style-scanner 0.0.6 → 0.0.7

data/lib/style_scanner/problems/base.rb

@@ -29,7 +29,9 @@ module StyleScanner
 
     def self.problem_class_names_from_dir
       Dir[(File.dirname(__FILE__) + "/../sentence_scans/*.rb")].
-        map {|filename| File.basename(filename, ".rb").split("_").map(&:capitalize).join } - ["Base"]
+      map {|filename| File.basename(filename, ".rb").
+      split("_").
+      map(&:capitalize).join } - ["Base"]
     end
 
     def self.dynamically_generate_problem_classes

data/lib/style_scanner/profiling_helpers.rb

@@ -1,8 +1,8 @@
+require 'ruby-prof'
 module StyleScanner
   module ProfilingHelpers
 
     def start_profiling
-      require 'ruby-prof'
       RubyProf.start
     end
 

data/lib/style_scanner/sentence.rb

@@ -28,7 +28,7 @@ module StyleScanner
       text_to_scan = text
       text_to_scan = stemmed_verbs if options[:stem_verbs]
       text_to_scan = text_to_scan.downcase if options[:strip_case]
-      text_to_scan.match /\b#{word}\b/
+      text_to_scan.match(/\b#{word}\b/) 
     end
 
     def user_friendly_readout

data/lib/style_scanner/sentence_scans/capitalization.rb

@@ -18,7 +18,9 @@ module StyleScanner
       )
 
       def scan
-        flag_lowercase(MONTHS)
+        flag_lowercase(MONTHS) do |word|
+          word == "may" && word.verb?
+        end
         flag_lowercase(ACRONYMS)
         flag_lowercase(DAYS)
         flag_lowercase(NATIONALITIES)
@@ -41,14 +43,22 @@ module StyleScanner
       end
 
       def flag_uppercase(collection)
-        collection.each do |word|
-          create_problem(word.downcase) if sentence.contains?(word, :strip_case => false)
-        end
+        flag_case_problem(collection, :downcase)
+      end
+
+      def flag_lowercase(collection, &skipping_conditions)
+        flag_case_problem(collection, :capitalize, &skipping_conditions)
       end
 
-      def flag_lowercase(collection)
-        collection.each do |word|
-          create_problem(word.capitalize) if sentence.contains?(word, :strip_case => false)
+      def flag_case_problem(collection, problem_case, &skipping_conditions)
+        words.each do |word|
+        # skip if the proc, when called with the tagged word, evaluates to true
+          next if skipping_conditions && skipping_conditions.call(word)
+
+          collection.each do |capitalization_word| 
+            create_problem(capitalization_word.send problem_case) if sentence.contains?(capitalization_word, :strip_case => false) && word == capitalization_word
+          end
+
         end
       end
 

data/lib/style_scanner/sentence_scans/ugly_word.rb

@@ -7,7 +7,7 @@ module StyleScanner
 
       def scan
         WORD_PAIRS.keys.each do |offender|
-          create_problem(replacement_word(offender)) if sentence.contains?(offender) 
+          create_problem("replace #{offender} with #{replacement_word(offender)}") if sentence.contains?(offender) 
         end
       end
 

data/lib/style_scanner/string.rb

@@ -8,7 +8,7 @@ module StyleScanner
 
     def stem_verbs
       strip_punctuation.split.map do |word|
-        is_a_verb?(word) ? word.stem : word
+        word.verb? ? word.stem : word
       end.join(" ")
     end
 
@@ -20,14 +20,12 @@ module StyleScanner
       @stemmed_verbs
     end 
 
-    private
-
-    def is_a_verb?(word)
-      tag(word).start_with?("V")
+    def verb?
+      tag.start_with?("V")
     end
 
-    def tag(word)
-      Tagger.new(self).tagged_words.find {|tagged_word| tagged_word.word == word}.tag
+    def tag
+      Tagger.new(self).tagged_words.find {|tagged_word| tagged_word.word == self }.tag
     rescue NoMethodError
       "Unknown"
     end

data/lib/style_scanner/tagged_word.rb

@@ -13,6 +13,10 @@ module StyleScanner
       @word = word 
     end
 
+    def ==(string)
+      word == string
+    end
+
     def tokenized
       word.downcase.gsub(/\W/, "")
     end
@@ -46,7 +50,8 @@ module StyleScanner
     end
 
     def verb?
-      tag.start_with?("V")
+      # account for modal verbs like may
+      tag.start_with?("V") || tag == "MD"
     end
 
