the modified version running there to the
-users of that server.  Therefore, public use of a modified version, on
-a publicly accessible server, gives the public access to the source
-code of the modified version.
-
-  An older license, called the Affero General Public License and
-published by Affero, was designed to accomplish similar goals.  This is
-a different license, not a version of the Affero GPL, but Affero has
-released a new version of the Affero GPL which permits relicensing under
-this license.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU Affero General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey verbatim copies of the Program's source code as you
-receive it, in any medium, provided that you conspicuously and
-appropriately publish on each copy an appropriate copyright notice;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Remote Network Interaction; Use with the GNU General Public License.
-
-  Notwithstanding any other provision of this License, if you modify the
-Program, your modified version must prominently offer all users
-interacting with it remotely through a computer network (if your version
-supports such interaction) an opportunity to receive the Corresponding
-Source of your version by providing access to the Corresponding Source
-from a network server at no charge, through some standard or customary
-means of facilitating copying of software.  This Corresponding Source
-shall include the Corresponding Source for any work covered by version 3
-of the GNU General Public License that is incorporated pursuant to the
-following paragraph.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the work with which it is combined will remain governed by version
-3 of the GNU General Public License.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU Affero General Public License from time to time.  Such new versions
-will be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-  Each version is given a distinguishing version number.  If the
-Program specifies that a certain numbered version of the GNU Affero General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU Affero General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU Affero General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGES.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU Affero General Public License for more details.
-
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If your software can interact with users remotely through a computer
-network, you should also make sure that it provides a way for users to
-get its source.  For example, if your program is a web application, its
-interface could display a "Source" link that leads users to an archive
-of the code.  There are many ways you could offer source, and different
-solutions will be better for different programs; see section 13 for the
-specific requirements.
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU AGPL, see
-<https://www.gnu.org/licenses/>.

LLM.md

@@ -1,7 +0,0 @@
-# redis
-
-[![codecov](https://codecov.io/github/redis/redis/graph/badge.svg?token=6bVHb5fRuz)](https://codecov.io/github/redis/redis)
-
-This document serves as both a quick start guide to Redis and a detailed resource for building it from source.
-
-- New to Redis? Start with [What is Redis](#what-is-redis) and [Getting Started](#getting-started)

Makefile

@@ -2,9 +2,6 @@
 
 SUBDIRS = src
 ifeq ($(BUILD_WITH_MODULES), yes)
-	ifeq ($(MAKECMDGOALS),32bit)
-    	$(error BUILD_WITH_MODULES=yes is not supported on 32 bit systems)
-	endif
 	SUBDIRS += modules
 endif
 

REDISCONTRIBUTIONS.txt

@@ -3,10 +3,9 @@ All rights reserved.
 
 Note: Continued Applicability of the BSD-3-Clause License
 
-Despite the shift to the dual-licensing model with version 7.4 (RSALv2 or SSPLv1) and
-the shift to a tri-license option with version 8.0 (RSALv2/SSPLv1/AGPLv3), portions of
-Redis Open Source remain available subject to the BSD-3-Clause License (BSD).
-See below for the full BSD license:
+Despite the shift to the dual-licensing model with Redis Community Edition version 7.4 (RSALv2 or SSPLv1), portions of
+Redis Community Edition remain available subject to the BSD-3-Clause License (BSD). See below for the full BSD
+license:
 
 Redistribution and use in source and binary forms, with or without modification, are permitted
 provided that the following conditions are met:

SECURITY.md

@@ -9,34 +9,20 @@ performance and security.
 We generally backport security issues to a single previous major version,
 unless this is not possible or feasible with a reasonable effort.
 
-| Version | Supported                                                              |
-|---------|------------------------------------------------------------------------|
-| 8.6.x   | :white_check_mark:                                                     |
-| 8.4.x   | :white_check_mark:                                                     |
-| 8.2.x   | :white_check_mark:                                                     |
-| 8.0.x   | :x:                                                                    |
-| 7.4.x   | :white_check_mark:                                                     |
-| 7.2.x   | :white_check_mark: support extended till 7.4 end of support            |
-| < 7.2.x | :x:                                                                    |
-| 6.2.x   | :white_check_mark: support extended                                    |
-| < 6.2.x | :x:                                                                    |
+| Version | Supported          |
+| ------- | ------------------ |
+| 7.4.x   | :white_check_mark: |
+| 7.2.x   | :white_check_mark: |
+| < 7.2.x | :x:                |
+| 6.2.x   | :white_check_mark: |
+| < 6.2.x | :x:                |
 
 ## Reporting a Vulnerability
 
-If you believe you have found a security vulnerability, to ensure proper review 
-and assessment, we kindly ask vulnerability reports be submitted through
-our [Redis Vulnerability Disclosure Program.](https://redis.io/redis-responsible-vulnerability-disclosure/)
-
-We have found this path to be beneficial for both researchers and us for 
-a number of reasons. Including, offering fast response times to researchers and 
-opportunities for us to invite those with exceptional reports into closed paid 
-engagements.  
-
-For those averse to using our chosen platform, we will also accept reports directly
-via GitHub's "Report a Vulnerability".  
-
-To contact the security team directly with questions use: [security@redis.com](mailto:security@redis.com)
-
+If you believe you've discovered a serious vulnerability, please contact the
+Redis core team at redis@redis.io. We will evaluate your report and if
+necessary issue a fix and an advisory. If the issue was previously undisclosed,
+we'll also mention your name in the credits.
 
 ## Responsible Disclosure
 
@@ -51,22 +37,3 @@ embargo on public disclosure.
 
 If you believe you should be on the list, please contact us and we will
 consider your request based on the above criteria.
-
-## Support across Operating Systems, Architectures, and Compilers
-
-Redis is primarily tested on modern Linux distributions, using contemporary
-Intel and AMD x86_64 CPUs, as well as ARM-based CPUs, and recent versions of
-the GCC compiler.
-Vulnerability reports that rely on unsupported or uncommon environments
-(for example, 32-bit architectures, non-Linux operating systems, or outdated
-toolchains) may be considered out of scope, even if the issue is technically
-valid. Such reports will be evaluated on a case-by-case basis at our discretion.
-
-## License Compatibility
-
-For security vulnerability patches released under Redis Open Source 7.4 and 
-thereafter, Redis permits users of earlier versions (7.2 and prior) to access 
-patches under the BSD3 license noted in REDISCONTRIBUTIONS.txt instead of the 
-full license requirements described in LICENSE.txt. Security fixes are tested 
-only against the specific versions for which they are provided. Applicability 
-or portability to other versions or forks has not been evaluated.

codecov.yml

@@ -1,19 +0,0 @@
-coverage:
-  status:
-    patch:
-      default:
-        informational: true
-    project:
-      default:
-        informational: true
-
-comment:
-  require_changes: false
-  require_head: false
-  require_base: false
-  layout: "condensed_header, diff, files"
-  hide_project_coverage: false
-  behavior: default
-
-github_checks:
-  annotations: false

deps/Makefile

@@ -12,23 +12,6 @@ BINCOLOR="\033[37;1m"
 MAKECOLOR="\033[32;1m"
 ENDCOLOR="\033[0m"
 
-DEPS_CFLAGS := $(CFLAGS)
-DEPS_LDFLAGS := $(LDFLAGS)
-CLANG := $(findstring clang,$(shell sh -c '$(CC) --version | head -1'))
-
-# MSan looks for errors related to uninitialized memory.
-# Make sure to build the dependencies with MSan as it needs all the code to be instrumented.
-# A library could be used to initialize memory but if it's not build with --fsanitize=memory then
-# MSan doesn't know about it and will spit false positive error when that memory is then used.
-ifeq ($(SANITIZER),memory)
-ifeq (clang, $(CLANG))
-	DEPS_CFLAGS+=-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-sanitize-recover=all -fno-omit-frame-pointer
-	DEPS_LDFLAGS+=-fsanitize=memory
-else
-    $(error "MemorySanitizer needs to be compiled and linked with clang. Please use CC=clang")
-endif
-endif
-
 default:
 	@echo "Explicit target required"
 
@@ -59,8 +42,7 @@ distclean:
 	-(cd jemalloc && [ -f Makefile ] && $(MAKE) distclean) > /dev/null || true
 	-(cd hdr_histogram && $(MAKE) clean) > /dev/null || true
 	-(cd fpconv && $(MAKE) clean) > /dev/null || true
-	-(cd tre && $(MAKE) clean) > /dev/null || true
-	-(cd xxhash && $(MAKE) clean) > /dev/null || true
+	-(cd fast_float && $(MAKE) clean) > /dev/null || true
 	-(rm -f .make-*)
 
 .PHONY: distclean
@@ -69,52 +51,43 @@ ifneq (,$(filter $(BUILD_TLS),yes module))
     HIREDIS_MAKE_FLAGS = USE_SSL=1
 endif
 
-# Special care is needed to pass additional CFLAGS/LDFLAGS to hiredis as it
-# modifies these variables in its Makefile.
 hiredis: .make-prerequisites
 	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd hiredis && $(MAKE) static $(HIREDIS_MAKE_FLAGS) HIREDIS_CFLAGS="$(DEPS_CFLAGS)" HIREDIS_LDFLAGS="$(DEPS_LDFLAGS)"
+	cd hiredis && $(MAKE) static $(HIREDIS_MAKE_FLAGS)
 
 .PHONY: hiredis
 
 linenoise: .make-prerequisites
 	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd linenoise && $(MAKE) CFLAGS="$(DEPS_CFLAGS)" LDFLAGS="$(DEPS_LDFLAGS)"
+	cd linenoise && $(MAKE)
 
 .PHONY: linenoise
 
 hdr_histogram: .make-prerequisites
 	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd hdr_histogram && $(MAKE) CFLAGS="$(DEPS_CFLAGS)" LDFLAGS="$(DEPS_LDFLAGS)"
+	cd hdr_histogram && $(MAKE)
 
 .PHONY: hdr_histogram
 
 fpconv: .make-prerequisites
 	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd fpconv && $(MAKE) CFLAGS="$(DEPS_CFLAGS)" LDFLAGS="$(DEPS_LDFLAGS)"
+	cd fpconv && $(MAKE)
 
 .PHONY: fpconv
 
-tre: .make-prerequisites
+fast_float: .make-prerequisites
 	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd tre && $(MAKE) CFLAGS="$(DEPS_CFLAGS)" LDFLAGS="$(DEPS_LDFLAGS)"
+	cd fast_float && $(MAKE) libfast_float
 
-.PHONY: tre
-
-
-XXHASH_CFLAGS = -fPIC $(DEPS_CFLAGS)
-xxhash: .make-prerequisites
-	@printf '%b %b\n' $(MAKECOLOR)MAKE$(ENDCOLOR) $(BINCOLOR)$@$(ENDCOLOR)
-	cd xxhash && $(MAKE) lib CFLAGS="$(XXHASH_CFLAGS)" LDFLAGS="$(DEPS_LDFLAGS)"
-.PHONY: xxhash
+.PHONY: fast_float
 
 ifeq ($(uname_S),SunOS)
 	# Make isinf() available
 	LUA_CFLAGS= -D__C99FEATURES__=1
 endif
 
-LUA_CFLAGS+= -Wall -DLUA_ANSI -DENABLE_CJSON_GLOBAL -DREDIS_STATIC='' -DLUA_USE_MKSTEMP $(DEPS_CFLAGS)
-LUA_LDFLAGS+= $(DEPS_LDFLAGS)
+LUA_CFLAGS+= -Wall -DLUA_ANSI -DENABLE_CJSON_GLOBAL -DREDIS_STATIC='' -DLUA_USE_MKSTEMP $(CFLAGS)
+LUA_LDFLAGS+= $(LDFLAGS)
 ifeq ($(LUA_DEBUG),yes)
 	LUA_CFLAGS+= -O0 -g -DLUA_USE_APICHECK
 else
@@ -137,8 +110,8 @@ lua: .make-prerequisites
 
 .PHONY: lua
 
-JEMALLOC_CFLAGS=$(ENABLE_LTO) $(CFLAGS)
-JEMALLOC_LDFLAGS=$(ENABLE_LTO) $(LDFLAGS)
+JEMALLOC_CFLAGS=$(CFLAGS)
+JEMALLOC_LDFLAGS=$(LDFLAGS)
 
 ifneq ($(DEB_HOST_GNU_TYPE),)
 JEMALLOC_CONFIGURE_OPTS += --host=$(DEB_HOST_GNU_TYPE)

deps/fast_float/Makefile

@@ -0,0 +1,24 @@
+# Fallback to gcc/g++ when $CC or $CXX is not in $PATH.
+CC ?= gcc
+CXX ?= g++
+
+CFLAGS=-Wall -O3
+# This avoids loosing the fastfloat specific compile flags when we override the CFLAGS via the main project
+FASTFLOAT_CFLAGS=-std=c++11 -DFASTFLOAT_ALLOWS_LEADING_PLUS
+LDFLAGS=
+
+libfast_float: fast_float_strtod.o
+	$(AR) -r libfast_float.a fast_float_strtod.o
+
+32bit: CFLAGS += -m32
+32bit: LDFLAGS += -m32
+32bit: libfast_float
+
+fast_float_strtod.o: fast_float_strtod.cpp
+	$(CXX) $(CFLAGS) $(FASTFLOAT_CFLAGS) -c fast_float_strtod.cpp $(LDFLAGS)
+
+clean:
+	rm -f *.o
+	rm -f *.a
+	rm -f *.h.gch
+	rm -rf *.dSYM

deps/fast_float/README.md

@@ -0,0 +1,21 @@
+README for fast_float v6.1.4
+
+----------------------------------------------
+
+We're using the fast_float library[1] in our (compiled-in)
+floating-point fast_float_strtod implementation for faster and more
+portable parsing of 64 decimal strings.
+
+The single file fast_float.h is an amalgamation of the entire library,
+which can be (re)generated with the amalgamate.py script (from the
+fast_float repository) via the command
+
+```
+git clone https://github.com/fastfloat/fast_float
+cd fast_float
+git checkout v6.1.4
+python3 ./script/amalgamate.py --license=MIT \
+  > $REDIS_SRC/deps/fast_float/fast_float.h
+```
+
+[1]: https://github.com/fastfloat/fast_float

deps/fast_float/fast_float_strtod.cpp

@@ -0,0 +1,32 @@
+#include "fast_float.h"
+#include <iostream>
+#include <string>
+#include <system_error>
+#include <cerrno>
+
+/* Convert NPTR to a double using the fast_float library.
+ *
+ * This function behaves similarly to the standard strtod function, converting
+ * the initial portion of the string pointed to by `nptr` to a `double` value,
+ * using the fast_float library for high performance. If the conversion fails,
+ * errno is set to EINVAL error code.
+ *
+ * @param nptr   A pointer to the null-terminated byte string to be interpreted.
+ * @param endptr A pointer to a pointer to character. If `endptr` is not NULL,
+ *               it will point to the character after the last character used
+ *               in the conversion.
+ * @return       The converted value as a double. If no valid conversion could
+ *               be performed, returns 0.0.
+ * If ENDPTR is not NULL, a pointer to the character after the last one used
+ * in the number is put in *ENDPTR.  */
+extern "C" double fast_float_strtod(const char *nptr, char **endptr) {
+  double result = 0.0;
+  auto answer = fast_float::from_chars(nptr, nptr + strlen(nptr), result);
+  if (answer.ec != std::errc()) {
+    errno = EINVAL;  // Fallback to  for other errors
+  }
+  if (endptr != NULL) {
+    *endptr = (char *)answer.ptr;
+  }
+  return result;
+}

deps/fast_float/fast_float_strtod.h

@@ -0,0 +1,15 @@
+
+#ifndef __FAST_FLOAT_STRTOD_H__
+#define __FAST_FLOAT_STRTOD_H__
+
+#if defined(__cplusplus)
+extern "C"
+{
+#endif
+    double fast_float_strtod(const char *in, char **out);
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __FAST_FLOAT_STRTOD_H__ */

deps/hiredis/Makefile

@@ -35,19 +35,14 @@ define REDIS_TEST_CONFIG
 endef
 export REDIS_TEST_CONFIG
 
-# Flags passed from outside so as not to override CFLAGS or LDFLAGS as they may
-# be changed inside this Makefile
-HIREDIS_CFLAGS=
-HIREDIS_LDFLAGS=
-
 # Fallback to gcc when $CC is not in $PATH.
 CC:=$(shell sh -c 'type $${CC%% *} >/dev/null 2>/dev/null && echo $(CC) || echo gcc')
 CXX:=$(shell sh -c 'type $${CXX%% *} >/dev/null 2>/dev/null && echo $(CXX) || echo g++')
 OPTIMIZATION?=-O3
 WARNINGS=-Wall -Wextra -Werror -Wstrict-prototypes -Wwrite-strings -Wno-missing-field-initializers
 DEBUG_FLAGS?= -g -ggdb
-REAL_CFLAGS=$(OPTIMIZATION) -fPIC $(CPPFLAGS) $(CFLAGS) $(WARNINGS) $(DEBUG_FLAGS) $(PLATFORM_FLAGS) $(HIREDIS_CFLAGS)
-REAL_LDFLAGS=$(LDFLAGS) $(HIREDIS_LDFLAGS)
+REAL_CFLAGS=$(OPTIMIZATION) -fPIC $(CPPFLAGS) $(CFLAGS) $(WARNINGS) $(DEBUG_FLAGS) $(PLATFORM_FLAGS)
+REAL_LDFLAGS=$(LDFLAGS)
 
 DYLIBSUFFIX=so
 STLIBSUFFIX=a

deps/hiredis/async.c

@@ -478,7 +478,7 @@ static int __redisGetSubscribeCallback(redisAsyncContext *ac, redisReply *reply,
 
     /* Match reply with the expected format of a pushed message.
      * The type and number of elements (3 to 4) are specified at:
-     * https://redis.io/docs/latest/develop/interact/pubsub/#format-of-pushed-messages */
+     * https://redis.io/topics/pubsub#format-of-pushed-messages */
     if ((reply->type == REDIS_REPLY_ARRAY && !(c->flags & REDIS_SUPPORTS_PUSH) && reply->elements >= 3) ||
         reply->type == REDIS_REPLY_PUSH) {
         assert(reply->element[0]->type == REDIS_REPLY_STRING);

deps/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h

@@ -70,6 +70,6 @@ void jemalloc_prefork(void);
 void jemalloc_postfork_parent(void);
 void jemalloc_postfork_child(void);
 void je_sdallocx_noflags(void *ptr, size_t size);
-void *malloc_default(size_t size, size_t *usize);
+void *malloc_default(size_t size);
 
 #endif /* JEMALLOC_INTERNAL_EXTERNS_H */

deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h

@@ -255,15 +255,15 @@ malloc_initialized(void) {
  * tail-call to the slowpath if they fire.
  */
 JEMALLOC_ALWAYS_INLINE void *
-imalloc_fastpath(size_t size, void *(fallback_alloc)(size_t, size_t *), size_t *usable_size) {
+imalloc_fastpath(size_t size, void *(fallback_alloc)(size_t)) {
 	LOG("core.malloc.entry", "size: %zu", size);
 	if (tsd_get_allocates() && unlikely(!malloc_initialized())) {
-		return fallback_alloc(size, usable_size);
+		return fallback_alloc(size);
 	}
 
 	tsd_t *tsd = tsd_get(false);
 	if (unlikely((size > SC_LOOKUP_MAXCLASS) || tsd == NULL)) {
-		return fallback_alloc(size, usable_size);
+		return fallback_alloc(size);
 	}
 	/*
 	 * The code below till the branch checking the next_event threshold may
@@ -307,7 +307,7 @@ imalloc_fastpath(size_t size, void *(fallback_alloc)(size_t, size_t *), size_t *
 	 * 0) in a single branch.
 	 */
 	if (unlikely(allocated_after >= threshold)) {
-		return fallback_alloc(size, usable_size);
+		return fallback_alloc(size);
 	}
 	assert(tsd_fast(tsd));
 
@@ -326,17 +326,15 @@ imalloc_fastpath(size_t size, void *(fallback_alloc)(size_t, size_t *), size_t *
 	ret = cache_bin_alloc_easy(bin, &tcache_success);
 	if (tcache_success) {
 		fastpath_success_finish(tsd, allocated_after, bin, ret);
-		if (usable_size) *usable_size = usize;
 		return ret;
 	}
 	ret = cache_bin_alloc(bin, &tcache_success);
 	if (tcache_success) {
 		fastpath_success_finish(tsd, allocated_after, bin, ret);
-		if (usable_size) *usable_size = usize;
 		return ret;
 	}
 
-	return fallback_alloc(size, usable_size);
+	return fallback_alloc(size);
 }
 
 JEMALLOC_ALWAYS_INLINE int

deps/jemalloc/include/jemalloc/jemalloc_macros.h.in

@@ -151,6 +151,3 @@
 /* This version of Jemalloc, modified for Redis, has the je_get_defrag_hint()
  * function. */
 #define JEMALLOC_FRAG_HINT
-
-/* This version of Jemalloc, modified for Redis, has the je_*_usable() family functions. */
-#define JEMALLOC_ALLOC_WITH_USIZE

deps/jemalloc/src/jemalloc.c

@@ -2697,7 +2697,7 @@ imalloc(static_opts_t *sopts, dynamic_opts_t *dopts) {
 
 JEMALLOC_NOINLINE
 void *
-malloc_default(size_t size, size_t *usize) {
+malloc_default(size_t size) {
 	void *ret;
 	static_opts_t sopts;
 	dynamic_opts_t dopts;
@@ -2731,7 +2731,6 @@ malloc_default(size_t size, size_t *usize) {
 
 	LOG("core.malloc.exit", "result: %p", ret);
 
-	if (usize) *usize = dopts.usize;
 	return ret;
 }
 
@@ -2740,15 +2739,11 @@ malloc_default(size_t size, size_t *usize) {
  * Begin malloc(3)-compatible functions.
  */
 
-static inline void *je_malloc_internal(size_t size, size_t *usize) {
-	return imalloc_fastpath(size, &malloc_default, usize);
-}
-
 JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
 void JEMALLOC_NOTHROW *
 JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
 je_malloc(size_t size) {
-	return je_malloc_internal(size, NULL);
+	return imalloc_fastpath(size, &malloc_default);
 }
 
 JEMALLOC_EXPORT int JEMALLOC_NOTHROW
@@ -2831,7 +2826,10 @@ je_aligned_alloc(size_t alignment, size_t size) {
 	return ret;
 }
 
-static void *je_calloc_internal(size_t num, size_t size, size_t *usize) {
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2)
+je_calloc(size_t num, size_t size) {
 	void *ret;
 	static_opts_t sopts;
 	dynamic_opts_t dopts;
@@ -2859,19 +2857,11 @@ static void *je_calloc_internal(size_t num, size_t size, size_t *usize) {
 
 	LOG("core.calloc.exit", "result: %p", ret);
 
-	if (usize) *usize = dopts.usize;
 	return ret;
 }
 
-JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
-void JEMALLOC_NOTHROW *
-JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2)
-je_calloc(size_t num, size_t size) {
-	return je_calloc_internal(num, size, NULL);
-}
-
 JEMALLOC_ALWAYS_INLINE void
-ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path, size_t *usable) {
+ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path) {
 	if (!slow_path) {
 		tsd_assert_fast(tsd);
 	}
@@ -2904,7 +2894,6 @@ ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path, size_t *usable) {
 		    true);
 	}
 	thread_dalloc_event(tsd, usize);
-	if (usable) *usable = usize;
 }
 
 JEMALLOC_ALWAYS_INLINE bool
@@ -3004,7 +2993,7 @@ isfree(tsd_t *tsd, void *ptr, size_t usize, tcache_t *tcache, bool slow_path) {
 
 JEMALLOC_NOINLINE
 void
-free_default(void *ptr, size_t *usize) {
+free_default(void *ptr) {
 	UTRACE(ptr, 0, 0);
 	if (likely(ptr != NULL)) {
 		/*
@@ -3022,14 +3011,14 @@ free_default(void *ptr, size_t *usize) {
 			tcache_t *tcache = tcache_get_from_ind(tsd,
 			    TCACHE_IND_AUTOMATIC, /* slow */ false,
 			    /* is_alloc */ false);
-			ifree(tsd, ptr, tcache, /* slow */ false, usize);
+			ifree(tsd, ptr, tcache, /* slow */ false);
 		} else {
 			tcache_t *tcache = tcache_get_from_ind(tsd,
 			    TCACHE_IND_AUTOMATIC, /* slow */ true,
 			    /* is_alloc */ false);
 			uintptr_t args_raw[3] = {(uintptr_t)ptr};
 			hook_invoke_dalloc(hook_dalloc_free, ptr, args_raw);
-			ifree(tsd, ptr, tcache, /* slow */ true, usize);
+			ifree(tsd, ptr, tcache, /* slow */ true);
 		}
 
 		check_entry_exit_locking(tsd_tsdn(tsd));
@@ -3073,7 +3062,7 @@ free_fastpath_nonfast_aligned(void *ptr, bool check_prof) {
 
 /* Returns whether or not the free attempt was successful. */
 JEMALLOC_ALWAYS_INLINE
-bool free_fastpath(void *ptr, size_t size, bool size_hint, size_t *usable_size) {
+bool free_fastpath(void *ptr, size_t size, bool size_hint) {
 	tsd_t *tsd = tsd_get(false);
 	/* The branch gets optimized away unless tsd_get_allocates(). */
 	if (unlikely(tsd == NULL)) {
@@ -3142,7 +3131,6 @@ bool free_fastpath(void *ptr, size_t size, bool size_hint, size_t *usable_size)
 	bool fail = maybe_check_alloc_ctx(tsd, ptr, &alloc_ctx);
 	if (fail) {
 		/* See the comment in isfree. */
-		if (usable_size) *usable_size = usize;
 		return true;
 	}
 
@@ -3163,23 +3151,18 @@ bool free_fastpath(void *ptr, size_t size, bool size_hint, size_t *usable_size)
 
 	*tsd_thread_deallocatedp_get(tsd) = deallocated_after;
 
-	if (usable_size) *usable_size = usize;
 	return true;
 }
 
-static inline void je_free_internal(void *ptr, size_t *usize) {
-	LOG("core.free.entry", "ptr: %p", ptr);
-
-	if (!free_fastpath(ptr, 0, false, usize)) {
-		free_default(ptr, usize);
-	}
-
-	LOG("core.free.exit", "");
-}
-
 JEMALLOC_EXPORT void JEMALLOC_NOTHROW
 je_free(void *ptr) {
-	je_free_internal(ptr, NULL);
+	LOG("core.free.entry", "ptr: %p", ptr);
+
+	if (!free_fastpath(ptr, 0, false)) {
+		free_default(ptr);
+	}
+
+	LOG("core.free.exit", "");
 }
 
 /*
@@ -3507,7 +3490,7 @@ irallocx_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t size,
 }
 
 static void *
-do_rallocx(void *ptr, size_t size, int flags, bool is_realloc, size_t *old_usable_size, size_t *new_usable_size) {
+do_rallocx(void *ptr, size_t size, int flags, bool is_realloc) {
 	void *p;
 	tsd_t *tsd;
 	size_t usize;
@@ -3572,8 +3555,6 @@ do_rallocx(void *ptr, size_t size, int flags, bool is_realloc, size_t *old_usabl
 		junk_alloc_callback(excess_start, excess_len);
 	}
 
-	if (old_usable_size) *old_usable_size = old_usize;
-	if (new_usable_size) *new_usable_size = usize;
 	return p;
 label_oom:
 	if (config_xmalloc && unlikely(opt_xmalloc)) {
@@ -3592,13 +3573,13 @@ JEMALLOC_ALLOC_SIZE(2)
 je_rallocx(void *ptr, size_t size, int flags) {
 	LOG("core.rallocx.entry", "ptr: %p, size: %zu, flags: %d", ptr,
 	    size, flags);
-	void *ret = do_rallocx(ptr, size, flags, false, NULL, NULL);
+	void *ret = do_rallocx(ptr, size, flags, false);
 	LOG("core.rallocx.exit", "result: %p", ret);
 	return ret;
 }
 
 static void *
-do_realloc_nonnull_zero(void *ptr, size_t *old_usize, size_t *new_usize) {
+do_realloc_nonnull_zero(void *ptr) {
 	if (config_stats) {
 		atomic_fetch_add_zu(&zero_realloc_count, 1, ATOMIC_RELAXED);
 	}
@@ -3609,7 +3590,7 @@ do_realloc_nonnull_zero(void *ptr, size_t *old_usize, size_t *new_usize) {
 		 * reduce the harm, and turn off the tcache while allocating, so
 		 * that we'll get a true first fit.
 		 */
-		return do_rallocx(ptr, 1, MALLOCX_TCACHE_NONE, true, old_usize, new_usize);
+		return do_rallocx(ptr, 1, MALLOCX_TCACHE_NONE, true);
 	} else if (opt_zero_realloc_action == zero_realloc_action_free) {
 		UTRACE(ptr, 0, 0);
 		tsd_t *tsd = tsd_fetch();
@@ -3620,10 +3601,7 @@ do_realloc_nonnull_zero(void *ptr, size_t *old_usize, size_t *new_usize) {
 		    /* is_alloc */ false);
 		uintptr_t args[3] = {(uintptr_t)ptr, 0};
 		hook_invoke_dalloc(hook_dalloc_realloc, ptr, args);
-		size_t usize;
-		ifree(tsd, ptr, tcache, true, &usize);
-		if (old_usize) *old_usize = usize;
-		if (new_usize) *new_usize = 0;
+		ifree(tsd, ptr, tcache, true);
 
 		check_entry_exit_locking(tsd_tsdn(tsd));
 		return NULL;
@@ -3639,15 +3617,18 @@ do_realloc_nonnull_zero(void *ptr, size_t *old_usize, size_t *new_usize) {
 	}
 }
 
-static inline void *je_realloc_internal(void *ptr, size_t size, size_t *old_usize, size_t *new_usize) {
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ALLOC_SIZE(2)
+je_realloc(void *ptr, size_t size) {
 	LOG("core.realloc.entry", "ptr: %p, size: %zu\n", ptr, size);
 
 	if (likely(ptr != NULL && size != 0)) {
-		void *ret = do_rallocx(ptr, size, 0, true, old_usize, new_usize);
+		void *ret = do_rallocx(ptr, size, 0, true);
 		LOG("core.realloc.exit", "result: %p", ret);
 		return ret;
 	} else if (ptr != NULL && size == 0) {
-		void *ret = do_realloc_nonnull_zero(ptr, old_usize, new_usize);
+		void *ret = do_realloc_nonnull_zero(ptr);
 		LOG("core.realloc.exit", "result: %p", ret);
 		return ret;
 	} else {
@@ -3676,19 +3657,10 @@ static inline void *je_realloc_internal(void *ptr, size_t size, size_t *old_usiz
 			    (uintptr_t)ret, args);
 		}
 		LOG("core.realloc.exit", "result: %p", ret);
-		if (old_usize) *old_usize = 0;
-		if (new_usize) *new_usize = dopts.usize;
 		return ret;
 	}
 }
 
-JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
-void JEMALLOC_NOTHROW *
-JEMALLOC_ALLOC_SIZE(2)
-je_realloc(void *ptr, size_t size) {
-	return je_realloc_internal(ptr, size, NULL, NULL);
-}
-
 JEMALLOC_ALWAYS_INLINE size_t
 ixallocx_helper(tsdn_t *tsdn, void *ptr, size_t old_usize, size_t size,
     size_t extra, size_t alignment, bool zero) {
@@ -3911,11 +3883,11 @@ je_dallocx(void *ptr, int flags) {
 	UTRACE(ptr, 0, 0);
 	if (likely(fast)) {
 		tsd_assert_fast(tsd);
-		ifree(tsd, ptr, tcache, false, NULL);
+		ifree(tsd, ptr, tcache, false);
 	} else {
 		uintptr_t args_raw[3] = {(uintptr_t)ptr, flags};
 		hook_invoke_dalloc(hook_dalloc_dallocx, ptr, args_raw);
-		ifree(tsd, ptr, tcache, true, NULL);
+		ifree(tsd, ptr, tcache, true);
 	}
 	check_entry_exit_locking(tsd_tsdn(tsd));
 
@@ -3963,7 +3935,7 @@ je_sdallocx(void *ptr, size_t size, int flags) {
 	LOG("core.sdallocx.entry", "ptr: %p, size: %zu, flags: %d", ptr,
 		size, flags);
 
-	if (flags != 0 || !free_fastpath(ptr, size, true, NULL)) {
+	if (flags != 0 || !free_fastpath(ptr, size, true)) {
 		sdallocx_default(ptr, size, flags);
 	}
 
@@ -3975,7 +3947,7 @@ je_sdallocx_noflags(void *ptr, size_t size) {
 	LOG("core.sdallocx.entry", "ptr: %p, size: %zu, flags: 0", ptr,
 		size);
 
-	if (!free_fastpath(ptr, size, true, NULL)) {
+	if (!free_fastpath(ptr, size, true)) {
 		sdallocx_default(ptr, size, 0);
 	}
 
@@ -4511,29 +4483,3 @@ get_defrag_hint(void* ptr) {
 	assert(ptr != NULL);
 	return iget_defrag_hint(TSDN_NULL, ptr);
 }
-
-JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
-void JEMALLOC_NOTHROW *
-JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
-malloc_with_usize(size_t size, size_t *usize) {
-	return je_malloc_internal(size, usize);
-}
-
-JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
-void JEMALLOC_NOTHROW *
-JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2)
-calloc_with_usize(size_t num, size_t size, size_t *usize) {
-	return je_calloc_internal(num, size, usize);
-}
-
-JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
-void JEMALLOC_NOTHROW *
-JEMALLOC_ALLOC_SIZE(2)
-realloc_with_usize(void *ptr, size_t size, size_t *old_usize, size_t *new_usize) {
-	return je_realloc_internal(ptr, size, old_usize, new_usize);
-}
-
-JEMALLOC_EXPORT void JEMALLOC_NOTHROW
-free_with_usize(void *ptr, size_t *usize) {
-	je_free_internal(ptr, usize);
-}

deps/jemalloc/src/jemalloc_cpp.cpp

@@ -94,8 +94,8 @@ handleOOM(std::size_t size, bool nothrow) {
 template <bool IsNoExcept>
 JEMALLOC_NOINLINE
 static void *
-fallback_impl(std::size_t size, std::size_t *usize) noexcept(IsNoExcept) {
-	void *ptr = malloc_default(size, NULL);
+fallback_impl(std::size_t size) noexcept(IsNoExcept) {
+	void *ptr = malloc_default(size);
 	if (likely(ptr != nullptr)) {
 		return ptr;
 	}
@@ -106,7 +106,7 @@ template <bool IsNoExcept>
 JEMALLOC_ALWAYS_INLINE
 void *
 newImpl(std::size_t size) noexcept(IsNoExcept) {
-	return imalloc_fastpath(size, &fallback_impl<IsNoExcept>, NULL);
+	return imalloc_fastpath(size, &fallback_impl<IsNoExcept>);
 }
 
 void *

deps/linenoise/linenoise.c

@@ -120,7 +120,6 @@
 #include <assert.h>
 #include "linenoise.h"
 
-#define SEQ_BUFFER_MAX_LENGTH 8
 #define LINENOISE_DEFAULT_HISTORY_MAX_LEN 100
 #define LINENOISE_MAX_LINE 4096
 static char *unsupported_term[] = {"dumb","cons25","emacs",NULL};
@@ -794,30 +793,6 @@ void linenoiseEditMoveRight(struct linenoiseState *l) {
     }
 }
 
-/* Consider letters/digits/underscore as “word”; others as delimiters. */
-static int isWordChar(char c) {
-    return (c == '_' || (c >= '0' && c <= '9') ||
-            (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'));
-}
-
-static void linenoiseEditMoveWordLeft(struct linenoiseState *l) {
-    if (l->pos == 0) return;
-    /* Skip any delimiters, then move left over the previous word */
-    while (l->pos > 0 && !isWordChar(l->buf[l->pos - 1])) l->pos--;
-    /* Then move to the start of that word */
-    while (l->pos > 0 && isWordChar(l->buf[l->pos - 1])) l->pos--;
-    refreshLine(l);
-}
-
-static void linenoiseEditMoveWordRight(struct linenoiseState *l) {
-    if (l->pos == l->len) return;
-    /* Skip the current word to the right */
-    while (l->pos < l->len && isWordChar(l->buf[l->pos])) l->pos++;
-    /* Then skip any delimiters to reach the next word */
-    while (l->pos < l->len && !isWordChar(l->buf[l->pos])) l->pos++;
-    refreshLine(l);
-}
-
 /* Move cursor to the start of the line. */
 void linenoiseEditMoveHome(struct linenoiseState *l) {
     if (l->pos != 0) {
@@ -1037,18 +1012,6 @@ static int linenoiseEdit(int stdin_fd, int stdout_fd, char *buf, size_t buflen,
              * Use two calls to handle slow terminals returning the two
              * chars at different times. */
             if (read(l.ifd,seq,1) == -1) break;
-
-            /* Handle Meta-b / Meta-f directly because it's a 2-byte sequence */
-            if (seq[0] == 'b' || seq[0] == 'f') {
-                if (reverse_search_mode_enabled) {
-                    disableReverseSearchMode(&l, buf, buflen, 1);
-                    break;
-                }
-                if (seq[0] == 'b') linenoiseEditMoveWordLeft(&l);   /* ESC b → word left */
-                else linenoiseEditMoveWordRight(&l);                /* ESC f → word right */
-                break;
-            }
-
             if (read(l.ifd,seq+1,1) == -1) break;
 
             if (reverse_search_mode_enabled) {
@@ -1059,50 +1022,14 @@ static int linenoiseEdit(int stdin_fd, int stdout_fd, char *buf, size_t buflen,
             /* ESC [ sequences. */
             if (seq[0] == '[') {
                 if (seq[1] >= '0' && seq[1] <= '9') {
-                    /* Extended escape, read additional bytes.
-                     * Examples: ESC [1;5C  ESC [3~ */
-                    char seq_buffer[SEQ_BUFFER_MAX_LENGTH];
-                    int i = 0;
-                    seq_buffer[i++] = seq[1];
-
-                    /* Read more bytes until we see a CSI final byte (range @..~).
-                     * Use SEQ_BUFFER_MAX_LENGTH-1 to reserve one position for '\0'. */
-                    char seq_char;
-                    while (i < SEQ_BUFFER_MAX_LENGTH - 1 && read(l.ifd, &seq_char, 1) == 1) {
-                        seq_buffer[i++] = seq_char;
-                        if (seq_char >= '@' && seq_char <= '~') break; /* CSI final byte */
-                    }
-                    seq_buffer[i] = '\0';
-
-                    /* The exact key mapping behavior depends on your keyboard/terminal setup.
-                     * For example, in MacOS terminal you can go to the profile keyboard setting
-                     * to see or configure the current mapping.
-                     *
-                     * Take action `[1;5C` (Ctrl + →) or `[1;3D` (Alt + ←) as examples:
-                     * [ indicates a CSI (Control Sequence Introducer), telling the terminal
-                     *    "What follows is a control command, not text"
-                     * 1 is how many units to move (default is 1 if omitted)
-                     * ; is the separator between parameters
-                     * 5 is the modifier mask for Ctrl. Other possible values include 1 (no modifier),
-                     *     2 (Shift), 3 (Alt), 4 (Shift + Alt), 6 (Shift + Ctrl), 7 (Alt + Ctrl), etc.
-                     * C is the cursor right command. Other commands include A (cursor up), B (cursor
-                     *     down), D (cursor left).
-                     */
-
-                    /* Word left: Ctrl + ← (modifier 5) or Alt + ← (modifier 3) */
-                    if (strcmp(seq_buffer, "1;5D") == 0 || strcmp(seq_buffer, "1;3D") == 0) {
-                        linenoiseEditMoveWordLeft(&l);
-                        break;
-                    }
-                    /* Word right: Ctrl + → (modifier 5) or Alt + → (modifier 3) */
-                    if (strcmp(seq_buffer, "1;5C") == 0 || strcmp(seq_buffer, "1;3C") == 0) {
-                        linenoiseEditMoveWordRight(&l);
-                        break;
-                    }
-                    /* Delete key */
-                    if (strcmp(seq_buffer, "3~") == 0) {
-                        linenoiseEditDelete(&l);
-                        break;
+                    /* Extended escape, read additional byte. */
+                    if (read(l.ifd,seq+2,1) == -1) break;
+                    if (seq[2] == '~') {
+                        switch(seq[1]) {
+                        case '3': /* Delete key. */
+                            linenoiseEditDelete(&l);
+                            break;
+                        }
                     }
                 } else {
                     switch(seq[1]) {

deps/lua/src/lbaselib.c

@@ -340,14 +340,13 @@ static int luaB_assert (lua_State *L) {
 
 
 static int luaB_unpack (lua_State *L) {
-  int i, e;
-  unsigned int n;
+  int i, e, n;
   luaL_checktype(L, 1, LUA_TTABLE);
   i = luaL_optint(L, 2, 1);
   e = luaL_opt(L, luaL_checkint, 3, luaL_getn(L, 1));
   if (i > e) return 0;  /* empty range */
-  n = (unsigned int)e - (unsigned int)i;  /* number of elements minus 1 */
-  if (n >= INT_MAX || !lua_checkstack(L, ++n))
+  n = e - i + 1;  /* number of elements */
+  if (n <= 0 || !lua_checkstack(L, n))  /* n <= 0 means arith. overflow */
     return luaL_error(L, "too many results to unpack");
   lua_rawgeti(L, 1, i);  /* push arg[i] (avoiding overflow problems) */
   while (i++ < e)  /* push arg[i + 1...e] */

deps/lua/src/llex.c

@@ -138,7 +138,6 @@ static void inclinenumber (LexState *ls) {
 
 
 void luaX_setinput (lua_State *L, LexState *ls, ZIO *z, TString *source) {
-  ls->t.token = 0;
   ls->decpoint = '.';
   ls->L = L;
   ls->lookahead.token = TK_EOS;  /* no look-ahead token */
@@ -207,13 +206,9 @@ static void read_numeral (LexState *ls, SemInfo *seminfo) {
     trydecpoint(ls, seminfo); /* try to update decimal point separator */
 }
 
-/*
-** reads a sequence '[=*[' or ']=*]', leaving the last bracket.
-** If a sequence is well-formed, return its number of '='s + 2; otherwise,
-** return 1 if there is no '='s or 0 otherwise (an unfinished '[==...').
-*/
-static size_t skip_sep (LexState *ls) {
-  size_t count = 0;
+
+static int skip_sep (LexState *ls) {
+  int count = 0;
   int s = ls->current;
   lua_assert(s == '[' || s == ']');
   save_and_next(ls);
@@ -221,13 +216,11 @@ static size_t skip_sep (LexState *ls) {
     save_and_next(ls);
     count++;
   }
-   return (ls->current == s) ? count + 2
-          : (count == 0) ? 1
-          : 0;
+  return (ls->current == s) ? count : (-count) - 1;
 }
 
 
-static void read_long_string (LexState *ls, SemInfo *seminfo, size_t sep) {
+static void read_long_string (LexState *ls, SemInfo *seminfo, int sep) {
   int cont = 0;
   (void)(cont);  /* avoid warnings when `cont' is not used */
   save_and_next(ls);  /* skip 2nd `[' */
@@ -277,8 +270,8 @@ static void read_long_string (LexState *ls, SemInfo *seminfo, size_t sep) {
     }
   } endloop:
   if (seminfo)
-    seminfo->ts = luaX_newstring(ls, luaZ_buffer(ls->buff) + sep,
-                                     luaZ_bufflen(ls->buff) - 2 * sep);
+    seminfo->ts = luaX_newstring(ls, luaZ_buffer(ls->buff) + (2 + sep),
+                                     luaZ_bufflen(ls->buff) - 2*(2 + sep));
 }
 
