Merged in cheesinglee/pygments-main (pull request #551)

Add Flatline lexer

7 files changed, 1079 insertions, 0 deletions

diff --git a/tests/examplefiles/StdGeneric.icl b/tests/examplefiles/StdGeneric.icl
new file mode 100644
index 00000000..2e6c3931
--- /dev/null
+++ b/tests/examplefiles/StdGeneric.icl
@@ -0,0 +1,92 @@
+implementation module StdGeneric
+
+import StdInt, StdMisc, StdClass, StdFunc
+
+generic bimap a b :: Bimap .a .b
+
+bimapId :: Bimap .a .a
+bimapId = { map_to = id, map_from = id }
+
+bimap{|c|} = { map_to = id, map_from = id }
+
+bimap{|PAIR|} bx by = { map_to= map_to, map_from=map_from }
+where
+	map_to (PAIR x y) 	= PAIR (bx.map_to x) (by.map_to y)
+	map_from (PAIR x y) 	= PAIR (bx.map_from x) (by.map_from y)
+bimap{|EITHER|} bl br = { map_to= map_to, map_from=map_from }
+where	
+	map_to (LEFT x) 	= LEFT (bl.map_to x)
+	map_to (RIGHT x)	= RIGHT (br.map_to x)
+	map_from (LEFT x) 	= LEFT (bl.map_from x)
+	map_from (RIGHT x) 	= RIGHT (br.map_from x)
+
+bimap{|(->)|} barg bres = { map_to = map_to, map_from = map_from }
+where
+	map_to f = comp3 bres.map_to f barg.map_from
+	map_from f = comp3 bres.map_from f barg.map_to
+
+bimap{|CONS|} barg = { map_to= map_to, map_from=map_from }
+where
+	map_to   (CONS x) = CONS (barg.map_to x)
+	map_from (CONS x) = CONS (barg.map_from x)
+
+bimap{|FIELD|} barg = { map_to= map_to, map_from=map_from }
+where
+	map_to   (FIELD x) = FIELD (barg.map_to x)
+	map_from (FIELD x) = FIELD (barg.map_from x)
+
+bimap{|OBJECT|} barg = { map_to= map_to, map_from=map_from }
+where
+	map_to   (OBJECT x) = OBJECT (barg.map_to x)
+	map_from (OBJECT x) = OBJECT (barg.map_from x)
+
+bimap{|Bimap|} x y = {map_to = map_to, map_from = map_from}
+where
+	map_to 	{map_to, map_from} = 
+		{ map_to 	= comp3 y.map_to map_to x.map_from
+		, map_from 	= comp3 x.map_to map_from y.map_from
+		}
+	map_from {map_to, map_from} = 
+		{ map_to 	= comp3 y.map_from map_to x.map_to
+		, map_from 	= comp3 x.map_from map_from y.map_to
+		}
+
+comp3 :: !(.a -> .b) u:(.c -> .a) !(.d -> .c) -> u:(.d -> .b)
+comp3 f g h
+	| is_id f
+		| is_id h
+			= cast g
+			= cast (\x -> g (h x))
+		| is_id h
+			= cast (\x -> f (g x))
+			= \x -> f (g (h x))
+where
+	is_id :: !.(.a -> .b) -> Bool
+	is_id f = code inline
+	{
+		eq_desc e_StdFunc_did 0 0
+		pop_a 1
+	}
+	
+	cast :: !u:a -> u:b
+	cast f = code inline
+	{
+		pop_a 0
+	}
+
+getConsPath :: !GenericConsDescriptor -> [ConsPos]
+getConsPath {gcd_index, gcd_type_def={gtd_num_conses}}
+	= doit gcd_index gtd_num_conses
+where
+	doit i n
+		| n == 0 	
+			= abort "getConsPath: zero conses\n"
+		| i >= n	
+			= abort "getConsPath: cons index >= number of conses"
+		| n == 1
+			= []
+		| i < (n/2)
+			= [ ConsLeft : doit i (n/2) ]
+		| otherwise
+			= [ ConsRight : doit (i - (n/2)) (n - (n/2)) ]
+			  	 							 	
\ No newline at end of file
diff --git a/tests/examplefiles/example2.cpp b/tests/examplefiles/example2.cpp
new file mode 100644
index 00000000..ccd99383
--- /dev/null
+++ b/tests/examplefiles/example2.cpp
@@ -0,0 +1,20 @@
+/*
+ * A Test file for the different string literals.
+ */
+
+#include <iostream>
+
+int main() {
+    char *_str      = "a normal string";
+    wchar_t *L_str  = L"a wide string";
+    char *u8_str    = u8"utf-8 string";
+    char16_t *u_str = u"utf-16 string";
+    char32_t *U_str = U"utf-32 string";
+    char *R_str     = R""""(raw string with
+"""
+as a delimiter)"""";
+
+    std::cout << R_str << std::endl;
+
+    return 0;
+}
diff --git a/tests/examplefiles/postgresql_test.txt b/tests/examplefiles/postgresql_test.txt
index 190d184f..28db5ee3 100644
--- a/tests/examplefiles/postgresql_test.txt
+++ b/tests/examplefiles/postgresql_test.txt
@@ -45,3 +45,37 @@ $$;
 SELECT U&'\0441\043B\043E\043D'
 FROM U&"\0441\043B\043E\043D";
 
+-- Escapes
+SELECT E'1\n2\n3';
+
+-- DO example from postgresql documentation
+/*
+ * PostgreSQL is Copyright © 1996-2016 by the PostgreSQL Global Development Group.
