diff options
| -rw-r--r-- | pygments/lexers/_mapping.py | 3 | ||||
| -rw-r--r-- | pygments/lexers/web.py | 86 | ||||
| -rw-r--r-- | tests/examplefiles/test.dtd | 89 |
3 files changed, 176 insertions, 2 deletions
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py index b3ab5b14..16af9528 100644 --- a/pygments/lexers/_mapping.py +++ b/pygments/lexers/_mapping.py @@ -31,7 +31,7 @@ LEXERS = { 'AppleScriptLexer': ('pygments.lexers.other', 'AppleScript', ('applescript',), ('*.applescript',), ()), 'AsymptoteLexer': ('pygments.lexers.other', 'Asymptote', ('asy', 'asymptote'), ('*.asy',), ('text/x-asymptote',)), 'AutohotkeyLexer': ('pygments.lexers.other', 'autohotkey', ('ahk',), ('*.ahk', '*.ahkl'), ('text/x-autohotkey',)), - 'AwkLexer': ('pygments.lexers.other', 'Awk', ('awk', 'gawk', 'mawk', 'nawk'), ('*.awk',), ('application/x-awk')), + 'AwkLexer': ('pygments.lexers.other', 'Awk', ('awk', 'gawk', 'mawk', 'nawk'), ('*.awk',), ()), 'BBCodeLexer': ('pygments.lexers.text', 'BBCode', ('bbcode',), (), ('text/x-bbcode',)), 'BaseMakefileLexer': ('pygments.lexers.text', 'Makefile', ('basemake',), (), ()), 'BashLexer': ('pygments.lexers.other', 'Bash', ('bash', 'sh', 'ksh'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass'), ('application/x-sh', 'application/x-shellscript')), @@ -71,6 +71,7 @@ LEXERS = { 'DelphiLexer': ('pygments.lexers.compiled', 'Delphi', ('delphi', 'pas', 'pascal', 'objectpascal'), ('*.pas',), ('text/x-pascal',)), 'DiffLexer': ('pygments.lexers.text', 'Diff', ('diff', 'udiff'), ('*.diff', '*.patch'), ('text/x-diff', 'text/x-patch')), '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',)), 'ErbLexer': ('pygments.lexers.templates', 'ERB', ('erb',), (), ('application/x-ruby-templating',)), diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py index 11bc2175..b6b6fc5a 100644 --- a/pygments/lexers/web.py +++ b/pygments/lexers/web.py @@ -26,7 +26,7 @@ __all__ = ['HtmlLexer', 'XmlLexer', 'JavascriptLexer', 'CssLexer', 'PhpLexer', 'ActionScriptLexer', 'XsltLexer', 'ActionScript3Lexer', 'MxmlLexer', 'HaxeLexer', 'HamlLexer', 'SassLexer', 'ScssLexer', 'ObjectiveJLexer', 'CoffeeScriptLexer', 'DuelLexer', 'ScamlLexer', - 'JadeLexer', 'XQueryLexer'] + 'JadeLexer', 'XQueryLexer', 'DtdLexer'] class JavascriptLexer(RegexLexer): @@ -826,6 +826,90 @@ class PhpLexer(RegexLexer): return rv +class DtdLexer(RegexLexer): + """ + a lexer for DTD (Document Type Definition). + """ + + flags = re.MULTILINE | re.DOTALL + + name = 'DTD' + aliases = ['dtd'] + filenames = ['*.dtd'] + mimetypes = ['application/xml-dtd'] + + tokens = { + 'root': [ + include('common'), + + (r'(<!ELEMENT)(\s+)([^\s]+)', + bygroups(Keyword, Text, Name.Tag), 'element'), + (r'(<!ATTLIST)(\s+)([^\s]+)', + bygroups(Keyword, Text, Name.Tag), 'attlist'), + (r'(<!ENTITY)(\s+)([^\s]+)', + bygroups(Keyword, Text, Name.Entity), 'entity'), + (r'(<!NOTATION)(\s+)([^\s]+)', + bygroups(Keyword, Text, Name.Tag), 'notation'), + (r'(<!\[)([^\[\s]+)(\s*)(\[)', # conditional sections + bygroups(Keyword, Name.Entity, Text, Keyword)), + + (r'(<!DOCTYPE)(\s+)([^>\s]+)', + bygroups(Keyword, Text, Name.Tag)), + (r'PUBLIC|SYSTEM', Keyword.Constant), + (r'[\[\]>]', Keyword), + ], + + 'common': [ + (r'\s+', Text), + (r'(%|&)[^;]*;', Name.Entity), + ('<!--', Comment, 'comment'), + (r'[(|)*,?