Improve contextual matcher

.github/workflows/tests.yml

@@ -7,9 +7,11 @@ on:
     branches: [master]
 
 env:
-  # UV_INDEX_STRATEGY: "unsafe-first-match"
-  # UV_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu"
+  UV_INDEX_STRATEGY: "unsafe-first-match"
+  UV_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu"
   PIP_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu"
+  UV_SYSTEM_PYTHON: 1
+  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
   linting:
@@ -22,7 +24,7 @@ jobs:
           # requites to grab the history of the PR
           fetch-depth: 0
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           cache: 'pip'
 
@@ -46,19 +48,6 @@ jobs:
           path: ~/.data/
           key: resources
 
-      # - name: Cache pip
-      #   uses: actions/cache@v3
-      #   with:
-      #     path: ~/.cache/pip
-      #     key: ${{ runner.os }}-python-${{ matrix.python-version }}-pip
-
-      - run: echo WEEK=$(date +%V) >>$GITHUB_ENV
-        shell: bash
-
-      # - uses: hynek/setup-cached-uv@v1
-      #   with:
-      #     cache-suffix: -tests-${{ matrix.python-version }}-${{ env.WEEK }}
-
       - name: Set up Java
         uses: actions/setup-java@v2
         with:
@@ -72,48 +61,28 @@ jobs:
           cache: 'pip'
 
       - name: Install dependencies
-        run: |
-          pip install poetry
-          pip install -e '.[dev]' pytest-xdist pip
+        run: pip install -e ".[dev]"
         if: matrix.python-version != '3.9' && matrix.python-version != '3.10' && matrix.python-version != '3.11' && matrix.python-version != '3.12'
-#          uv venv
-#          source .venv/bin/activate
-#          uv pip install -e '.[dev]' pytest-xdist pip
 
       - name: Install dependencies
-        run: |
-          pip install poetry
-          pip install -e '.[dev,setup]' pytest-xdist pip
+        run: pip install -e ".[dev,setup]"
         if: matrix.python-version == '3.9'
-#          uv venv
-#          source .venv/bin/activate
-#          uv pip install -e '.[dev]' pytest-xdist pip
 
       - name: Install dependencies
-        run: |
-          pip install poetry
-          pip install -e '.[dev-no-ml]' pytest-xdist pip
         # skip ML tests for 3.10 and 3.11
+        run: pip install -e ".[dev-no-ml]"
         if: matrix.python-version == '3.10' || matrix.python-version == '3.11' || matrix.python-version == '3.12'
 
       - name: Test with Pytest on Python ${{ matrix.python-version }}
         env:
           UMLS_API_KEY: ${{ secrets.UMLS_API_KEY }}
-        run: |
-          coverage run -m pytest --ignore tests/test_docs.py # -n auto
-          # coverage combine
-          # mv .coverage .coverage.${{ matrix.python-version }}
-#          source .venv/bin/activate
+        run: coverage run -m pytest --ignore tests/test_docs.py
         if: matrix.python-version != '3.9'
 
       - name: Test with Pytest on Python ${{ matrix.python-version }}
         env:
           UMLS_API_KEY: ${{ secrets.UMLS_API_KEY }}
-        run: |
-          coverage run -m pytest # -n auto
-          # coverage combine
-          # mv .coverage .coverage.${{ matrix.python-version }}
-#          source .venv/bin/activate
+        run: coverage run -m pytest
         if: matrix.python-version == '3.9'
 
       - name: Upload coverage data
@@ -137,33 +106,72 @@ jobs:
 
   documentation:
     name: Documentation
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2
 
-    - uses: actions/setup-python@v4
+    - uses: actions/setup-python@v5
       with:
-        python-version: "3.9"
+        python-version: 3.9
         cache: 'pip'
 
-    - run: echo WEEK=$(date +%V) >>$GITHUB_ENV
-      shell: bash
+    - name: Install dependencies
+      run: pip install -e ".[docs]"
 
