Fix PDF font embedding issues in thesis figures for submission to Papyrus @ UdeM. Requires pdffonts (poppler) and gs (ghostscript).

check_fonts.py

"""Check and fix PDF font embedding issues in thesis figures."""

import argparse
import shutil
import subprocess
from pathlib import Path


def check_pdf_fonts(pdf_path: str) -> list[str]:
    """
    Check a PDF for font issues. Returns list of problem descriptions.
    """
    try:
        result = subprocess.run(
            ["pdffonts", pdf_path],
            capture_output=True, text=True, timeout=30
        )
        if result.returncode != 0:
            return [f"error: {result.stderr.strip()}"]
    except Exception as e:
        return [f"error: {e}"]

    problems = []
    for line in result.stdout.split("\n")[2:]:  # Skip header lines
        if not line.strip():
            continue
        if "Type 3" in line:
            problems.append("Type 3 (bitmap)")
        if line.split()[0] == "[none]":
            problems.append("unnamed font")
        # Check for 'no' in emb column (columns: name type encoding emb sub uni)
        parts = line.split()
        if len(parts) >= 6 and parts[-4] == "no":
            problems.append("not embedded")

    return problems


def fix_pdf(input_path: Path, output_path: Path) -> bool:
    """
    Fix a PDF by converting fonts to outlines with Ghostscript.
    """
    output_path.parent.mkdir(parents=True, exist_ok=True)
    try:
        result = subprocess.run([
            "gs", "-dNOPAUSE", "-dBATCH", "-sDEVICE=pdfwrite",
            "-dNoOutputFonts",
            f"-sOutputFile={output_path}",
            str(input_path)
        ], capture_output=True, timeout=60)
        return result.returncode == 0
    except Exception:
        return False


def main():
    parser = argparse.ArgumentParser(description="Check/fix PDF font embedding issues")
    parser.add_argument("--fix", action="store_true", help="Create fixed copy")
    parser.add_argument("--source", default="PhD_Thesis", help="Source directory")
    parser.add_argument("--dest", default=None, help="Destination (default: <source>_fixed)")
    args = parser.parse_args()

    source = Path(args.source)
    dest = Path(args.dest or f"{args.source}_fixed")

    if not source.exists():
        print(f"Error: '{source}' not found")
        return

    # Find all PDFs in figures folders
    pdfs = list(source.glob("**/figures/**/*.pdf")) + list(source.glob("**/figures/*.pdf"))
    pdfs = sorted(set(pdfs))

    print(f"Checking {len(pdfs)} PDFs in {source}/\n")

    # Check each PDF
    problematic = {}
    for pdf in pdfs:
        issues = check_pdf_fonts(str(pdf))
        if issues:
            problematic[pdf] = issues
            print(f"❌ {pdf.relative_to(source)}")
            for issue in set(issues):
                print(f"   └── {issue}")
        else:
            print(f"✅ {pdf.relative_to(source)}")

    # Summary
    print(f"\n{'='*50}")
    print(f"Clean: {len(pdfs) - len(problematic)} | Problematic: {len(problematic)}")

    if not args.fix or not problematic:
        if problematic and not args.fix:
            print(f"\nRun with --fix to create fixed copy at {dest}/")
        return

    # Create fixed copy
    print(f"\nCreating fixed copy at {dest}/")
    if dest.exists():
        shutil.rmtree(dest)
    shutil.copytree(source, dest)

    # Fix problematic PDFs
    fixed, failed = 0, 0
    for pdf in problematic:
        relative = pdf.relative_to(source)
        dest_pdf = dest / relative
        temp_pdf = dest_pdf.with_suffix(".tmp.pdf")

        if fix_pdf(pdf, temp_pdf):
            temp_pdf.replace(dest_pdf)
            print(f"✅ Fixed: {relative}")
            fixed += 1
        else:
            if temp_pdf.exists():
                temp_pdf.unlink()
            print(f"❌ Failed: {relative}")
            failed += 1

    print(f"\nFixed: {fixed} | Failed: {failed}")
    print(f"Output: {dest}/")


if __name__ == "__main__":
    main()