feat: introduce redshift parser into mono

.github/workflows/tests.yml

@@ -0,0 +1,103 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  detect-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+      any_changed: ${{ steps.set-matrix.outputs.any_changed }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Get changed files
+        id: changed-files
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            echo "changed_files<<EOF" >> $GITHUB_OUTPUT
+            git diff --name-only origin/${{ github.base_ref }}..HEAD >> $GITHUB_OUTPUT
+            echo "EOF" >> $GITHUB_OUTPUT
+          else
+            echo "changed_files<<EOF" >> $GITHUB_OUTPUT
+            git diff --name-only HEAD~1..HEAD >> $GITHUB_OUTPUT
+            echo "EOF" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Set matrix for changed parsers
+        id: set-matrix
+        run: |
+          # List of all available parsers
+          ALL_PARSERS="redshift"
+          # Add more parsers here as they are added to the repository
+          # ALL_PARSERS="redshift mysql postgresql"
+
+          CHANGED_FILES="${{ steps.changed-files.outputs.changed_files }}"
+          CHANGED_PARSERS=""
+
+          for parser in $ALL_PARSERS; do
+            if echo "$CHANGED_FILES" | grep -q "^$parser/"; then
+              if [ -z "$CHANGED_PARSERS" ]; then
+                CHANGED_PARSERS="\"$parser\""
+              else
+                CHANGED_PARSERS="$CHANGED_PARSERS,\"$parser\""
+              fi
+            fi
+          done
+
+          if [ -n "$CHANGED_PARSERS" ]; then
+            echo "matrix={\"parser\":[$CHANGED_PARSERS]}" >> $GITHUB_OUTPUT
+            echo "any_changed=true" >> $GITHUB_OUTPUT
+            echo "Changed parsers: $CHANGED_PARSERS"
+          else
+            echo "matrix={\"parser\":[]}" >> $GITHUB_OUTPUT
+            echo "any_changed=false" >> $GITHUB_OUTPUT
+            echo "No parser changes detected"
+          fi
+
+  go-mod-tidy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+          cache-dependency-path: go.sum
+
+      - name: Verify go mod tidy
+        run: |
+          go mod tidy
+          git diff --exit-code -- go.mod go.sum
+
+  go-tests:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.any_changed == 'true'
+    runs-on: ubuntu-latest
+    strategy:
+      matrix: ${{ fromJSON(needs.detect-changes.outputs.matrix) }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+          cache-dependency-path: go.sum
+
+      - name: Run all tests
+        working-directory: ${{ matrix.parser }}
+        run: go test -p=8 -timeout 30m -ldflags "-w -s" -v ./... | tee test.log; exit ${PIPESTATUS[0]}
+      - name: Pretty print tests running time
+        working-directory: ${{ matrix.parser }}
+        # grep: filter out lines like "--- PASS: Test (15.04s)"
+        # sed: remove unnecessary characters
+        # awk: re-format lines to "PASS: Test (15.04s)"
+        # sort: cut into columns by delimiter ' ' (single space) and sort by column 3 (test time in seconds) as numeric type in reverse order (largest comes first)
+        # awk: accumulate sum by test time in seconds
+        run: grep --color=never -e '--- PASS:' -e '--- FAIL:' test.log | sed 's/[:()]//g' | awk '{print $2,$3,$4}' | sort -t' ' -nk3 -r | awk '{sum += $3; print $1,$2,$3,sum"s"}'

.gitignore

@@ -7,6 +7,7 @@
 *.dll
 *.so
 *.dylib
+**/.DS_Store
 
 # Test binary, built with `go test -c`
 *.test
@@ -28,5 +29,8 @@ go.work.sum
 .env
 
 # Editor/IDE
-# .idea/
-# .vscode/
+.idea/
+
+# Plguin
+# Intellij ANTLR plugin
+**/gen/

go.mod

@@ -0,0 +1,17 @@
+module github.com/bytebase/parser
+
+go 1.24.5
+
+require (
+	github.com/antlr4-go/antlr/v4 v4.13.1
+	github.com/stretchr/testify v1.10.0
+)
+
+require (
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)
+
+replace github.com/antlr4-go/antlr/v4 => github.com/bytebase/antlr/v4 v4.0.0-20240827034948-8c385f108920

go.sum

@@ -0,0 +1,14 @@
+github.com/bytebase/antlr/v4 v4.0.0-20240827034948-8c385f108920 h1:IfmPt5o5R70NKtOrs+QHOoCgViYZelZysGxVBvV4ybA=
+github.com/bytebase/antlr/v4 v4.0.0-20240827034948-8c385f108920/go.mod h1:ykhjIPiv0IWpu3OGXCHdz2eUSe8UNGGD6baqjs8jSuU=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
+github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 h1:vr/HnozRka3pE4EsMEg1lgkXJkTFJCVUX+S/ZT6wYzM=
+golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842/go.mod h1:XtvwrStGgqGPLc4cjQfWqZHG1YFdYs6swckp8vpsjnc=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

redshift/CLAUDE.md

@@ -0,0 +1,132 @@
+# Redshift Parser Development Guide
+
+## Project Overview
+
+This repository is a Redshift parser built with ANTLR 4, forked from github.com/bytebase/postgresql-parser. Due to incompatibility issues with PostgreSQL, this separate repository was created to support Amazon Redshift-specific syntax and features.
+
+## Architecture
+
+### Core Components
+
+1. **ANTLR Grammar Files**:
+   - `RedshiftLexer.g4` - Tokenization rules for Redshift SQL
+   - `RedshiftParser.g4` - Parser grammar with 200+ statement types
+   - Generated Go files: `redshift_parser.go`, `redshift_lexer.go`, etc.
+
+2. **Base Classes**:
+   - `redshift_parser_base.go` - Engine-aware parser with PostgreSQL/Redshift support
+   - `redshift_lexer_base.go` - Base lexer implementation
+   - `string_stack.go` - Utility for string stack operations
+
+3. **Supporting Files**:
+   - `keywords.go` - 600+ PostgreSQL keywords with reserved status
+   - `builtin_function.go` - Built-in function definitions
+   - `build.sh` - ANTLR code generation script
+
+### Engine Support
+
+The parser supports multiple database engines:
+- `EnginePostgreSQL` - Standard PostgreSQL syntax
+- `EngineRedshift` - Amazon Redshift-specific syntax extensions
+
+## Development Guidelines
+
+### Code Conventions
+
+1. **Follow existing patterns**: Always examine existing code before making changes
+2. **Token/Rule/Name Convention**: Maintain consistency with current ANTLR grammar naming
+3. **Engine-specific features**: Use engine detection for Redshift-specific syntax
+4. **Error handling**: Implement proper error listeners and recovery mechanisms
+
+### Testing Requirements
+
+**CRITICAL**: Every change must include a related test case.
+
+1. **Test Structure**:
+   - Add SQL test files to the `examples/` directory
+   - Use Go-based tests in `parser_test.go` and `engine_specific_test.go`
+   - Tests automatically parse all SQL files in `examples/`
+
+2. **Test Content Sources**:
+   - Reference https://docs.aws.amazon.com/redshift/latest/dg/c_SQL_commands.html
+   - Crawl syntax examples from AWS Redshift documentation
+   - Use real-world SQL examples when possible
+
+3. **Test Categories**:
+   - DDL: CREATE, ALTER, DROP statements
+   - DML: SELECT, INSERT, UPDATE, DELETE
+   - Redshift-specific: IDENTITY columns, DISTKEY, SORTKEY, etc.
+   - Advanced: Window functions, CTEs, JSON operations
+
+### Adding New Features
+
+1. **Grammar Changes**:
+   ```bash
+   # Edit RedshiftLexer.g4 or RedshiftParser.g4
+   # Run build script to regenerate Go code
+   make build
+   ```
+
+2. **Engine-Specific Logic**:
+   - Use `GetEngine()` method to detect Redshift vs PostgreSQL
+   - Implement conditional parsing for dialect-specific features
+   - See `engine_specific_test.go` for examples
+
+3. **Testing Process**:
+   - Create SQL test files in `examples/`
+   - Run tests: `go test -v`
+   - Verify both parsing success and error handling
+
+### Common Tasks
+
+#### Adding Redshift-Specific Syntax
+
+1. Identify the syntax difference from PostgreSQL
+2. Update the appropriate grammar file (lexer or parser)
+3. Add engine-specific logic if needed
+4. Create test cases with AWS documentation examples
+5. Verify tests pass for both engines
+
+#### Adding New Keywords
+
+1. Add to `keywords.go` with appropriate reserved status
+2. Update lexer grammar if needed
+3. Test keyword recognition in various contexts
+
+#### Adding Built-in Functions
+
+1. Add to `builtin_function.go` in appropriate category
+2. Update parser rules if function has special syntax
+3. Test function parsing and recognition
+
+## Build and Test Commands
+
+**IMPORTANT**: Always run `./build.sh` before running tests to generate the latest Go code from ANTLR grammars.
+
+```bash
+# Generate parser code from ANTLR grammars (REQUIRED before testing)
+make build
+
+# Run all tests
+go test -v
+
+# Run specific test
+go test -run TestParser -v
+
+# Run benchmarks
+go test -bench=. -v
+```
+
+## References
+
+- [AWS Redshift SQL Commands](https://docs.aws.amazon.com/redshift/latest/dg/c_SQL_commands.html)
+- [ANTLR 4 Documentation](https://github.com/antlr/antlr4/blob/master/doc/index.md)
+- [PostgreSQL Grammar Reference](https://github.com/tunnelvisionlabs/antlr4-postgresql)
+
+## Contributing
+
+1. Always add test cases for new features
+2. Follow existing code patterns and conventions
+3. Test against both PostgreSQL and Redshift engines
+4. Use AWS documentation for accurate syntax examples
+5. Ensure all tests pass before submitting changes

redshift/Makefile

@@ -0,0 +1,6 @@
+all: build test
+
+build:
+	antlr -Dlanguage=Go -package redshift -visitor -o . RedshiftLexer.g4 RedshiftParser.g4
+
+test: go test -v -run TestRedshiftParser