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
35 lines
1.3 KiB
Rust
35 lines
1.3 KiB
Rust
// Debug test to understand why content_edit fixtures produce same fingerprint
|
|
use pdftract_core::document::compute_pdf_fingerprint;
|
|
use std::path::PathBuf;
|
|
|
|
fn main() {
|
|
let fixtures_dir = PathBuf::from("tests/fingerprint/fixtures");
|
|
|
|
// Test content_edit_one_glyph
|
|
let dir = fixtures_dir.join("content_edit_one_glyph");
|
|
let v1 = dir.join("v1.pdf");
|
|
let v2 = dir.join("v2.pdf");
|
|
|
|
println!("=== Testing content_edit_one_glyph ===");
|
|
|
|
let fp1 = compute_pdf_fingerprint(&v1).expect("Failed to compute fingerprint for v1");
|
|
let fp2 = compute_pdf_fingerprint(&v2).expect("Failed to compute fingerprint for v2");
|
|
|
|
println!("v1 fingerprint: {}", fp1);
|
|
println!("v2 fingerprint: {}", fp2);
|
|
println!("Are they equal? {}", fp1 == fp2);
|
|
|
|
// Test content_edit_one_paragraph
|
|
let dir2 = fixtures_dir.join("content_edit_one_paragraph");
|
|
let v1p = dir2.join("v1.pdf");
|
|
let v2p = dir2.join("v2.pdf");
|
|
|
|
println!("\n=== Testing content_edit_one_paragraph ===");
|
|
|
|
let fp1p = compute_pdf_fingerprint(&v1p).expect("Failed to compute fingerprint for v1p");
|
|
let fp2p = compute_pdf_fingerprint(&v2p).expect("Failed to compute fingerprint for v2p");
|
|
|
|
println!("v1 fingerprint: {}", fp1p);
|
|
println!("v2 fingerprint: {}", fp2p);
|
|
println!("Are they equal? {}", fp1p == fp2p);
|
|
}
|