docsplit 0.5.0 → 0.5.1

data/docsplit.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name      = 'docsplit'
-  s.version   = '0.5.0'         # Keep version in sync with docsplit.rb
-  s.date      = '2010-10-18'
+  s.version   = '0.5.1'         # Keep version in sync with docsplit.rb
+  s.date      = '2010-04-26'
 
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"

data/lib/docsplit.rb

@@ -1,7 +1,7 @@
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.5.0' # Keep in sync with gemspec.
+  VERSION       = '0.5.1' # Keep in sync with gemspec.
 
   ROOT          = File.expand_path(File.dirname(__FILE__) + '/..')
 

data/lib/docsplit/text_cleaner.rb

@@ -24,12 +24,12 @@ module Docsplit
     REPEAT      = /([^0-9])\1{2,}/
     UPPER       = /[A-Z]/
     LOWER       = /[a-z]/
-    ACRONYM     = /^\(?[A-Z0-9\.]+('?s)?\)?[.,:]?$/
+    ACRONYM     = /^\(?[A-Z0-9\.-]+('?s)?\)?[.,:]?$/
     ALL_ALPHA   = /^[a-z]+$/i
     CONSONANT   = /(^y|[bcdfghjklmnpqrstvwxz])/i
     VOWEL       = /([aeiou]|y$)/i
     CONSONANT_5 = /[bcdfghjklmnpqrstvwxyz]{5}/i
-    VOWEL_4     = /[aeiou]{4}/i
+    VOWEL_5     = /[aeiou]{5}/i
     REPEATED    = /(\b\S{1,2}\s+)(\S{1,3}\s+){5,}(\S{1,2}\s+)/
     SINGLETONS  = /^[AaIi]$/
 
@@ -73,7 +73,7 @@ module Docsplit
       (w[1...-1].scan(PUNCT).uniq.length >= 3) ||
 
       # Four or more consecutive vowels, or five or more consecutive consonants.
-      ((w =~ VOWEL_4) || (w =~ CONSONANT_5)) ||
+      ((w =~ VOWEL_5) || (w =~ CONSONANT_5)) ||
 
       # Number of uppercase letters greater than lowercase letters, but the word is
       # not all uppercase + punctuation.

data/lib/docsplit/text_extractor.rb

@@ -64,7 +64,7 @@ module Docsplit
           tiff = "#{tempdir}/#{@pdf_name}_#{page}.tif"
           file = "#{base_path}_#{page}"
           run "MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm convert +adjoin #{MEMORY_ARGS} #{OCR_FLAGS} #{pdf}[#{page - 1}] #{tiff} 2>&1"
-          run "tesseract #{tiff} #{file} 2>&1"
+          run "tesseract #{tiff} #{file} -l eng 2>&1"
           clean_text(file + '.txt') if @clean_ocr
           FileUtils.remove_entry_secure tiff
         end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: docsplit
 version: !ruby/object:Gem::Version 
-  hash: 11
-  prerelease: false
+  hash: 9
+  prerelease: 
   segments: 
   - 0
   - 5
-  - 0
-  version: 0.5.0
+  - 1
+  version: 0.5.1
 platform: ruby
 authors: 
 - Jeremy Ashkenas
@@ -16,8 +16,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-10-18 00:00:00 -04:00
-default_executable: 
+date: 2010-04-26 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"
@@ -51,7 +50,6 @@ files:
 - docsplit.gemspec
 - LICENSE
 - README
-has_rdoc: false
 homepage: http://documentcloud.github.com/docsplit/
 licenses: []
 
@@ -81,7 +79,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: docsplit
-rubygems_version: 1.3.7
+rubygems_version: 1.7.2
 signing_key: 
 specification_version: 3
 summary: Break Apart Documents into Images, Text, Pages and PDFs