snuffle 0.9.1 → 0.10.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6b33ac8a8524d501103f6b30117995298fab5060
-  data.tar.gz: 9f9e2c6e58f44b28fad06aaf7645ec213b6466aa
+  metadata.gz: 585cee4f627767538a301e5a3aba547e9bb98a8e
+  data.tar.gz: 8ba7bbd451845b2f0f583e66c5283e5ad68d7ea7
 SHA512:
-  metadata.gz: 43437ee9b3eb9fae5729d66253d082ecb508d29e4d8e28559fd75de58d8ed51b8da347cdcef25e5ff9a456a96052a1acffc4ad9a46054254b2135dda540cb60a
-  data.tar.gz: 9f1d620ee9123654237e532c3236da8493e6e492f4dcfe791de39746438f126a17017c6c6ea5d81a146e2bc9a9b68bea52297fe5e5f2a89d46681f6e75ffa152
+  metadata.gz: 256627b9c70a1aabea211f082cdf3489e4130aad75ba6905f52fd57f5b3d9d10e6c959d71702674580620510bc7504d9bf9e6dea5e3e132f96c1f18e5a6ebcfa
+  data.tar.gz: 9cff92572661670b3d6562aadff50266951b1addfe7e43e17ff026ef3758f4466da6b268c2f17b412881e0e178f8c5ccf4b8da1bef575e7db88740c2ee7486bb

data/README.md

@@ -2,13 +2,18 @@
 
 Snuffle analyzes source code to identify "data clumps", clusters of attributes
 that are often used together. It uses this analysis to propose objects that
-may be extracted from a given class.
+may be extracted from a given class. It also looks for objects that are hinted
+at by method names and identifies them as "latent objects". For example, if you
+have `home_address` and `work_address` methods in a User class, Snuffle will
+tell you that you might want to extract those methods to a latent Address class.
+
+Please note that Snuffle is still pre-release and will not be ready for serious
+use until it hits version 1.0.0.
 
 ## TODO
 
 * Ignore data clumps called in "loose" class methods (e.g. attr_accessor)
-* Match on string concatenation
-* Consider weighting based on match type
+* Output files in folder hierarchy that mirrors source files
 
 ## Installation
 
@@ -26,13 +31,10 @@ Or install it yourself as:
 
 ## Usage
 
-    $ snuffle check example.rb
+    $ snuffle check lib/example.rb
 
-    +----------------------------+------------+-----------------------------+
-    |          Filename          | Host Class | Candidate Object Attributes |
-    +----------------------------+------------+-----------------------------+
-    | example.rb                 | Customer   | company_name, customer_name |
-    +----------------------------+------------+-----------------------------+
+    Checking lib/example.rb...
+    Results written to doc/snuffle/index.htm
 
 ## Contributing
 

data/lib/snuffle/cli.rb

@@ -5,21 +5,17 @@ module Snuffle
 
   class CLI < Thor
 
-    desc_text = "Formats are text (default, to STDOUT), html, and csv. "
-    desc_text << "Example: snuffle check foo/ -f html"
-
-    desc "check PATH_TO_FILE [-f FORMAT] [-t MAX_COMPLEXITY_ALLOWED]", desc_text
-    method_option :format, :type => :string, :default => 'text', :aliases => "-f"
-
+    desc "snuffle check PATH_TO_FILES", "Example: snuffle app/models/"
     def check(path="./")
       summaries = []
       file_list(path).each do |path_to_file|
+        puts "Checking #{path_to_file}..."
         summary = Snuffle::SourceFile.new(path_to_file: path_to_file).summary
-        report(summary, summary.source)
+        html_report(summary, summary.source)
         summaries << summary
       end
-      create_html_index(summaries)
-      puts results_files.join("\n")
+      create_html_index(summaries, path)
+      puts "Results written to #{results_files.last}"
     end
 
     default_task :check
@@ -39,32 +35,18 @@ module Snuffle
     def report(summary, source)
       text_report(summary)
       cvs_report(summary)
-      html_report(summary, source)
-    end
 
-    def create_html_index(summaries)
-      return unless options['format'] == 'html'
-      results_files << Snuffle::Formatters::HtmlIndex.new(summaries).export
     end
 
-    def cvs_report(summary)
-      return unless options['format'] == 'csv'
-      return unless summary.cohorts.count > 0
-      results_files << Snuffle::Formatters::Csv.new(summary).export
+    def create_html_index(summaries, start_path)
+      results_files << Snuffle::Formatters::HtmlIndex.new(summaries, start_path).export
     end
 
     def html_report(summary, source)
-      return unless options['format'] == 'html'
-      return unless summary.cohorts.count > 0
+      return unless summary.cohorts.count > 0 || summary.latent_objects.count > 0
       results_files << Snuffle::Formatters::Html.new(summary, source).export
     end
 
