Merge branch 'main' into fix-empty-bbox-serialization

.github/workflows/test.yml

@@ -1,8 +1,8 @@
 name: Lint, test, build, and publish
 
-on: 
+on:
   push:
-  
+
 
 jobs:
   lint_and_test:
@@ -13,9 +13,9 @@ jobs:
         python-version: [3.8, 3.9, '3.10', '3.11']
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies and kraken
@@ -30,7 +30,7 @@ jobs:
           flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
       - name: Run tests, except training tests
         run: |
-          pytest -k 'not test_train and not test_pageseg'
+          pytest -k 'not test_train'
 
   build-n-publish-pypi:
     name: Build and publish Python 🐍 distributions 📦 to PyPI and TestPyPI
@@ -39,11 +39,11 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
     - name: Set up Python 3.9
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: 3.9
     - name: Build a binary wheel and a source tarball
@@ -68,55 +68,54 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - uses: conda-incubator/setup-miniconda@v2
+      - uses: conda-incubator/setup-miniconda@v3
         with:
           python-version: 3.9
           miniforge-variant: Mambaforge
       - name: install dependencies build
         shell: bash -l {0}
-        run: mamba install "conda-build>=3.20" colorama pip ruamel ruamel.yaml rich jsonschema conda-verify anaconda-client mamba
-      # Runs the action with the following inputs or defaults if not specified.
-      - name: install boa
-        shell: bash -l {0}
-        run: pip install https://github.com/mamba-org/boa/archive/refs/tags/0.14.0.zip
-      - name: validate recipe
-        shell: bash -l {0}
-        id: conda_validation
-        run: |
-          PACKAGE_PATHS=$(conda mambabuild . --output --check -c conda-forge | tail -n 1)
-          echo "package_paths=$PACKAGE_PATHS" >> $GITHUB_OUTPUT
-      - name: run build
-        shell: bash -l {0}
-        run: conda mambabuild . -c conda-forge
-      - name: convert packages
-        shell: bash -l {0}
+        run: mamba install colorama pip ruamel ruamel.yaml rich jsonschema conda-verify anaconda-client
+      - name: Build linux-64 conda package
+        uses: prefix-dev/[email protected]
+        with:
+          recipe-path: "conda/recipe.yaml"
+          build-args: "--experimental --target-platform linux-64"
+      - name: Build osx-64 conda package
+        uses: prefix-dev/[email protected]
+        with:
+          recipe-path: "conda/recipe.yaml"
+          build-args: "--experimental --target-platform osx-64"
+#      - name: Build osx-arm64 conda package
+#        uses: prefix-dev/[email protected]
+#        with:
+#          recipe-path: "conda/recipe.yaml"
+#          build-args: "--experimental --target-platform osx-arm64"
+      - name: Upload conda package
         run: |
-          conda convert -p osx-arm64 -p osx-64 -o conda_convert ${{ steps.conda_validation.outputs.package_paths }}
-          mkdir conda_convert/linux-64
-          cp -f ${{ steps.conda_validation.outputs.package_paths }} conda_convert/linux-64
-      - name: upload to anaconda
-        shell: bash -l {0}
-        run: anaconda -t ${{ secrets.ANACONDA_TOKEN }} upload --no-progress --force conda_convert/*/*
+          for pkg in $(find output -type f \( -name "*.conda" -o -name "*.tar.bz2" \) ); do
+            echo "Uploading ${pkg}"
+            rattler-build upload anaconda -o mittagessen -a ${{ secrets.ANACONDA_TOKEN }} "${pkg}"
+          done
       - name: Upload conda artifacts to GH storage
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: conda_packages
-          path: conda_convert/*/*.tar.bz2
+          path: output/*/*.conda
 
   autodraft-gh-release:
     name: Create github release
     needs: [build-n-publish-anaconda, build-n-publish-pypi]
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: conda_packages
           path: conda
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: pypi_packages
           path: pypi
@@ -126,33 +125,33 @@ jobs:
           prerelease: false
           draft: true
           files: |
-            conda/*/*.tar.bz2
+            output/*/*.conda
             pypi/*
 
   publish-gh-pages:
-    name: Update kraken.re github pages 
+    name: Update kraken.re github pages
     needs: lint_and_test
     runs-on: ubuntu-latest
     if: |
       github.ref == 'refs/heads/main' ||
       startsWith(github.ref, 'refs/tags/')
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
       - name: Set up Python 3.9
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.9
       - name: Install sphinx-multiversion
         run:  python -m pip install sphinx-multiversion sphinx-autoapi
-      - name: Create docs 
+      - name: Create docs
         run:  sphinx-multiversion docs build/html
       - name: Create redirect
         run: cp docs/redirect.html build/html/index.html
       - name: Push gh-pages
-        uses: crazy-max/ghaction-github-pages@v3
+        uses: crazy-max/ghaction-github-pages@v4
         with:
           target_branch: gh-pages
           build_dir: build/html

README.rst

@@ -9,7 +9,7 @@ material.
 
 kraken's main features are:
 
-  - Fully trainable layout analysis and character recognition
+  - Fully trainable layout analysis, reading order, and character recognition
   - `Right-to-Left <https://en.wikipedia.org/wiki/Right-to-left>`_, `BiDi
     <https://en.wikipedia.org/wiki/Bi-directional_text>`_, and Top-to-Bottom
     script support
@@ -44,38 +44,38 @@ install the `pdf` extras package for PyPi:
 
   $ pip install kraken[pdf]
 
-or install `pyvips` manually with conda:
+or install `pyvips` manually with pip:
 
 ::
 
-  $ conda install -c conda-forge pyvips
+  $ pip install pyvips
 
-Conda environment files are provided which for the seamless installation of the
-main branch as well:
+Conda environment files are provided for the seamless installation of the main
+branch as well:
 
 ::
 
-  $ git clone https://github.com/mittagessen/kraken.git 
+  $ git clone https://github.com/mittagessen/kraken.git
   $ cd kraken
   $ conda env create -f environment.yml
 
 or:
 
 ::
 
-  $ git clone https://github.com/mittagessen/kraken.git 
+  $ git clone https://github.com/mittagessen/kraken.git
   $ cd kraken
   $ conda env create -f environment_cuda.yml
 
 for CUDA acceleration with the appropriate hardware.
 
 Finally you'll have to scrounge up a model to do the actual recognition of
-characters. To download the default model for printed English text and place it
+characters. To download the default model for printed French text and place it
 in the kraken directory for the current user:
 
 ::
 
-  $ kraken get 10.5281/zenodo.2577813 
+  $ kraken get 10.5281/zenodo.10592716
 
 A list of libre models available in the central repository can be retrieved by
 running:
@@ -105,13 +105,13 @@ To segment an image (binarized or not) with the new baseline segmenter:
 ::
 
   $ kraken -i image.tif lines.json segment -bl
- 
+
 
 To segment and OCR an image using the default model(s):
 
 ::
 
-  $ kraken -i image.tif image.txt segment -bl ocr
+  $ kraken -i image.tif image.txt segment -bl ocr -m catmus-print-fondue-large.mlmodel
 
 All subcommands and options are documented. Use the ``help`` option to get more
 information.
@@ -124,8 +124,8 @@ Have a look at the `docs <https://kraken.re>`_.
 Related Software
 ================
 
-These days kraken is quite closely linked to the `escriptorium
-<https://escriptorium.fr>`_ project developed in the same eScripta research
+These days kraken is quite closely linked to the `eScriptorium
+<https://gitlab.com/scripta/escriptorium/>`_ project developed in the same eScripta research
 group. eScriptorium provides a user-friendly interface for annotating data,
 training models, and inference (but also much more). There is a `gitter channel
 <https://gitter.im/escripta/escriptorium>`_ that is mostly intended for

conda/recipe.yaml

@@ -0,0 +1,55 @@
+context:
+  git_url: .
+  git_tag: ${{ git.latest_tag(git_url) }}
+
+package:
+  name: kraken
+  version: ${{ git_tag }}
+
+source:
+  git: ${{ git_url }}
+  tag: ${{ git_tag }}
+
+build:
+  script: pip install --no-deps .
+
+requirements:
+  build:
+    - python>=3.8,<3.12
+    - setuptools>=36.6.0,<70.0.0
+    - pbr
+  host:
+     - python>=3.8,<3.12
+  run:
+     - python>=3.8,<3.12
+     - python-bidi
+     - lxml
+     - regex
+     - requests
+     - click>=8.1
+     - numpy~=1.23.0
+     - pillow>=9.2.0
+     - scipy~=1.11.0
+     - jinja2~=3.0
+     - torchvision
+     - pytorch~=2.1.0
+     - cudatoolkit
+     - jsonschema
+     - scikit-image~=0.21.0
+     - scikit-learn~=1.2.1
+     - shapely~=1.8.5
+     - pyvips
+     - coremltools
+     - pyarrow
+     - lightning~=2.2
+     - torchmetrics>=1.1.0
+     - conda-forge::threadpoolctl~=3.4.0
+     - albumentations
+     - rich
+
+about:
+  homepage: https://kraken.re
+  license:  Apache-2.0
+  summary: 'OCR/HTR engine for all the languages'
+  repository: https://github.com/mittagessen/kraken
+  documentation: https://kraken.re