+ * 
+ * Postgres95 is Copyright © 1994-5 by the Regents of the University of California.
+ * 
+ * Permission to use, copy, modify, and distribute this software and its
+ * documentation for any purpose, without fee, and without a written agreement
+ * is hereby granted, provided that the above copyright notice and this paragraph
+ * and the following two paragraphs appear in all copies.
+ * 
+ * IN NO EVENT SHALL THE UNIVERSITY OF CALIFORNIA BE LIABLE TO ANY PARTY FOR
+ * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING
+ * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION,
+ * EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * 
+ * THE UNIVERSITY OF CALIFORNIA SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS-IS" BASIS,
+ * AND THE UNIVERSITY OF CALIFORNIA HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE,
+ * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
+ */
+DO $$DECLARE r record;
+BEGIN
+    FOR r IN SELECT table_schema, table_name FROM information_schema.tables
+             WHERE table_type = 'VIEW' AND table_schema = 'public'
+    LOOP
+        EXECUTE 'GRANT ALL ON ' || quote_ident(r.table_schema) || '.' || quote_ident(r.table_name) || ' TO webuser';
+    END LOOP;
+END$$;
diff --git a/tests/examplefiles/test.php b/tests/examplefiles/test.php
index 794961c1..e8efdc6a 100644
--- a/tests/examplefiles/test.php
+++ b/tests/examplefiles/test.php
@@ -535,5 +535,10 @@ $magic->__toString();
 
      EOF;
 
+echo <<<"some_delimiter"
+more heredoc testing
+continues on this line
+some_delimiter;
+
 ?>
 
diff --git a/tests/examplefiles/varnish.vcl b/tests/examplefiles/varnish.vcl
new file mode 100644
index 00000000..6258c313
--- /dev/null
+++ b/tests/examplefiles/varnish.vcl
@@ -0,0 +1,187 @@
+# This is the VCL configuration Varnish will automatically append to your VCL
+# file during compilation/loading. See the vcl(7) man page for details on syntax
+# and semantics.
+# New users is recommended to use the example.vcl file as a starting point.
+
+vcl 4.0;
+
+backend foo { .host = "192.168.1.1"; }
+
+probe blatti { .url = "foo"; }
+probe fooy {
+	.url = "beh";
+
+}
+
+acl foo {
+	"192.168.1.1";
+	"192.168.0.0"/24;
+	! "192.168.0.1";
+}
+
+include "foo.vcl";
+
+import std;
+
+sub vcl_init {
+	new b = director.foo();
+}
+
+sub vcl_recv {
+	ban(req.url ~ "foo");
+	rollback();
+}
+sub vcl_recv {
+    if (req.method == "PRI") {
+	/* We do not support SPDY or HTTP/2.0 */
+	return (synth(405));
+    }
+    if (req.method != "GET" &&
+      req.method != "HEAD" &&
+      req.method != "PUT" &&
+      req.method != "POST" &&
+      req.method != "TRACE" &&
+      req.method != "OPTIONS" &&
+      req.method != "DELETE") {
+        /* Non-RFC2616 or CONNECT which is weird. */
+        return (pipe);
+    }
+
+    if (req.method != "GET" && req.method != "HEAD") {
+        /* We only deal with GET and HEAD by default */
+        return (pass);
+    }
+    if (req.http.Authorization || req.http.Cookie) {
+        /* Not cacheable by default */
+        return (pass);
+    }
+    return (hash);
+}
+
+sub vcl_pipe {
+    # By default Connection: close is set on all piped requests, to stop
+    # connection reuse from sending future requests directly to the
+    # (potentially) wrong backend. If you do want this to happen, you can undo
+    # it here.