-    def text_report(summary)
-      return unless options['format'] == 'text'
-      puts
-      puts Snuffle::Formatters::Text.new(summary).export
-    end
-
     def results_files
       @results_files ||= []
     end

data/lib/snuffle/elements/method_definition.rb

@@ -0,0 +1,17 @@
+class Snuffle::Element::MethodDefinition
+
+  attr_accessor :node
+
+  def self.materialize(nodes=[])
+    nodes.each.map{|node| new(node) }
+  end
+
+  def initialize(node)
+    self.node = node
+  end
+
+  def method_name
+    node.name
+  end
+
+end

data/lib/snuffle/formatters/csv.rb

@@ -10,9 +10,6 @@ module Snuffle
       end
 
       def rows
-      #   summary.object_candidates.map do |candidate|
-      #     [summary.path_to_file, summary.class_name, "##{candidate.join(" #")}"].join(',')
-      #   end
         summary.cohorts.group_by{|c| c.values}.map do |cohort|
           [summary.path_to_file, summary.class_name, cohort[0].join("; "), cohort[1].map(&:line_numbers).join("; ")].join(',')
         end

data/lib/snuffle/formatters/html_index.rb

@@ -5,10 +5,11 @@ module Snuffle
 
       include Formatters::Base
 
-      attr_accessor :summaries
+      attr_accessor :summaries, :start_path
 
-      def initialize(summaries)
+      def initialize(summaries, start_path)
         self.summaries = summaries.sort{|a,b| a.cohorts.count <=> b.cohorts.count}.reverse
+        self.start_path = start_path
       end
 
       def header
@@ -18,7 +19,8 @@ module Snuffle
       def content
         Haml::Engine.new(output_template).render(
           Object.new, {
-            summaries: summaries,
+            summaries: self.summaries,
+            start_path: self.start_path,
             date: Time.now.strftime("%Y/%m/%d"),
             time: Time.now.strftime("%l:%M %P")
           }

data/lib/snuffle/formatters/templates/index.html.haml

@@ -2,54 +2,93 @@
 %html
   %head
     %title
-      Fukuzatsu
+      Snuffle
     %link{href: "http://cdn.datatables.net/1.10.0/css/jquery.dataTables.css", rel: "stylesheet"}
 
-    %style{media: "screen", type: "text/css"}
-      body { background: #49525a; color: #fff; font-family: arial, sans-serif; padding: 2em; }
+    :css
+      #{Rouge::Theme.find('thankful_eyes').render(scope: '.highlight')}
+      a:link, a:visited { color: #fff }
+      body { line-height: 1.5em; background: #49525a; color: #fff; font-family: arial, sans-serif; font-size: 14px; padding: 2em; }
+      div.column { float: left; width: 45%; }
+      div.file_listing { padding: .1em; border-radius: 5px; background: #000; width: 100%; border: 1px solid #000;}
+      div.file_meta { padding: 1em; border-radius: 5px; background: #440013; width: 98%; border: .5em solid #000;}
+      h1 { color:#fff; font-size: 1.25em; margin-top: .25em; }
+      h2 { color:#fff; font-size: .75em; margin-top: -1em; }
+      h3 { color:#fff; font-size: 1.1em;margin-top: 1em; }
+      h3.highlighted { background: rgba(170, 161, 57, .6); border-radius: 100px; padding: .25em; padding-left: 1em; color: #000;}
+      h3.highlighted-method { background: rgba(153, 51, 80, .6); border-radius: 100px; padding-left: 1em; }
+      li { margin-bottom: 1em;}
+      pre { line-height: 1.75em;}
+      pre.lineno { margin-top: -1.4em !important;}
+      span.highlighted { padding-left: 1em; display: inline-block; position: absolute; left: 0px; padding-right: 90%}
       table { width: 100%; box-shadow: 0 5px 0 rgba(0,0,0,.8); border-spacing: 0; border: 5px solid #000; border-radius: 5px; border-collapse: collapse; min-width: 50%; }
+      td { text-align: left; padding: .5em; padding-left: 1.25em !important;}
+      tfoot { background: #000; border-top: 10px solid #000; font-family: courier; margin-top: 4em; font-size: .75em;  }
+      th { background: #000; text-align: left; padding: .5em; }
+      tr.even { background: rgba(128, 128, 128, 0.5) !important;}
+      tr.even:hover, tr.odd:hover { background: rgba(128, 128, 128, 0.75) !important;}
+      tr.faint td { opacity: 0.5; font-style: italic; }
+      tr.header { background-color: #222; }
       tr.header th:first-child { border-radius: 5px 0 0 0; }
       tr.header th:last-child { border-radius: 0 5px 0 0; }
       tr.header th:only-child { border-radius: 5px 5px 0 0; }
-      tr.header { background-color: #222; }
-      tr.even { background: rgba(128, 128, 128, 0.5) !important;}
       tr.odd { background: rgba(128, 128, 128, 0.25) !important}
-      tr.even:hover, tr.odd:hover { background: rgba(128, 128, 128, 0.75) !important;}
-      tr.faint td { opacity: 0.5; font-style: italic; }
-      th { background: #000; text-align: left; padding: .5em; }
-      td { text-align: left; padding: .5em; padding-left: 1.25em !important;}
-      td.center { text-align: center; }
-      tfoot { background: #000; border-top: 10px solid #000; font-family: courier; margin-top: 4em; font-size: .75em;  }
-      a:link, a:visited { color: #fff }
-      div.file_meta { float: left; height: 3em; width: 30%; }
-      h1 { color:#fff; font-size: 1.25em; margin-top: .25em; }
-      h2 { color:#fff; font-size: .75em; margin-top: -1em; }
-      h3 { color:#fff; font-size: 1em; float: right; margin-top: 1em; }
+      .center { text-align: center; }
+      .clear { clear: both; }
+      .highlighted { background: rgba(170, 161, 57, .6); border-radius: 100px; }
+      .highlighted-method { background: rgba(153, 51, 80, .6); padding: .25em; border-radius: 100px; color: #fff; }
+      .indented {margin-left: 1em; }
+      .summary {padding: 1em; border-radius: 5px; background: rgb(41, 80, 109); width: 98%; border: .5em solid #000;}
+      .btn {
+        -webkit-border-radius: 28;
+        -moz-border-radius: 28;
+        border: none;
+        border-radius: 28px;
+        color: #ffffff;
+        background: #7d99af;
+        padding: 10px 20px 10px 20px;
+        text-decoration: none;
+      }
+
+      .btn:hover {
+        background: #4c708c;
+        border: none;
+        text-decoration: none;
+      }
+
 
