linkify-it-rb 1.2.0 → 2.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 82b2fb7b546639550e88ace3601ef00e6e250947
-  data.tar.gz: c858ce560f4f15ed72d70612ba6db5d136ced5a3
+  metadata.gz: 176768c4d108c26b13260d1e62c1cb30cd0491f5
+  data.tar.gz: a47bd97acdf25582ce67d65551a1d94678d56aa3
 SHA512:
-  metadata.gz: 17a3be5c92263a111057cfa856eb69feb4ead4b44cad7ba61aecba117d5fda188e42b0a545094be724aeba58dc00d2a0d260db7e3a00004f40da5d78a37c6eec
-  data.tar.gz: 00860971169d330cecebd36dfd2d1dff8b34aee1f75049240d27e1b8ddae0d1cf48d22f63debaab8e877f44f4cc64789d9a51262329c9b66cae01c46a0194da6
+  metadata.gz: 1cbcc4a1e42a24df990484e927b1049a81ff87a8bd0a53f43d32f9d0687ec2bcfb2ec81778e1fbd4a33e11c9e41796e4787d84b8f3f55461ed853dfe4b40c05e
+  data.tar.gz: 5b25b74826e53b4257fdc2b4ea1b0422659d44c9ec69e877ee37b396d9597654db71811d2593193552785cdb8a71258485d4a57a6447b2036cbf324386d0380f

data/README.md

@@ -1,11 +1,16 @@
 # linkify-it-rb
 
 [![Gem Version](https://badge.fury.io/rb/linkify-it-rb.svg)](http://badge.fury.io/rb/linkify-it-rb)
-
-Links recognition library with full unicode support. Focused on high quality link pattern detection in plain text.  For use with both Ruby and RubyMotion.
+[![Build Status](https://travis-ci.org/digitalmoksha/linkify-it-rb.svg?branch=master)](https://travis-ci.org/digitalmoksha/linkify-it-rb)
 
 This gem is a port of the [linkify-it javascript package](https://github.com/markdown-it/linkify-it) by Vitaly Puzrin, that is used for the [markdown-it](https://github.com/markdown-it/markdown-it) package.
 
+_Currently synced with linkify-it 2.0.3_
+
+---
+
+Links recognition library with full unicode support. Focused on high quality link pattern detection in plain text.  For use with both Ruby and RubyMotion.
+
 __[Javascript Demo](http://markdown-it.github.io/linkify-it/)__
 
 Features:
@@ -46,8 +51,8 @@ Usage examples
 ```ruby
 linkify = Linkify.new
 
-# add unoffocial `.onion` domain.
-linkify.tlds('.onion', true)     # Add unofficial `.onion` domain
+# Reload full tlds list & add unofficial `.onion` domain.
+linkify.tlds('onion', true)      # Add unofficial `.onion` domain
 linkify.add('git:', 'http:')     # Add `git:` ptotocol as "alias"
 linkify.add('ftp:', null)        # Disable `ftp:` ptotocol
 linkify.set({fuzzyIP: true})     # Enable IPs in fuzzy links (without schema)
@@ -59,7 +64,7 @@ linkify.match('Site github.com!'))
 => [#<Linkify::Match @schema="", @index=5, @lastIndex=15, @raw="github.com", @text="github.com", @url="github.com">]
 ```
 
-##### Exmple 2. Add twitter mentions handler
+##### Example 2. Add twitter mentions handler
 
 ```ruby
 linkify.add('@', {
@@ -96,7 +101,7 @@ By default understands:
 `schemas` is a Hash, where each key/value describes protocol/rule:
 
 - __key__ - link prefix (usually, protocol name with `:` at the end, `skype:`
-  for example). `linkify-it-rb` makes shure that prefix is not preceeded with
+  for example). `linkify-it-rb` makes sure that prefix is not preceded with
   alphanumeric char.
 - __value__ - rule to check tail after link prefix
   - _String_ - just alias to existing rule
@@ -108,10 +113,11 @@ By default understands:
 
 `options`:
 
-- __fuzzyLink__ - recognige URL-s without `http(s):` prefix. Default `true`.
