Merge PR #2754: Keep leading spaces and tabs when wrapping plain text into a PDF

crates/create/src/tests.rs

@@ -124,6 +124,18 @@ fn text_is_wrapped_and_paginated() {
     assert!(content(p.last().unwrap()).contains("(After a form feed) Tj"), "a form feed starts a page");
 }
 
+#[test]
+fn text_keeps_leading_spaces_and_tabs() {
+    let doc = reopen(&from_text("t", "    indented\n\ttabbed\nplain", LETTER, 11.0).unwrap());
+    let p = pages(&doc);
+    let c = doc.resolve(p[0].get(b"Contents").unwrap());
+    let Object::Stream(s) = &*c else { panic!() };
+    let content = String::from_utf8_lossy(&s.decoded().unwrap()).into_owned();
+    assert!(content.contains("(    indented) Tj"), "{content}");
+    assert!(content.contains("(    tabbed) Tj"), "{content}");
+    assert!(content.contains("(plain) Tj"), "{content}");
+}
+
 /// Text Helvetica can't draw is refused with its line and character, never set as `?`; text
 /// PdfCraft generates writes such characters as [U+XXXX] and says so.
 #[test]

crates/fonts/src/lib.rs

@@ -80,13 +80,19 @@ pub fn wrap_with(text: &str, size: f64, width: f64, measure: impl Fn(&str, f64)
     let mut lines = Vec::new();
     for para in text.split(['\n', '\r']) {
         let mut line = String::new();
+        // No word is on the line yet; an empty word (a leading space) still starts it.
+        let mut fresh = true;
         for word in para.split(' ') {
-            let candidate = if line.is_empty() { word.to_string() } else { format!("{line} {word}") };
-            if measure(&candidate, size) <= width || line.is_empty() && measure(word, size) <= width {
+            let candidate = if fresh { word.to_string() } else { format!("{line} {word}") };
+            if measure(&candidate, size) <= width || fresh && measure(word, size) <= width {
                 line = candidate;
+                fresh = false;
                 continue;
             }
-            if !line.is_empty() {
+            // Indentation alone is not a line: drop it before an over-long word.
+            if line.trim().is_empty() {
+                line.clear();
+            } else {
                 lines.push(std::mem::take(&mut line));
             }
             for ch in word.chars() {
@@ -95,6 +101,7 @@ pub fn wrap_with(text: &str, size: f64, width: f64, measure: impl Fn(&str, f64)
                 }
                 line.push(ch);
             }
+            fresh = line.is_empty();
         }
         lines.push(line);
     }
@@ -256,6 +263,20 @@ pub fn literal(bytes: &[u8]) -> Vec<u8> {
 mod tests {
     use super::*;
 
+    #[test]
+    fn wrap_keeps_leading_spaces() {
+        assert_eq!(wrap("    indented", 11.0, 500.0), ["    indented"]);
+        assert_eq!(wrap("  a b\n c", 11.0, 500.0), ["  a b", " c"]);
+        assert_eq!(wrap("", 11.0, 500.0), [""]);
+        // A single leading space before a word that must be broken leaves no blank first line.
+        let broken = wrap(" abcdefghijklmnopqrstuvwxyz", 11.0, 40.0);
+        assert!(broken.len() > 1 && broken.iter().all(|l| !l.is_empty()), "{broken:?}");
+        // So does indentation of two or more spaces: no whitespace-only line, same as one space.
+        let broken = wrap("  abcdefghijklmnopqrstuvwxyz", 11.0, 40.0);
+        assert!(broken.len() > 1 && broken.iter().all(|l| !l.trim().is_empty()), "{broken:?}");
+        assert_eq!(broken, wrap(" abcdefghijklmnopqrstuvwxyz", 11.0, 40.0));
+    }
+
     #[test]
     fn win_ansi_encodability_matches_the_encoder() {
         for c in ['a', 'é', 'ÿ', '€', '—', '™', '\t', '?'] {