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
34 lines
1.2 KiB
Rust
34 lines
1.2 KiB
Rust
use pdftract_core::sdk;
|
|
use pdftract_core::options::ExtractionOptions;
|
|
|
|
fn main() {
|
|
let path = std::path::Path::new("tests/sdk-conformance/fixtures/scientific_paper/01.pdf");
|
|
let options = ExtractionOptions::default();
|
|
|
|
match sdk::extract(path, &options) {
|
|
Ok(result) => {
|
|
println!("Extracted {} pages", result.pages.len());
|
|
if let Some(first_page) = result.pages.first() {
|
|
println!("First page index: {:?}", first_page.index);
|
|
println!("First page width: {:?}", first_page.width);
|
|
println!("First page height: {:?}", first_page.height);
|
|
println!("First page rotation: {:?}", first_page.rotation);
|
|
println!("First page spans: {}", first_page.spans.len());
|
|
println!("First page blocks: {}", first_page.blocks.len());
|
|
}
|
|
}
|
|
Err(e) => {
|
|
eprintln!("Extract failed: {}", e);
|
|
}
|
|
}
|
|
|
|
// Test metadata
|
|
match sdk::get_metadata(path) {
|
|
Ok(metadata) => {
|
|
println!("Metadata page_count: {}", metadata.page_count);
|
|
}
|
|
Err(e) => {
|
|
eprintln!("Get metadata failed: {}", e);
|
|
}
|
|
}
|
|
}
|