diff options
Diffstat (limited to 'pygments/lexers/python.py')
| -rw-r--r-- | pygments/lexers/python.py | 848 |
1 files changed, 848 insertions, 0 deletions
diff --git a/pygments/lexers/python.py b/pygments/lexers/python.py new file mode 100644 index 00000000..ea97b855 --- /dev/null +++ b/pygments/lexers/python.py @@ -0,0 +1,848 @@ +# -*- coding: utf-8 -*- +""" + pygments.lexers.python + ~~~~~~~~~~~~~~~~~~~~~~ + + Lexers for Python and related languages. + + :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import re + +from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \ + default, words, combined, do_insertions +from pygments.util import get_bool_opt, shebang_matches +from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ + Number, Punctuation, Generic, Other, Error +from pygments import unistring as uni + +__all__ = ['PythonLexer', 'PythonConsoleLexer', 'PythonTracebackLexer', + 'Python3Lexer', 'Python3TracebackLexer', 'CythonLexer', + 'DgLexer', 'NumPyLexer'] + +line_re = re.compile('.*?\n') + + +class PythonLexer(RegexLexer): + """ + For `Python <http://www.python.org>`_ source code. + """ + + name = 'Python' + aliases = ['python', 'py', 'sage'] + filenames = ['*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac', '*.sage'] + mimetypes = ['text/x-python', 'application/x-python'] + + tokens = { + 'root': [ + (r'\n', Text), + (r'^(\s*)([rRuU]{,2}"""(?:.|\n)*?""")', bygroups(Text, String.Doc)), + (r"^(\s*)([rRuU]{,2}'''(?:.|\n)*?''')", bygroups(Text, String.Doc)), + (r'[^\S\n]+', Text), + (r'\A#!.+$', Comment.Hashbang), + (r'#.*$', Comment.Single), + (r'[]{}:(),;[]', Punctuation), + (r'\\\n', Text), + (r'\\', Text), + (r'(in|is|and|or|not)\b', Operator.Word), + (r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator), + include('keywords'), + (r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'), + (r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'), + (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), + 'fromimport'), + (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), + 'import'), + include('builtins'), + include('backtick'), + ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), + ("(?:[rR]|[uU][rR]|[rR][uU])'''", String, 'tsqs'), + ('(?:[rR]|[uU][rR]|[rR][uU])"', String, 'dqs'), + ("(?:[rR]|[uU][rR]|[rR][uU])'", String, 'sqs'), + ('[uU]?"""', String, combined('stringescape', 'tdqs')), + ("[uU]?'''", String, combined('stringescape', 'tsqs')), + ('[uU]?"', String, combined('stringescape', 'dqs')), + ("[uU]?'", String, combined('stringescape', 'sqs')), + include('name'), + include('numbers'), + ], + 'keywords': [ + (words(( + 'assert', 'break', 'continue', 'del', 'elif', 'else', 'except', + 'exec', 'finally', 'for', 'global', 'if', 'lambda', 'pass', + 'print', 'raise', 'return', 'try', 'while', 'yield', + 'yield from', 'as', 'with'), suffix=r'\b'), + Keyword), + ], + 'builtins': [ + (words(( + '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', + 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', 'classmethod', + 'cmp', 'coerce', 'compile', 'complex', 'delattr', 'dict', 'dir', 'divmod', + 'enumerate', 'eval', 'execfile', 'exit', 'file', 'filter', 'float', + 'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id', + 'input', 'int', 'intern', 'isinstance', 'issubclass', 'iter', 'len', + 'list', 'locals', 'long', 'map', 'max', 'min', 'next', 'object', + 'oct', 'open', 'ord', 'pow', 'property', 'range', 'raw_input', 'reduce', + 'reload', 'repr', 'reversed', 'round', 'set', 'setattr', 'slice', + 'sorted', 'staticmethod', 'str', 'sum', 'super', 'tuple', 'type', + 'unichr', 'unicode', 'vars', 'xrange', 'zip'), + prefix=r'(?<!\.)', suffix=r'\b'), + Name.Builtin), + (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True' + r')\b', Name.Builtin.Pseudo), + (words(( + 'ArithmeticError', 'AssertionError', 'AttributeError', + 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', + 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', + 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', + 'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError', + 'MemoryError', 'NameError', 'NotImplemented', 'NotImplementedError', + 'OSError', 'OverflowError', 'OverflowWarning', 'PendingDeprecationWarning', + 'ReferenceError', 'RuntimeError', 'RuntimeWarning', 'StandardError', + 'StopIteration', 'SyntaxError', 'SyntaxWarning', 'SystemError', + 'SystemExit', 'TabError', 'TypeError', 'UnboundLocalError', + 'UnicodeDecodeError', 'UnicodeEncodeError', 'UnicodeError', + 'UnicodeTranslateError', 'UnicodeWarning', 'UserWarning', + 'ValueError', 'VMSError', 'Warning', 'WindowsError', + 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), + Name.Exception), + ], + 'numbers': [ + (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float), + (r'\d+[eE][+-]?[0-9]+j?', Number.Float), + (r'0[0-7]+j?', Number.Oct), + (r'0[bB][01]+', Number.Bin), + (r'0[xX][a-fA-F0-9]+', Number.Hex), + (r'\d+L', Number.Integer.Long), + (r'\d+j?', Number.Integer) + ], + 'backtick': [ + ('`.*?`', String.Backtick), + ], + 'name': [ + (r'@[\w.]+', Name.Decorator), + ('[a-zA-Z_]\w*', Name), + ], + 'funcname': [ + ('[a-zA-Z_]\w*', Name.Function, '#pop') + ], + 'classname': [ + ('[a-zA-Z_]\w*', Name.Class, '#pop') + ], + 'import': [ + (r'(?:[ \t]|\\\n)+', Text), + (r'as\b', Keyword.Namespace), + (r',', Operator), + (r'[a-zA-Z_][\w.]*', Name.Namespace), + default('#pop') # all else: go back + ], + 'fromimport': [ + (r'(?:[ \t]|\\\n)+', Text), + (r'import\b', Keyword.Namespace, '#pop'), + # if None occurs here, it's "raise x from None", since None can + # never be a module name + (r'None\b', Name.Builtin.Pseudo, '#pop'), + # sadly, in "raise x from y" y will be highlighted as namespace too + (r'[a-zA-Z_.][\w.]*', Name.Namespace), + # anything else here also means "raise x from y" and is therefore + # not an error + default('#pop'), + ], + 'stringescape': [ + (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' + r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + ], + 'strings': [ + # the old style '%s' % (...) string formatting + (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' + '[hlL]?[diouxXeEfFgGcrs%]', String.Interpol), + # backslashes, quotes and formatting signs must be parsed one at a time + (r'[^\\\'"%\n]+', String), + (r'[\'"\\]', String), + # unhandled string formatting sign + (r'%', String) + # newlines are an error (use "nl" state) + ], + 'nl': [ + (r'\n', String) + ], + 'dqs': [ + (r'"', String, '#pop'), + (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings + include('strings') + ], + 'sqs': [ + (r"'", String, '#pop'), + (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings + include('strings') + ], + 'tdqs': [ + (r'"""', String, '#pop'), + include('strings'), + include('nl') + ], + 'tsqs': [ + (r"'''", String, '#pop'), + include('strings'), + include('nl') + ], + } + + def analyse_text(text): + return shebang_matches(text, r'pythonw?(2(\.\d)?)?') or \ + 'import ' in text[:1000] + + +class Python3Lexer(RegexLexer): + """ + For `Python <http://www.python.org>`_ source code (version 3.0). + + .. versionadded:: 0.10 + """ + + name = 'Python 3' + aliases = ['python3', 'py3'] + filenames = [] # Nothing until Python 3 gets widespread + mimetypes = ['text/x-python3', 'application/x-python3'] + + flags = re.MULTILINE | re.UNICODE + + uni_name = "[%s][%s]*" % (uni.xid_start, uni.xid_continue) + + tokens = PythonLexer.tokens.copy() + tokens['keywords'] = [ + (words(( + 'assert', 'async', 'await', 'break', 'continue', 'del', 'elif', + 'else', 'except', 'finally', 'for', 'global', 'if', 'lambda', 'pass', + 'raise', 'nonlocal', 'return', 'try', 'while', 'yield', 'yield from', + 'as', 'with'), suffix=r'\b'), + Keyword), + (words(( + 'True', 'False', 'None'), suffix=r'\b'), + Keyword.Constant), + ] + tokens['builtins'] = [ + (words(( + '__import__', 'abs', 'all', 'any', 'bin', 'bool', 'bytearray', 'bytes', + 'chr', 'classmethod', 'cmp', 'compile', 'complex', 'delattr', 'dict', + 'dir', 'divmod', 'enumerate', 'eval', 'filter', 'float', 'format', + 'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id', + 'input', 'int', 'isinstance', 'issubclass', 'iter', 'len', 'list', + 'locals', 'map', 'max', 'memoryview', 'min', 'next', 'object', 'oct', + 'open', 'ord', 'pow', 'print', 'property', 'range', 'repr', 'reversed', + 'round', 'set', 'setattr', 'slice', 'sorted', 'staticmethod', 'str', + 'sum', 'super', 'tuple', 'type', 'vars', 'zip'), prefix=r'(?<!\.)', + suffix=r'\b'), + Name.Builtin), + (r'(?<!\.)(self|Ellipsis|NotImplemented)\b', Name.Builtin.Pseudo), + (words(( + 'ArithmeticError', 'AssertionError', 'AttributeError', + 'BaseException', 'BufferError', 'BytesWarning', 'DeprecationWarning', + 'EOFError', 'EnvironmentError', 'Exception', 'FloatingPointError', + 'FutureWarning', 'GeneratorExit', 'IOError', 'ImportError', + 'ImportWarning', 'IndentationError', 'IndexError', 'KeyError', + 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', + 'NotImplementedError', 'OSError', 'OverflowError', + 'PendingDeprecationWarning', 'ReferenceError', 'ResourceWarning', + 'RuntimeError', 'RuntimeWarning', 'StopIteration', + 'SyntaxError', 'SyntaxWarning', 'SystemError', 'SystemExit', 'TabError', + 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', + 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', + 'UnicodeWarning', 'UserWarning', 'ValueError', 'VMSError', 'Warning', + 'WindowsError', 'ZeroDivisionError', + # new builtin exceptions from PEP 3151 + 'BlockingIOError', 'ChildProcessError', 'ConnectionError', + 'BrokenPipeError', 'ConnectionAbortedError', 'ConnectionRefusedError', + 'ConnectionResetError', 'FileExistsError', 'FileNotFoundError', + 'InterruptedError', 'IsADirectoryError', 'NotADirectoryError', + 'PermissionError', 'ProcessLookupError', 'TimeoutError'), + prefix=r'(?<!\.)', suffix=r'\b'), + Name.Exception), + ] + tokens['numbers'] = [ + (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), + (r'0[oO][0-7]+', Number.Oct), + (r'0[bB][01]+', Number.Bin), + (r'0[xX][a-fA-F0-9]+', Number.Hex), + (r'\d+', Number.Integer) + ] + tokens['backtick'] = [] + tokens['name'] = [ + (r'@\w+', Name.Decorator), + (r'@', Operator), # new matrix multiplication operator + (uni_name, Name), + ] + tokens['funcname'] = [ + (uni_name, Name.Function, '#pop') + ] + tokens['classname'] = [ + (uni_name, Name.Class, '#pop') + ] + tokens['import'] = [ + (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), + (r'\.', Name.Namespace), + (uni_name, Name.Namespace), + (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), + default('#pop') # all else: go back + ] + tokens['fromimport'] = [ + (r'(\s+)(import)\b', bygroups(Text, Keyword), '#pop'), + (r'\.', Name.Namespace), + (uni_name, Name.Namespace), + default('#pop'), + ] + tokens['strings'] = [ + # the old style '%s' % (...) string formatting (still valid in Py3) + (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' + '[hlL]?[diouxXeEfFgGcrs%]', String.Interpol), + # the new style '{}'.format(...) string formatting + (r'\{' + '((\w+)((\.\w+)|(\[[^\]]+\]))*)?' # field name + '(\![sra])?' # conversion + '(\:(.?[<>=\^])?[-+ ]?#?0?(\d+)?,?(\.\d+)?[bcdeEfFgGnosxX%]?)?' + '\}', String.Interpol), + # backslashes, quotes and formatting signs must be parsed one at a time + (r'[^\\\'"%\{\n]+', String), + (r'[\'"\\]', String), + # unhandled string formatting sign + (r'%|(\{{1,2})', String) + # newlines are an error (use "nl" state) + ] + + def analyse_text(text): + return shebang_matches(text, r'pythonw?3(\.\d)?') + + +class PythonConsoleLexer(Lexer): + """ + For Python console output or doctests, such as: + + .. sourcecode:: pycon + + >>> a = 'foo' + >>> print a + foo + >>> 1 / 0 + Traceback (most recent call last): + File "<stdin>", line 1, in <module> + ZeroDivisionError: integer division or modulo by zero + + Additional options: + + `python3` + Use Python 3 lexer for code. Default is ``False``. + + .. versionadded:: 1.0 + """ + name = 'Python console session' + aliases = ['pycon'] + mimetypes = ['text/x-python-doctest'] + + def __init__(self, **options): + self.python3 = get_bool_opt(options, 'python3', False) + Lexer.__init__(self, **options) + + def get_tokens_unprocessed(self, text): + if self.python3: + pylexer = Python3Lexer(**self.options) + tblexer = Python3TracebackLexer(**self.options) + else: + pylexer = PythonLexer(**self.options) + tblexer = PythonTracebackLexer(**self.options) + + curcode = '' + insertions = [] + curtb = '' + tbindex = 0 + tb = 0 + for match in line_re.finditer(text): + line = match.group() + if line.startswith(u'>>> ') or line.startswith(u'... '): + tb = 0 + insertions.append((len(curcode), + [(0, Generic.Prompt, line[:4])])) + curcode += line[4:] + elif line.rstrip() == u'...' and not tb: + # only a new >>> prompt can end an exception block + # otherwise an ellipsis in place of the traceback frames + # will be mishandled + insertions.append((len(curcode), + [(0, Generic.Prompt, u'...')])) + curcode += line[3:] + else: + if curcode: + for item in do_insertions( + insertions, pylexer.get_tokens_unprocessed(curcode)): + yield item + curcode = '' + insertions = [] + if (line.startswith(u'Traceback (most recent call last):') or + re.match(u' File "[^"]+", line \\d+\\n$', line)): + tb = 1 + curtb = line + tbindex = match.start() + elif line == 'KeyboardInterrupt\n': + yield match.start(), Name.Class, line + elif tb: + curtb += line + if not (line.startswith(' ') or line.strip() == u'...'): + tb = 0 + for i, t, v in tblexer.get_tokens_unprocessed(curtb): + yield tbindex+i, t, v + curtb = '' + else: + yield match.start(), Generic.Output, line + if curcode: + for item in do_insertions(insertions, + pylexer.get_tokens_unprocessed(curcode)): + yield item + if curtb: + for i, t, v in tblexer.get_tokens_unprocessed(curtb): + yield tbindex+i, t, v + + +class PythonTracebackLexer(RegexLexer): + """ + For Python tracebacks. + + .. versionadded:: 0.7 + """ + + name = 'Python Traceback' + aliases = ['pytb'] + filenames = ['*.pytb'] + mimetypes = ['text/x-python-traceback'] + + tokens = { + 'root': [ + (r'^Traceback \(most recent call last\):\n', + Generic.Traceback, 'intb'), + # SyntaxError starts with this. + (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), + (r'^.*\n', Other), + ], + 'intb': [ + (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', + bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), + (r'^( File )("[^"]+")(, line )(\d+)(\n)', + bygroups(Text, Name.Builtin, Text, Number, Text)), + (r'^( )(.+)(\n)', + bygroups(Text, using(PythonLexer), Text)), + (r'^([ \t]*)(\.\.\.)(\n)', + bygroups(Text, Comment, Text)), # for doctests... + (r'^([^:]+)(: )(.+)(\n)', + bygroups(Generic.Error, Text, Name, Text), '#pop'), + (r'^([a-zA-Z_]\w*)(:?\n)', + bygroups(Generic.Error, Text), '#pop') + ], + } + + +class Python3TracebackLexer(RegexLexer): + """ + For Python 3.0 tracebacks, with support for chained exceptions. + + .. versionadded:: 1.0 + """ + + name = 'Python 3.0 Traceback' + aliases = ['py3tb'] + filenames = ['*.py3tb'] + mimetypes = ['text/x-python3-traceback'] + + tokens = { + 'root': [ + (r'\n', Text), + (r'^Traceback \(most recent call last\):\n', Generic.Traceback, 'intb'), + (r'^During handling of the above exception, another ' + r'exception occurred:\n\n', Generic.Traceback), + (r'^The above exception was the direct cause of the ' + r'following exception:\n\n', Generic.Traceback), + (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), + ], + 'intb': [ + (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', + bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), + (r'^( File )("[^"]+")(, line )(\d+)(\n)', + bygroups(Text, Name.Builtin, Text, Number, Text)), + (r'^( )(.+)(\n)', + bygroups(Text, using(Python3Lexer), Text)), + (r'^([ \t]*)(\.\.\.)(\n)', + bygroups(Text, Comment, Text)), # for doctests... + (r'^([^:]+)(: )(.+)(\n)', + bygroups(Generic.Error, Text, Name, Text), '#pop'), + (r'^([a-zA-Z_]\w*)(:?\n)', + bygroups(Generic.Error, Text), '#pop') + ], + } + + +class CythonLexer(RegexLexer): + """ + For Pyrex and `Cython <http://cython.org>`_ source code. + + .. versionadded:: 1.1 + """ + + name = 'Cython' + aliases = ['cython', 'pyx', 'pyrex'] + filenames = ['*.pyx', '*.pxd', '*.pxi'] + mimetypes = ['text/x-cython', 'application/x-cython'] + + tokens = { + 'root': [ + (r'\n', Text), + (r'^(\s*)("""(?:.|\n)*?""")', bygroups(Text, String.Doc)), + (r"^(\s*)('''(?:.|\n)*?''')", bygroups(Text, String.Doc)), + (r'[^\S\n]+', Text), + (r'#.*$', Comment), + (r'[]{}:(),;[]', Punctuation), + (r'\\\n', Text), + (r'\\', Text), + (r'(in|is|and|or|not)\b', Operator.Word), + (r'(<)([a-zA-Z0-9.?]+)(>)', + bygroups(Punctuation, Keyword.Type, Punctuation)), + (r'!=|==|<<|>>|[-~+/*%=<>&^|.?]', Operator), + (r'(from)(\d+)(<=)(\s+)(<)(\d+)(:)', + bygroups(Keyword, Number.Integer, Operator, Name, Operator, + Name, Punctuation)), + include('keywords'), + (r'(def|property)(\s+)', bygroups(Keyword, Text), 'funcname'), + (r'(cp?def)(\s+)', bygroups(Keyword, Text), 'cdef'), + (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'classname'), + (r'(from)(\s+)', bygroups(Keyword, Text), 'fromimport'), + (r'(c?import)(\s+)', bygroups(Keyword, Text), 'import'), + include('builtins'), + include('backtick'), + ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), + ("(?:[rR]|[uU][rR]|[rR][uU])'''", String, 'tsqs'), + ('(?:[rR]|[uU][rR]|[rR][uU])"', String, 'dqs'), + ("(?:[rR]|[uU][rR]|[rR][uU])'", String, 'sqs'), + ('[uU]?"""', String, combined('stringescape', 'tdqs')), + ("[uU]?'''", String, combined('stringescape', 'tsqs')), + ('[uU]?"', String, combined('stringescape', 'dqs')), + ("[uU]?'", String, combined('stringescape', 'sqs')), + include('name'), + include('numbers'), + ], + 'keywords': [ + (words(( + 'assert', 'break', 'by', 'continue', 'ctypedef', 'del', 'elif', + 'else', 'except', 'except?', 'exec', 'finally', 'for', 'gil', + 'global', 'if', 'include', 'lambda', 'nogil', 'pass', 'print', + 'raise', 'return', 'try', 'while', 'yield', 'as', 'with'), suffix=r'\b'), + Keyword), + (r'(DEF|IF|ELIF|ELSE)\b', Comment.Preproc), + ], + 'builtins': [ + (words(( + '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', + 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', + 'classmethod', 'cmp', 'coerce', 'compile', 'complex', 'delattr', + 'dict', 'dir', 'divmod', 'enumerate', 'eval', 'execfile', 'exit', + 'file', 'filter', 'float', 'frozenset', 'getattr', 'globals', + 'hasattr', 'hash', 'hex', 'id', 'input', 'int', 'intern', 'isinstance', + 'issubclass', 'iter', 'len', 'list', 'locals', 'long', 'map', 'max', + 'min', 'next', 'object', 'oct', 'open', 'ord', 'pow', 'property', + 'range', 'raw_input', 'reduce', 'reload', 'repr', 'reversed', + 'round', 'set', 'setattr', 'slice', 'sorted', 'staticmethod', + 'str', 'sum', 'super', 'tuple', 'type', 'unichr', 'unicode', + 'vars', 'xrange', 'zip'), prefix=r'(?<!