treat 0.1.1 → 0.1.2

data/lib/treat/{resources → languages/english}/tags.rb

@@ -1,60 +1,10 @@
-# encoding: UTF-8
-
 module Treat
-  module Resources
-    class Tags
+  module Languages
+    class English
 
       ClawsC5 = 0
       Brown = 1
       Penn = 2
-      Enju = 3
-
-      PTBWordTagToCategory = {
-        'CC' =>  :conjunction, # Coordinating conjunction
-        'CD' => :number, # Cardinal number
-        'DT' => :determiner, # Determiner
-        'DET' => :determiner, # Determiner
-        'EX' => :determiner, # Existential there
-        'FW' =>  :foreign, # Foreign word
-        'IN' =>  :preposition, # Preposition or subordinating conjunction
-        'JJ' =>  :adjective, # Adjective
-        'JJR' => :adjective, # Adjective, comparative
-        'JJS' => :adjective, # Adjective, superlative
-        'LS' =>  :list, # List item marker
-        'MD' =>  :modal, # Modal
-        'NN' =>  :noun, # Noun, singular or mass
-        'NNS' =>  :noun, # Noun, plural
-        'NNP' =>  :noun, # Proper noun, singular
-        'NNPS' =>  :noun, # Proper noun, plural
-        'PDT' =>  :determiner, # Predeterminer
-        'POS' =>  :determiner, # Possessive ending
-        'PRP' =>  :pronoun, # Personal pronoun
-        'PRP$' =>  :pronoun, # Possessive pronoun,
-        'PRPS' =>  :determiner, # Possessive determiner
-        'RB' =>  :adverb, # Adverb
-        'RBR' =>  :adverb, # Adverb, comparative
-        'RBS' =>  :adverb, # Adverb, superlative
-        'RP' =>  :particle, # Particle
-        'SYM' =>  :symbol, # Symbol
-        'TO' =>  :to, # to
-        'UH' =>  :interjection, # Interjection
-        'VB' =>  :verb, # Verb, base form
-        'VBD' =>  :verb, # Verb, past tense
-        'VBG' =>  :verb, # Verb, gerund or present participle
-        'VBN' =>  :verb, # Verb, past participle
-        'VBP' =>  :verb, # Verb, non-3rd person singular present
-        'VBZ' =>  :verb, # Verb, 3rd person singular present
-        'WDT' =>  :determiner, # Wh-determiner
-        'WP' =>  :pronoun, # Wh-pronoun
-        'WP$' =>  :pronoun, # Possessive wh-pronoun
-        'WRB' =>  :adverb, # Wh-adverb
-        ')' => :punctuation, # Right bracket
-        '(' => :punctuation,  # Left bracket
-        '.' => :punctuation, # Period
-        '\'\'' => :symbol, # Quote
-        ',' => :punctuation,
-        ';' => :punctuation
-      }
 
       PTBClauseTagDescription = [
         ['S', 'Simple declarative clause'],
@@ -89,141 +39,135 @@ module Treat
       ]
 
