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
25 lines
955 B
Rust
25 lines
955 B
Rust
//! Debug test to identify which fixture is causing hangs.
|
|
|
|
use pdftract_core::parser::object::ObjectParser;
|
|
use std::fs;
|
|
|
|
#[test]
|
|
fn debug_each_fixture() {
|
|
let fixtures = ["nested_dict", "mixed_array", "indirect_simple", "indirect_stream", "objstm_basic", "objstm_extends", "circular_self", "circular_three", "truncated_dict", "deep_nesting"];
|
|
|
|
for fixture in fixtures {
|
|
println!("Testing {}...", fixture);
|
|
let input = fs::read_to_string(format!("tests/object_parser/fixtures/{}.pdf.in", fixture))
|
|
.unwrap_or_else(|e| panic!("Failed to read {}: {}", fixture, e));
|
|
|
|
let wrapped = if input.trim().contains(" obj ") {
|
|
input.clone()
|
|
} else {
|
|
format!("1 0 obj {}\nendobj", input.trim())
|
|
};
|
|
|
|
let mut parser = ObjectParser::new(wrapped.as_bytes());
|
|
let result = parser.parse_indirect_object();
|
|
println!(" {}: {:?}", fixture, result.is_some());
|
|
}
|
|
}
|