Merge pull request #162 from ku-nlp/develop

v1.5.1

.github/dependabot.yml

@@ -8,7 +8,7 @@ updates:
   - package-ecosystem: "pip"
     directory: "/"
     schedule:
-      interval: "weekly" # TODO: Change to "monthly"
+      interval: "monthly"
       timezone: "Asia/Tokyo"
     target-branch: "develop"
     ignore:

.github/workflows/build.yml

@@ -7,18 +7,19 @@ jobs:
     name: Build the project
     runs-on: ${{ matrix.os }}
     strategy:
-      max-parallel: 15
+      max-parallel: 18
       fail-fast: false
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+          allow-prereleases: true # TODO: Remove this line when Python 3.12 is released
       - name: Install Poetry
         run: |
           pipx install poetry

.github/workflows/codeql-analysis.yml

@@ -38,7 +38,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL

.github/workflows/lint.yml

@@ -7,7 +7,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Set up Python 3.7
         uses: actions/setup-python@v4
         with:

.github/workflows/publish.yml

@@ -8,7 +8,7 @@ jobs:
   build-publish:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python 3.9
         uses: actions/setup-python@v4
         with:

.github/workflows/release.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Create Release
         id: create_release
         uses: actions/create-release@v1

.github/workflows/test-example.yml

@@ -11,12 +11,13 @@ jobs:
     container: kunlp/jumanpp-knp:ubuntu
     runs-on: ubuntu-20.04 # to meet the ubuntu version in the kunlp/jumanpp-knp:ubuntu container
     strategy:
+      max-parallel: 5
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install required apt packages
         run: |
           apt update -y
@@ -25,6 +26,7 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+          allow-prereleases: true # TODO: Remove this line when Python 3.12 is released
       - name: Install Poetry
         run: |
           python3 -m pip install --user pipx

.github/workflows/test.yml

@@ -8,12 +8,13 @@ jobs:
     container: kunlp/jumanpp-knp:ubuntu
     runs-on: ubuntu-20.04 # to meet the ubuntu version in the kunlp/jumanpp-knp:ubuntu container
     strategy:
+      max-parallel: 6
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install required apt packages
         run: |
           apt update -y
@@ -22,6 +23,7 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+          allow-prereleases: true # TODO: Remove this line when Python 3.12 is released
       - name: Install Poetry
         run: |
           python3 -m pip install --user pipx
@@ -34,8 +36,8 @@ jobs:
         run: |
           poetry install --no-interaction --without dev,docs --extras=cli
       - name: Install KWJA
-        # KWJA does not support Python 3.7
-        if: ${{ matrix.python-version != 3.7 }}
+        # KWJA does not support Python 3.7 or 3.12
+        if: ${{ matrix.python-version != 3.7 && matrix.python-version != 3.12 }}
         run: |
           pipx install kwja
           kwja --model-size tiny --text "テスト"

.pre-commit-config.yaml

@@ -8,8 +8,8 @@ repos:
       - id: check-yaml
       - id: check-toml
       - id: check-added-large-files
-  - repo: https://github.com/psf/black
-    rev: 23.7.0
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 23.9.0
     hooks:
       - id: black
   - repo: https://github.com/PyCQA/flake8

examples/apply_kwja.py

@@ -10,11 +10,11 @@
 # Create a KWJA instance.
 kwja = KWJA()
 
-# Apply KNP to a sentence.
-sent = kwja.apply_to_sentence(sys.argv[1])
+# Apply KWJA to a document.
+doc = kwja.apply_to_document(sys.argv[1])
 
 # Get information.
-for mrph in sent.morphemes:
+for mrph in doc.morphemes:
     print(f"Text: {mrph.text}")
     print(f"Reading: {mrph.reading}")
     print(f"Lemma: {mrph.lemma}")

