7f72171572
Initialize git, add Apache-2.0 LICENSE, .gitattributes (LF line endings), AGENTS.md (entry points, stack, discovery order, baseline checks), RUNBOOK.md (dev boot, prod deploy with overlay, ingestion, failures, rollback, scaling notes), .env.prod.example with rotated credential placeholders, and dev-only warnings on .env.example. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
37 lines
985 B
Python
37 lines
985 B
Python
"""PDF inspection helpers - decide whether OCR is required."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pikepdf
|
|
from pdfminer.high_level import extract_text
|
|
|
|
|
|
def page_count(path: Path | str) -> int:
|
|
with pikepdf.open(str(path)) as pdf:
|
|
return len(pdf.pages)
|
|
|
|
|
|
def has_searchable_text(path: Path | str, sample_pages: int = 3, min_chars: int = 80) -> bool:
|
|
"""Cheap check: extract text from first ``sample_pages`` and require ``min_chars``.
|
|
|
|
Returns False on any extraction error - safer to OCR than to skip.
|
|
"""
|
|
try:
|
|
text = extract_text(str(path), maxpages=sample_pages) or ""
|
|
except Exception:
|
|
return False
|
|
return len(text.strip()) >= min_chars
|
|
|
|
|
|
def is_pdf(path: Path | str) -> bool:
|
|
p = Path(path)
|
|
if not p.is_file() or p.suffix.lower() != ".pdf":
|
|
return False
|
|
try:
|
|
with open(p, "rb") as f:
|
|
return f.read(5) == b"%PDF-"
|
|
except OSError:
|
|
return False
|