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

Merge pull request #10393 from timvandermeij/document

Browse Source 
Convert `src/core/document.js` to ES6 syntax
This commit is contained in:
Tim van der Meij 2018-12-30 14:23:38 +01:00 committed by GitHub
commit 7c080584b6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 546 additions and 545 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/core/chunked_stream.js
View File

@ -12,6 +12,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/* eslint no-var: error */
import {
arrayByteLength, arraysToBytes, createPromiseCapability, isEmptyObj,

510
src/core/document.js
View File

@ -12,6 +12,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/* eslint no-var: error */
import {
assert, FormatError, getInheritableProperty, info, isArrayBuffer, isBool,
@ -28,17 +29,16 @@ import { OperatorList } from './operator_list';
import { PartialEvaluator } from './evaluator';
import { PDFFunctionFactory } from './function';
var Page = (function PageClosure() {
const DEFAULT_USER_UNIT = 1.0;
const LETTER_SIZE_MEDIABOX = [0, 0, 612, 792];
var DEFAULT_USER_UNIT = 1.0;
var LETTER_SIZE_MEDIABOX = [0, 0, 612, 792];
function isAnnotationRenderable(annotation, intent) {
function isAnnotationRenderable(annotation, intent) {
return (intent === 'display' && annotation.viewable) ||
(intent === 'print' && annotation.printable);
}
}
function Page({ pdfManager, xref, pageIndex, pageDict, ref, fontCache,
class Page {
constructor({ pdfManager, xref, pageIndex, pageDict, ref, fontCache,
builtInCMapCache, pdfFunctionFactory, }) {
this.pdfManager = pdfManager;
this.pageIndex = pageIndex;
@ -51,8 +51,8 @@ var Page = (function PageClosure() {
this.evaluatorOptions = pdfManager.evaluatorOptions;
this.resourcesPromise = null;
var uniquePrefix = 'p' + this.pageIndex + '_';
var idCounters = {
const uniquePrefix = `p${this.pageIndex}_`;
const idCounters = {
obj: 0,
};
this.idFactory = {
@ -62,12 +62,11 @@ var Page = (function PageClosure() {
};
}
Page.prototype = {
/**
* @private
*/
_getInheritableProperty(key, getArray = false) {
let value = getInheritableProperty({ dict: this.pageDict, key, getArray,
const value = getInheritableProperty({ dict: this.pageDict, key, getArray,
stopWhenFound: false, });
if (!Array.isArray(value)) {
return value;
@ -76,124 +75,123 @@ var Page = (function PageClosure() {
return value[0];
}
return Dict.merge(this.xref, value);
},
}
get content() {
return this.pageDict.get('Contents');
},
}
get resources() {
// For robustness: The spec states that a \Resources entry has to be
// present, but can be empty. Some document omit it still, in this case
// present, but can be empty. Some documents still omit it; in this case
// we return an empty dictionary.
return shadow(this, 'resources',
this._getInheritableProperty('Resources') || Dict.empty);
},
}
get mediaBox() {
var mediaBox = this._getInheritableProperty('MediaBox',
const mediaBox = this._getInheritableProperty('MediaBox',
/* getArray = */ true);
// Reset invalid media box to letter size.
if (!Array.isArray(mediaBox) || mediaBox.length !== 4) {
return shadow(this, 'mediaBox', LETTER_SIZE_MEDIABOX);
}
return shadow(this, 'mediaBox', mediaBox);
},
}
get cropBox() {
var cropBox = this._getInheritableProperty('CropBox',
const cropBox = this._getInheritableProperty('CropBox',
/* getArray = */ true);
// Reset invalid crop box to media box.
if (!Array.isArray(cropBox) || cropBox.length !== 4) {
return shadow(this, 'cropBox', this.mediaBox);
}
return shadow(this, 'cropBox', cropBox);
},
}
get userUnit() {
var obj = this.pageDict.get('UserUnit');
let obj = this.pageDict.get('UserUnit');
if (!isNum(obj) || obj <= 0) {
obj = DEFAULT_USER_UNIT;
}
return shadow(this, 'userUnit', obj);
},
}
get view() {
// From the spec, 6th ed., p.963:
// "The crop, bleed, trim, and art boxes should not ordinarily
// extend beyond the boundaries of the media box. If they do, they are
// effectively reduced to their intersection with the media box."
