twitter-text 1.9.0 → 1.9.1

data/lib/twitter-text/extractor.rb

@@ -201,15 +201,17 @@ module Twitter
         if !protocol
           next if !options[:extract_url_without_protocol] || before =~ Twitter::Regex[:invalid_url_without_protocol_preceding_chars]
           last_url = nil
-          last_url_invalid_match = nil
           domain.scan(Twitter::Regex[:valid_ascii_domain]) do |ascii_domain|
             last_url = {
               :url => ascii_domain,
               :indices => [start_position + $~.char_begin(0),
                            start_position + $~.char_end(0)]
             }
-            last_url_invalid_match = ascii_domain =~ Twitter::Regex[:invalid_short_domain]
-            urls << last_url unless last_url_invalid_match
+            if path ||
+                ascii_domain =~ Twitter::Regex[:valid_special_short_domain] ||
+                ascii_domain !~ Twitter::Regex[:invalid_short_domain]
+              urls << last_url
+            end
           end
 
           # no ASCII-only domain found. Skip the entire URL
@@ -218,7 +220,6 @@ module Twitter
           # last_url only contains domain. Need to add path and query if they exist.
           if path
             # last_url was not added. Add it to urls here.
-            urls << last_url if last_url_invalid_match
             last_url[:url] = url.sub(domain, last_url[:url])
             last_url[:indices][1] = end_position
           end

data/lib/twitter-text/regex.rb

@@ -189,39 +189,53 @@ module Twitter
 
     REGEXEN[:valid_gTLD] = %r{
       (?:
-        (?:academy|actor|aero|agency|arpa|asia|bar|bargains|berlin|best|bid|bike|biz|blue|boutique|build|builders|
-        buzz|cab|camera|camp|cards|careers|cat|catering|center|ceo|cheap|christmas|cleaning|clothing|club|codes|
-        coffee|com|community|company|computer|construction|contractors|cool|coop|cruises|dance|dating|democrat|
-        diamonds|directory|domains|edu|education|email|enterprises|equipment|estate|events|expert|exposed|farm|fish|
-        flights|florist|foundation|futbol|gallery|gift|glass|gov|graphics|guitars|guru|holdings|holiday|house|
-        immobilien|industries|info|institute|int|international|jobs|kaufen|kim|kitchen|kiwi|koeln|kred|land|lighting|
-        limo|link|luxury|management|mango|marketing|menu|mil|mobi|moda|monash|museum|nagoya|name|net|neustar|ninja|
-        okinawa|onl|org|partners|parts|photo|photography|photos|pics|pink|plumbing|post|pro|productions|properties|
-        pub|qpon|recipes|red|rentals|repair|report|reviews|rich|ruhr|sexy|shiksha|shoes|singles|social|solar|
-        solutions|supplies|supply|support|systems|tattoo|technology|tel|tienda|tips|today|tokyo|tools|training|
-        travel|uno|vacations|ventures|viajes|villas|vision|vote|voting|voto|voyage|wang|watch|wed|wien|wiki|works|
-        xxx|xyz|zone|дети|онлайн|орг|сайт|بازار|شبكة|みんな|中信|中文网|公司|公益|在线|我爱你|政务|游戏|移动|网络|集团|삼성)
-        (?=[^0-9a-z@]|$)
+        (?:
+        academy|accountants|actor|aero|agency|airforce|archi|arpa|asia|associates|axa|bar|bargains|bayern|berlin|best|
+        bid|bike|biz|black|blackfriday|blue|boutique|build|builders|buzz|cab|camera|camp|capital|cards|care|career|
+        careers|cash|cat|catering|center|ceo|cheap|christmas|citic|claims|cleaning|clinic|clothing|club|codes|coffee|
+        college|cologne|com|community|company|computer|construction|contractors|cooking|cool|coop|country|credit|
+        creditcard|cruises|dance|dating|democrat|dental|desi|diamonds|digital|directory|discount|domains|edu|education|
+        email|engineering|enterprises|equipment|estate|eus|events|exchange|expert|exposed|fail|farm|feedback|finance|
+        financial|fish|fishing|fitness|flights|florist|foo|foundation|frogans|fund|furniture|futbol|gal|gallery|gift|
+        glass|globo|gmo|gop|gov|graphics|gratis|gripe|guitars|guru|haus|holdings|holiday|horse|house|immobilien|
+        industries|info|institute|insure|int|international|investments|jetzt|jobs|kaufen|kim|kitchen|kiwi|koeln|kred|
+        land|lease|lighting|limited|limo|link|london|luxury|management|mango|marketing|media|meet|menu|miami|mil|mobi|
+        moda|moe|monash|moscow|museum|nagoya|name|net|neustar|ninja|nyc|okinawa|onl|org|paris|partners|parts|photo|
+        photography|photos|pics|pictures|pink|plumbing|post|pro|productions|properties|pub|qpon|quebec|recipes|red|
+        reisen|ren|rentals|repair|report|rest|reviews|rich|rocks|rodeo|ruhr|ryukyu|saarland|schule|services|sexy|
+        shiksha|shoes|singles|social|sohu|solar|solutions|soy|supplies|supply|support|surgery|systems|tattoo|tax|
+        technology|tel|tienda|tips|today|tokyo|tools|town|toys|trade|training|travel|university|uno|vacations|vegas|
+        ventures|viajes|villas|vision|vodka|vote|voting|voto|voyage|wang|watch|webcam|wed|wien|wiki|works|wtc|wtf|xxx|
+        xyz|yokohama|zone|дети|москва|онлайн|орг|сайт|بازار|شبكة|संगठन|みんな|世界|中信|中文网|公司|公益|商城|在线|我爱你|政务|机构|游戏|移动|组织机构|
+        网址|网络|集团|삼성
+        )(?=[^0-9a-z@]|$)
       )
     }ix
 
