From d58dac0fd384a803d41b92928706446bdbaae53c Mon Sep 17 00:00:00 2001
From: notmasteryet <async.processingjs@yahoo.com>
Date: Mon, 22 Aug 2011 22:50:17 -0500
Subject: [PATCH 1/2] Encoding for standard fonts; symbols encoding
---
fonts.js | 3 --
pdf.js | 109 ++++++++++++++++++++++++++++++++++++++++---------------
2 files changed, 79 insertions(+), 33 deletions(-)
diff --git a/fonts.js b/fonts.js
index 3d47ef4a2..9049255e7 100755
--- a/fonts.js
+++ b/fonts.js
@@ -404,9 +404,6 @@ var Font = (function Font() {
(fontName.indexOf('Italic') != -1);
this.loadedName = fontName.split('-')[0];
this.loading = false;
- this.charsToUnicode = function(s) {
- return s;
- };
return;
}
diff --git a/pdf.js b/pdf.js
index 469eec578..53d3b9853 100644
--- a/pdf.js
+++ b/pdf.js
@@ -3851,6 +3851,44 @@ var Encodings = {
'ucircumflex', 'udieresis', 'yacute', 'thorn', 'ydieresis'
]);
},
+ get symbolsEncoding() {
+ return shadow(this, 'symbolsEncoding',
+ [,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+ 'space', 'exclam', 'universal', 'numbersign', 'existential', 'percent',
+ 'ampersand', 'suchthat', 'parenleft', 'parenright', 'asteriskmath',
+ 'plus', 'comma', 'minus', 'period', 'slash', 'zero', 'one', 'two',
+ 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine', 'colon',
+ 'semicolon', 'less', 'equal', 'greater', 'question', 'congruent',
+ 'Alpha', 'Beta', 'Chi', 'Delta', 'Epsilon', 'Phi', 'Gamma', 'Eta',
+ 'Iota', 'theta1', 'Kappa', 'Lambda', 'Mu', 'Nu', 'Omicron', 'Pi',
+ 'Theta', 'Rho', 'Sigma', 'Tau', 'Upsilon', 'sigma1', 'Omega', 'Xi',
+ 'Psi', 'Zeta', 'bracketleft', 'therefore', 'bracketright',
+ 'perpendicular', 'underscore', 'radicalex', 'alpha', 'beta', 'chi',
+ 'delta', 'epsilon', 'phi', 'gamma', 'eta', 'iota', 'phi1', 'kappa',
+ 'lambda', 'mu', 'nu', 'omicron', 'pi', 'theta', 'rho', 'sigma', 'tau',
+ 'upsilon', 'omega1', 'omega', 'xi', 'psi', 'zeta', 'braceleft', 'bar',
+ 'braceright', 'similar',,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, 'Euro',
+ 'Upsilon1', 'minute', 'lessequal', 'fraction', 'infinity', 'florin',
+ 'club', 'diamond', 'heart', 'spade', 'arrowboth', 'arrowleft', 'arrowup',
+ 'arrowright', 'arrowdown', 'degree', 'plusminus', 'second',
+ 'greaterequal', 'multiply', 'proportional', 'partialdiff', 'bullet',
+ 'divide', 'notequal', 'equivalence', 'approxequal', 'ellipsis',
+ 'arrowvertex', 'arrowhorizex', 'carriagereturn', 'aleph', 'Ifraktur',
+ 'Rfraktur', 'weierstrass', 'circlemultiply', 'circleplus', 'emptyset',
+ 'intersection', 'union', 'propersuperset', 'reflexsuperset', 'notsubset',
+ 'propersubset', 'reflexsubset', 'element', 'notelement', 'angle',
+ 'gradient', 'registerserif', 'copyrightserif', 'trademarkserif',
+ 'product', 'radical', 'dotmath', 'logicalnot', 'logicaland', 'logicalor',
+ 'arrowdblboth', 'arrowdblleft', 'arrowdblup', 'arrowdblright',
+ 'arrowdbldown', 'lozenge', 'angleleft', 'registersans', 'copyrightsans',
+ 'trademarksans', 'summation', 'parenlefttp', 'parenleftex',
+ 'parenleftbt', 'bracketlefttp', 'bracketleftex', 'bracketleftbt',
+ 'bracelefttp', 'braceleftmid', 'braceleftbt', 'braceex', ,'angleright',
+ 'integral', 'integraltp', 'integralex', 'integralbt', 'parenrighttp',
+ 'parenrightex', 'parenrightbt', 'bracketrighttp', 'bracketrightex',
+ 'bracketrightbt', 'bracerighttp', 'bracerightmid', 'bracerightbt'
+ ]);
+ },
get zapfDingbatsEncoding() {
return shadow(this, 'zapfDingbatsEncoding',
[,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
@@ -4118,24 +4156,6 @@ var PartialEvaluator = (function() {
fd = fontDict.get('FontDescriptor');
}
- if (!fd) {
- var baseFontName = fontDict.get('BaseFont');
- if (!IsName(baseFontName))
- return null;
- // Using base font name as a font name.
