linkify-it-rb 2.0.3 → 4.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 176768c4d108c26b13260d1e62c1cb30cd0491f5
-  data.tar.gz: a47bd97acdf25582ce67d65551a1d94678d56aa3
+SHA256:
+  metadata.gz: 68c5de781544ec81b757b1099b8c24643449e121546d03cdda5da57d6b033afb
+  data.tar.gz: 9534d8d1a44ec68d531dea91df209b391d46aee363b04f2d0c30969debd77bf7
 SHA512:
-  metadata.gz: 1cbcc4a1e42a24df990484e927b1049a81ff87a8bd0a53f43d32f9d0687ec2bcfb2ec81778e1fbd4a33e11c9e41796e4787d84b8f3f55461ed853dfe4b40c05e
-  data.tar.gz: 5b25b74826e53b4257fdc2b4ea1b0422659d44c9ec69e877ee37b396d9597654db71811d2593193552785cdb8a71258485d4a57a6447b2036cbf324386d0380f
+  metadata.gz: 96664d9ffb34ac85e7038394dd9e1504625ae4ce87e5498ec62c0b698cb9ddbcae780a3f966a0c77abeca1c533ef5ce1984195d1d1e14b54bfcb563b7972255d
+  data.tar.gz: 4194118a1da63b10a827aca05f57254debee07759a06b25a5b0b71d1928be0669c92416afb76950c85fa85455ef944b0b2008d789254ad04ac254052a8805b34

data/README.md

@@ -1,11 +1,11 @@
 # linkify-it-rb
 
 [![Gem Version](https://badge.fury.io/rb/linkify-it-rb.svg)](http://badge.fury.io/rb/linkify-it-rb)
-[![Build Status](https://travis-ci.org/digitalmoksha/linkify-it-rb.svg?branch=master)](https://travis-ci.org/digitalmoksha/linkify-it-rb)
+[![Build Status](https://github.com/digitalmoksha/linkify-it-rb/actions/workflows/ci.yml/badge.svg)](https://github.com/digitalmoksha/linkify-it-rb/actions/workflows/ci.yml)
 
 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_
+_Currently synced with linkify-it 4.0.1_
 
 ---
 
@@ -53,8 +53,8 @@ linkify = Linkify.new
 
 # 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.add('git:', 'http:')     # Add `git:` protocol as "alias"
+linkify.add('ftp:', null)        # Disable `ftp:` protocol
 linkify.set({fuzzyIP: true})     # Enable IPs in fuzzy links (without schema)
 
 linkify.test('Site github.com!'))
@@ -106,8 +106,11 @@ By default understands:
 - __value__ - rule to check tail after link prefix
   - _String_ - just alias to existing rule
   - _Hash_
-    - _validate_ - validator block (should return matched length on success),
-      or `RegExp`.
+    - _validate_ - either a `RegExp (start with `^`, and don't include the
+      link prefix itself), or a validator block which, given arguments,
+      _text_, _pos_, and _self_, returns the length of a match in _text_
+      starting at index _pos_.  _pos_ is the index right after the link prefix.
+      _self_ can be used to access the linkify object to cache data.
     - _normalize_ - optional block to normalize text & url of matched result
       (for example, for twitter mentions).
 
@@ -152,6 +155,11 @@ Each match has:
 - __text__ - normalized text
 - __url__ - link, generated from matched text
 
+### .matchAtStart(text)
+
+Checks if a match exists at the start of the string. Returns `Match`
+(see docs for `match(text)`) or nil if no URL is at the start.
+Doesn't work with fuzzy links.
 
 ### .tlds(list[, keepOld])
 
@@ -162,12 +170,15 @@ to avoid false positives. By default this algorithm uses:
 - 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 that's not enougth, you can reload defaults with more detailed zones list.
+If that's not enough, you can reload defaults with more detailed zones list.
 
-### .add(schema, definition)
+### .add(key, value)
 
-Add new rule with `schema` prefix. For definition details see constructor
-description. To disable existing rule use `.add(name, nil)`
+Add a new schema to the schemas object.  As described in the constructor
+definition, `key` is a link prefix (`skype:`, for example), and `value`
+is a String to alias to another schema, or an Object with `validate` and
+optionally `normalize` definitions.  To disable an existing rule, use
+`.add(key, null)`.
 
