Merged default into add-wdiff-lexer

2 files changed, 61 insertions, 1 deletions

diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index c2251e51..1f3c6c27 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -403,6 +403,7 @@ LEXERS = {
     'VerilogLexer': ('pygments.lexers.hdl', 'verilog', ('verilog', 'v'), ('*.v',), ('text/x-verilog',)),
     'VhdlLexer': ('pygments.lexers.hdl', 'vhdl', ('vhdl',), ('*.vhdl', '*.vhd'), ('text/x-vhdl',)),
     'VimLexer': ('pygments.lexers.textedit', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'), ('text/x-vim',)),
+    'WDiffLexer': ('pygments.lexers.diff', 'WDiff', ('wdiff',), ('*.wdiff',), ()),
     'X10Lexer': ('pygments.lexers.x10', 'X10', ('x10', 'xten'), ('*.x10',), ('text/x-x10',)),
     'XQueryLexer': ('pygments.lexers.webmisc', 'XQuery', ('xquery', 'xqy', 'xq', 'xql', 'xqm'), ('*.xqy', '*.xquery', '*.xq', '*.xql', '*.xqm'), ('text/xquery', 'application/xquery')),
     'XmlDjangoLexer': ('pygments.lexers.templates', 'XML+Django/Jinja', ('xml+django', 'xml+jinja'), (), ('application/xml+django', 'application/xml+jinja')),
diff --git a/pygments/lexers/diff.py b/pygments/lexers/diff.py
index d3b1589d..2056fbff 100644
--- a/pygments/lexers/diff.py
+++ b/pygments/lexers/diff.py
@@ -9,11 +9,13 @@
     :license: BSD, see LICENSE for details.
 """
 
+import re
+
 from pygments.lexer import RegexLexer, include, bygroups
 from pygments.token import Text, Comment, Operator, Keyword, Name, Generic, \
     Literal
 
-__all__ = ['DiffLexer', 'DarcsPatchLexer']
+__all__ = ['DiffLexer', 'DarcsPatchLexer', 'WDiffLexer']
 
 
 class DiffLexer(RegexLexer):
@@ -104,3 +106,60 @@ class DarcsPatchLexer(RegexLexer):
             (r'[^\n\[]+', Generic.Deleted),
         ],
     }
+
+
+class WDiffLexer(RegexLexer):
+    """
+    A `wdiff <https://www.gnu.org/software/wdiff/>`_ lexer.
+
+    Note that:
+
+    * only to normal output (without option like -l).
+    * if target files of wdiff contain "[-", "-]", "{+", "+}",
+      especially they are unbalanced, this lexer will get confusing.
+
+    .. versionadded:: 2.1
+    """
+
+    name = 'WDiff'
+    aliases = ['wdiff',]
+    filenames = ['*.wdiff',]
+    mimetypes = []
+
+    flags = re.MULTILINE | re.DOTALL
+
+    # We can only assume "[-" after "[-" before "-]" is `nested`,
+    # for instance wdiff to wdiff outputs. We have no way to
+    # distinct these marker is of wdiff output from original text.
+
+    ins_op = r"\{\+"
+    ins_cl = r"\+\}"
+    del_op = r"\[\-"
+    del_cl = r"\-\]"
+    normal = r'[^{}[\]+-]+'  # for performance
+    tokens = {
+        'root': [
+            (ins_op, Generic.Inserted, 'inserted'),
+            (del_op, Generic.Deleted, 'deleted'),
+            (normal, Text),
+            (r'.', Text),
+        ],
+        'inserted': [
+            (ins_op, Generic.Inserted, '#push'),
+            (del_op, Generic.Inserted, '#push'),
+            (del_cl, Generic.Inserted, '#pop'),
+
+            (ins_cl, Generic.Inserted, '#pop'),
+            (normal, Generic.Inserted),
+            (r'.', Generic.Inserted),
+        ],
+        'deleted': [
+            (del_op, Generic.Deleted, '#push'),
+            (ins_op, Generic.Deleted, '#push'),
+            (ins_cl, Generic.Deleted, '#pop'),
+
+            (del_cl, Generic.Deleted, '#pop'),
+            (normal, Generic.Deleted),
+            (r'.', Generic.Deleted),
+        ],
+    }