ci: add linter action

notice about v0.3.0 development

.github/workflows/main.yml

@@ -0,0 +1,40 @@
+name: test & lint
+
+on:
+  push:
+    branches:
+      - '*'
+  pull_request:
+    types: [opened, reopened]
+  workflow_dispatch:
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dev dependencies
+        run: 'pip install .[dev]'
+      - name: Run tests
+        run: 'pytest -v'
+
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install dev dependencies
+        run: 'pip install .[dev]'
+      - name: Run linter
+        run: 'ruff check'

.github/workflows/test.yml

@@ -1,23 +0,0 @@
-name: Run tests
-on:
-  push:
-    branches:
-      - 'master'
-  pull_request:
-    types: [opened, reopened]
-  workflow_dispatch:
-jobs:
-  pytest:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
-
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - run: 'pip install -r requirements.dev.txt .'
-      - run: 'pytest -v'

.pre-commit-config.yaml

@@ -4,11 +4,10 @@ repos:
     hooks:
       - id: end-of-file-fixer
       - id: trailing-whitespace
-  - repo: https://github.com/psf/black
-    rev: 23.1.0
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.4
     hooks:
-      - id: black
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format

README.md

@@ -10,9 +10,14 @@ English | [简体中文](./README.zh_Hans.md)
 
 ## WIP
 
-> **Warning**
+> [!CAUTION]
 > This project is under active development, thus it is unstable and API may change frequently.
 
+> [!IMPORTANT]
+> v0.3.0 is under development, check out [this branch](https://github.com/283375/arcaea-offline/tree/0.3.0-refactor)!
+>
+> Once v0.3.0 is ready for release, this repository will be transferred to *[ArcaeaOffline](https://github.com/ArcaeaOffline)/core-python*
+
 ## What is this？
 
 This is the core library of `Arcaea Offline`, designed to manage player scores, calculate their potential, and provide various useful tools.

README.zh_Hans.md

@@ -8,9 +8,14 @@
 
 ## WIP
 
-> **Warning**
+> [!CAUTION]
 > 该项目正处于早期开发阶段，不能保证稳定性，且 API 可能随时变动。
 
+> [!IMPORTANT]
+> v0.3.0 正在[此分支](https://github.com/283375/arcaea-offline/tree/0.3.0-refactor)下开发！
+>
+> 在 v0.3.0 准备好发布后，此存储库将被迁移至 *[ArcaeaOffline](https://github.com/ArcaeaOffline)/core-python*。
+
 ## 这是什么？
 
 这是 `Arcaea Offline` 的核心依赖库，用于维护分数数据库、计算潜力值，并提供一些实用工具。

pyproject.toml

@@ -10,32 +10,44 @@ description = "Manage your local Arcaea score database."
 readme = "README.md"
 requires-python = ">=3.8"
 dependencies = [
+  "beautifulsoup4==4.12.2",
   "SQLAlchemy==2.0.20",
   "SQLAlchemy-Utils==0.41.1",
+  "Whoosh==2.7.4",
 ]
 classifiers = [
   "Development Status :: 3 - Alpha",
   "Programming Language :: Python :: 3",
 ]
 
+[project.optional-dependencies]
+dev = ["ruff~=0.4", "pre-commit~=3.3", "pytest~=7.4", "tox~=4.11"]
+
 [project.urls]
 "Homepage" = "https://github.com/283375/arcaea-offline"
 "Bug Tracker" = "https://github.com/283375/arcaea-offline/issues"
 
-[tool.isort]
-profile = "black"
-src_paths = ["src/arcaea_offline"]
-
 [tool.pyright]
 ignore = ["build/"]
 