     # Gerund verb = ING verb

data/lib/style_scanner/tagger.rb

@@ -19,6 +19,7 @@ module StyleScanner
       def parts_of_speech_tagger
         @eng_tagger ||= EngTagger.new
       end
+
     end
 
   end

data/lib/style_scanner/version.rb

@@ -1,3 +1,3 @@
 module StyleScanner
-  VERSION = "0.0.6"
+  VERSION = "0.0.7"
 end

data/readme.textile

@@ -1,6 +1,6 @@
-h1. Style
+h1. Style-Scanner
 
-Style, written by Jack Kinsella ("blog":http://www.jackkinsella.ie), helps you improve your English language writing. Based on stylistic advice given by authors such as Skunk and White, Bill Bryson and George Orwell, Style scans your text and markup files then lists issues found. Currently it spots the following problems:
+Style-Scanner, written by Jack Kinsella ("blog":http://www.jackkinsella.ie), helps you improve your English language writing. Based on stylistic advice given by authors such as Skrunk and White, Bill Bryson and George Orwell, Style-Scanner scans your text and markup files then lists issues found. Currently it spots the following problems:
 
 * *Use of 600 different clichés*
   He pushed the envelope
@@ -24,28 +24,31 @@ addd
 We went to the the shopping centre.
 * *Excess white space*
 We went   to the shopping centre.
+* *Capitalization Problems*
+On monday we will have an exam.
 
-_Linguistic analysis is a hard problem, so you cannot expect perfect results. Think of Style as guidelines to steer you in the right direction._
+_Linguistic analysis is a hard problem, so you cannot expect perfect results. Think of Style-Scanner as guidelines to alert you of
+possible faults. *Remember at best prescriptive stylistic guides can bring you up to a B minus standard of writing. * Anything more is beyond the scope of this tool._
 
 h2. Installation 
 
-Install Style using Ruby gems:
+Install Style-Scanner using Ruby gems:
 
 @gem install style-scanner@
 
-Next install Hunspell, an open source spell-checker that Style depends upon.
+Next install Hunspell, an open source spell-checker that Style-Scanner depends upon.
 
 @brew install hunspell@
 
 h2. Usage
 
-Style is command line only. Cd into the directory with the files you'd like to scan, then type 
+Style-Scanner is command line only. Cd into the directory with the files you'd like to scan, then type 
 
 @style-scanner filename@
 
-After a few seconds Style will print a list problems it finds.
+After a few seconds Style-Scanner will print a list problems it finds.
 
-Style is pipe friendly. 
+Style-Scanner is pipe friendly. 
 
 @cat filename | style-scanner@
 
@@ -76,6 +79,12 @@ Formats terminal output in red,green and other colours.
 "entagger":http://engtagger.rubyforge.org/
 Assigns parts of speech tags to English text based on a lookup dictionary and a set of probability values.
 
+"RedCloth":http://redcloth.org/
+Converts Textile to HTML
+
+"Sanitize":https://github.com/rgrove/sanitize
+Converts HTML to plain text
+
 h3. Other
 
 "Hunspell":http://hunspell.sourceforge.net/
@@ -87,51 +96,51 @@ Contribution is welcomed and encouraged, although no modifications will be accep
 
 h3. Parts of Speech
 
- | Tag | Part Of Speech | Examples |
-  |CC      | Conjunction, coordinating |              and, or |
-  | CD      | Adjective, cardinal number              | 3, fifteen |
-  | DET     | Determiner                              | this, each, some |
-  EX      Pronoun, existential there              there
-  FW      Foreign words
-  IN      Preposition / Conjunction               for, of, although, that
-  JJ      Adjective                               happy, bad
-  JJR     Adjective, comparative                  happier, worse
-  JJS     Adjective, superlative                  happiest, worst
-  LS      Symbol, list item                       A, A.
-  MD      Verb, modal                             can, could, 'll
-  NN      Noun                                    aircraft, data
-  NNP     Noun, proper                            London, Michael
-  NNPS    Noun, proper, plural                    Australians, Methodists
-  NNS     Noun, plural                            women, books
-  PDT     Determiner, prequalifier                quite, all, half
-  POS     Possessive                              's, '
-  PRP     Determiner, possessive second           mine, yours
-  PRPS    Determiner, possessive                  their, your
-  RB      Adverb                                  often, not, very, here
-  RBR     Adverb, comparative                     faster
-  RBS     Adverb, superlative                     fastest
-  RP      Adverb, particle                        up, off, out
-  SYM     Symbol                                  *
-  TO      Preposition                             to
-  UH      Interjection                            oh, yes, mmm
-  VB      Verb, infinitive                        take, live
-  VBD     Verb, past tense                        took, lived
-  VBG     Verb, gerund                            taking, living
-  VBN     Verb, past/passive participle           taken, lived
-  VBP     Verb, base present form                 take, live
-  VBZ     Verb, present 3SG -s form               takes, lives
-  WDT     Determiner, question                    which, whatever
-  WP      Pronoun, question                       who, whoever
-  WPS     Determiner, possessive & question       whose
-  WRB     Adverb, question                        when, how, however
-  PP      Punctuation, sentence ender             ., !, ?
-  PPC     Punctuation, comma                      ,
-  PPD     Punctuation, dollar sign                $
-  PPL     Punctuation, quotation mark left        ``
-  PPR     Punctuation, quotation mark right       ''
-  PPS     Punctuation, colon, semicolon, elipsis  :, ..., -
-  LRB     Punctuation, left bracket               (, {, [
-  RRB     Punctuation, right bracket              ), }, ]
+| Tag | Part Of Speech | Examples |
+|CC      | Conjunction, coordinating | and, or |
+| CD      | Adjective, cardinal number              | 3, fifteen |
+| DET     | Determiner                              | this, each, some |
+|EX|        Pronoun, existential there             |there |
+|FW|        Foreign words ||
+|IN|        Preposition / Conjunction              |for, of, although, that |
+|JJ|        Adjective                              |happy, bad |
+|JJR|        Adjective, comparative                | happier, worse |
+|JJS|        Adjective, superlative                | happiest, worst |
+|LS|        Symbol, list item                      |A, A. |
+|MD|        Verb, modal                            |can, could, 'll |
+|NN|        Noun                                   |aircraft, data |
+|NNP|        Noun, proper                          | London, Michael |
+|NNPS|        Noun, proper, plural                 |  Australians, Methodists |
+|NNS|        Noun, plural                          | women, books |
+|PDT|        Determiner, prequalifier              | quite, all, half |
+|POS|        Possessive                            | 's, ' |
+|PRP|        Determiner, possessive second         | mine, yours |
+|PRPS|        Determiner, possessive               |  their, your |
+|RB|        Adverb                                 |often, not, very, here |
+|RBR|        Adverb, comparative                   | faster |
+|RBS|        Adverb, superlative                   | fastest |
+|RP|        Adverb, particle                       |up, off, out |
+|SYM|        Symbol                                | * |
+|TO|        Preposition                            |to |
+|UH|        Interjection                           |oh, yes, mmm |
+|VB|        Verb, infinitive                       |take, live |
+|VBD|        Verb, past tense                      | took, lived |
+|VBG|        Verb, gerund                          | taking, living |
+|VBN|        Verb, past/passive participle         | taken, lived |
+|VBP|        Verb, base present form               | take, live |
+|VBZ|        Verb, present 3SG -s form             | takes, lives |
+|WDT|        Determiner, question                  | which, whatever |
+|WP|        Pronoun, question                      |who, whoever |
+|WPS|        Determiner, possessive & question     | whose |
+|WRB|        Adverb, question                      | when, how, however |
+|PP|        Punctuation, sentence ender            |., !, ? |
+|PPC|        Punctuation, comma                    | , |
+|PPD|        Punctuation, dollar sign              | $ |
+|PPL|        Punctuation, quotation mark left      | `` |
+|PPR|        Punctuation, quotation mark right     | '' |
+|PPS|        Punctuation, colon, semicolon, elipsis| :, ..., - |
+|LRB|        Punctuation, left bracket             | (, {, [ |
+|RRB|        Punctuation, right bracket            | ), }, ] |
 
 h2. Roadmap
 
@@ -142,9 +151,13 @@ h2. Roadmap
 8 Tense switches
 9 Improve tests by:
 a Creating a sentence helper
-b Making a better Rspec match (more informative erros)
+b Making a better Rspec matcher (more informative erros)
 c Automatically detecting the correct problem
-11 Performance tests
+10 Desktop app
+11 Globalize spell check
+12 Most overused words
+13 Suggestions for synonyms
+14 Code overview screencast
 
 h2. Contributors
 
@@ -153,5 +166,5 @@ Robert Dooley, developer in Galway Western, Ireland
 
 h2. Licence
 
-Style is released under the "MIT license":www.opensource.org/licenses/MIT
+Style-Scanner is released under the "MIT license":www.opensource.org/licenses/MIT
 Copyright "Jack Kinsella":www.jackkinsella.ie

data/spec/fixtures/sample_text.txt

@@ -1,2 +1,18 @@
-Making a cliché scanner is easier said than done. The devil is really in
-the details. We worked balls to the wall to get this working.
+Many people think that working on your language style is unimporant.
+I disagree. I prefer to use language instead of utilizing it.
+
+Good communication is easier said than done. An important point in good English language usuage is using English instead of Latin or French. E.g. Outside of academic contexts where space is in short supply it sounds pretentious to write e.g. instead of for example.
+
+I commonly make writing errors which can be spotted mechanically. For instance I   have  too much whitespace. I might might repeat a word
+twice in a row, by accident. I may use a fantastic adjective twice in the same fanstastic sentence without knowing it. I might make mistakes
+with capitalization, especially when I'm tired on a monday.  
+
+Sometimes I use words that add very little to a sentence. And sometimes sentences are written in a passive tense, robbing them of their verbal punch and concission.
+
+Style-Scanner is my solution. It's far from finished, but I'd invite any
+interested language hackers to participate. 
+
+Jack Kinsella
+Founder Bolivian Express
+Founder Oxbridge Notes
+Twitter @jackkinsella

