presume 0.0.2

data/lib/classes/resume_classifier.rb

@@ -0,0 +1,137 @@
+class ResumeClassifier
+
+  attr_accessor :text, :lines, :classifide_lines
+
+  def initialize(resume_text, name, presume)
+  	@text = resume_text	
+  	@classifide_lines = {}
+  	@lines = []
+    @user_name = name
+    @presume = presume
+    clean_text
+  	split_text
+  end
+
+  def lines_together
+    @lines_together ||= @lines.join("\n")
+  end
+
+  def tagged_lines_together
+    @tagged_lines_together ||= tgr.add_tags(lines_together)
+  end
+
+  def tagged_lines
+    @tagged_lines ||= tagged_lines_together.split("\n")
+  end
+  
+  def regex_name
+    Regexp.new(@user_name, "i")
+  end
+
+  def clean_text
+    separate_tabbed_words
+    remove_extra_spaces
+  end
+
+  def remove_extra_spaces
+    @text = @text.gsub(regex_remove_extra_spaces, ",")
+  end
+
+
+  def separate_tabbed_words
+    @text = @text.gsub(regex_separate_tabbed_words, ",")
+  end
+
+  def split_text
+  	@lines = @text.split("\n")
+  	remove_blanks
+  end
+
+  def remove_all_lines
+    @lines = []
+  end
+
+  def remove_blanks
+  	@lines = @lines.reject{|line| blank?(line)}
+  end
+
+  def number_of_lines
+  	@lines.length
+  end
+
+  def blank?(line)
+  	line[regex_characters_and_digits].nil?
+  end
+
+  def classify
+  	number_of_lines.times do |n|
+  		set_line_number(n)
+  		set_line(n)
+  		check_classifications
+  		merge_to_classifide_lines
+  	end
+  end
+
+  def line_text(n)
+  	@lines[n]
+  end
+
+  def set_line(number)
+  	@line = @lines[number]
+  end
+
+  def set_line_number(number)
+  	@line_number = number
+  end
+ 
+  def check_classifications
+  	classifications.each do |classification|
+		set_classification_instance(classification)
+  	end
+  end
+
+  def set_classification_instance(classification)
+  	instance_variable_set(("@" + classification).to_sym, classification?(classification))
+  end
+
+  def classification?(classification)
+  	@line[regex_(classification)]
+  end
+
+  def regex_(classification)
+  	send("regex_#{classification}")
+  end
+
+  def merge_to_classifide_lines
+  	pass_classification_instances_to_hash
+  	@classifide_lines.merge!({@line_number => Classifide.new(@line_classifications.merge(line_non_regex_classifications))})  	
+  end
+
+  def line_non_regex_classifications
+  	@non_regex_classications = {number_of_words: number_of_words, many_words: many_words, verbs: verbs?, text: @line, type: nil, id: @line_number, presume: @presume}
+  end
+
+  def remove_dates_and_cities
+    @date_and_city_less_line = @line.gsub(Regexp.union(regex_dates,regex_dates_2,regex_cities),"")
+  end
+  def number_of_words
+    @number_of_words = remove_dates_and_cities.split.size
+  end
+
+  def many_words
+  	@number_of_words >= 5
+  end
+
+  def verbs?
+  	if tagged_lines[@line_number].nil?
+  		@verbs = nil
+  	else
+  		@verbs = tagged_lines[@line_number][regex_engtagger_verbs]
+  	end
+  end
+
+  def pass_classification_instances_to_hash
+  	@line_classifications = Hash[classifications.map{|classification| [classification.to_sym, instance_variable_get("@#{classification}")]}]
+  end
+
+end

data/lib/classes/resume_searcher.rb

@@ -0,0 +1,4 @@
+class ResumeSearcher
+
+
+end

data/lib/classes/searchable.rb

@@ -0,0 +1,40 @@
+class Searchable
+
+	attr_accessor :raw_name, :duration
+	
+	def initialize(hash)
+		@raw_name = hash[:raw_name]
+		@duration = hash[:duration]
+	end
+
+	def names
+		if @names.nil?
+			@names = []
+			@searchable_words = @raw_name.downcase.split
+			@searchable_words.each do |word|
+				@names += [stemmed(word)]
+			end
+			@names
+		else
+			@names
+		end
+	end
+
+	def regex
+		if @regex.nil?
+			@regexes = ""
+			names.each do |name|
+				@regexes += '(?=.*' + name + ')'
+			end
+			@regexes += ".*"
+			@regex = Regexp.new(@regexes, "i")
+		else
+			@regex
+		end
+	end
+
+	def check_regex(searchable_title)
+		!searchable_title.downcase[regex].nil?
+	end
+
+end