   %body
+
+    .file_meta
+      %h1
+        Snuffle Analysis
+      %h2
+        = start_path
+
+    %br.clear
+
     %table{class: "output-table"}
+
       %thead
-        %tr.header
-          %th{colspan: 3}
-            .file_meta
-              %h1
-                Snuffle Analysis
         %tr
           %th
             File
           %th
             Host Module/Class
           %th
-            Object Candidates
+            Data Clumps
+          %th
+            Latent Objects
       %tbody
         - summaries.each_with_index do |summary, i|
-          %tr{class: "#{i % 2 == 1 ? 'odd' : 'even'} #{summary.cohorts.count == 0 ? 'faint' : ''}"}
+          %tr{class: "#{i % 2 == 1 ? 'odd' : 'even'} #{summary.has_results? ? 'faint' : ''}"}
             %td
-              - if summary.cohorts.count == 0
-                = summary.path_to_file
-              - else
+              - if summary.has_results?
                 %a{href: "source/#{summary.class_filename}.htm"}
                   = summary.path_to_file
+              - else
+                = summary.path_to_file
+
             %td
               - if summary.class_name.size > 30
                 = "..."
@@ -58,14 +97,17 @@
                 = summary.class_name
             %td
               = summary.cohorts.count
-      %tfoot
-        %tr
-          %td.center{colspan: 3}
-            %em
-              Analyzed on
-              = date
-              at
-              = time
-              by
-              %a{href: "https://gitlab.com/coraline/snuffle", target: "_new"}
-                Snuffle
+            %td
+              = summary.latent_objects.count
+
+    %br.clear
+
+    %p.center
+      %em
+        Analyzed on
+        = date
+        at
+        = time
+        by
+        %a{href: "https://gitlab.com/coraline/snuffle", target: "_new"}
+          Snuffle

