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
41 lines
1.4 KiB
Rust
41 lines
1.4 KiB
Rust
use pdftract_core::parser::xref::parse_traditional_xref;
|
|
use pdftract_core::parser::stream::MemorySource;
|
|
|
|
fn main() {
|
|
let pdf_data = std::fs::read("tests/fingerprint/fixtures/byte_identical/v1.pdf").unwrap();
|
|
|
|
// Find the trailer location manually
|
|
if let Some(trailer_pos) = pdf_data.windows(7).position(|w| w == b"trailer") {
|
|
println!("Found 'trailer' at offset: {}", trailer_pos);
|
|
|
|
// Print 100 bytes after "trailer"
|
|
let end_pos = (trailer_pos + 100).min(pdf_data.len());
|
|
println!("Bytes after 'trailer':");
|
|
for i in trailer_pos..end_pos {
|
|
if pdf_data[i] >= 32 && pdf_data[i] <= 126 {
|
|
print!("{}", pdf_data[i] as char);
|
|
} else {
|
|
print!("\\x{:02x}", pdf_data[i]);
|
|
}
|
|
}
|
|
println!();
|
|
}
|
|
|
|
let source = MemorySource::new(pdf_data);
|
|
let xref = parse_traditional_xref(&source, 439);
|
|
|
|
println!("\nXref entries: {}", xref.entries.len());
|
|
println!("Diagnostics: {}", xref.diagnostics.len());
|
|
for diag in &xref.diagnostics {
|
|
println!(" - {:?}: {}", diag.code, diag.message);
|
|
}
|
|
|
|
if let Some(trailer) = &xref.trailer {
|
|
println!("\nTrailer keys:");
|
|
for (key, value) in trailer.iter() {
|
|
println!(" '{}': {:?}", key, value);
|
|
}
|
|
} else {
|
|
println!("\nNo trailer found");
|
|
}
|
|
}
|