     REGEXEN[:valid_ccTLD] = %r{
       (?:
-        (?:ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bl|bm|bn|bo|bq|br|bs|
-        bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|
-        et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|
-        im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|
-        me|mf|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|
-        pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|
-        sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|um|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|
-        ye|yt|za|zm|zw|мон|рф|срб|укр|қаз|الاردن|الجزائر|السعودية|المغرب|امارات|ایران|بھارت|تونس|سودان|سورية|عمان|فلسطين|قطر|مصر|مليسيا|پاکستان|
-        भारत|বাংলা|ভারত|ਭਾਰਤ|ભારત|இந்தியா|இலங்கை|சிங்கப்பூர்|భారత్|ලංකා|ไทย|გე|中国|中國|台湾|台灣|新加坡|
-        香港|한국)
-        (?=[^0-9a-z@]|$)
+        (?:
+        ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bl|bm|bn|bo|bq|br|bs|bt|bv|bw|
+        by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|
+        fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|
+        is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mf|mg|mh|mk|ml|
+        mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|
+        ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|
+        tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|um|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw|мкд|мон|рф|
+        срб|укр|қаз|الاردن|الجزائر|السعودية|المغرب|امارات|ایران|بھارت|تونس|سودان|سورية|عمان|فلسطين|قطر|مصر|مليسيا|
+        پاکستان|भारत|বাংলা|ভারত|ਭਾਰਤ|ભારત|இந்தியா|இலங்கை|சிங்கப்பூர்|భారత్|ලංකා|ไทย|გე|中国|中國|台湾|台灣|新加坡|香港|한국
+        )(?=[^0-9a-z@]|$)
       )
     }ix
     REGEXEN[:valid_punycode] = /(?:xn--[0-9a-z]+)/i
 
+    REGEXEN[:valid_special_cctld] = %r{
+      (?:
+        (?:co|tv)
+        (?=[^0-9a-z@]|$)
+      )
+    }ix
+
     REGEXEN[:valid_domain] = /(?:
       #{REGEXEN[:valid_subdomain]}*#{REGEXEN[:valid_domain_name]}
       (?:#{REGEXEN[:valid_gTLD]}|#{REGEXEN[:valid_ccTLD]}|#{REGEXEN[:valid_punycode]})
@@ -238,6 +252,7 @@ module Twitter
 
     # This is used in Extractor to filter out unwanted URLs.
     REGEXEN[:invalid_short_domain] = /\A#{REGEXEN[:valid_domain_name]}#{REGEXEN[:valid_ccTLD]}\Z/io
+    REGEXEN[:valid_special_short_domain] = /\A#{REGEXEN[:valid_domain_name]}#{REGEXEN[:valid_special_cctld]}\Z/io
 
