Initial Daily Campaign Agent release
This commit is contained in:
joliehill294-hue
@@ -0,0 +1,261 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Normalize CSV/TSV/XLSX ad reports into deterministic Ad-level evidence JSON."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
import datetime as dt
|
||||
import json
|
||||
import math
|
||||
import re
|
||||
import sys
|
||||
import zipfile
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
from xml.etree import ElementTree as ET
|
||||
|
||||
NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main",
|
||||
"r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships"}
|
||||
|
||||
ALIASES = {
|
||||
"date": ["date", "日期", "day", "report date"],
|
||||
"campaign": ["campaign", "campaign name", "平台 campaign name", "external_campaign_name"],
|
||||
"ad_group": ["ad group", "ad group name", "平台 ad group name", "external_ad_group_name", "adgroup"],
|
||||
"ad": ["ad", "ad name", "平台 ad name", "external_ad_name", "广告名称", "素材名称"],
|
||||
"spend": ["spend", "cost", "消耗", "花费", "广告花费"],
|
||||
"installs": ["installs", "install", "归因安装量", "安装量", "转化数"],
|
||||
"retained": ["d1 retained", "d1 retention users", "d1 留存人数", "次留人数", "次日留存人数"],
|
||||
"impressions": ["impressions", "展示量", "曝光量"],
|
||||
"clicks": ["clicks", "点击量", "归因点击量"],
|
||||
}
|
||||
|
||||
|
||||
def norm(value: object) -> str:
|
||||
return re.sub(r"[\s_\-/]+", " ", str(value or "").strip().lower())
|
||||
|
||||
|
||||
def col_index(reference: str) -> int:
|
||||
letters = re.match(r"[A-Z]+", reference or "A").group(0)
|
||||
n = 0
|
||||
for char in letters:
|
||||
n = n * 26 + ord(char) - 64
|
||||
return n - 1
|
||||
|
||||
|
||||
def xlsx_rows(path: Path, sheet_name: str | None = None):
|
||||
with zipfile.ZipFile(path) as archive:
|
||||
shared = []
|
||||
if "xl/sharedStrings.xml" in archive.namelist():
|
||||
root = ET.fromstring(archive.read("xl/sharedStrings.xml"))
|
||||
for item in root.findall("m:si", NS):
|
||||
shared.append("".join(node.text or "" for node in item.iter(f"{{{NS['m']}}}t")))
|
||||
workbook = ET.fromstring(archive.read("xl/workbook.xml"))
|
||||
rels_root = ET.fromstring(archive.read("xl/_rels/workbook.xml.rels"))
|
||||
rels = {item.attrib["Id"]: item.attrib["Target"] for item in rels_root}
|
||||
sheets = []
|
||||
for sheet in workbook.find("m:sheets", NS):
|
||||
target = rels[sheet.attrib[f"{{{NS['r']}}}id"]].lstrip("/")
|
||||
if not target.startswith("xl/"):
|
||||
target = "xl/" + target
|
||||
sheets.append((sheet.attrib["name"], target))
|
||||
if sheet_name:
|
||||
matches = [entry for entry in sheets if entry[0] == sheet_name]
|
||||
if not matches:
|
||||
raise ValueError(f"Sheet not found: {sheet_name}; available: {', '.join(x[0] for x in sheets)}")
|
||||
sheets = matches
|
||||
name, target = sheets[0]
|
||||
root = ET.fromstring(archive.read(target))
|
||||
for row in root.findall(".//m:sheetData/m:row", NS):
|
||||
values = {}
|
||||
for cell in row.findall("m:c", NS):
|
||||
idx = col_index(cell.attrib.get("r", "A1"))
|
||||
kind = cell.attrib.get("t")
|
||||
value_node = cell.find("m:v", NS)
|
||||
inline = cell.find("m:is", NS)
|
||||
raw = value_node.text if value_node is not None else ""
|
||||
if kind == "s" and raw:
|
||||
value = shared[int(raw)]
|
||||
elif kind == "inlineStr" and inline is not None:
|
||||
value = "".join(n.text or "" for n in inline.iter(f"{{{NS['m']}}}t"))
|
||||
elif kind == "b":
|
||||
value = raw == "1"
|
||||
else:
|
||||
value = raw
|
||||
values[idx] = value
|
||||
if values:
|
||||
yield name, [values.get(i, "") for i in range(max(values) + 1)]
