theme-extractor 0.1.0__tar.gz

theme_extractor-0.1.0/.gitignore

@@ -0,0 +1,255 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,dotenv,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,macos,dotenv,python
+
+### dotenv ###
+.env
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/_generated/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,dotenv,python
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+
+# Local IDE metadata
+.idea/
+
+# Local environment files (keep template versioned)
+.env.*
+!.env.template
+
+# Local runtime artifacts
+*.sqlite
+*.sqlite3
+
+# Local project datasets, generated outputs and caches
+data/out/**
+data/raw/**
+data/models/**
+data/cache/**
+!data/out/.gitkeep
+!data/raw/.gitkeep
+!data/models/.gitkeep
+!data/cache/.gitkeep

theme_extractor-0.1.0/LICENSE.md

@@ -0,0 +1,21 @@
+# MIT License
+
+Copyright (c) 2026 Guillaume Lombardo
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+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 OR COPYRIGHT HOLDERS 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.

theme_extractor-0.1.0/PKG-INFO

@@ -0,0 +1,175 @@
+Metadata-Version: 2.4
+Name: theme-extractor
+Version: 0.1.0
+Summary: Parse a corpus, manage it and extract themes from a corpus.
+Project-URL: Homepage, https://github.com/Guillaume-Lombardo/theme-extractor
+Project-URL: Repository, https://github.com/Guillaume-Lombardo/theme-extractor
+Project-URL: Issues, https://github.com/Guillaume-Lombardo/theme-extractor/issues
+License: # MIT License
+        
+        Copyright (c) 2026 Guillaume Lombardo
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        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 OR COPYRIGHT HOLDERS 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.
+License-File: LICENSE.md
+Keywords: BERTopics,cli,corpus management,elasticsearch,keyBERT,llm,opensearch,python,sentence-transformers,text analysis,theme extraction
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.13
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: pydantic-settings>=2.12.0
+Requires-Dist: pydantic>=2.12.0
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: structlog>=25.5.0
+Description-Content-Type: text/markdown
+
+# theme-extractor
+
+Python toolkit to compare theme/topic extraction strategies on the same corpus, with:
+
+- one unified CLI
+- one unified JSON output schema
+- offline-first execution options
+- Elasticsearch/OpenSearch backend support
+
+## Why this project
+
+`theme-extractor` helps you answer one practical question:
+"Which extraction strategy works best for my corpus and constraints?"
+
+It lets you run baseline lexical methods, embedding-based methods, and LLM-assisted methods with consistent outputs for easier comparison.
+
+## Core Commands
+
+- `theme-extractor ingest`
+- `theme-extractor extract`
+- `theme-extractor benchmark`
+- `theme-extractor evaluate`
+- `theme-extractor report`
+- `theme-extractor doctor`
+
+## Quickstart
+
+Prerequisite: start one backend first (local Docker guide: [`/howto/docker-local.md`](howto/docker-local.md)).
+
+```bash
+uv sync --group elasticsearch
+uv run theme-extractor doctor --output data/out/doctor.json
