d0f52751ce
The indent trigger was using .abs() which fired on both increased indent (non-indented → indented) AND decreased indent (indented → non-indented). This caused drop-cap style paragraphs (indented first line, flush-left continuation) to incorrectly split into two blocks. Per plan Phase 4.4 heuristic #2, indent change should only trigger when the current line is MORE indented (to the right, larger x0) than the block average - i.e., a new paragraph starting after non-indented text. It should NOT trigger for decreased indent (first line indented, rest flush-left). Fix: Remove .abs() and only check if line_x0 - block_avg_x0 > threshold. Tests: - test_indented_first_line_new_block: PASS (non-indented → indented splits) - test_indented_first_line_of_paragraph_not_split: PASS (drop cap stays together) - All 179 line module tests: PASS
28 lines
1 KiB
Rust
28 lines
1 KiB
Rust
use std::path::Path;
|
|
use pdftract_core::document::parse_pdf_file;
|
|
|
|
fn main() {
|
|
let v1_path = Path::new("tests/fingerprint/fixtures/content_edit_one_glyph/v1.pdf");
|
|
let v2_path = Path::new("tests/fingerprint/fixtures/content_edit_one_glyph/v2.pdf");
|
|
|
|
let (v1_fp, v1_cat, v1_pages, _) = parse_pdf_file(v1_path).unwrap();
|
|
let (v2_fp, v2_cat, v2_pages, _) = parse_pdf_file(v2_path).unwrap();
|
|
|
|
println!("=== v1 ===");
|
|
println!("Fingerprint: {}", v1_fp);
|
|
println!("Pages: {}", v1_pages.len());
|
|
for (i, page) in v1_pages.iter().enumerate() {
|
|
println!(" Page {}: {} content streams, MediaBox {:?}", i, page.contents.len(), page.media_box);
|
|
}
|
|
|
|
println!();
|
|
println!("=== v2 ===");
|
|
println!("Fingerprint: {}", v2_fp);
|
|
println!("Pages: {}", v2_pages.len());
|
|
for (i, page) in v2_pages.iter().enumerate() {
|
|
println!(" Page {}: {} content streams, MediaBox {:?}", i, page.contents.len(), page.media_box);
|
|
}
|
|
|
|
println!();
|
|
println!("Fingerprints match: {}", v1_fp == v2_fp);
|
|
}
|