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
40 lines
1.5 KiB
Rust
40 lines
1.5 KiB
Rust
//! Debug fingerprint content streams.
|
|
//!
|
|
//! This test helps debug why content_edit fixtures have identical fingerprints.
|
|
|
|
use pdftract_core::document::parse_pdf_file;
|
|
use std::path::PathBuf;
|
|
|
|
fn main() {
|
|
let fixtures = vec![
|
|
"tests/fingerprint/fixtures/content_edit_one_glyph/v1.pdf",
|
|
"tests/fingerprint/fixtures/content_edit_one_glyph/v2.pdf",
|
|
"tests/fingerprint/fixtures/content_edit_one_paragraph/v1.pdf",
|
|
"tests/fingerprint/fixtures/content_edit_one_paragraph/v2.pdf",
|
|
];
|
|
|
|
for fixture in fixtures {
|
|
let path = PathBuf::from(fixture);
|
|
println!("\n=== {} ===", fixture);
|
|
|
|
match parse_pdf_file(&path) {
|
|
Ok((fingerprint, _catalog, pages, _resolver)) => {
|
|
println!("Fingerprint: {}", fingerprint);
|
|
println!("Pages: {}", pages.len());
|
|
|
|
for (i, page) in pages.iter().enumerate() {
|
|
println!(" Page {}:", i);
|
|
println!(" MediaBox: {:?}", page.media_box);
|
|
println!(" Contents: {} stream refs", page.contents.len());
|
|
for (j, content_ref) in page.contents.iter().enumerate() {
|
|
println!(" Content {}: {:?}", j, content_ref);
|
|
}
|
|
println!(" Resources keys: {:?}", page.resources.keys().collect::<Vec<_>>());
|
|
}
|
|
}
|
|
Err(e) => {
|
|
eprintln!("Error: {}", e);
|
|
}
|
|
}
|
|
}
|
|
}
|