gjp 0.6.0 → 0.7.0

data/README.md

@@ -15,8 +15,8 @@ Easiest install is via RubyGems:
 ## Usage
 
 Currently available tools:
-* `gjp get-pom JAR` will attempt to find an jar's pom.xml (either from the package itself or through search.maven.org);
-* `gjp get-source-address POM` will attempt to find the SCM Internet address of a pom.xml (from the file itself or through api.github.com);
+* `gjp get-pom NAME` will attempt to find a pom. `NAME` can be a jar file on your disk, a project directory, or simply a `name-version` string. `gjp` will get the pom either from the package itself or through search.maven.org using heuristic searching;
+* `gjp get-source-address POM` will attempt to find the SCM Internet address of a pom.xml at the `POM` filename or URI (from the file itself or through api.github.com);
 * `gjp get-source POM ADDRESS` downloads the source of a pom.xml's project from its SCM at ADDRESS;
 
 ## Source

data/bin/gjp

@@ -15,11 +15,15 @@
 # http://www.gnu.org/licenses/lgpl-2.1.html
 #
 
+if File.exist?(File.join(File.dirname(__FILE__), "..", ".git"))
+  $: << File.join(File.dirname(__FILE__), "..", "lib")
+end
+
 begin
-  require 'gjp'
+  require "gjp"
 rescue LoadError
-  require 'rubygems'
-  require 'gjp'
+  require "rubygems"
+  require "gjp"
 end
 
-MainCommand.run
+Gjp::MainCommand.run

data/lib/gjp.rb

@@ -1,3 +1,4 @@
+require "gjp/logger"
 require "gjp/version"
 require "gjp/logger"
 require "gjp/cli"

data/lib/gjp/cli.rb

@@ -1,51 +1,68 @@
 # encoding: UTF-8
-
+require "gjp/logger"
 require "clamp"
 
-class MainCommand < Clamp::Command
-  subcommand "get-pom", "Retrieves a pom corresponding to a jar" do
-    parameter "JAR", "jar file path"
-    option ["-v", "--verbose"], :flag, "verbose output"
-    option ["--very-verbose"], :flag, "very verbose output"
-    option ["--very-very-verbose"], :flag, "very very verbose output"
-
-    def execute
-      begin
-        init_logger    
-        puts PomGetter.get_pom(jar)
-      rescue Zip::ZipError
-        $stderr.puts "#{jar} does not seem to be a valid jar archive, skipping"
-      rescue TypeError
-        $stderr.puts "#{jar} seems to be a valid jar archive but is corrupt, skipping"
-      rescue RestClient::ResourceNotFound
-        $stderr.puts "Got an error while looking for #{jar} in search.maven.org" 
+# Initialize global logger
+Gjp.logger = ::Logger.new(STDERR)
+Gjp.logger.datetime_format = "%Y-%m-%d %H:%M "
+Gjp.logger.level = ::Logger::INFO
+Gjp.logger.formatter = proc do |severity, datetime, progname, msg|
+  "#{severity.chars.first}: #{msg}\n"
+end
+
+module Gjp
+  class MainCommand < Clamp::Command
+    subcommand "get-pom", "Retrieves a pom corresponding to a filename" do
+      parameter "NAME", "a jar file path, a project directory path or a non-existing filename in the `project-version` form"
+      option ["-v", "--verbose"], :flag, "verbose output"
+      option ["--very-verbose"], :flag, "very verbose output"
+      option ["--very-very-verbose"], :flag, "very very verbose output"
+
+      def configure_log_level(v, vv, vvv)
+        if vvv
+          Gjp.logger.level = Logger::DEBUG
+        elsif vv
+          Gjp.logger.level = Logger::INFO
+        elsif v
+          Gjp.logger.level = Logger::WARN
+        else
+          Gjp.logger.level = Logger::ERROR
+        end
+      end
+
+      def very_very_verbose=(flag)
+        configure_log_level(verbose?, very_verbose?, flag)
+      end
+
+      def very_verbose=(flag)
+        configure_log_level(verbose?, flag, very_very_verbose?)
+      end
+
+      def verbose=(flag)
+        configure_log_level(flag, very_verbose?, very_very_verbose?)
+      end
+      
+      def execute
+        puts Gjp::PomGetter.get_pom(name)
       end
     end
-  end
+      
+    subcommand "get-source-address", "Retrieves a project's SCM Internet address" do
+      parameter "POM", "project's pom file path"
+
+      def execute
+        puts Gjp::SourceAddressGetter.get_source_address(pom)
+      end    
+    end
     
