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

Convert the Parser class in src/core/parser.js to ES6 syntax

Browse Source
This commit is contained in:
Tim van der Meij 2019-03-10 14:09:31 +01:00
parent d587abbceb
commit 7d0ecee771
No known key found for this signature in database
GPG Key ID: 8C3FD2925A5F2762
1 changed files with 620 additions and 609 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

181
src/core/parser.js
View File

@ -34,7 +34,7 @@ const MAX_LENGTH_TO_CACHE = 1000;
const MAX_ADLER32_LENGTH = 5552; const MAX_ADLER32_LENGTH = 5552;
function computeAdler32(bytes) { function computeAdler32(bytes) {
let bytesLength = bytes.length; const bytesLength = bytes.length;
if (typeof PDFJSDev === 'undefined' || if (typeof PDFJSDev === 'undefined' ||
PDFJSDev.test('!PRODUCTION || TESTING')) { PDFJSDev.test('!PRODUCTION || TESTING')) {
assert(bytesLength < MAX_ADLER32_LENGTH, assert(bytesLength < MAX_ADLER32_LENGTH,
@ -49,22 +49,23 @@ function computeAdler32(bytes) {
return ((b % 65521) << 16) | (a % 65521); return ((b % 65521) << 16) | (a % 65521);
} }
var Parser = (function ParserClosure() { class Parser {
function Parser(lexer, allowStreams, xref, recoveryMode) { constructor(lexer, allowStreams, xref, recoveryMode = false) {
this.lexer = lexer; this.lexer = lexer;
this.allowStreams = allowStreams; this.allowStreams = allowStreams;
this.xref = xref; this.xref = xref;
this.recoveryMode = recoveryMode || false; this.recoveryMode = recoveryMode;
this.imageCache = Object.create(null); this.imageCache = Object.create(null);
this.refill(); this.refill();
} }
Parser.prototype = { refill() {
refill: function Parser_refill() {
this.buf1 = this.lexer.getObj(); this.buf1 = this.lexer.getObj();
this.buf2 = this.lexer.getObj(); this.buf2 = this.lexer.getObj();
}, }
shift: function Parser_shift() {
shift() {
if (isCmd(this.buf2, 'ID')) { if (isCmd(this.buf2, 'ID')) {
this.buf1 = this.buf2; this.buf1 = this.buf2;
this.buf2 = null; this.buf2 = null;
@ -72,8 +73,9 @@ var Parser = (function ParserClosure() {
this.buf1 = this.buf2; this.buf1 = this.buf2;
this.buf2 = this.lexer.getObj(); this.buf2 = this.lexer.getObj();
} }
}, }
tryShift: function Parser_tryShift() {
tryShift() {
try { try {
this.shift(); this.shift();
return true; return true;
@ -85,9 +87,10 @@ var Parser = (function ParserClosure() {
// state and call this.shift() twice to reset the buffers. // state and call this.shift() twice to reset the buffers.
return false; return false;
} }
}, }
getObj: function Parser_getObj(cipherTransform) {
var buf1 = this.buf1; getObj(cipherTransform) {
const buf1 = this.buf1;
this.shift(); this.shift();
if (buf1 instanceof Cmd) { if (buf1 instanceof Cmd) {
@ -95,7 +98,7 @@ var Parser = (function ParserClosure() {
case 'BI': // inline image case 'BI': // inline image
return this.makeInlineImage(cipherTransform); return this.makeInlineImage(cipherTransform);
case '[': // array case '[': // array
var array = []; const array = [];
while (!isCmd(this.buf1, ']') && !isEOF(this.buf1)) { while (!isCmd(this.buf1, ']') && !isEOF(this.buf1)) {
array.push(this.getObj(cipherTransform)); array.push(this.getObj(cipherTransform));
} }
@ -108,7 +111,7 @@ var Parser = (function ParserClosure() {
this.shift(); this.shift();
return array; return array;
case '<<': // dictionary or stream case '<<': // dictionary or stream
var dict = new Dict(this.xref); const dict = new Dict(this.xref);
while (!isCmd(this.buf1, '>>') && !isEOF(this.buf1)) { while (!isCmd(this.buf1, '>>') && !isEOF(this.buf1)) {
if (!isName(this.buf1)) { if (!isName(this.buf1)) {
info('Malformed dictionary: key must be a name object'); info('Malformed dictionary: key must be a name object');
@ -116,7 +119,7 @@ var Parser = (function ParserClosure() {
continue; continue;
} }
var key = this.buf1.name; const key = this.buf1.name;
this.shift(); this.shift();
if (isEOF(this.buf1)) { if (isEOF(this.buf1)) {
break; break;
@ -144,9 +147,9 @@ var Parser = (function ParserClosure() {
} }
if (Number.isInteger(buf1)) { // indirect reference or integer if (Number.isInteger(buf1)) { // indirect reference or integer
var num = buf1; const num = buf1;
if (Number.isInteger(this.buf1) && isCmd(this.buf2, 'R')) { if (Number.isInteger(this.buf1) && isCmd(this.buf2, 'R')) {
var ref = new Ref(num, this.buf1); const ref = new Ref(num, this.buf1);
this.shift(); this.shift();
this.shift(); this.shift();
return ref; return ref;
@ -155,7 +158,7 @@ var Parser = (function ParserClosure() {
} }
if (isString(buf1)) { // string if (isString(buf1)) { // string
var str = buf1; let str = buf1;
if (cipherTransform) { if (cipherTransform) {
str = cipherTransform.decryptString(str); str = cipherTransform.decryptString(str);
} }
@ -164,7 +167,8 @@ var Parser = (function ParserClosure() {
// simple object // simple object
return buf1; return buf1;
}, }
/** /**
* Find the end of the stream by searching for the /EI\s/. * Find the end of the stream by searching for the /EI\s/.
