Use filenames as a definitive answer (#2006)

* Separate find_by_extension and find_by_filename
find_by_extension now takes a path as argument and not only the file extension.
Currently only find_by_extension is used as a strategy.

* Add find_by_filename as first strategy
This commit is contained in:
Paul Chaignon
2016-12-12 21:34:33 +01:00
committed by Brandon Black
parent 9d8392dab8
commit 9b941a34f0
10 changed files with 435 additions and 29 deletions

View File

@@ -59,8 +59,9 @@ class << Linguist
# Strategies are called in turn until a single Language is returned. # Strategies are called in turn until a single Language is returned.
STRATEGIES = [ STRATEGIES = [
Linguist::Strategy::Modeline, Linguist::Strategy::Modeline,
Linguist::Shebang,
Linguist::Strategy::Filename, Linguist::Strategy::Filename,
Linguist::Shebang,
Linguist::Strategy::Extension,
Linguist::Heuristics, Linguist::Heuristics,
Linguist::Classifier Linguist::Classifier
] ]

View File

@@ -11,6 +11,7 @@ require 'linguist/samples'
require 'linguist/file_blob' require 'linguist/file_blob'
require 'linguist/blob_helper' require 'linguist/blob_helper'
require 'linguist/strategy/filename' require 'linguist/strategy/filename'
require 'linguist/strategy/extension'
require 'linguist/strategy/modeline' require 'linguist/strategy/modeline'
require 'linguist/shebang' require 'linguist/shebang'
@@ -129,41 +130,46 @@ module Linguist
# Public: Look up Languages by filename. # Public: Look up Languages by filename.
# #
# The behaviour of this method recently changed.
# See the second example below.
#
# filename - The path String. # filename - The path String.
# #
# Examples # Examples
# #
# Language.find_by_filename('Cakefile')
# # => [#<Language name="CoffeeScript">]
# Language.find_by_filename('foo.rb') # Language.find_by_filename('foo.rb')
# # => [#<Language name="Ruby">] # # => []
# #
# Returns all matching Languages or [] if none were found. # Returns all matching Languages or [] if none were found.
def self.find_by_filename(filename) def self.find_by_filename(filename)
basename = File.basename(filename) basename = File.basename(filename)
@filename_index[basename]
# find the first extension with language definitions
extname = FileBlob.new(filename).extensions.detect do |e|
!@extension_index[e].empty?
end
(@filename_index[basename] + @extension_index[extname]).compact.uniq
end end
# Public: Look up Languages by file extension. # Public: Look up Languages by file extension.
# #
# extname - The extension String. # The behaviour of this method recently changed.
# See the second example below.
#
# filename - The path String.
# #
# Examples # Examples
# #
# Language.find_by_extension('.rb') # Language.find_by_extension('dummy.rb')
# # => [#<Language name="Ruby">] # # => [#<Language name="Ruby">]
#
# Language.find_by_extension('rb') # Language.find_by_extension('rb')
# # => [#<Language name="Ruby">] # # => []
# #
# Returns all matching Languages or [] if none were found. # Returns all matching Languages or [] if none were found.
def self.find_by_extension(extname) def self.find_by_extension(filename)
extname = ".#{extname}" unless extname.start_with?(".") # find the first extension with language definitions
@extension_index[extname.downcase] extname = FileBlob.new(filename.downcase).extensions.detect do |e|
!@extension_index[e].empty?
end
@extension_index[extname]
end end
# Public: Look up Languages by interpreter. # Public: Look up Languages by interpreter.

View File

@@ -0,0 +1,10 @@
module Linguist
module Strategy
# Detects language based on extension
class Extension
def self.call(blob, _)
Language.find_by_extension(blob.name.to_s)
end
end
end
end

View File

@@ -1,9 +1,10 @@
module Linguist module Linguist
module Strategy module Strategy
# Detects language based on filename and/or extension # Detects language based on filename
class Filename class Filename
def self.call(blob, _) def self.call(blob, _)
Language.find_by_filename(blob.name.to_s) name = blob.name.to_s
Language.find_by_filename(name)
end end
end end
end end

29
test/fixtures/CMake/CMakeLists.txt vendored Normal file
View File

@@ -0,0 +1,29 @@
cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
project("To do list")
enable_testing()
if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU" OR
"${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(warnings "-Wall -Wextra -Werror")
elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "MSVC")
set(warnings "/W4 /WX /EHsc")
endif()
set(optimize "-O2")
if (NOT CONFIGURED_ONCE)
set(CMAKE_CXX_FLAGS "${warnings} ${optimize}"
CACHE STRING "Flags used by the compiler during all build types." FORCE)
set(CMAKE_C_FLAGS "${warnings} ${optimize}"
CACHE STRING "Flags used by the compiler during all build types." FORCE)
endif()
add_executable(toDo main.cpp ToDo.cpp)
add_test(toDoTest toDo)
set(CONFIGURED_ONCE TRUE CACHE INTERNAL
"A flag showing that CMake has configured at least once.")

