ramper 0.0.1 → 0.0.3

data/.gitignore

@@ -0,0 +1 @@
+*.gem

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,57 @@
+PATH
+  remote: .
+  specs:
+    ramper (0.0.2)
+      code_statistics (= 0.2.13)
+      courgette (= 0.3.0)
+      flay (= 2.6.1)
+      flog (= 4.3.2)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.0.0)
+    code_statistics (0.2.13)
+    commander (4.3.4)
+      highline (~> 1.7.2)
+    courgette (0.3.0)
+      commander
+      graph
+      parser
+    diff-lcs (1.2.5)
+    flay (2.6.1)
+      ruby_parser (~> 3.0)
+      sexp_processor (~> 4.0)
+    flog (4.3.2)
+      ruby_parser (~> 3.1, > 3.1.0)
+      sexp_processor (~> 4.4)
+    graph (2.8.0)
+    highline (1.7.2)
+    parser (2.2.2.6)
+      ast (>= 1.1, < 3.0)
+    rspec (3.3.0)
+      rspec-core (~> 3.3.0)
+      rspec-expectations (~> 3.3.0)
+      rspec-mocks (~> 3.3.0)
+    rspec-core (3.3.1)
+      rspec-support (~> 3.3.0)
+    rspec-expectations (3.3.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.3.0)
+    rspec-mocks (3.3.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.3.0)
+    rspec-support (3.3.0)
+    ruby_parser (3.7.0)
+      sexp_processor (~> 4.1)
+    sexp_processor (4.6.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  ramper!
+  rspec (= 3.3.0)
+
+BUNDLED WITH
+   1.10.5

data/README.md

@@ -0,0 +1,29 @@
+ramper
+======
+
+A ruby gem To help Developers to Ramp Up Faster.
+
+```
+gem install ramper
+```
+
+https://rubygems.org/gems/ramper
+
+```
+######### USAGE ########
+# ramper [a] Gives authorship summary. To figure out who to talk to.
+# ramper [fmc1] [n] Files with most changes
+# ramper [fmc2] [n] Returns top n files with most commit
+# ramper [child] [n] Displays classes that depend on the most other classes.
+# ramper [parent] [n] Displays classes that are depended on by the most other classes.
+# ramper [fmr] [n] Returns the top n recently changed files
+# ramper [flog] [f] Runs the flog metric on a file/dir. Higher numbers = more complex or painful code.
+# ramper [flay] [f] Runs the flay tool on a file/dir. Reports similar blocks of code.
+# ramper [s] Executes rake stats
+# ramper [m] [f] [flags] Computes metrics for a given file based on the flags given. Defaults to computing everything
+# find . -name *.rb -type f | ramper [b] [flags] Batch file metrics for input stream.
+# [flags] -f: flog stats, -a: top author and number of authors, -c: number of commits and first/last commit, -l: lines of code
+# ramper [help] this message
+# ramper [tips] Gives some tips on how to ramp up faster
+########################
+```

data/bin/ramper

@@ -1,45 +1,90 @@
 #!/usr/bin/env ruby
 require 'ramper'
 
-usage =
-"######### USAGE ########
+USAGE = <<END
+######### USAGE ########
+# ramper [a] #{Ramper.author_summary_help}
 # ramper [fmc1] [n] #{Ramper.files_with_most_changes_help}
 # ramper [fmc2] [n] #{Ramper.files_with_most_commit_help}
+# ramper [child] [n] #{Ramper.dependency_in_help}
+# ramper [parent] [n] #{Ramper.dependency_out_help}
+# ramper [fmr] [n] #{Ramper.files_most_recent_help}
+# ramper [flog] [f] #{Ramper.flog_help}
+# ramper [flay] [f] #{Ramper.flay_help}
 # ramper [s] #{Ramper.stats_help}
+# ramper [m] [f] [flags] #{Ramper.file_metrics_help}
+# find . -name *.rb -type f | ramper [b] [flags] #{Ramper.batch_metrics_help}
+# [flags] -f: flog stats, -a: top author and number of authors, -c: number of commits and first/last commit, -l: lines of code
 # ramper [help] this message
-########################"
+# ramper [tips] #{Ramper.tips_help}
+########################
+END
 
