formula_img2latex/tools/vergleich_bericht.py

#!/usr/bin/env python3
"""Visual before/after report of two runs on the same readings (--reuse), e.g. a rule change.

    python3 tools/vergleich_bericht.py --epub1 BAND1.epub --epub2 BAND2.epub \\
        --regeltest regeltest1-ohne:regeltest1-struktur --regeltest regeltest2-ohne:regeltest2-struktur \\
        --kalibrierung VORHER.json:NACHHER.json [--name struktur] [--titel "…"]

Each pair is VORHER:NACHHER (regeltest: names under vergleich/, calibration: report files). Writes
vergleich/<name>/index.html (not versioned): summary table, every changed decision or truth verdict,
and every match found only by the structural comparison, with original image and rendered readings.
"""

from __future__ import annotations

import argparse
import html
import json
import sys
import zipfile
from pathlib import Path

import numpy as np
from PIL import Image

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from konsens_bericht import orig_img, png_uri  # noqa: E402

from formula_img2latex.calibrate import _dvipng_jpeg, _rule_outcome  # noqa: E402
from formula_img2latex.decide import consensus_thresholds, decide_pair_tiebreak  # noqa: E402
from formula_img2latex.render import render_many  # noqa: E402
from formula_img2latex.tex import strip_delimiters  # noqa: E402

ROOT = Path(__file__).resolve().parents[1] / "vergleich"
LABEL = {"local": "Qwen", "p2t": "pix2text", "local2": "Gemma", "cloud": "GLM"}


class Page:
    """Collects cards; renders all TeX in one pdflatex batch at the end."""

    def __init__(self) -> None:
        self.parts: list[str] = []
        self.texes: list[tuple[str, bool, str]] = []   # (tex, display, preset)

    def img(self, tex: str | None, display: bool, preset: str) -> str:
        self.texes.append((strip_delimiters(tex or "") or "\\text{–}", display, preset))
        return f"@@IMG{len(self.texes) - 1}@@"

    def html(self) -> str:
        out = "".join(self.parts)
        for preset in sorted({p for _t, _d, p in self.texes}):
            idx = [k for k, (_t, _d, p) in enumerate(self.texes) if p == preset]
            for k, rr in zip(idx, render_many([self.texes[k][:2] for k in idx], preset)):
                if rr.ok:
                    g = (rr.rasterize(2.0) * 255).astype(np.uint8)
                    tag = f"<img src='{png_uri(Image.fromarray(255 - g))}'>"
                else:
                    tag = "<i>nicht setzbar</i>"
                out = out.replace(f"@@IMG{k}@@", tag)
        return out


def original(z: zipfile.ZipFile | None, name: str, truth: str, display: bool) -> str:
    try:
        if name.endswith("#synth.jpg"):
            data = _dvipng_jpeg(strip_delimiters(truth), display, 102) or b""
        else:
            data = z.read(name) if z else b""
        return f"<img src='{png_uri(orig_img(data, 2))}'>"
    except Exception:  # noqa: BLE001
        return "<i>–</i>"


def card(page: Page, cls: str, head: str, orig: str, truth: str, display: bool, preset: str,
         rows: list[tuple[str, str | None]]) -> None:
    trs = [f"<tr><th>Original</th><td>{orig}</td><td></td></tr>",
           f"<tr><th>richtig</th><td>{page.img(truth, display, preset)}</td><td><code>{html.escape(truth)}</code></td></tr>"]
    for label, tex in rows:
        trs.append(f"<tr><th>{label}</th><td>{page.img(tex, display, preset) if tex else '<i>–</i>'}</td>"
                   f"<td><code>{html.escape(tex or '–')}</code></td></tr>")
    page.parts.append(f"<section class={cls}><div class=v>{head}</div><table>{''.join(trs)}</table></section>")


def mark(ok: bool) -> str:
    return "<b class=ok>✓</b>" if ok else "<b class=no>✗</b>"


