PDF.js 源码解读: cmap

// 字体字典 /Encoding、/ToUnicode
//   → CMapFactory.create
//   → createBuiltInCMap(name)          内建名称 → .bcmap → BinaryCMapReader
//   → parseCMap(lexer)                 嵌入流 → Lexer → 文本操作符
//   → CMap.codespaceRanges / _map
//   → evaluator: 复合字体取 CID，ToUnicode 取 Unicode
//   → font / text layer

class CMap {
  constructor(builtInCMap = false) {
    // Codespace ranges are stored as follows:
    // [[1BytePairs], [2BytePairs], [3BytePairs], [4BytePairs]]
    // where nBytePairs are ranges e.g. [low1, high1, low2, high2, ...]
    this.codespaceRanges = [[], [], [], []];
    this.numCodespaceRanges = 0;
    // Map entries have one of two forms.
    // - cid chars are 16-bit unsigned integers, stored as integers.
    // - bf chars are variable-length byte sequences, stored as strings, with
    //   one byte per character.
    this._map = [];
    this.name = "";
    this.vertical = false;
    this.useCMap = null;
    this.builtInCMap = builtInCMap;
  }

  addCodespaceRange(n, low, high) {
    this.codespaceRanges[n - 1].push(low, high);
    this.numCodespaceRanges++;
  }

  readCharCode(str, offset, out) {
    let c = 0;
    const codespaceRanges = this.codespaceRanges;
    // 9.7.6.2 CMap Mapping
    // The code length is at most 4.
    for (let n = 0, nn = codespaceRanges.length; n < nn; n++) {
      c = ((c << 8) | str.charCodeAt(offset + n)) >>> 0;
      // Check each codespace range to see if it falls within.
      const codespaceRange = codespaceRanges[n];
      for (let k = 0, kk = codespaceRange.length; k < kk;) {
        const low = codespaceRange[k++];
        const high = codespaceRange[k++];
        if (c >= low && c <= high) {
          out.charcode = c;
          out.length = n + 1;
          return;
        }
      }
    }
    out.charcode = 0;
    out.length = 1;
  }

  getCharCodeLength(charCode) {
    const codespaceRanges = this.codespaceRanges;
    for (let n = 0, nn = codespaceRanges.length; n < nn; n++) {
      // Check each codespace range to see if it falls within.
      const codespaceRange = codespaceRanges[n];
      for (let k = 0, kk = codespaceRange.length; k < kk;) {
        const low = codespaceRange[k++];
        const high = codespaceRange[k++];
        if (charCode >= low && charCode <= high) {
          return n + 1;
        }
      }
    }
    return 1;
  }

  // This is used for both bf and cid chars.
  mapOne(src, dst) {
    this._map[src] = dst;
  }

  mapCidRange(low, high, dstLow) {
    if (high - low > MAX_MAP_RANGE) {
      throw new Error("mapCidRange - ignoring data above MAX_MAP_RANGE.");
    }
    while (low <= high) {
      this._map[low++] = dstLow++;
    }
  }

// Heuristic to avoid hanging the worker-thread for CMap data with ridiculously
// large ranges, such as e.g. 0xFFFFFFFF (fixes issue11922_reduced.pdf).
const MAX_MAP_RANGE = 2 ** 24 - 1; // = 0xFFFFFF

  mapBfRange(low, high, dstLow) {
    if (high - low > MAX_MAP_RANGE) {
      throw new Error("mapBfRange - ignoring data above MAX_MAP_RANGE.");
    }
    const lastByte = dstLow.length - 1;
    while (low <= high) {
      this._map[low++] = dstLow;
      // Only the last byte has to be incremented (in the normal case).
      const nextCharCode = dstLow.charCodeAt(lastByte) + 1;
      if (nextCharCode > 0xff) {
        dstLow =
          dstLow.substring(0, lastByte - 1) +
          String.fromCharCode(dstLow.charCodeAt(lastByte - 1) + 1) +
          "\x00";
        continue;
      }
      dstLow =
        dstLow.substring(0, lastByte) + String.fromCharCode(nextCharCode);
    }
  }

  mapBfRangeToArray(low, high, array) {
    if (high - low > MAX_MAP_RANGE) {
      throw new Error("mapBfRangeToArray - ignoring data above MAX_MAP_RANGE.");
    }
    const ii = array.length;
    let i = 0;
    while (low <= high && i < ii) {
      this._map[low] = array[i++];
      ++low;
    }
  }