var mediaBox = this.mediaBox, cropBox = this.cropBox;
const mediaBox = this.mediaBox, cropBox = this.cropBox;
if (mediaBox === cropBox) {
return shadow(this, 'view', mediaBox);
}
var intersection = Util.intersect(cropBox, mediaBox);
const intersection = Util.intersect(cropBox, mediaBox);
return shadow(this, 'view', intersection || mediaBox);
},
}
get rotate() {
var rotate = this._getInheritableProperty('Rotate') || 0;
// Normalize rotation so it's a multiple of 90 and between 0 and 270
let rotate = this._getInheritableProperty('Rotate') || 0;
// Normalize rotation so it's a multiple of 90 and between 0 and 270.
if (rotate % 90 !== 0) {
rotate = 0;
} else if (rotate >= 360) {
rotate = rotate % 360;
} else if (rotate < 0) {
// The spec doesn't cover negatives, assume its counterclockwise
// The spec doesn't cover negatives. Assume it's counterclockwise
// rotation. The following is the other implementation of modulo.
rotate = ((rotate % 360) + 360) % 360;
}
return shadow(this, 'rotate', rotate);
},
}
getContentStream() {
const content = this.content;
let stream;
getContentStream: function Page_getContentStream() {
var content = this.content;
var stream;
if (Array.isArray(content)) {
// fetching items
var xref = this.xref;
var i, n = content.length;
var streams = [];
for (i = 0; i < n; ++i) {
streams.push(xref.fetchIfRef(content[i]));
// Fetching the individual streams from the array.
const xref = this.xref;
const streams = [];
for (const stream of content) {
streams.push(xref.fetchIfRef(stream));
}
stream = new StreamsSequenceStream(streams);
} else if (isStream(content)) {
stream = content;
} else {
// replacing non-existent page content with empty one
// Replace non-existent page content with empty content.
stream = new NullStream();
}
return stream;
},
}
loadResources: function Page_loadResources(keys) {
loadResources(keys) {
if (!this.resourcesPromise) {
// TODO: add async `_getInheritableProperty` and remove this.
this.resourcesPromise = this.pdfManager.ensure(this, 'resources');
}
return this.resourcesPromise.then(() => {
let objectLoader = new ObjectLoader(this.resources, keys, this.xref);
const objectLoader = new ObjectLoader(this.resources, keys, this.xref);
return objectLoader.load();
});
},
}
getOperatorList({ handler, task, intent, renderInteractiveForms, }) {
var contentStreamPromise = this.pdfManager.ensure(this,
const contentStreamPromise = this.pdfManager.ensure(this,
'getContentStream');
var resourcesPromise = this.loadResources([
const resourcesPromise = this.loadResources([
'ExtGState',
'ColorSpace',
'Pattern',
'Shading',
'XObject',
'Font'
// ProcSet
// Properties
'Font',
]);
var partialEvaluator = new PartialEvaluator({
const partialEvaluator = new PartialEvaluator({
pdfManager: this.pdfManager,
xref: this.xref,
handler,
@ -205,21 +203,22 @@ var Page = (function PageClosure() {
pdfFunctionFactory: this.pdfFunctionFactory,
});
var dataPromises = Promise.all([contentStreamPromise, resourcesPromise]);
var pageListPromise = dataPromises.then(([contentStream]) => {
var opList = new OperatorList(intent, handler, this.pageIndex);
const dataPromises = Promise.all([contentStreamPromise, resourcesPromise]);
const pageListPromise = dataPromises.then(([contentStream]) => {
const opList = new OperatorList(intent, handler, this.pageIndex);
handler.send('StartRenderPage', {
transparency: partialEvaluator.hasBlendModes(this.resources),
pageIndex: this.pageIndex,
intent,
});
return partialEvaluator.getOperatorList({
stream: contentStream,
task,
resources: this.resources,
operatorList: opList,
}).then(function () {
}).then(function() {
return opList;
});
});
@ -227,7 +226,7 @@ var Page = (function PageClosure() {
// Fetch the page's annotations and add their operator lists to the
// page's operator list to render them.