 
@@ -353,9 +346,9 @@ static int llex (LexState *ls, SemInfo *seminfo) {
         /* else is a comment */
         next(ls);
         if (ls->current == '[') {
-          size_t sep = skip_sep(ls);
+          int sep = skip_sep(ls);
           luaZ_resetbuffer(ls->buff);  /* `skip_sep' may dirty the buffer */
-          if (sep >= 2) {
+          if (sep >= 0) {
             read_long_string(ls, NULL, sep);  /* long comment */
             luaZ_resetbuffer(ls->buff);
             continue;
@@ -367,14 +360,13 @@ static int llex (LexState *ls, SemInfo *seminfo) {
         continue;
       }
       case '[': {
-        size_t sep = skip_sep(ls);
-        if (sep >= 2) {
+        int sep = skip_sep(ls);
+        if (sep >= 0) {
           read_long_string(ls, seminfo, sep);
           return TK_STRING;
         }
-        else if (sep == 0)  /* '[=...' missing second bracket */
-          luaX_lexerror(ls, "invalid long string delimiter", TK_STRING);
-        return '[';
+        else if (sep == -1) return '[';
+        else luaX_lexerror(ls, "invalid long string delimiter", TK_STRING);
       }
       case '=': {
         next(ls);

deps/lua/src/lparser.c

@@ -384,17 +384,13 @@ Proto *luaY_parser (lua_State *L, ZIO *z, Mbuffer *buff, const char *name) {
   struct LexState lexstate;
   struct FuncState funcstate;
   lexstate.buff = buff;
-  TString *tname = luaS_new(L, name);
-  setsvalue2s(L, L->top, tname);
-  incr_top(L);
-  luaX_setinput(L, &lexstate, z, tname);
+  luaX_setinput(L, &lexstate, z, luaS_new(L, name));
   open_func(&lexstate, &funcstate);
   funcstate.f->is_vararg = VARARG_ISVARARG;  /* main func. is always vararg */
   luaX_next(&lexstate);  /* read first token */
   chunk(&lexstate);
   check(&lexstate, TK_EOS);
   close_func(&lexstate);
-  --L->top;
   lua_assert(funcstate.prev == NULL);
   lua_assert(funcstate.f->nups == 0);
   lua_assert(lexstate.fs == NULL);

deps/lua/src/ltable.c

@@ -434,7 +434,8 @@ static TValue *newkey (lua_State *L, Table *t, const TValue *key) {
 ** search function for integers
 */
 const TValue *luaH_getnum (Table *t, int key) {
-  if (1 <= key && key <= t->sizearray)
+  /* (1 <= key && key <= t->sizearray) */
+  if (cast(unsigned int, key-1) < cast(unsigned int, t->sizearray))
     return &t->array[key-1];
   else {
     lua_Number nk = cast_num(key);

deps/lua/src/lua_cjson.c

@@ -71,7 +71,6 @@
 #define DEFAULT_DECODE_INVALID_NUMBERS 1
 #define DEFAULT_ENCODE_KEEP_BUFFER 1
 #define DEFAULT_ENCODE_NUMBER_PRECISION 14
-#define DEFAULT_DECODE_ARRAY_WITH_ARRAY_MT 0
 
 #ifdef DISABLE_INVALID_NUMBERS
 #undef DEFAULT_DECODE_INVALID_NUMBERS
@@ -131,7 +130,6 @@ typedef struct {
 
     int decode_invalid_numbers;
     int decode_max_depth;
-    int decode_array_with_array_mt;
 } json_config_t;
 
 typedef struct {
@@ -305,14 +303,6 @@ static int json_cfg_encode_number_precision(lua_State *l)
     return json_integer_option(l, 1, &cfg->encode_number_precision, 1, 14);
 }
 
-/* Configures how to decode arrays */
-static int json_cfg_decode_array_with_array_mt(lua_State *l)
-{
-    json_config_t *cfg = json_arg_init(l, 1);
-
-    return json_enum_option(l, 1, &cfg->decode_array_with_array_mt, NULL, 1);
-}
-
 /* Configures JSON encoding buffer persistence */
 static int json_cfg_encode_keep_buffer(lua_State *l)
 {
@@ -403,7 +393,6 @@ static void json_create_config(lua_State *l)
     cfg->decode_invalid_numbers = DEFAULT_DECODE_INVALID_NUMBERS;
     cfg->encode_keep_buffer = DEFAULT_ENCODE_KEEP_BUFFER;
     cfg->encode_number_precision = DEFAULT_ENCODE_NUMBER_PRECISION;
-    cfg->decode_array_with_array_mt = DEFAULT_DECODE_ARRAY_WITH_ARRAY_MT;
 
 #if DEFAULT_ENCODE_KEEP_BUFFER > 0
     strbuf_init(&cfg->encode_buf, 0);
@@ -691,23 +680,6 @@ static void json_append_data(lua_State *l, json_config_t *cfg,
     case LUA_TTABLE:
         current_depth++;
         json_check_encode_depth(l, cfg, current_depth, json);
-
-        /* Check if this is an array */
-        int as_array = 0;
-        if (!lua_checkstack(l, 2))
-            luaL_error(l, "max lua stack reached");
-        if (lua_getmetatable(l, -1)) {
-            lua_getfield(l, -1, "__is_cjson_array");
-            as_array = lua_toboolean(l, -1);
-            lua_pop(l, 2); /* pop value and metatable */
-        }
-
-        if (as_array) {
-            len = lua_objlen(l, -1);
-            json_append_array(l, cfg, current_depth, json, len);
-            break;
-        }
-        
         len = lua_array_length(l, cfg, json);
         if (len > 0)
             json_append_array(l, cfg, current_depth, json, len);
@@ -1224,19 +1196,6 @@ static void json_parse_array_context(lua_State *l, json_parse_t *json)
 
     lua_newtable(l);
 
-    /* set array_mt on the table at the top of the stack */
-    if (json->cfg->decode_array_with_array_mt) {
-        /* Ensure sufficient stack space for metatable creation (metatable + boolean) */
-        if (!lua_checkstack(l, 2))
-            luaL_error(l, "max lua stack reached");
-        /* Mark this table so encoder can emit [] for empty arrays */
-        lua_newtable(l);
-        lua_pushboolean(l, 1);
-        lua_setfield(l, -2, "__is_cjson_array");
-        lua_enablereadonlytable(l, -1, 1); /* protect the metatable. */
-        lua_setmetatable(l, -2); /* set metatable for the array table */
-    }
-
     json_next_token(json, &token);
 
     /* Handle empty arrays */
@@ -1389,7 +1348,6 @@ static int lua_cjson_new(lua_State *l)
     luaL_Reg reg[] = {
         { "encode", json_encode },
         { "decode", json_decode },
-        { "decode_array_with_array_mt", json_cfg_decode_array_with_array_mt },
         { "encode_sparse_array", json_cfg_encode_sparse_array },
         { "encode_max_depth", json_cfg_encode_max_depth },
         { "decode_max_depth", json_cfg_decode_max_depth },

deps/tre/LICENSE

@@ -1,29 +0,0 @@
-This is the license, copyright notice, and disclaimer for TRE, a regex
-matching package (library and tools) with support for approximate
-matching.
-
-Copyright (c) 2001-2009 Ville Laurikari <vl@iki.fi>
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-
-  1. Redistributions of source code must retain the above copyright
-     notice, this list of conditions and the following disclaimer.
-
-  2. Redistributions in binary form must reproduce the above copyright
-     notice, this list of conditions and the following disclaimer in the
-     documentation and/or other materials provided with the distribution.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
-``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT
-HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

deps/tre/Makefile

@@ -1,79 +0,0 @@
-STD= -std=c99
-WARN= -Wall
-OPT= -Os
-
-ifeq ($(SANITIZER),address)
-	CFLAGS+=-fsanitize=address -fno-sanitize-recover=all -fno-omit-frame-pointer
-	LDFLAGS+=-fsanitize=address
-else
-ifeq ($(SANITIZER),undefined)
-	CFLAGS+=-fsanitize=undefined -fno-sanitize-recover=all -fno-omit-frame-pointer
-	LDFLAGS+=-fsanitize=undefined
-else
-ifeq ($(SANITIZER),thread)
-	CFLAGS+=-fsanitize=thread -fno-sanitize-recover=all -fno-omit-frame-pointer
-	LDFLAGS+=-fsanitize=thread
-else
-ifeq ($(SANITIZER),memory)
-	CFLAGS+=-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-sanitize-recover=all -fno-omit-frame-pointer
-	LDFLAGS+=-fsanitize=memory
-endif
-endif
-endif
-endif
-
-R_CFLAGS= $(STD) $(WARN) $(OPT) $(DEBUG) $(CFLAGS) -DTRE_REGEX_T_FIELD=value -Ilocal_includes -Ilib
-R_LDFLAGS= $(LDFLAGS)
-DEBUG= -g
-
-R_CC=$(CC) $(R_CFLAGS)
-R_LD=$(CC) $(R_LDFLAGS)
-
-AR= ar
-ARFLAGS= rcs
-
-TRE_OBJ=lib/regcomp.o lib/regerror.o lib/regexec.o lib/tre-ast.o lib/tre-compile.o \
-	lib/tre-filter.o lib/tre-match-backtrack.o lib/tre-match-parallel.o \
-	lib/tre-mem.o lib/tre-parse.o lib/tre-stack.o lib/xmalloc.o
-TRE_TESTS=tests/retest tests/test-str-source tests/test-literal-opt tests/test-malformed-regn
-
-libtre.a: $(TRE_OBJ)
-	$(AR) $(ARFLAGS) $@ $+
-
-check: $(TRE_TESTS)
-	@set -e; \
-	for test in $(TRE_TESTS); do \
-		echo "TEST $$test"; \
-		./$$test; \
-	done
-
-tests/retest: tests/retest.c libtre.a
-	$(R_LD) $(R_CFLAGS) -DHAVE_REGNEXEC -DHAVE_REGNCOMP -o $@ $< libtre.a
-
-tests/test-str-source: tests/test-str-source.c libtre.a
-	$(R_LD) $(R_CFLAGS) -o $@ $< libtre.a
-
-tests/test-literal-opt: tests/test-literal-opt.c libtre.a
-	$(R_LD) $(R_CFLAGS) -o $@ $< libtre.a
-
-tests/test-malformed-regn: tests/test-malformed-regn.c libtre.a
-	$(R_LD) $(R_CFLAGS) -o $@ $< libtre.a
-
-lib/regcomp.o: lib/regcomp.c local_includes/tre.h local_includes/tre-config.h lib/tre-internal.h lib/xmalloc.h
-lib/regerror.o: lib/regerror.c local_includes/tre.h
-lib/regexec.o: lib/regexec.c local_includes/tre.h lib/tre-internal.h lib/xmalloc.h
-lib/tre-ast.o: lib/tre-ast.c lib/tre-ast.h lib/tre-internal.h
-lib/tre-compile.o: lib/tre-compile.c lib/tre-compile.h lib/tre-internal.h lib/tre-mem.h lib/tre-parse.h lib/tre-stack.h lib/xmalloc.h
-lib/tre-filter.o: lib/tre-filter.c lib/tre-filter.h lib/tre-internal.h
-lib/tre-match-backtrack.o: lib/tre-match-backtrack.c lib/tre-internal.h lib/tre-match-utils.h lib/tre-mem.h lib/tre-stack.h
-lib/tre-match-parallel.o: lib/tre-match-parallel.c lib/tre-internal.h lib/tre-match-utils.h lib/tre-mem.h
-lib/tre-mem.o: lib/tre-mem.c lib/tre-mem.h
-lib/tre-parse.o: lib/tre-parse.c lib/tre-ast.h lib/tre-compile.h lib/tre-filter.h lib/tre-internal.h lib/tre-mem.h lib/tre-parse.h lib/tre-stack.h lib/xmalloc.h
-lib/tre-stack.o: lib/tre-stack.c lib/tre-internal.h lib/tre-stack.h
-lib/xmalloc.o: lib/xmalloc.c lib/xmalloc.h
-
-.c.o:
-	$(R_CC) -c -o $@ $<
-
-clean:
-	rm -f $(TRE_OBJ) libtre.a $(TRE_TESTS)

deps/tre/README.md

@@ -1,276 +0,0 @@
-Introduction
-============
-
-TRE is a lightweight, robust, and efficient POSIX compliant regexp
-matching library with some exciting features such as approximate
-(fuzzy) matching.
-
-The matching algorithm used in TRE uses linear worst-case time in
-the length of the text being searched, and quadratic worst-case
-time in the length of the used regular expression.
-
-In other words, the time complexity of the algorithm is O(M^2N), where
-M is the length of the regular expression and N is the length of the
-text.  The used space is also quadratic on the length of the regex,
-but does not depend on the searched string.  This quadratic behaviour
-occurs only on pathological cases which are probably very rare in
-practice.
-
-
-Hacking
-=======
-
-Here's how to work with this code.
-
-Prerequisites
--------------
-
-You will need the following tools installed on your system:
-
-  - autoconf
-  - automake
-  - gettext (including autopoint)
-  - libtool
-  - zip (optional)
-
-
-Building
---------
-
-First, prepare the tree.  Change to the root of the source directory
-and run
-
-    ./utils/autogen.sh
-
-This will regenerate various things using the prerequisite tools so
-that you end up with a buildable tree.
-
-After this, you can run the configure script and build TRE as usual:
-
-    ./configure
-    make
-    make check
-    make install
-
-
-Building a source code package
-------------------------------
-
-In a prepared tree, this command creates a source code tarball:
-
-    ./configure && make dist
-
-Alternatively, you can run
-
-    ./utils/build-sources.sh
-
-which builds the source code packages and puts them in the `dist`
-subdirectory.  This script needs a working `zip` command.
-
-
-Features
-========
-
-TRE is not just yet another regexp matcher. TRE has some features
-which are not there in most free POSIX compatible implementations.
-Most of these features are not present in non-free implementations
-either, for that matter.
-
-Approximate matching
---------------------
-
-Approximate pattern matching allows matches to be approximate, that
-is, allows the matches to be close to the searched pattern under some
-measure of closeness.  TRE uses the edit-distance measure (also known
-as the Levenshtein distance) where characters can be inserted,
-deleted, or substituted in the searched text in order to get an exact
-match.
-
-Each insertion, deletion, or substitution adds the distance, or cost,
-of the match.  TRE can report the matches which have a cost lower than
-some given threshold value.  TRE can also be used to search for
-matches with the lowest cost.
-
-TRE includes a version of the agrep (approximate grep) command line
-tool for approximate regexp matching in the style of grep. Unlike
-other agrep implementations (like the one by Sun Wu and Udi Manber
-from University of Arizona) TRE agrep allows full regexps of any
-length, any number of errors, and non-uniform costs for insertion,
-deletion and substitution.
-
-Strict standard conformance
----------------------------
-
-POSIX defines the behaviour of regexp functions precisely.  TRE
-attempts to conform to these specifications as strictly as possible.
-TRE always returns the correct matches for subpatterns, for example.
-Very few other implementations do this correctly.  In fact, the only
-other implementations besides TRE that I am aware of (free or not)
-that get it right are Rx by Tom Lord, Regex++ by John Maddock, and the
-AT&T ast regex by Glenn Fowler and Doug McIlroy.
-
-The standard TRE tries to conform to is the IEEE Std 1003.1-2001, or
-Open Group Base Specifications Issue 6, commonly referred to as
-“POSIX”.  The relevant parts are the base specifications on regular
-expressions (and the rationale) and the description of the `regcomp()`
-API.
-
-For an excellent survey on POSIX regexp matchers, see the testregex
-pages by Glenn Fowler of AT&T Labs Research.
-
-Predictable matching speed
---------------------------
-
-Because of the matching algorithm used in TRE, the maximum time
-consumed by any `regexec()` call is always directly proportional to
-the length of the searched string. There is one exception: if back
-references are used, the matching may take time that grows
-exponentially with the length of the string.  This is because matching
-back references is an NP complete problem, and almost certainly
-requires exponential time to match in the worst case.
-
-Predictable and modest memory consumption
------------------------------------------
-
-A `regexec()` call never allocates memory from the heap. TRE allocates
-all the memory it needs during a `regcomp()` call, and some temporary
-working space from the stack frame for the duration of the `regexec()`
-call.  The amount of temporary space needed is constant during
-matching and does not depend on the searched string. For regexps of
-reasonable size TRE needs less than 50K of dynamically allocated
-memory during the `regcomp()` call, less than 20K for the compiled
-pattern buffer, and less than two kilobytes of temporary working space
-from the stack frame during a `regexec()` call.  There is no time /
-memory tradeoff. TRE is also small in code size; statically linking
-with TRE increases the executable size less than 30K (gcc-3.2, x86,
-GNU/Linux).
-
-Wide character and multibyte character set support
---------------------------------------------------
-
-TRE supports multibyte character sets.  This makes it possible to use
-regexps seamlessly with, for example, Japanese locales.  TRE also
-provides a wide character API.
-
-Binary pattern and data support
--------------------------------
-
-TRE provides APIs which allow binary zero characters both in regexps
-and searched strings.  The standard API cannot be easily used to, for
-example, search for printable words from binary data (although it is
-possible with some hacking).  Searching for patterns which contain
-binary zeroes embedded is not possible at all with the standard API.
-
-Completely thread safe
-----------------------
-
-TRE is completely thread safe.  All the exported functions are
-re-entrant, and a single compiled regexp object can be used
-simultaneously in multiple contexts; e.g. in `main()` and a signal
-handler, or in many threads of a multithreaded application.
-
-Portable
---------
-
-TRE is portable across multiple platforms.  Below is a table of
-platforms and compilers used to develop and test TRE:
-
-<table>
-	<tr><th>Platform</th>				<th>Compiler</th></tr>
-	<tr><td>FreeBSD 14.1</td>			<td>Clang 18</td></tr>
-	<tr><td>Ubuntu 22.04</td>			<td>GCC 11</td></tr>
-	<tr><td>macOS 14.6</td>				<td>Clang 14</td></tr>
-	<tr><td>Windows 11</td>				<td>Microsoft Visual Studio 2022</td></tr>
-</table>
-
-TRE should compile without changes on most modern POSIX-like
-platforms, and be easily portable to any platform with a hosted C
-implementation.
-
-Depending on the platform, you may need to install libutf8 to get
-wide character and multibyte character set support.
-
-Free
-----
-
-TRE is released under a license which is essentially the same as the
-“2 clause” BSD-style license used in NetBSD.  See the file LICENSE for
-details.
-
-Roadmap
--------
-
-There are currently two features, both related to collating elements,
-missing from 100% POSIX compliance.  These are:
-
-* Support for collating elements (e.g. `[[.\<X>.]]`, where `\<X>` is a
-  collating element).  It is not possible to support multi-character
-  collating elements portably, since POSIX does not define a way to
-  determine whether a character sequence is a multi-character
-  collating element or not.
-
-* Support for equivalence classes, for example `[[=\<X>=]]`, where
-  `\<X>` is a collating element.  An equivalence class matches any
-  character which has the same primary collation weight as `\<X>`.
-  Again, POSIX provides no portable mechanism for determining the
-  primary collation weight of a collating element.
-
-Note that other portable regexp implementations don't support
-collating elements either.  The single exception is Regex++, which
-comes with its own database for collating elements for different
-locales.  Support for collating elements and equivalence classes has
-not been widely requested and is not very high on the TODO list at the
-moment.
-
-These are other features I'm planning to implement real soon now:
-
-* All the missing GNU extensions enabled in GNU regex, such as
-  `[[:<:]]` and `[[:>:]]`.
-
-* A `REG_SHORTEST` `regexec()` flag for returning the shortest match
-  instead of the longest match.
-
-* Perl-compatible syntax:
-  * `[:^class:]`
-    Matches anything but the characters in class.  Note that
-    `[^[:class:]]` works already, this would be just a convenience
-    shorthand.
-
-  * `\A`
-    Match only at beginning of string.
-
-  * `\Z`
-    Match only at end of string, or before newline at the end.
-
-  * `\z`
-    Match only at end of string.
-
-  * `\l`
-    Lowercase next char (think vi).
-
-  * `\u`
-    Uppercase next char (think vi).
-
-  * `\L`
-    Lowercase till `\E` (think vi).
-
-  * `\U`
-    Uppercase till `\E` (think vi).
-
-  * `(?=pattern)`
-    Zero-width positive look-ahead assertions.
-
-  * `(?!pattern)`
-    Zero-width negative look-ahead assertions.
-
-  * `(?<=pattern)`
-    Zero-width positive look-behind assertions.
-
-  * `(?<!pattern)`
-    Zero-width negative look-behind assertions.
-
-Documentation especially for the nonstandard features of TRE, such as
-approximate matching, is a work in progress (with “progress” loosely
-defined...)  If you want to find an extension to use, reading the
-`include/tre/tre.h` header might provide some additional hints if you
-are comfortable with C source code.

deps/tre/lib/regcomp.c

@@ -1,188 +0,0 @@
-/*
-  tre_regcomp.c - TRE POSIX compatible regex compilation functions.
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#include <string.h>
-#include <errno.h>
-#include <stdlib.h>
-
-#include "tre-internal.h"
-#include "xmalloc.h"
-
-int
-tre_regncomp(regex_t *preg, const char *regex, size_t n, int cflags)
-{
-  int ret;
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-#if TRE_WCHAR
-  tre_char_t *wregex;
-  size_t wlen;
-
-  wregex = xmalloc(sizeof(tre_char_t) * (n + 1));
-  if (wregex == NULL)
-    return REG_ESPACE;
-
-  /* If the current locale uses the standard single byte encoding of
-     characters, we don't do a multibyte string conversion.  If we did,
-     many applications which use the default locale would break since
-     the default "C" locale uses the 7-bit ASCII character set, and
-     all characters with the eighth bit set would be considered invalid. */
-#if TRE_MULTIBYTE
-  if (TRE_MB_CUR_MAX == 1)
-#endif /* TRE_MULTIBYTE */
-    {
-      size_t i;
-      const unsigned char *str = (const unsigned char *)regex;
-      tre_char_t *wstr = wregex;
-
-      for (i = 0; i < n; i++)
-	*(wstr++) = *(str++);
-      wlen = n;
-    }
-#if TRE_MULTIBYTE
-  else
-    {
-      size_t consumed;
-      tre_char_t *wcptr = wregex;
-#ifdef HAVE_MBSTATE_T
-      mbstate_t state;
-      memset(&state, '\0', sizeof(state));
-#endif /* HAVE_MBSTATE_T */
-      while (n > 0)
-	{
-	  consumed = tre_mbrtowc(wcptr, regex, n, &state);
-
-	  switch (consumed)
-	    {
-	    case 0:
-	      if (*regex == '\0')
-		consumed = 1;
-	      else
-		{
-		  xfree(wregex);
-		  return REG_BADPAT;
-		}
-	      break;
-	    case -1:
-	      DPRINT(("mbrtowc: error %d: %s.\n", errno, strerror(errno)));
-	      xfree(wregex);
-	      return REG_BADPAT;
-	    case -2:
-	      /* The last character wasn't complete.  Let's not call it a
-		 fatal error. */
-	      consumed = n;
-	      break;
-	    }
-	  regex += consumed;
-	  n -= consumed;
-	  wcptr++;
-	}
-      wlen = wcptr - wregex;
-    }
-#endif /* TRE_MULTIBYTE */
-
-  wregex[wlen] = L'\0';
-  ret = tre_compile(preg, wregex, wlen, cflags);
-  xfree(wregex);
-#else /* !TRE_WCHAR */
-  ret = tre_compile(preg, (const tre_char_t *)regex, n, cflags);
-#endif /* !TRE_WCHAR */
-
-  return ret;
-}
-
-/* this version takes bytes literally, to be used with raw vectors */
-int
-tre_regncompb(regex_t *preg, const char *regex, size_t n, int cflags)
-{
-  int ret;
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-#if TRE_WCHAR /* wide chars = we need to convert it all to the wide format */
-  tre_char_t *wregex;
-  size_t i;
-
-  wregex = xmalloc(sizeof(tre_char_t) * n);
-  if (wregex == NULL)
-    return REG_ESPACE;
-
-  for (i = 0; i < n; i++)
-    wregex[i] = (tre_char_t) ((unsigned char) regex[i]);
-
-  ret = tre_compile(preg, wregex, n, cflags | REG_USEBYTES);
-  xfree(wregex);
-#else /* !TRE_WCHAR */
-  ret = tre_compile(preg, (const tre_char_t *)regex, n, cflags | REG_USEBYTES);
-#endif /* !TRE_WCHAR */
-
-  return ret;
-}
-
-int
-tre_regcomp(regex_t *preg, const char *regex, int cflags)
-{
-  size_t n = regex ? strlen(regex) : 0;
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-  return tre_regncomp(preg, regex, n, cflags);
-}
-
-int
-tre_regcompb(regex_t *preg, const char *regex, int cflags)
-{
-  int ret;
-  tre_char_t *wregex;
-  size_t i, n = regex ? strlen(regex) : 0;
-  const unsigned char *str = (const unsigned char *)regex;
-  tre_char_t *wstr;
-
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-  wregex = xmalloc(sizeof(tre_char_t) * (n + 1));
-  if (wregex == NULL) return REG_ESPACE;
-  wstr = wregex;
-
-  for (i = 0; i < n; i++)
-    *(wstr++) = *(str++);
-  wregex[n] = L'\0';
-  ret = tre_compile(preg, wregex, n, cflags | REG_USEBYTES);
-  xfree(wregex);
-  return ret;
-}
-
-
-#ifdef TRE_WCHAR
-int
-tre_regwncomp(regex_t *preg, const wchar_t *regex, size_t n, int cflags)
-{
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-  return tre_compile(preg, regex, n, cflags);
-}
-
-int
-tre_regwcomp(regex_t *preg, const wchar_t *regex, int cflags)
-{
-  size_t n = regex ? wcslen(regex) : 0;
-  if (n > TRE_MAX_RE)
-    return REG_ESPACE;
-  return tre_compile(preg, regex, n, cflags);
-}
-#endif /* TRE_WCHAR */
-
-void
-tre_regfree(regex_t *preg)
-{
-  tre_free(preg);
-}
-
-/* EOF */

deps/tre/lib/regerror.c

@@ -1,86 +0,0 @@
-/*
-  tre_regerror.c - POSIX tre_regerror() implementation for TRE.
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#include <string.h>
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-#ifdef HAVE_WCTYPE_H
-#include <wctype.h>
-#endif /* HAVE_WCTYPE_H */
-
-#include "tre-internal.h"
-
-#ifdef HAVE_GETTEXT
-#include <libintl.h>
-#else
-#define dgettext(p, s) s
-#define gettext(s) s
-#endif
-
-#define _(String) dgettext(PACKAGE, String)
-#define gettext_noop(String) String
-
-#define xstr(s) str(s)
-#define str(s) #s
-
-/* Error message strings for error codes listed in `tre.h'.  This list
-   needs to be in sync with the codes listed there, naturally. */
-static const char *tre_error_messages[] =
-  { gettext_noop("No error"),							/* REG_OK */
-    gettext_noop("No match"),							/* REG_NOMATCH */
-    gettext_noop("Invalid regexp"),						/* REG_BADPAT */
-    gettext_noop("Unknown collating element"),					/* REG_ECOLLATE */
-    gettext_noop("Unknown character class name"),				/* REG_ECTYPE */
-    gettext_noop("Trailing backslash"),						/* REG_EESCAPE */
-    gettext_noop("Invalid back reference"),					/* REG_ESUBREG */
-    gettext_noop("Missing ']'"),						/* REG_EBRACK */
-    gettext_noop("Missing ')'"),						/* REG_EPAREN */
-    gettext_noop("Missing '}'"),						/* REG_EBRACE */
-    gettext_noop("Invalid contents of {}"),					/* REG_BADBR */
-    gettext_noop("Invalid character range"),					/* REG_ERANGE */
-    gettext_noop("Out of memory"),						/* REG_ESPACE */
-    gettext_noop("Invalid use of repetition operators"),			/* REG_BADRPT */
-    gettext_noop("Maximum repetition in {} larger than " xstr(RE_DUP_MAX)),	/* REG_BADMAX */
-  };
-
-size_t
-tre_regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
-{
-  const char *err;
-  size_t err_len;
-
-  /*LINTED*/(void)&preg;
-  if (errcode >= 0
-      && errcode < (int)(sizeof(tre_error_messages)
-			 / sizeof(*tre_error_messages)))
-    err = gettext(tre_error_messages[errcode]);
-  else
-    err = gettext("Unknown error");
-
-  err_len = strlen(err) + 1;
-  if (errbuf_size > 0 && errbuf != NULL)
-    {
-      if (err_len > errbuf_size)
-	{
-	  strncpy(errbuf, err, errbuf_size - 1);
-	  errbuf[errbuf_size - 1] = '\0';
-	}
-      else
-	{
-	  strcpy(errbuf, err);
-	}
-    }
-  return err_len;
-}
-
-/* EOF */

deps/tre/lib/regexec.c

@@ -1,584 +0,0 @@
-/*
-  tre_regexec.c - TRE POSIX compatible matching functions (and more).
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#ifdef TRE_USE_ALLOCA
-/* AIX requires this to be the first thing in the file.	 */
-#ifndef __GNUC__
-# if HAVE_ALLOCA_H
-#  include <alloca.h>
-# else
-#  ifdef _AIX
- #pragma alloca
-#  else
-#   ifndef alloca /* predefined by HP cc +Olibcalls */
-char *alloca ();
-#   endif
-#  endif
-# endif
-#endif
-#endif /* TRE_USE_ALLOCA */
-
-#include <assert.h>
-#include <stdlib.h>
-#include <string.h>
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-#ifdef HAVE_WCTYPE_H
-#include <wctype.h>
-#endif /* HAVE_WCTYPE_H */
-#ifndef TRE_WCHAR
-#include <ctype.h>
-#endif /* !TRE_WCHAR */
-#ifdef HAVE_MALLOC_H
-#include <malloc.h>
-#endif /* HAVE_MALLOC_H */
-#include <limits.h>
-
-#include "tre-internal.h"
-#include "xmalloc.h"
-
-/* Literal alternatives are grouped by the first byte so the matcher can
- * reach the relevant candidates in O(1). In nocase mode the lookup uses the
- * same folded byte mapping that was applied at compile time. */
-static void
-tre_litopt_candidate_range(const tre_literal_opt_t *opt, unsigned char first_byte,
-			   size_t *start, size_t *end)
-{
-  unsigned char key = opt->nocase ? opt->fold_map[first_byte] : first_byte;
-  *start = opt->start_offsets[key];
-  *end = opt->start_offsets[key + 1];
-}
-
-static int
-tre_litopt_bytes_equal(const unsigned char *haystack,
-		       const unsigned char *needle, size_t len,
-		       const unsigned char *fold_map)
-{
-  size_t i;
-
-  if (fold_map == NULL)
-    return memcmp(haystack, needle, len) == 0;
-
-  for (i = 0; i < len; i++)
-    if (fold_map[haystack[i]] != needle[i])
-      return 0;
-  return 1;
-}
-
-static int
-tre_litopt_contains_case(const unsigned char *haystack, size_t hay_len,
-			 const unsigned char *needle, size_t needle_len,
-			 int *match_end_ofs)
-{
-  const unsigned char *p;
-  size_t remaining;
-
-  if (needle_len > hay_len)
-    return 0;
-
-  p = haystack;
-  remaining = hay_len;
-  while (remaining >= needle_len)
-    {
-      p = memchr(p, needle[0], remaining - needle_len + 1);
-      if (p == NULL)
-	return 0;
-      if (memcmp(p, needle, needle_len) == 0)
-	{
-	  if (match_end_ofs != NULL)
-	    *match_end_ofs = (int)(p - haystack + needle_len);
-	  return 1;
-	}
-      remaining = hay_len - (size_t)(p - haystack) - 1;
-      p++;
-    }
-  return 0;
-}
-
-/* Nocase substring matching is still byte-oriented, but scanning once and
- * only checking literals that share the same folded first byte avoids the
- * old O(haystack * literals) restart pattern. */
-static int
-tre_litopt_contains_nocase(const tre_literal_opt_t *opt,
-			   const unsigned char *haystack, size_t hay_len,
-			   int *match_end_ofs)
-{
-  size_t i, start, end, j;
-
-  for (i = 0; i < hay_len; i++)
-    {
-      tre_litopt_candidate_range(opt, haystack[i], &start, &end);
-      for (j = start; j < end; j++)
-	{
-	  const tre_literal_opt_literal_t *lit = &opt->literals[j];
-	  if (lit->len <= hay_len - i
-	      && tre_litopt_bytes_equal(haystack + i, lit->data, lit->len,
-					opt->fold_map))
-	    {
-	      if (match_end_ofs != NULL)
-		*match_end_ofs = (int)(i + lit->len);
-	      return 1;
-	    }
-	}
-    }
-  return 0;
-}
-
-static reg_errcode_t
-tre_match_literal_opt(const tre_tnfa_t *tnfa, const char *string, size_t len,
-		      int eflags, int *match_end_ofs)
-{
-  const tre_literal_opt_t *opt = &tnfa->literal_opt;
-  const unsigned char *haystack = (const unsigned char *)string;
-  size_t start = 0, end = opt->num_literals, i;
-  const unsigned char *fold_map = opt->nocase ? opt->fold_map : NULL;
-
-  if ((opt->mode == TRE_LITERAL_OPT_PREFIX
-       || opt->mode == TRE_LITERAL_OPT_EXACT)
-      && (eflags & REG_NOTBOL))
-    return REG_NOMATCH;
-  if ((opt->mode == TRE_LITERAL_OPT_SUFFIX
-       || opt->mode == TRE_LITERAL_OPT_EXACT)
-      && (eflags & REG_NOTEOL))
-    return REG_NOMATCH;
-
-  if ((opt->mode == TRE_LITERAL_OPT_EXACT
-       || opt->mode == TRE_LITERAL_OPT_PREFIX)
-      && len > 0)
-    tre_litopt_candidate_range(opt, haystack[0], &start, &end);
-
-  if (opt->mode == TRE_LITERAL_OPT_CONTAINS)
-    {
-      if (opt->nocase)
-	return tre_litopt_contains_nocase(opt, haystack, len, match_end_ofs)
-	       ? REG_OK : REG_NOMATCH;
-
-      for (i = 0; i < opt->num_literals; i++)
-	{
-	  const tre_literal_opt_literal_t *lit = &opt->literals[i];
-	  if (tre_litopt_contains_case(haystack, len, lit->data, lit->len,
-				       match_end_ofs))
-	    return REG_OK;
-	}
-      return REG_NOMATCH;
-    }
-
-  for (i = start; i < end; i++)
-    {
-      const tre_literal_opt_literal_t *lit = &opt->literals[i];
-
-      switch (opt->mode)
-	{
-	case TRE_LITERAL_OPT_EXACT:
-	  if (len == lit->len
-	      && tre_litopt_bytes_equal(haystack, lit->data, len, fold_map))
-	    {
-	      if (match_end_ofs != NULL)
-		*match_end_ofs = (int)len;
-	      return REG_OK;
-	    }
-	  break;
-
-	case TRE_LITERAL_OPT_PREFIX:
-	  if (len >= lit->len
-	      && tre_litopt_bytes_equal(haystack, lit->data, lit->len,
-					fold_map))
-	    {
-	      if (match_end_ofs != NULL)
-		*match_end_ofs = (int)lit->len;
-	      return REG_OK;
-	    }
-	  break;
-
-	case TRE_LITERAL_OPT_SUFFIX:
-	  if (len >= lit->len
-	      && tre_litopt_bytes_equal(haystack + len - lit->len, lit->data,
-					lit->len, fold_map))
-	    {
-	      if (match_end_ofs != NULL)
-		*match_end_ofs = (int)len;
-	      return REG_OK;
-	    }
-	  break;
-
-	case TRE_LITERAL_OPT_CONTAINS:
-	case TRE_LITERAL_OPT_NONE:
-	  break;
-	}
-    }
-
-  return REG_NOMATCH;
-}
-
-
-/* Fills the POSIX.2 regmatch_t array according to the TNFA tag and match
-   endpoint values. */
-void
-tre_fill_pmatch(size_t nmatch, regmatch_t pmatch[], int cflags,
-		const tre_tnfa_t *tnfa, int *tags, int match_eo)
-{
-  tre_submatch_data_t *submatch_data;
-  unsigned int i, j;
-  int *parents;
-
-  i = 0;
-  if (match_eo >= 0 && !(cflags & REG_NOSUB))
-    {
-      /* Construct submatch offsets from the tags. */
-      DPRINT(("end tag = t%d = %d\n", tnfa->end_tag, match_eo));
-      submatch_data = tnfa->submatch_data;
-      while (i < tnfa->num_submatches && i < nmatch)
-	{
-	  if (submatch_data[i].so_tag == tnfa->end_tag)
-	    pmatch[i].rm_so = match_eo;
-	  else
-	    pmatch[i].rm_so = tags[submatch_data[i].so_tag];
-
-	  if (submatch_data[i].eo_tag == tnfa->end_tag)
-	    pmatch[i].rm_eo = match_eo;
-	  else
-	    pmatch[i].rm_eo = tags[submatch_data[i].eo_tag];
-
-	  /* If either of the endpoints were not used, this submatch
-	     was not part of the match. */
-	  if (pmatch[i].rm_so == -1 || pmatch[i].rm_eo == -1)
-	    pmatch[i].rm_so = pmatch[i].rm_eo = -1;
-
-	  DPRINT(("pmatch[%d] = {t%d = %d, t%d = %d}\n", i,
-		  submatch_data[i].so_tag, pmatch[i].rm_so,
-		  submatch_data[i].eo_tag, pmatch[i].rm_eo));
-	  i++;
-	}
-      /* Reset all submatches that are not within all of their parent
-	 submatches. */
-      i = 0;
-      while (i < tnfa->num_submatches && i < nmatch)
-	{
-	  if (pmatch[i].rm_eo == -1)
-	    assert(pmatch[i].rm_so == -1);
-	  assert(pmatch[i].rm_so <= pmatch[i].rm_eo);
-
-	  parents = submatch_data[i].parents;
-	  if (parents != NULL)
-	    for (j = 0; parents[j] >= 0; j++)
-	      {
-		DPRINT(("pmatch[%d] parent %d\n", i, parents[j]));
-		if (pmatch[i].rm_so < pmatch[parents[j]].rm_so
-		    || pmatch[i].rm_eo > pmatch[parents[j]].rm_eo)
-		  pmatch[i].rm_so = pmatch[i].rm_eo = -1;
-	      }
-	  i++;
-	}
-    }
-
-  while (i < nmatch)
-    {
-      pmatch[i].rm_so = -1;
-      pmatch[i].rm_eo = -1;
-      i++;
-    }
-}
-
-
-/*
-  Wrapper functions for POSIX compatible regexp matching.
-*/
-
-int
-tre_have_backrefs(const regex_t *preg)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  return tnfa->have_backrefs;
-}
-
-int
-tre_have_approx(const regex_t *preg)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  return tnfa->have_approx;
-}
-
-static int
-tre_match(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-	  tre_str_type_t type, size_t nmatch, regmatch_t pmatch[],
-	  int eflags)
-{
-  reg_errcode_t status;
-  int *tags = NULL, eo;
-  if (tnfa->num_tags > 0 && nmatch > 0)
-    {
-#ifdef TRE_USE_ALLOCA
-      tags = alloca(sizeof(*tags) * tnfa->num_tags);
-#else /* !TRE_USE_ALLOCA */
-      tags = xmalloc(sizeof(*tags) * tnfa->num_tags);
-#endif /* !TRE_USE_ALLOCA */
-      if (tags == NULL)
-	return REG_ESPACE;
-    }
-
-  if (type == STR_BYTE
-      && tnfa->literal_opt.mode != TRE_LITERAL_OPT_NONE
-      && (nmatch == 0 || (tnfa->cflags & REG_NOSUB))
-#ifdef TRE_APPROX
-      && !(eflags & REG_APPROX_MATCHER)
-#endif /* TRE_APPROX */
-      && !(eflags & REG_BACKTRACKING_MATCHER))
-    {
-      size_t byte_len = (len >= 0) ? (size_t)len : strlen((const char *)string);
-      status = tre_match_literal_opt(tnfa, string, byte_len, eflags, &eo);
-
-      /* Even when the caller asked for no submatches, regexec() still has to
-       * clear any pmatch entries it was handed. The normal matcher path does
-       * this through tre_fill_pmatch(), so mirror that behavior here. */
-      if (status == REG_OK && nmatch > 0)
-	tre_fill_pmatch(nmatch, pmatch, tnfa->cflags, tnfa, NULL, eo);
-
-#ifndef TRE_USE_ALLOCA
-      if (tags)
-	xfree(tags);
-#endif /* !TRE_USE_ALLOCA */
-      return status;
-    }
-
-  /* Dispatch to the appropriate matcher. */
-  if (tnfa->have_backrefs || eflags & REG_BACKTRACKING_MATCHER)
-    {
-      /* The regex has back references, use the backtracking matcher. */
-      if (type == STR_USER)
-	{
-	  const tre_str_source *source = string;
-	  if (source->rewind == NULL || source->compare == NULL)
-	    {
-	      /* The backtracking matcher requires rewind and compare
-		 capabilities from the input stream. */
-#ifndef TRE_USE_ALLOCA
-	      if (tags)
-		xfree(tags);
-#endif /* !TRE_USE_ALLOCA */
-	      return REG_BADPAT;
-	    }
-	}
-      status = tre_tnfa_run_backtrack(tnfa, string, len, type,
-				      tags, eflags, &eo);
-    }
-#ifdef TRE_APPROX
-  else if (tnfa->have_approx || eflags & REG_APPROX_MATCHER)
-    {
-      /* The regex uses approximate matching, use the approximate matcher. */
-      regamatch_t match;
-      regaparams_t params;
-      tre_regaparams_default(&params);
-      params.max_err = 0;
-      params.max_cost = 0;
-      status = tre_tnfa_run_approx(tnfa, string, len, type, tags,
-				   &match, params, eflags, &eo);
-    }
-#endif /* TRE_APPROX */
-  else
-    {
-      /* Exact matching, no back references, use the parallel matcher. */
-      status = tre_tnfa_run_parallel(tnfa, string, len, type,
-				     tags, eflags, &eo);
-    }
-
-  if (status == REG_OK)
-    /* A match was found, so fill the submatch registers. */
-    tre_fill_pmatch(nmatch, pmatch, tnfa->cflags, tnfa, tags, eo);
-#ifndef TRE_USE_ALLOCA
-  if (tags)
-    xfree(tags);
-#endif /* !TRE_USE_ALLOCA */
-  return status;
-}
-
-int
-tre_regnexec(const regex_t *preg, const char *str, size_t len,
-	 size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  tre_str_type_t type = (TRE_MB_CUR_MAX == 1) ? STR_BYTE : STR_MBS;
-
-  return tre_match(tnfa, str, len, type, nmatch, pmatch, eflags);
-}
-
-#ifdef TRE_USE_GNUC_REGEXEC_FPL
-int
-tre_regexec(const regex_t *preg, const char *str,
-	size_t nmatch, regmatch_t pmatch[_Restrict_arr_ _REGEX_NELTS (nmatch)],
-	int eflags)
-#else
-int
-tre_regexec(const regex_t *preg, const char *str,
-	size_t nmatch, regmatch_t pmatch[], int eflags)
-#endif
-{
-  return tre_regnexec(preg, str, -1, nmatch, pmatch, eflags);
-}
-
-int
-tre_regexecb(const regex_t *preg, const char *str,
-        size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-
-  return tre_match(tnfa, str, -1, STR_BYTE, nmatch, pmatch, eflags);
-}
-
-int
-tre_regnexecb(const regex_t *preg, const char *str, size_t len,
-        size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-
-  return tre_match(tnfa, str, len, STR_BYTE, nmatch, pmatch, eflags);
-}
-
-
-#ifdef TRE_WCHAR
-
-int
-tre_regwnexec(const regex_t *preg, const wchar_t *str, size_t len,
-	  size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  return tre_match(tnfa, str, len, STR_WIDE, nmatch, pmatch, eflags);
-}
-
-int
-tre_regwexec(const regex_t *preg, const wchar_t *str,
-	 size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  return tre_regwnexec(preg, str, -1, nmatch, pmatch, eflags);
-}
-
-#endif /* TRE_WCHAR */
-
-int
-tre_reguexec(const regex_t *preg, const tre_str_source *str,
-	 size_t nmatch, regmatch_t pmatch[], int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  return tre_match(tnfa, str, -1, STR_USER, nmatch, pmatch, eflags);
-}
-
-
-#ifdef TRE_APPROX
-
-/*
-  Wrapper functions for approximate regexp matching.
-*/
-
-static int
-tre_match_approx(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-		 tre_str_type_t type, regamatch_t *match, regaparams_t params,
-		 int eflags)
-{
-  reg_errcode_t status;
-  int *tags = NULL, eo;
-
-  /* If the regexp does not use approximate matching features, the
-     maximum cost is zero, and the approximate matcher isn't forced,
-     use the exact matcher instead. */
-  if (params.max_cost == 0 && !tnfa->have_approx
-      && !(eflags & REG_APPROX_MATCHER))
-    return tre_match(tnfa, string, len, type, match->nmatch, match->pmatch,
-		     eflags);
-
-  /* Back references are not supported by the approximate matcher. */
-  if (tnfa->have_backrefs)
-    return REG_BADPAT;
-
-  if (tnfa->num_tags > 0 && match->nmatch > 0)
-    {
-#if TRE_USE_ALLOCA
-      tags = alloca(sizeof(*tags) * tnfa->num_tags);
-#else /* !TRE_USE_ALLOCA */
-      tags = xmalloc(sizeof(*tags) * tnfa->num_tags);
-#endif /* !TRE_USE_ALLOCA */
-      if (tags == NULL)
-	return REG_ESPACE;
-    }
-  status = tre_tnfa_run_approx(tnfa, string, len, type, tags,
-			       match, params, eflags, &eo);
-  if (status == REG_OK)
-    tre_fill_pmatch(match->nmatch, match->pmatch, tnfa->cflags, tnfa, tags, eo);
-#ifndef TRE_USE_ALLOCA
-  if (tags)
-    xfree(tags);
-#endif /* !TRE_USE_ALLOCA */
-  return status;
-}
-
-int
-tre_reganexec(const regex_t *preg, const char *str, size_t len,
-	  regamatch_t *match, regaparams_t params, int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  tre_str_type_t type = (TRE_MB_CUR_MAX == 1) ? STR_BYTE : STR_MBS;
-
-  return tre_match_approx(tnfa, str, len, type, match, params, eflags);
-}
-
-int
-tre_regaexec(const regex_t *preg, const char *str,
-	 regamatch_t *match, regaparams_t params, int eflags)
-{
-  return tre_reganexec(preg, str, -1, match, params, eflags);
-}
-
-int
-tre_regaexecb(const regex_t *preg, const char *str,
-          regamatch_t *match, regaparams_t params, int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-
-  return tre_match_approx(tnfa, str, -1, STR_BYTE, match, params, eflags);
-}
-
-#ifdef TRE_WCHAR
-
-int
-tre_regawnexec(const regex_t *preg, const wchar_t *str, size_t len,
-	   regamatch_t *match, regaparams_t params, int eflags)
-{
-  tre_tnfa_t *tnfa = (void *)preg->TRE_REGEX_T_FIELD;
-  return tre_match_approx(tnfa, str, len, STR_WIDE,
-			  match, params, eflags);
-}
-
-int
-tre_regawexec(const regex_t *preg, const wchar_t *str,
-	  regamatch_t *match, regaparams_t params, int eflags)
-{
-  return tre_regawnexec(preg, str, -1, match, params, eflags);
-}
-
-#endif /* TRE_WCHAR */
-
-void
-tre_regaparams_default(regaparams_t *params)
-{
-  memset(params, 0, sizeof(*params));
-  params->cost_ins = 1;
-  params->cost_del = 1;
-  params->cost_subst = 1;
-  params->max_cost = INT_MAX;
-  params->max_ins = INT_MAX;
-  params->max_del = INT_MAX;
-  params->max_subst = INT_MAX;
-  params->max_err = INT_MAX;
-}
-
-#endif /* TRE_APPROX */
-
-/* EOF */