* @returns {number} The inline stream length. * @returns {number} The inline stream length.
@ -183,7 +187,7 @@ var Parser = (function ParserClosure() {
if (ch === SPACE || ch === LF || ch === CR) { if (ch === SPACE || ch === LF || ch === CR) {
maybeEIPos = stream.pos; maybeEIPos = stream.pos;
// Let's check that the next `n` bytes are ASCII... just to be sure. // Let's check that the next `n` bytes are ASCII... just to be sure.
let followingBytes = stream.peekBytes(n); const followingBytes = stream.peekBytes(n);
for (let i = 0, ii = followingBytes.length; i < ii; i++) { for (let i = 0, ii = followingBytes.length; i < ii; i++) {
ch = followingBytes[i]; ch = followingBytes[i];
if (ch === NUL && followingBytes[i + 1] !== NUL) { if (ch === NUL && followingBytes[i + 1] !== NUL) {
@ -235,14 +239,14 @@ var Parser = (function ParserClosure() {
endOffset--; endOffset--;
} }
return ((stream.pos - endOffset) - startPos); return ((stream.pos - endOffset) - startPos);
}, }
/** /**
* Find the EOI (end-of-image) marker 0xFFD9 of the stream. * Find the EOI (end-of-image) marker 0xFFD9 of the stream.
* @returns {number} The inline stream length. * @returns {number} The inline stream length.
*/ */
findDCTDecodeInlineStreamEnd: findDCTDecodeInlineStreamEnd(stream) {
function Parser_findDCTDecodeInlineStreamEnd(stream) { let startPos = stream.pos, foundEOI = false, b, markerLength, length;
var startPos = stream.pos, foundEOI = false, b, markerLength, length;
while ((b = stream.getByte()) !== -1) { while ((b = stream.getByte()) !== -1) {
if (b !== 0xFF) { // Not a valid marker. if (b !== 0xFF) { // Not a valid marker.
continue; continue;
@ -331,14 +335,15 @@ var Parser = (function ParserClosure() {
} }
this.inlineStreamSkipEI(stream); this.inlineStreamSkipEI(stream);
return length; return length;
}, }
/** /**
* Find the EOD (end-of-data) marker '~>' (i.e. TILDE + GT) of the stream. * Find the EOD (end-of-data) marker '~>' (i.e. TILDE + GT) of the stream.
* @returns {number} The inline stream length. * @returns {number} The inline stream length.
*/ */
findASCII85DecodeInlineStreamEnd(stream) { findASCII85DecodeInlineStreamEnd(stream) {
var TILDE = 0x7E, GT = 0x3E; const TILDE = 0x7E, GT = 0x3E;
var startPos = stream.pos, ch, length; let startPos = stream.pos, ch, length;
while ((ch = stream.getByte()) !== -1) { while ((ch = stream.getByte()) !== -1) {
if (ch === TILDE) { if (ch === TILDE) {
ch = stream.peekByte(); ch = stream.peekByte();
@ -363,15 +368,15 @@ var Parser = (function ParserClosure() {
} }
this.inlineStreamSkipEI(stream); this.inlineStreamSkipEI(stream);
return length; return length;
}, }
/** /**
* Find the EOD (end-of-data) marker '>' (i.e. GT) of the stream. * Find the EOD (end-of-data) marker '>' (i.e. GT) of the stream.