200
test/fixtures/CoffeeScript/Cakefile vendored Executable file
View File

@@ -0,0 +1,200 @@
http = require 'http'
https = require 'https'
fs = require 'fs'
path = require 'path'
{spawn, exec} = require 'child_process'
semver = require 'semver'
AdmZip = require('adm-zip')
GitHubApi = require 'github'
github = new GitHubApi(version: '3.0.0')
# ----------------
# Server / Builder
# ----------------
option '-P', '--production', 'run server in production mode'
option null, '--port [PORT]', 'listen on specified port (default 3333)'
LOCAL_BRUNCH = path.join('.', 'node_modules', '.bin', 'brunch')
spawnBrunch = (flags, env) ->
if fs.existsSync(LOCAL_BRUNCH)
brunch = spawn LOCAL_BRUNCH, flags, env
else
console.error 'Warning, using global brunch. Run `npm install`.'
brunch = spawn 'brunch', flags, env
brunch.stdout.on 'data', (data) -> console.log data.toString().trim()
brunch.stderr.on 'data', (data) -> console.log data.toString().trim()
runBrunchWatch = (options, shouldStartServer) ->
flags = ['w']
flags.push '-s' if shouldStartServer
if options.production?
flags.push('-P')
process.env.BRUNCH_ENV = 'production'
if options.port?
flags.push '-p'
flags.push options.port
spawnBrunch flags, process.env
task 'server', 'start the brunch server in development', (options) ->
runBrunchWatch(options, true)
task 'watch', 'build the app continuously without a server', (options) ->
runBrunchWatch(options, false)
task 'build', 'build for production', ->
process.env.BRUNCH_ENV = 'production'
spawnBrunch ['b', '-P'], process.env
task 'test', 'run brunch in the test environment', ->
flags = ['w', '-s']
process.env.BRUNCH_ENV = 'test'
spawnBrunch flags, process.env
# -------------
# Tapas Updates
# -------------
updateMessage = 'update Tapas to latest (Cakefile, package.json, portkey.json,
config.coffee, generators/*)'
task 'tapas:update', updateMessage, (options) ->
url = 'https://codeload.github.com/mutewinter/tapas-with-ember/zip/master'
filesToUpdate = [
'Cakefile'
'package.json'
'portkey.json'
'config.coffee'
'generators/'
'testem.json'
'bower.json'
]
https.get url, (res) ->
data = []
dataLen = 0
res.on('data', (chunk) ->
data.push(chunk)
dataLen += chunk.length
).on('end', ->
buf = new Buffer(dataLen)
pos = 0
for dataItem in data
dataItem.copy(buf, pos)
pos += dataItem.length
zip = new AdmZip(buf)
filesToUpdate.forEach (file) ->
targetFile = "tapas-with-ember-master/#{file}"
if /\/$/.test(file)
zip.extractEntryTo(targetFile, file, false, true)
else
zip.extractEntryTo(targetFile, '', false, true)
)
# --------------
# Script Updates
# --------------
EMBER_BASE_URL = 'http://builds.emberjs.com'
GITHUB_API_URL = 'https://api.github.com'
EMBER = {}
EMBER_DATA = {}
['release', 'beta', 'canary'].forEach (build) ->
EMBER[build] =
prod: "#{EMBER_BASE_URL}/#{build}/ember.prod.js"
