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
59 lines
2.1 KiB
Rust
59 lines
2.1 KiB
Rust
//! Quick test to verify SDK extraction works with fixtures
|
|
|
|
use pdftract_core::sdk;
|
|
use pdftract_core::options::ExtractionOptions;
|
|
|
|
fn main() -> anyhow::Result<()> {
|
|
let fixture_path = std::path::Path::new("tests/sdk-conformance/fixtures/scientific_paper/01.pdf");
|
|
|
|
println!("Testing extraction with: {:?}", fixture_path);
|
|
|
|
// Check if file exists
|
|
if !fixture_path.exists() {
|
|
println!("ERROR: Fixture file does not exist at {:?}", fixture_path);
|
|
anyhow::bail!("Fixture not found");
|
|
}
|
|
|
|
println!("File exists, size: {} bytes", std::fs::metadata(fixture_path)?.len());
|
|
|
|
// Try to get metadata first (lighter operation)
|
|
println!("\nTrying get_metadata...");
|
|
match sdk::get_metadata(fixture_path) {
|
|
Ok(metadata) => {
|
|
println!("SUCCESS: get_metadata returned:");
|
|
println!(" page_count: {}", metadata.page_count);
|
|
println!(" is_encrypted: {}", metadata.is_encrypted);
|
|
println!(" is_tagged: {}", metadata.is_tagged);
|
|
}
|
|
Err(e) => {
|
|
println!("ERROR: get_metadata failed: {}", e);
|
|
}
|
|
}
|
|
|
|
// Try full extraction
|
|
println!("\nTrying extract...");
|
|
let options = ExtractionOptions::default();
|
|
match sdk::extract(fixture_path, &options) {
|
|
Ok(result) => {
|
|
println!("SUCCESS: extract returned:");
|
|
println!(" fingerprint: {}", result.fingerprint);
|
|
println!(" pages: {}", result.pages.len());
|
|
if !result.pages.is_empty() {
|
|
let page = &result.pages[0];
|
|
println!(" First page:");
|
|
println!(" index: {}", page.index);
|
|
println!(" width: {:?}", page.width);
|
|
println!(" height: {:?}", page.height);
|
|
println!(" rotation: {:?}", page.rotation);
|
|
println!(" spans: {}", page.spans.len());
|
|
println!(" blocks: {}", page.blocks.len());
|
|
}
|
|
}
|
|
Err(e) => {
|
|
println!("ERROR: extract failed: {}", e);
|
|
anyhow::bail!("Extract failed");
|
|
}
|
|
}
|
|
|
|
Ok(())
|
|
}
|