[Pkg-javascript-commits] [pdf.js] 107/246: Adjust the heuristics to recognize more cases of unknown glyphs for |toUnicode| (issue 5070)

[David Prévot]

This is an automated email from the git hooks/post-receive script.

taffit pushed a commit to branch master
in repository pdf.js.

commit 8ecbb4da05272519572b96b6ebe818ae4f80ad42
Author: Jonas Jenwald <jonas.jenwald at gmail.com>
Date:   Mon Jul 28 18:41:47 2014 +0200

    Adjust the heuristics to recognize more cases of unknown glyphs for |toUnicode| (issue 5070)
---
 src/core/fonts.js       |  14 ++++++++++++++
 test/pdfs/.gitignore    |   1 +
 test/pdfs/issue5070.pdf | Bin 0 -> 34369 bytes
 test/test_manifest.json |   7 +++++++
 4 files changed, 22 insertions(+)

diff --git a/src/core/fonts.js b/src/core/fonts.js
index b4ab818..76b4eac 100644
--- a/src/core/fonts.js
+++ b/src/core/fonts.js
@@ -4300,6 +4300,7 @@ var Font = (function FontClosure() {
       if (!properties.composite /* is simple font */) {
         toUnicode = [];
         var encoding = properties.defaultEncoding.slice();
+        var baseEncodingName = properties.baseEncodingName;
         // Merge in the differences array.
         var differences = properties.differences;
         for (charcode in differences) {
@@ -4328,12 +4329,25 @@ var Font = (function FontClosure() {
                 }
                 break;
               case 'C': // Cddd glyph
+              case 'c': // cddd glyph
                 if (glyphName.length >= 3) {
                   code = +glyphName.substr(1);
                 }
                 break;
             }
             if (code) {
+              // If |baseEncodingName| is one the predefined encodings,
+              // and |code| equals |charcode|, using the glyph defined in the
+              // baseEncoding seems to yield a better |toUnicode| mapping
+              // (fixes issue 5070).
+              if (baseEncodingName && code === +charcode) {
+                var baseEncoding = Encodings[baseEncodingName];
+                if (baseEncoding && (glyphName = baseEncoding[charcode])) {
+                  toUnicode[charcode] =
+                    String.fromCharCode(GlyphsUnicode[glyphName]);
+                  continue;
+                }
+              }
               toUnicode[charcode] = String.fromCharCode(code);
             }
             continue;
diff --git a/test/pdfs/.gitignore b/test/pdfs/.gitignore
index 77da225..f468102 100644
--- a/test/pdfs/.gitignore
+++ b/test/pdfs/.gitignore
@@ -56,6 +56,7 @@
 !issue925.pdf
 !issue4668.pdf
 !issue5039.pdf
+!issue5070.pdf
 !gradientfill.pdf
 !bug903856.pdf
 !bug850854.pdf
diff --git a/test/pdfs/issue5070.pdf b/test/pdfs/issue5070.pdf
new file mode 100644
index 0000000..fe77923
Binary files /dev/null and b/test/pdfs/issue5070.pdf differ
diff --git a/test/test_manifest.json b/test/test_manifest.json
index b3af44c..15f1ea8 100644
--- a/test/test_manifest.json
+++ b/test/test_manifest.json
@@ -1067,6 +1067,13 @@
        "rounds": 1,
        "type": "eq"
     },
+    {  "id": "issue5070",
+       "file": "pdfs/issue5070.pdf",
+       "md5": "ec2ca0b4954c8390a5b3b0ffd79a8e92",
+       "link": false,
+       "rounds": 1,
+       "type": "eq"
+    },
     {  "id": "issue1257",
       "file": "pdfs/issue1257.pdf",
       "md5": "9111533826bc21ed774e8e01603a2f54",

-- 
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-javascript/pdf.js.git