106 lines
3.1 KiB
Python
106 lines
3.1 KiB
Python
"""文件格式转换:统一用 xlsx 作为工作副本。
|
||
|
||
支持 .xls / .xlsx / .csv / .ods。转换走 LibreOffice(已预装)。
|
||
"""
|
||
import csv
|
||
import shutil
|
||
import subprocess
|
||
import tempfile
|
||
from pathlib import Path
|
||
|
||
import openpyxl
|
||
|
||
from . import UserError
|
||
|
||
|
||
SUPPORTED_EXTS = {'.xls', '.xlsx', '.csv', '.ods'}
|
||
_CSV_ENCODINGS = ('utf-8-sig', 'utf-8', 'gbk', 'gb18030', 'latin-1')
|
||
|
||
|
||
def check_supported(path: Path) -> str:
|
||
ext = path.suffix.lower()
|
||
if ext not in SUPPORTED_EXTS:
|
||
raise UserError(
|
||
f"不支持的格式: {ext}(支持: {', '.join(sorted(SUPPORTED_EXTS))})"
|
||
)
|
||
return ext
|
||
|
||
|
||
def to_workbook(path: Path, work_dir: Path) -> Path:
|
||
"""把输入文件转成 xlsx 工作副本,返回 xlsx 路径。"""
|
||
ext = check_supported(path)
|
||
work_dir.mkdir(parents=True, exist_ok=True)
|
||
|
||
if ext == '.xlsx':
|
||
dst = work_dir / path.name
|
||
shutil.copy2(path, dst)
|
||
return dst
|
||
|
||
if ext == '.csv':
|
||
rows = _read_csv(path)
|
||
wb = openpyxl.Workbook()
|
||
ws = wb.active
|
||
ws.title = 'Sheet1'
|
||
# CSV 是文本格式:原样保留字段字符串(不做数字 coerce),回写才算真「最小改动」
|
||
for row in rows:
|
||
ws.append(list(row))
|
||
dst = work_dir / (path.stem + '.xlsx')
|
||
wb.save(dst)
|
||
return dst
|
||
|
||
return _libreoffice(path, work_dir, '.xlsx')
|
||
|
||
|
||
def from_workbook(xlsx: Path, dst: Path, original_ext: str):
|
||
"""把处理后的 xlsx 转回目标格式,写到 dst。"""
|
||
ext = original_ext.lower()
|
||
dst.parent.mkdir(parents=True, exist_ok=True)
|
||
|
||
if ext == '.xlsx':
|
||
shutil.copy2(xlsx, dst)
|
||
return
|
||
|
||
if ext == '.csv':
|
||
wb = openpyxl.load_workbook(xlsx, data_only=False)
|
||
ws = wb.active
|
||
with open(dst, 'w', encoding='utf-8-sig', newline='') as f:
|
||
w = csv.writer(f)
|
||
for row in ws.iter_rows(values_only=True):
|
||
w.writerow(['' if v is None else v for v in row])
|
||
return
|
||
|
||
with tempfile.TemporaryDirectory() as td:
|
||
produced = _libreoffice(xlsx, Path(td), ext)
|
||
shutil.copy2(produced, dst)
|
||
|
||
|
||
# ---------- 内部 ----------
|
||
|
||
def _libreoffice(src: Path, out_dir: Path, target_ext: str) -> Path:
|
||
out_dir.mkdir(parents=True, exist_ok=True)
|
||
target = target_ext.lstrip('.')
|
||
r = subprocess.run(
|
||
['libreoffice', '--headless', '--convert-to', target,
|
||
'--outdir', str(out_dir), str(src)],
|
||
capture_output=True, text=True, timeout=180,
|
||
)
|
||
if r.returncode != 0:
|
||
msg = (r.stderr or r.stdout).strip() or '无输出'
|
||
raise UserError(f"LibreOffice 转换失败: {msg}")
|
||
expected = out_dir / (src.stem + target_ext)
|
||
if not expected.exists():
|
||
raise UserError(f"LibreOffice 未生成输出: {expected}")
|
||
return expected
|
||
|
||
|
||
def _read_csv(path: Path):
|
||
last_err = None
|
||
for enc in _CSV_ENCODINGS:
|
||
try:
|
||
with open(path, encoding=enc, newline='') as f:
|
||
return list(csv.reader(f))
|
||
except UnicodeDecodeError as e:
|
||
last_err = e
|
||
continue
|
||
raise UserError(f"无法识别 CSV 编码: {path}(最后错误: {last_err})")
|