LALR(1) parser from official MySQL grammar

.github/workflows/mysql-parser-tests.yml

@@ -0,0 +1,53 @@
+name: MySQL Parser Tests
+
+on:
+  push:
+    branches:
+      - trunk
+    paths:
+      - '.github/workflows/mysql-parser-tests.yml'
+      - 'packages/mysql-parser/**'
+  pull_request:
+    paths:
+      - '.github/workflows/mysql-parser-tests.yml'
+      - 'packages/mysql-parser/**'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+# Disable permissions for all available scopes by default.
+# Any needed permissions should be configured at the job level.
+permissions: {}
+
+jobs:
+  test:
+    # The runtime supports PHP 7.2+; test the oldest and the latest.
+    name: PHP ${{ matrix.php }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read # Required to clone the repo.
+    strategy:
+      fail-fast: false
+      matrix:
+        php: [ '7.2', '8.5' ]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up PHP
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: ${{ matrix.php }}
+          coverage: none
+
+      - name: Install dependencies
+        working-directory: packages/mysql-parser
+        run: composer install --no-interaction --no-progress
+
+      - name: Run tests
+        working-directory: packages/mysql-parser
+        run: composer run test

packages/mysql-parser/.gitignore

@@ -0,0 +1 @@
+/build/

packages/mysql-parser/README.md

@@ -0,0 +1,78 @@
+# MySQL Parser
+
+A fast and complete **MySQL parser** in pure PHP with zero dependencies, generated
+directly from the **official MySQL grammar**.
+
+The runtime requires **PHP 7.2+** with no extensions.
+
+## How it works
+
+The grammar is compiled ahead of time from the official MySQL grammar sources.
+It outputs a compact parse table and a list of MySQL tokens for the lexer:
+
+```
+mysql-server sources
+  sql/sql_yacc.yy ──▶ Bison 3.8.2 ──▶ automaton.xml ─┬─▶ generate-parse-table.php ──▶ mysql-parse-table.php
+                                                     |
+  sql/lex.h ─────────────────────────────────────────┴─▶ generate-tokens.php ───────▶ class-wp-mysql-tokens.php
+```
+
+The runtime ships only the compiled artifacts and a thin parser implementation.
+In this package, the runtime lives under `src` and the grammar tooling in `tools`.
+
+A MySQL query is processed using the following pipeline:
+```
+MySQL query ──────────▶ WP_MySQL_Lexer ──────────▶ WP_Parser ──────────▶ AST
+              string                 WP_MySQL_Token[]               WP_Parser_Node(s)
+                                                                    WP_MySQL_Token(s)
+```
+
+## Usage
+
+```php
+require_once __DIR__ . '/vendor/autoload.php';
+
+$parser = WP_MySQL_Parser_Factory::create_parser();
+$tokens = ( new WP_MySQL_Lexer( 'SELECT 1 + 2' ) )->remaining_tokens();
+$ast    = $parser->parse( $tokens );
+```
+
+## Development
+This package includes the full grammar compilation pipeline. The generated artifacts
+are committed to the repository, and they only need to be regenerated on grammar
+changes or changes to the compilation pipeline itself. The grammar comes with a
+testing query corpus extracted from the MySQL server test suite.
+
+### Building the grammar
+To regenerate the compiled MySQL artifacts from MySQL sources, use:
+
+```bash
+composer run build-grammar
+```
+
+This requires `bash`, `curl`, `docker`, and `php` and executes the following steps:
+1. Fetch the grammar from https://github.com/mysql/mysql-server/.
+2. Run Bison in a Docker container to generate `build/automaton.xml`.
+3. Extract and compact the grammar and tokens, and save them in `src`.
+
+### Building the query corpus
+This package includes a testing corpus of about 70,000 MySQL queries extracted
+from the MySQL release that corresponds to the generated MySQL grammar version.
+To regenerate it, use:
+
+```bash
+composer run build-corpus
+```
+
+This requires `bash`, `git`, and `php`. It performs the following steps:
+1. Shallow-clone the `mysql-test` directory from MySQL server into `build/`.
+2. Extract SQL queries from the MySQL test files.
+3. Store the queries under `data/mysql-server-query-corpus/mysql-latest.csv`.
+
+## Tests and benchmarks
+To run lexer and parser tests and benchmarks, use:
+
+```bash
+composer run test        # PHPUnit suite, including the query corpus tests
+composer run benchmark   # Query throughput with and without JIT on the whole corpus
+```

packages/mysql-parser/bin/build-corpus

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+#
+# Build the MySQL server query corpus from the MySQL server test suite.
+#
+# Runs the full pipeline end to end:
+#   1. Fetch the mysql-test directory from the pinned mysql-server tag.
+#   2. Extract the SQL queries into data/mysql-server-query-corpus/.
+#
+# Requirements: bash, git, php. Override the MySQL version with MYSQL_TAG
+# (default: mysql-8.4.10).
+#
+set -euo pipefail
+
+package_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+tools_dir="$package_dir/tools"
+
+bash "$tools_dir/fetch-mysql-tests.sh"
+
+echo "Generating the query corpus ..."
+php "$tools_dir/generate-query-corpus.php"
+
+echo "Done."

packages/mysql-parser/bin/build-grammar

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+#
+# Build the MySQL parse table and token map from the official MySQL grammar.
+#
+# Runs the full pipeline end to end:
+#   1. Fetch sql_yacc.yy + lex.h from the pinned mysql-server tag.
+#   2. Run Bison 3.8.2 to produce the LALR automaton (automaton.xml).
+#   3. Generate src/mysql-parse-table.php from the automaton.
+#   4. Generate the lexer's token data block from lex.h and the automaton.
+#
+# Requirements: bash, curl, docker, php. Override the MySQL version with
+# MYSQL_TAG (default: mysql-8.4.10).
+#
+set -euo pipefail
+
+package_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+tools_dir="$package_dir/tools"
+build_dir="$package_dir/build"
+src_dir="$package_dir/src"
+
+mkdir -p "$src_dir"
+
+bash "$tools_dir/fetch-mysql-grammar.sh"
+bash "$tools_dir/run-bison.sh"
+
+echo "Generating parse table ..."
+php "$tools_dir/generate-parse-table.php" "$build_dir/automaton.xml" "$src_dir/mysql-parse-table.php"
+
+echo "Generating grammar tokens ..."
+php "$tools_dir/generate-tokens.php" "$build_dir/automaton.xml" "$build_dir/lex.h" "$src_dir/class-wp-mysql-lexer.php"
+
+echo "Done."

packages/mysql-parser/composer.json

@@ -0,0 +1,30 @@
+{
+	"name": "wordpress/mysql-parser",
+	"type": "library",
+	"description": "A fast and complete MySQL parser with zero dependencies.",
+	"license": "GPL-2.0-or-later",
+	"require": {
+		"php": ">=7.2"
+	},
+	"autoload": {
+		"classmap": [
+			"src/"
+		]
+	},
+	"require-dev": {
+		"phpunit/phpunit": "^8.5"
+	},
+	"scripts": {
+		"test": "phpunit",
+		"build-grammar": [
+			"./bin/build-grammar"
+		],
+		"build-corpus": [
+			"./bin/build-corpus"
+		],
+		"benchmark": [
+			"@php tests/benchmark.php",
+			"@php -d opcache.enable_cli=1 -d opcache.jit_buffer_size=64M -d opcache.jit=tracing tests/benchmark.php"
+		]
+	}
+}