linkhum 0.0.2 → 0.0.3

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    MjZjODJiMGM1N2Q2ZjdlOTkyN2IyMThkNGQ4MDI3NjgyMzJhYzExZA==
-  data.tar.gz: !binary |-
-    M2MwNTM2MGVmZjk5ZmZiMzMyOGU4YWFkN2Q2NDUyY2M0ODJlZWUzOA==
+SHA1:
+  metadata.gz: ad631369a4a44fc5562c929ebc4a8fa923e745a5
+  data.tar.gz: 184172a484e5eb074c8a28d269225ada3bd9c27f
 SHA512:
-  metadata.gz: !binary |-
-    OTY5ZGIzNzdkZjgzYWJkODcyYjJlZjYzMzM4NGRiNGViYjNhMjUxNTdmMTM0
-    NDNhMTY2NzE4NzNlMDY4ZWQ2NTA4OTE4ZmU0YzIyZGY1ZWY4Y2Y0NjZkNWFj
-    YTdkZGY1N2U3NmMzMTA0NjU2ZTlkYWRlYTgyZTcwNWI0NGU2NzA=
-  data.tar.gz: !binary |-
-    YWMwMDdhMzZjNzcxMDMyMTlhN2E0MmRkMGY1NDBmMzA0N2UwYWRjMjZjNGU5
-    MjljNGNmZTkxOTIxMDJlMjlkN2ZjZmY1MDhkODI0MjhmZTIyZjRmMWE0MzRm
-    N2NkMTM1OWQxYzQ1YTY1ZGFiYTlhODY3OWNhOTIwNzdhNGI5NDQ=
+  metadata.gz: bef81a104f120fcb54de689365516c1d4211e45652c299f024377c406234fc26eaec9c4924e8ff646b54d65c3e96d3a5c82d2a3d06d5e5ec675a46f53492863a
+  data.tar.gz: ad5e85a10b6c8a580fc8a58988fd13f891fce000255da24de010a8756ae8743fb98d85b4a583047615567cb3628ebcc7d8effe6171d1e5f9571ba903f8889c8b

data/README.md

@@ -12,7 +12,7 @@ Features:
 * customizable behavior.
 
 **NB**: the original algo was written by [squadette](https://github.com/squadette)
-and the test cases provided by users of _some secret social network_.
+and the test cases provided by users of [Mokum](https://mokum.place).
 Just gemifying this (on behalf of original author).
 
