dwc-archive 0.2.1 → 0.2.2

data/Rakefile

@@ -10,6 +10,7 @@ begin
     gem.email = "dmozzherin at gmail dot com"
     gem.homepage = "http://github.com/dimus/dwc-archive"
     gem.authors = ["Dmitry Mozzherin"]
+    gem.add_dependency "fastercsv" if RUBY_VERSION.match /^1.8/
     gem.add_development_dependency "rspec", ">= 1.2.9"
     gem.add_development_dependency "cucumber", ">= 0"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings

data/VERSION

@@ -1 +1 @@
-0.2.1
+0.2.2

data/features/step_definitions/dwc-archive_steps.rb

@@ -128,7 +128,7 @@ Then /^I can read its content into memory$/ do
   core_data, core_errors = @dwc.core.read
   core_data.class.should == Array
   core_data.size.should == 584
-  core_errors.size.should == 1
+  core_errors.size.should == 3
 end
 
 Then /^I can read extensions content into memory$/ do
@@ -147,7 +147,7 @@ Then /^I can read its core content using block$/ do
     res << [r.size, err.size]
   end
   res << [tail_data.size, tail_errors.size]
-  res.should == [[200,0],[200,0],[184,1]]
+  res.should == [[198,2],[200,0],[186,1]]
 end
 
 Then /^I can read extensions content using block$/ do

data/lib/dwc-archive/core.rb

@@ -8,16 +8,9 @@ class DarwinCore
       root_key = @archive.meta.keys[0]
       @data = @archive.meta[root_key][:core]
       raise CoreFileError("Cannot found core in meta.xml, is meta.xml valid?") unless @data
-      @properties = @data[:attributes]
-      @encoding = @properties[:encoding] || 'UTF-8'
-      raise CoreFileError("No support for encodings other than utf-8 or utf-16 at the moment") unless ["utf-8", "utf8", "utf-16", "utf16"].include? @encoding.downcase
       @id = @data[:id][:attributes]
-      @field_separator = get_field_separator
-      @quote_character = @properties[:fieldsEnclosedBy] || ""
-      @line_separator = @properties[:linesTerminatedBy] || "\n"
-      @ignore_headers = @properties[:ignoreHeaderLines] ? [1, true].include?(@properties[:ignoreHeaderLines]) : false
-      @file_path = get_file_path
-      @fields = get_fields
+      raise CoreFileError("Cannot find core identifier") unless @id
+      get_attributes(CoreFileError)
     end
   end
 end

data/lib/dwc-archive/errors.rb

@@ -4,4 +4,5 @@ class DarwinCore
   class UnpackingError < Error; end
   class InvalidArchiveError < Error; end
   class CoreFileError < Error; end
+  class ExtensionFileError < Error; end
 end

data/lib/dwc-archive/extension.rb

@@ -7,15 +7,9 @@ class DarwinCore
       @archive = archive
       @path = @archive.files_path
       @data = data
-      @properties = @data[:attributes]
-      @coreid = @data[:coreid][:attributes]
-      @encoding = @properties[:encoding] || 'UTF-8'
-      @quote_character = @properties[:fieldsEnclosedBy] || ""
-      @line_separator = @properties[:linesTerminatedBy] || "\n"
-      @ignore_headers = @properties[:ignoreHeaderLines] ? [1, true].include?(@properties[:ignoreHeaderLines]) : false
-      @field_separator = get_field_separator
-      @file_path = get_file_path
-      @fields = get_fields
+      @coreid = @data[:coreid][:attributes] 
+      raise ExtensionFileError("Extension has no coreid information") unless @coreid
+      get_attributes(ExtensionFileError)
     end
 
   end

data/lib/dwc-archive/ingester.rb

@@ -1,4 +1,4 @@
-class DarwinCore
+class DarwinCore 
   module Ingester
     attr_reader :data, :properties, :encoding, :fields_separator
     attr_reader :file_path, :fields, :line_separator, :quote_character, :ignore_headers
@@ -10,14 +10,7 @@ class DarwinCore
       args.merge!({:quote_char => @quote_character}) if @quote_character != ''
       CSV.open(@file_path, args).each_with_index do |r, i|
         index_fix = 0; next if @ignore_headers && i == 0
-        str = r.join('')
-        if defined? FasterCSV
-          require File.join(File.dirname(__FILE__), 'utf_regex_ruby18')
-          UTF8RGX === str ? res << r : errors << r
-        else
-          str = str.force_encoding('utf-8')
-          str.encoding.name == "UTF-8" && str.valid_encoding? ? res << r : errors << r
-        end
+        @fields.size > (r.size - 1) ? errors << r : process_csv_row(res, errors, r)
         if block_given? && (i + index_fix) % batch_size == 0
           yield [res, errors]
           res = []
@@ -28,6 +21,31 @@ class DarwinCore
     end
     
     private
+    def process_csv_row(result, errors, row)
+      str = row.join('')
+      if defined? FasterCSV
+        require File.join(File.dirname(__FILE__), 'utf_regex_ruby18')
+        UTF8RGX === str ? result << row : errors << row
+      else
+        str = str.force_encoding('utf-8')
+        str.encoding.name == "UTF-8" && str.valid_encoding? ? result << row : errors << row
+      end
+    end
+
+    def get_attributes(exception)
+      @properties = @data[:attributes]
+      @encoding = @properties[:encoding] || 'UTF-8'
+      raise exception("No support for encodings other than utf-8 or utf-16 at the moment") unless ["utf-8", "utf8", "utf-16", "utf16"].include? @encoding.downcase
+      @field_separator = get_field_separator
+      @quote_character = @properties[:fieldsEnclosedBy] || ""
+      @line_separator = @properties[:linesTerminatedBy] || "\n"
+      @ignore_headers = @properties[:ignoreHeaderLines] ? [1, true].include?(@properties[:ignoreHeaderLines]) : false
+      @file_path = get_file_path
+      raise exception("No file data") unless @file_path
+      @fields = get_fields
+      raise exception("No data fields are found") if @fields.empty?
+    end
+    
     def get_file_path
       file = @data[:location] || @data[:attributes][:location] || @data[:files][:location]
       File.join(@path, file)

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: dwc-archive
 version: !ruby/object:Gem::Version 
-  hash: 21
+  hash: 19
   prerelease: false
   segments: 
   - 0
   - 2
-  - 1
-  version: 0.2.1
+  - 2
+  version: 0.2.2
 platform: ruby
 authors: 
 - Dmitry Mozzherin
@@ -15,13 +15,27 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-05-19 00:00:00 -04:00
+date: 2010-05-21 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: rspec
+  name: fastercsv
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -33,11 +47,11 @@ dependencies:
         - 9
         version: 1.2.9
   type: :development
-  version_requirements: *id001
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: cucumber
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -47,7 +61,7 @@ dependencies:
         - 0
         version: "0"
   type: :development
-  version_requirements: *id002
+  version_requirements: *id003
 description: Darwin Core Archive is the current standard exchange format for GLobal Names Architecture modules. This gem makes it easy to incorporate files in Darwin Core Archive format into a ruby project.
 email: dmozzherin at gmail dot com
 executables: []