data/lib/snuffle/formatters/templates/output.html.haml

@@ -7,50 +7,198 @@
     %link{href: "http://cdn.datatables.net/1.10.0/css/jquery.dataTables.css", rel: "stylesheet"}
     %script{language: "javascript", src: "http://code.jquery.com/jquery-1.11.0.min.js", type: "text/javascript"}
     %script{language: "javascript", src: "http://code.jquery.com/jquery-migrate-1.2.1.min.js", type: "text/javascript"}
-    %script{language: "javascript", src: "http://cdn.datatables.net/1.10.0/js/jquery.dataTables.js", type: "text/javascript"}
-
-    %style{media: "screen", type: "text/css"}
-      = Rouge::Theme.find('thankful_eyes').render(scope: '.highlight')
+    %script{language: "javascript", src: "http://cdnjs.cloudflare.com/ajax/libs/highlight.js/8.0/highlight.min.js", type: "text/javascript"}
+    :css
+      #{Rouge::Theme.find('thankful_eyes').render(scope: '.highlight')}
+      a:link, a:visited { color: #fff }
       body { line-height: 1.5em; background: #49525a; color: #fff; font-family: arial, sans-serif; font-size: 14px; padding: 2em; }
-      pre.lineno { margin-top: -1.4em !important;}
-      pre { line-height: 1.75em;}
-      span.highlighted { background: rgba(200, 0, 0, .4); padding-left: 1em; border-radius: 100px; display: inline-block; position: absolute; left: 0px; padding-right: 90%}
-      div.file_meta { padding: 1em; border-radius: 5px; background: #000; height: 3em; width: 98%; }
+      div.column { float: left; width: 45%; }
+      div.file_listing { padding: .1em; border-radius: 5px; background: #000; width: 100%; border: 1px solid #000;}
+      div.file_meta { padding: 1em; border-radius: 5px; background: #440013; width: 98%; border: .5em solid #000;}
       h1 { color:#fff; font-size: 1.25em; margin-top: .25em; }
       h2 { color:#fff; font-size: .75em; margin-top: -1em; }
       h3 { color:#fff; font-size: 1.1em;margin-top: 1em; }
-      = ".indented {margin-left: 4em; }"
-  %body
+      h3.highlighted { background: rgba(170, 161, 57, .6); border-radius: 100px; padding: .25em; padding-left: 1em; color: #000;}
+      h3.highlighted-method { background: rgba(153, 51, 80, .6); border-radius: 100px; padding-left: 1em; }
+      li { margin-bottom: 1em;}
+      pre { line-height: 1.75em;}
+      pre.lineno { margin-top: -1.4em !important;}
+      span.highlighted { padding-left: 1em; display: inline-block; position: absolute; left: 0px; padding-right: 90%}
+      table { width: 100%; box-shadow: 0 5px 0 rgba(0,0,0,.8); border-spacing: 0; border: 5px solid #000; border-radius: 5px; border-collapse: collapse; min-width: 50%; }
+      td { text-align: left; padding: .5em; padding-left: 1.25em !important;}
+      tfoot { background: #000; border-top: 10px solid #000; font-family: courier; margin-top: 4em; font-size: .75em;  }
+      th { background: #000; text-align: left; padding: .5em; }
+      tr.even { background: rgba(128, 128, 128, 0.5) !important;}
+      tr.even:hover, tr.odd:hover { background: rgba(128, 128, 128, 0.75) !important;}
+      tr.faint td { opacity: 0.5; font-style: italic; }
+      tr.header { background-color: #222; }
+      tr.header th:first-child { border-radius: 5px 0 0 0; }
+      tr.header th:last-child { border-radius: 0 5px 0 0; }
+      tr.header th:only-child { border-radius: 5px 5px 0 0; }
+      tr.odd { background: rgba(128, 128, 128, 0.25) !important}
+      .btn.float-right { float: right; margin-top: -4em;}
+      .center { text-align: center; }
+      .clear { clear: both; }
+      .highlighted { background: rgba(170, 161, 57, .6); border-radius: 100px; }
+      .highlighted-method { background: rgba(153, 51, 80, .6); padding: .25em; border-radius: 100px; color: #fff; }
+      .indented {margin-left: 1em; }
+      .summary {padding: 1em; border-radius: 5px; background: rgb(41, 80, 109); width: 98%; border: .5em solid #000;}
+      .btn {
+        -webkit-border-radius: 28;
+        -moz-border-radius: 28;
+        border: none;
+        border-radius: 28px;
+        color: #ffffff;
+        background: #7d99af;
+        padding: 10px 20px 10px 20px;
+        text-decoration: none;
+      }
+
+      .btn:hover {
+        background: #4c708c;
+        border: none;
+        text-decoration: none;
+      }
 
     .file_meta
       %h1
         = summary.class_name
       %h2
         = summary.path_to_file
+      %input.btn.float-right{onclick: "history.back(-1)", type: "button", value: "Back"}
 
-    %h3.indented
-      Candidate object attributes:
+    %br.clear
 
-    %ul.indented
-      - summary.cohorts.group_by{|c| c.values.sort }.each do |values, cohorts|
-        - if cohorts.count > 0
-          %li
-            = values.map{|c| "##{c}" }.join(", ")
-            %br
-            = ":#{cohorts.map(&:line_numbers).join(', :')}"
+    %div.summary
+      %div.column
+        %h3.indented.highlighted
+          Data Clumps:
+        - if summary.cohorts.count == 0
+          %em.indented None
+        - else
+          %ul.indented
+            - summary.cohorts.group_by{|c| c.values.sort }.each do |values, cohorts|
+              - if cohorts.count > 0
+                %li
+                  = values.map{|c| ".#{c}" }.join(", ")
+                  %br
+                  (line
+                  = ":#{cohorts.map(&:line_numbers).join(', :')}"
+                  )
+      %div.column
+        %h3.indented.highlighted-method
+          Possible Latent Objects:
+        - if summary.latent_objects.count == 0
+          %em.indented None
+        - else
+          %ul.indented
+            - summary.latent_objects.each do |latent_object|
+              %li
+                = latent_object.object_candidate.titleize
+                %br
+                (
+                = ".#{latent_object.source_methods.join(', .')}"
+                )
+      %br.clear
 