-    # - uses: hynek/setup-cached-uv@v1
-    #   with:
-    #     cache-suffix: -docs-${{ matrix.python-version }}-${{ env.WEEK }}
+    - name: Set up Git
+      run: |
+        git config user.name ${{ github.actor }}
+        git config user.email ${{ github.actor }}@users.noreply.github.com
+        echo Current branch: $BRANCH_NAME
 
-    - name: Install dependencies
+    - name: Build documentation
       run: |
-        pip install '.[docs]'
-#        uv venv
-#        uv pip install '.[docs]'
+        mike deploy --no-redirect --rebase --update-aliases $BRANCH_NAME latest
+        mike set-default $BRANCH_NAME
 
+    - name: Put content of gh-pages to public folder
+      run: rm -rf public && mkdir public && git archive gh-pages | tar -x -C ./public/
 
-    - name: Build documentation
+    - name: Set up Vercel
+      run: npm install --global vercel@latest
+
+    - name: Pull Vercel environment
+      run: vercel pull --yes --environment=preview --token=${{ secrets.VERCEL_TOKEN }}
+
+    - name: Create new vercel project linked to this branch
+      run: vercel project add edsnlp-$BRANCH_NAME --token=${{ secrets.VERCEL_TOKEN }}
+
+    - name: Link public folder to the (maybe) new vercel project
+      run: vercel link --cwd public --project edsnlp-$BRANCH_NAME --yes --token=${{ secrets.VERCEL_TOKEN }}
+
+    - name: Deploy to Vercel
+      run: vercel deploy public/ --yes --token=${{ secrets.VERCEL_TOKEN }} --archive=tgz --prod > deployment-url.txt
+
+    - name: Post the documentation link
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       run: |
-        mkdocs build --clean
-#        source .venv/bin/activate
+        URL=https://edsnlp-$BRANCH_NAME.vercel.app/
+        COMMENT_BODY="## Docs preview URL\n\n$URL\n\n"
+        HEADER="Authorization: token $GITHUB_TOKEN"
+        PR_COMMENTS_URL="https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/comments"
+
+        # Fetch existing comments to find if one from this workflow already exists
+        COMMENTS=$(curl -s -H "$HEADER" "$PR_COMMENTS_URL")
+        COMMENT_ID=$(echo "$COMMENTS" | jq -r '.[] | select(.user.login == "github-actions[bot]" and (.body | startswith("## Docs preview URL"))) | .id')
+
+        # Check if we have a comment ID, if so, update it, otherwise create a new one
+        if [[ "$COMMENT_ID" ]]; then
+          # Update existing comment
+          curl -s -X PATCH -H "$HEADER" -H "Content-Type: application/json" -d "{\"body\": \"$COMMENT_BODY\"}" "https://api.github.com/repos/${{ github.repository }}/issues/comments/$COMMENT_ID"
+        else
+          # Post new comment
+          curl -s -X POST -H "$HEADER" -H "Content-Type: application/json" -d "{\"body\": \"$COMMENT_BODY\"}" "$PR_COMMENTS_URL"
+        fi
+
+        if [ $status -ne 0 ]; then
+          exit $status
+        fi
 
   simple-installation:
     name: Simple installation
@@ -175,21 +183,15 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
           cache: 'pip'
 
       - run: echo WEEK=$(date +%V) >>$GITHUB_ENV
         shell: bash
 
-      # - uses: hynek/setup-cached-uv@v1
-      #   with:
-      #     cache-suffix: -simple-install-${{ matrix.python-version }}-${{ env.WEEK }}
-
       - name: Install library
         run: |
           pip install ".[ml]" pytest
           pytest tests/pipelines/test_pipelines.py
-#          uv venv
-#          uv pip install .