return Promise.all([pageListPromise, this._parsedAnnotations]).then(
function ([pageOpList, annotations]) {
function([pageOpList, annotations]) {
if (annotations.length === 0) {
pageOpList.flush(true);
return pageOpList;
@ -235,40 +234,39 @@ var Page = (function PageClosure() {
// Collect the operator list promises for the annotations. Each promise
// is resolved with the complete operator list for a single annotation.
var i, ii, opListPromises = [];
for (i = 0, ii = annotations.length; i < ii; i++) {
if (isAnnotationRenderable(annotations[i], intent)) {
opListPromises.push(annotations[i].getOperatorList(
const opListPromises = [];
for (const annotation of annotations) {
if (isAnnotationRenderable(annotation, intent)) {
opListPromises.push(annotation.getOperatorList(
partialEvaluator, task, renderInteractiveForms));
}
}
return Promise.all(opListPromises).then(function(opLists) {
pageOpList.addOp(OPS.beginAnnotations, []);
for (i = 0, ii = opLists.length; i < ii; i++) {
pageOpList.addOpList(opLists[i]);
for (const opList of opLists) {
pageOpList.addOpList(opList);
}
pageOpList.addOp(OPS.endAnnotations, []);
pageOpList.flush(true);
return pageOpList;
});
});
},
}
extractTextContent({ handler, task, normalizeWhitespace,
sink, combineTextItems, }) {
var contentStreamPromise = this.pdfManager.ensure(this,
extractTextContent({ handler, task, normalizeWhitespace, sink,
combineTextItems, }) {
const contentStreamPromise = this.pdfManager.ensure(this,
'getContentStream');
var resourcesPromise = this.loadResources([
const resourcesPromise = this.loadResources([
'ExtGState',
'XObject',
'Font'
'Font',
]);
var dataPromises = Promise.all([contentStreamPromise, resourcesPromise]);
const dataPromises = Promise.all([contentStreamPromise, resourcesPromise]);
return dataPromises.then(([contentStream]) => {
var partialEvaluator = new PartialEvaluator({
const partialEvaluator = new PartialEvaluator({
pdfManager: this.pdfManager,
xref: this.xref,
handler,
@ -289,11 +287,11 @@ var Page = (function PageClosure() {
sink,
});
});
},
}
getAnnotationsData(intent) {
return this._parsedAnnotations.then(function(annotations) {
let annotationsData = [];
const annotationsData = [];
for (let i = 0, ii = annotations.length; i < ii; i++) {
if (!intent || isAnnotationRenderable(annotations[i], intent)) {
annotationsData.push(annotations[i].data);
@ -301,12 +299,12 @@ var Page = (function PageClosure() {
}
return annotationsData;
});
},
}
get annotations() {
return shadow(this, 'annotations',
this._getInheritableProperty('Annots') || []);
},
}
get _parsedAnnotations() {
const parsedAnnotations =
@ -329,26 +327,44 @@ var Page = (function PageClosure() {
});
return shadow(this, '_parsedAnnotations', parsedAnnotations);
},
};
}
}
return Page;
})();
/**
* The `PDFDocument` holds all the data of the PDF file. Compared to the
* `PDFDoc`, this one doesn't have any job management code.
* Right now there exists one PDFDocument on the main thread + one object
* for each worker. If there is no worker support enabled, there are two
* `PDFDocument` objects on the main thread created.