-    = source_lines
+    %br.clear
+
+    .file_listing
+      = source_lines
 
     %br
-    %input{onclick: "history.back(-1)", type: "button", value: "Back"}
+    %input.btn{onclick: "history.back(-1)", type: "button", value: "Back"}
+
+    %p.center
+      %em
+        Analyzed on
+        = date
+        at
+        = time
+        by
+        %a{href: "https://gitlab.com/coraline/snuffle", target: "_new"}
+          Snuffle
 
     :javascript
 
-      var line_numbers = #{summary.cohorts.map(&:line_numbers).flatten};
+      /*
+       * jQuery Highlight plugin
+       *
+       * Based on highlight v3 by Johann Burkard
+       * http://johannburkard.de/blog/programming/javascript/highlight-javascript-text-higlighting-jquery-plugin.html
+        *
+       * Copyright (c) 2009 Bartek Szopka
+       *
+       * Licensed under MIT license.
+       *
+       */
 
-      $('pre.lineno').html($('pre.lineno').html().split(/\s+/).map(function(val){ if (line_numbers.indexOf(parseInt(val)) > -1) { return "<span class='highlighted'>" + val + "</span>\n" } else { return "<span class='foo'>" + val + "</span>\n"};}))
+      jQuery.extend({
+          highlight: function (node, re, nodeName, className) {
+              if (node.nodeType === 3) {
+                  var match = node.data.match(re);
+                  if (match) {
+                      var highlight = document.createElement(nodeName || 'span');
+                      highlight.className = className || 'highlight';
+                      var wordNode = node.splitText(match.index);
+                      wordNode.splitText(match[0].length);
+                      var wordClone = wordNode.cloneNode(true);
+                      highlight.appendChild(wordClone);
+                      wordNode.parentNode.replaceChild(highlight, wordNode);
+                      return 1; //skip added node in parent
+                  }
+              } else if ((node.nodeType === 1 && node.childNodes) && // only element nodes that have children
+                      !/(script|style)/i.test(node.tagName) && // ignore script and style nodes
+                      !(node.tagName === nodeName.toUpperCase() && node.className === className)) { // skip if already highlighted
+                  for (var i = 0; i < node.childNodes.length; i++) {
+                      i += jQuery.highlight(node.childNodes[i], re, nodeName, className);
+                  }
+              }
+              return 0;
+          }
+      });
 
-      for (i = 0; i <= line_numbers; i ++) {
-        $('.code pre').html($('.code pre').html().split(/\s+/)[i].html("<span class='highlighted'>" + i + "</span>\n"))
-      }
+      jQuery.fn.unhighlight = function (options) {
+          var settings = { className: 'highlight', element: 'span' };
+          jQuery.extend(settings, options);
+
+          return this.find(settings.element + "." + settings.className).each(function () {
+              var parent = this.parentNode;
+              parent.replaceChild(this.firstChild, this);
+              parent.normalize();
+          }).end();
+      };
+
+      jQuery.fn.highlight = function (words, options) {
+          var settings = { className: 'highlight', element: 'span', caseSensitive: false, wordsOnly: false };
+          jQuery.extend(settings, options);
+
+          if (words.constructor === String) {
+              words = [words];
+          }
+          words = jQuery.grep(words, function(word, i){
+            return word != '';
+          });
+          words = jQuery.map(words, function(word, i) {
+            return word.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, "\\$&");
+          });
+          if (words.length == 0) { return this; };
+
+          var flag = settings.caseSensitive ? "" : "i";
+          var pattern = "(" + words.join("|") + ")";
+          if (settings.wordsOnly) {
+              pattern = "\\b" + pattern + "\\b";
+          }
+          var re = new RegExp(pattern, flag);
+
+          return this.each(function () {
+              jQuery.highlight(this, re, settings.element, settings.className);
+          });
+      };
+
+      var line_numbers = #{summary.cohorts.map(&:line_numbers).flatten};
+      var method_names = #{summary.latent_objects.map(&:object_candidate).flatten};
+
+      $('pre.lineno').html($('pre.lineno').html().split(/\s+/).map(function(val){ if (line_numbers.indexOf(parseInt(val)) > -1) { return "<span class='highlighted'>" + val + "</span>\n" } else { return "<span class='foo'>" + val + "</span>\n"};}));
 
