Convert the PDFDocument class in src/core/document.js to ES6 syntax
This commit is contained in:
Tim van der Meij
parent
612fc9fcc2
commit
d5e5d18430
@ -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,
|
||||
|
||||
@ -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,
|
||||
@ -329,20 +330,41 @@ class 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)) {
|
||||
@ -351,41 +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,
|
||||
@ -398,136 +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');
|
||||
@ -537,10 +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]) {
|
||||
@ -573,11 +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]);
|
||||
@ -590,13 +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;
|
||||
@ -618,7 +627,7 @@ var PDFDocument = (function PDFDocumentClosure() {
|
||||
info(reason);
|
||||
return catalog.getPageDict(pageIndex);
|
||||
});
|
||||
},
|
||||
}
|
||||
|
||||
getPage(pageIndex) {
|
||||
if (this._pagePromises[pageIndex] !== undefined) {
|
||||
@ -641,7 +650,7 @@ var PDFDocument = (function PDFDocumentClosure() {
|
||||
pdfFunctionFactory: this.pdfFunctionFactory,
|
||||
});
|
||||
});
|
||||
},
|
||||
}
|
||||
|
||||
checkFirstPage() {
|
||||
return this.getPage(0).catch((reason) => {
|
||||
@ -655,15 +664,12 @@ var PDFDocument = (function PDFDocumentClosure() {
|
||||
throw new XRefParseException();
|
||||
}
|
||||
});
|
||||
},
|
||||
}
|
||||
|
||||
cleanup: function PDFDocument_cleanup() {
|
||||
cleanup() {
|
||||
return this.catalog.cleanup();
|
||||
},
|
||||
};
|
||||
|
||||
return PDFDocument;
|
||||
})();
|
||||
}
|
||||
}
|
||||
|
||||
export {
|
||||
Page,
|
||||
|
||||
Loading…
Reference in New Issue
Block a user