data/lib/classes/searchables.rb

@@ -0,0 +1,24 @@
+class Searchables
+
+	attr_accessor :raw
+	
+	def initialize(hash)
+		@raw = hash
+		@all = {}
+	end
+
+	def duration(name)
+		@raw[name]
+	end
+
+	def all
+		if @all.empty?
+			@raw.keys.each do |name|
+				@all.merge!(name => Searchable.new({raw_name: name, duration: duration(name)}))
+			end
+			@all
+		else
+			@all
+		end
+	end
+end

data/lib/definitions/classifications.rb

@@ -0,0 +1,24 @@
+
+  def classifications
+    @classifications ||= ["name", "phone", "email", "address", "section", "professions", "companies", "schools", "dates", "cities"]
+  end
+
+  def non_regex_classifications
+    non_regex_classifications ||= ["number_of_words", "many_words", "verbs", "text", "type", "id", "presume"]
+  end
+
+  def both_classifications
+    @both_classifications ||= classifications + non_regex_classifications
+  end
+
+  def both_classifications_symboled
+    both_classifications_symboled ||= both_classifications.map {|x| x.to_sym}
+  end
+
+  def header_classifications
+    @header_classifications ||= ["professions", "companies", "schools", "dates", "cities"]
+  end
+
+  def set_time_at_inception(time, presume)
+    instance_variable_set("@#{time}", presume)
+  end

data/lib/definitions/machines.rb

@@ -0,0 +1,11 @@
+def tgr
+	@tgr ||= EngTagger.new
+end
+
+def stemmer
+	@stemmer ||= Lingua::Stemmer.new(:language => "en")
+end
+
+def stemmed(word)
+	stemmer.stem(word)
+end

data/lib/definitions/regex.rb

@@ -0,0 +1,79 @@
+  def regex_cities
+    @regex_cities ||= Regexp.new("([a-z]{2,} ){0,3}[a-z]{2,}\\, " + "\\b(AK|Alaska|AL|Alabama|AR|Arkansas|AZ|Arizona|CA|California|CO|Colorado|CT|Connecticut|DE|Delaware|FL|Florida|GA|Georgia|HI|Hawaii|IA|Iowa|ID|Idaho|IL|Illinois|IN|Indiana|KS|Kansas|KY|Kentucky|LA|Louisiana|MA|Massachusetts|MD|Maryland|ME|Maine|MI|Michigan|MN|Minnesota|MO|Missouri|MS|Mississippi|MT|Montana|NC|North Carolina|ND|North Dakota|NE|Nebraska|NH|New Hampshire|NJ|New Jersey|NM|New Mexico|NV|Nevada|NY|New York|OH|Ohio|OK|Oklahoma|OR|Oregon|PA|Pennsylvania|RI|Rhode Island|SC|South Carolina|SD|South Dakota|TN|Tennessee|TX|Texas|UT|Utah|VA|Virginia|VT|Vermont|WA|Washington|WI|Wisconsin|WV|West Virginia|WY|Wyoming|AB|Alberta|BC|British Columbia|MB|Manitoba|NB|New Brunswick|NL|Newfoundland and Labrador|NS|Nova Scotia|ON|Ontario|PE|Prince Edward Island|QC|Quebec|SK|Saskatchewan)" + "\\b", "i")
+  end
+
+  def regex_professions
+    @regex_professions ||= Regexp.new('([A-Z][a-z]* ){0,5}(coordinator|assistant|asst|manager|director|technician|analyst|associate|developer|programmer|nurse|consutlant|worker|clerk|receptionist|secretary|teacher|engineer|administrator|researcher|head of|admin|intern|database|leader|server|waitress|waiter|busboy)\b(\.|)( [A-Z][a-z]*){0,5}', 'i')
+  end 
+
+  def regex_schools
+    @regex_schools ||= Regexp.new("([a-z]{1,} ){0,5}(university|college)\\b(( [a-z]{1,}){0,5}|)", "i")
+  end
+
+  def regex_companies
+    @regex_companies ||= Regexp.new(/(([A-Z][a-z]* )*and ([A-Z][a-z]* )*|([A-Z][a-z]* )*)(Inc|INC|Corp|CORP|CO|Co|LTD|Ltd)\b(\.|)/)
+  end
+ 
+  def regex_address
+    @regex_address ||= Regexp.new("\\d (\\w{2,} ){1,2}(Alley|ALY|Annex|ANX|Arcade|ARC|Avenue|AVE|Bayou|YU|Beach|BCH|Bend|BND|Bluff|BLF|Bottom|BTM|Boulevard|BLVD|Branch|BR|Bridge|BRG|Brook|BRK|Burg|BG|Bypass|BYP|Camp|CP|Canyon|CYN|Cape|CPE|Causeway|CSWY|Center|CTR|Circle|CIR|Cliffs|CLFS|Club|CLB|Corner|COR|Corners|CORS|Course|CRSE|Court|CT|Courts|CTS|Cove|CV|Creek|CRK|Crescent|CRES|Crossing|XING|Dale|DL|Dam|DM|Divide|DV|Drive|DR|Estates|EST|Expressway|EXPY|Extension|EXT|Fall|FALL|Falls|FLS|Ferry|FRY|Field|FLD|Fields|FLDS|Flats|FLT|Ford|FOR|Forest|FRST|Forge|FGR|Fork|FORK|Forks|FRKS|Fort|FT|Freeway|FWY|Gardens|GDNS|Gateway|GTWY|Glen|GLN|Green|GN|Grove|GRV|Harbor|HBR|Haven|HVN|Heights|HTS|Highway|HWY|Hill|HL|Hills|HLS|Hollow|HOLW|Inlet|INLT|Island|IS|Islands|ISS|Isle|ISLE|Junction|JCT|Key|CY|Knolls|KNLS|Lake|LK|Lakes|LKS|Landing|LNDG|Lane|LN|Light|LGT|Loaf|LF|Locks|LCKS|Lodge|LDG|Loop|LOOP|Mall|MALL|Manor|MNR|Meadows|MDWS|Mill|ML|Mills|MLS|Mission|MSN|Mount|MT|Mountain|MTN|Neck|NCK|Orchard|ORCH|Oval|OVAL|Park|PARK|Parkway|PKY|Pass|PASS|Path|PATH|Pike|PIKE|Pines|PNES|Place|PL|Plain|PLN|Plains|PLNS|Plaza|PLZ|Point|PT|Port|PRT|Prairie|PR|Radial|RADL|Ranch|RNCH|Rapids|RPDS|Rest|RST|Ridge|RDG|River|RIV|Road|RD|Row|ROW|Run|RUN|Shoal|SHL|Shoals|SHLS|Shore|SHR|Shores|SHRS|Spring|SPG|Springs|SPGS|Spur|SPUR|Square|SQ|Station|STA|Stravenues|STRA|Stream|STRM|Street|ST|Summit|SMT|Terrace|TER|Trace|TRCE|Track|TRAK|Trail|TRL|Trailer|TRLR|Tunnel|TUNL|Turnpike|TPKE|Union|UN|Valley|VLY|Viaduct|VIA|View|VW|Village|VLG|Ville|VL|Vista|VIS|Walk|WALK|Way|WAY|Wells|WLS)(\\b|\\.\\b)", "i")
+  end
+
+  def regex_phone
+    @regex_phone ||= Regexp.new("\\d\\d\\d(|\\))(| |-)(\\(|)\\d\\d\\d(|\\))(| |-)\\d\\d\\d\\d", "i")    
+  end
+
+  def regex_email
+    @regex_email ||= Regexp.new("\\b(\\w){1,}@(\\w){1,}\\.(\\w){1,5}\\b", "i")
+  end
+
+  def regex_dates
+    @regex_dates ||= Regexp.union(regex_dates_1, regex_dates_2)
+  end
+
+  def regex_dates_1
+    @regex_dates_1 ||= Regexp.new("((January|Jan|March|Mar|May|May|July|Jul|September|Sep|Sept|November|Nov|February|Feb|April|Apr|June|Jun|August|Aug|October|Oct|December|Dec|Winter|Fall|Summer|Spring)( |)(\\d{2}\\b|\\d{4}\\b)( |)(–|-|to)( |)((January|Jan|March|Mar|May|May|July|Jul|September|Sep|Sept|November|Nov|February|Feb|April|Apr|June|Jun|August|Aug|October|Oct|December|Dec|Winter|Fall|Summer|Spring)( |)(\\d{2}\\b|\\d{4}\\b)|present|current|today)|(January|Jan|March|Mar|May|May|July|Jul|September|Sep|Sept|November|Nov|February|Feb|April|Apr|June|Jun|August|Aug|October|Oct|December|Dec|Winter|Fall|Summer|Spring)( |)(\\d{2}\\b|\\d{4}\\b))", "i")
+  end
+
+  def regex_dates_2
+    @regex_dates_2 ||= Regexp.new("((\\d{2}\\b)(| )(–|-|to)(| )(\\d{2}\\b|present\\b)|(\\d{4}\\b)(| )(–|-|to)(| )(\\d{4}\\b|present\\b))", "i")
+  end
+
+  def regex_month
+    @regex_month ||= Regexp.new('January|Jan|March|Mar|May|May|July|Jul|September|Sep|Sept|November|Nov|February|Feb|April|Apr|June|Jun|August|Aug|October|Oct|December|Dec', 'i')    
+  end
+
+  def regex_season
+    @regex_season ||= Regexp.new('Winter|Fall|Summer|Spring', 'i')
+  end
+
+  def regex_year
+    @regex_year ||= Regexp.new('\b\d\d\d\d\b|\b\d\d\b', 'i')
+  end
+
+  def regex_section
+    @regex_section ||= Regexp.new("([a-z]* ){0,5}(highlight|professional development|summary|experience|skills|education|qualifications|interests|profile)( [a-z]*){0,5}", "i")
+  end
+
+  def regex_new_lines_and_blanks
+    @regex_new_lines ||= Regexp.new(/\n\n\n\n|\n\n\n|\n\n|\n|   /)
+  end
+
+  def regex_engtagger_verbs
+    @regex_engtagger_verbs ||= Regexp.new(/<vb[a-z]{0,1}>/)
+  end
+
+  def regex_separate_tabbed_words
+    @regex_separate_tabbed_words ||= Regexp.new('(?<=[A-Za-z])(?=\d)|(?<=[a-z])(?=[A-Z])|(?<=\d)(?=[A-Za-z])')
+  end
+
+  def regex_remove_extra_spaces
+    @regex_remove_extra_spaces ||= Regexp.new('(?<=  ) ')
+  end
+
+  def regex_characters_and_digits
+    Regexp.new(/[A-Za-z]|\d/)
+  end
+
+  def regex_current
+    @regex_current ||= Regexp.new('current|present|today', 'i')
+  end

data/lib/presume.rb

@@ -0,0 +1,123 @@
+require "engtagger"
+require 'docx'
+require 'lingua/stemmer'
+require 'date'
+require "definitions/regex.rb"
+require "definitions/classifications.rb"
+require "definitions/machines.rb"
+require "sort/resume_builder.rb"
+require "sort/resume_classifier.rb"
+require "sort/classifide.rb"
+require "sort/header.rb"
+require "sort/bullet.rb"
+require "sort/searchable.rb"
+require "sort/searchables.rb"
+
+class Presume
+
+  attr_accessor :sections, :headers, :bullets, :all_types, :classifides
+  
+  def initialize(doc, name)
+    @resume_classifier = ResumeClassifier.new(doc, name, self)
+    @resume_classifier.classify
+    @resume_builder = ResumeBuilder.new(@resume_classifier.classifide_lines)
+    @resume_builder.first_pass
+    @resume_builder.second_pass
+    @resume_builder.build_resume
+    @sections = @resume_builder.resume[:sections]
+    @headers = @resume_builder.resume[:headers]
+    @bullets = @resume_builder.resume[:bullets]
+    @all_types = @resume_builder.resume[:all_types]
+  end
+
+  def get_sections_info
+    @sections.values
+  end
+
+  def get_sections_id
+    @sections.keys
+  end
+
+  def get_headers_info
+    @headers.values
+  end
+
+  def get_headers_id
+    @headers.keys
+  end
+
+  def get_bullets_info
+    @bullets.values
+  end
+
+  def get_bullets_ids
+    @bullets.keys
+  end
+
+  def get_id(id)
+    @all_types[id][0]
+  end
+
+  def searchables?(hash) #word phrase => duration
+    match_searchables_to_classifides(hash, @headers)
+  end
+
+  def skills?(hash) #word phrase => duration
+    match_searchables_to_classifides(hash, @bullets)
+  end
+
+    def match_searchables_to_classifides(hash, classifides)
+      setup_match_searchables(hash, classifides)
+      check_for_searchable_match
+      return @matched_searchables
+    end
+
+      def setup_match_searchables(hash, classifides)
+        set_classifides(classifides)
+        set_searchables(hash)
+        reset_matched_searchables
+      end
+
+        def set_classifides(classifides)
+          @classifides = classifides
+        end
+
+        def set_searchables(hash)
+          @searchables = Searchables.new(hash)
+        end
+
+        def reset_matched_searchables
+          @matched_searchables = []
+        end
+
+      def check_for_searchable_match
+        classifide_objects.each do |classifide|
+          searchable_objects.each do |searchable|
+            if matched_text?(classifide, searchable) and matched_duration?(classifide, searchable)
+              add_to_matched_searchables(classifide, searchable)
+            end
+          end
+        end
+      end
+
+        def classifide_objects
+          @classifides.values
+        end
+
+        def searchable_objects
+          @searchables.all.values
+        end
+
+        def matched_text?(classifide, searchable)
+          !classifide.text[searchable.regex].nil?
+        end
+
+        def matched_duration?(classifide, searchable)
+          classifide.duration >= searchable.duration
+        end
+
+        def add_to_matched_searchables(classifide, searchable)
+          @matched_searchables += [[searchable,classifide]]
+        end
+end
+