latex-decode 0.2.0 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 0d7ee959a3494ff7a4944bb79f65ce12c6d881dc
-  data.tar.gz: 7f3199fd6301438401a8a1e9f94fb2cc5dc555e4
+SHA256:
+  metadata.gz: 9192df4a57585120960f5b8f6e2aba62bd900cdd8c649a15cefca04f4819f2f3
+  data.tar.gz: 6d692566a583b9bb70a67763c6c803f4b7e98c2e9c50b006a720cee30b39c72d
 SHA512:
-  metadata.gz: 41713ce86f026006771e711511bf002992a7c7da8abeca6c88e3c1885a3611ead9c98a7ac2795c94d86a7141718427d5875d98b3f3db18fecc76835cf301a13d
-  data.tar.gz: 82a459edb974a2d31908d210f91acd1f7db64074d971df9716709ec62b3f7fb11cfa554bb14488101ed353b54d52c472a02361e0374ce2c9011f813a8f7b3c8e
+  metadata.gz: 6a52d3db67061ed7c206cfa9b52d99ea181ff02bc2be8a21b6b55ebab19f8528565f3b4a882cef8c3b84f0319b99c63e5eef16d7c779ed80fc3405871bf95379
+  data.tar.gz: 0ac36cc1adaeff8d919ab78dc98fcecaadb663519ae6c3bd201327041a704c7e24b170f1143d700be8b999bb1561eb4c36e723b8aaf640fc4f78fb2b9ebfa5c8

data/.travis.yml

@@ -2,14 +2,18 @@ language: ruby
 bundler_args: --without debug
 sudo: false
 cache: bundler
+before_install:
+  - gem update --system
+  - gem update bundler
 rvm:
-  - 1.9.3
-  - 2.0.0
-  - 2.1.0
-  - 2.2.0
+  - 2.3
+  - 2.4
+  - 2.5
+  - 2.6
+  - 2.7
   - jruby-19mode
   - jruby-head
-  - rbx-2
+#- rbx-2
 notifications:
   email:
     recipients:

data/Gemfile

@@ -15,7 +15,7 @@ group :debug do
   gem 'rubinius-compiler', :require => false, :platforms => :rbx
 end
 
-gem 'unicode', '~> 0.4', :platforms => [:mri, :rbx, :mswin, :mingw]
+gem 'unicode', '~> 0.4', :platforms => [:mri, :rbx, :mswin, :mingw] if RUBY_VERSION < '2.4'
 gem 'ritex', '~> 1.0.1'
 
 gem 'rubysl', '~> 2.0', :platforms => :rbx

data/features/punctuation.feature

@@ -29,15 +29,18 @@ Feature: Decode LaTeX punctuation directives
     | \\textoverline       | ‾       |
     | \\langle             | ⟨       |
     | \\rangle             | ⟩       |
+    | \\textquotesingle    | ’       |
 
 
   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/latex-decode.gemspec

@@ -12,12 +12,11 @@ Gem::Specification.new do |s|
   s.homepage    = 'http://github.com/inukshuk/latex-decode'
   s.summary     = 'Decodes LaTeX to Unicode.'
   s.description = 'Decodes strings formatted in LaTeX to equivalent Unicode strings.'
-  s.license     = 'GPL-3'
+  s.license     = 'GPL-3.0'
 
   if RUBY_PLATFORM =~ /java/
     s.platform    = 'java'
   else
-    s.add_dependency('unicode', '~> 0.4')
     s.platform    = 'ruby'
   end
 
@@ -30,4 +29,4 @@ Gem::Specification.new do |s|
   s.extra_rdoc_files = %w{README.md LICENSE}
 end
 
-# vim: syntax=ruby
+# vim: syntax=ruby

data/lib/latex/decode.rb

@@ -31,7 +31,7 @@ require 'latex/decode/greek'
 module LaTeX
 
   class << self
-    def decode (string)
+    def decode(string)
       return string unless string.respond_to?(:to_s)
 
       string = string.is_a?(String) ? string.dup : string.to_s

data/lib/latex/decode/base.rb

@@ -7,7 +7,7 @@ module LaTeX
       class << self
         attr_reader :patterns, :map
 
