72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
|
# Extract Juzhiyun manual: TOC + master-data / order / schedule chapters
|
||
|
|
from __future__ import annotations
|
||
|
|
import glob, os, re, fitz
|
||
|
|
|
||
|
|
ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||
|
|
pdf = glob.glob(os.path.join(ROOT, "demand", "*.pdf"))[0]
|
||
|
|
out_dir = os.path.join(ROOT, "demand", "_extracted")
|
||
|
|
os.makedirs(out_dir, exist_ok=True)
|
||
|
|
|
||
|
|
doc = fitz.open(pdf)
|
||
|
|
print(f"pages={doc.page_count} file={os.path.basename(pdf)}")
|
||
|
|
|
||
|
|
toc = doc.get_toc()
|
||
|
|
toc_path = os.path.join(out_dir, "juzhiyun_toc.txt")
|
||
|
|
with open(toc_path, "w", encoding="utf-8") as f:
|
||
|
|
for lv, title, page in toc:
|
||
|
|
f.write(f"{' ' * (lv - 1)}{title}\tp{page}\n")
|
||
|
|
print(f"toc entries={len(toc)} -> {toc_path}")
|
||
|
|
|
||
|
|
# Keywords to pull relevant pages
|
||
|
|
KEYS = [
|
||
|
|
"主数据", "物料", "BOM", "工艺路线", "工艺", "工序", "工厂", "车间", "产线",
|
||
|
|
"设备", "班次", "日历", "库存", "订单", "分解", "MRP", "排产", "计划",
|
||
|
|
"负荷", "甘特", "齐套", "采购", "委外", "生产订单", "工单",
|
||
|
|
]
|
||
|
|
|
||
|
|
# Build page index from TOC titles matching keys
|
||
|
|
interesting_pages: set[int] = set()
|
||
|
|
for lv, title, page in toc:
|
||
|
|
if any(k in title for k in KEYS):
|
||
|
|
# include this page and next few for section body
|
||
|
|
for p in range(max(1, page), min(doc.page_count, page + 4) + 1):
|
||
|
|
interesting_pages.add(p)
|
||
|
|
|
||
|
|
# Also scan first 30 pages of text for section headers if TOC sparse
|
||
|
|
if len(interesting_pages) < 20:
|
||
|
|
for i in range(min(80, doc.page_count)):
|
||
|
|
text = doc[i].get_text("text")
|
||
|
|
if any(k in text for k in ("主数据维护", "工艺路线", "物料管理", "订单管理", "生产计划", "排产")):
|
||
|
|
interesting_pages.add(i + 1)
|
||
|
|
|
||
|
|
print(f"interesting pages={len(interesting_pages)}")
|
||
|
|
|
||
|
|
# Extract full text of interesting pages + nearby
|
||
|
|
chunks = []
|
||
|
|
for pno in sorted(interesting_pages):
|
||
|
|
text = doc[pno - 1].get_text("text")
|
||
|
|
# compress blank lines
|
||
|
|
text = re.sub(r"\n{3,}", "\n\n", text).strip()
|
||
|
|
if text:
|
||
|
|
chunks.append(f"\n\n===== PAGE {pno} =====\n{text}")
|
||
|
|
|
||
|
|
body_path = os.path.join(out_dir, "juzhiyun_master_schedule.txt")
|
||
|
|
with open(body_path, "w", encoding="utf-8") as f:
|
||
|
|
f.write("".join(chunks))
|
||
|
|
print(f"extracted chars={sum(len(c) for c in chunks)} -> {body_path}")
|
||
|
|
|
||
|
|
# Also dump ALL page texts that look like menus / module names (shorter summary)
|
||
|
|
summary_lines = []
|
||
|
|
for i in range(doc.page_count):
|
||
|
|
text = doc[i].get_text("text")
|
||
|
|
hits = [k for k in KEYS if k in text]
|
||
|
|
if hits:
|
||
|
|
# first non-empty lines as context
|
||
|
|
lines = [ln.strip() for ln in text.splitlines() if ln.strip()][:8]
|
||
|
|
summary_lines.append(f"p{i+1} hits={hits[:6]} | {' | '.join(lines[:4])}")
|
||
|
|
|
||
|
|
sum_path = os.path.join(out_dir, "juzhiyun_page_hits.txt")
|
||
|
|
with open(sum_path, "w", encoding="utf-8") as f:
|
||
|
|
f.write("\n".join(summary_lines))
|
||
|
|
print(f"hit pages={len(summary_lines)} -> {sum_path}")
|