Files
knowledge-governance/scripts/axls_to_xlsx.py
T
姚章浩 f4e1ecc5f1 feat(artifact): 钉钉取件优先走 dws(DingTalk Workspace CLI),老路径保留为回退
- artifact_fetch.py: 新增 dingtalk dws 取件器(adoc→doc export、axls→sheet 转换、其余→drive 直下),
  ARTIFACT_DINGTALK_FETCHER=dws|auto|legacy 三级开关,auto 仅对可重试错误回落老路径;
  平台侧判定(pick_suffix/SLIDES/magic/大小上限/sha256/spool/空壳检查)全部保留;
  结果 JSON 字段不变(Go runner 用 DisallowUnknownFields 解析 stdout),取件器来源只写 stderr。
- axls_to_xlsx.py: 纯标准库 axls→xlsx(文本写入 sharedStrings 以通过空壳判定)。
- dws_error_map.py: dws 错误→平台 {ok,code,retryable,missing};未分类错误默认不重试。
- Dockerfile: alpine 增加 gcompat/libc6-compat;dws v1.0.63 固定版本+sha256 校验;构建期 dws version 自检。
- compose.yaml: worker 增加 dws 环境与凭据挂载(DWS_HOME 方案,XDG_DATA_HOME 不被 dws 识别)。
- 测试: artifact_fetch_test 新增 11 项(路由/回落语义/契约字段锁定);dws_error_map 17 断言。
- 实测: 真容器(--read-only --tmpfs --user 1000:1000) 端到端 adoc/axls/pdf 3/3 成功,docx sha 与平台基准一致。
2026-10-09 10:57:11 +08:00

189 lines
8.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""dws axls → xlsx 转换器(纯标准库,无 openpyxl)。
用途:dws 没有 axls 直出接口,只能 sheet range read 拿单元格;本脚本把单元格写成
合法的 .xlsx,供平台 artifact_fetch 的 dingtalk dws 取件器落盘入库。
兼容平台既有检查:
- `exported_doc_is_blank()` 对 spreadsheet 只读 `xl/sharedStrings.xml` → 本脚本**把文本写进 sharedStrings**,
否则会被判定为"空壳文档"而拒收。
- 必须 PK magic、能被子解析器识别为 xlsx。
归一化约定(与平台既有 xlsx 产物对齐):
- 单元格换行 CRLF/CR → LF
- 日期保持 dws 返回的显示文本(平台旧产物是 Excel 序列号,转换后语义一致)
dws 可执行文件解析顺序:$DWS_BIN → PATH 里的 dws。
"""
import argparse, json, os, re, shutil, subprocess, sys, zipfile
from xml.sax.saxutils import escape
NUM_RE = re.compile(r"^-?\d+(\.\d+)?$")
def dws_binary():
return os.environ.get("DWS_BIN") or shutil.which("dws") or "/usr/local/bin/dws"
def run_json(args, timeout=180):
# dws 的文件型 keychain 在 $HOME/.local/share/dws-cli,容器里用 DWS_HOME 单独指定
env = dict(os.environ)
dws_home = os.environ.get("DWS_HOME")
if dws_home:
env["HOME"] = dws_home
p = subprocess.run([dws_binary(), *args, "-f", "json"], capture_output=True, text=True,
timeout=timeout, env=env)
try:
return json.loads(p.stdout)
except Exception:
raise SystemExit(f"dws 调用失败: {' '.join(args)} :: {(p.stdout or p.stderr)[:300]}")
def fetch_sheets(node):
"""返回 [{'name':str,'cells':[[...]]}]"""
listing = run_json(["sheet", "list", "--node", node])
sheets = listing.get("sheets") or []
if not sheets:
raise SystemExit(f"sheet list 无工作表: {json.dumps(listing, ensure_ascii=False)[:200]}")
out = []
for s in sheets:
sid = s.get("sheetId") or s.get("name")
r = run_json(["sheet", "range", "read", "--node", node, "--sheet-id", sid])
out.append({"name": s.get("name") or sid, "cells": r.get("cells") or []})
return out
def norm(v):
if v is None:
return None
s = str(v)
if "\r" in s:
s = s.replace("\r\n", "\n").replace("\r", "\n")
return s
def col_letter(idx):
"""0-based 列号 → A/B/.../AA"""
s = ""
idx += 1
while idx:
idx, rem = divmod(idx - 1, 26)
s = chr(65 + rem) + s
return s
def sheet_name(name, used):
n = re.sub(r"[\[\]:*?/\\]", "_", str(name or "Sheet")).strip()[:31] or "Sheet"
base, i = n, 1
while n.lower() in used:
suffix = f"_{i}"
n = base[: 31 - len(suffix)] + suffix
i += 1
used.add(n.lower())
return n
def build_xlsx(sheets, path):
# 1) 收集共享字符串 + 每表 XML
shared, shared_idx = [], {}
def sidx(text):
if text not in shared_idx:
shared_idx[text] = len(shared)
shared.append(text)
return shared_idx[text]
used, sheet_xml, names = set(), [], []
for s in sheets:
sname = sheet_name(s.get("name"), used)
names.append(sname)
rows = s.get("cells") or []
chunks = []
for ri, row in enumerate(rows, start=1):
cells = []
for ci, cell in enumerate(row):
v = cell.get("value") if isinstance(cell, dict) else cell
v = norm(v)
