burisu-docsplit 0.7.6 → 0.7.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6e8e83657d34d345bf2187c4d97f62a68dbc9f67
-  data.tar.gz: 6235ba1a2fc9a737f7df72dfd4aa57afb8b416ad
+  metadata.gz: 370a33126963926b13bef202fb15e05127a02db0
+  data.tar.gz: 76024f613e3ad9a339cc207ac428037c4ba6f7ef
 SHA512:
-  metadata.gz: b669fbd7c68f94b0451cbb5753f83aaa7ef77d13247bb696e0222467310600b91b5a7ac1255a512873b79c5c78c5a21f3f5006a1b6b34626021cdca34f360fc4
-  data.tar.gz: b2f80cca13a78498c2742bc6ce14f2c778485f5c514600c37a43119901fba503a6fcc00dcc55d687b8fbecc4a9b4f1754ed8e95372e2e46576c8a1fb166648e6
+  metadata.gz: d3564ec6ea484e25fd09f8e3b135bdbfb31c02ed64e74f5f3f269c38fbd58ab9f2c0d63cf9387cedd7eb10549832d583819f2caf09e9d2c2b3316da1c31243e4
+  data.tar.gz: 6a88a1820ab2bf23a0dacab2d54d5949de9bee18d1ba2bda86ce67948dfec97f2dee8dd3195a01033199d2e0b5c28b8e530c7d493aaafa910d2781af82371ee8

data/docsplit.gemspec

@@ -1,7 +1,6 @@
 Gem::Specification.new do |s|
   s.name      = 'burisu-docsplit'
-  s.version   = '0.7.6'         # Keep version in sync with docsplit.rb
-
+  s.version   = '0.7.7'         # Keep version in sync with docsplit.rb
   s.homepage    = "http://documentcloud.github.com/docsplit/"
   s.summary     = "Break Apart Documents into Images, Text, Pages and PDFs"
   s.description = <<-EOS

data/lib/docsplit.rb

@@ -5,7 +5,7 @@ require 'shellwords'
 # The Docsplit module delegates to the Java PDF extractors.
 module Docsplit
 
-  VERSION       = '0.7.4' # Keep in sync with gemspec.
+  VERSION       = '0.7.5' # Keep in sync with gemspec.
 
   ESCAPE        = lambda {|x| Shellwords.shellescape(x) }
 

data/lib/docsplit/page_extractor.rb

@@ -9,13 +9,13 @@ module Docsplit
       extract_options opts
       [pdfs].flatten.each do |pdf|
         pdf_name = File.basename(pdf, File.extname(pdf))
-        page_path = File.join(@output, "#{pdf_name}_%d.pdf")
+        page_path = ESCAPE[File.join(@output, "#{pdf_name}")] + "_%d.pdf"
         FileUtils.mkdir_p @output unless File.exists?(@output)
         
         cmd = if DEPENDENCIES[:pdftailor] # prefer pdftailor, but keep pdftk for backwards compatability
-          "pdftailor unstitch --output #{ESCAPE[page_path]} #{ESCAPE[pdf]} 2>&1"
+          "pdftailor unstitch --output #{page_path} #{ESCAPE[pdf]} 2>&1"
         else
-          "pdftk #{ESCAPE[pdf]} burst output #{ESCAPE[page_path]} 2>&1"
+          "pdftk #{ESCAPE[pdf]} burst output #{page_path} 2>&1"
         end
         result = `#{cmd}`.chomp
         FileUtils.rm('doc_data.txt') if File.exists?('doc_data.txt')
@@ -33,4 +33,4 @@ module Docsplit
 
   end
 
-end
+end

data/lib/docsplit/pdf_extractor.rb

@@ -23,7 +23,7 @@ module Docsplit
       unless @@version_string
         null = windows? ? "NUL" : "/dev/null"
         @@version_string = `#{office_executable} -h 2>#{null}`.split("\n").first
-        if !!@@version_string.match(/[0-9]*/)
+        if !!@@version_string.to_s.match(/[0-9]*/)
           @@version_string = `#{office_executable} --version`.split("\n").first
         end
       end

data/lib/docsplit/transparent_pdfs.rb

@@ -8,17 +8,20 @@ module Docsplit
     # through further extraction.
     def ensure_pdfs(docs)
       [docs].flatten.map do |doc|
-        ext = File.extname(doc)
-        if ext.downcase == '.pdf' || File.open(doc, "rb", &:readline) =~ /\A\%PDF-\d+(\.\d+)?$/
+        if is_pdf?(doc)
           doc
         else
           tempdir = File.join(Dir.tmpdir, 'docsplit')
           extract_pdf([doc], {:output => tempdir})
-          File.join(tempdir, File.basename(doc, ext) + '.pdf')
+          File.join(tempdir, File.basename(doc, File.extname(doc)) + '.pdf')
         end
       end
     end
 
+    def is_pdf?(doc)
+      File.extname(doc).downcase == '.pdf' || File.open(doc, 'rb', &:readline) =~ /\A\%PDF-\d+(\.\d+)?/
+    end
+
   end
 
   extend TransparentPDFs

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: burisu-docsplit
 version: !ruby/object:Gem::Version
-  version: 0.7.6
+  version: 0.7.7
 platform: ruby
 authors:
 - Jeremy Ashkenas
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-27 00:00:00.000000000 Z
+date: 2014-10-18 00:00:00.000000000 Z
 dependencies: []
 description: |2
       Docsplit is a command-line utility and Ruby library for splitting apart
@@ -23,29 +23,29 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- LICENSE
+- README
+- bin/docsplit
+- docsplit.gemspec
+- lib/docsplit.rb
+- lib/docsplit/command_line.rb
 - lib/docsplit/image_extractor.rb
 - lib/docsplit/info_extractor.rb
-- lib/docsplit/transparent_pdfs.rb
-- lib/docsplit/text_extractor.rb
-- lib/docsplit/text_cleaner.rb
 - lib/docsplit/page_extractor.rb
 - lib/docsplit/pdf_extractor.rb
-- lib/docsplit/command_line.rb
-- lib/docsplit.rb
-- bin/docsplit
-- vendor/logging.properties
+- lib/docsplit/text_cleaner.rb
+- lib/docsplit/text_extractor.rb
+- lib/docsplit/transparent_pdfs.rb
 - vendor/conf/document-formats.js
-- vendor/jodconverter/jurt-3.2.1.jar
-- vendor/jodconverter/unoil-3.2.1.jar
 - vendor/jodconverter/commons-cli-1.1.jar
-- vendor/jodconverter/json-20090211.jar
-- vendor/jodconverter/ridl-3.2.1.jar
 - vendor/jodconverter/commons-io-1.4.jar
-- vendor/jodconverter/juh-3.2.1.jar
 - vendor/jodconverter/jodconverter-core-3.0-beta-4.jar
-- docsplit.gemspec
-- LICENSE
-- README
+- vendor/jodconverter/json-20090211.jar
+- vendor/jodconverter/juh-3.2.1.jar
+- vendor/jodconverter/jurt-3.2.1.jar
+- vendor/jodconverter/ridl-3.2.1.jar
+- vendor/jodconverter/unoil-3.2.1.jar
+- vendor/logging.properties
 homepage: http://documentcloud.github.com/docsplit/
 licenses:
 - MIT
@@ -56,17 +56,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.14
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Break Apart Documents into Images, Text, Pages and PDFs