 ### .set(options)
 

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

@@ -204,12 +204,14 @@ 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('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'i')
-    @re[:schema_search] = Regexp.new('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'ig')
+    @re[:schema_test]     = Regexp.new('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'i')
+    @re[:schema_search]   = Regexp.new('(^|(?!_)(?:[><\uff5c]|' + @re[:src_XPCc] + '))(' + slist + ')', 'i')
+    @re[:schema_at_start] = Regexp.new('^' + @re[:schema_search].source, 'i')
 
-    @re[:pretest]       = Regexp.new(
-                              '(' + @re[:schema_test].source + ')|' +
-                              '(' + @re[:host_fuzzy_test].source + ')|' + '@', 'i')
+    @re[:pretest] = Regexp.new(
+      '(' + @re[:schema_test].source + ')|(' + @re[:host_fuzzy_test].source + ')|@',
+      'i'
+    )
 
     #
     # Cleanup
@@ -505,6 +507,30 @@ class Linkify
     return nil
   end
 
+  # LinkifyIt#matchAtStart(text) -> Match|null
+  #
+  # Returns fully-formed (not fuzzy) link if it starts at the beginning
+  # of the string, and null otherwise.
+  #------------------------------------------------------------------------------
+  def matchAtStart(text)
+    # Reset scan cache
+    @__text_cache__ = text
+    @__index__      = -1
+
+    return unless text.length
+
+    m = @re[:schema_at_start].match(text)
+    return nil unless m
+
+    len = testSchemaAt(text, m[2], m[0].length)
+    return nil unless len > 0
+
+    @__schema__     = m[2];
+    @__index__      = m.begin(0) + m[1].length
+    @__last_index__ = m.begin(0) + m[0].length + len
+
+    return Match.createMatch(self, 0)
+  end
 
   # chainable
   # LinkifyIt#tlds(list [, keepOld]) -> this
@@ -561,4 +587,4 @@ class Linkify
   def onCompile
   end
 
-end
+end

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

@@ -32,11 +32,13 @@ module LinkifyRe
 
     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 = '(?=$|' + TEXT_SEPARATORS + '|' + SRC_Z_P_CC + ')(?!-|_|:\\d|\\.-|\\.(?!$|' + SRC_Z_P_CC + '))'
+    # moved SRC_HOST_TERMINATOR into re_src_host_terminator
 
     # moved SRC_PATH into re_src_path
 
-    SRC_EMAIL_NAME  = '[\\-;:&=\\+\\$,\\"\\.a-zA-Z0-9_]+'
+    # Allow anything in markdown spec, forbid quote (") at the first position
+    # because emails enclosed in quotes are far more common
+    SRC_EMAIL_NAME  = '[\\-;:&=\\+\\$,\\.a-zA-Z0-9_][\\-;:&=\\+\\$,\\"\\.a-zA-Z0-9_]*'
     SRC_XN          = 'xn--[a-z0-9\\-]{1,59}'
 
     # More to read about domain names
@@ -56,10 +58,7 @@ module LinkifyRe
         '|' +
         '(?:' + SRC_PSEUDO_LETTER + ')' +
         '|' +
-        # don't allow `--` in domain names, because:
-        # - that can conflict with markdown — / –
-        # - nobody use those anyway
-        '(?:' + SRC_PSEUDO_LETTER + '(?:-(?!-)|' + SRC_PSEUDO_LETTER + '){0,61}' + SRC_PSEUDO_LETTER + ')' +
+        '(?:' + SRC_PSEUDO_LETTER + '(?:-|' + SRC_PSEUDO_LETTER + '){0,61}' + SRC_PSEUDO_LETTER + ')' +
       ')'
 
     SRC_HOST =
@@ -80,23 +79,16 @@ 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
-
     #------------------------------------------------------------------------------
     # Main rules
 
     # Rude test fuzzy links by host, for quick deny
     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)
+  def build_re(opts = {})
     re = {
       src_Any:              SRC_ANY,
       src_Cc:               SRC_CC,
@@ -108,7 +100,7 @@ module LinkifyRe
       src_ip4:              SRC_IP4,
       src_auth:             SRC_AUTH,
       src_port:             SRC_PORT,
-      src_host_terminator:  SRC_HOST_TERMINATOR,
+      src_host_terminator:  re_src_host_terminator(opts),
       src_path:             re_src_path(opts),
       src_email_name:       SRC_EMAIL_NAME,
       src_xn:               SRC_XN,
@@ -118,60 +110,72 @@ module LinkifyRe
 
       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
+      src_host_strict:                  SRC_HOST + re_src_host_terminator(opts),
+      tpl_host_fuzzy_strict:            TPL_HOST_FUZZY + re_src_host_terminator(opts),
+      src_host_port_strict:             SRC_HOST + SRC_PORT + re_src_host_terminator(opts),
+      tpl_host_port_fuzzy_strict:       TPL_HOST_FUZZY + SRC_PORT + re_src_host_terminator(opts),
+      tpl_host_port_no_ip_fuzzy_strict: TPL_HOST_NO_IP_FUZZY + SRC_PORT + re_src_host_terminator(opts),
+
+      tpl_host_fuzzy_test:  TPL_HOST_FUZZY_TEST
     }
 
+    re[:tpl_email_fuzzy] =
+      '(^|' + TEXT_SEPARATORS + '|"|\\(|' + SRC_Z_CC + ')' +
+      '(' + SRC_EMAIL_NAME + '@' + re[:tpl_host_fuzzy_strict] + ')'
+
     # 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] + ')'
+        '((?![$+<=>^`|\uff5c])' + re[: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] + ')'
+      '((?![$+<=>^`|\uff5c])' + re[:tpl_host_port_no_ip_fuzzy_strict] + re[:src_path] + ')'
 
     return re
   end
 
   #------------------------------------------------------------------------------
-  def re_src_path(opts = nil)
+  def re_src_path(opts = {})
     '(?:' +
       '[/?#]' +
         '(?:' +
-          '(?!' + SRC_Z_CC + '|' + TEXT_SEPARATORS + '|[()\\[\\]{}.,"\'?!\\-]).|' +
+          '(?!' + 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
+          "\\'(?=" + SRC_PSEUDO_LETTER + '|[-])|' +  # allow `I'm_king` if no pair found
+          '\\.{2,}[a-zA-Z0-9%/&]|' + # google has many dots in "google search" links (#66, #81).
+                                     # github has ... in commit range links,
+                                     # Restrict to
                                      # - english
                                      # - percent-encoded
                                      # - parts of file path
+                                     # - params separator
                                      # until more examples found.
-          '\\.(?!' + SRC_Z_CC + '|[.]).|' +
+          '\\.(?!' + SRC_Z_CC + '|[.]|$)|' +
           (opts && opts[:'---'] ?
             '\\-(?!--(?:[^-]|$))(?:-*)|'  # `---` => long dash, terminate
           :
             '\\-+|'
           ) +
-          '\\,(?!' + SRC_Z_CC + ').|' +      # allow `,,,` in paths
-          '\\!(?!' + SRC_Z_CC + '|[!]).|' +
-          '\\?(?!' + SRC_Z_CC + '|[?]).' +
+          '\\,(?!' + SRC_Z_CC + '|$)|' +      # allow `,,,` in paths
+          '\\;(?!' + SRC_Z_CC + '|$)|' +      # allow `;` if not followed by space-like char
+          '\\!+(?!' + SRC_Z_CC + '|[!]|$)|' + # allow `!!!` in paths, but not at the end
+          '\\?(?!' + SRC_Z_CC + '|[?]|$)' +
         ')+' +
       '|\\/' +
     ')?'
-end
+  end
 
-end
+  #------------------------------------------------------------------------------
+  def re_src_host_terminator(opts = {})
+    '(?=$|' + TEXT_SEPARATORS + '|' + SRC_Z_P_CC + ')' +
+    '(?!' + (opts['---'] ? '-(?!--)|' : '-|') + '_|:\\d|\\.-|\\.(?!$|' + SRC_Z_P_CC + '))'
+  end
+end

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

@@ -1,5 +1,3 @@
 module LinkifyIt
-
-  VERSION = '2.0.3'
-
+  VERSION = '4.0.1'
 end

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

@@ -273,5 +273,39 @@ describe 'API' do
     l = Linkify.new(nil, { '---': true })
 
     expect(l.match('http://e.com/foo---bar')[0].text).to eq 'http://e.com/foo'
+    expect(l.match('text@example.com---foo')).to be_empty
+  end
+
+  #------------------------------------------------------------------------------
+  it 'should find a match at the start' do
+    l = Linkify.new
+
+    l.set({ fuzzyLink: true })
+
+    expect(l.matchAtStart('http://google.com 123').text).to eq 'http://google.com'
+    expect(l.matchAtStart('google.com 123')).to be_nil
+    expect(l.matchAtStart('  http://google.com 123')).to be_nil
+  end
+
+  #------------------------------------------------------------------------------
+  it 'matchAtStart should not interfere with normal match' do
+    l = Linkify.new
+
+    str = 'http://google.com http://google.com'
+    expect(l.matchAtStart(str)).not_to be_nil
+    expect(l.match(str).length).to eq 2
+
+    str = 'aaa http://google.com http://google.com'
+    expect(l.matchAtStart(str)).to be_nil
+    expect(l.match(str).length).to eq 2
+  end
+
+  #------------------------------------------------------------------------------
+  it 'should not match incomplete links' do
+    # regression test for https://github.com/markdown-it/markdown-it/issues/868
+    l = Linkify.new
+
+    expect(l.matchAtStart('http://')).to be_nil
+    expect(l.matchAtStart('https://')).to be_nil
   end
 end

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: linkify-it-rb
 version: !ruby/object:Gem::Version
-  version: 2.0.3
+  version: 4.0.1
 platform: ruby
 authors:
 - Brett Walker
 - Vitaly Puzrin
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-04-02 00:00:00.000000000 Z
+date: 2023-01-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: uc.micro-rb
@@ -26,19 +26,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.0'
 - !ruby/object:Gem::Dependency
-  name: bacon-expect
+  name: motion-expect
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
 description: Ruby version of linkify-it for motion-markdown-it, for Ruby and RubyMotion
 email: github@digitalmoksha.com
 executables: []
@@ -56,7 +56,7 @@ homepage: https://github.com/digitalmoksha/linkify-it-rb
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -71,9 +71,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.8
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: linkify-it for motion-markdown-it in Ruby
 test_files: