lexcql-parser 1.0.0__tar.gz

lexcql_parser-1.0.0/PKG-INFO

@@ -0,0 +1,167 @@
+Metadata-Version: 2.4
+Name: lexcql-parser
+Version: 1.0.0
+Summary: LexCQL Query Grammar and Parser
+Keywords: LexCQL,FCS,CQL,Query Parser
+Author: Erik Körner
+Author-email: Erik Körner <koerner@saw-leipzig.de>
+License-Expression: MIT
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Text Processing :: General
+Classifier: Topic :: Utilities
+Requires-Dist: antlr4-python3-runtime>=4.13.2
+Requires-Dist: antlr4-tools>=0.2.2 ; extra == 'antlr'
+Requires-Dist: twine>=6.2.0 ; extra == 'build'
+Requires-Dist: black>=26.1.0 ; extra == 'style'
+Requires-Dist: flake8>=7.3.0 ; extra == 'style'
+Requires-Dist: isort>=8.0.0 ; extra == 'style'
+Requires-Dist: pytest>=9.0.2 ; extra == 'test'
+Requires-Dist: pytest-clarity>=1.0.1 ; extra == 'test'
+Requires-Dist: pytest-cov>=7.0.0 ; extra == 'test'
+Requires-Dist: pytest-randomly>=4.0.1 ; extra == 'test'
+Requires-Python: >=3.10
+Project-URL: Source, https://github.com/Querela/lexcql-python.git
+Project-URL: Issues, https://github.com/Querela/lexcql-python/issues
+Provides-Extra: antlr
+Provides-Extra: build
+Provides-Extra: style
+Provides-Extra: test
+Description-Content-Type: text/markdown
+
+# LexCQL for Python
+
+A query parser for LexCQL, the query language for lexical resources in the CLARIN Federated Content Search (FCS).
+
+## Installation
+
+Install from PyPI:
+
+```bash
+pip install lexcql-parser
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/Querela/lexcql-python.git
+cd lexcql-python
+uv build
+
+# built package
+python3 -m pip install dist/lexcql_parser-<version>-py3-none-any.whl
+# or
+python3 -m pip install dist/lexcql_parser-<version>.tar.gz
+
+# for local development
+python3 -m pip install -e .
+```
+
+## Usage
+
+The high-level interface `lexcql.parser.QueryParser` wraps the ANTLR4 parse tree into a simplified query node tree that is easier to work with. The `lexcql-parser` exposes a simple parsing function with `lexcql.parse(input: str, enableSourceLocations: bool = True) -> lexcql.parser.QueryNode`:
+
+```python
+import lexcql
+
+## parsing a valid query into a query node tree
+# our query input string
+input = "Banane Or lemma =/lang=eng apple"
+# parse into QueryNode tree
+sc = lexcql.parse(input)
+# print stringified tree
+print(str(sc))
+
+## handling possibly invalid queries
+input = "broken query"
+try:
+    lexcql.parse(input)
+except lexcql.QueryParserException as ex:
+    print(f"Error: {ex}")
+```
+
+You can also use the more low-level ANTLR4 framework to parse the query string. A handy wrapper is provided with `lexcql.antlr_parse(input: str) -> LexParser.QueryContext`.
+
+```python
+from antlr4 import CommonTokenStream, InputStream
+from lexcql.parser import LexLexer, LexParser
+
+input = "example"
+input_stream = InputStream(input)
+lexer = LexLexer(input_stream)
+stream = CommonTokenStream(lexer)
+parser = LexParser(stream)
+tree: LexParser.QueryContext = parser.query()
+```
+
+## Development
+
+Fetch (or update) grammar files:
+
+```bash
+git clone https://github.com/clarin-eric/fcs-ql.git
+cp fcs-ql/src/main/antlr4/eu/clarin/sru/fcs/qlparser/lex/*.g4 src/lexcql/
+```
+
+(Re-)Generate python parser code:
+
+```bash
+# setup environment
+uv sync --extra antlr
+# NOTE: you can activate the environment (if you do not want to prefix everything with `uv run`)
+# NOTE: `uv` does not play nicely with `pyenv` - if you use `pyenv`, sourcing does NOT work!
+source .venv/bin/activate
+
+cd src/lexcql
+uv run antlr4 -Dlanguage=Python3 *.g4
+```
+
+Run style checks:
+
+```bash
+# setup environment
+uv sync --extra style
+
+uv run black --check .
+uv run flake8 . --show-source --statistics
+uv run isort --check --diff .
+```
+
+Run tests:
+
+```bash
+# setup environment
+uv sync --extra test
+
+uv run pytest
+```
+
+Run check before publishing:
+
+```bash
+# setup environment
+uv sync --extra build
+
+# build the package
+uv build
+# run metadata check
+uv run twine check --strict dist/*
+# (manual) check of package contents
+tar tvf dist/lexcql-*.tar.gz
+```
+
+## See also
+
+- [clarin-eric/fcq-ql](https://github.com/clarin-eric/fcs-ql) - FCS-QL/LexCQL Parser (Java)
+- [Querela/fcs-ql-python](https://github.com/Querela/fcs-ql-python) - FCS-QL Parser (Python)
+- [Specification on CLARIN FCS 2](https://www.clarin.eu/content/federated-content-search-clarin-fcs-technical-details) - CLARIN FCS Overview
+- [Specification on LexFCS](https://doi.org/10.5281/zenodo.7849753) - Published LexFCS Specification