+      $('.nf').highlight(method_names, { className: 'highlighted-method'});

data/lib/snuffle/latent_object.rb

@@ -0,0 +1,41 @@
+class Snuffle::LatentObject
+
+  include PoroPlus
+
+  attr_accessor :object_candidate, :source_methods
+
+  DUPLICATE_THRESHOLD = 1
+  STOPWORDS = [
+    "the", "be", "to", "of", "and", "a", "in", "that", "have", "I", "it", "for",
+    "not", "on", "with", "he", "as", "you", "do", "at", "this", "but", "his",
+    "by", "from", "they", "we", "say", "her", "she", "or", "an", "will", "my",
+    "one", "all", "would", "there", "their", "what", "so", "up", "out", "if",
+    "about", "who", "get", "which", "go", "me", "when", "make", "can", "like",
+    "time", "no", "just", "him", "know", "take", "into", "else", "other", "again",
+    "your", "good", "some", "could", "them", "see", "other", "than", "then",
+    "now", "look", "only", "come", "its", "over", "think", "also", "back", "else",
+    "after", "use", "two", "how", "our", "work", "first", "well", "way", "even",
+    "new", "want", "because", "any", "these", "give", "day", "most", "us", "call"
+  ]
+
+  def self.from(nodes)
+    potential_objects_with_methods(nodes).map do |k,v|
+      new(object_candidate: k, source_methods: v)
+    end
+  end
+
+  def self.potential_objects_with_methods(nodes, threshold=DUPLICATE_THRESHOLD)
+    method_candidates = Snuffle::Element::MethodDefinition.materialize(nodes.methods)
+    extract_candidates(method_candidates).select{|k,v| v.count > threshold }
+  end
+
+  def self.extract_candidates(methods)
+    methods.map(&:method_name).inject({}) do |words, method_name|
+      atoms = method_name.split('_') - STOPWORDS
+      atoms.each{ |word| words[word] ||= []; words[word] << method_name }
+      words
+    end
+  end
+
+end
+

data/lib/snuffle/node.rb

@@ -11,6 +11,7 @@ module Snuffle
     scope :by_type,     lambda{|type| where(:type => type)}
     scope :with_parent, lambda{|parent_id| where(parent_id: parent_id) }
     scope :hashes,      {type: :hash}
+    scope :methods,     {is_method: true}
 
     def self.nil
       new(type: :nil)
@@ -33,6 +34,10 @@ module Snuffle
       Snuffle::Node.where(parent_id: self.id)
     end
 
+    def is_method
+      self.type == :def || self.type == :defs
+    end
+
     def inspect
       {
         id: self.id,

data/lib/snuffle/source_file.rb

@@ -23,6 +23,10 @@ module Snuffle
       @cohorts ||= Cohort.from(self.nodes)
     end
 
+    def latent_objects
+      @latent_objects ||= LatentObject.from(self.nodes)
+    end
+
     def source
       return @source if @source
       end_pos = 0
@@ -42,6 +46,7 @@ module Snuffle
         class_name: class_name,
         path_to_file: self.path_to_file,
         cohorts: cohorts,
+        latent_objects: latent_objects,
         source: self.source
       )
     end
@@ -75,7 +80,7 @@ module Snuffle
           extracted_node = Snuffle::Node.new(
             type: ast_node.type,
             parent_id: parent_id,
-            name: name_from(ast_node),
+            name: name,
             line_numbers: lines.map(&:line_number)
           )
         else
@@ -98,9 +103,7 @@ module Snuffle
         if name_coords = node.loc.name
           name = source[name_coords.begin_pos, name_coords.end_pos - 1]
           return unless name =~ /[a-zA-Z]/
-          return name
-        else
-          "?"
+          return name.gsub(/^([A-Za-z0-9\_\?\!]+)(.+)$/m, '\1')
         end
       else
         return name_from(node.children.last)

data/lib/snuffle/summary.rb

@@ -2,12 +2,16 @@ module Snuffle
 
   class Summary
     include PoroPlus
-    attr_accessor :class_name, :path_to_file, :cohorts, :source
+    attr_accessor :class_name, :path_to_file, :cohorts, :latent_objects, :source
 
     def class_filename
       self.class_name.downcase.gsub(' ', '_')
     end
 
+    def has_results?
+      self.cohorts.count != 0 || self.latent_objects.count != 0
+    end
+
   end
 