\.)', suffix=r'\b'), + Name.Builtin), + (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True|NULL' + r')\b', Name.Builtin.Pseudo), + (words(( + 'ArithmeticError', 'AssertionError', 'AttributeError', + 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', + 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', 'IOError', + 'ImportError', 'ImportWarning', 'IndentationError', 'IndexError', 'KeyError', + 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', + 'NotImplemented', 'NotImplementedError', 'OSError', 'OverflowError', + 'OverflowWarning', 'PendingDeprecationWarning', 'ReferenceError', + 'RuntimeError', 'RuntimeWarning', 'StandardError', 'StopIteration', + 'SyntaxError', 'SyntaxWarning', 'SystemError', 'SystemExit', 'TabError', + 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', + 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', + 'UnicodeWarning', 'UserWarning', 'ValueError', 'Warning', + 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), + Name.Exception), + ], + 'numbers': [ + (r'(\d+\.?\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), + (r'0\d+', Number.Oct), + (r'0[xX][a-fA-F0-9]+', Number.Hex), + (r'\d+L', Number.Integer.Long), + (r'\d+', Number.Integer) + ], + 'backtick': [ + ('`.*?`', String.Backtick), + ], + 'name': [ + (r'@\w+', Name.Decorator), + ('[a-zA-Z_]\w*', Name), + ], + 'funcname': [ + ('[a-zA-Z_]\w*', Name.Function, '#pop') + ], + 'cdef': [ + (r'(public|readonly|extern|api|inline)\b', Keyword.Reserved), + (r'(struct|enum|union|class)\b', Keyword), + (r'([a-zA-Z_]\w*)(\s*)(?=[(:#=]|$)', + bygroups(Name.Function, Text), '#pop'), + (r'([a-zA-Z_]\w*)(\s*)(,)', + bygroups(Name.Function, Text, Punctuation)), + (r'from\b', Keyword, '#pop'), + (r'as\b', Keyword), + (r':', Punctuation, '#pop'), + (r'(?=["\'])', Text, '#pop'), + (r'[a-zA-Z_]\w*', Keyword.Type), + (r'.', Text), + ], + 'classname': [ + ('[a-zA-Z_]\w*', Name.Class, '#pop') + ], + 'import': [ + (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), + (r'[a-zA-Z_][\w.]*', Name.Namespace), + (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), + default('#pop') # all else: go back + ], + 'fromimport': [ + (r'(\s+)(c?import)\b', bygroups(Text, Keyword), '#pop'), + (r'[a-zA-Z_.][\w.]*', Name.Namespace), + # ``cdef foo from "header"``, or ``for foo from 0 < i < 10`` + default('#pop'), + ], + 'stringescape': [ + (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' + r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + ], + 'strings': [ + (r'%(\([a-zA-Z0-9]+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' + '[hlL]?[diouxXeEfFgGcrs%]', String.Interpol), + (r'[^\\\'"%\n]+', String), + # quotes, percents and backslashes must be parsed one at a time + (r'[\'"\\]', String), + # unhandled string formatting sign + (r'%', String) + # newlines are an error (use "nl" state) + ], + 'nl': [ + (r'\n', String) + ], + 'dqs': [ + (r'"', String, '#pop'), + (r'\\\\|\\"|\\\n', String.Escape), # included here again for raw strings + include('strings') + ], + 'sqs': [ + (r"'", String, '#pop'), + (r"\\\\|\\'|\\\n", String.Escape), # included here again for raw strings + include('strings') + ], + 'tdqs': [ + (r'"""', String, '#pop'), + include('strings'), + include('nl') + ], + 'tsqs': [ + (r"'''", String, '#pop'), + include('strings'), + include('nl') + ], + } + + +class DgLexer(RegexLexer): + """ + Lexer for `dg <http://pyos.github.com/dg>`_, + a functional and object-oriented programming language + running on the CPython 3 VM. + + .. versionadded:: 1.6 + """ + name = 'dg' + aliases = ['dg'] + filenames = ['*.dg'] + mimetypes = ['text/x-dg'] + + tokens = { + 'root': [ + (r'\s+', Text), + (r'#.*?$', Comment.Single), + + (r'(?i)0b[01]+', Number.Bin), + (r'(?i)0o[0-7]+', Number.Oct), + (r'(?i)0x[0-9a-f]+', Number.Hex), + (r'(?i)[+-]?[0-9]+\.[0-9]+(e[+-]?[0-9]+)?j?', Number.Float), + (r'(?i)[+-]?[0-9]+e[+-]?\d+j?', Number.Float), + (r'(?i)[+-]?