lexcql_parser-1.0.0/README.md

@@ -0,0 +1,127 @@
+# LexCQL for Python
+
+A query parser for LexCQL, the query language for lexical resources in the CLARIN Federated Content Search (FCS).
+
+## Installation
+
+Install from PyPI:
+
+```bash
+pip install lexcql-parser
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/Querela/lexcql-python.git
+cd lexcql-python
+uv build
+
+# built package
+python3 -m pip install dist/lexcql_parser-<version>-py3-none-any.whl
+# or
+python3 -m pip install dist/lexcql_parser-<version>.tar.gz
+
+# for local development
+python3 -m pip install -e .
+```
+
+## Usage
+
+The high-level interface `lexcql.parser.QueryParser` wraps the ANTLR4 parse tree into a simplified query node tree that is easier to work with. The `lexcql-parser` exposes a simple parsing function with `lexcql.parse(input: str, enableSourceLocations: bool = True) -> lexcql.parser.QueryNode`:
+
+```python
+import lexcql
+
+## parsing a valid query into a query node tree
+# our query input string
+input = "Banane Or lemma =/lang=eng apple"
+# parse into QueryNode tree
+sc = lexcql.parse(input)
+# print stringified tree
+print(str(sc))
+
+## handling possibly invalid queries
+input = "broken query"
+try:
+    lexcql.parse(input)
+except lexcql.QueryParserException as ex:
+    print(f"Error: {ex}")
+```
+
+You can also use the more low-level ANTLR4 framework to parse the query string. A handy wrapper is provided with `lexcql.antlr_parse(input: str) -> LexParser.QueryContext`.
+
+```python
+from antlr4 import CommonTokenStream, InputStream
+from lexcql.parser import LexLexer, LexParser
+
+input = "example"
+input_stream = InputStream(input)
+lexer = LexLexer(input_stream)
+stream = CommonTokenStream(lexer)
+parser = LexParser(stream)
+tree: LexParser.QueryContext = parser.query()
+```
+
+## Development
+
+Fetch (or update) grammar files:
+
+```bash
+git clone https://github.com/clarin-eric/fcs-ql.git
+cp fcs-ql/src/main/antlr4/eu/clarin/sru/fcs/qlparser/lex/*.g4 src/lexcql/
+```
+
+(Re-)Generate python parser code:
+
+```bash
+# setup environment
+uv sync --extra antlr
+# NOTE: you can activate the environment (if you do not want to prefix everything with `uv run`)
+# NOTE: `uv` does not play nicely with `pyenv` - if you use `pyenv`, sourcing does NOT work!
+source .venv/bin/activate
+
+cd src/lexcql
+uv run antlr4 -Dlanguage=Python3 *.g4
+```
+
+Run style checks:
+
+```bash
+# setup environment
+uv sync --extra style
+
+uv run black --check .
+uv run flake8 . --show-source --statistics
+uv run isort --check --diff .
+```
+
+Run tests:
+
+```bash
+# setup environment
+uv sync --extra test
+
+uv run pytest
+```
+
+Run check before publishing:
+
+```bash
+# setup environment
+uv sync --extra build
+
+# build the package
+uv build
+# run metadata check
+uv run twine check --strict dist/*
+# (manual) check of package contents
+tar tvf dist/lexcql-*.tar.gz
+```
+
+## See also
+
+- [clarin-eric/fcq-ql](https://github.com/clarin-eric/fcs-ql) - FCS-QL/LexCQL Parser (Java)
+- [Querela/fcs-ql-python](https://github.com/Querela/fcs-ql-python) - FCS-QL Parser (Python)
+- [Specification on CLARIN FCS 2](https://www.clarin.eu/content/federated-content-search-clarin-fcs-technical-details) - CLARIN FCS Overview
+- [Specification on LexFCS](https://doi.org/10.5281/zenodo.7849753) - Published LexFCS Specification