-  subcommand "get-source-address", "Retrieves a project's SCM Internet address" do
-    parameter "POM", "project's pom file path"
-    option ["-v", "--verbose"], :flag, "verbose output"
-    option ["--very-verbose"], :flag, "very verbose output"
-    option ["--very-very-verbose"], :flag, "very very verbose output"
-
-    def execute
-      init_logger
-      puts SourceAddressGetter.get_source_address(pom)
-    end    
-  end
-  
-  subcommand "get-source", "Retrieves a project's source code directory" do
-    parameter "ADDRESS", "project's SCM Internet address"
-    parameter "POM", "project's pom file path"
-    parameter "[DIRECTORY]", "directory in which to save the source code", :default => "."
-    option ["-v", "--verbose"], :flag, "verbose output"
-    option ["--very-verbose"], :flag, "very verbose output"
-    option ["--very-very-verbose"], :flag, "very very verbose output"
-
-    def execute
-      init_logger
-      puts SourceGetter.get_source(address, pom, directory)
-    end    
+    subcommand "get-source", "Retrieves a project's source code directory" do
+      parameter "ADDRESS", "project's SCM Internet address"
+      parameter "POM", "project's pom file path"
+      parameter "[DIRECTORY]", "directory in which to save the source code", :default => "."
+
+      def execute
+        puts Gjp::SourceGetter.get_source(address, pom, directory)
+      end    
+    end
   end
 end

data/lib/gjp/get_pom.rb

@@ -8,81 +8,100 @@ require "pathname"
 
 require "gjp/version_matcher"
 
-# implements the get-pom subcommand
-class PomGetter
+module Gjp
+  # implements the get-pom subcommand
+  class PomGetter
 
-  # returns the pom corresponding to a file or directory, if it can be found
-  def self.get_pom(file)
-    (get_pom_from_dir(file) or get_pom_from_jar(file) or get_pom_from_sha1(file) or get_pom_from_heuristic(file))
-  end
+    def self.log
+      Gjp.logger
+    end
+
+    # returns the pom corresponding to a filename
+    def self.get_pom(filename)
+      (get_pom_from_dir(filename) or get_pom_from_jar(filename) or get_pom_from_sha1(filename) or get_pom_from_heuristic(filename))
+    end
 
-  # returns the pom in a project directory
-  def self.get_pom_from_dir(dir)
-    if File.directory?(dir)
-      pom_path = File.join(dir, "pom.xml")
-      if File.file?(pom_path)
-          $log.info("pom.xml found in #{dir}/pom.xml")
+    # returns the pom in a project directory
+    def self.get_pom_from_dir(dir)
+      if File.directory?(dir)
+        pom_path = File.join(dir, "pom.xml")
+        if File.file?(pom_path)
+          log.info("pom.xml found in #{dir}/pom.xml")
           return File.read(pom_path)
+        end
       end
     end
-  end
-  
-  # returns a pom embedded in a jar file
-  def self.get_pom_from_jar(file)
-    Zip::ZipFile.foreach(file) do |entry|
-      if entry.name =~ /\/pom.xml$/
-        $log.info("pom.xml found in #{file}##{entry.name}")
-        return entry.get_input_stream.read
+    
+    # returns a pom embedded in a jar file
+    def self.get_pom_from_jar(file)
+      begin
+        Zip::ZipFile.foreach(file) do |entry|
+          if entry.name =~ /\/pom.xml$/
+            log.info("pom.xml found in #{file}##{entry.name}")
+            return entry.get_input_stream.read
+          end
+        end
+      rescue Zip::ZipError
+        log.info "#{file} does not seem to be a valid jar archive, skipping"
+      rescue TypeError
+        log.info "#{file} seems to be a valid jar archive but is corrupt, skipping"
       end
+      return nil
     end
-    return nil
-  end
-  
-  # returns a pom from search.maven.org with a jar sha1 search
-  def self.get_pom_from_sha1(file)
-    sha1 = Digest::SHA1.hexdigest File.read(file)
-    results = repository_search({:q => "1:\"#{sha1}\""}).select {|result| result["ec"].include?(".pom")}
-    result = results.first    
-    if result != nil
-      $log.info("pom.xml for #{file} found on search.maven.org for sha1 #{sha1} (#{result["g"]}:#{result["a"]}:#{result["v"]})")
-      return repository_download(result)
+    
+    # returns a pom from search.maven.org with a jar sha1 search
+    def self.get_pom_from_sha1(file)
+      begin
+        if File.file?(file)
+          sha1 = Digest::SHA1.hexdigest File.read(file)
+          results = repository_search({:q => "1:\"#{sha1}\""}).select {|result| result["ec"].include?(".pom")}
+          result = results.first    
+          if result != nil
+            log.info("pom.xml for #{file} found on search.maven.org for sha1 #{sha1} (#{result["g"]}:#{result["a"]}:#{result["v"]})")
+            return repository_download(result)
+          end
+        end
+        return nil
+      rescue RestClient::ResourceNotFound
+        $stderr.puts "Got an error while looking for #{file}'s SHA1 in search.maven.org" 
+      end
     end
-  end
 
-  # returns a pom from search.maven.org with a heuristic name search
-  def self.get_pom_from_heuristic(file)
-    filename = Pathname.new(file).basename.to_s
-    if filename =~ /([^\/]*)\.jar$/
-			my_artifact_id, my_version = VersionMatcher.split_version($1)
+    # returns a pom from search.maven.org with a heuristic name search
+    def self.get_pom_from_heuristic(filename)
+      begin
+        filename = Pathname.new(filename).basename.to_s.sub(/.jar$/, "")
+        my_artifact_id, my_version = VersionMatcher.split_version(filename)
 
