[svn] Add Groff lexer by Tim Hatch, find_error script, CSS lexer improvement.

Add analyse_text methods to some lexers.

3 files changed, 88 insertions, 4 deletions

diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index ab56d8c0..ff82b891 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -31,6 +31,7 @@ LEXERS = {
     'ErbLexer': ('pygments.lexers.templates', 'ERB', ('erb',), (), ()),
     'GenshiLexer': ('pygments.lexers.templates', 'Genshi', ('genshi', 'kid', 'xml+genshi', 'xml+kid'), ('*.kid',), ()),
     'GenshiTextLexer': ('pygments.lexers.templates', 'Genshi Text', ('genshitext',), (), ()),
+    'GroffLexer': ('pygments.lexers.text', 'Groff', ('groff', 'nroff', 'man'), ('*.[1234567]', '*.man'), ('application/x-troff',)),
     'HtmlDjangoLexer': ('pygments.lexers.templates', 'HTML+Django/Jinja', ('html+django', 'html+jinja'), (), ()),
     'HtmlGenshiLexer': ('pygments.lexers.templates', 'HTML+Genshi', ('html+genshi', 'html+kid'), (), ()),
     'HtmlLexer': ('pygments.lexers.web', 'HTML', ('html',), ('*.html', '*.htm', '*.xhtml'), ('text/html', 'application/xhtml+xml')),
diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py
index c322badf..8e9a2f13 100644
--- a/pygments/lexers/text.py
+++ b/pygments/lexers/text.py
@@ -5,7 +5,8 @@
 
     Lexers for non-source code file types: Diff, Makefiles, Ini configs etc.
 
-    :copyright: 2006 by Armin Ronacher, Georg Brandl.
+    :copyright: 2006 by Armin Ronacher, Georg Brandl,
+                Tim Hatch <tim@timhatch.com>.
     :license: BSD, see LICENSE for more details.
 """
 
@@ -17,7 +18,7 @@ from pygments.token import \
 
 
 __all__ = ['IniLexer', 'MakefileLexer', 'DiffLexer', 'IrcLogsLexer',
-           'TexLexer']
+           'TexLexer', 'GroffLexer']
 
 
 class IniLexer(RegexLexer):
@@ -35,6 +36,12 @@ class IniLexer(RegexLexer):
         ]
     }
 
+    def analyse_text(text):
+        npos = text.find('\n')
+        if npos < 3:
+            return False
+        return text[0] == '[' and text[npos-1] == ']'
+
 
 class MakefileLexer(RegexLexer):
     name = 'Makefile'
@@ -98,6 +105,14 @@ class DiffLexer(RegexLexer):
         ]
     }
 
+    def analyse_text(text):
+        if text[:7] == 'Index: ':
+            return True
+        if text[:5] == 'diff ':
+            return True
+        if text[:4] == '--- ':
+            return 0.9
+
 
 class IrcLogsLexer(RegexLexer):
     name = 'IRC logs'
@@ -184,3 +199,61 @@ class TexLexer(RegexLexer):
             (r'', Text, '#pop'),
         ],
     }
+
+    def analyse_text(text):
+        for start in ("\\documentclass", "\\input", "\\documentstyle",
+                      "\\relax"):
+            if text[:len(start)] == start:
+                return True
+
+
+class GroffLexer(RegexLexer):
+    """
+    Lexer for the roff format, supporting groff extensions.  Mainly useful
+    for highlighting manpages.
+    """
+    name = 'Groff'
+    aliases = ['groff', 'nroff', 'man']
+    filenames = ['*.[1234567]', '*.man']
+    mimetypes = ['application/x-troff', 'text/troff']
+
+    tokens = {
+        'root': [
+            (r'(?i)(\.)(\w+)', bygroups(Text, Keyword), 'request'),
+            (r'\.', Text, 'request'),
+            # Regular characters, slurp till we find a backslash or newline
+            (r'[^\\\n]*', Text, 'textline'),
+        ],
+        'textline': [
+            include('escapes'),
+            (r'[^\\\n]+', Text),
+            (r'\n', Text, '#pop'),
+        ],
+        'escapes': [
+            # groff has many ways to write escapes.
+            (r'\\"[^\n]*', Comment),
+            (r'\\[fn]\w', String.Escape),
+            (r'\\\(..', String.Escape),
+            (r'\\.\[.*\]', String.Escape),
+            (r'\\.', String.Escape),
+            (r'\\\n', Text, 'request'),
+        ],
+        'request': [
+            (r'\n', Text, '#pop'),
+            include('escapes'),
+            (r'"[^\n"]+"', String.Double),
+            (r'\d+', Number),
+            (r'\S+', String),
+            (r'\s+', Text),
+        ],
+    }
+
+    def analyse_text(text):
+        if text[0] != '.':
+            return False
+        if text[:3] == '.\\"':
+            return True
+        if text[:4] == '.TH ':
+            return True
+        if text[1:3].isalnum() and text[3].isspace():
+            return 0.9
diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py
index 904c8c11..28320308 100644
--- a/pygments/lexers/web.py
+++ b/pygments/lexers/web.py
@@ -5,7 +5,8 @@
 
     Lexers for web-related languages: JavaScript, CSS, HTML, XML, PHP.
 
-    :copyright: 2006 by Georg Brandl, Armin Ronacher.
+    :copyright: 2006 by Georg Brandl, Armin Ronacher,
+                Tim Hatch <tim@timhatch.com>.
     :license: BSD, see LICENSE for more details.
 """
 
@@ -15,7 +16,7 @@ try:
 except NameError:
     from sets import Set as set
 
-from pygments.lexer import Lexer, RegexLexer, bygroups, using
+from pygments.lexer import Lexer, RegexLexer, bygroups, using, include
 from pygments.token import \
      Text, Comment, Operator, Keyword, Name, String, Number, Other
 from pygments.util import get_bool_opt, get_list_opt, looks_like_xml, \
@@ -65,6 +66,11 @@ class CssLexer(RegexLexer):
 
     tokens = {
         'root': [
+            (r'(@media)(\s+)(\w+)(\s*)({)', bygroups(Keyword, Text, String,
+             Text, Operator), 'media'),
+            include('basics'),
+        ],
+        'basics': [
             (r'\s+', Text),
             (r'/\*(?:.|\n)*?\*/', Comment),
             (r'{', Operator, 'content'),
@@ -76,6 +82,10 @@ class CssLexer(RegexLexer):
             (r'"(\\\\|\\"|[^"])*"', String.Double),
             (r"'(\\\\|\\'|[^'])*'", String.Single)
         ],
+        'media': [
+            include('basics'),
+            (r'}', Operator, '#pop')
+        ],
         'content': [
             (r'\s+', Text),
             (r'}', Operator, '#pop'),