mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-10 21:11:52 +00:00
76 lines
3.5 KiB
Rust
76 lines
3.5 KiB
Rust
//! A replacement through the run sources must leave the rows it does not reach as they were.
|
|
use std::sync::Arc;
|
|
|
|
use pdfcraft_cos::{Document, SaveOptions, write_incremental};
|
|
|
|
use super::*;
|
|
|
|
fn page(content: &str) -> Document {
|
|
let objs: Vec<String> = vec![
|
|
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
|
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(),
|
|
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>".into(),
|
|
format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()),
|
|
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>".into(),
|
|
];
|
|
let mut out = b"%PDF-1.7\n".to_vec();
|
|
let mut offs = Vec::new();
|
|
for (i, o) in objs.iter().enumerate() {
|
|
offs.push(out.len());
|
|
out.extend_from_slice(format!("{} 0 obj\n{o}\nendobj\n", i + 1).as_bytes());
|
|
}
|
|
let x = out.len();
|
|
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.len() + 1).as_bytes());
|
|
for o in offs {
|
|
out.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes());
|
|
}
|
|
out.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{x}\n%%EOF\n", objs.len() + 1).as_bytes());
|
|
Document::open(Arc::new(out)).unwrap()
|
|
}
|
|
|
|
fn content(doc: &Document) -> String {
|
|
let bytes = write_incremental(doc, &SaveOptions::default()).unwrap();
|
|
let doc = Document::open(Arc::new(bytes)).unwrap();
|
|
let p = pdfcraft_model::pages(&doc).swap_remove(0);
|
|
let list = match doc.resolve(p.dict.get(b"Contents").unwrap()).as_ref() {
|
|
Object::Array(a) => a.clone(),
|
|
_ => vec![p.dict.get(b"Contents").unwrap().clone()],
|
|
};
|
|
let mut out = Vec::new();
|
|
for o in &list {
|
|
if let Object::Stream(s) = &*doc.resolve(o) {
|
|
out.extend(s.decoded().unwrap_or_default());
|
|
}
|
|
}
|
|
String::from_utf8_lossy(&out).into_owned()
|
|
}
|
|
|
|
#[test]
|
|
fn replace_keeps_untouched_rows() {
|
|
let mut doc = page("BT /F1 10 Tf 12 TL 100 700 Td [(Hello) -300 (World)] TJ T* (second row here) Tj ET");
|
|
let block = text_blocks(&doc, 0).unwrap().swap_remove(0);
|
|
let start = block.editor_text.find("here").expect("the second row's word is in the paragraph");
|
|
let (text, sources) = block.replaced(std::slice::from_ref(&(start..start + 4)), "there").expect("the range is on boundaries");
|
|
let style = BlockStyle { sources, ..Default::default() };
|
|
rewrite_block(&mut doc, 0, 0, Some(&text), &style).unwrap();
|
|
let after = content(&doc);
|
|
assert!(after.contains("-300"), "the first row keeps its TJ kerning: {after}");
|
|
}
|
|
|
|
/// The rewrite keeps every space typed, so a deleted word must not leave its two neighbouring
|
|
/// spaces behind; a run of spaces the paragraph had is left as it was.
|
|
#[test]
|
|
fn a_deleted_word_leaves_one_space() {
|
|
let doc = page("BT /F1 10 Tf 100 700 Td (one two three) Tj ET");
|
|
let block = text_blocks(&doc, 0).unwrap().swap_remove(0);
|
|
assert_eq!(block.editor_text, "one two three");
|
|
let two = block.editor_text.find("two").unwrap();
|
|
let (text, _) = block.replaced(std::slice::from_ref(&(two..two + 3)), "").unwrap();
|
|
assert_eq!(text, "one three");
|
|
let one = block.editor_text.find("one").unwrap();
|
|
let (text, _) = block.replaced(std::slice::from_ref(&(one..one + 3)), "").unwrap();
|
|
assert_eq!(text, " two three");
|
|
let (text, _) = block.replaced(std::slice::from_ref(&(two..two + 3)), "2").unwrap();
|
|
assert_eq!(text, "one 2 three");
|
|
}
|