[0-9]+j?', Number.Integer), + + (r"(?i)(br|r?b?)'''", String, combined('stringescape', 'tsqs', 'string')), + (r'(?i)(br|r?b?)"""', String, combined('stringescape', 'tdqs', 'string')), + (r"(?i)(br|r?b?)'", String, combined('stringescape', 'sqs', 'string')), + (r'(?i)(br|r?b?)"', String, combined('stringescape', 'dqs', 'string')), + + (r"`\w+'*`", Operator), + (r'\b(and|in|is|or|where)\b', Operator.Word), + (r'[!$%&*+\-./:<-@\\^|~;,]+', Operator), + + (words(( + 'bool', 'bytearray', 'bytes', 'classmethod', 'complex', 'dict', 'dict\'', + 'float', 'frozenset', 'int', 'list', 'list\'', 'memoryview', 'object', + 'property', 'range', 'set', 'set\'', 'slice', 'staticmethod', 'str', 'super', + 'tuple', 'tuple\'', 'type'), prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), + Name.Builtin), + (words(( + '__import__', 'abs', 'all', 'any', 'bin', 'bind', 'chr', 'cmp', 'compile', + 'complex', 'delattr', 'dir', 'divmod', 'drop', 'dropwhile', 'enumerate', + 'eval', 'exhaust', 'filter', 'flip', 'foldl1?', 'format', 'fst', 'getattr', + 'globals', 'hasattr', 'hash', 'head', 'hex', 'id', 'init', 'input', + 'isinstance', 'issubclass', 'iter', 'iterate', 'last', 'len', 'locals', + 'map', 'max', 'min', 'next', 'oct', 'open', 'ord', 'pow', 'print', 'repr', + 'reversed', 'round', 'setattr', 'scanl1?', 'snd', 'sorted', 'sum', 'tail', + 'take', 'takewhile', 'vars', 'zip'), prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), + Name.Builtin), + (r"(?<!\.)(self|Ellipsis|NotImplemented|None|True|False)(?!['\w])", + Name.Builtin.Pseudo), + + (r"(?<!\.)[A-Z]\w*(Error|Exception|Warning)'*(?!['\w])", + Name.Exception), + (r"(?<!\.)(Exception|GeneratorExit|KeyboardInterrupt|StopIteration|" + r"SystemExit)(?!['\w])", Name.Exception), + + (r"(?<![\w.])(except|finally|for|if|import|not|otherwise|raise|" + r"subclass|while|with|yield)(?!['\w])", Keyword.Reserved), + + (r"[A-Z_]+'*(?!['\w])", Name), + (r"[A-Z]\w+'*(?!['\w])", Keyword.Type), + (r"\w+'*", Name), + + (r'[()]', Punctuation), + (r'.', Error), + ], + 'stringescape': [ + (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' + r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + ], + 'string': [ + (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' + '[hlL]?[diouxXeEfFgGcrs%]', String.Interpol), + (r'[^\\\'"%\n]+', String), + # quotes, percents and backslashes must be parsed one at a time + (r'[\'"\\]', String), + # unhandled string formatting sign + (r'%', String), + (r'\n', String) + ], + 'dqs': [ + (r'"', String, '#pop') + ], + 'sqs': [ + (r"'", String, '#pop') + ], + 'tdqs': [ + (r'"""', String, '#pop') + ], + 'tsqs': [ + (r"'''", String, '#pop') + ], + } + + +class NumPyLexer(PythonLexer): + """ + A Python lexer recognizing Numerical Python builtins. + + .. versionadded:: 0.10 + """ + + name = 'NumPy' + aliases = ['numpy'] + + # override the mimetypes to not inherit them from python + mimetypes = [] + filenames = [] + + EXTRA_KEYWORDS = set(( + 'abs', 'absolute', 'accumulate', 'add', 'alen', 'all', 'allclose', + 'alltrue', 'alterdot', 'amax', 'amin', 'angle', 'any', 'append', + 'apply_along_axis', 'apply_over_axes', 'arange', 'arccos', 'arccosh', + 'arcsin', 'arcsinh', 'arctan', 'arctan2', 'arctanh', 'argmax', 'argmin', + 'argsort', 'argwhere', 'around', 'array', 'array2string', 'array_equal', + 'array_equiv', 'array_repr', 'array_split', 'array_str', 'arrayrange', + 'asanyarray', 'asarray', 'asarray_chkfinite', 'ascontiguousarray', + 'asfarray', 'asfortranarray', 'asmatrix', 'asscalar', 'astype', + 'atleast_1d', 'atleast_2d', 'atleast_3d', 'average', 'bartlett', + 'base_repr', 'beta', 'binary_repr', 'bincount', 'binomial', + 'bitwise_and', 'bitwise_not', 'bitwise_or', 'bitwise_xor', 'blackman', + 'bmat', 'broadcast', 'byte_bounds', 'bytes', 'byteswap', 'c_', + 'can_cast', 'ceil', 'choose', 'clip', 'column_stack', 'common_type', + 'compare_chararrays', 