*/
var PDFDocument = (function PDFDocumentClosure() {
var FINGERPRINT_FIRST_BYTES = 1024;
var EMPTY_FINGERPRINT = '\x00\x00\x00\x00\x00\x00\x00' +
const FINGERPRINT_FIRST_BYTES = 1024;
const EMPTY_FINGERPRINT = '\x00\x00\x00\x00\x00\x00\x00' +
'\x00\x00\x00\x00\x00\x00\x00\x00\x00';
function PDFDocument(pdfManager, arg) {
var stream;
function find(stream, needle, limit, backwards) {
const pos = stream.pos;
const end = stream.end;
if (pos + limit > end) {
limit = end - pos;
}
const strBuf = [];
for (let i = 0; i < limit; ++i) {
strBuf.push(String.fromCharCode(stream.getByte()));
}
const str = strBuf.join('');
stream.pos = pos;
const index = backwards ? str.lastIndexOf(needle) : str.indexOf(needle);
if (index === -1) {
return false;
}
stream.pos += index;
return true;
}
/**
* The `PDFDocument` class holds all the data of the PDF file. There exists
* one `PDFDocument` object on the main thread and one object for each worker.
* If no worker support is enabled, two `PDFDocument` objects are created on
* the main thread.
*/
class PDFDocument {
constructor(pdfManager, arg) {
let stream;
if (isStream(arg)) {
stream = arg;
} else if (isArrayBuffer(arg)) {
@ -357,41 +373,150 @@ var PDFDocument = (function PDFDocumentClosure() {
throw new Error('PDFDocument: Unknown argument type');
}
if (stream.length <= 0) {
throw new Error('PDFDocument: stream must have data');
throw new Error('PDFDocument: Stream must have data');
}
this.pdfManager = pdfManager;
this.stream = stream;
this.xref = new XRef(stream, pdfManager);
let evaluatorOptions = pdfManager.evaluatorOptions;
this.pdfFunctionFactory = new PDFFunctionFactory({
xref: this.xref,
isEvalSupported: evaluatorOptions.isEvalSupported,
isEvalSupported: pdfManager.evaluatorOptions.isEvalSupported,
});
this._pagePromises = [];
}
function find(stream, needle, limit, backwards) {
var pos = stream.pos;
var end = stream.end;
var strBuf = [];
if (pos + limit > end) {
limit = end - pos;
}
for (var n = 0; n < limit; ++n) {
strBuf.push(String.fromCharCode(stream.getByte()));
}
var str = strBuf.join('');
stream.pos = pos;
var index = backwards ? str.lastIndexOf(needle) : str.indexOf(needle);
if (index === -1) {
return false; /* not found */
}
stream.pos += index;
return true; /* found */
parse(recoveryMode) {
this.setup(recoveryMode);
const version = this.catalog.catDict.get('Version');
if (isName(version)) {
this.pdfFormatVersion = version.name;
}
// Check if AcroForms are present in the document.
try {
this.acroForm = this.catalog.catDict.get('AcroForm');
if (this.acroForm) {
this.xfa = this.acroForm.get('XFA');
const fields = this.acroForm.get('Fields');
if ((!fields || !Array.isArray(fields) || fields.length === 0) &&
!this.xfa) {
this.acroForm = null; // No fields and no XFA, so it's not a form.
}
}
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
info('Cannot fetch AcroForm entry; assuming no AcroForms are present');
this.acroForm = null;
}
}
get linearization() {
let linearization = null;
try {
linearization = Linearization.create(this.stream);
} catch (err) {
if (err instanceof MissingDataException) {
throw err;
}
info(err);
}
return shadow(this, 'linearization', linearization);
}
get startXRef() {
const stream = this.stream;
let startXRef = 0;
if (this.linearization) {
// Find the end of the first object.
stream.reset();
if (find(stream, 'endobj', 1024)) {
startXRef = stream.pos + 6;
}
} else {
// Find `startxref` by checking backwards from the end of the file.
