feat: Add multi-language documentation support (Task #16)
- Language detection (11 languages supported) - Filename pattern recognition (file.en.md, file_en.md, file-en.md) - Content-based detection with confidence scoring - Multi-language organization and filtering - Translation status tracking - Export by language capability - 22 tests passing (100%) Files: - multilang_support.py: Core language engine - test_multilang_support.py: Comprehensive tests Supported Languages: - English, Spanish, French, German, Portuguese, Italian - Chinese, Japanese, Korean - Russian, Arabic Features: - LanguageDetector with pattern matching - MultiLanguageManager for organization - Translation completeness tracking - Script detection (Latin, Han, Cyrillic, etc.) - Export to language-specific files Week 2: 7/9 tasks complete (78%) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
yusyus
436
src/skill_seekers/cli/multilang_support.py
Normal file
436
src/skill_seekers/cli/multilang_support.py
Normal file
@@ -0,0 +1,436 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Multi-language Documentation Support
|
||||
|
||||
Provides language detection, multi-language structure handling,
|
||||
and translation-ready format generation.
|
||||
"""
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Set
|
||||
from dataclasses import dataclass
|
||||
from collections import Counter
|
||||
import json
|
||||
|
||||
|
||||
@dataclass
|
||||
class LanguageInfo:
|
||||
"""Language information for a document."""
|
||||
code: str # ISO 639-1 code (e.g., 'en', 'es', 'zh')
|
||||
name: str # Full name (e.g., 'English', 'Spanish', 'Chinese')
|
||||
confidence: float # Detection confidence (0.0-1.0)
|
||||
script: Optional[str] = None # Script type (e.g., 'Latin', 'Cyrillic')
|
||||
|
||||
|
||||
@dataclass
|
||||
class TranslationStatus:
|
||||
"""Translation status for a document."""
|
||||
source_language: str
|
||||
target_languages: List[str]
|
||||
translated_languages: Set[str]
|
||||
missing_languages: Set[str]
|
||||
completeness: float # Percentage (0.0-1.0)
|
||||
|
||||
|
||||
class LanguageDetector:
|
||||
"""
|
||||
Detect document language using heuristics.
|
||||
|
||||
Uses character patterns, common words, and script detection.
|
||||
"""
|
||||
|
||||
# Common word patterns by language
|
||||
LANGUAGE_PATTERNS = {
|
||||
'en': [
|
||||
r'\b(the|and|is|are|in|to|of|for|with|on|at|by|from)\b',
|
||||
r'\b(this|that|these|those|what|which|who|where|when)\b',
|
||||
],
|
||||
'es': [
|
||||
r'\b(el|la|los|las|de|en|y|a|es|por|para|con|su)\b',
|
||||
r'\b(que|no|un|una|como|más|pero|muy|todo|ya)\b',
|
||||
],
|
||||
'fr': [
|
||||
r'\b(le|la|les|de|et|en|un|une|pour|dans|que|sur|avec)\b',
|
||||
r'\b(est|sont|ce|qui|plus|ne|pas|nous|vous|tout)\b',
|
||||
],
|
||||
'de': [
|
||||
r'\b(der|die|das|und|in|zu|den|von|ist|mit|für|auf)\b',
|
||||
r'\b(ein|eine|nicht|sich|auch|werden|an|als|ich|sie)\b',
|
||||
],
|
||||
'zh': [
|
||||
r'[\u4e00-\u9fff]', # Chinese characters
|
||||
r'(的|了|和|是|在|有|我|他|不|这)',
|
||||
],
|
||||
'ja': [
|
||||
r'[\u3040-\u309f]', # Hiragana
|
||||
r'[\u30a0-\u30ff]', # Katakana
|
||||
r'[\u4e00-\u9faf]', # Kanji
|
||||
],
|
||||
'ko': [
|
||||
r'[\uac00-\ud7af]', # Hangul
|
||||
r'(의|가|이|은|들|는|좀|잘|께|을)',
|
||||
],
|
||||
'ru': [
|
||||
r'[\u0400-\u04ff]', # Cyrillic
|
||||
r'\b(и|в|не|на|с|что|он|по|а|как|это|все)\b',
|
||||
],
|
||||
'pt': [
|
||||
r'\b(o|a|de|e|do|da|em|um|para|é|com|não|os|as)\b',
|
||||
r'\b(que|se|mais|por|dos|das|como|mas|uma|ou)\b',
|
||||
],
|
||||
'it': [
|
||||
r'\b(il|la|di|e|a|da|in|che|per|un|una|non|del)\b',
|
||||
r'\b(con|alla|della|al|nel|sono|come|più|ma|dei)\b',
|
||||
],
|
||||
'ar': [
|
||||
r'[\u0600-\u06ff]', # Arabic
|
||||
r'(في|من|على|إلى|هذا|ما|أن|كان|هو|التي)',
|
||||
],
|
||||
}
|
||||
|
||||
# Language names
|
||||
LANGUAGE_NAMES = {
|
||||
'en': 'English',
|
||||
'es': 'Spanish',
|
||||
'fr': 'French',
|
||||
'de': 'German',
|
||||
'zh': 'Chinese',
|
||||
'ja': 'Japanese',
|
||||
'ko': 'Korean',
|
||||
'ru': 'Russian',
|
||||
'pt': 'Portuguese',
|
||||
'it': 'Italian',
|
||||
'ar': 'Arabic',
|
||||
}
|
||||
|
||||
# Script types
|
||||
SCRIPTS = {
|
||||
'en': 'Latin', 'es': 'Latin', 'fr': 'Latin', 'de': 'Latin',
|
||||
'pt': 'Latin', 'it': 'Latin',
|
||||
'zh': 'Han', 'ja': 'Japanese', 'ko': 'Hangul',
|
||||
'ru': 'Cyrillic', 'ar': 'Arabic',
|
||||
}
|
||||
|
||||
def detect(self, text: str, sample_size: int = 2000) -> LanguageInfo:
|
||||
"""
|
||||
Detect language of text.
|
||||
|
||||
Args:
|
||||
text: Text to analyze
|
||||
sample_size: Number of characters to sample
|
||||
|
||||
Returns:
|
||||
LanguageInfo with detected language
|
||||
"""
|
||||
if not text.strip():
|
||||
return LanguageInfo('en', 'English', 0.0)
|
||||
|
||||
# Sample text for efficiency
|
||||
sample = text[:sample_size].lower()
|
||||
|
||||
# Score each language
|
||||
scores = {}
|
||||
for lang_code, patterns in self.LANGUAGE_PATTERNS.items():
|
||||
score = 0
|
||||
for pattern in patterns:
|
||||
matches = len(re.findall(pattern, sample, re.IGNORECASE))
|
||||
score += matches
|
||||
|
||||
scores[lang_code] = score
|
||||
|
||||
# Find best match
|
||||
if not scores or max(scores.values()) == 0:
|
||||
# Default to English
|
||||
return LanguageInfo('en', 'English', 0.1)
|
||||
|
||||
best_lang = max(scores, key=scores.get)
|
||||
total_score = sum(scores.values())
|
||||
confidence = scores[best_lang] / total_score if total_score > 0 else 0.0
|
||||
|
||||
return LanguageInfo(
|
||||
code=best_lang,
|
||||
name=self.LANGUAGE_NAMES.get(best_lang, best_lang.upper()),
|
||||
confidence=min(confidence, 1.0),
|
||||
script=self.SCRIPTS.get(best_lang)
|
||||
)
|
||||
|
||||
def detect_from_filename(self, filename: str) -> Optional[str]:
|
||||
"""
|
||||
Detect language from filename pattern.
|
||||
|
||||
Supports patterns like:
|
||||
- file.en.md
|
||||
- file_en.md
|
||||
- en/file.md
|
||||
- file-en.md
|
||||
|
||||
Args:
|
||||
filename: Filename to analyze
|
||||
|
||||
Returns:
|
||||
ISO 639-1 language code or None
|
||||
"""
|
||||
# Pattern: file.en.md
|
||||
match = re.search(r'\.([a-z]{2})\.md$', filename)
|
||||
if match and match.group(1) in self.LANGUAGE_NAMES:
|
||||
return match.group(1)
|
||||
|
||||
# Pattern: file_en.md or file-en.md
|
||||
match = re.search(r'[_-]([a-z]{2})\.md$', filename)
|
||||
if match and match.group(1) in self.LANGUAGE_NAMES:
|
||||
return match.group(1)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
class MultiLanguageManager:
|
||||
"""
|
||||
Manages multi-language documentation structure.
|
||||
|
||||
Organizes documents by language and tracks translations.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize multi-language manager."""
|
||||
self.detector = LanguageDetector()
|
||||
self.documents: Dict[str, List[Dict]] = {} # lang_code -> [docs]
|
||||
self.primary_language: Optional[str] = None
|
||||
|
||||
def add_document(
|
||||
self,
|
||||
file_path: str,
|
||||
content: str,
|
||||
metadata: Optional[Dict] = None,
|
||||
force_language: Optional[str] = None
|
||||
) -> None:
|
||||
"""
|
||||
Add document with language detection.
|
||||
|
||||
Args:
|
||||
file_path: Path to document
|
||||
content: Document content
|
||||
metadata: Additional metadata
|
||||
force_language: Override language detection
|
||||
"""
|
||||
# Detect language
|
||||
if force_language:
|
||||
lang_code = force_language
|
||||
lang_info = LanguageInfo(
|
||||
code=lang_code,
|
||||
name=self.detector.LANGUAGE_NAMES.get(lang_code, lang_code.upper()),
|
||||
confidence=1.0,
|
||||
script=self.detector.SCRIPTS.get(lang_code)
|
||||
)
|
||||
else:
|
||||
# Try filename pattern first
|
||||
filename_lang = self.detector.detect_from_filename(file_path)
|
||||
if filename_lang:
|
||||
lang_code = filename_lang
|
||||
lang_info = LanguageInfo(
|
||||
code=lang_code,
|
||||
name=self.detector.LANGUAGE_NAMES.get(lang_code, lang_code.upper()),
|
||||
confidence=0.95,
|
||||
script=self.detector.SCRIPTS.get(lang_code)
|
||||
)
|
||||
else:
|
||||
# Detect from content
|
||||
lang_info = self.detector.detect(content)
|
||||
lang_code = lang_info.code
|
||||
|
||||
# Set primary language (first added or most common)
|
||||
if self.primary_language is None:
|
||||
self.primary_language = lang_code
|
||||
|
||||
# Store document
|
||||
if lang_code not in self.documents:
|
||||
self.documents[lang_code] = []
|
||||
|
||||
doc = {
|
||||
'file_path': file_path,
|
||||
'content': content,
|
||||
'language': lang_info.code,
|
||||
'language_name': lang_info.name,
|
||||
'confidence': lang_info.confidence,
|
||||
'script': lang_info.script,
|
||||
'metadata': metadata or {}
|
||||
}
|
||||
|
||||
self.documents[lang_code].append(doc)
|
||||
|
||||
def get_languages(self) -> List[str]:
|
||||
"""Get list of detected languages."""
|
||||
return sorted(self.documents.keys())
|
||||
|
||||
def get_document_count(self, language: Optional[str] = None) -> int:
|
||||
"""
|
||||
Get document count for a language.
|
||||
|
||||
Args:
|
||||
language: Language code (None for all)
|
||||
|
||||
Returns:
|
||||
Number of documents
|
||||
"""
|
||||
if language:
|
||||
return len(self.documents.get(language, []))
|
||||
return sum(len(docs) for docs in self.documents.values())
|
||||
|
||||
def get_translation_status(self, base_language: Optional[str] = None) -> TranslationStatus:
|
||||
"""
|
||||
Get translation status.
|
||||
|
||||
Args:
|
||||
base_language: Base language (None for primary)
|
||||
|
||||
Returns:
|
||||
Translation status summary
|
||||
"""
|
||||
base_lang = base_language or self.primary_language or 'en'
|
||||
|
||||
all_languages = set(self.documents.keys())
|
||||
base_count = self.get_document_count(base_lang)
|
||||
|
||||
if base_count == 0:
|
||||
return TranslationStatus(
|
||||
source_language=base_lang,
|
||||
target_languages=[],
|
||||
translated_languages=set(),
|
||||
missing_languages=set(),
|
||||
completeness=0.0
|
||||
)
|
||||
|
||||
# Check which languages have translations
|
||||
translated = set()
|
||||
for lang in all_languages:
|
||||
if lang != base_lang and self.get_document_count(lang) > 0:
|
||||
translated.add(lang)
|
||||
|
||||
# Commonly expected languages for completeness
|
||||
expected_languages = {'en', 'es', 'fr', 'de', 'zh', 'ja'}
|
||||
missing = expected_languages - all_languages
|
||||
|
||||
completeness = len(all_languages) / len(expected_languages)
|
||||
|
||||
return TranslationStatus(
|
||||
source_language=base_lang,
|
||||
target_languages=list(all_languages - {base_lang}),
|
||||
translated_languages=translated,
|
||||
missing_languages=missing,
|
||||
completeness=min(completeness, 1.0)
|
||||
)
|
||||
|
||||
def export_by_language(self, output_dir: Path) -> Dict[str, Path]:
|
||||
"""
|
||||
Export documents organized by language.
|
||||
|
||||
Args:
|
||||
output_dir: Output directory
|
||||
|
||||
Returns:
|
||||
Dictionary mapping language codes to output paths
|
||||
"""
|
||||
output_dir = Path(output_dir)
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
exports = {}
|
||||
|
||||
for lang_code, docs in self.documents.items():
|
||||
lang_file = output_dir / f"documents_{lang_code}.json"
|
||||
|
||||
export_data = {
|
||||
'language': lang_code,
|
||||
'language_name': self.detector.LANGUAGE_NAMES.get(lang_code, lang_code.upper()),
|
||||
'document_count': len(docs),
|
||||
'documents': docs
|
||||
}
|
||||
|
||||
lang_file.write_text(json.dumps(export_data, indent=2, ensure_ascii=False))
|
||||
exports[lang_code] = lang_file
|
||||
|
||||
return exports
|
||||
|
||||
def generate_translation_report(self) -> str:
|
||||
"""
|
||||
Generate human-readable translation report.
|
||||
|
||||
Returns:
|
||||
Formatted report string
|
||||
"""
|
||||
lines = ["=" * 60]
|
||||
lines.append("MULTI-LANGUAGE DOCUMENTATION REPORT")
|
||||
lines.append("=" * 60)
|
||||
lines.append("")
|
||||
|
||||
# Summary
|
||||
languages = self.get_languages()
|
||||
total_docs = self.get_document_count()
|
||||
|
||||
lines.append("📊 Summary:")
|
||||
lines.append(f" Languages: {len(languages)}")
|
||||
lines.append(f" Total documents: {total_docs}")
|
||||
lines.append(f" Primary language: {self.primary_language or 'Unknown'}")
|
||||
lines.append("")
|
||||
|
||||
# Language breakdown
|
||||
lines.append("🌍 Language Breakdown:")
|
||||
for lang in languages:
|
||||
count = self.get_document_count(lang)
|
||||
lang_name = self.detector.LANGUAGE_NAMES.get(lang, lang.upper())
|
||||
percentage = (count / total_docs * 100) if total_docs > 0 else 0
|
||||
lines.append(f" {lang_name} ({lang}): {count} docs ({percentage:.1f}%)")
|
||||
lines.append("")
|
||||
|
||||
# Translation status
|
||||
status = self.get_translation_status()
|
||||
lines.append("📝 Translation Status:")
|
||||
lines.append(f" Source: {status.source_language}")
|
||||
lines.append(f" Translated to: {', '.join(status.translated_languages) or 'None'}")
|
||||
lines.append(f" Completeness: {status.completeness * 100:.1f}%")
|
||||
|
||||
if status.missing_languages:
|
||||
lines.append(f" Missing: {', '.join(sorted(status.missing_languages))}")
|
||||
lines.append("")
|
||||
|
||||
lines.append("=" * 60)
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def example_usage():
|
||||
"""Example usage of multi-language support."""
|
||||
from pathlib import Path
|
||||
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
# Add documents in different languages
|
||||
manager.add_document(
|
||||
"README.md",
|
||||
"# Getting Started\n\nThis is an English document about the project.",
|
||||
{"category": "overview"}
|
||||
)
|
||||
|
||||
manager.add_document(
|
||||
"README.es.md",
|
||||
"# Empezando\n\nEste es un documento en español sobre el proyecto.",
|
||||
{"category": "overview"}
|
||||
)
|
||||
|
||||
manager.add_document(
|
||||
"README.fr.md",
|
||||
"# Commencer\n\nCeci est un document en français sur le projet.",
|
||||
{"category": "overview"}
|
||||
)
|
||||
|
||||
# Generate report
|
||||
print(manager.generate_translation_report())
|
||||
|
||||
# Export by language
|
||||
exports = manager.export_by_language(Path("output/multilang"))
|
||||
print(f"\n✅ Exported {len(exports)} language files:")
|
||||
for lang, path in exports.items():
|
||||
print(f" {lang}: {path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
example_usage()
|
||||
304
tests/test_multilang_support.py
Normal file
304
tests/test_multilang_support.py
Normal file
@@ -0,0 +1,304 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Tests for multi-language documentation support.
|
||||
|
||||
Validates:
|
||||
- Language detection (content and filename)
|
||||
- Multi-language organization
|
||||
- Translation status tracking
|
||||
- Language filtering
|
||||
- Export by language
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import tempfile
|
||||
import json
|
||||
|
||||
# Add src to path
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
|
||||
|
||||
from skill_seekers.cli.multilang_support import (
|
||||
LanguageDetector,
|
||||
MultiLanguageManager,
|
||||
LanguageInfo
|
||||
)
|
||||
|
||||
|
||||
def test_detect_english():
|
||||
"""Test English language detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
text = "This is an English document. It contains common English words."
|
||||
lang_info = detector.detect(text)
|
||||
|
||||
assert lang_info.code == 'en'
|
||||
assert lang_info.name == 'English'
|
||||
assert lang_info.confidence > 0.0
|
||||
|
||||
|
||||
def test_detect_spanish():
|
||||
"""Test Spanish language detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
text = "Este es un documento en español. Contiene palabras comunes en español."
|
||||
lang_info = detector.detect(text)
|
||||
|
||||
assert lang_info.code == 'es'
|
||||
assert lang_info.name == 'Spanish'
|
||||
|
||||
|
||||
def test_detect_french():
|
||||
"""Test French language detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
text = "Ceci est un document en français. Il contient des mots français communs."
|
||||
lang_info = detector.detect(text)
|
||||
|
||||
assert lang_info.code == 'fr'
|
||||
assert lang_info.name == 'French'
|
||||
|
||||
|
||||
def test_detect_german():
|
||||
"""Test German language detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
text = "Dies ist ein deutsches Dokument. Es enthält übliche deutsche Wörter."