if v is None or v == "":
continue
ref = f"{col_letter(ci)}{ri}"
if NUM_RE.match(v):
cells.append(f'<c r="{ref}"><v>{v}</v></c>')
else:
cells.append(f'<c r="{ref}" t="s"><v>{sidx(v)}</v></c>')
if cells:
chunks.append(f'<row r="{ri}">{"".join(cells)}</row>')
sheet_xml.append(
'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">'
f'<sheetData>{"".join(chunks)}</sheetData></worksheet>')
n = len(names)
ct = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'
'<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>'
'<Default Extension="xml" ContentType="application/xml"/>'
'<Override PartName="/xl/workbook.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml"/>'
'<Override PartName="/xl/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml"/>'
'<Override PartName="/xl/sharedStrings.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml"/>'
+ "".join(f'<Override PartName="/xl/worksheets/sheet{i+1}.xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml"/>' for i in range(n))
+ '</Types>')
rels = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
'<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="xl/workbook.xml"/>'
'</Relationships>')
wb = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" '
'xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"><sheets>'
+ "".join(f'<sheet name="{escape(names[i])}" sheetId="{i+1}" r:id="rId{i+1}"/>' for i in range(n))
+ '</sheets></workbook>')
wb_rels = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
+ "".join(f'<Relationship Id="rId{i+1}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet" Target="worksheets/sheet{i+1}.xml"/>' for i in range(n))
+ f'<Relationship Id="rId{n+1}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>'
+ f'<Relationship Id="rId{n+2}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings" Target="sharedStrings.xml"/>'
+ '</Relationships>')
styles = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
'<styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">'
'<fonts count="1"><font><sz val="11"/><name val="Calibri"/></font></fonts>'
'<fills count="1"><fill><patternFill patternType="none"/></fill></fills>'
'<borders count="1"><border/></borders>'
'<cellStyleXfs count="1"><xf/></cellStyleXfs>'
'<cellXfs count="1"><xf/></cellXfs></styleSheet>')
sst = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'
f'<sst xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" count="{len(shared)}" uniqueCount="{len(shared)}">'
+ "".join(f"<si><t xml:space=\"preserve\">{escape(t)}</t></si>" for t in shared)
+ '</sst>')
with zipfile.ZipFile(path, "w", zipfile.ZIP_DEFLATED) as z:
z.writestr("[Content_Types].xml", ct)
z.writestr("_rels/.rels", rels)
z.writestr("xl/workbook.xml", wb)
z.writestr("xl/_rels/workbook.xml.rels", wb_rels)
z.writestr("xl/styles.xml", styles)
z.writestr("xl/sharedStrings.xml", sst)
for i, xml in enumerate(sheet_xml):
z.writestr(f"xl/worksheets/sheet{i+1}.xml", xml)
return {"sheets": names, "shared_strings": len(shared)}
def main():
ap = argparse.ArgumentParser()
ap.add_argument("--node")
ap.add_argument("--cells-json")
ap.add_argument("--out", required=True)
a = ap.parse_args()
if a.cells_json:
sheets = json.load(open(a.cells_json))["sheets"]
elif a.node:
sheets = fetch_sheets(a.node)
else:
raise SystemExit("需要 --node 或 --cells-json")
info = build_xlsx(sheets, a.out)
rows = sum(len(s.get("cells") or []) for s in sheets)
print(json.dumps({"success": True, "out": a.out, "sheets": info["sheets"],
"sheet_count": len(sheets), "rows": rows,
"shared_strings": info["shared_strings"]}, ensure_ascii=False))
if __name__ == "__main__":
main()