deps/tre/lib/tre-ast.c

@@ -1,226 +0,0 @@
-/*
-  tre-ast.c - Abstract syntax tree (AST) routines
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-#include <assert.h>
-
-#include "tre-ast.h"
-#include "tre-mem.h"
-
-tre_ast_node_t *
-tre_ast_new_node(tre_mem_t mem, tre_ast_type_t type, size_t size)
-{
-  tre_ast_node_t *node;
-
-  node = tre_mem_calloc(mem, sizeof(*node));
-  if (!node)
-    return NULL;
-  node->obj = tre_mem_calloc(mem, size);
-  if (!node->obj)
-    return NULL;
-  node->type = type;
-  node->nullable = -1;
-  node->submatch_id = -1;
-
-  return node;
-}
-
-tre_ast_node_t *
-tre_ast_new_literal(tre_mem_t mem, int code_min, int code_max)
-{
-  tre_ast_node_t *node;
-  tre_literal_t *lit;
-
-  node = tre_ast_new_node(mem, LITERAL, sizeof(tre_literal_t));
-  if (!node)
-    return NULL;
-  lit = node->obj;
-  lit->code_min = code_min;
-  lit->code_max = code_max;
-  lit->position = -1;
-
-  return node;
-}
-
-tre_ast_node_t *
-tre_ast_new_iter(tre_mem_t mem, tre_ast_node_t *arg, int min, int max,
-		 int minimal)
-{
-  tre_ast_node_t *node;
-  tre_iteration_t *iter;
-
-  node = tre_ast_new_node(mem, ITERATION, sizeof(tre_iteration_t));
-  if (!node)
-    return NULL;
-  iter = node->obj;
-  iter->arg = arg;
-  iter->min = min;
-  iter->max = max;
-  iter->minimal = minimal;
-  node->num_submatches = arg->num_submatches;
-
-  return node;
-}
-
-tre_ast_node_t *
-tre_ast_new_union(tre_mem_t mem, tre_ast_node_t *left, tre_ast_node_t *right)
-{
-  tre_ast_node_t *node;
-
-  node = tre_ast_new_node(mem, UNION, sizeof(tre_union_t));
-  if (node == NULL)
-    return NULL;
-  ((tre_union_t *)node->obj)->left = left;
-  ((tre_union_t *)node->obj)->right = right;
-  node->num_submatches = left->num_submatches + right->num_submatches;
-
-  return node;
-}
-
-tre_ast_node_t *
-tre_ast_new_catenation(tre_mem_t mem, tre_ast_node_t *left,
-		       tre_ast_node_t *right)
-{
-  tre_ast_node_t *node;
-
-  node = tre_ast_new_node(mem, CATENATION, sizeof(tre_catenation_t));
-  if (node == NULL)
-    return NULL;
-  ((tre_catenation_t *)node->obj)->left = left;
-  ((tre_catenation_t *)node->obj)->right = right;
-  node->num_submatches = left->num_submatches + right->num_submatches;
-
-  return node;
-}
-
-#ifdef TRE_DEBUG
-
-static void
-tre_findent(FILE *stream, int i)
-{
-  while (i-- > 0)
-    fputc(' ', stream);
-}
-
-void
-tre_print_params(int *params)
-{
-  int i;
-  if (params)
-    {
-      DPRINT(("params ["));
-      for (i = 0; i < TRE_PARAM_LAST; i++)
-	{
-	  if (params[i] == TRE_PARAM_UNSET)
-	    DPRINT(("unset"));
-	  else if (params[i] == TRE_PARAM_DEFAULT)
-	    DPRINT(("default"));
-	  else
-	    DPRINT(("%d", params[i]));
-	  if (i < TRE_PARAM_LAST - 1)
-	    DPRINT((", "));
-	}
-      DPRINT(("]"));
-    }
-}
-
-static void
-tre_do_print(FILE *stream, tre_ast_node_t *ast, int indent)
-{
-  int code_min, code_max, pos;
-  int num_tags = ast->num_tags;
-  tre_literal_t *lit;
-  tre_iteration_t *iter;
-
-  tre_findent(stream, indent);
-  switch (ast->type)
-    {
-    case LITERAL:
-      lit = ast->obj;
-      code_min = lit->code_min;
-      code_max = lit->code_max;
-      pos = lit->position;
-      if (IS_EMPTY(lit))
-	{
-	  fprintf(stream, "literal empty\n");
-	}
-      else if (IS_ASSERTION(lit))
-	{
-	  int i;
-	  char *assertions[] = { "bol", "eol", "ctype", "!ctype",
-				 "bow", "eow", "wb", "!wb" };
-	  if (code_max >= ASSERT_LAST << 1)
-	    assert(0);
-	  fprintf(stream, "assertions: ");
-	  for (i = 0; (1 << i) <= ASSERT_LAST; i++)
-	    if (code_max & (1 << i))
-	      fprintf(stream, "%s ", assertions[i]);
-	  fprintf(stream, "\n");
-	}
-      else if (IS_TAG(lit))
-	{
-	  fprintf(stream, "tag %d\n", code_max);
-	}
-      else if (IS_BACKREF(lit))
-	{
-	  fprintf(stream, "backref %d, pos %d\n", code_max, pos);
-	}
-      else if (IS_PARAMETER(lit))
-	{
-	  tre_print_params(lit->u.params);
-	  fprintf(stream, "\n");
-	}
-      else
-	{
-	  fprintf(stream, "literal (%c, %c) (%d, %d), pos %d, sub %d, "
-		  "%d tags\n", code_min, code_max, code_min, code_max, pos,
-		  ast->submatch_id, num_tags);
-	}
-      break;
-    case ITERATION:
-      iter = ast->obj;
-      fprintf(stream, "iteration {%d, %d}, sub %d, %d tags, %s\n",
-	      iter->min, iter->max, ast->submatch_id, num_tags,
-	      iter->minimal ? "minimal" : "greedy");
-      tre_do_print(stream, iter->arg, indent + 2);
-      break;
-    case UNION:
-      fprintf(stream, "union, sub %d, %d tags\n", ast->submatch_id, num_tags);
-      tre_do_print(stream, ((tre_union_t *)ast->obj)->left, indent + 2);
-      tre_do_print(stream, ((tre_union_t *)ast->obj)->right, indent + 2);
-      break;
-    case CATENATION:
-      fprintf(stream, "catenation, sub %d, %d tags\n", ast->submatch_id,
-	      num_tags);
-      tre_do_print(stream, ((tre_catenation_t *)ast->obj)->left, indent + 2);
-      tre_do_print(stream, ((tre_catenation_t *)ast->obj)->right, indent + 2);
-      break;
-    default:
-      assert(0);
-      break;
-    }
-}
-
-static void
-tre_ast_fprint(FILE *stream, tre_ast_node_t *ast)
-{
-  tre_do_print(stream, ast, 0);
-}
-
-void
-tre_ast_print(tre_ast_node_t *tree)
-{
-  printf("AST:\n");
-  tre_ast_fprint(stdout, tree);
-}
-
-#endif /* TRE_DEBUG */
-
-/* EOF */

deps/tre/lib/tre-ast.h

@@ -1,128 +0,0 @@
-/*
-  tre-ast.h - Abstract syntax tree (AST) definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-
-#ifndef TRE_AST_H
-#define TRE_AST_H 1
-
-#include "tre-mem.h"
-#include "tre-internal.h"
-#include "tre-compile.h"
-
-/* The different AST node types. */
-typedef enum {
-  LITERAL,
-  CATENATION,
-  ITERATION,
-  UNION
-} tre_ast_type_t;
-
-/* Special subtypes of TRE_LITERAL. */
-#define EMPTY	  -1   /* Empty leaf (denotes empty string). */
-#define ASSERTION -2   /* Assertion leaf. */
-#define TAG	  -3   /* Tag leaf. */
-#define BACKREF	  -4   /* Back reference leaf. */
-#define PARAMETER -5   /* Parameter. */
-
-#define IS_SPECIAL(x)	((x)->code_min < 0)
-#define IS_EMPTY(x)	((x)->code_min == EMPTY)
-#define IS_ASSERTION(x) ((x)->code_min == ASSERTION)
-#define IS_TAG(x)	((x)->code_min == TAG)
-#define IS_BACKREF(x)	((x)->code_min == BACKREF)
-#define IS_PARAMETER(x) ((x)->code_min == PARAMETER)
-
-
-/* A generic AST node.  All AST nodes consist of this node on the top
-   level with `obj' pointing to the actual content. */
-typedef struct {
-  tre_ast_type_t type;   /* Type of the node. */
-  void *obj;             /* Pointer to actual node. */
-  int nullable;
-  int submatch_id;
-  unsigned int num_submatches;
-  unsigned int num_tags;
-  tre_pos_and_tags_t *firstpos;
-  tre_pos_and_tags_t *lastpos;
-} tre_ast_node_t;
-
-
-/* A "literal" node.  These are created for assertions, back references,
-   tags, matching parameter settings, and all expressions that match one
-   character. */
-typedef struct {
-  long code_min;
-  long code_max;
-  int position;
-  union {
-    tre_ctype_t class;
-    int *params;
-  } u;
-  tre_ctype_t *neg_classes;
-} tre_literal_t;
-
-/* A "catenation" node.	 These are created when two regexps are concatenated.
-   If there are more than one subexpressions in sequence, the `left' part
-   holds all but the last, and `right' part holds the last subexpression
-   (catenation is left associative). */
-typedef struct {
-  tre_ast_node_t *left;
-  tre_ast_node_t *right;
-} tre_catenation_t;
-
-/* An "iteration" node.	 These are created for the "*", "+", "?", and "{m,n}"
-   operators. */
-typedef struct {
-  /* Subexpression to match. */
-  tre_ast_node_t *arg;
-  /* Minimum number of consecutive matches. */
-  int min;
-  /* Maximum number of consecutive matches. */
-  int max;
-  /* If 0, match as many characters as possible, if 1 match as few as
-     possible.	Note that this does not always mean the same thing as
-     matching as many/few repetitions as possible. */
-  unsigned int minimal:1;
-  /* Approximate matching parameters (or NULL). */
-  int *params;
-} tre_iteration_t;
-
-/* An "union" node.  These are created for the "|" operator. */
-typedef struct {
-  tre_ast_node_t *left;
-  tre_ast_node_t *right;
-} tre_union_t;
-
-tre_ast_node_t *
-tre_ast_new_node(tre_mem_t mem, tre_ast_type_t type, size_t size);
-
-tre_ast_node_t *
-tre_ast_new_literal(tre_mem_t mem, int code_min, int code_max);
-
-tre_ast_node_t *
-tre_ast_new_iter(tre_mem_t mem, tre_ast_node_t *arg, int min, int max,
-		 int minimal);
-
-tre_ast_node_t *
-tre_ast_new_union(tre_mem_t mem, tre_ast_node_t *left, tre_ast_node_t *right);
-
-tre_ast_node_t *
-tre_ast_new_catenation(tre_mem_t mem, tre_ast_node_t *left,
-		       tre_ast_node_t *right);
-
-#ifdef TRE_DEBUG
-void
-tre_ast_print(tre_ast_node_t *tree);
-
-/* XXX - rethink AST printing API */
-void
-tre_print_params(int *params);
-#endif /* TRE_DEBUG */
-
-#endif /* TRE_AST_H */
-
-/* EOF */

deps/tre/lib/tre-compile.h

@@ -1,27 +0,0 @@
-/*
-  tre-compile.h: Regex compilation definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-
-#ifndef TRE_COMPILE_H
-#define TRE_COMPILE_H 1
-
-typedef struct {
-  int position;
-  int code_min;
-  int code_max;
-  int *tags;
-  int assertions;
-  tre_ctype_t class;
-  tre_ctype_t *neg_classes;
-  int backref;
-  int *params;
-} tre_pos_and_tags_t;
-
-#endif /* TRE_COMPILE_H */
-
-/* EOF */

deps/tre/lib/tre-filter.c

@@ -1,73 +0,0 @@
-/*
-  tre-filter.c: Histogram filter to quickly find regexp match candidates
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-/* The idea of this filter is quite simple.  First, let's assume the
-   search pattern is a simple string.  In order for a substring of a
-   longer string to match the search pattern, it must have the same
-   numbers of different characters as the pattern, and those
-   characters must occur in the same order as they occur in pattern. */
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-#include <stdio.h>
-#include "tre-internal.h"
-#include "tre-filter.h"
-
-int
-tre_filter_find(const unsigned char *str, size_t len, tre_filter_t *filter)
-{
-  unsigned short counts[256];
-  unsigned int i;
-  unsigned int window_len = filter->window_len;
-  tre_filter_profile_t *profile = filter->profile;
-  const unsigned char *str_orig = str;
-
-  DPRINT(("tre_filter_find: %.*s\n", len, str));
-
-  for (i = 0; i < elementsof(counts); i++)
-    counts[i] = 0;
-
-  i = 0;
-  while (*str && i < window_len && i < len)
-    {
-      counts[*str]++;
-      i++;
-      str++;
-      len--;
-    }
-
-  while (len > 0)
-    {
-      tre_filter_profile_t *p;
-      counts[*str]++;
-      counts[*(str - window_len)]--;
-
-      p = profile;
-      while (p->ch)
-	{
-	  if (counts[p->ch] < p->count)
-	    break;
-	  p++;
-	}
-      if (!p->ch)
-	{
-	  DPRINT(("Found possible match at %d\n",
-		  str - str_orig));
-	  return str - str_orig;
-	}
-      else
-	{
-	  DPRINT(("No match so far...\n"));
-	}
-      len--;
-      str++;
-    }
-  DPRINT(("This string cannot match.\n"));
-  return -1;
-}

deps/tre/lib/tre-filter.h

@@ -1,19 +0,0 @@
-
-
-
-
-typedef struct {
-  unsigned char ch;
-  unsigned char count;
-} tre_filter_profile_t;
-
-typedef struct {
-  /* Length of the window where the character counts are kept. */
-  int window_len;
-  /* Required character counts table. */
-  tre_filter_profile_t *profile;
-} tre_filter_t;
-
-
-int
-tre_filter_find(const unsigned char *str, size_t len, tre_filter_t *filter);

deps/tre/lib/tre-internal.h

@@ -1,319 +0,0 @@
-/*
-  tre-internal.h - TRE internal definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifndef TRE_INTERNAL_H
-#define TRE_INTERNAL_H 1
-
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-
-#ifdef HAVE_WCTYPE_H
-#include <wctype.h>
-#endif /* HAVE_WCTYPE_H */
-
-#ifdef HAVE_SYS_TYPES_H
-#include <sys/types.h>
-#endif /* HAVE_SYS_TYPES_H */
-
-#include <limits.h>
-#include <ctype.h>
-#include "../local_includes/tre.h"
-
-#define TRE_MAX_RE	65536
-#define TRE_MAX_STRING	INT_MAX
-#define TRE_MAX_STACK	1048576
-
-#ifdef TRE_DEBUG
-#include <stdio.h>
-#define DPRINT(msg) do {printf msg; fflush(stdout);} while(/*CONSTCOND*/(void)0,0)
-#else /* !TRE_DEBUG */
-#define DPRINT(msg) do { } while(/*CONSTCOND*/(void)0,0)
-#endif /* !TRE_DEBUG */
-
-#define elementsof(x)	( sizeof(x) / sizeof(x[0]) )
-
-#ifdef HAVE_MBRTOWC
-#define tre_mbrtowc(pwc, s, n, ps) (mbrtowc((pwc), (s), (n), (ps)))
-#else /* !HAVE_MBRTOWC */
-#ifdef HAVE_MBTOWC
-#define tre_mbrtowc(pwc, s, n, ps) (mbtowc((pwc), (s), (n)))
-#endif /* HAVE_MBTOWC */
-#endif /* !HAVE_MBRTOWC */
-
-#ifdef TRE_MULTIBYTE
-#ifdef HAVE_MBSTATE_T
-#define TRE_MBSTATE
-#endif /* TRE_MULTIBYTE */
-#endif /* HAVE_MBSTATE_T */
-
-/* Define the character types and functions. */
-#ifdef TRE_WCHAR
-
-/* Wide characters. */
-typedef wint_t tre_cint_t;
-#if WCHAR_MAX <= INT_MAX
-#define TRE_CHAR_MAX WCHAR_MAX
-#else /* WCHAR_MAX > INT_MAX */
-#define TRE_CHAR_MAX INT_MAX
-#endif
-
-#ifdef TRE_MULTIBYTE
-#define TRE_MB_CUR_MAX MB_CUR_MAX
-#else /* !TRE_MULTIBYTE */
-#define TRE_MB_CUR_MAX 1
-#endif /* !TRE_MULTIBYTE */
-
-#define tre_isalnum iswalnum
-#define tre_isalpha iswalpha
-#ifdef HAVE_ISWBLANK
-#define tre_isblank iswblank
-#endif /* HAVE_ISWBLANK */
-#define tre_iscntrl iswcntrl
-#define tre_isdigit iswdigit
-#define tre_isgraph iswgraph
-#define tre_islower iswlower
-#define tre_isprint iswprint
-#define tre_ispunct iswpunct
-#define tre_isspace iswspace
-#define tre_isupper iswupper
-#define tre_isxdigit iswxdigit
-
-#define tre_tolower towlower
-#define tre_toupper towupper
-#define tre_strlen  wcslen
-
-#else /* !TRE_WCHAR */
-
-/* 8 bit characters. */
-typedef short tre_cint_t;
-#define TRE_CHAR_MAX 255
-#define TRE_MB_CUR_MAX 1
-
-#define tre_isalnum isalnum
-#define tre_isalpha isalpha
-#ifdef HAVE_ISASCII
-#define tre_isascii isascii
-#endif /* HAVE_ISASCII */
-#ifdef HAVE_ISBLANK
-#define tre_isblank isblank
-#endif /* HAVE_ISBLANK */
-#define tre_iscntrl iscntrl
-#define tre_isdigit isdigit
-#define tre_isgraph isgraph
-#define tre_islower islower
-#define tre_isprint isprint
-#define tre_ispunct ispunct
-#define tre_isspace isspace
-#define tre_isupper isupper
-#define tre_isxdigit isxdigit
-
-#define tre_tolower(c) (tre_cint_t)(tolower(c))
-#define tre_toupper(c) (tre_cint_t)(toupper(c))
-#define tre_strlen(s)  (strlen((const char*)s))
-
-#endif /* !TRE_WCHAR */
-
-#if defined(TRE_WCHAR) && defined(HAVE_ISWCTYPE) && defined(HAVE_WCTYPE)
-#define TRE_USE_SYSTEM_WCTYPE 1
-#endif
-
-#ifdef TRE_USE_SYSTEM_WCTYPE
-/* Use system provided iswctype() and wctype(). */
-typedef wctype_t tre_ctype_t;
-#define tre_isctype iswctype
-#define tre_ctype   wctype
-#else /* !TRE_USE_SYSTEM_WCTYPE */
-/* Define our own versions of iswctype() and wctype(). */
-typedef int (*tre_ctype_t)(tre_cint_t);
-#define tre_isctype(c, type) ( (type)(c) )
-tre_ctype_t tre_ctype(const char *name);
-#endif /* !TRE_USE_SYSTEM_WCTYPE */
-
-typedef enum { STR_WIDE, STR_BYTE, STR_MBS, STR_USER } tre_str_type_t;
-
-/* Returns number of bytes to add to (char *)ptr to make it
-   properly aligned for the type. */
-#define ALIGN(ptr, type) \
-  ((((long)ptr) % sizeof(type)) \
-   ? (sizeof(type) - (((long)ptr) % sizeof(type))) \
-   : 0)
-
-#undef MAX
-#undef MIN
-#define MAX(a, b) (((a) >= (b)) ? (a) : (b))
-#define MIN(a, b) (((a) <= (b)) ? (a) : (b))
-
-/* Define STRF to the correct printf formatter for strings. */
-#ifdef TRE_WCHAR
-#define STRF "ls"
-#else /* !TRE_WCHAR */
-#define STRF "s"
-#endif /* !TRE_WCHAR */
-
-/* TNFA transition type. A TNFA state is an array of transitions,
-   the terminator is a transition with NULL `state'. */
-typedef struct tnfa_transition tre_tnfa_transition_t;
-
-struct tnfa_transition {
-  /* Range of accepted characters. */
-  tre_cint_t code_min;
-  tre_cint_t code_max;
-  /* Pointer to the destination state. */
-  tre_tnfa_transition_t *state;
-  /* ID number of the destination state. */
-  int state_id;
-  /* -1 terminated array of tags (or NULL). */
-  int *tags;
-  /* Matching parameters settings (or NULL). */
-  int *params;
-  /* Assertion bitmap. */
-  int assertions;
-  /* Assertion parameters. */
-  union {
-    /* Character class assertion. */
-    tre_ctype_t class;
-    /* Back reference assertion. */
-    int backref;
-  } u;
-  /* Negative character class assertions. */
-  tre_ctype_t *neg_classes;
-};
-
-
-/* Assertions. */
-#define ASSERT_AT_BOL		  1   /* Beginning of line. */
-#define ASSERT_AT_EOL		  2   /* End of line. */
-#define ASSERT_CHAR_CLASS	  4   /* Character class in `class'. */
-#define ASSERT_CHAR_CLASS_NEG	  8   /* Character classes in `neg_classes'. */
-#define ASSERT_AT_BOW		 16   /* Beginning of word. */
-#define ASSERT_AT_EOW		 32   /* End of word. */
-#define ASSERT_AT_WB		 64   /* Word boundary. */
-#define ASSERT_AT_WB_NEG	128   /* Not a word boundary. */
-#define ASSERT_BACKREF		256   /* A back reference in `backref'. */
-#define ASSERT_LAST		256
-
-/* Tag directions. */
-typedef enum {
-  TRE_TAG_MINIMIZE = 0,
-  TRE_TAG_MAXIMIZE = 1
-} tre_tag_direction_t;
-
-/* Parameters that can be changed dynamically while matching. */
-typedef enum {
-  TRE_PARAM_COST_INS	    = 0,
-  TRE_PARAM_COST_DEL	    = 1,
-  TRE_PARAM_COST_SUBST	    = 2,
-  TRE_PARAM_COST_MAX	    = 3,
-  TRE_PARAM_MAX_INS	    = 4,
-  TRE_PARAM_MAX_DEL	    = 5,
-  TRE_PARAM_MAX_SUBST	    = 6,
-  TRE_PARAM_MAX_ERR	    = 7,
-  TRE_PARAM_DEPTH	    = 8,
-  TRE_PARAM_LAST	    = 9
-} tre_param_t;
-
-/* Unset matching parameter */
-#define TRE_PARAM_UNSET -1
-
-/* Signifies the default matching parameter value. */
-#define TRE_PARAM_DEFAULT -2
-
-/* Instructions to compute submatch register values from tag values
-   after a successful match.  */
-struct tre_submatch_data {
-  /* Tag that gives the value for rm_so (submatch start offset). */
-  int so_tag;
-  /* Tag that gives the value for rm_eo (submatch end offset). */
-  int eo_tag;
-  /* List of submatches this submatch is contained in. */
-  int *parents;
-};
-
-typedef struct tre_submatch_data tre_submatch_data_t;
-
-typedef enum {
-  TRE_LITERAL_OPT_NONE = 0,
-  TRE_LITERAL_OPT_CONTAINS,
-  TRE_LITERAL_OPT_PREFIX,
-  TRE_LITERAL_OPT_SUFFIX,
-  TRE_LITERAL_OPT_EXACT
-} tre_literal_opt_mode_t;
-
-typedef struct {
-  unsigned char *data;
-  size_t len;
-} tre_literal_opt_literal_t;
-
-typedef struct {
-  tre_literal_opt_mode_t mode;
-  int nocase;
-  size_t num_literals;
-  /* Folded byte mapping used by the nocase fast path. */
-  unsigned char fold_map[256];
-  /* Literal index ranges grouped by the first literal byte. */
-  size_t start_offsets[257];
-  tre_literal_opt_literal_t *literals;
-} tre_literal_opt_t;
-
-
-/* TNFA definition. */
-typedef struct tnfa tre_tnfa_t;
-
-struct tnfa {
-  tre_tnfa_transition_t *transitions;
-  unsigned int num_transitions;
-  tre_tnfa_transition_t *initial;
-  tre_tnfa_transition_t *final;
-  tre_submatch_data_t *submatch_data;
-  char *firstpos_chars;
-  int first_char;
-  unsigned int num_submatches;
-  tre_tag_direction_t *tag_directions;
-  int *minimal_tags;
-  int num_tags;
-  int num_minimals;
-  int end_tag;
-  int num_states;
-  int cflags;
-  int have_backrefs;
-  int have_approx;
-  int params_depth;
-  tre_literal_opt_t literal_opt;
-};
-
-int
-tre_compile(regex_t *preg, const tre_char_t *regex, size_t n, int cflags);
-
-void
-tre_free(regex_t *preg);
-
-void
-tre_fill_pmatch(size_t nmatch, regmatch_t pmatch[], int cflags,
-		const tre_tnfa_t *tnfa, int *tags, int match_eo);
-
-reg_errcode_t
-tre_tnfa_run_parallel(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-		      tre_str_type_t type, int *match_tags, int eflags,
-		      int *match_end_ofs);
-
-reg_errcode_t
-tre_tnfa_run_backtrack(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-		       tre_str_type_t type, int *match_tags, int eflags,
-		       int *match_end_ofs);
-
-#ifdef TRE_APPROX
-reg_errcode_t
-tre_tnfa_run_approx(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-		    tre_str_type_t type, int *match_tags, regamatch_t *match,
-		    regaparams_t params, int eflags, int *match_end_ofs);
-#endif /* TRE_APPROX */
-
-#endif /* TRE_INTERNAL_H */
-
-/* EOF */

deps/tre/lib/tre-match-backtrack.c

@@ -1,676 +0,0 @@
-/*
-  tre-match-backtrack.c - TRE backtracking regex matching engine
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-/*
-  This matcher is for regexps that use back referencing.  Regexp matching
-  with back referencing is an NP-complete problem on the number of back
-  references.  The easiest way to match them is to use a backtracking
-  routine which basically goes through all possible paths in the TNFA
-  and chooses the one which results in the best (leftmost and longest)
-  match.  This can be spectacularly expensive and may run out of stack
-  space, but there really is no better known generic algorithm.	 Quoting
-  Henry Spencer from comp.compilers:
-  <URL: http://compilers.iecc.com/comparch/article/93-03-102>
-
-    POSIX.2 REs require longest match, which is really exciting to
-    implement since the obsolete ("basic") variant also includes
-    \<digit>.  I haven't found a better way of tackling this than doing
-    a preliminary match using a DFA (or simulation) on a modified RE
-    that just replicates subREs for \<digit>, and then doing a
-    backtracking match to determine whether the subRE matches were
-    right.  This can be rather slow, but I console myself with the
-    thought that people who use \<digit> deserve very slow execution.
-    (Pun unintentional but very appropriate.)
-
-*/
-
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#ifdef TRE_USE_ALLOCA
-/* AIX requires this to be the first thing in the file.	 */
-#ifndef __GNUC__
-# if HAVE_ALLOCA_H
-#  include <alloca.h>
-# else
-#  ifdef _AIX
- #pragma alloca
-#  else
-#   ifndef alloca /* predefined by HP cc +Olibcalls */
-char *alloca ();
-#   endif
-#  endif
-# endif
-#endif
-#endif /* TRE_USE_ALLOCA */
-
-#include <assert.h>
-#include <stdlib.h>
-#include <string.h>
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-#ifdef HAVE_WCTYPE_H
-#include <wctype.h>
-#endif /* HAVE_WCTYPE_H */
-#ifndef TRE_WCHAR
-#include <ctype.h>
-#endif /* !TRE_WCHAR */
-#ifdef HAVE_MALLOC_H
-#include <malloc.h>
-#endif /* HAVE_MALLOC_H */
-
-#include "tre-internal.h"
-#include "tre-mem.h"
-#include "tre-match-utils.h"
-#include "xmalloc.h"
-
-typedef struct {
-  int pos;
-  const char *str_byte;
-#ifdef TRE_WCHAR
-  const wchar_t *str_wide;
-#endif /* TRE_WCHAR */
-  tre_tnfa_transition_t *state;
-  int state_id;
-  int next_c;
-  int *tags;
-#ifdef TRE_MBSTATE
-  mbstate_t mbstate;
-#endif /* TRE_MBSTATE */
-} tre_backtrack_item_t;
-
-typedef struct tre_backtrack_struct {
-  tre_backtrack_item_t item;
-  struct tre_backtrack_struct *prev;
-  struct tre_backtrack_struct *next;
-} *tre_backtrack_t;
-
-#ifdef TRE_WCHAR
-#define BT_STACK_WIDE_IN(_str_wide)	stack->item.str_wide = (_str_wide)
-#define BT_STACK_WIDE_OUT		(str_wide) = stack->item.str_wide
-#else /* !TRE_WCHAR */
-#define BT_STACK_WIDE_IN(_str_wide)
-#define BT_STACK_WIDE_OUT
-#endif /* !TRE_WCHAR */
-
-#ifdef TRE_MBSTATE
-#define BT_STACK_MBSTATE_IN  stack->item.mbstate = (mbstate)
-#define BT_STACK_MBSTATE_OUT (mbstate) = stack->item.mbstate
-#else /* !TRE_MBSTATE */
-#define BT_STACK_MBSTATE_IN
-#define BT_STACK_MBSTATE_OUT
-#endif /* !TRE_MBSTATE */
-
-
-#ifdef TRE_USE_ALLOCA
-#define tre_bt_mem_new		  tre_mem_newa
-#define tre_bt_mem_alloc	  tre_mem_alloca
-#define tre_bt_mem_destroy(obj)	  do { } while (0)
-#define xafree(obj)		  do { } while (0) /* do nothing, obj was obtained with alloca() */
-#else /* !TRE_USE_ALLOCA */
-#define tre_bt_mem_new		  tre_mem_new
-#define tre_bt_mem_alloc	  tre_mem_alloc
-#define tre_bt_mem_destroy	  tre_mem_destroy
-#define xafree(obj)		  xfree(obj)
-#endif /* !TRE_USE_ALLOCA */
-
-
-#define BT_STACK_PUSH(_pos, _str_byte, _str_wide, _state, _state_id, _next_c, _tags, _mbstate) \
-  do									      \
-    {									      \
-      int i;								      \
-      if (!stack->next)							      \
-	{								      \
-	  tre_backtrack_t s;						      \
-	  s = tre_bt_mem_alloc(mem, sizeof(*s));			      \
-	  if (!s)							      \
-	    {								      \
-	      tre_bt_mem_destroy(mem);					      \
-	      if (tags)							      \
-		xafree(tags);						      \
-	      if (pmatch)						      \
-		xafree(pmatch);						      \
-	      if (states_seen)						      \
-		xafree(states_seen);					      \
-	      return REG_ESPACE;					      \
-	    }								      \
-	  s->prev = stack;						      \
-	  s->next = NULL;						      \
-	  s->item.tags = tre_bt_mem_alloc(mem,				      \
-					  sizeof(*tags) * tnfa->num_tags);    \
-	  if (!s->item.tags)						      \
-	    {								      \
-	      tre_bt_mem_destroy(mem);					      \
-	      if (tags)							      \
-		xafree(tags);						      \
-	      if (pmatch)						      \
-		xafree(pmatch);						      \
-	      if (states_seen)						      \
-		xafree(states_seen);					      \
-	      return REG_ESPACE;					      \
-	    }								      \
-	  stack->next = s;						      \
-	  stack = s;							      \
-	}								      \
-      else								      \
-	stack = stack->next;						      \
-      stack->item.pos = (_pos);						      \
-      stack->item.str_byte = (_str_byte);				      \
-      BT_STACK_WIDE_IN(_str_wide);					      \
-      stack->item.state = (_state);					      \
-      stack->item.state_id = (_state_id);				      \
-      stack->item.next_c = (_next_c);					      \
-      for (i = 0; i < tnfa->num_tags; i++)				      \
-	stack->item.tags[i] = (_tags)[i];				      \
-      BT_STACK_MBSTATE_IN;						      \
-    }									      \
-  while (/*CONSTCOND*/(void)0,0)
-
-#define BT_STACK_POP()							      \
-  do									      \
-    {									      \
-      int i;								      \
-      assert(stack->prev);						      \
-      pos = stack->item.pos;						      \
-      if (type == STR_USER)                                                   \
-        str_source->rewind(pos + pos_add_next, str_source->context);          \
-      str_byte = stack->item.str_byte;					      \
-      BT_STACK_WIDE_OUT;						      \
-      state = stack->item.state;					      \
-      next_c = (tre_char_t) stack->item.next_c;					      \
-      for (i = 0; i < tnfa->num_tags; i++)				      \
-	tags[i] = stack->item.tags[i];					      \
-      BT_STACK_MBSTATE_OUT;						      \
-      stack = stack->prev;						      \
-    }									      \
-  while (/*CONSTCOND*/(void)0,0)
-
-#undef MIN
-#define MIN(a, b) ((a) <= (b) ? (a) : (b))
-
-reg_errcode_t
-tre_tnfa_run_backtrack(const tre_tnfa_t *tnfa, const void *string,
-		       ssize_t len, tre_str_type_t type, int *match_tags,
-		       int eflags, int *match_end_ofs)
-{
-  /* State variables required by GET_NEXT_WCHAR. */
-  tre_char_t prev_c = 0, next_c = 0;
-  const char *str_byte = string;
-  ssize_t pos = 0;
-  unsigned int pos_add_next = 1;
-#ifdef TRE_WCHAR
-  const wchar_t *str_wide = string;
-#ifdef TRE_MBSTATE
-  mbstate_t mbstate;
-#endif /* TRE_MBSTATE */
-#endif /* TRE_WCHAR */
-  int reg_notbol = eflags & REG_NOTBOL;
-  int reg_noteol = eflags & REG_NOTEOL;
-  int reg_newline = tnfa->cflags & REG_NEWLINE;
-  int str_user_end = 0;
-
-  /* These are used to remember the necessary values of the above
-     variables to return to the position where the current search
-     started from. */
-  int next_c_start;
-  const char *str_byte_start;
-  int pos_start = -1;
-#ifdef TRE_WCHAR
-  const wchar_t *str_wide_start;
-#endif /* TRE_WCHAR */
-#ifdef TRE_MBSTATE
-  mbstate_t mbstate_start;
-#endif /* TRE_MBSTATE */
-  reg_errcode_t ret;
-
-  /* End offset of best match so far, or -1 if no match found yet. */
-  int match_eo = -1;
-  /* Tag arrays. */
-  int *next_tags, *tags = NULL;
-  /* Current TNFA state. */
-  tre_tnfa_transition_t *state;
-  int *states_seen = NULL;
-
-  /* Memory allocator to for allocating the backtracking stack. */
-  tre_mem_t mem = tre_bt_mem_new();
-
-  /* The backtracking stack. */
-  tre_backtrack_t stack;
-
-  tre_tnfa_transition_t *trans_i;
-  regmatch_t *pmatch = NULL;
-
-  /*
-   * TRE internals tend to use int instead of size_t for positions or
-   * lengths and don't check for overflow.  This will take time to fix
-   * properly.  In the meantime, simply limit the input to what we can
-   * handle.
-   */
-  if (len > TRE_MAX_STRING)
-    len = TRE_MAX_STRING;
-
-#ifdef TRE_MBSTATE
-  memset(&mbstate, '\0', sizeof(mbstate));
-#endif /* TRE_MBSTATE */
-
-  if (!mem)
-    return REG_ESPACE;
-  stack = tre_bt_mem_alloc(mem, sizeof(*stack));
-  if (!stack)
-    {
-      ret = REG_ESPACE;
-      goto error_exit;
-    }
-  stack->prev = NULL;
-  stack->next = NULL;
-
-  DPRINT(("tnfa_execute_backtrack, input type %d\n", type));
-  DPRINT(("len = %zd\n", len));
-
-#ifdef TRE_USE_ALLOCA
-  tags = alloca(sizeof(*tags) * tnfa->num_tags);
-  pmatch = alloca(sizeof(*pmatch) * tnfa->num_submatches);
-  states_seen = alloca(sizeof(*states_seen) * tnfa->num_states);
-#else /* !TRE_USE_ALLOCA */
-  if (tnfa->num_tags)
-    {
-      tags = xmalloc(sizeof(*tags) * tnfa->num_tags);
-      if (!tags)
-	{
-	  ret = REG_ESPACE;
-	  goto error_exit;
-	}
-    }
-  if (tnfa->num_submatches)
-    {
-      pmatch = xmalloc(sizeof(*pmatch) * tnfa->num_submatches);
-      if (!pmatch)
-	{
-	  ret = REG_ESPACE;
-	  goto error_exit;
-	}
-    }
-  if (tnfa->num_states)
-    {
-      states_seen = xmalloc(sizeof(*states_seen) * tnfa->num_states);
-      if (!states_seen)
-	{
-	  ret = REG_ESPACE;
-	  goto error_exit;
-	}
-    }
-#endif /* !TRE_USE_ALLOCA */
-
- retry:
-  {
-    int i;
-    for (i = 0; i < tnfa->num_tags; i++)
-      {
-	tags[i] = -1;
-	if (match_tags)
-	  match_tags[i] = -1;
-      }
-    for (i = 0; i < tnfa->num_states; i++)
-      states_seen[i] = 0;
-  }
-
-  state = NULL;
-  pos = pos_start;
-  if (type == STR_USER)
-    str_source->rewind(pos + pos_add_next, str_source->context);
-  GET_NEXT_WCHAR();
-  pos_start = pos;
-  next_c_start = next_c;
-  str_byte_start = str_byte;
-#ifdef TRE_WCHAR
-  str_wide_start = str_wide;
-#endif /* TRE_WCHAR */
-#ifdef TRE_MBSTATE
-  mbstate_start = mbstate;
-#endif /* TRE_MBSTATE */
-
-  /* Handle initial states. */
-  next_tags = NULL;
-  for (trans_i = tnfa->initial; trans_i->state; trans_i++)
-    {
-      DPRINT(("> init %p, prev_c %lc\n", trans_i->state, (tre_cint_t)prev_c));
-      if (trans_i->assertions && CHECK_ASSERTIONS(trans_i->assertions))
-	{
-	  DPRINT(("assert failed\n"));
-	  continue;
-	}
-      if (state == NULL)
-	{
-	  /* Start from this state. */
-	  state = trans_i->state;
-	  next_tags = trans_i->tags;
-	}
-      else
-	{
-	  /* Backtrack to this state. */
-	  DPRINT(("saving state %d for backtracking\n", trans_i->state_id));
-	  BT_STACK_PUSH(pos, str_byte, str_wide, trans_i->state,
-			trans_i->state_id, next_c, tags, mbstate);
-	  {
-	    int *tmp = trans_i->tags;
-	    if (tmp)
-	      while (*tmp >= 0)
-		stack->item.tags[*tmp++] = pos;
-	  }
-	}
-    }
-
-  if (next_tags)
-    for (; *next_tags >= 0; next_tags++)
-      tags[*next_tags] = pos;
-
-
-  DPRINT(("entering match loop, pos %zd, str_byte %p\n", pos, str_byte));
-  DPRINT(("pos:chr/code | state and tags\n"));
-  DPRINT(("-------------+------------------------------------------------\n"));
-
-  if (state == NULL)
-    goto backtrack;
-
-  while (/*CONSTCOND*/(void)1,1)
-    {
-      tre_tnfa_transition_t *next_state;
-      int empty_br_match;
-
-      DPRINT(("start loop\n"));
-      if (state == tnfa->final)
-	{
-	  DPRINT(("  match found, %d %zd\n", match_eo, pos));
-	  if (match_eo < pos
-	      || (match_eo == pos
-		  && match_tags
-		  && tre_tag_order(tnfa->num_tags, tnfa->tag_directions,
-				   tags, match_tags)))
-	    {
-	      int i;
-	      /* This match wins the previous match. */
-	      DPRINT(("	 win previous\n"));
-	      match_eo = pos;
-	      if (match_tags)
-		for (i = 0; i < tnfa->num_tags; i++)
-		  match_tags[i] = tags[i];
-	    }
-	  /* Our TNFAs never have transitions leaving from the final state,
-	     so we jump right to backtracking. */
-	  goto backtrack;
-	}
-
-#ifdef TRE_DEBUG
-      DPRINT(("%3zd:%2lc/%05d | %p ", pos, (tre_cint_t)next_c, (int)next_c,
-	      state));
-      {
-	int i;
-	for (i = 0; i < tnfa->num_tags; i++)
-	  DPRINT(("%d%s", tags[i], i < tnfa->num_tags - 1 ? ", " : ""));
-	DPRINT(("\n"));
-      }
-#endif /* TRE_DEBUG */
-
-      /* Go to the next character in the input string. */
-      empty_br_match = 0;
-      trans_i = state;
-      if (trans_i->state && trans_i->assertions & ASSERT_BACKREF)
-	{
-	  /* This is a back reference state.  All transitions leaving from
-	     this state have the same back reference "assertion".  Instead
-	     of reading the next character, we match the back reference. */
-	  int so, eo, bt = trans_i->u.backref;
-	  int bt_len;
-	  int result;
-
-	  DPRINT(("  should match back reference %d\n", bt));
-	  /* Get the substring we need to match against.  Remember to
-	     turn off REG_NOSUB temporarily. */
-	  tre_fill_pmatch(bt + 1, pmatch, tnfa->cflags & ~REG_NOSUB,
-			  tnfa, tags, pos);
-	  so = pmatch[bt].rm_so;
-	  eo = pmatch[bt].rm_eo;
-	  bt_len = eo - so;
-
-#ifdef TRE_DEBUG
-	  {
-	    int slen;
-	    if (len < 0)
-	      slen = bt_len;
-	    else
-	      slen = MIN(bt_len, len - pos);
-
-	    if (type == STR_BYTE)
-	      {
-		DPRINT(("  substring (len %d) is [%d, %d[: '%.*s'\n",
-			bt_len, so, eo, bt_len, (char*)string + so));
-		DPRINT(("  current string is '%.*s'\n", slen, str_byte - 1));
-	      }
-#ifdef TRE_WCHAR
-	    else if (type == STR_WIDE)
-	      {
-		DPRINT(("  substring (len %d) is [%d, %d[: '%.*" STRF "'\n",
-			bt_len, so, eo, bt_len, (wchar_t*)string + so));
-		DPRINT(("  current string is '%.*" STRF "'\n",
-			slen, str_wide - 1));
-	      }
-#endif /* TRE_WCHAR */
-	  }
-#endif
-
-	  if (len < 0)
-	    {
-	      if (type == STR_USER)
-		result = str_source->compare((unsigned)so, (unsigned)pos,
-					     (unsigned)bt_len,
-					     str_source->context);
-#ifdef TRE_WCHAR
-	      else if (type == STR_WIDE)
-		result = wcsncmp((const wchar_t*)string + so, str_wide - 1,
-				 (size_t)bt_len);
-#endif /* TRE_WCHAR */
-	      else
-		result = strncmp((const char*)string + so, str_byte - 1,
-				 (size_t)bt_len);
-	    }
-	  else if (len - pos < bt_len)
-	    result = 1;
-#ifdef TRE_WCHAR
-	  else if (type == STR_WIDE)
-	    result = wmemcmp((const wchar_t*)string + so, str_wide - 1,
-			     (size_t)bt_len);
-#endif /* TRE_WCHAR */
-	  else
-	    result = memcmp((const char*)string + so, str_byte - 1,
-			    (size_t)bt_len);
-
-	  if (result == 0)
-	    {
-	      /* Back reference matched.  Check for infinite loop. */
-	      if (bt_len == 0)
-		empty_br_match = 1;
-	      if (empty_br_match && states_seen[trans_i->state_id])
-		{
-		  DPRINT(("  avoid loop\n"));
-		  goto backtrack;
-		}
-
-	      states_seen[trans_i->state_id] = empty_br_match;
-
-	      /* Advance in input string and resync `prev_c', `next_c'
-		 and pos. */
-	      DPRINT(("	 back reference matched\n"));
-	      str_byte += bt_len - 1;
-#ifdef TRE_WCHAR
-	      str_wide += bt_len - 1;
-#endif /* TRE_WCHAR */
-	      pos += bt_len - 1;
-	      GET_NEXT_WCHAR();
-	      DPRINT(("	 pos now %zd\n", pos));
-	    }
-	  else
-	    {
-	      DPRINT(("	 back reference did not match\n"));
-	      goto backtrack;
-	    }
-	}
-      else
-	{
-	  /* Check for end of string. */
-	  if (len < 0)
-	    {
-	      if (type == STR_USER)
-		{
-		  if (str_user_end)
-		    goto backtrack;
-		}
-	      else if (next_c == L'\0' || pos >= TRE_MAX_STRING)
-		goto backtrack;
-	    }
-	  else
-	    {
-	      if (pos >= len)
-		goto backtrack;
-	    }
-
-	  /* Read the next character. */
-	  GET_NEXT_WCHAR();
-	}
-
-      next_state = NULL;
-      for (trans_i = state; trans_i->state; trans_i++)
-	{
-	  DPRINT(("  transition %d-%d (%c-%c) %d to %d\n",
-		  trans_i->code_min, trans_i->code_max,
-		  trans_i->code_min, trans_i->code_max,
-		  trans_i->assertions, trans_i->state_id));
-	  if (trans_i->code_min <= (tre_cint_t)prev_c
-	      && trans_i->code_max >= (tre_cint_t)prev_c)
-	    {
-	      if (trans_i->assertions
-		  && (CHECK_ASSERTIONS(trans_i->assertions)
-		      || CHECK_CHAR_CLASSES(trans_i, tnfa, eflags)))
-		{
-		  DPRINT(("  assertion failed\n"));
-		  continue;
-		}
-
-	      if (next_state == NULL)
-		{
-		  /* First matching transition. */
-		  DPRINT(("  Next state is %d\n", trans_i->state_id));
-		  next_state = trans_i->state;
-		  next_tags = trans_i->tags;
-		}
-	      else
-		{
-		  /* Second matching transition.  We may need to backtrack here
-		     to take this transition instead of the first one, so we
-		     push this transition in the backtracking stack so we can
-		     jump back here if needed. */
-		  DPRINT(("  saving state %d for backtracking\n",
-			  trans_i->state_id));
-		  BT_STACK_PUSH(pos, str_byte, str_wide, trans_i->state,
-				trans_i->state_id, next_c, tags, mbstate);
-		  {
-		    int *tmp;
-		    for (tmp = trans_i->tags; tmp && *tmp >= 0; tmp++)
-		      stack->item.tags[*tmp] = pos;
-		  }
-#if 0 /* XXX - it's important not to look at all transitions here to keep
-	 the stack small! */
-		  break;
-#endif
-		}
-	    }
-	}
-
-      if (next_state != NULL)
-	{
-	  /* Matching transitions were found.  Take the first one. */
-	  state = next_state;
-
-	  /* Update the tag values. */
-	  if (next_tags)
-	    while (*next_tags >= 0)
-	      tags[*next_tags++] = pos;
-	}
-      else
-	{
-	backtrack:
-	  /* A matching transition was not found.  Try to backtrack. */
-	  if (stack->prev)
-	    {
-	      DPRINT(("	 backtracking\n"));
-	      if (stack->item.state->assertions & ASSERT_BACKREF)
-		{
-		  DPRINT(("  states_seen[%d] = 0\n",
-			  stack->item.state_id));
-		  states_seen[stack->item.state_id] = 0;
-		}
-
-	      BT_STACK_POP();
-	    }
-	  else if (match_eo < 0)
-	    {
-	      /* Try starting from a later position in the input string. */
-	      /* Check for end of string. */
-	      if (len < 0)
-		{
-		  if (next_c_start == L'\0' || pos_start >= TRE_MAX_STRING)
-		    {
-		      DPRINT(("end of string.\n"));
-		      break;
-		    }
-		}
-	      else
-		{
-		  if (pos_start >= len)
-		    {
-		      DPRINT(("end of string.\n"));
-		      break;
-		    }
-		}
-	      DPRINT(("restarting from next start position\n"));
-	      next_c = (tre_char_t) next_c_start;
-#ifdef TRE_MBSTATE
-	      mbstate = mbstate_start;
-#endif /* TRE_MBSTATE */
-	      str_byte = str_byte_start;
-#ifdef TRE_WCHAR
-	      str_wide = str_wide_start;
-#endif /* TRE_WCHAR */
-	      goto retry;
-	    }
-	  else
-	    {
-	      DPRINT(("finished\n"));
-	      break;
-	    }
-	}
-    }
-
-  ret = match_eo >= 0 ? REG_OK : REG_NOMATCH;
-  *match_end_ofs = match_eo;
-
- error_exit:
-  tre_bt_mem_destroy(mem);
-#ifndef TRE_USE_ALLOCA
-  if (tags)
-    xafree(tags);
-  if (pmatch)
-    xafree(pmatch);
-  if (states_seen)
-    xafree(states_seen);
-#endif /* !TRE_USE_ALLOCA */
-
-  return ret;
-}

