# -*- coding: utf-8 -*-
"""Measure where the first real employment evidence starts on page one (review finding F18).

Usage: python resume_builder/helpers/page_metrics.py <resume.pdf> [more.pdf ...]
Requires pdftotext (ships with MiKTeX).

The review reported ~50-55% for four packages. This reproduces that measurement from the
compiled PDF so a change can be checked rather than asserted. The percentage is a diagnostic,
never a target: no pixel goal, no forced page-two filling.
"""
import re
import shutil
import subprocess
import sys
import tempfile
from pathlib import Path

HEADINGS = ("professional experience", "berufserfahrung", "experience")


def measure(pdf: Path) -> dict:
    executable = shutil.which("pdftotext")
    if not executable:
        raise RuntimeError("pdftotext is required on PATH (Poppler or MiKTeX)")
    with tempfile.TemporaryDirectory() as work:
        out = Path(work) / "bbox.xml"
        subprocess.run([executable, "-bbox", "-f", "1", "-l", "1", str(pdf), str(out)],
                       capture_output=True, check=True)
        xml = out.read_text(encoding="utf-8", errors="replace")
    page = re.search(r'<page width="([\d.]+)" height="([\d.]+)"', xml)
    if page is None:
        raise ValueError("No page geometry found in pdftotext output")
    height = float(page.group(2))
    words = [(float(m.group(2)), m.group(5).lower())
             for m in re.finditer(
                 r'<word xMin="([\d.]+)" yMin="([\d.]+)" xMax="([\d.]+)" yMax="([\d.]+)">([^<]*)</word>',
                 xml)]
    rows = {}
    for y, text in words:
        rows.setdefault(round(y, 1), []).append(text)
    first_y = next((y for y, row in sorted(rows.items()) if " ".join(row).strip() in HEADINGS), None)
    lines = len(rows)
    return {
        "height": height,
        "experience_y": first_y,
        "experience_pct": round(100 * first_y / height, 1) if first_y else None,
        "page1_text_lines": lines,
        "page1_words": len(words),
    }


if __name__ == "__main__":
    for argument in sys.argv[1:]:
        pdf = Path(argument)
        data = measure(pdf)
        pct = data["experience_pct"]
        print(f"{pdf.parent.name:<34} experience starts at "
              f"{pct if pct is not None else '?':>5}% of page 1 | "
              f"{data['page1_text_lines']:>3} text lines, {data['page1_words']:>4} words")