From 80e8ee7ce6b5c221feecbf490f83fadd0d7626ba Mon Sep 17 00:00:00 2001 From: Joshua Peek Date: Mon, 23 Jul 2012 13:15:27 -0500 Subject: [PATCH] Rename Sample -> Samples --- Rakefile | 6 +++--- lib/linguist/blob_helper.rb | 4 ++-- lib/linguist/language.rb | 6 +++--- lib/linguist/{sample.rb => samples.rb} | 2 +- test/test_blob.rb | 4 ++-- test/test_classifier.rb | 16 ++++++++-------- 6 files changed, 19 insertions(+), 19 deletions(-) rename lib/linguist/{sample.rb => samples.rb} (99%) diff --git a/Rakefile b/Rakefile index cade0dc1..753cadf5 100644 --- a/Rakefile +++ b/Rakefile @@ -9,8 +9,8 @@ end file 'lib/linguist/samples.yml' => Dir['samples/**/*'] do |f| - require 'linguist/sample' - File.open(f.name, 'w') { |io| Linguist::Sample.serialize_to_yaml(Linguist::Sample::DATA, io) } + require 'linguist/samples' + File.open(f.name, 'w') { |io| Linguist::Samples.serialize_to_yaml(Linguist::Samples::DATA, io) } end CLOBBER.include 'lib/linguist/samples.yml' @@ -31,7 +31,7 @@ namespace :classifier do next if file_language.nil? || file_language == 'Text' begin data = open(file_url).read - guessed_language, score = Linguist::Classifier.new(Sample::DATA).classify(data).first + guessed_language, score = Linguist::Classifier.new(Samples::DATA).classify(data).first total += 1 guessed_language == file_language ? correct += 1 : incorrect += 1 diff --git a/lib/linguist/blob_helper.rb b/lib/linguist/blob_helper.rb index b9326120..39d62c0d 100644 --- a/lib/linguist/blob_helper.rb +++ b/lib/linguist/blob_helper.rb @@ -2,7 +2,7 @@ require 'linguist/classifier' require 'linguist/language' require 'linguist/mime' require 'linguist/pathname' -require 'linguist/sample' +require 'linguist/samples' require 'charlock_holmes' require 'escape_utils' @@ -442,7 +442,7 @@ module Linguist if Language.ambiguous?(extname) possible_languages = Language.all.select { |l| l.extensions.include?(extname) }.map(&:name) if possible_languages.any? - if result = Classifier.new(Sample::DATA).classify(data, possible_languages).first + if result = Classifier.new(Samples::DATA).classify(data, possible_languages).first Language[result[0]] end end diff --git a/lib/linguist/language.rb b/lib/linguist/language.rb index 88ccb9fb..43179369 100644 --- a/lib/linguist/language.rb +++ b/lib/linguist/language.rb @@ -2,7 +2,7 @@ require 'escape_utils' require 'pygments' require 'yaml' -require 'linguist/sample' +require 'linguist/samples' module Linguist # Language names that are recognizable by GitHub. Defined languages @@ -441,8 +441,8 @@ module Linguist end end - extensions = Sample.extensions - filenames = Sample.filenames + extensions = Samples.extensions + filenames = Samples.filenames popular = YAML.load_file(File.expand_path("../popular.yml", __FILE__)) YAML.load_file(File.expand_path("../languages.yml", __FILE__)).each do |name, options| diff --git a/lib/linguist/sample.rb b/lib/linguist/samples.rb similarity index 99% rename from lib/linguist/sample.rb rename to lib/linguist/samples.rb index 4c3f5e9a..f85f9ae0 100644 --- a/lib/linguist/sample.rb +++ b/lib/linguist/samples.rb @@ -3,7 +3,7 @@ require 'yaml' module Linguist # Model for accessing classifier training data. - module Sample + module Samples # Samples live in test/ for now, we'll eventually move them out PATH = File.expand_path("../../../samples", __FILE__) diff --git a/test/test_blob.rb b/test/test_blob.rb index fc62349d..2bf580e8 100644 --- a/test/test_blob.rb +++ b/test/test_blob.rb @@ -1,5 +1,5 @@ require 'linguist/file_blob' -require 'linguist/sample' +require 'linguist/samples' require 'test/unit' require 'mime/types' @@ -275,7 +275,7 @@ class TestBlob < Test::Unit::TestCase end def test_language - Sample.each do |sample| + Samples.each do |sample| blob = blob(sample[:path]) language = Linguist::Language.find_by_alias(sample[:language]) assert_equal language, blob.language, blob.name diff --git a/test/test_classifier.rb b/test/test_classifier.rb index 2d55aa07..90a7d239 100644 --- a/test/test_classifier.rb +++ b/test/test_classifier.rb @@ -1,6 +1,6 @@ require 'linguist/classifier' require 'linguist/language' -require 'linguist/sample' +require 'linguist/samples' require 'linguist/tokenizer' require 'linguist/md5' @@ -18,8 +18,8 @@ class TestClassifier < Test::Unit::TestCase end def test_instance_freshness - serialized = Linguist::MD5.hexdigest(Sample::DATA) - latest = Linguist::MD5.hexdigest(Linguist::Sample.classifier.to_hash) + serialized = Linguist::MD5.hexdigest(Samples::DATA) + latest = Linguist::MD5.hexdigest(Linguist::Samples.classifier.to_hash) # Just warn, it shouldn't scare people off by breaking the build. if serialized != latest @@ -55,16 +55,16 @@ class TestClassifier < Test::Unit::TestCase end def test_instance_classify_empty - results = Classifier.new(Sample::DATA).classify("") + results = Classifier.new(Samples::DATA).classify("") assert results.first[1] < 0.5, results.first.inspect end def test_instance_classify_nil - assert_equal [], Classifier.new(Sample::DATA).classify(nil) + assert_equal [], Classifier.new(Samples::DATA).classify(nil) end def test_verify - data = Sample::DATA + data = Samples::DATA assert_equal data['languages_total'], data['languages'].inject(0) { |n, (_, c)| n += c } assert_equal data['tokens_total'], data['language_tokens'].inject(0) { |n, (_, c)| n += c } @@ -72,7 +72,7 @@ class TestClassifier < Test::Unit::TestCase end def test_classify_ambiguous_languages - Sample.each do |sample| + Samples.each do |sample| language = Linguist::Language.find_by_alias(sample[:language]) next unless language.overrides.any? @@ -80,7 +80,7 @@ class TestClassifier < Test::Unit::TestCase languages = Language.all.select { |l| l.extensions.include?(extname) }.map(&:name) next unless languages.length > 1 - results = Classifier.new(Sample::DATA).classify(File.read(sample[:path]), languages) + results = Classifier.new(Samples::DATA).classify(File.read(sample[:path]), languages) assert_equal language.name, results.first[0], "#{sample[:path]}\n#{results.inspect}" end end