+    # unset bereq.http.connection;
+    return (pipe);
+}
+
+sub vcl_pass {
+    return (fetch);
+}
+
+sub vcl_hash {
+    hash_data(req.url);
+    if (req.http.host) {
+        hash_data(req.http.host);
+    } else {
+        hash_data(server.ip);
+    }
+    return (lookup);
+}
+
+sub vcl_purge {
+    return (synth(200, "Purged"));
+}
+
+sub vcl_hit {
+    if (obj.ttl >= 0s) {
+        // A pure unadultered hit, deliver it
+        return (deliver);
+    }
+    if (obj.ttl + obj.grace > 0s) {
+        // Object is in grace, deliver it
+        // Automatically triggers a background fetch
+        return (deliver);
+    }
+    // fetch & deliver once we get the result
+    return (miss);
+}
+
+sub vcl_miss {
+    return (fetch);
+}
+
+sub vcl_deliver {
+    set resp.http.x-storage = storage.s0.free;
+    return (deliver);
+}
+
+/*
+ * We can come here "invisibly" with the following errors: 413, 417 & 503
+ */
+sub vcl_synth {
+    set resp.http.Content-Type = "text/html; charset=utf-8";
+    set resp.http.Retry-After = "5";
+    synthetic( {"<!DOCTYPE html>
+<html>
+  <head>
+    <title>"} + resp.status + " " + resp.reason + {"</title>
+  </head>
+  <body>
+    <h1>Error "} + resp.status + " " + resp.reason + {"</h1>
+    <p>"} + resp.reason + {"</p>
+    <h3>Guru Meditation:</h3>
+    <p>XID: "} + req.xid + {"</p>
+    <hr>
+    <p>Varnish cache server</p>
+  </body>
+</html>
+"} );
+    return (deliver);
+}
+
+#######################################################################
+# Backend Fetch
+
+sub vcl_backend_fetch {
+    return (fetch);
+}
+
+sub vcl_backend_response {
+    if (beresp.ttl <= 0s ||
+      beresp.http.Set-Cookie ||
+      beresp.http.Surrogate-control ~ "no-store" ||
+      (!beresp.http.Surrogate-Control &&
+        beresp.http.Cache-Control ~ "no-cache|no-store|private") ||
+      beresp.http.Vary == "*") {
+        /*
+        * Mark as "Hit-For-Pass" for the next 2 minutes
+        */
+        set beresp.ttl = 120s;
+        set beresp.uncacheable = true;
+    }
+    return (deliver);
+}
+
+sub vcl_backend_error {
+    set beresp.http.Content-Type = "text/html; charset=utf-8";
+    set beresp.http.Retry-After = "5";
+    synthetic( {"<!DOCTYPE html>
+<html>
+  <head>
+    <title>"} + beresp.status + " " + beresp.reason + {"</title>
+  </head>
+  <body>
+    <h1>Error "} + beresp.status + " " + beresp.reason + {"</h1>
+    <p>"} + beresp.reason + {"</p>
+    <h3>Guru Meditation:</h3>
+    <p>XID: "} + bereq.xid + {"</p>
+    <hr>
+    <p>Varnish cache server</p>
+  </body>
+</html>
+"} );
+    return (deliver);
+}
+
+#######################################################################
+# Housekeeping
+
+sub vcl_init {
+}
+
+sub vcl_fini {
+    return (ok);
+}
diff --git a/tests/examplefiles/wdiff_example1.wdiff b/tests/examplefiles/wdiff_example1.wdiff
new file mode 100644
index 00000000..ca760812
--- /dev/null
+++ b/tests/examplefiles/wdiff_example1.wdiff
@@ -0,0 +1,731 @@
+.. -*- mode: rst -*-
+
+{+.. highlight:: python+}
+
+====================
+Write your own lexer
+====================
+
+If a lexer for your favorite language is missing in the Pygments package, you
+can easily write your own and extend Pygments.
+
+All you need can be found inside the :mod:`pygments.lexer` module.  As you can
+read in the :doc:`API documentation <api>`, a lexer is a class that is
+initialized with some keyword arguments (the lexer options) and that provides a
+:meth:`.get_tokens_unprocessed()` method which is given a string or unicode
+object with the data to [-parse.-] {+lex.+}
+
+The :meth:`.get_tokens_unprocessed()` method must return an iterator or iterable
+containing tuples in the form ``(index, token, value)``.  Normally you don't
+need to do this since there are [-numerous-] base lexers {+that do most of the work and that+}
+you can subclass.
+
+
+RegexLexer
+==========
+
+[-A very powerful (but quite easy to use)-]
+
+{+The+} lexer {+base class used by almost all of Pygments' lexers+} is the
+:class:`RegexLexer`.  This
+[-lexer base-] class allows you to define lexing rules in terms of
+*regular expressions* for different *states*.
+
+States are groups of regular expressions that are matched against the input
+string at the *current position*.  If one of these expressions matches, a
+corresponding action is performed [-(normally-] {+(such as+} yielding a token with a specific
+[-type),-]
+{+type, or changing state),+} the current position is set to where the last match
+ended and the matching process continues with the first regex of the current
+state.
+
+Lexer states are kept [-in-] {+on+} a [-state-] stack: each time a new state is entered, the new
+state is pushed onto the stack.  The most basic lexers (like the `DiffLexer`)
+just need one state.
+
+Each state is defined as a list of tuples in the form (`regex`, `action`,
+`new_state`) where the last item is optional.  In the most basic form, `action`
+is a token type (like `Name.Builtin`).  That means: When `regex` matches, emit a
+token with the match text and type `tokentype` and push `new_state` on the state
+stack.  If the new state is ``'#pop'``, the topmost state is popped from the
+stack instead. [-(To-]  {+To+} pop more than one state, use ``'#pop:2'`` and so [-on.)-] {+on.+}
+``'#push'`` is a synonym for pushing the current state on the stack.
+
+The following example shows the `DiffLexer` from the builtin lexers.  Note that
+it contains some additional attributes `name`, `aliases` and `filenames` which
+aren't required for a lexer.  They are used by the builtin lexer lookup
+functions.
+
+[-.. sourcecode:: python-] {+::+}
+
+    from pygments.lexer import RegexLexer
+    from pygments.token import *
+
+    class DiffLexer(RegexLexer):
+        name = 'Diff'
+        aliases = ['diff']
+        filenames = ['*.diff']
+
+        tokens = {
+            'root': [
+                (r' .*\n', Text),
+                (r'\+.*\n', Generic.Inserted),
+                (r'-.*\n', Generic.Deleted),
+                (r'@.*\n', Generic.Subheading),
+                (r'Index.*\n', Generic.Heading),
+                (r'=.*\n', Generic.Heading),
+                (r'.*\n', Text),
+            ]
+        }
+
+As you can see this lexer only uses one state.  When the lexer starts scanning
+the text, it first checks if the current character is a space.  If this is true
+it scans everything until newline and returns the [-parsed-] data as {+a+} `Text` [-token.-] {+token (which
+is the "no special highlighting" token).+}
+
+If this rule doesn't match, it checks if the current char is a plus sign.  And
+so on.
