textractor 0.1.4 → 0.1.5

data/.rspec

@@ -0,0 +1 @@
+-c -f progress -r ./spec/spec_helper

data/Gemfile.lock

@@ -6,12 +6,20 @@ PATH
 GEM
   remote: http://rubygems.org/
   specs:
-    rspec (1.3.0)
+    diff-lcs (1.1.2)
+    rspec (2.1.0)
+      rspec-core (~> 2.1.0)
+      rspec-expectations (~> 2.1.0)
+      rspec-mocks (~> 2.1.0)
+    rspec-core (2.1.0)
+    rspec-expectations (2.1.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.1.0)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
   bundler (>= 1.0.0)
-  rspec (~> 1.3.0)
+  rspec (~> 2.1.0)
   textractor!

data/README.md

@@ -10,6 +10,18 @@ In order to use textractor you have to install a few command line tools.
 
 ### OS X
 
+#### Homebrew
+
+    brew install xpdf links
+
+Download wv-1.2.4 and install from source: http://sourceforge.net/projects/wvware/files/wv/1.2.4/wv-1.2.4.tar.gz/download
+
+    ./configure
+    make
+    make install
+
+#### MacPorts
+
     port install wv xpdf links
 
 I recommend using also passing +no_x11 to the install command, but this may not work on all systems due to dependency issues.

data/Rakefile

@@ -1,16 +1,16 @@
 require 'bundler'
 Bundler::GemHelper.install_tasks
 
-require 'spec/rake/spectask'
-Spec::Rake::SpecTask.new(:spec) do |spec|
-  spec.libs << 'lib' << 'spec'
-  spec.spec_files = FileList['spec/**/*_spec.rb']
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec) do |task|
+  task.rspec_opts = ["-c", "-f progress", "-r ./spec/spec_helper.rb"]
+  task.pattern = 'spec/**/*_spec.rb'
 end
 
-Spec::Rake::SpecTask.new(:rcov) do |spec|
-  spec.libs << 'lib' << 'spec'
-  spec.pattern = 'spec/**/*_spec.rb'
-  spec.rcov = true
+RSpec::Core::RakeTask.new(:rcov) do |task|
+  task.pattern = 'spec/**/*_spec.rb'
+  task.rcov = true
 end
 
 task :default => :spec

data/autotest/discover.rb

@@ -0,0 +1 @@
+Autotest.add_discovery { "rspec2" }

data/lib/textractor/extractors/doc_extractor.rb

@@ -13,7 +13,7 @@ module Textractor::Extractors
     end
 
     def text_from_path(path)
-      command = "wvWare -c utf-8 --nographics -x #{wvText_path} #{path}"
+      command = "wvWare -c utf-8 --nographics -x #{wvText_path} '#{path}'"
       puts command if $DEBUG
       `#{command}`.strip
     end

data/lib/textractor/extractors/docx_extractor.rb

@@ -14,7 +14,7 @@ module Textractor::Extractors
 
 
     def text_from_path(path)
-      `#{docx2txt_path} #{path} -`.strip
+      `#{docx2txt_path} '#{path}' -`.strip
     end
 
     private

data/lib/textractor/extractors/pdf_extractor.rb

@@ -3,7 +3,7 @@ module Textractor::Extractors
   class PDFExtractor
 
     def text_from_path(path)
-      `pdftotext #{path} - 2>/dev/null`.strip
+      `pdftotext '#{path}' - 2>/dev/null`.strip
     end
 
   end

data/lib/textractor/version.rb

@@ -1,3 +1,3 @@
 module Textractor
-  VERSION = '0.1.4'
+  VERSION = '0.1.5'
 end

data/spec/fixtures/document .txt

@@ -0,0 +1 @@
+text

data/spec/integration/textractor_spec.rb

@@ -55,4 +55,20 @@ describe Textractor do
     }.to raise_error(Textractor::ContentTypeNotRegistered)
   end
 
+  it 'returns the contents of doc files with a space in the path' do
+    Textractor.text_from_path(fixture_path("document .doc")).should == 'text'
+  end
+
+  it 'returns the contents of docx files with a space in the path' do
+    Textractor.text_from_path(fixture_path("document .docx")).should == 'text'
+  end
+
+  it 'returns the contents of pdf files with a space in the path' do
+    Textractor.text_from_path(fixture_path("document .pdf")).should == 'text'
+  end
+
+  it 'returns the contents of txt files with a space in the path' do
+    Textractor.text_from_path(fixture_path("document .txt")).should == 'text'
+  end
+
 end

data/spec/spec_helper.rb

@@ -1,15 +1,14 @@
-require 'rubygems'
-require 'bundler/setup'
-require 'spec'
-
 $LOAD_PATH.unshift(File.dirname(__FILE__))
 
+require 'rubygems'
+require 'bundler/setup'
+require 'rspec'
 require 'textractor'
 
 def fixture_path(path)
   File.expand_path(File.join(File.dirname(__FILE__), 'fixtures', path))
 end
 
-Spec::Runner.configure do |config|
+RSpec.configure do |config|
 
 end

data/spec/textractor_spec.rb

@@ -1,4 +1,4 @@
-require 'spec/spec_helper'
+require 'spec_helper'
 
 class TestExtractor
 

data/textractor.gemspec

@@ -1,4 +1,3 @@
-# -*- encoding: utf-8 -*-
 require File.expand_path("../lib/textractor/version", __FILE__)
 
 Gem::Specification.new do |s|
@@ -15,7 +14,7 @@ Gem::Specification.new do |s|
   s.rubyforge_project         = "textractor"
 
   s.add_development_dependency "bundler", ">= 1.0.0"
-  s.add_development_dependency "rspec",   "~> 1.3.0"
+  s.add_development_dependency "rspec",   "~> 2.1.0"
 
   s.files        = `git ls-files`.split("\n")
   s.executables  = `git ls-files`.split("\n").map{|f| f =~ /^bin\/(.*)/ ? $1 : nil}.compact

data/vendor/docx2txt/docx2txt.pl

@@ -228,7 +228,9 @@ if ($ENV{OS} =~ /^Windows/) {
 if ($inpIsDir eq 'y') {
     readFileInto("$ARGV[0]/word/document.xml", $content);
 } else {
-    $content = `"$unzip" -p "$ARGV[0]" word/document.xml 2>$nulldevice`;
+    # Special fix for single quotes, they get un-escaped earlier
+    $ARGV[0] =~ s/\'/\'\\\'\'/g;
+    $content = `"$unzip" -p '$ARGV[0]' word/document.xml 2>$nulldevice`;
 }
 
 die "Failed to extract required information from <$ARGV[0]>!\n" if ! $content;
@@ -260,7 +262,7 @@ binmode $txtfile;    # Ensure no auto-conversion of '\n' to '\r\n' on Windows.
 if ($inpIsDir eq 'y') {
     readFileInto("$ARGV[0]/word/_rels/document.xml.rels", $_);
 } else {
-    $_ = `"$unzip" -p "$ARGV[0]" word/_rels/document.xml.rels 2>$nulldevice`;
+    $_ = `"$unzip" -p '$ARGV[0]' word/_rels/document.xml.rels 2>$nulldevice`;
 }
 
 my %docurels;

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: textractor
 version: !ruby/object:Gem::Version 
-  hash: 19
-  prerelease: false
+  hash: 17
+  prerelease: 
   segments: 
   - 0
   - 1
-  - 4
-  version: 0.1.4
+  - 5
+  version: 0.1.5
 platform: ruby
 authors: 
 - Michael Guterl
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-11-06 00:00:00 -04:00
+date: 2011-07-20 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -42,12 +42,12 @@ dependencies:
     requirements: 
     - - ~>
       - !ruby/object:Gem::Version 
-        hash: 27
+        hash: 11
         segments: 
+        - 2
         - 1
-        - 3
         - 0
-        version: 1.3.0
+        version: 2.1.0
   type: :development
   version_requirements: *id002
 description: simple wrapper around CLI for extracting text from PDF and Word documents
@@ -63,11 +63,13 @@ extra_rdoc_files:
 files: 
 - .document
 - .gitignore
+- .rspec
 - Gemfile
 - Gemfile.lock
 - LICENSE
 - README.md
 - Rakefile
+- autotest/discover.rb
 - bin/textractor
 - lib/textractor.rb
 - lib/textractor/content_type_detector.rb
@@ -79,13 +81,16 @@ files:
 - lib/textractor/extractors/pdf_extractor.rb
 - lib/textractor/extractors/text_extractor.rb
 - lib/textractor/version.rb
+- spec/fixtures/document .doc
+- spec/fixtures/document .docx
+- spec/fixtures/document .pdf
+- spec/fixtures/document .txt
 - spec/fixtures/document.doc
 - spec/fixtures/document.docx
 - spec/fixtures/document.pdf
 - spec/fixtures/document.txt
 - spec/fixtures/no_extension
 - spec/integration/textractor_spec.rb
-- spec/spec.opts
 - spec/spec_helper.rb
 - spec/textractor_spec.rb
 - support/wvText.xml
@@ -137,7 +142,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: textractor
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: simple wrapper around CLI for extracting text from PDF and Word documents

data/spec/spec.opts

@@ -1 +0,0 @@
---color