Files
Document_Translator/app/api/files.py
2025-09-04 10:21:16 +08:00

691 lines
23 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
檔案管理 API
Author: PANJIT IT Team
Created: 2024-01-28
Modified: 2024-01-28
"""
import json
import zipfile
import tempfile
from pathlib import Path
from flask import Blueprint, request, jsonify, send_file, current_app, g
from werkzeug.utils import secure_filename
from app.utils.decorators import jwt_login_required, rate_limit
from app.utils.validators import validate_file, validate_languages, validate_job_uuid
from app.utils.helpers import (
save_uploaded_file,
create_response,
format_file_size,
generate_download_token
)
from app.utils.exceptions import ValidationError, FileProcessingError
from app.utils.logger import get_logger
from app.models.job import TranslationJob
from app.models.log import SystemLog
files_bp = Blueprint('files', __name__, url_prefix='/files')
logger = get_logger(__name__)
@files_bp.route('/upload', methods=['POST'])
@jwt_login_required
@rate_limit(max_requests=20, per_seconds=3600) # 每小時最多20次上傳
def upload_file():
"""檔案上傳"""
try:
# 檢查是否有檔案
if 'file' not in request.files:
return jsonify(create_response(
success=False,
error='NO_FILE',
message='未選擇檔案'
)), 400
file_obj = request.files['file']
# 驗證檔案
file_info = validate_file(file_obj)
# 取得翻譯設定
source_language = request.form.get('source_language', 'auto')
target_languages_str = request.form.get('target_languages', '[]')
try:
target_languages = json.loads(target_languages_str)
except json.JSONDecodeError:
return jsonify(create_response(
success=False,
error='INVALID_TARGET_LANGUAGES',
message='目標語言格式錯誤'
)), 400
# 驗證語言設定
lang_info = validate_languages(source_language, target_languages)
# 建立翻譯任務
job = TranslationJob(
user_id=g.current_user_id,
original_filename=file_info['filename'],
file_extension=file_info['file_extension'],
file_size=file_info['file_size'],
file_path='', # 暫時為空,稍後更新
source_language=lang_info['source_language'],
target_languages=lang_info['target_languages'],
status='PENDING'
)
# 先保存到資料庫以取得 job_uuid
from app import db
db.session.add(job)
db.session.commit()
# 儲存檔案
file_result = save_uploaded_file(file_obj, job.job_uuid)
if not file_result['success']:
# 如果儲存失敗,刪除任務記錄
db.session.delete(job)
db.session.commit()
raise FileProcessingError(f"檔案儲存失敗: {file_result['error']}")
# 更新任務的檔案路徑
job.file_path = file_result['file_path']
# 新增原始檔案記錄
job.add_original_file(
filename=file_result['filename'],
file_path=file_result['file_path'],
file_size=file_result['file_size']
)
db.session.commit()
# 計算佇列位置
queue_position = TranslationJob.get_queue_position(job.job_uuid)
# 記錄日誌
SystemLog.info(
'files.upload',
f'File uploaded successfully: {file_info["filename"]}',
user_id=g.current_user_id,
job_id=job.id,
extra_data={
'filename': file_info['filename'],
'file_size': file_info['file_size'],
'source_language': source_language,
'target_languages': target_languages
}
)
logger.info(f"File uploaded successfully: {job.job_uuid} - {file_info['filename']}")
# 觸發翻譯任務
try:
from app.tasks.translation import process_translation_job
# 嘗試使用 Celery 異步處理
try:
task = process_translation_job.delay(job.id)
logger.info(f"Translation task queued with Celery: {task.id} for job {job.job_uuid}")
except Exception as celery_error:
logger.warning(f"Celery not available, falling back to synchronous processing: {str(celery_error)}")
# Celery 不可用時,使用同步處理
try:
from app.services.translation_service import TranslationService
service = TranslationService()
# 在後台執行翻譯(同步處理)
logger.info(f"Starting synchronous translation for job {job.job_uuid}")
result = service.translate_document(job.job_uuid)
logger.info(f"Synchronous translation completed for job {job.job_uuid}: {result}")
except Exception as sync_error:
logger.error(f"Synchronous translation failed for job {job.job_uuid}: {str(sync_error)}")
job.update_status('FAILED', error_message=f"翻譯處理失敗: {str(sync_error)}")
db.session.commit()
except Exception as e:
logger.error(f"Failed to process translation for job {job.job_uuid}: {str(e)}")
job.update_status('FAILED', error_message=f"任務處理失敗: {str(e)}")
db.session.commit()
return jsonify(create_response(
success=True,
data={
'job_uuid': job.job_uuid,
'original_filename': job.original_filename,
'file_size': job.file_size,
'file_size_formatted': format_file_size(job.file_size),
'source_language': job.source_language,
'target_languages': job.target_languages,
'status': job.status,
'queue_position': queue_position,
'created_at': job.created_at.isoformat()
},
message='檔案上傳成功,已加入翻譯佇列'
))
except ValidationError as e:
logger.warning(f"File upload validation error: {str(e)}")
return jsonify(create_response(
success=False,
error=e.error_code,
message=str(e)
)), 400
except FileProcessingError as e:
logger.error(f"File processing error: {str(e)}")
return jsonify(create_response(
success=False,
error='FILE_PROCESSING_ERROR',
message=str(e)
)), 500
except Exception as e:
logger.error(f"File upload error: {str(e)}")
SystemLog.error(
'files.upload_error',
f'File upload failed: {str(e)}',
user_id=g.current_user_id,
extra_data={'error': str(e)}
)
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='檔案上傳失敗'
)), 500
@files_bp.route('/<job_uuid>/download/<language_code>', methods=['GET'])
@jwt_login_required
def download_file(job_uuid, language_code):
"""下載翻譯檔案"""
try:
# 驗證 UUID 格式
validate_job_uuid(job_uuid)
# 取得任務
job = TranslationJob.query.filter_by(job_uuid=job_uuid).first()
if not job:
return jsonify(create_response(
success=False,
error='JOB_NOT_FOUND',
message='任務不存在'
)), 404
# 檢查權限
if job.user_id != g.current_user_id and not g.is_admin:
return jsonify(create_response(
success=False,
error='PERMISSION_DENIED',
message='無權限存取此檔案'
)), 403
# 檢查任務狀態
if job.status != 'COMPLETED':
return jsonify(create_response(
success=False,
error='JOB_NOT_COMPLETED',
message='任務尚未完成'
)), 400
# 尋找對應的翻譯檔案
translated_file = None
for file_record in job.files:
if file_record.file_type == 'TRANSLATED' and file_record.language_code == language_code:
translated_file = file_record
break
if not translated_file:
return jsonify(create_response(
success=False,
error='FILE_NOT_FOUND',
message=f'找不到 {language_code} 的翻譯檔案'
)), 404
# 檢查檔案是否存在
file_path = Path(translated_file.file_path)
if not file_path.exists():
logger.error(f"File not found on disk: {file_path}")
return jsonify(create_response(
success=False,
error='FILE_NOT_FOUND_ON_DISK',
message='檔案在伺服器上不存在'
)), 404
# 記錄下載日誌
SystemLog.info(
'files.download',
f'File downloaded: {translated_file.filename}',
user_id=g.current_user_id,
job_id=job.id,
extra_data={
'filename': translated_file.filename,
'language_code': language_code,
'file_size': translated_file.file_size
}
)
logger.info(f"File downloaded: {job.job_uuid} - {language_code}")
# 發送檔案
return send_file(
str(file_path),
as_attachment=True,
download_name=translated_file.filename,
mimetype='application/octet-stream'
)
except ValidationError as e:
return jsonify(create_response(
success=False,
error=e.error_code,
message=str(e)
)), 400
except Exception as e:
logger.error(f"File download error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='檔案下載失敗'
)), 500
@files_bp.route('/<job_uuid>/download/original', methods=['GET'])
@jwt_login_required
def download_original_file(job_uuid):
"""下載原始檔案"""
try:
# 驗證 UUID 格式
validate_job_uuid(job_uuid)
# 取得任務
job = TranslationJob.query.filter_by(job_uuid=job_uuid).first()
if not job:
return jsonify(create_response(
success=False,
error='JOB_NOT_FOUND',
message='任務不存在'
)), 404
# 檢查權限
if job.user_id != g.current_user_id and not g.is_admin:
return jsonify(create_response(
success=False,
error='PERMISSION_DENIED',
message='無權限存取此檔案'
)), 403
# 取得原始檔案
original_file = job.get_original_file()
if not original_file:
return jsonify(create_response(
success=False,
error='ORIGINAL_FILE_NOT_FOUND',
message='找不到原始檔案記錄'
)), 404
# 檢查檔案是否存在
file_path = Path(original_file.file_path)
if not file_path.exists():
logger.error(f"Original file not found on disk: {file_path}")
return jsonify(create_response(
success=False,
error='FILE_NOT_FOUND_ON_DISK',
message='原始檔案在伺服器上不存在'
)), 404
# 記錄下載日誌
SystemLog.info(
'files.download_original',
f'Original file downloaded: {original_file.filename}',
user_id=g.current_user_id,
job_id=job.id,
extra_data={
'filename': original_file.filename,
'file_size': original_file.file_size
}
)
logger.info(f"Original file downloaded: {job.job_uuid}")
# 發送檔案
return send_file(
str(file_path),
as_attachment=True,
download_name=job.original_filename,
mimetype='application/octet-stream'
)
except ValidationError as e:
return jsonify(create_response(
success=False,
error=e.error_code,
message=str(e)
)), 400
except Exception as e:
logger.error(f"Original file download error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='原始檔案下載失敗'
)), 500
@files_bp.route('/supported-formats', methods=['GET'])
def get_supported_formats():
"""取得支援的檔案格式"""
try:
formats = {
'.docx': {
'name': 'Word 文件 (.docx)',
'description': 'Microsoft Word 2007+ 格式',
'icon': 'file-word'
},
'.doc': {
'name': 'Word 文件 (.doc)',
'description': 'Microsoft Word 97-2003 格式',
'icon': 'file-word'
},
'.pptx': {
'name': 'PowerPoint 簡報 (.pptx)',
'description': 'Microsoft PowerPoint 2007+ 格式',
'icon': 'file-powerpoint'
},
'.xlsx': {
'name': 'Excel 試算表 (.xlsx)',
'description': 'Microsoft Excel 2007+ 格式',
'icon': 'file-excel'
},
'.xls': {
'name': 'Excel 試算表 (.xls)',
'description': 'Microsoft Excel 97-2003 格式',
'icon': 'file-excel'
},
'.pdf': {
'name': 'PDF 文件 (.pdf)',
'description': 'Portable Document Format',
'icon': 'file-pdf'
}
}
max_size = current_app.config.get('MAX_CONTENT_LENGTH', 26214400)
return jsonify(create_response(
success=True,
data={
'supported_formats': formats,
'max_file_size': max_size,
'max_file_size_formatted': format_file_size(max_size)
}
))
except Exception as e:
logger.error(f"Get supported formats error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='取得支援格式失敗'
)), 500
@files_bp.route('/supported-languages', methods=['GET'])
def get_supported_languages():
"""取得支援的語言"""
try:
from app.utils.helpers import get_supported_languages
languages = get_supported_languages()
return jsonify(create_response(
success=True,
data={
'supported_languages': languages
}
))
except Exception as e:
logger.error(f"Get supported languages error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='取得支援語言失敗'
)), 500
@files_bp.route('/<job_uuid>/download/batch', methods=['GET'])
@jwt_login_required
def download_batch_files(job_uuid):
"""批量下載所有翻譯檔案為 ZIP"""
try:
# 驗證 UUID 格式
validate_job_uuid(job_uuid)
# 取得任務
job = TranslationJob.query.filter_by(job_uuid=job_uuid).first()
if not job:
return jsonify(create_response(
success=False,
error='JOB_NOT_FOUND',
message='任務不存在'
)), 404
# 檢查權限
if job.user_id != g.current_user_id and not g.is_admin:
return jsonify(create_response(
success=False,
error='PERMISSION_DENIED',
message='無權限存取此檔案'
)), 403
# 檢查任務狀態
if job.status != 'COMPLETED':
return jsonify(create_response(
success=False,
error='JOB_NOT_COMPLETED',
message='任務尚未完成'
)), 400
# 收集所有翻譯檔案
translated_files = job.get_translated_files()
if not translated_files:
return jsonify(create_response(
success=False,
error='NO_TRANSLATED_FILES',
message='沒有找到翻譯檔案'
)), 404
# 建立臨時 ZIP 檔案
temp_dir = tempfile.gettempdir()
zip_filename = f"{job.original_filename.split('.')[0]}_translations_{job.job_uuid[:8]}.zip"
zip_path = Path(temp_dir) / zip_filename
try:
with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zip_file:
files_added = 0
# 添加原始檔案
original_file = job.get_original_file()
if original_file and Path(original_file.file_path).exists():
zip_file.write(
original_file.file_path,
f"original/{original_file.filename}"
)
files_added += 1
# 添加所有翻譯檔案(避免重複)
added_files = set() # 追蹤已添加的檔案,避免重複
for tf in translated_files:
file_path = Path(tf.file_path)
if file_path.exists():
# 按語言建立資料夾結構
archive_name = f"{tf.language_code}/{tf.filename}"
# 檢查是否已經添加過這個檔案
if archive_name not in added_files:
zip_file.write(str(file_path), archive_name)
added_files.add(archive_name)
files_added += 1
else:
logger.warning(f"Translation file not found: {tf.file_path}")
if files_added == 0:
return jsonify(create_response(
success=False,
error='NO_FILES_TO_ZIP',
message='沒有可用的檔案進行壓縮'
)), 404
# 檢查 ZIP 檔案是否建立成功
if not zip_path.exists():
return jsonify(create_response(
success=False,
error='ZIP_CREATION_FAILED',
message='ZIP 檔案建立失敗'
)), 500
# 記錄下載日誌
SystemLog.info(
'files.download_batch',
f'Batch files downloaded: {zip_filename}',
user_id=g.current_user_id,
job_id=job.id,
extra_data={
'zip_filename': zip_filename,
'files_count': files_added,
'job_uuid': job_uuid
}
)
logger.info(f"Batch files downloaded: {job.job_uuid} - {files_added} files in ZIP")
# 發送 ZIP 檔案
return send_file(
str(zip_path),
as_attachment=True,
download_name=zip_filename,
mimetype='application/zip'
)
finally:
# 清理臨時檔案(在發送後會自動清理)
pass
except ValidationError as e:
return jsonify(create_response(
success=False,
error=e.error_code,
message=str(e)
)), 400
except Exception as e:
logger.error(f"Batch download error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='批量下載失敗'
)), 500
@files_bp.route('/<job_uuid>/download/combine', methods=['GET'])
@jwt_login_required
def download_combine_file(job_uuid):
"""下載合併檔案"""
try:
# 驗證 UUID 格式
validate_job_uuid(job_uuid)
# 取得當前用戶
current_user_id = g.current_user_id
# 查找任務
job = TranslationJob.query.filter_by(
job_uuid=job_uuid,
user_id=current_user_id
).first()
if not job:
return jsonify(create_response(
success=False,
error='JOB_NOT_FOUND',
message='任務不存在'
)), 404
# 檢查任務狀態
if job.status != 'COMPLETED':
return jsonify(create_response(
success=False,
error='JOB_NOT_COMPLETED',
message='任務尚未完成'
)), 400
# 尋找 combine 檔案
combine_file = None
for file in job.files:
if file.filename.lower().find('combine') != -1 or file.file_type == 'combined':
combine_file = file
break
if not combine_file:
return jsonify(create_response(
success=False,
error='COMBINE_FILE_NOT_FOUND',
message='找不到合併檔案'
)), 404
# 檢查檔案是否存在
file_path = Path(combine_file.file_path)
if not file_path.exists():
return jsonify(create_response(
success=False,
error='FILE_NOT_FOUND',
message='合併檔案已被刪除'
)), 404
logger.info(f"Combine file downloaded: {job.job_uuid} - {combine_file.filename}")
# 發送檔案
return send_file(
str(file_path),
as_attachment=True,
download_name=combine_file.filename,
mimetype='application/octet-stream'
)
except ValidationError as e:
return jsonify(create_response(
success=False,
error=e.error_code,
message=str(e)
)), 400
except Exception as e:
logger.error(f"Combine file download error: {str(e)}")
return jsonify(create_response(
success=False,
error='SYSTEM_ERROR',
message='合併檔案下載失敗'
)), 500