deps/tre/lib/tre-match-parallel.c

@@ -1,538 +0,0 @@
-/*
-  tre-match-parallel.c - TRE parallel regex matching engine
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-/*
-  This algorithm searches for matches basically by reading characters
-  in the searched string one by one, starting at the beginning.	 All
-  matching paths in the TNFA are traversed in parallel.	 When two or
-  more paths reach the same state, exactly one is chosen according to
-  tag ordering rules; if returning submatches is not required it does
-  not matter which path is chosen.
-
-  The worst case time required for finding the leftmost and longest
-  match, or determining that there is no match, is always linearly
-  dependent on the length of the text being searched.
-
-  This algorithm cannot handle TNFAs with back referencing nodes.
-  See `tre-match-backtrack.c'.
-*/
-
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#ifdef TRE_USE_ALLOCA
-/* AIX requires this to be the first thing in the file.	 */
-#ifndef __GNUC__
-# if HAVE_ALLOCA_H
-#  include <alloca.h>
-# else
-#  ifdef _AIX
- #pragma alloca
-#  else
-#   ifndef alloca /* predefined by HP cc +Olibcalls */
-char *alloca ();
-#   endif
-#  endif
-# endif
-#endif
-#endif /* TRE_USE_ALLOCA */
-
-#include <assert.h>
-#include <stdint.h>
-#include <stdlib.h>
-#include <string.h>
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-#ifdef HAVE_WCTYPE_H
-#include <wctype.h>
-#endif /* HAVE_WCTYPE_H */
-#ifndef TRE_WCHAR
-#include <ctype.h>
-#endif /* !TRE_WCHAR */
-#ifdef HAVE_MALLOC_H
-#include <malloc.h>
-#endif /* HAVE_MALLOC_H */
-
-#include "tre-internal.h"
-#include "tre-match-utils.h"
-#include "xmalloc.h"
-
-
-
-typedef struct {
-  tre_tnfa_transition_t *state;
-  int *tags;
-} tre_tnfa_reach_t;
-
-typedef struct {
-  int pos;
-  int **tags;
-} tre_reach_pos_t;
-
-
-#ifdef TRE_DEBUG
-static void
-tre_print_reach(const tre_tnfa_reach_t *reach, int num_tags)
-{
-  int i;
-
-  while (reach->state != NULL)
-    {
-      DPRINT((" %p", (void *)reach->state));
-      if (num_tags > 0)
-	{
-	  DPRINT(("/"));
-	  for (i = 0; i < num_tags; i++)
-	    {
-	      DPRINT(("%d:%d", i, reach->tags[i]));
-	      if (i < (num_tags-1))
-		DPRINT((","));
-	    }
-	}
-      reach++;
-    }
-  DPRINT(("\n"));
-
-}
-#endif /* TRE_DEBUG */
-
-reg_errcode_t
-tre_tnfa_run_parallel(const tre_tnfa_t *tnfa, const void *string, ssize_t len,
-		      tre_str_type_t type, int *match_tags, int eflags,
-		      int *match_end_ofs)
-{
-  /* State variables required by GET_NEXT_WCHAR. */
-  tre_char_t prev_c = 0, next_c = 0;
-  const char *str_byte = string;
-  ssize_t pos = -1;
-  unsigned int pos_add_next = 1;
-#ifdef TRE_WCHAR
-  const wchar_t *str_wide = string;
-#ifdef TRE_MBSTATE
-  mbstate_t mbstate;
-#endif /* TRE_MBSTATE */
-#endif /* TRE_WCHAR */
-  reg_errcode_t ret;
-  int reg_notbol = eflags & REG_NOTBOL;
-  int reg_noteol = eflags & REG_NOTEOL;
-  int reg_newline = tnfa->cflags & REG_NEWLINE;
-  int str_user_end = 0;
-
-  char *buf;
-  tre_tnfa_transition_t *trans_i;
-  tre_tnfa_reach_t *reach, *reach_next, *reach_i, *reach_next_i;
-  tre_reach_pos_t *reach_pos;
-  int *tag_i;
-  int num_tags, i;
-
-  int match_eo = -1;	   /* end offset of match (-1 if no match found yet) */
-  int new_match = 0;
-  int *tmp_tags = NULL;
-  int *tmp_iptr;
-
-  /*
-   * TRE internals tend to use int instead of size_t for positions or
-   * lengths and don't check for overflow.  This will take time to fix
-   * properly.  In the meantime, simply limit the input to what we can
-   * handle.
-   */
-  if (len > TRE_MAX_STRING)
-    len = TRE_MAX_STRING;
-
-#ifdef TRE_MBSTATE
-  memset(&mbstate, '\0', sizeof(mbstate));
-#endif /* TRE_MBSTATE */
-
-  DPRINT(("tre_tnfa_run_parallel, input type %d\n", type));
-
-  if (!match_tags)
-    num_tags = 0;
-  else
-    num_tags = tnfa->num_tags;
-
-  /* Allocate memory for temporary data required for matching.	This needs to
-     be done for every matching operation to be thread safe.  This allocates
-     everything in a single large block from the stack frame using alloca()
-     or with malloc() if alloca is unavailable. */
-  {
-    size_t tbytes, rbytes, pbytes, xbytes, total_bytes;
-    size_t num_states = (size_t)tnfa->num_states;
-    size_t state_tag_bytes, reach_bytes;
-    size_t padding = (sizeof(long) - 1) * 4;
-    char *tmp_buf;
-
-    if (num_states > SIZE_MAX / sizeof(*reach_pos))
-      return REG_ESPACE;
-    pbytes = sizeof(*reach_pos) * num_states;
-
-    if (num_states + 1 > SIZE_MAX / sizeof(*reach_next))
-      return REG_ESPACE;
-    rbytes = sizeof(*reach_next) * (num_states + 1);
-
-    if ((size_t)num_tags > SIZE_MAX / sizeof(*tmp_tags))
-      return REG_ESPACE;
-    tbytes = sizeof(*tmp_tags) * (size_t)num_tags;
-
-    if ((size_t)num_tags > SIZE_MAX / sizeof(int))
-      return REG_ESPACE;
-    xbytes = sizeof(int) * (size_t)num_tags;
-
-    if (num_states > 0 && xbytes > SIZE_MAX / num_states)
-      return REG_ESPACE;
-    state_tag_bytes = xbytes * num_states;
-
-    if (rbytes > SIZE_MAX - state_tag_bytes)
-      return REG_ESPACE;
-    reach_bytes = rbytes + state_tag_bytes;
-
-    if (reach_bytes > (SIZE_MAX - padding - tbytes - pbytes) / 2)
-      return REG_ESPACE;
-
-    /* Compute the length of the block we need. */
-    total_bytes =
-      padding + reach_bytes * 2 + tbytes + pbytes;
-
-    /* Allocate the memory. */
-#ifdef TRE_USE_ALLOCA
-    buf = alloca(total_bytes);
-#else /* !TRE_USE_ALLOCA */
-    buf = xmalloc(total_bytes);
-#endif /* !TRE_USE_ALLOCA */
-    if (buf == NULL)
-      return REG_ESPACE;
-    memset(buf, 0, total_bytes);
-
-    /* Get the various pointers within tmp_buf (properly aligned). */
-    tmp_tags = (void *)buf;
-    tmp_buf = buf + tbytes;
-    tmp_buf += ALIGN(tmp_buf, long);
-    reach_next = (void *)tmp_buf;
-    tmp_buf += rbytes;
-    tmp_buf += ALIGN(tmp_buf, long);
-    reach = (void *)tmp_buf;
-    tmp_buf += rbytes;
-    tmp_buf += ALIGN(tmp_buf, long);
-    reach_pos = (void *)tmp_buf;
-    tmp_buf += pbytes;
-    tmp_buf += ALIGN(tmp_buf, long);
-    for (i = 0; i < tnfa->num_states; i++)
-      {
-	reach[i].tags = (void *)tmp_buf;
-	tmp_buf += xbytes;
-	reach_next[i].tags = (void *)tmp_buf;
-	tmp_buf += xbytes;
-      }
-  }
-
-  for (i = 0; i < tnfa->num_states; i++)
-    reach_pos[i].pos = -1;
-
-  /* If only one character can start a match, find it first. */
-  if (tnfa->first_char >= 0 && type == STR_BYTE && str_byte)
-    {
-      const char *orig_str = str_byte;
-      int first = tnfa->first_char;
-
-      if (len >= 0)
-	str_byte = memchr(orig_str, first, (size_t)len);
-      else
-	str_byte = strchr(orig_str, first);
-      if (str_byte == NULL)
-	{
-#ifndef TRE_USE_ALLOCA
-	  if (buf)
-	    xfree(buf);
-#endif /* !TRE_USE_ALLOCA */
-	  return REG_NOMATCH;
-	}
-      DPRINT(("skipped %lu chars\n", (unsigned long)(str_byte - orig_str)));
-      if (str_byte >= orig_str + 1)
-	prev_c = (unsigned char)*(str_byte - 1);
-      next_c = (unsigned char)*str_byte;
-      pos = str_byte - orig_str;
-      if (len < 0 || pos < len)
-	str_byte++;
-    }
-  else
-    {
-      GET_NEXT_WCHAR();
-      pos = 0;
-    }
-
-#if 0
-  /* Skip over characters that cannot possibly be the first character
-     of a match. */
-  if (tnfa->firstpos_chars != NULL)
-    {
-      char *chars = tnfa->firstpos_chars;
-
-      if (len < 0)
-	{
-	  const char *orig_str = str_byte;
-	  /* XXX - use strpbrk() and wcspbrk() because they might be
-	     optimized for the target architecture.  Try also strcspn()
-	     and wcscspn() and compare the speeds. */
-	  while (next_c != L'\0' && !chars[next_c])
-	    {
-	      next_c = *str_byte++;
-	    }
-	  prev_c = *(str_byte - 2);
-	  pos += str_byte - orig_str;
-	  DPRINT(("skipped %d chars\n", str_byte - orig_str));
-	}
-      else
-	{
-	  while (pos <= len && !chars[next_c])
-	    {
-	      prev_c = next_c;
-	      next_c = (unsigned char)(*str_byte++);
-	      pos++;
-	    }
-	}
-    }
-#endif
-
-  DPRINT(("length: %zd\n", len));
-  DPRINT(("pos:chr/code | states and tags\n"));
-  DPRINT(("-------------+------------------------------------------------\n"));
-
-  reach_next_i = reach_next;
-  while (/*CONSTCOND*/(void)1,1)
-    {
-      /* If no match found yet, add the initial states to `reach_next'. */
-      if (match_eo < 0)
-	{
-	  DPRINT((" init >"));
-	  trans_i = tnfa->initial;
-	  while (trans_i->state != NULL)
-	    {
-	      if (reach_pos[trans_i->state_id].pos < pos)
-		{
-		  if (trans_i->assertions
-		      && CHECK_ASSERTIONS(trans_i->assertions))
-		    {
-		      DPRINT(("assertion failed\n"));
-		      trans_i++;
-		      continue;
-		    }
-
-		  DPRINT((" %p", (void *)trans_i->state));
-		  reach_next_i->state = trans_i->state;
-		  for (i = 0; i < num_tags; i++)
-		    reach_next_i->tags[i] = -1;
-		  tag_i = trans_i->tags;
-		  if (tag_i)
-		    while (*tag_i >= 0)
-		      {
-			if (*tag_i < num_tags)
-			  reach_next_i->tags[*tag_i] = pos;
-			tag_i++;
-		      }
-		  if (reach_next_i->state == tnfa->final)
-		    {
-		      DPRINT(("	 found empty match\n"));
-		      match_eo = pos;
-		      new_match = 1;
-		      for (i = 0; i < num_tags; i++)
-			match_tags[i] = reach_next_i->tags[i];
-		    }
-		  reach_pos[trans_i->state_id].pos = pos;
-		  reach_pos[trans_i->state_id].tags = &reach_next_i->tags;
-		  reach_next_i++;
-		}
-	      trans_i++;
-	    }
-	  DPRINT(("\n"));
-	  reach_next_i->state = NULL;
-	}
-      else
-	{
-	  if (num_tags == 0 || reach_next_i == reach_next)
-	    /* We have found a match. */
-	    break;
-	}
-
-      /* Check for end of string. */
-      if (len < 0)
-	{
-	  if (type == STR_USER)
-	    {
-	      if (str_user_end)
-		break;
-	    }
-	  else if (next_c == L'\0' || pos >= TRE_MAX_STRING)
-	    break;
-	}
-      else
-	{
-	  if (pos >= len)
-	    break;
-	}
-
-      GET_NEXT_WCHAR();
-
-#ifdef TRE_DEBUG
-      DPRINT(("%3zd:%2lc/%05d |", pos - 1, (tre_cint_t)prev_c, (int)prev_c));
-      tre_print_reach(reach_next, num_tags);
-      DPRINT(("%3zd:%2lc/%05d |", pos, (tre_cint_t)next_c, (int)next_c));
-      tre_print_reach(reach_next, num_tags);
-#endif /* TRE_DEBUG */
-
-      /* Swap `reach' and `reach_next'. */
-      reach_i = reach;
-      reach = reach_next;
-      reach_next = reach_i;
-
-      /* For each state in `reach', weed out states that don't fulfill the
-	 minimal matching conditions. */
-      if (tnfa->num_minimals && new_match)
-	{
-	  new_match = 0;
-	  reach_next_i = reach_next;
-	  for (reach_i = reach; reach_i->state; reach_i++)
-	    {
-	      int skip = 0;
-	      for (i = 0; tnfa->minimal_tags[i] >= 0; i += 2)
-		{
-		  int end = tnfa->minimal_tags[i];
-		  int start = tnfa->minimal_tags[i + 1];
-		  DPRINT(("  Minimal start %d, end %d\n", start, end));
-		  if (end >= num_tags)
-		    {
-		      DPRINT(("	 Throwing %p out.\n", reach_i->state));
-		      skip = 1;
-		      break;
-		    }
-		  else if (reach_i->tags[start] == match_tags[start]
-			   && reach_i->tags[end] < match_tags[end])
-		    {
-		      DPRINT(("	 Throwing %p out because t%d < %d\n",
-			      reach_i->state, end, match_tags[end]));
-		      skip = 1;
-		      break;
-		    }
-		}
-	      if (!skip)
-		{
-		  reach_next_i->state = reach_i->state;
-		  tmp_iptr = reach_next_i->tags;
-		  reach_next_i->tags = reach_i->tags;
-		  reach_i->tags = tmp_iptr;
-		  reach_next_i++;
-		}
-	    }
-	  reach_next_i->state = NULL;
-
-	  /* Swap `reach' and `reach_next'. */
-	  reach_i = reach;
-	  reach = reach_next;
-	  reach_next = reach_i;
-	}
-
-      /* For each state in `reach' see if there is a transition leaving with
-	 the current input symbol to a state not yet in `reach_next', and
-	 add the destination states to `reach_next'. */
-      reach_next_i = reach_next;
-      for (reach_i = reach; reach_i->state; reach_i++)
-	{
-	  for (trans_i = reach_i->state; trans_i->state; trans_i++)
-	    {
-	      /* Does this transition match the input symbol? */
-	      if (trans_i->code_min <= (tre_cint_t)prev_c &&
-		  trans_i->code_max >= (tre_cint_t)prev_c)
-		{
-		  if (trans_i->assertions
-		      && (CHECK_ASSERTIONS(trans_i->assertions)
-			  || CHECK_CHAR_CLASSES(trans_i, tnfa, eflags)))
-		    {
-		      DPRINT(("assertion failed\n"));
-		      continue;
-		    }
-
-		  /* Compute the tags after this transition. */
-		  for (i = 0; i < num_tags; i++)
-		    tmp_tags[i] = reach_i->tags[i];
-		  tag_i = trans_i->tags;
-		  if (tag_i != NULL)
-		    while (*tag_i >= 0)
-		      {
-			if (*tag_i < num_tags)
-			  tmp_tags[*tag_i] = pos;
-			tag_i++;
-		      }
-
-		  if (reach_pos[trans_i->state_id].pos < pos)
-		    {
-		      /* Found an unvisited node. */
-		      reach_next_i->state = trans_i->state;
-		      tmp_iptr = reach_next_i->tags;
-		      reach_next_i->tags = tmp_tags;
-		      tmp_tags = tmp_iptr;
-		      reach_pos[trans_i->state_id].pos = pos;
-		      reach_pos[trans_i->state_id].tags = &reach_next_i->tags;
-
-		      if (reach_next_i->state == tnfa->final
-			  && (match_eo == -1
-			      || (num_tags > 0
-				  && reach_next_i->tags[0] <= match_tags[0])))
-			{
-			  DPRINT(("  found match %p\n", trans_i->state));
-			  match_eo = pos;
-			  new_match = 1;
-			  for (i = 0; i < num_tags; i++)
-			    match_tags[i] = reach_next_i->tags[i];
-			}
-		      reach_next_i++;
-
-		    }
-		  else
-		    {
-		      assert(reach_pos[trans_i->state_id].pos == pos);
-		      /* Another path has also reached this state.  We choose
-			 the winner by examining the tag values for both
-			 paths. */
-		      if (tre_tag_order(num_tags, tnfa->tag_directions,
-					tmp_tags,
-					*reach_pos[trans_i->state_id].tags))
-			{
-			  /* The new path wins. */
-			  tmp_iptr = *reach_pos[trans_i->state_id].tags;
-			  *reach_pos[trans_i->state_id].tags = tmp_tags;
-			  if (trans_i->state == tnfa->final)
-			    {
-			      DPRINT(("	 found better match\n"));
-			      match_eo = pos;
-			      new_match = 1;
-			      for (i = 0; i < num_tags; i++)
-				match_tags[i] = tmp_tags[i];
-			    }
-			  tmp_tags = tmp_iptr;
-			}
-		    }
-		}
-	    }
-	}
-      reach_next_i->state = NULL;
-    }
-
-  DPRINT(("match end offset = %d\n", match_eo));
-
-  *match_end_ofs = match_eo;
-  ret = match_eo >= 0 ? REG_OK : REG_NOMATCH;
-
-#ifndef TRE_USE_ALLOCA
-  if (buf)
-    xfree(buf);
-#endif /* !TRE_USE_ALLOCA */
-  return ret;
-}
-
-/* EOF */

deps/tre/lib/tre-match-utils.h

@@ -1,215 +0,0 @@
-/*
-  tre-match-utils.h - TRE matcher helper definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#define str_source ((const tre_str_source*)string)
-
-#ifdef TRE_WCHAR
-
-#ifdef TRE_MULTIBYTE
-
-/* Wide character and multibyte support. */
-
-#define GET_NEXT_WCHAR()						      \
-  do {									      \
-    prev_c = next_c;							      \
-    if (type == STR_BYTE)						      \
-      {									      \
-	pos++;								      \
-	if (len >= 0 && pos >= len)					      \
-	  next_c = '\0';						      \
-	else								      \
-	  next_c = (unsigned char)(*str_byte++);			      \
-      }									      \
-    else if (type == STR_WIDE)						      \
-      {									      \
-	pos++;								      \
-	if (len >= 0 && pos >= len)					      \
-	  next_c = L'\0';						      \
-	else								      \
-	  next_c = *str_wide++;						      \
-      }									      \
-    else if (type == STR_MBS)						      \
-      {									      \
-        pos += pos_add_next;					      	      \
-	if (str_byte == NULL)						      \
-	  next_c = L'\0';						      \
-	else								      \
-	  {								      \
-	    size_t w;							      \
-	    size_t max;							      \
-	    if (len >= 0)						      \
-	      max = len - pos;						      \
-	    else							      \
-	      max = 32;							      \
-	    if (max <= 0)						      \
-	      {								      \
-		next_c = L'\0';						      \
-		pos_add_next = 1;					      \
-	      }								      \
-	    else							      \
-	      {								      \
-		w = tre_mbrtowc(&next_c, str_byte, (size_t)max, &mbstate);    \
-		if (w == (size_t)-1 || w == (size_t)-2)			      \
-		  return REG_NOMATCH;					      \
-		if (w == 0 && len >= 0)					      \
-		  {							      \
-		    pos_add_next = 1;					      \
-		    next_c = 0;						      \
-		    str_byte++;						      \
-		  }							      \
-		else							      \
-		  {							      \
-		    pos_add_next = w;					      \
-		    str_byte += w;					      \
-		  }							      \
-	      }								      \
-	  }								      \
-      }									      \
-    else if (type == STR_USER)						      \
-      {									      \
-        pos += pos_add_next;					      	      \
-	str_user_end = str_source->get_next_char(&next_c, &pos_add_next,      \
-                                                 str_source->context);	      \
-      }									      \
-  } while(/*CONSTCOND*/(void)0,0)
-
-#else /* !TRE_MULTIBYTE */
-
-/* Wide character support, no multibyte support. */
-
-#define GET_NEXT_WCHAR()						      \
-  do {									      \
-    prev_c = next_c;							      \
-    if (type == STR_BYTE)						      \
-      {									      \
-	pos++;								      \
-	if (len >= 0 && pos >= len)					      \
-	  next_c = '\0';						      \
-	else								      \
-	  next_c = (unsigned char)(*str_byte++);			      \
-      }									      \
-    else if (type == STR_WIDE)						      \
-      {									      \
-	pos++;								      \
-	if (len >= 0 && pos >= len)					      \
-	  next_c = L'\0';						      \
-	else								      \
-	  next_c = *str_wide++;						      \
-      }									      \
-    else if (type == STR_USER)						      \
-      {									      \
-        pos += pos_add_next;					      	      \
-	str_user_end = str_source->get_next_char(&next_c, &pos_add_next,      \
-                                                 str_source->context);	      \
-      }									      \
-  } while(/*CONSTCOND*/(void)0,0)
-
-#endif /* !TRE_MULTIBYTE */
-
-#else /* !TRE_WCHAR */
-
-/* No wide character or multibyte support. */
-
-#define GET_NEXT_WCHAR()						      \
-  do {									      \
-    prev_c = next_c;							      \
-    if (type == STR_BYTE)						      \
-      {									      \
-	pos++;								      \
-	if (len >= 0 && pos >= len)					      \
-	  next_c = '\0';						      \
-	else								      \
-	  next_c = (unsigned char)(*str_byte++);			      \
-      }									      \
-    else if (type == STR_USER)						      \
-      {									      \
-	pos += pos_add_next;						      \
-	str_user_end = str_source->get_next_char(&next_c, &pos_add_next,      \
-						 str_source->context);	      \
-      }									      \
-  } while(/*CONSTCOND*/(void)0,0)
-
-#endif /* !TRE_WCHAR */
-
-
-
-#define IS_WORD_CHAR(c)	 ((c) == L'_' || tre_isalnum(c))
-
-#define CHECK_ASSERTIONS(assertions)					      \
-  (((assertions & ASSERT_AT_BOL)					      \
-    && (pos > 0 || reg_notbol)						      \
-    && (prev_c != L'\n' || !reg_newline))				      \
-   || ((assertions & ASSERT_AT_EOL)					      \
-       && (next_c != L'\0' || reg_noteol)				      \
-       && (next_c != L'\n' || !reg_newline))				      \
-   || ((assertions & ASSERT_AT_BOW)					      \
-       && (IS_WORD_CHAR(prev_c) || !IS_WORD_CHAR(next_c)))	              \
-   || ((assertions & ASSERT_AT_EOW)					      \
-       && (!IS_WORD_CHAR(prev_c) || IS_WORD_CHAR(next_c)))		      \
-   || ((assertions & ASSERT_AT_WB)					      \
-       && (pos != 0 && next_c != L'\0'					      \
-	   && IS_WORD_CHAR(prev_c) == IS_WORD_CHAR(next_c)))		      \
-   || ((assertions & ASSERT_AT_WB_NEG)					      \
-       && (pos == 0 || next_c == L'\0'					      \
-	   || IS_WORD_CHAR(prev_c) != IS_WORD_CHAR(next_c))))
-
-#define CHECK_CHAR_CLASSES(trans_i, tnfa, eflags)                             \
-  (((trans_i->assertions & ASSERT_CHAR_CLASS)                                 \
-       && !(tnfa->cflags & REG_ICASE)                                         \
-       && !tre_isctype((tre_cint_t)prev_c, trans_i->u.class))                 \
-    || ((trans_i->assertions & ASSERT_CHAR_CLASS)                             \
-        && (tnfa->cflags & REG_ICASE)                                         \
-        && !tre_isctype(tre_tolower((tre_cint_t)prev_c),trans_i->u.class)     \
-	&& !tre_isctype(tre_toupper((tre_cint_t)prev_c),trans_i->u.class))    \
-    || ((trans_i->assertions & ASSERT_CHAR_CLASS_NEG)                         \
-        && tre_neg_char_classes_match(trans_i->neg_classes,(tre_cint_t)prev_c,\
-                                      tnfa->cflags & REG_ICASE)))
-
-
-
-
-/* Returns 1 if `t1' wins `t2', 0 otherwise. */
-inline static int
-tre_tag_order(int num_tags, tre_tag_direction_t *tag_directions,
-	      int *t1, int *t2)
-{
-  int i;
-  for (i = 0; i < num_tags; i++)
-    {
-      if (tag_directions[i] == TRE_TAG_MINIMIZE)
-	{
-	  if (t1[i] < t2[i])
-	    return 1;
-	  if (t1[i] > t2[i])
-	    return 0;
-	}
-      else
-	{
-	  if (t1[i] > t2[i])
-	    return 1;
-	  if (t1[i] < t2[i])
-	    return 0;
-	}
-    }
-  /*  assert(0);*/
-  return 0;
-}
-
-inline static int
-tre_neg_char_classes_match(tre_ctype_t *classes, tre_cint_t wc, int icase)
-{
-  DPRINT(("neg_char_classes_test: %p, %d, %d\n", classes, wc, icase));
-  while (*classes != (tre_ctype_t)0)
-    if ((!icase && tre_isctype(wc, *classes))
-	|| (icase && (tre_isctype(tre_toupper(wc), *classes)
-		      || tre_isctype(tre_tolower(wc), *classes))))
-      return 1; /* Match. */
-    else
-      classes++;
-  return 0; /* No match. */
-}

deps/tre/lib/tre-mem.c

@@ -1,155 +0,0 @@
-/*
-  tre-mem.c - TRE memory allocator
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-/*
-  This memory allocator is for allocating small memory blocks efficiently
-  in terms of memory overhead and execution speed.  The allocated blocks
-  cannot be freed individually, only all at once.  There can be multiple
-  allocators, though.
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-#include <stdlib.h>
-#include <string.h>
-
-#include "tre-internal.h"
-#include "tre-mem.h"
-#include "xmalloc.h"
-
-
-/* Returns a new memory allocator or NULL if out of memory. */
-tre_mem_t
-tre_mem_new_impl(int provided, void *provided_block)
-{
-  tre_mem_t mem;
-  if (provided)
-    {
-      mem = provided_block;
-      memset(mem, 0, sizeof(*mem));
-    }
-  else
-    mem = xcalloc(1, sizeof(*mem));
-  if (mem == NULL)
-    return NULL;
-  return mem;
-}
-
-
-/* Frees the memory allocator and all memory allocated with it. */
-void
-tre_mem_destroy(tre_mem_t mem)
-{
-  tre_list_t *tmp, *l = mem->blocks;
-
-  while (l != NULL)
-    {
-      xfree(l->data);
-      tmp = l->next;
-      xfree(l);
-      l = tmp;
-    }
-  xfree(mem);
-}
-
-
-/* Allocates a block of `size' bytes from `mem'.  Returns a pointer to the
-   allocated block or NULL if an underlying malloc() failed. */
-void *
-tre_mem_alloc_impl(tre_mem_t mem, int provided, void *provided_block,
-		   int zero, size_t size)
-{
-  void *ptr;
-
-  if (mem->failed)
-    {
-      DPRINT(("tre_mem_alloc: oops, called after failure?!\n"));
-      return NULL;
-    }
-
-#ifdef MALLOC_DEBUGGING
-  if (!provided)
-    {
-      ptr = xmalloc(1);
-      if (ptr == NULL)
-	{
-	  DPRINT(("tre_mem_alloc: xmalloc forced failure\n"));
-	  mem->failed = 1;
-	  return NULL;
-	}
-      xfree(ptr);
-    }
-#endif /* MALLOC_DEBUGGING */
-
-  if (mem->n < size)
-    {
-      /* We need more memory than is available in the current block.
-	 Allocate a new block. */
-      tre_list_t *l;
-      if (provided)
-	{
-	  DPRINT(("tre_mem_alloc: using provided block\n"));
-	  if (provided_block == NULL)
-	    {
-	      DPRINT(("tre_mem_alloc: provided block was NULL\n"));
-	      mem->failed = 1;
-	      return NULL;
-	    }
-	  mem->ptr = provided_block;
-	  mem->n = TRE_MEM_BLOCK_SIZE;
-	}
-      else
-	{
-	  size_t block_size;
-	  if (size * 8 > TRE_MEM_BLOCK_SIZE)
-	    block_size = size * 8;
-	  else
-	    block_size = TRE_MEM_BLOCK_SIZE;
-	  DPRINT(("tre_mem_alloc: allocating new %zu byte block\n",
-		  block_size));
-	  l = xmalloc(sizeof(*l));
-	  if (l == NULL)
-	    {
-	      mem->failed = 1;
-	      return NULL;
-	    }
-	  l->data = xmalloc(block_size);
-	  if (l->data == NULL)
-	    {
-	      xfree(l);
-	      mem->failed = 1;
-	      return NULL;
-	    }
-	  l->next = NULL;
-	  if (mem->current != NULL)
-	    mem->current->next = l;
-	  if (mem->blocks == NULL)
-	    mem->blocks = l;
-	  mem->current = l;
-	  mem->ptr = l->data;
-	  mem->n = block_size;
-	}
-    }
-
-  /* Make sure the next pointer will be aligned. */
-  size += ALIGN(mem->ptr + size, long);
-
-  /* Allocate from current block. */
-  ptr = mem->ptr;
-  mem->ptr += size;
-  mem->n -= size;
-
-  /* Set to zero if needed. */
-  if (zero)
-    memset(ptr, 0, size);
-
-  return ptr;
-}
-
-/* EOF */

deps/tre/lib/tre-mem.h

@@ -1,66 +0,0 @@
-/*
-  tre-mem.h - TRE memory allocator interface
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifndef TRE_MEM_H
-#define TRE_MEM_H 1
-
-#include <stdlib.h>
-
-#define TRE_MEM_BLOCK_SIZE 1024
-
-typedef struct tre_list {
-  void *data;
-  struct tre_list *next;
-} tre_list_t;
-
-typedef struct tre_mem_struct {
-  tre_list_t *blocks;
-  tre_list_t *current;
-  char *ptr;
-  size_t n;
-  int failed;
-  void **provided;
-} *tre_mem_t;
-
-
-tre_mem_t tre_mem_new_impl(int provided, void *provided_block);
-void *tre_mem_alloc_impl(tre_mem_t mem, int provided, void *provided_block,
-			 int zero, size_t size);
-
-/* Returns a new memory allocator or NULL if out of memory. */
-#define tre_mem_new()  tre_mem_new_impl(0, NULL)
-
-/* Allocates a block of `size' bytes from `mem'.  Returns a pointer to the
-   allocated block or NULL if an underlying malloc() failed. */
-#define tre_mem_alloc(mem, size) tre_mem_alloc_impl(mem, 0, NULL, 0, size)
-
-/* Allocates a block of `size' bytes from `mem'.  Returns a pointer to the
-   allocated block or NULL if an underlying malloc() failed.  The memory
-   is set to zero. */
-#define tre_mem_calloc(mem, size) tre_mem_alloc_impl(mem, 0, NULL, 1, size)
-
-#ifdef TRE_USE_ALLOCA
-/* alloca() versions.  Like above, but memory is allocated with alloca()
-   instead of malloc(). */
-
-#define tre_mem_newa() \
-  tre_mem_new_impl(1, alloca(sizeof(struct tre_mem_struct)))
-
-#define tre_mem_alloca(mem, size)					      \
-  ((mem)->n >= (size)							      \
-   ? tre_mem_alloc_impl((mem), 1, NULL, 0, (size))			      \
-   : tre_mem_alloc_impl((mem), 1, alloca(TRE_MEM_BLOCK_SIZE), 0, (size)))
-#endif /* TRE_USE_ALLOCA */
-
-
-/* Frees the memory allocator and all memory allocated with it. */
-void tre_mem_destroy(tre_mem_t mem);
-
-#endif /* TRE_MEM_H */
-
-/* EOF */

deps/tre/lib/tre-parse.h

@@ -1,52 +0,0 @@
-/*
-  tre-parse.c - Regexp parser definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifndef TRE_PARSE_H
-#define TRE_PARSE_H 1
-
-/* Parse context. */
-typedef struct {
-  /* Memory allocator.	The AST is allocated using this. */
-  tre_mem_t mem;
-  /* Stack used for keeping track of regexp syntax. */
-  tre_stack_t *stack;
-  /* The parse result. */
-  tre_ast_node_t *result;
-  /* The regexp to parse and its length. */
-  const tre_char_t *re;
-  /* The first character of the entire regexp. */
-  const tre_char_t *re_start;
-  /* The first character after the end of the regexp. */
-  const tre_char_t *re_end;
-  size_t len;
-  /* Current submatch ID. */
-  int submatch_id;
-  /* The highest back reference or -1 if none seen so far. */
-  int max_backref;
-  /* This flag is set if the regexp uses approximate matching. */
-  int have_approx;
-  /* This flag is set if the regexp changes cflags inline using (?...) */
-  int have_inline_cflags;
-  /* Compilation flags. */
-  int cflags;
-  /* If this flag is set the top-level submatch is not captured. */
-  int nofirstsub;
-  /* The currently set approximate matching parameters. */
-  int params[TRE_PARAM_LAST];
-  /* the MB_CUR_MAX in use */
-  int mb_cur_max;
-} tre_parse_ctx_t;
-
-/* Parses a wide character regexp pattern into a syntax tree.  This parser
-   handles both syntaxes (BRE and ERE), including the TRE extensions. */
-reg_errcode_t
-tre_parse(tre_parse_ctx_t *ctx);
-
-#endif /* TRE_PARSE_H */
-
-/* EOF */

deps/tre/lib/tre-stack.c

@@ -1,123 +0,0 @@
-/*
-  tre-stack.c - Simple stack implementation
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-#include <stdlib.h>
-#include <assert.h>
-
-#include "tre-internal.h"
-#include "tre-stack.h"
-#include "xmalloc.h"
-
-union tre_stack_item {
-  void *voidptr_value;
-  int int_value;
-};
-
-struct tre_stack_rec {
-  size_t size;
-  size_t max_size;
-  size_t ptr;
-  union tre_stack_item *stack;
-};
-
-
-tre_stack_t *
-tre_stack_new(size_t size, size_t max_size)
-{
-  tre_stack_t *s;
-
-  s = xmalloc(sizeof(*s));
-  if (s != NULL)
-    {
-      s->stack = xmalloc(sizeof(*s->stack) * size);
-      if (s->stack == NULL)
-	{
-	  xfree(s);
-	  return NULL;
-	}
-      s->size = size;
-      s->max_size = max_size;
-      s->ptr = 0;
-    }
-  return s;
-}
-
-void
-tre_stack_destroy(tre_stack_t *s)
-{
-  xfree(s->stack);
-  xfree(s);
-}
-
-size_t
-tre_stack_num_items(tre_stack_t *s)
-{
-  return s->ptr;
-}
-
-static reg_errcode_t
-tre_stack_push(tre_stack_t *s, union tre_stack_item value)
-{
-  if (s->ptr < s->size)
-    {
-      s->stack[s->ptr] = value;
-      s->ptr++;
-    }
-  else
-    {
-      if (s->size >= s->max_size)
-	{
-	  DPRINT(("tre_stack_push: stack full\n"));
-	  return REG_ESPACE;
-	}
-      else
-	{
-	  union tre_stack_item *new_buffer;
-	  size_t new_size;
-	  DPRINT(("tre_stack_push: trying to realloc more space\n"));
-	  new_size = s->size + s->size;
-	  if (new_size > s->max_size)
-	    new_size = s->max_size;
-	  new_buffer = xrealloc(s->stack, sizeof(*new_buffer) * new_size);
-	  if (new_buffer == NULL)
-	    {
-	      DPRINT(("tre_stack_push: realloc failed.\n"));
-	      return REG_ESPACE;
-	    }
-	  DPRINT(("tre_stack_push: realloc succeeded.\n"));
-	  assert(new_size > s->size);
-	  s->size = new_size;
-	  s->stack = new_buffer;
-	  tre_stack_push(s, value);
-	}
-    }
-  return REG_OK;
-}
-
-#define define_pushf(typetag, type)  \
-  declare_pushf(typetag, type) {     \
-    union tre_stack_item item;	     \
-    item.typetag ## _value = value;  \
-    return tre_stack_push(s, item);  \
-}
-
-define_pushf(int, int)
-define_pushf(voidptr, void *)
-
-#define define_popf(typetag, type)		    \
-  declare_popf(typetag, type) {			    \
-    return s->stack[--s->ptr].typetag ## _value;    \
-  }
-
-define_popf(int, int)
-define_popf(voidptr, void *)
-
-/* EOF */