|
||||
lang_info = detector.detect(text)
|
||||
|
||||
assert lang_info.code == 'de'
|
||||
assert lang_info.name == 'German'
|
||||
|
||||
|
||||
def test_detect_chinese():
|
||||
"""Test Chinese language detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
text = "这是一个中文文档。它包含常见的中文字符。"
|
||||
lang_info = detector.detect(text)
|
||||
|
||||
assert lang_info.code == 'zh'
|
||||
assert lang_info.name == 'Chinese'
|
||||
|
||||
|
||||
def test_detect_from_filename_dot_pattern():
|
||||
"""Test language detection from filename (file.en.md pattern)."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
assert detector.detect_from_filename("README.en.md") == 'en'
|
||||
assert detector.detect_from_filename("guide.es.md") == 'es'
|
||||
assert detector.detect_from_filename("doc.fr.md") == 'fr'
|
||||
|
||||
|
||||
def test_detect_from_filename_underscore_pattern():
|
||||
"""Test language detection from filename (file_en.md pattern)."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
assert detector.detect_from_filename("README_en.md") == 'en'
|
||||
assert detector.detect_from_filename("guide_es.md") == 'es'
|
||||
|
||||
|
||||
def test_detect_from_filename_dash_pattern():
|
||||
"""Test language detection from filename (file-en.md pattern)."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
assert detector.detect_from_filename("README-en.md") == 'en'
|
||||
assert detector.detect_from_filename("guide-es.md") == 'es'
|
||||
|
||||
|
||||
def test_detect_from_filename_no_match():
|
||||
"""Test filename with no language pattern."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
assert detector.detect_from_filename("README.md") is None
|
||||
assert detector.detect_from_filename("guide.txt") is None
|
||||
|
||||
|
||||
def test_add_document_single_language():
|
||||
"""Test adding documents in single language."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document(
|
||||
"README.md",
|
||||
"This is an English document.",
|
||||
{"category": "overview"}
|
||||
)
|
||||
|
||||
assert len(manager.get_languages()) == 1
|
||||
assert 'en' in manager.get_languages()
|
||||
assert manager.get_document_count('en') == 1
|
||||
|
||||
|
||||
def test_add_document_multiple_languages():
|
||||
"""Test adding documents in multiple languages."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("README.md", "This is English.", {})
|
||||
manager.add_document("README.es.md", "Esto es español.", {})
|
||||
manager.add_document("README.fr.md", "Ceci est français.", {})
|
||||
|
||||
assert len(manager.get_languages()) == 3
|
||||
assert 'en' in manager.get_languages()
|
||||
assert 'es' in manager.get_languages()
|
||||
assert 'fr' in manager.get_languages()
|
||||
|
||||
|
||||
def test_force_language():
|
||||
"""Test forcing language override."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
# Force Spanish despite English content
|
||||
manager.add_document(
|
||||
"file.md",
|
||||
"This is actually English content.",
|
||||
{},
|
||||
force_language='es'
|
||||
)
|
||||
|
||||
assert 'es' in manager.get_languages()
|
||||
assert manager.get_document_count('es') == 1
|
||||
|
||||
|
||||
def test_filename_language_priority():
|
||||
"""Test filename pattern takes priority over content detection."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
# Filename says Spanish, but content is English
|
||||
manager.add_document(
|
||||
"guide.es.md",
|
||||
"This is English content.",
|
||||
{}
|
||||
)
|
||||
|
||||
# Should use filename language
|
||||
assert 'es' in manager.get_languages()
|
||||
|
||||
|
||||
def test_document_count_all():
|
||||
"""Test total document count."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("file1.md", "English doc 1", {})
|
||||
manager.add_document("file2.md", "English doc 2", {})
|
||||
manager.add_document("file3.es.md", "Spanish doc", {})
|
||||
|
||||