+
+If no rule matches at the current position, the current char is emitted as an
+`Error` token that indicates a [-parsing-] {+lexing+} error, and the position is increased by
+[-1.-]
+{+one.+}
+
+
+Adding and testing a new lexer
+==============================
+
+To make [-pygments-] {+Pygments+} aware of your new lexer, you have to perform the following
+steps:
+
+First, change to the current directory containing the [-pygments-] {+Pygments+} source code:
+
+.. [-sourcecode::-] {+code-block::+} console
+
+    $ cd .../pygments-main
+
+{+Select a matching module under ``pygments/lexers``, or create a new module for
+your lexer class.+}
+
+Next, make sure the lexer is known from outside of the module.  All modules in
+the ``pygments.lexers`` specify ``__all__``. For example, [-``other.py`` sets:
+
+.. sourcecode:: python-] {+``esoteric.py`` sets::+}
+
+    __all__ = ['BrainfuckLexer', 'BefungeLexer', ...]
+
+Simply add the name of your lexer class to this list.
+
+Finally the lexer can be made [-publically-] {+publicly+} known by rebuilding the lexer mapping:
+
+.. [-sourcecode::-] {+code-block::+} console
+
+    $ make mapfiles
+
+To test the new lexer, store an example file with the proper extension in
+``tests/examplefiles``.  For example, to test your ``DiffLexer``, add a
+``tests/examplefiles/example.diff`` containing a sample diff output.
+
+Now you can use pygmentize to render your example to HTML:
+
+.. [-sourcecode::-] {+code-block::+} console
+
+    $ ./pygmentize -O full -f html -o /tmp/example.html tests/examplefiles/example.diff
+
+Note that this [-explicitely-] {+explicitly+} calls the ``pygmentize`` in the current directory
+by preceding it with ``./``. This ensures your modifications are used.
+Otherwise a possibly already installed, unmodified version without your new
+lexer would have been called from the system search path (``$PATH``).
+
+To view the result, open ``/tmp/example.html`` in your browser.
+
+Once the example renders as expected, you should run the complete test suite:
+
+.. [-sourcecode::-] {+code-block::+} console
+
+    $ make test
+
+{+It also tests that your lexer fulfills the lexer API and certain invariants,
+such as that the concatenation of all token text is the same as the input text.+}
+
+
+Regex Flags
+===========
+
+You can either define regex flags {+locally+} in the regex (``r'(?x)foo bar'``) or
+{+globally+} by adding a `flags` attribute to your lexer class.  If no attribute is
+defined, it defaults to `re.MULTILINE`.  For more [-informations-] {+information+} about regular
+expression flags see the {+page about+} `regular expressions`_ [-help page-] in the [-python-] {+Python+}
+documentation.
+
+.. _regular expressions: [-http://docs.python.org/lib/re-syntax.html-] {+http://docs.python.org/library/re.html#regular-expression-syntax+}
+
+
+Scanning multiple tokens at once
+================================
+
+{+So far, the `action` element in the rule tuple of regex, action and state has
+been a single token type.  Now we look at the first of several other possible
+values.+}
+
+Here is a more complex lexer that highlights INI files.  INI files consist of
+sections, comments and [-key-] {+``key+} = [-value pairs:
+
+.. sourcecode:: python-] {+value`` pairs::+}
+
+    from pygments.lexer import RegexLexer, bygroups
+    from pygments.token import *
+
+    class IniLexer(RegexLexer):
+        name = 'INI'
+        aliases = ['ini', 'cfg']
+        filenames = ['*.ini', '*.cfg']
+
+        tokens = {
+            'root': [
+                (r'\s+', Text),
+                (r';.*?$', Comment),
+                (r'\[.*?\]$', Keyword),
+                (r'(.*?)(\s*)(=)(\s*)(.*?)$',
+                 bygroups(Name.Attribute, Text, Operator, Text, String))
+            ]
+        }
+
+The lexer first looks for whitespace, comments and section names. [-And later-]  {+Later+} it
+looks for a line that looks like a key, value pair, separated by an ``'='``
+sign, and optional whitespace.
+
+The `bygroups` helper [-makes sure that-] {+yields+} each {+capturing+} group [-is yielded-] {+in the regex+} with a different
+token type.  First the `Name.Attribute` token, then a `Text` token for the
+optional whitespace, after that a `Operator` token for the equals sign. Then a
+`Text` token for the whitespace again.  The rest of the line is returned as
+`String`.
+
+Note that for this to work, every part of the match must be inside a capturing
+group (a ``(...)``), and there must not be any nested capturing groups.  If you
+nevertheless need a group, use a non-capturing group defined using this syntax:
+[-``r'(?:some|words|here)'``-]
+{+``(?:some|words|here)``+} (note the ``?:`` after the beginning parenthesis).
+
+If you find yourself needing a capturing group inside the regex which shouldn't
+be part of the output but is used in the regular expressions for backreferencing
+(eg: ``r'(<(foo|bar)>)(.*?)(</\2>)'``), you can pass `None` to the bygroups
+function and [-it will skip-] that group will be skipped in the output.
