Initial commit

.ci/beforeBuild.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+
+curl -L https://github.com/KOLANICH-libs/glossary.py/files/7643704/glossary.zip > glossary.zip;
+unzip glossary.zip;
+#sudo dpkg -i glossary_0.1.1_amd64.deb;
+curl -L https://raw.githubusercontent.com/waltonseymour/glossary/master/MOCK_DATA.csv > tests/MOCK_DATA.csv;
+bash -c "cd ./tests; glossary index ./MOCK_DATA.csv";

.ci/pythonPackagesToInstallFromGit.txt

@@ -0,0 +1,2 @@
+https://github.com/prebuilder/fsutilz.py.git
+https://github.com/kaitai-io/kaitai_struct_python_runtime.git

.editorconfig

@@ -0,0 +1,12 @@
+root = true
+
+[*]
+charset = utf-8
+indent_style = tab
+indent_size = 4
+insert_final_newline = true
+end_of_line = lf
+
+[*.{yml,yaml}]
+indent_style = space
+indent_size = 2

.github/.templateMarker

@@ -0,0 +1 @@
+KOLANICH/python_project_boilerplate.py

.github/dependabot.yml

@@ -0,0 +1,8 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    allow:
+      - dependency-type: "all"

.github/workflows/CI.yml

@@ -0,0 +1,15 @@
+name: CI
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: typical python workflow
+        uses: KOLANICH-GHActions/typical-python-workflow@master
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -0,0 +1,15 @@
+/tests/.glossary
+/tests/MOCK_DATA.csv
+/kaitai_struct_formats
+
+__pycache__
+*.pyc
+*.pyo
+/*.egg-info
+*.srctrlbm
+*.srctrldb
+build
+dist
+.eggs
+monkeytype.sqlite3
+/.ipynb_checkpoints

.gitlab-ci.yml

@@ -0,0 +1,51 @@
+image: registry.gitlab.com/kolanich-subgroups/docker-images/fixed_python:latest
+
+variables:
+  DOCKER_DRIVER: overlay2
+  SAST_ANALYZER_IMAGE_TAG: latest
+  SAST_DISABLE_DIND: "true"
+  SAST_CONFIDENCE_LEVEL: 5
+  CODECLIMATE_VERSION: latest
+
+include:
+  - template: SAST.gitlab-ci.yml
+  - template: Code-Quality.gitlab-ci.yml
+  - template: License-Management.gitlab-ci.yml
+
+build:
+  tags:
+    - shared
+    - linux
+  stage: build
+  variables:
+    GIT_DEPTH: "1"
+    PYTHONUSERBASE: ${CI_PROJECT_DIR}/python_user_packages
+
+  before_script:
+    - export PATH="$PATH:$PYTHONUSERBASE/bin" # don't move into `variables`
+    - apt-get update
+    # todo:
+    #- apt-get -y install 
+    #- pip3 install --upgrade 
+    #- python3 ./fix_python_modules_paths.py
+
+  script:
+    - python3 -m build -nw bdist_wheel
+    - mv ./dist/*.whl ./dist/glossary-0.CI-py3-none-any.whl
+    - pip3 install --upgrade ./dist/*.whl
+    - coverage run --source=glossary -m --branch pytest --junitxml=./rspec.xml ./tests/test.py
+    - coverage report -m
+    - coverage xml
+
+  coverage: "/^TOTAL(?:\\s+\\d+){4}\\s+(\\d+%).+/"
+
+  cache:
+    paths:
+      - $PYTHONUSERBASE
+
+  artifacts:
+    paths:
+      - dist
+    reports:
+      junit: ./rspec.xml
+      cobertura: ./coverage.xml

Code_Of_Conduct.md

@@ -0,0 +1 @@
+No codes of conduct!