       PTBWordTagDescription = [
-=begin
-CC - Coordinating conjunction
-CD - Cardinal number
-DT - Determiner
-EX - Existential there
-FW - Foreign word
-IN - Preposition or subordinating conjunction
-JJ - Adjective
-JJR - Adjective, comparative
-JJS - Adjective, superlative
-LS - List item marker
-MD - Modal
-NN - Noun, singular or mass
-NNS - Noun, plural
-NNP - Proper noun, singular
-NNPS - Proper noun, plural
-PDT - Predeterminer
-POS - Possessive ending
-PRP - Personal pronoun
-PRP$ - Possessive pronoun (prolog version PRP-S)
-RB - Adverb
-RBR - Adverb, comparative
-RBS - Adverb, superlative
-RP - Particle
-SYM - Symbol
-TO - to
-UH - Interjection
-VB - Verb, base form
-VBD - Verb, past tense
-VBG - Verb, gerund or present participle
-VBN - Verb, past participle
-VBP - Verb, non-3rd person singular present
-VBZ - Verb, 3rd person singular present
-WDT - Wh-determiner
-WP - Wh-pronoun
-WP$ - Possessive wh-pronoun (prolog version WP-S)
-WRB - Wh-adverb
-
-=end  
+        ['CC', 'Coordinating conjunction'],
+        ['CD', 'Cardinal number'],
+        ['DT', 'Determiner'],
+        ['EX', 'Existential there'],
+        ['FW', 'Foreign word'],
+        ['IN', 'Preposition or subordinating conjunction'],
+        ['JJ', 'Adjective'],
+        ['JJR', 'Adjective, comparative'],
+        ['JJS', 'Adjective, superlative'],
+        ['LS', 'List item marker'],
+        ['MD', 'Modal'],
+        ['NN', 'Noun, singular or mass'],
+        ['NNS', 'Noun, plural'],
+        ['NNP', 'Proper noun, singular'],
+        ['NNPS', 'Proper noun, plural'],
+        ['PDT', 'Predeterminer'],
+        ['POS', 'Possessive ending'],
+        ['PRP', 'Personal pronoun'],
+        ['PRP$', 'Possessive pronoun (prolog version PRP-S)'],
+        ['RB', 'Adverb'],
+        ['RBR', 'Adverb, comparative'],
+        ['RBS', 'Adverb, superlative'],
+        ['RP', 'Particle'],
+        ['SYM', 'Symbol'],
+        ['TO', 'to'],
+        ['UH', 'Interjection'],
+        ['VB', 'Verb, base form'],
+        ['VBD', 'Verb, past tense'],
+        ['VBG', 'Verb, gerund or present participle'],
+        ['VBN', 'Verb, past participle'],
+        ['VBP', 'Verb, non 3rd person singular present'],
+        ['VBZ', 'Verb, 3rd person singular present'],
+        ['WDT', 'Wh-determiner'],
+        ['WP', 'Wh-pronoun'],
+        ['WP$', 'Possessive wh-pronoun (prolog version WP-S)'],
+        ['WRB', 'Wh-adverb']
       ]
+      
       BrownWordTagDescription = [
-=begin
 
-Tag	Description	Examples
+        ['.',	'sentence closer	. ; ? !'],
+        ['(',	'left parent']	 ,
+        [')',	'right parent'],
+        ['*',	'not'],
+        ['--',	'dash'],
+        [',',	'comma'],
+        [':',	'colon'],
+        ['ABL', 'pre-qualifier	quite, rather'],
+        ['ABN', 'pre-quantifier	half, all'],
+        ['ABX', 'pre-quantifier	both'],
+        ['AP', 'post-determiner	many, several, next'],
+        ['AT', 'article	a, the, no'],
+        ['BE', 'be	 '],
+        ['BED', 'were	 '],
+        ['BEDZ', 'was	 '],
+        ['BEG', 'being	 '],
+        ['BEM', 'am	 '],
+        ['BEN', 'been	 '],
+        ['BER', 'are, art	 '],
+        ['BEZ', 'is	 '],
+        ['CC', 'coordinating conjunction	and, or'],
+        ['CD', 'cardinal numeral	one, two, 2, etc.'],
+        ['CS', 'subordinating conjunction	if, although'],
+        ['DO', 'do	 '],
+        ['DOD', 'did	 '],
+        ['DOZ', 'does	 '],
+        ['DT', 'singular determiner	this, that'],
+        ['DTI', 'singular or plural determiner/quantifier	some, any'],
+        ['DTS', 'plural determiner	these, those'],
+        ['DTX', 'determiner/double conjunction	either'],
+        ['EX', 'existentil there	 '],
+        ['FW', 'foreign word (hyphenated before regular tag)	 '],
+        ['HL', 'word occurring in headline (hyphenated after regular tag)	 '],
+        ['HV', 'have	 '],
+        ['HVD', 'had (past tense)	 '],
+        ['HVG', 'having	 '],
+        ['HVN', 'had (past participle)	 '],
+        ['HVZ', 'has	 '],
+        ['IN', 'preposition	 '],
+        ['JJ', 'adjective	 '],
+        ['JJR', 'comparative adjective	 '],
+        ['JJS', 'semantically superlative adjective	 chief, top'],
+        ['JJT', 'morphologically superlative adjective	biggest'],
+        ['MD', 'modal auxiliary	can, should, will'],
+        ['NC', 'cited word (hyphenated after regular tag)	 '],
+        ['NN', 'singular or mass noun	 '],
+        ['NN$', 'possessive singular noun	 '],
+        ['NNS', 'plural noun	 '],
+        ['NNS$', 'possessive plural noun	 '],
+        ['NP', 'proper noun or part of name phrase	 '],
+        ['NP$', 'possessive proper noun	 '],
+        ['NPS', 'plural proper noun	 '],
+        ['NPS$', 'possessive plural proper noun	 '],
+        ['NR', 'adverbial noun	home, today, west'],
+        ['NRS', 'plural adverbial noun'],
+        ['OD', 'ordinal numeral	first, 2nd'],
+        ['PN', 'nominal pronoun	everybody, nothing'],
+        ['PN$', 'possessive nominal pronoun	 '],
+        ['PP$', 'possessive personal pronoun	my, our'],
+        ['PP$$', 'second (nominal) possessive pronoun	mine, ours'],
+        ['PPL', 'singular reflexive/intensive personal pronoun	myself'],
+        ['PPLS', 'plural reflexive/intensive personal pronoun	ourselves'],
+        ['PPO', 'objective personal pronoun	me, him, it, them'],
+        ['PPS', '3rd. singular nominative pronoun	he, she, it, one'],
+        ['PPSS', 'other nominative personal pronoun	I, we, they, you'],
+        ['QL', 'qualifier	very, fairly'],
+        ['QLP', 'post-qualifier	enough, indeed'],
+        ['RB', 'adverb	 '],
+        ['RBR', 'comparative adverb	 '],
+        ['RBT', 'superlative adverb	 '],
+        ['RN', 'nominal adverb	here then, indoors	 '],
+        ['RP', 'adverb/particle	about, off, up'],
+        ['TL', 'word occurring in title (hyphenated after regular tag)'],
+        ['TO', 'infinitive marker to	 '],
+        ['UH', 'interjection, exclamation	 '],
+        ['VB', 'verb, base form	 '],
+        ['VBD', 'verb, past tense	 '],
+        ['VBG', 'verb, present participle/gerund	 '],
+        ['VBN', 'verb, past participle	 '],
+        ['VBZ', 'verb, 3rd. singular present	 '],
+        ['WDT', 'wh- determiner	what, which'],
+        ['WP$', 'possessive wh- pronoun	whose'],
+        ['WPO', 'objective wh- pronoun	whom, which, that'],
+        ['WPS', 'nominative wh- pronoun	who, which, that'],
+        ['WQL', 'wh- qualifier	how'],
+        ['WRB', 'wh- adverb	how, where, when']
 
