13 lines
830 B
Python
13 lines
830 B
Python
import json
|
|
from pathlib import Path
|
|
from pypdf import PdfReader
|
|
from central.app.datasets.ba_st_mva import parse_page
|
|
|
|
source = Path("sources/raw/bootstrap_v1/decreto_2012_13780_ricms_anexo_1_vigente_2026.pdf")
|
|
records, rejected = [], []
|
|
for page, value in enumerate(PdfReader(source).pages, start=1):
|
|
found, failed = parse_page(value.extract_text() or "", page)
|
|
records.extend(found); rejected.extend(failed)
|
|
Path("docs/ba_st_mva_inspection.json").write_text(json.dumps({"records": records, "rejected": rejected}, ensure_ascii=False, indent=2), encoding="utf-8")
|
|
print(json.dumps({"pages": page, "records": len(records), "rejected": len(rejected), "cest": sum(bool(x["cest"]) for x in records), "ncm": sum(bool(x["ncm_sh"]) for x in records), "mva": sum(bool(x["mva_original"] or x["mva_adjusted"]) for x in records)}))
|