MANIFEST.in

@@ -0,0 +1,4 @@
+include UNLICENSE
+include *.md
+include tests
+include .editorconfig

ReadMe.md

@@ -0,0 +1,8 @@
+glossary.py [![Unlicensed work](https://raw.githubusercontent.com/unlicense/unlicense.org/master/static/favicon.png)](https://unlicense.org/)
+===========
+[wheel (GHA via `nightly.link`)](https://nightly.link/KOLANICH-libs/glossary.py/workflows/CI/master/glossary-0.CI-py3-none-any.whl)
+[![GitHub Actions](https://github.com/KOLANICH-libs/glossary.py/workflows/CI/badge.svg)](https://github.com/KOLANICH-libs/glossary.py/actions/)
+[![Libraries.io Status](https://img.shields.io/librariesio/github/KOLANICH-libs/glossary.py.svg)](https://libraries.io/github/KOLANICH-libs/glossary.py)
+[![Code style: antiflash](https://img.shields.io/badge/code%20style-antiflash-FFF.svg)](https://github.com/KOLANICH-tools/antiflash.py)
+
+A pure python implementation of reader for index files produced by [`glossary`](https://github.com/waltonseymour/glossary) tool.

UNLICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <https://unlicense.org/>

glossary/__init__.py

@@ -0,0 +1,66 @@
+from pathlib import Path
+import typing
+
+import kaitaistruct
+from fsutilz import MMap
+
+from glossary.kaitai.glossary_index import GlossaryIndex
+
+from .kaitai.glossary_index import GlossaryIndex
+
+
+class Glossary:
+	__slots__ = ("path", "indexDir", "iF", "gIF", "map", "index")
+
+	DEFAULT_SUBDIR = ".glossary"
+	DEFAULT_METAINDEX_FILE_NAME = "top_index.bin"
+	DEFAULT_INDEX_FILE_NAME = "index.bin"
+
+	def __init__(self, path: Path, indexDir: typing.Optional[Path] = None) -> None:
+		self.path = path
+		if indexDir is None:
+			indexDir = path.parent / self.__class__.DEFAULT_SUBDIR
+		self.indexDir = indexDir
+		self.iF = None
+		self.gIF = None
+		self.map = None
+		self.index = None
+
+	def __exit__(self, *args, **kwargs) -> None:
+		self.index = None
+		if self.iF is not None:
+			self.iF.__exit__(*args, **kwargs)
+			self.iF = None
+
+		if self.gIF is not None:
+			self.gIF.__exit__(*args, **kwargs)
+			self.gIF = None
+
+		if self.map is not None:
+			self.map.__exit__(*args, **kwargs)
+			self.map = None
+
+	def parseMetaIndex(self) -> None:
+		globalIdxFile = self.indexDir / self.__class__.DEFAULT_METAINDEX_FILE_NAME
+		self.gIF = MMap(globalIdxFile).__enter__()
+		self.index = GlossaryIndex(kaitaistruct.KaitaiStream(self.iF), kaitaistruct.KaitaiStream(self.gIF))
+		self.gIF.__exit__(None, None, None)
+		self.gIF = None
+
+	def __enter__(self) -> "Glossary":
+		idxFile = self.indexDir / self.__class__.DEFAULT_INDEX_FILE_NAME
+		self.iF = MMap(idxFile).__enter__()
+		self.parseMetaIndex()
+		self.map = MMap(self.path).__enter__()
+		return self
+
+	def getLine(self, rec_descriptor: GlossaryIndex.RecordDescriptor) -> bytes:
+		line = self.map[rec_descriptor.record.offset :]
+		l = line.find(b"\n")
+		if l >= 0:
+			line = line[:l]
+		return line
+
+	def __iter__(self) -> typing.Iterator[bytes]:
+		for rec in self.index.records:
+			yield self.getLine(rec)