|
||||
|
||||
|
||||
def tabular_rows(path: Path, sheet: str | None = None):
|
||||
suffix = path.suffix.lower()
|
||||
if suffix == ".xlsx":
|
||||
iterator = xlsx_rows(path, sheet)
|
||||
try:
|
||||
sheet_name, headers = next(iterator)
|
||||
except StopIteration:
|
||||
raise ValueError("Workbook contains no rows")
|
||||
for _, row in iterator:
|
||||
yield sheet_name, headers, row
|
||||
return
|
||||
delimiter = "\t" if suffix == ".tsv" else ","
|
||||
with path.open("r", encoding="utf-8-sig", newline="") as handle:
|
||||
reader = csv.reader(handle, delimiter=delimiter)
|
||||
try:
|
||||
headers = next(reader)
|
||||
except StopIteration:
|
||||
raise ValueError("File contains no rows")
|
||||
for row in reader:
|
||||
yield path.name, headers, row
|
||||
|
||||
|
||||
def resolve_columns(headers: list[str], mapping: dict[str, str] | None = None) -> dict[str, int]:
|
||||
normalized = {norm(header): i for i, header in enumerate(headers)}
|
||||
result = {}
|
||||
for field, aliases in ALIASES.items():
|
||||
requested = (mapping or {}).get(field)
|
||||
candidates = [requested] if requested else aliases
|
||||
for candidate in candidates:
|
||||
if norm(candidate) in normalized:
|
||||
result[field] = normalized[norm(candidate)]
|
||||
break
|
||||
missing = [field for field in ("date", "ad", "spend", "installs") if field not in result]
|
||||
if missing:
|
||||
raise ValueError(f"Missing required columns: {', '.join(missing)}. Headers: {headers}")
|
||||
return result
|
||||
|
||||
|
||||
def number(value: object) -> float:
|
||||
text = str(value or "").strip().replace(",", "").replace("$", "").replace("¥", "")
|
||||
if not text or text.lower() in {"nan", "none", "null", "-"}:
|
||||
return 0.0
|
||||
if text.endswith("%"):
|
||||
return float(text[:-1]) / 100
|
||||
return float(text)
|
||||
|
||||
|
||||
def date_value(value: object) -> dt.date:
|
||||
text = str(value or "").strip()
|
||||
if re.fullmatch(r"\d+(\.\d+)?", text):
|
||||
serial = int(float(text))
|
||||
if serial > 1000:
|
||||
return dt.date(1899, 12, 30) + dt.timedelta(days=serial)
|
||||
for fmt in ("%Y-%m-%d", "%Y/%m/%d", "%Y.%m.%d", "%m/%d/%Y", "%d/%m/%Y"):
|
||||
try:
|
||||
return dt.datetime.strptime(text[:10], fmt).date()
|
||||
except ValueError:
|
||||
pass
|
||||
try:
|
||||
return dt.datetime.fromisoformat(text.replace("Z", "+00:00")).date()
|
||||
except ValueError as exc:
|
||||
raise ValueError(f"Unrecognized date: {text!r}") from exc
|
||||
|
||||
|
||||
def ratio(numerator: float, denominator: float):
|
||||
return None if denominator == 0 else numerator / denominator
|
||||
|
||||
|
||||
def rounded(value):
|
||||
if value is None:
|
||||
return None
|
||||
return round(value, 6)
|
||||
|
||||
|
||||
def metrics(rows):
|
||||
spend = sum(r["spend"] for r in rows)
|
||||
installs = sum(r["installs"] for r in rows)
|
||||
retained = sum(r["retained"] for r in rows)
|
||||
return {
|
||||
"spend": rounded(spend), "installs": rounded(installs), "retained": rounded(retained),
|
||||
"cpi": rounded(ratio(spend, installs)),
|
||||
"retention_rate": rounded(ratio(retained, installs)),
|
||||
"retention_cost": rounded(ratio(spend, retained)),
|
||||
"delivery_days": len({r["date"] for r in rows if r["spend"] > 0}),
|
||||
}
|
||||
|
||||
|
||||
def in_window(rows, end: dt.date, days: int):
|
||||
start = end - dt.timedelta(days=days - 1)
|
||||
return [row for row in rows if start <= row["date"] <= end]
|
||||
|
||||
|
||||
def main(argv=None):
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("input", type=Path)
|
||||
parser.add_argument("--analysis-date", help="YYYY-MM-DD; defaults to latest source date")
|
||||
parser.add_argument("--retention-lag-days", type=int, default=1)
|
||||
parser.add_argument("--sheet")
|
||||
parser.add_argument("--mapping", type=Path, help="JSON mapping canonical fields to source headers")
|
||||
parser.add_argument("--output", type=Path, required=True)
|
||||
args = parser.parse_args(argv)
|
||||
if not args.input.exists():
|
||||
parser.error(f"Input not found: {args.input}")
|
||||
mapping = json.loads(args.mapping.read_text(encoding="utf-8")) if args.mapping else None
|
||||
records, source_headers, source_sheet = [], None, None
|
||||
for source_sheet, source_headers, row in tabular_rows(args.input, args.sheet):
|
||||
columns = resolve_columns(source_headers, mapping)
|
||||
def get(field):
|
||||
idx = columns.get(field)
|
||||
return row[idx] if idx is not None and idx < len(row) else ""
|
||||
if not any(str(v).strip() for v in row):
|
||||
continue
|
||||
ad = str(get("ad")).strip()
|
||||
if not ad:
|
||||
continue
|
||||
records.append({
|
||||
"date": date_value(get("date")), "campaign": str(get("campaign")).strip(),
|
||||
"ad_group": str(get("ad_group")).strip(), "ad": ad,
|
||||
"spend": number(get("spend")), "installs": number(get("installs")),
|
||||
"retained": number(get("retained")), "impressions": number(get("impressions")),
|
||||
"clicks": number(get("clicks")),
|
||||
})
|
||||
if not records:
|
||||
raise ValueError("No usable Ad-level records found")
|
||||
latest = max(row["date"] for row in records)
|
||||
analysis_date = dt.date.fromisoformat(args.analysis_date) if args.analysis_date else latest
|
||||
mature_date = analysis_date - dt.timedelta(days=args.retention_lag_days)
|
||||
by_ad = defaultdict(list)
|
||||
for row in records:
|
||||
by_ad[(row["campaign"], row["ad_group"], row["ad"])].append(row)
|
||||
ads = []
|
||||
for (campaign, ad_group, ad), rows in by_ad.items():
|
||||
all_dates = [r["date"] for r in rows]
|
||||
acquisition_7 = in_window(rows, analysis_date, 7)
|
||||
retention_7 = in_window(rows, mature_date, 7)
|
||||
previous_7 = in_window(rows, mature_date - dt.timedelta(days=7), 7)
|
||||
ads.append({
|
||||
"ad": ad, "ad_group_context": ad_group or None, "campaign_context": campaign or None,
|
||||
"first_date": min(all_dates).isoformat(), "last_date": max(all_dates).isoformat(),
|
||||
"age_days_at_analysis": (analysis_date - min(all_dates)).days + 1,
|
||||
"analysis_day": metrics([r for r in rows if r["date"] == analysis_date]),
|
||||
"recent_7_acquisition": metrics(acquisition_7),
|
||||
"recent_7_mature_retention": metrics(retention_7),
|
||||
"previous_7_mature_retention": metrics(previous_7),
|
||||
"recent_14_mature_retention": metrics(in_window(rows, mature_date, 14)),
|
||||
})
|
||||
ads.sort(key=lambda x: (-x["recent_7_acquisition"]["spend"], x["ad"]))
|
||||
result = {
|
||||
"contract_version": "1.0", "source": {"file": args.input.name, "sheet": source_sheet,
|
||||
"row_count": len(records), "columns": source_headers},
|
||||
"dates": {"analysis_date": analysis_date.isoformat(), "latest_source_date": latest.isoformat(),
|
||||
"retention_mature_date": mature_date.isoformat(), "retention_lag_days": args.retention_lag_days},
|
||||
"portfolio": {"analysis_day": metrics([r for r in records if r["date"] == analysis_date]),
|
||||
"recent_7_acquisition": metrics(in_window(records, analysis_date, 7)),
|
||||
"recent_7_mature_retention": metrics(in_window(records, mature_date, 7))},
|
||||
"ads": ads,
|
||||
"notes": ["Ratios are recomputed from summed numerators and denominators.",
|
||||