dev: "#{EMBER_BASE_URL}/#{build}/ember.js"
EMBER_DATA[build] =
prod: "#{EMBER_BASE_URL}/#{build}/ember-data.prod.js"
dev: "#{EMBER_BASE_URL}/#{build}/ember-data.js"
EMBER['tag'] =
prod: "#{EMBER_BASE_URL}/tags/{{tag}}/ember.prod.js"
dev: "#{EMBER_BASE_URL}/tags/{{tag}}/ember.js"
EMBER_DATA['tag'] =
prod: "#{EMBER_BASE_URL}/tags/{{tag}}/ember-data.prod.js"
dev: "#{EMBER_BASE_URL}/tags/{{tag}}/ember-data.js"
downloadFile = (src, dest) ->
console.log('Downloading ' + src + ' to ' + dest)
data = ''
request = http.get src, (response) ->
response.on('data', (chunk) ->
data += chunk
)
response.on('end', ->
fs.writeFileSync(dest, data)
)
downloadEmberFile = (src, dest) ->
downloadFile(src, "vendor/ember/#{dest}")
listTags = (user, repo, since, name, command) ->
github.repos.getTags(user: user, repo: repo, (resp, tags) ->
for tag in tags
if semver.valid(tag.name) and !semver.lt(tag.name, since)
firstTag = tag.name unless firstTag
console.log " #{tag.name}"
console.log "Install with cake -t \"#{firstTag}\" #{command}"
)
installEmberFiles = (project, filename, options) ->
if 'tag' of options
# Download a Tag
tag = options.tag
tag = "v#{tag}" unless /^v/.test(tag)
downloadEmberFile(project['tag'].dev.replace(/{{tag}}/, tag),
"development/#{filename}")
downloadEmberFile(project['tag'].prod.replace(/{{tag}}/, tag),
"production/#{filename}")
else
# Download a Channel
channel = options.channel ? 'release'
downloadEmberFile project[channel].dev, "development/#{filename}"
downloadEmberFile project[channel].prod, "production/#{filename}"
# Channel
option '-c', '--channel "[CHANNEL_NAME]"',
'relase, beta, or canary (http://emberjs.com/builds)'
# Tag
option '-t', '--tag "[TAG_NAME]"',
'a tagged release to install. Run cake ember:list to see known tags'
# -----
# Ember
# -----
task 'ember:install', 'install latest Ember', (options) ->
installEmberFiles(EMBER, 'ember.js', options)
task 'ember:list', 'list tagged relases of Ember since v1.0.0', (options) ->
listTags 'emberjs', 'ember.js', 'v1.0.0', 'Ember', 'ember:install'
# ----------
# Ember Data
# ----------
task 'ember-data:install', 'install latest Ember Data', (options) ->
options.channel or= 'beta'
installEmberFiles(EMBER_DATA, 'ember-data.js', options)
task 'ember-data:list', 'list tagged relases of Ember Data', (options) ->
listTags 'emberjs', 'data', 'v0.0.1', 'Ember Data',
'ember-data:install'
# -----------
# Ember Model
# -----------
EMBER_MODEL =
dev: 'http://builds.erikbryn.com/ember-model/ember-model-latest.js'
prod: 'http://builds.erikbryn.com/ember-model/ember-model-latest.prod.js'
task 'ember-model:install', 'install latest Ember Model', (options) ->
downloadEmberFile EMBER_MODEL.dev, 'development/ember-model.js'
downloadEmberFile EMBER_MODEL.prod, 'production/ember-model.js'