data/spec/integrations/command_line_spec.rb

@@ -16,7 +16,7 @@ module StyleScanner
     end
 
     it "calls the scanner when cmd line called with a file" do
-      %x(style '#{file}').should match "cliché"
+      %x(style-scanner '#{file}').should match "cliché"
     end
 
     it "works with HTML input" do

data/spec/sentence_scans/capitalization_spec.rb

@@ -9,6 +9,8 @@ module StyleScanner
       let(:season) {Sentence.new("We travelled to England in the Summer.")}
       let(:month) {Sentence.new("We travelled to England in march.")}
       let(:uppercase_month) {Sentence.new("We travelled to England in March.")}
+      let(:may_month) {Sentence.new("Reaching deals with Indian bureaucrats and Chinese mandarins set to defend the interests and the data of their countries rapidly growing online firms may be downright impossible.")}
+      let(:may_verb) {Sentence.new "Reaching deals may be impossible."}
       let(:day) {Sentence.new "We arrive on wednesday"}
 
       it "catches lowercase months" do
@@ -26,6 +28,12 @@ module StyleScanner
       it "flags wrongly capitalized seasons" do
         should_problem season, Problems::Capitalization
       end
+      it "flags may month lowercase" do
+        should_problem may_month, Problems::Capitalization
+      end
+      it "does not flay may the verb" do
+        should_not_problem may_verb, Problems::Capitalization
+      end
       it "catches nationalities and languages" do
         should_problem nationality, Problems::Capitalization
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: style-scanner
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
   prerelease: 
 platform: ruby
 authors:
@@ -9,12 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-01 00:00:00.000000000 +01:00
-default_executable: 
+date: 2012-02-28 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: punkt-segmenter
-  requirement: &2152642100 !ruby/object:Gem::Requirement
+  requirement: &2156771100 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152642100
+  version_requirements: *2156771100
 - !ruby/object:Gem::Dependency
   name: engtagger
-  requirement: &2152641680 !ruby/object:Gem::Requirement
+  requirement: &2156724140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152641680
+  version_requirements: *2156724140
 - !ruby/object:Gem::Dependency
   name: colorize
-  requirement: &2152641260 !ruby/object:Gem::Requirement
+  requirement: &2156722600 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +43,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152641260
+  version_requirements: *2156722600
 - !ruby/object:Gem::Dependency
   name: sanitize
-  requirement: &2152640780 !ruby/object:Gem::Requirement
+  requirement: &2156720920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +54,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152640780
+  version_requirements: *2156720920
 - !ruby/object:Gem::Dependency
   name: trollop
-  requirement: &2152640240 !ruby/object:Gem::Requirement
+  requirement: &2156720000 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -66,10 +65,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152640240
+  version_requirements: *2156720000
 - !ruby/object:Gem::Dependency
   name: RedCloth
-  requirement: &2152639800 !ruby/object:Gem::Requirement
+  requirement: &2156718700 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -77,10 +76,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2152639800
+  version_requirements: *2156718700
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2152639380 !ruby/object:Gem::Requirement
+  requirement: &2156717720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -88,10 +87,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152639380
+  version_requirements: *2156717720
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2152638940 !ruby/object:Gem::Requirement
+  requirement: &2156716680 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -99,10 +98,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152638940
+  version_requirements: *2156716680
 - !ruby/object:Gem::Dependency
   name: ruby-debug19
-  requirement: &2152638480 !ruby/object:Gem::Requirement
+  requirement: &2156682120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -110,10 +109,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152638480
+  version_requirements: *2156682120
 - !ruby/object:Gem::Dependency
   name: looksee
-  requirement: &2152638060 !ruby/object:Gem::Requirement
+  requirement: &2156680820 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -121,10 +120,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152638060
+  version_requirements: *2156680820
 - !ruby/object:Gem::Dependency
   name: ruby-prof
-  requirement: &2152637620 !ruby/object:Gem::Requirement
+  requirement: &2156680040 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -132,7 +131,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152637620
+  version_requirements: *2156680040
 description: Flag errors with your writing Style
 email:
 - jack.kinsella@gmail.com
@@ -208,7 +207,6 @@ files:
 - spec/tagged_word_spec.rb
 - spec/tagger_spec.rb
 - style-scanner.gemspec
-has_rdoc: true
 homepage: http://www.jackkinsella.ie
 licenses: []
 post_install_message: 
@@ -221,15 +219,21 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 3022405515345769719
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: 3022405515345769719
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.6.2
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: ! 'Formal English Style Guide: Write more effectively'