  lookup(code) {
    return this._map[code];
  }
 
  contains(code) {
    return this._map[code] !== undefined;
  }

  forEach(callback) {
    // Most maps have fewer than 65536 entries, and for those we use normal
    // array iteration. But really sparse tables are possible -- e.g. with
    // indices in the *billions*. For such tables we use for..in, which isn't
    // ideal because it stringifies the indices for all present elements, but
    // it does avoid iterating over every undefined entry.
    const map = this._map;
    const length = map.length;
    if (length <= 0x10000) {
      for (let i = 0; i < length; i++) {
        if (map[i] !== undefined) {
          callback(i, map[i]);
        }
      }
    } else {
      for (const i in map) {
        callback(i, map[i]);
      }
    }
  }

  charCodeOf(value) {
    // `Array.prototype.indexOf` is *extremely* inefficient for arrays which
    // are both very sparse and very large (see issue8372.pdf).
    const map = this._map;
    if (map.length <= 0x10000) {
      return map.indexOf(value);
    }
    for (const charCode in map) {
      if (map[charCode] === value) {
        return charCode | 0;
      }
    }
    return -1;
  }

  get length() {
    return this._map.length;
  }
 
  get isIdentityCMap() {
    if (!(this.name === "Identity-H" || this.name === "Identity-V")) {
      return false;
    }
    if (this._map.length !== 0x10000) {
      return false;
    }
    for (let i = 0; i < 0x10000; i++) {
      if (this._map[i] !== i) {
        return false;
      }
    }
    return true;
  }

// A special case of CMap, where the _map array implicitly has a length of
// 65536 and each element is equal to its index.
class IdentityCMap extends CMap {
  constructor(vertical, n) {
    super();
 
    this.vertical = vertical;
    this.addCodespaceRange(n, 0, 0xffff);
  }

  mapCidRange(low, high, dstLow) {
    unreachable("should not call mapCidRange");
  }
 
  mapBfRange(low, high, dstLow) {
    unreachable("should not call mapBfRange");
  }
 
  mapBfRangeToArray(low, high, array) {
    unreachable("should not call mapBfRangeToArray");
  }
 
  mapOne(src, dst) {
    unreachable("should not call mapCidOne");
  }

  lookup(code) {
    return Number.isInteger(code) && code <= 0xffff ? code : undefined;
  }
 
  contains(code) {
    return Number.isInteger(code) && code <= 0xffff;
  }
 
  charCodeOf(value) {
    return Number.isInteger(value) && value <= 0xffff ? value : -1;
  }

  getMap() {
    // Sometimes identity maps must be instantiated, but it's rare.
    const map = new Array(0x10000);
    for (let i = 0; i <= 0xffff; i++) {
      map[i] = i;
    }
    return map;
  }

function strToInt(str) {
  let a = 0;
  for (let i = 0; i < str.length; i++) {
    a = (a << 8) | str.charCodeAt(i);
  }
  return a >>> 0;
}

function expectString(obj) {
  if (typeof obj !== 'string') {
    throw new FormatError('Malformed CMap: expected string.');
  }
}
 
function expectInt(obj) {
  if (!Number.isInteger(obj)) {
    throw new FormatError('Malformed CMap: expected int.');
  }
}

function parseBfChar(cMap, lexer) {
  while (true) {
    let obj = lexer.getObj();
    if (obj === EOF) {
      break;
    }
    if (isCmd(obj, 'endbfchar')) {
      return;
    }
    expectString(obj);
    const src = strToInt(obj);
    obj = lexer.getObj();
    // TODO are /dstName used?
    expectString(obj);
    const dst = obj;
    cMap.mapOne(src, dst);
  }
}

function parseBfRange(cMap, lexer) {
  while (true) {
    let obj = lexer.getObj();
    if (obj === EOF) {
      break;
    }
    if (isCmd(obj, 'endbfrange')) {
      return;
    }
    expectString(obj);
    const low = strToInt(obj);
    obj = lexer.getObj();
    expectString(obj);
    const high = strToInt(obj);
    obj = lexer.getObj();
    if (Number.isInteger(obj) || typeof obj === 'string') {
      const dstLow = Number.isInteger(obj) ? String.fromCharCode(obj) : obj;
      cMap.mapBfRange(low, high, dstLow);
    } else if (isCmd(obj, '[')) {
      obj = lexer.getObj();
      const array = [];
      while (!isCmd(obj, ']') && obj !== EOF) {
        array.push(obj);
        obj = lexer.getObj();
      }
      cMap.mapBfRangeToArray(low, high, array);
    } else {
      break;
    }
  }
  throw new FormatError('Invalid bf range.');
}