def regeltest(page: Page, summary: list[str], pair: str, z: zipfile.ZipFile | None) -> None:
    a, b = pair.split(":")
    ra, rb = (json.loads((ROOT / n / "ergebnis.json").read_text(encoding="utf-8")) for n in (a, b))
    sa, sb = ra["summary"], rb["summary"]
    st = sb.get("structural", {})
    summary.append(f"<tr><td><a href='../{b}/index.html'>{html.escape(b)}</a> "
                   f"<small>(<a href='../{a}/index.html'>vorher</a>)</small></td><td>{sa['formulas']}</td>"
                   f"<td>{sa['accepted']} / {sa['wrong']}</td><td><b>{sb['accepted']} / {sb['wrong']}</b></td>"
                   f"<td>{sa['review']} → {sb['review']}</td><td>{st.get('agree', 0)} / {st.get('truth', 0)}</td></tr>")
    old = {c["name"]: c for c in ra["cases"]}
    preset = rb.get("preset", "cm")
    tools = ["local", "p2t", "local2"]
    for c in rb["cases"]:
        o = old[c["name"]]
        changed = c["status"] != o["status"]
        struct = [i for i, j, how in c["agree"] if how == "strukturell"] or [
            k for k, h in enumerate(c.get("ok_how", [])) if h == "strukturell"]
        verdict = [p for p in range(3) if c["readings"][p] and o["readings"][p] and c["ok"][p] != o["ok"][p]]
        if not (changed or struct or verdict):
            continue
        right = c["status"] == "auto_accepted" and c["right"]
        cls = "bad" if c["status"] == "auto_accepted" and not c["right"] else "good" if right else "rev"
        head = (f"{html.escape(b)} · {'Entscheidung geändert: ' + o['status'] + ' → ' if changed else ''}"
                f"{c['status']} · {html.escape(c['reason'])}"
                + (" · Urteil gegen Wahrheit geändert: " + ", ".join(LABEL[tools[p]] for p in verdict) if verdict else ""))
        rows = [(f"{mark(c['ok'][p])} {LABEL[t]}" + (" (" + c["ok_how"][p] + ")" if c.get("ok_how") and c["ok_how"][p] else ""),
                 (c["readings"][p] or {}).get("tex")) for p, t in enumerate(tools) if c["readings"][p]]
        card(page, cls, head, original(z, c["name"], c["truth"], c["display"]), c["truth"], c["display"], preset, rows)


def kalibrierung(page: Page, summary: list[str], pair: str, z: zipfile.ZipFile | None) -> None:
    a, b = pair.split(":")
    ka, kb = (json.loads(Path(p).read_text(encoding="utf-8")) for p in (a, b))
    th = consensus_thresholds()
    for sa, sb in zip(ka["sets"], kb["sets"]):
        names = sb["engines"]
        idx = [names.index(e) for e in ("local", "p2t", "local2")]
        old = {r["name"]: r for r in sa["results"]}
        acc = {"ohne": [0, 0], "mit": [0, 0]}
        synth = sb["label"].endswith("Gehrke-Stil]")
        preset = "cm" if synth else "txfonts"
        for r in sb["results"]:
            o = old[r["name"]]
            use_o = _rule_outcome(o, idx, th, decide_pair_tiebreak, True)
            use_n = _rule_outcome(r, idx, th, decide_pair_tiebreak, True)
            for key, rr, u in (("ohne", o, use_o), ("mit", r, use_n)):
                if u is not None:
                    acc[key][0] += 1
                    acc[key][1] += not rr["ok"][u]
            struct = [(i, j) for i, j, how in r["agree_all"] if how == "strukturell"]
            struct_t = [k for k, h in enumerate(r.get("ok_how", [])) if h == "strukturell"]
            verdict_ch = [k for k in range(len(names)) if r["ok"][k] != o["ok"][k]]
            if (use_o is None) == (use_n is None) and not struct and not struct_t and not verdict_ch:
                continue
            verdict = ("übernommen" if use_n is not None else "nicht übernommen")
            if (use_o is None) != (use_n is None):
                verdict = f"Entscheidung geändert: {'übernommen' if use_o is not None else 'nicht übernommen'} → {verdict}"
            wrong = use_n is not None and not r["ok"][use_n]
            cls = "bad" if wrong else "good" if use_n is not None else "rev"
            how = "; ".join([f"{LABEL.get(names[i], names[i])} = {LABEL.get(names[j], names[j])} strukturell" for i, j in struct]
                            + [f"{LABEL.get(names[k], names[k])} = Wahrheit strukturell" for k in struct_t]
                            + ["Urteil gegen Wahrheit geändert: " + ", ".join(LABEL.get(names[k], names[k]) for k in verdict_ch)]
                            * bool(verdict_ch))
            rows = [(f"{mark(r['ok'][k])} {LABEL.get(e, e)}" + (" ← verwendet" if k == use_n else ""),
                     r["readings"][k].get("tex")) for k, e in enumerate(names)]
            card(page, cls, f"Kalibrierung {html.escape(sb['label'])} · {verdict} · {html.escape(how)}",
                 original(z, r["name"], r["truth"], r["display"]), r["truth"], r["display"], preset, rows)
        n = sb["formulas"]
        summary.append(f"<tr><td>Kalibrierung Band 1 {html.escape(sb['label'].split('[')[-1].rstrip(']'))}</td><td>{n}</td>"
                       f"<td>{acc['ohne'][0]} / {acc['ohne'][1]}</td><td><b>{acc['mit'][0]} / {acc['mit'][1]}</b></td>"
                       f"<td>–</td><td>{len(sb.get('structural_examples', []))}</td></tr>")


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--epub1", type=Path, default=None, help="Göllmann Band 1 (Kalibrierung)")
    ap.add_argument("--epub2", type=Path, default=None, help="Göllmann Band 2 (Regeltests)")
    ap.add_argument("--regeltest", action="append", default=[], help="OHNE:MIT (Namen unter vergleich/)")
    ap.add_argument("--kalibrierung", action="append", default=[], help="OHNE.json:MIT.json")
    ap.add_argument("--name", default="struktur")
    ap.add_argument("--titel", default="Vergleich vorher / nachher")
    args = ap.parse_args()
    z1 = zipfile.ZipFile(args.epub1) if args.epub1 else None
    z2 = zipfile.ZipFile(args.epub2) if args.epub2 else None
    page = Page()
    summary: list[str] = []
    for pair in args.regeltest:
        regeltest(page, summary, pair, z2)
    for pair in args.kalibrierung:
        kalibrierung(page, summary, pair, z1)
    head = (f"<h1>{html.escape(args.titel)}</h1>"
            "<p>Dieselben gespeicherten Lesarten, zweimal entschieden: vorher und nachher. "
            "Regel <code>p2t</code>, mit Pandoc und Bild-Veto. ✓/✗ = gleiche Formel wie die Wahrheit.</p>"
            "<table class=sum><tr><th>Messung</th><th>Formeln</th><th>vorher: automatisch / falsch</th>"
            "<th>nachher: automatisch / falsch</th><th>Review</th><th>nur strukturell gleich (Paare / Wahrheit)</th></tr>"
            + "".join(summary) + "</table>"
            "<p>Unten: jede geänderte Entscheidung, jedes geänderte Urteil gegen die Wahrheit und jede "
            "Übereinstimmung, die <b>nur</b> die Strukturstufe gefunden hat. Grün = übernommen und richtig, <b style='color:#a32020'>Rot = übernommen, aber falsch</b>, "
            "Gelb = Review. Bitte prüfen: Sind die als gleich gewerteten Lesarten wirklich dieselbe Formel?</p>")
    page.parts.insert(0, head)
    out = ROOT / args.name
    out.mkdir(parents=True, exist_ok=True)
    (out / "index.html").write_text(
        "<!doctype html><meta charset=utf-8><title>Vergleich</title><style>"
        "body{font:14px system-ui,sans-serif;margin:16px;background:#f6f6f3}section{background:#fff;border:1px solid #ddd;"
        "border-left:6px solid #999;border-radius:6px;padding:6px 10px;margin:10px 0}section.good{border-left-color:#1f7a3a}"
        "section.bad{border-left-color:#a32020;background:#fff5f5}section.rev{border-left-color:#c88a00}"
        ".v{font-weight:600;font-size:13px}table.sum{border-collapse:collapse;background:#fff}"
        "table.sum td,table.sum th{border:1px solid #ccc;padding:4px 10px;width:auto}"
        "th{text-align:left;font-weight:400;color:#555;width:190px;vertical-align:middle}td{padding:3px 8px;vertical-align:middle}"
        ".ok{color:#1f7a3a}.no{color:#a32020}code{font-size:12px}img{max-width:640px}</style>" + page.html(),
        encoding="utf-8")
    print(out / "index.html")
    return 0


if __name__ == "__main__":
    sys.exit(main())