97
test/fixtures/Dockerfile/Dockerfile vendored Executable file
View File

@@ -0,0 +1,97 @@
FROM ubuntu:14.04
MAINTAINER Wesley Hales <wesleyhales@gmail.com>
# Install.
RUN \
sed -i 's/# \(.*multiverse$\)/\1/g' /etc/apt/sources.list && \
apt-get update && \
apt-get -y upgrade && \
apt-get install -y build-essential && \
apt-get install -y software-properties-common && \
apt-get install -y byobu curl git htop man unzip vim wget && \
rm -rf /var/lib/apt/lists/*
# Set environment variables.
ENV HOME /root
# Define working directory.
WORKDIR /root
# Install Java.
RUN \
echo oracle-java7-installer shared/accepted-oracle-license-v1-1 select true | debconf-set-selections && \
add-apt-repository -y ppa:webupd8team/java && \
apt-get update && \
apt-get install -y oracle-java7-installer && \
rm -rf /var/lib/apt/lists/* \
echo "done"
# Install Phantom2 build requirements (Won't build on systems < 2GB ram)
RUN \
sudo apt-get update && apt-get -y install g++ flex bison gperf ruby perl \
libsqlite3-dev libfontconfig1-dev libicu-dev libfreetype6 libssl-dev libjpeg-dev libqt5webkit5-dev
#####################################build latest phantom
######################################+++++ only do this in dev when needed
#RUN rm -rf phantomjs
#RUN git clone git://github.com/ariya/phantomjs.git
#RUN cd /root/phantomjs/ && ./build.sh --confirm
#RUN ln -s /root/phantomjs/bin/phantomjs /usr/bin/phantomjs
######################################+++++ END only do this in dev when needed
######################################+++++ comment out when building new version of phantomjs
ADD phantomjs /root/phantomjs
RUN ln -s /root/phantomjs /usr/bin/phantomjs
######################################+++++ END comment out when building new version of phantomjs
RUN git clone git://github.com/wesleyhales/speedgun.git
#RUN mkdir /root/speedgun/core/reports
#VOLUME ["/root/speedgun/core/reports"]
RUN cd speedgun/core && phantomjs --ssl-protocol=any --ignore-ssl-errors=yes speedgun.js http://www.google.com performance csv
RUN cd /root && wget https://dl.dropboxusercontent.com/u/12278845/server.tar
RUN cd /root && tar -xvf server.tar
#RUN echo "cd /root/jboss-as-7.1.1.Final-fluxui/ && ./bin/standalone.sh --server-config=standalone-full.xml -b 0.0.0.0" >> /root/.bashrc
# install maven
RUN sudo apt-get update && apt-get install -y maven
ADD src /root/src
ADD pom.xml /root/pom.xml
RUN mvn clean install
#RUN cp -rf /root/target/speedgun.war /root/jboss-as-7.1.1.Final-fluxui/standalone/deployments/
RUN ln -s /root/target/speedgun /root/jboss-as-7.1.1.Final-fluxui/standalone/deployments/speedgun.war
RUN touch /root/jboss-as-7.1.1.Final-fluxui/standalone/deployments/speedgun.war.dodeploy
# Cleanup old JMS queue
RUN rm -rf /root/jboss-as-7.1.1.Final-fluxui/standalone/tmp/ /root/jboss-as-7.1.1.Final-fluxui/standalone/data/*
RUN mkdir /root/jboss-as-7.1.1.Final-fluxui/speedgun
RUN cd /root/jboss-as-7.1.1.Final-fluxui/speedgun && curl -O https://raw.githubusercontent.com/wesleyhales/speedgun/master/core/speedgun.js
RUN cd /root/jboss-as-7.1.1.Final-fluxui/speedgun && curl -O https://raw.githubusercontent.com/wesleyhales/speedgun/master/core/config.json
COPY server-entrypoint.sh /
ENTRYPOINT ["/server-entrypoint.sh"]
RUN apt-get install -y postgresql-client
COPY speedgun.sql /
EXPOSE 3306 8080 8443
#CMD ["postgres"]

5
test/fixtures/Makefile/Makefile vendored Executable file
View File

@@ -0,0 +1,5 @@
SUBDIRS:=components test
.PHONY: ${SUBDIRS} clean
all:${SUBDIRS}
${SUBDIRS}:
${MAKE} -C $@ all

57
test/fixtures/Maven POM/pom.xml vendored Normal file
View File

@@ -0,0 +1,57 @@
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>awilbur.personal</groupId>
<artifactId>hudsel</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>jar</packaging>
<name>hudsel</name>
<properties>
<suiteXmlFile>src/test/resources/testng.xml</suiteXmlFile>
<skipTests>false</skipTests>
</properties>
<dependencies>
<!-- Adding TestNG for unit test support -->
<dependency>
<groupId>org.testng</groupId>
<artifactId>testng</artifactId>
<version>6.8</version>
</dependency>
<!-- Adding Selenium dependency -->
<dependency>
<groupId>org.seleniumhq.selenium</groupId>
<artifactId>selenium-server</artifactId>
<version>2.41.0</version>
</dependency>
</dependencies>
<build>
<plugins>
<!-- using the compiler plug-in to specify that this project is to be compiled with JDK 1.6 -->
<!-- This is needed so that we get the JDK annotation support that was introduced recently -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.6</source>
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.6</version>
<configuration>
<!-- You can specify a specific testng.xml file here <suiteXmlFiles>
<suiteXmlFile>src/test/resources/testng-sample.xml</suiteXmlFile> </suiteXmlFiles> -->
<!-- Or dynamically with something like '-DsuiteXmlFile=src/test/resources/testng-sample.xml' -->
<suiteXmlFiles>
<suiteXmlFile>${suiteXmlFile}</suiteXmlFile>
</suiteXmlFiles>
<!-- Build with '-DskipTests=true' to bypass test execution @ build time Default: false -->
<skipTests>${skipTests}</skipTests>
<testFailureIgnore>true</testFailureIgnore>
</configuration>
</plugin>
</plugins>
</build>
</project>

View File

@@ -170,10 +170,16 @@ class TestLanguage < Minitest::Test
def test_find_by_extension def test_find_by_extension
assert_equal [], Language.find_by_extension('.factor-rc') assert_equal [], Language.find_by_extension('.factor-rc')
assert_equal [], Language.find_by_extension('foo.rb') assert_equal [Language['Limbo'], Language['M'], Language['MUF'], Language['Mathematica'], Language['Matlab'], Language['Mercury'], Language['Objective-C']], Language.find_by_extension('foo.m')
assert_equal [Language['Ruby']], Language.find_by_extension('rb') assert_equal [Language['Ruby']], Language.find_by_extension('foo.rb')
assert_equal [Language['Ruby']], Language.find_by_extension('.rb') assert_equal [Language['Ruby']], Language.find_by_extension('foo/bar.rb')
assert_equal [Language['Limbo'], Language['M'], Language['MUF'], Language['Mathematica'], Language['Matlab'], Language['Mercury'], Language['Objective-C']], Language.find_by_extension('.m') assert_equal [Language['Ruby']], Language.find_by_extension('PKGBUILD.rb')
assert_equal ['C', 'C++', 'Objective-C'], Language.find_by_extension('foo.h').map(&:name).sort
assert_equal [], Language.find_by_extension('rb')
assert_equal [], Language.find_by_extension('.null')
assert_equal [Language['HTML+Django']], Language.find_by_extension('index.jinja')
assert_equal [Language['Chapel']], Language.find_by_extension('examples/hello.chpl')
assert_equal [], Language.find_by_filename('F.I.L.E.')
end end
def test_find_all_by_extension def test_find_all_by_extension
@@ -186,23 +192,17 @@ class TestLanguage < Minitest::Test
def test_find_by_filename def test_find_by_filename
assert_equal [Language['Shell']], Language.find_by_filename('PKGBUILD') assert_equal [Language['Shell']], Language.find_by_filename('PKGBUILD')
assert_equal [Language['Ruby']], Language.find_by_filename('foo.rb')
assert_equal [Language['Ruby']], Language.find_by_filename('foo/bar.rb')
assert_equal [Language['Ruby']], Language.find_by_filename('Rakefile') assert_equal [Language['Ruby']], Language.find_by_filename('Rakefile')
assert_equal [Language['Ruby']], Language.find_by_filename('PKGBUILD.rb')
assert_equal Language['ApacheConf'], Language.find_by_filename('httpd.conf').first assert_equal Language['ApacheConf'], Language.find_by_filename('httpd.conf').first
assert_equal [Language['ApacheConf']], Language.find_by_filename('.htaccess') assert_equal [Language['ApacheConf']], Language.find_by_filename('.htaccess')
assert_equal Language['Nginx'], Language.find_by_filename('nginx.conf').first assert_equal Language['Nginx'], Language.find_by_filename('nginx.conf').first
assert_equal ['C', 'C++', 'Objective-C'], Language.find_by_filename('foo.h').map(&:name).sort assert_equal [], Language.find_by_filename('foo.rb')
assert_equal [], Language.find_by_filename('rb') assert_equal [], Language.find_by_filename('rb')
assert_equal [], Language.find_by_filename('.null') assert_equal [], Language.find_by_filename('.null')
assert_equal [Language['Shell']], Language.find_by_filename('.bashrc') assert_equal [Language['Shell']], Language.find_by_filename('.bashrc')
assert_equal [Language['Shell']], Language.find_by_filename('bash_profile') assert_equal [Language['Shell']], Language.find_by_filename('bash_profile')
assert_equal [Language['Shell']], Language.find_by_filename('.zshrc') assert_equal [Language['Shell']], Language.find_by_filename('.zshrc')
assert_equal [Language['Clojure']], Language.find_by_filename('riemann.config') assert_equal [Language['Clojure']], Language.find_by_filename('riemann.config')
assert_equal [Language['HTML+Django']], Language.find_by_filename('index.jinja')
assert_equal [Language['Chapel']], Language.find_by_filename('examples/hello.chpl')
assert_equal [], Language.find_by_filename('F.I.L.E.')
end end
def test_find_by_interpreter def test_find_by_interpreter