Merge pull request #20334 from calixteman/issue20319

Only apply word spacing when there is a 0x20 in the text chunk

src/core/evaluator.js

@@ -2927,7 +2927,7 @@ class PartialEvaluator {
 
       for (let i = 0, ii = glyphs.length; i < ii; i++) {
         const glyph = glyphs[i];
-        const { category } = glyph;
+        const { category, originalCharCode } = glyph;
 
         if (category.isInvisibleFormatMark) {
           continue;
@@ -2941,6 +2941,10 @@ class PartialEvaluator {
         }
         let scaledDim = glyphWidth * scale;
 
+        if (originalCharCode === 0x20) {
+          charSpacing += textState.wordSpacing;
+        }
+
         if (!keepWhiteSpace && category.isWhitespace) {
           // Don't push a " " in the textContentItem
           // (except when it's between two non-spaces chars),
@@ -2948,13 +2952,13 @@ class PartialEvaluator {
           // compareWithLastPosition.
           // This way we can merge real spaces and spaces due to cursor moves.
           if (!font.vertical) {
-            charSpacing += scaledDim + textState.wordSpacing;
+            charSpacing += scaledDim;
             textState.translateTextMatrix(
               charSpacing * textState.textHScale,
               0
             );
           } else {
-            charSpacing += -scaledDim + textState.wordSpacing;
+            charSpacing += -scaledDim;
             textState.translateTextMatrix(0, -charSpacing);
           }
           saveLastChar(" ");

test/pdfs/.gitignore

@@ -746,3 +746,5 @@
 !issue20232.pdf
 !bug1989304.pdf
 !comments.pdf
+!issue20319_1.pdf
+!issue20319_2.pdf

test/pdfs/issue20319_2.pdf

@@ -0,0 +1,80 @@
+%PDF-1.7
+1 0 obj
+<< /Type /Catalog
+   /Pages 2 0 R
+>>
+endobj
+
+2 0 obj
+<< /Type /Pages
+   /Kids [3 0 R]
+   /Count 1
+>>
+endobj
+
+3 0 obj
+<< /Type /Page
+   /Parent 2 0 R
+   /MediaBox [0 0 200 200]
+   /Resources <<
+       /Font << /F1 4 0 R >>
+   >>
+   /Contents 5 0 R
+>>
+endobj
+
+4 0 obj
+<< /Type /Font
+   /Subtype /Type3
+   /Name /F1
+   /FontBBox [0 0 500 500]
+   /FontMatrix [0.001 0 0 0.001 0 0]
+   /Encoding << /Differences [32 /A 33 /A] >>
+   /CharProcs << /A 6 0 R >>
+   /FirstChar 32
+   /LastChar 33
+   /Widths [500 500]
+   /Resources << >>
+>>
+endobj
+
+5 0 obj
+<< /Length 45 >>
+stream
+BT
+/F1 20 Tf
+50 Tw
+100 100 Td
+<212021> Tj 
+ET
+endstream
+endobj
+
+6 0 obj
+<< /Length 77 >>
+stream
+500 0 d0
+50 50 50 400 re
+400 50 50 400 re
+50 400 400 50 re
+50 200 400 50 re
+f
+endstream
+endobj
+
+xref
+0 7
+0000000000 65535 f 
+0000000009 00000 n 
+0000000062 00000 n 
+0000000126 00000 n 
+0000000275 00000 n 
+0000000554 00000 n 
+0000000650 00000 n 
+trailer
+<< /Size 7
+   /Root 1 0 R
+>>
+startxref
+778
+%%EOF

test/unit/api_spec.js

@@ -4027,6 +4027,37 @@ Caron Broadcasting, Inc., an Ohio corporation (“Lessee”).`)
       expect(items[1].fontName).not.toEqual(items[0].fontName);
     });
 
+    it("gets text content with word spacing (issue 20319)", async function () {
+      const loadingTask = getDocument(
+        buildGetDocumentParams("issue20319_1.pdf")
+      );
+      const pdfDoc = await loadingTask.promise;
+      const pdfPage = await pdfDoc.getPage(1);
+      const { items } = await pdfPage.getTextContent({
+        disableNormalization: true,
+      });
+      const text = mergeText(items);
+
+      expect(text).toEqual("A A");
+
+      await loadingTask.destroy();
+    });
+
+    it("gets text content with word spacing and a fake space (issue 20319)", async function () {
+      const loadingTask = getDocument(
+        buildGetDocumentParams("issue20319_2.pdf")
+      );
+      const pdfDoc = await loadingTask.promise;
+      const pdfPage = await pdfDoc.getPage(1);
+      const { items } = await pdfPage.getTextContent({
+        disableNormalization: true,
+      });
+      const text = mergeText(items);
+      expect(text).toEqual("AA A");
+
+      await loadingTask.destroy();
+    });
+
     it("gets empty structure tree", async function () {
       const tree = await page.getStructTree();