2 changed files with 183 additions and 0 deletions
@ -0,0 +1,107 @@
@@ -0,0 +1,107 @@
|
||||
/* -*- Mode: Java; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */ |
||||
/* vim: set shiftwidth=2 tabstop=2 autoindent cindent expandtab: */ |
||||
/* Any copyright is dedicated to the Public Domain. |
||||
* http://creativecommons.org/publicdomain/zero/1.0/ */
|
||||
|
||||
// Dummy XML Parser
|
||||
|
||||
function DOMNodeMock(nodeName, nodeValue) { |
||||
this.nodeName = nodeName; |
||||
this.nodeValue = nodeValue; |
||||
Object.defineProperty(this, 'parentNode', {value: null, writable: true}); |
||||
} |
||||
DOMNodeMock.prototype = { |
||||
get firstChild() { |
||||
return this.childNodes[0]; |
||||
}, |
||||
get nextSibling() { |
||||
var index = this.parentNode.childNodes.indexOf(this); |
||||
return this.parentNode.childNodes[index + 1]; |
||||
}, |
||||
get textContent() { |
||||
if (!this.childNodes) { |
||||
return this.nodeValue || ''; |
||||
} |
||||
return this.childNodes.map(function (child) { |
||||
return child.textContent; |
||||
}).join(''); |
||||
}, |
||||
hasChildNodes: function () { |
||||
return this.childNodes && this.childNodes.length > 0; |
||||
} |
||||
}; |
||||
|
||||
function decodeXML(text) { |
||||
if (text.indexOf('&') < 0) { |
||||
return text; |
||||
} |
||||
return text.replace(/&(#(x[0-9a-f]+|\d+)|\w+);/gi, function (all, entityName, number) { |
||||
if (number) { |
||||
return String.fromCharCode(number[0] === 'x' ? parseInt(number.substring(1), 16) : +number); |
||||
} |
||||
switch (entityName) { |
||||
case 'amp': |
||||
return '&'; |
||||
case 'lt': |
||||
return '<'; |
||||
case 'gt': |
||||
return '>'; |
||||
case 'quot': |
||||
return '\"'; |
||||
case 'apos': |
||||
return '\''; |
||||
} |
||||
return '&' + entityName + ';'; |
||||
}); |
||||
} |
||||
|
||||
function DOMParserMock() {}; |
||||
DOMParserMock.prototype = { |
||||
parseFromString: function (content) { |
||||
content = content.replace(/<\?[\s\S]*?\?>|<!--[\s\S]*?-->/g, '').trim(); |
||||
var nodes = []; |
||||
content = content.replace(/>([\s\S]+?)</g, function (all, text) { |
||||
var i = nodes.length; |
||||
var node = new DOMNodeMock('#text', decodeXML(text)); |
||||
nodes.push(node); |
||||
if (node.textContent.trim().length === 0) { |
||||
return '><'; // ignoring whitespaces
|
||||
} |
||||
return '>' + i + ',<'; |
||||
}); |
||||
content = content.replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, function (all, text) { |
||||
var i = nodes.length; |
||||
var node = new DOMNodeMock('#text', text); |
||||
nodes.push(node); |
||||
return i + ','; |
||||
}); |
||||
var lastLength; |
||||
do { |
||||
lastLength = nodes.length; |
||||
content = content.replace(/<([\w\:]+)((?:[\s\w:=]|'[^']*'|"[^"]*")*)(?:\/>|>([\d,]*)<\/[^>]+>)/g, |
||||
function (all, name, attrs, content) { |
||||
var i = nodes.length; |
||||
var node = new DOMNodeMock(name); |
||||
var children = []; |
||||
if (content) { |
||||
content = content.split(','); |
||||
content.pop(); |
||||
content.forEach(function (child) { |
||||
var childNode = nodes[+child]; |
||||
childNode.parentNode = node; |
||||
children.push(childNode); |
||||
}) |
||||
} |
||||
node.childNodes = children; |
||||
nodes.push(node); |
||||
return i + ','; |
||||
|
||||
}); |
||||
} while(lastLength < nodes.length); |
||||
return { |
||||
documentElement: nodes.pop() |
||||
}; |
||||
} |
||||
}; |
||||
|
||||
exports.DOMParserMock = DOMParserMock; |
@ -0,0 +1,76 @@
@@ -0,0 +1,76 @@
|
||||
/* -*- Mode: Java; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */ |
||||
/* vim: set shiftwidth=2 tabstop=2 autoindent cindent expandtab: */ |
||||
/* Any copyright is dedicated to the Public Domain. |
||||
* http://creativecommons.org/publicdomain/zero/1.0/ */
|
||||
|
||||
//
|
||||
// Basic node example that prints document metadata and text content.
|
||||
// Requires single file built version of PDF.js -- please run
|
||||
// `node make singlefile` before running the example.
|
||||
//
|
||||
|
||||
var fs = require('fs'); |
||||
|
||||
// HACK few hacks to let PDF.js be loaded not as a module in global space.
|
||||
global.window = global; |
||||
global.navigator = { userAgent: "node" }; |
||||
global.PDFJS = {}; |
||||
global.DOMParser = require('./domparsermock.js').DOMParserMock; |
||||
|
||||
require('../../build/singlefile/build/pdf.combined.js'); |
||||
|
||||
// Loading file from file system into typed array
|
||||
var pdfPath = process.argv[2] || '../../web/compressed.tracemonkey-pldi-09.pdf'; |
||||
var data = new Uint8Array(fs.readFileSync(pdfPath)); |
||||
|
||||
// Will be using promises to load document, pages and misc data instead of
|
||||
// callback.
|
||||
PDFJS.getDocument(data).then(function (doc) { |
||||
var numPages = doc.numPages; |
||||
console.log('# Document Loaded'); |
||||
console.log('Number of Pages: ' + numPages); |
||||
console.log(); |
||||
|
||||
var lastPromise; // will be used to chain promises
|
||||
lastPromise = doc.getMetadata().then(function (data) { |
||||
console.log('# Metadata Is Loaded'); |
||||
console.log('## Info'); |
||||
console.log(JSON.stringify(data.info, null, 2)); |
||||
console.log(); |
||||
if (data.metadata) { |
||||
console.log('## Metadata'); |
||||
console.log(JSON.stringify(data.metadata.metadata, null, 2)); |
||||
console.log(); |
||||
} |
||||
}); |
||||
|
||||
var loadPage = function (pageNum) { |
||||
return doc.getPage(pageNum).then(function (page) { |
||||
console.log('# Page ' + pageNum); |
||||
var viewport = page.getViewport(1.0 /* scale */); |
||||
console.log('Size: ' + viewport.width + 'x' + viewport.height); |
||||
console.log(); |
||||
return page.getTextContent().then(function (content) { |
||||
// Content contains lots of information about the text layout and
|
||||
// styles, but we need only strings at the moment
|
||||
var strings = content.items.map(function (item) { |
||||
return item.str; |
||||
}); |
||||
console.log('## Text Content'); |
||||
console.log(strings.join(' ')); |
||||
}).then(function () { |
||||
console.log(); |
||||
}); |
||||
}) |
||||
}; |
||||
// Loading of the first page will wait on metadata and subsequent loadings
|
||||
// will wait on the previous pages.
|
||||
for (var i = 1; i <= numPages; i++) { |
||||
lastPromise = lastPromise.then(loadPage.bind(null, i)); |
||||
} |
||||
return lastPromise; |
||||
}).then(function () { |
||||
console.log('# End of Document'); |
||||
}, function (err) { |
||||
console.error('Error: ' + err); |
||||
}); |
Loading…
Reference in new issue