Merge branch 'main' into issue-135-fix-court-string-matching

freelawproject · Jul 18, 2024 · 37f237f · 37f237f
2 parents c9b4d78 + 5d3cf67
commit 37f237f
Show file tree

Hide file tree

Showing 13 changed files with 969 additions and 976 deletions.
diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
@@ -17,12 +17,12 @@ jobs:
       #       check-out repo and set-up python
       #----------------------------------------------
       - name: Check out repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Set up python
         id: setup-python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.11
+          python-version: 3.12
       #----------------------------------------------
       #   Alert PR to eyecite benchmark test
       #----------------------------------------------
@@ -32,9 +32,9 @@ jobs:
           recreate: true
           message: |
             Eyecite Benchmarking in progress...
-            
+
             For details, see: https://github.com/freelawproject/eyecite/actions/workflows/benchmark.yml
-            
+
             This message will be updated when the test is completed.
 
       #----------------------------------------------
@@ -43,7 +43,7 @@ jobs:
       # That we should drop once groups is released for main
       #----------------------------------------------
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
@@ -52,7 +52,7 @@ jobs:
       #----------------------------------------------
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
@@ -103,14 +103,14 @@ jobs:
           poetry run python benchmark/benchmark.py --branches ${{ steps.branch1.outputs.hash }}
           git stash --include-untracked
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: freelawproject/eyecite
           ref: main
 
       - name: Load cached venv 2
         id: cached-poetry-dependencies2
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
@@ -164,12 +164,12 @@ jobs:
       #       check-out repo and set-up python
       #----------------------------------------------
       - name: Check out repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Set up python
         id: setup-python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.11
+          python-version: 3.12
       #----------------------------------------------
       #   Alert PR to eyecite benchmark test
       #----------------------------------------------
@@ -187,7 +187,7 @@ jobs:
       #  -----  install & configure poetry  -----
       #----------------------------------------------
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
@@ -197,7 +197,7 @@ jobs:
       #----------------------------------------------
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
           key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -12,26 +12,30 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2-beta
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
-          python-version: "3.9"
+          python-version: "3.12"
 
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
 
       - name: Install hyperscan
         run: sudo apt-get install libhyperscan-dev
 
+      - name: Get full Python version
+        id: full-python-version
+        run: echo "version=$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")" >> $GITHUB_OUTPUT
+
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-${{ runner.os }}-${{ hashFiles('**/poetry.lock')}}
+          key: venv-${{ runner.os }}-cache-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock')}}-v20210414
 
       - name: Install dependencies
         run: poetry install
@@ -47,10 +51,10 @@ jobs:
         uses: psf/black@stable
 
       - name: Run flake8
-        uses: py-actions/flake8@v1
+        uses: py-actions/flake8@v2
 
       - name: isort Import Sorter
-        uses: isort/isort-action@v0.1.0
+        uses: isort/isort-action@v1
 
       - name: pylint Error Checker
         run: pylint --fail-under 9 -f colorized eyecite
@@ -61,23 +65,27 @@ jobs:
   lint-report:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2-beta
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
+          python-version: "3.12"
 
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
 
+      - name: Get full Python version
+        id: full-python-version
+        run: echo "version=$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")" >> $GITHUB_OUTPUT
+
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-${{ runner.os }}-${{ hashFiles('**/poetry.lock')}}
+          key: venv-${{ runner.os }}-cache-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock')}}-v20210414
 
       - name: Install dependencies
         run: poetry install
@@ -95,7 +103,7 @@ jobs:
           pylint-json2html -f json -o pylint-report.html
 
       - name: Upload report
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: pylint report
           path: pylint-report.html
diff --git a/.github/workflows/pdoc.yml b/.github/workflows/pdoc.yml
@@ -9,26 +9,30 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
+          python-version: "3.11"
 
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
 
       - name: Install hyperscan
         run: sudo apt-get install libhyperscan-dev
 
+      - name: Get full Python version
+        id: full-python-version
+        run: echo "version=$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")" >> $GITHUB_OUTPUT
+
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}-v2021-09-23
+          key: venv-${{ runner.os }}-cache-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock')}}-v20210414
 
       - name: Install dependencies
         run: poetry install
@@ -52,7 +56,7 @@ jobs:
           sed -i 's/AhocorasickTokenizer(.*\]))/AhocorasickTokenizer()/' ./eyecite/index.html
 
