1 files changed, 75 insertions, 0 deletions
diff --git a/pygments/lexers/special.py b/pygments/lexers/special.py
new file mode 100644
index 00000000..9076ca51
--- /dev/null
+++ b/pygments/lexers/special.py
@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.special
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Special lexers.
+
+    :copyright: 2006 by Georg Brandl.
+    :license: GNU LGPL, see LICENSE for more details.
+"""
+
+import re
+import cStringIO
+
+from pygments.lexer import Lexer, RegexLexer
+from pygments.token import Token, \
+     Text, Comment, Operator, Keyword, Name, String, Number
+
+
+__all__ = ['TextLexer', 'RawTokenLexer']
+
+
+class TextLexer(Lexer):
+    name = 'Text only'
+    aliases = ['text']
+    filenames = ['*.txt']
+
+    def get_tokens_unprocessed(self, text):
+        yield 0, Text, text
+
+
+_ttype_cache = {}
+
+line_re = re.compile('.*?\n')
+
+class RawTokenLexer(Lexer):
+    """
+    Recreate a token stream formatted with the RawTokenFormatter.
+
+    Additional options accepted:
+
+    ``compress``
+        If set to "gz" or "bz2", decompress the token stream with
+        the given compression algorithm (default: '').
+    """
+    name = 'Raw token data'
+    aliases = ['raw']
+    filenames = ['*.raw']
+
+    def __init__(self, **options):
+        self.compress = options.get('compress', '')
+        Lexer.__init__(self, **options)
+
+    def get_tokens(self, text):
+        if self.compress == 'gz':
+            import gzip
+            gzipfile = gzip.GzipFile('', 'rb', 9, cStringIO.StringIO(text))
+            text = gzipfile.read()
+        elif self.compress == 'bz2':
+            import bz2
+            text = bz2.decompress(text)
+        return Lexer.get_tokens(self, text)
+
+    def get_tokens_unprocessed(self, text):
+        for match in line_re.finditer(text):
+            ttypestr, val = match.group().split('\t', 1)
+            ttype = _ttype_cache.get(ttypestr)
+            if not ttype:
+                ttype = Token
+                ttypes = ttypestr.split('.')[1:]
+                for ttype_ in ttypes:
+                    ttype = getattr(ttype, ttype_)
+                _ttype_cache[ttypestr] = ttype
+            val = val[1:-2].decode('string-escape')
+            yield 0, ttype, val