[svn] Added JSP and Batchfile lexers by Tim Hatch.

16 files changed, 212 insertions, 39 deletions

diff --git a/CHANGES b/CHANGES
index b2ae0f2d..b45f1cf6 100644
--- a/CHANGES
+++ b/CHANGES
@@ -5,6 +5,10 @@ Version 0.7
 -----------
 (codename to be selected, released Feb XX, 2007)
 
+- Added Java Server Pages lexer, thanks to Tim Hatch.
+
+- Added Windows Batchfile lexer, thanks to Tim Hatch.
+
 - Added Trac Wiki markup lexer, thanks to Tim Hatch.
 
 - Added Python traceback lexer, thanks to Tim Hatch.
diff --git a/TODO b/TODO
index 0df3fa44..53eaf8a8 100644
--- a/TODO
+++ b/TODO
@@ -6,7 +6,6 @@ for 0.7
 
 - new lexers:
   * Haskell
-  * JSP
   * (Q)BASIC
   * Lisp
   * IPython sessions
@@ -14,7 +13,6 @@ for 0.7
   * LaTeX special formatting?
   * OCaml
   * Nemerle
-  * Windows batch files
   * Assembler
   * Objective C
   * MySQL/PostgreSQL/SQLite
@@ -27,7 +25,6 @@ for 0.7
     backtrack to death...
   * add support for function name highlighting to C++ lexer
 
-
 - automatically get help for lexers/formatters/options from docstrings
 
 - a MoinMoin parser
diff --git a/pygments/formatters/html.py b/pygments/formatters/html.py
index d323c781..cc2a4c19 100644
--- a/pygments/formatters/html.py
+++ b/pygments/formatters/html.py
@@ -167,7 +167,7 @@ class HtmlFormatter(Formatter):
     Additional options accepted:
 
     `nowrap`
-        If set to ``True``, don't wrap the tokens at all, not even in a ``<pre>``
+        If set to ``True``, don't wrap the tokens at all, not even inside a ``<pre>``
         tag. This disables all other options (default: ``False``).
 
     `noclasses`
diff --git a/pygments/formatters/latex.py b/pygments/formatters/latex.py
index d8bdb8a3..69b67a9d 100644
--- a/pygments/formatters/latex.py
+++ b/pygments/formatters/latex.py
@@ -70,7 +70,7 @@ class LatexFormatter(Formatter):
     containing ``\newcommand`` commands defining the commands used inside the
     ``Verbatim`` environments. If the argument `arg` is true,
     ``\renewcommand`` is used instead.
-    
+
     Additional options accepted:
 
     `docclass`
@@ -84,7 +84,7 @@ class LatexFormatter(Formatter):
     `verboptions`
         Additional options given to the Verbatim environment (see the *fancyvrb*
         docs for possible values) (default: ``''``).
-    
+
     """
 
     def __init__(self, **options):
diff --git a/pygments/formatters/rtf.py b/pygments/formatters/rtf.py
index 9bfed9d8..466c555b 100644
--- a/pygments/formatters/rtf.py
+++ b/pygments/formatters/rtf.py
@@ -20,7 +20,7 @@ class RtfFormatter(Formatter):
     Formats tokens as RTF markup. This formatter automatically outputs full RTF
     documents with color information and other useful stuff. Perfect for Copy and
     Paste into Microsoft® Word® documents.
-    
+
     *New in Pygments 0.6.*
 
     Additional options accepted:
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index 0ee8a0e0..b41aba03 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -17,6 +17,7 @@ LEXERS = {
     'ApacheConfLexer': ('pygments.lexers.text', 'ApacheConf', ('apacheconf', 'aconf', 'apache'), ('.htaccess', 'apache.conf', 'apache2.conf'), ()),
     'BBCodeLexer': ('pygments.lexers.text', 'BBCode', ('bbcode',), (), ()),
     'BashLexer': ('pygments.lexers.other', 'Bash', ('bash', 'sh'), ('*.sh',), ('application/x-sh', 'application/x-shellscript')),
+    'BatchLexer': ('pygments.lexers.other', 'Batchfile', ('bat',), ('*.bat', '*.cmd'), ('application/x-dos-batch',)),
     'BooLexer': ('pygments.lexers.dotnet', 'Boo', ('boo',), ('*.boo',), ('text/x-boo',)),
     'BrainfuckLexer': ('pygments.lexers.other', 'Brainfuck', ('brainfuck', 'bf'), ('*.bf', '*.b'), ()),
     'CLexer': ('pygments.lexers.compiled', 'C', ('c',), ('*.c', '*.h'), ('text/x-chdr', 'text/x-csrc')),
@@ -49,6 +50,7 @@ LEXERS = {
     'JavascriptLexer': ('pygments.lexers.web', 'JavaScript', ('js', 'javascript'), ('*.js',), ('application/x-javascript', 'text/x-javascript', 'text/javascript')),
     'JavascriptPhpLexer': ('pygments.lexers.templates', 'JavaScript+PHP', ('js+php', 'javascript+php'), (), ()),
     'JavascriptSmartyLexer': ('pygments.lexers.templates', 'JavaScript+Smarty', ('js+smarty', 'javascript+smarty'), (), ()),
+    'JspLexer': ('pygments.lexers.templates', 'Java Server Page', ('jsp',), ('*.jsp',), ()),
     'LuaLexer': ('pygments.lexers.agile', 'Lua', ('lua',), ('*.lua',), ('text/x-lua', 'application/x-lua')),
     'MakefileLexer': ('pygments.lexers.text', 'Makefile', ('make', 'makefile', 'mf'), ('*.mak', 'Makefile', 'makefile'), ('text/x-makefile',)),
     'MakoCssLexer': ('pygments.lexers.templates', 'CSS+Mako', ('css+mako',), (), ()),
diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py
index 5c91ebf9..b4c33f73 100644
--- a/pygments/lexers/agile.py
+++ b/pygments/lexers/agile.py
@@ -34,7 +34,7 @@ class PythonLexer(RegexLexer):
     """
     For `Python <http://www.python.org>`_ source code.
     """
-    
+
     name = 'Python'
     aliases = ['python', 'py']
     filenames = ['*.py', '*.pyw']
@@ -222,7 +222,7 @@ class PythonTracebackLexer(RegexLexer):
 
     *New in Pygments 0.7.*
     """
-    
+
     name = 'PythonTraceback'
     aliases = ['pytb']
     filenames = ['*.pytb']
@@ -618,7 +618,7 @@ class PerlLexer(RegexLexer):
     """
     For `Perl <http://www.perl.org>`_ source code.
     """
-    
+
     name = 'Perl'
     aliases = ['perl', 'pl']
     filenames = ['*.pl', '*.pm']
diff --git a/pygments/lexers/compiled.py b/pygments/lexers/compiled.py
index 36d80d66..6c33b10b 100644
--- a/pygments/lexers/compiled.py
+++ b/pygments/lexers/compiled.py
@@ -689,7 +689,7 @@ class JavaLexer(RegexLexer):
     """
     For `Java <http://www.sun.com/java/>`_ source code.
     """
-    
+
     name = 'Java'
     aliases = ['java']
     filenames = ['*.java']
diff --git a/pygments/lexers/dotnet.py b/pygments/lexers/dotnet.py
index f47532ba..63ae8e6a 100644
--- a/pygments/lexers/dotnet.py
+++ b/pygments/lexers/dotnet.py
@@ -22,7 +22,7 @@ class CSharpLexer(RegexLexer):
     For `C# <http://msdn2.microsoft.com/en-us/vcsharp/default.aspx>`_
     source code.
     """
-    
+
     name = 'C#'
     aliases = ['csharp', 'c#']
     filenames = ['*.cs']
@@ -83,7 +83,7 @@ class BooLexer(RegexLexer):
     """
     For `Boo <http://boo.codehaus.org/>`_ source code.
     """
-    
+
     name = 'Boo'
     aliases = ['boo']
     filenames = ['*.boo']
@@ -152,7 +152,7 @@ class VbNetLexer(RegexLexer):
     `Visual Basic.NET <http://msdn2.microsoft.com/en-us/vbasic/default.aspx>`_
     source code.
     """
-    
+
     name = 'VB.net'
     aliases = ['vb.net', 'vbnet']
     filenames = ['*.vb', '*.bas']
diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py
index cec162b4..37132e4f 100644
--- a/pygments/lexers/other.py
+++ b/pygments/lexers/other.py
@@ -17,7 +17,7 @@ from pygments.token import Error, Punctuation, \
 from pygments.util import shebang_matches
 
 
-__all__ = ['SqlLexer', 'BrainfuckLexer', 'BashLexer']
+__all__ = ['SqlLexer', 'BrainfuckLexer', 'BashLexer', 'BatchLexer']
 
 
 class SqlLexer(RegexLexer):
@@ -171,7 +171,7 @@ class BashLexer(RegexLexer):
 
     *New in Pygments 0.6.*
     """
-    
+
     name = 'Bash'
     aliases = ['bash', 'sh']
     filenames = ['*.sh']
@@ -218,3 +218,58 @@ class BashLexer(RegexLexer):
 
     def analyse_text(text):
         return shebang_matches(text, r'(ba|z|)sh')
+
+
+class BatchLexer(RegexLexer):
+    """
+    Lexer for the DOS/Windows Batch file format.
+
+    *New in Pygments 0.7.*
+    """
+    name = 'Batchfile'
+    aliases = ['bat']
+    filenames = ['*.bat', '*.cmd']
+    mimetypes = ['application/x-dos-batch']
+
+    flags = re.MULTILINE | re.IGNORECASE
+
+    tokens = {
+        'root': [
+            # Lines can start with @ to prevent echo
+            (r'^\s*@', Punctuation),
+            (r'".*?"', String.Double),
+            (r"'.*?'", String.Single),
+            # If made more specific, make sure you still allow expansions
+            # like %~$VAR:zlt
+            (r'%%?[~$:\w]+%?', Name.Variable),
+            (r'(::|rem).*', Comment), # Technically :: only works at BOL
+            (r'(set)(\s+)(\w+)', bygroups(Keyword, Text, Name.Variable)),
+            (r'(call)(\s+)(:\w+)', bygroups(Keyword, Text, Name.Label)),
+            (r'(goto)(\s+)(\w+)', bygroups(Keyword, Text, Name.Label)),
+            (r'\b(set|call|echo|on|off|endlocal|for|do|goto|if|pause|rem|'
+             r'setlocal|shift|errorlevel|exist|defined|cmdextversion|'
+             r'errorlevel|else|cd|md|del|deltree|cls|choice)\b', Keyword),
+            (r'equ|neq|lss|leq|gtr|geq', Operator),
+            include('basic'),
+            (r'.', Text),
+        ],
+        'echo': [
+            # Escapes only valid within echo args?
+            (r'\^\^|\^<|\^>|\^\|', String.Escape),
+            (r'\n', Text, '#pop'),
+            include('basic'),
+            (r'[^\'"^]+', Text),
+        ],
+        'basic': [
+            (r'".*?"', String.Double),
+            (r"'.*?'", String.Single),
+            (r'`.*?`', String.Backtick),
+            (r'-?\d+', Number),
+            (r',', Punctuation),
+            (r'=', Operator),
+            (r'/\S+', Name),
+            (r':\w+', Name.Label),
+            (r'\w:\w+', Text),
+            (r'([<>|])(\s*)(\w+)', bygroups(Punctuation, Text, Name)),
+        ],
+    }
diff --git a/pygments/lexers/templates.py b/pygments/lexers/templates.py
index 7c8c356d..5b6d5e0e 100644
--- a/pygments/lexers/templates.py
+++ b/pygments/lexers/templates.py
@@ -19,6 +19,7 @@ except NameError:
 from pygments.lexers.web import \
      PhpLexer, HtmlLexer, XmlLexer, JavascriptLexer, CssLexer
 from pygments.lexers.agile import PythonLexer
+from pygments.lexers.compiled import JavaLexer
 from pygments.lexer import Lexer, DelegatingLexer, RegexLexer, bygroups, \
      include, using, this
 from pygments.token import Error, Punctuation, \
@@ -36,7 +37,7 @@ __all__ = ['HtmlPhpLexer', 'XmlPhpLexer', 'CssPhpLexer',
            'MyghtyLexer', 'MyghtyHtmlLexer', 'MyghtyXmlLexer',
            'MyghtyCssLexer', 'MyghtyJavascriptLexer', 'MakoLexer',
            'MakoHtmlLexer', 'MakoXmlLexer', 'MakoJavascriptLexer',
-           'MakoCssLexer']
+           'MakoCssLexer', 'JspLexer']
 
