typogrowth 0.9.1 → 0.9.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 !binary "U0hBMQ==":
-  metadata.gz: 8e2f320681c171005dd2e3b76459c3fbf4ae1046
-  data.tar.gz: c8fc540e85c5f9117865753bfc253b3d6f1f7487
+  metadata.gz: d96c37d2c10f0fc9f73caaeda6be11910a725c7d
+  data.tar.gz: abc183314746913a04adca10b88e380e75981a61
 !binary "U0hBNTEy":
-  metadata.gz: 84020ddf3dc6e4ca88fbb3533f64f20c19baa9fc6bc4fe7ccbc75b2959ecef1cf6e7c869e09fe404770a63e18ed06962cb7e325b6d0837dd6635b17c1104b5ed
-  data.tar.gz: 8617b80ae6d37ea526a18a899d62e98db4d37e699d7835f473b850430dbc9561e345fd1a3384b22b3dafe1d11537a404bc128db664ea43f43e847fef7c76fefa
+  metadata.gz: 9277400dec9a0f43219676988fdac4dfc6e1b257537a9bdf8ba2218abcdf35c473d223f9ed9a07c02b14838687ca9aee923bf380bf3f5047e50534809ef016b2
+  data.tar.gz: 5fd258973bb34862e20c77a0ec8a6b203bb5d60be67ee9736e3a5b90107b21d63625507b5dfd8bac2bb9c7acd9cc40d944c57895de06b533fa9caba2cdba613b

data/.travis.yml

@@ -1,5 +1,4 @@
 language: ruby
 rvm:
-  - 1.9.3
   - 2.0.0
   - 2.1.0

data/features/step_definitions/typogrowth_steps.rb

@@ -11,7 +11,7 @@ end
 
 When(/^input string is processed with Typogrowl’s typography parser with lang "(.*?)"$/) do |lang|
   @content.gsub! /\\+"/, '"'
-  @typo = Typogrowth.parse @content, lang
+  @typo = Typogrowth.parse @content, lang: lang
 end
 
 When(/^input string is modified inplace with typo!$/) do

data/features/typogrowth.feature

@@ -30,8 +30,8 @@ Feature: Text is to be typographed (spacing and pubctuation are to be sanitized)
         | input                          | output                             |
         | "И Бог сказал: \"Я - слышу \"Бум\" и \"Бам\" где-то там\" , и стало светло." | "И Бог сказал: «Я — слышу „Бум“ и „Бам“ где-то там», и стало светло." |
         | "И Бог сказал: \"Я - слышу \"Бум \"и\" Бам\" где-то там\" , и стало светло." | "И Бог сказал: «Я — слышу „Бум «и» Бам“ где-то там», и стало светло." |
-        | "Строка со ссылкой: http://wikipedia.org (ссылка)." | "Строка со ссылкой: http://wikipedia.org (ссылка)." | 
- 
+        | "Строка со ссылкой: http://wikipedia.org (ссылка)." | "Строка со ссылкой: http://wikipedia.org (ссылка)." |
+
   Scenario Outline: Spacing before/after punctuation
     Given the input string is <input>
     When input string is processed with Typogrowl’s typography parser
@@ -47,12 +47,16 @@ Feature: Text is to be typographed (spacing and pubctuation are to be sanitized)
         | "Here is http://wikipedia.org. See?."  | "Here is http://wikipedia.org. See?." |
         | "Here is exclamation ellipsis!.."      | "Here is exclamation ellipsis!.."     |
         | "Here is exclamation ellipsis! . ."    | "Here is exclamation ellipsis!.."     |
+        | "Here we go ; semicolon .. ."          | "Here we go; semicolon…"              |
+        | "Here are ' english ' quotes . ."      | "Here are ‘english’ quotes.."         |
+        | "Here are " english " quotes . ."      | "Here are “english” quotes.."         |
+        | "Here we go : colon . ."               | "Here we go: colon.."                 |
 
