typogrowth 0.9.7 → 0.9.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 !binary "U0hBMQ==":
-  metadata.gz: 53a02d4e8ed6d038744689a72340501f7320edbd
-  data.tar.gz: 13da2fe67adcd6bfb6794f97371badaf639bf16a
+  metadata.gz: d51d831d3067a678c4d7f440f08532b0aadcf108
+  data.tar.gz: 296addd6996aafb254597f7c81092edd1fa75241
 !binary "U0hBNTEy":
-  metadata.gz: 1843bc3d26f9a29e4c5ae603a1778ead2534007a0343723445c114440551198999db0420d7abfc084c7ea0e5d60d25bec38437a112a26cda8f1e26332e46926a
-  data.tar.gz: 897f8982e04275fc5529ba666c1317493d43f3e9a8a5159a50aad8d07b9aad4d1d209402c6261800584fbf44ac51448364fb78372cc572f2cfdc3b8536acc5ef
+  metadata.gz: 2e385ed3b085ebdf1a50b67003f42e5184ca7a7f047272aac1391ecc72a082cef9b5a462a098cce8bb283a0c0a82b8986552c43779b4ebcfb5231b4ec43bf4c2
+  data.tar.gz: babea8b38641f4da8ba5f90907f9b6aba0d86316a2ba2dc8239a5caecf98fd2b51dc87b9ec52483e27c3137f5724e65b020ab945f432ff952a3458fa6f9d9cc3

data/features/step_definitions/typogrowth_steps.rb

@@ -4,6 +4,10 @@ Given(/^the input string is "(.*?)"$/) do |str|
   @content = str
 end
 
+Given(/^the input string is$/) do |str|
+  @content = str
+end
+
 When(/^input string is processed with Typogrowl’s typography parser$/) do
   @content.gsub! /\\+"/, '"'
   @typo = Typogrowth.parse @content
@@ -14,6 +18,11 @@ When(/^input string is processed with Typogrowl’s typography parser with lang
   @typo = Typogrowth.parse @content, lang: lang
 end
 
+When(/^input string is processed with Typogrowl’s typography parser with section "(.*?)"$/) do |sect|
+  @content.gsub! /\\+"/, '"'
+  @typo = @content.typo sections: sect.to_sym
+end
+
 When(/^input string is modified inplace with typo!$/) do
   @typoed = @content.dup
   @typoed.typo!
@@ -31,12 +40,16 @@ Then(/^the typoed result should equal to "(.*?)"$/) do |str|
   @typo.should == str
 end
 
+Then(/^the typoed result should equal to$/) do |str|
+  @typo.should == str
+end
+
 Then(/^the call to string’s typo should equal to "(.*?)"$/) do |str|
   @content.typo.should == str
 end
 
 Then(/^the call to string’s typo with lang "(.*?)" should equal to "(.*?)"$/) do |lang, str|
-  @content.typo('ru').should == str
+  @content.typo(lang: 'ru').should == str
 end
 
 Then(/^typoed result should equal to "(.*?)"$/) do |str|

data/features/typogrowth.feature

@@ -76,7 +76,8 @@ Feature: Text is to be typographed (spacing and pubctuation are to be sanitized)
 
     Examples:
         | input                                  | output                                |
-        | "<p><img src="http://mudasobwa.ru/i/self.jpg">Here: http://wikipedia.ru</p>" | "<p><img src="http://mudasobwa.ru/i/self.jpg">Here: http://wikipedia.ru</p>"                      |
+        | "<p><img src="http://mudasobwa.ru/i/self.jpg">Here: http://wikipedia.ru</p>" | "<p><img src="http://mudasobwa.ru/i/self.jpg">Here: http://wikipedia.ru</p>" |
+        | "<p>http://mudasobwa.ru/i/self.jpg With caption<br/> <small><a href='http://wikipedia.ru'>Wiki</a></small> </p>" | "<p>http://mudasobwa.ru/i/self.jpg With caption<br/> <small><a href='http://wikipedia.ru'>Wiki</a></small> </p>" |
 