 
 class ErbLexer(Lexer):
@@ -464,7 +465,7 @@ class MakoJavascriptLexer(DelegatingLexer):
 
     *New in Pygments 0.7.*
     """
-    
+
     name = 'JavaScript+Mako'
     aliases = ['js+mako', 'javascript+mako']
 
@@ -529,7 +530,7 @@ class GenshiMarkupLexer(RegexLexer):
     Base lexer for Genshi markup, used by `HtmlGenshiLexer` and
     `GenshiLexer`.
     """
-    
+
     flags = re.DOTALL
 
     tokens = {
@@ -678,7 +679,7 @@ class RhtmlLexer(DelegatingLexer):
 
     Nested Javascript and CSS is highlighted too.
     """
-    
+
     name = 'RHTML'
     aliases = ['rhtml', 'html+erb', 'html+ruby']
     filenames = ['*.rhtml']
@@ -700,7 +701,7 @@ class XmlErbLexer(DelegatingLexer):
     Subclass of `ErbLexer` which highlights data outside preprocessor
     directives with the `XmlLexer`.
     """
-    
+
     name = 'XML+Ruby'
     aliases = ['xml+erb', 'xml+ruby']
     alias_filenames = ['*.xml']
@@ -719,7 +720,7 @@ class CssErbLexer(DelegatingLexer):
     """
     Subclass of `ErbLexer` which highlights unlexed data with the `CssLexer`.
     """
-    
+
     name = 'CSS+Ruby'
     aliases = ['css+erb', 'css+ruby']
     alias_filenames = ['*.xml']
@@ -755,7 +756,7 @@ class HtmlPhpLexer(DelegatingLexer):
 
     Nested Javascript and CSS is highlighted too.
     """
-    
+
     name = 'HTML+PHP'
     aliases = ['html+php']
     filenames = ['*.phtml']
@@ -779,7 +780,7 @@ class XmlPhpLexer(DelegatingLexer):
     """
     Subclass of `PhpLexer` that higlights unhandled data with the `XmlLexer`.
     """
-    
+
     name = 'XML+PHP'
     aliases = ['xml+php']
     alias_filenames = ['*.xml', '*.php', '*.php[345]']
@@ -798,7 +799,7 @@ class CssPhpLexer(DelegatingLexer):
     """
     Subclass of `PhpLexer` which highlights unmatched data with the `CssLexer`.
     """
-    
+
     name = 'CSS+PHP'
     aliases = ['css+php']
     alias_filenames = ['*.css']
@@ -855,7 +856,7 @@ class XmlSmartyLexer(DelegatingLexer):
     Subclass of the `SmartyLexer` that highlights unlexed data with the
     `XmlLexer`.
     """
-    
+
     name = 'XML+Smarty'
     aliases = ['xml+smarty']
     alias_filenames = ['*.xml', '*.tpl']
@@ -952,7 +953,7 @@ class CssDjangoLexer(DelegatingLexer):
     Subclass of the `DjangoLexer` that highlights unlexed data with the
     `CssLexer`.
     """
-    
+
     name = 'CSS+Django/Jinja'
     aliases = ['css+django', 'css+jinja']
     alias_filenames = ['*.css']
@@ -981,3 +982,47 @@ class JavascriptDjangoLexer(DelegatingLexer):
 