+
+
+Changing states
+===============
+
+Many lexers need multiple states to work as expected.  For example, some
+languages allow multiline comments to be nested.  Since this is a recursive
+pattern it's impossible to lex just using regular expressions.
+
+Here is [-the solution:
+
+.. sourcecode:: python-] {+a lexer that recognizes C++ style comments (multi-line with ``/* */``
+and single-line with ``//`` until end of line)::+}
+
+    from pygments.lexer import RegexLexer
+    from pygments.token import *
+
+    class [-ExampleLexer(RegexLexer):-] {+CppCommentLexer(RegexLexer):+}
+        name = 'Example Lexer with states'
+
+        tokens = {
+            'root': [
+                (r'[^/]+', Text),
+                (r'/\*', Comment.Multiline, 'comment'),
+                (r'//.*?$', Comment.Singleline),
+                (r'/', Text)
+            ],
+            'comment': [
+                (r'[^*/]', Comment.Multiline),
+                (r'/\*', Comment.Multiline, '#push'),
+                (r'\*/', Comment.Multiline, '#pop'),
+                (r'[*/]', Comment.Multiline)
+            ]
+        }
+
+This lexer starts lexing in the ``'root'`` state. It tries to match as much as
+possible until it finds a slash (``'/'``).  If the next character after the slash
+is [-a star-] {+an asterisk+} (``'*'``) the `RegexLexer` sends those two characters to the
+output stream marked as `Comment.Multiline` and continues [-parsing-] {+lexing+} with the rules
+defined in the ``'comment'`` state.
+
+If there wasn't [-a star-] {+an asterisk+} after the slash, the `RegexLexer` checks if it's a
+[-singleline-]
+{+Singleline+} comment [-(eg:-] {+(i.e.+} followed by a second slash).  If this also wasn't the
+case it must be a single [-slash-] {+slash, which is not a comment starter+} (the separate
+regex for a single slash must also be given, else the slash would be marked as
+an error token).
+
+Inside the ``'comment'`` state, we do the same thing again.  Scan until the
+lexer finds a star or slash.  If it's the opening of a multiline comment, push
+the ``'comment'`` state on the stack and continue scanning, again in the
+``'comment'`` state.  Else, check if it's the end of the multiline comment.  If
+yes, pop one state from the stack.
+
+Note: If you pop from an empty stack you'll get an `IndexError`.  (There is an
+easy way to prevent this from happening: don't ``'#pop'`` in the root state).
+
+If the `RegexLexer` encounters a newline that is flagged as an error token, the
+stack is emptied and the lexer continues scanning in the ``'root'`` state.  This
+[-helps-]
+{+can help+} producing error-tolerant highlighting for erroneous input, e.g. when a
+single-line string is not closed.
+
+
+Advanced state tricks
+=====================
+
+There are a few more things you can do with states:
+
+- You can push multiple states onto the stack if you give a tuple instead of a
+  simple string as the third item in a rule tuple.  For example, if you want to
+  match a comment containing a directive, something [-like::-] {+like:
+
+  .. code-block:: text+}
+
+      /* <processing directive>    rest of comment */
+
+  you can use this [-rule:
+
+  .. sourcecode:: python-] {+rule::+}
+
+      tokens = {
+          'root': [
+              (r'/\* <', Comment, ('comment', 'directive')),
+              ...
+          ],
+          'directive': [
+              (r'[^>]*', Comment.Directive),
+              (r'>', Comment, '#pop'),
+          ],
+          'comment': [
+              (r'[^*]+', Comment),
+              (r'\*/', Comment, '#pop'),
+              (r'\*', Comment),
+          ]
+      }
+
+  When this encounters the above sample, first ``'comment'`` and ``'directive'``
+  are pushed onto the stack, then the lexer continues in the directive state
+  until it finds the closing ``>``, then it continues in the comment state until
+  the closing ``*/``.  Then, both states are popped from the stack again and
+  lexing continues in the root state.
+
+  .. versionadded:: 0.9
+     The tuple can contain the special ``'#push'`` and ``'#pop'`` (but not
+     ``'#pop:n'``) directives.
+
+
+- You can include the rules of a state in the definition of another.  This is
+  done by using `include` from [-`pygments.lexer`:
+
+  .. sourcecode:: python-] {+`pygments.lexer`::+}
+
+      from pygments.lexer import RegexLexer, bygroups, include
+      from pygments.token import *
+
+      class ExampleLexer(RegexLexer):
+          tokens = {
+              'comments': [
+                  (r'/\*.*?\*/', Comment),
+                  (r'//.*?\n', Comment),
+              ],
+              'root': [
+                  include('comments'),
+                  (r'(function )(\w+)( {)',
+                   bygroups(Keyword, Name, Keyword), 'function'),
+                  (r'.', Text),
+              ],
+              'function': [
+                  (r'[^}/]+', Text),
+                  include('comments'),
+                  (r'/', Text),
+                  [-(r'}',-]
+                  {+(r'\}',+} Keyword, '#pop'),
+              ]
+          }
+
+  This is a hypothetical lexer for a language that consist of functions and
+  comments.  Because comments can occur at toplevel and in functions, we need
+  rules for comments in both states.  As you can see, the `include` helper saves
+  repeating rules that occur more than once (in this example, the state
+  ``'comment'`` will never be entered by the lexer, as it's only there to be
+  included in ``'root'`` and ``'function'``).
+
+- Sometimes, you may want to "combine" a state from existing ones.  This is
+  possible with the [-`combine`-] {+`combined`+} helper from `pygments.lexer`.
+
+  If you, instead of a new state, write ``combined('state1', 'state2')`` as the
+  third item of a rule tuple, a new anonymous state will be formed from state1
+  and state2 and if the rule matches, the lexer will enter this state.
+
+  This is not used very often, but can be helpful in some cases, such as the
+  `PythonLexer`'s string literal processing.
+
+- If you want your lexer to start lexing in a different state you can modify the
+  stack by [-overloading-] {+overriding+} the `get_tokens_unprocessed()` [-method:
+
+  .. sourcecode:: python-] {+method::+}
+
+      from pygments.lexer import RegexLexer
+
+      class [-MyLexer(RegexLexer):-] {+ExampleLexer(RegexLexer):+}
+          tokens = {...}
+
+          def get_tokens_unprocessed(self, [-text):
+              stack = ['root', 'otherstate']-] {+text, stack=('root', 'otherstate')):+}
+              for item in RegexLexer.get_tokens_unprocessed(text, stack):
+                  yield item
+
+  Some lexers like the `PhpLexer` use this to make the leading ``<?php``
+  preprocessor comments optional.  Note that you can crash the lexer easily by
+  putting values into the stack that don't exist in the token map.  Also
+  removing ``'root'`` from the stack can result in strange errors!
+
+- [-An-] {+In some lexers, a state should be popped if anything is encountered that isn't
+  matched by a rule in the state.  You could use an+} empty regex at the end of [-a-]
+  {+the+} state list, [-combined with ``'#pop'``, can
+  act as-] {+but Pygments provides+} a [-return point-] {+more obvious way of spelling that:
+  ``default('#pop')`` is equivalent to ``('', Text, '#pop')``.
+
+  .. versionadded:: 2.0
+
+
+Subclassing lexers derived+} from {+RegexLexer
+==========================================
+
+.. versionadded:: 1.6
+
+Sometimes multiple languages are very similar, but should still be lexed by
+different lexer classes.
+
+When subclassing+} a {+lexer derived from RegexLexer, the ``tokens`` dictionaries
+defined in the parent and child class are merged.  For example::
+
+      from pygments.lexer import RegexLexer, inherit
+      from pygments.token import *
+
+      class BaseLexer(RegexLexer):
+          tokens = {
+              'root': [
+                  ('[a-z]+', Name),
+                  (r'/\*', Comment, 'comment'),
+                  ('"', String, 'string'),
+                  ('\s+', Text),
+              ],
+              'string': [
+                  ('[^"]+', String),
+                  ('"', String, '#pop'),
+              ],
+              'comment': [
+                  ...
+              ],
+          }
+
+      class DerivedLexer(BaseLexer):
+          tokens = {
+              'root': [
+                  ('[0-9]+', Number),
+                  inherit,
+              ],
+              'string': [
+                  (r'[^"\\]+', String),
+                  (r'\\.', String.Escape),
+                  ('"', String, '#pop'),
+              ],
+          }
+
+The `BaseLexer` defines two states, lexing names and strings.  The
+`DerivedLexer` defines its own tokens dictionary, which extends the definitions
+of the base lexer:
+
+* The "root"+} state {+has an additional rule and then the special object `inherit`,
+  which tells Pygments to insert the token definitions of the parent class at+}
+  that [-doesn't have a clear end marker.-] {+point.
+
+* The "string" state is replaced entirely, since there is not `inherit` rule.
+
+* The "comment" state is inherited entirely.+}
+
+
+Using multiple lexers
+=====================
+
+Using multiple lexers for the same input can be tricky.  One of the easiest
+combination techniques is shown here: You can replace the [-token type-] {+action+} entry in a rule
+tuple [-(the second item)-] with a lexer class.  The matched text will then be lexed with that lexer,
+and the resulting tokens will be yielded.
+
+For example, look at this stripped-down HTML [-lexer:
+
+.. sourcecode:: python-] {+lexer::+}
+
+    from pygments.lexer import RegexLexer, bygroups, using
+    from pygments.token import *
+    from [-pygments.lexers.web-] {+pygments.lexers.javascript+} import JavascriptLexer
+
+    class HtmlLexer(RegexLexer):
+        name = 'HTML'
+        aliases = ['html']
+        filenames = ['*.html', '*.htm']
+
+        flags = re.IGNORECASE | re.DOTALL
+        tokens = {
+            'root': [
+                ('[^<&]+', Text),
+                ('&.*?;', Name.Entity),
+                (r'<\s*script\s*', Name.Tag, ('script-content', 'tag')),
+                (r'<\s*[a-zA-Z0-9:]+', Name.Tag, 'tag'),
+                (r'<\s*/\s*[a-zA-Z0-9:]+\s*>', Name.Tag),
+            ],
+            'script-content': [
+                (r'(.+?)(<\s*/\s*script\s*>)',
+                 bygroups(using(JavascriptLexer), Name.Tag),
+                 '#pop'),
+            ]
+        }
+
+Here the content of a ``<script>`` tag is passed to a newly created instance of
+a `JavascriptLexer` and not processed by the `HtmlLexer`.  This is done using
+the `using` helper that takes the other lexer class as its parameter.