-if ARGV.length == 0
-  puts usage
-  exit
-end
 
 def get_n
-  n = 10
-  if ARGV.length == 2
-    if ARGV[1].to_i > 0
-      n = ARGV[1].to_i
+  arg_to_number(1, 10)
+end
+
+def maybe_n
+  arg_to_number(1, false)
+end
+
+def arg_to_number(index, default)
+  n = default
+  if ARGV.length == index + 1
+    if ARGV[index].to_i > 0
+      n = ARGV[index].to_i
     else
-      puts usage
+      puts USAGE
       exit
-    end    
+    end
   end
-
   n
 end
 
-case ARGV[0]
-when 'fmc1'
-  Ramper.files_with_most_changes get_n
-
-when 'fmc2'
-  Ramper.files_with_most_commit get_n
-
-when 's'
-  Ramper.stats
+def get_filename
+  ARGV.length >= 2 ? ARGV[1] : './'
+end
 
-else
-  puts usage
-  exit
+def get_flags
+  ARGV.drop(2)
+end
 
+def compute_metrics
+  if ARGV.length == 0
+    return USAGE
+  end
+  case ARGV[0]
+    when 'fmc1'
+      puts Ramper.files_with_most_changes(get_n)
+    when 'fmc2'
+      Ramper.files_with_most_commit(get_n)
+    when 'fmr'
+      Ramper.files_most_recent(get_n)
+    when 'child'
+      Ramper.dependency_in(maybe_n)
+    when 'parent'
+      Ramper.dependency_out(maybe_n)
+    when 's'
+      Ramper.stats
+    when 'a'
+      Ramper.author_summary
+    when 'flog'
+      Ramper.flog(get_filename)
+    when 'flay'
+      Ramper.flay(get_filename)
+    when 'm'
+      Ramper.file_metrics(get_filename, get_flags)
+    when 'b'
+      Ramper.batch_metrics(get_flags)
+    # TODO: remove this and use parameters
+    when 'test'
+      Ramper.batch_from_most_list([], Ramper.method(:files_most_recent), 10)
+    when 'tips'
+      Ramper.tips
+    else
+      USAGE
+  end
 end
+
+puts compute_metrics

data/lib/dependency_analyzer.rb

@@ -0,0 +1,29 @@
+require 'courgette/directory_analyser'
+
+class DependencyAnalyzer
+  def initialize
+    @graph = Courgette::DirectoryAnalyser.new.tap { |da| da.analyse('**/*.rb') }.graph
+    @stats = @graph.nodes.map { |node| { :in => @graph.dependency_count(node), :out => @graph.depender_count(node), :name => node.join("::") } }
+  end
+  
+  def get_in_stats(n)
+    get_stats(maybe_take(@stats.sort { |a, b| b[:in] <=> a[:in] }, n), :in)
+  end
+  
+  def get_out_stats(n)
+    get_stats(maybe_take(@stats.sort { |a, b| b[:out] <=> a[:out] }, n), :out)
+  end
+  
+  def get_stats(stat_array, stat_index)
+    stat_array.map { |x| "#{x[stat_index]} #{x[:name]}" }.join("\n")
+  end
+
+  private
+  def maybe_take(array, n)
+    if n
+      array.take(n)
+    else
+      array
+    end
+  end
+end

data/lib/ramper.rb

@@ -1,38 +1,154 @@
+require 'dependency_analyzer'
+require 'ramper_file_metrics'
+
 class Ramper
+  VERSION = "0.0.3"
+  
   def self.version
-    puts "0.0.1v"
-  end
-
-  def self.execute(command)
-    puts "#{command}"
-    puts `#{command}`
+    puts VERSION
   end
 
   def self.files_with_most_changes_help
     "Files with most changes"
   end
+  
   def self.files_with_most_changes(n)
-    n =  n+1 # TODO Hack, Below returns n+1 lines
     # http://stackoverflow.com/questions/7686582/finding-most-changed-files-in-git
-    execute("git log --pretty=format: --name-only | sort | uniq -c | sort -rg | head -#{n}")
+    `git log --pretty=format: --name-only | sed '/^$/d' | sort | uniq -c | sort -rg | head -#{n}`
   end
 
