Initial commit

.gitignore

@@ -0,0 +1 @@
+node_modules

.npmignore

@@ -0,0 +1 @@
+test/

index.js

@@ -0,0 +1,37 @@
+var _ = require('lodash')
+var Parser = require('pdf2json')
+
+//clear the pdf logger
+require('util')._logN = function() { }
+
+//given a path to a pdf
+//turn it into a json structure
+module.exports = function(path, cb) {
+  var parser = new Parser()
+  parser.on('pdfParser_dataReady', function(result) {
+
+    //attach some handy methods to the result object
+
+    //get text on a particular page
+    result.data.Pages.forEach(function(page) {
+      page.getText = function() {
+        return _(page.Texts).map('R').flatten().map('T').map(decodeURIComponent).value()
+      }
+    })
+
+    //get text from a page by page number (0 indexed)
+    result.getTextOnPage = function(number) {
+      return result.data.Pages[number].getText()
+    }
+
+    //get all text in document
+    result.getText = function() {
+      return _(this.data.Pages).map(function(p) { return p.getText() }).flatten().value()
+    }
+
+    return cb(null, result.getText(), result)
+  })
+
+  parser.on('pdfParser_dataError', cb)
+  parser.loadPDF(path)
+}

package.json

@@ -0,0 +1,30 @@
+{
+  "name": "pdf-text",
+  "version": "0.0.0",
+  "description": "Extract an array of text chunks from a pdf",
+  "main": "index.js",
+  "scripts": {
+    "test": "mocha"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git://github.com/brianc/node-pdf-text.git"
+  },
+  "keywords": [
+    "pdf",
+    "text"
+  ],
+  "author": "Brian M. Carlson",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/brianc/node-pdf-text/issues"
+  },
+  "devDependencies": {
+    "mocha": "~1.14.0",
+    "okay": "~0.3.0"
+  },
+  "dependencies": {
+    "pdf2json": "~0.5.6",
+    "lodash": "~2.3.0"
+  }
+}

test/index.js

@@ -0,0 +1,34 @@
+var ok = require('okay')
+var pdfText = require('../')
+var assert = require('assert')
+
+describe('pdf-text', function() {
+  before(function(done) {
+    self = this
+    pdfText(__dirname + '/w4.pdf', ok(done, function(text, res) {
+      self.text = text
+      self.result = res
+      done()
+    }))
+  })
+
+  it('returns array of text', function() {
+    assert(require('util').isArray(this.text))
+  })
+
+  it('returns the pdf document', function() {
+    assert(this.result)
+    assert.equal(this.text.length, self.result.getText().length)
+  })
+
+  it('returns correct text', function() {
+    assert.equal(this.text.indexOf('Form W-4 (2013)'), 0)
+    assert(this.text.indexOf('Additional amount, if any, you want withheld from each paycheck'))
+    assert(this.text.indexOf('See the instructions for your income tax return.'))
+  })
+
+  it('returns correct results per page', function() {
+    assert.equal(this.result.getTextOnPage(0).indexOf('Additional amount, if any, you want withheld from each paycheck'), -1)
+    assert(this.result.getTextOnPage(1).indexOf('See the instructions for your income tax return.'))
+  })
+})