+- __fuzzyLink__ - recognize URL-s without `http(s)://` head. Default `true`.
 - __fuzzyIP__ - allow IPs in fuzzy links above. Can conflict with some texts
   like version numbers. Default `false`.
-- __fuzzyEmail__ - recognize emails without `mailto:` prefix.
+- __fuzzyEmail__ - recognize emails without `mailto:` prefix. Default `true`.
+- __---__ - set `true` to terminate link with `---` (if it's considered as long dash).
 
 
 ### .test(text)
@@ -149,16 +155,14 @@ Each match has:
 
 ### .tlds(list[, keepOld])
 
-Load (or merge) new tlds list. These are used for fuzzy links (without prefix)
+Load (or merge) new tlds list. These are needed for fuzzy links (without schema)
 to avoid false positives. By default this algorithm uses:
 
-- hostname with any 2-letter root zones are ok.
-- biz|com|edu|gov|net|org|pro|web|xxx|aero|asia|coop|info|museum|name|shop|рф
-  are ok.
+- 2-letter root zones are ok.
+- biz|com|edu|gov|net|org|pro|web|xxx|aero|asia|coop|info|museum|name|shop|рф are ok.
 - encoded (`xn--...`) root zones are ok.
 
-If list is replaced, then exact match for 2-chars root zones will be checked.
-
+If that's not enougth, you can reload defaults with more detailed zones list.
 
 ### .add(schema, definition)
 

data/lib/linkify-it-rb.rb

@@ -1,18 +1,18 @@
-# encoding: utf-8
-
 if defined?(Motion::Project::Config)
-  
+
   lib_dir_path = File.dirname(File.expand_path(__FILE__))
   Motion::Project::App.setup do |app|
-    app.files.unshift(Dir.glob(File.join(lib_dir_path, "linkify-it-rb/**/*.rb")))
+    app.files.unshift(Dir.glob(File.join(lib_dir_path, 'linkify-it-rb/**/*.rb')))
+
+    app.files_dependencies File.join(lib_dir_path, 'linkify-it-rb/index.rb') => File.join(lib_dir_path, 'linkify-it-rb/re.rb')
   end
-  
+
   require 'uc.micro-rb'
 
 else
-  
+
   require 'uc.micro-rb'
   require 'linkify-it-rb/re'
   require 'linkify-it-rb/index'
-  
+
 end

data/lib/linkify-it-rb/index.rb

@@ -1,15 +1,15 @@
 class Linkify
   include ::LinkifyRe
-  
+
   attr_accessor   :__index__, :__last_index__, :__text_cache__, :__schema__, :__compiled__
   attr_accessor   :re, :bypass_normalizer
-  
+
   # RE pattern for 2-character tlds (autogenerated by ./support/tlds_2char_gen.js)
   TLDS_2CH_SRC_RE = 'a[cdefgilmnoqrstuwxz]|b[abdefghijmnorstvwyz]|c[acdfghiklmnoruvwxyz]|d[ejkmoz]|e[cegrstu]|f[ijkmor]|g[abdefghilmnpqrstuwy]|h[kmnrtu]|i[delmnoqrst]|j[emop]|k[eghimnprwyz]|l[abcikrstuvy]|m[acdeghklmnopqrstuvwxyz]|n[acefgilopruz]|om|p[aefghklmnrstwy]|qa|r[eosuw]|s[abcdeghijklmnortuvxyz]|t[cdfghjklmnortvwz]|u[agksyz]|v[aceginu]|w[fs]|y[et]|z[amw]'
 
   # DON'T try to make PRs with changes. Extend TLDs with LinkifyIt.tlds() instead
   TLDS_DEFAULT = 'biz|com|edu|gov|net|org|pro|web|xxx|aero|asia|coop|info|museum|name|shop|рф'.split('|')
-  
+
   DEFAULT_OPTIONS = {
     fuzzyLink: true,
     fuzzyEmail: true,
@@ -23,7 +23,7 @@ class Linkify
 
         if (!obj.re[:http])
