Add Smalltalk lexer, #300.

4 files changed, 82 insertions, 4 deletions

diff --git a/pygments/formatters/_mapping.py b/pygments/formatters/_mapping.py
index e2ed1a83..776bc4d3 100755
--- a/pygments/formatters/_mapping.py
+++ b/pygments/formatters/_mapping.py
@@ -33,7 +33,7 @@ FORMATTERS = {
     NullFormatter: ('Text only', ('text', 'null'), ('*.txt',), 'Output the text unchanged without any formatting.'),
     RawTokenFormatter: ('Raw tokens', ('raw', 'tokens'), ('*.raw',), 'Format tokens as a raw representation for storing token streams.'),
     RtfFormatter: ('RTF', ('rtf',), ('*.rtf',), 'Format 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\xc2\xae Word\xc2\xae documents.'),
-    SvgFormatter: ('SVG', ('svg',), ('*.svg',), 'Format tokens as an SVG graphics file.  This formatter is still experimental.'),
+    SvgFormatter: ('SVG', ('svg',), ('*.svg',), 'Format tokens as an SVG graphics file.  This formatter is still experimental. Each line of code is a ``<text>`` element with explicit ``x`` and ``y`` coordinates containing ``<tspan>`` elements with the individual token styles.'),
     Terminal256Formatter: ('Terminal256', ('terminal256', 'console256', '256'), (), 'Format tokens with ANSI color sequences, for output in a 256-color terminal or console. Like in `TerminalFormatter` color sequences are terminated at newlines, so that paging the output works correctly.'),
     TerminalFormatter: ('Terminal', ('terminal', 'console'), (), 'Format tokens with ANSI color sequences, for output in a text console. Color sequences are terminated at newlines, so that paging the output works correctly.')
 }
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index 26905d9b..38cae698 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -26,7 +26,7 @@ LEXERS = {
     'CObjdumpLexer': ('pygments.lexers.asm', 'c-objdump', ('c-objdump',), ('*.c-objdump',), ('text/x-c-objdump',)),
     'CSharpLexer': ('pygments.lexers.dotnet', 'C#', ('csharp', 'c#'), ('*.cs',), ('text/x-csharp',)),
     'CommonLispLexer': ('pygments.lexers.functional', 'Common Lisp', ('common-lisp', 'cl'), ('*.cl', '*.lisp', '*.el'), ('text/x-common-lisp',)),
-    'CppLexer': ('pygments.lexers.compiled', 'C++', ('cpp', 'c++'), ('*.cpp', '*.hpp', '*.c++', '*.h++'), ('text/x-c++hdr', 'text/x-c++src')),
+    'CppLexer': ('pygments.lexers.compiled', 'C++', ('cpp', 'c++'), ('*.cpp', '*.hpp', '*.c++', '*.h++', '*.cc', '*.hh', '*.cxx', '*.hxx'), ('text/x-c++hdr', 'text/x-c++src')),
     'CppObjdumpLexer': ('pygments.lexers.asm', 'cpp-objdump', ('cpp-objdump', 'c++-objdumb', 'cxx-objdump'), ('*.cpp-objdump', '*.c++-objdump', '*.cxx-objdump'), ('text/x-cpp-objdump',)),
     'CssDjangoLexer': ('pygments.lexers.templates', 'CSS+Django/Jinja', ('css+django', 'css+jinja'), (), ('text/css+django', 'text/css+jinja')),
     'CssErbLexer': ('pygments.lexers.templates', 'CSS+Ruby', ('css+erb', 'css+ruby'), (), ('text/css+ruby',)),
@@ -100,6 +100,7 @@ LEXERS = {
     'RubyConsoleLexer': ('pygments.lexers.agile', 'Ruby irb session', ('rbcon', 'irb'), (), ('text/x-ruby-shellsession',)),
     'RubyLexer': ('pygments.lexers.agile', 'Ruby', ('rb', 'ruby'), ('*.rb', '*.rbw', 'Rakefile', '*.rake', '*.gemspec', '*.rbx'), ('text/x-ruby', 'application/x-ruby')),
     'SchemeLexer': ('pygments.lexers.functional', 'Scheme', ('scheme', 'scm'), ('*.scm',), ('text/x-scheme', 'application/x-scheme')),
+    'SmalltalkLexer': ('pygments.lexers.other', 'Smalltalk', ('smalltalk', 'squeak'), ('*.st',), ('text/x-smalltalk',)),
     'SmartyLexer': ('pygments.lexers.templates', 'Smarty', ('smarty',), ('*.tpl',), ('application/x-smarty',)),
     'SourcesListLexer': ('pygments.lexers.text', 'Debian Sourcelist', ('sourceslist', 'sources.list'), ('sources.list',), ()),
     'SqlLexer': ('pygments.lexers.other', 'SQL', ('sql',), ('*.sql',), ('text/x-sql',)),
diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py
index 6d2ecf20..3598b890 100644
--- a/pygments/lexers/other.py
+++ b/pygments/lexers/other.py
@@ -18,7 +18,8 @@ from pygments.util import shebang_matches
 