-      result = repository_search({:q => my_artifact_id}).first
-      if result != nil
+        result = repository_search({:q => my_artifact_id}).first
+        if result != nil
           results = repository_search({:q => "g:\"#{result["g"]}\" AND a:\"#{result["a"]}\"", :core => "gav"})
           their_versions = results.map {|doc| doc["v"]}
           best_matched_version = if my_version != nil then VersionMatcher.best_match(my_version, their_versions) else their_versions.max end
           best_matched_result = (results.select{|result| result["v"] == best_matched_version}).first
-          
-          $log.warn("pom.xml for #{file} found on search.maven.org with heuristic search (#{best_matched_result["g"]}:#{best_matched_result["a"]}:#{best_matched_result["v"]})")
-          
+            
+          log.warn("pom.xml for #{filename} found on search.maven.org with heuristic search (#{best_matched_result["g"]}:#{best_matched_result["a"]}:#{best_matched_result["v"]})")
+            
           return repository_download(best_matched_result)
+        end
+      rescue RestClient::ResourceNotFound
+        $stderr.puts "Got an error while looking for #{filename} in search.maven.org" 
+      end
+    end
+    
+    # returns a JSON result from search.maven.com
+    def self.repository_search(params)
+        response = RestClient.get "http://search.maven.org/solrsearch/select", {:params => params.merge({"rows" => "100", "wt" => "json"})}
+        json = JSON.parse(response.to_s)
+        return json["response"]["docs"]
+    end
+    
+    # downloads a POM from a search.maven.com search result
+    def self.repository_download(result)
+      if result != nil
+        path = "#{result["g"].gsub(".", "/")}/#{result["a"]}/#{result["v"]}/#{result["a"]}-#{result["v"]}.pom"
+        return (RestClient.get "http://search.maven.org/remotecontent", {:params => {:filepath => path}}).to_s
       end
-		end
-  end
-  
-  # returns a JSON result from search.maven.com
-  def self.repository_search(params)
-    response = RestClient.get "http://search.maven.org/solrsearch/select", {:params => params.merge({"rows" => "100", "wt" => "json"})}
-    json = JSON.parse(response.to_s)
-    return json["response"]["docs"]
-  end
-  
-  # downloads a POM from a search.maven.com search result
-  def self.repository_download(result)
-    if result != nil
-      path = "#{result["g"].gsub(".", "/")}/#{result["a"]}/#{result["v"]}/#{result["a"]}-#{result["v"]}.pom"
-      return (RestClient.get "http://search.maven.org/remotecontent", {:params => {:filepath => path}}).to_s
     end
   end
-  
 end
-

data/lib/gjp/get_source.rb

@@ -2,80 +2,84 @@
 
 require "rest_client"
 
-# implements the get-source subcommand
-class SourceGetter
+module Gjp
+  # implements the get-source subcommand
+  class SourceGetter
+    def self.log
+      Gjp.logger
+    end
 
-  # downloads a project's source into a specified directory
-  def self.get_source(address, pomfile, directory)
-    $log.info("downloading: #{address} in #{directory}, pomfile: #{pomfile}")
-    
-    dummy, prefix, scm_address = address.split(/^([^:]+):(.*)$/)
-    $log.info("prefix: #{prefix}, scm_address: #{scm_address}")
-	
-		get_source_from_scm(prefix, scm_address, pomfile, directory)
-  end
+    # downloads a project's source into a specified directory
+    def self.get_source(address, pomfile, directory)
+      log.info("downloading: #{address} in #{directory}, pomfile: #{pomfile}")
+      
+      dummy, prefix, scm_address = address.split(/^([^:]+):(.*)$/)
+      log.info("prefix: #{prefix}, scm_address: #{scm_address}")
+  	
+  		get_source_from_scm(prefix, scm_address, pomfile, directory)
+    end
 
-  # checks code out from an scm
-  def self.get_source_from_scm(prefix, scm_address, pomfile, directory)
-    pom = Pom.new(pomfile)
-    dir = File.join(directory, "#{pom.group_id}:#{pom.artifact_id}:#{pom.version}")
-		begin
-	    Dir::mkdir(dir)
-		rescue Errno::EEXIST
-			$log.warn("Source directory exists, leaving...")
-		end
-    
-		if prefix == "git"
-			get_source_from_git(scm_address, dir, pom.version)
-    elsif prefix == "svn"
-			get_source_from_svn(scm_address, dir, pom.version)
-		end
-  end
+    # checks code out from an scm
+    def self.get_source_from_scm(prefix, scm_address, pomfile, directory)
+      pom = Pom.new(pomfile)
+      dir = File.join(directory, "#{pom.group_id}:#{pom.artifact_id}:#{pom.version}")
+  		begin
+  	    Dir::mkdir(dir)
+  		rescue Errno::EEXIST
+  			log.warn("Source directory exists, leaving...")
+  		end
+      
+  		if prefix == "git"
+  			get_source_from_git(scm_address, dir, pom.version)
+      elsif prefix == "svn"
+  			get_source_from_svn(scm_address, dir, pom.version)
+  		end
+    end
 
-  # checks code out of git
-	def self.get_source_from_git(scm_address, dir, version)
-		`git clone #{scm_address} #{dir}`
-		
-		Dir.chdir(dir) do
-			tags = `git tag`.split("\n")
-		  
-			if tags.any?
-				best_tag = get_best_tag(tags, version)		 	
-				$log.info("checking out tag: #{best_tag}")
+    # checks code out of git
+  	def self.get_source_from_git(scm_address, dir, version)
+  		`git clone #{scm_address} #{dir}`
+  		
+  		Dir.chdir(dir) do
+  			tags = `git tag`.split("\n")
+  		  
+  			if tags.any?
+  				best_tag = get_best_tag(tags, version)		 	
+  				log.info("checking out tag: #{best_tag}")
 
-				`git checkout #{best_tag}`
-			end	
-		end
-	end
+  				`git checkout #{best_tag}`
+  			end	
+  		end
+  	end
 
-  # checks code out of svn
-	def self.get_source_from_svn(scm_address, dir, version)
-		`svn checkout #{scm_address} #{dir}`
-		
-		Dir.chdir(dir) do
-			tags = `svn ls "^/tags"`.split("\n")
-			
-			if tags.any?
-				best_tag = get_best_tag(tags, version)		 	
-				$log.info("checking out tag: #{best_tag}")
+    # checks code out of svn
+  	def self.get_source_from_svn(scm_address, dir, version)
+  		`svn checkout #{scm_address} #{dir}`
+  		
+  		Dir.chdir(dir) do
+  			tags = `svn ls "^/tags"`.split("\n")
+  			
+  			if tags.any?
+  				best_tag = get_best_tag(tags, version)		 	
+  				log.info("checking out tag: #{best_tag}")
 
-				`svn checkout #{scm_address}/tags/#{best_tag}`
-			end
-		end
-	end
+  				`svn checkout #{scm_address}/tags/#{best_tag}`
+  			end
+  		end
+  	end
 
-	# return the (heuristically) most similar tag to the specified version
-	def self.get_best_tag(tags, version)
-		versions_to_tags =Hash[
-			*tags.map do |tag|
-				[VersionMatcher.split_version(tag)[1], tag]
-			end.flatten
-		]
-			
-	  $log.info("found the following versions and tags: #{versions_to_tags}")
+  	# return the (heuristically) most similar tag to the specified version
+  	def self.get_best_tag(tags, version)
+  		versions_to_tags =Hash[
+  			*tags.map do |tag|
+  				[VersionMatcher.split_version(tag)[1], tag]
+  			end.flatten
+  		]
+  			
+  	  log.info("found the following versions and tags: #{versions_to_tags}")
 
-		best_version = VersionMatcher.best_match(version, versions_to_tags.keys)
-		versions_to_tags[best_version]
-	end
+  		best_version = VersionMatcher.best_match(version, versions_to_tags.keys)
+  		versions_to_tags[best_version]
+  	end
+  end
 end
-

data/lib/gjp/get_source_address.rb

@@ -4,45 +4,50 @@ require "rest_client"
 require "json"
 require "open-uri"
 
-# implements the get-source-address subcommand
-class SourceAddressGetter
+module Gjp
+  # implements the get-source-address subcommand
+  class SourceAddressGetter
+    def self.log
+      Gjp.logger
+    end
 
-  # returns the pom corresponding to a file or directory, if it can be found
-  def self.get_source_address(file)
-    $log.info("looking for source address for: #{file}")
-    (get_source_address_from_pom(file) or get_source_address_from_github(file))
-  end
+    # returns the pom corresponding to a file or directory, if it can be found
+    def self.get_source_address(file)
+      log.info("looking for source address for: #{file}")
+      (get_source_address_from_pom(file) or get_source_address_from_github(file))
+    end
 
-  # returns an scm address in a pom file
-  def self.get_source_address_from_pom(file)
-    pom = Pom.new(file)
-    result = pom.connection_address
+    # returns an scm address in a pom file
+    def self.get_source_address_from_pom(file)
+      pom = Pom.new(file)
+      result = pom.connection_address
 
-    if result != nil
-      $log.info("address found in pom")
-      result
+      if result != nil
+        log.info("address found in pom")
+        result
+      end
     end
-  end
-  
-  # returns an scm address looking for it on github
-  def self.get_source_address_from_github(file)
-    pom = Pom.new(file)
-
-    result = (github_search(pom.artifact_id) or github_search(pom.artifact_id.split("-").first) or github_search(pom.group_id))
     
-    if result != nil
-      $log.info("address found on Github: #{result}")
-      result
+    # returns an scm address looking for it on github
+    def self.get_source_address_from_github(file)
+      pom = Pom.new(file)
+
+      result = (github_search(pom.artifact_id) or github_search(pom.artifact_id.split("-").first) or github_search(pom.group_id))
+      
+      if result != nil
+        log.info("address found on Github: #{result}")
+        result
+      end
     end
-  end
-  
-  # returns a Giuthub repo address based on the keyword
-  def self.github_search(keyword)
-    if keyword != "" and keyword != nil
-      response = RestClient.get "https://api.github.com/legacy/repos/search/" + CGI::escape(keyword), :user_agent => "gjp/" + Gjp::VERSION, :language => "java", :sort => "forks"
-      json = JSON.parse(response.to_s)
     