 ## Install
@@ -167,10 +167,38 @@ SeveralArgs.urlify('@cool_dude')
 # Receives "cool", "dude"
 ```
 
+### "Parse only" mode
+
+If your demands for resulting strings construction is far more complicated
+than default LinkHum behavior, you can use its `#parse` command to split
+string into tokens, and process them by yourself. All URL-detection
+goodness and `special`s still will be with you:
+
+```ruby
+class MyParser < LinkHum
+  # You don't need rendering blocks for your specials
+  # Second argument is special's name, it is optional
+  special /@(\S+)\b/, :username
+  special /\#(\S+)\b/, :tag
+end
+
+MyParser.parse("Here is @dude. He is #cute. Is he on http://facebook.com?")
+# => [
+#   {type: :text    , content: 'Here is '},
+#   {type: :username, content: '@dude', captures: ['dude']},
+#   {type: :text    , content: '. He is '},
+#   {type: :tag     , content: '#cute', captures: ['cute']},
+#   {type: :text    , content: '. Is he on '},
+#   {type: :url     , content: 'http://facebook.com'},
+#   {type: :text    , content: '?'}
+# ]
+```
+
 ## Credits
 
 * [squadette](https://github.com/squadette) -- author of original code;
-* users of _some secret social network_ -- testing and advicing;
+* users of [Mokum](https://mokum.place) -- testing and advicing (and now
+  you can observe LinkHum work online at Mokum);
 * [zverok](https://github.com/zverok) -- gemifying, documenting and
   writing specs.
 

data/lib/linkhum.rb

@@ -1,6 +1,7 @@
 # encoding: utf-8
 require 'addressable/uri'
 require 'cgi'
+require 'strscan'
 
 class LinkHum
   class << self
@@ -10,76 +11,125 @@ class LinkHum
       new(text).urlify(options.merge(link_processor: block))
     end
 
+    def parse(text)
+      new(text).parse
+    end
+
     def specials
-      @specials ||= []
+      @specials ||= {}
     end
 
-    def special(pattern = nil, &block)
-      specials << [pattern, block]
+    RESERVED_NAMES = [:text, :url, :special]
+
+    def special(pattern, name = nil, &block)
+      name ||= "special_#{specials.count + 1}".to_sym
+
+      RESERVED_NAMES.include?(name) and fail(ArgumentError, "#{name} is reserved")
+      specials.key?(name) and fail(ArgumentError, "#{name} is already defined")
+      
+      specials[name] = [pattern, block]
     end
   end
 
   PROTOCOLS = '(?:https?|ftp)'
-  SPLIT_PATTERN = %r{(#{PROTOCOLS}://\p{^Space}+)}i
+  URL_PATTERN = %r{(#{PROTOCOLS}://\p{^Space}+)}i
 
   MAX_DISPLAY_LENGTH = 64
 
   def initialize(text)
     @text = text
-    @components = @text.split(SPLIT_PATTERN)
+  end
+
+  def parse
+    (@text.split(URL_PATTERN) + ['']).tap{|components|
+      (components).each_cons(2){|left, right|
+        # ['http://google.com', '/ and stuff'] => ['http://google.com/', ' and stuff']
+        shift_punct(left, right) if url?(left) && !url?(right)
+      }
+    }.reject(&:empty?).
+    map{|str|
+      url?(str) ? {type: :url, content: str} : parse_specials(str)
+    }.flatten
   end
 
   def urlify(options = {})
-    @components.map{|str|
-      SPLIT_PATTERN =~ str ? process_url(str, options) : process_text(str)
+    parse.map{|component|
+      case component[:type]
+      when :url
+        process_url(component[:content], options)
+      when :text
+        process_text(component[:content])
+      else
+        process_special(component)
+      end
     }.join
   end
 
   private
 
-  def process_url(str, options)
-    url, punct = str.scan(%r{\A(#{PROTOCOLS}://.+?)(\p{Punct}*)\Z}i).flatten
-    return str unless url
-
+  def url?(str)
+    str =~ URL_PATTERN
+  end
+  
+  # NB: nasty inplace strings changing is going on inside, beware!
+  def shift_punct(url, text_after)
+    url_, punct = url.scan(%r{\A(#{PROTOCOLS}://.+?)(\p{Punct}*)\Z}i).flatten
+    return unless url_
+    
     if punct[0] == '/' || (punct[0] == ')' && url.include?('('))
-      url << punct.slice!(0)
+      url_ << punct.slice!(0)
     end
     
-    make_link(url, options) + punct
+    url.replace(url_)
+    text_after.prepend(punct)
   end
 
-  def process_text(str)
-    str = CGI.escapeHTML(str)
-    
-    if self.class.specials.empty?
-      str
-    else
-      replace_specials(str)
+  def parse_specials(str)
+    res = []
+    str = str.dup
+    while !str.empty?
+      md = (specials_pattern.match(str)) or break
+      md.length.zero? and fail(RuntimeError, "Empty string matched by special at '#{str}'")
+      
+      res << {type: :text, content: md.pre_match}
+      res << {type: :special, content: md[0]}
+      str = md.post_match
     end
+    res << {type: :text, content: str}
+    res.reject{|r| r[:content].empty?}.each{|r|
+      update_special(r) if r[:type] == :special
+    }
   end
 
-  def replace_specials(str)
-    patterns = self.class.specials.map(&:first)
-    blocks = self.class.specials.map(&:last)
-    
-    str.gsub(Regexp.union(patterns)) do |s|
-      pattern = patterns.detect{|p| s[p] == s}
-      idx = patterns.index(pattern)
-      
-      if idx && (u = blocks[idx].call(*arguments(pattern, s)))
-        "<a href='#{screen_feet(u)}'>#{s}</a>"
-      else
-        s
-      end
+  def specials_pattern
+    @specials_pattern ||= Regexp.union(self.class.specials.values.map(&:first))
+  end
+
+  def update_special(hash)
+    str = hash[:content]
+    name, (pattern, block) = self.class.specials.detect{|n, (p, b)| str[p] == str}
+    if name
+      hash.update(type: name, captures: pattern.match(str).captures)
     end
   end
 
-  def arguments(pattern, string)
-    m = pattern.match(string)
-    m.captures.empty? ? m[0] : m.captures
+  def process_text(str)
+    CGI.escapeHTML(str)
+  end
+
+  def process_special(special)
+    return special[:content] if special[:type] == :special
+    
+    _pattern, block = self.class.specials[special[:type]]
+    args = special[:captures] || [special[:match]]
+    if u = block.call(*args)
+      "<a href='#{screen_feet(u)}'>#{special[:content]}</a>"
+    else
+      special[:content]
+    end
   end
 
-  def make_link(url, options)
+  def process_url(url, options)
     uri = Addressable::URI.parse(url) rescue nil
     return url unless uri
 

data/linkhum.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name     = 'linkhum'
-  s.version  = '0.0.2'
+  s.version  = '0.0.3'
   s.authors  = ['Alexey Makhotkin', 'Victor Shepelev']
   s.email    = 'zverok.offline@gmail.com'
   s.homepage = 'https://github.com/zverok/linkhum'
@@ -28,5 +28,6 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'rspec-its', '~> 1'
   s.add_development_dependency 'nokogiri'
   s.add_development_dependency 'rubocop'
+  s.add_development_dependency 'rubygems-tasks'
   #s.add_development_dependency 'dokaz'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: linkhum
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Alexey Makhotkin
@@ -9,90 +9,104 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-07-16 00:00:00.000000000 Z
+date: 2015-12-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
 - !ruby/object:Gem::Dependency
   name: rspec-its
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubygems-tasks
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: 
@@ -101,7 +115,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .dokaz
+- ".dokaz"
 - CHANGELOG.md
 - LICENSE.txt
 - README.md
@@ -117,12 +131,12 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
@@ -132,4 +146,3 @@ signing_key:
 specification_version: 4
 summary: Humane link urlifier
 test_files: []
-has_rdoc: