first commit

.github/workflows/publish.yml

@@ -0,0 +1,29 @@
+name: Python package
+on:
+  push:
+    tags:
+      - "v*.*.*"
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install python dependencies
+        run: |
+          pip install poetry
+          poetry install
+          poetry remove torch
+          poetry run pip install torch --index-url https://download.pytorch.org/whl/cpu
+      - name: Build package
+        run: |
+          poetry build
+      - name: Publish package
+        env:
+          PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          poetry config pypi-token.pypi "$PYPI_TOKEN"
+          poetry publish

.github/workflows/tests.yml

@@ -0,0 +1,41 @@
+name: Integration test with benchmark
+
+on: [push]
+
+env:
+  TESSDATA_PREFIX: "/usr/share/tesseract-ocr/4.00/tessdata"
+  TORCH_DEVICE: "cpu"
+  OCR_ENGINE: "tesseract" # So we don't have to install ghostscript, which takes a long time
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          cat scripts/install/apt-requirements.txt | xargs sudo apt-get install -y
+      - name: Show tessdata folders
+        run: ls /usr/share/tesseract-ocr/
+      - name: Install python dependencies
+        run: |
+          pip install poetry
+          poetry install
+          poetry remove torch
+          poetry run pip install torch --index-url https://download.pytorch.org/whl/cpu
+      - name: Download benchmark data
+        run: |
+          wget -O benchmark_data.zip "https://drive.google.com/uc?export=download&id=1ktVDYPEeyHlKLaF56FnHjI5VjVnYa1xL"
+          unzip benchmark_data.zip
+      - name: Run benchmark test
+        run: |
+          poetry run python benchmark.py benchmark_data/pdfs benchmark_data/references report.json
+          poetry run python scripts/verify_benchmark_scores.py report.json
+        
+          
+

.gitignore

@@ -0,0 +1,168 @@
+private.py
+.DS_Store
+local.env
+experiments
+test_data
+training
+wandb
+
+# 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/
+
+# 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
+.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/

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "args": ["thinkpython.pdf", "output.md", "--parallel_factor", "2", "--max_pages", "10"]
+        }
+    ]
+}