deps/tre/lib/tre-stack.h

@@ -1,76 +0,0 @@
-/*
-  tre-stack.h: Stack definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-
-#ifndef TRE_STACK_H
-#define TRE_STACK_H 1
-
-#include "../local_includes/tre.h"
-
-typedef struct tre_stack_rec tre_stack_t;
-
-/* Creates a new stack object with initial size `size' and maximum size
-   `max_size'. Pushing an additional item onto a full stack will resize
-   the stack to double its capacity until the maximum is reached. Returns
-   the stack object or NULL if out of memory. */
-tre_stack_t *
-tre_stack_new(size_t size, size_t max_size);
-
-/* Frees the stack object. */
-void
-tre_stack_destroy(tre_stack_t *s);
-
-/* Returns the current number of items on the stack. */
-size_t
-tre_stack_num_items(tre_stack_t *s);
-
-/* Each tre_stack_push_*(tre_stack_t *s, <type> value) function pushes
-   `value' on top of stack `s'.  Returns REG_ESPACE if out of memory.
-   This tries to realloc() more space before failing if maximum size
-   has not yet been reached.  Returns REG_OK if successful. */
-#define declare_pushf(typetag, type)					      \
-  reg_errcode_t tre_stack_push_ ## typetag(tre_stack_t *s, type value)
-
-declare_pushf(voidptr, void *);
-declare_pushf(int, int);
-
-/* Each tre_stack_pop_*(tre_stack_t *s) function pops the topmost
-   element off of stack `s' and returns it.  The stack must not be
-   empty. */
-#define declare_popf(typetag, type)		  \
-  type tre_stack_pop_ ## typetag(tre_stack_t *s)
-
-declare_popf(voidptr, void *);
-declare_popf(int, int);
-
-/* Just to save some typing. */
-#define STACK_PUSH(s, typetag, value)					      \
-  do									      \
-    {									      \
-      status = tre_stack_push_ ## typetag(s, value);			      \
-    }									      \
-  while (/*CONSTCOND*/(void)0,0)
-
-#define STACK_PUSHX(s, typetag, value)					      \
-  {									      \
-    status = tre_stack_push_ ## typetag(s, value);			      \
-    if (status != REG_OK)						      \
-      break;								      \
-  }
-
-#define STACK_PUSHR(s, typetag, value)					      \
-  {									      \
-    reg_errcode_t _status;						      \
-    _status = tre_stack_push_ ## typetag(s, value);			      \
-    if (_status != REG_OK)						      \
-      return _status;							      \
-  }
-
-#endif /* TRE_STACK_H */
-
-/* EOF */

deps/tre/lib/xmalloc.c

@@ -1,362 +0,0 @@
-/*
-  xmalloc.c - Simple malloc debugging library implementation
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-/*
-  TODO:
-   - red zones
-   - group dumps by source location
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#include <stdint.h>
-#include <stdlib.h>
-#include <assert.h>
-#include <stdio.h>
-#define XMALLOC_INTERNAL 1
-#include "xmalloc.h"
-
-
-/*
-  Internal stuff.
-*/
-
-typedef struct hashTableItemRec {
-  void *ptr;
-  size_t bytes;
-  const char *file;
-  int line;
-  const char *func;
-  struct hashTableItemRec *next;
-} hashTableItem;
-
-typedef struct {
-  hashTableItem **table;
-} hashTable;
-
-static int xmalloc_peak;
-int xmalloc_current;
-static int xmalloc_peak_blocks;
-int xmalloc_current_blocks;
-static int xmalloc_fail_after;
-
-#define TABLE_BITS 8
-#define TABLE_MASK ((1 << TABLE_BITS) - 1)
-#define TABLE_SIZE (1 << TABLE_BITS)
-
-static hashTable *
-hash_table_new(void)
-{
-  hashTable *tbl;
-
-  tbl = malloc(sizeof(*tbl));
-
-  if (tbl != NULL)
-    {
-      tbl->table = calloc(TABLE_SIZE, sizeof(*tbl->table));
-
-      if (tbl->table == NULL)
-	{
-	  free(tbl);
-	  return NULL;
-	}
-    }
-
-  return tbl;
-}
-
-static unsigned int
-hash_void_ptr(void *ptr)
-{
-  unsigned int hash;
-  unsigned int i;
-
-  /* I took this hash function just off the top of my head, I have
-     no idea whether it is bad or very bad. */
-  hash = 0;
-  for (i = 0; i < sizeof(ptr) * 8 / TABLE_BITS; i++)
-    {
-      hash ^= (uintptr_t)ptr >> i * 8;
-      hash += i * 17;
-      hash &= TABLE_MASK;
-    }
-  return hash;
-}
-
-static void
-hash_table_add(hashTable *tbl, void *ptr, size_t bytes,
-	       const char *file, int line, const char *func)
-{
-  unsigned int i;
-  hashTableItem *item, *new;
-
-  i = hash_void_ptr(ptr);
-
-  item = tbl->table[i];
-  if (item != NULL)
-    while (item->next != NULL)
-      item = item->next;
-
-  new = malloc(sizeof(*new));
-  assert(new != NULL);
-  new->ptr = ptr;
-  new->bytes = bytes;
-  new->file = file;
-  new->line = line;
-  new->func = func;
-  new->next = NULL;
-  if (item != NULL)
-    item->next = new;
-  else
-    tbl->table[i] = new;
-
-  xmalloc_current += bytes;
-  if (xmalloc_current > xmalloc_peak)
-    xmalloc_peak = xmalloc_current;
-  xmalloc_current_blocks++;
-  if (xmalloc_current_blocks > xmalloc_peak_blocks)
-    xmalloc_peak_blocks = xmalloc_current_blocks;
-}
-
-static void
-#if defined(__GNUC__) && __GNUC__ >= 11
-__attribute__((access(none, 2)))
-#endif
-hash_table_del(hashTable *tbl, void *ptr)
-{
-  int i;
-  hashTableItem *item, *prev;
-
-  i = hash_void_ptr(ptr);
-
-  item = tbl->table[i];
-  if (item == NULL)
-    {
-      printf("xfree: invalid ptr %p\n", ptr);
-      abort();
-    }
-  prev = NULL;
-  while (item->ptr != ptr)
-    {
-      prev = item;
-      item = item->next;
-    }
-  if (item->ptr != ptr)
-    {
-      printf("xfree: invalid ptr %p\n", ptr);
-      abort();
-    }
-
-  xmalloc_current -= item->bytes;
-  xmalloc_current_blocks--;
-
-  if (prev != NULL)
-    {
-      prev->next = item->next;
-      free(item);
-    }
-  else
-    {
-      tbl->table[i] = item->next;
-      free(item);
-    }
-}
-
-static hashTable *xmalloc_table = NULL;
-
-static void
-xmalloc_init(void)
-{
-  if (xmalloc_table == NULL)
-    {
-      xmalloc_table = hash_table_new();
-      xmalloc_peak = 0;
-      xmalloc_peak_blocks = 0;
-      xmalloc_current = 0;
-      xmalloc_current_blocks = 0;
-      xmalloc_fail_after = -1;
-    }
-  assert(xmalloc_table != NULL);
-  assert(xmalloc_table->table != NULL);
-}
-
-
-
-/*
-  Public API.
-*/
-
-void
-xmalloc_configure(int fail_after)
-{
-  xmalloc_init();
-  xmalloc_fail_after = fail_after;
-}
-
-int
-xmalloc_dump_leaks(void)
-{
-  unsigned int i;
-  unsigned int num_leaks = 0;
-  size_t leaked_bytes = 0;
-  hashTableItem *item;
-
-  xmalloc_init();
-
-  for (i = 0; i < TABLE_SIZE; i++)
-    {
-      item = xmalloc_table->table[i];
-      while (item != NULL)
-	{
-	  printf("%s:%d: %s: %zu bytes at %p not freed\n",
-		 item->file, item->line, item->func, item->bytes, item->ptr);
-	  num_leaks++;
-	  leaked_bytes += item->bytes;
-	  item = item->next;
-	}
-    }
-  if (num_leaks == 0)
-    printf("No memory leaks.\n");
-  else
-    printf("%u unfreed memory chuncks, total %zu unfreed bytes.\n",
-	   num_leaks, leaked_bytes);
-  printf("Peak memory consumption %d bytes (%.1f kB, %.1f MB) in %d blocks ",
-	 xmalloc_peak, (double)xmalloc_peak / 1024,
-	 (double)xmalloc_peak / (1024*1024), xmalloc_peak_blocks);
-  printf("(average ");
-  if (xmalloc_peak_blocks)
-    printf("%d", ((xmalloc_peak + xmalloc_peak_blocks / 2)
-		  / xmalloc_peak_blocks));
-  else
-    printf("N/A");
-  printf(" bytes per block).\n");
-
-  return num_leaks;
-}
-
-void *
-xmalloc_impl(size_t size, const char *file, int line, const char *func)
-{
-  void *ptr;
-
-  xmalloc_init();
-  assert(size > 0);
-
-  if (xmalloc_fail_after == 0)
-    {
-      xmalloc_fail_after = -2;
-#if 0
-      printf("xmalloc: forced failure %s:%d: %s\n", file, line, func);
-#endif
-      return NULL;
-    }
-  else if (xmalloc_fail_after == -2)
-    {
-      printf("xmalloc: called after failure from %s:%d: %s\n",
-	     file, line, func);
-      assert(0);
-    }
-  else if (xmalloc_fail_after > 0)
-    xmalloc_fail_after--;
-
-  ptr = malloc(size);
-  if (ptr != NULL)
-    hash_table_add(xmalloc_table, ptr, (int)size, file, line, func);
-  return ptr;
-}
-
-void *
-xcalloc_impl(size_t nmemb, size_t size, const char *file, int line,
-	     const char *func)
-{
-  void *ptr;
-
-  xmalloc_init();
-  assert(size > 0);
-
-  if (xmalloc_fail_after == 0)
-    {
-      xmalloc_fail_after = -2;
-#if 0
-      printf("xcalloc: forced failure %s:%d: %s\n", file, line, func);
-#endif
-      return NULL;
-    }
-  else if (xmalloc_fail_after == -2)
-    {
-      printf("xcalloc: called after failure from %s:%d: %s\n",
-	     file, line, func);
-      assert(0);
-    }
-  else if (xmalloc_fail_after > 0)
-    xmalloc_fail_after--;
-
-  ptr = calloc(nmemb, size);
-  if (ptr != NULL)
-    hash_table_add(xmalloc_table, ptr, (int)(nmemb * size), file, line, func);
-  return ptr;
-}
-
-void
-xfree_impl(void *ptr, const char *file, int line, const char *func)
-{
-  /*LINTED*/(void)&file;
-  /*LINTED*/(void)&line;
-  /*LINTED*/(void)&func;
-  xmalloc_init();
-
-  if (ptr != NULL)
-    hash_table_del(xmalloc_table, ptr);
-  free(ptr);
-}
-
-void *
-xrealloc_impl(void *ptr, size_t new_size, const char *file, int line,
-	      const char *func)
-{
-  void *new_ptr;
-
-  xmalloc_init();
-  assert(ptr != NULL);
-  assert(new_size > 0);
-
-  if (xmalloc_fail_after == 0)
-    {
-      xmalloc_fail_after = -2;
-      return NULL;
-    }
-  else if (xmalloc_fail_after == -2)
-    {
-      printf("xrealloc: called after failure from %s:%d: %s\n",
-	     file, line, func);
-      assert(0);
-    }
-  else if (xmalloc_fail_after > 0)
-    xmalloc_fail_after--;
-
-  new_ptr = realloc(ptr, new_size);
-  if (new_ptr != NULL && new_ptr != ptr)
-    {
-#if defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wuse-after-free"
-#endif
-      hash_table_del(xmalloc_table, ptr);
-#if defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12
-#pragma GCC diagnostic pop
-#endif
-      hash_table_add(xmalloc_table, new_ptr, (int)new_size, file, line, func);
-    }
-  return new_ptr;
-}
-
-
-
-/* EOF */

deps/tre/lib/xmalloc.h

@@ -1,77 +0,0 @@
-/*
-  xmalloc.h - Simple malloc debugging library API
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifndef _XMALLOC_H
-#define _XMALLOC_H 1
-
-void *xmalloc_impl(size_t size, const char *file, int line, const char *func);
-void *xcalloc_impl(size_t nmemb, size_t size, const char *file, int line,
-		   const char *func);
-void xfree_impl(void *ptr, const char *file, int line, const char *func);
-void *xrealloc_impl(void *ptr, size_t new_size, const char *file, int line,
-		    const char *func);
-int xmalloc_dump_leaks(void);
-void xmalloc_configure(int fail_after);
-
-
-#ifndef XMALLOC_INTERNAL
-#ifdef MALLOC_DEBUGGING
-
-/* Version 2.4 and later of GCC define a magical variable `__PRETTY_FUNCTION__'
-   which contains the name of the function currently being defined.
-#  define __XMALLOC_FUNCTION	 __PRETTY_FUNCTION__
-   This is broken in G++ before version 2.6.
-   C9x has a similar variable called __func__, but prefer the GCC one since
-   it demangles C++ function names.  */
-# ifdef __GNUC__
-#  if __GNUC__ > 2 || (__GNUC__ == 2 \
-		       && __GNUC_MINOR__ >= (defined __cplusplus ? 6 : 4))
-#   define __XMALLOC_FUNCTION	 __PRETTY_FUNCTION__
-#  else
-#   define __XMALLOC_FUNCTION	 ((const char *) 0)
-#  endif
-# else
-#  if defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L
-#   define __XMALLOC_FUNCTION	 __func__
-#  else
-#   define __XMALLOC_FUNCTION	 ((const char *) 0)
-#  endif
-# endif
-
-#define xmalloc(size) xmalloc_impl(size, __FILE__, __LINE__, \
-				   __XMALLOC_FUNCTION)
-#define xcalloc(nmemb, size) xcalloc_impl(nmemb, size, __FILE__, __LINE__, \
-					  __XMALLOC_FUNCTION)
-#define xfree(ptr) xfree_impl(ptr, __FILE__, __LINE__, __XMALLOC_FUNCTION)
-#define xrealloc(ptr, new_size) xrealloc_impl(ptr, new_size, __FILE__, \
-					      __LINE__, __XMALLOC_FUNCTION)
-#undef malloc
-#undef calloc
-#undef free
-#undef realloc
-
-#define malloc	USE_XMALLOC_INSTEAD_OF_MALLOC
-#define calloc	USE_XCALLOC_INSTEAD_OF_CALLOC
-#define free	USE_XFREE_INSTEAD_OF_FREE
-#define realloc USE_XREALLOC_INSTEAD_OF_REALLOC
-
-#else /* !MALLOC_DEBUGGING */
-
-#include <stdlib.h>
-
-#define xmalloc(size) malloc(size)
-#define xcalloc(nmemb, size) calloc(nmemb, size)
-#define xfree(ptr) free(ptr)
-#define xrealloc(ptr, new_size) realloc(ptr, new_size)
-
-#endif /* !MALLOC_DEBUGGING */
-#endif /* !XMALLOC_INTERNAL */
-
-#endif /* _XMALLOC_H */
-
-/* EOF */

deps/tre/local_includes/regex.h

@@ -1,48 +0,0 @@
-/*
-  regex.h - TRE legacy API
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-  This header is for source level compatibility with old code using
-  the <tre/regex.h> header which defined the TRE API functions without
-  a prefix.  New code should include <tre/tre.h> instead.
-
-*/
-
-#ifndef TRE_REXEX_H
-#define TRE_REGEX_H 1
-
-#ifdef USE_LOCAL_TRE_H
-/* Use the header(s) from the TRE package that this file is part of.
-   (Yes, this file is in local_include too, but the explict path
-   means there is no way to get a system tre.h by accident.) */
-#include "../local_includes/tre.h"
-#else
-/* Use the header(s) from an installed version of the TRE package
-   (so that this application matches the installed libtre),
-   not the one(s) in the local_includes directory. */
-#include <tre/tre.h>
-#endif
-
-#ifndef TRE_USE_SYSTEM_REGEX_H
-#define regcomp	   tre_regcomp
-#define regerror   tre_regerror
-#define regexec	   tre_regexec
-#define regfree	   tre_regfree
-#endif /* TRE_USE_SYSTEM_REGEX_H */
-
-#define regacomp   tre_regacomp
-#define regaexec   tre_regaexec
-#define regancomp  tre_regancomp
-#define reganexec  tre_reganexec
-#define regawncomp tre_regawncomp
-#define regawnexec tre_regawnexec
-#define regncomp   tre_regncomp
-#define regnexec   tre_regnexec
-#define regwcomp   tre_regwcomp
-#define regwexec   tre_regwexec
-#define regwncomp  tre_regwncomp
-#define regwnexec  tre_regwnexec
-
-#endif /* TRE_REGEX_H */

deps/tre/local_includes/tre-config.h

@@ -1,14 +0,0 @@
-/* Minimal TRE configuration for Redis.
- *
- * We use TRE as a byte-oriented regex matcher for ARGREP. Redis SDS values are
- * binary-safe byte strings, so we intentionally keep the dependency build
- * simple: no wide-char path, no multibyte locale handling, and no approximate
- * matching engine.
- */
-
-#define HAVE_SYS_TYPES_H 1
-
-#define TRE_VERSION "redis-vendored"
-#define TRE_VERSION_1 0
-#define TRE_VERSION_2 0
-#define TRE_VERSION_3 0

deps/tre/local_includes/tre.h

@@ -1,344 +0,0 @@
-/*
-  tre.h - TRE public API definitions
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifndef TRE_H
-#define TRE_H 1
-
-#ifdef USE_LOCAL_TRE_H
-/* Make certain to use the header(s) from the TRE package that this
-   file is part of by giving the full path to the header from this directory. */
-#include "../local_includes/tre-config.h"
-#else
-/* Use the header in the same directory as this file if there is one. */
-#include "tre-config.h"
-#endif
-
-#ifdef HAVE_SYS_TYPES_H
-#include <sys/types.h>
-#endif /* HAVE_SYS_TYPES_H */
-
-#ifdef HAVE_LIBUTF8_H
-#include <libutf8.h>
-#endif /* HAVE_LIBUTF8_H */
-
-#ifdef TRE_USE_SYSTEM_REGEX_H
-/* Include the system regex.h to make TRE ABI compatible with the
-   system regex. */
-#include TRE_SYSTEM_REGEX_H_PATH
-#define tre_regcomp  regcomp
-#define tre_regexec  regexec
-#define tre_regerror regerror
-#define tre_regfree  regfree
-/* The GNU C regex has a number of refinements to the POSIX standard for the
-   formal parameter list of the regexec() function, and some of those fail to
-   compile when using LLVM.  The refinements seem to be opt-out rather than
-   opt-in when using a recent gcc, and they produce a warning when TRE tries
-   to mimic the API without the refinements.  The TRE code still works but
-   the warnings are distracting, so try to #define a flag to indicate when to 
-   add the refinements to TRE's parameter list too. */
-#ifdef __GNUC__
-/* Try to test something that looks pretty REGEX specific and hope we don't
-   need a zillion different platform+compiler specific tests to deal with this. */
-#ifdef _REGEX_NELTS
-/* Define a TRE specific flag here so that:
-   1) there is only one place where code has to be changed if the test above is not adequate, and
-   2) the flag can be used in any other parts of the TRE source that might be affected by the
-      GNUC refinements.
-   Note that this flag is only defined when all of TRE_USE_SYSTEM_REGEX_H, __GNUC__, and _REGEX_NELTS are defined. */
-#define TRE_USE_GNUC_REGEXEC_FPL 1
-#endif
-#endif
-#endif /* TRE_USE_SYSTEM_REGEX_H */
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#ifdef TRE_USE_SYSTEM_REGEX_H
-
-#ifndef REG_OK
-#define REG_OK 0
-#endif /* !REG_OK */
-
-#ifndef HAVE_REG_ERRCODE_T
-typedef int reg_errcode_t;
-#endif /* !HAVE_REG_ERRCODE_T */
-
-#if !defined(REG_NOSPEC) && !defined(REG_LITERAL)
-#define REG_LITERAL 0x1000
-#endif
-
-/* Extra tre_regcomp() return error codes. */
-#define REG_BADMAX REG_BADBR
-
-/* Extra tre_regcomp() flags. */
-#ifndef REG_BASIC
-#define REG_BASIC	0
-#endif /* !REG_BASIC */
-#define REG_RIGHT_ASSOC (REG_LITERAL << 1)
-#ifdef REG_UNGREEDY
-/* We're going to use TRE code, so we need the TRE define (dodge problem in MacOS). */
-#undef REG_UNGREEDY
-#endif
-#define REG_UNGREEDY    (REG_RIGHT_ASSOC << 1)
-
-#define REG_USEBYTES    (REG_UNGREEDY << 1)
-
-/* Extra tre_regexec() flags. */
-#define REG_APPROX_MATCHER	 0x1000
-#ifdef REG_BACKTRACKING_MATCHER
-/* We're going to use TRE code, so we need the TRE define (dodge problem in MacOS). */
-#undef REG_BACKTRACKING_MATCHER
-#endif
-#define REG_BACKTRACKING_MATCHER (REG_APPROX_MATCHER << 1)
-
-#else /* !TRE_USE_SYSTEM_REGEX_H */
-
-/* If the we're not using system regex.h, we need to define the
-   structs and enums ourselves. */
-
-typedef int regoff_t;
-typedef struct {
-  size_t re_nsub;  /* Number of parenthesized subexpressions. */
-  void *value;	   /* For internal use only. */
-} regex_t;
-
-typedef struct {
-  regoff_t rm_so;
-  regoff_t rm_eo;
-} regmatch_t;
-
-
-typedef enum {
-  REG_OK = 0,		/* No error. */
-  /* POSIX tre_regcomp() return error codes.  (In the order listed in the
-     standard.)	 */
-  REG_NOMATCH,		/* No match. */
-  REG_BADPAT,		/* Invalid regexp. */
-  REG_ECOLLATE,		/* Unknown collating element. */
-  REG_ECTYPE,		/* Unknown character class name. */
-  REG_EESCAPE,		/* Trailing backslash. */
-  REG_ESUBREG,		/* Invalid back reference. */
-  REG_EBRACK,		/* "[]" imbalance */
-  REG_EPAREN,		/* "\(\)" or "()" imbalance */
-  REG_EBRACE,		/* "\{\}" or "{}" imbalance */
-  REG_BADBR,		/* Invalid content of {} */
-  REG_ERANGE,		/* Invalid use of range operator */
-  REG_ESPACE,		/* Out of memory.  */
-  REG_BADRPT,		/* Invalid use of repetition operators. */
-  REG_BADMAX,		/* Maximum repetition in {} too large */
-} reg_errcode_t;
-
-/* POSIX tre_regcomp() flags. */
-#define REG_EXTENDED	1
-#define REG_ICASE	(REG_EXTENDED << 1)
-#define REG_NEWLINE	(REG_ICASE << 1)
-#define REG_NOSUB	(REG_NEWLINE << 1)
-
-/* Extra tre_regcomp() flags. */
-#define REG_BASIC	0
-#define REG_LITERAL	(REG_NOSUB << 1)
-#define REG_RIGHT_ASSOC (REG_LITERAL << 1)
-#define REG_UNGREEDY    (REG_RIGHT_ASSOC << 1)
-#define REG_USEBYTES    (REG_UNGREEDY << 1)
-
-/* POSIX tre_regexec() flags. */
-#define REG_NOTBOL 1
-#define REG_NOTEOL (REG_NOTBOL << 1)
-
-/* Extra tre_regexec() flags. */
-#define REG_APPROX_MATCHER	 (REG_NOTEOL << 1)
-#define REG_BACKTRACKING_MATCHER (REG_APPROX_MATCHER << 1)
-
-#endif /* !TRE_USE_SYSTEM_REGEX_H */
-
-/* REG_NOSPEC and REG_LITERAL mean the same thing. */
-#if defined(REG_LITERAL) && !defined(REG_NOSPEC)
-#define REG_NOSPEC	REG_LITERAL
-#elif defined(REG_NOSPEC) && !defined(REG_LITERAL)
-#define REG_LITERAL	REG_NOSPEC
-#endif /* defined(REG_NOSPEC) */
-
-/* The maximum number of iterations in a bound expression. */
-#undef RE_DUP_MAX
-#define RE_DUP_MAX 255
-
-/* The POSIX.2 regexp functions */
-extern int
-tre_regcomp(regex_t *preg, const char *regex, int cflags);
-
-#ifdef TRE_USE_GNUC_REGEXEC_FPL
-extern int
-tre_regexec(const regex_t *preg, const char *string,
-	size_t nmatch, regmatch_t pmatch[_Restrict_arr_ _REGEX_NELTS (nmatch)],
-	int eflags);
-#else
-extern int
-tre_regexec(const regex_t *preg, const char *string, size_t nmatch,
-	regmatch_t pmatch[], int eflags);
-#endif
-
-extern int
-tre_regcompb(regex_t *preg, const char *regex, int cflags);
-
-extern int
-tre_regexecb(const regex_t *preg, const char *string, size_t nmatch,
-	regmatch_t pmatch[], int eflags);
-
-extern size_t
-tre_regerror(int errcode, const regex_t *preg, char *errbuf,
-	 size_t errbuf_size);
-
-extern void
-tre_regfree(regex_t *preg);
-
-#ifdef TRE_WCHAR
-#ifdef HAVE_WCHAR_H
-#include <wchar.h>
-#endif /* HAVE_WCHAR_H */
-
-/* Wide character versions (not in POSIX.2). */
-extern int
-tre_regwcomp(regex_t *preg, const wchar_t *regex, int cflags);
-
-extern int
-tre_regwexec(const regex_t *preg, const wchar_t *string,
-	 size_t nmatch, regmatch_t pmatch[], int eflags);
-#endif /* TRE_WCHAR */
-
-/* Versions with a maximum length argument and therefore the capability to
-   handle null characters in the middle of the strings (not in POSIX.2). */
-extern int
-tre_regncomp(regex_t *preg, const char *regex, size_t len, int cflags);
-
-extern int
-tre_regnexec(const regex_t *preg, const char *string, size_t len,
-	 size_t nmatch, regmatch_t pmatch[], int eflags);
-
-/* regn*b versions take byte literally as 8-bit values */
-extern int
-tre_regncompb(regex_t *preg, const char *regex, size_t n, int cflags);
-
-extern int
-tre_regnexecb(const regex_t *preg, const char *str, size_t len,
-	  size_t nmatch, regmatch_t pmatch[], int eflags);
-
-#ifdef TRE_WCHAR
-extern int
-tre_regwncomp(regex_t *preg, const wchar_t *regex, size_t len, int cflags);
-
-extern int
-tre_regwnexec(const regex_t *preg, const wchar_t *string, size_t len,
-	  size_t nmatch, regmatch_t pmatch[], int eflags);
-#endif /* TRE_WCHAR */
-
-#ifdef TRE_APPROX
-
-/* Approximate matching parameter struct. */
-typedef struct {
-  int cost_ins;	       /* Default cost of an inserted character. */
-  int cost_del;	       /* Default cost of a deleted character. */
-  int cost_subst;      /* Default cost of a substituted character. */
-  int max_cost;	       /* Maximum allowed cost of a match. */
-
-  int max_ins;	       /* Maximum allowed number of inserts. */
-  int max_del;	       /* Maximum allowed number of deletes. */
-  int max_subst;       /* Maximum allowed number of substitutes. */
-  int max_err;	       /* Maximum allowed number of errors total. */
-} regaparams_t;
-
-/* Approximate matching result struct. */
-typedef struct {
-  size_t nmatch;       /* Length of pmatch[] array. */
-  regmatch_t *pmatch;  /* Submatch data. */
-  int cost;	       /* Cost of the match. */
-  int num_ins;	       /* Number of inserts in the match. */
-  int num_del;	       /* Number of deletes in the match. */
-  int num_subst;       /* Number of substitutes in the match. */
-} regamatch_t;
-
-
-/* Approximate matching functions. */
-extern int
-tre_regaexec(const regex_t *preg, const char *string,
-	 regamatch_t *match, regaparams_t params, int eflags);
-
-extern int
-tre_reganexec(const regex_t *preg, const char *string, size_t len,
-	  regamatch_t *match, regaparams_t params, int eflags);
-
-extern int
-tre_regaexecb(const regex_t *preg, const char *string,
-	  regamatch_t *match, regaparams_t params, int eflags);
-
-#ifdef TRE_WCHAR
-/* Wide character approximate matching. */
-extern int
-tre_regawexec(const regex_t *preg, const wchar_t *string,
-	  regamatch_t *match, regaparams_t params, int eflags);
-
-extern int
-tre_regawnexec(const regex_t *preg, const wchar_t *string, size_t len,
-	   regamatch_t *match, regaparams_t params, int eflags);
-#endif /* TRE_WCHAR */
-
-/* Sets the parameters to default values. */
-extern void
-tre_regaparams_default(regaparams_t *params);
-#endif /* TRE_APPROX */
-
-#ifdef TRE_WCHAR
-typedef wchar_t tre_char_t;
-#else /* !TRE_WCHAR */
-typedef unsigned char tre_char_t;
-#endif /* !TRE_WCHAR */
-
-typedef struct {
-  int (*get_next_char)(tre_char_t *c, unsigned int *pos_add, void *context);
-  void (*rewind)(size_t pos, void *context);
-  int (*compare)(size_t pos1, size_t pos2, size_t len, void *context);
-  void *context;
-} tre_str_source;
-
-extern int
-tre_reguexec(const regex_t *preg, const tre_str_source *string,
-	 size_t nmatch, regmatch_t pmatch[], int eflags);
-
-/* Returns the version string.	The returned string is static. */
-extern char *
-tre_version(void);
-
-/* Returns the value for a config parameter.  The type to which `result'
-   must point to depends of the value of `query', see documentation for
-   more details. */
-extern int
-tre_config(int query, void *result);
-
-enum {
-  TRE_CONFIG_APPROX,
-  TRE_CONFIG_WCHAR,
-  TRE_CONFIG_MULTIBYTE,
-  TRE_CONFIG_SYSTEM_ABI,
-  TRE_CONFIG_VERSION
-};
-
-/* Returns 1 if the compiled pattern has back references, 0 if not. */
-extern int
-tre_have_backrefs(const regex_t *preg);
-
-/* Returns 1 if the compiled pattern uses approximate matching features,
-   0 if not. */
-extern int
-tre_have_approx(const regex_t *preg);
-
-#ifdef __cplusplus
-}
-#endif
-#endif				/* TRE_H */
-
-/* EOF */

deps/tre/tests/test-literal-opt.c

@@ -1,303 +0,0 @@
-/*
-  test-literal-opt.c - Validate TRE literal optimization against the
-  generic matcher.
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#include <locale.h>
-#include <stdio.h>
-#include <string.h>
-
-#include "tre-internal.h"
-
-#define PMATCH_SLOTS 4
-#define RC_ANY -9999
-
-typedef struct {
-  const char *name;
-  const char *pattern;
-  size_t pattern_len;
-  int cflags;
-  const char *string;
-  size_t string_len;
-  int eflags;
-  int expected_rc;
-  tre_literal_opt_mode_t expected_mode;
-} litopt_case_t;
-
-static void
-init_pmatch(regmatch_t pmatch[], size_t count)
-{
-  size_t i;
-
-  for (i = 0; i < count; i++)
-    {
-      pmatch[i].rm_so = 111;
-      pmatch[i].rm_eo = 222;
-    }
-}
-
-static int
-same_pmatch(const regmatch_t a[], const regmatch_t b[], size_t count)
-{
-  size_t i;
-
-  for (i = 0; i < count; i++)
-    if (a[i].rm_so != b[i].rm_so || a[i].rm_eo != b[i].rm_eo)
-      return 0;
-  return 1;
-}
-
-static int
-pmatch_cleared(const regmatch_t pmatch[], size_t count)
-{
-  size_t i;
-
-  for (i = 0; i < count; i++)
-    if (pmatch[i].rm_so != -1 || pmatch[i].rm_eo != -1)
-      return 0;
-  return 1;
-}
-
-static int
-run_case(const litopt_case_t *tc)
-{
-  regex_t preg;
-  tre_tnfa_t *tnfa;
-  regmatch_t fast[PMATCH_SLOTS], slow[PMATCH_SLOTS];
-  tre_literal_opt_mode_t saved_mode;
-  char errbuf[256];
-  int errcode, fast_rc, slow_rc;
-
-  memset(&preg, 0, sizeof(preg));
-  errcode = tre_regncompb(&preg, tc->pattern, tc->pattern_len, tc->cflags);
-  if (errcode != REG_OK)
-    {
-      tre_regerror(errcode, &preg, errbuf, sizeof(errbuf));
-      fprintf(stderr, "%s: compile failed: %s\n", tc->name, errbuf);
-      return 1;
-    }
-
-  tnfa = (tre_tnfa_t *)preg.value;
-  if (tnfa->literal_opt.mode != tc->expected_mode)
-    {
-      fprintf(stderr, "%s: optimizer mode %d, expected %d\n",
-              tc->name, (int)tnfa->literal_opt.mode, (int)tc->expected_mode);
-      tre_regfree(&preg);
-      return 1;
-    }
-
-  init_pmatch(fast, PMATCH_SLOTS);
-  init_pmatch(slow, PMATCH_SLOTS);
-
-  fast_rc = tre_regnexecb(&preg, tc->string, tc->string_len,
-                          PMATCH_SLOTS, fast, tc->eflags);
-
-  saved_mode = tnfa->literal_opt.mode;
-  tnfa->literal_opt.mode = TRE_LITERAL_OPT_NONE;
-  slow_rc = tre_regnexecb(&preg, tc->string, tc->string_len,
-                          PMATCH_SLOTS, slow, tc->eflags);
-  tnfa->literal_opt.mode = saved_mode;
-
-  if (fast_rc != slow_rc)
-    {
-      fprintf(stderr, "%s: fast rc %d, slow rc %d\n",
-              tc->name, fast_rc, slow_rc);
-      tre_regfree(&preg);
-      return 1;
-    }
-
-  if (tc->expected_rc != RC_ANY && fast_rc != tc->expected_rc)
-    {
-      fprintf(stderr, "%s: rc %d, expected %d\n",
-              tc->name, fast_rc, tc->expected_rc);
-      tre_regfree(&preg);
-      return 1;
-    }
-
-  if (!same_pmatch(fast, slow, PMATCH_SLOTS))
-    {
-      fprintf(stderr, "%s: fast and slow pmatch differ\n", tc->name);
-      tre_regfree(&preg);
-      return 1;
-    }
-
-  if ((tc->cflags & REG_NOSUB) && fast_rc == REG_OK
-      && !pmatch_cleared(fast, PMATCH_SLOTS))
-    {
-      fprintf(stderr, "%s: REG_NOSUB match did not clear pmatch\n", tc->name);
-      tre_regfree(&preg);
-      return 1;
-    }
-
-  tre_regfree(&preg);
-  return 0;
-}
-
-int
-main(void)
-{
-  static const char nonascii_pattern[] = { (char)0xc0, '|', (char)0xe0 };
-  static const char nonascii_haystack[] = { 'x', (char)0xe0, 'y' };
-  static const litopt_case_t cases[] = {
-    {
-      "contains basic",
-      "foo|bar|baz",
-      sizeof("foo|bar|baz") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "xxbaryy",
-      sizeof("xxbaryy") - 1,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_CONTAINS
-    },
-    {
-      "contains ignores bol/eol flags",
-      "foo|bar|baz",
-      sizeof("foo|bar|baz") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "xxbaryy",
-      sizeof("xxbaryy") - 1,
-      REG_NOTBOL | REG_NOTEOL,
-      REG_OK,
-      TRE_LITERAL_OPT_CONTAINS
-    },
-    {
-      "prefix basic",
-      "^(foo|bar|baz)",
-      sizeof("^(foo|bar|baz)") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "barrier",
-      sizeof("barrier") - 1,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_PREFIX
-    },
-    {
-      "prefix respects REG_NOTBOL",
-      "^(foo|bar|baz)",
-      sizeof("^(foo|bar|baz)") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "barrier",
-      sizeof("barrier") - 1,
-      REG_NOTBOL,
-      REG_NOMATCH,
-      TRE_LITERAL_OPT_PREFIX
-    },
-    {
-      "suffix basic",
-      "(foo|bar|baz)$",
-      sizeof("(foo|bar|baz)$") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "crowbar",
-      sizeof("crowbar") - 1,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_SUFFIX
-    },
-    {
-      "suffix respects REG_NOTEOL",
-      "(foo|bar|baz)$",
-      sizeof("(foo|bar|baz)$") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "crowbar",
-      sizeof("crowbar") - 1,
-      REG_NOTEOL,
-      REG_NOMATCH,
-      TRE_LITERAL_OPT_SUFFIX
-    },
-    {
-      "exact basic",
-      "^(foo|bar|baz)$",
-      sizeof("^(foo|bar|baz)$") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "bar",
-      sizeof("bar") - 1,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_EXACT
-    },
-    {
-      "exact respects REG_NOTBOL",
-      "^(foo|bar|baz)$",
-      sizeof("^(foo|bar|baz)$") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "bar",
-      sizeof("bar") - 1,
-      REG_NOTBOL,
-      REG_NOMATCH,
-      TRE_LITERAL_OPT_EXACT
-    },
-    {
-      "exact respects REG_NOTEOL",
-      "^(foo|bar|baz)$",
-      sizeof("^(foo|bar|baz)$") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "bar",
-      sizeof("bar") - 1,
-      REG_NOTEOL,
-      REG_NOMATCH,
-      TRE_LITERAL_OPT_EXACT
-    },
-    {
-      "empty alternation disables optimization",
-      "(|foo|bar)",
-      sizeof("(|foo|bar)") - 1,
-      REG_EXTENDED | REG_NOSUB,
-      "",
-      0,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_NONE
-    },
-    {
-      "inline flag disable stays generic",
-      "foo(?-i:zap)zot",
-      sizeof("foo(?-i:zap)zot") - 1,
-      REG_EXTENDED | REG_ICASE | REG_NOSUB,
-      "FoOzApZOt",
-      sizeof("FoOzApZOt") - 1,
-      0,
-      REG_NOMATCH,
-      TRE_LITERAL_OPT_NONE
-    },
-    {
-      "inline flag disable still matches exact scoped bytes",
-      "foo(?-i:zap)zot",
-      sizeof("foo(?-i:zap)zot") - 1,
-      REG_EXTENDED | REG_ICASE | REG_NOSUB,
-      "FoOzapZOt",
-      sizeof("FoOzapZOt") - 1,
-      0,
-      REG_OK,
-      TRE_LITERAL_OPT_NONE
-    },
-    {
-      "nocase non-ascii bytes stay in sync",
-      nonascii_pattern,
-      sizeof(nonascii_pattern),
-      REG_EXTENDED | REG_ICASE | REG_NOSUB,
-      nonascii_haystack,
-      sizeof(nonascii_haystack),
-      0,
-      RC_ANY,
-      TRE_LITERAL_OPT_CONTAINS
-    }
-  };
-  size_t i;
-  int failures = 0;
-
-  setlocale(LC_CTYPE, "en_US.ISO-8859-1");
-
-  for (i = 0; i < elementsof(cases); i++)
-    failures += run_case(&cases[i]);
-
-  return failures;
-}

deps/tre/tests/test-malformed-regn.c

@@ -1,85 +0,0 @@
-/*
-  test-malformed-regn.c - Verify exact-length edge-case regexps compile or fail
-  cleanly both with and without a trailing NUL byte.
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-*/
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#include "tre.h"
-
-typedef struct {
-  const char *name;
-  const char *pattern;
-  int expected_err;
-} malformed_case_t;
-
-static int
-run_case(const malformed_case_t *tc, int nul_terminated)
-{
-  regex_t preg;
-  size_t len = strlen(tc->pattern);
-  size_t alloc_len = len + (nul_terminated ? 1 : 0);
-  char *pattern = malloc(alloc_len ? alloc_len : 1);
-  int errcode;
-
-  if (pattern == NULL)
-    {
-      fprintf(stderr, "%s: out of memory\n", tc->name);
-      return 1;
-    }
-
-  if (len > 0)
-    memcpy(pattern, tc->pattern, len);
-  if (nul_terminated)
-    pattern[len] = '\0';
-
-  memset(&preg, 0, sizeof(preg));
-  errcode = tre_regncompb(&preg, pattern, len, REG_EXTENDED | REG_NOSUB);
-  if (errcode == REG_OK)
-    tre_regfree(&preg);
-
-  free(pattern);
-
-  if (errcode != tc->expected_err)
-    {
-      char errbuf[128];
-      memset(&preg, 0, sizeof(preg));
-      tre_regerror(errcode, &preg, errbuf, sizeof(errbuf));
-      fprintf(stderr, "%s (%s): got %d (%s), expected %d\n",
-	      tc->name, nul_terminated ? "nul" : "exact",
-	      errcode, errbuf, tc->expected_err);
-      return 1;
-    }
-
-  return 0;
-}
-
-int
-main(void)
-{
-  static const malformed_case_t cases[] = {
-    { "open paren", "(", REG_EPAREN },
-    { "open bracket", "[", REG_EBRACK },
-    { "unterminated comment", "(?#", REG_BADPAT },
-    { "unterminated inline flags", "(?i", REG_BADPAT },
-    { "short hex escape", "\\x", REG_OK },
-    { "unterminated wide hex", "\\x{", REG_EBRACE },
-    { "empty wide hex", "\\x{}", REG_OK }
-  };
-  size_t i;
-
-  for (i = 0; i < sizeof(cases) / sizeof(*cases); i++)
-    {
-      if (run_case(&cases[i], 0))
-	return 1;
-      if (run_case(&cases[i], 1))
-	return 1;
-    }
-
-  return 0;
-}

deps/tre/tests/test-str-source.c

@@ -1,192 +0,0 @@
-/*
-  test-str-source.c - Sample program for using tre_reguexec()
-
-  This software is released under a BSD-style license.
-  See the file LICENSE for details and copyright.
-
-*/
-
-#ifdef HAVE_CONFIG_H
-#include <config.h>
-#endif /* HAVE_CONFIG_H */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-/* look for getopt in order to use a -o option for output. */
-#if defined(HAVE_UNISTD_H)
-#include <unistd.h>
-#elif defined(HAVE_GETOPT_H)
-#include <getopt.h>
-#endif
-
-#include "tre-internal.h"
-
-static FILE *outf = NULL;
-
-/* Context structure for the tre_str_source wrappers.  */
-typedef struct {
-  /* Our string. */
-  const char *str;
-  /* Current position in the string. */
-  size_t pos;
-} str_handler_ctx;
-
-/* The get_next_char() handler.  Sets `c' to the value of the next character,
-   and increases `pos_add' by the number of bytes read.  Returns 1 if the
-   string has ended, 0 if there are more characters. */
-static int
-str_handler_get_next(tre_char_t *c, unsigned int *pos_add, void *context)
-{
-  str_handler_ctx *ctx = context;
-  unsigned char ch = ctx->str[ctx->pos];
-
-#ifdef TRE_DEBUG
-  fprintf(outf, "str[%lu] = %d\n", (unsigned long)ctx->pos, ch);
-#endif /* TRE_DEBUG */
-  *c = ch;
-  if (ch)
-    ctx->pos++;
-  *pos_add = 1;
-
-  return ch == '\0';
-}
-
-/* The rewind() handler.  Resets the current position in the input string. */
-static void
-str_handler_rewind(size_t pos, void *context)
-{
-  str_handler_ctx *ctx = context;
-
-#ifdef TRE_DEBUG
-  fprintf(outf, "rewind to %lu\n", (unsigned long)pos);
-#endif /* TRE_DEBUG */
-  ctx->pos = pos;
-}
-
-/* The compare() handler.  Compares two substrings in the input and returns
-   0 if the substrings are equal, and a nonzero value if not. */
-static int
-str_handler_compare(size_t pos1, size_t pos2, size_t len, void *context)
-{
-  str_handler_ctx *ctx = context;
-#ifdef TRE_DEBUG
-  fprintf(outf, "comparing %lu-%lu and %lu-%lu\n",
-	 (unsigned long)pos1, (unsigned long)pos1 + len,
-	 (unsigned long)pos2, (unsigned long)pos2 + len);
-#endif /* TRE_DEBUG */
-  return strncmp(ctx->str + pos1, ctx->str + pos2, len);
-}
-
-/* Creates a tre_str_source wrapper around the string `str'.  Returns the
-   tre_str_source object or NULL if out of memory. */
-static tre_str_source *
-make_str_source(const char *str)
-{
-  tre_str_source *s;
-  str_handler_ctx *ctx;
-
-  s = calloc(1, sizeof(*s));
-  if (!s)
-    return NULL;
-
-  ctx = malloc(sizeof(str_handler_ctx));
-  if (!ctx)
-    {
-      free(s);
-      return NULL;
-    }
-
-  ctx->str = str;
-  ctx->pos = 0;
-  s->context = ctx;
-  s->get_next_char = str_handler_get_next;
-  s->rewind = str_handler_rewind;
-  s->compare = str_handler_compare;
-
-  return s;
-}
-
-/* Frees the memory allocated for `s'. */
-static void
-free_str_source(tre_str_source *s)
-{
-  free(s->context);
-  free(s);
-}
-
-/* Run one test with tre_reguexec.  Returns 1 if the regex matches, 0 if
-   it doesn't, and -1 if an error occurs. */
-static int
-test_reguexec(const char *str, const char *regex)
-{
-  regex_t preg;
-  tre_str_source *source;
-  regmatch_t pmatch[5];
-  int ret;
-
-  if ((source = make_str_source(str)) == NULL)
-    {
-      fprintf(stderr, "Out of memory\n");
-      ret = -1;
-    }
-  else
-    {
-      if (tre_regcomp(&preg, regex, REG_EXTENDED) != REG_OK)
-	{
-	  fprintf(stderr, "Failed to compile /%s/\n", regex);
-	  ret = -1;
-	}
-      else
-	{
-	  if (tre_reguexec(&preg, source, elementsof(pmatch), pmatch, 0) == 0)
-	    {
-	      fprintf(outf, "Match: /%s/ matches \"%.*s\" in \"%s\"\n", regex,
-		      (int)(pmatch[0].rm_eo - pmatch[0].rm_so),
-		      str + pmatch[0].rm_so, str);
-	      ret = 1;
-	    }
-	  else
-	    {
-	      fprintf(outf, "No match: /%s/ in \"%s\"\n", regex, str);
-	      ret = 0;
-	    }
-	  tre_regfree(&preg);
-	}
-      free_str_source(source);
-    }
-  return ret;
-}
-
-int
-main(int argc, char **argv)
-{
-  int ret = 0;
-  outf = stdout;
-#if defined(HAVE_UNISTD_H) || defined(HAVE_GETOPT_H)
-  int opt;
-  while ((opt = getopt(argc, argv, "o:")) != EOF)
-    {
-      switch (opt)
-	{
-	case 'o':
-	  if ((outf = fopen(optarg, "w")) == NULL)
-	    {
-	      perror(optarg);
-	      exit(1);
-	    }
-	  break;
-	default:
-	  /* getopt() will have printed an error message already */
-	  exit(1);
-	}
-    }
-#endif
-  ret += test_reguexec("xfoofofoofoo", "(foo)\\1") != 1;
-  ret += test_reguexec("catcat", "(cat|dog)\\1") != 1;
-  ret += test_reguexec("catdog", "(cat|dog)\\1") != 0;
-  ret += test_reguexec("dogdog", "(cat|dog)\\1") != 1;
-  ret += test_reguexec("dogcat", "(cat|dog)\\1") != 0;
-
-  return ret;
-}

