Merge pull request #5 from spraakbanken/2-annotate-sentence

2 annotate sentence

.github/workflows/test.yml

@@ -79,64 +79,6 @@ jobs:
           # name: codecov-umbrella
           verbose: true
 
-  doctests:
-    # This action runs doctests for coverage collection and uploads them to codecov.io.
-    # This requires the secret `CODECOV_TOKEN` be set as secret on GitHub, both for 
-    # Actions and Dependabot
-
-    name: "${{ matrix.os }} / 3.8 / doctest"
-    strategy:
-      max-parallel: 4
-      fail-fast: false
-      matrix:
-        os: [ubuntu] 
-
-    runs-on: ${{ matrix.os }}-latest
-    continue-on-error: true # allow failure until doctests are added
-    env:
-      OS: ${{ matrix.os }}-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Set up the environment
-        uses: pdm-project/setup-pdm@v4
-        id: setup-python
-        with:
-          python-version: ${{ env.MINIMUM_PYTHON_VERSION }}
-
-      - name: Load cached venv
-        id: cached-venv
-        uses: actions/cache@v4
-        with:
-          path: .venv
-          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/pyproject.toml') }}-${{ hashFiles('.github/workflows/test.yml') }}
-
-      - name: Install dependencies
-        if: steps.cached-venv.outputs.cache-hit != 'true'
-        run: make install-dev
-      #----------------------------------------------
-      # Run tests and upload coverage
-      #----------------------------------------------
-      - name: make doc-tests
-        run: make doc-tests cov_report=xml
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          # directory: ./coverage
-          env_vars: OS,PYTHON,TESTTYPE
-          fail_ci_if_error: true
-          # files: ./coverage/coverage.xml
-          # flags: unittests
-          # name: codecov-umbrella
-          verbose: true
-        env:
-          PYTHON: ${{ env.MINIMUM_PYTHON_VERSION }}
-          TESTTYPE: doctest
-
   minimal:
     # This action chooses the oldest version of the dependencies permitted by Cargo.toml to ensure
     # that this crate is compatible with the minimal version that this crate and its dependencies
@@ -169,7 +111,6 @@ jobs:
     if: always()
     needs: 
       - coverage
-      - doctests
       - minimal
     runs-on: ubuntu-latest
     permissions: {}

.gitignore

@@ -159,3 +159,7 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 .pdm-python
+
+/examples/*/.snakemake
+/examples/*/export
+/examples/*/sparv-workdir

Makefile

@@ -50,7 +50,7 @@ help:
 	@echo ""
 	@echo "publish [branch=]"
 	@echo "   pushes the given branch including tags to origin, for CI to publish based on tags. (Default: branch='main')"
-	@echo "   Typically used after `make bumpversion`"
+	@echo "   Typically used after 'make bumpversion'"
 	@echo ""
 	@echo "prepare-release"
 	@echo "   run tasks to prepare a release"
@@ -89,6 +89,11 @@ install-dev:
 install:
 	pdm sync --prod
 
+lock: pdm.lock
+
+pdm.lock: pyproject.toml
+	pdm lock
+
 .PHONY: test
 test:
 	${INVENV} pytest -vv ${tests}
@@ -142,20 +147,27 @@ publish:
 
 
 .PHONY: prepare-release
-prepare-release: tests/requirements-testing.lock
+prepare-release: update-changelog tests/requirements-testing.lock
 
 # we use lock extension so that dependabot doesn't pick up changes in this file
-tests/requirements-testing.lock: pyproject.toml
+tests/requirements-testing.lock: pyproject.toml pdm.lock
 	pdm export --dev --format requirements --output $@
 
-.PHONY: kb-bert-prepare-release
-sparv-sbx-sentence-sentiment-kb-sent-prepare-release: sparv-sbx-sentence-sentiment-kb-sent/CHANGELOG.md
-
+.PHONY: update-changelog
 update-changelog: CHANGELOG.md sparv-sbx-sentence-sentiment-kb-sent/CHANGELOG.md
 
+.PHONY: CHANGELOG.md
 CHANGELOG.md:
 	git cliff --unreleased --prepend $@
 
+# update snapshots for `syrupy`
+.PHONY: snapshot-update
+snapshot-update:
+	${INVENV} pytest --snapshot-update
+
+.PHONY: kb-bert-prepare-release
+sparv-sbx-sentence-sentiment-kb-sent-prepare-release: sparv-sbx-sentence-sentiment-kb-sent/CHANGELOG.md
+
 .PHONY: sparv-sbx-sentence-sentiment-kb-sent/CHANGELOG.md
 sparv-sbx-sentence-sentiment-kb-sent/CHANGELOG.md:
 	git cliff --unreleased --include-path "sparv-sbx-sentence-sentiment-kb-sent/**/*" --include-path "examples/sparv-sbx-sentence-sentiment-kb-sent/**/*" --prepend $@

examples/sparv-sbx-sentence-sentiment-kb-sent/config.yaml

@@ -0,0 +1,16 @@
+metadata:
+    id: example-sparv-sbx-sentence-kb-sent
+    language: swe
+
+import:
+    importer: text_import:parse
+
+export:
+    annotations:
+        - <sentence>
+        # - <token:word>
+        - <token>:stanza.pos
+        - <sentence>:sbx_sentence_sentiment_kb_sent.sbx-sentence-sentiment--kb-sent
+
+sparv:
+    compression: none

examples/sparv-sbx-sentence-sentiment-kb-sent/source/small.txt

@@ -0,0 +1 @@
+../../texts/small.txt

examples/texts/small.txt

@@ -0,0 +1,3 @@
+Stora regnmängder väntas under måndagen och SMHI har utfärdat en gul varning för skyfallsliknande regn över stora delar av landets södra halva.
+Jag är förvånad, chockad och bestört över det här, säger Anders Persson till SVT Nyheter Småland.
+Vi hoppas och tror att detta också snabbt ska kunna komma på plats, säger Garborg.