- return {
- name: baseFontName.name.replace(/[\+,\-]/g, '_'),
- fontDict: fontDict,
- properties: {}
- };
- }
-
- var descriptor = xref.fetch(fd);
-
- var fontName = xref.fetchIfRef(descriptor.get('FontName'));
- assertWellFormed(IsName(fontName), 'invalid font name');
- fontName = fontName.name.replace(/[\+,\-]/g, '_');
-
var encodingMap = {};
var charset = [];
if (compositeFont) {
@@ -4200,14 +4220,6 @@ var PartialEvaluator = (function() {
GlyphsUnicode[data.name];
}
}
-
- // Get the font charset if any
- var charset = descriptor.get('CharSet');
- if (charset) {
- assertWellFormed(IsString(charset), 'invalid charset');
- charset = charset.split('/');
- charset.shift();
- }
} else if (IsName(encoding)) {
var encoding = Encodings[encoding.name];
if (!encoding)
@@ -4217,11 +4229,10 @@ var PartialEvaluator = (function() {
for (var j = 0; j < encoding.length; j++)
encodingMap[index++] = GlyphsUnicode[encoding[j]];
+ // firstChar and width are required
+ // (except for 14 standard fonts)
var firstChar = xref.fetchIfRef(fontDict.get('FirstChar'));
- var widths = xref.fetchIfRef(fontDict.get('Widths'));
- assertWellFormed(IsArray(widths) && IsInt(firstChar),
- 'invalid font Widths or FirstChar');
-
+ var widths = xref.fetchIfRef(fontDict.get('Widths')) || [];
for (var j = 0; j < widths.length; j++) {
if (widths[j])
charset.push(encoding[j + firstChar]);
@@ -4296,6 +4307,36 @@ var PartialEvaluator = (function() {
}
}
+ if (!fd) {
+ var baseFontName = fontDict.get('BaseFont');
+ if (!IsName(baseFontName))
+ return null;
+ // Using base font name as a font name.
+ baseFontName = baseFontName.name.replace(/[\+,\-]/g, '_');
+ if (baseFontName == 'Symbol') {
+ // special case for symbols
+ var encoding = Encodings.symbolsEncoding;
+ for (var i = 0, n = encoding.length, j; i < n; i++) {
+ if (!(j = encoding[i]))
+ continue;
+ encodingMap[i] = GlyphsUnicode[j] || 0;
+ }
+ }
+ return {
+ name: baseFontName,
+ fontDict: fontDict,
+ properties: {
+ encoding: encodingMap
+ }
+ };
+ }
+
+ var descriptor = xref.fetch(fd);
+
+ var fontName = xref.fetchIfRef(descriptor.get('FontName'));
+ assertWellFormed(IsName(fontName), 'invalid font name');
+ fontName = fontName.name.replace(/[\+,\-]/g, '_');
+
var fontFile = descriptor.get('FontFile', 'FontFile2', 'FontFile3');
if (fontFile) {
fontFile = xref.fetchIfRef(fontFile);
@@ -4307,6 +4348,14 @@ var PartialEvaluator = (function() {
}
}
+ if (descriptor.has('CharSet')) {
+ // Get the font charset if any (meaningful only in Type 1)
+ charset = descriptor.get('CharSet');
+ assertWellFormed(IsString(charset), 'invalid charset');
+ charset = charset.split('/');
+ charset.shift();
+ }
+
var widths = fontDict.get('Widths');
if (widths) {
var glyphWidths = {};
From b90c6945b81db9de81f0a55f25b0bd75d01f770b Mon Sep 17 00:00:00 2001
From: notmasteryet <async.processingjs@yahoo.com>
Date: Tue, 23 Aug 2011 17:06:45 -0500
Subject: [PATCH 2/2] Sanitizing base font name before comparison with 'Symbol'
---
pdf.js | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/pdf.js b/pdf.js
index 53d3b9853..47363401b 100644
--- a/pdf.js
+++ b/pdf.js
@@ -4313,7 +4313,7 @@ var PartialEvaluator = (function() {
return null;
// Using base font name as a font name.
baseFontName = baseFontName.name.replace(/[\+,\-]/g, '_');
- if (baseFontName == 'Symbol') {
+ if (/^Symbol(_?(Bold|Italic))*$/.test(baseFontName)) {
// special case for symbols
var encoding = Encodings.symbolsEncoding;
for (var i = 0, n = encoding.length, j; i < n; i++) {