deps/xxhash/.gitignore

@@ -1,6 +0,0 @@
-# Ignore:
-libxxhash.*
-xxh*sum
-
-# But include:
-!libxxhash.pc.in

deps/xxhash/LICENSE

@@ -1,26 +0,0 @@
-xxHash Library
-Copyright (c) 2012-2021 Yann Collet
-All rights reserved.
-
-BSD 2-Clause License (https://www.opensource.org/licenses/bsd-license.php)
-
-Redistribution and use in source and binary forms, with or without modification,
-are permitted provided that the following conditions are met:
-
-* Redistributions of source code must retain the above copyright notice, this
-  list of conditions and the following disclaimer.
-
-* Redistributions in binary form must reproduce the above copyright notice, this
-  list of conditions and the following disclaimer in the documentation and/or
-  other materials provided with the distribution.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
-ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

deps/xxhash/Makefile

@@ -1,687 +0,0 @@
-# ################################################################
-# xxHash Makefile
-# Copyright (C) 2012-2024 Yann Collet
-#
-# GPL v2 License
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# You can contact the author at:
-#   - xxHash homepage: https://www.xxhash.com
-#   - xxHash source repository: https://github.com/Cyan4973/xxHash
-# ################################################################
-# xxhsum: provides 32/64 bits hash of one or multiple files, or stdin
-# ################################################################
-
-# Version numbers
-SED ?= sed
-SED_ERE_OPT ?= -E
-LIBVER_MAJOR_SCRIPT:=`$(SED) -n '/define XXH_VERSION_MAJOR/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < xxhash.h`
-LIBVER_MINOR_SCRIPT:=`$(SED) -n '/define XXH_VERSION_MINOR/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < xxhash.h`
-LIBVER_PATCH_SCRIPT:=`$(SED) -n '/define XXH_VERSION_RELEASE/s/.*[[:blank:]]\([0-9][0-9]*\).*/\1/p' < xxhash.h`
-LIBVER_MAJOR := $(shell echo $(LIBVER_MAJOR_SCRIPT))
-LIBVER_MINOR := $(shell echo $(LIBVER_MINOR_SCRIPT))
-LIBVER_PATCH := $(shell echo $(LIBVER_PATCH_SCRIPT))
-LIBVER := $(LIBVER_MAJOR).$(LIBVER_MINOR).$(LIBVER_PATCH)
-
-MAKEFLAGS += --no-print-directory
-CFLAGS ?= -O3
-DEBUGFLAGS+=-Wall -Wextra -Wconversion -Wcast-qual -Wcast-align -Wshadow \
-            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-            -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
-            -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
-            -Wredundant-decls -Wstrict-overflow=2
-CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
-FLAGS   = $(CFLAGS) $(CPPFLAGS)
-XXHSUM_VERSION = $(LIBVER)
-
-# Define *.exe as extension for Windows systems
-ifneq (,$(filter Windows%,$(OS)))
-EXT =.exe
-else
-EXT =
-endif
-
-# automatically enable runtime vector dispatch on x86/64 targets
-detect_x86_arch = $(shell $(CC) -dumpmachine | grep -E 'i[3-6]86|x86_64')
-ifneq ($(strip $(call detect_x86_arch)),)
-    #note: can be overridden at compile time, by setting DISPATCH=0
-    DISPATCH ?= 1
-else
-    ifeq ($(DISPATCH),1)
-        $(info "Note: DISPATCH=1 is only supported on x86/x64 targets")
-    endif
-    override DISPATCH := 0
-endif
-
-ifeq ($(NODE_JS),1)
-    # Link in unrestricted filesystem support
-    LDFLAGS += -sNODERAWFS
-    # Set flag to fix isatty() support
-    CPPFLAGS += -DXSUM_NODE_JS=1
-endif
-
-# OS X linker doesn't support -soname, and use different extension
-# see: https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html
-UNAME ?= $(shell uname)
-ifeq ($(UNAME), Darwin)
-	SHARED_EXT = dylib
-	SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT)
-	SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT)
-	SONAME_FLAGS = -install_name $(LIBDIR)/libxxhash.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER)
-else
-	SONAME_FLAGS = -Wl,-soname=libxxhash.$(SHARED_EXT).$(LIBVER_MAJOR)
-	SHARED_EXT = so
-	SHARED_EXT_MAJOR = $(SHARED_EXT).$(LIBVER_MAJOR)
-	SHARED_EXT_VER = $(SHARED_EXT).$(LIBVER)
-endif
-
-LIBXXH = libxxhash.$(SHARED_EXT_VER)
-
-CLI_DIR = cli
-CLI_SRCS = $(wildcard $(CLI_DIR)/*.c)
-CLI_OBJS = $(CLI_SRCS:.c=.o)
-
-## define default before including multiconf.make
-## generate CLI and libraries in release mode (default for `make`)
-.PHONY: default
-default: DEBUGFLAGS=
-default: lib xxhsum_and_links
-
-C_SRCDIRS = . $(CLI_DIR) fuzz
-include build/make/multiconf.make
-
-.PHONY: all
-all: lib xxhsum xxhsum_inlinedXXH
-
-## xxhsum is the command line interface (CLI)
-ifeq ($(DISPATCH),1)
-xxhsum: CPPFLAGS += -DXXHSUM_DISPATCH=1
-XXHSUM_ADD_O = xxh_x86dispatch.o
-endif
-$(eval $(call c_program,xxhsum,xxhash.o $(CLI_OBJS) $(XXHSUM_ADD_O)))
-
-.PHONY: xxhsum_and_links
-xxhsum_and_links: xxhsum xxh32sum xxh64sum xxh128sum xxh3sum
-
-LN ?= ln
-
-xxh32sum xxh64sum xxh128sum xxh3sum: xxhsum
-	$(LN) -sf $<$(EXT) $@$(EXT)
-
-## generate CLI in 32-bits mode
-xxhsum32: CFLAGS += -m32
-ifeq ($(DISPATCH),1)
-xxhsum32: CPPFLAGS += -DXXHSUM_DISPATCH=1
-endif
-$(eval $(call c_program,xxhsum32,xxhash.o $(CLI_OBJS) $(XXHSUM_ADD_O)))
-
-## Warning: dispatch only works for x86/x64 systems
-dispatch: CPPFLAGS += -DXXHSUM_DISPATCH=1
-$(eval $(call c_program,dispatch,xxhash.o xxh_x86dispatch.o $(CLI_OBJS)))
-
-xxhsum_inlinedXXH: CPPFLAGS += -DXXH_INLINE_ALL
-$(eval $(call c_program,xxhsum_inlinedXXH,$(CLI_OBJS)))
-
-
-# =================================================
-# library
-
-libxxhash.a:
-$(eval $(call static_library,libxxhash.a,xxhash.o))
-
-$(LIBXXH): LDFLAGS += $(SONAME_FLAGS)
-ifeq (,$(filter Windows%,$(OS)))
-$(LIBXXH): CFLAGS += -fPIC
-endif
-LIBXXHASH_OBJS := xxhash.o $(if $(filter 1,$(LIBXXH_DISPATCH)),xxh_x86dispatch.o)
-$(eval $(call c_dynamic_library,$(LIBXXH),$(LIBXXHASH_OBJS)))
-
-libxxhash.$(SHARED_EXT_MAJOR): $(LIBXXH)
-	$(LN) -sf $< $@
-
-libxxhash.$(SHARED_EXT): libxxhash.$(SHARED_EXT_MAJOR)
-	$(LN) -sf $< $@
-
-.PHONY: libxxhash  ## generate dynamic xxhash library
-libxxhash: $(LIBXXH) libxxhash.$(SHARED_EXT_MAJOR) libxxhash.$(SHARED_EXT)
-
-.PHONY: lib  ## generate static and dynamic xxhash libraries
-lib: libxxhash.a libxxhash
-
-
-# helper targets
-
-AWK  ?= awk
-GREP ?= grep
-SORT ?= sort
-NM   ?= nm
-
-.PHONY: list
-list:  ## list all Makefile targets
-	$(MAKE) -pRrq -f $(lastword $(MAKEFILE_LIST)) : 2>/dev/null | $(AWK) -v RS= -F: '/^# File/,/^# Finished Make data base/ {if ($$1 !~ "^[#.]") {print $$1}}' | $(SORT) | egrep -v -e '^[^[:alnum:]]' -e '^$@$$' | xargs
-
-.PHONY: help
-help:  ## list documented targets
-	$(GREP) -E '^[0-9a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | \
-	$(SORT) | \
-	$(AWK) 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
-
-.PHONY: clean
-clean:
-	$(RM) -r *.dSYM   # Mac OS-X specific
-	$(RM) core *.o *.obj *.$(SHARED_EXT) *.$(SHARED_EXT).* *.a libxxhash.pc
-	$(RM) xxhsum.wasm xxhsum.js xxhsum.html
-	$(RM) xxh32sum$(EXT) xxh64sum$(EXT) xxh128sum$(EXT) xxh3sum$(EXT)
-	$(RM) fuzzer
-	$(MAKE) -C tests clean
-	$(MAKE) -C tests/bench clean
-	$(MAKE) -C tests/collisions clean
-	@echo cleaning completed
-
-
-# =================================================
-# tests
-# =================================================
-
-# make check can be run with cross-compiled binaries on emulated environments (qemu user mode)
-# by setting $(RUN_ENV) to the target emulation environment
-.PHONY: check
-check: xxhsum test_sanity   ## basic tests for xxhsum CLI, set RUN_ENV for emulated environments
-	# stdin
-	# If you get "Wrong parameters" on Emscripten+Node.js, recompile with `NODE_JS=1`
-	$(RUN_ENV) ./xxhsum$(EXT) < xxhash.c
-	# multiple files
-	$(RUN_ENV) ./xxhsum$(EXT) xxhash.*
-	# internal bench
-	$(RUN_ENV) ./xxhsum$(EXT) -bi0
-	# long bench command
-	$(RUN_ENV) ./xxhsum$(EXT) --benchmark-all -i0
-	# bench multiple variants
-	$(RUN_ENV) ./xxhsum$(EXT) -b1,2,3 -i0
-	# file bench
-	$(RUN_ENV) ./xxhsum$(EXT) -bi0 xxhash.c
-	# 32-bit
-	$(RUN_ENV) ./xxhsum$(EXT) -H0 xxhash.c
-	# 128-bit
-	$(RUN_ENV) ./xxhsum$(EXT) -H2 xxhash.c
-	# XXH3 (enforce BSD style)
-	$(RUN_ENV) ./xxhsum$(EXT) -H3 xxhash.c | grep "XXH3"
-	# request incorrect variant
-	$(RUN_ENV) ./xxhsum$(EXT) -H9 xxhash.c ; test $$? -eq 1
-	@printf "\n .......   checks completed successfully   ....... \n"
-
-.PHONY: test-unicode
-test-unicode:
-	$(MAKE) -C tests test_unicode
-
-.PHONY: test_sanity
-test_sanity:
-	$(MAKE) -C tests test_sanity
-
-.PHONY: test-mem
-VALGRIND = valgrind --leak-check=yes --error-exitcode=1
-test-mem: RUN_ENV = $(VALGRIND)
-test-mem: xxhsum check
-
-.PHONY: test32
-test32: xxhsum32
-	@echo ---- test 32-bit ----
-	./xxhsum32 -bi0 xxhash.c
-
-TEST_FILES = xxhsum$(EXT) xxhash.c xxhash.h
-.PHONY: test-xxhsum-c
-test-xxhsum-c: xxhsum
-	# xxhsum to/from pipe
-	./xxhsum $(TEST_FILES) | ./xxhsum -c -
-	./xxhsum -H0 $(TEST_FILES) | ./xxhsum -c -
-	# xxhsum -c is unable to verify checksum of file from STDIN (#470)
-	./xxhsum < README.md > .test.README.md.xxh
-	./xxhsum -c .test.README.md.xxh < README.md
-	# xxhsum -q does not display "Loading" message into stderr (#251)
-	! ./xxhsum -q $(TEST_FILES) 2>&1 | grep Loading
-	# xxhsum does not display "Loading" message into stderr either
-	! ./xxhsum $(TEST_FILES) 2>&1 | grep Loading
-	# Check that xxhsum do display filename that it failed to open.
-	LC_ALL=C ./xxhsum nonexistent 2>&1 | grep "Error: Could not open 'nonexistent'"
-	# xxhsum to/from file, shell redirection
-	./xxhsum $(TEST_FILES) > .test.xxh64
-	./xxhsum --tag $(TEST_FILES) > .test.xxh64_tag
-	./xxhsum --little-endian $(TEST_FILES) > .test.le_xxh64
-	./xxhsum --tag --little-endian $(TEST_FILES) > .test.le_xxh64_tag
-	./xxhsum -H0 $(TEST_FILES) > .test.xxh32
-	./xxhsum -H0 --tag $(TEST_FILES) > .test.xxh32_tag
-	./xxhsum -H0 --little-endian $(TEST_FILES) > .test.le_xxh32
-	./xxhsum -H0 --tag --little-endian $(TEST_FILES) > .test.le_xxh32_tag
-	./xxhsum -H2 $(TEST_FILES) > .test.xxh128
-	./xxhsum -H2 --tag $(TEST_FILES) > .test.xxh128_tag
-	./xxhsum -H2 --little-endian $(TEST_FILES) > .test.le_xxh128
-	./xxhsum -H2 --tag --little-endian $(TEST_FILES) > .test.le_xxh128_tag
-	./xxhsum -H3 $(TEST_FILES) > .test.xxh3
-	./xxhsum -H3 --tag $(TEST_FILES) > .test.xxh3_tag
-	./xxhsum -H3 --little-endian $(TEST_FILES) > .test.le_xxh3
-	./xxhsum -H3 --tag --little-endian $(TEST_FILES) > .test.le_xxh3_tag
-	./xxhsum -c .test.xxh*
-	./xxhsum -c --little-endian .test.le_xxh*
-	./xxhsum -c .test.*_tag
-	# read list of files from stdin
-	./xxhsum -c < .test.xxh32
-	./xxhsum -c < .test.xxh64
-	./xxhsum -c < .test.xxh128
-	./xxhsum -c < .test.xxh3
-	cat .test.xxh* | ./xxhsum -c -
-	# check variant with '*' marker as second separator
-	$(SED) 's/  / \*/' .test.xxh32 | ./xxhsum -c
-	# bsd-style output
-	./xxhsum --tag xxhsum* | $(GREP) XXH64
-	./xxhsum --tag -H0 xxhsum* | $(GREP) XXH32
-	./xxhsum --tag -H1 xxhsum* | $(GREP) XXH64
-	./xxhsum --tag -H2 xxhsum* | $(GREP) XXH128
-	./xxhsum --tag -H3 xxhsum* | $(GREP) XXH3
-	./xxhsum       -H3 xxhsum* | $(GREP) XXH3_ # prefix for GNU format
-	./xxhsum --tag -H32 xxhsum* | $(GREP) XXH32
-	./xxhsum --tag -H64 xxhsum* | $(GREP) XXH64
-	./xxhsum --tag -H128 xxhsum* | $(GREP) XXH128
-	./xxhsum --tag -H0 --little-endian xxhsum* | $(GREP) XXH32_LE
-	./xxhsum --tag -H1 --little-endian xxhsum* | $(GREP) XXH64_LE
-	./xxhsum --tag -H2 --little-endian xxhsum* | $(GREP) XXH128_LE
-	./xxhsum --tag -H3 --little-endian xxhsum* | $(GREP) XXH3_LE
-	./xxhsum --tag -H32 --little-endian xxhsum* | $(GREP) XXH32_LE
-	./xxhsum --tag -H64 --little-endian xxhsum* | $(GREP) XXH64_LE
-	./xxhsum --tag -H128 --little-endian xxhsum* | $(GREP) XXH128_LE
-	# check bsd-style
-	./xxhsum --tag xxhsum* | ./xxhsum -c
-	./xxhsum --tag -H32 --little-endian xxhsum* | ./xxhsum -c
-	# xxhsum -c warns improperly format lines.
-	echo '12345678 ' >>.test.xxh32
-	./xxhsum -c .test.xxh32 | $(GREP) improperly
-	echo '123456789  file' >>.test.xxh64
-	./xxhsum -c .test.xxh64 | $(GREP) improperly
-	# Expects "FAILED"
-	echo "0000000000000000  LICENSE" | ./xxhsum -c -; test $$? -eq 1
-	echo "00000000  LICENSE" | ./xxhsum -c -; test $$? -eq 1
-	# Expects "FAILED open or read"
-	echo "0000000000000000  test-expects-file-not-found" | ./xxhsum -c -; test $$? -eq 1
-	echo "00000000  test-expects-file-not-found" | ./xxhsum -c -; test $$? -eq 1
-	# --filelist
-	echo xxhash.c > .test.filenames
-	$(RUN_ENV) ./xxhsum$(EXT) --filelist .test.filenames
-	# --filelist from stdin
-	cat .test.filenames | $(RUN_ENV) ./xxhsum$(EXT) --filelist
-	@$(RM) .test.*
-
-CC_VERSION := $(shell $(CC) --version 2>/dev/null)
-ifneq (,$(findstring clang,$(CC_VERSION)))
-fuzzer: CFLAGS += -fsanitize=fuzzer
-$(eval $(call c_program,fuzzer, fuzz/fuzzer.o xxhash.o))
-else
-fuzzer: this_target_requires_clang # intentional fail
-endif
-
-.PHONY: test-filename-escape
-test-filename-escape:
-	$(MAKE) -C tests test_filename_escape
-
-.PHONY: test-cli-comment-line
-test-cli-comment-line:
-	$(MAKE) -C tests test_cli_comment_line
-
-.PHONY: test-cli-ignore-missing
-test-cli-ignore-missing:
-	$(MAKE) -C tests test_cli_ignore_missing
-
-.PHONY: armtest
-armtest:
-	@echo ---- test ARM compilation ----
-	CC=arm-linux-gnueabi-gcc MOREFLAGS="-Werror -static" $(MAKE) xxhsum
-
-.PHONY: arm64test
-arm64test:
-	@echo ---- test ARM64 compilation ----
-	CC=aarch64-linux-gnu-gcc MOREFLAGS="-Werror -static" $(MAKE) xxhsum
-
-.PHONY: clangtest
-clangtest:
-	@echo ---- test clang compilation ----
-	CC=clang MOREFLAGS="-Werror -Wconversion -Wno-sign-conversion" $(MAKE) all
-
-.PHONY: gcc-og-test
-gcc-og-test:
-	@echo ---- test gcc -Og compilation ----
-	CFLAGS="-Og -Wall -Wextra -Wundef -Wshadow -Wcast-align -Werror -fPIC" CPPFLAGS="-DXXH_NO_INLINE_HINTS" MOREFLAGS="-Werror" $(MAKE) all
-
-.PHONY: cxxtest
-cxxtest:
-	@echo ---- test C++ compilation ----
-	CC="$(CXX) -Wno-deprecated" $(MAKE) all CFLAGS="-O3 -Wall -Wextra -Wundef -Wshadow -Wcast-align -Werror -fPIC"
-
-# In strict C90 mode, there is no `long long` type support,
-# consequently, only XXH32 can be compiled.
-.PHONY: c90test
-ifeq ($(NO_C90_TEST),true)
-c90test:
-	@echo no c90 compatibility test
-else
-c90test: CPPFLAGS += -DXXH_NO_LONG_LONG
-c90test: CFLAGS += -std=c90 -Werror -pedantic
-c90test: xxhash.c
-	@echo ---- test strict C90 compilation [xxh32 only] ----
-	$(RM) xxhash.o
-	$(CC) $(FLAGS) $^ -c
-	$(NM) xxhash.o | $(GREP) XXH64 ; test $$? -eq 1
-	$(RM) xxhash.o
-endif
-
-.PHONY: noxxh3test
-noxxh3test: CPPFLAGS += -DXXH_NO_XXH3
-noxxh3test: CFLAGS += -Werror -pedantic -Wno-long-long  # XXH64 requires long long support
-noxxh3test: OFILE = xxh_noxxh3.o
-noxxh3test: xxhash.c
-	@echo ---- test compilation without XXH3 ----
-	$(CC) $(FLAGS) -c $^ -o $(OFILE)
-	$(NM) $(OFILE) | $(GREP) XXH3_ ; test $$? -eq 1
-	$(RM) $(OFILE)
-
-.PHONY: nostreamtest
-nostreamtest: CPPFLAGS += -DXXH_NO_STREAM
-nostreamtest: CFLAGS += -Werror -pedantic -Wno-long-long  # XXH64 requires long long support
-nostreamtest: OFILE = xxh_nostream.o
-nostreamtest: xxhash.c
-	@echo ---- test compilation without streaming ----
-	$(CC) $(FLAGS) -c $^ -o $(OFILE)
-	$(NM) $(OFILE) | $(GREP) update ; test $$? -eq 1
-	$(RM) $(OFILE)
-
-.PHONY: nostdlibtest
-nostdlibtest: CPPFLAGS += -DXXH_NO_STDLIB
-nostdlibtest: CFLAGS += -Werror -pedantic -Wno-long-long  # XXH64 requires long long support
-nostdlibtest: OFILE = xxh_nostdlib.o
-nostdlibtest: xxhash.c
-	@echo ---- test compilation without \<stdlib.h\> ----
-	$(CC) $(FLAGS) -c $^ -o $(OFILE)
-	$(NM) $(OFILE) | $(GREP) "U _free\|U free" ; test $$? -eq 1
-	$(RM) $(OFILE)
-
-.PHONY: usan
-usan: CC=clang
-usan: CXX=clang++
-usan:  ## check CLI runtime for undefined behavior, using clang's sanitizer
-	@echo ---- check undefined behavior - sanitize ----
-	$(MAKE) test CC=$(CC) CXX=$(CXX) MOREFLAGS="-g -fsanitize=undefined -fno-sanitize-recover=all"
-
-.PHONY: staticAnalyze
-SCANBUILD ?= scan-build
-staticAnalyze: clean  ## check C source files using $(SCANBUILD) static analyzer
-	@echo ---- static analyzer - $(SCANBUILD) ----
-	CFLAGS="-g -Werror" $(SCANBUILD) --status-bugs -v $(MAKE) all
-
-CPPCHECK ?= cppcheck
-.PHONY: cppcheck
-cppcheck:  ## check C source files using $(CPPCHECK) static analyzer
-	@echo ---- static analyzer - $(CPPCHECK) ----
-	$(CPPCHECK) . --force --enable=warning,portability,performance,style --error-exitcode=1 > /dev/null
-
-.PHONY: namespaceTest
-namespaceTest:  ## ensure XXH_NAMESPACE redefines all public symbols
-	$(CC) -c xxhash.c
-	$(CC) -DXXH_NAMESPACE=TEST_ -c xxhash.c -o xxhash2.o
-	$(CC) xxhash.o xxhash2.o $(CLI_SRCS)  -o xxhsum2  # will fail if one namespace missing (symbol collision)
-	$(RM) *.o xxhsum2  # clean
-
-MAN = $(CLI_DIR)/xxhsum.1
-MD2ROFF ?= ronn
-MD2ROFF_FLAGS ?= --roff --warnings --manual="User Commands" --organization="xxhsum $(XXHSUM_VERSION)"
-$(MAN): $(CLI_DIR)/xxhsum.1.md xxhash.h
-	cat $< | $(MD2ROFF) $(MD2ROFF_FLAGS) | $(SED) -n '/^\.\\\".*/!p' > $@
-
-.PHONY: man
-man: $(MAN)  ## generate man page from markdown source
-
-.PHONY: clean-man
-clean-man:
-	$(RM) xxhsum.1
-
-.PHONY: preview-man
-preview-man: man
-	man ./xxhsum.1
-
-.PHONY: test
-test: DEBUGFLAGS += -DXXH_DEBUGLEVEL=1
-test: all namespaceTest check test-xxhsum-c c90test test-tools noxxh3test nostdlibtest
-
-# this test checks that including "xxhash.h" multiple times and with different directives still compiles properly
-.PHONY: test-multiInclude
-test-multiInclude:
-	$(MAKE) -C tests test_multiInclude
-
-.PHONY: test-inline-notexposed
-test-inline-notexposed: xxhsum_inlinedXXH
-	$(NM) xxhsum_inlinedXXH | $(GREP) "t _XXH32_" ; test $$? -eq 1  # no XXH32 symbol should be left
-	$(NM) xxhsum_inlinedXXH | $(GREP) "t _XXH64_" ; test $$? -eq 1  # no XXH64 symbol should be left
-
-.PHONY: test-inline
-test-inline: test-inline-notexposed test-multiInclude
-
-
-.PHONY: test-all
-test-all: CFLAGS += -Werror
-test-all: test test32 test-unicode clangtest gcc-og-test cxxtest usan test-inline listL120 trailingWhitespace test-xxh-nnn-sums
-
-.PHONY: test-tools
-test-tools:
-	CFLAGS=-Werror $(MAKE) -C tests/bench
-	CFLAGS=-Werror $(MAKE) -C tests/collisions check
-
-.PHONY: test-xxh-nnn-sums
-test-xxh-nnn-sums: xxhsum_and_links
-	./xxhsum    README.md > tmp.xxhsum.out    # xxhsum outputs xxh64
-	./xxh32sum  README.md > tmp.xxh32sum.out
-	./xxh64sum  README.md > tmp.xxh64sum.out
-	./xxh128sum README.md > tmp.xxh128sum.out
-	./xxh3sum   README.md > tmp.xxh3sum.out
-	cat tmp.xxhsum.out
-	cat tmp.xxh32sum.out
-	cat tmp.xxh64sum.out
-	cat tmp.xxh128sum.out
-	cat tmp.xxh3sum.out
-	./xxhsum -c tmp.xxhsum.out
-	./xxhsum -c tmp.xxh32sum.out
-	./xxhsum -c tmp.xxh64sum.out
-	./xxhsum -c tmp.xxh128sum.out
-	./xxhsum -c tmp.xxh3sum.out
-	./xxh32sum -c tmp.xxhsum.out            ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh32sum -c tmp.xxh32sum.out
-	./xxh32sum -c tmp.xxh64sum.out          ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh32sum -c tmp.xxh128sum.out         ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh32sum -c tmp.xxh3sum.out           ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh64sum -c tmp.xxhsum.out
-	./xxh64sum -c tmp.xxh32sum.out          ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh64sum -c tmp.xxh64sum.out
-	./xxh64sum -c tmp.xxh128sum.out         ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh64sum -c tmp.xxh3sum.out           ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh128sum -c tmp.xxhsum.out           ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh128sum -c tmp.xxh32sum.out         ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh128sum -c tmp.xxh64sum.out         ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh128sum -c tmp.xxh128sum.out
-	./xxh128sum -c tmp.xxh3sum.out          ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh3sum -c tmp.xxhsum.out             ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh3sum -c tmp.xxh32sum.out           ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh3sum -c tmp.xxh64sum.out           ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh3sum -c tmp.xxh128sum.out          ; test $$? -eq 1  # expects "no properly formatted"
-	./xxh3sum -c tmp.xxh3sum.out
-
-.PHONY: listL120
-listL120:  # extract lines >= 120 characters in *.{c,h}, by Takayuki Matsuoka (note: $$, for Makefile compatibility)
-	find . -type f -name '*.c' -o -name '*.h' | while read -r filename; do awk 'length > 120 {print FILENAME "(" FNR "): " $$0}' $$filename; done
-
-.PHONY: trailingWhitespace
-trailingWhitespace:
-	! $(GREP) -E "`printf '[ \\t]$$'`" cli/*.c cli/*.h cli/*.1 *.c *.h LICENSE Makefile build/cmake/CMakeLists.txt
-
-.PHONY: lint-unicode
-lint-unicode:
-	./tests/unicode_lint.sh
-
-# =========================================================
-# make install is validated only for the following targets
-# =========================================================
-ifneq (,$(filter Linux Darwin GNU/kFreeBSD GNU Haiku OpenBSD FreeBSD NetBSD DragonFly SunOS CYGWIN% , $(UNAME)))
-
-DESTDIR     ?=
-# directory variables: GNU conventions prefer lowercase
-# see https://www.gnu.org/prep/standards/html_node/Makefile-Conventions.html
-# support both lower and uppercase (BSD), use uppercase in script
-prefix      ?= /usr/local
-PREFIX      ?= $(prefix)
-exec_prefix ?= $(PREFIX)
-EXEC_PREFIX ?= $(exec_prefix)
-libdir      ?= $(EXEC_PREFIX)/lib
-LIBDIR      ?= $(libdir)
-includedir  ?= $(PREFIX)/include
-INCLUDEDIR  ?= $(includedir)
-bindir      ?= $(EXEC_PREFIX)/bin
-BINDIR      ?= $(bindir)
-datarootdir ?= $(PREFIX)/share
-mandir      ?= $(datarootdir)/man
-man1dir     ?= $(mandir)/man1
-
-ifneq (,$(filter $(UNAME),FreeBSD NetBSD DragonFly))
-PKGCONFIGDIR ?= $(PREFIX)/libdata/pkgconfig
-else
-PKGCONFIGDIR ?= $(LIBDIR)/pkgconfig
-endif
-
-ifneq (,$(filter $(UNAME),OpenBSD NetBSD DragonFly SunOS))
-MANDIR  ?= $(PREFIX)/man/man1
-else
-MANDIR  ?= $(man1dir)
-endif
-
-ifneq (,$(filter $(UNAME),SunOS))
-INSTALL ?= ginstall
-else
-INSTALL ?= install
-endif
-
-INSTALL_PROGRAM ?= $(INSTALL)
-INSTALL_DATA    ?= $(INSTALL) -m 644
-MAKE_DIR        ?= $(INSTALL) -d -m 755
-
-
-# Escape special symbols by putting each character into its separate class
-EXEC_PREFIX_REGEX ?= $(shell echo "$(EXEC_PREFIX)" | $(SED) $(SED_ERE_OPT) -e "s/([^^])/[\1]/g" -e "s/\\^/\\\\^/g")
-PREFIX_REGEX ?= $(shell echo "$(PREFIX)" | $(SED) $(SED_ERE_OPT) -e "s/([^^])/[\1]/g" -e "s/\\^/\\\\^/g")
-
-PCLIBDIR ?= $(shell echo "$(LIBDIR)"     | $(SED) -n $(SED_ERE_OPT) -e "s@^$(EXEC_PREFIX_REGEX)(/|$$)@@p")
-PCINCDIR ?= $(shell echo "$(INCLUDEDIR)" | $(SED) -n $(SED_ERE_OPT) -e "s@^$(PREFIX_REGEX)(/|$$)@@p")
-PCEXECDIR?= $(if $(filter $(PREFIX),$(EXEC_PREFIX)),$$\{prefix\},$(EXEC_PREFIX))
-
-ifeq (,$(PCLIBDIR))
-# Additional prefix check is required, since the empty string is technically a
-# valid PCLIBDIR
-ifeq (,$(shell echo "$(LIBDIR)" | $(SED) -n $(SED_ERE_OPT) -e "\\@^$(EXEC_PREFIX_REGEX)(/|$$)@ p"))
-$(error configured libdir ($(LIBDIR)) is outside of exec_prefix ($(EXEC_PREFIX)), can't generate pkg-config file)
-endif
-endif
-
-ifeq (,$(PCINCDIR))
-# Additional prefix check is required, since the empty string is technically a
-# valid PCINCDIR
-ifeq (,$(shell echo "$(INCLUDEDIR)" | $(SED) -n $(SED_ERE_OPT) -e "\\@^$(PREFIX_REGEX)(/|$$)@ p"))
-$(error configured includedir ($(INCLUDEDIR)) is outside of prefix ($(PREFIX)), can't generate pkg-config file)
-endif
-endif
-
-libxxhash.pc: libxxhash.pc.in
-	@echo creating pkgconfig
-	$(SED) $(SED_ERE_OPT) -e 's|@PREFIX@|$(PREFIX)|' \
-          -e 's|@EXECPREFIX@|$(PCEXECDIR)|' \
-          -e 's|@LIBDIR@|$$\{exec_prefix\}/$(PCLIBDIR)|' \
-          -e 's|@INCLUDEDIR@|$$\{prefix\}/$(PCINCDIR)|' \
-          -e 's|@VERSION@|$(LIBVER)|' \
-          $< > $@
-
-
-install_libxxhash.a: libxxhash.a
-	@echo Installing libxxhash.a
-	$(MAKE_DIR) $(DESTDIR)$(LIBDIR)
-	$(INSTALL_DATA) libxxhash.a $(DESTDIR)$(LIBDIR)
-
-install_libxxhash: libxxhash
-	@echo Installing libxxhash
-	$(MAKE_DIR) $(DESTDIR)$(LIBDIR)
-	$(INSTALL_PROGRAM) $(LIBXXH) $(DESTDIR)$(LIBDIR)
-	ln -sf $(LIBXXH) $(DESTDIR)$(LIBDIR)/libxxhash.$(SHARED_EXT_MAJOR)
-	ln -sf libxxhash.$(SHARED_EXT_MAJOR) $(DESTDIR)$(LIBDIR)/libxxhash.$(SHARED_EXT)
-
-install_libxxhash.includes:
-	$(INSTALL) -d -m 755 $(DESTDIR)$(INCLUDEDIR)   # includes
-	$(INSTALL_DATA) xxhash.h $(DESTDIR)$(INCLUDEDIR)
-	$(INSTALL_DATA) xxh3.h $(DESTDIR)$(INCLUDEDIR) # for compatibility, will be removed in v0.9.0
-ifeq ($(LIBXXH_DISPATCH),1)
-	$(INSTALL_DATA) xxh_x86dispatch.h $(DESTDIR)$(INCLUDEDIR)
-endif
-
-install_libxxhash.pc: libxxhash.pc
-	@echo Installing pkgconfig
-	$(MAKE_DIR) $(DESTDIR)$(PKGCONFIGDIR)/
-	$(INSTALL_DATA) libxxhash.pc $(DESTDIR)$(PKGCONFIGDIR)/
-
-install_xxhsum: xxhsum
-	@echo Installing xxhsum
-	$(MAKE_DIR) $(DESTDIR)$(BINDIR)/
-	$(INSTALL_PROGRAM) xxhsum$(EXT) $(DESTDIR)$(BINDIR)/xxhsum$(EXT)
-	ln -sf xxhsum$(EXT) $(DESTDIR)$(BINDIR)/xxh32sum$(EXT)
-	ln -sf xxhsum$(EXT) $(DESTDIR)$(BINDIR)/xxh64sum$(EXT)
-	ln -sf xxhsum$(EXT) $(DESTDIR)$(BINDIR)/xxh128sum$(EXT)
-	ln -sf xxhsum$(EXT) $(DESTDIR)$(BINDIR)/xxh3sum$(EXT)
-
-install_man:
-	@echo Installing man pages
-	$(MAKE_DIR) $(DESTDIR)$(MANDIR)/
-	$(INSTALL_DATA) $(MAN) $(DESTDIR)$(MANDIR)/xxhsum.1
-	ln -sf xxhsum.1 $(DESTDIR)$(MANDIR)/xxh32sum.1
-	ln -sf xxhsum.1 $(DESTDIR)$(MANDIR)/xxh64sum.1
-	ln -sf xxhsum.1 $(DESTDIR)$(MANDIR)/xxh128sum.1
-	ln -sf xxhsum.1 $(DESTDIR)$(MANDIR)/xxh3sum.1
-
-.PHONY: install
-## install libraries, CLI, links and man pages
-install: install_libxxhash.a install_libxxhash install_libxxhash.includes install_libxxhash.pc install_xxhsum install_man
-	@echo xxhash installation completed
-
-.PHONY: uninstall
-uninstall:  ## uninstall libraries, CLI, links and man page
-	$(RM) $(DESTDIR)$(LIBDIR)/libxxhash.a
-	$(RM) $(DESTDIR)$(LIBDIR)/libxxhash.$(SHARED_EXT)
-	$(RM) $(DESTDIR)$(LIBDIR)/libxxhash.$(SHARED_EXT_MAJOR)
-	$(RM) $(DESTDIR)$(LIBDIR)/$(LIBXXH)
-	$(RM) $(DESTDIR)$(INCLUDEDIR)/xxhash.h
-	$(RM) $(DESTDIR)$(INCLUDEDIR)/xxh3.h
-	$(RM) $(DESTDIR)$(INCLUDEDIR)/xxh_x86dispatch.h
-	$(RM) $(DESTDIR)$(PKGCONFIGDIR)/libxxhash.pc
-	$(RM) $(DESTDIR)$(BINDIR)/xxh32sum
-	$(RM) $(DESTDIR)$(BINDIR)/xxh64sum
-	$(RM) $(DESTDIR)$(BINDIR)/xxh128sum
-	$(RM) $(DESTDIR)$(BINDIR)/xxh3sum
-	$(RM) $(DESTDIR)$(BINDIR)/xxhsum
-	$(RM) $(DESTDIR)$(MANDIR)/xxh32sum.1
-	$(RM) $(DESTDIR)$(MANDIR)/xxh64sum.1
-	$(RM) $(DESTDIR)$(MANDIR)/xxh128sum.1
-	$(RM) $(DESTDIR)$(MANDIR)/xxh3sum.1
-	$(RM) $(DESTDIR)$(MANDIR)/xxhsum.1
-	@echo xxhsum successfully uninstalled
-
-endif

deps/xxhash/build/make/README.md

@@ -1,71 +0,0 @@
-# multiconf.make
-
-**multiconf.make** is a self-contained Makefile include that lets you build the **same targets under many different flag sets**. For example debug vs release, ASan vs UBSan, GCC vs Clang.
-Each different set of flags generates object files into its own **dedicated cache directory**, so objects compiled with one configuration are never reused by another.
-Object files from previous configurations are preserved, so swapping back to a previous configuration only requires compiling objects which have actually changed.
-
----
-
-## Benefits at a glance
-
-| Benefit | What `multiconf.make` does |
-| --- | --- |
-| **Isolated configs** | Stores objects into `cachedObjs/<hash>/`, one directory per unique flag set. |
-| **Fast switching** | Reusing an old config is instant—link only, no recompilation. |
-| **Header deps** | Edits to headers trigger only needed rebuilds. |
-| **One-liner targets** | Macros (`c_program`, `cxx_program`, …) hide all rule boilerplate. |
-| **Parallel-ready** | Safe with `make -j`, no duplicate compiles of shared sources. |
-| **Controlled verbosity** | Default only lists objects, while `V=1` display full commands. |
-| **`clean` included** | `make clean` deletes all objects, binaries and links. |
-
----
-
-## Quick Start
-
-### 1 · List your sources
-
-```make
-C_SRCDIRS   := src src/cdeps    # all .c are in these directories
-CXX_SRCDIRS := src src/cxxdeps  # all .cpp are in these directories
-```
-
-### 2 · Add and include
-
-```make
-# root/Makefile
-include multiconf.make
-```
-
-### 3 · Declare targets
-
-```make
-app:
-$(eval $(call c_program,app,app.o cdeps/obj.o))
-
-test:
-$(eval $(call cxx_program,test, test.o cxxdeps/objcxx.o))
-
-lib.a:
-$(eval $(call static_library,lib.a, lib.o cdeps/obj.o))
-
-lib.so:
-$(eval $(call c_dynamic_library,lib.so, lib.o cdeps/obj.o))
-```
-
-### 4 · Build any config you like
-
-```sh
-# Release with GCC
-make CFLAGS="-O3"
-
-# Debug with Clang + AddressSanitizer (new cache dir)
-make CC=clang CFLAGS="-g -O0 -fsanitize=address"
-
-# Switch back to GCC release (objects still valid, relink only)
-make CFLAGS="-O3"
-```
-
-Objects for each command live in different sub-folders; nothing overlaps.
-
----
-