+uv run theme-extractor ingest --input data/raw --output data/out/ingest.json
+uv run theme-extractor benchmark \
+  --methods baseline_tfidf,terms,significant_terms,keybert,bertopic \
+  --backend elasticsearch \
+  --backend-url http://localhost:9200 \
+  --index theme_extractor \
+  --focus both \
+  --output data/out/benchmark.json
+uv run theme-extractor evaluate \
+  --input data/out/benchmark.json \
+  --output data/out/evaluation.json
+uv run theme-extractor report \
+  --input data/out/benchmark.json \
+  --output data/out/report_benchmark.md
+```
+
+Run `significant_text` separately with `--agg-field content` (see [`/howto/benchmark.md`](howto/benchmark.md)).
+
+## Methods Available
+
+- Baselines:
+  - `baseline_tfidf`
+  - `terms`
+  - `significant_terms`
+  - `significant_text`
+- Semantic:
+  - `keybert`
+  - `bertopic` (embedding on/off, reduction `none/svd/nmf/umap`, clustering `kmeans/hdbscan`)
+- Generative:
+  - `llm` (offline fallback behavior supported)
+
+## What You Get
+
+- Unified extraction schema:
+  - topic-first output (`topics`)
+  - optional document-topic links (`document_topics`)
+  - execution notes and metadata (`notes`, `metadata`)
+- Benchmark output:
+  - per-method outputs
+  - comparison block
+- Quantitative proxies via `evaluate`:
+  - topic coherence proxy
+  - inter-topic diversity
+  - run-to-run stability
+
+## Documentation Map (How-To)
+
+Detailed operations are intentionally kept in `/howto`:
+
+- [`/howto/ingest.md`](howto/ingest.md): ingestion, cleaning, stopwords, streaming mode
+- [`/howto/extract.md`](howto/extract.md): single-method extraction and interpretation
+- [`/howto/benchmark.md`](howto/benchmark.md): multi-method comparison workflow
+- [`/howto/report.md`](howto/report.md): markdown reporting workflow
+- [`/howto/release.md`](howto/release.md): PyPI/TestPyPI release workflow
+- [`/howto/docker-local.md`](howto/docker-local.md): local Docker stacks (Elasticsearch/OpenSearch)
+- [`/howto/troubleshooting.md`](howto/troubleshooting.md): common failures and fixes
+
+Sphinx documentation is available under `/docs` (includes README, how-to pages, and API docstrings).
+
+Build locally:
+
+```bash
+uv run sphinx-build -b html docs docs/_build/html
+```
+
+## Configuration
+
+Use `.env.template` as bootstrap:
+
+```bash
+cp .env.template .env
+set -a; source .env; set +a
+```
+
+Important variable groups:
+
+- backend/runtime (`THEME_EXTRACTOR_BACKEND*`, `THEME_EXTRACTOR_PROXY_URL`)
+- ingestion stopwords (`THEME_EXTRACTOR_DEFAULT_STOPWORDS_ENABLED`, `THEME_EXTRACTOR_AUTO_STOPWORDS_*`)
+- PDF OCR fallback (`THEME_EXTRACTOR_PDF_OCR_*`) for scanned PDFs
+- `.msg` extraction (`THEME_EXTRACTOR_MSG_*`) for metadata and attachment policy
+- local model resolution (`THEME_EXTRACTOR_LOCAL_MODELS_DIR`)
+- BERTopic embedding cache (`THEME_EXTRACTOR_BERTOPIC_EMBEDDING_CACHE_*`)
+
+## Project Governance
+
+- [`AGENTS.md`](AGENTS.md): operating rules
+- [`plan.md`](plan.md): phased roadmap
+- [`agent.md`](agent.md): agent charter
+
+## Community Standards
+
+- [`CONTRIBUTING.md`](CONTRIBUTING.md)
+- [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md)
+- [`SECURITY.md`](SECURITY.md)
+- [`SUPPORT.md`](SUPPORT.md)

theme_extractor-0.1.0/README.md

@@ -0,0 +1,127 @@
+# theme-extractor
+
+Python toolkit to compare theme/topic extraction strategies on the same corpus, with:
+
+- one unified CLI
+- one unified JSON output schema
+- offline-first execution options
+- Elasticsearch/OpenSearch backend support
+
+## Why this project
+
+`theme-extractor` helps you answer one practical question:
+"Which extraction strategy works best for my corpus and constraints?"
+
+It lets you run baseline lexical methods, embedding-based methods, and LLM-assisted methods with consistent outputs for easier comparison.
+
+## Core Commands
+
+- `theme-extractor ingest`
+- `theme-extractor extract`
+- `theme-extractor benchmark`
+- `theme-extractor evaluate`
+- `theme-extractor report`
+- `theme-extractor doctor`
+
+## Quickstart
+
+Prerequisite: start one backend first (local Docker guide: [`/howto/docker-local.md`](howto/docker-local.md)).
+
+```bash
+uv sync --group elasticsearch
+uv run theme-extractor doctor --output data/out/doctor.json
+uv run theme-extractor ingest --input data/raw --output data/out/ingest.json
+uv run theme-extractor benchmark \
+  --methods baseline_tfidf,terms,significant_terms,keybert,bertopic \
+  --backend elasticsearch \
+  --backend-url http://localhost:9200 \
+  --index theme_extractor \
+  --focus both \
+  --output data/out/benchmark.json
+uv run theme-extractor evaluate \
+  --input data/out/benchmark.json \
+  --output data/out/evaluation.json
+uv run theme-extractor report \
+  --input data/out/benchmark.json \
+  --output data/out/report_benchmark.md
+```
+
+Run `significant_text` separately with `--agg-field content` (see [`/howto/benchmark.md`](howto/benchmark.md)).
+
+## Methods Available
+
+- Baselines:
+  - `baseline_tfidf`
+  - `terms`
+  - `significant_terms`
+  - `significant_text`
+- Semantic:
+  - `keybert`
+  - `bertopic` (embedding on/off, reduction `none/svd/nmf/umap`, clustering `kmeans/hdbscan`)
+- Generative:
+  - `llm` (offline fallback behavior supported)
+
+## What You Get
+
+- Unified extraction schema:
+  - topic-first output (`topics`)
+  - optional document-topic links (`document_topics`)
+  - execution notes and metadata (`notes`, `metadata`)
+- Benchmark output:
+  - per-method outputs
+  - comparison block
+- Quantitative proxies via `evaluate`:
+  - topic coherence proxy
+  - inter-topic diversity
+  - run-to-run stability
+
+## Documentation Map (How-To)
+
+Detailed operations are intentionally kept in `/howto`:
+
+- [`/howto/ingest.md`](howto/ingest.md): ingestion, cleaning, stopwords, streaming mode
+- [`/howto/extract.md`](howto/extract.md): single-method extraction and interpretation
+- [`/howto/benchmark.md`](howto/benchmark.md): multi-method comparison workflow
+- [`/howto/report.md`](howto/report.md): markdown reporting workflow
+- [`/howto/release.md`](howto/release.md): PyPI/TestPyPI release workflow
+- [`/howto/docker-local.md`](howto/docker-local.md): local Docker stacks (Elasticsearch/OpenSearch)
+- [`/howto/troubleshooting.md`](howto/troubleshooting.md): common failures and fixes
+
+Sphinx documentation is available under `/docs` (includes README, how-to pages, and API docstrings).
+
+Build locally:
+
+```bash
+uv run sphinx-build -b html docs docs/_build/html
+```
+
+## Configuration
+
+Use `.env.template` as bootstrap:
+
+```bash
+cp .env.template .env
+set -a; source .env; set +a
+```
+
+Important variable groups:
+
+- backend/runtime (`THEME_EXTRACTOR_BACKEND*`, `THEME_EXTRACTOR_PROXY_URL`)
+- ingestion stopwords (`THEME_EXTRACTOR_DEFAULT_STOPWORDS_ENABLED`, `THEME_EXTRACTOR_AUTO_STOPWORDS_*`)
+- PDF OCR fallback (`THEME_EXTRACTOR_PDF_OCR_*`) for scanned PDFs
+- `.msg` extraction (`THEME_EXTRACTOR_MSG_*`) for metadata and attachment policy
+- local model resolution (`THEME_EXTRACTOR_LOCAL_MODELS_DIR`)
+- BERTopic embedding cache (`THEME_EXTRACTOR_BERTOPIC_EMBEDDING_CACHE_*`)
+
+## Project Governance
+
+- [`AGENTS.md`](AGENTS.md): operating rules
+- [`plan.md`](plan.md): phased roadmap
+- [`agent.md`](agent.md): agent charter
+
+## Community Standards
+
+- [`CONTRIBUTING.md`](CONTRIBUTING.md)
+- [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md)
+- [`SECURITY.md`](SECURITY.md)
+- [`SUPPORT.md`](SUPPORT.md)

theme_extractor-0.1.0/howto/README.md

@@ -0,0 +1,13 @@
+# How-To Guides
+
+This folder contains practical command recipes to run the package end-to-end.
+
+- `ingest.md`: build an ingestion output from local files.
+- `extract.md`: run one extraction strategy and interpret the output.
+- `benchmark.md`: compare multiple strategies and choose a candidate.
+- `report.md`: generate and read markdown reports from JSON outputs.
+- `release.md`: publish package distributions to TestPyPI/PyPI.
+- `docker-local.md`: start/stop local Elasticsearch or OpenSearch stacks.
+- `troubleshooting.md`: common issues and practical fixes.
+
+All commands are executed from the project root.

