piola 0.0.7

data/lib/piola/splitting.rb

@@ -0,0 +1,49 @@
+require 'active_support/core_ext/object/blank'
+
+module Piola
+
+  module Splitting
+
+    # Converts a string into a word array without extra spaces, etc
+    def to_arr(options = {})
+      str = self
+      str = str.strip
+      str = str.gsub(',', ' ')
+      str = str.gsub('.', ' ')
+      str = str.gsub(/ +/, ' ')
+      arr = str.split(' ')
+      arr = arr.compact
+      arr = arr.uniq unless options[:non_unique]
+      arr
+    end
+
+    # Converts a string into a parragraph array
+    def string_to_parragraph_arr
+      str = self
+      str = str.strip
+      str = str.gsub(',', ' ')
+      str = str.gsub('.', ' ')
+      str = str.gsub(/ +/, ' ')
+      str = str.strip
+      str = str.gsub("\r", "\n")
+      arr = str.split("\n")
+      
+      arr.map do |part|
+        part.strip if part.strip.present?
+      end.compact
+    end
+
+    # Converts a string into a parragaph array with only important sentences
+    def string_to_important_parragraph_arr
+      arr = self.string_to_parragraph_arr
+
+      arr.map do |part|
+        part if part.count_words >= 5 && !part.html_leftover?
+      end.compact.uniq
+    end
+
+  end
+
+end
+
+String.send :include, Piola::Splitting

data/lib/piola/sql.rb

@@ -0,0 +1,210 @@
+require 'active_support/core_ext/object/blank'
+require 'active_support/core_ext/array/extract_options'
+
+module Piola
+
+  module Sql
+
+    # Converts a string to a sql search string
+    def sql_search(fields)
+      str = self
+      str = str.gsub("'", '')
+      str = str.gsub('"', '')
+      str = str.gsub("\\", '')
+      str = str.gsub("%", '')
+      str = str.gsub("/", ' ')
+      str = str.gsub(":", ' ')
+      str = str.gsub("=", ' ')
+      str = str.gsub("?", ' ')
+
+      if str.strip.present?
+        arr   = str.to_arr
+        rows  = []
+        cells = []
+
+        fields.each do |field|
+          cells = []
+
+          arr.each do |a|
+            cells << "(#{field} LIKE \"%#{a}%\")"
+          end
+
+          rows << "(" + cells.join(" AND ") + ")"
+        end
+
+        return rows.join(" OR ")
+      else
+        return '0'
+      end
+    end
+
+    # Converts a string to a sql search query
+    def searchify(*args)
+      fields  = args.first
+      options = args.extract_options!
+
+      operator = options[:operator] || :and
+      operator = operator.to_s.upcase
+
+      str = self
+      str = str.gsub(/ +/, ' ')
+      str = str.gsub("'", '')
+      str = str.gsub("\\", '')
+      str = str.gsub("%", '')
+      str = str.gsub("/", ' ')
+      str = str.gsub(":", ' ')
+      str = str.gsub("=", ' ')
+      str = str.gsub("?", ' ')
+      str = str.strip
+
+      return '0' unless str.present?
+
+      exact_words         = []
+      exacts              = []
+      regulars            = []
+      exact_word_excludes = []
+      exact_excludes      = []
+      excludes            = []
+
+      # Check for exact excludes
+      exact_excludes_matches = str.scan(/-"(.*?)"/)
+
+      exact_excludes_matches.each do |match|
+        match = match.first
+
+        # Remove match from main string
+        str = str.gsub(/-"#{match}"/, '').strip
+
+        exact_excludes << match.strip
+      end
+
+      # Check for exact word excludes
+      exact_word_excludes_matches = str.scan(/-`(.*?)`/)
+
+      exact_word_excludes_matches.each do |match|
+        match = match.first
+
+        # Remove match from main string
+        str = str.gsub(/-`#{match}`/, '').strip
+
+        exact_word_excludes << match.strip
+      end
+
+      # Check for exact words
+      exact_word_matches = str.scan(/`(.*?)`/)
+
+      exact_word_matches.each do |match|
+        match = match.first
+
+        # Remove match from main string
+        str = str.gsub(/`#{match}`/, '').strip
+
+        exact_words << match.strip
+      end
+
+      # Check for exact searches
+      exact_matches = str.scan(/"(.*?)"/)
+
+      exact_matches.each do |match|
+        match = match.first
+
+        # Remove match from main string
+        str = str.gsub(/"#{match}"/, '').strip
+
+        exacts << match.strip
+      end
+
+      # Check for excludes with spaces after them
+      exclude_matches = str.scan(/-.+? /)
+
+      exclude_matches.each do |match|
+        match.strip!
+        match = match.gsub(/-/, '')
+
+        # Remove match from main string
+        str = str.gsub(/-#{match}/, '').strip
+
+        excludes << match.strip
+      end
+
+      # Check for excludes at the end of the string
+      exclude_matches = str.scan(/-.+?$/)
+
+      exclude_matches.each do |match|
+        match.strip!
+        match = match.gsub(/-/, '')
+
+        # Remove match from main string
+        str = str.gsub(/-#{match}/, '').strip
+
+        excludes << match.strip
+      end
+
+      # Check for regular searches
+      regulars = str.to_arr
+
+      # Build the query
+      query   = []
+      rows    = []
+      cells   = []
+
+      # Includes
+      query_includes = ""
+
+      if exact_words.any? || exacts.any? || regulars.any?
+        fields.each do |field|
+          cells = []
+
+          exact_words.each do |matcher|
+            cells << "(#{field} LIKE \"% #{matcher.remove_quotes} %\" OR #{field} LIKE \"% #{matcher.remove_quotes}.%\" OR #{field} LIKE \"% #{matcher.remove_quotes},%\")"
+          end
+
+          [exacts, regulars].each do |matchers|
+            matchers.each do |matcher|
+              cells << "#{field} LIKE \"%#{matcher.remove_quotes}%\""
+            end
+          end
+
+          rows << cells.join(" #{operator} ")
+        end
+
+        query_includes = rows.join(" OR ")
+        query << "(#{query_includes})"
+      end
+
+      # Excludes
+      query_excludes = ""
+
+      if exact_word_excludes.any? || exact_excludes.any? || excludes.any?
+        rows  = []
+        cells = []
+
+        fields.each do |field|
+          cells = []
+
+          exact_word_excludes.each do |matcher|
+            cells << "(#{field} NOT LIKE \"% #{matcher.remove_quotes} %\" OR #{field} NOT LIKE \"% #{matcher.remove_quotes}.%\" OR #{field} NOT LIKE \"% #{matcher.remove_quotes},%\")"
+          end
+
+          [exact_excludes, excludes].each do |matchers|
+            matchers.each do |matcher|
+              cells << "#{field} NOT LIKE \"%#{matcher.remove_quotes}%\""
+            end
+          end
+
+          rows << cells.join(" #{operator} ")
+        end
+
+        query_excludes = rows.join(" AND ")
+        query << "(#{query_excludes})"
+      end
+
+      return query.join(" AND ") if query.any?
+      return '0'
+    end
+
+  end
+
+end
+
+String.send :include, Piola::Sql