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rhoknp"
-version = "1.5.0"
+version = "1.5.1"
 description = "Yet another Python binding for Juman++/KNP/KWJA"
 license = "MIT"
 authors = [
@@ -57,10 +57,10 @@ Sphinx = [
     { version = "^5.3", python = "<3.8" },
     { version = "^7.0", python = ">=3.8" },
 ]
-# sphinx-prompt 1.7.0 requires python < 3.11, which will be fixed in the next version
 sphinx-prompt = [
     { version = "~1.5.0", python = "<3.8" },
-    { version = "^1.6", python = ">=3.8,<3.11" },
+    { version = "^1.6", python = ">=3.8,<3.9" },
+    { version = "^1.8", python = ">=3.9" },
 ]
 sphinx-copybutton = "^0.5.0"
 myst-parser = [
@@ -84,7 +84,7 @@ rhoknp = "rhoknp.cli.cli:app"
 
 [tool.black]
 line-length = 120
-target-version = ["py37", "py38", "py39", "py310", "py311"]
+target-version = ["py37", "py38", "py39", "py310", "py311", "py312"]
 
 [tool.isort]
 line_length = 120

src/rhoknp/cli/static/css/style.css

@@ -1,12 +1,12 @@
 /* templates/components/raw_input.jinja2 */
 .input-text {
   white-space: pre-wrap;
-  margin: 0em 0.5em 1em;
+  margin: 0 0.5em 1em;
   padding: 0.5em;
 }
 
 .result {
-  margin: 0em 0.5em 1em;
+  margin: 0 0.5em 1em;
   padding: 0.5em;
 }
 

src/rhoknp/processors/kwja.py

@@ -45,10 +45,10 @@ def __init__(
             tasks: List[str] = self.options[self.options.index("--tasks") + 1].split(",")
             if "word" in tasks:
                 self._output_format = "knp"
-            elif "char" in tasks:
-                self._output_format = "words"
             elif "seq2seq" in tasks:
                 self._output_format = "jumanpp"
+            elif "char" in tasks:
+                self._output_format = "words"
             elif "senter" in tasks:
                 self._output_format = "line_by_line"
             elif "typo" in tasks:

src/rhoknp/units/base_phrase.py

@@ -247,12 +247,13 @@ def from_knp(cls, knp_text: str) -> "BasePhrase":
         match = cls.PAT.match(first_line)
         if match is None:
             raise ValueError(f"malformed base phrase line: {first_line}")
-        parent_index = int(match["pid"]) if match["pid"] is not None else None
-        dep_type = DepType(match["dtype"]) if match["dtype"] is not None else None
-        features = FeatureDict.from_fstring(match["feats"] or "")
-        rel_tags = RelTagList.from_fstring(match["feats"] or "")
-        memo_tag = MemoTag.from_fstring(match["feats"] or "")
-        base_phrase = cls(parent_index, dep_type, features, rel_tags, memo_tag)
+        base_phrase = cls(
+            parent_index=int(match["pid"]) if match["pid"] is not None else None,
+            dep_type=DepType(match["dtype"]) if match["dtype"] is not None else None,
+            features=FeatureDict.from_fstring(match["feats"] or ""),
+            rel_tags=RelTagList.from_fstring(match["feats"] or ""),
+            memo_tag=MemoTag.from_fstring(match["feats"] or ""),
+        )
 
         morphemes: List[Morpheme] = []
         for line in lines:

src/rhoknp/units/morpheme.py

@@ -301,8 +301,6 @@ def _from_jumanpp_line(cls, jumanpp_line: str, homograph: bool = False) -> "Morp
         match_attr = cls._ATTRIBUTE_PAT.match(match["attrs"]) or cls._ATTRIBUTE_PAT_REPEATED.match(match["attrs"])
         assert match_attr is not None
         attributes = match_attr.groups()
-        semantics = SemanticsDict.from_sstring(match["sems"] or "")
-        features = FeatureDict.from_fstring(match["feats"] or "")
         return cls(
             surf,
             attributes[0],
@@ -315,8 +313,8 @@ def _from_jumanpp_line(cls, jumanpp_line: str, homograph: bool = False) -> "Morp
             int(attributes[7]),
             attributes[8],
             int(attributes[9]),
-            semantics,
-            features,
+            semantics=SemanticsDict.from_sstring(match["sems"] or ""),
+            features=FeatureDict.from_fstring(match["feats"] or ""),
             homograph=homograph,
         )