 end

data/lib/snuffle/version.rb

@@ -1,3 +1,3 @@
 module Snuffle
-  VERSION = "0.9.1"
+  VERSION = "0.10.1"
 end

data/lib/snuffle.rb

@@ -12,11 +12,13 @@ require_relative "snuffle/formatters/csv"
 require_relative "snuffle/formatters/html"
 require_relative "snuffle/formatters/html_index"
 require_relative "snuffle/formatters/text"
+require_relative "snuffle/latent_object"
 require_relative "snuffle/line_of_code"
 require_relative "snuffle/node"
 require_relative "snuffle/source_file"
 require_relative "snuffle/summary"
 require_relative "snuffle/elements/hash"
+require_relative "snuffle/elements/method_definition"
 require_relative "snuffle/util/histogram"
 
 module Snuffle

data/snuffle.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ["coraline@idolhands.com"]
   spec.summary       = %q{Snuffle detects data clumps in your Ruby code.}
   spec.description   = %q{Snuffle detects data clumps and other hints of extractable objects in your Ruby code.}
-  spec.homepage      = ""
+  spec.homepage      = "https://gitlab.com/coraline/snuffle/tree/master"
   spec.license       = "MIT"
 
   spec.files         = `git ls-files -z`.split("\x0")

data/spec/fixtures/latent_object_fixture.rb

@@ -0,0 +1,24 @@
+class Account
+
+  attr_accessor :user
+
+  def initialize(user)
+    self.user = user
+  end
+
+  def status
+  end
+
+  def active?
+  end
+
+  def user_name
+  end
+
+  def user_address
+  end
+
+  def user_email
+  end
+
+end

data/spec/fixtures/program_2.rb

@@ -6,6 +6,9 @@ class Customer
 
   MY_CONSTANT = "TheOtherZachIsThePrimaryZach"
 
+  def self.api_root
+  end
+
   def my_condition
     puts "MAGIC" if true == false
   end

data/spec/fixtures/program_4.rb

@@ -0,0 +1,14 @@
+class LoadedAttrAccessor
+
+  attr_accessor :name, :email, :password
+  attr_accessor :city, :state, :postal_code
+
+  def address
+    {
+      city: city,
+      state: state,
+      postal_code: postal_code
+    }
+  end
+
+end

data/spec/snuffle/latent_object_spec.rb

@@ -0,0 +1,39 @@
+require 'spec_helper'
+
+describe Snuffle::LatentObject do
+
+  let(:program_2) { Snuffle::SourceFile.new(path_to_file: "spec/fixtures/latent_object_fixture.rb") }
+
+  describe ".from" do
+
+    let(:results) { Snuffle::LatentObject.from(program_2.nodes) }
+
+    it "returns an array of LatentObject instances" do
+      expect(results.first.class.name).to eq "Snuffle::LatentObject"
+    end
+
+    it "returns instances with object candidates" do
+      expect(results.first.object_candidate).to eq "user"
+    end
+
+    it "returns instances with source methods" do
+      expect(results.first.source_methods).to eq ["user_name", "user_address", "user_email"]
+    end
+
+  end
+
+  describe ".potential_objects_with_methods" do
+
+    let(:results) { Snuffle::LatentObject.potential_objects_with_methods(program_2.nodes) }
+
+    it "finds repeated words " do
+      expect(results.keys).to eq(["user"])
+    end
+
+    it "finds methods that repeated words appear in" do
+      expect(results['user']).to eq(["user_name", "user_address", "user_email"])
+    end
+
+  end
+
+end

data/spec/snuffle/node_spec.rb

@@ -0,0 +1,18 @@
+require "spec_helper"
+
+Snuffle::Node.class_variable_set(:@@objects, [])
+
+describe Snuffle::Node do
+
+  let(:source)  { Snuffle::SourceFile.new }
+  let(:parent)  { Snuffle::Node.new(id: 1, parent_id: :root, type: :hash) }
+  let(:child_1) { Snuffle::Node.new(id: 2, parent_id: 1, type: :hash) }
+  let(:child_2) { Snuffle::Node.new(id: 3, parent_id: 1, type: :hash) }
+
+  describe ".nil" do
+    it "returns a default object" do
+      expect(Snuffle::Node.nil.type).to eq(:nil)
+    end
+  end
+
+end

data/spec/snuffle/source_file_spec.rb

@@ -3,31 +3,49 @@ require 'pry'
 
 describe Snuffle::SourceFile do
 
-  let(:program_2) {Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_2.rb") }
-  let(:program_3) {Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_3.rb") }
+  let(:program_2) { Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_2.rb") }
+  let(:program_3) { Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_3.rb") }
+  let(:program_4) { Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_4.rb") }
 
-  describe "#object_candidates" do
+  describe "#cohorts" do
 
     it "does not match hash values with non-hash values" do
       attr_accessor_args = ['city', 'postal_code', 'state']
-      values = program_2.summary.object_candidates
+      values = program_2.summary.cohorts.map(&:values)
       expect(values.include?(attr_accessor_args)).to be_falsey
     end
 
     it "matches elements with the same type" do
       args = ['company_name', 'customer_name']
-      values = program_3.summary.object_candidates
+      values = program_3.summary.cohorts.map(&:values)
       expect(values.include?(args)).to be_truthy
     end
 