   def self.files_with_most_commit_help
     "Returns top n files with most commit"
   end
+  
   def self.files_with_most_commit(n)
     # http://stackoverflow.com/questions/5669621/git-find-out-which-files-have-had-the-most-commits
-    puts `git rev-list --objects --all | awk '$2' | sort -k2 | uniq -cf1 | sort -rn |
+    `git rev-list --objects --all | awk '$2' | sort -k2 | uniq -cf1 | sort -rn |
       while read frequency sample path
-      do 
+      do
          [ "blob" == "$(git cat-file -t $sample)" ] && echo -e "$frequency\t$path";
-      done | head -n #{n}`
+      done | head -#{n}`.gsub(/^-e /, '') #there's a bug with bash adds -e to each line
+  end
+
+  def self.files_most_recent_help
+    "Returns the top n recently changed files"
+  end
+  
+  def self.files_most_recent(n)
+    require 'time'
+    # http://serverfault.com/questions/401437/how-to-retrieve-the-last-modification-date-of-all-files-in-a-git-repository
+    `git ls-tree -r --name-only HEAD | while read filename; do
+      echo "$(git log -1 --format="%at" -- $filename) $filename"
+      done | sort -rg | head -#{n}`.gsub(/^(\d+) /) { |_| "#{Time.at($1.to_i).iso8601} " }
   end
 
   def self.stats_help
     "Executes rake stats"
   end
+  
   def self.stats
-    execute "rake stats"
+    require 'rake'
+    require 'code_statistics'
+    
+    Rake::Task[:stats].execute
+  end
+
+  def self.author_summary_help
+    "Gives authorship summary. To figure out who to talk to."
+  end
+  
+  def self.author_summary
+    # http://stackoverflow.com/questions/1265040/how-to-count-total-lines-changed-by-a-specific-author-in-a-git-repository
+    `git shortlog -sne --no-merges`
+  end
+
+  def self.flog_help
+    "Runs the flog metric on a file/dir. Higher numbers = more complex or painful code."
+  end
+  
+  def self.flog(file)
+    `flog #{file}`
+  end
+
+  def self.flay_help
+    "Runs the flay tool on a file/dir. Reports similar blocks of code."
+  end
+  
+  def self.flay(file)
+    `flay #{file}`
+  end
+
+  def self.dependency_in_help
+    "Displays classes that depend on the most other classes."
+  end
+  
+  def self.dependency_in(n)
+    DependencyAnalyzer.new.get_in_stats n
+  end
+
+  def self.dependency_out_help
+    "Displays classes that are depended on by the most other classes."
+  end
+  
+  def self.dependency_out(n)
+    DependencyAnalyzer.new.get_out_stats n
+  end
+
+  def self.file_metrics_help
+    "Computes metrics for a given file based on the flags given. Defaults to computing everything"
+  end
+
+  def self.file_metrics(file, options)
+    file_metric_calc = RamperFileMetrics.new(options)
+    puts file_metric_calc.process_file_format
+    puts file_metric_calc.process_file(file)
+  end
+
+  def self.batch_metrics_help
+    "Batch file metrics for input stream."
+  end
+
+  def self.batch_metrics(options)
+    file_metric_calc = RamperFileMetrics.new(options)
+    puts file_metric_calc.process_file_format
+    while (line=STDIN.gets)
+      puts file_metric_calc.process_file(line.chomp)
+    end
+    exit
+  end
+
+  def self.batch_from_most_list(options, most_function, most_param)
+    file_metric_calc = RamperFileMetrics.new(options)
+    puts file_metric_calc.process_file_format
+    pull_files_from_stats_list(most_function.call(most_param)).each do |line|
+      puts file_metric_calc.process_file(line)
+    end
+    exit
+  end
+
+  private
+
+  def self.pull_files_from_stats_list(list)
+    list.split("\n").map { |l| /\s(\S*?)$/.match(l) { |_| $1 } }
+  end
+
+  def self.tips_help
+    "Gives some tips on how to ramp up faster"
+  end
+
+  def self.tips
+'######### Tips ########
+# Talk to developer to understand overall architecture, block diagram, dependencies.
+# Use pen and paper (or IDE) and draw UML diagrams like Class Diagram, Sequence Diagrams to understand structure.
+# Follow Top Down Approach. Start from Top View. Then drill down to Mid View and then Low level view features.
+# Build code, Run tests, Run Interface, Change something and see tests fail.
+# Run code in a debugger to see the stack trace/code flow.
+# Use "git grep" to search about git code base. More "git help grep".
+# Jumping around definition and references in an IDE helps a lot.
+# Write a glossary. It can cover class names, function names, datatype names, common prefixes
+#   and file names conventions. This can be contributed back to the project as documentation.
+# Read the test suite. This will give you a better idea of what the library does.
+# Use "git blame" to see when things have been changed.
+########################'
   end
 end