-      (json["repositories"].map {|repository| "git:" + repository["url"]}).first
+    # returns a Giuthub repo address based on the keyword
+    def self.github_search(keyword)
+      if keyword != "" and keyword != nil
+        response = RestClient.get "https://api.github.com/legacy/repos/search/" + CGI::escape(keyword), :user_agent => "gjp/" + Gjp::VERSION, :language => "java", :sort => "forks"
+        json = JSON.parse(response.to_s)
+      
+        (json["repositories"].map {|repository| "git:" + repository["url"]}).first
+      end
     end
   end
 end

data/lib/gjp/logger.rb

@@ -2,23 +2,16 @@
 
 require "logger"
 
-def init_logger(level = nil)
-  $log = Logger.new(STDERR)
-  $log.level = if level == nil
-    if very_very_verbose?
-      Logger::DEBUG
-    elsif very_verbose?
-      Logger::INFO
-    elsif verbose?
-      Logger::WARN
-    else
-      Logger::ERROR
-    end
-  else
-    level
+module Gjp
+  def self.logger=(logger)
+    @logger = logger
   end
-  
-  $log.formatter = proc do |severity, datetime, progname, msg|
-    "#{severity.chars.first}: #{msg}\n"
+
+  def self.logger
+    @logger ||= Logger.new('/dev/null')
+  end
+
+  def logger
+    Gjp.logger
   end
 end

data/lib/gjp/pom.rb

@@ -1,30 +1,34 @@
-# encoding: UTF-8
+  # encoding: UTF-8
 
 require "nokogiri"
+require "open-uri"
 
-# encapsulates a pom.xml file
-class Pom
-  def initialize(filename)
-    @doc = Nokogiri::XML(File.read(filename))
-    @doc.remove_namespaces!
-  end
-  
-  def connection_address
-    connection_nodes = @doc.xpath("//scm/connection/text()")    
-    if connection_nodes.any?
-      connection_nodes.first.to_s.sub(/^scm:/, "")
+module Gjp
+  # encapsulates a pom.xml file
+  class Pom
+    def initialize(filename)
+      @doc = Nokogiri::XML(open(filename).read)
+      @doc.remove_namespaces!
+    end
+    
+    def connection_address
+      connection_nodes = @doc.xpath("//scm/connection/text()")    
+      if connection_nodes.any?
+        connection_nodes.first.to_s.sub(/^scm:/, "")
+      end
+    end
+    
+    def group_id
+      @doc.xpath("project/groupId/text()").to_s
+    end
+    
+    def artifact_id
+      @doc.xpath("project/artifactId/text()").to_s
+    end
+    
+    def version
+      @doc.xpath("project/version/text()").to_s
     end
-  end
-  
-  def group_id
-    @doc.xpath("project/groupId/text()").to_s
-  end
-  
-  def artifact_id
-    @doc.xpath("project/artifactId/text()").to_s
-  end
-  
-  def version
-    @doc.xpath("project/version/text()").to_s
   end
 end
+

data/lib/gjp/version.rb

@@ -1,5 +1,5 @@
 # encoding: UTF-8
 
 module Gjp
-  VERSION = "0.6.0"
+  VERSION = "0.7.0"
 end

data/lib/gjp/version_matcher.rb

@@ -2,93 +2,92 @@
 
 require "text"
 
-# heuristically matches version strings
-class VersionMatcher 
-
-	# heuristically extracts a version number from a full name
-  # assumes that all leading non-numeric chars are not related the version
-  # returns a version string
-	def self.extract_version(full_name)
-		full_name.sub /^[^0-9]+/, ""
-	end  
+module Gjp
+  # heuristically matches version strings
+  class VersionMatcher 
+    def self.log
+      Gjp.logger
+    end
 
-	# heuristically splits a full name into an artifact name and version string
-  # assumes that version strings begin with a numeric character and are separated
-  # by a ., -, _, ~ or space
-  # returns a [name, version] pair
-	def self.split_version(full_name)	
-    matches = full_name.match(/(.*?)(?:[\.\-\_ ~,]?([0-9].*))?$/)
-    if matches != nil and matches.length > 1
-      [matches[1], matches[2]]
-		else
-			[full_string, nil]
-		end
-	end
+  	# heuristically splits a full name into an artifact name and version string
+    # assumes that version strings begin with a numeric character and are separated
+    # by a ., -, _, ~ or space
+    # returns a [name, version] pair
+  	def self.split_version(full_name)	
+      matches = full_name.match(/(.*?)(?:[\.\-\_ ~,]?([0-9].*))?$/)
+      if matches != nil and matches.length > 1
+        [matches[1], matches[2]]
+  		else
+  			[full_string, nil]
+  		end
+  	end
 