mypy.ini

@@ -0,0 +1,2 @@
+[mypy]
+python_version = 3.8

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "sparv-sbx-sentence-sentiment-workspace"
 dependencies = []
-requires-python = ">=3.8,<3.12"
+requires-python = ">=3.8.1,<3.12"
 version = "0.0.0"
 
 [tool.pdm.dev-dependencies]
@@ -10,6 +10,7 @@ dev = [
     "pytest>=8.1.1",
     "pytest-cov>=4.1.0",
     "mypy>=1.9.0",
-    "ruff>=0.3.2",
+    "ruff>=0.4.5",
     "bump-my-version>=0.19.0",
+    "syrupy>=4.6.1",
 ]

ruff.toml

@@ -0,0 +1,61 @@
+line-length = 97
+
+target-version = "py38"
+
+[lint]
+select = [
+  "A",    # flake8-builtins
+  "ANN",  # flake8-annotations
+  "ARG",  # flake8-unused-arguments
+  "B",    # flake8-bugbear
+  "C4",   # flake8-comprehensions
+  "COM",  # flake8-commas
+  "D",    # pydocstyle
+  "D400", # pydocstyle: ends-in-period
+  "D401", # pydocstyle: non-imperative-mood
+  "E",    # pycodestyle: errors
+  "F",    # Pyflakes
+  "FLY",  # flynt
+  "FURB", # refurb
+  "G",    # flake8-logging-format
+  "I",    # isort
+  "ISC",  # flake8-implicit-str-concat
+  "N",    # pep8-naming
+  "PERF", # Perflint
+  "PIE",  # flake8-pie
+  "PL",   # Pylint
+  #   "PT",   # flake8-pytest-style
+  "PTH", # flake8-use-pathlib
+  "Q",   # flake8-quotes
+  "RET", # flake8-return
+  "RSE", # flake8-raise
+  "RUF", # Ruff-specific rules
+  "SIM", # flake8-simplify
+  "T20", # flake8-print
+  "TID", # flake8-tidy-imports
+  "UP",  # pyupgrade
+  "W",   # pycodestyle: warnings
+]
+ignore = [
+  "ANN101", # flake8-annotations: missing-type-self (deprecated)
+  "ANN102", # flake8-annotations: missing-type-cls (deprecated)
+  "ANN401", # flake8-annotations: any-type
+  "B008",   # flake8-bugbear: function-call-in-default-argument
+  "ISC001",
+  "COM812", # flake8-commas: missing-trailing-comma
+  "PLR09",  # Pylint: too-many-*
+  "SIM105", # flake8-simplify: suppressible-exception
+]
+preview = true
+
+# Avoid trying to fix flake8-bugbear (`B`) violations.
+unfixable = ["B"]
+
+
+[lint.pydocstyle]
+convention = "google"
+
+
+# Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
+[lint.per-file-ignores]
+"*/tests/*" = ["D", "ARG002", "E501"]

sparv-sbx-sentence-sentiment-kb-sent/README.md

@@ -13,7 +13,7 @@ Plugin for applying bert masking as a [Sparv](https://github.com/spraakbanken/sp
 
 ## Install
 
-First, install Sparv, as suggested:
+First, install Sparv as suggested:
 
 ```bash
 pipx install sparv-pipeline

sparv-sbx-sentence-sentiment-kb-sent/pyproject.toml

@@ -3,12 +3,13 @@ name = "sparv-sbx-sentence-sentiment-kb-sent"
 version = "0.1.0"
 description = "A sparv plugin for computing word neighbours using a BERT model."
 authors = [
+    { name = "Språkbanken Text", email = "[email protected]" },
     { name = "Kristoffer Andersson", email = "[email protected]" },
 ]
 dependencies = ["sparv-pipeline >=5.2.0", "transformers>=4.34.1"]
 license = "MIT"
 readme = "README.md"
-requires-python = ">= 3.8,<3.12"
+requires-python = ">= 3.8.1,<3.12"
 classifiers = [
     "Development Status :: 3 - Alpha",
     # "Development Status :: 4 - Beta",
@@ -54,4 +55,7 @@ allow-direct-references = true
 
 
 [tool.pdm.dev-dependencies]
-dev = ["pytest>=8.0.0"]
+dev = [
+    "pytest>=8.0.0",
+    "syrupy>=4.6.1",
+]

sparv-sbx-sentence-sentiment-kb-sent/src/sbx_sentence_sentiment_kb_sent/__init__.py

@@ -1 +1,8 @@
+"""Sparv plugin for annotating sentences with sentiment analysis."""
+
+from sbx_sentence_sentiment_kb_sent.annotations import annotate_sentence_sentiment
+
+__all__ = ["annotate_sentence_sentiment"]
+
+__description__ = "Annotate sentence with sentiment analysis."
 __version__ = "0.1.0"