* @returns {number} The inline stream length. * @returns {number} The inline stream length.
*/ */
findASCIIHexDecodeInlineStreamEnd: findASCIIHexDecodeInlineStreamEnd(stream) {
function Parser_findASCIIHexDecodeInlineStreamEnd(stream) { const GT = 0x3E;
var GT = 0x3E; let startPos = stream.pos, ch, length;
var startPos = stream.pos, ch, length;
while ((ch = stream.getByte()) !== -1) { while ((ch = stream.getByte()) !== -1) {
if (ch === GT) { if (ch === GT) {
break; break;
@ -386,13 +391,14 @@ var Parser = (function ParserClosure() {
} }
this.inlineStreamSkipEI(stream); this.inlineStreamSkipEI(stream);
return length; return length;
}, }
/** /**
* Skip over the /EI/ for streams where we search for an EOD marker. * Skip over the /EI/ for streams where we search for an EOD marker.
*/ */
inlineStreamSkipEI: function Parser_inlineStreamSkipEI(stream) { inlineStreamSkipEI(stream) {
var E = 0x45, I = 0x49; const E = 0x45, I = 0x49;
var state = 0, ch; let state = 0, ch;
while ((ch = stream.getByte()) !== -1) { while ((ch = stream.getByte()) !== -1) {
if (state === 0) { if (state === 0) {
state = (ch === E) ? 1 : 0; state = (ch === E) ? 1 : 0;
@ -402,18 +408,20 @@ var Parser = (function ParserClosure() {
break; break;
} }
} }
}, }
makeInlineImage: function Parser_makeInlineImage(cipherTransform) {
var lexer = this.lexer; makeInlineImage(cipherTransform) {
var stream = lexer.stream; const lexer = this.lexer;
const stream = lexer.stream;
// Parse dictionary. // Parse dictionary.
let dict = new Dict(this.xref), dictLength; const dict = new Dict(this.xref);
let dictLength;
while (!isCmd(this.buf1, 'ID') && !isEOF(this.buf1)) { while (!isCmd(this.buf1, 'ID') && !isEOF(this.buf1)) {
if (!isName(this.buf1)) { if (!isName(this.buf1)) {
throw new FormatError('Dictionary key must be a name object'); throw new FormatError('Dictionary key must be a name object');
} }
var key = this.buf1.name; const key = this.buf1.name;
this.shift(); this.shift();
if (isEOF(this.buf1)) { if (isEOF(this.buf1)) {
break; break;
@ -425,18 +433,20 @@ var Parser = (function ParserClosure() {
} }
// Extract the name of the first (i.e. the current) image filter. // Extract the name of the first (i.e. the current) image filter.
var filter = dict.get('Filter', 'F'), filterName; const filter = dict.get('Filter', 'F');
let filterName;
if (isName(filter)) { if (isName(filter)) {
filterName = filter.name; filterName = filter.name;
} else if (Array.isArray(filter)) { } else if (Array.isArray(filter)) {
var filterZero = this.xref.fetchIfRef(filter[0]); const filterZero = this.xref.fetchIfRef(filter[0]);
if (isName(filterZero)) { if (isName(filterZero)) {
filterName = filterZero.name; filterName = filterZero.name;
} }
} }
// Parse image stream. // Parse image stream.
let startPos = stream.pos, length; const startPos = stream.pos;
let length;
if (filterName === 'DCTDecode' || filterName === 'DCT') { if (filterName === 'DCTDecode' || filterName === 'DCT') {
length = this.findDCTDecodeInlineStreamEnd(stream); length = this.findDCTDecodeInlineStreamEnd(stream);
} else if (filterName === 'ASCII85Decode' || filterName === 'A85') { } else if (filterName === 'ASCII85Decode' || filterName === 'A85') {
@ -446,26 +456,26 @@ var Parser = (function ParserClosure() {
} else { } else {
length = this.findDefaultInlineStreamEnd(stream); length = this.findDefaultInlineStreamEnd(stream);
} }
var imageStream = stream.makeSubStream(startPos, length, dict); let imageStream = stream.makeSubStream(startPos, length, dict);
// Cache all images below the MAX_LENGTH_TO_CACHE threshold by their // Cache all images below the MAX_LENGTH_TO_CACHE threshold by their
// adler32 checksum. // adler32 checksum.
