Merge pull request #9 from spraakbanken/fix-names

fix names

.github/workflows/test.yml

@@ -106,12 +106,54 @@ jobs:
       - name: make test
         run: make test
 
+  run-example:
+    name: ubuntu / 3.8 / run-example / ${{ matrix.example-name }}
+    strategy:
+      max-parallel: 4
+      fail-fast: false
+      matrix:
+        example-name:
+          - sparv-sbx-sentence-sentiment-kb-sent
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+      #----------------------------------------------
+      #  -----  setup python   -----
+      #----------------------------------------------
+      - 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') }}-${{ hashFiles('.github/workflows/ci.yml') }}
+
+      - name: Install dependencies
+        if: steps.cached-venv.outputs.cache-hit != 'true'
+        run: make install-dev
+
+      - name: Run example
+        run: |
+          source .venv/bin/activate
+          cd examples/${{ matrix.example-name }}
+          echo "" | sparv setup
+          sparv run
+          ls -R
+  
   # https://github.com/marketplace/actions/alls-green#why used for branch protection checks
   test-check:
     if: always()
     needs: 
       - coverage
       - minimal
+      - run-example
     runs-on: ubuntu-latest
     permissions: {}
     steps:

.pre-commit-config.yaml

@@ -0,0 +1,34 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-yaml
+        stages: [commit]
+      - id: check-json
+        stages: [commit]
+      - id: check-toml
+        stages: [commit]
+      - id: check-merge-conflict
+        stages: [commit]
+      - id: check-case-conflict
+        stages: [commit]
+      - id: detect-private-key
+        stages: [commit]
+      # - id: end-of-file-fixer
+      - id: check-added-large-files
+        stages: [commit]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.4.4
+    hooks:
+      # Run the linter.
+      - id: ruff
+      # Run the formatter.
+      - id: ruff-format
+  - repo: https://github.com/crate-ci/committed
+    rev: v1.0.20
+    hooks:
+      - id: committed
+        stages: [commit-msg]

Makefile

@@ -165,7 +165,7 @@ CHANGELOG.md:
 snapshot-update:
 	${INVENV} pytest --snapshot-update
 
-.PHONY: kb-bert-prepare-release
+.PHONY: sparv-sbx-sentence-sentiment-kb-sent-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

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

@@ -5,6 +5,9 @@ metadata:
 import:
     importer: text_import:parse
 
+sbx_sentence_sentiment_kb_sent:
+    num_decimals: 3
+
 export:
     annotations:
         - <sentence>

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

@@ -9,7 +9,7 @@
 
 [![CI(release)](https://github.com/spraakbanken/sparv-sbx-sentiment-analysis/actions/workflows/release-sentence-sentiment-kb-sent.yml/badge.svg)](https://github.com/spraakbanken/sparv-sbx-sentiment-analysis/actions/workflows/release-sentence-sentiment-kb-sent.yml)
 
-Plugin for applying bert masking as a [Sparv](https://github.com/spraakbanken/sparv-pipeline) annotation.
+Plugin for computing sentence sentiment as a [Sparv](https://github.com/spraakbanken/sparv-pipeline) annotation.
 
 ## Install
 
@@ -33,15 +33,15 @@ annotation exclusively by adding it as the only annotation to export under `xml_
 ```yaml
 xml_export:
     annotations:
-        - <token>:sbx_sentence_sentiment_kb_sent.sentence-sentiment--kb-bert
+        - <sentence>:sbx_sentence_sentiment_kb_sent.sentence-sentiment--kb-sent
 ```
 
 To use it together with other annotations you might add it under `export`:
 
 ```yaml
 export:
     annotations:
-        - <token>:sbx_sentence_sentiment_kb_sent.sentence-sentiment--kb-bert
+        - <sentence>:sbx_sentence_sentiment_kb_sent.sentence-sentiment--kb-sent
         ...
 ```
 

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

@@ -1,7 +1,7 @@
 [project]
 name = "sparv-sbx-sentence-sentiment-kb-sent"
 version = "0.1.0"
-description = "A sparv plugin for computing word neighbours using a BERT model."
+description = "A sparv plugin for computing sentence sentiment."
 authors = [
     { name = "Språkbanken Text", email = "[email protected]" },
     { name = "Kristoffer Andersson", email = "[email protected]" },
@@ -55,7 +55,4 @@ allow-direct-references = true
 
 
 [tool.pdm.dev-dependencies]
-dev = [
-    "pytest>=8.0.0",
-    "syrupy>=4.6.1",
-]
+dev = ["pytest>=8.0.0", "syrupy>=4.6.1"]

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

@@ -3,6 +3,7 @@
 from sparv import api as sparv_api  # type: ignore [import-untyped]
 
 from sbx_sentence_sentiment_kb_sent.annotations import annotate_sentence_sentiment
+from sbx_sentence_sentiment_kb_sent.constants import PROJECT_NAME
 
 __all__ = ["annotate_sentence_sentiment"]
 
@@ -11,7 +12,7 @@
 
 __config__ = [
     sparv_api.Config(
-        "sbx_sentence_sentiment_kb_bert.num_decimals",
+        f"{PROJECT_NAME}.num_decimals",
         description="The number of decimals to round the score to",
         default=3,
     ),

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

@@ -1,7 +1,8 @@
-"""Sparv annotator."""
+"""Sparv annotator for sentiment analysis on sentences."""
 
 from sparv import api as sparv_api  # type: ignore [import-untyped]
 
+from sbx_sentence_sentiment_kb_sent.constants import PROJECT_NAME
 from sbx_sentence_sentiment_kb_sent.sentiment_analyzer import SentimentAnalyzer
 
 logger = sparv_api.get_logger(__name__)
@@ -10,20 +11,20 @@
 @sparv_api.annotator("Sentiment analysis of sentences", language=["swe"])
 def annotate_sentence_sentiment(
     out_sentence_sentiment: sparv_api.Output = sparv_api.Output(
-        "<sentence>:sbx_sentence_sentiment_kb_sent.sentence-sentiment--kb-sent",
+        f"<sentence>:{PROJECT_NAME}.sentence-sentiment--kb-sent",
         # cls="sbx_sentence_sentiment_kb_sent",
         description="Sentiment analysis of sentence with KBLab/robust-swedish-sentiment-multiclass",  # noqa: E501
     ),
     word: sparv_api.Annotation = sparv_api.Annotation("<token:word>"),
     sentence: sparv_api.Annotation = sparv_api.Annotation("<sentence>"),
-    num_decimals_str: str = sparv_api.Config("sbx_sentence_sentiment_kb_sent.num_decimals"),
+    num_decimals_str: str = sparv_api.Config(f"{PROJECT_NAME}.num_decimals"),
 ) -> None:
     """Sentiment analysis of sentence with KBLab/robust-swedish-sentiment-multiclass."""
     try:
         num_decimals = int(num_decimals_str)
     except ValueError as exc:
         raise sparv_api.SparvErrorMessage(
-            f"'sbx_word_prediction_kb_bert.num_decimals' must contain an 'int' got: '{num_decimals_str}'"  # noqa: E501
+            f"'{PROJECT_NAME}.num_decimals' must contain an 'int' got: '{num_decimals_str}'"
         ) from exc
     sentences, _orphans = sentence.get_children(word)
     token_word = list(word.read())

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

@@ -0,0 +1,3 @@
+"""Constants used in this project."""
+
+PROJECT_NAME: str = "sbx_sentence_sentiment_kb_sent"