fix: use dynamic count for beginbfrange declaration (#1660)

* fix: use dynamic count for beginbfrange declaration

Fixes garbled text copying in Chrome/Edge for PDFs with >256 unique characters

* Add changelog line

Addressed an issue with garbled text copying in Chrome/Edge for PDFs containing more than 256 unique characters.

* test: add tests for beginbfrange count declaration

Add test cases to verify that the beginbfrange count declaration
in ToUnicode CMap matches the actual number of bfrange entries.

- Test for fonts with >256 characters (multiple ranges)
- Test for fonts with <=256 characters (single range)

These tests ensure the fix for the beginbfrange count bug is
correct and prevent regression.

Related to #1659

* Revert "test: add tests for beginbfrange count declaration"

This reverts commit dda6f4a.

* Rewrite tests for beginbfrange count declaraton. Fix code style issue.

* fix(tests): remove unused variables in font.spec.js

Replace for loops with unused match variables with spread operator
to directly get array length, fixing ESLint no-unused-vars errors.

- Replace loop counting with [...rangeMatches].length
- Fixes ESLint errors at lines 152 and 197 in tests/unit/font.spec.js
- All tests pass successfully

---------

Co-authored-by: zhang_xiaoning <[email protected]>

Author: markbruce

CHANGELOG.md

@@ -2,6 +2,8 @@
 
 ### Unreleased
 
+- Fix garbled text copying in Chrome/Edge for PDFs with >256 unique characters (#1659)
+
 ### [v0.17.2] - 2025-08-30
 
 - Fix rendering lists that spans across pages

lib/font/embedded.js

@@ -274,7 +274,7 @@ begincmap
 1 begincodespacerange
 <0000><ffff>
 endcodespacerange
-1 beginbfrange
+${ranges.length} beginbfrange
 ${ranges.join('\n')}
 endbfrange
 endcmap

tests/unit/font.spec.js

@@ -98,6 +98,108 @@ describe('EmbeddedFont', () => {
 
       expect(glyphs).toBe(398 + 1);
     });
+
+    test('beginbfrange count should match actual number of ranges', () => {
+      const doc = new PDFDocument({ compress: false });
+      const font = PDFFontFactory.open(
+        doc,
+        'tests/fonts/Roboto-Regular.ttf',
+        undefined,
+        'F1099',
+      );
+
+      // Generate more than 256 unique characters to trigger multiple bfrange entries
+      // Each chunk is 256 characters, so we need >256 to get multiple ranges
+      const chars = [];
+
+      // Add ASCII characters (0-127)
+      for (let i = 32; i < 127; i++) {
+        chars.push(String.fromCharCode(i));
+      }
+
+      // Add extended Latin characters (128-255)
+      for (let i = 160; i < 256; i++) {
+        chars.push(String.fromCharCode(i));
+      }
+
+      // Add additional Unicode characters to exceed 256
+      const additionalChars =
+        'ÁÀÂÄÅÃÆÇÐÉÈÊËÍÌÎÏÑÓÒÔÖÕØŒÞÚÙÛÜÝŸáàâäãåæçðéèêëíìîïıñóòôöõøœßþúùûüýÿĀĂĄĆČĎĐĒĖĘĚĞĢĪĮİĶŁĹĻĽŃŅŇŌŐŔŖŘŠŚŞȘŢȚŤŪŮŰŲŽŹŻāăąćčďđēėęěğģīįķłĺļľńņňōőŕŗřšśşșţțťūůűųžźż';
+
+      const allChars = chars.join('') + additionalChars;
+      font.encode(allChars);
+
+      const docData = logData(doc);
+      font.toUnicodeCmap();
+      const text = docData.map((d) => d.toString('utf8')).join('');
+
+      // Extract the count declaration from "N beginbfrange"
+      const beginbfrangeMatch = text.match(/(\d+)\s+beginbfrange/);
+      expect(beginbfrangeMatch).not.toBeNull();
+      const declaredCount = parseInt(beginbfrangeMatch[1], 10);
+
+      // Count actual bfrange entries
+      let actualRangeCount = 0;
+      const bfrangeBlockMatch = text.match(
+        /beginbfrange\n((?:.|\n)*?)\nendbfrange/,
+      );
+      if (bfrangeBlockMatch) {
+        const bfrangeContent = bfrangeBlockMatch[1];
+        // Match each bfrange line: <start> <end> [entries]
+        const rangeMatches = bfrangeContent.matchAll(
+          /^<([0-9a-f]+)>\s+<([0-9a-f]+)>\s+\[/gm,
+        );
+        actualRangeCount = [...rangeMatches].length;
+      }
+
+      // The declared count must match the actual number of ranges
+      expect(declaredCount).toBe(actualRangeCount);
+      expect(actualRangeCount).toBeGreaterThan(1); // Should have multiple ranges when >256 chars
+    });
+
+    test('beginbfrange count should be 1 for fonts with <=256 characters', () => {
+      const doc = new PDFDocument({ compress: false });
+      const font = PDFFontFactory.open(
+        doc,
+        'tests/fonts/Roboto-Regular.ttf',
+        undefined,
+        'F1099',
+      );
+
+      // Generate exactly 256 characters
+      const chars = [];
+      for (let i = 0; i < 256; i++) {
+        chars.push(String.fromCharCode(i + 32)); // Start from space (32) to avoid control chars
+      }
+      font.encode(chars.join(''));
+
+      const docData = logData(doc);
+      font.toUnicodeCmap();
+      const text = docData.map((d) => d.toString('utf8')).join('');
+
+      // Extract the count declaration
+      const beginbfrangeMatch = text.match(/(\d+)\s+beginbfrange/);
+      expect(beginbfrangeMatch).not.toBeNull();
+      const declaredCount = parseInt(beginbfrangeMatch[1], 10);
+
+      // Count actual bfrange entries
+      let actualRangeCount = 0;
+      const bfrangeBlockMatch = text.match(
+        /beginbfrange\n((?:.|\n)*?)\nendbfrange/,
+      );
+      if (bfrangeBlockMatch) {
+        const bfrangeContent = bfrangeBlockMatch[1];
+        const rangeMatches = bfrangeContent.matchAll(
+          /^<([0-9a-f]+)>\s+<([0-9a-f]+)>\s+\[/gm,
+        );
+        actualRangeCount = [...rangeMatches].length;
+      }
+
+      // For <=256 characters, should have exactly 1 range
+      expect(declaredCount).toBe(1);
+      expect(actualRangeCount).toBe(1);
+      expect(declaredCount).toBe(actualRangeCount);
+    });
   });
 });