'compress', 'concatenate', 'conj', 'conjugate', + 'convolve', 'copy', 'corrcoef', 'correlate', 'cos', 'cosh', 'cov', + 'cross', 'cumprod', 'cumproduct', 'cumsum', 'delete', 'deprecate', + 'diag', 'diagflat', 'diagonal', 'diff', 'digitize', 'disp', 'divide', + 'dot', 'dsplit', 'dstack', 'dtype', 'dump', 'dumps', 'ediff1d', 'empty', + 'empty_like', 'equal', 'exp', 'expand_dims', 'expm1', 'extract', 'eye', + 'fabs', 'fastCopyAndTranspose', 'fft', 'fftfreq', 'fftshift', 'fill', + 'finfo', 'fix', 'flat', 'flatnonzero', 'flatten', 'fliplr', 'flipud', + 'floor', 'floor_divide', 'fmod', 'frexp', 'fromarrays', 'frombuffer', + 'fromfile', 'fromfunction', 'fromiter', 'frompyfunc', 'fromstring', + 'generic', 'get_array_wrap', 'get_include', 'get_numarray_include', + 'get_numpy_include', 'get_printoptions', 'getbuffer', 'getbufsize', + 'geterr', 'geterrcall', 'geterrobj', 'getfield', 'gradient', 'greater', + 'greater_equal', 'gumbel', 'hamming', 'hanning', 'histogram', + 'histogram2d', 'histogramdd', 'hsplit', 'hstack', 'hypot', 'i0', + 'identity', 'ifft', 'imag', 'index_exp', 'indices', 'inf', 'info', + 'inner', 'insert', 'int_asbuffer', 'interp', 'intersect1d', + 'intersect1d_nu', 'inv', 'invert', 'iscomplex', 'iscomplexobj', + 'isfinite', 'isfortran', 'isinf', 'isnan', 'isneginf', 'isposinf', + 'isreal', 'isrealobj', 'isscalar', 'issctype', 'issubclass_', + 'issubdtype', 'issubsctype', 'item', 'itemset', 'iterable', 'ix_', + 'kaiser', 'kron', 'ldexp', 'left_shift', 'less', 'less_equal', 'lexsort', + 'linspace', 'load', 'loads', 'loadtxt', 'log', 'log10', 'log1p', 'log2', + 'logical_and', 'logical_not', 'logical_or', 'logical_xor', 'logspace', + 'lstsq', 'mat', 'matrix', 'max', 'maximum', 'maximum_sctype', + 'may_share_memory', 'mean', 'median', 'meshgrid', 'mgrid', 'min', + 'minimum', 'mintypecode', 'mod', 'modf', 'msort', 'multiply', 'nan', + 'nan_to_num', 'nanargmax', 'nanargmin', 'nanmax', 'nanmin', 'nansum', + 'ndenumerate', 'ndim', 'ndindex', 'negative', 'newaxis', 'newbuffer', + 'newbyteorder', 'nonzero', 'not_equal', 'obj2sctype', 'ogrid', 'ones', + 'ones_like', 'outer', 'permutation', 'piecewise', 'pinv', 'pkgload', + 'place', 'poisson', 'poly', 'poly1d', 'polyadd', 'polyder', 'polydiv', + 'polyfit', 'polyint', 'polymul', 'polysub', 'polyval', 'power', 'prod', + 'product', 'ptp', 'put', 'putmask', 'r_', 'randint', 'random_integers', + 'random_sample', 'ranf', 'rank', 'ravel', 'real', 'real_if_close', + 'recarray', 'reciprocal', 'reduce', 'remainder', 'repeat', 'require', + 'reshape', 'resize', 'restoredot', 'right_shift', 'rint', 'roll', + 'rollaxis', 'roots', 'rot90', 'round', 'round_', 'row_stack', 's_', + 'sample', 'savetxt', 'sctype2char', 'searchsorted', 'seed', 'select', + 'set_numeric_ops', 'set_printoptions', 'set_string_function', + 'setbufsize', 'setdiff1d', 'seterr', 'seterrcall', 'seterrobj', + 'setfield', 'setflags', 'setmember1d', 'setxor1d', 'shape', + 'show_config', 'shuffle', 'sign', 'signbit', 'sin', 'sinc', 'sinh', + 'size', 'slice', 'solve', 'sometrue', 'sort', 'sort_complex', 'source', + 'split', 'sqrt', 'square', 'squeeze', 'standard_normal', 'std', + 'subtract', 'sum', 'svd', 'swapaxes', 'take', 'tan', 'tanh', 'tensordot', + 'test', 'tile', 'tofile', 'tolist', 'tostring', 'trace', 'transpose', + 'trapz', 'tri', 'tril', 'trim_zeros', 'triu', 'true_divide', 'typeDict', + 'typename', 'uniform', 'union1d', 'unique', 'unique1d', 'unravel_index', + 'unwrap', 'vander', 'var', 'vdot', 'vectorize', 'view', 'vonmises', + 'vsplit', 'vstack', 'weibull', 'where', 'who', 'zeros', 'zeros_like' + )) + + 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 + + def analyse_text(text): + return (shebang_matches(text, r'pythonw?(2(\.\d)?)?') or + 'import ' in text[:1000]) \ + and ('import numpy' in text or 'from numpy import' in text) |