 
 __all__ = ['SqlLexer', 'MySqlLexer', 'BrainfuckLexer', 'BashLexer',
-           'BatchLexer', 'BefungeLexer', 'RedcodeLexer', 'MOOCodeLexer']
+           'BatchLexer', 'BefungeLexer', 'RedcodeLexer', 'MOOCodeLexer',
+           'SmalltalkLexer']
 
 
 class SqlLexer(RegexLexer):
@@ -469,3 +470,74 @@ class MOOCodeLexer(RegexLexer):
             (r'([a-zA-Z_0-9]+)', Text),
         ]
     }
+
+class SmalltalkLexer(RegexLexer):
+    """
+    For `Smalltalk <http://www.smalltalk.org/>`_ syntax.
+    Contributed by Stefan Matthias Aust.
+
+    *New in Pygments 1.0.*
+    """
+    name = 'Smalltalk'
+    filenames = ['*.st']
+    aliases = ['smalltalk', 'squeak']
+    mimetypes = ['text/x-smalltalk']
+
+    tokens = {
+        'root' : [
+            # Squeak fileout format (optional)
+            (r'^"[^"]*"!', Keyword),
+            (r"^'[^']*'!", Keyword),
+            (r'^(!)(\w+)( commentStamp: )(.*?)( prior: .*?!\n)(.*?)(!)',
+                bygroups(Keyword, Name.Class, Keyword, String, Keyword, Text, Keyword)),
+            (r'^(!)(\w+(?: class)?)( methodsFor: )(\'[^\']*\')(.*?!)',
+                bygroups(Keyword, Name.Class, Keyword, String, Keyword)),
+            (r'^(\w+)( subclass: )(#\w+)'
+             r'(\s+instanceVariableNames: )(.*?)'
+             r'(\s+classVariableNames: )(.*?)'
+             r'(\s+poolDictionaries: )(.*?)'
+             r'(\s+category: )(.*?)(!)',
+                bygroups(Name.Class, Keyword, String.Symbol, Keyword, String, Keyword,
+                         String, Keyword, String, Keyword, String, Keyword)),
+            (r'^(\w+(?: class)?)(\s+instanceVariableNames: )(.*?)(!)',
+                bygroups(Name.Class, Keyword, String, Keyword)),
+            (r'(!\n)(\].*)(! !)$', bygroups(Keyword, Text, Keyword)),
+            (r'! !$', Keyword),
+            # skip whitespace and comments
+            (r'\s+', Text),
+            (r'"[^"]*"', Comment),
+            # method patterns
+            (r'^(\w+)(\s*:\s*)(\w+\s*)', bygroups(Name.Function, Punctuation,
+                                                  Name.Variable), 'pattern'),
+            (r'^([-+*/\\~<>=|&!?,@%]+\s*)(\w+)', bygroups(Name.Function, Name.Variable)),
+            (r'^(\w+)', Name.Function),
+            # literals
+            (r'\'[^\']*\'', String),
+            (r'\$.', String.Char),
+            (r'#\(', String.Symbol, 'parenth'),
+            (r'(\d+r)?-?\d+(\.\d+)?(e-?\d+)?', Number),
+            (r'#("[^"]*"|[-+*/\\~<>=|&!?,@%]+|[\w:]+)', String.Symbol),
+            # blocks variables
+            (r'(\[\s*)((?::\w+\s*)+)(\|)', bygroups(Text, Name.Variable, Text)),
+            # temporaries
+            (r'(\|)([\w\s]*)(\|)', bygroups(Operator, Name.Variable, Operator)),
+            # names
+            (r'\b(ifTrue:|ifFalse:|whileTrue:|whileFalse:|timesRepeat:)', Name.Builtin),
+            (r'\b(self|super)\b', Name.Builtin.Pseudo),
+            (r'\b[A-Z]\w*:', Name),
+            (r'\b[A-Z]\w*\b', Name), #Name.Class),
+            (r'\w+:?|[-+*/\\~<>=|&!?,@%]+', Name), #Name.Function),
+            # syntax
+            (r'\^|:=', Operator),
+            (r'[\[\](){}.;]', Text),
+        ],
+        'parenth' : [
+            (r'\)', String.Symbol, '#pop'),
+            include('root'),
+        ],
+        'pattern' : [
+            (r'(\w+)(\s*:\s*)(\w+\s*)', bygroups(Name.Function, Punctuation,
+                                                 Name.Variable)),
+            (r'', Text, '#pop'),
+        ],
+    }
diff --git a/scripts/find_error.py b/scripts/find_error.py
index e210028a..a7719b3f 100644
--- a/scripts/find_error.py
+++ b/scripts/find_error.py
@@ -40,12 +40,17 @@ def main(fn):
     for type, val in lx.get_tokens(text):
         if type == Error:
             print "Error parsing", fn
-            print "\n".join(['   ' + repr(x) for x in ntext[-5:]])
+            print "\n".join(['   ' + repr(x) for x in ntext[-num:]])
             print `val` + "<<<"
             return
         ntext.append((type,val))
 
 
+num = 10
+
 if __name__ == "__main__":
+    if sys.argv[1][:2] == '-n':
+        num = int(sys.argv[1][2:])
+        del sys.argv[1]
     for f in sys.argv[1:]:
         main(f)