PDF.js 源码解读: encodings

// 字体字典 /Encoding、/Differences
//   → evaluator.js            解析出 baseEncodingName 与 differences
//   → encodings.js            getEncoding(名字) → 256 项编码表     （本篇）
//   → fonts_utils.js          type1FontGlyphMapping(表 + glyphNames) → glyph id
//   → fonts.js                buildToFontChar(表 + glyphlist) → Unicode
//   → font_renderer.js        按 glyph id 取轮廓

// prettier-ignore
const StandardEncoding = [
  "", "", "", "", "", "", "", "", "", "", "", "", "", "", "",
  // ...
  "space", "exclam", "quotedbl", "numbersign", "dollar", "percent",
  "ampersand", "quoteright", "parenleft", "parenright", "asterisk", "plus",
  "comma", "hyphen", "period", "slash", "zero", "one", "two", "three",
  // ...
  "asciicircum", "underscore", "quoteleft", "a", "b", "c", "d", "e", "f",
  "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u",
  // ...
  "exclamdown", "cent", "sterling", "fraction", "yen", "florin", "section",
  "currency", "quotesingle", "quotedblleft", "guillemotleft", "guilsinglleft",
  // ...
  "Lslash", "Oslash", "OE", "ordmasculine", "", "", "", "", "", "ae",
  "", "", "", "dotlessi", "", "", "lslash", "oslash", "oe", "germandbls", "",
  "", "", ""];

  "asciitilde", "bullet", "Euro", "bullet", "quotesinglbase", "florin",
  "quotedblbase", "ellipsis", "dagger", "daggerdbl", "circumflex",
  "perthousand", "Scaron", "guilsinglleft", "OE", "bullet", "Zcaron",
  "bullet", "bullet", "quoteleft", "quoteright", "quotedblleft",
  "quotedblright", "bullet", "endash", "emdash", "tilde", "trademark",
  "scaron", "guilsinglright", "oe", "bullet", "zcaron", "Ydieresis", "space",

  "", "Adieresis", "Aring", "Ccedilla", "Eacute", "Ntilde", "Odieresis",
  "Udieresis", "aacute", "agrave", "acircumflex", "adieresis", "atilde",
  "aring", "ccedilla", "eacute", "egrave", "ecircumflex", "edieresis",
  // ...
  "Omega", "ae", "oslash", "questiondown", "exclamdown", "logicalnot",
  "radical", "florin", "approxequal", "Delta", "guillemotleft",
  "guillemotright", "ellipsis", "space", "Agrave", "Atilde", "Otilde", "OE",
  // ...
  "Icircumflex", "Idieresis", "Igrave", "Oacute", "Ocircumflex", "apple",
  "Ograve", "Uacute", "Ucircumflex", "Ugrave", "dotlessi", "circumflex",

  "space", "exclam", "universal", "numbersign", "existential", "percent",
  "ampersand", "suchthat", "parenleft", "parenright", "asteriskmath", "plus",
  "comma", "minus", "period", "slash", "zero", "one", "two", "three", "four",
  // ...
  "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",
  // ...
  "Euro", "Upsilon1", "minute", "lessequal", "fraction", "infinity", "florin",
  "club", "diamond", "heart", "spade", "arrowboth", "arrowleft", "arrowup",
  "arrowright", "arrowdown", "degree", "plusminus", "second", "greaterequal",

const getSymbolGlyphIdEncoding = getLookupTableFactory(t => {
  let glyphId = 3;
  for (const [firstCharCode, lastCharCode] of [
    [0x20, 0x7e],
    [0xa1, 0xfe],
  ]) {
    for (let charCode = firstCharCode; charCode <= lastCharCode; charCode++) {
      t[glyphId++] = SymbolSetEncoding[charCode];
    }
  }
}, /* useArray = */ true);

  "space", "a1", "a2", "a202", "a3", "a4", "a5", "a119", "a118", "a117",
  "a11", "a12", "a13", "a14", "a15", "a16", "a105", "a17", "a18", "a19",
  // ...
  "a57", "a58", "a59", "a60", "a61", "a62", "a63", "a64", "a65", "a66",
  "a67", "a68", "a69", "a70", "a71", "a72", "a73", "a74", "a203", "a75",

  "space", "exclamsmall", "Hungarumlautsmall", "", "dollaroldstyle",
  "dollarsuperior", "ampersandsmall", "Acutesmall", "parenleftsuperior",
  "parenrightsuperior", "twodotenleader", "onedotenleader", "comma",
  "hyphen", "period", "fraction", "zerooldstyle", "oneoldstyle",
  // ...
  "Asmall", "Bsmall", "Csmall", "Dsmall", "Esmall", "Fsmall", "Gsmall",
  "Hsmall", "Ismall", "Jsmall", "Ksmall", "Lsmall", "Msmall", "Nsmall",
  // ...
  "questiondownsmall", "oneeighth", "threeeighths", "fiveeighths",
  "seveneighths", "onethird", "twothirds", "", "", "zerosuperior",

  "space", "exclamsmall", "Hungarumlautsmall", "centoldstyle",
  "dollaroldstyle", "dollarsuperior", "ampersandsmall", "Acutesmall",
  "parenleftsuperior", "parenrightsuperior", "twodotenleader",
  "onedotenleader", "comma", "hyphen", "period", "fraction", "zerooldstyle",

if (dict.has('Encoding')) {
  encoding = dict.get('Encoding');
  if (encoding instanceof Dict) {
    baseEncodingName = encoding.get('BaseEncoding');
    baseEncodingName = baseEncodingName instanceof Name ? baseEncodingName.name : null;
    // Load the differences between the base and original
    if (encoding.has('Differences')) {
      const diffEncoding = encoding.get('Differences');
      let index = 0;
      for (const entry of diffEncoding) {
        const data = xref.fetchIfRef(entry);
        if (typeof data === 'number') {
          index = data;
        } else if (data instanceof Name) {
          differences[index++] = data.name;
        } else {
          throw new FormatError(`Invalid entry in 'Differences' array: ${data}`);
        }
      }
    }
  } else if (encoding instanceof Name) {
    baseEncodingName = encoding.name;
  } else {
    // ...
  }
  // According to table 114 if the encoding is a named encoding it must be
  // one of these predefined encodings.
  if (
    baseEncodingName !== 'MacRomanEncoding' &&
    baseEncodingName !== 'MacExpertEncoding' &&
    baseEncodingName !== 'WinAnsiEncoding'
  ) {
    baseEncodingName = null;
  }
}

function getEncoding(encodingName) {
  switch (encodingName) {
    case 'WinAnsiEncoding':
      return WinAnsiEncoding;
    case 'StandardEncoding':
      return StandardEncoding;
    case 'MacRomanEncoding':
      return MacRomanEncoding;
    case 'SymbolSetEncoding':
      return SymbolSetEncoding;
    case 'ZapfDingbatsEncoding':
      return ZapfDingbatsEncoding;
    case 'ExpertEncoding':
      return ExpertEncoding;
    case 'MacExpertEncoding':
      return MacExpertEncoding;
    default:
      return null;
  }
}

    if (baseEncodingName) {
      properties.defaultEncoding = getEncoding(baseEncodingName);
    } else {
      let isSymbolicFont = !!(properties.flags & FontFlags.Symbolic);
      const isNonsymbolicFont = !!(properties.flags & FontFlags.Nonsymbolic);
      // ...
      // According to "Table 114" in section "9.6.6.1 General" (under
      // "9.6.6 Character Encoding") of the PDF specification, a Nonsymbolic
      // font should use the `StandardEncoding` if no encoding is specified.
      encoding = StandardEncoding;

function buildToFontChar(encoding, glyphsUnicodeMap, differences) {
  const toFontChar = [];
  let unicode;
  for (let i = 0, ii = encoding.length; i < ii; i++) {
    unicode = getUnicodeForGlyph(encoding[i], glyphsUnicodeMap);
    if (unicode !== -1) {
      toFontChar[i] = unicode;
    }
  }
  for (const charCode in differences) {
    unicode = getUnicodeForGlyph(differences[charCode], glyphsUnicodeMap);
    if (unicode !== -1) {
      toFontChar[+charCode] = unicode;
    }
  }
  return toFontChar;
}

if (pos === 0 || pos === 1) {
  predefined = true;
  format = pos;
  const baseEncoding = pos ? ExpertEncoding : StandardEncoding;
  for (i = 0, ii = charset.length; i < ii; i++) {
    const index = baseEncoding.indexOf(charset[i]);
    if (index !== -1) {
      encoding[index] = i;
    }
  }
}