fix(charset): Implemented charset according to specification (#616)

ln-north · web-flow · commit 7aa959c0d8a9 · 2023-12-04T23:42:43.000+01:00
* fix(charset): Implemented charset according to specification

* fix(coding-style): Format coding-style
diff --git a/src/encoding.js b/src/encoding.js
@@ -45,6 +45,71 @@ const cffStandardStrings = [
     'Uacutesmall', 'Ucircumflexsmall', 'Udieresissmall', 'Yacutesmall', 'Thornsmall', 'Ydieresissmall', '001.000',
     '001.001', '001.002', '001.003', 'Black', 'Bold', 'Book', 'Light', 'Medium', 'Regular', 'Roman', 'Semibold'];
 
+// Strings below index 392 are standard CFF strings and are not encoded in the font.
+
+const cffISOAdobeStrings = [
+    '.notdef', 'space', 'exclam', 'quotedbl', 'numbersign', 'dollar', 'percent', 'ampersand', 'quoteright',
+    'parenleft', 'parenright', 'asterisk', 'plus', 'comma', 'hyphen', 'period', 'slash', 'zero', 'one', 'two',
+    'three', 'four', 'five', 'six', 'seven', 'eight', 'nine', 'colon', 'semicolon', 'less', 'equal', 'greater',
+    'question', 'at', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S',
+    'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'bracketleft', 'backslash', 'bracketright', 'asciicircum', 'underscore',
+    'quoteleft', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't',
+    'u', 'v', 'w', 'x', 'y', 'z', 'braceleft', 'bar', 'braceright', 'asciitilde', 'exclamdown', 'cent', 'sterling',
+    'fraction', 'yen', 'florin', 'section', 'currency', 'quotesingle', 'quotedblleft', 'guillemotleft', 'guilsinglleft',
+    'guilsinglright', 'fi', 'fl', 'endash', 'dagger', 'daggerdbl', 'periodcentered', 'paragraph', 'bullet',
+    'quotesinglbase', 'quotedblbase', 'quotedblright', 'guillemotright', 'ellipsis', 'perthousand', 'questiondown',
+    'grave', 'acute', 'circumflex', 'tilde', 'macron', 'breve', 'dotaccent', 'dieresis', 'ring', 'cedilla',
+    'hungarumlaut', 'ogonek', 'caron', 'emdash', 'AE', 'ordfeminine', 'Lslash', 'Oslash', 'OE', 'ordmasculine', 'ae',
+    'dotlessi', 'lslash', 'oslash', 'oe', 'germandbls', 'onesuperior', 'logicalnot', 'mu', 'trademark', 'Eth',
+    'onehalf', 'plusminus', 'Thorn', 'onequarter', 'divide', 'brokenbar', 'degree', 'thorn', 'threequarters',
+    'twosuperior', 'registered', 'minus', 'eth', 'multiply', 'threesuperior', 'copyright', 'Aacute', 'Acircumflex',
+    'Adieresis', 'Agrave', 'Aring', 'Atilde', 'Ccedilla', 'Eacute', 'Ecircumflex', 'Edieresis', 'Egrave', 'Iacute',
+    'Icircumflex', 'Idieresis', 'Igrave', 'Ntilde', 'Oacute', 'Ocircumflex', 'Odieresis', 'Ograve', 'Otilde', 'Scaron',
+    'Uacute', 'Ucircumflex', 'Udieresis', 'Ugrave', 'Yacute', 'Ydieresis', 'Zcaron', 'aacute', 'acircumflex',
+    'adieresis', 'agrave', 'aring', 'atilde', 'ccedilla', 'eacute', 'ecircumflex', 'edieresis', 'egrave', 'iacute',
+    'icircumflex', 'idieresis', 'igrave', 'ntilde', 'oacute', 'ocircumflex', 'odieresis', 'ograve', 'otilde', 'scaron',
+    'uacute', 'ucircumflex', 'udieresis', 'ugrave', 'yacute', 'ydieresis', 'zcaron'];
+
+const cffIExpertStrings = [
+    '.notdef', 'space', 'exclamsmall', 'Hungarumlautsmall', 'dollaroldstyle', 'dollarsuperior', 'ampersandsmall',
+    'Acutesmall', 'parenleftsuperior', 'parenrightsuperior', 'twodotenleader', 'onedotenleader', 'comma', 'hyphen',
+    'period', 'fraction', 'zerooldstyle', 'oneoldstyle', 'twooldstyle', 'threeoldstyle', 'fouroldstyle', 'fiveoldstyle',
+    'sixoldstyle', 'sevenoldstyle', 'eightoldstyle', 'nineoldstyle', 'colon', 'semicolon', 'commasuperior',
+    'threequartersemdash', 'periodsuperior', 'questionsmall', 'asuperior', 'bsuperior', 'centsuperior', 'dsuperior',
+    'esuperior', 'isuperior', 'lsuperior', 'msuperior', 'nsuperior', 'osuperior', 'rsuperior', 'ssuperior', 'tsuperior',
+    'ff', 'fi', 'fl', 'ffi', 'ffl', 'parenleftinferior', 'parenrightinferior', 'Circumflexsmall', 'hyphensuperior',
+    'Gravesmall', 'Asmall', 'Bsmall', 'Csmall', 'Dsmall', 'Esmall', 'Fsmall', 'Gsmall', 'Hsmall', 'Ismall', 'Jsmall',
+    'Ksmall', 'Lsmall', 'Msmall', 'Nsmall', 'Osmall', 'Psmall', 'Qsmall', 'Rsmall', 'Ssmall', 'Tsmall', 'Usmall',
+    'Vsmall', 'Wsmall', 'Xsmall', 'Ysmall', 'Zsmall', 'colonmonetary', 'onefitted', 'rupiah', 'Tildesmall',
+    'exclamdownsmall', 'centoldstyle', 'Lslashsmall', 'Scaronsmall', 'Zcaronsmall', 'Dieresissmall', 'Brevesmall',
+    'Caronsmall', 'Dotaccentsmall', 'Macronsmall', 'figuredash', 'hypheninferior', 'Ogoneksmall', 'Ringsmall',
+    'Cedillasmall', 'onequarter', 'onehalf', 'threequarters', 'questiondownsmall', 'oneeighth', 'threeeighths',
+    'fiveeighths', 'seveneighths', 'onethird', 'twothirds', 'zerosuperior', 'onesuperior', 'twosuperior', 'threesuperior',
+    'foursuperior', 'fivesuperior', 'sixsuperior', 'sevensuperior', 'eightsuperior', 'ninesuperior', 'zeroinferior',
+    'oneinferior', 'twoinferior', 'threeinferior', 'fourinferior', 'fiveinferior', 'sixinferior', 'seveninferior',
+    'eightinferior', 'nineinferior', 'centinferior', 'dollarinferior', 'periodinferior', 'commainferior', 'Agravesmall',
+    'Aacutesmall', 'Acircumflexsmall', 'Atildesmall', 'Adieresissmall', 'Aringsmall', 'AEsmall', 'Ccedillasmall',
+    'Egravesmall', 'Eacutesmall', 'Ecircumflexsmall', 'Edieresissmall', 'Igravesmall', 'Iacutesmall', 'Icircumflexsmall',
+    'Idieresissmall', 'Ethsmall', 'Ntildesmall', 'Ogravesmall', 'Oacutesmall', 'Ocircumflexsmall', 'Otildesmall',
+    'Odieresissmall', 'OEsmall', 'Oslashsmall', 'Ugravesmall', 'Uacutesmall', 'Ucircumflexsmall', 'Udieresissmall',
+    'Yacutesmall', 'Thornsmall', 'Ydieresissmall'
+];
+
+const cffExpertSubsetStrings = [
+    '.notdef', 'space', 'dollaroldstyle', 'dollarsuperior', 'parenleftsuperior', 'parenrightsuperior', 'twodotenleader',
+    'onedotenleader', 'comma', 'hyphen', 'period', 'fraction', 'zerooldstyle', 'oneoldstyle', 'twooldstyle',
+    'threeoldstyle', 'fouroldstyle', 'fiveoldstyle', 'sixoldstyle', 'sevenoldstyle', 'eightoldstyle', 'nineoldstyle',
+    'colon', 'semicolon', 'commasuperior', 'threequartersemdash', 'periodsuperior', 'asuperior', 'bsuperior',
+    'centsuperior', 'dsuperior', 'esuperior', 'isuperior', 'lsuperior', 'msuperior', 'nsuperior', 'osuperior',
+    'rsuperior', 'ssuperior', 'tsuperior', 'ff', 'fi', 'fl', 'ffi', 'ffl', 'parenleftinferior', 'parenrightinferior',
+    'hyphensuperior', 'colonmonetary', 'onefitted', 'rupiah', 'centoldstyle', 'figuredash', 'hypheninferior',
+    'onequarter', 'onehalf', 'threequarters', 'oneeighth', 'threeeighths', 'fiveeighths', 'seveneighths', 'onethird',
+    'twothirds', 'zerosuperior', 'onesuperior', 'twosuperior', 'threesuperior', 'foursuperior', 'fivesuperior',
+    'sixsuperior', 'sevensuperior', 'eightsuperior', 'ninesuperior', 'zeroinferior', 'oneinferior', 'twoinferior',
+    'threeinferior', 'fourinferior', 'fiveinferior', 'sixinferior', 'seveninferior', 'eightinferior', 'nineinferior',
+    'centinferior', 'dollarinferior', 'periodinferior', 'commainferior'
+];
+
 const cffStandardEncoding = [
     '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '',
     '', '', '', '', 'space', 'exclam', 'quotedbl', 'numbersign', 'dollar', 'percent', 'ampersand', 'quoteright',
@@ -258,11 +323,7 @@ function addGlyphNamesAll(font) {
     for (let i = 0; i < font.glyphs.length; i += 1) {
         glyph = font.glyphs.get(i);
         if (font.cffEncoding) {
-            if (font.isCIDFont) {
-                glyph.name = 'gid' + i;
-            } else {
-                glyph.name = font.cffEncoding.charset[i];
-            }
+            glyph.name = font.cffEncoding.charset[i];
         } else if (font.glyphNames.names) {
             glyph.name = font.glyphNames.glyphIndexToName(i);
         }
@@ -303,6 +364,9 @@ function addGlyphNames(font, opt) {
 