           # compile lazily, because "host"-containing variables can change on tlds update.
-          obj.re[:http] = Regexp.new('^\\/\\/' + LinkifyRe::SRC_AUTH + LinkifyRe::SRC_HOST_PORT_STRICT + LinkifyRe::SRC_PATH, 'i')
+          obj.re[:http] = Regexp.new('^\\/\\/' + obj.re[:src_auth] + obj.re[:src_host_port_strict] + obj.re[:src_path], 'i')
         end
         if obj.re[:http] =~ tail
           return tail.match(obj.re[:http])[0].length
@@ -38,13 +38,24 @@ class Linkify
         tail = text.slice(pos..-1)
 
         if (!obj.re[:no_http])
-          # compile lazily, becayse "host"-containing variables can change on tlds update.
-          obj.re[:no_http] = Regexp.new('^' + LinkifyRe::SRC_AUTH + LinkifyRe::SRC_HOST_PORT_STRICT + LinkifyRe::SRC_PATH, 'i')
+          # compile lazily, because "host"-containing variables can change on tlds update.
+          obj.re[:no_http] = Regexp.new(
+            '^' +
+            obj.re[:src_auth] +
+            # Don't allow single-level domains, because of false positives like '//test'
+            # with code comments
+            '(?:localhost|(?:(?:' + obj.re[:src_domain] + ')\\.)+' + obj.re[:src_domain_root] + ')' +
+            obj.re[:src_port] +
+            obj.re[:src_host_terminator] +
+            obj.re[:src_path],
+            'i'
+          )
         end
 
         if (obj.re[:no_http] =~ tail)
-          # should not be `://`, that protects from errors in protocol name
+          # should not be `://` & `///`, that protects from errors in protocol name
           return 0 if (pos >= 3 && text[pos - 3] == ':')
+          return 0 if (pos >= 3 && text[pos - 3] == '/')
           return tail.match(obj.re[:no_http])[0].length
         end
         return 0
@@ -55,7 +66,7 @@ class Linkify
         tail = text.slice(pos..-1)
 
         if (!obj.re[:mailto])
-          obj.re[:mailto] = Regexp.new('^' + LinkifyRe::SRC_EMAIL_NAME + '@' + LinkifyRe::SRC_HOST_STRICT, 'i')
+          obj.re[:mailto] = Regexp.new('^' + obj.re[:src_email_name] + '@' + obj.re[:src_host_strict], 'i')
         end
         if (obj.re[:mailto] =~ tail)
           return tail.match(obj.re[:mailto])[0].length
@@ -104,18 +115,21 @@ class Linkify
   #
   #------------------------------------------------------------------------------
   def compile
-    @re = { src_xn: LinkifyRe::SRC_XN }
+    @re = build_re(@__opts__)
 
     # Define dynamic patterns
     tlds = @__tlds__.dup
+
+    onCompile
+
     tlds.push(TLDS_2CH_SRC_RE) if (!@__tlds_replaced__)
     tlds.push(@re[:src_xn])
 
-    @re[:src_tlds] = tlds.join('|')
-    @re[:email_fuzzy]      = Regexp.new(LinkifyRe::TPL_EMAIL_FUZZY.gsub('%TLDS%', @re[:src_tlds]), true)
-    @re[:link_fuzzy]       = Regexp.new(LinkifyRe::TPL_LINK_FUZZY.gsub('%TLDS%', @re[:src_tlds]), true)
-    @re[:link_no_ip_fuzzy] = Regexp.new(LinkifyRe::TPL_LINK_NO_IP_FUZZY.gsub('%TLDS%', @re[:src_tlds]), true)
-    @re[:host_fuzzy_test]  = Regexp.new(LinkifyRe::TPL_HOST_FUZZY_TEST.gsub('%TLDS%', @re[:src_tlds]), true)
+    @re[:src_tlds]         = tlds.join('|')
+    @re[:email_fuzzy]      = Regexp.new(@re[:tpl_email_fuzzy].gsub('%TLDS%', @re[:src_tlds]), true)
+    @re[:link_fuzzy]       = Regexp.new(@re[:tpl_link_fuzzy].gsub('%TLDS%', @re[:src_tlds]), true)
+    @re[:link_no_ip_fuzzy] = Regexp.new(@re[:tpl_link_no_ip_fuzzy].gsub('%TLDS%', @re[:src_tlds]), true)
+    @re[:host_fuzzy_test]  = Regexp.new(@re[:tpl_host_fuzzy_test].gsub('%TLDS%', @re[:src_tlds]), true)
 
     #
     # Compile each schema
@@ -190,8 +204,8 @@ class Linkify
     slist = @__compiled__.select {|name, val| name.length > 0 && !val.nil? }.keys.map {|str| escapeRE(str)}.join('|')
 
     # (?!_) cause 1.5x slowdown
-    @re[:schema_test]   = Regexp.new('(^|(?!_)(?:>|' + LinkifyRe::SRC_Z_P_CC + '))(' + slist + ')', 'i')
-    @re[:schema_search] = Regexp.new('(^|(?!_)(?:>|' + LinkifyRe::SRC_Z_P_CC + '))(' + slist + ')', 'ig')
+    @re[:schema_test]   = Regexp.new('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'i')
+    @re[:schema_search] = Regexp.new('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'ig')
 
     @re[:pretest]       = Regexp.new(
                               '(' + @re[:schema_test].source + ')|' +
@@ -203,12 +217,12 @@ class Linkify
 
     resetScanCache
   end
-    
+
   # Match result. Single element of array, returned by [[LinkifyIt#match]]
   #------------------------------------------------------------------------------
   class Match
     attr_accessor   :schema, :index, :lastIndex, :raw, :text, :url
-    
+
     def initialize(obj, shift)
       start = obj.__index__
       endt  = obj.__last_index__
@@ -288,11 +302,14 @@ class Linkify
   #
   #------------------------------------------------------------------------------
   def initialize(schemas = {}, options = {})
+    schemas = {} unless schemas
+
+    # not needed
     # if (!(this instanceof LinkifyIt)) {
     #   return new LinkifyIt(schemas, options);
     # }
 
-    #--- not needed, if you want to pass options, then must also pass schemas
+    # not needed, if you want to pass options, then must also pass schemas
     # if options.empty?
     #   if (isOptionsObj(schemas)) {
     #     options = schemas;
@@ -321,7 +338,6 @@ class Linkify
     compile
   end
 
-
   # chainable
   # LinkifyIt#add(schema, definition)
   # - schema (String): rule name (fixed pattern prefix)
@@ -356,7 +372,7 @@ class Linkify
     @__index__      = -1
 
     return false if (!text.length)
-    
+
     # try to scan for link with schema - that's the most simple rule
     if @re[:schema_test] =~ text
       re = @re[:schema_search]
@@ -449,7 +465,7 @@ class Linkify
   # LinkifyIt#match(text) -> Array|null
   #
   # Returns array of found link descriptions or `null` on fail. We strongly suggest
-  # to use [[LinkifyIt#test]] first, for best speed.
+  # recommend to use [[LinkifyIt#test]] first, for best speed.
   #
   # ##### Result match description
   #
@@ -527,7 +543,7 @@ class Linkify
   #------------------------------------------------------------------------------
   def normalize(match)
     return if @bypass_normalizer
-    
+
     # Do minimal possible changes by default. Need to collect feedback prior
     # to move forward https://github.com/markdown-it/linkify-it/issues/1
 
@@ -538,4 +554,11 @@ class Linkify
     end
   end
 
+  # LinkifyIt#onCompile()
+  #
+  # Override to modify basic RegExp-s.
