MEGA INFRA
301d0fff44
Reads our Candy PDF (deterministically, no OCR or model needed) and populates the consultant's own workbook using their formulas, column layout and PAYMENT column. Nothing is ever silently overwritten: every disagreement is reported, can be settled inside the app, and regenerated. - extract Candy text PDF -> tree (x-position column detection) - template layout detect, sequence align, write, totals, overrides - validate qty x rate and children-vs-subtotal reconciliation - profiles per-consultant layout profiles, stored on a volume Shipped with a Dockerfile + docker-compose for Coolify.
76 lines
2.5 KiB
Python
76 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
BOQ PDF -> Excel + CSV
|
|
|
|
python3 run.py tender.pdf # writes out/BOQ_<name>.xlsx + .csv
|
|
python3 run.py tender.pdf --report # also prints the validation report
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import re
|
|
import sys
|
|
|
|
from boq_engine.extract import extract
|
|
from boq_engine.populate import flatten, populate_template, to_csv
|
|
from boq_engine.validate import validate
|
|
|
|
|
|
def safe(name: str) -> str:
|
|
return re.sub(r"[^A-Za-z0-9]+", "_", name).strip("_")[:60]
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("pdf")
|
|
ap.add_argument("-o", "--outdir", default="out")
|
|
ap.add_argument("--contract", default="")
|
|
ap.add_argument("--title", default="BILL OF QUANTITIES")
|
|
ap.add_argument("--vat", type=float, default=15.0)
|
|
ap.add_argument("--report", action="store_true")
|
|
ap.add_argument("--json", dest="json_out")
|
|
args = ap.parse_args()
|
|
|
|
base = safe(os.path.splitext(os.path.basename(args.pdf))[0])
|
|
os.makedirs(args.outdir, exist_ok=True)
|
|
xlsx = os.path.join(args.outdir, f"{base}.xlsx")
|
|
csvp = os.path.join(args.outdir, f"{base}.csv")
|
|
jsonp = args.json_out or os.path.join(args.outdir, f"{base}.json")
|
|
|
|
print(f"reading {args.pdf}")
|
|
tree = extract(args.pdf)
|
|
rep = validate(tree)
|
|
|
|
stats = populate_template(tree, xlsx, title=args.title,
|
|
contract=args.contract, vat_pct=args.vat)
|
|
nrows = to_csv(tree, csvp)
|
|
with open(jsonp, "w", encoding="utf-8") as fh:
|
|
json.dump({"tree": tree, "validation": rep.as_dict()}, fh,
|
|
indent=1, default=str)
|
|
|
|
print(f"\n priced lines {stats['lines']}")
|
|
print(f" groups {stats['groups']}")
|
|
print(f" 'Rate only' {stats['rate_only']}")
|
|
print(f" odd units {stats['unknown_units']} (highlighted in the workbook)")
|
|
print(f" csv rows {nrows}")
|
|
print(f" validation {len(rep.errors)} error(s), {len(rep.warnings)} warning(s)")
|
|
|
|
if rep.errors or args.report:
|
|
print("\nVALIDATION")
|
|
for i in rep.issues:
|
|
if i.severity == "info" and not args.report:
|
|
continue
|
|
mark = {"error": "ERROR", "warn": "WARN ", "info": "INFO "}[i.severity]
|
|
print(f" {mark} {i.code}")
|
|
print(f" {i.where}")
|
|
print(f" {i.detail}")
|
|
|
|
print(f"\nwrote {xlsx}\nwrote {csvp}\nwrote {jsonp}")
|
|
return 1 if rep.errors else 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|