"Campaign and Ad Group are identity context only; no parent-level ranking is produced.",
|
||||
"This file contains evidence only. KPI verdicts and actions require the Skill decision gates."],
|
||||
}
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
args.output.write_text(json.dumps(result, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
print(f"Wrote {args.output} ({len(ads)} Ads; analysis date {analysis_date})")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
raise SystemExit(main())
|
||||
except (ValueError, zipfile.BadZipFile, json.JSONDecodeError) as exc:
|
||||
print(f"error: {exc}", file=sys.stderr)
|
||||
raise SystemExit(2)
|
||||
@@ -0,0 +1,181 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Build a restrained four-section DOCX from the Skill's brief JSON contract."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import datetime as dt
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from xml.sax.saxutils import escape
|
||||
from zipfile import ZIP_DEFLATED, ZipFile
|
||||
|
||||
W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
|
||||
FORBIDDEN = ("核心判断", "规则一", "规则二", "Campaign层级", "层级判断")
|
||||
|
||||
|
||||
def run(text, bold=False, color="1F2937", size=20):
|
||||
props = (f'<w:rFonts w:ascii="Arial" w:hAnsi="Arial" w:eastAsia="Microsoft YaHei"/>'
|
||||
f'<w:color w:val="{color}"/><w:sz w:val="{size}"/><w:szCs w:val="{size}"/>'
|
||||
+ ("<w:b/><w:bCs/>" if bold else ""))
|
||||
return f'<w:r><w:rPr>{props}</w:rPr><w:t xml:space="preserve">{escape(str(text))}</w:t></w:r>'
|
||||
|
||||
|
||||
def para(text="", bold=False, color="1F2937", size=20, align=None, before=0,
|
||||
after=90, keep_next=False, border=False):
|
||||
ppr = [f'<w:spacing w:before="{before}" w:after="{after}" w:line="276" w:lineRule="auto"/>',
|
||||
"<w:keepLines/>"]
|
||||
if align:
|
||||
ppr.append(f'<w:jc w:val="{align}"/>')
|
||||
if keep_next:
|
||||
ppr.append("<w:keepNext/>")
|
||||
if border:
|
||||
ppr.append('<w:pBdr><w:bottom w:val="single" w:sz="8" w:space="5" w:color="2E74B5"/></w:pBdr>')
|
||||
return f'<w:p><w:pPr>{"".join(ppr)}</w:pPr>{run(text, bold, color, size)}</w:p>'
|
||||
|
||||
|
||||
def rich(label, text):
|
||||
props = '<w:spacing w:before="20" w:after="110" w:line="276" w:lineRule="auto"/>'
|
||||
return f'<w:p><w:pPr>{props}</w:pPr>{run(label + "：", True, "0B2545", 20)}{run(text)}</w:p>'
|
||||
|
||||
|
||||
def heading(text, major=True):
|
||||
return para(text, True, "0B2545" if major else "2E74B5", 28 if major else 23,
|
||||
before=240 if major else 150, after=110, keep_next=True, border=major)
|
||||
|
||||
|
||||
def cell(value, width, header=False, align="left"):
|
||||
fill = '<w:shd w:val="clear" w:fill="E8EEF5"/>' if header else ""
|
||||
tcpr = (f'<w:tcW w:w="{width}" w:type="dxa"/>{fill}<w:vAlign w:val="center"/>'
|
||||
'<w:tcMar><w:top w:w="85" w:type="dxa"/><w:left w:w="100" w:type="dxa"/>'
|
||||
'<w:bottom w:w="85" w:type="dxa"/><w:right w:w="100" w:type="dxa"/></w:tcMar>')
|
||||
return f'<w:tc><w:tcPr>{tcpr}</w:tcPr>{para(value, header, "1F3A5F" if header else "1F2937", 17, align, after=0)}</w:tc>'
|
||||
|
||||
|
||||
def table(headers, rows, widths, aligns=None):
|
||||
if sum(widths) != 9360 or len(headers) != len(widths):
|
||||
raise ValueError("Every table width list must match headers and sum to 9360")
|
||||
aligns = aligns or ["left"] * len(widths)
|
||||
borders = "".join(f'<w:{edge} w:val="single" w:sz="4" w:color="CBD5E1"/>'
|
||||
for edge in ("top", "left", "bottom", "right", "insideH", "insideV"))
|
||||
props = f'<w:tblW w:w="9360" w:type="dxa"/><w:tblLayout w:type="fixed"/><w:tblBorders>{borders}</w:tblBorders>'