let cacheKey; let cacheKey;
if (length < MAX_LENGTH_TO_CACHE && dictLength < MAX_ADLER32_LENGTH) { if (length < MAX_LENGTH_TO_CACHE && dictLength < MAX_ADLER32_LENGTH) {
var imageBytes = imageStream.getBytes(); const imageBytes = imageStream.getBytes();
imageStream.reset(); imageStream.reset();
const initialStreamPos = stream.pos; const initialStreamPos = stream.pos;
// Set the stream position to the beginning of the dictionary data... // Set the stream position to the beginning of the dictionary data...
stream.pos = lexer.beginInlineImagePos; stream.pos = lexer.beginInlineImagePos;
// ... and fetch the bytes of the *entire* dictionary. // ... and fetch the bytes of the *entire* dictionary.
let dictBytes = stream.getBytes(dictLength); const dictBytes = stream.getBytes(dictLength);
// Finally, don't forget to reset the stream position. // Finally, don't forget to reset the stream position.
stream.pos = initialStreamPos; stream.pos = initialStreamPos;
cacheKey = computeAdler32(imageBytes) + '_' + computeAdler32(dictBytes); cacheKey = computeAdler32(imageBytes) + '_' + computeAdler32(dictBytes);
let cacheEntry = this.imageCache[cacheKey]; const cacheEntry = this.imageCache[cacheKey];
if (cacheEntry !== undefined) { if (cacheEntry !== undefined) {
this.buf2 = Cmd.get('EI'); this.buf2 = Cmd.get('EI');
this.shift(); this.shift();
@ -482,7 +492,7 @@ var Parser = (function ParserClosure() {
imageStream = this.filter(imageStream, dict, length); imageStream = this.filter(imageStream, dict, length);
imageStream.dict = dict; imageStream.dict = dict;
if (cacheKey !== undefined) { if (cacheKey !== undefined) {
imageStream.cacheKey = 'inline_' + length + '_' + cacheKey; imageStream.cacheKey = `inline_${length}_${cacheKey}`;
this.imageCache[cacheKey] = imageStream; this.imageCache[cacheKey] = imageStream;
} }
@ -490,7 +500,7 @@ var Parser = (function ParserClosure() {
this.shift(); this.shift();
return imageStream; return imageStream;
}, }
_findStreamLength(startPos, signature) { _findStreamLength(startPos, signature) {
const { stream, } = this.lexer; const { stream, } = this.lexer;
@ -521,28 +531,28 @@ var Parser = (function ParserClosure() {
stream.pos += scanLength; stream.pos += scanLength;
} }
return -1; return -1;
}, }
makeStream: function Parser_makeStream(dict, cipherTransform) { makeStream(dict, cipherTransform) {
var lexer = this.lexer; const lexer = this.lexer;
var stream = lexer.stream; let stream = lexer.stream;
// get stream start position // Get the stream's start position.
lexer.skipToNextLine(); lexer.skipToNextLine();
const startPos = stream.pos - 1; const startPos = stream.pos - 1;
// get length // Get the length.
var length = dict.get('Length'); let length = dict.get('Length');
if (!Number.isInteger(length)) { if (!Number.isInteger(length)) {
info('Bad ' + length + ' attribute in stream'); info(`Bad length "${length}" in stream`);
length = 0; length = 0;
} }
// skip over the stream data // Skip over the stream data.
stream.pos = startPos + length; stream.pos = startPos + length;
lexer.nextChar(); lexer.nextChar();
// Shift '>>' and check whether the new object marks the end of the stream // Shift '>>' and check whether the new object marks the end of the stream.
