// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: 2025 ai-ad4 and the FreePDFEditor contributors
//
// Corpus.h — synthetic labelled corpus generator for Spike B.
//
// The real labelled corpus (~2,000 pages with ground-truth paragraph/column
// segmentation, §8.1) is large and has licensing constraints; for the M0 spike
// we generate a controlled synthetic corpus: glyph runs whose text and
// paragraph boundaries are known by construction, laid out as a single LTR
// column with realistic leading, wrapping, and paragraph breaks. This lets us
// score the reconstruction pipeline's F1 on a corpus where the ground truth
// is exact, and where we can dial in difficulty (mixed leading, short last
// lines, list markers) to find where the 80% solution breaks.
//
// The synthetic generator is deliberately simple — it does not exercise the
// hard cases (multi-column, RTL, vertical CJK, rotated text). Those need the
// script corpus (§8.1) and are out of scope for the M0 spike's "does the
// pipeline shape work and score" question.

#ifndef FREEPDFEDITOR_SPIKE_B_CORPUS_H
#define FREEPDFEDITOR_SPIKE_B_CORPUS_H

#include "GlyphRun.h"

#include <vector>

namespace freepdfeditor::spike::b {

// One generated document: the glyph runs the pipeline sees, plus the
// ground-truth paragraph boundaries the scorer compares against.
struct SyntheticDoc {
    std::vector<GlyphRun> runs;
    std::vector<GroundTruthParagraph> truth;
    std::string name;
};

// Generate `n` synthetic documents with varying difficulty. Each document has
// 3–8 paragraphs of 1–5 lines, with:
//   - consistent leading within a paragraph (±10%)
//   - a paragraph gap (extra leading) between paragraphs
//   - last lines shorter than the column (paragraph break signal)
//   - occasional list items (markers that should start a new paragraph)
std::vector<SyntheticDoc> generate_corpus(std::size_t n);

} // namespace freepdfeditor::spike::b

#endif // FREEPDFEDITOR_SPIKE_B_CORPUS_H