     def analyse_text(text):
         return DjangoLexer.analyse_text(text) - 0.05
+
+class JspRootLexer(RegexLexer):
+    """
+    Base for the `JspLexer`. Yields `Token.Other` for area outside of
+    JSP tags.
+
+    *New in Pygments 0.7.*
+    """
+
+    tokens = {
+        'root': [
+            (r'<%\S?', Keyword, 'sec'),
+            # FIXME: I want to make these keywords but still parse attributes.
+            (r'</?jsp:(forward|getProperty|include|plugin|setProperty|useBean).*?>',
+             Keyword),
+            (r'[^<]+', Other),
+            (r'<', Other),
+        ],
+        'sec': [
+            (r'%>', Keyword, '#pop'),
+            (r'[\w\W]+?(?=%>|\Z)', using(JavaLexer)),
+        ],
+    }
+
+class JspLexer(DelegatingLexer):
+    """
+    Lexer for Java Server Pages.
+
+    *New in Pygments 0.7.*
+    """
+    name = 'Java Server Page'
+    aliases = ['jsp']
+    filenames = ['*.jsp']
+
+    def __init__(self, **options):
+        super(JspLexer, self).__init__(XmlLexer, JspRootLexer, **options)
+
+    def analyse_text(text):
+        rv = JavaLexer.analyse_text(text) - 0.01
+        if looks_like_xml(text):
+            rv += 0.4
+        if '<%' in text and '%>' in text:
+            rv += 0.1
+        return rv
diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py
index ba03ff01..29f569aa 100644
--- a/pygments/lexers/text.py
+++ b/pygments/lexers/text.py
@@ -60,7 +60,7 @@ class SourcesListLexer(RegexLexer):
 
     *New in Pygments 0.7.*
     """
-    
+
     name= 'Debian Sourcelist'
     aliases = ['sourceslist', 'sources.list']
     filenames = ['sources.list']
@@ -107,7 +107,7 @@ class MakefileLexer(RegexLexer):
     """
     Lexer for Makefiles.
     """
-    
+
     name = 'Makefile'
     aliases = ['make', 'makefile', 'mf']
     filenames = ['*.mak', 'Makefile', 'makefile']
@@ -154,7 +154,7 @@ class DiffLexer(RegexLexer):
     """
     Lexer for unified or context-style diffs or patches.
     """
-    
+
     name = 'Diff'
     aliases = ['diff']
     filenames = ['*.diff', '*.patch']
@@ -186,7 +186,7 @@ class IrcLogsLexer(RegexLexer):
     """
     Lexer for IRC logs in **irssi** or **xchat** style.
     """
-    
+
     name = 'IRC logs'
     aliases = ['irc']
 
@@ -232,7 +232,7 @@ class BBCodeLexer(RegexLexer):
 
     *New in Pygments 0.6.*
     """
-    
+
     name = 'BBCode'
     aliases = ['bbcode']
 
@@ -251,7 +251,7 @@ class TexLexer(RegexLexer):
     """
     Lexer for the TeX and LaTeX typesetting languages.
     """
-    
+
     name = 'TeX'
     aliases = ['tex', 'latex']
     filenames = ['*.tex', '*.aux', '*.toc']
@@ -366,7 +366,7 @@ class ApacheConfLexer(RegexLexer):
 