-        def inherited (base)
+        def inherited(base)
           subclasses << base
         end
 
@@ -15,11 +15,11 @@ module LaTeX
           @subclasses ||= []
         end
 
-        def decode (string)
+        def decode(string)
           decode!(string.dup)
         end
 
-        def decode! (string)
+        def decode!(string)
           patterns.each do |pattern|
             string.gsub!(pattern) { |m| [$2,map[$1],$3].compact.join }
           end
@@ -32,22 +32,25 @@ module LaTeX
 
       module_function
 
-      def normalize (string)
+      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
 
-      def strip_braces (string)
+      def strip_braces(string)
         string.gsub!(/(^|[^\\])([\{\}]+)/, '\1')
         string.gsub!(/\\(\{|\})/, '\1')
         string

data/lib/latex/decode/compatibility.rb

@@ -33,27 +33,35 @@ if RUBY_PLATFORM == 'java'
   end
 
 else
-  begin
-    require 'unicode'
-
-    # Use the Unicode gem
+  if RUBY_VERSION >= '2.3'
     module LaTeX
       def self.normalize_C(string)
-        Unicode::normalize_C(string)
+        string.unicode_normalize(:nfc)
       end
     end
-  rescue LoadError
+  else
     begin
-      require 'active_support/multibyte/chars'
+      require 'unicode'
 
-      # Use ActiveSupport's normalizer
+      # Use the Unicode gem
       module LaTeX
         def self.normalize_C(string)
-          ActiveSupport::Multibyte::Chars.new(string).normalize(:c).to_s
+          Unicode::normalize_C(string)
         end
       end
     rescue LoadError
-      fail "Failed to load unicode normalizer: please gem install unicode (or active_support)"
+      begin
+        require 'active_support/multibyte/chars'
+
+        # Use ActiveSupport's normalizer
+        module LaTeX
+          def self.normalize_C(string)
+            ActiveSupport::Multibyte::Chars.new(string).normalize(:c).to_s
+          end
+        end
+      rescue LoadError
+        fail "Failed to load unicode normalizer: please gem install unicode (or active_support)"
+      end
     end
   end
 end

data/lib/latex/decode/maths.rb

@@ -6,7 +6,7 @@ module LaTeX
         /\$([^\$]+)\$/
       ].freeze
 
-      def self.decode! (string)
+      def self.decode!(string)
         patterns.each do |pattern|
           string.gsub!(pattern) do
             LaTeX.to_math_ml($1)

data/lib/latex/decode/punctuation.rb

@@ -30,6 +30,7 @@ module LaTeX
         textasciicircum    ^
         textbackslash      \\
         textasciitilde     ~
+        textquotesingle    '
       }].freeze
 
       @symbols = Hash[*%w[

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 = '0.2.0'.freeze
+    VERSION = '0.3.2'.freeze
   end
 end

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: latex-decode
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.2
 platform: ruby
 authors:
 - Sylvester Keil
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-02-02 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: unicode
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.4'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.4'
+date: 2020-10-14 00:00:00.000000000 Z
+dependencies: []
 description: Decodes strings formatted in LaTeX to equivalent Unicode strings.
 email:
 - http://sylvester.keil.or.at
@@ -49,6 +35,7 @@ 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
@@ -63,9 +50,9 @@ files:
 - lib/latex/decode/version.rb
 homepage: http://github.com/inukshuk/latex-decode
 licenses:
-- GPL-3
+- GPL-3.0
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--line-numbers"
 - "--inline-source"
@@ -87,9 +74,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.5
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: Decodes LaTeX to Unicode.
 test_files:
@@ -102,5 +88,5 @@ test_files:
 - features/special_characters.feature
 - features/step_definitions/latex.rb
 - features/support/env.rb
+- features/symbols.feature
 - features/umlauts.feature
-has_rdoc: