summaryrefslogtreecommitdiff
path: root/pygments
diff options
context:
space:
mode:
authorGeorg Brandl <georg@python.org>2013-01-09 12:26:50 +0100
committerGeorg Brandl <georg@python.org>2013-01-09 12:26:50 +0100
commit68a10f38d3814e2292849306a815387c6259ce06 (patch)
treec4e686a0b5ef7f08f1bef6b33eedf0bc16d7f47f /pygments
parent2ca4dbd36a06c8f7d2d6f349f5921d558c138b19 (diff)
parente9e7db92d57ea2ab45b1094a48168b0d7e5a72a3 (diff)
downloadpygments-68a10f38d3814e2292849306a815387c6259ce06.tar.gz
Merged in gentoo90/pygments-main/nsis (pull request #136: Add NSIS script lexer)
Diffstat (limited to 'pygments')
-rw-r--r--pygments/cmdline.py8
-rw-r--r--pygments/lexer.py5
-rw-r--r--pygments/lexers/_mapping.py6
-rw-r--r--pygments/lexers/_robotframeworklexer.py546
-rw-r--r--pygments/lexers/asm.py4
-rw-r--r--pygments/lexers/compiled.py238
-rw-r--r--pygments/lexers/jvm.py2
-rw-r--r--pygments/lexers/math.py17
-rw-r--r--pygments/lexers/other.py95
-rw-r--r--pygments/lexers/text.py47
-rw-r--r--pygments/lexers/web.py2
11 files changed, 918 insertions, 52 deletions
diff --git a/pygments/cmdline.py b/pygments/cmdline.py
index 1f14cf5d..6fa80305 100644
--- a/pygments/cmdline.py
+++ b/pygments/cmdline.py
@@ -192,6 +192,14 @@ def main(args=sys.argv):
usage = USAGE % ((args[0],) * 6)
+ if sys.platform in ['win32', 'cygwin']:
+ try:
+ # Provide coloring under Windows, if possible
+ import colorama
+ colorama.init()
+ except ImportError:
+ pass
+
try:
popts, args = getopt.getopt(args[1:], "l:f:F:o:O:P:LS:a:N:hVHg")
except getopt.GetoptError, err:
diff --git a/pygments/lexer.py b/pygments/lexer.py
index ad2c72d1..7cb212d5 100644
--- a/pygments/lexer.py
+++ b/pygments/lexer.py
@@ -163,6 +163,10 @@ class Lexer(object):
text = decoded
else:
text = text.decode(self.encoding)
+ else:
+ if text.startswith(u'\ufeff'):
+ text = text[len(u'\ufeff'):]
+
# text now *is* a unicode string
text = text.replace('\r\n', '\n')
text = text.replace('\r', '\n')
@@ -694,4 +698,3 @@ def do_insertions(insertions, tokens):
except StopIteration:
insleft = False
break # not strictly necessary
-
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index ae3d2361..963431d4 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -83,7 +83,8 @@ LEXERS = {
'DjangoLexer': ('pygments.lexers.templates', 'Django/Jinja', ('django', 'jinja'), (), ('application/x-django-templating', 'application/x-jinja')),
'DtdLexer': ('pygments.lexers.web', 'DTD', ('dtd',), ('*.dtd',), ('application/xml-dtd',)),
'DuelLexer': ('pygments.lexers.web', 'Duel', ('duel', 'Duel Engine', 'Duel View', 'JBST', 'jbst', 'JsonML+BST'), ('*.duel', '*.jbst'), ('text/x-duel', 'text/x-jbst')),
- 'DylanLexer': ('pygments.lexers.compiled', 'Dylan', ('dylan',), ('*.dylan', '*.dyl'), ('text/x-dylan',)),
+ 'DylanLexer': ('pygments.lexers.compiled', 'Dylan', ('dylan',), ('*.dylan', '*.dyl', '*.intr'), ('text/x-dylan',)),
+ 'DylanLidLexer': ('pygments.lexers.compiled', 'DylanLID', ('dylan-lid', 'lid'), ('*.lid', '*.hdp'), ('text/x-dylan-lid',)),
'ECLLexer': ('pygments.lexers.other', 'ECL', ('ecl',), ('*.ecl',), ('application/x-ecl',)),
'ECLexer': ('pygments.lexers.compiled', 'eC', ('ec',), ('*.ec', '*.eh'), ('text/x-echdr', 'text/x-ecsrc')),
'ElixirConsoleLexer': ('pygments.lexers.functional', 'Elixir iex session', ('iex',), (), ('text/x-elixir-shellsession',)),
@@ -122,6 +123,7 @@ LEXERS = {
'HtmlPhpLexer': ('pygments.lexers.templates', 'HTML+PHP', ('html+php',), ('*.phtml',), ('application/x-php', 'application/x-httpd-php', 'application/x-httpd-php3', 'application/x-httpd-php4', 'application/x-httpd-php5')),
'HtmlSmartyLexer': ('pygments.lexers.templates', 'HTML+Smarty', ('html+smarty',), (), ('text/html+smarty',)),
'HttpLexer': ('pygments.lexers.text', 'HTTP', ('http',), (), ()),
+ 'HxmlLexer': ('pygments.lexers.text', 'Hxml', ('haxeml', 'hxml'), ('*.hxml',), ()),
'HybrisLexer': ('pygments.lexers.other', 'Hybris', ('hybris', 'hy'), ('*.hy', '*.hyb'), ('text/x-hybris', 'application/x-hybris')),
'IniLexer': ('pygments.lexers.text', 'INI', ('ini', 'cfg'), ('*.ini', '*.cfg'), ('text/x-ini',)),
'IoLexer': ('pygments.lexers.agile', 'Io', ('io',), ('*.io',), ('text/x-iosrc',)),
@@ -207,6 +209,7 @@ LEXERS = {
'PrologLexer': ('pygments.lexers.compiled', 'Prolog', ('prolog',), ('*.prolog', '*.pro', '*.pl'), ('text/x-prolog',)),
'PropertiesLexer': ('pygments.lexers.text', 'Properties', ('properties',), ('*.properties',), ('text/x-java-properties',)),
'ProtoBufLexer': ('pygments.lexers.other', 'Protocol Buffer', ('protobuf',), ('*.proto',), ()),
+ 'PuppetLexer': ('pygments.lexers.other', 'Puppet', ('puppet',), ('*.pp',), ()),
'PyPyLogLexer': ('pygments.lexers.text', 'PyPy Log', ('pypylog', 'pypy'), ('*.pypylog',), ('application/x-pypylog',)),
'Python3Lexer': ('pygments.lexers.agile', 'Python 3', ('python3', 'py3'), (), ('text/x-python3', 'application/x-python3')),
'Python3TracebackLexer': ('pygments.lexers.agile', 'Python 3.0 Traceback', ('py3tb',), ('*.py3tb',), ('text/x-python3-traceback',)),
@@ -229,6 +232,7 @@ LEXERS = {
'RedcodeLexer': ('pygments.lexers.other', 'Redcode', ('redcode',), ('*.cw',), ()),
'RegeditLexer': ('pygments.lexers.text', 'reg', (), ('*.reg',), ('text/x-windows-registry',)),
'RhtmlLexer': ('pygments.lexers.templates', 'RHTML', ('rhtml', 'html+erb', 'html+ruby'), ('*.rhtml',), ('text/html+ruby',)),
+ 'RobotFrameworkLexer': ('pygments.lexers.other', 'RobotFramework', ('RobotFramework', 'robotframework'), ('*.txt',), ('text/x-robotframework',)),
'RstLexer': ('pygments.lexers.text', 'reStructuredText', ('rst', 'rest', 'restructuredtext'), ('*.rst', '*.rest'), ('text/x-rst', 'text/prs.fallenstein.rst')),
'RubyConsoleLexer': ('pygments.lexers.agile', 'Ruby irb session', ('rbcon', 'irb'), (), ('text/x-ruby-shellsession',)),
'RubyLexer': ('pygments.lexers.agile', 'Ruby', ('rb', 'ruby', 'duby'), ('*.rb', '*.rbw', 'Rakefile', '*.rake', '*.gemspec', '*.rbx', '*.duby'), ('text/x-ruby', 'application/x-ruby')),
diff --git a/pygments/lexers/_robotframeworklexer.py b/pygments/lexers/_robotframeworklexer.py
new file mode 100644
index 00000000..f3b5f223
--- /dev/null
+++ b/pygments/lexers/_robotframeworklexer.py
@@ -0,0 +1,546 @@
+# Copyright 2012 Nokia Siemens Networks Oyj
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import re
+
+from pygments.lexer import Lexer
+from pygments.token import Token
+
+
+HEADING = Token.Generic.Heading
+SETTING = Token.Keyword.Namespace
+IMPORT = Token.Name.Namespace
+TC_KW_NAME = Token.Generic.Subheading
+KEYWORD = Token.Name.Function
+ARGUMENT = Token.String
+VARIABLE = Token.Name.Variable
+COMMENT = Token.Comment
+SEPARATOR = Token.Punctuation
+SYNTAX = Token.Punctuation
+GHERKIN = Token.Generic.Emph
+ERROR = Token.Error
+
+
+def normalize(string, remove=''):
+ string = string.lower()
+ for char in remove + ' ':
+ if char in string:
+ string = string.replace(char, '')
+ return string
+
+
+class RobotFrameworkLexer(Lexer):
+ """
+ For `Robot Framework <http://robotframework.org>`_ test data.
+
+ Supports both space and pipe separated plain text formats.
+
+ *New in Pygments 1.6.*
+ """
+ name = 'RobotFramework'
+ aliases = ['RobotFramework', 'robotframework']
+ filenames = ['*.txt']
+ mimetypes = ['text/x-robotframework']
+
+ def __init__(self, **options):
+ options['tabsize'] = 2
+ options['encoding'] = 'UTF-8'
+ Lexer.__init__(self, **options)
+
+ def get_tokens_unprocessed(self, text):
+ row_tokenizer = RowTokenizer()
+ var_tokenizer = VariableTokenizer()
+ index = 0
+ for row in text.splitlines():
+ for value, token in row_tokenizer.tokenize(row):
+ for value, token in var_tokenizer.tokenize(value, token):
+ if value:
+ yield index, token, unicode(value)
+ index += len(value)
+
+
+class VariableTokenizer(object):
+
+ def tokenize(self, string, token):
+ var = VariableSplitter(string, identifiers='$@%')
+ if var.start < 0 or token in (COMMENT, ERROR):
+ yield string, token
+ return
+ for value, token in self._tokenize(var, string, token):
+ if value:
+ yield value, token
+
+ def _tokenize(self, var, string, orig_token):
+ before = string[:var.start]
+ yield before, orig_token
+ yield var.identifier + '{', SYNTAX
+ for value, token in self.tokenize(var.base, VARIABLE):
+ yield value, token
+ yield '}', SYNTAX
+ if var.index:
+ yield '[', SYNTAX
+ for value, token in self.tokenize(var.index, VARIABLE):
+ yield value, token
+ yield ']', SYNTAX
+ for value, token in self.tokenize(string[var.end:], orig_token):
+ yield value, token
+
+
+class RowTokenizer(object):
+
+ def __init__(self):
+ self._table = UnknownTable()
+ self._splitter = RowSplitter()
+ testcases = TestCaseTable()
+ settings = SettingTable(testcases.set_default_template)
+ variables = VariableTable()
+ keywords = KeywordTable()
+ self._tables = {'settings': settings, 'setting': settings,
+ 'metadata': settings,
+ 'variables': variables, 'variable': variables,
+ 'testcases': testcases, 'testcase': testcases,
+ 'keywords': keywords, 'keyword': keywords,
+ 'userkeywords': keywords, 'userkeyword': keywords}
+
+ def tokenize(self, row):
+ commented = False
+ heading = False
+ for index, value in enumerate(self._splitter.split(row)):
+ # First value, and every second after that, is a separator.
+ index, separator = divmod(index-1, 2)
+ if value.startswith('#'):
+ commented = True
+ elif index == 0 and value.startswith('*'):
+ self._table = self._start_table(value)
+ heading = True
+ for value, token in self._tokenize(value, index, commented,
+ separator, heading):
+ yield value, token
+ self._table.end_row()
+
+ def _start_table(self, header):
+ name = normalize(header, remove='*')
+ return self._tables.get(name, UnknownTable())
+
+ def _tokenize(self, value, index, commented, separator, heading):
+ if commented:
+ yield value, COMMENT
+ elif separator:
+ yield value, SEPARATOR
+ elif heading:
+ yield value, HEADING
+ else:
+ for value, token in self._table.tokenize(value, index):
+ yield value, token
+
+
+class RowSplitter(object):
+ _space_splitter = re.compile('( {2,})')
+ _pipe_splitter = re.compile('((?:^| +)\|(?: +|$))')
+
+ def split(self, row):
+ splitter = (row.startswith('| ') and self._split_from_pipes
+ or self._split_from_spaces)
+ for value in splitter(row.rstrip()):
+ yield value
+ yield '\n'
+
+ def _split_from_spaces(self, row):
+ yield '' # Start with (pseudo)separator similarly as with pipes
+ for value in self._space_splitter.split(row):
+ yield value
+
+ def _split_from_pipes(self, row):
+ _, separator, rest = self._pipe_splitter.split(row, 1)
+ yield separator
+ while self._pipe_splitter.search(rest):
+ cell, separator, rest = self._pipe_splitter.split(rest, 1)
+ yield cell
+ yield separator
+ yield rest
+
+
+class Tokenizer(object):
+ _tokens = None
+
+ def __init__(self):
+ self._index = 0
+
+ def tokenize(self, value):
+ values_and_tokens = self._tokenize(value, self._index)
+ self._index += 1
+ if isinstance(values_and_tokens, type(Token)):
+ values_and_tokens = [(value, values_and_tokens)]
+ return values_and_tokens
+
+ def _tokenize(self, value, index):
+ index = min(index, len(self._tokens) - 1)
+ return self._tokens[index]
+
+ def _is_assign(self, value):
+ if value.endswith('='):
+ value = value[:-1].strip()
+ var = VariableSplitter(value, identifiers='$@')
+ return var.start == 0 and var.end == len(value)
+
+
+class Comment(Tokenizer):
+ _tokens = (COMMENT,)
+
+
+class Setting(Tokenizer):
+ _tokens = (SETTING, ARGUMENT)
+ _keyword_settings = ('suitesetup', 'suiteprecondition', 'suiteteardown',
+ 'suitepostcondition', 'testsetup', 'testprecondition',
+ 'testteardown', 'testpostcondition', 'testtemplate')
+ _import_settings = ('library', 'resource', 'variables')
+ _other_settings = ('documentation', 'metadata', 'forcetags', 'defaulttags',
+ 'testtimeout')
+ _custom_tokenizer = None
+
+ def __init__(self, template_setter=None):
+ Tokenizer.__init__(self)
+ self._template_setter = template_setter
+
+ def _tokenize(self, value, index):
+ if index == 1 and self._template_setter:
+ self._template_setter(value)
+ if index == 0:
+ normalized = normalize(value)
+ if normalized in self._keyword_settings:
+ self._custom_tokenizer = KeywordCall(support_assign=False)
+ elif normalized in self._import_settings:
+ self._custom_tokenizer = ImportSetting()
+ elif normalized not in self._other_settings:
+ return ERROR
+ elif self._custom_tokenizer:
+ return self._custom_tokenizer.tokenize(value)
+ return Tokenizer._tokenize(self, value, index)
+
+
+class ImportSetting(Tokenizer):
+ _tokens = (IMPORT, ARGUMENT)
+
+
+class TestCaseSetting(Setting):
+ _keyword_settings = ('setup', 'precondition', 'teardown', 'postcondition',
+ 'template')
+ _import_settings = ()
+ _other_settings = ('documentation', 'tags', 'timeout')
+
+ def _tokenize(self, value, index):
+ if index == 0:
+ type = Setting._tokenize(self, value[1:-1], index)
+ return [('[', SYNTAX), (value[1:-1], type), (']', SYNTAX)]
+ return Setting._tokenize(self, value, index)
+
+
+class KeywordSetting(TestCaseSetting):
+ _keyword_settings = ('teardown',)
+ _other_settings = ('documentation', 'arguments', 'return', 'timeout')
+
+
+class Variable(Tokenizer):
+ _tokens = (SYNTAX, ARGUMENT)
+
+ def _tokenize(self, value, index):
+ if index == 0 and not self._is_assign(value):
+ return ERROR
+ return Tokenizer._tokenize(self, value, index)
+
+
+class KeywordCall(Tokenizer):
+ _tokens = (KEYWORD, ARGUMENT)
+
+ def __init__(self, support_assign=True):
+ Tokenizer.__init__(self)
+ self._keyword_found = not support_assign
+ self._assigns = 0
+
+ def _tokenize(self, value, index):
+ if not self._keyword_found and self._is_assign(value):
+ self._assigns += 1
+ return SYNTAX # VariableTokenizer tokenizes this later.
+ if self._keyword_found:
+ return Tokenizer._tokenize(self, value, index - self._assigns)
+ self._keyword_found = True
+ return GherkinTokenizer().tokenize(value, KEYWORD)
+
+
+class GherkinTokenizer(object):
+ _gherkin_prefix = re.compile('^(Given|When|Then|And) ', re.IGNORECASE)
+
+ def tokenize(self, value, token):
+ match = self._gherkin_prefix.match(value)
+ if not match:
+ return [(value, token)]
+ end = match.end()
+ return [(value[:end], GHERKIN), (value[end:], token)]
+
+
+class TemplatedKeywordCall(Tokenizer):
+ _tokens = (ARGUMENT,)
+
+
+class ForLoop(Tokenizer):
+
+ def __init__(self):
+ Tokenizer.__init__(self)
+ self._in_arguments = False
+
+ def _tokenize(self, value, index):
+ token = self._in_arguments and ARGUMENT or SYNTAX
+ if value.upper() in ('IN', 'IN RANGE'):
+ self._in_arguments = True
+ return token
+
+
+class _Table(object):
+ _tokenizer_class = None
+
+ def __init__(self, prev_tokenizer=None):
+ self._tokenizer = self._tokenizer_class()
+ self._prev_tokenizer = prev_tokenizer
+ self._prev_values_on_row = []
+
+ def tokenize(self, value, index):
+ if self._continues(value, index):
+ self._tokenizer = self._prev_tokenizer
+ yield value, SYNTAX
+ else:
+ for value_and_token in self._tokenize(value, index):
+ yield value_and_token
+ self._prev_values_on_row.append(value)
+
+ def _continues(self, value, index):
+ return value == '...' and all(self._is_empty(t)
+ for t in self._prev_values_on_row)
+
+ def _is_empty(self, value):
+ return value in ('', '\\')
+
+ def _tokenize(self, value, index):
+ return self._tokenizer.tokenize(value)
+
+ def end_row(self):
+ self.__init__(prev_tokenizer=self._tokenizer)
+
+
+class UnknownTable(_Table):
+ _tokenizer_class = Comment
+
+ def _continues(self, value, index):
+ return False
+
+
+class VariableTable(_Table):
+ _tokenizer_class = Variable
+
+
+class SettingTable(_Table):
+ _tokenizer_class = Setting
+
+ def __init__(self, template_setter, prev_tokenizer=None):
+ _Table.__init__(self, prev_tokenizer)
+ self._template_setter = template_setter
+
+ def _tokenize(self, value, index):
+ if index == 0 and normalize(value) == 'testtemplate':
+ self._tokenizer = Setting(self._template_setter)
+ return _Table._tokenize(self, value, index)
+
+ def end_row(self):
+ self.__init__(self._template_setter, prev_tokenizer=self._tokenizer)
+
+
+class TestCaseTable(_Table):
+ _setting_class = TestCaseSetting
+ _test_template = None
+ _default_template = None
+
+ @property
+ def _tokenizer_class(self):
+ if self._test_template or (self._default_template and
+ self._test_template is not False):
+ return TemplatedKeywordCall
+ return KeywordCall
+
+ def _continues(self, value, index):
+ return index > 0 and _Table._continues(self, value, index)
+
+ def _tokenize(self, value, index):
+ if index == 0:
+ if value:
+ self._test_template = None
+ return GherkinTokenizer().tokenize(value, TC_KW_NAME)
+ if index == 1 and self._is_setting(value):
+ if self._is_template(value):
+ self._test_template = False
+ self._tokenizer = self._setting_class(self.set_test_template)
+ else:
+ self._tokenizer = self._setting_class()
+ if index == 1 and self._is_for_loop(value):
+ self._tokenizer = ForLoop()
+ if index == 1 and self._is_empty(value):
+ return [(value, SYNTAX)]
+ return _Table._tokenize(self, value, index)
+
+ def _is_setting(self, value):
+ return value.startswith('[') and value.endswith(']')
+
+ def _is_template(self, value):
+ return normalize(value) == '[template]'
+
+ def _is_for_loop(self, value):
+ return value.startswith(':') and normalize(value, remove=':') == 'for'
+
+ def set_test_template(self, template):
+ self._test_template = self._is_template_set(template)
+
+ def set_default_template(self, template):
+ self._default_template = self._is_template_set(template)
+
+ def _is_template_set(self, template):
+ return normalize(template) not in ('', '\\', 'none', '${empty}')
+
+
+class KeywordTable(TestCaseTable):
+ _tokenizer_class = KeywordCall
+ _setting_class = KeywordSetting
+
+ def _is_template(self, value):
+ return False
+
+
+# Following code copied directly from Robot Framework 2.7.5.
+
+class VariableSplitter:
+
+ def __init__(self, string, identifiers):
+ self.identifier = None
+ self.base = None
+ self.index = None
+ self.start = -1
+ self.end = -1
+ self._identifiers = identifiers
+ self._may_have_internal_variables = False
+ try:
+ self._split(string)
+ except ValueError:
+ pass
+ else:
+ self._finalize()
+
+ def get_replaced_base(self, variables):
+ if self._may_have_internal_variables:
+ return variables.replace_string(self.base)
+ return self.base
+
+ def _finalize(self):
+ self.identifier = self._variable_chars[0]
+ self.base = ''.join(self._variable_chars[2:-1])
+ self.end = self.start + len(self._variable_chars)
+ if self._has_list_variable_index():
+ self.index = ''.join(self._list_variable_index_chars[1:-1])
+ self.end += len(self._list_variable_index_chars)
+
+ def _has_list_variable_index(self):
+ return self._list_variable_index_chars\
+ and self._list_variable_index_chars[-1] == ']'
+
+ def _split(self, string):
+ start_index, max_index = self._find_variable(string)
+ self.start = start_index
+ self._open_curly = 1
+ self._state = self._variable_state
+ self._variable_chars = [string[start_index], '{']
+ self._list_variable_index_chars = []
+ self._string = string
+ start_index += 2
+ for index, char in enumerate(string[start_index:]):
+ index += start_index # Giving start to enumerate only in Py 2.6+
+ try:
+ self._state(char, index)
+ except StopIteration:
+ return
+ if index == max_index and not self._scanning_list_variable_index():
+ return
+
+ def _scanning_list_variable_index(self):
+ return self._state in [self._waiting_list_variable_index_state,
+ self._list_variable_index_state]
+
+ def _find_variable(self, string):
+ max_end_index = string.rfind('}')
+ if max_end_index == -1:
+ return ValueError('No variable end found')
+ if self._is_escaped(string, max_end_index):
+ return self._find_variable(string[:max_end_index])
+ start_index = self._find_start_index(string, 1, max_end_index)
+ if start_index == -1:
+ return ValueError('No variable start found')
+ return start_index, max_end_index
+
+ def _find_start_index(self, string, start, end):
+ index = string.find('{', start, end) - 1
+ if index < 0:
+ return -1
+ if self._start_index_is_ok(string, index):
+ return index
+ return self._find_start_index(string, index+2, end)
+
+ def _start_index_is_ok(self, string, index):
+ return string[index] in self._identifiers\
+ and not self._is_escaped(string, index)
+
+ def _is_escaped(self, string, index):
+ escaped = False
+ while index > 0 and string[index-1] == '\\':
+ index -= 1
+ escaped = not escaped
+ return escaped
+
+ def _variable_state(self, char, index):
+ self._variable_chars.append(char)
+ if char == '}' and not self._is_escaped(self._string, index):
+ self._open_curly -= 1
+ if self._open_curly == 0:
+ if not self._is_list_variable():
+ raise StopIteration
+ self._state = self._waiting_list_variable_index_state
+ elif char in self._identifiers:
+ self._state = self._internal_variable_start_state
+
+ def _is_list_variable(self):
+ return self._variable_chars[0] == '@'
+
+ def _internal_variable_start_state(self, char, index):
+ self._state = self._variable_state
+ if char == '{':
+ self._variable_chars.append(char)
+ self._open_curly += 1
+ self._may_have_internal_variables = True
+ else:
+ self._variable_state(char, index)
+
+ def _waiting_list_variable_index_state(self, char, index):
+ if char != '[':
+ raise StopIteration
+ self._list_variable_index_chars.append(char)
+ self._state = self._list_variable_index_state
+
+ def _list_variable_index_state(self, char, index):
+ self._list_variable_index_chars.append(char)
+ if char == ']':
+ raise StopIteration
diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py
index c1d46bcb..a87ca9c2 100644
--- a/pygments/lexers/asm.py
+++ b/pygments/lexers/asm.py
@@ -240,8 +240,8 @@ class LlvmLexer(RegexLexer):
r'|linkonce_odr|weak|weak_odr|appending|dllimport|dllexport'
r'|common|default|hidden|protected|extern_weak|external'
r'|thread_local|zeroinitializer|undef|null|to|tail|target|triple'
- r'|deplibs|datalayout|volatile|nuw|nsw|exact|inbounds|align'
- r'|addrspace|section|alias|module|asm|sideeffect|gc|dbg'
+ r'|datalayout|volatile|nuw|nsw|nnan|ninf|nsz|arcp|fast|exact|inbounds'
+ r'|align|addrspace|section|alias|module|asm|sideeffect|gc|dbg'
r'|ccc|fastcc|coldcc|x86_stdcallcc|x86_fastcallcc|arm_apcscc'
r'|arm_aapcscc|arm_aapcs_vfpcc'
diff --git a/pygments/lexers/compiled.py b/pygments/lexers/compiled.py
index 66b782e5..f8055fc5 100644
--- a/pygments/lexers/compiled.py
+++ b/pygments/lexers/compiled.py
@@ -27,7 +27,8 @@ __all__ = ['CLexer', 'CppLexer', 'DLexer', 'DelphiLexer', 'ECLexer',
'DylanLexer', 'ObjectiveCLexer', 'FortranLexer', 'GLShaderLexer',
'PrologLexer', 'CythonLexer', 'ValaLexer', 'OocLexer', 'GoLexer',
'FelixLexer', 'AdaLexer', 'Modula2Lexer', 'BlitzMaxLexer',
- 'NimrodLexer', 'FantomLexer', 'RustLexer', 'CudaLexer', 'MonkeyLexer']
+ 'NimrodLexer', 'FantomLexer', 'RustLexer', 'CudaLexer', 'MonkeyLexer',
+ 'DylanLidLexer']
class CLexer(RegexLexer):
@@ -1057,40 +1058,176 @@ class DylanLexer(RegexLexer):
name = 'Dylan'
aliases = ['dylan']
- filenames = ['*.dylan', '*.dyl']
+ filenames = ['*.dylan', '*.dyl', '*.intr']
mimetypes = ['text/x-dylan']
- flags = re.DOTALL
+ flags = re.IGNORECASE
+
+ builtins = set([
+ 'subclass', 'abstract', 'block', 'concrete', 'constant', 'class',
+ 'compiler-open', 'compiler-sideways', 'domain', 'dynamic',
+ 'each-subclass', 'exception', 'exclude', 'function', 'generic',
+ 'handler', 'inherited', 'inline', 'inline-only', 'instance',
+ 'interface', 'import', 'keyword', 'library', 'macro', 'method',
+ 'module', 'open', 'primary', 'required', 'sealed', 'sideways',
+ 'singleton', 'slot', 'thread', 'variable', 'virtual'])
+
+ keywords = set([
+ 'above', 'afterwards', 'begin', 'below', 'by', 'case', 'cleanup',
+ 'create', 'define', 'else', 'elseif', 'end', 'export', 'finally',
+ 'for', 'from', 'if', 'in', 'let', 'local', 'otherwise', 'rename',
+ 'select', 'signal', 'then', 'to', 'unless', 'until', 'use', 'when',
+ 'while'])
+
+ operators = set([
+ '~', '+', '-', '*', '|', '^', '=', '==', '~=', '~==', '<', '<=',
+ '>', '>=', '&', '|'])
+
+ functions = set([
+ 'abort', 'abs', 'add', 'add!', 'add-method', 'add-new', 'add-new!',
+ 'all-superclasses', 'always', 'any?', 'applicable-method?', 'apply',
+ 'aref', 'aref-setter', 'as', 'as-lowercase', 'as-lowercase!',
+ 'as-uppercase', 'as-uppercase!', 'ash', 'backward-iteration-protocol',
+ 'break', 'ceiling', 'ceiling/', 'cerror', 'check-type', 'choose',
+ 'choose-by', 'complement', 'compose', 'concatenate', 'concatenate-as',
+ 'condition-format-arguments', 'condition-format-string', 'conjoin',
+ 'copy-sequence', 'curry', 'default-handler', 'dimension', 'dimensions',
+ 'direct-subclasses', 'direct-superclasses', 'disjoin', 'do',
+ 'do-handlers', 'element', 'element-setter', 'empty?', 'error', 'even?',
+ 'every?', 'false-or', 'fill!', 'find-key', 'find-method', 'first',
+ 'first-setter', 'floor', 'floor/', 'forward-iteration-protocol',
+ 'function-arguments', 'function-return-values',
+ 'function-specializers', 'gcd', 'generic-function-mandatory-keywords',
+ 'generic-function-methods', 'head', 'head-setter', 'identity',
+ 'initialize', 'instance?', 'integral?', 'intersection',
+ 'key-sequence', 'key-test', 'last', 'last-setter', 'lcm', 'limited',
+ 'list', 'logand', 'logbit?', 'logior', 'lognot', 'logxor', 'make',
+ 'map', 'map-as', 'map-into', 'max', 'member?', 'merge-hash-codes',
+ 'min', 'modulo', 'negative', 'negative?', 'next-method',
+ 'object-class', 'object-hash', 'odd?', 'one-of', 'pair', 'pop',
+ 'pop-last', 'positive?', 'push', 'push-last', 'range', 'rank',
+ 'rcurry', 'reduce', 'reduce1', 'remainder', 'remove', 'remove!',
+ 'remove-duplicates', 'remove-duplicates!', 'remove-key!',
+ 'remove-method', 'replace-elements!', 'replace-subsequence!',
+ 'restart-query', 'return-allowed?', 'return-description',
+ 'return-query', 'reverse', 'reverse!', 'round', 'round/',
+ 'row-major-index', 'second', 'second-setter', 'shallow-copy',
+ 'signal', 'singleton', 'size', 'size-setter', 'slot-initialized?',
+ 'sort', 'sort!', 'sorted-applicable-methods', 'subsequence-position',
+ 'subtype?', 'table-protocol', 'tail', 'tail-setter', 'third',
+ 'third-setter', 'truncate', 'truncate/', 'type-error-expected-type',
+ 'type-error-value', 'type-for-copy', 'type-union', 'union', 'values',
+ 'vector', 'zero?'])
+
+ valid_name = '\\\\?[a-zA-Z0-9' + re.escape('!&*<>|^$%@_-+~?/=') + ']+'
+
+ def get_tokens_unprocessed(self, text):
+ for index, token, value in RegexLexer.get_tokens_unprocessed(self, text):
+ if token is Name:
+ if value in self.builtins:
+ yield index, Name.Builtin, value
+ continue
+ if value in self.keywords:
+ yield index, Keyword, value
+ continue
+ if value in self.functions:
+ yield index, Name.Builtin, value
+ continue
+ if value in self.operators:
+ yield index, Operator, value
+ continue
+ yield index, token, value
tokens = {
'root': [
- (r'\b(subclass|abstract|block|c(on(crete|stant)|lass)|domain'
- r'|ex(c(eption|lude)|port)|f(unction(al)?)|generic|handler'
- r'|i(n(herited|line|stance|terface)|mport)|library|m(acro|ethod)'
- r'|open|primary|sealed|si(deways|ngleton)|slot'
- r'|v(ariable|irtual))\b', Name.Builtin),
- (r'<\w+>', Keyword.Type),
+ # Whitespace
+ (r'\s+', Text),
+
+ # single line comment
+ (r'//.*?\n', Comment.Single),
+
+ # lid header
+ (r'([A-Za-z0-9-]+)(:)([ \t]*)(.*(?:\n[ \t].+)*)',
+ bygroups(Name.Attribute, Operator, Text, String)),
+
+ ('', Text, 'code') # no header match, switch to code
+ ],
+ 'code': [
+ # Whitespace
+ (r'\s+', Text),
+
+ # single line comment
(r'//.*?\n', Comment.Single),
- (r'/\*[\w\W]*?\*/', Comment.Multiline),
+
+ # multi-line comment
+ (r'/\*', Comment.Multiline, 'comment'),
+
+ # strings and characters
(r'"', String, 'string'),
(r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
- (r'=>|\b(a(bove|fterwards)|b(e(gin|low)|y)|c(ase|leanup|reate)'
- r'|define|else(if)?|end|f(inally|or|rom)|i[fn]|l(et|ocal)|otherwise'
- r'|rename|s(elect|ignal)|t(hen|o)|u(n(less|til)|se)|wh(en|ile))\b',
- Keyword),
- (r'([ \t])([!\$%&\*\/:<=>\?~_^a-zA-Z0-9.+\-]*:)',
- bygroups(Text, Name.Variable)),
- (r'([ \t]*)(\S+[^:])([ \t]*)(\()([ \t]*)',
- bygroups(Text, Name.Function, Text, Punctuation, Text)),
- (r'-?[0-9.]+', Number),
- (r'[(),;]', Punctuation),
- (r'\$[a-zA-Z0-9-]+', Name.Constant),
- (r'[!$%&*/:<>=?~^.+\[\]{}-]+', Operator),
- (r'\s+', Text),
- (r'#"[a-zA-Z0-9-]+"', Keyword),
+
+ # binary integer
+ (r'#[bB][01]+', Number),
+
+ # octal integer
+ (r'#[oO][0-7]+', Number.Oct),
+
+ # floating point
+ (r'[-+]?(\d*\.\d+(e[-+]?\d+)?|\d+(\.\d*)?e[-+]?\d+)', Number.Float),
+
+ # decimal integer
+ (r'[-+]?\d+', Number.Integer),
+
+ # hex integer
+ (r'#[xX][0-9a-fA-F]+', Number.Hex),
+
+ # Macro parameters
+ (r'(\?' + valid_name + ')(:)(token|name|variable|expression|body|case-body|\*)',
+ bygroups(Name.Tag, Operator, Name.Builtin)),
+ (r'(\?)(:)(token|name|variable|expression|body|case-body|\*)',
+ bygroups(Name.Tag, Operator, Name.Builtin)),
+ (r'\?' + valid_name, Name.Tag),
+
+ # Punctuation
+ (r'(=>|::|#\(|#\[|##|\?|\?\?|\?=|[(){}\[\],\.;])', Punctuation),
+
+ # Most operators are picked up as names and then re-flagged.
+ # This one isn't valid in a name though, so we pick it up now.
+ (r':=', Operator),
+
+ # Pick up #t / #f before we match other stuff with #.
+ (r'#[tf]', Literal),
+
+ # #"foo" style keywords
+ (r'#"', String.Symbol, 'keyword'),
+
+ # #rest, #key, #all-keys, etc.
(r'#[a-zA-Z0-9-]+', Keyword),
- (r'#(\(|\[)', Punctuation),
- (r'[a-zA-Z0-9-_]+', Name.Variable),
+
+ # required-init-keyword: style keywords.
+ (valid_name + ':', Keyword),
+
+ # class names
+ (r'<' + valid_name + '>', Name.Class),
+
+ # define variable forms.
+ (r'\*' + valid_name + '\*', Name.Variable.Global),
+
+ # define constant forms.
+ (r'\$' + valid_name, Name.Constant),
+
+ # everything else. We re-flag some of these in the method above.
+ (valid_name, Name),
+ ],
+ 'comment': [
+ (r'[^*/]', Comment.Multiline),
+ (r'/\*', Comment.Multiline, '#push'),
+ (r'\*/', Comment.Multiline, '#pop'),
+ (r'[*/]', Comment.Multiline)
+ ],
+ 'keyword': [
+ (r'"', String.Symbol, '#pop'),
+ (r'[^\\"]+', String.Symbol), # all other characters
],
'string': [
(r'"', String, '#pop'),
@@ -1098,7 +1235,36 @@ class DylanLexer(RegexLexer):
(r'[^\\"\n]+', String), # all other characters
(r'\\\n', String), # line continuation
(r'\\', String), # stray backslash
- ],
+ ]
+ }
+
+
+class DylanLidLexer(RegexLexer):
+ """
+ For Dylan LID (Library Interchange Definition) files.
+
+ *New in Pygments 1.6.*
+ """
+
+ name = 'DylanLID'
+ aliases = ['dylan-lid', 'lid']
+ filenames = ['*.lid', '*.hdp']
+ mimetypes = ['text/x-dylan-lid']
+
+ flags = re.IGNORECASE
+
+ tokens = {
+ 'root': [
+ # Whitespace
+ (r'\s+', Text),
+
+ # single line comment
+ (r'//.*?\n', Comment.Single),
+
+ # lid header
+ (r'(.*?)(:)([ \t]*)(.*(?:\n[ \t].+)*)',
+ bygroups(Name.Attribute, Operator, Text, String)),
+ ]
}
@@ -2943,13 +3109,13 @@ class RustLexer(RegexLexer):
(r'/[*](.|\n)*?[*]/', Comment.Multiline),
# Keywords
- (r'(alt|as|assert|be|break|check|claim|class|const'
- r'|cont|copy|crust|do|else|enum|export|fail'
- r'|false|fn|for|if|iface|impl|import|let|log'
- r'|loop|mod|mut|native|pure|resource|ret|true'
- r'|type|unsafe|use|white|note|bind|prove|unchecked'
- r'|with|syntax|u8|u16|u32|u64|i8|i16|i32|i64|uint'
- r'|int|f32|f64)\b', Keyword),
+ (r'(as|assert|break|const'
+ r'|copy|do|else|enum|extern|fail'
+ r'|false|fn|for|if|impl|let|log'
+ r'|loop|match|mod|move|mut|once|priv|pub|pure'
+ r'|ref|return|static|struct|trait|true|type|unsafe|use|while'
+ r'|u8|u16|u32|u64|i8|i16|i32|i64|uint'
+ r'|int|float|f32|f64|str)\b', Keyword),
# Character Literal
(r"""'(\\['"\\nrt]|\\x[0-9a-fA-F]{2}|\\[0-7]{1,3}"""
@@ -2978,8 +3144,8 @@ class RustLexer(RegexLexer):
(r'#\[', Comment.Preproc, 'attribute['),
(r'#\(', Comment.Preproc, 'attribute('),
# Macros
- (r'#[A-Za-z_][A-Za-z0-9_]*\[', Comment.Preproc, 'attribute['),
- (r'#[A-Za-z_][A-Za-z0-9_]*\(', Comment.Preproc, 'attribute('),
+ (r'[A-Za-z_][A-Za-z0-9_]*!\[', Comment.Preproc, 'attribute['),
+ (r'[A-Za-z_][A-Za-z0-9_]*!\(', Comment.Preproc, 'attribute('),
],
'number_lit': [
(r'(([ui](8|16|32|64)?)|(f(32|64)?))?', Keyword, '#pop'),
diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py
index 83eb02f5..d337c3f2 100644
--- a/pygments/lexers/jvm.py
+++ b/pygments/lexers/jvm.py
@@ -675,7 +675,7 @@ class ClojureLexer(RegexLexer):
(r'::?' + valid_name, String.Symbol),
# special operators
- (r'~@|[`\'#^~&]', Operator),
+ (r'~@|[`\'#^~&@]', Operator),
# highlight the special forms
(_multi_escape(special_forms), Keyword),
diff --git a/pygments/lexers/math.py b/pygments/lexers/math.py
index 0e78bb49..5f6bb7c8 100644
--- a/pygments/lexers/math.py
+++ b/pygments/lexers/math.py
@@ -11,6 +11,7 @@
import re
+from pygments.util import shebang_matches
from pygments.lexer import Lexer, RegexLexer, bygroups, include, \
combined, do_insertions
from pygments.token import Comment, String, Punctuation, Keyword, Name, \
@@ -97,8 +98,8 @@ class JuliaLexer(RegexLexer):
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name),
# numbers
- (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float),
- (r'\d+[eE][+-]?[0-9]+', Number.Float),
+ (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
+ (r'\d+[eEf][+-]?[0-9]+', Number.Float),
(r'0b[01]+', Number.Binary),
(r'0o[0-7]+', Number.Oct),
(r'0x[a-fA-F0-9]+', Number.Hex),
@@ -342,6 +343,10 @@ class MatlabLexer(RegexLexer):
# (not great, but handles common cases...)
(r'(?<=[\w\)\]])\'', Operator),
+ (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
+ (r'\d+[eEf][+-]?[0-9]+', Number.Float),
+ (r'\d+', Number.Integer),
+
(r'(?<![\w\)\]])\'', String, 'string'),
('[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'.', Text),
@@ -788,6 +793,10 @@ class OctaveLexer(RegexLexer):
(r'"[^"]*"', String),
+ (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
+ (r'\d+[eEf][+-]?[0-9]+', Number.Float),
+ (r'\d+', Number.Integer),
+
# quote can be transpose, instead of string:
# (not great, but handles common cases...)
(r'(?<=[\w\)\]])\'', Operator),
@@ -859,6 +868,10 @@ class ScilabLexer(RegexLexer):
(r'(?<=[\w\)\]])\'', Operator),
(r'(?<![\w\)\]])\'', String, 'string'),
+ (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
+ (r'\d+[eEf][+-]?[0-9]+', Number.Float),
+ (r'\d+', Number.Integer),
+
('[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'.', Text),
],
diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py
index 8cef26ca..35a8a813 100644
--- a/pygments/lexers/other.py
+++ b/pygments/lexers/other.py
@@ -19,6 +19,7 @@ from pygments.util import get_bool_opt
from pygments.lexers.web import HtmlLexer
from pygments.lexers._openedgebuiltins import OPENEDGEKEYWORDS
+from pygments.lexers._robotframeworklexer import RobotFrameworkLexer
# backwards compatibility
from pygments.lexers.sql import SqlLexer, MySqlLexer, SqliteConsoleLexer
@@ -32,7 +33,8 @@ __all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'MOOCodeLexer',
'AutohotkeyLexer', 'GoodDataCLLexer', 'MaqlLexer', 'ProtoBufLexer',
'HybrisLexer', 'AwkLexer', 'Cfengine3Lexer', 'SnobolLexer',
'ECLLexer', 'UrbiscriptLexer', 'OpenEdgeLexer', 'BroLexer',
- 'MscgenLexer', 'KconfigLexer', 'VGLLexer', 'SourcePawnLexer', 'NSISLexer']
+ 'MscgenLexer', 'KconfigLexer', 'VGLLexer', 'SourcePawnLexer',
+ 'RobotFrameworkLexer', 'PuppetLexer', 'NSISLexer']
class ECLLexer(RegexLexer):
@@ -1255,7 +1257,8 @@ class ModelicaLexer(RegexLexer):
],
'classes': [
(r'(block|class|connector|function|model|package|'
- r'record|type)\b', Name.Class),
+ r'record|type)(\s+)([A-Za-z_]+)',
+ bygroups(Keyword, Text, Name.Class))
],
'string': [
(r'"', String, '#pop'),
@@ -2771,7 +2774,7 @@ class OpenEdgeLexer(RegexLexer):
keywords = (r'(?i)(^|(?<=[^0-9a-z_\-]))(' +
r'|'.join(OPENEDGEKEYWORDS) +
- r')\s*($|(?=[^0-9a-z_\-]))')
+ r')\s*($|(?=[^0-9a-z_\-]))')
tokens = {
'root': [
(r'/\*', Comment.Multiline, 'comment'),
@@ -3156,10 +3159,91 @@ class SourcePawnLexer(RegexLexer):
if value in self.SM_TYPES:
token = Keyword.Type
elif value in self._functions:
- tokens = Name.Builtin
+ token = Name.Builtin
yield index, token, value
+class PuppetLexer(RegexLexer):
+ """
+ For `Puppet <http://puppetlabs.com/>`__ configuration DSL.
+
+ *New in Pygments 1.6.*
+ """
+ name = 'Puppet'
+ aliases = ['puppet']
+ filenames = ['*.pp']
+
+ tokens = {
+ 'root': [
+ include('comments'),
+ include('keywords'),
+ include('names'),
+ include('numbers'),
+ include('operators'),
+ include('strings'),
+
+ (r'[]{}:(),;[]', Punctuation),
+ (r'[^\S\n]+', Text),
+ ],
+
+ 'comments': [
+ (r'\s*#.*$', Comment),
+ (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
+ ],
+
+ 'operators': [
+ (r'(=>|\?|<|>|=|\+|-|/|\*|~|!|\|)', Operator),
+ (r'(in|and|or|not)\b', Operator.Word),
+ ],
+
+ 'names': [
+ ('[a-zA-Z_][a-zA-Z0-9_]*', Name.Attribute),
+ (r'(\$\S+)(\[)(\S+)(\])', bygroups(Name.Variable, Punctuation,
+ String, Punctuation)),
+ (r'\$\S+', Name.Variable),
+ ],
+
+ 'numbers': [
+ # Copypasta from the Python lexer
+ (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[xX][a-fA-F0-9]+', Number.Hex),
+ (r'\d+L', Number.Integer.Long),
+ (r'\d+j?', Number.Integer)
+ ],
+
+ 'keywords': [
+ # Left out 'group' and 'require'
+ # Since they're often used as attributes
+ (r'(?i)(absent|alert|alias|audit|augeas|before|case|check|class|'
+ r'computer|configured|contained|create_resources|crit|cron|debug|'
+ r'default|define|defined|directory|else|elsif|emerg|err|exec|'
+ r'extlookup|fail|false|file|filebucket|fqdn_rand|generate|host|if|'
+ r'import|include|info|inherits|inline_template|installed|'
+ r'interface|k5login|latest|link|loglevel|macauthorization|'
+ r'mailalias|maillist|mcx|md5|mount|mounted|nagios_command|'
+ r'nagios_contact|nagios_contactgroup|nagios_host|'
+ r'nagios_hostdependency|nagios_hostescalation|nagios_hostextinfo|'
+ r'nagios_hostgroup|nagios_service|nagios_servicedependency|'
+ r'nagios_serviceescalation|nagios_serviceextinfo|'
+ r'nagios_servicegroup|nagios_timeperiod|node|noop|notice|notify|'
+ r'package|present|purged|realize|regsubst|resources|role|router|'
+ r'running|schedule|scheduled_task|search|selboolean|selmodule|'
+ r'service|sha1|shellquote|split|sprintf|ssh_authorized_key|sshkey|'
+ r'stage|stopped|subscribe|tag|tagged|template|tidy|true|undef|'
+ r'unmounted|user|versioncmp|vlan|warning|yumrepo|zfs|zone|'
+ r'zpool)\b', Keyword),
+ ],
+
+ 'strings': [
+ (r'"([^"])*"', String),
+ (r'\'([^\'])*\'', String),
+ ],
+
+ }
+
+
class NSISLexer(RegexLexer):
"""
For `NSIS <http://nsis.sourceforge.net/>`_ scripts.
@@ -3187,7 +3271,8 @@ class NSISLexer(RegexLexer):
('.', Text),
],
'basic': [
- (r'(\n)(Function)(\s+)([\.\_a-zA-Z][\.\_a-zA-Z0-9]*)\b',bygroups(Text, Keyword, Text, Name.Function)),
+ (r'(\n)(Function)(\s+)([\.\_a-zA-Z][\.\_a-zA-Z0-9]*)\b',
+ bygroups(Text, Keyword, Text, Name.Function)),
(r'\b([_a-zA-Z][_a-zA-Z0-9]*)(::)([a-zA-Z][a-zA-Z0-9]*)\b',
bygroups(Keyword.Namespace, Punctuation, Name.Function)),
(r'\b([_a-zA-Z][_a-zA-Z0-9]*)(:)', bygroups(Name.Label, Punctuation)),
diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py
index ca50665e..7b3624d0 100644
--- a/pygments/lexers/text.py
+++ b/pygments/lexers/text.py
@@ -25,7 +25,7 @@ __all__ = ['IniLexer', 'PropertiesLexer', 'SourcesListLexer', 'BaseMakefileLexer
'RstLexer', 'VimLexer', 'GettextLexer', 'SquidConfLexer',
'DebianControlLexer', 'DarcsPatchLexer', 'YamlLexer',
'LighttpdConfLexer', 'NginxConfLexer', 'CMakeLexer', 'HttpLexer',
- 'PyPyLogLexer', 'RegeditLexer']
+ 'PyPyLogLexer', 'RegeditLexer', 'HxmlLexer']
class IniLexer(RegexLexer):
@@ -1749,8 +1749,8 @@ class PyPyLogLexer(RegexLexer):
],
"jit-log": [
(r"\[\w+\] jit-log-.*?}$", Keyword, "#pop"),
-
(r"^\+\d+: ", Comment),
+ (r"--end of the loop--", Comment),
(r"[ifp]\d+", Name),
(r"ptr\d+", Name),
(r"(\()(\w+(?:\.\w+)?)(\))",
@@ -1760,7 +1760,7 @@ class PyPyLogLexer(RegexLexer):
(r"-?\d+", Number.Integer),
(r"'.*'", String),
(r"(None|descr|ConstClass|ConstPtr|TargetToken)", Name),
- (r"<.*?>", Name.Builtin),
+ (r"<.*?>+", Name.Builtin),
(r"(label|debug_merge_point|jump|finish)", Name.Class),
(r"(int_add_ovf|int_add|int_sub_ovf|int_sub|int_mul_ovf|int_mul|"
r"int_floordiv|int_mod|int_lshift|int_rshift|int_and|int_or|"
@@ -1800,3 +1800,44 @@ class PyPyLogLexer(RegexLexer):
(r"#.*?$", Comment),
],
}
+
+
+class HxmlLexer(RegexLexer):
+ """
+ Lexer for `haXe build <http://haxe.org/doc/compiler>`_ files.
+
+ *New in Pygments 1.6.*
+ """
+ name = 'Hxml'
+ aliases = ['haxeml', 'hxml']
+ filenames = ['*.hxml']
+
+ tokens = {
+ 'root': [
+ # Seperator
+ (r'(--)(next)', bygroups(Punctuation, Generic.Heading)),
+ # Compiler switches with one dash
+ (r'(-)(prompt|debug|v)', bygroups(Punctuation, Keyword.Keyword)),
+ # Compilerswitches with two dashes
+ (r'(--)(neko-source|flash-strict|flash-use-stage|no-opt|no-traces|'
+ r'no-inline|times|no-output)', bygroups(Punctuation, Keyword)),
+ # Targets and other options that take an argument
+ (r'(-)(cpp|js|neko|x|as3|swf9?|swf-lib|php|xml|main|lib|D|resource|'
+ r'cp|cmd)( +)(.+)',
+ bygroups(Punctuation, Keyword, Whitespace, String)),
+ # Options that take only numerical arguments
+ (r'(-)(swf-version)( +)(\d+)',
+ bygroups(Punctuation, Keyword, Number.Integer)),
+ # An Option that defines the size, the fps and the background
+ # color of an flash movie
+ (r'(-)(swf-header)( +)(\d+)(:)(\d+)(:)(\d+)(:)([A-Fa-f0-9]{6})',
+ bygroups(Punctuation, Keyword, Whitespace, Number.Integer,
+ Punctuation, Number.Integer, Punctuation, Number.Integer,
+ Punctuation, Number.Hex)),
+ # options with two dashes that takes arguments
+ (r'(--)(js-namespace|php-front|php-lib|remap|gen-hx-classes)( +)'
+ r'(.+)', bygroups(Punctuation, Keyword, Whitespace, String)),
+ # Single line comment, multiline ones are not allowed.
+ (r'#.*', Comment.Single)
+ ]
+ }
diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py
index 79245d34..c6e58f01 100644
--- a/pygments/lexers/web.py
+++ b/pygments/lexers/web.py
@@ -1762,7 +1762,7 @@ class ScssLexer(RegexLexer):
(r'(@include)( [\w-]+)', bygroups(Keyword, Name.Decorator), 'value'),
(r'@extend', Keyword, 'selector'),
(r'@[a-z0-9_-]+', Keyword, 'selector'),
- (r'(\$[\w-]\w*)([ \t]*:)', bygroups(Name.Variable, Operator), 'value'),
+ (r'(\$[\w-]*\w)([ \t]*:)', bygroups(Name.Variable, Operator), 'value'),
(r'(?=[^;{}][;}])', Name.Attribute, 'attr'),
(r'(?=[^;{}:]+:[^a-z])', Name.Attribute, 'attr'),
(r'', Text, 'selector'),