data/lib/piola/uri.rb

@@ -0,0 +1,25 @@
+module Piola
+
+  module Uri
+
+    def uri_escape
+      require 'uri'
+
+      str = URI.escape(self)
+
+      return str
+    end
+
+    def uri_unescape
+      require 'uri'
+
+      str = URI.unescape(self)
+
+      return str
+    end
+
+  end
+
+end
+
+String.send :include, Piola::Uri

data/lib/piola/version.rb

@@ -0,0 +1,3 @@
+module Piola
+  VERSION = "0.0.7"
+end

data/piola.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/piola/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["David Jairala"]
+  gem.email         = ["davidjairala@gmail.com"]
+  gem.description   = %q{String extensions and quality of life methods}
+  gem.summary       = %q{Provides a bunch of extensions for Strings, HTML manipulation methods, splitting, spanish language quality of life, etc.}
+  gem.homepage      = ""
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "piola"
+  gem.require_paths = ["lib"]
+  gem.version       = Piola::VERSION
+
+  gem.add_dependency 'htmlentities',  ["~> 4.3.1"]
+  gem.add_dependency 'activesupport', [">= 3.0.0"]
+end

data/spec/encoding_spec.rb

@@ -0,0 +1,38 @@
+# encoding: utf-8
+require 'spec_helper'
+
+describe Piola::Encoding do
+
+  describe '#to_iso' do
+
+    it "should correctly convert an UTF8 string to ISO" do
+      'ááá'.to_iso.should_not be_utf8
+      'ááá'.to_iso.should be_iso
+    end
+
+  end
+
+  describe '#to_utf8' do
+
+    it "should correctly convert an ISO string to UTF8" do
+      'ááá'.force_encoding('ISO-8859-1').to_utf8.should eql('ááá')
+      'ááá'.force_encoding('ISO-8859-1').to_utf8.should be_utf8
+    end
+
+    it "should correctly convert an UTF8 string to ISO and back" do
+      'á'.to_iso.to_utf8.should eql('á')
+      'á'.to_iso.to_utf8.should be_utf8
+    end
+
+  end
+
+  describe '#utf8?' do
+    it { 'foo bar baz'.should be_utf8 }
+    it { 'ááá'.should         be_utf8 }
+  end
+
+  describe '#iso?' do
+    it { 'á'.to_iso.should be_iso }
+  end
+
+end