     *New in Pygments 0.6.*
     """
-    
+
     name = 'ApacheConf'
     aliases = ['apacheconf', 'aconf', 'apache']
     filenames = ['.htaccess', 'apache.conf', 'apache2.conf']
diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py
index bbd6d76e..ef480894 100644
--- a/pygments/lexers/web.py
+++ b/pygments/lexers/web.py
@@ -31,7 +31,7 @@ class JavascriptLexer(RegexLexer):
     """
     For JavaScript source code.
     """
-    
+
     name = 'JavaScript'
     aliases = ['js', 'javascript']
     filenames = ['*.js']
@@ -68,7 +68,7 @@ class CssLexer(RegexLexer):
     """
     For CSS (Cascading Style Sheets).
     """
-    
+
     name = 'CSS'
     aliases = ['css']
     filenames = ['*.css']
@@ -202,7 +202,7 @@ class HtmlLexer(RegexLexer):
     For HTML 4 and XHTML 1 markup. Nested JavaScript and CSS is highlighted
     by the appropriate lexer.
     """
-    
+
     name = 'HTML'
     aliases = ['html']
     filenames = ['*.html', '*.htm', '*.xhtml']
@@ -397,7 +397,7 @@ class XmlLexer(RegexLexer):
     """
     Generic lexer for XML (eXtensible Markup Language).
     """
-    
+
     flags = re.MULTILINE | re.DOTALL
 
     name = 'XML'
diff --git a/tests/examplefiles/batchfile.bat b/tests/examplefiles/batchfile.bat
new file mode 100644
index 00000000..49a53cec
--- /dev/null
+++ b/tests/examplefiles/batchfile.bat
@@ -0,0 +1,46 @@
+rem this is a demo file.
+@rem
+@echo off
+
+call c:\temp.bat somearg
+call :lab somearg
+rem This next one is wrong in the vim lexer!
+call c:temp.bat
+
+echo "Hi!"
+echo hi
+echo on
+echo off
+echo.
+@echo off
+if exist *.log echo The log file has arrived.
+rem These are all escapes, also done incorrectly by the vim lexer
+echo ^^ ^> ^< ^|
+
+x=beginning
+setlocal
+x = new text
+endlocal
+
+for %%var in (*.jpg) do echo %%var
+for /D %%var in (a b c) do echo %%var
+for /R C:\temp %%var in (*.jpg) do iexplore.exe %%var
+rem Vim has this one wrong too.
+for /L %%var in (10,-1,1) do echo %%var
+for /F %%var in ("hi!") do echo %%var
+for /F "eol=c,skip=1,usebackq" %%var in (`command`) do echo %%var %~l %~fl %~dl %~pl %~nl %~xl %~sl %~al %~tl %~zl %~$PATH:l %~dpl %~dp$PATH:l %~ftzal
+
+echo some file ?! > somefile.txt
+
+set PATH=%PATH%;c:\windows
+
+goto answer%errorlevel%
+    :answer0
+    echo Hi it's zero
+    :answer1
+    echo New
+
+if exist a del a
+else echo A is missing!
+
+
diff --git a/tests/examplefiles/test.jsp b/tests/examplefiles/test.jsp
new file mode 100644
index 00000000..1c6664da
--- /dev/null
+++ b/tests/examplefiles/test.jsp
@@ -0,0 +1,24 @@
+<!-- This page was loaded on <%= (new java.util.Date()).toLocaleString() %> -->
+<%= var x = 1;
+%>
+<%! int i = 0; %>
+<%! int a, b, c; %>
+<%! Circle a = new Circle(2.0); %>
+
+<%
+      String name = null;
+      if (request.getParameter("name") == null) {
+%>
+<%@ include file="error.html" %>
+<%
+      } else {
+      foo.setName(request.getParameter("name"));
+      if (foo.getName().equalsIgnoreCase("integra"))
+      name = "acura";
+      if (name.equalsIgnoreCase( "acura" )) {
+%>
+
+<jsp:useBean id="calendar" scope="page" class="employee.Calendar" />
+<h2>
+Calendar of <jsp:getProperty name="calendar" property="username" />
+</h2>
diff --git a/tests/run.py b/tests/run.py
index 590ae8df..d2599331 100644
--- a/tests/run.py
+++ b/tests/run.py
@@ -71,7 +71,7 @@ def run_tests():
                  if (entry.startswith('test_') and entry.endswith('.py'))]
         files.sort()
 
-    WIDTH = 60
+    WIDTH = 70
 
     print >>sys.stderr, 'Pygments Test Suite running, stand by...'.center(WIDTH)
     print >>sys.stderr, ('(using Python %s)' % sys.version.split()[0]).center(WIDTH)