150 lines
5.6 KiB
Python
150 lines
5.6 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
測試修復後的DOCX翻譯功能
|
||
"""
|
||
|
||
import sys
|
||
import os
|
||
from pathlib import Path
|
||
|
||
# Fix encoding for Windows console
|
||
if sys.stdout.encoding != 'utf-8':
|
||
sys.stdout.reconfigure(encoding='utf-8')
|
||
if sys.stderr.encoding != 'utf-8':
|
||
sys.stderr.reconfigure(encoding='utf-8')
|
||
|
||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'app'))
|
||
|
||
from app import create_app, db
|
||
from app.services.translation_service import DocxParser
|
||
import tempfile
|
||
|
||
def test_fixed_docx_translation():
|
||
"""測試修復後的DOCX翻譯功能"""
|
||
|
||
app = create_app()
|
||
|
||
with app.app_context():
|
||
print("=== 測試修復後的DOCX翻譯功能 ===")
|
||
|
||
# 使用現有的DOCX文件測試
|
||
original_path = r"C:\Users\EGG\WORK\data\user_scrip\TOOL\Document_translator_V2\uploads\9c6548ac-2f59-45f4-aade-0a9b3895bbfd\original_-OR026_9c6548ac.docx"
|
||
|
||
if not Path(original_path).exists():
|
||
print(f"原始文件不存在: {original_path}")
|
||
return
|
||
|
||
print(f"使用原始文件: {original_path}")
|
||
|
||
# 創建解析器
|
||
parser = DocxParser(original_path)
|
||
|
||
# 測試輸出目錄
|
||
output_dir = Path(tempfile.gettempdir()) / "test_docx_translation"
|
||
output_dir.mkdir(exist_ok=True)
|
||
|
||
print(f"輸出目錄: {output_dir}")
|
||
|
||
# 測試英文翻譯生成
|
||
print(f"\n🔄 測試英文翻譯生成...")
|
||
try:
|
||
# 使用空的translations字典，因為我們現在從快取讀取
|
||
empty_translations = {}
|
||
|
||
en_output_path = parser.generate_translated_document(
|
||
empty_translations,
|
||
'en',
|
||
output_dir
|
||
)
|
||
|
||
print(f"✅ 英文翻譯文件生成成功: {en_output_path}")
|
||
|
||
# 檢查生成的文件
|
||
output_file = Path(en_output_path)
|
||
if output_file.exists():
|
||
print(f"文件大小: {output_file.stat().st_size:,} bytes")
|
||
|
||
# 檢查文件內容
|
||
try:
|
||
from docx import Document
|
||
doc = Document(str(output_file))
|
||
paragraphs = [p.text.strip() for p in doc.paragraphs if p.text.strip()]
|
||
|
||
print(f"總段落數: {len(paragraphs)}")
|
||
|
||
# 分析語言內容
|
||
chinese_count = 0
|
||
english_count = 0
|
||
|
||
for para in paragraphs:
|
||
has_chinese = any('\u4e00' <= c <= '\u9fff' for c in para)
|
||
has_english = any(ord(c) < 128 and c.isalpha() for c in para)
|
||
|
||
if has_chinese:
|
||
chinese_count += 1
|
||
if has_english:
|
||
english_count += 1
|
||
|
||
print(f"含中文段落: {chinese_count}")
|
||
print(f"含英文段落: {english_count}")
|
||
|
||
# 顯示一些範例段落
|
||
print(f"\n📄 前5段落範例:")
|
||
for i, para in enumerate(paragraphs[:5]):
|
||
has_chinese = any('\u4e00' <= c <= '\u9fff' for c in para)
|
||
has_english = any(ord(c) < 128 and c.isalpha() for c in para)
|
||
|
||
status = ""
|
||
if has_chinese and has_english:
|
||
status = "🔄 中英混合"
|
||
elif has_english:
|
||
status = "🇺🇸 純英文"
|
||
elif has_chinese:
|
||
status = "🇨🇳 純中文"
|
||
else:
|
||
status = "❓ 未知"
|
||
|
||
print(f" 段落 {i+1}: {status} - {para[:80]}...")
|
||
|
||
# 判斷翻譯效果
|
||
if english_count > chinese_count:
|
||
print(f"\n✅ 翻譯效果良好 - 英文段落多於中文段落")
|
||
elif english_count > 0:
|
||
print(f"\n⚠️ 翻譯部分成功 - 有英文內容但仍有很多中文")
|
||
else:
|
||
print(f"\n❌ 翻譯失敗 - 沒有英文內容")
|
||
|
||
except Exception as e:
|
||
print(f"❌ 讀取生成文件失敗: {e}")
|
||
else:
|
||
print(f"❌ 生成的文件不存在")
|
||
|
||
except Exception as e:
|
||
print(f"❌ 英文翻譯生成失敗: {e}")
|
||
|
||
# 測試越南文翻譯生成
|
||
print(f"\n🔄 測試越南文翻譯生成...")
|
||
try:
|
||
vi_output_path = parser.generate_translated_document(
|
||
empty_translations,
|
||
'vi',
|
||
output_dir
|
||
)
|
||
|
||
print(f"✅ 越南文翻譯文件生成成功: {vi_output_path}")
|
||
|
||
# 檢查生成的文件大小
|
||
output_file = Path(vi_output_path)
|
||
if output_file.exists():
|
||
print(f"文件大小: {output_file.stat().st_size:,} bytes")
|
||
else:
|
||
print(f"❌ 生成的文件不存在")
|
||
|
||
except Exception as e:
|
||
print(f"❌ 越南文翻譯生成失敗: {e}")
|
||
|
||
print(f"\n🏁 測試完成")
|
||
|
||
if __name__ == "__main__":
|
||
test_fixed_docx_translation() |