officex2str 0.0.9 → 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 7e56e217a644021b0cbc911758ff81e3e3a5902f
+  data.tar.gz: cac9cc64a9741e37d90b19114dc36f44a7cee8ac
+SHA512:
+  metadata.gz: 40aee55eff82441f5093c3c23fa681ec2b2d3016c7f5ce3744139793dfd0769c324e1f6bef28ae29acdd3fbddebfdf6b1ffdc7e941a6b27854b17b22fed4e36d
+  data.tar.gz: e8596c262b56057fb3c0542fe8537af139c8bc36724ee72ffb653bd16b419a3817c11fa59203463086491e2acabcf5878e3050648b979c964d41dafc81b4f564

data/lib/officex2str.rb

@@ -25,8 +25,14 @@ class Officex2str
 
   def convert
     if valid_file?
-      extract_xmls
-      xml_to_str
+      text = []
+      select_target_entries.each do |entry|
+        doc = Nokogiri.XML(entry.get_input_stream.read, nil, 'utf8')
+        # XLSXではrPhタグに漢字のフリガナが自動的に挿入されるため除外
+        doc.css('rPh').remove
+        text << doc.to_str
+      end
+      text.join(' ')
     else
       raise InvalidFileTypeError, "Not recognized file type"
     end
@@ -50,12 +56,4 @@ private
     end
   end
 
-  def extract_xmls
-    select_target_entries.map{|entry| xmls << entry.get_input_stream.read }
-  end
-
-  def xml_to_str
-    return '' if xmls.empty?
-    xmls.inject(""){|result, xml| result << Nokogiri.XML(xml, nil, 'utf8').to_str }
-  end
 end

data/lib/officex2str/version.rb

@@ -1,3 +1,3 @@
 class Officex2str
-  VERSION = "0.0.9"
+  VERSION = "0.1.0"
 end

data/spec/officex2str_spec.rb

@@ -60,6 +60,10 @@ describe Officex2str do
         subject.should include("STG003")
         subject.should_not include("sonicgarden")
         subject.should_not include("sheet")
+        # フリガナの自動保存分除去確認
+        subject.should_not include('カブシキガイシャ')
+        subject.should_not include('フクスウタイオウ')
+        subject.should_not include('カイシャ')
       end
     end
 

metadata

@@ -1,20 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: officex2str
 version: !ruby/object:Gem::Version
-  version: 0.0.9
-  prerelease: 
+  version: 0.1.0
 platform: ruby
 authors:
 - interu
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-14 00:00:00.000000000 Z
+date: 2016-03-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - '='
       - !ruby/object:Gem::Version
@@ -22,7 +20,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - '='
       - !ruby/object:Gem::Version
@@ -30,7 +27,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - '='
       - !ruby/object:Gem::Version
@@ -38,7 +34,6 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - '='
       - !ruby/object:Gem::Version
@@ -46,49 +41,43 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.4.7
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.4.7
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: mime-types
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: convert office 2010 files to str
@@ -98,7 +87,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - LICENSE
 - README.md
@@ -114,33 +103,26 @@ files:
 - spec/spec_helper.rb
 homepage: ''
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -2505515257273957175
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -2505515257273957175
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: convert office 2010 files(docx,xlsx,pptx) to str
 test_files:
 - spec/officex2str_spec.rb