.gitignore

@@ -24,6 +24,7 @@ site/
 *.cpp
 *.so
 *.c
+public/
 
 # Unit test / coverage reports
 htmlcov/
@@ -71,3 +72,4 @@ _build/
 docs/reference
 docs/changelog.md
 docs/contributing.md
+.vercel

.pre-commit-config.yaml

@@ -22,7 +22,7 @@ repos:
   # ruff
   - repo: https://github.com/charliermarsh/ruff-pre-commit
     # Ruff version.
-    rev: 'v0.6.4'
+    rev: 'v0.9.6'
     hooks:
       - id: ruff
         args: ['--config', 'pyproject.toml', '--fix', '--show-fixes']

changelog.md

@@ -5,13 +5,24 @@
 ### Added
 
 - Support for numpy>2.0, and formal support for Python 3.11 and Python 3.12
+- Expose the defaults patterns of `eds.negation`, `eds.hypothesis`, `eds.family`, `eds.history` and `eds.reported_speech` under a `eds.negation.default_patterns` attribute
+- Added a `context_getter` SpanGetter argument to the `eds.matcher` class to only retrieve entities inside the spans returned by the getter
+- Added a `filter_expr` parameter to scorers to filter the documents to score
+- Added a new `required` field to `eds.contextual_matcher` assign patterns to only match if the required field has been found, and an `include` parameter (similar to `exclude`) to search for required patterns without assigning them to the entity
+- Added context strings (e.g., "words[0:5] | sent[0:1]") to the `eds.contextual_matcher` component to allow for more complex patterns in the selection of the window around the trigger spans.
+- Include and exclude patterns in the contextual matcher now dismiss matches that occur inside the anchor pattern (e.g. "anti" exclude pattern for anchor pattern "antibiotics" will not match the "anti" part of "antibiotics")
+- Pull Requests will now build a public accessible preview of the docs
+
+### Changed
+- Improve the contextual matcher documentation.
 
 ### Fixed
 
 - `edsnlp.package` now correctly detect if a project uses an old-style poetry pyproject or a PEP621 pyproject.toml.
 - PEP621 projects containing nested directories (e.g., "my_project/pipes/foo.py") are now supported.
 - Try several paths to find current pip executable
-- Compatibility with Optuna 4.3.0
+- The parameter "value_extract" of `eds.score` now correctly handles lists of patterns.
+- "Zero variance error" when computing param tuning importance are now catched and converted as a warning
 
 ## v0.16.0 (2025-0.3-26)
 

docs/assets/fragments/alcohol-examples.md

@@ -73,12 +73,12 @@
     spans = doc.spans["alcohol"]
 
     spans
-    # Out: [Alcoolism non sevré]
+    # Out: [Alcoolisme non sevré]
 
     span = spans[0]
 
-    span._.detailed_status
-    # Out: None # "sevré" is negated, so no "ABTINENCE" status
+    span._.detailed_status  # "sevré" is negated, so no "ABTINENCE" status
+    # Out: None
     ```
 
 
@@ -90,7 +90,7 @@
     spans = doc.spans["alcohol"]
 
     spans
-    # Out: [Alcool: 0]
+    # Out: [Alcool]
 
     span = spans[0]
 

docs/assets/fragments/peptic-ulcer-disease-examples.md

@@ -41,7 +41,7 @@
     spans = doc.spans["peptic_ulcer_disease"]
 
     spans
-    # Out: [ulcères]
+    # Out: [gastrique: blabla blabla blabla blabla blabla quelques ulcères]
 
     span = spans[0]
 

docs/assets/fragments/tobacco-examples.md

@@ -66,7 +66,7 @@
     spans = doc.spans["tobacco"]
 
     spans
-    # Out: [Tabac: 0]
+    # Out: [Tabac]
 
     span = spans[0]
 
@@ -77,7 +77,7 @@
     # Out: True
 
     span._.assigned
-    # Out: {'zero_after': [0]}
+    # Out: {'zero_after': 0}
     ```
 
 

docs/assets/stylesheets/extra.css

@@ -190,3 +190,20 @@ a.discrete-link {
     font-size: 1rem;
     align-content: center;
 }
+
+.doc-param-details .subdoc {
+    padding: 0;
+    box-shadow: none;
+    border-color: var(--md-typeset-table-color);
+}
+
+.doc-param-details .subdoc > div > div > div>  table {
+    padding: 0;
+    box-shadow: none;
+    border: none;
+}
+
+.doc-param-details .subdoc > summary {
+    margin: 0;
+    font-weight: normal;
+}