function parseCidChar(cMap, lexer) {
  while (true) {
    let obj = lexer.getObj();
    if (obj === EOF) {
      break;
    }
    if (isCmd(obj, 'endcidchar')) {
      return;
    }
    expectString(obj);
    const src = strToInt(obj);
    obj = lexer.getObj();
    expectInt(obj);
    const dst = obj;
    cMap.mapOne(src, dst);
  }
}

function parseCidRange(cMap, lexer) {
  while (true) {
    let obj = lexer.getObj();
    if (obj === EOF) {
      break;
    }
    if (isCmd(obj, 'endcidrange')) {
      return;
    }
    expectString(obj);
    const low = strToInt(obj);
    obj = lexer.getObj();
    expectString(obj);
    const high = strToInt(obj);
    obj = lexer.getObj();
    expectInt(obj);
    const dstLow = obj;
    cMap.mapCidRange(low, high, dstLow);
  }
}

function parseCodespaceRange(cMap, lexer) {
  while (true) {
    let obj = lexer.getObj();
    if (obj === EOF) {
      break;
    }
    if (isCmd(obj, 'endcodespacerange')) {
      return;
    }
    if (typeof obj !== 'string') {
      break;
    }
    const low = strToInt(obj);
    obj = lexer.getObj();
    if (typeof obj !== 'string') {
      break;
    }
    const high = strToInt(obj);
    cMap.addCodespaceRange(obj.length, low, high);
  }
  throw new FormatError('Invalid codespace range.');
}

function parseWMode(cMap, lexer) {
  const obj = lexer.getObj();
  if (Number.isInteger(obj)) {
    cMap.vertical = !!obj;
  }
}
 
function parseCMapName(cMap, lexer) {
  const obj = lexer.getObj();
  if (obj instanceof Name) {
    cMap.name = obj.name;
  }
}

async function parseCMap(cMap, lexer, fetchBuiltInCMap, useCMap) {
  let previous, embeddedUseCMap;
  objLoop: while (true) {
    try {
      const obj = lexer.getObj();
      if (obj === EOF) {
        break;
      } else if (obj instanceof Name) {
        if (obj.name === 'WMode') {
          parseWMode(cMap, lexer);
        } else if (obj.name === 'CMapName') {
          parseCMapName(cMap, lexer);
        }
        previous = obj;
      } else if (obj instanceof Cmd) {
        switch (obj.cmd) {
          case 'endcmap':
            break objLoop;
          case 'usecmap':
            if (previous instanceof Name) {
              embeddedUseCMap = previous.name;
            }
            break;
          case 'begincodespacerange':
            parseCodespaceRange(cMap, lexer);
            break;
          case 'beginbfchar':
            parseBfChar(cMap, lexer);
            break;
          case 'begincidchar':
            parseCidChar(cMap, lexer);
            break;
          case 'beginbfrange':
            parseBfRange(cMap, lexer);
            break;
          case 'begincidrange':
            parseCidRange(cMap, lexer);
            break;
        }
      }
    } catch (ex) {
      if (ex instanceof MissingDataException) {
        throw ex;
      }
      warn('Invalid cMap data: ' + ex);
      continue;
    }
  }
 
  if (!useCMap && embeddedUseCMap) {
    // Load the useCMap definition from the file only if there wasn't one
    // specified.
    useCMap = embeddedUseCMap;
  }
  if (useCMap) {
    return extendCMap(cMap, fetchBuiltInCMap, useCMap);
  }
  return cMap;
}

if (!useCMap && embeddedUseCMap) {
  // Load the useCMap definition from the file only if there wasn't one
  // specified.
  useCMap = embeddedUseCMap;
}
if (useCMap) {
  return extendCMap(cMap, fetchBuiltInCMap, useCMap);
}