-[tool.pylint.main]
-jobs = 0
-
-[tool.pylint.logging]
-disable = [
-  "missing-module-docstring",
-  "missing-class-docstring",
-  "missing-function-docstring",
-  "not-callable", # false positive to sqlalchemy `func.*`, remove this when pylint-dev/pylint(#8138) closed
+[tool.ruff.lint]
+# Full list: https://docs.astral.sh/ruff/rules
+select = [
+  "E",   # pycodestyle (Error)
+  "W",   # pycodestyle (Warning)
+  "F",   # pyflakes
+  "I",   # isort
+  "PL",  # pylint
+  "N",   # pep8-naming
+  "FBT", # flake8-boolean-trap
+  "A",   # flake8-builtins
+  "DTZ", # flake8-datetimez
+  "LOG", # flake8-logging
+  "Q",   # flake8-quotes
+  "G",   # flake8-logging-format
+  "PIE", # flake8-pie
+  "PT",  # flake8-pytest-style
+]
+ignore = [
+  "E501", # line-too-long
 ]

requirements.dev.txt

@@ -1,6 +1,4 @@
-black==23.3.0
-isort==5.12.0
-pre-commit==3.3.1
-pylint==3.0.2
-pytest==7.4.3
-tox==4.11.3
+ruff~=0.4
+pre-commit~=3.3
+pytest~=7.4
+tox~=4.11

requirements.txt

@@ -1,2 +1,4 @@
+beautifulsoup4==4.12.2
 SQLAlchemy==2.0.20
 SQLAlchemy-Utils==0.41.1
+Whoosh==2.7.4

src/arcaea_offline/constants/enums/__init__.py

@@ -1,3 +0,0 @@
-from .clear_type import ArcaeaScoreClearType
-from .modifier import ArcaeaScoreModifier
-from .rating_class import ArcaeaRatingClass

src/arcaea_offline/constants/enums/clear_type.py

@@ -1,10 +0,0 @@
-from enum import IntEnum
-
-
-class ArcaeaScoreClearType(IntEnum):
-    TRACK_LOST = 0
-    NORMAL_CLEAR = 1
-    FULL_RECALL = 2
-    PURE_MEMORY = 3
-    HARD_CLEAR = 4
-    EASY_CLEAR = 5

src/arcaea_offline/constants/enums/modifier.py

@@ -1,7 +0,0 @@
-from enum import IntEnum
-
-
-class ArcaeaScoreModifier(IntEnum):
-    NORMAL = 0
-    EASY = 1
-    HARD = 2

src/arcaea_offline/constants/enums/rating_class.py

@@ -1,9 +0,0 @@
-from enum import IntEnum
-
-
-class ArcaeaRatingClass(IntEnum):
-    PAST = 0
-    PRESENT = 1
-    FUTURE = 2
-    BEYOND = 3
-    ETERNAL = 4

src/arcaea_offline/database.py

@@ -5,16 +5,10 @@ from typing import Iterable, List, Optional, Type, Union
 from sqlalchemy import Engine, func, inspect, select
 from sqlalchemy.orm import DeclarativeBase, InstrumentedAttribute, sessionmaker
 
-from arcaea_offline.external.arcsong.arcsong_json import ArcSongJsonBuilder
-from arcaea_offline.external.exports import (
-    ArcaeaOfflineDEFV2_Score,
-    ScoreExport,
-    exporters,
-)
-from arcaea_offline.singleton import Singleton
-
-from .models.v4.config import ConfigBase, Property
-from .models.v4.scores import (
+from .external.arcsong.arcsong_json import ArcSongJsonBuilder
+from .external.exports import ArcaeaOfflineDEFV2_Score, ScoreExport, exporters
+from .models.config import ConfigBase, Property
+from .models.scores import (
     CalculatedPotential,
     Score,
     ScoreBest,
@@ -22,7 +16,7 @@ from .models.v4.scores import (
     ScoresBase,
     ScoresViewBase,
 )
-from .models.v4.songs import (
+from .models.songs import (
     Chart,
     ChartInfo,
     Difficulty,
@@ -34,6 +28,7 @@ from .models.v4.songs import (
     SongsBase,
     SongsViewBase,
 )
+from .singleton import Singleton
 
 logger = logging.getLogger(__name__)
 

src/arcaea_offline/database/__init__.py

@@ -1 +0,0 @@
-from .db import Database

src/arcaea_offline/searcher.py

@@ -0,0 +1,111 @@
+from typing import List, Union
+
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+from whoosh.analysis import NgramFilter, StandardAnalyzer
+from whoosh.fields import ID, KEYWORD, TEXT, Schema
+from whoosh.filedb.filestore import RamStorage
+from whoosh.qparser import FuzzyTermPlugin, MultifieldParser, OrGroup
+
+from .models.songs import Song, SongLocalized
+from .utils.search_title import recover_search_title
+
+
+class Searcher:
+    def __init__(self):
+        self.text_analyzer = StandardAnalyzer() | NgramFilter(minsize=2, maxsize=5)
+        self.song_schema = Schema(
+            song_id=ID(stored=True, unique=True),
+            title=TEXT(analyzer=self.text_analyzer, spelling=True),
+            artist=TEXT(analyzer=self.text_analyzer, spelling=True),
+            source=TEXT(analyzer=self.text_analyzer, spelling=True),
+            keywords=KEYWORD(lowercase=True, stored=True, scorable=True),
+        )
+        self.storage = RamStorage()
+        self.index = self.storage.create_index(self.song_schema)
+
+        self.default_query_parser = MultifieldParser(
+            ["song_id", "title", "artist", "source", "keywords"],
+            self.song_schema,
+            group=OrGroup,
+        )
+        self.default_query_parser.add_plugin(FuzzyTermPlugin())
+
+    def import_songs(self, session: Session):
+        writer = self.index.writer()
+        songs = list(session.scalars(select(Song)))
+        song_localize_stmt = select(SongLocalized)
+        for song in songs:
+            stmt = song_localize_stmt.where(SongLocalized.id == song.id)
+            sl = session.scalar(stmt)
+            song_id = song.id
+            possible_titles: List[Union[str, None]] = [song.title]
+            possible_artists: List[Union[str, None]] = [song.artist]
+            possible_sources: List[Union[str, None]] = [song.source]
+            if sl:
+                possible_titles.extend(
+                    [sl.title_ja, sl.title_ko, sl.title_zh_hans, sl.title_zh_hant]
+                )
+                possible_titles.extend(
+                    recover_search_title(sl.search_title_ja)
+                    + recover_search_title(sl.search_title_ko)
+                    + recover_search_title(sl.search_title_zh_hans)
+                    + recover_search_title(sl.search_title_zh_hant)
+                )
+                possible_artists.extend(
+                    recover_search_title(sl.search_artist_ja)
+                    + recover_search_title(sl.search_artist_ko)
+                    + recover_search_title(sl.search_artist_zh_hans)
+                    + recover_search_title(sl.search_artist_zh_hant)
+                )
+                possible_sources.extend(
+                    [
+                        sl.source_ja,
+                        sl.source_ko,
+                        sl.source_zh_hans,
+                        sl.source_zh_hant,
+                    ]
+                )
+
+            # remove empty items in list
+            titles = [t for t in possible_titles if t != "" and t is not None]
+            artists = [t for t in possible_artists if t != "" and t is not None]
+            sources = [t for t in possible_sources if t != "" and t is not None]
+
+            writer.update_document(
+                song_id=song_id,
+                title=" ".join(titles),
+                artist=" ".join(artists),
+                source=" ".join(sources),
+                keywords=" ".join([song_id] + titles + artists + sources),
+            )
+
+        writer.commit()
+
+    def did_you_mean(self, string: str):
+        results = set()
+
+        with self.index.searcher() as searcher:
+            corrector_keywords = searcher.corrector("keywords")  # type: ignore
+            corrector_song_id = searcher.corrector("song_id")  # type: ignore
+            corrector_title = searcher.corrector("title")  # type: ignore
+            corrector_artist = searcher.corrector("artist")  # type: ignore
+            corrector_source = searcher.corrector("source")  # type: ignore
+
+            results.update(corrector_keywords.suggest(string))
+            results.update(corrector_song_id.suggest(string))
+            results.update(corrector_title.suggest(string))
+            results.update(corrector_artist.suggest(string))
+            results.update(corrector_source.suggest(string))
+
+        if string in results:
+            results.remove(string)
+
+        return list(results)
+
+    def search(self, string: str, *, limit: int = 10):
+        query_string = f"{string}"
+        query = self.default_query_parser.parse(query_string)
+        with self.index.searcher() as searcher:
+            results = searcher.search(query, limit=limit)
+            return [result.get("song_id") for result in results]