benchflow-ai/skillsbench/academic-pdf-redaction

# ❌ WRONG - This removes ALL text from the page:
for block in page.get_text("blocks"):
    page.add_redact_annot(fitz.Rect(block[:4]))
# ❌ WRONG - Drawing rectangles over text:
page.draw_rect(fitz.Rect(0, 0, 600, 100), fill=(0,0,0))
# ✅ CORRECT - Only redact specific search matches:
for rect in page.search_for("John Smith"):
    page.add_redact_annot(rect)

import fitz
import os
def redact_with_pymupdf(input_path: str, output_path: str, patterns: list[str]):
    """Redact specific patterns from PDF using PyMuPDF."""
    doc = fitz.open(input_path)
    original_len = sum(len(p.get_text()) for p in doc)
    # Find References page - stop redacting there
    references_page = None
    for i, page in enumerate(doc):
        if "references" in page.get_text().lower():
            references_page = i
            break
    for page_num, page in enumerate(doc):
        if references_page is not None and page_num >= references_page:
            continue  # Skip References section
        for pattern in patterns:
            # ONLY redact exact search matches
            for rect in page.search_for(pattern):
                page.add_redact_annot(rect, fill=(0, 0, 0))
        page.apply_redactions()
    os.makedirs(os.path.dirname(output_path), exist_ok=True)
    doc.save(output_path)
    doc.close()
    # MUST verify after saving
    verify_redaction(input_path, output_path)

import fitz
def verify_redaction(original_path, output_path):
    """Verify redaction didn't corrupt the PDF."""
    orig = fitz.open(original_path)
    redc = fitz.open(output_path)
    orig_len = sum(len(p.get_text()) for p in orig)
    redc_len = sum(len(p.get_text()) for p in redc)
    print(f"Original: {len(orig)} pages, {orig_len} chars")
    print(f"Redacted: {len(redc)} pages, {redc_len} chars")
    print(f"Retained: {redc_len/orig_len:.1%}")
    # DEFENSIVE CHECKS - fail fast if something went wrong
    if len(redc) != len(orig):
        raise ValueError(f"Page count changed: {len(orig)} -> {len(redc)}")
    if redc_len < 1000:
        raise ValueError(f"PDF corrupted: only {redc_len} chars remain!")
    if redc_len < orig_len * 0.7:
        raise ValueError(f"Too much removed: kept only {redc_len/orig_len:.0%}")
    orig.close()
    redc.close()
    print("✓ Verification passed")