glossary/kaitai/glossary_index.py

@@ -0,0 +1,70 @@
+# This is a generated file! Please edit source .ksy file and use kaitai-struct-compiler to rebuild
+
+from pkg_resources import parse_version
+import kaitaistruct
+from kaitaistruct import KaitaiStruct, KaitaiStream, BytesIO
+
+
+if parse_version(kaitaistruct.__version__) < parse_version('0.9'):
+    raise Exception("Incompatible Kaitai Struct Python API: 0.9 or later is required, but you have %s" % (kaitaistruct.__version__))
+
+class GlossaryIndex(KaitaiStruct):
+    """'glossary' is a tool written in Rust to index flat files delimited by line breaks.
+    In fact the index can be used for any binary files.
+    
+    .. seealso::
+       Source - https://github.com/waltonseymour/glossary/blob/7cfc390d20afd7373749aa94e0b4ce0f30709f97/src/write.rs
+    """
+    def __init__(self, index_io, _io, _parent=None, _root=None):
+        self._io = _io
+        self._parent = _parent
+        self._root = _root if _root else self
+        self.index_io = index_io
+        self._read()
+
+    def _read(self):
+        self.records = []
+        i = 0
+        while not self._io.is_eof():
+            self.records.append(GlossaryIndex.RecordDescriptor(self._io, self, self._root))
+            i += 1
+
+
+    class RecordDescriptor(KaitaiStruct):
+        def __init__(self, _io, _parent=None, _root=None):
+            self._io = _io
+            self._parent = _parent
+            self._root = _root if _root else self
+            self._read()
+
+        def _read(self):
+            self.size = self._io.read_u8le()
+            self.offset = self._io.read_u8le()
+
+        class Record(KaitaiStruct):
+            def __init__(self, size, _io, _parent=None, _root=None):
+                self._io = _io
+                self._parent = _parent
+                self._root = _root if _root else self
+                self.size = size
+                self._read()
+
+            def _read(self):
+                self.key = self._io.read_bytes(self.size)
+                self.offset = self._io.read_u8le()
+
+
+        @property
+        def record(self):
+            if hasattr(self, '_m_record'):
+                return self._m_record if hasattr(self, '_m_record') else None
+
+            io = self._root.index_io
+            _pos = io.pos()
+            io.seek(self.offset)
+            self._m_record = GlossaryIndex.RecordDescriptor.Record(self.size, io, self, self._root)
+            io.seek(_pos)
+            return self._m_record if hasattr(self, '_m_record') else None
+
+
+

pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["setuptools>=61.2.0", "wheel", "setuptools_scm[toml]>=3.4.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "glossary"
+authors = [{name = "KOLANICH"}]
+description = "A pure python implementation of a reader for indexes produced by glossary tool."
+readme = "ReadMe.md"
+keywords = ["glossary"]
+license = {text = "Unlicense"}
+classifiers = [
+	"Programming Language :: Python",
+	"Programming Language :: Python :: 3",
+	"Development Status :: 4 - Beta",
+	"Environment :: Other Environment",
+	"Intended Audience :: Developers",
+	"License :: Public Domain",
+	#"License :: Public Domain :: Unlicense",
+	"Operating System :: OS Independent",
+	"Topic :: Software Development :: Libraries :: Python Modules",
+]
+requires-python = ">=3.4"
+dependencies = [
+	"kaitaistruct",
+	"fsutilz @ https://github.com/prebuilder/fsutilz.py",
+]
+dynamic = ["version"]
+
+
+[project.urls]
+Homepage = "https://github.com/KOLANICH-libs/glossary.py"
+
+[tool.setuptools]
+zip-safe = true
+include-package-data = false
+
+[tool.setuptools.packages]
+find = {namespaces = false}
+
+[tool.setuptools_scm]
+
+[tool.kaitai.repos."https://github.com/KOLANICH/kaitai_struct_formats.git"."glossary_index"]
+update = true
+search = false
+localPath = "kaitai_struct_formats" # rel to pyproject.toml dir
+outputDir = "glossary/kaitai" # rel to localPath
+inputDir = "database"
+
+[tool.kaitai.repos."https://github.com/KOLANICH/kaitai_struct_formats.git"."glossary_index".formats.glossary_index]
+path = "glossary_index.ksy"

tests/tests.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+import csv
+import sys
+import unittest
+from pathlib import Path
+
+thisDir = Path(__file__).parent
+
+sys.path.insert(0, str(thisDir.parent))
+
+from collections import OrderedDict
+
+dict = OrderedDict
+
+from glossary import Glossary
+
+
+class Tests(unittest.TestCase):
+	def testReading(self):
+		with Glossary(thisDir / "MOCK_DATA.csv") as p:
+			for line in p:
+				iD = tuple(csv.reader([line.decode("utf-8")]))[0]
+
+
+if __name__ == "__main__":
+	unittest.main()