   Scenario Outline: Language recognition
     Given the input string is <input>
@@ -98,3 +99,41 @@ Feature: Text is to be typographed (spacing and pubctuation are to be sanitized)
         | "Here 'you' go."          | "Here “you” go."                      |
         | "Тут 'русский' язык."     | "Тут «русский» язык."                 |
 
+  Scenario Outline: Section pick-up
+    Given the input string is <input>
+    When input string is processed with Typogrowl’s typography parser with section "quotes"
+    Then the typoed result should equal to <output>
+
+    Examples:
+        | input                         | output                            |
+        | "Here 'you' - go."            | "Here “you” - go."                |
+        | "Тут 'русский' --- язык."     | "Тут «русский» --- язык."         |
+
+  Scenario Outline: Predefined shadows
+    Given the input string is <input>
+    When input string is processed with Typogrowl’s typography parser
+    Then the typoed result should equal to <output>
+
+    Examples:
+        | input                         | output                            |
+        | "This is λsystem.dllλ file."  | "This is λsystem.dllλ file."      |
+        | "This is ✓8:35✓ time."       | "This is ✓8:35✓ time."           |
+
+  Scenario: Inplace tags
+    Given the input string is
+    """
+    http://qipowl.herokuapp.com/images/owl.png
+
+    ☞ Video embedded:
+
+    http://www.youtube.com/watch?v=KFKxlYNfT_o
+    """
+    When input string is processed with Typogrowl’s typography parser
+    Then the typoed result should equal to
+    """
+    http://qipowl.herokuapp.com/images/owl.png
+
+    ☞ Video embedded:
+
+    http://www.youtube.com/watch?v=KFKxlYNfT_o
+    """

data/lib/config/shadows.yaml

@@ -0,0 +1,3 @@
+:grip :
+  - 'λ'
+  - '✓'

data/lib/config/typogrowth.yaml

@@ -1,4 +1,4 @@
-:quotes :
+:sequence :
   :punctuation :
     :re : '(?<quote>''|"|\))\s*(?<punct>[.,!?]+)'
     :default :
@@ -6,6 +6,7 @@
     :ru :
       - '\k<quote>\k<punct>'
 
+:quotes :
   # That's a 6.3" man, he sees sunsets at 10°20'30" E.
   #             ⇑
   :inch :
@@ -78,7 +79,6 @@
     :us :
       - '’'
       - '”'
-
   # That's a 6.3" man, he sees sunsets at 10°20'30" E.
   #     ⇑
   :apostrophe_post :
@@ -113,12 +113,24 @@
       - '”'
 
 :punctuation :
+  :bloody_quote_en :
+    :re : '(“)(?:\s+)'
+    :default :
+      - '\1'
+    :ru :
+      - '\1 '
+  :bloody_quote_ru :
+    :re : '(?:\s+)(“)'
+    :default :
+      - ' \1'
+    :ru :
+      - '\1'
   :opening_orphan :
-    :re : '([(¿¡§#№]|\p{Sc})(?:\s+)'
+    :re : '([(¿¡§#№‘„«]|\p{Sc})(?:\s+)'
     :default :
       - '\1'
   :closing_orphan :
-    :re : '(?:\s+)([.,:;!?)])'
+    :re : '(?:\s+)([.,:;!?)”’»])'
     :default :
       - '\1'
   :closing_clamped :
@@ -134,7 +146,7 @@
     :default :
       - '…'
   :mdash :
-    :re : '\s*(?<dash> - |--|–|—)\s*'
+    :re : '\p{Space}*(?<dash>\s-\s|--|–|—)\s*'
     :default :
       - '—'
     :ru :
@@ -153,6 +165,6 @@
     :default :
       - ' \1'
   :extra_spaces :
-    :re : '\s+'
+    :re : ' +'
     :default :
       - ' '

data/lib/typogrowth.rb

@@ -33,14 +33,6 @@ module Typogrowth
   class Parser
     attr_reader :yaml, :shadows
 
