hi-pdf-parser 0.0.5__tar.gz

hi_pdf_parser-0.0.5/.dockerignore

@@ -0,0 +1,40 @@
+# Ignore Python cache files
+__pycache__/
+**/__pycache__/
+*.pyc
+*.pyo
+*.pyd
+
+# Ignore virtual environments
+env/
+venv/
+
+# Ignore development artifacts
+*.log
+*.db
+*.sqlite3
+
+# Ignore configuration and sensitive files
+**/.env
+*.env
+*.ini
+*.cfg
+
+# Ignore IDE and editor settings
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# Ignore Git files
+.git/
+.gitignore
+
+# Ignore Docker files themselves (optional if not needed in the image)
+.dockerignore
+Dockerfile*
+
+# Ignore build artifacts (if applicable)
+build/
+dist/
+*.egg-info

hi_pdf_parser-0.0.5/.github/workflows/publish-pypi.yml

@@ -0,0 +1,57 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v[0-9]+.[0-9]+.[0-9]+"
+      - "[0-9]+.[0-9]+.[0-9]+"
+
+permissions:
+  contents: read
+
+jobs:
+  publish:
+    name: Build and publish
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/hi-pdf-parser
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Verify tag matches package version
+        run: |
+          python - <<'PY'
+          import os
+          import tomllib
+
+          ref_name = os.environ["GITHUB_REF_NAME"]
+          tag_version = ref_name[1:] if ref_name.startswith("v") else ref_name
+          with open("pyproject.toml", "rb") as file:
+              project_version = tomllib.load(file)["project"]["version"]
+
+          if tag_version != project_version:
+              raise SystemExit(
+                  f"Tag version {tag_version!r} does not match "
+                  f"pyproject.toml version {project_version!r}"
+              )
+          PY
+
+      - name: Install build tooling
+        run: python -m pip install --upgrade uv
+
+      - name: Build distributions
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

hi_pdf_parser-0.0.5/.gitignore

@@ -0,0 +1,446 @@
+model_artifacts/
+scratch/
+.md-lint
+actionlint
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,macos,virtualenv,pycharm,visualstudiocode,emacs,vim,jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,macos,virtualenv,pycharm,visualstudiocode,emacs,vim,jupyternotebooks
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### 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
+
+### PyCharm ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm Patch ###
+# Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721
+
+# *.iml
+# modules.xml
+# .idea/misc.xml
+# *.ipr
+
+# Sonarlint plugin
+# https://plugins.jetbrains.com/plugin/7973-sonarlint
+.idea/**/sonarlint/
+
+# SonarQube Plugin
+# https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin
+.idea/**/sonarIssues.xml
+
+# Markdown Navigator plugin
+# https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced
+.idea/**/markdown-navigator.xml
+.idea/**/markdown-navigator-enh.xml
+.idea/**/markdown-navigator/
+
+# Cache file creation bug
+# See https://youtrack.jetbrains.com/issue/JBR-2257
+.idea/$CACHE_FILE$
+
+# CodeStream plugin
+# https://plugins.jetbrains.com/plugin/12206-codestream
+.idea/codestream.xml
+
+# Azure Toolkit for IntelliJ plugin
+# https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij
+.idea/**/azureSettings.xml
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+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/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+
+# IPython
+
+# 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
+.env
+.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/
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg  # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+
+### Visual Studio Code ###
+.vscode/
+
+### VirtualEnv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+pyvenv.cfg
+pip-selfcheck.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
+
+
+# Docs
+# docs/**/*.png
+# docs/**/*.svg
+
+# Makefile
+.action-lint
+.markdown-lint

hi_pdf_parser-0.0.5/.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+fail_fast: true
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.6
+    hooks:
+      # Run the Ruff formatter.
+      - id: ruff-format
+        name: "Ruff formatter"
+        args: [--config=pyproject.toml]
+        files: '^(hi_pdf_parser|tests).*\.(py|ipynb)$'
+      # Run the Ruff linter.
+      - id: ruff
+        name: "Ruff linter"
+        args: [--exit-non-zero-on-fix, --fix, --config=pyproject.toml]
+        files: '^(hi_pdf_parser|tests).*\.(py|ipynb)$'
+  - repo: local
+    hooks:
+      - id: system
+        name: MyPy
+        entry: uv run --no-sync mypy hi_pdf_parser
+        pass_filenames: false
+        language: system
+        files: '\.py$'
+  - repo: https://github.com/astral-sh/uv-pre-commit
+    # uv version.
+    rev: 0.7.17
+    hooks:
+      - id: uv-lock

hi_pdf_parser-0.0.5/.python-version

@@ -0,0 +1 @@
+3.11

hi_pdf_parser-0.0.5/Dockerfile

@@ -0,0 +1,25 @@
+ARG BASE_IMAGE=python:3.11-slim-bookworm
+
+FROM ${BASE_IMAGE} AS exporter
+
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+
+WORKDIR /app
+
+ADD pyproject.toml uv.lock .
+
+RUN /root/.local/bin/uv export --extra server --no-hashes --no-dev -o requirements.txt
+
+FROM ${BASE_IMAGE}
+
+COPY --from=exporter --chown=nobody:nogroup /app/requirements.txt .
+
+RUN pip install -r requirements.txt
+
+USER nobody:nogroup
+
+WORKDIR /app
+
+COPY hi_pdf_parser ./hi_pdf_parser
+
+CMD ["python3", "-m", "hi_pdf_parser", "serve"]