 export {
     cffStandardStrings,
+    cffISOAdobeStrings,
+    cffIExpertStrings,
+    cffExpertSubsetStrings,
     cffStandardEncoding,
     cffExpertEncoding,
     standardNames,
diff --git a/src/glyphset.js b/src/glyphset.js
@@ -78,11 +78,7 @@ GlyphSet.prototype.get = function(index) {
         }
 
         if (this.font.cffEncoding) {
-            if (this.font.isCIDFont) {
-                glyph.name = 'gid' + index;
-            } else {
-                glyph.name = this.font.cffEncoding.charset[index];
-            }
+            glyph.name = this.font.cffEncoding.charset[index];
         } else if (this.font.glyphNames.names) {
             glyph.name = this.font.glyphNames.glyphIndexToName(index);
         }
diff --git a/src/tables/cff.js b/src/tables/cff.js
@@ -5,7 +5,14 @@
 
 // @TODO: refactor parsing using stateful parser?
 
-import { CffEncoding, cffStandardEncoding, cffExpertEncoding, cffStandardStrings } from '../encoding.js';
+import { 
+    CffEncoding, 
+    cffStandardEncoding, 
+    cffExpertEncoding, 
+    cffStandardStrings, 
+    cffISOAdobeStrings,
+    cffIExpertStrings,
+    cffExpertSubsetStrings } from '../encoding.js';
 import glyphset from '../glyphset.js';
 import parse from '../parse.js';
 import Path from '../path.js';
@@ -499,7 +506,7 @@ function gatherCFFTopDicts(data, start, cffIndex, strings, version) {
 // Parse the CFF charset table, which contains internal names for all the glyphs.
 // This function will return a list of glyph names.
 // See Adobe TN #5176 chapter 13, "Charsets".
-function parseCFFCharset(data, start, nGlyphs, strings) {
+function parseCFFCharset(data, start, nGlyphs, strings, isCIDFont) {
     let sid;
     let count;
     const parser = new parse.Parser(data, start);
@@ -512,14 +519,24 @@ function parseCFFCharset(data, start, nGlyphs, strings) {
     if (format === 0) {
         for (let i = 0; i < nGlyphs; i += 1) {
             sid = parser.parseSID();
-            charset.push(getCFFString(strings, sid) || sid);
+
+            if(isCIDFont) {
+                charset.push(sid);
+            } else {
+                charset.push(getCFFString(strings, sid) || sid);
+            }
+            
         }
     } else if (format === 1) {
         while (charset.length <= nGlyphs) {
             sid = parser.parseSID();
             count = parser.parseCard8();
             for (let i = 0; i <= count; i += 1) {
-                charset.push(getCFFString(strings, sid) || sid);
+                if(isCIDFont) {
+                    charset.push('cid' + ('00000' + sid).slice(-5));
+                } else {
+                    charset.push(getCFFString(strings, sid) || sid);    
+                }
                 sid += 1;
             }
         }
@@ -528,7 +545,11 @@ function parseCFFCharset(data, start, nGlyphs, strings) {
             sid = parser.parseSID();
             count = parser.parseCard16();
             for (let i = 0; i <= count; i += 1) {
-                charset.push(getCFFString(strings, sid) || sid);
+                if(isCIDFont) {
+                    charset.push('cid' + ('00000' + sid).slice(-5));
+                } else {
+                    charset.push(getCFFString(strings, sid) || sid);    
+                }
                 sid += 1;
             }
         }
@@ -541,16 +562,16 @@ function parseCFFCharset(data, start, nGlyphs, strings) {
 
 // Parse the CFF encoding data. Only one encoding can be specified per font.
 // See Adobe TN #5176 chapter 12, "Encodings".
-function parseCFFEncoding(data, start, charset) {
+function parseCFFEncoding(data, start) {
     let code;
-    const enc = {};
+    const encoding = {};
     const parser = new parse.Parser(data, start);
     const format = parser.parseCard8();
     if (format === 0) {
         const nCodes = parser.parseCard8();
         for (let i = 0; i < nCodes; i += 1) {
             code = parser.parseCard8();
-            enc[code] = i;
+            encoding[code] = i;
         }
     } else if (format === 1) {
         const nRanges = parser.parseCard8();
@@ -559,15 +580,15 @@ function parseCFFEncoding(data, start, charset) {
             const first = parser.parseCard8();
             const nLeft = parser.parseCard8();
             for (let j = first; j <= first + nLeft; j += 1) {
-                enc[j] = code;
+                encoding[j] = code;
                 code += 1;
             }
         }
     } else {
         throw new Error('Unknown encoding format ' + format);
     }
 
-    return new CffEncoding(enc, charset);
+    return encoding;
 }
 
 function parseBlend(operands) {
@@ -1265,17 +1286,31 @@ function parseCFFTable(data, start, font, opt) {
     }
 
     if (header.formatMajor < 2) {
-        const charset = parseCFFCharset(data, start + topDict.charset, font.nGlyphs, stringIndex.objects);
+        let charset = [];
+        let encoding = [];
+
+        if(topDict.charset === 0) {
+            charset = cffISOAdobeStrings;
+        } else if(topDict.charset === 1) {
+            charset = cffIExpertStrings;
+        } else if (topDict.charset === 2) {
+            charset = cffExpertSubsetStrings;
+        } else {
+            charset = parseCFFCharset(data, start + topDict.charset, font.nGlyphs, stringIndex.objects, font.isCIDFont);
+        }
+
         if (topDict.encoding === 0) {
             // Standard encoding
-            font.cffEncoding = new CffEncoding(cffStandardEncoding, charset);
+            encoding = cffStandardEncoding;
         } else if (topDict.encoding === 1) {
             // Expert encoding
-            font.cffEncoding = new CffEncoding(cffExpertEncoding, charset);
+            encoding = cffExpertEncoding;
         } else {
-            font.cffEncoding = parseCFFEncoding(data, start + topDict.encoding, charset);
+            encoding = parseCFFEncoding(data, start + topDict.encoding);
         }
         
+        font.cffEncoding = new CffEncoding(encoding, charset);
+
         // Prefer the CMAP encoding to the CFF encoding.
         font.encoding = font.encoding || font.cffEncoding;
     }
diff --git a/test/opentypeSpec.js b/test/opentypeSpec.js
@@ -66,7 +66,7 @@ describe('opentype.js', function() {
         assert.equal(font.unitsPerEm, 1000);
         assert.equal(font.glyphs.length, 257);
         const aGlyph = font.glyphs.get(2);
-        assert.equal(aGlyph.name, 'gid2');
+        assert.equal(aGlyph.name, 'cid00002');
         assert.equal(aGlyph.unicode, 1);
         assert.equal(aGlyph.path.commands.length, 24);
         assert.deepEqual(font.stringToGlyphIndexes('🌺'), [59]);
@@ -156,7 +156,7 @@ describe('opentype.js on low memory mode', function() {
         assert.equal(font.unitsPerEm, 1000);
         assert.equal(font.glyphs.length, 0);
         const aGlyph = font.glyphs.get(2);
-        assert.equal(aGlyph.name, 'gid2');
+        assert.equal(aGlyph.name, 'cid00002');
         assert.equal(aGlyph.unicode, 1);
         assert.equal(aGlyph.path.commands.length, 24);
         assert.deepEqual(font.stringToGlyphIndexes('🌺'), [59]);

Original file line number	Diff line number	Diff line change
`@@ -78,11 +78,7 @@ GlyphSet.prototype.get = function(index) {`
`78`	`78`	`}`
`79`	`79`
`80`	`80`	`if (this.font.cffEncoding) {`
`81`		`- if (this.font.isCIDFont) {`
`82`		`- glyph.name = 'gid' + index;`
`83`		`- } else {`
`84`		`- glyph.name = this.font.cffEncoding.charset[index];`
`85`		`- }`
	`81`	`+ glyph.name = this.font.cffEncoding.charset[index];`
`86`	`82`	`} else if (this.font.glyphNames.names) {`
`87`	`83`	`glyph.name = this.font.glyphNames.glyphIndexToName(index);`
`88`	`84`	`}`