+  #------------------------------------------------------------------------------
+  def onCompile
+  end
+
 end

data/lib/linkify-it-rb/re.rb

@@ -1,57 +1,40 @@
 module LinkifyRe
-    
+
     # Use direct extract instead of `regenerate` to reduce size
     SRC_ANY = UCMicro::Properties::Any::REGEX.source
     SRC_CC  = UCMicro::Categories::Cc::REGEX.source
     SRC_Z   = UCMicro::Categories::Z::REGEX.source
     SRC_P   = UCMicro::Categories::P::REGEX.source
 
-    # \p{\Z\P\Cc} (white spaces + control + punctuation)
+    # \p{\Z\P\Cc\Cf} (white spaces + control + format + punctuation)
     SRC_Z_P_CC = [ SRC_Z, SRC_P, SRC_CC ].join('|')
 
     # \p{\Z\Cc} (white spaces + control)
     SRC_Z_CC = [ SRC_Z, SRC_CC ].join('|')
 
+    # Experimental. List of chars, completely prohibited in links
+    # because can separate it from other part of text
+    TEXT_SEPARATORS = '[><\uff5c]'
+
     # All possible word characters (everything without punctuation, spaces & controls)
     # Defined via punctuation & spaces to save space
     # Should be something like \p{\L\N\S\M} (\w but without `_`)
-    SRC_PSEUDO_LETTER       = '(?:(?!' + SRC_Z_P_CC + ')' + SRC_ANY + ')'
+    SRC_PSEUDO_LETTER       = '(?:(?!' + TEXT_SEPARATORS + '|' + SRC_Z_P_CC + ')' + SRC_ANY + ')'
     # The same as above but without [0-9]
-    SRC_PSEUDO_LETTER_NON_D = '(?:(?![0-9]|' + SRC_Z_P_CC + ')' + SRC_ANY + ')'
+    # SRC_PSEUDO_LETTER_NON_D = '(?:(?![0-9]|' + SRC_Z_P_CC + ')' + SRC_ANY + ')'
 
     #------------------------------------------------------------------------------
 
     SRC_IP4   = '(?:(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)'
-    SRC_AUTH  = '(?:(?:(?!' + SRC_Z_CC + ').)+@)?'
+
+    # Prohibit any of "@/[]()" in user/pass to avoid wrong domain fetch.
+    SRC_AUTH  = '(?:(?:(?!' + SRC_Z_CC + '|[@/\\[\\]()]).)+@)?'
 
     SRC_PORT  = '(?::(?:6(?:[0-4]\\d{3}|5(?:[0-4]\\d{2}|5(?:[0-2]\\d|3[0-5])))|[1-5]?\\d{1,4}))?'
 
-    SRC_HOST_TERMINATOR = '(?=$|' + SRC_Z_P_CC + ')(?!-|_|:\\d|\\.-|\\.(?!$|' + SRC_Z_P_CC + '))'
+    SRC_HOST_TERMINATOR = '(?=$|' + TEXT_SEPARATORS + '|' + SRC_Z_P_CC + ')(?!-|_|:\\d|\\.-|\\.(?!$|' + SRC_Z_P_CC + '))'
 
-    SRC_PATH = 
-      '(?:' +
-        '[/?#]' +
-          '(?:' +
-            '(?!' + SRC_Z_CC + '|[()\\[\\]{}.,"\'?!\\-]).|' +
-            '\\[(?:(?!' + SRC_Z_CC + '|\\]).)*\\]|' +
-            '\\((?:(?!' + SRC_Z_CC + '|[)]).)*\\)|' +
-            '\\{(?:(?!' + SRC_Z_CC + '|[}]).)*\\}|' +
-            '\\"(?:(?!' + SRC_Z_CC + '|["]).)+\\"|' +
-            "\\'(?:(?!" + SRC_Z_CC + "|[']).)+\\'|" +
-            "\\'(?=" + SRC_PSEUDO_LETTER + ').|' +  # allow `I'm_king` if no pair found
-            '\\.{2,3}[a-zA-Z0-9%/]|' + # github has ... in commit range links. Restrict to
-                                       # - english
-                                       # - percent-encoded
-                                       # - parts of file path
-                                       # until more examples found.
-            '\\.(?!' + SRC_Z_CC + '|[.]).|' +
-            '\\-(?!--(?:[^-]|$))(?:-*)|' +  # `---` => long dash, terminate
-            '\\,(?!' + SRC_Z_CC + ').|' +      # allow `,,,` in paths
-            '\\!(?!' + SRC_Z_CC + '|[!]).|' +
-            '\\?(?!' + SRC_Z_CC + '|[?]).' +
-          ')+' +
-        '|\\/' +
-      ')?'
