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
888 B
Rust
28 lines
888 B
Rust
use pdftract_core::document::parse_pdf_file;
|
|
use pdftract_core::parser::xref::XrefResolver;
|
|
|
|
fn main() {
|
|
let args: Vec<String> = std::env::args().collect();
|
|
if args.len() < 2 {
|
|
eprintln!("Usage: {} <pdf-path>", args[0]);
|
|
std::process::exit(1);
|
|
}
|
|
|
|
let pdf_path = std::path::Path::new(&args[1]);
|
|
|
|
println!("Parsing: {:?}", pdf_path);
|
|
|
|
// Try parsing the PDF
|
|
match parse_pdf_file(pdf_path) {
|
|
Ok((fingerprint, catalog, pages, resolver)) => {
|
|
println!("Success!");
|
|
println!(" Fingerprint: {}", fingerprint);
|
|
println!(" Pages ref: {:?}", catalog.pages_ref);
|
|
println!(" Number of pages: {}", pages.len());
|
|
println!(" Is tagged: {}", catalog.mark_info.map(|m| m.is_tagged).unwrap_or(false));
|
|
}
|
|
Err(e) => {
|
|
println!("Error: {:?}", e);
|
|
}
|
|
}
|
|
}
|