     REGEXEN[:valid_port_number] = /[0-9]+/
 

data/twitter-text.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name = "twitter-text"
-  s.version = "1.9.0"
+  s.version = "1.9.1"
   s.authors = ["Matt Sanford", "Patrick Ewing", "Ben Cherry", "Britt Selvitelle",
                "Raffi Krikorian", "J.P. Cummins", "Yoshimasa Niwa", "Keita Fujii", "James Koval"]
   s.email = ["matt@twitter.com", "patrick.henry.ewing@gmail.com", "bcherry@gmail.com", "bs@brittspace.com",
@@ -19,8 +19,8 @@ Gem::Specification.new do |s|
   s.add_development_dependency "nokogiri", "~> 1.5.10"
   s.add_development_dependency "rake"
   s.add_development_dependency "rdoc"
-  s.add_development_dependency "rspec"
-  s.add_development_dependency "simplecov"
+  s.add_development_dependency "rspec", "~> 2.14.0"
+  s.add_development_dependency "simplecov", "~> 0.8.0"
   s.add_runtime_dependency     "unf", "~> 0.1.0"
 
   s.files         = `git ls-files`.split("\n")

metadata

@@ -1,9 +1,15 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: twitter-text
-version: !ruby/object:Gem::Version
-  version: 1.9.0
+version: !ruby/object:Gem::Version 
+  hash: 49
+  prerelease: 
+  segments: 
+  - 1
+  - 9
+  - 1
+  version: 1.9.1
 platform: ruby
-authors:
+authors: 
 - Matt Sanford
 - Patrick Ewing
 - Ben Cherry
@@ -16,108 +22,118 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-18 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
+
+date: 2014-07-18 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
   name: multi_json
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.3'
-  type: :development
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.3'
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.5.10
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 9
+        segments: 
+        - 1
+        - 3
+        version: "1.3"
   type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 1
+        - 5
+        - 10
         version: 1.5.10
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
   type: :development
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: rake
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rdoc
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
     - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
   type: :development
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: rdoc
   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:
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
     - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
   type: :development
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  name: rspec
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 55
+        segments: 
+        - 2
+        - 14
+        - 0
+        version: 2.14.0
   type: :development
+  version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  name: simplecov
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 63
+        segments: 
+        - 0
+        - 8
+        - 0
+        version: 0.8.0
+  type: :development
+  version_requirements: *id006
+- !ruby/object:Gem::Dependency 
   name: unf
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 0.1.0
-  type: :runtime
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 27
+        segments: 
+        - 0
+        - 1
+        - 0
         version: 0.1.0
+  type: :runtime
+  version_requirements: *id007
 description: A gem that provides text handling for Twitter
-email:
+email: 
 - matt@twitter.com
 - patrick.henry.ewing@gmail.com
 - bcherry@gmail.com
@@ -128,14 +144,17 @@ email:
 - keita@twitter.com
 - jkoval@twitter.com
 executables: []
+
 extensions: []
+
 extra_rdoc_files: []
-files:
-- ".gemtest"
-- ".gitignore"
-- ".gitmodules"
-- ".rspec"
-- ".travis.yml"
+
+files: 
+- .gemtest
+- .gitignore
+- .gitmodules
+- .rspec
+- .travis.yml
 - Gemfile
 - LICENSE
 - README.rdoc
@@ -165,30 +184,39 @@ files:
 - test/conformance_test.rb
 - twitter-text.gemspec
 homepage: http://twitter.com
-licenses:
+licenses: 
 - Apache 2.0
-metadata: {}
 post_install_message: 
 rdoc_options: []
-require_paths:
+
+require_paths: 
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
-  requirements:
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
   - - ">="
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
-  requirements:
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
   - - ">="
-    - !ruby/object:Gem::Version
-      version: '0'
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
 requirements: []
+
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 1.8.15
 signing_key: 
-specification_version: 4
+specification_version: 3
 summary: Twitter text handling library
-test_files:
+test_files: 
 - spec/autolinking_spec.rb
 - spec/extractor_spec.rb
 - spec/hithighlighter_spec.rb

checksums.yaml

@@ -1,7 +0,0 @@
----
-SHA1:
-  metadata.gz: d032fd2fa1300bbc000a2e7a8f718fc5a7b33e12
-  data.tar.gz: ac18985474a651ee6ca291e9cdb5fc7116f2d346
-SHA512:
-  metadata.gz: 7f2c3e340d6768091cc0cfca016f0fbb292deae6f02b6aa4045ce353aadd0e538195b5ed71abb285a82eae40fbdf7c9751271430ea1874f8087b1f1e7b5ed3a5
-  data.tar.gz: d5ab53a8920d232b2b1c6cdf03e6d5a723d12923d2da461329181af0ceb166cac8c034a3f4f715061cf6d007b00aadb745a97817d47984b6f770a86ddb6a8ba6