#25, #26: fix GFM style autolinks parsing

One problem was caused by too aggressive normal text lexing, which
won the autolink rule. The other one was just poor link regex,
it is improved to match the added examples.

src/org/intellij/markdown/flavours/gfm/lexer/gfm.flex

@@ -188,7 +188,9 @@ TAG_END = "</" {TAG_NAME} {WHITE_SPACE}* ">"
 SCHEME = [a-zA-Z]+
 AUTOLINK = "<" {SCHEME} ":" [^ \t\f\n<>]+ ">"
 EMAIL_AUTOLINK = "<" [a-zA-Z0-9.!#$%&'*+/=?\^_`{|}~-]+ "@"[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])? (\.[a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)* ">"
-GFM_AUTOLINK = (("http" "s"? | "ftp")"://" | "www.") ({ALPHANUM}([a-zA-Z0-9-]*{ALPHANUM})? ".")+ [a-zA-Z]{2,6} ("/"[a-zA-Z0-9.,+%_&!?#=-]+)* "/"?
+
+HOST_PART={ALPHANUM}([a-zA-Z0-9_-]*{ALPHANUM})?
+GFM_AUTOLINK = (("http" "s"? | "ftp" | "file")"://" | "www.") {HOST_PART} ("." {HOST_PART})* (":" [0-9]+)? ("/"[a-zA-Z0-9.,+%_&()!?#=-]+)* [a-zA-Z0-9#/]
 
 %state TAG_START, AFTER_LINE_START, PARSE_DELIMITED, CODE
 
@@ -285,7 +287,7 @@ GFM_AUTOLINK = (("http" "s"? | "ftp")"://" | "www.") ({ALPHANUM}([a-zA-Z0-9-]*{A
 
   {GFM_AUTOLINK} { return GFMTokenTypes.GFM_AUTOLINK; }
 
-  {ALPHANUM}+ / {WHITE_SPACE}+ {GFM_AUTOLINK} {
+  {ALPHANUM}+ (({WHITE_SPACE}+ | "_"+) {ALPHANUM}+)* / {WHITE_SPACE}+ {GFM_AUTOLINK} {
     return Token.TEXT;
   }
 

test/data/html/puppetApache.pos.txt

@@ -1873,7 +1873,8 @@ Specifies an array of <code md-src-pos="55005..55018">path =&gt; URI</code>
 <code md-src-pos="56049..56057">params</code>
  is an optional parameter. It allows to provide the ProxyPass key=value parameters (Connection settings).
 <code md-src-pos="56163..56171">setenv</code>
- is optional and is an array to set environment variables for the proxy directive, for details see http://httpd.apache.org/docs/current/mod/mod_proxy.html#envsettings</p>
+ is optional and is an array to set environment variables for the proxy directive, for details see <a href="http://httpd.apache.org/docs/current/mod/mod_proxy.html#envsettings" md-src-pos="56270..56337">http://httpd.apache.org/docs/current/mod/mod_proxy.html#envsettings</a>
+</p>
 <h5 md-src-pos="56339..56362">
 <code md-src-pos="56344..56362">proxy_dest_match</code>
 </h5>

test/data/html/ruby17351.txt

@@ -11,8 +11,8 @@ This is a single .war file deployment of <strong>Knowtify Log Analytics</strong>
 <ol>
 <li>
 <p>
-Red Hat 7 family (version 7.x  Red Hat Enterprise Linux, CentOS, Fedora, Scientific Linux, Oracle Linux and others) Commands for the Red Hat 6 family, where different, are noted in square brackets [RH6: ~command~ ] see: <a href="http://www.unixmen.com/postgresql-9-4-released-install-centos-7/,">http://www.unixmen.com/postgresql-9-4-released-install-centos-7/,</a>
- and <a href="http://www.postgresql.org/download/linux/redhat/">http://www.postgresql.org/download/linux/redhat/</a>
+Red Hat 7 family (version 7.x  Red Hat Enterprise Linux, CentOS, Fedora, Scientific Linux, Oracle Linux and others) Commands for the Red Hat 6 family, where different, are noted in square brackets [RH6: ~command~ ] see: <a href="http://www.unixmen.com/postgresql-9-4-released-install-centos-7/">http://www.unixmen.com/postgresql-9-4-released-install-centos-7/</a>
+, and <a href="http://www.postgresql.org/download/linux/redhat/">http://www.postgresql.org/download/linux/redhat/</a>
 </p>
 <ol>
 <li>
@@ -540,7 +540,7 @@ Download TAR.GZ from Elastic: <code>wget https://download.elastic.co/logstash/lo
 </ol>
 </li>
 <li>
-install the solr_http output plugin (info at https://<a href="www.elastic.co/guide/en/logstash/current/plugins-outputs-solr_http.html">www.elastic.co/guide/en/logstash/current/plugins-outputs-solr_http.html</a>
+install the solr_http output plugin (info at <a href="https://www.elastic.co/guide/en/logstash/current/plugins-outputs-solr_http.html">https://www.elastic.co/guide/en/logstash/current/plugins-outputs-solr_http.html</a>
 ):<ol>
 <li>
 <code>cd /opt/logstash-1.5.4</code>
@@ -624,7 +624,7 @@ Test in a newly opened command prompt with <code>cd %JAVA_HOME%</code>
 </ol>
 </li>
 <li>
-Install the Windows Event Log input plugin (info at https://<a href="www.elastic.co/guide/en/logstash/current/plugins-inputs-eventlog.html#plugins-inputs-eventlog-type">www.elastic.co/guide/en/logstash/current/plugins-inputs-eventlog.html#plugins-inputs-eventlog-type</a>
+Install the Windows Event Log input plugin (info at <a href="https://www.elastic.co/guide/en/logstash/current/plugins-inputs-eventlog.html#plugins-inputs-eventlog-type">https://www.elastic.co/guide/en/logstash/current/plugins-inputs-eventlog.html#plugins-inputs-eventlog-type</a>
 ):<ol>
 <li>
 <code>cd %LOGSTASH_HOME%</code>
@@ -635,7 +635,7 @@ install the plugin: <code>bin\plugin install logstash-input-eventlog</code>
 </ol>
 </li>
 <li>
-Install the solr_http output plugin (info at https://<a href="www.elastic.co/guide/en/logstash/current/plugins-outputs-solr">www.elastic.co/guide/en/logstash/current/plugins-outputs-solr</a>
+Install the solr_http output plugin (info at <a href="https://www.elastic.co/guide/en/logstash/current/plugins-outputs-solr">https://www.elastic.co/guide/en/logstash/current/plugins-outputs-solr</a>
 _http.html):<ol>
 <li>
 <code>cd %LOGSTASH_HOME%</code>
@@ -657,7 +657,9 @@ Create a run.bat file in %LOGSTASH_HOME%\bin. It should contain this command <co
 </li>
 <li>
 To install Logstash to run as a Windows Service:<ol>
-<li>Download NSSM from http://nssm.cc/</li>
+<li>
+Download NSSM from <a href="http://nssm.cc/">http://nssm.cc/</a>
+</li>
 <li>Unzip NSSM-??.zip to a temporary directory</li>
 <li>Copy the win32 or win64 version (as appropriate) of nssm.exe to %LOGSTASH_HOME%\bin</li>
 <li>

test/data/parser/gfmAutolink.md

@@ -4,6 +4,7 @@ http://aa.aa
 https://aa.aa
 ftp://aa.aa
 ssh://aa.aa
+file://aa.aa
 www.aa.aa/
 www.aa.aa//
 www.aa.aa/script.php?a=b&x=%20y#hashtag
@@ -14,4 +15,33 @@ www.aa.aa/script.php?a=b&x=%20y#hashtag
 
 [www.not.rendered.as.autolink.too][www.and.this.too]
 
-Google Group: https://groups.google.com/forum/#!forum/markdown-here
+Google Group: https://groups.google.com/forum/#!forum/markdown-here
+
+JetBrains Account portal 
+https://account.jetbrains.com
+JetBrains Account portal https://account.jetbrains.com
+JetBrains Online Store https://www.jetbrains.com/store
+
+Check out library called Exposed: https://github.com/JetBrains/Exposed.
+
+Credits for the testdata to https://mathiasbynens.be/demo/url-regex:
+
+http://142.42.1.1:8080/
+
+http://142.42.1.1:8080
+
+http://localhost:8080
+
+http://localhost.com:8080
+
+http://foo.com/blah_(wikipedia)#cite-1
+
+http://foo.com/blah_(wikipedia)_blah#cite-1
+
+http://foo.com/(something)?after=parens
+
+http://code.google.com/events/#&product=browser
+
+http://a.b-c.de
+
+https://foo_bar.example.com/

test/data/parser/gfmAutolink.txt

@@ -14,6 +14,8 @@ Markdown:MARKDOWN_FILE
     Markdown::(':')
     Markdown:TEXT('//aa.aa')
     Markdown:EOL('\n')
+    Markdown:GFM_AUTOLINK('file://aa.aa')
+    Markdown:EOL('\n')
     Markdown:GFM_AUTOLINK('www.aa.aa/')
     Markdown:EOL('\n')
     Markdown:GFM_AUTOLINK('www.aa.aa/')
@@ -56,4 +58,74 @@ Markdown:MARKDOWN_FILE
     Markdown:TEXT('Google Group')
     Markdown::(':')
     WHITE_SPACE(' ')
-    Markdown:GFM_AUTOLINK('https://groups.google.com/forum/#!forum/markdown-here')
+    Markdown:GFM_AUTOLINK('https://groups.google.com/forum/#!forum/markdown-here')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:TEXT('JetBrains Account portal')
+    WHITE_SPACE(' ')
+    Markdown:EOL('\n')
+    Markdown:GFM_AUTOLINK('https://account.jetbrains.com')
+    Markdown:EOL('\n')
+    Markdown:TEXT('JetBrains Account portal')
+    WHITE_SPACE(' ')
+    Markdown:GFM_AUTOLINK('https://account.jetbrains.com')
+    Markdown:EOL('\n')
+    Markdown:TEXT('JetBrains Online Store')
+    WHITE_SPACE(' ')
+    Markdown:GFM_AUTOLINK('https://www.jetbrains.com/store')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:TEXT('Check out library called Exposed')
+    Markdown::(':')
+    WHITE_SPACE(' ')
+    Markdown:GFM_AUTOLINK('https://github.com/JetBrains/Exposed')
+    Markdown:TEXT('.')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:TEXT('Credits for the testdata to')
+    WHITE_SPACE(' ')
+    Markdown:GFM_AUTOLINK('https://mathiasbynens.be/demo/url-regex')
+    Markdown::(':')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://142.42.1.1:8080/')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://142.42.1.1:8080')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://localhost:8080')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://localhost.com:8080')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://foo.com/blah_(wikipedia)#cite-1')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://foo.com/blah_(wikipedia)_blah#cite-1')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://foo.com/(something)?after=parens')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://code.google.com/events/#&product=browser')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('http://a.b-c.de')
+  Markdown:EOL('\n')
+  Markdown:EOL('\n')
+  Markdown:PARAGRAPH
+    Markdown:GFM_AUTOLINK('https://foo_bar.example.com/')