-.	sentence closer	. ; ? !
-(	left paren	 
-)	right paren	 
-*	not, n't	 
---	dash	 
-,	comma	 
-:	colon	 
-ABL	pre-qualifier	quite, rather
-ABN	pre-quantifier	half, all
-ABX	pre-quantifier	both
-AP	post-determiner	many, several, next
-AT	article	a, the, no
-BE	be	 
-BED	were	 
-BEDZ	was	 
-BEG	being	 
-BEM	am	 
-BEN	been	 
-BER	are, art	 
-BEZ	is	 
-CC	coordinating conjunction	and, or
-CD	cardinal numeral	one, two, 2, etc.
-CS	subordinating conjunction	if, although
-DO	do	 
-DOD	did	 
-DOZ	does	 
-DT	singular determiner	this, that
-DTI	singular or plural determiner/quantifier	some, any
-DTS	plural determiner	these, those
-DTX	determiner/double conjunction	either
-EX	existentil there	 
-FW	foreign word (hyphenated before regular tag)	 
-HL	word occurring in headline (hyphenated after regular tag)	 
-HV	have	 
-HVD	had (past tense)	 
-HVG	having	 
-HVN	had (past participle)	 
-HVZ	has	 
-IN	preposition	 
-JJ	adjective	 
-JJR	comparative adjective	 
-JJS	semantically superlative adjective	 chief, top
-JJT	morphologically superlative adjective	biggest
-MD	modal auxiliary	can, should, will
-NC	cited word (hyphenated after regular tag)	 
-NN	singular or mass noun	 
-NN$	possessive singular noun	 
-NNS	plural noun	 
-NNS$	possessive plural noun	 
-NP	proper noun or part of name phrase	 
-NP$	possessive proper noun	 
-NPS	plural proper noun	 
-NPS$	possessive plural proper noun	 
-NR	adverbial noun	home, today, west
-NRS	plural adverbial noun
-OD	ordinal numeral	first, 2nd
-PN	nominal pronoun	everybody, nothing
-PN$	possessive nominal pronoun	 
-PP$	possessive personal pronoun	my, our
-PP$$	second (nominal) possessive pronoun	mine, ours
-PPL	singular reflexive/intensive personal pronoun	myself
-PPLS	plural reflexive/intensive personal pronoun	ourselves
-PPO	objective personal pronoun	me, him, it, them
-PPS	3rd. singular nominative pronoun	he, she, it, one
-PPSS	other nominative personal pronoun	I, we, they, you
-QL	qualifier	very, fairly
-QLP	post-qualifier	enough, indeed
-RB	adverb	 
-RBR	comparative adverb	 
-RBT	superlative adverb	 
-RN	nominal adverb	here then, indoors	 
-RP	adverb/particle	about, off, up
-TL	word occurring in title (hyphenated after	 
- 	regular tag)	 
-TO	infinitive marker to	 
-UH	interjection, exclamation	 
-VB	verb, base form	 
-VBD	verb, past tense	 
-VBG	verb, present participle/gerund	 
-VBN	verb, past participle	 
-VBZ	verb, 3rd. singular present	 
-WDT	wh- determiner	what, which
-WP$	possessive wh- pronoun	whose
-WPO	objective wh- pronoun	whom, which, that
-WPS	nominative wh- pronoun	who, which, that
-WQL	wh- qualifier	how
-WRB	wh- adverb	how, where, when
-
-=end    
       ]
+      # A description of Enju categories.
       EnjuCatDescription = [
         ['ADJ',	'Adjective'],
         ['ADV',	'Adverb'],
@@ -330,7 +274,7 @@ WRB	wh- adverb	how, where, when
         'Noun, proper, plural', ['NP0', 'NPS', 'NNPS'],
         'Noun, adverbial', ['NN0', 'NR', 'NN'],
         'Noun, adverbial, plural', ['NN2', 'NRS', 'NNS'],
-        'Pronoun, nominal (indefinite)', ['PNI', 'PN', 'NN'],
+        'Pronoun, nominal (indefinite)', ['PNI', 'PN', 'PRP'],
         'Pronoun, personal, subject', ['PNP', 'PPSS', 'PRP'],
         'Pronoun, personal, subject, 3SG', ['PNP', 'PPS', 'PRP'],
         'Pronoun, personal, object', ['PNP', 'PPO', 'PRP'],
@@ -387,7 +331,6 @@ WRB	wh- adverb	how, where, when
         'Symbol, alphabetical', ['ZZ0', '', ''],
         'Symbol, list item', ['', '', 'LS']
       ]
-
     end
   end
 end

data/lib/treat/languages/english.rb

@@ -0,0 +1,33 @@
+module Treat
+  module Languages
+    class English
+      require 'treat/languages/english/tags'
+      require 'treat/languages/english/categories'
+      Extractors = {
+        time: [:chronic],
+        topics: [:reuters],
+        topic_words: [:lda],
+        key_sentences: [:topics_frequency]
+      }
+      Processors = {
+        chunkers: [:txt],
+        parsers: [:enju, :stanford],
+        segmenters: [:tactful, :punkt, :stanford],
+        tokenizers: [:multilingual, :macintyre, :perl, :punkt, :tactful, :stanford]
+      }
+      Lexicalizers = {
+        category: [:from_tag],
+        linkages: [:naive],
+        synsets: [:wordnet, :rita_wn],
+        tag: [:brill, :lingua, :stanford]
+      }
+      Inflectors = {
+        conjugations: [:linguistics],
+        declensions: [:linguistics, :english],
+        stem: [:porter_c, :porter, :uea],
+        ordinal_words: [:linguistics],
+        cardinal_words: [:linguistics]
+      }
+    end
+  end
+end

data/lib/treat/languages/french.rb

@@ -0,0 +1,17 @@
+module Treat
+  module Languages
+    class French
+      Extractors = {}
+      Inflectors = {}
+      Lexicalizers = {
+        tag: [:stanford]
+      }
+      Processors = {
+        chunkers: [:txt],
+        parsers: [:stanford],
+        segmenters: [:tactful, :punkt, :stanford],
+        tokenizers: [:multilingual, :macintyre, :perl, :punkt, :tactful, :stanford]
+      }
+    end
+  end
+end

data/lib/treat/languages/german.rb

@@ -0,0 +1,17 @@
+module Treat
+  module Languages
+    class German
+      Extractors = {}
+      Inflectors = {}
+      Lexicalizers = {
+        tag: [:stanford]
+      }
+      Processors = {
+        chunkers: [:txt],
+        parsers: [:stanford],
+        segmenters: [:tactful, :punkt, :stanford],
+        tokenizers: [:multilingual, :macintyre, :perl, :punkt, :tactful, :stanford]
+      }
+    end
+  end
+end

data/lib/treat/languages/italian.rb

@@ -0,0 +1,14 @@
+module Treat
+  module Languages
+    class Italian
+      Extractors = {}
+      Inflectors = {}
+      Lexicalizers = {}
+      Processors = {
+        chunkers: [:txt],
+        segmenters: [:tactful, :punkt, :stanford],
+        tokenizers: [:multilingual, :macintyre, :perl, :punkt, :tactful, :stanford]
+      }
+    end
+  end
+end

data/lib/treat/languages/xinhua.rb

@@ -0,0 +1,12 @@
+module Treat
+  module Languages
+    class Xinhua
+      Extractors = {}
+      Inflectors = {}
+      Lexicalizers = {}
+      Processors = {
+        parsers: [:stanford]
+      }
+    end
+  end
+end

data/lib/treat/languages.rb

@@ -0,0 +1,91 @@
+module Treat
+  # This module provides linguistic resources
+  # for the Treat library, including information
+  # about language codes, the functions available
+  # for each language, and the different tags used
+  # to markup that language.
+  module Languages
+    Dir["#{Treat.lib}/treat/languages/*.rb"].each { |file| require file }
+    ISO639_1 = 1
+    ISO639_2 = 2
+    # Describe a language code (ISO-639-1 or ISO-639-2)
+    # or its full text description in full French or English.
+    def self.describe(lang, desc_lang = :en)
+      raise "Must provide a non-nil language identifier to describe." if lang.nil?
+      lang = find(lang).to_s
+      if [:en, :eng, :english, :anglais].include?(desc_lang)
+        l = @@english_full.key(lang)
+      elsif [:fr, :fra, :french, :french].include?(desc_lang)
+        l = @@french_full.key(lang)
+      else
+        raise Treat::Exception,
+        "Unknown language to describe: #{desc_lang}."
+      end
+      not_found(lang) if l.nil?
+      l.intern
+    end
+    # Raise an error message when a language code
+    # or description is not found and suggest
+    # possible misspellings.
+    def self.not_found(lang)
+      msg = "Language '#{lang}' does not exist."
+      all = @@iso639_2.keys + @@iso639_1.keys +
+      @@english_full.keys + @@french_full.keys
+      msg += did_you_mean?(all, lang)
+      raise Treat::Exception, msg
+    end
+    # Return the class representing a language.
+    def self.get(lang)
+      const_get(Treat::Languages.describe(lang).to_s.capitalize)
+    end
+    # Find a language by ISO-639-1 or ISO-639-2 code
+    # or full name (in English or French) and return
+    # the ISO-639-1 or ISO-639-2 language code as a
+    # lowercase identifier.
+    def self.find(lang, rc = ISO639_2)
+      raise "Must provide a non-nil language identifier to describe." if lang.nil?
+      get_languages
+      lang = lang.to_s.downcase
+      if @@iso639_1.has_key?(lang)
+        return :"#{lang}" if rc == ISO639_1
+        return :"#{@@iso639_1[lang]}" if rc == ISO639_2
+      elsif @@iso639_2.has_key?(lang)
+        return :"#{lang}" if rc == ISO639_2
+        return :"#{@@iso639_2[lang]}" if rc == ISO639_1
+      elsif @@english_full.has_key?(lang)
+        return :"#{@@english_full[lang]}" if rc == ISO639_2
+        return :"#{@@iso639_2[@@english_full[lang]]}" if rc == ISO639_1
+      elsif @@french_full.has_key?(lang)
+        return :"#{@@french_full[lang]}" if rc == ISO639_2
+        return :"#{@@iso639_1[@@french_full[lang]]}" if rc == ISO639_2
+      else
+        not_found(lang)
+      end
+    end
+    @@loaded = false
+    # Get the languages from the dictionary.
+    def self.get_languages
+      return if @@loaded
+      @@iso639_1 = {}; @@iso639_2 = {};
+      @@english_full = {}; @@french_full = {}
+      languages = IO.readlines(Treat.lib + '/treat/languages/list.txt')
+      languages.each do |language|
+        iso639_2, iso639_1, english_desc, french_desc =
+        language.split(',')
+        @@iso639_1[iso639_1] = iso639_2
+        @@iso639_2[iso639_2] = iso639_1
+        unless english_desc.nil?
+          english_desc.strip.downcase.split('|').each do |l|
+            @@english_full[l.downcase.strip] = iso639_2
+          end
+        end
+        unless french_desc.nil?
+          french_desc.strip.downcase.split('|').each do |l|
+            @@french_full[l.downcase.strip] = iso639_2
+          end
+        end
+      end
+      @@loaded = true
+    end
+  end
+end

data/lib/treat/lexicalizers/category/from_tag.rb

@@ -4,24 +4,36 @@ module Treat
       # A class that detects the category of a word from its tag,
       # using the default tagger for the language of the entity.
       class FromTag
+        DefaultOptions = { tagger: nil }
         # Find the category of the current entity.
         # Options:
         # :tagger => (Symbol) force the use of a tagger.
         # :tag_to_cat => (Hash) a list of categories for each possible tag.
         def self.category(entity, options = {})
-          if options.empty?
-            options = {
-              tagger: nil,
-              tag_to_cat: Treat::Resources::Tags::PTBWordTagToCategory
-            }
-          end
+          options = DefaultOptions.merge(options)
           tag = options[:tagger].nil? ? entity.tag : entity.tag(options[:tagger])
-          cat = options[:tag_to_cat][tag]
+          lang = Treat::Languages.get(entity.language)
+          cat = lang::WordTagToCategory[tag]
           if cat.nil?
             warn "Category not found for tag #{tag}."
             :unknown
           else
-            cat
+            if cat.size == 1
+              return cat[0]
+            else
+              if entity.has?(:tag_set)
+                if cat[entity.tag_set]
+                  return cat[entity.tag_set]
+                else
+                  raise Treat::Exception,
+                  "The specified tag set (#{entity.tag_set})" +
+                  " does not contain the tag #{tag}."
+                end
+              else
+                raise Treat::Exception,
+                "No information can be found regarding which tag set to use."
+              end
+            end
           end
         end
       end

data/lib/treat/lexicalizers/synsets/rita_wn.rb

@@ -4,7 +4,7 @@ module Treat
       # Currently not implemented.
       class RitaWn
         # Require the Ruby-Java bridge.
-        #silently do
+        #silence_warnings do
           require 'rjb'
           # Load the RitaWN jars.
           Rjb::load("#{Treat.bin}/jwnl/jwnl.jar", [])

data/lib/treat/lexicalizers/tag/brill.rb

@@ -25,7 +25,7 @@ module Treat
         patch = false
         # Require the 'rbtagger' gem.
         begin
-          silently { require 'rbtagger' }
+          silence_warnings { require 'rbtagger' }
         # This whole mess is required to deal with
         # the fact that the 'rbtagger' gem defines
         # a top-level module called 'Word', which
@@ -73,6 +73,7 @@ module Treat
           # Create the tagger if necessary
           @@tagger ||= ::Brill::Tagger.new(options[:lexicon],
           options[:lexical_rules], options[:contextual_rules])
+          entity.set :tag_set, :penn
           # Perform tagging.
           if entity.type == :word
             # Setup the context of the word

data/lib/treat/lexicalizers/tag/lingua.rb

@@ -17,7 +17,7 @@ module Treat
       # http://cpansearch.perl.org/src/ACOBURN/Lingua-EN-Tagger-0.15/
       class Lingua
         # Require the 'engtagger' gem.
-        silently { require 'engtagger' }
+        silence_warnings { require 'engtagger' }
         # Hold the tagger.
         @@tagger = nil
         # Hold the user-set options
@@ -46,6 +46,7 @@ module Treat
             @@tagger = nil # Reset the tagger
           end
           @@tagger ||= ::EngTagger.new(@@options)
+          entity.set :tag_set, :penn
           left = entity.left
           if left.nil? || left.type != :word
             left_tag = 'pp'