+    xit "does not match loose class method calls" do
+      values = program_4.summary.cohorts.map(&:values)
+      expect(values.empty?).to be_truthy
+    end
+
+  end
+
+  describe "#name_from" do
+
+    let(:program) { Snuffle::SourceFile.new(path_to_file: "spec/fixtures/latent_object_fixture.rb") }
+    let(:node)    { program.send(:ast).children[2].children[1] }
+
+    it "pulls the name of a method" do
+      expect(program.send(:name_from, node)).to eq('initialize')
+    end
+
   end
 
   describe "#class_name" do
 
-    let(:top_level) { "require 'something'; class Foo; def bar; puts 'hi'; end; end"}
+    let(:top_level)    { "require 'something'; class Foo; def bar; puts 'hi'; end; end"}
     let(:namespaced_1) { "require 'something'; class Foo::Bar; def bar; puts 'hi'; end; end"}
     let(:namespaced_2) { "require 'something'; module Foo; module Bar; class Baz; def bar; puts 'hi'; end; end; end; end"}
-    let(:source_file) { Snuffle::SourceFile.new }
+    let(:namespaced_3) { "class Foo; module Bar; class Baz; class << self; end; end; end; end" }
+    let(:source_file)  { Snuffle::SourceFile.new }
 
     it "picks up a non-nested class name" do
       source_file.source = top_level
@@ -44,7 +62,11 @@ describe Snuffle::SourceFile do
       expect(source_file.class_name).to eq("Foo::Bar::Baz")
     end
 
-  end
+    xit "picks up crazily nested names" do
+      source_file.source = namespaced_3
+      expect(source_file.class_name).to eq("Foo::Bar::Baz")
+    end
 
+  end
 
 end

data/test.rb

@@ -1,5 +1,5 @@
 require 'snuffle'
 
 def source_file
-  @source_file ||= Snuffle::SourceFile.new(path_to_file: "spec/fixtures/program_2.rb")
+  @source_file ||= Snuffle::SourceFile.new(path_to_file: "spec/fixtures/latent_object_fixture.rb")
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: snuffle
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.10.1
 platform: ruby
 authors:
 - Coraline Ada Ehmke
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-17 00:00:00.000000000 Z
+date: 2014-07-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: parser
@@ -200,6 +200,7 @@ files:
 - lib/snuffle/cli.rb
 - lib/snuffle/cohort.rb
 - lib/snuffle/elements/hash.rb
+- lib/snuffle/elements/method_definition.rb
 - lib/snuffle/formatters/base.rb
 - lib/snuffle/formatters/csv.rb
 - lib/snuffle/formatters/html.rb
@@ -207,6 +208,7 @@ files:
 - lib/snuffle/formatters/templates/index.html.haml
 - lib/snuffle/formatters/templates/output.html.haml
 - lib/snuffle/formatters/text.rb
+- lib/snuffle/latent_object.rb
 - lib/snuffle/line_of_code.rb
 - lib/snuffle/node.rb
 - lib/snuffle/source_file.rb
@@ -215,16 +217,20 @@ files:
 - lib/snuffle/version.rb
 - snuffle.gemspec
 - spec/fixtures/account.rb
+- spec/fixtures/latent_object_fixture.rb
 - spec/fixtures/program_1.rb
 - spec/fixtures/program_2.rb
 - spec/fixtures/program_3.rb
+- spec/fixtures/program_4.rb
 - spec/snuffle/elements/hash_spec.rb
+- spec/snuffle/latent_object_spec.rb
 - spec/snuffle/line_of_code_spec.rb
+- spec/snuffle/node_spec.rb
 - spec/snuffle/source_file_spec.rb
 - spec/snuffle/util/histogram_spec.rb
 - spec/spec_helper.rb
 - test.rb
-homepage: ''
+homepage: https://gitlab.com/coraline/snuffle/tree/master
 licenses:
 - MIT
 metadata: {}
@@ -250,11 +256,15 @@ specification_version: 4
 summary: Snuffle detects data clumps in your Ruby code.
 test_files:
 - spec/fixtures/account.rb
+- spec/fixtures/latent_object_fixture.rb
 - spec/fixtures/program_1.rb
 - spec/fixtures/program_2.rb
 - spec/fixtures/program_3.rb
+- spec/fixtures/program_4.rb
 - spec/snuffle/elements/hash_spec.rb
+- spec/snuffle/latent_object_spec.rb
 - spec/snuffle/line_of_code_spec.rb
+- spec/snuffle/node_spec.rb
 - spec/snuffle/source_file_spec.rb
 - spec/snuffle/util/histogram_spec.rb
 - spec/spec_helper.rb