latex-decode 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ab76545e91f882f2219178cfed05479ff8863c41
-  data.tar.gz: 14deebe77e665682d8e6ac4185136b0944643649
+  metadata.gz: b72cef2bcae3250f385227cc6280b46453f9a8a9
+  data.tar.gz: 594fa9c2ccf9ae5b29935813d850459981679d4f
 SHA512:
-  metadata.gz: 13508082cf84fe12b62fac4ccf1faee0becb2b0f2ffe5d0836f3fc43c55293ba97f8d8d4ef630f083d5e84b30fd4bf61f47014d79b2d134a6940ca8859b962b3
-  data.tar.gz: e6712e11c0ea93d8e92edcb6bbfdf10295ce9171b68337919cab04d275f04f13277bdc56cb9e562c1f7f146d5c6ad54114d97e74b9fd86b1c39903000968bad2
+  metadata.gz: fc225084cca699158fb8ecaa31770d01da0c9fdef2fbf85a15e79d314f06a6515fed8a8a0ff7e1c3502bbb950693fb2672d8d7447eeed102c4d3459c3f0561ea
+  data.tar.gz: 534f83cba6ca70064c95c41a249a2bc389f39a8e5507ff4def143a34bc8fa3b239f109975ddeca10d7b0a085b5dcf593b09695db602514dc03a4e916a0c48e1f

data/features/punctuation.feature

@@ -33,12 +33,14 @@ Feature: Decode LaTeX punctuation directives
 
 
   Scenarios: Punctuation symbols
-    | latex   | unicode | description |
-    | -       | -       | hyphen      |
-    | --      | –       | en-dash     |
-    | ---     | —       | em-dash     |
-    | \\~{}   | ~       | tilde       |
-    | X\\ X   | X X     | space       |
+    | latex              | unicode | description |
+    | -                  | -       | hyphen      |
+    | --                 | –       | en-dash     |
+    | ---                | —       | em-dash     |
+    | \\~{}              | ~       | tilde       |
+    | \\textasciitilde{} | ~       | tilde       |
+    | \\textasciitilde   | ~       | tilde       |
+    | X\\ X              | X X     | space       |
 
   Scenarios: Quotation marks
     | latex   | unicode | description         |

data/features/symbols.feature

@@ -0,0 +1,21 @@
+Feature: Decode LaTeX symbol directives
+  As a hacker who works with LaTeX
+  I want to be able to decode LaTeX symbol directives
+
+  Scenario Outline: LaTeX to Unicode transformation
+    When I decode the string '<latex>'
+    Then the result should be '<unicode>'
+
+  Scenarios: Arrows
+    | latex                | unicode |
+    | \\leftarrow          | ←       |
+    | \\uparrow            | ↑       |
+    | \\downarrow          | ↓       |
+    | \\rightarrow         | →       |
+
+  Scenarios: Whitespace
+    | latex | unicode | description        |
+    | x\\,x | x x     | small space        |
+    | x~x   | x x     | non-breaking space |
+    | ~x    |  x      | non-breaking space |
+

data/lib/latex/decode/base.rb

@@ -35,15 +35,18 @@ module LaTeX
       def normalize (string)
         string.gsub!(/\\(?:i|j)\b/) { |m| m == '\\i' ? 'ı' : 'ȷ' }
 
-				# \foo\ bar -> \foo{} bar
+        # \foo\ bar -> \foo{} bar
         string.gsub!(/(\\[a-zA-Z]+)\\(\s+)/, '\1{}\2')
 
-				# Aaaa\o, -> Aaaa\o{},
+        # Aaaa\o, -> Aaaa\o{},
         string.gsub!(/([^{]\\\w)([;,.:%])/, '\1{}\2')
 
-				# \c cb -> \c{cb}
+        # \c cb -> \c{cb}
         string.gsub!(/(\\[^\sij&#\$\{\}_~%])\s+([[:alpha:]]+)\b/i, '\1{\2}')
 
+        # non-breaking spaces
+        string.gsub!(/(\A|[^\\])~/, LaTeX.to_unicode("\\1\u00a0"))
+
         string
       end
 

data/lib/latex/decode/symbols.rb

@@ -4,7 +4,8 @@ module LaTeX
   module Decode
 
     class Symbols < Decoder
-      @map = Hash[*%w{
+
+      @map = Hash[*%W{
         textcolonmonetary ₡
         textlira          ₤
         textnaira         ₦
@@ -211,7 +212,8 @@ module LaTeX
         tone1             ˩
         ss                ß
         ,                 \u2009
-      }].freeze
+      }.map { |s| LaTeX.to_unicode(s) }].freeze
+
 
       @patterns = [
         /\\(#{ map.keys.map { |k| Regexp.escape(k) }.join('|') })(?:\{\}|\s+|\b)/ou

data/lib/latex/decode/version.rb

@@ -1,5 +1,5 @@
 module LaTeX
   module Decode
-    VERSION = '0.2.1'.freeze
+    VERSION = '0.2.2'.freeze
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: latex-decode
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Sylvester Keil
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-25 00:00:00.000000000 Z
+date: 2015-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode
@@ -49,6 +49,7 @@ files:
 - features/special_characters.feature
 - features/step_definitions/latex.rb
 - features/support/env.rb
+- features/symbols.feature
 - features/umlauts.feature
 - latex-decode.gemspec
 - lib/latex/decode.rb
@@ -102,5 +103,6 @@ test_files:
 - features/special_characters.feature
 - features/step_definitions/latex.rb
 - features/support/env.rb
+- features/symbols.feature
 - features/umlauts.feature
 has_rdoc: