// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: 2025 ai-ad4 and the FreePDFEditor contributors
//
// Reconstruct.h — the text reconstruction pipeline (plan §4.1). Takes a set
// of GlyphRuns and produces Paragraphs, then scores them against ground truth.
//
// This is the M0 Spike B harness. The full §4.1 pipeline has six steps; this
// implementation covers steps 2–5 (run assembly, line detection, reading
// order, paragraph grouping) which are the ones the F1 gate scores. Step 1
// (glyph→Unicode) is exercised separately via the font cmap / ToUnicode path;
// step 6 (frame geometry) is a post-processing step not needed for the
// paragraph-boundary F1 metric.

#ifndef FREEPDFEDITOR_SPIKE_B_RECONSTRUCT_H
#define FREEPDFEDITOR_SPIKE_B_RECONSTRUCT_H

#include "GlyphRun.h"

#include <vector>

namespace freepdfeditor::spike::b {

struct ReconstructionResult {
    std::vector<Line> lines;
    std::vector<Paragraph> paragraphs;
};

// Run the reconstruction pipeline over `runs`. `font_size_tolerance` controls
// the baseline-clustering tolerance (default 0.25 × font size per §4.1 step 3).
ReconstructionResult reconstruct(const std::vector<GlyphRun>& runs,
                                 float font_size_tolerance = 0.25f);

// Score predicted paragraphs against ground truth by boundary F1: a predicted
// paragraph boundary is "correct" if it falls within `tolerance` (in device
// units) of a ground-truth boundary. Returns precision, recall and F1.
struct BoundaryScore {
    std::size_t true_boundaries = 0;
    std::size_t predicted_boundaries = 0;
    std::size_t matched = 0;
    double precision = 0.0;
    double recall = 0.0;
    double f1 = 0.0;
};
BoundaryScore score_boundaries(const std::vector<Paragraph>& predicted,
                                const std::vector<GroundTruthParagraph>& truth,
                                float tolerance);

} // namespace freepdfeditor::spike::b

#endif // FREEPDFEDITOR_SPIKE_B_RECONSTRUCT_H