   Scenario: Inplace string modification
     Given the input string is "Foo 'Bar' Baz"
     When input string is modified inplace with typo!
     Then typoed result should equal to "Foo “Bar” Baz"
-    
+
   Scenario Outline: Orphans handling
     Given the input string is <input>
     When input string is processed with Typogrowl’s typography parser
@@ -62,4 +66,4 @@ Feature: Text is to be typographed (spacing and pubctuation are to be sanitized)
     Examples:
         | input                                  | output                                |
         | "This is a cat."                       | "This is a cat."                      |
-    
+

data/lib/config/typogrowth.yaml

@@ -34,14 +34,14 @@
   :apostrophe_pre :
     :pattern : ''''
     :re : '(?<=\p{Alpha})('')(?=\p{Alpha})'
-    :default : 
+    :default :
       - '♻'
   # And God said 'Foos' game is over'.
   #                  ⇑
   :apostrophe_squeez :
     :pattern : ''''
     :re : '(?<=s)('')(?=\s)'
-    :default : 
+    :default :
       - '♻'
   # And God said "∇×(∇×F) = ∇(∇·F) − ∇2F" and there was light.
   #              ⇑
@@ -87,6 +87,19 @@
     :default :
       - '’'
 
+  :quotes_single :
+    :re : '\s+''\s+(.+?)\s+''\s+'
+    :default :
+      - ' ‘\1’ '
+    :ru :
+      - ' «\1» '
+  :quotes_double :
+    :re : '\s+"\s+(.+?)\s+"\s+'
+    :default :
+      - ' “\1” '
+    :ru :
+      - ' «\1» '
+
   :alone_single :
     :re : '('')'
     :alert: true
@@ -99,20 +112,6 @@
     :default :
       - '”'
 
-:others :
-  :ellipsis :
-    :re : '\.{3,}'
-    :default :
-      - '…'
-  :mdash :
-    :re : '\s*(?<dash> - |--)\s*'
-    :default :
-      - '—'
-    :ru :
-      - ' — '
-    :us :
-      - ' – '
-
 :punctuation :
   :opening_orphan :
     :re : '([(¿¡§#№]|\p{Sc})(?:\s+)'
@@ -130,7 +129,20 @@
     :re : '([!?.]+)(?:\s*)(\.+)'
     :default :
       - '\1\2'
-      
+  :ellipsis :
+    :re : '\.{3,}'
+    :default :
+      - '…'
+  :mdash :
+    :re : '\s*(?<dash> - |--|–|—)\s*'
+    :default :
+      - '—'
+    :ru :
+      - ' — '
+    :us :
+      - ' – '
+
+# MUST be the last section, since it’ kinda cleanup
 :orphans :
   :dangling_right :
     :re : '(?<=\s|\A)(\p{L})\s+'

data/lib/typogrowth/string.rb

@@ -7,11 +7,11 @@ class String
   # Typographyes the string and returns a result
   # See Typogrowth::Parser#parse
   def typo lang = nil
-    Typogrowth::Parser.parse(self, lang ? lang : I18n.locale)
+    Typogrowth::Parser.parse(self, lang: lang ? lang : I18n.locale)
   end
   # Typographyes the string inplace
   # See Typogrowth::Parser#parse!
   def typo! lang = nil
-    Typogrowth::Parser.parse!(self, lang ? lang : I18n.locale)
+    Typogrowth::Parser.parse!(self, lang: lang ? lang : I18n.locale)
   end
 end

data/lib/typogrowth/version.rb

@@ -1,3 +1,3 @@
 module Typogrowth
-  VERSION = "0.9.1"
+  VERSION = "0.9.3"
 end

data/lib/typogrowth.rb

@@ -8,15 +8,15 @@ require_relative 'typogrowth/version'
 require_relative 'typogrowth/string'
 require_relative 'utils/hash_recursive_merge'
 