-	# returns the "best match" between a version number and a set of available version numbers
-  # using a heuristic criterion. Idea:
-  #  - split the version number in chunks divided by ., - etc.
-  #  - every chunk with same index is "compared", differences make up a score
-  #  - "comparison" is a subtraction if the chunk is an integer, a string distance measure otherwise
-  #  - score weighs differently on chunk index (first chunks are most important)
-  #  - lowest score wins
-  def self.best_match(my_version, their_versions)
-    $log.debug("version comparison: #{my_version} vs #{their_versions.join(', ')}")
-  
-    my_chunks = my_version.split /[\.\-\_ ~,]/
-    their_chunks_hash = Hash[
-      their_versions.map do |their_version|
-        their_chunks_for_version = their_version.split /[\.\-\_ ~,]/
-        their_chunks_for_version += [nil]*[my_chunks.length - their_chunks_for_version.length, 0].max
-        [their_version, their_chunks_for_version]
-      end
-    ]
+  	# returns the "best match" between a version number and a set of available version numbers
+    # using a heuristic criterion. Idea:
+    #  - split the version number in chunks divided by ., - etc.
+    #  - every chunk with same index is "compared", differences make up a score
+    #  - "comparison" is a subtraction if the chunk is an integer, a string distance measure otherwise
+    #  - score weighs differently on chunk index (first chunks are most important)
+    #  - lowest score wins
+    def self.best_match(my_version, their_versions)
+      log.debug("version comparison: #{my_version} vs #{their_versions.join(', ')}")
     
-    max_chunks_length = ([my_chunks.length] + their_chunks_hash.values.map {|chunk| chunk.length}).max
-    
-    scoreboard = []
-    their_versions.each do |their_version|
-      their_chunks = their_chunks_hash[their_version]
-      score = 0
-      their_chunks.each_with_index do |their_chunk, i|
-        score_multiplier = 100**(max_chunks_length -i -1)
-        my_chunk = my_chunks[i]
-        score += chunk_distance(my_chunk, their_chunk) * score_multiplier
+      my_chunks = my_version.split /[\.\-\_ ~,]/
+      their_chunks_hash = Hash[
+        their_versions.map do |their_version|
+          their_chunks_for_version = their_version.split /[\.\-\_ ~,]/
+          their_chunks_for_version += [nil]*[my_chunks.length - their_chunks_for_version.length, 0].max
+          [their_version, their_chunks_for_version]
+        end
+      ]
+      
+      max_chunks_length = ([my_chunks.length] + their_chunks_hash.values.map {|chunk| chunk.length}).max
+      
+      scoreboard = []
+      their_versions.each do |their_version|
+        their_chunks = their_chunks_hash[their_version]
+        score = 0
+        their_chunks.each_with_index do |their_chunk, i|
+          score_multiplier = 100**(max_chunks_length -i -1)
+          my_chunk = my_chunks[i]
+          score += chunk_distance(my_chunk, their_chunk) * score_multiplier
+        end
+        scoreboard << {:version => their_version, :score => score}
       end
-      scoreboard << {:version => their_version, :score => score}
-    end
-    
-    scoreboard = scoreboard.sort_by {|element| element[:score]}
+      
+      scoreboard = scoreboard.sort_by {|element| element[:score]}
 
-    $log.debug("scoreboard: ")
-    scoreboard.each_with_index do |element, i|
-      $log.debug("  #{i+1}. #{element[:version]} (score: #{element[:score]})")
+      log.debug("scoreboard: ")
+      scoreboard.each_with_index do |element, i|
+        log.debug("  #{i+1}. #{element[:version]} (score: #{element[:score]})")
+      end
+      
+      winner = scoreboard.first
+      
+      if winner != nil
+        return winner[:version]
+      end
     end
     
-    winner = scoreboard.first
-    
-    if winner != nil
-      return winner[:version]
-    end
-  end
-  
-  # returns a score representing the distance between two version chunks
-  # for integers, the score is the difference between their values
-  # for strings, the score is the Levenshtein distance
-  # in any case score is normalized between 0 (identical) and 99 (very different/uncomparable)
-  def self.chunk_distance(my_chunk, their_chunk)
-    if my_chunk == nil
-      my_chunk = "0"
-    end
-    if their_chunk == nil
-      their_chunk = "0"
-    end
-    if my_chunk.is_i? and their_chunk.is_i?
-      return [(my_chunk.to_i - their_chunk.to_i).abs, 99].min
-    else
-      return [Text::Levenshtein.distance(my_chunk.upcase, their_chunk.upcase), 99].min
+    # returns a score representing the distance between two version chunks
+    # for integers, the score is the difference between their values
+    # for strings, the score is the Levenshtein distance
+    # in any case score is normalized between 0 (identical) and 99 (very different/uncomparable)
+    def self.chunk_distance(my_chunk, their_chunk)
+      if my_chunk == nil
+        my_chunk = "0"
+      end
+      if their_chunk == nil
+        their_chunk = "0"
+      end
+      if my_chunk.is_i? and their_chunk.is_i?
+        return [(my_chunk.to_i - their_chunk.to_i).abs, 99].min
+      else
+        return [Text::Levenshtein.distance(my_chunk.upcase, their_chunk.upcase), 99].min
+      end
     end
   end
+
 end
 
 class String
@@ -96,4 +95,3 @@ class String
     !!(self =~ /^[0-9]+$/)
   end
 end
-

data/spec/lib/get_pom_spec.rb

@@ -2,33 +2,33 @@
 
 require 'spec_helper'
 
-describe PomGetter do
+describe Gjp::PomGetter do
   describe ".get_pom" do
     it "gets the pom from a directory" do
       dir_path = File.join("spec", "data", "commons-logging")
       pom_path = File.join(dir_path, "pom.xml")
-      PomGetter.get_pom(dir_path).should eq(File.read(pom_path))
+      Gjp::PomGetter.get_pom(dir_path).should eq(File.read(pom_path))
     end
     
     it "gets the pom from a jar" do
       dir_path = File.join("spec", "data", "commons-logging")
       pom_path = File.join(dir_path, "pom.xml")
       jar_path = File.join(dir_path, "commons-logging-1.1.1.jar")
-      PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
+      Gjp::PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
     end
 
     it "gets the pom from sha1" do
       dir_path = File.join("spec", "data", "antlr")
       pom_path = File.join(dir_path, "pom.xml")
       jar_path = File.join(dir_path, "antlr-2.7.2.jar")
-      PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
+      Gjp::PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
     end
     
     it "gets the pom from a heuristic" do
       dir_path = File.join("spec", "data", "nailgun")
       pom_path = File.join(dir_path, "pom.xml")
       jar_path = File.join(dir_path, "nailgun-0.7.1.jar")
-      PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
+      Gjp::PomGetter.get_pom(jar_path).should eq(File.read(pom_path))
     end         
   end
 end

data/spec/lib/get_source_address_spec.rb

@@ -2,16 +2,16 @@
 
 require 'spec_helper'
 
-describe SourceAddressGetter do
+describe Gjp::SourceAddressGetter do
   describe ".get_source_address" do
     it "gets the source address from a pom file" do
       pom_path = File.join("spec", "data", "commons-logging", "pom.xml")
-      SourceAddressGetter.get_source_address(pom_path).should eq "svn:http://svn.apache.org/repos/asf/commons/proper/logging/tags/commons-logging-1.1.1"
+      Gjp::SourceAddressGetter.get_source_address(pom_path).should eq "svn:http://svn.apache.org/repos/asf/commons/proper/logging/tags/commons-logging-1.1.1"
     end
     
     it "gets the source address from Github" do
       pom_path = File.join("spec", "data", "antlr", "pom.xml")
-      SourceAddressGetter.get_source_address(pom_path).should eq "git:https://github.com/antlr/antlr4"
+      Gjp::SourceAddressGetter.get_source_address(pom_path).should eq "git:https://github.com/antlr/antlr4"
     end
   end
 end

data/spec/lib/get_source_spec.rb

@@ -3,7 +3,7 @@
 require "spec_helper"
 require "fileutils"
 
-describe SourceGetter do
+describe Gjp::SourceGetter do
   describe ".get_source_from_git" do
     it "gets the sources from a git repo" do
       dir_path = File.join("spec", "data", "nailgun")
@@ -13,7 +13,7 @@ describe SourceGetter do
 
       FileUtils.rm_rf(repo_path)
 
-      SourceGetter.get_source("git:git@github.com:martylamb/nailgun.git", pom_path, dir_path)
+      Gjp::SourceGetter.get_source("git:git@github.com:martylamb/nailgun.git", pom_path, dir_path)
 
       File.open(file_path).readline.should eq "nailgun\n"
     end
@@ -28,7 +28,7 @@ describe SourceGetter do
 
       FileUtils.rm_rf(repo_path)
 
-      SourceGetter.get_source("svn:http://svn.apache.org/repos/asf/struts/struts2/tags/STRUTS_2_3_14/apps", pom_path, dir_path)
+      Gjp::SourceGetter.get_source("svn:http://svn.apache.org/repos/asf/struts/struts2/tags/STRUTS_2_3_14/apps", pom_path, dir_path)
 
       File.open(file_path).readline.should eq "README.txt - showcase\n"
     end

data/spec/lib/pom_spec.rb

@@ -2,30 +2,38 @@
 
 require 'spec_helper'
 
-describe Pom do
-  let(:pom) { Pom.new(File.join("spec", "data", "commons-logging", "pom.xml")) }
-  
-  describe "#connection_address" do
-    it "reads the SCM connection address" do
-      pom.connection_address.should eq "svn:http://svn.apache.org/repos/asf/commons/proper/logging/tags/commons-logging-1.1.1"
+describe Gjp::Pom do
+  [ File.join("spec", "data", "commons-logging", "pom.xml"),
+    'http://search.maven.org/remotecontent?filepath=commons-logging/commons-logging/1.1.1/commons-logging-1.1.1.pom'].each do |loc|
+
+    let(:pom) { Gjp::Pom.new(loc) }
+
+    describe "#connection_address" do
+      it "reads the SCM connection address" do
+        pom.connection_address.should eq "svn:http://svn.apache.org/repos/asf/commons/proper/logging/tags/commons-logging-1.1.1"
+      end
+
+      it "reads the SCM connection address from a remote repository" do
+        pom.connection_address.should eq "svn:http://svn.apache.org/repos/asf/commons/proper/logging/tags/commons-logging-1.1.1"
+      end
     end
-  end
-  
-  describe "#group_id" do
-    it "reads the group id" do
-      pom.group_id.should eq "commons-logging"
+
+    describe "#group_id" do
+      it "reads the group id" do
+        pom.group_id.should eq "commons-logging"
+      end
     end
-  end
 