lexcql_parser-1.0.0/pyproject.toml

@@ -0,0 +1,88 @@
+[project]
+name = "lexcql-parser"
+version = "1.0.0"
+description = "LexCQL Query Grammar and Parser"
+readme = "README.md"
+license = "MIT"
+authors = [
+    { name = "Erik Körner", email = "koerner@saw-leipzig.de" }
+]
+keywords = [
+    "LexCQL",
+    "FCS",
+    "CQL",
+    "Query Parser"
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Text Processing :: General",
+    "Topic :: Utilities",
+]
+requires-python = ">=3.10"
+dependencies = [
+    "antlr4-python3-runtime>=4.13.2",
+]
+
+[project.urls]
+Source = "https://github.com/Querela/lexcql-python.git"
+Issues = "https://github.com/Querela/lexcql-python/issues"
+
+[project.optional-dependencies]
+antlr = [
+    "antlr4-tools>=0.2.2",
+]
+test = [
+    "pytest>=9.0.2",
+    "pytest-clarity>=1.0.1",
+    "pytest-cov>=7.0.0",
+    "pytest-randomly>=4.0.1",
+]
+style = [
+    "black>=26.1.0",
+    "flake8>=7.3.0",
+    "isort>=8.0.0",
+]
+build = [
+    "twine>=6.2.0",
+]
+
+[build-system]
+requires = ["uv_build>=0.10.2,<0.11.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-name = "lexcql"
+source-exclude = [".antlr"]
+
+[tool.black]
+line-length = 120
+extend-exclude = '''
+(
+  (Lex(Lexer|Parser(Listener)?)).py
+)
+'''
+
+[tool.isort]
+force_single_line = true
+line_length = 120
+known_first_party = "lexcql"
+default_section = "THIRDPARTY"
+forced_separate = "test_lexcql"
+skip = [
+    ".venv",
+    "dist",
+    "src/lexcql/LexParser.py",
+    "src/lexcql/LexLexer.py",
+    "src/lexcql/LexParserListener.py",
+]
+skip_gitignore = true

