Merge pull request #3205 from github/language-id

Language ids
This commit is contained in:
Arfon Smith
2016-09-13 11:27:25 -07:00
committed by GitHub
5 changed files with 1651 additions and 1506 deletions

View File

@@ -33,6 +33,7 @@ To add support for a new language:
0. Add your grammar to [`grammars.yml`][grammars] by running `script/convert-grammars --add vendor/grammars/MyGrammar`.
0. Download the license for the grammar: `script/licensed`. Be careful to only commit the file for the new grammar, as this script may update licenses for other grammars as well.
0. Add samples for your language to the [samples directory][samples] in the correct subdirectory.
0. Add a `language_id` for your language. See `script/set-language-ids` for more information. **You should only ever need to run `script/set-language-ids --update`. Anything other than this risks breaking GitHub search :cry:**
0. Open a pull request, linking to a [GitHub search result](https://github.com/search?utf8=%E2%9C%93&q=extension%3Aboot+NOT+nothack&type=Code&ref=searchresults) showing in-the-wild usage.
In addition, if your new language defines an extension that's already listed in [`languages.yml`][languages] (such as `.foo`) then sometimes a few more steps will need to be taken:
@@ -84,7 +85,7 @@ Linguist is maintained with :heart: by:
- @arfon (GitHub Staff)
- @larsbrinkhoff
- @pchaigno
As Linguist is a production dependency for GitHub we have a couple of workflow restrictions:
- Anyone with commit rights can merge Pull Requests provided that there is a :+1: from a GitHub member of staff

View File

@@ -20,10 +20,11 @@ module Linguist
#
# Languages are defined in `lib/linguist/languages.yml`.
class Language
@languages = []
@index = {}
@name_index = {}
@alias_index = {}
@languages = []
@index = {}
@name_index = {}
@alias_index = {}
@language_id_index = {}
@extension_index = Hash.new { |h,k| h[k] = [] }
@interpreter_index = Hash.new { |h,k| h[k] = [] }
@@ -84,6 +85,8 @@ module Linguist
@filename_index[filename] << language
end
@language_id_index[language.language_id] = language
language
end
@@ -193,6 +196,19 @@ module Linguist
@interpreter_index[interpreter]
end
# Public: Look up Languages by its language_id.
#
# language_id - Integer of language_id
#
# Examples
#
# Language.find_by_id(100)
# # => [#<Language name="Elixir">]
#
# Returns the matching Language
def self.find_by_id(language_id)
@language_id_index[language_id.to_i]
end
# Public: Look up Language by its name.
#
@@ -289,6 +305,9 @@ module Linguist
# Set legacy search term
@search_term = attributes[:search_term] || default_alias_name
# Set the language_id
@language_id = attributes[:language_id]
# Set extensions or default to [].
@extensions = attributes[:extensions] || []
@interpreters = attributes[:interpreters] || []
@@ -351,6 +370,17 @@ module Linguist
# Returns the name String
attr_reader :search_term
# Public: Get language_id (used in GitHub search)
#
# Examples
#
# # => "1"
# # => "2"
# # => "3"
#
# Returns the integer language_id
attr_reader :language_id
# Public: Get the name of a TextMate-compatible scope
#
# Returns the scope
@@ -547,6 +577,7 @@ module Linguist
:group_name => options['group'],
:searchable => options.fetch('searchable', true),
:search_term => options['search_term'],
:language_id => options['language_id'],
:extensions => Array(options['extensions']),
:interpreters => options['interpreters'].sort,
:filenames => options['filenames'],

File diff suppressed because it is too large Load Diff

82
script/set-language-ids Executable file
View File

@@ -0,0 +1,82 @@
#!/usr/bin/env ruby
require 'yaml'
require 'pry'
header = <<-EOF
# Defines all Languages known to GitHub.
#
# type - Either data, programming, markup, prose, or nil
# aliases - An Array of additional aliases (implicitly
# includes name.downcase)
# ace_mode - A String name of the Ace Mode used for highlighting whenever
# a file is edited. This must match one of the filenames in http://git.io/3XO_Cg.
# Use "text" if a mode does not exist.
# wrap - Boolean wrap to enable line wrapping (default: false)
# extensions - An Array of associated extensions (the first one is
# considered the primary extension, the others should be
# listed alphabetically)
# interpreters - An Array of associated interpreters
# searchable - Boolean flag to enable searching (defaults to true)
# search_term - Deprecated: Some languages may be indexed under a
# different alias. Avoid defining new exceptions.
# language_id - Integer used as a language-name-independent indexed field so that we can rename
# languages in Linguist without reindexing all the code on GitHub. Must not be
# changed for existing languages without the explicit permission of GitHub staff.
# color - CSS hex color to represent the language.
# tm_scope - The TextMate scope that represents this programming
# language. This should match one of the scopes listed in
# the grammars.yml file. Use "none" if there is no grammar
# for this language.
# group - Name of the parent language. Languages in a group are counted
# in the statistics as the parent language.
#
# Any additions or modifications (even trivial) should have corresponding
# test changes in `test/test_blob.rb`.
#
# Please keep this list alphabetized. Capitalization comes before lowercase.
EOF
generated = true if ARGV[0] == "--force"
update = true if ARGV[0] == "--update"
if generated
puts "You're regenerating all of the language_id attributes for all Linguist "
puts "languages defined in languages.yml. This is almost certainly NOT what"
puts "you meant to do!"
language_index = 0
languages = YAML.load(File.read("lib/linguist/languages.yml"))
languages.each do |name, vals|
vals.merge!('language_id' => language_index)
language_index += 1
end
File.write("lib/linguist/languages.yml", header + YAML.dump(languages))
elsif update
puts "Adding new language_id attributes to languages.yml that don't have one set"
languages = YAML.load(File.read("lib/linguist/languages.yml"))
# First grab the maximum language_id
language_ids = []
languages.each { |name, vals| language_ids << vals['language_id'] if vals.has_key?('language_id')}
max_language_id = language_ids.max
puts "Current maximum language_id is #{max_language_id}"
missing_count = 0
language_index = max_language_id
languages.each do |name, vals|
unless vals.has_key?('language_id')
language_index += 1
missing_count += 1
vals.merge!('language_id' => language_index)
end
end
File.write("lib/linguist/languages.yml", header + YAML.dump(languages))
puts "Updated language_id attributes for #{missing_count} languages"
else
puts "Whatever you want me to do, I can't figure it out. Giving up..."
end

View File

@@ -67,6 +67,22 @@ class TestLanguage < Minitest::Test
assert_nil Language.find_by_alias(nil)
end
# Note these are set by script/set-language-ids. If these tests fail then someone
# has changed the language_id fields set in languages.yml which is almost certainly
# not what you want to happen (these fields are used in GitHub's search indexes)
def test_language_ids
assert_equal 4, Language['ANTLR'].language_id
assert_equal 54, Language['Ceylon'].language_id
assert_equal 326, Language['Ruby'].language_id
assert_equal 421, Language['xBase'].language_id
end
def test_find_by_id
assert_equal Language['Elixir'], Language.find_by_id(100)
assert_equal Language['Ruby'], Language.find_by_id(326)
assert_equal Language['xBase'], Language.find_by_id(421)
end
def test_groups
# Test a couple identity cases
assert_equal Language['Perl'], Language['Perl'].group
@@ -386,6 +402,22 @@ class TestLanguage < Minitest::Test
assert missing.empty?, message
end
def test_all_languages_have_a_language_id_set
missing = Language.all.select { |language| language.language_id.nil? }
message = "The following languages do not have a language_id listed in languages.yml. Please add language_id fields for all new languages.\n"
missing.each { |language| message << "#{language.name}\n" }
assert missing.empty?, message
end
def test_all_language_id_are_unique
duplicates = Language.all.group_by{ |language| language.language_id }.select { |k, v| v.size > 1 }.map(&:first)
message = "The following language_id are used several times in languages.yml. Please use script/set-language-ids --update as per the contribution guidelines.\n"
duplicates.each { |language_id| message << "#{language_id}\n" }
assert duplicates.empty?, message
end
def test_all_languages_have_a_valid_ace_mode
ace_fixture_path = File.join('test', 'fixtures', 'ace_modes.json')
skip("No ace_modes.json file") unless File.exist?(ace_fixture_path)