const step = 1024;
const startXRefLength = 'startxref'.length;
let found = false, pos = stream.end;
while (!found && pos > 0) {
pos -= step - startXRefLength;
if (pos < 0) {
pos = 0;
}
stream.pos = pos;
found = find(stream, 'startxref', step, true);
}
if (found) {
stream.skip(9);
let ch;
do {
ch = stream.getByte();
} while (isSpace(ch));
let str = '';
while (ch >= 0x20 && ch <= 0x39) { // < '9'
str += String.fromCharCode(ch);
ch = stream.getByte();
}
startXRef = parseInt(str, 10);
if (isNaN(startXRef)) {
startXRef = 0;
}
}
}
return shadow(this, 'startXRef', startXRef);
}
// Find the header, get the PDF format version and setup the
// stream to start from the header.
checkHeader() {
const stream = this.stream;
stream.reset();
if (!find(stream, '%PDF-', 1024)) {
// May not be a PDF file, but don't throw an error and let
// parsing continue.
return;
}
stream.moveStart();
// Read the PDF format version.
const MAX_PDF_VERSION_LENGTH = 12;
let version = '', ch;
while ((ch = stream.getByte()) > 0x20) { // Space
if (version.length >= MAX_PDF_VERSION_LENGTH) {
break;
}
version += String.fromCharCode(ch);
}
if (!this.pdfFormatVersion) {
// Remove the "%PDF-" prefix.
this.pdfFormatVersion = version.substring(5);
}
}
parseStartXRef() {
this.xref.setStartXRef(this.startXRef);
}
setup(recoveryMode) {
this.xref.parse(recoveryMode);
this.catalog = new Catalog(this.pdfManager, this.xref);
}
get numPages() {
const linearization = this.linearization;
const num = linearization ? linearization.numPages : this.catalog.numPages;
return shadow(this, 'numPages', num);
}
get documentInfo() {
const DocumentInfoValidators = {
Title: isString,
Author: isString,
@ -404,136 +529,13 @@ var PDFDocument = (function PDFDocumentClosure() {
Trapped: isName,
};
PDFDocument.prototype = {
parse: function PDFDocument_parse(recoveryMode) {
this.setup(recoveryMode);
var version = this.catalog.catDict.get('Version');
if (isName(version)) {
this.pdfFormatVersion = version.name;
}
try {
// checking if AcroForm is present
this.acroForm = this.catalog.catDict.get('AcroForm');
if (this.acroForm) {
this.xfa = this.acroForm.get('XFA');
var fields = this.acroForm.get('Fields');
if ((!fields || !Array.isArray(fields) || fields.length === 0) &&
!this.xfa) {
// no fields and no XFA -- not a form (?)
this.acroForm = null;
}
}
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
info('Something wrong with AcroForm entry');
this.acroForm = null;
}
},
get linearization() {
let linearization = null;
try {
linearization = Linearization.create(this.stream);
} catch (err) {
if (err instanceof MissingDataException) {
throw err;
}
info(err);
}
// shadow the prototype getter with a data property
return shadow(this, 'linearization', linearization);
},
get startXRef() {
var stream = this.stream;
var startXRef = 0;
var linearization = this.linearization;
if (linearization) {
// Find end of first obj.
stream.reset();
if (find(stream, 'endobj', 1024)) {
startXRef = stream.pos + 6;
}
} else {
// Find startxref by jumping backward from the end of the file.
var step = 1024;
var found = false, pos = stream.end;
while (!found && pos > 0) {
pos -= step - 'startxref'.length;
if (pos < 0) {
pos = 0;
}
stream.pos = pos;
found = find(stream, 'startxref', step, true);
}
if (found) {
stream.skip(9);
var ch;
do {
ch = stream.getByte();
} while (isSpace(ch));
var str = '';
while (ch >= 0x20 && ch <= 0x39) { // < '9'
str += String.fromCharCode(ch);
ch = stream.getByte();
}
startXRef = parseInt(str, 10);
if (isNaN(startXRef)) {
startXRef = 0;
}
}
}
// shadow the prototype getter with a data property
return shadow(this, 'startXRef', startXRef);
},
// Find the header, remove leading garbage and setup the stream
// starting from the header.
checkHeader: function PDFDocument_checkHeader() {
var stream = this.stream;
stream.reset();
if (find(stream, '%PDF-', 1024)) {
// Found the header, trim off any garbage before it.
stream.moveStart();
// Reading file format version
var MAX_VERSION_LENGTH = 12;
var version = '', ch;
while ((ch = stream.getByte()) > 0x20) { // SPACE
if (version.length >= MAX_VERSION_LENGTH) {
break;
}
version += String.fromCharCode(ch);
}
if (!this.pdfFormatVersion) {
// removing "%PDF-"-prefix
this.pdfFormatVersion = version.substring(5);
}
return;
}
// May not be a PDF file, continue anyway.
},
parseStartXRef: function PDFDocument_parseStartXRef() {
var startXRef = this.startXRef;
this.xref.setStartXRef(startXRef);
},
setup: function PDFDocument_setup(recoveryMode) {
this.xref.parse(recoveryMode);
this.catalog = new Catalog(this.pdfManager, this.xref);
},
get numPages() {
var linearization = this.linearization;
var num = linearization ? linearization.numPages : this.catalog.numPages;
// shadow the prototype getter
return shadow(this, 'numPages', num);
},
get documentInfo() {
const docInfo = {
PDFFormatVersion: this.pdfFormatVersion,
IsLinearized: !!this.linearization,
IsAcroFormPresent: !!this.acroForm,
IsXFAPresent: !!this.xfa,
};
let infoDict;
try {
infoDict = this.xref.trailer.get('Info');
@ -543,10 +545,11 @@ var PDFDocument = (function PDFDocumentClosure() {
}
info('The document information dictionary is invalid.');
}
if (isDict(infoDict)) {
// Fill the document info with valid entries from the specification,
// as well as any existing well-formed custom entries.
for (let key of infoDict.getKeys()) {
for (const key of infoDict.getKeys()) {
const value = infoDict.get(key);
if (DocumentInfoValidators[key]) {
@ -579,11 +582,11 @@ var PDFDocument = (function PDFDocumentClosure() {
}
}
return shadow(this, 'documentInfo', docInfo);
},
get fingerprint() {
var xref = this.xref, hash, fileID = '';
var idArray = xref.trailer.get('ID');
}
get fingerprint() {
let hash;
const idArray = this.xref.trailer.get('ID');
if (Array.isArray(idArray) && idArray[0] && isString(idArray[0]) &&
idArray[0] !== EMPTY_FINGERPRINT) {
hash = stringToBytes(idArray[0]);
@ -596,13 +599,13 @@ var PDFDocument = (function PDFDocumentClosure() {
FINGERPRINT_FIRST_BYTES), 0, FINGERPRINT_FIRST_BYTES);
}
for (var i = 0, n = hash.length; i < n; i++) {
var hex = hash[i].toString(16);
fileID += hex.length === 1 ? '0' + hex : hex;
let fingerprint = '';
for (const hashPart of hash) {
const hex = hashPart.toString(16);
fingerprint += (hex.length === 1 ? '0' + hex : hex);
}
return shadow(this, 'fingerprint', fingerprint);
}
return shadow(this, 'fingerprint', fileID);
},
_getLinearizationPage(pageIndex) {
const { catalog, linearization, } = this;
@ -624,7 +627,7 @@ var PDFDocument = (function PDFDocumentClosure() {
info(reason);
return catalog.getPageDict(pageIndex);
});
},
}
getPage(pageIndex) {
if (this._pagePromises[pageIndex] !== undefined) {
@ -647,7 +650,7 @@ var PDFDocument = (function PDFDocumentClosure() {
pdfFunctionFactory: this.pdfFunctionFactory,
});
});
},
}
checkFirstPage() {
return this.getPage(0).catch((reason) => {
@ -661,15 +664,12 @@ var PDFDocument = (function PDFDocumentClosure() {
throw new XRefParseException();
}
});
},
}
cleanup: function PDFDocument_cleanup() {
cleanup() {
return this.catalog.cleanup();
},
};
return PDFDocument;
})();
}
}
export {
Page,