PDFBOX-5384: use workaround from PDF.js

git-svn-id: https://svn.apache.org/repos/asf/pdfbox/trunk@1922164 13f79535-47bb-0310-9956-ffa450edef68
apache · Nov 27, 2024 · dbcf6d2 · dbcf6d2
1 parent daba47a
commit dbcf6d2
Showing 1 changed file with 7 additions and 1 deletion.
diff --git a/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/font/PDFont.java b/pdfbox/src/main/java/org/apache/pdfbox/pdmodel/font/PDFont.java
@@ -144,7 +144,13 @@ private CMap loadUnicodeCmap()
             cmap = readCMap(toUnicode);
             if (cmap != null && !cmap.hasUnicodeMappings())
             {
-                LOG.warn("Invalid ToUnicode CMap in font {}", getName());
+                String name = getName();
+                LOG.warn("Invalid ToUnicode CMap in font {}", name);
+                if (name != null && (name.startsWith("Tahoma") || name.startsWith("Verdana")))
+                {
+                    // PDFBOX-5384: workaround inspired by PDF.js 15719 and 11242
+                    return null;
+                }
                 String cmapName = cmap.getName() != null ? cmap.getName() : "";
                 String ordering = cmap.getOrdering() != null ? cmap.getOrdering() : "";
                 COSName encoding = dict.getCOSName(COSName.ENCODING);