deps/xxhash/build/make/multiconf.make

@@ -1,293 +0,0 @@
-# ##########################################################################
-# multiconf.make
-# Copyright (C) Yann Collet
-#
-# GPL v2 License
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
-#
-# ##########################################################################
-
-
-# Provides c_program(_shared_o) and cxx_program(_shared_o) target generation macros
-# Provides static_library and c_dynamic_library target generation macros
-# Support recompilation of only impacted units when an associated *.h is updated.
-# Provides V=1 / VERBOSE=1 support. V=2 is used for debugging purposes.
-# Complement target clean: delete objects and binaries created by this script
-
-# Requires:
-# - C_SRCDIRS, CXX_SRCDIRS, ASM_SRCDIRS defined
-#   OR
-#   C_SRCS, CXX_SRCS and ASM_SRCS variables defined
-#   *and* vpath set to find all source files
-#   OR
-#   C_OBJS, CXX_OBJS and ASM_OBJS variables defined
-#   *and* vpath set to find all source files
-# - directory `cachedObjs/` available to cache object files.
-#   alternatively: set CACHE_ROOT to some different value.
-# Optional:
-# - HASH can be set to a different custom hash program.
-
-# *_program*: generates a recipe for a target that will be built in a cache directory.
-# The cache directory is automatically derived from CACHE_ROOT and list of flags and compilers.
-# *_shared_o* variants are optional optimization variants, that share the same objects across multiple targets.
-# However, as a consequence, all these objects must have exactly the same list of flags,
-# which in practice means that there must be no target-level modification (like: target: CFLAGS += someFlag).
-# If unsure, only use the standard variants, c_program and cxx_program.
-
-# All *_program* macro functions take up to 4 argument:
-# - The name of the target
-# - The list of object files to build in the cache directory
-# - An optional list of dependencies for linking, that will not be built
-# - An optional complementary recipe code, that will run after compilation and link
-
-
-# Silent mode is default; use V = 1 or VERBOSE = 1 to see compilation lines
-VERBOSE ?= $(V)
-$(VERBOSE).SILENT:
-
-# Directory where object files will be built
-CACHE_ROOT ?= cachedObjs
-
-# --------------------------------------------------------------------------------------------
-
-# Dependency management
-DEPFLAGS = -MT $@ -MMD -MP -MF
-
-# Include dependency files
-include $(wildcard $(CACHE_ROOT)/**/*.d)
-include $(wildcard $(CACHE_ROOT)/generic/*/*.d)
-
-# --------------------------------------------------------------------------------------------
-
-# Automatic determination of build artifacts cache directory, keyed on build
-# flags, so that we can do incremental, parallel builds of different binaries
-# with different build flags without collisions.
-
-UNAME ?= $(shell uname)
-ifeq ($(UNAME), Darwin)
-  HASH ?= md5
-else ifeq ($(UNAME), FreeBSD)
-  HASH ?= gmd5sum
-else ifeq ($(UNAME), OpenBSD)
-  HASH ?= md5
-endif
-HASH ?= md5sum
-
-HAVE_HASH := $(shell echo 1 | $(HASH) > /dev/null && echo 1 || echo 0)
-ifeq ($(HAVE_HASH),0)
-  $(info warning : could not find HASH ($(HASH)), required to differentiate builds using different flags)
-  HASH_FUNC = generic/$(1)
-else
-  HASH_FUNC = $(firstword $(shell echo $(2) | $(HASH) ))
-endif
-
-
-MKDIR ?= mkdir
-LN ?= ln
-
-# --------------------------------------------------------------------------------------------
-# The following macros are used to create object files in the cache directory.
-# The object files are named after the source file, but with a different path.
-
-# Create build directories on-demand.
-#
-# For some reason, make treats the directory as an intermediate file and tries
-# to delete it. So we work around that by marking it "precious". Solution found
-# here:
-# http://ismail.badawi.io/blog/2017/03/28/automatic-directory-creation-in-make/
-.PRECIOUS: $(CACHE_ROOT)/%/.
-$(CACHE_ROOT)/%/. :
-	$(MKDIR) -p $@
-
-
-define addTargetAsmObject  # targetName, addlDeps
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2))))
-
-.PRECIOUS: $$(CACHE_ROOT)/%/$(1)
-$$(CACHE_ROOT)/%/$(1) : $(1:.o=.S) $(2) | $$(CACHE_ROOT)/%/.
-	@echo AS $$@
-	$$(CC) $$(CPPFLAGS) $$(CXXFLAGS) $$(DEPFLAGS) $$(CACHE_ROOT)/$$*/$(1:.o=.d) -c $$< -o $$@
-
-endef # addTargetAsmObject
-
-define addTargetCObject  # targetName, addlDeps
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2)))) #debug print
-
-.PRECIOUS: $$(CACHE_ROOT)/%/$(1)
-$$(CACHE_ROOT)/%/$(1) : $(1:.o=.c) $(2) | $$(CACHE_ROOT)/%/.
-	@echo CC $$@
-	$$(CC) $$(CPPFLAGS) $$(CFLAGS) $$(DEPFLAGS) $$(CACHE_ROOT)/$$*/$(1:.o=.d) -c $$< -o $$@
-
-endef # addTargetCObject
-
-define addTargetCxxObject  # targetName, suffix, addlDeps
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2),$(3))))
-
-.PRECIOUS: $$(CACHE_ROOT)/%/$(1)
-$$(CACHE_ROOT)/%/$(1) : $(1:.o=.$(2)) $(3) | $$(CACHE_ROOT)/%/.
-	@echo CXX $$@
-	$$(CXX) $$(CPPFLAGS) $$(CXXFLAGS) $$(DEPFLAGS) $$(CACHE_ROOT)/$$*/$(1:.o=.d) -c $$< -o $$@
-
-endef # addTargetCxxObject
-
-# Create targets for individual object files
-C_SRCDIRS += .
-vpath %.c $(C_SRCDIRS)
-CXX_SRCDIRS += .
-vpath %.cpp $(CXX_SRCDIRS)
-vpath %.cc $(CXX_SRCDIRS)
-ASM_SRCDIRS += .
-vpath %.S $(ASM_SRCDIRS)
-
-# If C_SRCDIRS, CXX_SRCDIRS and ASM_SRCDIRS are not defined, use C_SRCS, CXX_SRCS and ASM_SRCS
-C_SRCS   ?= $(notdir $(foreach dir,$(C_SRCDIRS),$(wildcard $(dir)/*.c)))
-CPP_SRCS ?= $(notdir $(foreach dir,$(CXX_SRCDIRS),$(wildcard $(dir)/*.cpp)))
-CC_SRCS  ?= $(notdir $(foreach dir,$(CXX_SRCDIRS),$(wildcard $(dir)/*.cc)))
-CXX_SRCS ?= $(CPP_SRCS) $(CC_SRCS)
-ASM_SRCS ?= $(notdir $(foreach dir,$(ASM_SRCDIRS),$(wildcard $(dir)/*.S)))
-
-# If C_SRCS, CXX_SRCS and ASM_SRCS are not defined, use C_OBJS, CXX_OBJS and ASM_OBJS
-C_OBJS   ?= $(patsubst %.c,%.o,$(C_SRCS))
-CPP_OBJS ?= $(patsubst %.cpp,%.o,$(CPP_SRCS))
-CC_OBJS  ?= $(patsubst %.cc,%.o,$(CC_SRCS))
-CXX_OBJS ?= $(CPP_OBJS) $(CC_OBJS) # Note: not used
-ASM_OBJS ?= $(patsubst %.S,%.o,$(ASM_SRCS))
-
-$(foreach OBJ,$(C_OBJS),$(eval $(call addTargetCObject,$(OBJ))))
-$(foreach OBJ,$(CPP_OBJS),$(eval $(call addTargetCxxObject,$(OBJ),cpp)))
-$(foreach OBJ,$(CC_OBJS),$(eval $(call addTargetCxxObject,$(OBJ),cc)))
-$(foreach OBJ,$(ASM_OBJS),$(eval $(call addTargetAsmObject,$(OBJ))))
-
-# --------------------------------------------------------------------------------------------
-# The following macros are used to create targets in the user Makefile.
-# Binaries are built in the cache directory, and then symlinked to the current directory.
-# The cache directory is automatically derived from CACHE_ROOT and list of flags and compilers.
-
-
-# static_library - Create build rules for a static library with caching
-# Parameters:
-#   1. libName       - Library name (becomes output file and phony target)
-#   2. objectDeps    - Object file dependencies (will be built in cache path)
-# The following parameters are all optional:
-#   3. extraDeps     - Additional dependencies (no cache path prefix)
-#   4. postBuildCmds - Extra commands to run after AR
-#   5. extraHash     - Additional key to compute the unique cache path
-# Example:
-#   $(call static_library,libmath.a,vector.o matrix.o,$(CONFIG_H),strip $@,$(VERSION))
-define static_library  # libName, objectDeps, extraDeps, postBuildCmds, extraHash
-
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2),$(3),$(4),$(5))))
-MCM_ALL_BINS += $(1)
-
-$$(CACHE_ROOT)/%/$(1) : $$(addprefix $$(CACHE_ROOT)/%/,$(2)) $(3)
-	@echo AR $$@
-	$$(AR) $$(ARFLAGS) $$@ $$^
-	$(4)
-
-.PHONY: $(1)
-$(1) : ARFLAGS = rcs
-$(1) : $$(CACHE_ROOT)/$$(call HASH_FUNC,$(1),$(2) $$(CPPFLAGS) $$(CC) $$(CFLAGS) $$(CXX) $$(CXXFLAGS) $$(AR) $$(ARFLAGS) $(5))/$(1)
-	$$(LN) -sf $$< $$@
-
-endef # static_library
-
-
-# c_dynamic_library - Create build rules for a C dynamic/shared library with caching
-# Parameters:
-#   1. libName      - Library name (becomes output file and phony target)
-#   2. objectDeps   - Object file dependencies (will be built in cache path)
-# The following parameters are all optional:
-#   3. extraDeps    - Additional dependencies (no cache path prefix)
-#   4. postLinkCmds - Extra commands to run after linking
-#   5. extraHash    - Additional key to compute the unique cache path
-# Example:
-#   $(call c_dynamic_library,libmath.so,vector.o matrix.o,$(CONFIG_H),strip $@,$(VERSION))
-define c_dynamic_library  # libName, objectDeps, extraDeps, postLinkCmds, extraHash
-
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2),$(3),$(4),$(5))))
-MCM_ALL_BINS += $(1)
-
-$$(CACHE_ROOT)/%/$(1) : $$(addprefix $$(CACHE_ROOT)/%/,$(2)) $(3)
-	@echo LD $$@
-	$$(CC) $$(CPPFLAGS) $$(CFLAGS) $$(LDFLAGS) -shared -o $$@ $$^ $$(LDLIBS)
-	$(4)
-
-.PHONY: $(1)
-$(1) : CFLAGS += -fPIC
-$(1) : $$(CACHE_ROOT)/$$(call HASH_FUNC,$(1),$(2) $$(CPPFLAGS) $$(CC) $$(CFLAGS) $$(LDFLAGS) $$(LDLIBS) $(5))/$(1)
-	$$(LN) -sf $$< $$@
-
-endef # c_dynamic_library
-
-
-# program_base - Create build rules for an executable program with caching
-# Parameters:
-#   1. progName      - Executable name (becomes output file and phony target)
-#   2. objectDeps    - Object file dependencies (will be prefixed with cache path)
-# Parameters 3 to 5 are optional:
-#   3. extraDeps     - Additional dependencies (without cache path prefix)
-#   4. postLinkCmds  - Extra commands to run after linking
-#   5. extraHash     - Additional data to include in cache path hash
-# Parameters 6 & 7 are compulsory:
-#   6. compiler      - Variable name of compiler to use (CC or CXX)
-#   7. compilerFlags - Variable name of compiler flags to use (CFLAGS or CXXFLAGS)
-# Example:
-#   $(call program_base,myapp,main.o utils.o,$(CONFIG_H),strip $@,$(VERSION),CC,CFLAGS)
-#   $(call program_base,mycppapp,main.o utils.o,$(CONFIG_H),strip $@,$(VERSION),CXX,CXXFLAGS)
-define program_base  # progName, objectDeps, extraDeps, postLinkCmds, extraHash, compiler, compilerFlags
-
-$$(if $$(filter 2,$$(V)),$$(info $$(call $(0),$(1),$(2),$(3),$(4),$(5),$(6),$(7))))
-MCM_ALL_BINS += $(1)
-
-$$(CACHE_ROOT)/%/$(1) : $$(addprefix $$(CACHE_ROOT)/%/,$(2)) $(3)
-	@echo LD $$@
-	$$($(6)) $$(CPPFLAGS) $$($(7)) $$^ -o $$@ $$(LDFLAGS) $$(LDLIBS)
-	$(4)
-
-.PHONY: $(1)
-$(1) : $$(CACHE_ROOT)/$$(call HASH_FUNC,$(1),$$($(6)) $$(CPPFLAGS) $$($(7)) $$(LDFLAGS) $$(LDLIBS) $(5))/$(1)
-	$$(LN) -sf $$< $$@$(EXT)
-
-endef # program_base
-# Note: $(EXT) must be set to .exe for Windows
-
-define c_program  # progName, objectDeps, extraDeps, postLinkCmds
-$$(eval $$(call program_base,$(1),$(2),$(3),$(4),$(1)$(2),CC,CFLAGS))
-endef # c_program
-
-define c_program_shared_o  # progName, objectDeps, extraDeps, postLinkCmds
-$$(eval $$(call program_base,$(1),$(2),$(3),$(4),,CC,CFLAGS))
-endef # c_program_shared_o
-
-define cxx_program  # progName, objectDeps, extraDeps, postLinkCmds
-$$(eval $$(call program_base,$(1),$(2),$(3),$(4),$(1)$(2),CXX,CXXFLAGS))
-endef # cxx_program
-
-define cxx_program_shared_o  # progName, objectDeps, extraDeps, postLinkCmds
-$$(eval $$(call program_base,$(1),$(2),$(3),$(4),,CXX,CXXFLAGS))
-endef # cxx_program_shared_o
-
-# --------------------------------------------------------------------------------------------
-
-# Cleaning: delete all objects and binaries created by this script
-.PHONY: clean_cache
-clean_cache:
-	$(RM) -rf $(CACHE_ROOT)
-	$(RM) $(MCM_ALL_BINS)
-
-# automatically attach to standard clean target
-.PHONY: clean
-clean: clean_cache

deps/xxhash/xxhash.c

@@ -1,42 +0,0 @@
-/*
- * xxHash - Extremely Fast Hash algorithm
- * Copyright (C) 2012-2023 Yann Collet
- *
- * BSD 2-Clause License (https://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *    * Redistributions of source code must retain the above copyright
- *      notice, this list of conditions and the following disclaimer.
- *    * Redistributions in binary form must reproduce the above
- *      copyright notice, this list of conditions and the following disclaimer
- *      in the documentation and/or other materials provided with the
- *      distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You can contact the author at:
- *   - xxHash homepage: https://www.xxhash.com
- *   - xxHash source repository: https://github.com/Cyan4973/xxHash
- */
-
-/*
- * xxhash.c instantiates functions defined in xxhash.h
- */
-
-#define XXH_STATIC_LINKING_ONLY /* access advanced declarations */
-#define XXH_IMPLEMENTATION      /* access definitions */
-
-#include "xxhash.h"

hanzo/LLM.md

@@ -1,167 +0,0 @@
-# Hanzo Memory (Redis Fork)
-
-## Overview
-
-**Hanzo Memory** is a fork of Redis optimized for the Hanzo AI platform's caching and real-time needs. It provides:
-
-- **Session Storage** - User sessions, API keys
-- **Rate Limiting** - Token bucket, sliding window
-- **Real-time PubSub** - WebSocket notifications
-- **Caching Layer** - LLM responses, embeddings
-- **Queue Management** - Background job processing
-
-Repository: https://github.com/hanzoai/redis
-
-## Quick Start
-
-```bash
-# Start Redis with Hanzo config
-cd hanzo
-docker compose up -d
-
-# Connect to Redis
-docker exec -it hanzo-redis redis-cli
-
-# Test connection
-PING
-```
-
-## Hanzo Modules
-
-Pre-configured modules:
-- **RedisJSON** - Native JSON support
-- **RediSearch** - Full-text search
-- **RedisTimeSeries** - Time-series data
-- **RedisBloom** - Probabilistic data structures
-
-## Key Namespaces
-
-```
-hanzo:session:{session_id}     - User sessions
-hanzo:api_key:{key_hash}       - API key data
-hanzo:rate:{org_id}:{endpoint} - Rate limit counters
-hanzo:cache:llm:{hash}         - LLM response cache
-hanzo:cache:embed:{hash}       - Embedding cache
-hanzo:queue:{queue_name}       - Job queues
-hanzo:pubsub:{channel}         - Real-time channels
-```
-
-## Integration Points
-
-### With hanzo/console (LangFuse fork)
-
-Console uses Redis for caching:
-```env
-REDIS_URL=redis://localhost:6379
-```
-
-### With hanzo/llm (LiteLLM fork)
-
-LLM Gateway caches responses:
-```env
-REDIS_HOST=localhost
-REDIS_PORT=6379
-REDIS_PASSWORD=hanzo_dev
-```
-
-### With hanzo/iam (Casdoor fork)
-
-IAM uses for session storage:
-```env
-redisEndpoint=localhost:6379
-```
-
-## Syncing with Upstream
-
-```bash
-# Fetch upstream changes
-git fetch upstream
-
-# Merge upstream unstable
-git merge upstream/unstable
-
-# Keep hanzo/ directory
-git checkout --ours hanzo/
-
-git push origin unstable
-```
-
-## Performance Tuning
-
-### Memory Management
-
-```
-# redis.conf
-maxmemory 2gb
-maxmemory-policy allkeys-lru
-
-# Persistence
-save 900 1
-save 300 10
-save 60 10000
-appendonly yes
-appendfsync everysec
-```
-
-### Client Limits
-
-```
-# Connection limits
-maxclients 10000
-timeout 300
-
-# Slow log
-slowlog-log-slower-than 10000
-slowlog-max-len 128
-```
-
-## Docker Compose
-
-See `hanzo/compose.yml` for local development with:
-- Redis Stack (includes modules)
-- RedisInsight for management
-- Prometheus metrics export
-
-## Caching Patterns
-
-### LLM Response Caching
-
-```python
-# Cache key: sha256(model + prompt + params)
-cache_key = f"hanzo:cache:llm:{hash}"
-ttl = 3600  # 1 hour
-
-# Set with JSON
-redis.json().set(cache_key, "$", response)
-redis.expire(cache_key, ttl)
-```
-
-### Rate Limiting (Sliding Window)
-
-```python
-# Key: hanzo:rate:{org_id}:{endpoint}
-key = f"hanzo:rate:{org_id}:chat_completions"
-window_seconds = 60
-max_requests = 100
-
-# Lua script for atomic operation
-```
-
-### Session Storage
-
-```python
-# Key: hanzo:session:{session_id}
-session_key = f"hanzo:session:{session_id}"
-ttl = 86400  # 24 hours
-
-redis.json().set(session_key, "$", session_data)
-redis.expire(session_key, ttl)
-```
-
-## Related Repositories
-
-- **hanzo/console** - AI observability (caching)
-- **hanzo/llm** - LLM Gateway (response cache)
-- **hanzo/iam** - Identity management (sessions)
-- **hanzo/datastore** - ClickHouse fork (OLAP)
-- **hanzo/relational** - PostgreSQL fork (OLTP)

hanzo/compose.yml

@@ -1,42 +0,0 @@
-services:
-  redis:
-    image: redis/redis-stack:latest
-    container_name: hanzo-redis
-    ports:
-      - "6379:6379"   # Redis
-      - "8001:8001"   # RedisInsight
-    volumes:
-      - redis-data:/data
-      - ./redis.conf:/usr/local/etc/redis/redis.conf:ro
-    environment:
-      REDIS_ARGS: "--requirepass ${REDIS_PASSWORD:-hanzo_dev}"
-    healthcheck:
-      test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD:-hanzo_dev}", "ping"]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-    restart: unless-stopped
-    command: >
-      redis-stack-server
-      --appendonly yes
-      --maxmemory 2gb
-      --maxmemory-policy allkeys-lru
-
-  exporter:
-    image: oliver006/redis_exporter:latest
-    container_name: hanzo-redis-exporter
-    ports:
-      - "9121:9121"
-    environment:
-      REDIS_ADDR: redis://redis:6379
-      REDIS_PASSWORD: ${REDIS_PASSWORD:-hanzo_dev}
-    depends_on:
-      - redis
-    restart: unless-stopped
-
-volumes:
-  redis-data:
-
-networks:
-  default:
-    name: hanzo-memory

hanzo/redis.conf

@@ -1,68 +0,0 @@
-# Hanzo Memory - Redis Configuration
-
-# Network
-bind 0.0.0.0
-port 6379
-tcp-backlog 511
-timeout 300
-tcp-keepalive 300
-
-# Memory
-maxmemory 2gb
-maxmemory-policy allkeys-lru
-maxmemory-samples 5
-
-# Persistence
-save 900 1
-save 300 10
-save 60 10000
-stop-writes-on-bgsave-error yes
-rdbcompression yes
-rdbchecksum yes
-dbfilename dump.rdb
-
-# Append-only file
-appendonly yes
-appendfilename "appendonly.aof"
-appendfsync everysec
-no-appendfsync-on-rewrite no
-auto-aof-rewrite-percentage 100
-auto-aof-rewrite-min-size 64mb
-
-# Logging
-loglevel notice
-logfile ""
-
-# Clients
-maxclients 10000
-
-# Slow log
-slowlog-log-slower-than 10000
-slowlog-max-len 128
-
-# Event notifications (for pub/sub)
-notify-keyspace-events "Ex"
-
-# Lua scripting
-lua-time-limit 5000
-
-# Latency monitoring
-latency-monitor-threshold 100
-
-# Active defragmentation
-activedefrag yes
-active-defrag-ignore-bytes 100mb
-active-defrag-threshold-lower 10
-active-defrag-threshold-upper 100
-active-defrag-cycle-min 1
-active-defrag-cycle-max 25
-
-# Thread I/O
-io-threads 4
-io-threads-do-reads yes
-
-# Module loading (redis-stack includes these)
-# loadmodule /opt/redis-stack/lib/rejson.so
-# loadmodule /opt/redis-stack/lib/redisearch.so
-# loadmodule /opt/redis-stack/lib/redistimeseries.so
-# loadmodule /opt/redis-stack/lib/redisbloom.so

modules/Makefile

@@ -11,7 +11,7 @@ all: prepare_source
 get_source:
 	$(call submake,$@)
 
-prepare_source: get_source setup_environment
+prepare_source: get_source handle-werrors setup_environment
 
 clean:
 	$(call submake,$@)
@@ -25,14 +25,14 @@ pristine:
 install:
 	$(call submake,$@)
 
-setup_environment: install-rust
+setup_environment: install-rust handle-werrors
 
 clean_environment: uninstall-rust
 
 # Keep all of the Rust stuff in one place
 install-rust:
 ifeq ($(INSTALL_RUST_TOOLCHAIN),yes)
-	@RUST_VERSION=1.94.0; \
+	@RUST_VERSION=1.80.1; \
 	ARCH="$$(uname -m)"; \
 	if ldd --version 2>&1 | grep -q musl; then LIBC_TYPE="musl"; else LIBC_TYPE="gnu"; fi; \
 	echo "Detected architecture: $${ARCH} and libc: $${LIBC_TYPE}"; \
@@ -40,24 +40,24 @@ ifeq ($(INSTALL_RUST_TOOLCHAIN),yes)
 		'x86_64') \
 			if [ "$${LIBC_TYPE}" = "musl" ]; then \
 				RUST_INSTALLER="rust-$${RUST_VERSION}-x86_64-unknown-linux-musl"; \
-				RUST_SHA256="9a358120ce1491a4d5b7f71a41e4e97b380b5db5d4ec31f7110f5b3090bd3d55"; \
+				RUST_SHA256="37bbec6a7b9f55fef79c451260766d281a7a5b9d2e65c348bbc241127cf34c8d"; \
 			else \
 				RUST_INSTALLER="rust-$${RUST_VERSION}-x86_64-unknown-linux-gnu"; \
-				RUST_SHA256="e8fa4185f3ef6ae32725ff638b1ecdbff28f5d651dc0b3111e2539350d03b15a"; \
+				RUST_SHA256="85e936d5d36970afb80756fa122edcc99bd72a88155f6bdd514f5d27e778e00a"; \
 			fi ;; \
 		'aarch64') \
 			if [ "$${LIBC_TYPE}" = "musl" ]; then \
 				RUST_INSTALLER="rust-$${RUST_VERSION}-aarch64-unknown-linux-musl"; \
-				RUST_SHA256="008b3f0fc4175c956ecbfa4e0c48865ec3f953741b2926e75e8ded7e3adfdb19"; \
+				RUST_SHA256="dd668c2d82f77c5458deb023932600fae633fff8d7f876330e01bc47e9976d17"; \
 			else \
 				RUST_INSTALLER="rust-$${RUST_VERSION}-aarch64-unknown-linux-gnu"; \
-				RUST_SHA256="c6fd6d1c925ed986df3b2c0b89bbc90ce15afb62e4d522a054e7d50c856b3c1a"; \
+				RUST_SHA256="2e89bad7857711a1c11d017ea28fbfeec54076317763901194f8f5decbac1850"; \
 			fi ;; \
 		*) echo >&2 "Unsupported architecture: '$${ARCH}'"; exit 1 ;; \
 	esac; \
 	echo "Downloading and installing Rust standalone installer: $${RUST_INSTALLER}"; \
 	wget --quiet -O $${RUST_INSTALLER}.tar.xz https://static.rust-lang.org/dist/$${RUST_INSTALLER}.tar.xz; \
-	echo "$${RUST_SHA256} $${RUST_INSTALLER}.tar.xz" | sha256sum -c --status || { echo "Rust standalone installer checksum failed!"; exit 1; }; \
+	echo "$${RUST_SHA256} $${RUST_INSTALLER}.tar.xz" | sha256sum -c --quiet || { echo "Rust standalone installer checksum failed!"; exit 1; }; \
 	tar -xf $${RUST_INSTALLER}.tar.xz; \
 	(cd $${RUST_INSTALLER} && ./install.sh); \
 	rm -rf $${RUST_INSTALLER}
@@ -74,4 +74,17 @@ ifeq ($(INSTALL_RUST_TOOLCHAIN),yes)
 	fi
 endif
 
-.PHONY: all clean distclean install $(SUBDIRS) setup_environment clean_environment install-rust uninstall-rust
+handle-werrors: get_source
+ifeq ($(DISABLE_WERRORS),yes)
+	@echo "Disabling -Werror for all modules"
+	@for dir in $(SUBDIRS); do \
+		echo "Processing $$dir"; \
+		find $$dir/src -type f \
+			\( -name "Makefile" \
+			-o -name "*.mk" \
+			-o -name "CMakeLists.txt" \) \
+			-exec sed -i 's/-Werror//g' {} +; \
+	done
+endif
+
+.PHONY: all clean distclean install $(SUBDIRS) setup_environment clean_environment install-rust uninstall-rust handle-werrors

modules/common.mk

@@ -25,7 +25,6 @@ all: $(TARGET_MODULE)
 
 $(TARGET_MODULE): get_source
 	$(MAKE) -C $(SRC_DIR)
-	cp ${TARGET_MODULE} ./
 
 get_source: $(SRC_DIR)/.prepared
 
@@ -36,9 +35,8 @@ $(SRC_DIR)/.prepared:
 
 clean:
 	-$(MAKE) -C $(SRC_DIR) clean
-	-rm -f ./*.so
 
-distclean: clean
+distclean:
 	-$(MAKE) -C $(SRC_DIR) distclean
 
 pristine:

modules/redisbloom/Makefile

@@ -1,5 +1,5 @@
 SRC_DIR = src
-MODULE_VERSION = v8.8.0
+MODULE_VERSION = v7.99.1
 MODULE_REPO = https://github.com/redisbloom/redisbloom
 TARGET_MODULE = $(SRC_DIR)/bin/$(FULL_VARIANT)/redisbloom.so
 

modules/redisearch/Makefile

@@ -1,20 +1,7 @@
 SRC_DIR = src
-MODULE_VERSION = v8.8.0
+MODULE_VERSION = v7.99.1
 MODULE_REPO = https://github.com/redisearch/redisearch
 TARGET_MODULE = $(SRC_DIR)/bin/$(FULL_VARIANT)/search-community/redisearch.so
 
-# Enable link-time optimization for RediSearch by default. Override with LTO=0.
-LTO ?= 1
-export LTO
-
-# Use the committed C headers for Rust modules, rather than regenerating them
-# from Rust source. Override with REDISEARCH_GENERATE_HEADERS=1.
-REDISEARCH_GENERATE_HEADERS ?= 0
-export REDISEARCH_GENERATE_HEADERS
-
-  # Set INLINE_LSE_ATOMICS=1 for perf improvement on common ARM CPUs (i.e. Graviton2/3/4); no effect on x86 or macOS.
-  # Default 0 keeps the binary runnable on pre-Armv8.1-a cores (Cortex-A72, Graviton1, RPi4) that would otherwise SIGILL at module load.
-INLINE_LSE_ATOMICS ?= 0
-export INLINE_LSE_ATOMICS
-
 include ../common.mk
+

modules/redisjson/Makefile

@@ -1,5 +1,5 @@
 SRC_DIR = src
-MODULE_VERSION = v8.8.0
+MODULE_VERSION = v7.99.1
 MODULE_REPO = https://github.com/redisjson/redisjson
 TARGET_MODULE = $(SRC_DIR)/bin/$(FULL_VARIANT)/rejson.so
 

modules/redistimeseries/Makefile

@@ -1,5 +1,5 @@
 SRC_DIR = src
-MODULE_VERSION = v8.8.0
+MODULE_VERSION = v7.99.1
 MODULE_REPO = https://github.com/redistimeseries/redistimeseries
 TARGET_MODULE = $(SRC_DIR)/bin/$(FULL_VARIANT)/redistimeseries.so
 

modules/vector-sets/.gitignore

@@ -1,11 +0,0 @@
-__pycache__
-misc
-*.so
-*.xo
-*.o
-.DS_Store
-w2v
-word2vec.bin
-TODO
-*.txt
-*.rdb

modules/vector-sets/Makefile

@@ -1,87 +0,0 @@
-# Compiler settings
-CC = cc
-
-ifdef SANITIZER
-ifeq ($(SANITIZER),address)
-	SAN=-fsanitize=address
-else
-ifeq ($(SANITIZER),undefined)
-	SAN=-fsanitize=undefined
-else
-ifeq ($(SANITIZER),thread)
-	SAN=-fsanitize=thread
-else
-    $(error "unknown sanitizer=${SANITIZER}")
-endif
-endif
-endif
-endif
-
-CFLAGS = -O2 -Wall -Wextra -g $(SAN) -std=c11
-LDFLAGS = -lm $(SAN)
-
-# Detect OS
-uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
-uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
-
-# Shared library compile flags for linux / osx
-ifeq ($(uname_S),Linux)
-	SHOBJ_CFLAGS ?= -W -Wall -fno-common -g -ggdb -std=c11 -O2
-	SHOBJ_LDFLAGS ?= -shared
-ifneq (,$(findstring armv,$(uname_M)))
-	SHOBJ_LDFLAGS += -latomic
-endif
-ifneq (,$(findstring aarch64,$(uname_M)))
-	SHOBJ_LDFLAGS += -latomic
-endif
-else
-	SHOBJ_CFLAGS ?= -W -Wall -dynamic -fno-common -g -ggdb -std=c11 -O3
-	SHOBJ_LDFLAGS ?= -bundle -undefined dynamic_lookup
-endif
-
-# OS X 11.x doesn't have /usr/lib/libSystem.dylib and needs an explicit setting.
-ifeq ($(uname_S),Darwin)
-ifeq ("$(wildcard /usr/lib/libSystem.dylib)","")
-LIBS = -L /Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/usr/lib -lsystem
-endif
-endif
-
-.SUFFIXES: .c .so .xo .o
-
-all: vset.so
-
-.c.xo:
-	$(CC) -I. $(CFLAGS) $(SHOBJ_CFLAGS) -fPIC -c $< -o $@
-
-vset.xo: ../../src/redismodule.h expr.c
-
-vset.so: vset.xo hnsw.xo vset_config.xo
-	$(CC) -o $@ $^ $(SHOBJ_LDFLAGS) $(LIBS) $(SAN) -lc
-
-# Example sources / objects
-SRCS = hnsw.c w2v.c vset_config.c
-OBJS = $(SRCS:.c=.o)
-
-TARGET = w2v
-MODULE = vset.so
-
-# Default target
-all: $(TARGET) $(MODULE)
-
-# Example linking rule
-$(TARGET): $(OBJS)
-	$(CC) $(OBJS) $(LDFLAGS) -o $(TARGET)
-
-# Compilation rule for object files
-%.o: %.c
-	$(CC) $(CFLAGS) -c $< -o $@
-
-expr-test: expr.c fastjson.c fastjson_test.c
-	$(CC) $(CFLAGS) expr.c -o expr-test -DTEST_MAIN -lm
-
-# Clean rule
-clean:
-	rm -f $(TARGET) $(OBJS) *.xo *.so
-
-# Declare phony targets
-.PHONY: all clean