+    # moved SRC_PATH into re_src_path
 
     SRC_EMAIL_NAME  = '[\\-;:&=\\+\\$,\\"\\.a-zA-Z0-9_]+'
     SRC_XN          = 'xn--[a-z0-9\\-]{1,59}'
@@ -59,15 +42,15 @@ module LinkifyRe
     # More to read about domain names
     # http://serverfault.com/questions/638260/
 
-    SRC_DOMAIN_ROOT = 
-      # Can't have digits and dashes
+    SRC_DOMAIN_ROOT =
+      # Allow letters & digits (http://test1)
       '(?:' +
         SRC_XN +
         '|' +
-        SRC_PSEUDO_LETTER_NON_D + '{1,63}' +
+        SRC_PSEUDO_LETTER + '{1,63}' +
       ')'
 
-    SRC_DOMAIN = 
+    SRC_DOMAIN =
       '(?:' +
         SRC_XN +
         '|' +
@@ -79,14 +62,15 @@ module LinkifyRe
         '(?:' + SRC_PSEUDO_LETTER + '(?:-(?!-)|' + SRC_PSEUDO_LETTER + '){0,61}' + SRC_PSEUDO_LETTER + ')' +
       ')'
 
-    SRC_HOST = 
+    SRC_HOST =
       '(?:' +
-        SRC_IP4 +
-      '|' +
-        '(?:(?:(?:' + SRC_DOMAIN + ')\\.)*' + SRC_DOMAIN_ROOT + ')' +
+      # Don't need IP check, because digits are already allowed in normal domain names
+      # SRC_IP4 +
+      # '|' +
+        '(?:(?:(?:' + SRC_DOMAIN + ')\\.)*' + SRC_DOMAIN + ')' +
       ')'
 
-    TPL_HOST_FUZZY = 
+    TPL_HOST_FUZZY =
       '(?:' +
         SRC_IP4 +
       '|' +
@@ -96,27 +80,98 @@ module LinkifyRe
     TPL_HOST_NO_IP_FUZZY =
       '(?:(?:(?:' + SRC_DOMAIN + ')\\.)+(?:%TLDS%))'
 
-    SRC_HOST_STRICT            = SRC_HOST + SRC_HOST_TERMINATOR
-    TPL_HOST_FUZZY_STRICT      = TPL_HOST_FUZZY + SRC_HOST_TERMINATOR
-    SRC_HOST_PORT_STRICT       = SRC_HOST + SRC_PORT + SRC_HOST_TERMINATOR
-    TPL_HOST_PORT_FUZZY_STRICT = TPL_HOST_FUZZY + SRC_PORT + SRC_HOST_TERMINATOR
-    TPL_HOST_PORT_NO_IP_FUZZY_STRICT = TPL_HOST_NO_IP_FUZZY + SRC_PORT + SRC_HOST_TERMINATOR
-      
+    SRC_HOST_STRICT                   = SRC_HOST + SRC_HOST_TERMINATOR
+    TPL_HOST_FUZZY_STRICT             = TPL_HOST_FUZZY + SRC_HOST_TERMINATOR
+    SRC_HOST_PORT_STRICT              = SRC_HOST + SRC_PORT + SRC_HOST_TERMINATOR
+    TPL_HOST_PORT_FUZZY_STRICT        = TPL_HOST_FUZZY + SRC_PORT + SRC_HOST_TERMINATOR
+    TPL_HOST_PORT_NO_IP_FUZZY_STRICT  = TPL_HOST_NO_IP_FUZZY + SRC_PORT + SRC_HOST_TERMINATOR
+
     #------------------------------------------------------------------------------
     # Main rules
 
     # Rude test fuzzy links by host, for quick deny
-    TPL_HOST_FUZZY_TEST = 'localhost|\\.\\d{1,3}\\.|(?:\\.(?:%TLDS%)(?:' + SRC_Z_P_CC + '|$))'
-    TPL_EMAIL_FUZZY     = '(^|>|' + SRC_Z_CC + ')(' + SRC_EMAIL_NAME + '@' + TPL_HOST_FUZZY_STRICT + ')'
-    TPL_LINK_FUZZY =
-        # Fuzzy link can't be prepended with .:/\- and non punctuation.