+]', Operator), + (r'"[^"]*"', String.Double), + (r'\'[^\']*\'', String.Single), + ], + + 'comment': [ + ('[^-]+', Comment), + ('-->', Comment, '#pop'), + ('-', Comment), + ], + + 'element': [ + include('common'), + (r'EMPTY|ANY|#PCDATA', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Tag), + (r'>', Keyword, '#pop'), + ], + + 'attlist': [ + include('common'), + (r'CDATA|IDREFS|IDREF|ID|NMTOKENS|NMTOKEN|ENTITIES|ENTITY|NOTATION', Keyword.Constant), + (r'#REQUIRED|#IMPLIED|#FIXED', Keyword.Constant), + (r'xml:space|xml:lang', Keyword.Reserved), + (r'[^>\s\|()?+*,]+', Name.Attribute), + (r'>', Keyword, '#pop'), + ], + + 'entity': [ + include('common'), + (r'SYSTEM|PUBLIC|NDATA', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Entity), + (r'>', Keyword, '#pop'), + ], + + 'notation': [ + include('common'), + (r'SYSTEM|PUBLIC', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Attribute), + (r'>', Keyword, '#pop'), + ], + } + + def analyse_text(text): + if not looks_like_xml(text) and \ + ('<!ELEMENT' in text or '<!ATTLIST' in text or '<!ENTITY' in text): + return 0.8 + class XmlLexer(RegexLexer): """ Generic lexer for XML (eXtensible Markup Language). diff --git a/tests/examplefiles/test.dtd b/tests/examplefiles/test.dtd new file mode 100644 index 00000000..639b411a --- /dev/null +++ b/tests/examplefiles/test.dtd @@ -0,0 +1,89 @@ +<!DOCTYPE html> + +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> + + +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd" [ + <!-- an internal subset can be embedded here --> +]> + +<!DOCTYPE greeting SYSTEM "hello.dtd"> + +<!DOCTYPE greeting [ + <!ELEMENT greeting (#PCDATA)> + +<!-- examples from XML spec --> + +<!ELEMENT br EMPTY> +<!ELEMENT p (#PCDATA|emph)* > +<!ELEMENT %name.para; %content.para; > +<!ELEMENT container ANY> + +<!ELEMENT spec (front, body, back?)> +<!ELEMENT div1 (head, (p | list | note)*, div2*)> +<!ELEMENT dictionary-body (%div.mix; | %dict.mix;)*> + +<!ELEMENT p (#PCDATA|a|ul|b|i|em)*> +<!ELEMENT p (#PCDATA | %font; | %phrase; | %special; | %form;)* > +<!ELEMENT b (#PCDATA)> + +<!ATTLIST termdef + id ID #REQUIRED + name CDATA #IMPLIED> +<!ATTLIST list + type (bullets|ordered|glossary) "ordered"> +<!ATTLIST form + method CDATA #FIXED "POST"> + +<!ENTITY d "
"> +<!ENTITY a "
"> +<!ENTITY da "
"> + +<!ENTITY % ISOLat2 + SYSTEM "http://www.xml.com/iso/isolat2-xml.entities" > + +<!ENTITY Pub-Status "This is a pre-release of the + specification."> + + <!ENTITY open-hatch + SYSTEM "http://www.textuality.com/boilerplate/OpenHatch.xml"> +<!ENTITY open-hatch + PUBLIC "-//Textuality//TEXT Standard open-hatch boilerplate//EN" + "http://www.textuality.com/boilerplate/OpenHatch.xml"> +<!ENTITY hatch-pic + SYSTEM "../grafix/OpenHatch.gif" + NDATA gif > + +<!NOTATION gif PUBLIC "gif viewer"> + +<!ENTITY % YN '"Yes"' > +<!ENTITY WhatHeSaid "He said %YN;" > + +<!ENTITY EndAttr "27'" > + +<!ENTITY % pub "Éditions Gallimard" > +<!ENTITY rights "All rights reserved" > +<!ENTITY book "La Peste: Albert Camus, +© 1947 %pub;. &rights;" > + +<!ENTITY lt "&#60;"> +<!ENTITY gt ">"> +<!ENTITY amp "&#38;"> +<!ENTITY apos "'"> +<!ENTITY quot """> + +<!ENTITY % draft 'INCLUDE' > +<!ENTITY % final 'IGNORE' > + +<![%draft;[ +<!ELEMENT book (comments*, title, body, supplements?)> +]]> +<![%final;[ +<!ELEMENT book (title, body, supplements?)> +]]> + +]> + + |