-# 
-# = String typographing with language support. 
-# 
-# Parses and corrects the typography in strings. It supports 
+#
+# = String typographing with language support.
+#
+# Parses and corrects the typography in strings. It supports
 # different language rules and user rules customization.
-# 
+#
 # The package also monkeypatches `String` class with both
 # `typo` and `typo!` methods.
-# 
+#
 # Category::    Ruby
 # Author::      Alexei Matyushkin <am@mudasobwa.ru>
 # Copyright::   2013 The Authors
@@ -27,58 +27,69 @@ require_relative 'utils/hash_recursive_merge'
 module Typogrowth
   # Internal exception class just to make the exception distinction possible
   class MalformedRulesFile < Exception ; end
-  
-  # Parses and corrects the typography in strings. It supports 
+
+  # Parses and corrects the typography in strings. It supports
   # different language rules and easy user rules customization.
   class Parser
-    attr_reader :yaml
-    
+    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.
-    # 
+    #
     # To supply your own rules to processing:
-    # 
-    # - create a +hash+ of additional rules in the same form as in the 
+    #
+    # - create a +hash+ of additional rules in the same form as in the
     # standard `typogrowth.yaml` file shipped with a project
     # - merge the hash with the standard one using this function
-    # 
+    #
     # For instance, to add french rules one is to merge in the following yaml:
-    # 
+    #
     #     :quotes :
     #       :punctuation :
     #         :fr : "\\k<quote>\\k<punct>"
     #     …
     #
-    def self.merge custom
-      instance.yaml.rmerge!(custom)
+    def merge custom
+      yaml.rmerge!(custom)
     end
-    
+
     #
     # Inplace version of string typographying.
-    # 
+    #
     # Retrieves the string and changes all the typewriters quotes (doubles
     # and sigles), to inches, minutes, seconds, proper quotation signs.
-    # 
-    # While the input strings are e.g. 
-    #     
+    #
+    # While the input strings are e.g.
+    #
     #     And God said "Baz heard "Bar" once" , and there was light.
     #     That's a 6.3" man, he sees sunsets at 10°20'30" E.
-    #     
+    #
     # It will produce:
-    # 
+    #
     #     And God said “Baz heard ‘Bar’ once,” and there was light.
     #     That’s a 6.3″ man, he sees sunsets at 10°20′30″ E.
-    #     
+    #
     # The utility also handles dashes as well.
-    # 
+    #
     # @param str [String] the string to be typographyed inplace
     # @param lang the language to use rules for
     #
-    def self.parse str, lang = :default
+    def parse str, lang: :default, shadows: []
       lang = lang.to_sym
+      delims = Parser.safe_delimiters str
       str.split(/\R{2,}/).map { |para|
-        para.gsub(URI.regexp) { |m| "⚓#{Base64.encode64 m}⚓" }
-        instance.yaml.each { |key, values|
+        @shadows.concat([*shadows]).uniq.each { |re|
+          para.gsub!(re) { |m| "#{delims.first}#{Base64.encode64 m}#{delims.last}" }
+        }
+        @yaml.each { |key, values|
           values.each { |k, v|
             if !!v[:re]
               v[lang] = v[:default] if (!v[lang] || v[lang].size.zero?)
@@ -93,14 +104,14 @@ module Typogrowth
                 para.gsub!(/#{v[lang].first}/) { |m|
                   prev = $`
                   obsoletes = prev.count(v[lang].join)
-                  compliants = values[v[:compliant].to_sym][lang] || 
+                  compliants = values[v[:compliant].to_sym][lang] ||
                                values[v[:compliant].to_sym][:default]
                   obsoletes -= prev.count(compliants.join) \
                     if !!v[:compliant]
                   !!v[:slave] ?
                     obsoletes -= prev.count(v[:original]) + 1 :
                     obsoletes += prev.count(v[:original])
-                  
+
                   v[lang][obsoletes % v[lang].size]
                 }
               end
@@ -111,35 +122,45 @@ module Typogrowth
       }.join(%Q(
 
 ))
-      .gsub(/⚓(.*)⚓/m) { |m| Base64.decode64 m }
+      .gsub(/#{delims.first}(.*)#{delims.last}/m) { |m| Base64.decode64 m }
+    end
+
+    def add_shadows re
+      @shadows.concat [*re]
+    end
+
+    def del_shadows re
+      @shadows.delete_if { |stored| [*re].include? stored }
+    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
     end
 
     # Out-of-place version of `String` typographing. See #parse!
-    def self.parse! str, lang = :default
-      str.replace self.parse(str, lang)
+    def self.parse! str, lang: :default, shadows: []
+      str.replace self.parse str, lang: lang, shadows: shadows
     end
-  private
+
     DEFAULT_SET = 'typogrowth'
-    
-    def initialize file
+    HTML_TAG_RE = /<[A-Za-z]+(.*?)>/
+
+    def initialize file = nil
+      file = DEFAULT_SET unless file
       @yaml = YAML.load_file "#{File.dirname(__FILE__)}/config/#{file}.yaml"
       @yaml.delete(:placeholder)
+      @shadows = [URI.regexp, HTML_TAG_RE]
     end
 
-    @@instance = Parser.new(DEFAULT_SET)
-    
-    def self.instance 
-      @@instance
-    end
-        
-    private_class_method :new  
   end
 
-  def self.parse str, lang = :default
-    Parser.parse str, lang
+  def self.parse str, lang: :default, shadows: []
+    Parser.parse str, lang: lang, shadows: shadows
   end
-  def self.parse! str, lang = :default
-    Parser.parse! str, lang
+
+  def self.parse! str, lang: :default, shadows: []
+    Parser.parse! str, lang: lang, shadows: shadows
   end
 end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: typogrowth
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.9.3
 platform: ruby
 authors:
 - Alexei Matyushkin