theme_extractor-0.1.0/pyproject.toml

@@ -0,0 +1,117 @@
+[project]
+name = "theme-extractor"
+version = "0.1.0"
+description = "Parse a corpus, manage it and extract themes from a corpus."
+readme = "README.md"
+requires-python = ">=3.13"
+license = { file = "LICENSE.md" }
+keywords = ["theme extraction", "corpus management", "text analysis", "python", "elasticsearch", "cli", "opensearch", "llm", "keyBERT", "sentence-transformers", "BERTopics"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Software Development :: Build Tools",
+    "Topic :: Text Processing :: Markup",
+]
+dependencies = [
+    "pydantic>=2.12.0",
+    "pydantic-settings>=2.12.0",
+    "httpx>=0.28.1",
+    "structlog>=25.5.0",
+    "pyyaml>=6.0.3",
+    "scikit-learn>=1.3.0",
+    "numpy>=2.0.0",
+]
+
+[dependency-groups]
+dev = [
+    "ruff>=0.15.0",
+    "ty>=0.0.15",
+    "pytest>=9.0.2",
+    "pytest-cov>=7.0.0",
+    "pytest-mock>=3.15.1",
+    "pytest-sugar>=1.1.1",
+    "pre-commit>=4.5.1",
+    "detect-secrets>=1.5.0",
+    "sphinx>=9.1.0",
+    "myst-parser>=5.0.0",
+]
+bert = [
+  "keyBERT>=0.7.0",
+  "sentence-transformers>=5.2.2",
+  "BERTopic>=0.15.0",
+  "umap-learn>=0.5.3",
+  "numba>=0.63.1",
+  "llvmlite>=0.46.0",
+]
+elasticsearch = [
+  "elasticsearch>=9.3.0",
+]
+opensearch = [
+  "opensearch-py>=3.1.0",
+]
+llm = [
+  "openai>=1.68.2",
+]
+
+[build-system]
+requires = ["hatchling", "build"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/theme_extractor"]
+include = ["src/theme_extractor/**"]
+exclude = ["src/theme_extractor/**/*.pyc", "src/theme_extractor/__pycache__/**"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/theme_extractor/**", "README.md", "LICENSE.md", "pyproject.toml"]
+exclude = ["src/theme_extractor/**/*.pyc", "src/theme_extractor/__pycache__/**"]
+
+
+[project.scripts]
+theme-extractor = "theme_extractor.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/Guillaume-Lombardo/theme-extractor"
+Repository = "https://github.com/Guillaume-Lombardo/theme-extractor"
+Issues = "https://github.com/Guillaume-Lombardo/theme-extractor/issues"
+
+
+[tool.pytest.ini_options]
+minversion = "9.0"
+testpaths = ["tests"]
+addopts = "-ra -q -m unit --strict-markers --cov=src --cov-report=term-missing:skip-covered --cov-report=html"
+pythonpath = ["src"]
+markers = [
+    "unit: mark a test as a unit test.",
+    "integration: mark a test as an integration test.",
+    "end2end: mark a test as an end-to-end test.",
+]
+
+[tool.coverage.run]
+branch = true
+source = ["src/theme_extractor"]
+omit = ["*/tests/*"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "def __repr__",
+    "def __str__",
+    "if self.debug",
+    "if settings.DEBUG",
+    "if __name__ .__main__.:",
+    "pragma: no cover",
+    "raise AssertionError",
+    "raise NotImplementedError",
+]
+show_missing = true
+skip_covered = true
+precision = 2
+fail_under = 80
+
+[tool.coverage.html]
+directory = "htmlcov"
+title = "Theme Extractor Coverage Report"