modules/vector-sets/README.md

@@ -1,733 +0,0 @@
-**IMPORTANT:** *Please note that this is a merged module, it's part of the Redis binary now, and you don't need to build it and load it into Redis. Compiling Redis version 8 or greater will result into having the Vector Sets commands available. However, you could compile this module as a shared library in order to load it in older versions of Redis.*
-
-This module implements Vector Sets for Redis, a new Redis data type similar
-to Sorted Sets but having string elements associated to a vector instead of
-a score. The fundamental goal of Vector Sets is to make possible adding items,
-and later get a subset of the added items that are the most similar to a
-specified vector (often a learned embedding), or the most similar to the vector
-of an element that is already part of the Vector Set.
-
-Moreover, Vector sets implement optional filtered search capabilities: it is possible to associate attributes to all or to a subset of elements in the set, and then, using the `FILTER` option of the `VSIM` command, to ask for items similar to a given vector but also passing a filter specified as a simple mathematical expression (Like `".year > 1950"` or similar). This means that **you can have vector similarity and scalar filters at the same time**.
-
-## Installation
-
-**WARNING:** If you are running **Redis 8.0 RC1 or greater** you don't need to install anything, just compile Redis, and the Vector Sets commands will be part of the default install. Otherwise to test Vector Sets with older Redis versions follow the following instructions.
-
-Build with:
-
-    make
-
-Then load the module with the following command line, or by inserting the needed directives in the `redis.conf` file.
-
-    ./redis-server --loadmodule vset.so
-
-To run tests, I suggest using this:
-
-    ./redis-server --save "" --enable-debug-command yes
-
-The execute the tests with:
-
-    ./test.py
-
-## Reference of available commands
-
-**VADD: add items into a vector set**
-
-    VADD key [REDUCE dim] FP32|VALUES vector element [CAS] [NOQUANT | Q8 | BIN]
-             [EF build-exploration-factor] [SETATTR <attributes>] [M <numlinks>]
-
-Add a new element into the vector set specified by the key.
-The vector can be provided as FP32 blob of values, or as floating point
-numbers as strings, prefixed by the number of elements (3 in the example):
-
-    VADD mykey VALUES 3 0.1 1.2 0.5 my-element
-
-Meaning of the options:
-
-`REDUCE` implements random projection, in order to reduce the
-dimensionality of the vector. The projection matrix is saved and reloaded
-along with the vector set. **Please note that** the `REDUCE` option must be passed immediately before the vector, like in `REDUCE 50 VALUES ...`.
-
-`CAS` performs the operation partially using threads, in a
-check-and-set style. The neighbor candidates collection, which is slow, is
-performed in the background, while the command is executed in the main thread.
-
-`NOQUANT` forces the vector to be created (in the first VADD call to a given key) without integer 8 quantization, which is otherwise the default.
-
-`BIN` forces the vector to use binary quantization instead of int8. This is much faster and uses less memory, but has impacts on the recall quality. The distance is computed as normalized Hamming distance (`hamming_bits * 2 / dim`), yielding values in [0, 2] consistent with cosine distance semantics, not raw Hamming bit counts.
-
-`Q8` forces the vector to use signed 8 bit quantization. This is the default, and the option only exists in order to make sure to check at insertion time if the vector set is of the same format.
-
-`EF` plays a role in the effort made to find good candidates when connecting the new node to the existing HNSW graph. The default is 200. Using a larger value, may help to have a better recall. To improve the recall it is also possible to increase `EF` during `VSIM` searches.
-
-`SETATTR` associates attributes to the newly created entry or update the entry attributes (if it already exists). It is the same as calling the `VSETATTR` attribute separately, so please check the documentation of that command in the filtered search section of this documentation.
-
-`M` defaults to 16 and is the HNSW famous `M` parameters. It is the maximum number of connections that each node of the graph have with other nodes: more connections mean more memory, but a better ability to explore the graph. Nodes at layer zero (every node exists at least at layer zero) have `M*2` connections, while the other layers only have `M` connections. This means that, for instance, an `M` of 64 will use at least 1024 bytes of memory for each node! That is, `64 links * 2 times * 8 bytes pointers`, and even more, since on average each node has something like 1.33 layers (but the other layers have just `M` connections, instead of `M*2`). If you don't have a recall quality problem, the default is fine, and uses a limited amount of memory.
-
-**VSIM: return elements by vector similarity**
-
-    VSIM key [ELE|FP32|VALUES] <vector or element> [WITHSCORES] [WITHATTRIBS] [COUNT num] [EPSILON delta] [EF search-exploration-factor] [FILTER expression] [FILTER-EF max-filtering-effort] [TRUTH] [NOTHREAD]
-
-The command returns similar vectors, for simplicity (and verbosity) in the following example, instead of providing a vector using FP32 or VALUES (like in `VADD`), we will ask for elements having a vector similar to a given element already in the sorted set:
-
-    > VSIM word_embeddings ELE apple
-     1) "apple"
-     2) "apples"
-     3) "pear"
-     4) "fruit"
-     5) "berry"
-     6) "pears"
-     7) "strawberry"
-     8) "peach"
-     9) "potato"
-    10) "grape"
-
-It is possible to specify a `COUNT` and also to get the similarity score (from 1 to 0, where 1 is identical, 0 is opposite vector) between the query and the returned items.
-
-    > VSIM word_embeddings ELE apple WITHSCORES COUNT 3
-    1) "apple"
-    2) "0.9998867657923256"
-    3) "apples"
-    4) "0.8598527610301971"
-    5) "pear"
-    6) "0.8226882219314575"
-
-It is also possible to specify a `EPSILON`, that is a floating point number between 0 and 1 in order to only return elements that have a distance that is no further than the specified one. In vector sets, the returned elements have a similarity score (when compared to the query vector) that is between 1 and 0, where 1 means identical, 0 opposite vectors. If for instance the `EPSILON` option is specified with an argument of 0.2, it means that we will get only elements that have a similarity of 0.8 or better (a distance < 0.2). This is useful when a large `COUNT` is specified, yet we don't want elements that are too far away our query vector.
-
-The `EF` argument is the exploration factor: the higher it is, the slower the command becomes, but the better the index is explored to find nodes that are near to our query. Sensible values are from 50 to 1000.
-
-The `TRUTH` option forces the command to perform a linear scan of all the entries inside the set, without using the graph search inside the HNSW, so it returns the best matching elements (the perfect result set) that can be used in order to easily calculate the recall. Of course the linear scan is `O(N)`, so it is much slower than the `log(N)` (considering a small `COUNT`) provided by the HNSW index.
-
-The `NOTHREAD` option forces the command to execute the search on the data structure in the main thread. Normally `VSIM` spawns a thread instead. This may be useful for benchmarking purposes, or when we work with extremely small vector sets and don't want to pay the cost of spawning a thread. It is possible that in the future this option will be automatically used by Redis when we detect small vector sets. Note that this option blocks the server for all the time needed to complete the command, so it is a source of potential latency issues: if you are in doubt, never use it.
-
-The `WITHSCORES` option returns, for each returned element, a floating point number representing how near the element is from the query, as a similarity between 0 and 1, where 0 means the vectors are opposite, and 1 means they are pointing exactly in the same direction (maximum similarity).
-
-The `WITHATTRIBS` option returns, for each element, the JSON attribute associated with the element, or NULL for the elements missing an attribute.
-
-For `FILTER` and `FILTER-EF` options, please check the filtered search section of this documentation.
-
-Note that when `WITHSCORES` and `WITHATTRIBS` are provided at the same time, the RESP2 reply guarantees that the returned elements are always in the sequence *ele*,*score*,*attribs*, while RESP3 replies will be in the form *ele > score|attrib* when just one is provided, or *ele -> [score,attrib]* when both are provided, that is, when both options are used and RESP3 is used the score and attribute will be a two-items array associated to the element key.
-
-**VDIM: return the dimension of the vectors inside the vector set**
-
-    VDIM keyname
-
-Example:
-
-    > VDIM word_embeddings
-    (integer) 300
-
-Note that in the case of vectors that were populated using the `REDUCE`
-option, for random projection, the vector set will report the size of
-the projected (reduced) dimension. Yet the user should perform all the
-queries using full-size vectors.
-
-**VCARD: return the number of elements in a vector set**
-
-    VCARD key
-
-Example:
-
-    > VCARD word_embeddings
-    (integer) 3000000
-
-
-**VREM: remove elements from vector set**
-
-    VREM key element
-
-Example:
-
-    > VADD vset VALUES 3 1 0 1 bar
-    (integer) 1
-    > VREM vset bar
-    (integer) 1
-    > VREM vset bar
-    (integer) 0
-
-VREM does not perform thumstone / logical deletion, but will actually reclaim
-the memory from the vector set, so it is save to add and remove elements
-in a vector set in the context of long running applications that continuously
-update the same index.
-
-**VEMB: return the approximated vector of an element**
-
-    VEMB key element
-
-Example:
-
-    > VEMB word_embeddings SQL
-      1) "0.18208661675453186"
-      2) "0.08535309880971909"
-      3) "0.1365649551153183"
-      4) "-0.16501599550247192"
-      5) "0.14225517213344574"
-      ... 295 more elements ...
-
-Because vector sets perform insertion time normalization and optional
-quantization, the returned vector could be approximated. `VEMB` will take
-care to de-quantized and de-normalize the vector before returning it.
-
-It is possible to ask VEMB to return raw data, that is, the internal representation used by the vector: fp32, int8, or a bitmap for binary quantization. This behavior is triggered by the `RAW` option of of VEMB:
-
-    VEMB word_embedding apple RAW
-
-In this case the return value of the command is an array of three or more elements:
-1. The name of the quantization used, that is one of: "fp32", "bin", "q8".
-2. The a string blob containing the raw data, 4 bytes fp32 floats for fp32, a bitmap for binary quants, or int8 bytes array for q8 quants.
-3. A float representing the l2 of the vector before normalization. You need to multiply by this vector if you want to de-normalize the value for any reason.
-
-For q8 quantization, an additional elements is also returned: the quantization
-range, so the integers from -127 to 127 represent (normalized) components
-in the range `-range`, `+range`.
-
-**VISMEMBER: test if a given element already exists**
-
-This command will return 1 (or true) if the specified element is already in the vector set, otherwise 0 (or false) is returned.
-
-    VISMEMBER key element
-
-As with other existence check Redis commands, if the key does not exist it is considered as if it was empty, thus the element is reported as non existing.
-
-**VRANGE: return elements in a lexicographical range
-
-    VRANGE key start end count
-
-The `VRANGE` command has many different use cases, but its main goal is to
-provide a stateless iterator for the elements inside a vector set: that is,
-it allows to retrieve all the elements inside a vector set in small amounts
-for each call, without an explicit cursor, and with guarantees about what
-the user will miss in case the vector set is changing (elements added and/or
-removed) during the iteration.
-
-The command usage is straightforward:
-
-```
-> VRANGE word_embeddings_int8 [Redis + 10
- 1) "Redis"
- 2) "Rediscover"
- 3) "Rediscover_Ashland"
- 4) "Rediscover_Northern_Ireland"
- 5) "Rediscovered"
- 6) "Rediscovered_Bookshop"
- 7) "Rediscovering"
- 8) "Rediscovering_God"
- 9) "Rediscovering_Lost"
-10) "Rediscovers"
-```
-
-The above command returns 10 (or less, if less are available in the specified range) elements from "Redis" (inclusive) to the maximum possible element. The comparison is performed byte by byte, as `memcmp()` would do, in this way the elements have a total order. The start and end range can be either a string, prefixed by `[` or `(` (the prefix is mandatory) to tell the command if the range is inclusive or exclusive, or can be the special symbols `-` and `+` that means the maximum and minimum element.
-
-So for instance if I want to iterate all the elements, ten elements for each call, I'll proceed as such:
-
-```
-> VRANGE mykey - + 10
- 1) "a"
- 2) "a-league"
- 3) "a."
- 4) "a.d."
- 5) "a.k.a."
- 6) "a.m."
- 7) "a1"
- 8) "a2"
- 9) "a3"
-10) "a7"
-```
-
-This will give me the first 10 elements. Then I want the next ten elements
-starting from the last element in the previous result, but *excluding* it,
-so the next range will use the `(` prefix with the last element of the
-previous call, that was `"a7"`:
-
-```
-> VRANGE mykey (a7 + 10
- 1) "a930913"
- 2) "aa"
- 3) "aaa"
- 4) "aaron"
- 5) "ab"
- 6) "aba"
- 7) "abandon"
- 8) "abandoned"
- 9) "abandoning"
-10) "abandonment"
-```
-
-And so forth.
-
-The command count is mandatory, however a negative count means to return all the elements in the set. This means that `VRANGE mykey - + -1` will return every element. Of course, iterating like that means that it is possible to block the server for a long time.
-
-The command time complexity is O(1) to seek to the element (considering the element would be of reasonable size), since we use a Radix Tree in the underlying implementation, plus the time to yield "M" elements. So if M is small, each call is just executed in constant time. However the iteration of a total set (via multiple calls) of N elements is O(N). Basically: this command, with a small count, will never produce latency issues in the Redis server.
-
-In case the elements are changing continuously as the set is iterated, the guarantees are very simple: each range will produce exactly the elements that were present in the range in the moment the `VRANGE` command was executed. In other words, an iteration performed in this way is *guaranteed* to return all the elements that stayed within the vector set from the start to the end of the iteration. Elements removed or added in the meantime may be returned or not depending on the moment they were added or removed.
-
-**VLINKS: introspection command that shows neighbors for a node**
-
-    VLINKS key element [WITHSCORES]
-
-The command reports the neighbors for each level.
-
-**VINFO: introspection command that shows info about a vector set**
-
-    VINFO key
-
-Example:
-
-    > VINFO word_embeddings
-     1) quant-type
-     2) int8
-     3) vector-dim
-     4) (integer) 300
-     5) size
-     6) (integer) 3000000
-     7) max-level
-     8) (integer) 12
-     9) vset-uid
-    10) (integer) 1
-    11) hnsw-max-node-uid
-    12) (integer) 3000000
-
-**VSETATTR: associate or remove the JSON attributes of elements**
-
-    VSETATTR key element "{... json ...}"
-
-Each element of a vector set can be optionally associated with a JSON string
-in order to use the `FILTER` option of `VSIM` to filter elements by scalars
-(see the filtered search section for more information). This command can set,
-update (if already set) or delete (if you set to an empty string) the
-associated JSON attributes of an element.
-
-The command returns 0 if the element or the key don't exist, without
-raising an error, otherwise 1 is returned, and the element attributes
-are set or updated.
-
-**VGETATTR: retrieve the JSON attributes of elements**
-
-    VGETATTR key element
-
-The command returns the JSON attribute associated with an element, or
-null if there is no element associated, or no element at all, or no key.
-
-**VRANDMEMBER: return random members from a vector set**
-
-    VRANDMEMBER key [count]
-
-Return one or more random elements from a vector set.
-
-The semantics of this command are similar to Redis's native SRANDMEMBER command:
-
-- When called without count, returns a single random element from the set, as a single string (no array reply).
-- When called with a positive count, returns up to count distinct random elements (no duplicates).
-- When called with a negative count, returns count random elements, potentially with duplicates.
-- If the count value is larger than the set size (and positive), only the entire set is returned.
-
-If the key doesn't exist, returns a Null reply if count is not given, or an empty array if a count is provided.
-
-Examples:
-
-    > VADD vset VALUES 3 1 0 0 elem1
-    (integer) 1
-    > VADD vset VALUES 3 0 1 0 elem2
-    (integer) 1
-    > VADD vset VALUES 3 0 0 1 elem3
-    (integer) 1
-
-    # Return a single random element
-    > VRANDMEMBER vset
-    "elem2"
-
-    # Return 2 distinct random elements
-    > VRANDMEMBER vset 2
-    1) "elem1"
-    2) "elem3"
-
-    # Return 3 random elements with possible duplicates
-    > VRANDMEMBER vset -3
-    1) "elem2"
-    2) "elem2"
-    3) "elem1"
-
-    # Return more elements than in the set (returns all elements)
-    > VRANDMEMBER vset 10
-    1) "elem1"
-    2) "elem2"
-    3) "elem3"
-
-    # When key doesn't exist
-    > VRANDMEMBER nonexistent
-    (nil)
-    > VRANDMEMBER nonexistent 3
-    (empty array)
-
-This command is particularly useful for:
-
-1. Selecting random samples from a vector set for testing or training.
-2. Performance testing by retrieving random elements for subsequent similarity searches.
-
-When the user asks for unique elements (positev count) the implementation optimizes for two scenarios:
-- For small sample sizes (less than 20% of the set size), it uses a dictionary to avoid duplicates, and performs a real random walk inside the graph.
-- For large sample sizes (more than 20% of the set size), it starts from a random node and sequentially traverses the internal list, providing faster performances but not really "random" elements.
-
-The command has `O(N)` worst-case time complexity when requesting many unique elements (it uses linear scanning), or `O(M*log(N))` complexity when the users asks for `M` random elements in a sorted set of `N` elements, with `M` much smaller than `N`.
-
-# Filtered search
-
-Each element of the vector set can be associated with a set of attributes specified as a JSON blob:
-
-    > VADD vset VALUES 3 1 1 1 a SETATTR '{"year": 1950}'
-    (integer) 1
-    > VADD vset VALUES 3 -1 -1 -1 b SETATTR '{"year": 1951}'
-    (integer) 1
-
-Specifying an attribute with the `SETATTR` option of `VADD` is exactly equivalent to adding an element and then setting (or updating, if already set) the attributes JSON string. Also the symmetrical `VGETATTR` command returns the attribute associated to a given element.
-
-    > VADD vset VALUES 3 0 1 0 c
-    (integer) 1
-    > VSETATTR vset c '{"year": 1952}'
-    (integer) 1
-    > VGETATTR vset c
-    "{\"year\": 1952}"
-
-At this point, I may use the FILTER option of VSIM to only ask for the subset of elements that are verified by my expression:
-
-    > VSIM vset VALUES 3 0 0 0 FILTER '.year > 1950'
-    1) "c"
-    2) "b"
-
-The items will be returned again in order of similarity (most similar first), but only the items with the year field matching the expression is returned.
-
-The expressions are similar to what you would write inside the `if` statement of JavaScript or other familiar programming languages: you can use `and`, `or`, the obvious math operators like `+`, `-`, `/`, `>=`, `<`, ... and so forth (see the expressions section for more info). The selectors of the JSON object attributes start with a dot followed by the name of the key inside the JSON objects.
-
-Elements with invalid JSON or not having a given specified field **are considered as not matching** the expression, but will not generate any error at runtime.
-
-## FILTER expressions capabilities
-
-FILTER expressions allow you to perform complex filtering on vector similarity results using a JavaScript-like syntax. The expression is evaluated against each element's JSON attributes, with only elements that satisfy the expression being included in the results.
-
-### Expression Syntax
-
-Expressions support the following operators and capabilities:
-
-1. **Arithmetic operators**: `+`, `-`, `*`, `/`, `%` (modulo), `**` (exponentiation)
-2. **Comparison operators**: `>`, `>=`, `<`, `<=`, `==`, `!=`
-3. **Logical operators**: `and`/`&&`, `or`/`||`, `!`/`not`
-4. **Containment operator**: `in`
-5. **Parentheses** for grouping: `(...)`
-
-### Selector Notation
-
-Attributes are accessed using dot notation:
-
-- `.year` references the "year" attribute
-- `.movie.year` would **NOT** reference the "year" field inside a "movie" object, only keys that are at the first level of the JSON object are accessible.
-
-### JSON and expressions data types
-
-Expressions can work with:
-
-- Numbers (dobule precision floats)
-- Strings (enclosed in single or double quotes)
-- Booleans (no native type: they are represented as 1 for true, 0 for false)
-- Arrays (for use with the `in` operator: `value in [1, 2, 3]`)
-
-JSON attributes are converted in this way:
-
-- Numbers will be converted to numbers.
-- Strings to strings.
-- Booleans to 0 or 1 number.
-- Arrays to tuples (for "in" operator), but only if composed of just numbers and strings.
-
-Any other type is ignored, and accessig it will make the expression evaluate to false.
-
-### The IN operator
-
-The `IN` operator works in two ways, it can test for membership in an array, like in:
-
-    5 in [1, 2, 3]
-    "foo" in [1, "foo", "bar"]
-
-But can also check for substrings, in case the A and B operators are both strings.
-
-    "foo" in "barfoobar" # Will evaluate to true
-    "zap" in "foobar" # Will evaluate to false
-
-### Examples
-
-```
-# Find items from the 1980s
-VSIM movies VALUES 3 0.5 0.8 0.2 FILTER '.year >= 1980 and .year < 1990'
-
-# Find action movies with high ratings
-VSIM movies VALUES 3 0.5 0.8 0.2 FILTER '.genre == "action" and .rating > 8.0'
-
-# Find movies directed by either Spielberg or Nolan
-VSIM movies VALUES 3 0.5 0.8 0.2 FILTER '.director in ["Spielberg", "Nolan"]'
-
-# Complex condition with numerical operations
-VSIM movies VALUES 3 0.5 0.8 0.2 FILTER '(.year - 2000) ** 2 < 100 and .rating / 2 > 4'
-```
-
-### Error Handling
-
-Elements with any of the following conditions are considered not matching:
-- Missing the queried JSON attribute
-- Having invalid JSON in their attributes
-- Having a JSON value that cannot be converted to the expected type
-
-This behavior allows you to safely filter on optional attributes without generating errors.
-
-### FILTER effort
-
-The `FILTER-EF` option controls the maximum effort spent when filtering vector search results.
-
-When performing vector similarity search with filtering, Vector Sets perform the standard similarity search as they apply the filter expression to each node. Since many results might be filtered out, Vector Sets may need to examine a lot more candidates than the requested `COUNT` to ensure sufficient matching results are returned. Actually, if the elements matching the filter are very rare or if there are less than elements matching than the specified count, this would trigger a full scan of the HNSW graph.
-
-For this reason, by default, the maximum effort is limited to a reasonable amount of nodes explored.
-
-### Modifying the FILTER effort
-
-1. By default, Vector Sets will explore up to `COUNT * 100` candidates to find matching results.
-2. You can control this exploration with the `FILTER-EF` parameter.
-3. A higher `FILTER-EF` value increases the chances of finding all relevant matches at the cost of increased processing time.
-4. A `FILTER-EF` of zero will explore as many nodes as needed in order to actually return the number of elements specified by `COUNT`.
-5. Even when a high `FILTER-EF` value is specified **the implementation will do a lot less work** if the elements passing the filter are very common, because of the early stop conditions of the HNSW implementation (once the specified amount of elements is reached and the quality check of the other candidates trigger an early stop).
-
-```
-VSIM key [ELE|FP32|VALUES] <vector or element> COUNT 10 FILTER '.year > 2000' FILTER-EF 500
-```
-
-In this example, Vector Sets will examine up to 500 potential nodes. Of course if count is reached before exploring 500 nodes, and the quality checks show that it is not possible to make progresses on similarity, the search is ended sooner.
-
-### Performance Considerations
-
-- If you have highly selective filters (few items match), use a higher `FILTER-EF`, or just design your application in order to handle a result set that is smaller than the requested count. Note that anyway the additional elements may be too distant than the query vector.
-- For less selective filters, the default should be sufficient.
-- Very selective filters with low `FILTER-EF` values may return fewer items than requested.
-- Extremely high values may impact performance without significantly improving results.
-
-The optimal `FILTER-EF` value depends on:
-1. The selectivity of your filter.
-2. The distribution of your data.
-3. The required recall quality.
-
-A good practice is to start with the default and increase if needed when you observe fewer results than expected.
-
-### Testing a larg-ish data set
-
-To really see how things work at scale, you can [download](https://antirez.com/word2vec_with_attribs.rdb) the following dataset:
-
-    wget https://antirez.com/word2vec_with_attribs.rdb
-
-It contains the 3 million words in Word2Vec having as attribute a JSON with just the length of the word. Because of the length distribution of words in large amounts of texts, where longer words become less and less common, this is ideal to check how filtering behaves with a filter verifying as true with less and less elements in a vector set.
-
-For instance:
-
-    > VSIM word_embeddings_bin ele "pasta" FILTER ".len == 6"
-     1) "pastas"
-     2) "rotini"
-     3) "gnocci"
-     4) "panino"
-     5) "salads"
-     6) "breads"
-     7) "salame"
-     8) "sauces"
-     9) "cheese"
-    10) "fritti"
-
-This will easily retrieve the desired amount of items (`COUNT` is 10 by default) since there are many items of length 6. However:
-
-    > VSIM word_embeddings_bin ele "pasta" FILTER ".len == 33"
-    1) "skinless_boneless_chicken_breasts"
-    2) "boneless_skinless_chicken_breasts"
-    3) "Boneless_skinless_chicken_breasts"
-
-This time even if we asked for 10 items, we only get 3, since the default filter effort will be `10*100 = 1000`. We can tune this giving the effort in an explicit way, with the risk of our query being slower, of course:
-
-    > VSIM word_embeddings_bin ele "pasta" FILTER ".len == 33" FILTER-EF 10000
-     1) "skinless_boneless_chicken_breasts"
-     2) "boneless_skinless_chicken_breasts"
-     3) "Boneless_skinless_chicken_breasts"
-     4) "mozzarella_feta_provolone_cheddar"
-     5) "Greatfood.com_R_www.greatfood.com"
-     6) "Pepperidge_Farm_Goldfish_crackers"
-     7) "Prosecuted_Mobsters_Rebuilt_Dying"
-     8) "Crispy_Snacker_Sandwiches_Popcorn"
-     9) "risultati_delle_partite_disputate"
-    10) "Peppermint_Mocha_Twist_Gingersnap"
-
-This time we get all the ten items, even if the last one will be quite far from our query vector. We encourage to experiment with this test dataset in order to understand better the dynamics of the implementation and the natural tradeoffs of filtered search.
-
-**Keep in mind** that by default, Redis Vector Sets will try to avoid a likely very useless huge scan of the HNSW graph, and will be more happy to return few or no elements at all, since this is almost always what the user actually wants in the context of retrieving *similar* items to the query.
-
-# Single Instance Scalability and Latency
-
-Vector Sets implement a threading model that allows Redis to handle many concurrent requests: by default `VSIM` is always threaded, and `VADD` is not (but can be partially threaded using the `CAS` option). This section explains how the threading and locking mechanisms work, and what to expect in terms of performance.
-
-## Threading Model
-
-- The `VSIM` command runs in a separate thread by default, allowing Redis to continue serving other commands.
-- A maximum of 32 threads can run concurrently (defined by `HNSW_MAX_THREADS`).
-- When this limit is reached, additional `VSIM` requests are queued - Redis remains responsive, no latency event is generated.
-- The `VADD` command with the `CAS` option also leverages threading for the computation-heavy candidate search phase, but the insertion itself is performed in the main thread. `VADD` always runs in a sub-millisecond time, so this is not a source of latency, but having too many hundreds of writes per second can be challenging to handle with a single instance. Please, look at the next section about multiple instances scalability.
-- Commands run within Lua scripts, MULTI/EXEC blocks, or from replication are executed in the main thread to ensure consistency.
-
-```
-> VSIM vset VALUES 3 1 1 1 FILTER '.year > 2000'  # This runs in a thread.
-> VADD vset VALUES 3 1 1 1 element CAS            # Candidate search runs in a thread.
-```
-
-## Locking Mechanism
-
-Vector Sets use a read/write locking mechanism to coordinate access:
-
-- Reads (`VSIM`, `VEMB`, etc.) acquire a read lock, allowing multiple concurrent reads.
-- Writes (`VADD`, `VREM`, etc.) acquire a write lock, temporarily blocking all reads.
-- When a write lock is requested while reads are in progress, the write operation waits for all reads to complete.
-- Once a write lock is granted, all reads are blocked until the write completes.
-- Each thread has a dedicated slot for tracking visited nodes during graph traversal, avoiding contention. This improves performances but limits the maximum number of concurrent threads, since each node has a memory cost proportional to the number of slots.
-
-## DEL latency
-
-Deleting a very large vector set (millions of elements) can cause latency spikes, as deletion rebuilds connections between nodes. This may change in the future.
-The deletion latency is most noticeable when using `DEL` on a key containing a large vector set or when the key expires.
-
-## Performance Characteristics
-
-- Search operations (`VSIM`) scale almost linearly with the number of CPU cores available, up to the thread limit. You can expect a Vector Set composed of million of items associated with components of dimension 300, with the default int8 quantization, to deliver around 50k VSIM operations per second in a single host.
-- Insertion operations (`VADD`) are more computationally expensive than searches, and can't be threaded: expect much lower throughput, in the range of a few thousands inserts per second.
-- Binary quantization offers significantly faster search performance at the cost of some recall quality, while int8 quantization, the default, seems to have very small impacts on recall quality, while it significantly improves performances and space efficiency.
-- The `EF` parameter has a major impact on both search quality and performance - higher values mean better recall but slower searches.
-- Graph traversal time scales logarithmically with the number of elements, making Vector Sets efficient even with millions of vectors
-
-## Loading / Saving performances
-
-Vector Sets are able to serialize on disk the graph structure as it is in memory, so loading back the data does not need to rebuild the HNSW graph. This means that Redis can load millions of items per minute. For instance 3 million items with 300 components vectors can be loaded back into memory into around 15 seconds.
-
-# Scaling vector sets to multiple instances
-
-The fundamental way vector sets can be scaled to very large data sets
-and to many Redis instances is that a given very large set of vectors
-can be partitioned into N different Redis keys, that can also live into
-different Redis instances.
-
-For instance, I could add my elements into `key0`, `key1`, `key2`, by hashing
-the item in some way, like doing `crc32(item)%3`, effectively splitting
-the dataset into three different parts. However once I want all the vectors
-of my dataset near to a given query vector, I could simply perform the
-`VSIM` command against all the three keys, merging the results by
-score (so the commands must be called using the `WITHSCORES` option) on
-the client side: once the union of the results are ordered by the
-similarity score, the query is equivalent to having a single key `key1+2+3`
-containing all the items.
-
-There are a few interesting facts to note about this pattern:
-
-1. It is possible to have a logical sorted set that is as big as the sum of all the Redis instances we are using.
-2. Deletion operations remain simple, we can hash the key and select the key where our item belongs.
-3. However, even if I use 10 different Redis instances, I'm not going to reach 10x the **read** operations per second, compared to using a single server: for each logical query, I need to query all the instances. Yet, smaller graphs are faster to navigate, so there is some win even from the point of view of CPU usage.
-4. Insertions, so **write** queries, will be scaled linearly: I can add N items against N instances at the same time, splitting the insertion load evenly. This is very important since vector sets, being based on HNSW data structures, are slower to add items than to query similar items, by a very big factor.
-5. While it cannot guarantee always the best results, with proper timeout management this system may be considered *highly available*, since if a subset of N instances are reachable, I'll be still be able to return similar items to my query vector.
-
-Notably, this pattern can be implemented in a way that avoids paying the sum of the round trip time with all the servers: it is possible to send the queries at the same time to all the instances, so that latency will be equal the slower reply out of of the N servers queries.
-
-# Optimizing memory usage
-
-Vector Sets, or better, HNSWs, the underlying data structure used by Vector Sets, combined with the features provided by the Vector Sets themselves (quantization, random projection, filtering, ...) form an implementation that has a non-trivial space of parameters that can be tuned. Despite to the complexity of the implementation and of vector similarity problems, here there is a list of simple ideas that can drive the user to pick the best settings:
-
-* 8 bit quantization (the default) is almost always a win. It reduces the memory usage of vectors by a factor of 4, yet the performance penalty in terms of recall is minimal. It also reduces insertion and search time by around 2 times or more.
-* Binary quantization is much more extreme: it makes vector sets a lot faster, but increases the recall error in a sensible way, for instance from 95% to 80% if all the parameters remain the same. Yet, the speedup is really big, and the memory usage of vectors, compaerd to full precision vectors, 32 times smaller.
-* Vectors memory usage are not the only responsible for Vector Set high memory usage per entry: nodes contain, on average `M*2 + M*0.33` pointers, where M is by default 16 (but can be tuned in `VADD`, see the `M` option). Also each node has the string item and the optional JSON attributes: those should be as small as possible in order to avoid contributing more to the memory usage.
-* The `M` parameter should be increased to 32 or more only when a near perfect recall is really needed.
-* It is possible to gain space (less memory usage) sacrificing time (more CPU time) by using a low `M` (the default of 16, for instance) and a high `EF` (the effort parameter of `VSIM`) in order to scan the graph more deeply.
-* When memory usage is seriosu concern, and there is the suspect the vectors we are storing don't contain as much information - at least for our use case - to justify the number of components they feature, random projection (the `REDUCE` option of `VADD`) could be tested to see if dimensionality reduction is possible with acceptable precision loss.
-
-## Random projection tradeoffs
-
-Sometimes learned vectors are not as information dense as we could guess, that
-is there are components having similar meanings in the space, and components
-having values that don't really represent features that matter in our use case.
-
-At the same time, certain vectors are very big, 1024 components or more. In this cases, it is possible to use the random projection feature of Redis Vector Sets in order to reduce both space (less RAM used) and space (more operstions per second). The feature is accessible via the `REDUCE` option of the `VADD` command. However, keep in mind that you need to test how much reduction impacts the performances of your vectors in term of recall and quality of the results you get back.
-
-## What is a random projection?
-
-The concept of Random Projection is relatively simple to grasp. For instance, a projection that turns a 100 components vector into a 10 components vector will perform a different linear transformation between the 100 components and each of the target 10 components. Please note that *each of the target components* will get some random amount of all the 100 original components. It is mathematically proved that this process results in a vector space where elements still have similar distances among them, but still some information will get lost.
-
-## Examples of projections and loss of precision
-
-To show you a bit of a extreme case, let's take Word2Vec 3 million items and compress them from 300 to 100, 50 and 25 components vectors. Then, we check the recall compared to the ground truth against each of the vector sets produced in this way (using different `REDUCE` parameters of `VADD`). This is the result, obtained asking for the top 10 elements.
-
-```
-----------------------------------------------------------------------
-Key                            Average Recall % Std Dev
-----------------------------------------------------------------------
-word_embeddings_int8           95.98           12.14
-  ^ This is the same key used for ground truth, but without TRUTH option
-word_embeddings_reduced_100    40.20           20.13
-word_embeddings_reduced_50     24.42           16.89
-word_embeddings_reduced_25     14.31           9.99
-```
-
-Here the dimensionality reduction we are using is quite extreme: from 300 to 100 means that 66.6% of the original information is lost. The recall drops from 96% to 40%, down to 24% and 14% for even more extreme dimension reduction.
-
-Reducing the dimension of vectors that are already relatively small, like the above example, of 300 components, will provide only relatively small memory savings, especially because by default Vector Sets use `int8` quantization, that will use only one byte per component:
-
-```
-> MEMORY USAGE word_embeddings_int8
-(integer) 3107002888
-> MEMORY USAGE word_embeddings_reduced_100
-(integer) 2507122888
-```
-
-Of course going, for example, from 2048 component vectors to 1024 would provide a much more sensible memory saving, even with the `int8` quantization used by Vector Sets, assuming the recall loss is acceptable. Other than the memory saving, there is also the reduction in CPU time, translating to more operations per second.
-
-Another thing to note is that, with certain embedding models, binary quantization (that offers a 8x reduction of memory usage compared to 8 bit quants, and a very big speedup in computation) performs much better than reducing the dimension of vectors of the same amount via random projections:
-
-```
-word_embeddings_bin            35.48           19.78
-```
-
-Here in the same test did above: we have a 35% recall which is not too far than the 40% obtained with a random projection from 300 to 100 components. However, while the first technique reduces the size by 3 times, the size reduced of binary quantization is by 8 times.
-
-```
-> memory usage word_embeddings_bin
-(integer) 2327002888
-```
-
-In this specific case the key uses JSON attributes and has a graph connection overhead that is much bigger than the 300 bits each vector takes, but, as already said, for big vectors (1024 components, for instance) or for lower values of `M` (see `VADD`, the `M` parameter connects the level of connectivity, so it changes the amount of pointers used per node) the memory saving is much stronger.
-
-# Vector Sets troubleshooting and understandability
-
-## Debugging poor recall or unexpected results
-
-Vector graphs and similarity queries pose many challenges mainly due to the following three problems:
-
-1. The error due to the approximated nature of Vector Sets is hard to evaluate.
-2. The error added by the quantization is often depends on the exact vector space (the embedding we are using **and** how far apart the elements we represent into such embeddings are).
-3. We live in the illusion that learned embeddings capture the best similarity possible among elements, which is obviously not always true, and highly application dependent.
-
-The only way to debug such problems, is the ability to inspect step by step what is happening inside our application, and the structure of the HNSW graph itself. To do so, we suggest to consider the following tools:
-
-1. The `TRUTH` option of the `VSIM` command is able to return the ground truth of the most similar elements, without using the HNSW graph, but doing a linear scan.
-2. The `VLINKS` command allows to explore the graph to see if the connections among nodes make sense, and to investigate why a given node may be more isolated than expected. Such command can also be used in a different way, when we want very fast "similar items" without paying the HNSW traversal time. It exploits the fact that we have a direct reference from each element in our vector set to each node in our HNSW graph.
-3. The `WITHSCORES` option, in the supported commands, return a value that is directly related to the *cosine similarity* between the query and the items vectors, the interval of the similarity is simply rescaled from the -1, 1 original range to 0, 1, otherwise the metric is identical.
-
-## Clients, latency and bandwidth usage
-
-During Vector Sets testing, we discovered that often clients introduce considerable latecy and CPU usage (in the client side, not in Redis) for two main reasons:
-
-1. Often the serialization to `VALUES ... list of floats ...` can be very slow.
-2. The vector payload of floats represented as strings is very large, resulting in high bandwidth usage and latency, compared to other Redis commands.
-
-Switching from `VALUES` to `FP32` as a method for transmitting vectors may easily provide 10-20x speedups.
-
-# Implementation details
-
-Vector sets are based on the `hnsw.c` implementation of the HNSW data structure with extensions for speed and functionality.
-
-The main features are:
-
-* Proper nodes deletion with relinking.
-* 8 bits and binary quantization.
-* Threaded queries.
-* Filtered search with predicate callback.

modules/vector-sets/commands.json

@@ -1,446 +0,0 @@
-{
-  "VADD": {
-    "summary": "Add one or more elements to a vector set, or update its vector if it already exists",
-    "complexity": "O(log(N)) for each element added, where N is the number of elements in the vector set.",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": -5,
-    "function": "vaddCommand",
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "token": "REDUCE",
-        "name": "reduce",
-        "type": "block",
-        "optional": true,
-        "arguments": [
-          {
-            "name": "dim",
-            "type": "integer"
-          }
-        ]
-      },
-      {
-        "name": "format",
-        "type": "oneof",
-        "arguments": [
-          {
-            "name": "fp32",
-            "type": "pure-token",
-            "token": "FP32"
-          },
-          {
-            "name": "values",
-            "type": "pure-token",
-            "token": "VALUES"
-          }
-        ]
-      },
-      {
-        "name": "vector",
-        "type": "string"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      },
-      {
-        "token": "CAS",
-        "name": "cas",
-        "type": "pure-token",
-        "optional": true
-      },
-      {
-        "name": "quant_type",
-        "type": "oneof",
-        "optional": true,
-        "arguments": [
-          {
-            "name": "noquant",
-            "type": "pure-token",
-            "token": "NOQUANT"
-          },
-          {
-            "name": "bin",
-            "type": "pure-token",
-            "token": "BIN"
-          },
-          {
-            "name": "q8",
-            "type": "pure-token",
-            "token": "Q8"
-          }
-        ]
-      },
-      {
-        "token": "EF",
-        "name": "build-exploration-factor",
-        "type": "integer",
-        "optional": true
-      },
-      {
-        "token": "SETATTR",
-        "name": "attributes",
-        "type": "string",
-        "optional": true
-      },
-      {
-        "token": "M",
-        "name": "numlinks",
-        "type": "integer",
-        "optional": true
-      }
-    ],
-    "command_flags": [
-      "WRITE",
-      "DENYOOM"
-    ]
-  },
-  "VREM": {
-    "summary": "Remove an element from a vector set",
-    "complexity": "O(log(N)) for each element removed, where N is the number of elements in the vector set.",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 3,
-    "function": "vremCommand",
-    "command_flags": [
-      "WRITE"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      }
-    ]
-  },
-  "VSIM": {
-    "summary": "Return elements by vector similarity",
-    "complexity": "O(log(N)) where N is the number of elements in the vector set.",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": -4,
-    "function": "vsimCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "format",
-        "type": "oneof",
-        "arguments": [
-          {
-            "name": "ele",
-            "type": "pure-token",
-            "token": "ELE"
-          },
-          {
-            "name": "fp32",
-            "type": "pure-token",
-            "token": "FP32"
-          },
-          {
-            "name": "values",
-            "type": "pure-token",
-            "token": "VALUES"
-          }
-        ]
-      },
-      {
-        "name": "vector_or_element",
-        "type": "string"
-      },
-      {
-        "token": "WITHSCORES",
-        "name": "withscores",
-        "type": "pure-token",
-        "optional": true
-      },
-      {
-        "token": "WITHATTRIBS",
-        "name": "withattribs",
-        "type": "pure-token",
-        "optional": true
-      },
-      {
-        "token": "COUNT",
-        "name": "count",
-        "type": "integer",
-        "optional": true
-      },
-      {
-        "token": "EPSILON",
-        "name": "max_distance",
-        "type": "double",
-        "optional": true
-      },
-      {
-        "token": "EF",
-        "name": "search-exploration-factor",
-        "type": "integer",
-        "optional": true
-      },
-      {
-        "token": "FILTER",
-        "name": "expression",
-        "type": "string",
-        "optional": true
-      },
-      {
-        "token": "FILTER-EF",
-        "name": "max-filtering-effort",
-        "type": "integer",
-        "optional": true
-      },
-      {
-        "token": "TRUTH",
-        "name": "truth",
-        "type": "pure-token",
-        "optional": true
-      },
-      {
-        "token": "NOTHREAD",
-        "name": "nothread",
-        "type": "pure-token",
-        "optional": true
-      }
-    ]
-  },
-  "VDIM": {
-    "summary": "Return the dimension of vectors in the vector set",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 2,
-    "function": "vdimCommand",
-    "command_flags": [
-      "READONLY",
-      "FAST"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      }
-    ]
-  },
-  "VCARD": {
-    "summary": "Return the number of elements in a vector set",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 2,
-    "function": "vcardCommand",
-    "command_flags": [
-      "READONLY",
-      "FAST"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      }
-    ]
-  },
-  "VEMB": {
-    "summary": "Return the vector associated with an element",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": -3,
-    "function": "vembCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      },
-      {
-        "token": "RAW",
-        "name": "raw",
-        "type": "pure-token",
-        "optional": true
-      }
-    ]
-  },
-  "VLINKS": {
-    "summary": "Return the neighbors of an element at each layer in the HNSW graph",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": -3,
-    "function": "vlinksCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      },
-      {
-        "token": "WITHSCORES",
-        "name": "withscores",
-        "type": "pure-token",
-        "optional": true
-      }
-    ]
-  },
-  "VINFO": {
-    "summary": "Return information about a vector set",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 2,
-    "function": "vinfoCommand",
-    "command_flags": [
-      "READONLY",
-      "FAST"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      }
-    ]
-  },
-  "VSETATTR": {
-    "summary": "Associate or remove the JSON attributes of elements",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 4,
-    "function": "vsetattrCommand",
-    "command_flags": [
-      "WRITE"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      },
-      {
-        "name": "json",
-        "type": "string"
-      }
-    ]
-  },
-  "VGETATTR": {
-    "summary": "Retrieve the JSON attributes of elements",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": 3,
-    "function": "vgetattrCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      }
-    ]
-  },
-  "VRANDMEMBER": {
-    "summary": "Return one or multiple random members from a vector set",
-    "complexity": "O(N) where N is the absolute value of the count argument.",
-    "group": "vector_set",
-    "since": "8.0.0",
-    "arity": -2,
-    "function": "vrandmemberCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "count",
-        "type": "integer",
-        "optional": true
-      }
-    ]
-  },
-  "VISMEMBER": {
-    "summary": "Check if an element exists in a vector set",
-    "complexity": "O(1)",
-    "group": "vector_set",
-    "since": "8.2.0",
-    "arity": 3,
-    "function": "vismemberCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "element",
-        "type": "string"
-      }
-    ]
-  },
-  "VRANGE": {
-    "summary": "Return elements in a lexicographical range",
-    "complexity": "O(log(K)+M) where K is the number of elements in the start prefix, and M is the number of elements returned. In practical terms, the command is just O(M)",
-    "group": "vector_set",
-    "since": "8.4.0",
-    "arity": -4,
-    "function": "vrangeCommand",
-    "command_flags": [
-      "READONLY"
-    ],
-    "arguments": [
-      {
-        "name": "key",
-        "type": "key"
-      },
-      {
-        "name": "start",
-        "type": "string"
-      },
-      {
-        "name": "end",
-        "type": "string"
-      },
-      {
-        "name": "count",
-        "type": "integer",
-        "optional": true
-      }
-    ]
-  }
-}

modules/vector-sets/examples/cli-tool/.gitignore

@@ -1 +0,0 @@
-venv

modules/vector-sets/examples/cli-tool/README.md

@@ -1,44 +0,0 @@
-This tool is similar to redis-cli (but very basic) but allows
-to specify arguments that are expanded as vectors by calling
-ollama to get the embedding.
-
-Whatever is passed as !"foo bar" gets expanded into
-    VALUES ... embedding ...
-
-You must have ollama running with the mxbai-emb-large model
-already installed for this to work.
-
-Example:
-
-    redis> KEYS *
-    1) food_items
-    2) glove_embeddings_bin
-    3) many_movies_mxbai-embed-large_BIN
-    4) many_movies_mxbai-embed-large_NOQUANT
-    5) word_embeddings
-    6) word_embeddings_bin
-    7) glove_embeddings_fp32
-
-    redis> VSIM food_items !"drinks with fruit"
-    1) (Fruit)Juices,Lemonade,100ml,50 cal,210 kJ
-    2) (Fruit)Juices,Limeade,100ml,128 cal,538 kJ
-    3) CannedFruit,Canned Fruit Cocktail,100g,81 cal,340 kJ
-    4) (Fruit)Juices,Energy-Drink,100ml,87 cal,365 kJ
-    5) Fruits,Lime,100g,30 cal,126 kJ
-    6) (Fruit)Juices,Coconut Water,100ml,19 cal,80 kJ
-    7) Fruits,Lemon,100g,29 cal,122 kJ
-    8) (Fruit)Juices,Clamato,100ml,60 cal,252 kJ
-    9) Fruits,Fruit salad,100g,50 cal,210 kJ
-    10) (Fruit)Juices,Capri-Sun,100ml,41 cal,172 kJ
-
-    redis> vsim food_items !"barilla"
-    1) Pasta&Noodles,Spirelli,100g,367 cal,1541 kJ
-    2) Pasta&Noodles,Farfalle,100g,358 cal,1504 kJ
-    3) Pasta&Noodles,Capellini,100g,353 cal,1483 kJ
-    4) Pasta&Noodles,Spaetzle,100g,368 cal,1546 kJ
-    5) Pasta&Noodles,Cappelletti,100g,164 cal,689 kJ
-    6) Pasta&Noodles,Penne,100g,351 cal,1474 kJ
-    7) Pasta&Noodles,Shells,100g,353 cal,1483 kJ
-    8) Pasta&Noodles,Linguine,100g,357 cal,1499 kJ
-    9) Pasta&Noodles,Rotini,100g,353 cal,1483 kJ
-    10) Pasta&Noodles,Rigatoni,100g,353 cal,1483 kJ

modules/vector-sets/examples/cli-tool/cli.py

@@ -1,160 +0,0 @@
-#
-# Copyright (c) 2009-Present, Redis Ltd.
-# All rights reserved.
-#
-# Licensed under your choice of (a) the Redis Source Available License 2.0
-# (RSALv2); or (b) the Server Side Public License v1 (SSPLv1); or (c) the
-# GNU Affero General Public License v3 (AGPLv3).
-#
-
-#!/usr/bin/env python3
-import argparse
-import redis
-import requests
-import re
-import shlex
-from prompt_toolkit import PromptSession
-from prompt_toolkit.history import InMemoryHistory
-
-# Default Ollama embeddings URL (can be overridden with --ollama-url)
-OLLAMA_URL = "http://localhost:11434/api/embeddings"
-
-def get_embedding(text):
-    """Get embedding from local Ollama API"""
-    url = OLLAMA_URL
-    payload = {
-        "model": "mxbai-embed-large",
-        "prompt": text
-    }
-    try:
-        response = requests.post(url, json=payload)
-        response.raise_for_status()
-        return response.json()['embedding']
-    except requests.exceptions.RequestException as e:
-        raise Exception(f"Failed to get embedding: {str(e)}")
-
-def process_embedding_patterns(text):
-    """Process !"text" and !!"text" patterns in the command"""
-
-    def replace_with_embedding(match):
-        text = match.group(1)
-        embedding = get_embedding(text)
-        return f"VALUES {len(embedding)} {' '.join(map(str, embedding))}"
-
-    def replace_with_embedding_and_text(match):
-        text = match.group(1)
-        embedding = get_embedding(text)
-        # Return both the embedding values and the original text as next argument
-        return f'VALUES {len(embedding)} {" ".join(map(str, embedding))} "{text}"'
-
-    # First handle !!"text" pattern (must be done before !"text")
-    text = re.sub(r'!!"([^"]*)"', replace_with_embedding_and_text, text)
-    # Then handle !"text" pattern
-    text = re.sub(r'!"([^"]*)"', replace_with_embedding, text)
-    return text
-
-def parse_command(command):
-    """Parse command respecting quoted strings"""
-    try:
-        # Use shlex to properly handle quoted strings
-        return shlex.split(command)
-    except ValueError as e:
-        raise Exception(f"Invalid command syntax: {str(e)}")
-
-def format_response(response):
-    """Format the response to match Redis protocol style"""
-    if response is None:
-        return "(nil)"
-    elif isinstance(response, bool):
-        return "+OK" if response else "(error) Operation failed"
-    elif isinstance(response, (list, set)):
-        if not response:
-            return "(empty list or set)"
-        return "\n".join(f"{i+1}) {item}" for i, item in enumerate(response))
-    elif isinstance(response, int):
-        return f"(integer) {response}"
-    else:
-        return str(response)
-
-def main():
-    global OLLAMA_URL
-
-    parser = argparse.ArgumentParser(prog="cli.py", add_help=False)
-    parser.add_argument("--ollama-url", dest="ollama_url",
-                        help="Ollama embeddings API URL (default: {OLLAMA_URL})",
-                        default=OLLAMA_URL)
-    args, _ = parser.parse_known_args()
-    OLLAMA_URL = args.ollama_url
-
-    # Default connection to localhost:6379
-    r = redis.Redis(host='localhost', port=6379, decode_responses=True)
-
-    try:
-        # Test connection
-        r.ping()
-        print("Connected to Redis. Type your commands (CTRL+D to exit):")
-        print("Special syntax:")
-        print("  !\"text\"  - Replace with embedding")
-        print("  !!\"text\" - Replace with embedding and append text as value")
-        print("  \"text\"   - Quote strings containing spaces")
-    except redis.ConnectionError:
-        print("Error: Could not connect to Redis server")
-        return
-
-    # Setup prompt session with history
-    session = PromptSession(history=InMemoryHistory())
-
-    # Main loop
-    while True:
-        try:
-            # Read input with line editing support
-            command = session.prompt("redis> ")
-
-            # Skip empty commands
-            if not command.strip():
-                continue
-
-            # Process any embedding patterns before parsing
-            try:
-                processed_command = process_embedding_patterns(command)
-            except Exception as e:
-                print(f"(error) Embedding processing failed: {str(e)}")
-                continue
-
-            # Parse the command respecting quoted strings
-            try:
-                parts = parse_command(processed_command)
-            except Exception as e:
-                print(f"(error) {str(e)}")
-                continue
-
-            if not parts:
-                continue
-
-            cmd = parts[0].lower()
-            args = parts[1:]
-
-            # Execute command
-            try:
-                method = getattr(r, cmd, None)
-                if method is not None:
-                    result = method(*args)
-                else:
-                    # Use execute_command for unknown commands
-                    result = r.execute_command(cmd, *args)
-                print(format_response(result))
-            except AttributeError:
-                print(f"(error) Unknown command '{cmd}'")
-
-        except EOFError:
-            print("\nGoodbye!")
-            break
-        except KeyboardInterrupt:
-            continue  # Allow Ctrl+C to clear current line
-        except redis.RedisError as e:
-            print(f"(error) {str(e)}")
-        except Exception as e:
-            print(f"(error) {str(e)}")
-
-if __name__ == "__main__":
-    main()

modules/vector-sets/examples/glove-100/README

@@ -1,3 +0,0 @@
-wget http://ann-benchmarks.com/glove-100-angular.hdf5
-python insert.py
-python recall.py (use --k <count> optionally, default top-10)

modules/vector-sets/examples/glove-100/insert.py

@@ -1,56 +0,0 @@
-#
-# Copyright (c) 2009-Present, Redis Ltd.
-# All rights reserved.
-#
-# Licensed under your choice of (a) the Redis Source Available License 2.0
-# (RSALv2); or (b) the Server Side Public License v1 (SSPLv1); or (c) the
-# GNU Affero General Public License v3 (AGPLv3).
-#
-
-import h5py
-import redis
-from tqdm import tqdm
-
-# Initialize Redis connection
-redis_client = redis.Redis(host='localhost', port=6379, decode_responses=True, encoding='utf-8')
-
-def add_to_redis(index, embedding):
-    """Add embedding to Redis using VADD command"""
-    args = ["VADD", "glove_embeddings", "VALUES", "100"]  # 100 is vector dimension
-    args.extend(map(str, embedding))
-    args.append(f"{index}")  # Using index as identifier since we don't have words
-    args.append("EF")
-    args.append("200")
-    # args.append("NOQUANT")
-    # args.append("BIN")
-    redis_client.execute_command(*args)
-
-def main():
-    with h5py.File('glove-100-angular.hdf5', 'r') as f:
-        # Get the train dataset
-        train_vectors = f['train']
-        total_vectors = train_vectors.shape[0]
-
-        print(f"Starting to process {total_vectors} vectors...")
-
-        # Process in batches to avoid memory issues
-        batch_size = 1000
-
-        for i in tqdm(range(0, total_vectors, batch_size)):
-            batch_end = min(i + batch_size, total_vectors)
-            batch = train_vectors[i:batch_end]
-
-            for j, vector in enumerate(batch):
-                try:
-                    current_index = i + j
-                    add_to_redis(current_index, vector)
-
-                except Exception as e:
-                    print(f"Error processing vector {current_index}: {str(e)}")
-                    continue
-
-            if (i + batch_size) % 10000 == 0:
-                print(f"Processed {i + batch_size} vectors")
-
-if __name__ == "__main__":
-    main()

modules/vector-sets/examples/glove-100/recall.py

@@ -1,87 +0,0 @@
-#
-# Copyright (c) 2009-Present, Redis Ltd.
-# All rights reserved.
-#
-# Licensed under your choice of (a) the Redis Source Available License 2.0
-# (RSALv2); or (b) the Server Side Public License v1 (SSPLv1); or (c) the
-# GNU Affero General Public License v3 (AGPLv3).
-#
-
-import h5py
-import redis
-import numpy as np
-from tqdm import tqdm
-import argparse
-
-# Initialize Redis connection
-redis_client = redis.Redis(host='localhost', port=6379, decode_responses=True, encoding='utf-8')
-
-def get_redis_neighbors(query_vector, k):
-    """Get nearest neighbors using Redis VSIM command"""
-    args = ["VSIM", "glove_embeddings_bin", "VALUES", "100"]
-    args.extend(map(str, query_vector))
-    args.extend(["COUNT", str(k)])
-    args.extend(["EF", 100])
-    if False:
-        print(args)
-        exit(1)
-    results = redis_client.execute_command(*args)
-    return [int(res) for res in results]
-
-def calculate_recall(ground_truth, predicted, k):
-    """Calculate recall@k"""
-    relevant = set(ground_truth[:k])
-    retrieved = set(predicted[:k])
-    return len(relevant.intersection(retrieved)) / len(relevant)
-
-def main():
-    parser = argparse.ArgumentParser(description='Evaluate Redis VSIM recall')
-    parser.add_argument('--k', type=int, default=10, help='Number of neighbors to evaluate (default: 10)')
-    parser.add_argument('--batch', type=int, default=100, help='Progress update frequency (default: 100)')
-    args = parser.parse_args()
-
-    k = args.k
-    batch_size = args.batch
-
-    with h5py.File('glove-100-angular.hdf5', 'r') as f:
-        test_vectors = f['test'][:]
-        ground_truth_neighbors = f['neighbors'][:]
-        
-        num_queries = len(test_vectors)
-        recalls = []
-        
-        print(f"Evaluating recall@{k} for {num_queries} test queries...")
-        
-        for i in tqdm(range(num_queries)):
-            try:
-                # Get Redis results
-                redis_neighbors = get_redis_neighbors(test_vectors[i], k)
-                
-                # Get ground truth for this query
-                true_neighbors = ground_truth_neighbors[i]
-                
-                # Calculate recall
-                recall = calculate_recall(true_neighbors, redis_neighbors, k)
-                recalls.append(recall)
-                
-                if (i + 1) % batch_size == 0:
-                    current_avg_recall = np.mean(recalls)
-                    print(f"Current average recall@{k} after {i+1} queries: {current_avg_recall:.4f}")
-                
-            except Exception as e:
-                print(f"Error processing query {i}: {str(e)}")
-                continue
-        
-        final_recall = np.mean(recalls)
-        print("\nFinal Results:")
-        print(f"Average recall@{k}: {final_recall:.4f}")
-        print(f"Total queries evaluated: {len(recalls)}")
-        
-        # Save detailed results
-        with open(f'recall_evaluation_results_k{k}.txt', 'w') as f:
-            f.write(f"Average recall@{k}: {final_recall:.4f}\n")
-            f.write(f"Total queries evaluated: {len(recalls)}\n")
-            f.write(f"Individual query recalls: {recalls}\n")
-
-if __name__ == "__main__":
-    main()

modules/vector-sets/examples/movies/.gitignore

@@ -1,2 +0,0 @@
-mpst_full_data.csv
-partition.json