+
+Note the combination of `bygroups` and `using`.  This makes sure that the
+content up to the ``</script>`` end tag is processed by the `JavascriptLexer`,
+while the end tag is yielded as a normal token with the `Name.Tag` type.
+
+[-As an additional goodie, if the lexer class is replaced by `this` (imported from
+`pygments.lexer`), the "other" lexer will be the current one (because you cannot
+refer to the current class within the code that runs at class definition time).-]
+
+Also note the ``(r'<\s*script\s*', Name.Tag, ('script-content', 'tag'))`` rule.
+Here, two states are pushed onto the state stack, ``'script-content'`` and
+``'tag'``.  That means that first ``'tag'`` is processed, which will [-parse-] {+lex+}
+attributes and the closing ``>``, then the ``'tag'`` state is popped and the
+next state on top of the stack will be ``'script-content'``.
+
+{+Since you cannot refer to the class currently being defined, use `this`
+(imported from `pygments.lexer`) to refer to the current lexer class, i.e.
+``using(this)``.  This construct may seem unnecessary, but this is often the
+most obvious way of lexing arbitrary syntax between fixed delimiters without
+introducing deeply nested states.+}
+
+The `using()` helper has a special keyword argument, `state`, which works as
+follows: if given, the lexer to use initially is not in the ``"root"`` state,
+but in the state given by this argument.  This [-*only* works-] {+does not work+} with [-a `RegexLexer`.-] {+advanced
+`RegexLexer` subclasses such as `ExtendedRegexLexer` (see below).+}
+
+Any other keywords arguments passed to `using()` are added to the keyword
+arguments used to create the lexer.
+
+
+Delegating Lexer
+================
+
+Another approach for nested lexers is the `DelegatingLexer` which is for example
+used for the template engine lexers.  It takes two lexers as arguments on
+initialisation: a `root_lexer` and a `language_lexer`.
+
+The input is processed as follows: First, the whole text is lexed with the
+`language_lexer`.  All tokens yielded with [-a-] {+the special+} type of ``Other`` are
+then concatenated and given to the `root_lexer`.  The language tokens of the
+`language_lexer` are then inserted into the `root_lexer`'s token stream at the
+appropriate positions.
+
+[-.. sourcecode:: python-] {+::+}
+
+    from pygments.lexer import DelegatingLexer
+    from pygments.lexers.web import HtmlLexer, PhpLexer
+
+    class HtmlPhpLexer(DelegatingLexer):
+        def __init__(self, **options):
+            super(HtmlPhpLexer, self).__init__(HtmlLexer, PhpLexer, **options)
+
+This procedure ensures that e.g. HTML with template tags in it is highlighted
+correctly even if the template tags are put into HTML tags or attributes.
+
+If you want to change the needle token ``Other`` to something else, you can give
+the lexer another token type as the third [-parameter:
+
+.. sourcecode:: python-] {+parameter::+}
+
+    DelegatingLexer.__init__(MyLexer, OtherLexer, Text, **options)
+
+
+Callbacks
+=========
+
+Sometimes the grammar of a language is so complex that a lexer would be unable
+to [-parse-] {+process+} it just by using regular expressions and stacks.
+
+For this, the `RegexLexer` allows callbacks to be given in rule tuples, instead
+of token types (`bygroups` and `using` are nothing else but preimplemented
+callbacks).  The callback must be a function taking two arguments:
+
+* the lexer itself
+* the match object for the last matched rule
+
+The callback must then return an iterable of (or simply yield) ``(index,
+tokentype, value)`` tuples, which are then just passed through by
+`get_tokens_unprocessed()`.  The ``index`` here is the position of the token in
+the input string, ``tokentype`` is the normal token type (like `Name.Builtin`),
+and ``value`` the associated part of the input string.
+
+You can see an example [-here:
+
+.. sourcecode:: python-] {+here::+}
+
+    from pygments.lexer import RegexLexer
+    from pygments.token import Generic
+
+    class HypotheticLexer(RegexLexer):
+
+        def headline_callback(lexer, match):
+            equal_signs = match.group(1)
+            text = match.group(2)
+            yield match.start(), Generic.Headline, equal_signs + text + equal_signs
+
+        tokens = {
+            'root': [
+                (r'(=+)(.*?)(\1)', headline_callback)
+            ]
+        }
+
+If the regex for the `headline_callback` matches, the function is called with
+the match object.  Note that after the callback is done, processing continues
+normally, that is, after the end of the previous match.  The callback has no
+possibility to influence the position.
+
+There are not really any simple examples for lexer callbacks, but you can see
+them in action e.g. in the [-`compiled.py`_ source code-] {+`SMLLexer` class+} in [-the `CLexer` and
+`JavaLexer` classes.-] {+`ml.py`_.+}
+
+.. [-_compiled.py: http://bitbucket.org/birkenfeld/pygments-main/src/tip/pygments/lexers/compiled.py-] {+_ml.py: http://bitbucket.org/birkenfeld/pygments-main/src/tip/pygments/lexers/ml.py+}
+
+
+The ExtendedRegexLexer class
+============================
+
+The `RegexLexer`, even with callbacks, unfortunately isn't powerful enough for
+the funky syntax rules of [-some-] languages [-that will go unnamed,-] such as Ruby.
+
+But fear not; even then you don't have to abandon the regular expression
+[-approach. For-]
+{+approach:+} Pygments has a subclass of `RegexLexer`, the `ExtendedRegexLexer`.
+All features known from RegexLexers are available here too, and the tokens are
+specified in exactly the same way, *except* for one detail:
+
+The `get_tokens_unprocessed()` method holds its internal state data not as local
+variables, but in an instance of the `pygments.lexer.LexerContext` class, and
+that instance is passed to callbacks as a third argument. This means that you
+can modify the lexer state in callbacks.
+
+The `LexerContext` class has the following members:
+
+* `text` -- the input text
+* `pos` -- the current starting position that is used for matching regexes
+* `stack` -- a list containing the state stack
+* `end` -- the maximum position to which regexes are matched, this defaults to
+  the length of `text`
+
+Additionally, the `get_tokens_unprocessed()` method can be given a
+`LexerContext` instead of a string and will then process this context instead of
+creating a new one for the string argument.
+
+Note that because you can set the current position to anything in the callback,
+it won't be automatically be set by the caller after the callback is finished.
+For example, this is how the hypothetical lexer above would be written with the
+[-`ExtendedRegexLexer`:
+
+.. sourcecode:: python-]
+{+`ExtendedRegexLexer`::+}
+
+    from pygments.lexer import ExtendedRegexLexer
+    from pygments.token import Generic
+
+    class ExHypotheticLexer(ExtendedRegexLexer):
+
+        def headline_callback(lexer, match, ctx):
+            equal_signs = match.group(1)
+            text = match.group(2)
+            yield match.start(), Generic.Headline, equal_signs + text + equal_signs
+            ctx.pos = match.end()
+
+        tokens = {
+            'root': [
+                (r'(=+)(.*?)(\1)', headline_callback)
+            ]
+        }
+
+This might sound confusing (and it can really be). But it is needed, and for an
+example look at the Ruby lexer in [-`agile.py`_.-] {+`ruby.py`_.+}
+
+.. [-_agile.py: https://bitbucket.org/birkenfeld/pygments-main/src/tip/pygments/lexers/agile.py
+
+
+Filtering-] {+_ruby.py: https://bitbucket.org/birkenfeld/pygments-main/src/tip/pygments/lexers/ruby.py
+
+
+Handling Lists of Keywords
+==========================
+
+For a relatively short list (hundreds) you can construct an optimized regular
+expression directly using ``words()`` (longer lists, see next section).  This
+function handles a few things for you automatically, including escaping
+metacharacters and Python's first-match rather than longest-match in
+alternations.  Feel free to put the lists themselves in
+``pygments/lexers/_$lang_builtins.py`` (see examples there), and generated by
+code if possible.
+
+An example of using ``words()`` is something like::
+
+    from pygments.lexer import RegexLexer, words, Name
+
+    class MyLexer(RegexLexer):
+
+        tokens = {
+            'root': [
+                (words(('else', 'elseif'), suffix=r'\b'), Name.Builtin),
+                (r'\w+', Name),
+            ],
+        }
+
+As you can see, you can add ``prefix`` and ``suffix`` parts to the constructed
+regex.
+
+
+Modifying+} Token Streams
+=======================
+
+Some languages ship a lot of builtin functions (for example PHP).  The total
+amount of those functions differs from system to system because not everybody
+has every extension installed.  In the case of PHP there are over 3000 builtin
+functions.  That's an [-incredible-] {+incredibly+} huge amount of functions, much more than you
+[-can-]
+{+want to+} put into a regular expression.
+
+But because only `Name` tokens can be function names [-it's-] {+this is+} solvable by
+overriding the ``get_tokens_unprocessed()`` method.  The following lexer
+subclasses the `PythonLexer` so that it highlights some additional names as
+pseudo [-keywords:
+
+.. sourcecode:: python-] {+keywords::+}
+
+    from [-pygments.lexers.agile-] {+pygments.lexers.python+} import PythonLexer
+    from pygments.token import Name, Keyword
+
+    class MyPythonLexer(PythonLexer):
+        EXTRA_KEYWORDS = [-['foo',-] {+set(('foo',+} 'bar', 'foobar', 'barfoo', 'spam', [-'eggs']-] {+'eggs'))+}
+
+        def get_tokens_unprocessed(self, text):
+            for index, token, value in PythonLexer.get_tokens_unprocessed(self, text):
+                if token is Name and value in self.EXTRA_KEYWORDS:
+                    yield index, Keyword.Pseudo, value
+                else:
+                    yield index, token, value
+
+The `PhpLexer` and `LuaLexer` use this method to resolve builtin functions.
+
+[-.. note:: Do not confuse this with the :doc:`filter <filters>` system.-]
diff --git a/tests/examplefiles/wdiff_example3.wdiff b/tests/examplefiles/wdiff_example3.wdiff
new file mode 100644
index 00000000..0bbd6d65
--- /dev/null
+++ b/tests/examplefiles/wdiff_example3.wdiff
@@ -0,0 +1,10 @@
+This example is unbalanced open-close.
+We can't treat these easily.
+
+{+ added? -]
+[- deleted? +}
+
+suddenly closed -]
+suddenly closed +}
+
+{+ added? [- deleted?