integrated weechatlog lexer directly into the existing irc lexer

2 files changed, 15 insertions, 35 deletions

diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index 862c84da..e71c9035 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -48,7 +48,7 @@ LEXERS = {
     'HtmlPhpLexer': ('pygments.lexers.templates', 'HTML+PHP', ('html+php',), ('*.phtml',), ('application/x-php', 'application/x-httpd-php', 'application/x-httpd-php3', 'application/x-httpd-php4', 'application/x-httpd-php5')),
     'HtmlSmartyLexer': ('pygments.lexers.templates', 'HTML+Smarty', ('html+smarty',), (), ('text/html+smarty',)),
     'IniLexer': ('pygments.lexers.text', 'INI', ('ini', 'cfg'), ('*.ini', '*.cfg'), ('text/x-ini',)),
-    'IrcLogsLexer': ('pygments.lexers.text', 'IRC logs', ('irc',), (), ('text/x-irclog',)),
+    'IrcLogsLexer': ('pygments.lexers.text', 'IRC logs', ('irc',), ('*.weechatlog',), ('text/x-irclog',)),
     'JavaLexer': ('pygments.lexers.compiled', 'Java', ('java',), ('*.java',), ('text/x-java',)),
     'JavascriptDjangoLexer': ('pygments.lexers.templates', 'JavaScript+Django/Jinja', ('js+django', 'javascript+django', 'js+jinja', 'javascript+jinja'), (), ('application/x-javascript+django', 'application/x-javascript+jinja', 'text/x-javascript+django', 'text/x-javascript+jinja', 'text/javascript+django', 'text/javascript+jinja')),
     'JavascriptErbLexer': ('pygments.lexers.templates', 'JavaScript+Ruby', ('js+erb', 'javascript+erb', 'js+ruby', 'javascript+ruby'), (), ('application/x-javascript+ruby', 'text/x-javascript+ruby', 'text/javascript+ruby')),
@@ -95,7 +95,6 @@ LEXERS = {
     'TextLexer': ('pygments.lexers.special', 'Text only', ('text',), ('*.txt',), ('text/plain',)),
     'VbNetLexer': ('pygments.lexers.dotnet', 'VB.net', ('vb.net', 'vbnet'), ('*.vb', '*.bas'), ('text/x-vbnet', 'text/x-vba')),
     'VimLexer': ('pygments.lexers.text', 'VimL', ('vim',), ('*.vim', '.vimrc'), ('text/x-vim',)),
-    'WeechatLogLexer': ('pygments.lexers.text', 'Weechat Log', ('weechatlog',), ('*.weechatlog',), ('text/x-weechatlog',)),
     'XmlDjangoLexer': ('pygments.lexers.templates', 'XML+Django/Jinja', ('xml+django', 'xml+jinja'), (), ('application/xml+django', 'application/xml+jinja')),
     'XmlErbLexer': ('pygments.lexers.templates', 'XML+Ruby', ('xml+erb', 'xml+ruby'), (), ('application/xml+ruby',)),
     'XmlLexer': ('pygments.lexers.web', 'XML', ('xml',), ('*.xml', '*.xsl', '*.rss', '*.xslt'), ('text/xml', 'application/xml', 'image/svg+xml', 'application/rss+xml', 'application/atom+xml', 'application/xsl+xml', 'application/xslt+xml')),
diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py
index 12abd35d..4ed18d17 100644
--- a/pygments/lexers/text.py
+++ b/pygments/lexers/text.py
@@ -30,7 +30,7 @@ from pygments.util import get_bool_opt
 __all__ = ['IniLexer', 'SourcesListLexer', 'MakefileLexer', 'DiffLexer',
            'IrcLogsLexer', 'TexLexer', 'GroffLexer', 'ApacheConfLexer',
            'BBCodeLexer', 'MoinWikiLexer', 'RstLexer', 'VimLexer',
-           'GettextLexer', 'WeechatLogLexer']
+           'GettextLexer']
 
 
 class IniLexer(RegexLexer):
@@ -202,17 +202,25 @@ class IrcLogsLexer(RegexLexer):
 
     name = 'IRC logs'
     aliases = ['irc']
+    filenames = ['*.weechatlog']
     mimetypes = ['text/x-irclog']
 
     flags = re.VERBOSE | re.MULTILINE
     timestamp = r"""
-        ( (?: \[|\()?                  # Opening bracket or paren for the timestamp
+        (
+          # irssi / xchat and others
+          (?: \[|\()?                  # Opening bracket or paren for the timestamp
             (?:                        # Timestamp
                 (?: (?:\d{1,4} [-/]?)+ # Date as - or /-separated groups of digits
                  [T ])?                # Date/time separator: T or space
                 (?: \d?\d [:.]?)+      # Time as :/.-separated groups of 1 or 2 digits
             )
-          (?: \]|\))?\s+ )?            # Closing bracket or paren for the timestamp
+          (?: \]|\))?\s+               # Closing bracket or paren for the timestamp
+        |
+          # weechat
+          \d{4}\s\w{3}\s\d{2}\s        # Date
+          \d{2}:\d{2}:\d{2}\s+         # Time + Whitespace
+        )?
     """
     tokens = {
         'root': [
@@ -227,9 +235,9 @@ class IrcLogsLexer(RegexLexer):
              bygroups(Comment.Preproc, Keyword, Generic.Inserted)),
             # join/part msgs
             ("^" + timestamp + r"""
-                (\s*(?:[*]{3}|-!-)\s*) # Star(s)
-                ([^\s]+\s+)            # Nick + Space
-                (.*?\n)                # Rest of message """,
+                (\s*(?:\*{3}|<?-[!@=P]?->?)\s*)  # Star(s) or symbols
+                ([^\s]+\s+)                     # Nick + Space
+                (.*?\n)                         # Rest of message """,
              bygroups(Comment.Preproc, Keyword, String, Comment)),
             (r"^.*?\n", Text),
         ],
@@ -702,30 +710,3 @@ class GettextLexer(RegexLexer):
              bygroups(Name.Variable, Number.Integer, Name.Variable, Text, String)),
         ]
     }
-
-
-class WeechatLogLexer(RegexLexer):
-	"""
-	Lexer for weechat log files.
-	
-	*New in Pygments 0.9.*
-	"""
-	name = 'Weechat Log'
-	aliases = ['weechatlog']
-	filenames = ['*.weechatlog']
-	mimetypes = ['text/x-weechatlog']
-	
-	tokens = {
-		'root' : [
-			# date
-			(r'(\d{4} \w{3} \d{2} \d{2}:\d{2}:\d{2})(\s+)',
-				bygroups(Comment.Preproc, Whitespace)),
-			# operators
-			(r'(-=-|<--|-->|-@-|-P-)(.*)', bygroups(Operator, Text)),
-			# messages
-			(r'(<)(\w+)(>)(.*)', bygroups(Operator, Name, Operator, Text)),
-			# log start/end
-			(r'(\*\*\*\*[\w\s]+)(\d{4} \w{3} \d{2} \d{2}:\d{2}:\d{2}\s+)(\*\*\*\*)',
-				Comment)
-		]
-	}