async function extendCMap(cMap, fetchBuiltInCMap, useCMap) {
  cMap.useCMap = await createBuiltInCMap(useCMap, fetchBuiltInCMap);
  // If there aren't any code space ranges defined clone all the parent ones
  // into this cMap.
  if (cMap.numCodespaceRanges === 0) {
    const useCodespaceRanges = cMap.useCMap.codespaceRanges;
    for (let i = 0; i < useCodespaceRanges.length; i++) {
      cMap.codespaceRanges[i] = useCodespaceRanges[i].slice();
    }
    cMap.numCodespaceRanges = cMap.useCMap.numCodespaceRanges;
  }
  // Merge the map into the current one, making sure not to override
  // any previously defined entries.
  cMap.useCMap.forEach(function (key, value) {
    if (!cMap.contains(key)) {
      cMap.mapOne(key, value);
    }
  });
 
  return cMap;
}

async function createBuiltInCMap(name, fetchBuiltInCMap) {
  if (name === 'Identity-H') {
    return new IdentityCMap(false, 2);
  } else if (name === 'Identity-V') {
    return new IdentityCMap(true, 2);
  }
  if (!BUILT_IN_CMAPS.includes(name)) {
    throw new Error('Unknown CMap name: ' + name);
  }
  if (!fetchBuiltInCMap) {
    throw new Error('Built-in CMap parameters are not provided.');
  }
 
  const { cMapData, isCompressed } = await fetchBuiltInCMap(name);
  const cMap = new CMap(true);
 
  if (isCompressed) {
    return new BinaryCMapReader().process(cMapData, cMap, useCMap =>
      extendCMap(cMap, fetchBuiltInCMap, useCMap),
    );
  }
  const lexer = new Lexer(new Stream(cMapData));
  return parseCMap(cMap, lexer, fetchBuiltInCMap, null);
}

class CMapFactory {
  static async create({ encoding, fetchBuiltInCMap, useCMap }) {
    if (encoding instanceof Name) {
      return createBuiltInCMap(encoding.name, fetchBuiltInCMap);
    } else if (encoding instanceof BaseStream) {
      if (encoding.isAsync) {
        const bytes = await encoding.asyncGetBytes();
        if (bytes) {
          encoding = new Stream(bytes, 0, bytes.length, encoding.dict);
        }
      }
      const parsedCMap = await parseCMap(
        /* cMap = */ new CMap(),
        /* lexer = */ new Lexer(encoding),
        fetchBuiltInCMap,
        useCMap,
      );
 
      if (parsedCMap.isIdentityCMap) {
        return createBuiltInCMap(parsedCMap.name, fetchBuiltInCMap);
      }
      return parsedCMap;
    }
    throw new Error('Encoding required.');
  }
}

if (composite) {
  const cidEncoding = baseDict.get('Encoding');
  if (cidEncoding instanceof Name) {
    properties.cidEncoding = cidEncoding.name;
  }
  const cMap = await CMapFactory.create({
    encoding: cidEncoding,
    fetchBuiltInCMap: this._fetchBuiltInCMapBound,
    useCMap: null,
  });
  properties.cMap = cMap;
  properties.vertical = properties.cMap.vertical;
}

  async readToUnicode(cmapObj) {
    if (!cmapObj) {
      return null;
    }
    if (cmapObj instanceof Name) {
      const cmap = await CMapFactory.create({
        encoding: cmapObj,
        fetchBuiltInCMap: this._fetchBuiltInCMapBound,
        useCMap: null,
      });
 
      if (cmap instanceof IdentityCMap) {
        return new IdentityToUnicodeMap(0, 0xffff);
      }
      return new ToUnicodeMap(cmap.getMap());
    }

  async fetchBuiltInCMap(name) {
    const cachedData = this.builtInCMapCache.get(name);
    if (cachedData) {
      return cachedData;
    }
    let data;
 
    if (this.options.useWorkerFetch) {
      // Only compressed CMaps are (currently) supported here.
      data = {
        cMapData: await fetchBinaryData(`${this.options.cMapUrl}${name}.bcmap`),
        isCompressed: true,
      };
    } else {
      if (typeof PDFJSDev !== "undefined" && PDFJSDev.test("MOZCENTRAL")) {
        throw new Error("Only worker-thread fetching supported.");
      }
      // Get the data on the main-thread instead.
      data = {
        cMapData: await this.handler.sendWithPromise("FetchBinaryData", {
          kind: "cMapUrl",
          filename: `${name}${this.options.cMapPacked ? ".bcmap" : ""}`,
        }),
        isCompressed: this.options.cMapPacked,
      };
    }
    // Cache the CMap data, to avoid fetching it repeatedly.
    this.builtInCMapCache.set(name, data);
 
    return data;
  }