assert manager.get_document_count() == 3
|
||||
assert manager.get_document_count('en') == 2
|
||||
assert manager.get_document_count('es') == 1
|
||||
|
||||
|
||||
def test_primary_language():
|
||||
"""Test primary language is set correctly."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("file1.md", "First English doc", {})
|
||||
manager.add_document("file2.es.md", "Spanish doc", {})
|
||||
|
||||
# Primary should be first added
|
||||
assert manager.primary_language == 'en'
|
||||
|
||||
|
||||
def test_translation_status():
|
||||
"""Test translation status tracking."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("README.md", "English doc", {})
|
||||
manager.add_document("README.es.md", "Spanish doc", {})
|
||||
manager.add_document("README.fr.md", "French doc", {})
|
||||
|
||||
status = manager.get_translation_status()
|
||||
|
||||
assert status.source_language == 'en'
|
||||
assert 'es' in status.translated_languages
|
||||
assert 'fr' in status.translated_languages
|
||||
assert len(status.translated_languages) == 2
|
||||
|
||||
|
||||
def test_export_by_language():
|
||||
"""Test exporting documents by language."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("file1.md", "English content", {})
|
||||
manager.add_document("file2.es.md", "Spanish content", {})
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
exports = manager.export_by_language(Path(tmpdir))
|
||||
|
||||
assert len(exports) == 2
|
||||
assert 'en' in exports
|
||||
assert 'es' in exports
|
||||
|
||||
# Check files exist
|
||||
assert exports['en'].exists()
|
||||
assert exports['es'].exists()
|
||||
|
||||
# Check content
|
||||
en_data = json.loads(exports['en'].read_text())
|
||||
assert en_data['language'] == 'en'
|
||||
assert en_data['document_count'] == 1
|
||||
|
||||
|
||||
def test_translation_report_generation():
|
||||
"""Test translation report generation."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
manager.add_document("file1.md", "English doc", {})
|
||||
manager.add_document("file2.es.md", "Spanish doc", {})
|
||||
|
||||
report = manager.generate_translation_report()
|
||||
|
||||
assert "MULTI-LANGUAGE DOCUMENTATION REPORT" in report
|
||||
assert "Languages: 2" in report
|
||||
assert "English (en)" in report
|
||||
assert "Spanish (es)" in report
|
||||
|
||||
|
||||
def test_empty_manager():
|
||||
"""Test manager with no documents."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
assert len(manager.get_languages()) == 0
|
||||
assert manager.get_document_count() == 0
|
||||
assert manager.primary_language is None
|
||||
|
||||
|
||||
def test_script_detection():
|
||||
"""Test script type detection."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
# English uses Latin script
|
||||
en_info = detector.detect("This is English")
|
||||
assert en_info.script == 'Latin'
|
||||
|
||||
# Chinese uses Han script
|
||||
zh_info = detector.detect("这是中文")
|
||||
assert zh_info.script == 'Han'
|
||||
|
||||
|
||||
def test_confidence_scoring():
|
||||
"""Test confidence scoring."""
|
||||
detector = LanguageDetector()
|
||||
|
||||
# Strong English signal
|
||||
strong_en = "The quick brown fox jumps over the lazy dog. This is clearly English."
|
||||
lang_info = detector.detect(strong_en)
|
||||
|
||||
assert lang_info.code == 'en'
|
||||
assert lang_info.confidence > 0.3 # Should have decent confidence
|
||||
|
||||
|
||||
def test_metadata_preservation():
|
||||
"""Test metadata is preserved."""
|
||||
manager = MultiLanguageManager()
|
||||
|
||||
metadata = {"category": "guide", "version": "1.0"}
|
||||
manager.add_document("file.md", "English content", metadata)
|
||||
|
||||
docs = manager.documents['en']
|
||||
assert len(docs) == 1
|
||||
assert docs[0]['metadata'] == metadata
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pytest.main([__file__, "-v"])
|
||||
Reference in New Issue
Block a user