docsplit 0.7.2 → 0.7.3

checksums.yaml

@@ -0,0 +1,7 @@
+--- 
+SHA512: 
+  data.tar.gz: e50c360ba40c1aa51cd563d9a08d0c5a444b50c4e97635133aec13f17fcc4e541e20d2bb9867ca316486df9a501852ed482801bed26986e88dbc472bd2609d65
+  metadata.gz: 5da217d234a3b390963f2c6259ab859ecf805d71c60138c335eebdd9ae4c166cce63e825cee2e10c7e3029c47e4530e53b2d84dbdc91ab222c0a98c6f342d32a
+SHA1: 
+  data.tar.gz: 03c2ec2439773679080a055463d35e7004d1decf
+  metadata.gz: ddd8d4475b4a34fcfd2abb013d2824295718aa8c

data/LICENSE

@@ -1,6 +1,7 @@
 JODConverter ius licensed under the LGPL: gnu.org/licenses/lgpl.html
 
-Copyright (c) 2009 Jeremy Ashkenas, DocumentCloud
+Copyright (c) 2009-2011 Jeremy Ashkenas, DocumentCloud
+Copyright (c) 2011-2013 Jeremy Ashkenas, DocumentCloud and Investigative Reporters & Editors
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.7.2'         # Keep version in sync with docsplit.rb
-  s.date      = '2013-02-21'
+  s.version   = '0.7.3'         # Keep version in sync with docsplit.rb
+  s.date      = '2014-02-16'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"
@@ -15,6 +15,7 @@ Gem::Specification.new do |s|
   s.authors           = ['Jeremy Ashkenas', 'Samuel Clay', 'Ted Han']
   s.email             = 'opensource@documentcloud.org'
   s.rubyforge_project = 'docsplit'
+  s.license           = 'MIT'
 
   s.require_paths     = ['lib']
   s.executables       = ['docsplit']

data/lib/docsplit.rb

@@ -5,7 +5,7 @@ require 'shellwords'
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.7.2' # Keep in sync with gemspec.
+  VERSION       = '0.7.3' # Keep in sync with gemspec.
 
   ESCAPE        = lambda {|x| Shellwords.shellescape(x) }
 

data/lib/docsplit/command_line.rb

@@ -96,6 +96,7 @@ Options:
         end
         opts.on('-l', '--language [LANGUAGE]', 'set the language (ISO 639-2/T code) for text extraction') do |l|
           @options[:language] = l
+          @options[:clean] = false
         end
         opts.on('-r', '--rolling', 'generate images from each previous image') do |r|
           @options[:rolling] = true

data/lib/docsplit/info_extractor.rb

@@ -27,7 +27,7 @@ module Docsplit
       raise ExtractionFailed, result if $? != 0
       # ruby  1.8 (iconv) and 1.9 (String#encode) :
       if String.method_defined?(:encode)
-        result.encode!('UTF-8', 'UTF-8', :invalid => :replace)
+        result.encode!('UTF-8', 'binary', :invalid => :replace, :undef => :replace, :replace => "") unless result.valid_encoding?
       else
         require 'iconv' unless defined?(Iconv)
         ic = Iconv.new('UTF-8//IGNORE','UTF-8')

data/lib/docsplit/pdf_extractor.rb

@@ -19,7 +19,12 @@ module Docsplit
     # The first line of the help output holds the name and version number
     # of the office software to be used for extraction.
     def version_string
-      @@help ||= `#{office_executable} -h 2>&1`.split("\n").first
+      versionstr =  `#{office_executable} -h 2>&1`.split("\n").first
+        if !!versionstr.match(/[0-9]*/)
+                versionstr =  `#{office_executable} --version`.split("\n").first
+        end
+        @@help ||= versionstr
+
     end
     def libre_office?
       !!version_string.match(/^LibreOffice/)
@@ -37,7 +42,7 @@ module Docsplit
       if windows?
         office_names       = ["LibreOffice 3", "LibreOffice 4", "OpenOffice.org 3"]
         program_files_path = ENV["CommonProgramFiles"]
-        search_paths       = office_name.map{ |program| File.join(program_files_path, program) }
+        search_paths       = office_names.map{ |program| File.join(program_files_path, program) }
       elsif osx?
         search_paths = %w(
           /Applications/LibreOffice.app/Contents
@@ -46,8 +51,10 @@ module Docsplit
       else # probably linux/unix
         search_paths = %w(
           /usr/lib/libreoffice
+          /usr/lib64/libreoffice
           /opt/libreoffice
           /usr/lib/openoffice
+          /usr/lib64/openoffice
           /opt/openoffice.org3
         )
       end

data/lib/docsplit/text_cleaner.rb

@@ -35,8 +35,13 @@ module Docsplit
     # For the time being, `clean` uses the regular StringScanner, and not the
     # multibyte-aware version, coercing to ASCII first.
     def clean(text)
-      require 'iconv' unless defined?(Iconv)
-      text    = Iconv.iconv('ascii//translit//ignore', 'utf-8', text).first
+      if String.method_defined?(:encode)
+        text.encode!('ascii', :invalid => :replace, :undef => :replace, :replace => '?')
+      else
+        require 'iconv' unless defined?(Iconv)
+        text = Iconv.iconv('ascii//translit//ignore', 'utf-8', text).first
+      end
+
       scanner = StringScanner.new(text)
       cleaned = []
       spaced  = false

metadata

@@ -1,28 +1,28 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: docsplit
-version: !ruby/object:Gem::Version
-  version: 0.7.2
-  prerelease: 
+version: !ruby/object:Gem::Version 
+  version: 0.7.3
 platform: ruby
-authors:
+authors: 
 - Jeremy Ashkenas
 - Samuel Clay
 - Ted Han
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-02-21 00:00:00.000000000 Z
+
+date: 2014-02-16 00:00:00 Z
 dependencies: []
-description: ! "    Docsplit is a command-line utility and Ruby library for splitting
-  apart\n    documents into their component parts: searchable UTF-8 plain text, page\n
-  \   images or thumbnails in any format, PDFs, single pages, and document\n    metadata
-  (title, author, number of pages...)\n"
+
+description: "    Docsplit is a command-line utility and Ruby library for splitting apart\n    documents into their component parts: searchable UTF-8 plain text, page\n    images or thumbnails in any format, PDFs, single pages, and document\n    metadata (title, author, number of pages...)\n"
 email: opensource@documentcloud.org
-executables:
+executables: 
 - docsplit
 extensions: []
+
 extra_rdoc_files: []
-files:
+
+files: 
 - lib/docsplit/command_line.rb
 - lib/docsplit/image_extractor.rb
 - lib/docsplit/info_extractor.rb
@@ -47,28 +47,30 @@ files:
 - LICENSE
 - README
 homepage: http://documentcloud.github.com/docsplit/
-licenses: []
+licenses: 
+- MIT
+metadata: {}
+
 post_install_message: 
 rdoc_options: []
-require_paths:
+
+require_paths: 
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - &id001 
+    - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - *id001
 requirements: []
+
 rubyforge_project: docsplit
-rubygems_version: 1.8.24
+rubygems_version: 2.0.13
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Break Apart Documents into Images, Text, Pages and PDFs
 test_files: []
-has_rdoc: 
+