if (this.tryShift() && isCmd(this.buf2, 'endstream')) { if (this.tryShift() && isCmd(this.buf2, 'endstream')) {
this.shift(); // 'stream' this.shift(); // 'stream'
} else { } else {
@ -561,7 +571,7 @@ var Parser = (function ParserClosure() {
const end = ENDSTREAM_SIGNATURE.length - i; const end = ENDSTREAM_SIGNATURE.length - i;
const TRUNCATED_SIGNATURE = ENDSTREAM_SIGNATURE.slice(0, end); const TRUNCATED_SIGNATURE = ENDSTREAM_SIGNATURE.slice(0, end);
let maybeLength = this._findStreamLength(startPos, const maybeLength = this._findStreamLength(startPos,
TRUNCATED_SIGNATURE); TRUNCATED_SIGNATURE);
if (maybeLength >= 0) { if (maybeLength >= 0) {
// Ensure that the byte immediately following the truncated // Ensure that the byte immediately following the truncated
@ -596,10 +606,12 @@ var Parser = (function ParserClosure() {
stream = this.filter(stream, dict, length); stream = this.filter(stream, dict, length);
stream.dict = dict; stream.dict = dict;
return stream; return stream;
}, }
filter: function Parser_filter(stream, dict, length) {
var filter = dict.get('Filter', 'F'); filter(stream, dict, length) {
var params = dict.get('DecodeParms', 'DP'); let filter = dict.get('Filter', 'F');
let params = dict.get('DecodeParms', 'DP');
if (isName(filter)) { if (isName(filter)) {
if (Array.isArray(params)) { if (Array.isArray(params)) {
warn('/DecodeParms should not contain an Array, ' + warn('/DecodeParms should not contain an Array, ' +
@ -608,14 +620,14 @@ var Parser = (function ParserClosure() {
return this.makeFilter(stream, filter.name, length, params); return this.makeFilter(stream, filter.name, length, params);
} }
var maybeLength = length; let maybeLength = length;
if (Array.isArray(filter)) { if (Array.isArray(filter)) {
var filterArray = filter; let filterArray = filter;
var paramsArray = params; let paramsArray = params;
for (var i = 0, ii = filterArray.length; i < ii; ++i) { for (let i = 0, ii = filterArray.length; i < ii; ++i) {
filter = this.xref.fetchIfRef(filterArray[i]); filter = this.xref.fetchIfRef(filterArray[i]);
if (!isName(filter)) { if (!isName(filter)) {
throw new FormatError('Bad filter name: ' + filter); throw new FormatError(`Bad filter name "${filter}"`);
} }
params = null; params = null;
@ -623,22 +635,24 @@ var Parser = (function ParserClosure() {
params = this.xref.fetchIfRef(paramsArray[i]); params = this.xref.fetchIfRef(paramsArray[i]);
} }
stream = this.makeFilter(stream, filter.name, maybeLength, params); stream = this.makeFilter(stream, filter.name, maybeLength, params);
// after the first stream the length variable is invalid // After the first stream the `length` variable is invalid.
maybeLength = null; maybeLength = null;
} }
} }
return stream; return stream;
}, }
makeFilter: function Parser_makeFilter(stream, name, maybeLength, params) {
makeFilter(stream, name, maybeLength, params) {
// Since the 'Length' entry in the stream dictionary can be completely // Since the 'Length' entry in the stream dictionary can be completely
// wrong, e.g. zero for non-empty streams, only skip parsing the stream // wrong, e.g. zero for non-empty streams, only skip parsing the stream
// when we can be absolutely certain that it actually is empty. // when we can be absolutely certain that it actually is empty.
if (maybeLength === 0) { if (maybeLength === 0) {
warn('Empty "' + name + '" stream.'); warn(`Empty "${name}" stream.`);
return new NullStream(); return new NullStream();
} }
try { try {
var xrefStreamStats = this.xref.stats.streamTypes; const xrefStreamStats = this.xref.stats.streamTypes;
if (name === 'FlateDecode' || name === 'Fl') { if (name === 'FlateDecode' || name === 'Fl') {
xrefStreamStats[StreamType.FLATE] = true; xrefStreamStats[StreamType.FLATE] = true;
if (params) { if (params) {
@ -649,7 +663,7 @@ var Parser = (function ParserClosure() {
} }
if (name === 'LZWDecode' || name === 'LZW') { if (name === 'LZWDecode' || name === 'LZW') {
xrefStreamStats[StreamType.LZW] = true; xrefStreamStats[StreamType.LZW] = true;
var earlyChange = 1; let earlyChange = 1;
if (params) { if (params) {
if (params.has('EarlyChange')) { if (params.has('EarlyChange')) {
earlyChange = params.get('EarlyChange'); earlyChange = params.get('EarlyChange');
@ -688,20 +702,17 @@ var Parser = (function ParserClosure() {
xrefStreamStats[StreamType.JBIG] = true; xrefStreamStats[StreamType.JBIG] = true;
return new Jbig2Stream(stream, maybeLength, stream.dict, params); return new Jbig2Stream(stream, maybeLength, stream.dict, params);
} }
warn('filter "' + name + '" not supported yet'); warn(`Filter "${name}" is not supported.`);
return stream; return stream;
} catch (ex) { } catch (ex) {
if (ex instanceof MissingDataException) { if (ex instanceof MissingDataException) {
throw ex; throw ex;
} }
warn('Invalid stream: \"' + ex + '\"'); warn(`Invalid stream: "${ex}"`);
return new NullStream(); return new NullStream();
} }
}, }
}; }
return Parser;
})();
var Lexer = (function LexerClosure() { var Lexer = (function LexerClosure() {
function Lexer(stream, knownCommands) { function Lexer(stream, knownCommands) {