diff options
Diffstat (limited to 'pygments/lexers/text.py')
| -rw-r--r-- | pygments/lexers/text.py | 198 |
1 files changed, 159 insertions, 39 deletions
diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py index de9979cf..c0679aa6 100644 --- a/pygments/lexers/text.py +++ b/pygments/lexers/text.py @@ -5,7 +5,7 @@ Lexers for non-source code file types. - :copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -25,7 +25,8 @@ __all__ = ['IniLexer', 'PropertiesLexer', 'SourcesListLexer', 'BaseMakefileLexer 'RstLexer', 'VimLexer', 'GettextLexer', 'SquidConfLexer', 'DebianControlLexer', 'DarcsPatchLexer', 'YamlLexer', 'LighttpdConfLexer', 'NginxConfLexer', 'CMakeLexer', 'HttpLexer', - 'PyPyLogLexer', 'RegeditLexer', 'HxmlLexer', 'EbnfLexer'] + 'PyPyLogLexer', 'RegeditLexer', 'HxmlLexer', 'EbnfLexer', + 'TodotxtLexer'] class IniLexer(RegexLexer): @@ -61,7 +62,7 @@ class RegeditLexer(RegexLexer): <http://en.wikipedia.org/wiki/Windows_Registry#.REG_files>`_ files produced by regedit. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'reg' @@ -102,7 +103,7 @@ class PropertiesLexer(RegexLexer): """ Lexer for configuration files in Java's properties format. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Properties' @@ -124,7 +125,7 @@ class SourcesListLexer(RegexLexer): """ Lexer that highlights debian sources.list files. - *New in Pygments 0.7.* + .. versionadded:: 0.7 """ name = 'Debian Sourcelist' @@ -180,7 +181,7 @@ class MakefileLexer(Lexer): name = 'Makefile' aliases = ['make', 'makefile', 'mf', 'bsdmake'] - filenames = ['*.mak', 'Makefile', 'makefile', 'Makefile.*', 'GNUmakefile'] + filenames = ['*.mak', '*.mk', 'Makefile', 'makefile', 'Makefile.*', 'GNUmakefile'] mimetypes = ['text/x-makefile'] r_special = re.compile(r'^(?:' @@ -207,12 +208,17 @@ class MakefileLexer(Lexer): for item in do_insertions(ins, lex.get_tokens_unprocessed(done)): yield item + def analyse_text(text): + # Many makefiles have $(BIG_CAPS) style variables + if re.search(r'\$\([A-Z_]+\)', text): + return 0.1 + class BaseMakefileLexer(RegexLexer): """ Lexer for simple Makefiles (no preprocessing). - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Base Makefile' @@ -222,8 +228,10 @@ class BaseMakefileLexer(RegexLexer): tokens = { 'root': [ + # recipes (need to allow spaces because of expandtabs) (r'^(?:[\t ]+.*\n|\n)+', using(BashLexer)), - (r'\$\((?:.*\\\n|.*\n)+', using(BashLexer)), + # special variables + (r'\$[<@$+%?|*]', Keyword), (r'\s+', Text), (r'#.*?\n', Comment), (r'(export)(\s+)(?=[a-zA-Z0-9_${}\t -]+\n)', @@ -238,7 +246,15 @@ class BaseMakefileLexer(RegexLexer): # targets (r'([^\n:]+)(:+)([ \t]*)', bygroups(Name.Function, Operator, Text), 'block-header'), - # TODO: add paren handling (grr) + # expansions + (r'\$\(', Keyword, 'expansion'), + ], + 'expansion': [ + (r'[^$a-zA-Z_)]+', Text), + (r'[a-zA-Z_]+', Name.Variable), + (r'\$', Keyword), + (r'\(', Keyword, '#push'), + (r'\)', Keyword, '#pop'), ], 'export': [ (r'[a-zA-Z0-9_${}-]+', Name.Variable), @@ -246,12 +262,13 @@ class BaseMakefileLexer(RegexLexer): (r'\s+', Text), ], 'block-header': [ - (r'[^,\\\n#]+', Number), - (r',', Punctuation), - (r'#.*?\n', Comment), + (r'[,|]', Punctuation), + (r'#.*?\n', Comment, '#pop'), (r'\\\n', Text), # line continuation - (r'\\.', Text), - (r'(?:[\t ]+.*\n|\n)+', using(BashLexer), '#pop'), + (r'\$\(', Keyword, 'expansion'), + (r'[a-zA-Z_]+', Name), + (r'\n', Text, '#pop'), + (r'.', Text), ], } @@ -297,7 +314,7 @@ class DarcsPatchLexer(RegexLexer): format. Examples of this format are derived by commands such as ``darcs annotate --patch`` and ``darcs send``. - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Darcs Patch' aliases = ['dpatch'] @@ -410,7 +427,7 @@ class BBCodeLexer(RegexLexer): """ A lexer that highlights BBCode(-like) syntax. - *New in Pygments 0.6.* + .. versionadded:: 0.6 """ name = 'BBCode' @@ -501,7 +518,7 @@ class GroffLexer(RegexLexer): Lexer for the (g)roff typesetting language, supporting groff extensions. Mainly useful for highlighting manpage sources. - *New in Pygments 0.6.* + .. versionadded:: 0.6 """ name = 'Groff' @@ -556,7 +573,7 @@ class ApacheConfLexer(RegexLexer): Lexer for configuration files following the Apache config file format. - *New in Pygments 0.6.* + .. versionadded:: 0.6 """ name = 'ApacheConf' @@ -595,7 +612,7 @@ class MoinWikiLexer(RegexLexer): """ For MoinMoin (and Trac) Wiki markup. - *New in Pygments 0.7.* + .. versionadded:: 0.7 """ name = 'MoinMoin/Trac Wiki markup' @@ -640,14 +657,17 @@ class RstLexer(RegexLexer): """ For `reStructuredText <http://docutils.sf.net/rst.html>`_ markup. - *New in Pygments 0.7.* + .. versionadded:: 0.7 Additional options accepted: `handlecodeblocks` - Highlight the contents of ``.. sourcecode:: langauge`` and - ``.. code:: language`` directives with a lexer for the given - language (default: ``True``). *New in Pygments 0.8.* + Highlight the contents of ``.. sourcecode:: language``, + ``.. code:: language`` and ``.. code-block:: language`` + directives with a lexer for the given language (default: + ``True``). + + .. versionadded:: 0.8 """ name = 'reStructuredText' aliases = ['rst', 'rest', 'restructuredtext'] @@ -731,7 +751,7 @@ class RstLexer(RegexLexer): (r'^(\s*)(\|)( .+\n(?:\| .+\n)*)', bygroups(Text, Operator, using(this, state='inline'))), # Sourcecode directives - (r'^( *\.\.)(\s*)((?:source)?code)(::)([ \t]*)([^\n]+)' + (r'^( *\.\.)(\s*)((?:source)?code(?:-block)?)(::)([ \t]*)([^\n]+)' r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*|)\n)+)', _handle_sourcecode), # A directive @@ -755,7 +775,7 @@ class RstLexer(RegexLexer): (r'^( *)(:.*?:)([ \t]+)(.*?)$', bygroups(Text, Name.Class, Text, Name.Function)), # Definition list - (r'^([^ ].*(?<!::)\n)((?:(?: +.*)\n)+)', + (r'^([^\s].*(?<!::)\n)((?:(?: +.*)\n)+)', bygroups(using(this, state='inline'), using(this, state='inline'))), # Code blocks (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*|)\n)+)', @@ -806,7 +826,7 @@ class VimLexer(RegexLexer): """ Lexer for VimL script files. - *New in Pygments 0.8.* + .. versionadded:: 0.8 """ name = 'VimL' aliases = ['vim'] @@ -823,7 +843,7 @@ class VimLexer(RegexLexer): # TODO: regexes can have other delims (r'/(\\\\|\\/|[^\n/])*/', String.Regex), (r'"(\\\\|\\"|[^\n"])*"', String.Double), - (r"'(\\\\|\\'|[^\n'])*'", String.Single), + (r"'(''|[^\n'])*'", String.Single), # Who decided that doublequote was a good comment character?? (r'(?<=\s)"[^\-:.%#=*].*', Comment), @@ -890,7 +910,7 @@ class GettextLexer(RegexLexer): """ Lexer for Gettext catalog files. - *New in Pygments 0.9.* + .. versionadded:: 0.9 """ name = 'Gettext Catalog' aliases = ['pot', 'po'] @@ -918,7 +938,7 @@ class SquidConfLexer(RegexLexer): """ Lexer for `squid <http://www.squid-cache.org/>`_ configuration files. - *New in Pygments 0.9.* + .. versionadded:: 0.9 """ name = 'SquidConf' @@ -1050,7 +1070,7 @@ class DebianControlLexer(RegexLexer): """ Lexer for Debian ``control`` files and ``apt-cache show <pkg>`` outputs. - *New in Pygments 0.9.* + .. versionadded:: 0.9 """ name = 'Debian Control file' aliases = ['control', 'debcontrol'] @@ -1120,7 +1140,7 @@ class YamlLexer(ExtendedRegexLexer): Lexer for `YAML <http://yaml.org/>`_, a human-friendly data serialization language. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'YAML' @@ -1522,7 +1542,7 @@ class LighttpdConfLexer(RegexLexer): """ Lexer for `Lighttpd <http://lighttpd.net/>`_ configuration files. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'Lighttpd configuration file' aliases = ['lighty', 'lighttpd'] @@ -1550,7 +1570,7 @@ class NginxConfLexer(RegexLexer): """ Lexer for `Nginx <http://nginx.net/>`_ configuration files. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'Nginx configuration file' aliases = ['nginx'] @@ -1596,7 +1616,7 @@ class CMakeLexer(RegexLexer): """ Lexer for `CMake <http://cmake.org/Wiki/CMake>`_ files. - *New in Pygments 1.2.* + .. versionadded:: 1.2 """ name = 'CMake' aliases = ['cmake'] @@ -1640,6 +1660,7 @@ class CMakeLexer(RegexLexer): (r'\(', Punctuation, '#push'), (r'\)', Punctuation, '#pop'), (r'(\${)(.+?)(})', bygroups(Operator, Name.Variable, Operator)), + (r'(\$<)(.+?)(>)', bygroups(Operator, Name.Variable, Operator)), (r'(?s)".*?"', String.Double), (r'\\\S+', String), (r'[^\)$"# \t\n]+', String), @@ -1656,7 +1677,7 @@ class CMakeLexer(RegexLexer): ], 'ws': [ (r'[ \t]+', Text), - (r'#.+\n', Comment), + (r'#.*\n', Comment), ] } @@ -1665,7 +1686,7 @@ class HttpLexer(RegexLexer): """ Lexer for HTTP sessions. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'HTTP' @@ -1734,7 +1755,7 @@ class PyPyLogLexer(RegexLexer): """ Lexer for PyPy log files. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = "PyPy Log" aliases = ["pypylog", "pypy"] @@ -1806,7 +1827,7 @@ class HxmlLexer(RegexLexer): """ Lexer for `haXe build <http://haxe.org/doc/compiler>`_ files. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'Hxml' aliases = ['haxeml', 'hxml'] @@ -1849,7 +1870,7 @@ class EbnfLexer(RegexLexer): <http://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_Form>`_ grammars. - *New in Pygments 1.7.* + .. versionadded:: 2.0 """ name = 'EBNF' @@ -1891,3 +1912,102 @@ class EbnfLexer(RegexLexer): (r'([a-zA-Z][a-zA-Z0-9 \-]*)', Keyword), ], } + +class TodotxtLexer(RegexLexer): + """ + Lexer for `Todo.txt <http://todotxt.com/>`_ todo list format. + + .. versionadded:: 2.0 + """ + + name = 'Todotxt' + aliases = ['todotxt'] + # *.todotxt is not a standard extension for Todo.txt files; including it + # makes testing easier, and also makes autodetecting file type easier. + filenames = ['todo.txt', '*.todotxt'] + mimetypes = ['text/x-todo'] + + ## Aliases mapping standard token types of Todo.txt format concepts + CompleteTaskText = Operator # Chosen to de-emphasize complete tasks + IncompleteTaskText = Text # Incomplete tasks should look like plain text + + # Priority should have most emphasis to indicate importance of tasks + Priority = Generic.Heading + # Dates should have next most emphasis because time is important + Date = Generic.Subheading + + # Project and context should have equal weight, and be in different colors + Project = Generic.Error + Context = String + + # If tag functionality is added, it should have the same weight as Project + # and Context, and a different color. Generic.Traceback would work well. + + # Regex patterns for building up rules; dates, priorities, projects, and + # contexts are all atomic + # TODO: Make date regex more ISO 8601 compliant + date_regex = r'\d{4,}-\d{2}-\d{2}' + priority_regex = r'\([A-Z]\)' + project_regex = r'\+\S+' + context_regex = r'@\S+' + + # Compound regex expressions + complete_one_date_regex = r'(x )(' + date_regex + r')' + complete_two_date_regex = (complete_one_date_regex + r'( )(' + + date_regex + r')') + priority_date_regex = r'(' + priority_regex + r')( )(' + date_regex + r')' + + tokens = { + # Should parse starting at beginning of line; each line is a task + 'root': [ + ## Complete task entry points: two total: + # 1. Complete task with two dates + (complete_two_date_regex, bygroups(CompleteTaskText, Date, + CompleteTaskText, Date), + 'complete'), + # 2. Complete task with one date + (complete_one_date_regex, bygroups(CompleteTaskText, Date), + 'complete'), + + ## Incomplete task entry points: six total: + # 1. Priority plus date + (priority_date_regex, bygroups(Priority, IncompleteTaskText, Date), + 'incomplete'), + # 2. Priority only + (priority_regex, Priority, 'incomplete'), + # 3. Leading date + (date_regex, Date, 'incomplete'), + # 4. Leading context + (context_regex, Context, 'incomplete'), + # 5. Leading project + (project_regex, Project, 'incomplete'), + # 6. Non-whitespace catch-all + ('\S+', IncompleteTaskText, 'incomplete'), + ], + + # Parse a complete task + 'complete': [ + # Newline indicates end of task, should return to root + (r'\s*\n', CompleteTaskText, '#pop'), + # Tokenize contexts and projects + (context_regex, Context), + (project_regex, Project), + # Tokenize non-whitespace text + ('\S+', CompleteTaskText), + # Tokenize whitespace not containing a newline + ('\s+', CompleteTaskText), + ], + + # Parse an incomplete task + 'incomplete': [ + # Newline indicates end of task, should return to root + (r'\s*\n', IncompleteTaskText, '#pop'), + # Tokenize contexts and projects + (context_regex, Context), + (project_regex, Project), + # Tokenize non-whitespace text + ('\S+', IncompleteTaskText), + # Tokenize whitespace not containing a newline + ('\s+', IncompleteTaskText), + ], + } |