// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: 2025 ai-ad4 and the FreePDFEditor contributors
//
// Spike B main: run the reconstruction pipeline over the synthetic corpus and
// report paragraph-boundary F1. Exit 0 if F1 meets the §14 M0 target (≥ 0.85),
// 1 otherwise. The release gate is ≥ 0.93 (§8.2) but that is for the real
// labelled corpus; the M0 spike uses the synthetic corpus and the lower bar.

#include "Corpus.h"
#include "Reconstruct.h"
#include "../common/SpikeRunner.h"

#include <cstdio>
#include <vector>

int main(int argc, char** argv)
{
    const std::size_t n_docs = (argc >= 2) ? std::size_t(std::atoi(argv[1])) : 200;
    const double target = (argc >= 3) ? std::stod(argv[2]) : 0.85;

    auto corpus = freepdfeditor::spike::b::generate_corpus(n_docs);
    if (corpus.empty()) {
        freepdfeditor::spike::SpikeResult r{};
        r.spike = "B";
        r.name = "glyph→Unicode + line/paragraph reconstruction";
        r.metric_name = "paragraph_boundary_f1";
        r.target = target;
        r.gate_met = false;
        r.notes = "empty corpus";
        return freepdfeditor::spike::emit_json_report(r);
    }

    std::size_t total_true = 0, total_pred = 0, total_matched = 0;
    std::size_t docs_perfect = 0;

    for (auto& doc : corpus) {
        auto result = freepdfeditor::spike::b::reconstruct(doc.runs);
        // Boundary tolerance: 0.4 × the leading (14.4pt) ≈ 5.76pt. Generous
        // enough that a paragraph gap is matched even if the pipeline's
        // paragraph bottom is off by a line; tight enough that distinct
        // paragraphs aren't conflated.
        auto score = freepdfeditor::spike::b::score_boundaries(
            result.paragraphs, doc.truth, 5.76f);
        total_true += score.true_boundaries;
        total_pred += score.predicted_boundaries;
        total_matched += score.matched;
        if (score.true_boundaries == score.predicted_boundaries &&
            score.matched == score.true_boundaries) {
            ++docs_perfect;
        }
    }

    double precision = total_pred ? double(total_matched) / double(total_pred) : 0.0;
    double recall = total_true ? double(total_matched) / double(total_true) : 0.0;
    double f1 = (precision + recall) > 0
        ? 2.0 * precision * recall / (precision + recall) : 0.0;

    freepdfeditor::spike::SpikeResult r{};
    r.spike = "B";
    r.name = "glyph→Unicode + line/paragraph reconstruction";
    r.total = corpus.size();
    r.passed = docs_perfect;
    r.failed = corpus.size() - docs_perfect;
    r.errored = 0;
    r.metric_name = "paragraph_boundary_f1";
    r.metric_value = f1;
    r.target = target;
    r.gate_met = f1 >= target;
    r.notes = "synthetic single-column LTR corpus; "
              "precision=" + std::to_string(precision) +
              " recall=" + std::to_string(recall) +
              " perfect=" + std::to_string(docs_perfect) + "/" +
              std::to_string(corpus.size()) +
              "; real labelled corpus (§8.1) needed for the 0.93 release gate";
    return freepdfeditor::spike::emit_json_report(r);
}