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
57 lines
2.4 KiB
Rust
57 lines
2.4 KiB
Rust
//! Debug test for page tree resolution
|
|
|
|
use pdftract_core::document::parse_pdf_file;
|
|
use pdftract_core::parser::xref::XrefResolver;
|
|
use pdftract_core::parser::object::PdfObject;
|
|
use std::path::Path;
|
|
|
|
fn main() {
|
|
let v1_path = Path::new("tests/fingerprint/fixtures/content_edit_one_glyph/v1.pdf");
|
|
|
|
let (fp, cat, pages, resolver) = parse_pdf_file(v1_path).unwrap();
|
|
|
|
println!("=== Debug Info ===");
|
|
println!("Fingerprint: {}", fp);
|
|
println!("Catalog pages_ref: {:?}", cat.pages_ref);
|
|
println!("Number of pages: {}", pages.len());
|
|
|
|
// Resolve the pages reference directly
|
|
match resolver.resolve(cat.pages_ref) {
|
|
Ok(pages_obj) => {
|
|
println!("Resolved pages_obj: {:?}", pages_obj);
|
|
if let Some(dict) = pages_obj.as_dict() {
|
|
println!("Pages dict keys: {:?}", dict.keys().collect::<Vec<_>>());
|
|
if let Some(count) = dict.get("Count") {
|
|
println!("Count: {:?}", count);
|
|
}
|
|
if let Some(kids) = dict.get("Kids") {
|
|
println!("Kids type: {:?}", std::mem::discriminant(kids));
|
|
if let Some(arr) = kids.as_array() {
|
|
println!("Kids array length: {}", arr.len());
|
|
for (i, kid) in arr.iter().enumerate() {
|
|
println!(" Kid {}: {:?}", i, kid);
|
|
if let PdfObject::Ref(ref_) = kid {
|
|
match resolver.resolve(*ref_) {
|
|
Ok(kid_obj) => {
|
|
println!(" Resolved to: {:?}", kid_obj);
|
|
if let Some(kid_dict) = kid_obj.as_dict() {
|
|
if let Some(type_name) = kid_dict.get("Type") {
|
|
println!(" Type: {:?}", type_name);
|
|
}
|
|
}
|
|
}
|
|
Err(e) => {
|
|
println!(" Failed to resolve: {:?}", e);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
Err(e) => {
|
|
println!("Failed to resolve pages_ref: {:?}", e);
|
|
}
|
|
}
|
|
}
|