Merge pull request #3641 from pat26-dotcom/fix/3623-pdf-import-word-gap

Fix #3623: a word gap between two sizes reads as a space in PDF import

crates/pdf/src/import_text.rs

@@ -1,6 +1,6 @@
 //! Text as editable point type: glyphs drawn one after another on the same baseline make one
 //! point text object of their Unicode text, a run per font, size and paint (a gap wider than a
-//! fifth of the size reads as a space). Fonts are named from the file's base font name (its
+//! fifth of the smaller size beside it reads as a space). Fonts are named from the file's base font name (its
 //! subset prefix dropped, the family matched against the fonts available); a font that isn't
 //! available keeps its name, and the text shows in the fallback font until it is.
 //!
@@ -124,7 +124,8 @@ struct Gap {
     at: usize,
     /// From the end of the glyph before to the start of the next (points).
     width: f64,
-    /// The larger of the two glyphs' sizes (points).
+    /// The smaller of the two glyphs' sizes (points): a word gap beside a much larger glyph is
+    /// narrow for the large size (#3623).
     em: f64,
     /// Along the line, not turned along a curve.
     on_line: bool,
@@ -156,6 +157,8 @@ pub(crate) struct TextLine {
     visible: Point,
     /// The last glyph's baseline direction.
     last_dir: Vec2,
+    /// The last glyph's size (points).
+    last_size: f64,
     /// Each glyph's baseline origin, then where the last one ends.
     baseline: Vec<Point>,
     runs: Vec<(Look, String)>,
@@ -207,6 +210,7 @@ impl TextLine {
             last: at.origin,
             visible: at.origin,
             last_dir: at.dir,
+            last_size: at.size,
             baseline: vec![],
             runs: vec![],
             upright: None,
@@ -297,7 +301,7 @@ impl TextLine {
                 return false;
             }
             if !run.ends_with(' ') && !text.starts_with(' ') {
-                self.gaps.push(Gap { at: bytes, width: gap, em: size, on_line });
+                self.gaps.push(Gap { at: bytes, width: gap, em: self.last_size.min(at.size), on_line });
             }
             // A space the file draws between two glyphs spans the gaps on both sides of it.
             let drawn = self.drawn_space.take();
@@ -322,6 +326,7 @@ impl TextLine {
         }
         self.last = at.origin;
         self.last_dir = at.dir;
+        self.last_size = at.size;
         self.baseline.push(at.origin);
         self.advances.push(advance);
         true

crates/pdf/src/tests_live_text.rs

@@ -164,6 +164,27 @@ fn evenly_wide_gaps_stay_spaces() {
     }
 }
 
+/// A word set beside a much larger one, apart by a gap and no space glyph (as a browser prints a
+/// margin between two sizes), reads as two words: the gap is measured against the smaller size
+/// (#3623). Set close, the two sizes stay one word.
+#[test]
+fn a_gap_between_two_sizes_is_measured_against_the_smaller() {
+    let font = vectorcraft_text::FontDb::global().find_postscript("SourceSans3-Regular").unwrap();
+    let advance = |c: char, size: f32| font.advance(font.glyph_for(c)) as f32 / font.units_per_em() as f32 * size;
+    // 3.4 pt: 0.17 em of the 20 pt "4", 0.43 em of the 8 pt "hours".
+    for (gap, want) in [(3.4_f32, "4 hours"), (0.4, "4hours")] {
+        let lines = [(20.0, 60.0, 20.0, "4"), (20.0 + advance('4', 20.0) + gap, 60.0, 8.0, "hours")];
+        let d = import_with_report(&text_pdf(&lines, false), &ImportOptions::default()).unwrap().document;
+        let t = texts(&d);
+        assert_eq!(t.len(), 1, "gap {gap} pt: {t:?}");
+        assert_eq!(t[0].plain_text(), want, "gap {gap} pt");
+    }
+    // The small size first.
+    let lines = [(20.0, 60.0, 8.0, "ca"), (20.0 + advance('c', 8.0) + advance('a', 8.0) + 3.4, 60.0, 20.0, "4")];
+    let t = texts(&import_with_report(&text_pdf(&lines, false), &ImportOptions::default()).unwrap().document);
+    assert_eq!(t.iter().map(TextObject::plain_text).collect::<Vec<_>>(), ["ca 4"]);
+}
+
 /// Embedded font data is untrusted: anything that isn't a CID-keyed CFF is no table, never a panic.
 #[test]
 fn cid_tables_ignore_fonts_that_are_not_cid_keyed_cff() {