rika 0.9.1-java → 0.9.2-java

data/spec/fixtures/text_file.txt

@@ -1 +1 @@
-First they ignore you, then they ridicule you, then they fight you, then you win.
+First they ignore you, then they ridicule you, then they fight you, then you win.

data/spec/fixtures/text_file_without_extension

@@ -0,0 +1 @@
+First they ignore you, then they ridicule you, then they fight you, then you win.

data/spec/rika_spec.rb

@@ -10,26 +10,41 @@ describe Rika::Parser do
     @image_parser = Rika::Parser.new(file_path("image.jpg"))
   end
 
-  it "should crash if file does not exists" do
+  it "should raise error if file does not exists" do
     lambda { Rika::Parser.new(file_path("nonsense.txt")) }.should raise_error(IOError, "File does not exist")
   end
 
+  it "should detect file type without a file extension" do
+    parser = Rika::Parser.new(file_path("text_file_without_extension"))
+    parser.metadata["Content-Type"].should == "text/plain; charset=ISO-8859-1"
+  end
+
   describe '#content' do
     it "should return the content in a text file" do
       @txt_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
     end
 
     it "should return the content in a docx file" do
-      @docx_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+      @docx_parser.content.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
     end
 
     it "should return the content in a pdf file" do 
-      @pdf_parser.content.strip.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
+      @pdf_parser.content.should == "First they ignore you, then they ridicule you, then they fight you, then you win."
     end
 
     it "should return no content for an image" do
       @image_parser.content.should be_empty
     end
+
+    it "should only return max content length" do
+      parser = Rika::Parser.new(file_path("text_file.txt"), 5)
+      parser.content.should == "First"
+    end
+
+    it "should be possible to read files over 100k by default" do
+      parser = Rika::Parser.new(file_path("over_100k_file.txt"))
+      parser.content.length.should == 101_761
+    end
   end
 
   # We just test a few of the metadata fields for some common file formats 

metadata

@@ -2,14 +2,14 @@
 name: rika
 version: !ruby/object:Gem::Version
   prerelease:
-  version: 0.9.1
+  version: 0.9.2
 platform: java
 authors:
 - Richard Nyström
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2012-09-16 00:00:00.000000000 Z
+date: 2012-09-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -43,46 +43,53 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
-- lib/apache-mime4j-core-0.7.2.jar
-- lib/apache-mime4j-dom-0.7.2.jar
-- lib/asm-3.1.jar
-- lib/aspectjrt-1.6.11.jar
-- lib/bcmail-jdk15-1.45.jar
-- lib/bcprov-jdk15-1.45.jar
-- lib/boilerpipe-1.1.0.jar
-- lib/commons-codec-1.5.jar
-- lib/commons-compress-1.4.1.jar
-- lib/commons-logging-1.1.1.jar
-- lib/dom4j-1.6.1.jar
-- lib/fontbox-1.7.0.jar
-- lib/isoparser-1.0-RC-1.jar
-- lib/jempbox-1.7.0.jar
-- lib/juniversalchardet-1.0.3.jar
-- lib/metadata-extractor-2.4.0-beta-1.jar
-- lib/pdfbox-1.7.0.jar
-- lib/poi-3.8.jar
-- lib/poi-ooxml-3.8.jar
-- lib/poi-ooxml-schemas-3.8.jar
-- lib/poi-scratchpad-3.8.jar
 - lib/rika.rb
 - lib/rika/version.rb
-- lib/rome-0.9.jar
-- lib/tagsoup-1.2.1.jar
-- lib/tika-core-1.2.jar
-- lib/tika-parsers-1.2.jar
-- lib/vorbis-java-core-0.1-tests.jar
-- lib/vorbis-java-core-0.1.jar
-- lib/vorbis-java-tika-0.1.jar
-- lib/xmlbeans-2.3.0.jar
-- lib/xz-1.0.jar
+- pom.xml
 - rika.gemspec
 - spec/fixtures/document.doc
 - spec/fixtures/document.docx
 - spec/fixtures/document.pdf
 - spec/fixtures/image.jpg
+- spec/fixtures/over_100k_file.txt
 - spec/fixtures/text_file.txt
+- spec/fixtures/text_file_without_extension
 - spec/rika_spec.rb
 - spec/spec_helper.rb
+- target/dependency/apache-mime4j-core-0.7.2.jar
+- target/dependency/apache-mime4j-dom-0.7.2.jar
+- target/dependency/asm-3.1.jar
+- target/dependency/aspectjrt-1.6.11.jar
+- target/dependency/bcmail-jdk15-1.45.jar
+- target/dependency/bcprov-jdk15-1.45.jar
+- target/dependency/boilerpipe-1.1.0.jar
+- target/dependency/commons-codec-1.5.jar
+- target/dependency/commons-compress-1.4.1.jar
+- target/dependency/commons-logging-1.1.1.jar
+- target/dependency/dom4j-1.6.1.jar
+- target/dependency/fontbox-1.7.0.jar
+- target/dependency/geronimo-stax-api_1.0_spec-1.0.1.jar
+- target/dependency/isoparser-1.0-RC-1.jar
+- target/dependency/jdom-1.0.jar
+- target/dependency/jempbox-1.7.0.jar
+- target/dependency/juniversalchardet-1.0.3.jar
+- target/dependency/metadata-extractor-2.4.0-beta-1.jar
+- target/dependency/netcdf-4.2-min.jar
+- target/dependency/pdfbox-1.7.0.jar
+- target/dependency/poi-3.8.jar
+- target/dependency/poi-ooxml-3.8.jar
+- target/dependency/poi-ooxml-schemas-3.8.jar
+- target/dependency/poi-scratchpad-3.8.jar
+- target/dependency/rome-0.9.jar
+- target/dependency/slf4j-api-1.5.6.jar
+- target/dependency/tagsoup-1.2.1.jar
+- target/dependency/tika-core-1.2.jar
+- target/dependency/tika-parsers-1.2.jar
+- target/dependency/vorbis-java-core-0.1-tests.jar
+- target/dependency/vorbis-java-core-0.1.jar
+- target/dependency/vorbis-java-tika-0.1.jar
+- target/dependency/xmlbeans-2.3.0.jar
+- target/dependency/xz-1.0.jar
 homepage: https://github.com/ricn/rika
 licenses: []
 post_install_message:
@@ -114,6 +121,8 @@ test_files:
 - spec/fixtures/document.docx
 - spec/fixtures/document.pdf
 - spec/fixtures/image.jpg
+- spec/fixtures/over_100k_file.txt
 - spec/fixtures/text_file.txt
+- spec/fixtures/text_file_without_extension
 - spec/rika_spec.rb
 - spec/spec_helper.rb