-        # but can start with > (markdown blockquote)
-        '(^|(?![.:/\\-_@])(?:[$+<=>^`|]|' + SRC_Z_P_CC + '))' +
-        '((?![$+<=>^`|])' + TPL_HOST_PORT_FUZZY_STRICT + SRC_PATH + ')'
-
-    TPL_LINK_NO_IP_FUZZY =
-        # Fuzzy link can't be prepended with .:/\- and non punctuation.
-        # but can start with > (markdown blockquote)
-        '(^|(?![.:/\\-_@])(?:[$+<=>^`|]|' + SRC_Z_P_CC + '))' +
-        '((?![$+<=>^`|])' + TPL_HOST_PORT_NO_IP_FUZZY_STRICT + SRC_PATH + ')'
+    TPL_HOST_FUZZY_TEST = 'localhost|www\\.|\\.\\d{1,3}\\.|(?:\\.(?:%TLDS%)(?:' + SRC_Z_P_CC + '|>|$))'
+    TPL_EMAIL_FUZZY     = '(^|' + TEXT_SEPARATORS + '|\\(|' +SRC_Z_CC + ')(' + SRC_EMAIL_NAME + '@' + TPL_HOST_FUZZY_STRICT + ')'
+
+    # moved TPL_LINK_FUZZY and TPL_LINK_NO_IP_FUZZY into build_re
+
+  #------------------------------------------------------------------------------
+  def build_re(opts)
+    re = {
+      src_Any:              SRC_ANY,
+      src_Cc:               SRC_CC,
+      src_Z:                SRC_Z,
+      src_P:                SRC_P,
+      src_XPCc:             SRC_Z_P_CC,
+      src_ZCc:              SRC_Z_CC,
+      src_pseudo_letter:    SRC_PSEUDO_LETTER,
+      src_ip4:              SRC_IP4,
+      src_auth:             SRC_AUTH,
+      src_port:             SRC_PORT,
+      src_host_terminator:  SRC_HOST_TERMINATOR,
+      src_path:             re_src_path(opts),
+      src_email_name:       SRC_EMAIL_NAME,
+      src_xn:               SRC_XN,
+      src_domain_root:      SRC_DOMAIN_ROOT,
+      src_domain:           SRC_DOMAIN,
+      src_host:             SRC_HOST,
+
+      tpl_host_fuzzy:                   TPL_HOST_FUZZY,
+      tpl_host_no_ip_fuzzy:             TPL_HOST_NO_IP_FUZZY,
+      src_host_strict:                  SRC_HOST_STRICT,
+      tpl_host_fuzzy_strict:            TPL_HOST_FUZZY_STRICT,
+      src_host_port_strict:             SRC_HOST_PORT_STRICT,
+      tpl_host_port_fuzzy_strict:       TPL_HOST_PORT_FUZZY_STRICT,
+      tpl_host_port_no_ip_fuzzy_strict: TPL_HOST_PORT_NO_IP_FUZZY_STRICT,
+
+      tpl_host_fuzzy_test:  TPL_HOST_FUZZY_TEST,
+      tpl_email_fuzzy:      TPL_EMAIL_FUZZY
+    }
+
+    # Fuzzy link can't be prepended with .:/\- and non punctuation.
+    # but can start with > (markdown blockquote)
+    re[:tpl_link_fuzzy] =
+        '(^|(?![.:/\\-_@])(?:[$+<=>^`|\uff5c]|' + SRC_Z_P_CC + '))' +
+        '((?![$+<=>^`|\uff5c])' + TPL_HOST_PORT_FUZZY_STRICT + re[:src_path] + ')'
+
+    # Fuzzy link can't be prepended with .:/\- and non punctuation.
+    # but can start with > (markdown blockquote)
+    re[:tpl_link_no_ip_fuzzy] =
+      '(^|(?![.:/\\-_@])(?:[$+<=>^`|\uff5c]|' + SRC_Z_P_CC + '))' +
+      '((?![$+<=>^`|\uff5c])' + TPL_HOST_PORT_NO_IP_FUZZY_STRICT + re[:src_path] + ')'
+
+    return re
+  end
+
+  #------------------------------------------------------------------------------
+  def re_src_path(opts = nil)
+    '(?:' +
+      '[/?#]' +
+        '(?:' +
+          '(?!' + SRC_Z_CC + '|' + TEXT_SEPARATORS + '|[()\\[\\]{}.,"\'?!\\-]).|' +
+          '\\[(?:(?!' + SRC_Z_CC + '|\\]).)*\\]|' +
+          '\\((?:(?!' + SRC_Z_CC + '|[)]).)*\\)|' +
+          '\\{(?:(?!' + SRC_Z_CC + '|[}]).)*\\}|' +
+          '\\"(?:(?!' + SRC_Z_CC + '|["]).)+\\"|' +
+          "\\'(?:(?!" + SRC_Z_CC + "|[']).)+\\'|" +
+          "\\'(?=" + SRC_PSEUDO_LETTER + '|[-]).|' +  # allow `I'm_king` if no pair found
+          '\\.{2,3}[a-zA-Z0-9%/]|' + # github has ... in commit range links. Restrict to
+                                     # - english
+                                     # - percent-encoded
+                                     # - parts of file path
+                                     # until more examples found.
+          '\\.(?!' + SRC_Z_CC + '|[.]).|' +
+          (opts && opts[:'---'] ?
+            '\\-(?!--(?:[^-]|$))(?:-*)|'  # `---` => long dash, terminate
+          :
+            '\\-+|'
+          ) +
+          '\\,(?!' + SRC_Z_CC + ').|' +      # allow `,,,` in paths
+          '\\!(?!' + SRC_Z_CC + '|[!]).|' +
+          '\\?(?!' + SRC_Z_CC + '|[?]).' +
+        ')+' +
+      '|\\/' +
+    ')?'
+end
+
 end

data/lib/linkify-it-rb/version.rb

@@ -1,5 +1,5 @@
 module LinkifyIt
 
-  VERSION = '1.2.0'
+  VERSION = '2.0.3'
 
 end

data/spec/linkify-it-rb/test_spec.rb

@@ -255,4 +255,23 @@ describe 'API' do
     expect(l.match('1.1.1.1.')[0].text).to eq '1.1.1.1'
   end
 
+  #------------------------------------------------------------------------------
+  it 'should not hang in fuzzy mode with sequences of astrals' do
+    l = Linkify.new
+
+    l.set({ fuzzyLink: true })
+
+    expect(l.match('😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡 .com')).to eq []
+  end
+
+  #------------------------------------------------------------------------------
+  it 'should accept `---` if enabled' do
+    l = Linkify.new
+
+    expect(l.match('http://e.com/foo---bar')[0].text).to eq 'http://e.com/foo---bar'
+
+    l = Linkify.new(nil, { '---': true })
+
+    expect(l.match('http://e.com/foo---bar')[0].text).to eq 'http://e.com/foo'
+  end
 end

data/spec/spec_helper.rb

@@ -1,2 +1,2 @@
-require 'byebug'
+require 'pry-byebug'
 require 'linkify-it-rb'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: linkify-it-rb
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 2.0.3
 platform: ruby
 authors:
 - Brett Walker
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-11-14 00:00:00.000000000 Z
+date: 2018-04-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: uc.micro-rb
@@ -25,6 +25,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: bacon-expect
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
 description: Ruby version of linkify-it for motion-markdown-it, for Ruby and RubyMotion
 email: github@digitalmoksha.com
 executables: []
@@ -58,10 +72,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5
+rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
 summary: linkify-it for motion-markdown-it in Ruby
 test_files:
-- spec/linkify-it-rb/test_spec.rb
 - spec/spec_helper.rb
+- spec/linkify-it-rb/test_spec.rb