lexcql_parser-1.0.0/src/lexcql/LexLexer.g4

@@ -0,0 +1,39 @@
+lexer grammar LexLexer;
+
+/* search clauses */
+
+L_PAREN: '(';
+R_PAREN: ')';
+
+/* relations */
+
+EQUAL: '=';
+GREATER: '>';
+LESSER: '<';
+GREATER_EQUAL: '>=';
+LESSER_EQUAL: '<=';
+NOT_EQUAL: '<>';
+EQUAL_EQUAL: '==';
+
+/* modifiers */
+
+SLASH: '/';
+
+/* booleans */
+
+AND: [Aa][Nn][Dd];
+OR: [Oo][Rr];
+NOT: [Nn][Oo][Tt];
+
+/* terminals */
+
+DOT: '.';
+
+QUOTED_STRING: '"' ('\\' ["\\] | ~["\\])* '"';
+
+// whitespace must be explicit here as inverted sets can use rules/fragments
+SIMPLE_STRING: (~["\\()/<=> \t\n\r])+;
+
+/* whitespace */
+
+WS: [ \t\n\r] -> channel(HIDDEN);

lexcql_parser-1.0.0/src/lexcql/LexLexer.interp

@@ -0,0 +1,68 @@
+token literal names:
+null
+'('
+')'
+'='
+'>'
+'<'
+'>='
+'<='
+'<>'
+'=='
+'/'
+null
+null
+null
+'.'
+null
+null
+null
+
+token symbolic names:
+null
+L_PAREN
+R_PAREN
+EQUAL
+GREATER
+LESSER
+GREATER_EQUAL
+LESSER_EQUAL
+NOT_EQUAL
+EQUAL_EQUAL
+SLASH
+AND
+OR
+NOT
+DOT
+QUOTED_STRING
+SIMPLE_STRING
+WS
+
+rule names:
+L_PAREN
+R_PAREN
+EQUAL
+GREATER
+LESSER
+GREATER_EQUAL
+LESSER_EQUAL
+NOT_EQUAL
+EQUAL_EQUAL
+SLASH
+AND
+OR
+NOT
+DOT
+QUOTED_STRING
+SIMPLE_STRING
+WS
+
+channel names:
+DEFAULT_TOKEN_CHANNEL
+HIDDEN
+
+mode names:
+DEFAULT_MODE
+
+atn:
+[4, 0, 17, 92, 6, -1, 2, 0, 7, 0, 2, 1, 7, 1, 2, 2, 7, 2, 2, 3, 7, 3, 2, 4, 7, 4, 2, 5, 7, 5, 2, 6, 7, 6, 2, 7, 7, 7, 2, 8, 7, 8, 2, 9, 7, 9, 2, 10, 7, 10, 2, 11, 7, 11, 2, 12, 7, 12, 2, 13, 7, 13, 2, 14, 7, 14, 2, 15, 7, 15, 2, 16, 7, 16, 1, 0, 1, 0, 1, 1, 1, 1, 1, 2, 1, 2, 1, 3, 1, 3, 1, 4, 1, 4, 1, 5, 1, 5, 1, 5, 1, 6, 1, 6, 1, 6, 1, 7, 1, 7, 1, 7, 1, 8, 1, 8, 1, 8, 1, 9, 1, 9, 1, 10, 1, 10, 1, 10, 1, 10, 1, 11, 1, 11, 1, 11, 1, 12, 1, 12, 1, 12, 1, 12, 1, 13, 1, 13, 1, 14, 1, 14, 1, 14, 1, 14, 5, 14, 77, 8, 14, 10, 14, 12, 14, 80, 9, 14, 1, 14, 1, 14, 1, 15, 4, 15, 85, 8, 15, 11, 15, 12, 15, 86, 1, 16, 1, 16, 1, 16, 1, 16, 0, 0, 17, 1, 1, 3, 2, 5, 3, 7, 4, 9, 5, 11, 6, 13, 7, 15, 8, 17, 9, 19, 10, 21, 11, 23, 12, 25, 13, 27, 14, 29, 15, 31, 16, 33, 17, 1, 0, 9, 2, 0, 65, 65, 97, 97, 2, 0, 78, 78, 110, 110, 2, 0, 68, 68, 100, 100, 2, 0, 79, 79, 111, 111, 2, 0, 82, 82, 114, 114, 2, 0, 84, 84, 116, 116, 2, 0, 34, 34, 92, 92, 8, 0, 9, 10, 13, 13, 32, 32, 34, 34, 40, 41, 47, 47, 60, 62, 92, 92, 3, 0, 9, 10, 13, 13, 32, 32, 94, 0, 1, 1, 0, 0, 0, 0, 3, 1, 0, 0, 0, 0, 5, 1, 0, 0, 0, 0, 7, 1, 0, 0, 0, 0, 9, 1, 0, 0, 0, 0, 11, 1, 0, 0, 0, 0, 13, 1, 0, 0, 0, 0, 15, 1, 0, 0, 0, 0, 17, 1, 0, 0, 0, 0, 19, 1, 0, 0, 0, 0, 21, 1, 0, 0, 0, 0, 23, 1, 0, 0, 0, 0, 25, 1, 0, 0, 0, 0, 27, 1, 0, 0, 0, 0, 29, 1, 0, 0, 0, 0, 31, 1, 0, 0, 0, 0, 33, 1, 0, 0, 0, 1, 35, 1, 0, 0, 0, 3, 37, 1, 0, 0, 0, 5, 39, 1, 0, 0, 0, 7, 41, 1, 0, 0, 0, 9, 43, 1, 0, 0, 0, 11, 45, 1, 0, 0, 0, 13, 48, 1, 0, 0, 0, 15, 51, 1, 0, 0, 0, 17, 54, 1, 0, 0, 0, 19, 57, 1, 0, 0, 0, 21, 59, 1, 0, 0, 0, 23, 63, 1, 0, 0, 0, 25, 66, 1, 0, 0, 0, 27, 70, 1, 0, 0, 0, 29, 72, 1, 0, 0, 0, 31, 84, 1, 0, 0, 0, 33, 88, 1, 0, 0, 0, 35, 36, 5, 40, 0, 0, 36, 2, 1, 0, 0, 0, 37, 38, 5, 41, 0, 0, 38, 4, 1, 0, 0, 0, 39, 40, 5, 61, 0, 0, 40, 6, 1, 0, 0, 0, 41, 42, 5, 62, 0, 0, 42, 8, 1, 0, 0, 0, 43, 44, 5, 60, 0, 0, 44, 10, 1, 0, 0, 0, 45, 46, 5, 62, 0, 0, 46, 47, 5, 61, 0, 0, 47, 12, 1, 0, 0, 0, 48, 49, 5, 60, 0, 0, 49, 50, 5, 61, 0, 0, 50, 14, 1, 0, 0, 0, 51, 52, 5, 60, 0, 0, 52, 53, 5, 62, 0, 0, 53, 16, 1, 0, 0, 0, 54, 55, 5, 61, 0, 0, 55, 56, 5, 61, 0, 0, 56, 18, 1, 0, 0, 0, 57, 58, 5, 47, 0, 0, 58, 20, 1, 0, 0, 0, 59, 60, 7, 0, 0, 0, 60, 61, 7, 1, 0, 0, 61, 62, 7, 2, 0, 0, 62, 22, 1, 0, 0, 0, 63, 64, 7, 3, 0, 0, 64, 65, 7, 4, 0, 0, 65, 24, 1, 0, 0, 0, 66, 67, 7, 1, 0, 0, 67, 68, 7, 3, 0, 0, 68, 69, 7, 5, 0, 0, 69, 26, 1, 0, 0, 0, 70, 71, 5, 46, 0, 0, 71, 28, 1, 0, 0, 0, 72, 78, 5, 34, 0, 0, 73, 74, 5, 92, 0, 0, 74, 77, 7, 6, 0, 0, 75, 77, 8, 6, 0, 0, 76, 73, 1, 0, 0, 0, 76, 75, 1, 0, 0, 0, 77, 80, 1, 0, 0, 0, 78, 76, 1, 0, 0, 0, 78, 79, 1, 0, 0, 0, 79, 81, 1, 0, 0, 0, 80, 78, 1, 0, 0, 0, 81, 82, 5, 34, 0, 0, 82, 30, 1, 0, 0, 0, 83, 85, 8, 7, 0, 0, 84, 83, 1, 0, 0, 0, 85, 86, 1, 0, 0, 0, 86, 84, 1, 0, 0, 0, 86, 87, 1, 0, 0, 0, 87, 32, 1, 0, 0, 0, 88, 89, 7, 8, 0, 0, 89, 90, 1, 0, 0, 0, 90, 91, 6, 16, 0, 0, 91, 34, 1, 0, 0, 0, 4, 0, 76, 78, 86, 1, 0, 1, 0]

lexcql_parser-1.0.0/src/lexcql/LexLexer.py

@@ -0,0 +1,98 @@
+# Generated from LexLexer.g4 by ANTLR 4.13.2
+from antlr4 import *
+from io import StringIO
+import sys
+if sys.version_info[1] > 5:
+    from typing import TextIO
+else:
+    from typing.io import TextIO
+
+
+def serializedATN():
+    return [
+        4,0,17,92,6,-1,2,0,7,0,2,1,7,1,2,2,7,2,2,3,7,3,2,4,7,4,2,5,7,5,2,
+        6,7,6,2,7,7,7,2,8,7,8,2,9,7,9,2,10,7,10,2,11,7,11,2,12,7,12,2,13,
+        7,13,2,14,7,14,2,15,7,15,2,16,7,16,1,0,1,0,1,1,1,1,1,2,1,2,1,3,1,
+        3,1,4,1,4,1,5,1,5,1,5,1,6,1,6,1,6,1,7,1,7,1,7,1,8,1,8,1,8,1,9,1,
+        9,1,10,1,10,1,10,1,10,1,11,1,11,1,11,1,12,1,12,1,12,1,12,1,13,1,
+        13,1,14,1,14,1,14,1,14,5,14,77,8,14,10,14,12,14,80,9,14,1,14,1,14,
+        1,15,4,15,85,8,15,11,15,12,15,86,1,16,1,16,1,16,1,16,0,0,17,1,1,
+        3,2,5,3,7,4,9,5,11,6,13,7,15,8,17,9,19,10,21,11,23,12,25,13,27,14,
+        29,15,31,16,33,17,1,0,9,2,0,65,65,97,97,2,0,78,78,110,110,2,0,68,
+        68,100,100,2,0,79,79,111,111,2,0,82,82,114,114,2,0,84,84,116,116,
+        2,0,34,34,92,92,8,0,9,10,13,13,32,32,34,34,40,41,47,47,60,62,92,
+        92,3,0,9,10,13,13,32,32,94,0,1,1,0,0,0,0,3,1,0,0,0,0,5,1,0,0,0,0,
+        7,1,0,0,0,0,9,1,0,0,0,0,11,1,0,0,0,0,13,1,0,0,0,0,15,1,0,0,0,0,17,
+        1,0,0,0,0,19,1,0,0,0,0,21,1,0,0,0,0,23,1,0,0,0,0,25,1,0,0,0,0,27,
+        1,0,0,0,0,29,1,0,0,0,0,31,1,0,0,0,0,33,1,0,0,0,1,35,1,0,0,0,3,37,
+        1,0,0,0,5,39,1,0,0,0,7,41,1,0,0,0,9,43,1,0,0,0,11,45,1,0,0,0,13,
+        48,1,0,0,0,15,51,1,0,0,0,17,54,1,0,0,0,19,57,1,0,0,0,21,59,1,0,0,
+        0,23,63,1,0,0,0,25,66,1,0,0,0,27,70,1,0,0,0,29,72,1,0,0,0,31,84,
+        1,0,0,0,33,88,1,0,0,0,35,36,5,40,0,0,36,2,1,0,0,0,37,38,5,41,0,0,
+        38,4,1,0,0,0,39,40,5,61,0,0,40,6,1,0,0,0,41,42,5,62,0,0,42,8,1,0,
+        0,0,43,44,5,60,0,0,44,10,1,0,0,0,45,46,5,62,0,0,46,47,5,61,0,0,47,
+        12,1,0,0,0,48,49,5,60,0,0,49,50,5,61,0,0,50,14,1,0,0,0,51,52,5,60,
+        0,0,52,53,5,62,0,0,53,16,1,0,0,0,54,55,5,61,0,0,55,56,5,61,0,0,56,
+        18,1,0,0,0,57,58,5,47,0,0,58,20,1,0,0,0,59,60,7,0,0,0,60,61,7,1,
+        0,0,61,62,7,2,0,0,62,22,1,0,0,0,63,64,7,3,0,0,64,65,7,4,0,0,65,24,
