twitter_to_csv 0.0.4 → 0.0.5

data/README.markdown

@@ -37,7 +37,7 @@ You can extract URLs from the tweet into their own columns by including `--url-c
 
 ## Field names
 
-Use `--sample-fields 1000`` to output the occurrence count of different Twitter fields, like so:
+Use `--sample-fields 1000` to output the occurrence count of different Twitter fields, like so:
 
     twitter_to_csv --username <your twitter username> --password <your twitter password> --sample-fields 1000
 

data/lib/twitter_to_csv/csv_builder.rb

@@ -14,10 +14,10 @@ module TwitterToCsv
       @num_samples = 0
     end
 
-    def run
+    def run(&block)
       log_csv_header if options[:csv] && !options[:csv_appending]
       if options[:replay_from_file]
-        replay_from options[:replay_from_file]
+        replay_from options[:replay_from_file], &block
       else
         begin
           TwitterWatcher.new(options).run do |status|
@@ -35,10 +35,11 @@ module TwitterToCsv
       end
     end
 
-    def handle_status(status)
+    def handle_status(status, &block)
       if (options[:require_english] && is_english?(status)) || !options[:require_english]
         log_json(status) if options[:json]
         log_csv(status) if options[:csv]
+        yield_status(status, &block) if block
         sample_fields(status) if options[:sample_fields]
         STDERR.puts "Logging: #{status['text']}" if options[:verbose]
       end
@@ -55,7 +56,15 @@ module TwitterToCsv
     end
 
     def log_csv(status)
-      csv_row = options[:fields].map do |field|
+      options[:csv].puts output_row(status).to_csv(:encoding => 'UTF-8', :force_quotes => true)
+    end
+
+    def yield_status(status, &block)
+      block.call output_row(status)
+    end
+
+    def output_row(status)
+      row = options[:fields].map do |field|
         field.split(".").inject(status) { |memo, segment|
           memo && memo[segment]
         }.to_s
@@ -63,18 +72,18 @@ module TwitterToCsv
 
       if options[:url_columns] && options[:url_columns] > 0
         urls = status['text'].scan(URL_REGEX).flatten.compact
-        options[:url_columns].times { |i| csv_row << urls[i].to_s }
+        options[:url_columns].times { |i| row << urls[i].to_s }
       end
 
-      options[:csv].puts csv_row.to_csv(:encoding => 'UTF-8', :force_quotes => true)
+      row
     end
 
-    def replay_from(filename)
+    def replay_from(filename, &block)
       File.open(filename, "r") do |file|
         until file.eof?
           line = file.readline
           next if line =~ /\A------SEP.RATOR------\Z/i
-          handle_status JSON.parse(line)
+          handle_status JSON.parse(line), &block
         end
       end
     end

data/lib/twitter_to_csv/version.rb

@@ -1,3 +1,3 @@
 module TwitterToCsv
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: twitter_to_csv
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-30 00:00:00.000000000Z
+date: 2012-03-31 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70329976472640 !ruby/object:Gem::Requirement
+  requirement: &81656020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70329976472640
+  version_requirements: *81656020
 - !ruby/object:Gem::Dependency
   name: twitter-stream
-  requirement: &70329976472220 !ruby/object:Gem::Requirement
+  requirement: &81655810 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70329976472220
+  version_requirements: *81655810
 - !ruby/object:Gem::Dependency
   name: em-http-request
-  requirement: &70329976471800 !ruby/object:Gem::Requirement
+  requirement: &81655600 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70329976471800
+  version_requirements: *81655600
 - !ruby/object:Gem::Dependency
   name: unsupervised-language-detection
-  requirement: &70329976471380 !ruby/object:Gem::Requirement
+  requirement: &81655390 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,7 +54,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70329976471380
+  version_requirements: *81655390
 description: ''
 email:
 - andrew@iterationlabs.com
@@ -97,10 +97,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: twitter_to_csv
-rubygems_version: 1.8.6
+rubygems_version: 1.8.16
 signing_key: 
 specification_version: 3
 summary: Dump the Twitter streaming API to a CSV or JSON file
-test_files:
-- spec/csv_builder_spec.rb
-- spec/spec_helper.rb
+test_files: []