-    def self.safe_delimiters str
-      delimiters = ['❮', '❯']
-      loop do
-        break delimiters unless str.match(/#{delimiters.join('|')}/)
-        delimiters.map! {|d| d*2}
-      end
-    end
-
     #
     # Recursively merges the initial settings with custom.
     #
@@ -82,14 +74,15 @@ module Typogrowth
     # @param str [String] the string to be typographyed inplace
     # @param lang the language to use rules for
     #
-    def parse str, lang: :default, shadows: []
+    def parse str, lang: :default, shadows: [], sections: nil
       lang = lang.to_sym
-      delims = Parser.safe_delimiters str
+      delims = str.safe_delimiters
       str.split(/\R{2,}/).map { |para|
-        @shadows.concat([*shadows]).uniq.each { |re|
+        [*shadows].concat(@shadows).uniq.each { |re|
           para.gsub!(re) { |m| "#{delims.first}#{Base64.encode64 m}#{delims.last}" }
         }
         @yaml.each { |key, values|
+          next if sections && ![*sections].include?(key)
           values.each { |k, v|
             if !!v[:re]
               v[lang] = v[:default] if (!v[lang] || v[lang].size.zero?)
@@ -128,12 +121,25 @@ module Typogrowth
     end
 
     def is_ru? str, shadows: []
-      clean = @shadows.concat([*shadows]).uniq.inject(str) { |memo, re|
+      clean = [*shadows].concat(@shadows).uniq.inject(str) { |memo, re|
         memo.gsub(re, '')
       }
       clean.scan(/[А-Яа-я]/).size > clean.length / 3
     end
 
+    def defuse str, elements, shadows: []
+      delims = str.safe_delimiters
+      s = str.dup
+      [*shadows].concat(@shadows).uniq.each { |re|
+        s.gsub!(re) { |m| "#{delims.first}#{Base64.encode64 m}#{delims.last}" }
+      }
+#      s.gsub(Regexp.union(elements), ' \1 ')
+      s.gsub(/(#{elements.map {|e| Regexp.escape e}.join('|')})/, ' \1 ')
+       .gsub(/#{delims.first}(.*?)#{delims.last}/m) { |m|
+         Base64.decode64(m).force_encoding('UTF-8')
+       }
+    end
+
     def add_shadows re
       @shadows.concat [*re]
     end
@@ -143,13 +149,13 @@ module Typogrowth
     end
 
     # Out-of-place version of `String` typographing. See #parse!
-    def self.parse str, lang: :default, shadows: []
-      Parser.new.parse str, lang: lang, shadows: shadows
+    def self.parse str, lang: :default, shadows: [], sections: nil
+      Parser.new.parse str, lang: lang, shadows: shadows, sections: sections
     end
 
     # Out-of-place version of `String` typographing. See #parse!
-    def self.parse! str, lang: :default, shadows: []
-      str.replace self.parse str, lang: lang, shadows: shadows
+    def self.parse! str, lang: :default, shadows: [], sections: nil
+      str.replace self.parse str, lang: lang, shadows: shadows, sections: sections
     end
 
     # Out-of-place version of `String` typographing. See #parse!
@@ -157,30 +163,47 @@ module Typogrowth
       @@instance.is_ru? str, shadows: shadows
     end
 
+    # Out-of-place version of `String` typographing. See #parse!
+    def self.defuse str, elements, shadows: []
+      Parser.new.defuse str, elements, shadows: shadows
+    end
+
     DEFAULT_SET = 'typogrowth'
-    HTML_TAG_RE = /<[^>]*>/
+    DEFAULT_SHADOWS = 'shadows'
+    HTML_TAG_RE = /<\s*[A-Za-z][^>]*>/
 
-    def initialize file = nil
+    def initialize file = nil, shadows = nil
       file = DEFAULT_SET unless file
       @yaml = YAML.load_file "#{File.dirname(__FILE__)}/config/#{file}.yaml"
       @yaml.delete(:placeholder)
-      @shadows = [HTML_TAG_RE, URI.regexp(['ftp', 'http', 'https', 'mailto'])]
+      shadows = DEFAULT_SHADOWS unless shadows
+      shadows = YAML.load_file("#{File.dirname(__FILE__)}/config/#{shadows}.yaml")
+      @shadows = ([
+        (shadows[:custom].map { |g| /#{g}/ } if shadows[:custom]),
+        (shadows[:grip].map { |g| /(?<=#{g})([^#{g}]*)(?=#{g})/m } if shadows[:grip]),
+        HTML_TAG_RE,
+        URI.regexp(['ftp', 'http', 'https', 'mailto'])
+      ] - [nil]).flatten
     end
 
     # Ready-to-use single instance
     @@instance = Parser.new
   end
 
-  def self.parse str, lang: :default, shadows: []
-    Parser.parse str, lang: lang, shadows: shadows
+  def self.parse str, lang: :default, shadows: [], sections: nil
+    Parser.parse str, lang: lang, shadows: shadows, sections: sections
   end
 
-  def self.parse! str, lang: :default, shadows: []
-    Parser.parse! str, lang: lang, shadows: shadows
+  def self.parse! str, lang: :default, shadows: [], sections: nil
+    Parser.parse! str, lang: lang, shadows: shadows, sections: sections
   end
 
   def self.is_ru? str, shadows: []
     Parser.is_ru? str, shadows: shadows
   end
+
+  def self.defuse str, elements, shadows: []
+    Parser.defuse str, elements, shadows: shadows
+  end
 end
 

data/lib/typogrowth/string.rb

@@ -1,21 +1,63 @@
 # encoding: utf-8
 
 require 'i18n'
+require 'base64'
 require_relative '../typogrowth'
 
 class String
+  PUNCTUATION = '¿?¡!()„“”‚‘’«».,:;'.split //
+
   # Typographyes the string and returns a result
   # See Typogrowth::Parser#parse
-  def typo lang = nil
-    Typogrowth.parse(self, lang: lang ? lang : is_ru? ? "ru" : I18n.locale)
+  def typo lang: nil, sections: nil, shadows: nil
+    Typogrowth.parse(
+      self,
+      lang: lang ? lang : is_ru? ? "ru" : I18n.locale,
+      shadows: shadows,
+      sections: sections
+    )
   end
   # Typographyes the string inplace
   # See Typogrowth::Parser#parse!
-  def typo! lang = nil
-    Typogrowth.parse!(self, lang: lang ? lang : is_ru? ? "ru" : I18n.locale)
+  def typo! lang: nil, sections: nil, shadows: nil
+    Typogrowth.parse!(
+      self,
+      lang: lang ? lang : is_ru? ? "ru" : I18n.locale,
+      shadows: shadows,
+      sections: sections
+    )
   end
 
-  def is_ru? shadows = []
+  def is_ru? shadows: []
     Typogrowth.is_ru? self, shadows: shadows
   end
+
+  def defuse elements = nil, shadows: []
+    Typogrowth.defuse self, elements || PUNCTUATION, shadows: shadows
+  end
+
+  def psub pattern, exclusion, replacement
+    delims = self.safe_delimiters
+    s = self.dup
+    [*exclusion].each { |re|
+      re = /#{re}/ unless Regexp === re
+      s.gsub!(re) { |m| "#{delims.first}#{Base64.encode64 m}#{delims.last}" }
+    }
+    s.gsub! pattern, replacement
+    s.gsub!(/#{delims.first}(.*?)#{delims.last}/m) { |m|
+      Base64.decode64(m).force_encoding('UTF-8')
+    }
+    s
+  end
+
+# private
+
+  def safe_delimiters
+    delimiters = ['❮', '❯']
+    loop do
+      break delimiters unless self.match(/#{delimiters.join('|')}/)
+      delimiters.map! {|d| d*2}
+    end
+  end
+
 end

data/lib/typogrowth/version.rb

@@ -1,3 +1,3 @@
 module Typogrowth
-  VERSION = "0.9.7"
+  VERSION = "0.9.8"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: typogrowth
 version: !ruby/object:Gem::Version
-  version: 0.9.7
+  version: 0.9.8
 platform: ruby
 authors:
 - Alexei Matyushkin
@@ -128,6 +128,7 @@ files:
 - features/step_definitions/typogrowth_steps.rb
 - features/support/env.rb
 - features/typogrowth.feature
+- lib/config/shadows.yaml
 - lib/config/typogrowth.yaml
 - lib/typogrowth.rb
 - lib/typogrowth/string.rb