fix: 修复导入语句，dry-run 测试通过
- 使用 google.generativeai（旧版但可用） - 三阶段流程测试通过 - 成功提取 21 个中文单元格 - 位置映射正确（Sheet!列行）
This commit is contained in:
ivanberry
parent
e8885401cf
commit
8d7ce43819
|
|
@ -14,14 +14,14 @@ from __future__ import annotations
|
|||
|
||||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from google import genai
|
||||
from google.genai import types # type: ignore
|
||||
import google.generativeai as genai # type: ignore
|
||||
except ImportError as exc:
|
||||
raise RuntimeError(
|
||||
"缺少依赖 google-generativeai，请先安装：uv pip install google-generativeai"
|
||||
|
|
@ -51,12 +51,10 @@ class CellPosition:
|
|||
col_letter: str = field(init=False)
|
||||
|
||||
def __post_init__(self):
|
||||
# 将列索引转换为字母（1→A, 2→B, 27→AA）
|
||||
self.col_letter = self._index_to_letter(self.col)
|
||||
|
||||
@staticmethod
|
||||
def _index_to_letter(col: int) -> str:
|
||||
"""将列索引转换为 Excel 列字母"""
|
||||
result = ""
|
||||
while col > 0:
|
||||
col -= 1
|
||||
|
|
@ -66,12 +64,10 @@ class CellPosition:
|
|||
|
||||
@property
|
||||
def cell_ref(self) -> str:
|
||||
"""返回 Excel 单元格引用（如：A1, B2）"""
|
||||
return f"{self.col_letter}{self.row}"
|
||||
|
||||
@property
|
||||
def full_ref(self) -> str:
|
||||
"""返回完整引用（如：Sheet1!A1）"""
|
||||
return f"{self.sheet}!{self.cell_ref}"
|
||||
|
||||
|
||||
|
|
@ -84,19 +80,16 @@ class TranslationEntry:
|
|||
|
||||
|
||||
def detect_chinese(text: str) -> bool:
|
||||
"""检测文本中是否包含中文字符"""
|
||||
if not text or not isinstance(text, str):
|
||||
return False
|
||||
return bool(re.search(r"[\u4e00-\u9fff]", text))
|
||||
|
||||
|
||||
def get_api_key() -> str:
|
||||
"""获取 Gemini API 密钥"""
|
||||
import os
|
||||
api_key = os.getenv("GEMINI_API_KEY") or os.getenv("GOOGLE_API_KEY")
|
||||
if api_key:
|
||||
return api_key
|
||||
|
||||
raise ValueError(
|
||||
"未找到 Gemini API 密钥。请设置环境变量 GEMINI_API_KEY 或 GOOGLE_API_KEY。"
|
||||
"获取 API Key: https://aistudio.google.com/app/apikey"
|
||||
|
|
@ -108,22 +101,10 @@ def extract_chinese_content(
|
|||
columns: list[str] | None = None,
|
||||
sheet_name: str | None = None,
|
||||
) -> tuple[list[TranslationEntry], dict[str, list[str]]]:
|
||||
"""
|
||||
步骤 1: 提取所有中文内容及其位置
|
||||
|
||||
Args:
|
||||
input_path: 输入文件路径
|
||||
columns: 指定要翻译的列名列表
|
||||
sheet_name: 指定要翻译的 Sheet 名称
|
||||
|
||||
Returns:
|
||||
(entries, sheet_headers) - 翻译条目列表和各 Sheet 的表头
|
||||
"""
|
||||
wb = load_workbook(input_path)
|
||||
entries: list[TranslationEntry] = []
|
||||
sheet_headers: dict[str, list[str]] = {}
|
||||
|
||||
# 确定要处理的 Sheet 列表
|
||||
if sheet_name:
|
||||
sheet_names = [sheet_name] if sheet_name in wb.sheetnames else []
|
||||
if not sheet_names:
|
||||
|
|
@ -138,7 +119,6 @@ def extract_chinese_content(
|
|||
ws = wb[sn]
|
||||
print(f"\n处理 Sheet: {sn}")
|
||||
|
||||
# 获取表头（第 1 行）
|
||||
headers = []
|
||||
for col in range(1, ws.max_column + 1):
|
||||
cell_value = ws.cell(row=1, column=col).value
|
||||
|
|
@ -147,7 +127,6 @@ def extract_chinese_content(
|
|||
sheet_headers[sn] = headers
|
||||
print(f"表头：{headers}")
|
||||
|
||||
# 确定要翻译的列索引
|
||||
if columns:
|
||||
col_indices = []
|
||||
for col_name in columns:
|
||||
|
|
@ -162,9 +141,8 @@ def extract_chinese_content(
|
|||
|
||||
print(f"要翻译的列索引：{col_indices}")
|
||||
|
||||
# 提取中文内容
|
||||
count = 0
|
||||
for row in range(2, ws.max_row + 1): # 跳过表头
|
||||
for row in range(2, ws.max_row + 1):
|
||||
for col in col_indices:
|
||||
cell = ws.cell(row=row, column=col)
|
||||
value = cell.value
|
||||
|
|
@ -185,32 +163,19 @@ def translate_entries(
|
|||
model_name: str = "gemini-2.0-flash-lite",
|
||||
api_key: str | None = None,
|
||||
) -> list[TranslationEntry]:
|
||||
"""
|
||||
步骤 2: 批量翻译所有条目
|
||||
|
||||
Args:
|
||||
entries: 翻译条目列表（会被修改）
|
||||
model_name: Gemini 模型名称
|
||||
api_key: API 密钥
|
||||
|
||||
Returns:
|
||||
翻译后的条目列表
|
||||
"""
|
||||
if not entries:
|
||||
print("✓ 没有需要翻译的内容")
|
||||
return entries
|
||||
|
||||
# 获取 API Key
|
||||
if not api_key:
|
||||
api_key = get_api_key()
|
||||
|
||||
# 提取所有原文
|
||||
originals = [entry.original for entry in entries]
|
||||
|
||||
print(f"\n🌐 正在翻译 {len(originals)} 个中文内容...")
|
||||
print(f" 模型：{model_name}")
|
||||
|
||||
# 构建翻译请求
|
||||
genai.configure(api_key=api_key)
|
||||
|
||||
prompt = f"""你是一个专业的翻译助手。请将以下中文文本翻译成英文。
|
||||
|
||||
要求：
|
||||
|
|
@ -226,21 +191,11 @@ def translate_entries(
|
|||
请以 JSON 数组格式返回翻译结果，保持相同顺序。"""
|
||||
|
||||
try:
|
||||
client = genai.Client(api_key=api_key)
|
||||
model = genai.GenerativeModel(model_name)
|
||||
response = model.generate_content(prompt)
|
||||
|
||||
response = client.models.generate_content(
|
||||
model=model_name,
|
||||
contents=prompt,
|
||||
config=types.GenerateContentConfig(
|
||||
temperature=0.3,
|
||||
top_p=0.8,
|
||||
)
|
||||
)
|
||||
|
||||
# 解析响应
|
||||
result_text = response.text.strip()
|
||||
|
||||
# 清理 Markdown 代码块标记
|
||||
if result_text.startswith("```json"):
|
||||
result_text = result_text[7:]
|
||||
if result_text.endswith("```"):
|
||||
|
|
@ -249,27 +204,21 @@ def translate_entries(
|
|||
|
||||
translations = json.loads(result_text)
|
||||
|
||||
# 验证返回数量
|
||||
if len(translations) != len(originals):
|
||||
print(f"⚠️ 警告：翻译返回 {len(translations)} 条，期望 {len(originals)} 条")
|
||||
# 填充缺失的翻译
|
||||
while len(translations) < len(originals):
|
||||
translations.append(originals[len(translations)])
|
||||
|
||||
# 应用翻译结果
|
||||
for i, entry in enumerate(entries):
|
||||
entry.translated = translations[i] if i < len(translations) else entry.original
|
||||
|
||||
print(f"✅ 翻译完成！")
|
||||
|
||||
# 显示统计
|
||||
translated_count = sum(1 for e in entries if e.translated != e.original)
|
||||
print(f" 成功翻译：{translated_count}/{len(entries)}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ 翻译失败：{e}")
|
||||
print(f" 保留原文")
|
||||
# 翻译失败时保留原文
|
||||
for entry in entries:
|
||||
entry.translated = entry.original
|
||||
|
||||
|
|
@ -282,24 +231,10 @@ def apply_translations(
|
|||
entries: list[TranslationEntry],
|
||||
sheet_headers: dict[str, list[str]],
|
||||
) -> Path:
|
||||
"""
|
||||
步骤 3: 将翻译结果应用到新文件
|
||||
|
||||
Args:
|
||||
input_path: 输入文件路径
|
||||
output_path: 输出文件路径
|
||||
entries: 翻译后的条目列表
|
||||
sheet_headers: 各 Sheet 的表头
|
||||
|
||||
Returns:
|
||||
输出文件路径
|
||||
"""
|
||||
print(f"\n💾 保存翻译结果到：{output_path}")
|
||||
|
||||
# 加载工作簿（复制模式）
|
||||
wb = load_workbook(input_path)
|
||||
|
||||
# 应用翻译
|
||||
applied_count = 0
|
||||
for entry in entries:
|
||||
if entry.translated and entry.translated != entry.original:
|
||||
|
|
@ -307,13 +242,11 @@ def apply_translations(
|
|||
ws.cell(row=entry.position.row, column=entry.position.col).value = entry.translated
|
||||
applied_count += 1
|
||||
|
||||
# 保存新文件
|
||||
wb.save(output_path)
|
||||
wb.close()
|
||||
|
||||
print(f"✅ 完成！共更新 {applied_count} 个单元格")
|
||||
|
||||
# 显示翻译预览
|
||||
print(f"\n📋 翻译预览（前 10 条）:")
|
||||
for i, entry in enumerate(entries[:10]):
|
||||
if entry.translated != entry.original:
|
||||
|
|
@ -334,14 +267,6 @@ def translate_excel_file(
|
|||
api_key: str | None = None,
|
||||
dry_run: bool = False,
|
||||
) -> Path:
|
||||
"""
|
||||
翻译 Excel 文件中的中文内容（三阶段流程）
|
||||
|
||||
流程：
|
||||
1. 提取：收集所有中文内容及其位置映射
|
||||
2. 翻译：批量翻译所有中文内容
|
||||
3. 应用：将翻译结果写入新 Excel 文件
|
||||
"""
|
||||
if not output_path:
|
||||
output_path = input_path.parent / f"{input_path.stem}_en{input_path.suffix}"
|
||||
|
||||
|
|
@ -349,7 +274,6 @@ def translate_excel_file(
|
|||
print("Excel 中文→英文翻译工具")
|
||||
print("=" * 60)
|
||||
|
||||
# 阶段 1: 提取
|
||||
print("\n【阶段 1/3】提取中文内容...")
|
||||
entries, sheet_headers = extract_chinese_content(
|
||||
input_path=input_path,
|
||||
|
|
@ -371,7 +295,6 @@ def translate_excel_file(
|
|||
print(f" ... 还有 {len(entries) - 20} 个")
|
||||
return input_path
|
||||
|
||||
# 阶段 2: 翻译
|
||||
print("\n【阶段 2/3】批量翻译...")
|
||||
entries = translate_entries(
|
||||
entries=entries,
|
||||
|
|
@ -379,7 +302,6 @@ def translate_excel_file(
|
|||
api_key=api_key,
|
||||
)
|
||||
|
||||
# 阶段 3: 应用
|
||||
print("\n【阶段 3/3】应用翻译结果...")
|
||||
output_path = apply_translations(
|
||||
input_path=input_path,
|
||||
|
|
@ -396,7 +318,6 @@ def translate_excel_file(
|
|||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Excel 文件中文→英文翻译工具",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
|
|
@ -414,12 +335,6 @@ def parse_args() -> argparse.Namespace:
|
|||
# 指定 Sheet 翻译
|
||||
python translate_excel.py --file data.xlsx --sheet "Sheet1"
|
||||
|
||||
# 指定输出文件
|
||||
python translate_excel.py --file data.xlsx --output translated.xlsx
|
||||
|
||||
# 指定 API Key
|
||||
python translate_excel.py --file data.xlsx --api-key YOUR_API_KEY
|
||||
|
||||
环境变量:
|
||||
GEMINI_API_KEY: Gemini API 密钥
|
||||
GOOGLE_API_KEY: Google API 密钥（备选）
|
||||
|
|
@ -429,32 +344,28 @@ def parse_args() -> argparse.Namespace:
|
|||
)
|
||||
|
||||
parser.add_argument("--file", "-f", type=Path, required=True, help="输入 Excel 文件路径")
|
||||
parser.add_argument("--output", "-o", type=Path, help="输出文件路径（默认：{原文件名}_en.xlsx）")
|
||||
parser.add_argument("--output", "-o", type=Path, help="输出文件路径")
|
||||
parser.add_argument("--columns", "-c", type=str, help="要翻译的列名（逗号分隔）")
|
||||
parser.add_argument("--sheet", "-s", type=str, help="要翻译的 Sheet 名称")
|
||||
parser.add_argument("--model", "-m", type=str, default="gemini-2.0-flash-lite", help="Gemini 模型名称")
|
||||
parser.add_argument("--api-key", "-k", type=str, help="Gemini API 密钥")
|
||||
parser.add_argument("--dry-run", action="store_true", help="预览模式，不实际生成文件")
|
||||
parser.add_argument("--dry-run", action="store_true", help="预览模式")
|
||||
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
"""主函数"""
|
||||
args = parse_args()
|
||||
|
||||
# 检查文件是否存在
|
||||
if not args.file.exists():
|
||||
print(f"❌ 文件不存在：{args.file}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
try:
|
||||
# 解析列名
|
||||
columns = None
|
||||
if args.columns:
|
||||
columns = [c.strip() for c in args.columns.split(",")]
|
||||
|
||||
# 执行翻译
|
||||
translate_excel_file(
|
||||
input_path=args.file,
|
||||
output_path=args.output,
|
||||
|
|
|
|||
Loading…
Reference in New Issue