data/lib/ramper_file_metrics.rb

@@ -0,0 +1,103 @@
+require 'flog_cli'
+
+class RamperFileMetrics
+
+  def initialize(flags)
+    if flags.empty?
+      selected = Array.new(CSV_COLS.count, true)
+    else
+      selected    = Array.new(CSV_COLS.count, false)
+      selected[0] = true
+      #TODO: use command line parser
+      #TODO: change array to hash
+      flags.each do |f|
+        case f
+          when '-a'
+            selected[3] = true
+          when '-c'
+            selected[2] = true
+          when '-f'
+            selected[4] = true
+          when '-l'
+            selected[1] = true
+        end
+      end
+    end
+
+    @csv_header       = CSV_COLS.select.with_index { |_, ind| selected[ind] }
+    @selected_metrics = METRICS.select.with_index { |_, ind| selected[ind] }
+  end
+
+  def process_file_format
+    @csv_header.flatten.join(', ')
+  end
+
+  def process_file(file)
+    @selected_metrics.map.with_index do |m, ind|
+      begin
+        m.call(file)
+      rescue => e
+        Array.new(@csv_header[ind].count, "Error #{e.message}".gsub(",", ";"))
+      end
+    end.flatten.join(', ')
+  end
+
+  private
+
+  def self.start_end_dates_commits(file)
+    dates       = `git log -- #{file} | grep 'Date: '`.split("\n")
+    start_date  = DateTime.parse(dates.last.strip.gsub(/Date:   /, ''))
+    end_date    = DateTime.parse(dates.first.strip.gsub(/Date:   /, ''))
+    num_commits = dates.count
+
+    [start_date, end_date, num_commits]
+  end
+
+  def self.lines_of_code(file)
+    `wc -l #{file}`.split(" ").first.strip
+  end
+
+  def self.get_git_author_stats(file)
+    `git log --pretty=short --no-merges -- #{file} | git shortlog -sne`.split("\n")
+  end
+
+  def self.author_stats(file)
+    authors            = get_git_author_stats(file)
+    author_table       = authors.map { |line| /\s+(\d+)\t(.*) <(.*)>/.match(line) { |_| { :count => $1.to_i, :name => $2, :email => $3 } } }
+    unique_email_table = combine_authors(author_table, :email)
+    unique_table       = combine_authors(unique_email_table, :name)
+    num_authors        = unique_table.count
+    top_author         = unique_table.max { |a, b| a[:count] <=> b[:count] }
+    top_author         = "#{top_author[:name]} <#{top_author[:email]}>"
+
+    [top_author, num_authors]
+  end
+
+  def self.combine_authors(original_table, combine_key)
+    other_key  = combine_key == :name ? :email : :name
+    result_map = Hash.new { |h, k| h[k]=[] }
+    original_table.each { |row| result_map[row[combine_key]].push(row.reject { |k, _| k==combine_key }) }
+    result_map.map { |key, val| { :count      => val.inject(0) { |tot_count, x| tot_count + x[:count] },
+                                  combine_key => key,
+                                  other_key   => val.max { |a, b| a[:count] <=> b[:count] }[other_key] } }
+  end
+
+  def self.flog_file(file)
+    if /.*\.rb/.match(file)
+      flogger = FlogCLI.new
+      flogger.flog(file)
+      flog_tot = flogger.total_score.round(2)
+      flog_avg = flogger.average.round(2)
+
+      [flog_tot, flog_avg]
+    else
+      Array.new(2, "N/A")
+    end
+  end
+
+  # self.method blows up unless it is after the functions are defined
+  CSV_COLS = ['File', 'LOC', ['First edit', 'Most recent edit', '# of commits'],
+              ['Top author', '# of authors'], ['Flog score', 'Flog/method average']]
+  METRICS  = [Proc.new { |x| x }, self.method(:lines_of_code), self.method(:start_end_dates_commits),
+              self.method(:author_stats), self.method(:flog_file)]
+end

data/ramper.gemspec

@@ -0,0 +1,24 @@
+$:.unshift File.expand_path('../lib', __FILE__)
+require 'ramper'
+
+Gem::Specification.new do |s|
+  s.name          = 'ramper'
+  s.version       = Ramper::VERSION
+  s.date          = '2015-07-20'
+  s.summary       = "ramper!"
+  s.description   = "Ramp Up!"
+  s.authors       = ["Ankush Raina"]
+  s.email         = 'araina@groupon.com'
+  s.files         = `git ls-files -z`.split("\x0")
+  s.require_paths = ["lib"]
+  s.homepage      = 'http://rubygems.org/gems/ramper'
+  s.license       = 'Groupon Inc'
+  s.executables << 'ramper'
+
+  s.add_runtime_dependency "flog", ["4.3.2"]
+  s.add_runtime_dependency "flay", ["2.6.1"]
+  s.add_runtime_dependency "courgette", ["0.3.0"]
+  s.add_runtime_dependency "code_statistics", ["0.2.13"]
+
+  s.add_development_dependency "rspec", ["3.3.0"]
+end

data/spec/ramper_file_metrics_spec.rb

@@ -0,0 +1,56 @@
+require 'rspec'
+require 'ramper_file_metrics'
+
+describe 'RamperFileMetrics' do
+
+  context '.combine_authors' do
+    it 'should return the same table if it has no dupes in the given field: email' do
+      orig = [{ :count => 2, :name => 'name', :email => 'email1' },
+              { :count => 2, :name => 'name', :email => 'email2' },
+              { :count => 2, :name => 'name', :email => 'email3' }]
+      RamperFileMetrics.combine_authors(orig, :email).should == orig
+    end
+    it 'should return the same table if it has no dupes in the given field: name' do
+      orig = [{ :count => 2, :name => 'name1', :email => 'email' },
+              { :count => 2, :name => 'name2', :email => 'email' },
+              { :count => 2, :name => 'name3', :email => 'email' }]
+      RamperFileMetrics.combine_authors(orig, :name).should == orig
+    end
+
+    it 'should combine elements if it has dupes in the given field: email' do
+      orig = [{ :count => 1, :name => 'name1', :email => 'email' },
+              { :count => 2, :name => 'name2', :email => 'email' },
+              { :count => 3, :name => 'name3', :email => 'email' }]
+      new  = [{ :count => 6, :name => 'name3', :email => 'email' }]
+      RamperFileMetrics.combine_authors(orig, :email).should == new
+    end
+
+    it 'should combine elements if it has dupes in the given field: name' do
+      orig = [{ :count => 1, :name => 'name', :email => 'email1' },
+              { :count => 2, :name => 'name', :email => 'email2' },
+              { :count => 3, :name => 'name', :email => 'email3' }]
+      new  = [{ :count => 6, :name => 'name', :email => 'email3' }]
+      RamperFileMetrics.combine_authors(orig, :name).should == new
+    end
+  end
+
+  context '.author_stats' do
+
+    it 'should have resolved duplicates in either field' do
+      RamperFileMetrics.stub(:get_git_author_stats).and_return(["     8	j1 <j>",
+                                                                "     5	a <a1>",
+                                                                "     3	a <a2>",
+                                                                "     1	j2 <j>"])
+      RamperFileMetrics.author_stats('').should == ["j1 <j>", 2]
+    end
+
+    it 'should have combined by email first' do
+      RamperFileMetrics.stub(:get_git_author_stats).and_return(["     8	j1 <j>",
+                                                                "     5	a1 <a1>",
+                                                                "     3	a2 <a2>",
+                                                                "     4	a1 <a2>",
+                                                                "     1	j2 <j>"])
+      RamperFileMetrics.author_stats('').should == ["a1 <a2>", 2]
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ramper
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,8 +9,88 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-07-19 00:00:00.000000000 Z
-dependencies: []
+date: 2015-07-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: flog
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 4.3.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 4.3.2
+- !ruby/object:Gem::Dependency
+  name: flay
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.6.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 2.6.1
+- !ruby/object:Gem::Dependency
+  name: courgette
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+- !ruby/object:Gem::Dependency
+  name: code_statistics
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.2.13
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.2.13
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 3.3.0
 description: Ramp Up!
 email: araina@groupon.com
 executables:
@@ -18,8 +98,16 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/ramper.rb
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- README.md
 - bin/ramper
+- lib/dependency_analyzer.rb
+- lib/ramper.rb
+- lib/ramper_file_metrics.rb
+- ramper.gemspec
+- spec/ramper_file_metrics_spec.rb
 homepage: http://rubygems.org/gems/ramper
 licenses:
 - Groupon Inc