+        1,0,0,0,66,67,7,1,0,0,67,68,7,3,0,0,68,69,7,5,0,0,69,26,1,0,0,0,
+        70,71,5,46,0,0,71,28,1,0,0,0,72,78,5,34,0,0,73,74,5,92,0,0,74,77,
+        7,6,0,0,75,77,8,6,0,0,76,73,1,0,0,0,76,75,1,0,0,0,77,80,1,0,0,0,
+        78,76,1,0,0,0,78,79,1,0,0,0,79,81,1,0,0,0,80,78,1,0,0,0,81,82,5,
+        34,0,0,82,30,1,0,0,0,83,85,8,7,0,0,84,83,1,0,0,0,85,86,1,0,0,0,86,
+        84,1,0,0,0,86,87,1,0,0,0,87,32,1,0,0,0,88,89,7,8,0,0,89,90,1,0,0,
+        0,90,91,6,16,0,0,91,34,1,0,0,0,4,0,76,78,86,1,0,1,0
+    ]
+
+class LexLexer(Lexer):
+
+    atn = ATNDeserializer().deserialize(serializedATN())
+
+    decisionsToDFA = [ DFA(ds, i) for i, ds in enumerate(atn.decisionToState) ]
+
+    L_PAREN = 1
+    R_PAREN = 2
+    EQUAL = 3
+    GREATER = 4
+    LESSER = 5
+    GREATER_EQUAL = 6
+    LESSER_EQUAL = 7
+    NOT_EQUAL = 8
+    EQUAL_EQUAL = 9
+    SLASH = 10
+    AND = 11
+    OR = 12
+    NOT = 13
+    DOT = 14
+    QUOTED_STRING = 15
+    SIMPLE_STRING = 16
+    WS = 17
+
+    channelNames = [ u"DEFAULT_TOKEN_CHANNEL", u"HIDDEN" ]
+
+    modeNames = [ "DEFAULT_MODE" ]
+
+    literalNames = [ "<INVALID>",
+            "'('", "')'", "'='", "'>'", "'<'", "'>='", "'<='", "'<>'", "'=='", 
+            "'/'", "'.'" ]
+
+    symbolicNames = [ "<INVALID>",
+            "L_PAREN", "R_PAREN", "EQUAL", "GREATER", "LESSER", "GREATER_EQUAL", 
+            "LESSER_EQUAL", "NOT_EQUAL", "EQUAL_EQUAL", "SLASH", "AND", 
+            "OR", "NOT", "DOT", "QUOTED_STRING", "SIMPLE_STRING", "WS" ]
+
+    ruleNames = [ "L_PAREN", "R_PAREN", "EQUAL", "GREATER", "LESSER", "GREATER_EQUAL", 
+                  "LESSER_EQUAL", "NOT_EQUAL", "EQUAL_EQUAL", "SLASH", "AND", 
+                  "OR", "NOT", "DOT", "QUOTED_STRING", "SIMPLE_STRING", 
+                  "WS" ]
+
+    grammarFileName = "LexLexer.g4"
+
+    def __init__(self, input=None, output:TextIO = sys.stdout):
+        super().__init__(input, output)
+        self.checkVersion("4.13.2")
+        self._interp = LexerATNSimulator(self, self.atn, self.decisionsToDFA, PredictionContextCache())
+        self._actions = None
+        self._predicates = None
+
+

lexcql_parser-1.0.0/src/lexcql/LexLexer.tokens

@@ -0,0 +1,28 @@
+L_PAREN=1
+R_PAREN=2
+EQUAL=3
+GREATER=4
+LESSER=5
+GREATER_EQUAL=6
+LESSER_EQUAL=7
+NOT_EQUAL=8
+EQUAL_EQUAL=9
+SLASH=10
+AND=11
+OR=12
+NOT=13
+DOT=14
+QUOTED_STRING=15
+SIMPLE_STRING=16
+WS=17
+'('=1
+')'=2
+'='=3
+'>'=4
+'<'=5
+'>='=6
+'<='=7
+'<>'=8
+'=='=9
+'/'=10
+'.'=14

lexcql_parser-1.0.0/src/lexcql/LexParser.g4

@@ -0,0 +1,79 @@
+parser grammar LexParser;
+options {
+	tokenVocab = LexLexer;
+}
+
+/* ABNF: https://docs.oasis-open.org/search-ws/searchRetrieve/v1.0/os/part5-cql/searchRetrieve-v1.0-os-part5-cql.html */
+/* Test in: http://lab.antlr.org/ */
+/* Slides: https://www.esa.informatik.tu-darmstadt.de/archive/twiki/pub/Lectures/Compiler113De/antlr-v4-handout.pdf */
+
+/* search clauses */
+
+//  ! original ABNF rule: does not work due to left-recursion
+//
+//  query: search_clause_group;
+//  search_clause_group: (search_clause_group boolean_modified subquery) | subquery;
+//  subquery: (L_PAREN query R_PAREN) | search_clause;
+
+//  flat lists as alternative? need to be interpreted left to right
+//
+//  search_clause_group: (subquery boolean_modified)* subquery;
+//  search_clause_group: subquery (boolean_modified subquery)*;
+
+// simplify and make it flat
+query: boolean_query EOF;
+
+boolean_query: subquery (boolean_modified subquery)*;
+
+subquery: L_PAREN boolean_query R_PAREN | search_clause;
+
+search_clause: (index relation_modified)? search_term;
+
+search_term: SIMPLE_STRING | QUOTED_STRING;
+
+/* indexes */
+
+index: simple_name | prefix_name;
+
+/* relations */
+
+relation_modified: relation modifier_list?;
+
+relation: relation_name | relation_symbol;
+
+relation_name: simple_name | prefix_name;
+
+relation_symbol:
+	EQUAL
+	| GREATER
+	| LESSER
+	| GREATER_EQUAL
+	| LESSER_EQUAL
+	| NOT_EQUAL
+	| EQUAL_EQUAL;
+
+/* booleans */
+
+boolean_modified: r_boolean modifier_list?;
+
+r_boolean: AND | OR | NOT;
+
+/* modifiers */
+
+modifier_list: modifier+;
+
+modifier: SLASH modifier_name modifier_relation?;
+
+modifier_name: simple_name;
+
+modifier_relation: relation_symbol modifier_value;
+
+modifier_value: SIMPLE_STRING | QUOTED_STRING;
+
+/* terminal aliases */
+
+prefix_name: prefix DOT simple_name;
+
+prefix: simple_name;
+
+simple_name: SIMPLE_STRING;