|
||||
grid = "".join(f'<w:gridCol w:w="{width}"/>' for width in widths)
|
||||
header = "".join(cell(value, width, True, aligns[i]) for i, (value, width) in enumerate(zip(headers, widths)))
|
||||
xml_rows = [f'<w:tr><w:trPr><w:tblHeader/></w:trPr>{header}</w:tr>']
|
||||
for row in rows:
|
||||
normalized = list(row) + [""] * (len(headers) - len(row))
|
||||
cells = "".join(cell(normalized[i], width, False, aligns[i]) for i, width in enumerate(widths))
|
||||
xml_rows.append(f'<w:tr><w:trPr><w:cantSplit/></w:trPr>{cells}</w:tr>')
|
||||
return f'<w:tbl><w:tblPr>{props}</w:tblPr><w:tblGrid>{grid}</w:tblGrid>{"".join(xml_rows)}</w:tbl>'
|
||||
|
||||
|
||||
def rows(items, fields):
|
||||
return [[str(item.get(field, "")) for field in fields] for item in items]
|
||||
|
||||
|
||||
def validate(data):
|
||||
required = ("analysis_date", "portfolio_kpis", "learning_pool", "stable_pool", "actions", "good_ads")
|
||||
missing = [key for key in required if key not in data]
|
||||
if missing:
|
||||
raise ValueError("Missing brief keys: " + ", ".join(missing))
|
||||
payload = json.dumps(data, ensure_ascii=False)
|
||||
found = [term for term in FORBIDDEN if term in payload]
|
||||
if found:
|
||||
raise ValueError("Forbidden daily-brief content: " + ", ".join(found))
|
||||
for item in data["stable_pool"]:
|
||||
tier = str(item.get("tier", ""))
|
||||
if tier and not any(tier.startswith(prefix) for prefix in ("S-优质", "A-稳定", "B-波动待优化", "C-劣质")):
|
||||
raise ValueError(f"Invalid stable tier: {tier}")
|
||||
|
||||
|
||||
def document_body(data):
|
||||
title = data.get("title") or f'{data["analysis_date"]} Campaign Triage'
|
||||
label = data.get("account_label", "广告投放日报")
|
||||
mature = data.get("retention_mature_date")
|
||||
date_line = f'投放数据日：{data["analysis_date"]}' + (f' ｜ D1次留成熟日：{mature}' if mature else "")
|
||||
body = [para(label, True, "64748B", 18, after=55), para(title, True, "0B2545", 34, after=60),
|
||||
para(date_line, color="475569", size=19, after=160, border=True)]
|
||||
body += [heading("1. 是否达标"), table(
|
||||
["指标", "实际值", "目标", "结论", "口径"],
|
||||
rows(data["portfolio_kpis"], ["metric", "actual", "target", "verdict", "basis"]),
|
||||
[1450, 1300, 1300, 1200, 4110], ["left", "center", "center", "center", "left"])]
|
||||
if data.get("kpi_note"):
|
||||
body.append(rich("口径说明", data["kpi_note"]))
|
||||
body += [heading("2. 问题分析"), heading("学习期池排名", False)]
|
||||
learning = data["learning_pool"]
|
||||
if learning:
|
||||
body.append(table(["排名", "Ad", "阶段", "成熟表现", "决定"],
|
||||
rows(learning, ["rank", "ad", "stage", "evidence", "decision"]),
|
||||
[650, 2300, 950, 3400, 2060], ["center", "left", "center", "left", "left"]))
|
||||
else:
|
||||
body.append(para("无", color="475569"))
|
||||
body.append(heading("稳定期池排名", False))
|
||||
stable = data["stable_pool"]
|
||||
if stable:
|
||||
body.append(table(["排名", "分级", "Ad", "判断", "决定"],
|
||||
rows(stable, ["rank", "tier", "ad", "evidence", "decision"]),
|
||||
[650, 1550, 2050, 3000, 2110], ["center", "center", "left", "left", "left"]))
|
||||
else:
|
||||
body.append(para("无", color="475569"))
|
||||
body.append(heading("3. 建议动作"))
|
||||
actions = data["actions"]
|
||||
if actions:
|
||||
body.append(table(["动作", "对象", "证据", "预算影响"],
|
||||
rows(actions, ["action", "ad", "evidence", "budget_impact"]),
|
||||
[1100, 2500, 4260, 1500], ["center", "left", "left", "center"]))
|
||||
else:
|
||||
body.append(para("无", color="475569"))
|
||||
for note in data.get("action_notes", []):
|
||||
body.append(rich(note.get("label", "说明"), note.get("text", "")))
|
||||
body.append(heading("4. 近7天表现好的 Ads（3–5个）"))
|
||||
good = data["good_ads"]
|
||||
if good:
|
||||
body.append(table(["排名", "Ad", "近7日数据", "为什么好", "下一步"],
|
||||
rows(good, ["rank", "ad", "data", "why_good", "next_step"]),
|
||||
[650, 1900, 2900, 2400, 1510], ["center", "left", "left", "left", "left"]))
|
||||
else:
|
||||
body.append(para("无符合标准的成熟 Ad；不降低标准凑数。", color="475569"))
|
||||
if data.get("data_note"):
|
||||
body += [heading("数据与决策说明", False), para(data["data_note"], color="475569", size=18)]
|
||||
body.append(para("以上均为人工决策建议，未执行任何平台变更。", True, "0B2545", 19, before=60, after=0, border=True))
|
||||
return "".join(body)
|
||||
|
||||
|
||||
def write_docx(data, output: Path):
|
||||
validate(data)
|
||||
body = document_body(data)
|
||||
sect = '<w:sectPr><w:pgSz w:w="12240" w:h="15840"/><w:pgMar w:top="1080" w:right="1440" w:bottom="1080" w:left="1440" w:header="720" w:footer="720"/></w:sectPr>'
|
||||
document = f'<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="{W}"><w:body>{body}{sect}</w:body></w:document>'
|
||||
styles = f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:styles xmlns:w="{W}">
|
||||
<w:docDefaults><w:rPrDefault><w:rPr><w:rFonts w:ascii="Arial" w:hAnsi="Arial" w:eastAsia="Microsoft YaHei"/><w:sz w:val="20"/><w:szCs w:val="20"/><w:color w:val="1F2937"/></w:rPr></w:rPrDefault></w:docDefaults>
|
||||
<w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/><w:qFormat/></w:style></w:styles>'''
|
||||
content_types = '''<?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="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/><Override PartName="/word/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml"/><Override PartName="/docProps/core.xml" ContentType="application/vnd.openxmlformats-package.core-properties+xml"/></Types>'''
|
||||
root_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="word/document.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties" Target="docProps/core.xml"/></Relationships>'''
|
||||
doc_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/styles" Target="styles.xml"/></Relationships>'''
|
||||
stamp = dt.datetime.now(dt.timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
core = f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?><cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><dc:title>{escape(data.get("title", "Daily Campaign Triage"))}</dc:title><dc:creator>daily-campaign-triage</dc:creator><dcterms:created xsi:type="dcterms:W3CDTF">{stamp}</dcterms:created><dcterms:modified xsi:type="dcterms:W3CDTF">{stamp}</dcterms:modified></cp:coreProperties>'''
|
||||
output.parent.mkdir(parents=True, exist_ok=True)
|
||||
with ZipFile(output, "w", ZIP_DEFLATED) as archive:
|
||||
for name, payload in (("[Content_Types].xml", content_types), ("_rels/.rels", root_rels),
|
||||
("word/document.xml", document), ("word/styles.xml", styles),
|
||||
("word/_rels/document.xml.rels", doc_rels), ("docProps/core.xml", core)):
|
||||
archive.writestr(name, payload)
|
||||
|
||||
|
||||
def main(argv=None):
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("input", type=Path, help="Brief JSON")
|
||||
parser.add_argument("--output", type=Path, required=True)
|
||||
args = parser.parse_args(argv)
|
||||
data = json.loads(args.input.read_text(encoding="utf-8"))
|
||||
write_docx(data, args.output)
|
||||
print(f"Wrote {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
main()
|
||||
except (ValueError, json.JSONDecodeError) as exc:
|
||||
print(f"error: {exc}", file=sys.stderr)
|
||||
raise SystemExit(2)
|
||||
Reference in New Issue
Block a user