       - name: Deploy 🚀
-        uses: JamesIves/github-pages-deploy-action@4.1.5
+        uses: JamesIves/github-pages-deploy-action@v4
         with:
           branch: gh-pages
           folder: api_documentation/eyecite
diff --git a/.github/workflows/pypi.yml b/.github/workflows/pypi.yml
@@ -7,9 +7,9 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -14,30 +14,34 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v1
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Install Poetry
-        uses: snok/[email protected].3
+        uses: snok/[email protected].4
         with:
           virtualenvs-create: true
           virtualenvs-in-project: true
 
       - name: Install hyperscan
         run: sudo apt-get install libhyperscan-dev
 
+      - name: Get full Python version
+        id: full-python-version
+        run: echo "version=$(python -c "import sys; print('-'.join(str(v) for v in sys.version_info))")" >> $GITHUB_OUTPUT
+
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
+          key: venv-${{ runner.os }}-cache-${{ steps.full-python-version.outputs.version }}-${{ hashFiles('**/poetry.lock')}}-v20210414
 
       - name: Install dependencies
         run: poetry install

diff --git a/CHANGES.md b/CHANGES.md
@@ -8,23 +8,79 @@ Features:
 - None
 
 Changes:
-- As noted in 2.3.3 (2021-03-23), the old `NonopinionCitation` class was renamed `UnknownCitation` to better reflect its purpose. Support for the old class name has now been completely deprecated. This change is purely semantic -- there is no change in how these citations are handled.
-
-Fixes:
 - None
 
+Fixes:
+- Strengthens error handling during the loading of the cached Hyperscan database. This ensures that an invalid cache triggers a rebuild.
 
 
 ## Current
 
-**2.5.2 - 2023-05-23**
+**2.6.4 - 2024-06-03**
 
 Fixes:
- - Update dependencies and add Python 3.11 support.
 
+- Bump eyecite to for InvalidError/hyperscan bug
 
 ## Past
 
+**2.6.3 - 2024-04-09**
+
+Fixes:
+
+- Addresses compatibility issues identified with the current version of hyperscan(0.7.7).
+
+**2.6.2 - 2024-03-19**
+
+Fixes:
+
+- Adds missing closing parentheses to the corrected_citation_full method in FullCaseCitation and FullJournalCitation classes.
+
+**2.6.1 - 2024-02-29**
+
+Fixes:
+
+ - Improves reliability of utils.hash_sha256() by providing a default function to handle non-serializable objects.
+
+**2.6.0 - 2024-02-07**
+
+Features:
+
+ - Removes Python 3.8 and 3.9 support
+ - Adds Python 3.12 support
+
+Changes:
+
+- The hashing and equality behavior of `CitationBase` objects has changed in subtle ways in order to conform with user intuitions and define previously ill-defined behavior. Most importantly, to compare two `eyecite` objects going forward, simply use the native Python syntax `citation1 == citation2`. You can also take the hash of each object and compare that with identical results: `hash(citation1) == hash(citation2)`. This broad change has several more specific implications:
+  - Citation objects that are created from text with a normalized/corrected reporter are now treated as equal to objects created from text *without* a normalized/corrected reporter (e.g., `1 U.S. 1` versus `1 U. S. 1` are now treated as equal)
+  - Citation objects that are created from text with a nominative reporter are now treated as equal to objects created from text *without* a nominative reporter (e.g., `5 U.S. 137` versus `5 U.S. (1 Cranch) 137` are now treated as equal)
+  - Any `IdCitation` and `UnknownCitation` object will always be treated as unequal to any other object
+  - Previously, `CitationBase` objects had a `comparison_hash()` method. This method was never intended to be a "public" method and has been removed.
+  - Citation hashes are now stable and reproducible across module loadings of `eyecite`, as we are now using `hashlib.sha256` under the hood. However, note that due to `hashlib`'s implementation details, hashes with NOT be consistent across 32 and 64 machines.
+
+- As noted in 2.3.3 (2021-03-23), the old `NonopinionCitation` class was renamed `UnknownCitation` to better reflect its purpose. Support for the old class name has now been completely deprecated. This change is purely semantic -- there is no change in how these citations are handled.
+
+Fixes:
+
+ - Update dependencies for reporters-db
+
+**2.5.5 - 2024-01-10**
+
+Yanked.
+
+**2.5.4 - 2024-01-10**
+
+Yanked.
+
+**2.5.3 - 2024-01-10**
+
+Yanked.
+
+**2.5.2 - 2023-05-23**
+
+Fixes:
+ - Update dependencies and add Python 3.11 support.
+
 **2.5.1 - 2023-03-09**
 
 Fixes: