Sakurai/pdf.js
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Slightly re-factor PartialEvaluator._simpleFontToUnicode

Browse Source 
Given the sheer number of heuristics added to this method over the years, moving the *valid* unicode found case to the top should improve readability of the code.
This commit is contained in:
Jonas Jenwald 2022-10-05 12:52:22 +02:00
parent c6cc7c6e6a
commit fa47d4b9b1
1 changed files with 67 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/core/evaluator.js
View File

@ -3526,11 +3526,16 @@ class PartialEvaluator {
for (const charcode in encoding) {
// a) Map the character code to a character name.
let glyphName = encoding[charcode];
// b) Look up the character name in the Adobe Glyph List (see the
// Bibliography) to obtain the corresponding Unicode value.
if (glyphName === "") {
continue;
} else if (glyphsUnicodeMap[glyphName] === undefined) {
}
// b) Look up the character name in the Adobe Glyph List (see the
// Bibliography) to obtain the corresponding Unicode value.
let unicode = glyphsUnicodeMap[glyphName];
if (unicode !== undefined) {
toUnicode[charcode] = String.fromCharCode(unicode);
continue;
}
// (undocumented) c) Few heuristics to recognize unknown glyphs
// NOTE: Adobe Reader does not do this step, but OSX Preview does
let code = 0;
@ -3562,10 +3567,7 @@ class PartialEvaluator {
// containing glyph, i.e. base 16, codes instead.
// In that case we need to re-parse the *entire* encoding to
// prevent broken text-selection (fixes issue9655_reduced.pdf).
if (
Number.isNaN(code) &&
Number.isInteger(parseInt(codeStr, 16))
) {
if (Number.isNaN(code) && Number.isInteger(parseInt(codeStr, 16))) {
return this._simpleFontToUnicode(
properties,
/* forceGlyphs */ true
@ -3573,11 +3575,12 @@ class PartialEvaluator {
}
}
break;
default: // 'uniXXXX'/'uXXXX{XX}' glyphs
const unicode = getUnicodeForGlyph(glyphName, glyphsUnicodeMap);
case "u": // 'uniXXXX'/'uXXXX{XX}' glyphs
unicode = getUnicodeForGlyph(glyphName, glyphsUnicodeMap);
if (unicode !== -1) {
code = unicode;
}
break;
}
if (code > 0 && code <= 0x10ffff && Number.isInteger(code)) {
// If `baseEncodingName` is one the predefined encodings, and `code`
@ -3594,9 +3597,6 @@ class PartialEvaluator {
}
toUnicode[charcode] = String.fromCodePoint(code);
}
continue;
}
toUnicode[charcode] = String.fromCharCode(glyphsUnicodeMap[glyphName]);
}
return toUnicode;
}