data/spec/html_spec.rb

@@ -0,0 +1,83 @@
+# encoding: utf-8
+require 'spec_helper'
+
+describe Piola::Html do
+
+  describe '#strip_tags' do
+
+    it "should remove tags from html docs" do
+      txt = '<div id="baz_id"><p>foo bar baz.<br></p></div><div style="clear:both;"></div>'
+      txt.strip_tags.should eql('foo bar baz.')
+    end
+
+    it "removes quoted tags" do
+      txt = '&lt;div id="baz_id"&gt;&lt;p&gt;foo bar baz.&lt;br&gt;&lt;/p&gt;&lt;/div&gt;&lt;div style="clear:both;"&gt;&lt;/div&gt;'
+      txt.strip_tags.should eql('foo bar baz.')
+    end
+
+  end
+
+  describe '#strip_tags_enters' do
+
+    let(:txt) { %Q{<div id="baz_id">
+                <p>
+                  foo (bar) baz.
+                  <br>
+                </p>
+              </div><div style="clear:both;"></div>} }
+
+    it "should remove tags but leave enters in their places" do
+      txt.strip_tags_enters.should eql("\n\n\n\nfoo baz.\n\n\n\n\n")
+    end
+
+    it "should not remove parenthesis when specified" do
+      txt.strip_tags_enters(false).should eql("\n\n\n\nfoo (bar) baz.\n\n\n\n\n")
+    end
+
+  end
+
+  describe '#html_encode' do
+
+    it "should convert special chars to html entities" do
+      txt = 'áéíñÑÁ'
+      txt.html_encode.should eql('&aacute;&eacute;&iacute;&ntilde;&Ntilde;&Aacute;')
+    end
+
+  end
+
+  describe '#html_decode' do
+
+    it "should convert html entities to special chars" do
+      txt = 'áéíñÑÁ'
+      txt.html_encode.should eql('&aacute;&eacute;&iacute;&ntilde;&Ntilde;&Aacute;')
+    end
+
+  end
+
+  describe '#html_leftover?' do
+
+    it 'returns true if the string has any html leftovers' do
+      txt = '/* Style Definitions */ table MsoNormalTable mso-style-name:"Tabla normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5 4pt 0cm 5 4pt; mso-para-margin:0cm; mso-para-margin-bottom: 0001pt; mso-pagination:widow-orphan; font-size:10 0pt; font-family:"Calibri" "sans-serif"; mso-bidi-font-family:"Times New Roman";'
+      txt.should be_html_leftover
+    end
+
+    it 'returns true for strings with brackets' do
+      'this is {a test'.should              be_html_leftover
+      'this is }another test'.should        be_html_leftover
+      'this { is yet another } test'.should be_html_leftover
+    end
+
+    it 'returns true for strings with < or >' do
+      'this is <a test'.should              be_html_leftover
+      'this is >another test'.should        be_html_leftover
+      'this < is yet another > test'.should be_html_leftover
+    end
+
+    it 'returns false if normal string' do
+      txt = 'Hasta ayer no se confirmó que el mandatario vaya a ofrecer alguna rueda de prensa o visite algún medio de comunicación tampoco se conoce sobre la agenda que vaya a tener luego de culminada la grabación del programa sabatino'
+      txt.should_not be_html_leftover
+    end
+
+  end
+
+end

data/spec/importance_spec.rb

@@ -0,0 +1,56 @@
+# encoding: utf-8
+require 'spec_helper'
+
+describe Piola::Importance do
+
+  describe '#count_words' do
+
+    it "should count the quantity of words in a string" do
+      'foo bar baz'.count_words.should eql(3)
+    end
+
+  end
+
+  describe '#longest_parragraph' do
+
+    it "should fetch the longest parragraph from a text" do
+      txt = "this is the first parragraph\nthis is quite the longest parragraph by far as far as the eye can see\nanother for good measure"
+      txt.longest_parragraph.should eql('this is quite the longest parragraph by far as far as the eye can see')
+    end
+
+  end
+
+  describe '#important_words' do
+
+    it "should fetch the most important words from a text" do
+      txt = "Incrementar bonificación es la oferta común de precandidatos"
+      txt.important_words.should eql('Incrementar bonificación oferta común precandidatos')
+    end
+
+  end
+
+  describe '#just_words' do
+
+    it "should return just the most important clean words of a string" do
+      txt = "Incrementar bonificación es la oferta común de precandidatos (other not important stuff)"
+      txt.just_words.should eql('incrementar bonificacion oferta comun precandidatos')
+    end
+
+    it 'strips quotes (even weird ones)' do
+      txt = "‘assange esta peor que una prision’ \"more quotes\""
+      txt.just_words.should eql('assange esta peor prision more quotes')
+    end
+
+    it 'removes words with equal or less than 3 chars' do
+      txt = "this is a test"
+      txt.just_words.should eql('this test')
+    end
+
+    it "doesn't remove words with 3 chars when option is passed" do
+      txt = "this is a test"
+      txt.just_words(small_words: true).should eql('this is a test')
+    end
+
+  end
+
+end