-  describe "#artifact_id" do
-    it "reads the artifact id" do
-      pom.artifact_id.should eq "commons-logging"
+    describe "#artifact_id" do
+      it "reads the artifact id" do
+        pom.artifact_id.should eq "commons-logging"
+      end
     end
-  end
-  
-  describe "#version" do
-    it "reads the version" do
-      pom.version.should eq "1.1.1"
+
+    describe "#version" do
+      it "reads the version" do
+        pom.version.should eq "1.1.1"
+      end
     end
   end
 end

data/spec/lib/version_matcher_spec.rb

@@ -2,63 +2,57 @@
 
 require 'spec_helper'
 
-describe VersionMatcher do      
+describe Gjp::VersionMatcher do      
 	
 	it "splits full names into names and version numbers" do
-		VersionMatcher.split_version("moio-3.2beta1").should eq(["moio", "3.2beta1"])
-		VersionMatcher.split_version("3.2beta1").should eq(["3", "2beta1"])
-		VersionMatcher.split_version("v3.2beta1").should eq(["v", "3.2beta1"])
-	end
-
-	it "extracts version numbers" do
-		VersionMatcher.extract_version("moio-3.2beta1").should eq("3.2beta1")
-		VersionMatcher.extract_version("3.2beta1").should eq("3.2beta1")
-		VersionMatcher.extract_version("v3.2beta1").should eq("3.2beta1")
+		Gjp::VersionMatcher.split_version("moio-3.2beta1").should eq(["moio", "3.2beta1"])
+		Gjp::VersionMatcher.split_version("3.2beta1").should eq(["", "3.2beta1"])
+		Gjp::VersionMatcher.split_version("v3.2beta1").should eq(["v", "3.2beta1"])
 	end
 
 	it "computes chunk distances" do
-		VersionMatcher.chunk_distance(nil, "1").should eq(1)
-		VersionMatcher.chunk_distance("alpha", nil).should eq(5)
+		Gjp::VersionMatcher.chunk_distance(nil, "1").should eq(1)
+		Gjp::VersionMatcher.chunk_distance("alpha", nil).should eq(5)
 		
-		VersionMatcher.chunk_distance("1", "1").should eq(0)
-		VersionMatcher.chunk_distance("1", "9").should eq(8)
-		VersionMatcher.chunk_distance("1", "999").should eq(99)
+		Gjp::VersionMatcher.chunk_distance("1", "1").should eq(0)
+		Gjp::VersionMatcher.chunk_distance("1", "9").should eq(8)
+		Gjp::VersionMatcher.chunk_distance("1", "999").should eq(99)
 
-		VersionMatcher.chunk_distance("snap", "SNAP").should eq(0)
-		VersionMatcher.chunk_distance("snap", "snippete").should eq(5)
-		VersionMatcher.chunk_distance("snap", "l"*999).should eq(99)
+		Gjp::VersionMatcher.chunk_distance("snap", "SNAP").should eq(0)
+		Gjp::VersionMatcher.chunk_distance("snap", "snippete").should eq(5)
+		Gjp::VersionMatcher.chunk_distance("snap", "l"*999).should eq(99)
 		
-		VersionMatcher.chunk_distance("1", "SNAP").should eq(4)
+		Gjp::VersionMatcher.chunk_distance("1", "SNAP").should eq(4)
 		
-		VersionMatcher.chunk_distance("0", "10").should eq(10)
-		VersionMatcher.chunk_distance("0", "9").should eq(9)
+		Gjp::VersionMatcher.chunk_distance("0", "10").should eq(10)
+		Gjp::VersionMatcher.chunk_distance("0", "9").should eq(9)
 	end
 	
 	it "finds the best match" do
 		my_version = "1.0"
 		available_versions = ["1.0", "1", "2.0", "1.0.1", "4.5.6.7.8"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.0")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.0")
 		
 		available_versions = ["3.0", "2.0", "1.0.1"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.0.1")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.0.1")
 
 		available_versions = ["1.snap", "2.0", "4.0.1"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
 
 		available_versions = ["1.10", "1.9", "2.0", "3.0.1"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.9")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.9")
 		
 		my_version = "1.snap"
 		available_versions = ["1.snap", "1"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
 
 		my_version = "1.very-very_very_longish"
 		available_versions = ["1.snap", "1"]
-		VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should eq("1.snap")
 
 		my_version = "1.snap"
 		available_versions = []
-		VersionMatcher.best_match(my_version, available_versions).should be_nil
+		Gjp::VersionMatcher.best_match(my_version, available_versions).should be_nil
 	end
 end
 

data/spec/spec_helper.rb

@@ -3,4 +3,8 @@
 require "gjp"
 require "logger"
 
-init_logger(Logger::INFO)
+Gjp.logger = ::Logger.new(STDERR)
+Gjp.logger.level = ::Logger::INFO
+Gjp.logger.formatter = proc do |severity, datetime, progname, msg|
+  "#{severity.chars.first}: #{msg}\n"
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gjp
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.7.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-03 00:00:00.000000000 Z
+date: 2013-06-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake