From e2cc2530fc6d54ebc975c01a4ff887ce12f0a736 Mon Sep 17 00:00:00 2001 From: Pavel Aharoni Date: Wed, 29 Mar 2017 13:35:45 +0300 Subject: [SDC-6] sdc-distribution-client 1707 rebasing Change-Id: I322a05fd79beb6ba4fee4d32afffecf531b86e98 Signed-off-by: Pavel Aharoni --- .../site-packages/pip/_vendor/html5lib/__init__.py | 23 + .../pip/_vendor/html5lib/constants.py | 3086 ++++++++++++++++++++ .../pip/_vendor/html5lib/filters/__init__.py | 0 .../pip/_vendor/html5lib/filters/_base.py | 12 + .../html5lib/filters/alphabeticalattributes.py | 20 + .../html5lib/filters/inject_meta_charset.py | 65 + .../pip/_vendor/html5lib/filters/lint.py | 93 + .../pip/_vendor/html5lib/filters/optionaltags.py | 205 ++ .../pip/_vendor/html5lib/filters/sanitizer.py | 12 + .../pip/_vendor/html5lib/filters/whitespace.py | 38 + .../pip/_vendor/html5lib/html5parser.py | 2725 +++++++++++++++++ .../site-packages/pip/_vendor/html5lib/ihatexml.py | 285 ++ .../pip/_vendor/html5lib/inputstream.py | 905 ++++++ .../pip/_vendor/html5lib/sanitizer.py | 271 ++ .../pip/_vendor/html5lib/serializer/__init__.py | 16 + .../_vendor/html5lib/serializer/htmlserializer.py | 309 ++ .../pip/_vendor/html5lib/tokenizer.py | 1731 +++++++++++ .../pip/_vendor/html5lib/treebuilders/__init__.py | 76 + .../pip/_vendor/html5lib/treebuilders/_base.py | 377 +++ .../pip/_vendor/html5lib/treebuilders/dom.py | 290 ++ .../pip/_vendor/html5lib/treebuilders/etree.py | 337 +++ .../_vendor/html5lib/treebuilders/etree_lxml.py | 369 +++ .../pip/_vendor/html5lib/treewalkers/__init__.py | 57 + .../pip/_vendor/html5lib/treewalkers/_base.py | 196 ++ .../pip/_vendor/html5lib/treewalkers/dom.py | 46 + .../pip/_vendor/html5lib/treewalkers/etree.py | 131 + .../_vendor/html5lib/treewalkers/genshistream.py | 69 + .../pip/_vendor/html5lib/treewalkers/lxmletree.py | 208 ++ .../pip/_vendor/html5lib/treewalkers/pulldom.py | 63 + .../pip/_vendor/html5lib/trie/__init__.py | 12 + .../pip/_vendor/html5lib/trie/_base.py | 37 + .../pip/_vendor/html5lib/trie/datrie.py | 44 + .../site-packages/pip/_vendor/html5lib/trie/py.py | 67 + .../site-packages/pip/_vendor/html5lib/utils.py | 78 + 34 files changed, 12253 insertions(+) create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/constants.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/_base.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/lint.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/optionaltags.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/sanitizer.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/whitespace.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/html5parser.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/ihatexml.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/inputstream.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/sanitizer.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/serializer/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/serializer/htmlserializer.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/tokenizer.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treebuilders/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treebuilders/_base.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treebuilders/dom.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treebuilders/etree.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treebuilders/etree_lxml.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/_base.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/dom.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/etree.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/genshistream.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/lxmletree.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/treewalkers/pulldom.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/trie/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/trie/_base.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/trie/datrie.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/trie/py.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/utils.py (limited to 'jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib') diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/__init__.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/__init__.py new file mode 100644 index 0000000..10e2b74 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/__init__.py @@ -0,0 +1,23 @@ +""" +HTML parsing library based on the WHATWG "HTML5" +specification. The parser is designed to be compatible with existing +HTML found in the wild and implements well-defined error recovery that +is largely compatible with modern desktop web browsers. + +Example usage: + +import html5lib +f = open("my_document.html") +tree = html5lib.parse(f) +""" + +from __future__ import absolute_import, division, unicode_literals + +from .html5parser import HTMLParser, parse, parseFragment +from .treebuilders import getTreeBuilder +from .treewalkers import getTreeWalker +from .serializer import serialize + +__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder", + "getTreeWalker", "serialize"] +__version__ = "1.0b1" diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/constants.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/constants.py new file mode 100644 index 0000000..1866dd7 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/constants.py @@ -0,0 +1,3086 @@ +from __future__ import absolute_import, division, unicode_literals + +import string +import gettext +_ = gettext.gettext + +EOF = None + +E = { + "null-character": + _("Null character in input stream, replaced with U+FFFD."), + "invalid-codepoint": + _("Invalid codepoint in stream."), + "incorrectly-placed-solidus": + _("Solidus (/) incorrectly placed in tag."), + "incorrect-cr-newline-entity": + _("Incorrect CR newline entity, replaced with LF."), + "illegal-windows-1252-entity": + _("Entity used with illegal number (windows-1252 reference)."), + "cant-convert-numeric-entity": + _("Numeric entity couldn't be converted to character " + "(codepoint U+%(charAsInt)08x)."), + "illegal-codepoint-for-numeric-entity": + _("Numeric entity represents an illegal codepoint: " + "U+%(charAsInt)08x."), + "numeric-entity-without-semicolon": + _("Numeric entity didn't end with ';'."), + "expected-numeric-entity-but-got-eof": + _("Numeric entity expected. Got end of file instead."), + "expected-numeric-entity": + _("Numeric entity expected but none found."), + "named-entity-without-semicolon": + _("Named entity didn't end with ';'."), + "expected-named-entity": + _("Named entity expected. Got none."), + "attributes-in-end-tag": + _("End tag contains unexpected attributes."), + 'self-closing-flag-on-end-tag': + _("End tag contains unexpected self-closing flag."), + "expected-tag-name-but-got-right-bracket": + _("Expected tag name. Got '>' instead."), + "expected-tag-name-but-got-question-mark": + _("Expected tag name. Got '?' instead. (HTML doesn't " + "support processing instructions.)"), + "expected-tag-name": + _("Expected tag name. Got something else instead"), + "expected-closing-tag-but-got-right-bracket": + _("Expected closing tag. Got '>' instead. Ignoring ''."), + "expected-closing-tag-but-got-eof": + _("Expected closing tag. Unexpected end of file."), + "expected-closing-tag-but-got-char": + _("Expected closing tag. Unexpected character '%(data)s' found."), + "eof-in-tag-name": + _("Unexpected end of file in the tag name."), + "expected-attribute-name-but-got-eof": + _("Unexpected end of file. Expected attribute name instead."), + "eof-in-attribute-name": + _("Unexpected end of file in attribute name."), + "invalid-character-in-attribute-name": + _("Invalid character in attribute name"), + "duplicate-attribute": + _("Dropped duplicate attribute on tag."), + "expected-end-of-tag-name-but-got-eof": + _("Unexpected end of file. Expected = or end of tag."), + "expected-attribute-value-but-got-eof": + _("Unexpected end of file. Expected attribute value."), + "expected-attribute-value-but-got-right-bracket": + _("Expected attribute value. Got '>' instead."), + 'equals-in-unquoted-attribute-value': + _("Unexpected = in unquoted attribute"), + 'unexpected-character-in-unquoted-attribute-value': + _("Unexpected character in unquoted attribute"), + "invalid-character-after-attribute-name": + _("Unexpected character after attribute name."), + "unexpected-character-after-attribute-value": + _("Unexpected character after attribute value."), + "eof-in-attribute-value-double-quote": + _("Unexpected end of file in attribute value (\")."), + "eof-in-attribute-value-single-quote": + _("Unexpected end of file in attribute value (')."), + "eof-in-attribute-value-no-quotes": + _("Unexpected end of file in attribute value."), + "unexpected-EOF-after-solidus-in-tag": + _("Unexpected end of file in tag. Expected >"), + "unexpected-character-after-solidus-in-tag": + _("Unexpected character after / in tag. Expected >"), + "expected-dashes-or-doctype": + _("Expected '--' or 'DOCTYPE'. Not found."), + "unexpected-bang-after-double-dash-in-comment": + _("Unexpected ! after -- in comment"), + "unexpected-space-after-double-dash-in-comment": + _("Unexpected space after -- in comment"), + "incorrect-comment": + _("Incorrect comment."), + "eof-in-comment": + _("Unexpected end of file in comment."), + "eof-in-comment-end-dash": + _("Unexpected end of file in comment (-)"), + "unexpected-dash-after-double-dash-in-comment": + _("Unexpected '-' after '--' found in comment."), + "eof-in-comment-double-dash": + _("Unexpected end of file in comment (--)."), + "eof-in-comment-end-space-state": + _("Unexpected end of file in comment."), + "eof-in-comment-end-bang-state": + _("Unexpected end of file in comment."), + "unexpected-char-in-comment": + _("Unexpected character in comment found."), + "need-space-after-doctype": + _("No space after literal string 'DOCTYPE'."), + "expected-doctype-name-but-got-right-bracket": + _("Unexpected > character. Expected DOCTYPE name."), + "expected-doctype-name-but-got-eof": + _("Unexpected end of file. Expected DOCTYPE name."), + "eof-in-doctype-name": + _("Unexpected end of file in DOCTYPE name."), + "eof-in-doctype": + _("Unexpected end of file in DOCTYPE."), + "expected-space-or-right-bracket-in-doctype": + _("Expected space or '>'. Got '%(data)s'"), + "unexpected-end-of-doctype": + _("Unexpected end of DOCTYPE."), + "unexpected-char-in-doctype": + _("Unexpected character in DOCTYPE."), + "eof-in-innerhtml": + _("XXX innerHTML EOF"), + "unexpected-doctype": + _("Unexpected DOCTYPE. Ignored."), + "non-html-root": + _("html needs to be the first start tag."), + "expected-doctype-but-got-eof": + _("Unexpected End of file. Expected DOCTYPE."), + "unknown-doctype": + _("Erroneous DOCTYPE."), + "expected-doctype-but-got-chars": + _("Unexpected non-space characters. Expected DOCTYPE."), + "expected-doctype-but-got-start-tag": + _("Unexpected start tag (%(name)s). Expected DOCTYPE."), + "expected-doctype-but-got-end-tag": + _("Unexpected end tag (%(name)s). Expected DOCTYPE."), + "end-tag-after-implied-root": + _("Unexpected end tag (%(name)s) after the (implied) root element."), + "expected-named-closing-tag-but-got-eof": + _("Unexpected end of file. Expected end tag (%(name)s)."), + "two-heads-are-not-better-than-one": + _("Unexpected start tag head in existing head. Ignored."), + "unexpected-end-tag": + _("Unexpected end tag (%(name)s). Ignored."), + "unexpected-start-tag-out-of-my-head": + _("Unexpected start tag (%(name)s) that can be in head. Moved."), + "unexpected-start-tag": + _("Unexpected start tag (%(name)s)."), + "missing-end-tag": + _("Missing end tag (%(name)s)."), + "missing-end-tags": + _("Missing end tags (%(name)s)."), + "unexpected-start-tag-implies-end-tag": + _("Unexpected start tag (%(startName)s) " + "implies end tag (%(endName)s)."), + "unexpected-start-tag-treated-as": + _("Unexpected start tag (%(originalName)s). Treated as %(newName)s."), + "deprecated-tag": + _("Unexpected start tag %(name)s. Don't use it!"), + "unexpected-start-tag-ignored": + _("Unexpected start tag %(name)s. Ignored."), + "expected-one-end-tag-but-got-another": + _("Unexpected end tag (%(gotName)s). " + "Missing end tag (%(expectedName)s)."), + "end-tag-too-early": + _("End tag (%(name)s) seen too early. Expected other end tag."), + "end-tag-too-early-named": + _("Unexpected end tag (%(gotName)s). Expected end tag (%(expectedName)s)."), + "end-tag-too-early-ignored": + _("End tag (%(name)s) seen too early. Ignored."), + "adoption-agency-1.1": + _("End tag (%(name)s) violates step 1, " + "paragraph 1 of the adoption agency algorithm."), + "adoption-agency-1.2": + _("End tag (%(name)s) violates step 1, " + "paragraph 2 of the adoption agency algorithm."), + "adoption-agency-1.3": + _("End tag (%(name)s) violates step 1, " + "paragraph 3 of the adoption agency algorithm."), + "adoption-agency-4.4": + _("End tag (%(name)s) violates step 4, " + "paragraph 4 of the adoption agency algorithm."), + "unexpected-end-tag-treated-as": + _("Unexpected end tag (%(originalName)s). Treated as %(newName)s."), + "no-end-tag": + _("This element (%(name)s) has no end tag."), + "unexpected-implied-end-tag-in-table": + _("Unexpected implied end tag (%(name)s) in the table phase."), + "unexpected-implied-end-tag-in-table-body": + _("Unexpected implied end tag (%(name)s) in the table body phase."), + "unexpected-char-implies-table-voodoo": + _("Unexpected non-space characters in " + "table context caused voodoo mode."), + "unexpected-hidden-input-in-table": + _("Unexpected input with type hidden in table context."), + "unexpected-form-in-table": + _("Unexpected form in table context."), + "unexpected-start-tag-implies-table-voodoo": + _("Unexpected start tag (%(name)s) in " + "table context caused voodoo mode."), + "unexpected-end-tag-implies-table-voodoo": + _("Unexpected end tag (%(name)s) in " + "table context caused voodoo mode."), + "unexpected-cell-in-table-body": + _("Unexpected table cell start tag (%(name)s) " + "in the table body phase."), + "unexpected-cell-end-tag": + _("Got table cell end tag (%(name)s) " + "while required end tags are missing."), + "unexpected-end-tag-in-table-body": + _("Unexpected end tag (%(name)s) in the table body phase. Ignored."), + "unexpected-implied-end-tag-in-table-row": + _("Unexpected implied end tag (%(name)s) in the table row phase."), + "unexpected-end-tag-in-table-row": + _("Unexpected end tag (%(name)s) in the table row phase. Ignored."), + "unexpected-select-in-select": + _("Unexpected select start tag in the select phase " + "treated as select end tag."), + "unexpected-input-in-select": + _("Unexpected input start tag in the select phase."), + "unexpected-start-tag-in-select": + _("Unexpected start tag token (%(name)s in the select phase. " + "Ignored."), + "unexpected-end-tag-in-select": + _("Unexpected end tag (%(name)s) in the select phase. Ignored."), + "unexpected-table-element-start-tag-in-select-in-table": + _("Unexpected table element start tag (%(name)s) in the select in table phase."), + "unexpected-table-element-end-tag-in-select-in-table": + _("Unexpected table element end tag (%(name)s) in the select in table phase."), + "unexpected-char-after-body": + _("Unexpected non-space characters in the after body phase."), + "unexpected-start-tag-after-body": + _("Unexpected start tag token (%(name)s)" + " in the after body phase."), + "unexpected-end-tag-after-body": + _("Unexpected end tag token (%(name)s)" + " in the after body phase."), + "unexpected-char-in-frameset": + _("Unexpected characters in the frameset phase. Characters ignored."), + "unexpected-start-tag-in-frameset": + _("Unexpected start tag token (%(name)s)" + " in the frameset phase. Ignored."), + "unexpected-frameset-in-frameset-innerhtml": + _("Unexpected end tag token (frameset) " + "in the frameset phase (innerHTML)."), + "unexpected-end-tag-in-frameset": + _("Unexpected end tag token (%(name)s)" + " in the frameset phase. Ignored."), + "unexpected-char-after-frameset": + _("Unexpected non-space characters in the " + "after frameset phase. Ignored."), + "unexpected-start-tag-after-frameset": + _("Unexpected start tag (%(name)s)" + " in the after frameset phase. Ignored."), + "unexpected-end-tag-after-frameset": + _("Unexpected end tag (%(name)s)" + " in the after frameset phase. Ignored."), + "unexpected-end-tag-after-body-innerhtml": + _("Unexpected end tag after body(innerHtml)"), + "expected-eof-but-got-char": + _("Unexpected non-space characters. Expected end of file."), + "expected-eof-but-got-start-tag": + _("Unexpected start tag (%(name)s)" + ". Expected end of file."), + "expected-eof-but-got-end-tag": + _("Unexpected end tag (%(name)s)" + ". Expected end of file."), + "eof-in-table": + _("Unexpected end of file. Expected table content."), + "eof-in-select": + _("Unexpected end of file. Expected select content."), + "eof-in-frameset": + _("Unexpected end of file. Expected frameset content."), + "eof-in-script-in-script": + _("Unexpected end of file. Expected script content."), + "eof-in-foreign-lands": + _("Unexpected end of file. Expected foreign content"), + "non-void-element-with-trailing-solidus": + _("Trailing solidus not allowed on element %(name)s"), + "unexpected-html-element-in-foreign-content": + _("Element %(name)s not allowed in a non-html context"), + "unexpected-end-tag-before-html": + _("Unexpected end tag (%(name)s) before html."), + "XXX-undefined-error": + _("Undefined error (this sucks and should be fixed)"), +} + +namespaces = { + "html": "http://www.w3.org/1999/xhtml", + "mathml": "http://www.w3.org/1998/Math/MathML", + "svg": "http://www.w3.org/2000/svg", + "xlink": "http://www.w3.org/1999/xlink", + "xml": "http://www.w3.org/XML/1998/namespace", + "xmlns": "http://www.w3.org/2000/xmlns/" +} + +scopingElements = frozenset(( + (namespaces["html"], "applet"), + (namespaces["html"], "caption"), + (namespaces["html"], "html"), + (namespaces["html"], "marquee"), + (namespaces["html"], "object"), + (namespaces["html"], "table"), + (namespaces["html"], "td"), + (namespaces["html"], "th"), + (namespaces["mathml"], "mi"), + (namespaces["mathml"], "mo"), + (namespaces["mathml"], "mn"), + (namespaces["mathml"], "ms"), + (namespaces["mathml"], "mtext"), + (namespaces["mathml"], "annotation-xml"), + (namespaces["svg"], "foreignObject"), + (namespaces["svg"], "desc"), + (namespaces["svg"], "title"), +)) + +formattingElements = frozenset(( + (namespaces["html"], "a"), + (namespaces["html"], "b"), + (namespaces["html"], "big"), + (namespaces["html"], "code"), + (namespaces["html"], "em"), + (namespaces["html"], "font"), + (namespaces["html"], "i"), + (namespaces["html"], "nobr"), + (namespaces["html"], "s"), + (namespaces["html"], "small"), + (namespaces["html"], "strike"), + (namespaces["html"], "strong"), + (namespaces["html"], "tt"), + (namespaces["html"], "u") +)) + +specialElements = frozenset(( + (namespaces["html"], "address"), + (namespaces["html"], "applet"), + (namespaces["html"], "area"), + (namespaces["html"], "article"), + (namespaces["html"], "aside"), + (namespaces["html"], "base"), + (namespaces["html"], "basefont"), + (namespaces["html"], "bgsound"), + (namespaces["html"], "blockquote"), + (namespaces["html"], "body"), + (namespaces["html"], "br"), + (namespaces["html"], "button"), + (namespaces["html"], "caption"), + (namespaces["html"], "center"), + (namespaces["html"], "col"), + (namespaces["html"], "colgroup"), + (namespaces["html"], "command"), + (namespaces["html"], "dd"), + (namespaces["html"], "details"), + (namespaces["html"], "dir"), + (namespaces["html"], "div"), + (namespaces["html"], "dl"), + (namespaces["html"], "dt"), + (namespaces["html"], "embed"), + (namespaces["html"], "fieldset"), + (namespaces["html"], "figure"), + (namespaces["html"], "footer"), + (namespaces["html"], "form"), + (namespaces["html"], "frame"), + (namespaces["html"], "frameset"), + (namespaces["html"], "h1"), + (namespaces["html"], "h2"), + (namespaces["html"], "h3"), + (namespaces["html"], "h4"), + (namespaces["html"], "h5"), + (namespaces["html"], "h6"), + (namespaces["html"], "head"), + (namespaces["html"], "header"), + (namespaces["html"], "hr"), + (namespaces["html"], "html"), + (namespaces["html"], "iframe"), + # Note that image is commented out in the spec as "this isn't an + # element that can end up on the stack, so it doesn't matter," + (namespaces["html"], "image"), + (namespaces["html"], "img"), + (namespaces["html"], "input"), + (namespaces["html"], "isindex"), + (namespaces["html"], "li"), + (namespaces["html"], "link"), + (namespaces["html"], "listing"), + (namespaces["html"], "marquee"), + (namespaces["html"], "menu"), + (namespaces["html"], "meta"), + (namespaces["html"], "nav"), + (namespaces["html"], "noembed"), + (namespaces["html"], "noframes"), + (namespaces["html"], "noscript"), + (namespaces["html"], "object"), + (namespaces["html"], "ol"), + (namespaces["html"], "p"), + (namespaces["html"], "param"), + (namespaces["html"], "plaintext"), + (namespaces["html"], "pre"), + (namespaces["html"], "script"), + (namespaces["html"], "section"), + (namespaces["html"], "select"), + (namespaces["html"], "style"), + (namespaces["html"], "table"), + (namespaces["html"], "tbody"), + (namespaces["html"], "td"), + (namespaces["html"], "textarea"), + (namespaces["html"], "tfoot"), + (namespaces["html"], "th"), + (namespaces["html"], "thead"), + (namespaces["html"], "title"), + (namespaces["html"], "tr"), + (namespaces["html"], "ul"), + (namespaces["html"], "wbr"), + (namespaces["html"], "xmp"), + (namespaces["svg"], "foreignObject") +)) + +htmlIntegrationPointElements = frozenset(( + (namespaces["mathml"], "annotaion-xml"), + (namespaces["svg"], "foreignObject"), + (namespaces["svg"], "desc"), + (namespaces["svg"], "title") +)) + +mathmlTextIntegrationPointElements = frozenset(( + (namespaces["mathml"], "mi"), + (namespaces["mathml"], "mo"), + (namespaces["mathml"], "mn"), + (namespaces["mathml"], "ms"), + (namespaces["mathml"], "mtext") +)) + +spaceCharacters = frozenset(( + "\t", + "\n", + "\u000C", + " ", + "\r" +)) + +tableInsertModeElements = frozenset(( + "table", + "tbody", + "tfoot", + "thead", + "tr" +)) + +asciiLowercase = frozenset(string.ascii_lowercase) +asciiUppercase = frozenset(string.ascii_uppercase) +asciiLetters = frozenset(string.ascii_letters) +digits = frozenset(string.digits) +hexDigits = frozenset(string.hexdigits) + +asciiUpper2Lower = dict([(ord(c), ord(c.lower())) + for c in string.ascii_uppercase]) + +# Heading elements need to be ordered +headingElements = ( + "h1", + "h2", + "h3", + "h4", + "h5", + "h6" +) + +voidElements = frozenset(( + "base", + "command", + "event-source", + "link", + "meta", + "hr", + "br", + "img", + "embed", + "param", + "area", + "col", + "input", + "source", + "track" +)) + +cdataElements = frozenset(('title', 'textarea')) + +rcdataElements = frozenset(( + 'style', + 'script', + 'xmp', + 'iframe', + 'noembed', + 'noframes', + 'noscript' +)) + +booleanAttributes = { + "": frozenset(("irrelevant",)), + "style": frozenset(("scoped",)), + "img": frozenset(("ismap",)), + "audio": frozenset(("autoplay", "controls")), + "video": frozenset(("autoplay", "controls")), + "script": frozenset(("defer", "async")), + "details": frozenset(("open",)), + "datagrid": frozenset(("multiple", "disabled")), + "command": frozenset(("hidden", "disabled", "checked", "default")), + "hr": frozenset(("noshade")), + "menu": frozenset(("autosubmit",)), + "fieldset": frozenset(("disabled", "readonly")), + "option": frozenset(("disabled", "readonly", "selected")), + "optgroup": frozenset(("disabled", "readonly")), + "button": frozenset(("disabled", "autofocus")), + "input": frozenset(("disabled", "readonly", "required", "autofocus", "checked", "ismap")), + "select": frozenset(("disabled", "readonly", "autofocus", "multiple")), + "output": frozenset(("disabled", "readonly")), +} + +# entitiesWindows1252 has to be _ordered_ and needs to have an index. It +# therefore can't be a frozenset. +entitiesWindows1252 = ( + 8364, # 0x80 0x20AC EURO SIGN + 65533, # 0x81 UNDEFINED + 8218, # 0x82 0x201A SINGLE LOW-9 QUOTATION MARK + 402, # 0x83 0x0192 LATIN SMALL LETTER F WITH HOOK + 8222, # 0x84 0x201E DOUBLE LOW-9 QUOTATION MARK + 8230, # 0x85 0x2026 HORIZONTAL ELLIPSIS + 8224, # 0x86 0x2020 DAGGER + 8225, # 0x87 0x2021 DOUBLE DAGGER + 710, # 0x88 0x02C6 MODIFIER LETTER CIRCUMFLEX ACCENT + 8240, # 0x89 0x2030 PER MILLE SIGN + 352, # 0x8A 0x0160 LATIN CAPITAL LETTER S WITH CARON + 8249, # 0x8B 0x2039 SINGLE LEFT-POINTING ANGLE QUOTATION MARK + 338, # 0x8C 0x0152 LATIN CAPITAL LIGATURE OE + 65533, # 0x8D UNDEFINED + 381, # 0x8E 0x017D LATIN CAPITAL LETTER Z WITH CARON + 65533, # 0x8F UNDEFINED + 65533, # 0x90 UNDEFINED + 8216, # 0x91 0x2018 LEFT SINGLE QUOTATION MARK + 8217, # 0x92 0x2019 RIGHT SINGLE QUOTATION MARK + 8220, # 0x93 0x201C LEFT DOUBLE QUOTATION MARK + 8221, # 0x94 0x201D RIGHT DOUBLE QUOTATION MARK + 8226, # 0x95 0x2022 BULLET + 8211, # 0x96 0x2013 EN DASH + 8212, # 0x97 0x2014 EM DASH + 732, # 0x98 0x02DC SMALL TILDE + 8482, # 0x99 0x2122 TRADE MARK SIGN + 353, # 0x9A 0x0161 LATIN SMALL LETTER S WITH CARON + 8250, # 0x9B 0x203A SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + 339, # 0x9C 0x0153 LATIN SMALL LIGATURE OE + 65533, # 0x9D UNDEFINED + 382, # 0x9E 0x017E LATIN SMALL LETTER Z WITH CARON + 376 # 0x9F 0x0178 LATIN CAPITAL LETTER Y WITH DIAERESIS +) + +xmlEntities = frozenset(('lt;', 'gt;', 'amp;', 'apos;', 'quot;')) + +entities = { + "AElig": "\xc6", + "AElig;": "\xc6", + "AMP": "&", + "AMP;": "&", + "Aacute": "\xc1", + "Aacute;": "\xc1", + "Abreve;": "\u0102", + "Acirc": "\xc2", + "Acirc;": "\xc2", + "Acy;": "\u0410", + "Afr;": "\U0001d504", + "Agrave": "\xc0", + "Agrave;": "\xc0", + "Alpha;": "\u0391", + "Amacr;": "\u0100", + "And;": "\u2a53", + "Aogon;": "\u0104", + "Aopf;": "\U0001d538", + "ApplyFunction;": "\u2061", + "Aring": "\xc5", + "Aring;": "\xc5", + "Ascr;": "\U0001d49c", + "Assign;": "\u2254", + "Atilde": "\xc3", + "Atilde;": "\xc3", + "Auml": "\xc4", + "Auml;": "\xc4", + "Backslash;": "\u2216", + "Barv;": "\u2ae7", + "Barwed;": "\u2306", + "Bcy;": "\u0411", + "Because;": "\u2235", + "Bernoullis;": "\u212c", + "Beta;": "\u0392", + "Bfr;": "\U0001d505", + "Bopf;": "\U0001d539", + "Breve;": "\u02d8", + "Bscr;": "\u212c", + "Bumpeq;": "\u224e", + "CHcy;": "\u0427", + "COPY": "\xa9", + "COPY;": "\xa9", + "Cacute;": "\u0106", + "Cap;": "\u22d2", + "CapitalDifferentialD;": "\u2145", + "Cayleys;": "\u212d", + "Ccaron;": "\u010c", + "Ccedil": "\xc7", + "Ccedil;": "\xc7", + "Ccirc;": "\u0108", + "Cconint;": "\u2230", + "Cdot;": "\u010a", + "Cedilla;": "\xb8", + "CenterDot;": "\xb7", + "Cfr;": "\u212d", + "Chi;": "\u03a7", + "CircleDot;": "\u2299", + "CircleMinus;": "\u2296", + "CirclePlus;": "\u2295", + "CircleTimes;": "\u2297", + "ClockwiseContourIntegral;": "\u2232", + "CloseCurlyDoubleQuote;": "\u201d", + "CloseCurlyQuote;": "\u2019", + "Colon;": "\u2237", + "Colone;": "\u2a74", + "Congruent;": "\u2261", + "Conint;": "\u222f", + "ContourIntegral;": "\u222e", + "Copf;": "\u2102", + "Coproduct;": "\u2210", + "CounterClockwiseContourIntegral;": "\u2233", + "Cross;": "\u2a2f", + "Cscr;": "\U0001d49e", + "Cup;": "\u22d3", + "CupCap;": "\u224d", + "DD;": "\u2145", + "DDotrahd;": "\u2911", + "DJcy;": "\u0402", + "DScy;": "\u0405", + "DZcy;": "\u040f", + "Dagger;": "\u2021", + "Darr;": "\u21a1", + "Dashv;": "\u2ae4", + "Dcaron;": "\u010e", + "Dcy;": "\u0414", + "Del;": "\u2207", + "Delta;": "\u0394", + "Dfr;": "\U0001d507", + "DiacriticalAcute;": "\xb4", + "DiacriticalDot;": "\u02d9", + "DiacriticalDoubleAcute;": "\u02dd", + "DiacriticalGrave;": "`", + "DiacriticalTilde;": "\u02dc", + "Diamond;": "\u22c4", + "DifferentialD;": "\u2146", + "Dopf;": "\U0001d53b", + "Dot;": "\xa8", + "DotDot;": "\u20dc", + "DotEqual;": "\u2250", + "DoubleContourIntegral;": "\u222f", + "DoubleDot;": "\xa8", + "DoubleDownArrow;": "\u21d3", + "DoubleLeftArrow;": "\u21d0", + "DoubleLeftRightArrow;": "\u21d4", + "DoubleLeftTee;": "\u2ae4", + "DoubleLongLeftArrow;": "\u27f8", + "DoubleLongLeftRightArrow;": "\u27fa", + "DoubleLongRightArrow;": "\u27f9", + "DoubleRightArrow;": "\u21d2", + "DoubleRightTee;": "\u22a8", + "DoubleUpArrow;": "\u21d1", + "DoubleUpDownArrow;": "\u21d5", + "DoubleVerticalBar;": "\u2225", + "DownArrow;": "\u2193", + "DownArrowBar;": "\u2913", + "DownArrowUpArrow;": "\u21f5", + "DownBreve;": "\u0311", + "DownLeftRightVector;": "\u2950", + "DownLeftTeeVector;": "\u295e", + "DownLeftVector;": "\u21bd", + "DownLeftVectorBar;": "\u2956", + "DownRightTeeVector;": "\u295f", + "DownRightVector;": "\u21c1", + "DownRightVectorBar;": "\u2957", + "DownTee;": "\u22a4", + "DownTeeArrow;": "\u21a7", + "Downarrow;": "\u21d3", + "Dscr;": "\U0001d49f", + "Dstrok;": "\u0110", + "ENG;": "\u014a", + "ETH": "\xd0", + "ETH;": "\xd0", + "Eacute": "\xc9", + "Eacute;": "\xc9", + "Ecaron;": "\u011a", + "Ecirc": "\xca", + "Ecirc;": "\xca", + "Ecy;": "\u042d", + "Edot;": "\u0116", + "Efr;": "\U0001d508", + "Egrave": "\xc8", + "Egrave;": "\xc8", + "Element;": "\u2208", + "Emacr;": "\u0112", + "EmptySmallSquare;": "\u25fb", + "EmptyVerySmallSquare;": "\u25ab", + "Eogon;": "\u0118", + "Eopf;": "\U0001d53c", + "Epsilon;": "\u0395", + "Equal;": "\u2a75", + "EqualTilde;": "\u2242", + "Equilibrium;": "\u21cc", + "Escr;": "\u2130", + "Esim;": "\u2a73", + "Eta;": "\u0397", + "Euml": "\xcb", + "Euml;": "\xcb", + "Exists;": "\u2203", + "ExponentialE;": "\u2147", + "Fcy;": "\u0424", + "Ffr;": "\U0001d509", + "FilledSmallSquare;": "\u25fc", + "FilledVerySmallSquare;": "\u25aa", + "Fopf;": "\U0001d53d", + "ForAll;": "\u2200", + "Fouriertrf;": "\u2131", + "Fscr;": "\u2131", + "GJcy;": "\u0403", + "GT": ">", + "GT;": ">", + "Gamma;": "\u0393", + "Gammad;": "\u03dc", + "Gbreve;": "\u011e", + "Gcedil;": "\u0122", + "Gcirc;": "\u011c", + "Gcy;": "\u0413", + "Gdot;": "\u0120", + "Gfr;": "\U0001d50a", + "Gg;": "\u22d9", + "Gopf;": "\U0001d53e", + "GreaterEqual;": "\u2265", + "GreaterEqualLess;": "\u22db", + "GreaterFullEqual;": "\u2267", + "GreaterGreater;": "\u2aa2", + "GreaterLess;": "\u2277", + "GreaterSlantEqual;": "\u2a7e", + "GreaterTilde;": "\u2273", + "Gscr;": "\U0001d4a2", + "Gt;": "\u226b", + "HARDcy;": "\u042a", + "Hacek;": "\u02c7", + "Hat;": "^", + "Hcirc;": "\u0124", + "Hfr;": "\u210c", + "HilbertSpace;": "\u210b", + "Hopf;": "\u210d", + "HorizontalLine;": "\u2500", + "Hscr;": "\u210b", + "Hstrok;": "\u0126", + "HumpDownHump;": "\u224e", + "HumpEqual;": "\u224f", + "IEcy;": "\u0415", + "IJlig;": "\u0132", + "IOcy;": "\u0401", + "Iacute": "\xcd", + "Iacute;": "\xcd", + "Icirc": "\xce", + "Icirc;": "\xce", + "Icy;": "\u0418", + "Idot;": "\u0130", + "Ifr;": "\u2111", + "Igrave": "\xcc", + "Igrave;": "\xcc", + "Im;": "\u2111", + "Imacr;": "\u012a", + "ImaginaryI;": "\u2148", + "Implies;": "\u21d2", + "Int;": "\u222c", + "Integral;": "\u222b", + "Intersection;": "\u22c2", + "InvisibleComma;": "\u2063", + "InvisibleTimes;": "\u2062", + "Iogon;": "\u012e", + "Iopf;": "\U0001d540", + "Iota;": "\u0399", + "Iscr;": "\u2110", + "Itilde;": "\u0128", + "Iukcy;": "\u0406", + "Iuml": "\xcf", + "Iuml;": "\xcf", + "Jcirc;": "\u0134", + "Jcy;": "\u0419", + "Jfr;": "\U0001d50d", + "Jopf;": "\U0001d541", + "Jscr;": "\U0001d4a5", + "Jsercy;": "\u0408", + "Jukcy;": "\u0404", + "KHcy;": "\u0425", + "KJcy;": "\u040c", + "Kappa;": "\u039a", + "Kcedil;": "\u0136", + "Kcy;": "\u041a", + "Kfr;": "\U0001d50e", + "Kopf;": "\U0001d542", + "Kscr;": "\U0001d4a6", + "LJcy;": "\u0409", + "LT": "<", + "LT;": "<", + "Lacute;": "\u0139", + "Lambda;": "\u039b", + "Lang;": "\u27ea", + "Laplacetrf;": "\u2112", + "Larr;": "\u219e", + "Lcaron;": "\u013d", + "Lcedil;": "\u013b", + "Lcy;": "\u041b", + "LeftAngleBracket;": "\u27e8", + "LeftArrow;": "\u2190", + "LeftArrowBar;": "\u21e4", + "LeftArrowRightArrow;": "\u21c6", + "LeftCeiling;": "\u2308", + "LeftDoubleBracket;": "\u27e6", + "LeftDownTeeVector;": "\u2961", + "LeftDownVector;": "\u21c3", + "LeftDownVectorBar;": "\u2959", + "LeftFloor;": "\u230a", + "LeftRightArrow;": "\u2194", + "LeftRightVector;": "\u294e", + "LeftTee;": "\u22a3", + "LeftTeeArrow;": "\u21a4", + "LeftTeeVector;": "\u295a", + "LeftTriangle;": "\u22b2", + "LeftTriangleBar;": "\u29cf", + "LeftTriangleEqual;": "\u22b4", + "LeftUpDownVector;": "\u2951", + "LeftUpTeeVector;": "\u2960", + "LeftUpVector;": "\u21bf", + "LeftUpVectorBar;": "\u2958", + "LeftVector;": "\u21bc", + "LeftVectorBar;": "\u2952", + "Leftarrow;": "\u21d0", + "Leftrightarrow;": "\u21d4", + "LessEqualGreater;": "\u22da", + "LessFullEqual;": "\u2266", + "LessGreater;": "\u2276", + "LessLess;": "\u2aa1", + "LessSlantEqual;": "\u2a7d", + "LessTilde;": "\u2272", + "Lfr;": "\U0001d50f", + "Ll;": "\u22d8", + "Lleftarrow;": "\u21da", + "Lmidot;": "\u013f", + "LongLeftArrow;": "\u27f5", + "LongLeftRightArrow;": "\u27f7", + "LongRightArrow;": "\u27f6", + "Longleftarrow;": "\u27f8", + "Longleftrightarrow;": "\u27fa", + "Longrightarrow;": "\u27f9", + "Lopf;": "\U0001d543", + "LowerLeftArrow;": "\u2199", + "LowerRightArrow;": "\u2198", + "Lscr;": "\u2112", + "Lsh;": "\u21b0", + "Lstrok;": "\u0141", + "Lt;": "\u226a", + "Map;": "\u2905", + "Mcy;": "\u041c", + "MediumSpace;": "\u205f", + "Mellintrf;": "\u2133", + "Mfr;": "\U0001d510", + "MinusPlus;": "\u2213", + "Mopf;": "\U0001d544", + "Mscr;": "\u2133", + "Mu;": "\u039c", + "NJcy;": "\u040a", + "Nacute;": "\u0143", + "Ncaron;": "\u0147", + "Ncedil;": "\u0145", + "Ncy;": "\u041d", + "NegativeMediumSpace;": "\u200b", + "NegativeThickSpace;": "\u200b", + "NegativeThinSpace;": "\u200b", + "NegativeVeryThinSpace;": "\u200b", + "NestedGreaterGreater;": "\u226b", + "NestedLessLess;": "\u226a", + "NewLine;": "\n", + "Nfr;": "\U0001d511", + "NoBreak;": "\u2060", + "NonBreakingSpace;": "\xa0", + "Nopf;": "\u2115", + "Not;": "\u2aec", + "NotCongruent;": "\u2262", + "NotCupCap;": "\u226d", + "NotDoubleVerticalBar;": "\u2226", + "NotElement;": "\u2209", + "NotEqual;": "\u2260", + "NotEqualTilde;": "\u2242\u0338", + "NotExists;": "\u2204", + "NotGreater;": "\u226f", + "NotGreaterEqual;": "\u2271", + "NotGreaterFullEqual;": "\u2267\u0338", + "NotGreaterGreater;": "\u226b\u0338", + "NotGreaterLess;": "\u2279", + "NotGreaterSlantEqual;": "\u2a7e\u0338", + "NotGreaterTilde;": "\u2275", + "NotHumpDownHump;": "\u224e\u0338", + "NotHumpEqual;": "\u224f\u0338", + "NotLeftTriangle;": "\u22ea", + "NotLeftTriangleBar;": "\u29cf\u0338", + "NotLeftTriangleEqual;": "\u22ec", + "NotLess;": "\u226e", + "NotLessEqual;": "\u2270", + "NotLessGreater;": "\u2278", + "NotLessLess;": "\u226a\u0338", + "NotLessSlantEqual;": "\u2a7d\u0338", + "NotLessTilde;": "\u2274", + "NotNestedGreaterGreater;": "\u2aa2\u0338", + "NotNestedLessLess;": "\u2aa1\u0338", + "NotPrecedes;": "\u2280", + "NotPrecedesEqual;": "\u2aaf\u0338", + "NotPrecedesSlantEqual;": "\u22e0", + "NotReverseElement;": "\u220c", + "NotRightTriangle;": "\u22eb", + "NotRightTriangleBar;": "\u29d0\u0338", + "NotRightTriangleEqual;": "\u22ed", + "NotSquareSubset;": "\u228f\u0338", + "NotSquareSubsetEqual;": "\u22e2", + "NotSquareSuperset;": "\u2290\u0338", + "NotSquareSupersetEqual;": "\u22e3", + "NotSubset;": "\u2282\u20d2", + "NotSubsetEqual;": "\u2288", + "NotSucceeds;": "\u2281", + "NotSucceedsEqual;": "\u2ab0\u0338", + "NotSucceedsSlantEqual;": "\u22e1", + "NotSucceedsTilde;": "\u227f\u0338", + "NotSuperset;": "\u2283\u20d2", + "NotSupersetEqual;": "\u2289", + "NotTilde;": "\u2241", + "NotTildeEqual;": "\u2244", + "NotTildeFullEqual;": "\u2247", + "NotTildeTilde;": "\u2249", + "NotVerticalBar;": "\u2224", + "Nscr;": "\U0001d4a9", + "Ntilde": "\xd1", + "Ntilde;": "\xd1", + "Nu;": "\u039d", + "OElig;": "\u0152", + "Oacute": "\xd3", + "Oacute;": "\xd3", + "Ocirc": "\xd4", + "Ocirc;": "\xd4", + "Ocy;": "\u041e", + "Odblac;": "\u0150", + "Ofr;": "\U0001d512", + "Ograve": "\xd2", + "Ograve;": "\xd2", + "Omacr;": "\u014c", + "Omega;": "\u03a9", + "Omicron;": "\u039f", + "Oopf;": "\U0001d546", + "OpenCurlyDoubleQuote;": "\u201c", + "OpenCurlyQuote;": "\u2018", + "Or;": "\u2a54", + "Oscr;": "\U0001d4aa", + "Oslash": "\xd8", + "Oslash;": "\xd8", + "Otilde": "\xd5", + "Otilde;": "\xd5", + "Otimes;": "\u2a37", + "Ouml": "\xd6", + "Ouml;": "\xd6", + "OverBar;": "\u203e", + "OverBrace;": "\u23de", + "OverBracket;": "\u23b4", + "OverParenthesis;": "\u23dc", + "PartialD;": "\u2202", + "Pcy;": "\u041f", + "Pfr;": "\U0001d513", + "Phi;": "\u03a6", + "Pi;": "\u03a0", + "PlusMinus;": "\xb1", + "Poincareplane;": "\u210c", + "Popf;": "\u2119", + "Pr;": "\u2abb", + "Precedes;": "\u227a", + "PrecedesEqual;": "\u2aaf", + "PrecedesSlantEqual;": "\u227c", + "PrecedesTilde;": "\u227e", + "Prime;": "\u2033", + "Product;": "\u220f", + "Proportion;": "\u2237", + "Proportional;": "\u221d", + "Pscr;": "\U0001d4ab", + "Psi;": "\u03a8", + "QUOT": "\"", + "QUOT;": "\"", + "Qfr;": "\U0001d514", + "Qopf;": "\u211a", + "Qscr;": "\U0001d4ac", + "RBarr;": "\u2910", + "REG": "\xae", + "REG;": "\xae", + "Racute;": "\u0154", + "Rang;": "\u27eb", + "Rarr;": "\u21a0", + "Rarrtl;": "\u2916", + "Rcaron;": "\u0158", + "Rcedil;": "\u0156", + "Rcy;": "\u0420", + "Re;": "\u211c", + "ReverseElement;": "\u220b", + "ReverseEquilibrium;": "\u21cb", + "ReverseUpEquilibrium;": "\u296f", + "Rfr;": "\u211c", + "Rho;": "\u03a1", + "RightAngleBracket;": "\u27e9", + "RightArrow;": "\u2192", + "RightArrowBar;": "\u21e5", + "RightArrowLeftArrow;": "\u21c4", + "RightCeiling;": "\u2309", + "RightDoubleBracket;": "\u27e7", + "RightDownTeeVector;": "\u295d", + "RightDownVector;": "\u21c2", + "RightDownVectorBar;": "\u2955", + "RightFloor;": "\u230b", + "RightTee;": "\u22a2", + "RightTeeArrow;": "\u21a6", + "RightTeeVector;": "\u295b", + "RightTriangle;": "\u22b3", + "RightTriangleBar;": "\u29d0", + "RightTriangleEqual;": "\u22b5", + "RightUpDownVector;": "\u294f", + "RightUpTeeVector;": "\u295c", + "RightUpVector;": "\u21be", + "RightUpVectorBar;": "\u2954", + "RightVector;": "\u21c0", + "RightVectorBar;": "\u2953", + "Rightarrow;": "\u21d2", + "Ropf;": "\u211d", + "RoundImplies;": "\u2970", + "Rrightarrow;": "\u21db", + "Rscr;": "\u211b", + "Rsh;": "\u21b1", + "RuleDelayed;": "\u29f4", + "SHCHcy;": "\u0429", + "SHcy;": "\u0428", + "SOFTcy;": "\u042c", + "Sacute;": "\u015a", + "Sc;": "\u2abc", + "Scaron;": "\u0160", + "Scedil;": "\u015e", + "Scirc;": "\u015c", + "Scy;": "\u0421", + "Sfr;": "\U0001d516", + "ShortDownArrow;": "\u2193", + "ShortLeftArrow;": "\u2190", + "ShortRightArrow;": "\u2192", + "ShortUpArrow;": "\u2191", + "Sigma;": "\u03a3", + "SmallCircle;": "\u2218", + "Sopf;": "\U0001d54a", + "Sqrt;": "\u221a", + "Square;": "\u25a1", + "SquareIntersection;": "\u2293", + "SquareSubset;": "\u228f", + "SquareSubsetEqual;": "\u2291", + "SquareSuperset;": "\u2290", + "SquareSupersetEqual;": "\u2292", + "SquareUnion;": "\u2294", + "Sscr;": "\U0001d4ae", + "Star;": "\u22c6", + "Sub;": "\u22d0", + "Subset;": "\u22d0", + "SubsetEqual;": "\u2286", + "Succeeds;": "\u227b", + "SucceedsEqual;": "\u2ab0", + "SucceedsSlantEqual;": "\u227d", + "SucceedsTilde;": "\u227f", + "SuchThat;": "\u220b", + "Sum;": "\u2211", + "Sup;": "\u22d1", + "Superset;": "\u2283", + "SupersetEqual;": "\u2287", + "Supset;": "\u22d1", + "THORN": "\xde", + "THORN;": "\xde", + "TRADE;": "\u2122", + "TSHcy;": "\u040b", + "TScy;": "\u0426", + "Tab;": "\t", + "Tau;": "\u03a4", + "Tcaron;": "\u0164", + "Tcedil;": "\u0162", + "Tcy;": "\u0422", + "Tfr;": "\U0001d517", + "Therefore;": "\u2234", + "Theta;": "\u0398", + "ThickSpace;": "\u205f\u200a", + "ThinSpace;": "\u2009", + "Tilde;": "\u223c", + "TildeEqual;": "\u2243", + "TildeFullEqual;": "\u2245", + "TildeTilde;": "\u2248", + "Topf;": "\U0001d54b", + "TripleDot;": "\u20db", + "Tscr;": "\U0001d4af", + "Tstrok;": "\u0166", + "Uacute": "\xda", + "Uacute;": "\xda", + "Uarr;": "\u219f", + "Uarrocir;": "\u2949", + "Ubrcy;": "\u040e", + "Ubreve;": "\u016c", + "Ucirc": "\xdb", + "Ucirc;": "\xdb", + "Ucy;": "\u0423", + "Udblac;": "\u0170", + "Ufr;": "\U0001d518", + "Ugrave": "\xd9", + "Ugrave;": "\xd9", + "Umacr;": "\u016a", + "UnderBar;": "_", + "UnderBrace;": "\u23df", + "UnderBracket;": "\u23b5", + "UnderParenthesis;": "\u23dd", + "Union;": "\u22c3", + "UnionPlus;": "\u228e", + "Uogon;": "\u0172", + "Uopf;": "\U0001d54c", + "UpArrow;": "\u2191", + "UpArrowBar;": "\u2912", + "UpArrowDownArrow;": "\u21c5", + "UpDownArrow;": "\u2195", + "UpEquilibrium;": "\u296e", + "UpTee;": "\u22a5", + "UpTeeArrow;": "\u21a5", + "Uparrow;": "\u21d1", + "Updownarrow;": "\u21d5", + "UpperLeftArrow;": "\u2196", + "UpperRightArrow;": "\u2197", + "Upsi;": "\u03d2", + "Upsilon;": "\u03a5", + "Uring;": "\u016e", + "Uscr;": "\U0001d4b0", + "Utilde;": "\u0168", + "Uuml": "\xdc", + "Uuml;": "\xdc", + "VDash;": "\u22ab", + "Vbar;": "\u2aeb", + "Vcy;": "\u0412", + "Vdash;": "\u22a9", + "Vdashl;": "\u2ae6", + "Vee;": "\u22c1", + "Verbar;": "\u2016", + "Vert;": "\u2016", + "VerticalBar;": "\u2223", + "VerticalLine;": "|", + "VerticalSeparator;": "\u2758", + "VerticalTilde;": "\u2240", + "VeryThinSpace;": "\u200a", + "Vfr;": "\U0001d519", + "Vopf;": "\U0001d54d", + "Vscr;": "\U0001d4b1", + "Vvdash;": "\u22aa", + "Wcirc;": "\u0174", + "Wedge;": "\u22c0", + "Wfr;": "\U0001d51a", + "Wopf;": "\U0001d54e", + "Wscr;": "\U0001d4b2", + "Xfr;": "\U0001d51b", + "Xi;": "\u039e", + "Xopf;": "\U0001d54f", + "Xscr;": "\U0001d4b3", + "YAcy;": "\u042f", + "YIcy;": "\u0407", + "YUcy;": "\u042e", + "Yacute": "\xdd", + "Yacute;": "\xdd", + "Ycirc;": "\u0176", + "Ycy;": "\u042b", + "Yfr;": "\U0001d51c", + "Yopf;": "\U0001d550", + "Yscr;": "\U0001d4b4", + "Yuml;": "\u0178", + "ZHcy;": "\u0416", + "Zacute;": "\u0179", + "Zcaron;": "\u017d", + "Zcy;": "\u0417", + "Zdot;": "\u017b", + "ZeroWidthSpace;": "\u200b", + "Zeta;": "\u0396", + "Zfr;": "\u2128", + "Zopf;": "\u2124", + "Zscr;": "\U0001d4b5", + "aacute": "\xe1", + "aacute;": "\xe1", + "abreve;": "\u0103", + "ac;": "\u223e", + "acE;": "\u223e\u0333", + "acd;": "\u223f", + "acirc": "\xe2", + "acirc;": "\xe2", + "acute": "\xb4", + "acute;": "\xb4", + "acy;": "\u0430", + "aelig": "\xe6", + "aelig;": "\xe6", + "af;": "\u2061", + "afr;": "\U0001d51e", + "agrave": "\xe0", + "agrave;": "\xe0", + "alefsym;": "\u2135", + "aleph;": "\u2135", + "alpha;": "\u03b1", + "amacr;": "\u0101", + "amalg;": "\u2a3f", + "amp": "&", + "amp;": "&", + "and;": "\u2227", + "andand;": "\u2a55", + "andd;": "\u2a5c", + "andslope;": "\u2a58", + "andv;": "\u2a5a", + "ang;": "\u2220", + "ange;": "\u29a4", + "angle;": "\u2220", + "angmsd;": "\u2221", + "angmsdaa;": "\u29a8", + "angmsdab;": "\u29a9", + "angmsdac;": "\u29aa", + "angmsdad;": "\u29ab", + "angmsdae;": "\u29ac", + "angmsdaf;": "\u29ad", + "angmsdag;": "\u29ae", + "angmsdah;": "\u29af", + "angrt;": "\u221f", + "angrtvb;": "\u22be", + "angrtvbd;": "\u299d", + "angsph;": "\u2222", + "angst;": "\xc5", + "angzarr;": "\u237c", + "aogon;": "\u0105", + "aopf;": "\U0001d552", + "ap;": "\u2248", + "apE;": "\u2a70", + "apacir;": "\u2a6f", + "ape;": "\u224a", + "apid;": "\u224b", + "apos;": "'", + "approx;": "\u2248", + "approxeq;": "\u224a", + "aring": "\xe5", + "aring;": "\xe5", + "ascr;": "\U0001d4b6", + "ast;": "*", + "asymp;": "\u2248", + "asympeq;": "\u224d", + "atilde": "\xe3", + "atilde;": "\xe3", + "auml": "\xe4", + "auml;": "\xe4", + "awconint;": "\u2233", + "awint;": "\u2a11", + "bNot;": "\u2aed", + "backcong;": "\u224c", + "backepsilon;": "\u03f6", + "backprime;": "\u2035", + "backsim;": "\u223d", + "backsimeq;": "\u22cd", + "barvee;": "\u22bd", + "barwed;": "\u2305", + "barwedge;": "\u2305", + "bbrk;": "\u23b5", + "bbrktbrk;": "\u23b6", + "bcong;": "\u224c", + "bcy;": "\u0431", + "bdquo;": "\u201e", + "becaus;": "\u2235", + "because;": "\u2235", + "bemptyv;": "\u29b0", + "bepsi;": "\u03f6", + "bernou;": "\u212c", + "beta;": "\u03b2", + "beth;": "\u2136", + "between;": "\u226c", + "bfr;": "\U0001d51f", + "bigcap;": "\u22c2", + "bigcirc;": "\u25ef", + "bigcup;": "\u22c3", + "bigodot;": "\u2a00", + "bigoplus;": "\u2a01", + "bigotimes;": "\u2a02", + "bigsqcup;": "\u2a06", + "bigstar;": "\u2605", + "bigtriangledown;": "\u25bd", + "bigtriangleup;": "\u25b3", + "biguplus;": "\u2a04", + "bigvee;": "\u22c1", + "bigwedge;": "\u22c0", + "bkarow;": "\u290d", + "blacklozenge;": "\u29eb", + "blacksquare;": "\u25aa", + "blacktriangle;": "\u25b4", + "blacktriangledown;": "\u25be", + "blacktriangleleft;": "\u25c2", + "blacktriangleright;": "\u25b8", + "blank;": "\u2423", + "blk12;": "\u2592", + "blk14;": "\u2591", + "blk34;": "\u2593", + "block;": "\u2588", + "bne;": "=\u20e5", + "bnequiv;": "\u2261\u20e5", + "bnot;": "\u2310", + "bopf;": "\U0001d553", + "bot;": "\u22a5", + "bottom;": "\u22a5", + "bowtie;": "\u22c8", + "boxDL;": "\u2557", + "boxDR;": "\u2554", + "boxDl;": "\u2556", + "boxDr;": "\u2553", + "boxH;": "\u2550", + "boxHD;": "\u2566", + "boxHU;": "\u2569", + "boxHd;": "\u2564", + "boxHu;": "\u2567", + "boxUL;": "\u255d", + "boxUR;": "\u255a", + "boxUl;": "\u255c", + "boxUr;": "\u2559", + "boxV;": "\u2551", + "boxVH;": "\u256c", + "boxVL;": "\u2563", + "boxVR;": "\u2560", + "boxVh;": "\u256b", + "boxVl;": "\u2562", + "boxVr;": "\u255f", + "boxbox;": "\u29c9", + "boxdL;": "\u2555", + "boxdR;": "\u2552", + "boxdl;": "\u2510", + "boxdr;": "\u250c", + "boxh;": "\u2500", + "boxhD;": "\u2565", + "boxhU;": "\u2568", + "boxhd;": "\u252c", + "boxhu;": "\u2534", + "boxminus;": "\u229f", + "boxplus;": "\u229e", + "boxtimes;": "\u22a0", + "boxuL;": "\u255b", + "boxuR;": "\u2558", + "boxul;": "\u2518", + "boxur;": "\u2514", + "boxv;": "\u2502", + "boxvH;": "\u256a", + "boxvL;": "\u2561", + "boxvR;": "\u255e", + "boxvh;": "\u253c", + "boxvl;": "\u2524", + "boxvr;": "\u251c", + "bprime;": "\u2035", + "breve;": "\u02d8", + "brvbar": "\xa6", + "brvbar;": "\xa6", + "bscr;": "\U0001d4b7", + "bsemi;": "\u204f", + "bsim;": "\u223d", + "bsime;": "\u22cd", + "bsol;": "\\", + "bsolb;": "\u29c5", + "bsolhsub;": "\u27c8", + "bull;": "\u2022", + "bullet;": "\u2022", + "bump;": "\u224e", + "bumpE;": "\u2aae", + "bumpe;": "\u224f", + "bumpeq;": "\u224f", + "cacute;": "\u0107", + "cap;": "\u2229", + "capand;": "\u2a44", + "capbrcup;": "\u2a49", + "capcap;": "\u2a4b", + "capcup;": "\u2a47", + "capdot;": "\u2a40", + "caps;": "\u2229\ufe00", + "caret;": "\u2041", + "caron;": "\u02c7", + "ccaps;": "\u2a4d", + "ccaron;": "\u010d", + "ccedil": "\xe7", + "ccedil;": "\xe7", + "ccirc;": "\u0109", + "ccups;": "\u2a4c", + "ccupssm;": "\u2a50", + "cdot;": "\u010b", + "cedil": "\xb8", + "cedil;": "\xb8", + "cemptyv;": "\u29b2", + "cent": "\xa2", + "cent;": "\xa2", + "centerdot;": "\xb7", + "cfr;": "\U0001d520", + "chcy;": "\u0447", + "check;": "\u2713", + "checkmark;": "\u2713", + "chi;": "\u03c7", + "cir;": "\u25cb", + "cirE;": "\u29c3", + "circ;": "\u02c6", + "circeq;": "\u2257", + "circlearrowleft;": "\u21ba", + "circlearrowright;": "\u21bb", + "circledR;": "\xae", + "circledS;": "\u24c8", + "circledast;": "\u229b", + "circledcirc;": "\u229a", + "circleddash;": "\u229d", + "cire;": "\u2257", + "cirfnint;": "\u2a10", + "cirmid;": "\u2aef", + "cirscir;": "\u29c2", + "clubs;": "\u2663", + "clubsuit;": "\u2663", + "colon;": ":", + "colone;": "\u2254", + "coloneq;": "\u2254", + "comma;": ",", + "commat;": "@", + "comp;": "\u2201", + "compfn;": "\u2218", + "complement;": "\u2201", + "complexes;": "\u2102", + "cong;": "\u2245", + "congdot;": "\u2a6d", + "conint;": "\u222e", + "copf;": "\U0001d554", + "coprod;": "\u2210", + "copy": "\xa9", + "copy;": "\xa9", + "copysr;": "\u2117", + "crarr;": "\u21b5", + "cross;": "\u2717", + "cscr;": "\U0001d4b8", + "csub;": "\u2acf", + "csube;": "\u2ad1", + "csup;": "\u2ad0", + "csupe;": "\u2ad2", + "ctdot;": "\u22ef", + "cudarrl;": "\u2938", + "cudarrr;": "\u2935", + "cuepr;": "\u22de", + "cuesc;": "\u22df", + "cularr;": "\u21b6", + "cularrp;": "\u293d", + "cup;": "\u222a", + "cupbrcap;": "\u2a48", + "cupcap;": "\u2a46", + "cupcup;": "\u2a4a", + "cupdot;": "\u228d", + "cupor;": "\u2a45", + "cups;": "\u222a\ufe00", + "curarr;": "\u21b7", + "curarrm;": "\u293c", + "curlyeqprec;": "\u22de", + "curlyeqsucc;": "\u22df", + "curlyvee;": "\u22ce", + "curlywedge;": "\u22cf", + "curren": "\xa4", + "curren;": "\xa4", + "curvearrowleft;": "\u21b6", + "curvearrowright;": "\u21b7", + "cuvee;": "\u22ce", + "cuwed;": "\u22cf", + "cwconint;": "\u2232", + "cwint;": "\u2231", + "cylcty;": "\u232d", + "dArr;": "\u21d3", + "dHar;": "\u2965", + "dagger;": "\u2020", + "daleth;": "\u2138", + "darr;": "\u2193", + "dash;": "\u2010", + "dashv;": "\u22a3", + "dbkarow;": "\u290f", + "dblac;": "\u02dd", + "dcaron;": "\u010f", + "dcy;": "\u0434", + "dd;": "\u2146", + "ddagger;": "\u2021", + "ddarr;": "\u21ca", + "ddotseq;": "\u2a77", + "deg": "\xb0", + "deg;": "\xb0", + "delta;": "\u03b4", + "demptyv;": "\u29b1", + "dfisht;": "\u297f", + "dfr;": "\U0001d521", + "dharl;": "\u21c3", + "dharr;": "\u21c2", + "diam;": "\u22c4", + "diamond;": "\u22c4", + "diamondsuit;": "\u2666", + "diams;": "\u2666", + "die;": "\xa8", + "digamma;": "\u03dd", + "disin;": "\u22f2", + "div;": "\xf7", + "divide": "\xf7", + "divide;": "\xf7", + "divideontimes;": "\u22c7", + "divonx;": "\u22c7", + "djcy;": "\u0452", + "dlcorn;": "\u231e", + "dlcrop;": "\u230d", + "dollar;": "$", + "dopf;": "\U0001d555", + "dot;": "\u02d9", + "doteq;": "\u2250", + "doteqdot;": "\u2251", + "dotminus;": "\u2238", + "dotplus;": "\u2214", + "dotsquare;": "\u22a1", + "doublebarwedge;": "\u2306", + "downarrow;": "\u2193", + "downdownarrows;": "\u21ca", + "downharpoonleft;": "\u21c3", + "downharpoonright;": "\u21c2", + "drbkarow;": "\u2910", + "drcorn;": "\u231f", + "drcrop;": "\u230c", + "dscr;": "\U0001d4b9", + "dscy;": "\u0455", + "dsol;": "\u29f6", + "dstrok;": "\u0111", + "dtdot;": "\u22f1", + "dtri;": "\u25bf", + "dtrif;": "\u25be", + "duarr;": "\u21f5", + "duhar;": "\u296f", + "dwangle;": "\u29a6", + "dzcy;": "\u045f", + "dzigrarr;": "\u27ff", + "eDDot;": "\u2a77", + "eDot;": "\u2251", + "eacute": "\xe9", + "eacute;": "\xe9", + "easter;": "\u2a6e", + "ecaron;": "\u011b", + "ecir;": "\u2256", + "ecirc": "\xea", + "ecirc;": "\xea", + "ecolon;": "\u2255", + "ecy;": "\u044d", + "edot;": "\u0117", + "ee;": "\u2147", + "efDot;": "\u2252", + "efr;": "\U0001d522", + "eg;": "\u2a9a", + "egrave": "\xe8", + "egrave;": "\xe8", + "egs;": "\u2a96", + "egsdot;": "\u2a98", + "el;": "\u2a99", + "elinters;": "\u23e7", + "ell;": "\u2113", + "els;": "\u2a95", + "elsdot;": "\u2a97", + "emacr;": "\u0113", + "empty;": "\u2205", + "emptyset;": "\u2205", + "emptyv;": "\u2205", + "emsp13;": "\u2004", + "emsp14;": "\u2005", + "emsp;": "\u2003", + "eng;": "\u014b", + "ensp;": "\u2002", + "eogon;": "\u0119", + "eopf;": "\U0001d556", + "epar;": "\u22d5", + "eparsl;": "\u29e3", + "eplus;": "\u2a71", + "epsi;": "\u03b5", + "epsilon;": "\u03b5", + "epsiv;": "\u03f5", + "eqcirc;": "\u2256", + "eqcolon;": "\u2255", + "eqsim;": "\u2242", + "eqslantgtr;": "\u2a96", + "eqslantless;": "\u2a95", + "equals;": "=", + "equest;": "\u225f", + "equiv;": "\u2261", + "equivDD;": "\u2a78", + "eqvparsl;": "\u29e5", + "erDot;": "\u2253", + "erarr;": "\u2971", + "escr;": "\u212f", + "esdot;": "\u2250", + "esim;": "\u2242", + "eta;": "\u03b7", + "eth": "\xf0", + "eth;": "\xf0", + "euml": "\xeb", + "euml;": "\xeb", + "euro;": "\u20ac", + "excl;": "!", + "exist;": "\u2203", + "expectation;": "\u2130", + "exponentiale;": "\u2147", + "fallingdotseq;": "\u2252", + "fcy;": "\u0444", + "female;": "\u2640", + "ffilig;": "\ufb03", + "fflig;": "\ufb00", + "ffllig;": "\ufb04", + "ffr;": "\U0001d523", + "filig;": "\ufb01", + "fjlig;": "fj", + "flat;": "\u266d", + "fllig;": "\ufb02", + "fltns;": "\u25b1", + "fnof;": "\u0192", + "fopf;": "\U0001d557", + "forall;": "\u2200", + "fork;": "\u22d4", + "forkv;": "\u2ad9", + "fpartint;": "\u2a0d", + "frac12": "\xbd", + "frac12;": "\xbd", + "frac13;": "\u2153", + "frac14": "\xbc", + "frac14;": "\xbc", + "frac15;": "\u2155", + "frac16;": "\u2159", + "frac18;": "\u215b", + "frac23;": "\u2154", + "frac25;": "\u2156", + "frac34": "\xbe", + "frac34;": "\xbe", + "frac35;": "\u2157", + "frac38;": "\u215c", + "frac45;": "\u2158", + "frac56;": "\u215a", + "frac58;": "\u215d", + "frac78;": "\u215e", + "frasl;": "\u2044", + "frown;": "\u2322", + "fscr;": "\U0001d4bb", + "gE;": "\u2267", + "gEl;": "\u2a8c", + "gacute;": "\u01f5", + "gamma;": "\u03b3", + "gammad;": "\u03dd", + "gap;": "\u2a86", + "gbreve;": "\u011f", + "gcirc;": "\u011d", + "gcy;": "\u0433", + "gdot;": "\u0121", + "ge;": "\u2265", + "gel;": "\u22db", + "geq;": "\u2265", + "geqq;": "\u2267", + "geqslant;": "\u2a7e", + "ges;": "\u2a7e", + "gescc;": "\u2aa9", + "gesdot;": "\u2a80", + "gesdoto;": "\u2a82", + "gesdotol;": "\u2a84", + "gesl;": "\u22db\ufe00", + "gesles;": "\u2a94", + "gfr;": "\U0001d524", + "gg;": "\u226b", + "ggg;": "\u22d9", + "gimel;": "\u2137", + "gjcy;": "\u0453", + "gl;": "\u2277", + "glE;": "\u2a92", + "gla;": "\u2aa5", + "glj;": "\u2aa4", + "gnE;": "\u2269", + "gnap;": "\u2a8a", + "gnapprox;": "\u2a8a", + "gne;": "\u2a88", + "gneq;": "\u2a88", + "gneqq;": "\u2269", + "gnsim;": "\u22e7", + "gopf;": "\U0001d558", + "grave;": "`", + "gscr;": "\u210a", + "gsim;": "\u2273", + "gsime;": "\u2a8e", + "gsiml;": "\u2a90", + "gt": ">", + "gt;": ">", + "gtcc;": "\u2aa7", + "gtcir;": "\u2a7a", + "gtdot;": "\u22d7", + "gtlPar;": "\u2995", + "gtquest;": "\u2a7c", + "gtrapprox;": "\u2a86", + "gtrarr;": "\u2978", + "gtrdot;": "\u22d7", + "gtreqless;": "\u22db", + "gtreqqless;": "\u2a8c", + "gtrless;": "\u2277", + "gtrsim;": "\u2273", + "gvertneqq;": "\u2269\ufe00", + "gvnE;": "\u2269\ufe00", + "hArr;": "\u21d4", + "hairsp;": "\u200a", + "half;": "\xbd", + "hamilt;": "\u210b", + "hardcy;": "\u044a", + "harr;": "\u2194", + "harrcir;": "\u2948", + "harrw;": "\u21ad", + "hbar;": "\u210f", + "hcirc;": "\u0125", + "hearts;": "\u2665", + "heartsuit;": "\u2665", + "hellip;": "\u2026", + "hercon;": "\u22b9", + "hfr;": "\U0001d525", + "hksearow;": "\u2925", + "hkswarow;": "\u2926", + "hoarr;": "\u21ff", + "homtht;": "\u223b", + "hookleftarrow;": "\u21a9", + "hookrightarrow;": "\u21aa", + "hopf;": "\U0001d559", + "horbar;": "\u2015", + "hscr;": "\U0001d4bd", + "hslash;": "\u210f", + "hstrok;": "\u0127", + "hybull;": "\u2043", + "hyphen;": "\u2010", + "iacute": "\xed", + "iacute;": "\xed", + "ic;": "\u2063", + "icirc": "\xee", + "icirc;": "\xee", + "icy;": "\u0438", + "iecy;": "\u0435", + "iexcl": "\xa1", + "iexcl;": "\xa1", + "iff;": "\u21d4", + "ifr;": "\U0001d526", + "igrave": "\xec", + "igrave;": "\xec", + "ii;": "\u2148", + "iiiint;": "\u2a0c", + "iiint;": "\u222d", + "iinfin;": "\u29dc", + "iiota;": "\u2129", + "ijlig;": "\u0133", + "imacr;": "\u012b", + "image;": "\u2111", + "imagline;": "\u2110", + "imagpart;": "\u2111", + "imath;": "\u0131", + "imof;": "\u22b7", + "imped;": "\u01b5", + "in;": "\u2208", + "incare;": "\u2105", + "infin;": "\u221e", + "infintie;": "\u29dd", + "inodot;": "\u0131", + "int;": "\u222b", + "intcal;": "\u22ba", + "integers;": "\u2124", + "intercal;": "\u22ba", + "intlarhk;": "\u2a17", + "intprod;": "\u2a3c", + "iocy;": "\u0451", + "iogon;": "\u012f", + "iopf;": "\U0001d55a", + "iota;": "\u03b9", + "iprod;": "\u2a3c", + "iquest": "\xbf", + "iquest;": "\xbf", + "iscr;": "\U0001d4be", + "isin;": "\u2208", + "isinE;": "\u22f9", + "isindot;": "\u22f5", + "isins;": "\u22f4", + "isinsv;": "\u22f3", + "isinv;": "\u2208", + "it;": "\u2062", + "itilde;": "\u0129", + "iukcy;": "\u0456", + "iuml": "\xef", + "iuml;": "\xef", + "jcirc;": "\u0135", + "jcy;": "\u0439", + "jfr;": "\U0001d527", + "jmath;": "\u0237", + "jopf;": "\U0001d55b", + "jscr;": "\U0001d4bf", + "jsercy;": "\u0458", + "jukcy;": "\u0454", + "kappa;": "\u03ba", + "kappav;": "\u03f0", + "kcedil;": "\u0137", + "kcy;": "\u043a", + "kfr;": "\U0001d528", + "kgreen;": "\u0138", + "khcy;": "\u0445", + "kjcy;": "\u045c", + "kopf;": "\U0001d55c", + "kscr;": "\U0001d4c0", + "lAarr;": "\u21da", + "lArr;": "\u21d0", + "lAtail;": "\u291b", + "lBarr;": "\u290e", + "lE;": "\u2266", + "lEg;": "\u2a8b", + "lHar;": "\u2962", + "lacute;": "\u013a", + "laemptyv;": "\u29b4", + "lagran;": "\u2112", + "lambda;": "\u03bb", + "lang;": "\u27e8", + "langd;": "\u2991", + "langle;": "\u27e8", + "lap;": "\u2a85", + "laquo": "\xab", + "laquo;": "\xab", + "larr;": "\u2190", + "larrb;": "\u21e4", + "larrbfs;": "\u291f", + "larrfs;": "\u291d", + "larrhk;": "\u21a9", + "larrlp;": "\u21ab", + "larrpl;": "\u2939", + "larrsim;": "\u2973", + "larrtl;": "\u21a2", + "lat;": "\u2aab", + "latail;": "\u2919", + "late;": "\u2aad", + "lates;": "\u2aad\ufe00", + "lbarr;": "\u290c", + "lbbrk;": "\u2772", + "lbrace;": "{", + "lbrack;": "[", + "lbrke;": "\u298b", + "lbrksld;": "\u298f", + "lbrkslu;": "\u298d", + "lcaron;": "\u013e", + "lcedil;": "\u013c", + "lceil;": "\u2308", + "lcub;": "{", + "lcy;": "\u043b", + "ldca;": "\u2936", + "ldquo;": "\u201c", + "ldquor;": "\u201e", + "ldrdhar;": "\u2967", + "ldrushar;": "\u294b", + "ldsh;": "\u21b2", + "le;": "\u2264", + "leftarrow;": "\u2190", + "leftarrowtail;": "\u21a2", + "leftharpoondown;": "\u21bd", + "leftharpoonup;": "\u21bc", + "leftleftarrows;": "\u21c7", + "leftrightarrow;": "\u2194", + "leftrightarrows;": "\u21c6", + "leftrightharpoons;": "\u21cb", + "leftrightsquigarrow;": "\u21ad", + "leftthreetimes;": "\u22cb", + "leg;": "\u22da", + "leq;": "\u2264", + "leqq;": "\u2266", + "leqslant;": "\u2a7d", + "les;": "\u2a7d", + "lescc;": "\u2aa8", + "lesdot;": "\u2a7f", + "lesdoto;": "\u2a81", + "lesdotor;": "\u2a83", + "lesg;": "\u22da\ufe00", + "lesges;": "\u2a93", + "lessapprox;": "\u2a85", + "lessdot;": "\u22d6", + "lesseqgtr;": "\u22da", + "lesseqqgtr;": "\u2a8b", + "lessgtr;": "\u2276", + "lesssim;": "\u2272", + "lfisht;": "\u297c", + "lfloor;": "\u230a", + "lfr;": "\U0001d529", + "lg;": "\u2276", + "lgE;": "\u2a91", + "lhard;": "\u21bd", + "lharu;": "\u21bc", + "lharul;": "\u296a", + "lhblk;": "\u2584", + "ljcy;": "\u0459", + "ll;": "\u226a", + "llarr;": "\u21c7", + "llcorner;": "\u231e", + "llhard;": "\u296b", + "lltri;": "\u25fa", + "lmidot;": "\u0140", + "lmoust;": "\u23b0", + "lmoustache;": "\u23b0", + "lnE;": "\u2268", + "lnap;": "\u2a89", + "lnapprox;": "\u2a89", + "lne;": "\u2a87", + "lneq;": "\u2a87", + "lneqq;": "\u2268", + "lnsim;": "\u22e6", + "loang;": "\u27ec", + "loarr;": "\u21fd", + "lobrk;": "\u27e6", + "longleftarrow;": "\u27f5", + "longleftrightarrow;": "\u27f7", + "longmapsto;": "\u27fc", + "longrightarrow;": "\u27f6", + "looparrowleft;": "\u21ab", + "looparrowright;": "\u21ac", + "lopar;": "\u2985", + "lopf;": "\U0001d55d", + "loplus;": "\u2a2d", + "lotimes;": "\u2a34", + "lowast;": "\u2217", + "lowbar;": "_", + "loz;": "\u25ca", + "lozenge;": "\u25ca", + "lozf;": "\u29eb", + "lpar;": "(", + "lparlt;": "\u2993", + "lrarr;": "\u21c6", + "lrcorner;": "\u231f", + "lrhar;": "\u21cb", + "lrhard;": "\u296d", + "lrm;": "\u200e", + "lrtri;": "\u22bf", + "lsaquo;": "\u2039", + "lscr;": "\U0001d4c1", + "lsh;": "\u21b0", + "lsim;": "\u2272", + "lsime;": "\u2a8d", + "lsimg;": "\u2a8f", + "lsqb;": "[", + "lsquo;": "\u2018", + "lsquor;": "\u201a", + "lstrok;": "\u0142", + "lt": "<", + "lt;": "<", + "ltcc;": "\u2aa6", + "ltcir;": "\u2a79", + "ltdot;": "\u22d6", + "lthree;": "\u22cb", + "ltimes;": "\u22c9", + "ltlarr;": "\u2976", + "ltquest;": "\u2a7b", + "ltrPar;": "\u2996", + "ltri;": "\u25c3", + "ltrie;": "\u22b4", + "ltrif;": "\u25c2", + "lurdshar;": "\u294a", + "luruhar;": "\u2966", + "lvertneqq;": "\u2268\ufe00", + "lvnE;": "\u2268\ufe00", + "mDDot;": "\u223a", + "macr": "\xaf", + "macr;": "\xaf", + "male;": "\u2642", + "malt;": "\u2720", + "maltese;": "\u2720", + "map;": "\u21a6", + "mapsto;": "\u21a6", + "mapstodown;": "\u21a7", + "mapstoleft;": "\u21a4", + "mapstoup;": "\u21a5", + "marker;": "\u25ae", + "mcomma;": "\u2a29", + "mcy;": "\u043c", + "mdash;": "\u2014", + "measuredangle;": "\u2221", + "mfr;": "\U0001d52a", + "mho;": "\u2127", + "micro": "\xb5", + "micro;": "\xb5", + "mid;": "\u2223", + "midast;": "*", + "midcir;": "\u2af0", + "middot": "\xb7", + "middot;": "\xb7", + "minus;": "\u2212", + "minusb;": "\u229f", + "minusd;": "\u2238", + "minusdu;": "\u2a2a", + "mlcp;": "\u2adb", + "mldr;": "\u2026", + "mnplus;": "\u2213", + "models;": "\u22a7", + "mopf;": "\U0001d55e", + "mp;": "\u2213", + "mscr;": "\U0001d4c2", + "mstpos;": "\u223e", + "mu;": "\u03bc", + "multimap;": "\u22b8", + "mumap;": "\u22b8", + "nGg;": "\u22d9\u0338", + "nGt;": "\u226b\u20d2", + "nGtv;": "\u226b\u0338", + "nLeftarrow;": "\u21cd", + "nLeftrightarrow;": "\u21ce", + "nLl;": "\u22d8\u0338", + "nLt;": "\u226a\u20d2", + "nLtv;": "\u226a\u0338", + "nRightarrow;": "\u21cf", + "nVDash;": "\u22af", + "nVdash;": "\u22ae", + "nabla;": "\u2207", + "nacute;": "\u0144", + "nang;": "\u2220\u20d2", + "nap;": "\u2249", + "napE;": "\u2a70\u0338", + "napid;": "\u224b\u0338", + "napos;": "\u0149", + "napprox;": "\u2249", + "natur;": "\u266e", + "natural;": "\u266e", + "naturals;": "\u2115", + "nbsp": "\xa0", + "nbsp;": "\xa0", + "nbump;": "\u224e\u0338", + "nbumpe;": "\u224f\u0338", + "ncap;": "\u2a43", + "ncaron;": "\u0148", + "ncedil;": "\u0146", + "ncong;": "\u2247", + "ncongdot;": "\u2a6d\u0338", + "ncup;": "\u2a42", + "ncy;": "\u043d", + "ndash;": "\u2013", + "ne;": "\u2260", + "neArr;": "\u21d7", + "nearhk;": "\u2924", + "nearr;": "\u2197", + "nearrow;": "\u2197", + "nedot;": "\u2250\u0338", + "nequiv;": "\u2262", + "nesear;": "\u2928", + "nesim;": "\u2242\u0338", + "nexist;": "\u2204", + "nexists;": "\u2204", + "nfr;": "\U0001d52b", + "ngE;": "\u2267\u0338", + "nge;": "\u2271", + "ngeq;": "\u2271", + "ngeqq;": "\u2267\u0338", + "ngeqslant;": "\u2a7e\u0338", + "nges;": "\u2a7e\u0338", + "ngsim;": "\u2275", + "ngt;": "\u226f", + "ngtr;": "\u226f", + "nhArr;": "\u21ce", + "nharr;": "\u21ae", + "nhpar;": "\u2af2", + "ni;": "\u220b", + "nis;": "\u22fc", + "nisd;": "\u22fa", + "niv;": "\u220b", + "njcy;": "\u045a", + "nlArr;": "\u21cd", + "nlE;": "\u2266\u0338", + "nlarr;": "\u219a", + "nldr;": "\u2025", + "nle;": "\u2270", + "nleftarrow;": "\u219a", + "nleftrightarrow;": "\u21ae", + "nleq;": "\u2270", + "nleqq;": "\u2266\u0338", + "nleqslant;": "\u2a7d\u0338", + "nles;": "\u2a7d\u0338", + "nless;": "\u226e", + "nlsim;": "\u2274", + "nlt;": "\u226e", + "nltri;": "\u22ea", + "nltrie;": "\u22ec", + "nmid;": "\u2224", + "nopf;": "\U0001d55f", + "not": "\xac", + "not;": "\xac", + "notin;": "\u2209", + "notinE;": "\u22f9\u0338", + "notindot;": "\u22f5\u0338", + "notinva;": "\u2209", + "notinvb;": "\u22f7", + "notinvc;": "\u22f6", + "notni;": "\u220c", + "notniva;": "\u220c", + "notnivb;": "\u22fe", + "notnivc;": "\u22fd", + "npar;": "\u2226", + "nparallel;": "\u2226", + "nparsl;": "\u2afd\u20e5", + "npart;": "\u2202\u0338", + "npolint;": "\u2a14", + "npr;": "\u2280", + "nprcue;": "\u22e0", + "npre;": "\u2aaf\u0338", + "nprec;": "\u2280", + "npreceq;": "\u2aaf\u0338", + "nrArr;": "\u21cf", + "nrarr;": "\u219b", + "nrarrc;": "\u2933\u0338", + "nrarrw;": "\u219d\u0338", + "nrightarrow;": "\u219b", + "nrtri;": "\u22eb", + "nrtrie;": "\u22ed", + "nsc;": "\u2281", + "nsccue;": "\u22e1", + "nsce;": "\u2ab0\u0338", + "nscr;": "\U0001d4c3", + "nshortmid;": "\u2224", + "nshortparallel;": "\u2226", + "nsim;": "\u2241", + "nsime;": "\u2244", + "nsimeq;": "\u2244", + "nsmid;": "\u2224", + "nspar;": "\u2226", + "nsqsube;": "\u22e2", + "nsqsupe;": "\u22e3", + "nsub;": "\u2284", + "nsubE;": "\u2ac5\u0338", + "nsube;": "\u2288", + "nsubset;": "\u2282\u20d2", + "nsubseteq;": "\u2288", + "nsubseteqq;": "\u2ac5\u0338", + "nsucc;": "\u2281", + "nsucceq;": "\u2ab0\u0338", + "nsup;": "\u2285", + "nsupE;": "\u2ac6\u0338", + "nsupe;": "\u2289", + "nsupset;": "\u2283\u20d2", + "nsupseteq;": "\u2289", + "nsupseteqq;": "\u2ac6\u0338", + "ntgl;": "\u2279", + "ntilde": "\xf1", + "ntilde;": "\xf1", + "ntlg;": "\u2278", + "ntriangleleft;": "\u22ea", + "ntrianglelefteq;": "\u22ec", + "ntriangleright;": "\u22eb", + "ntrianglerighteq;": "\u22ed", + "nu;": "\u03bd", + "num;": "#", + "numero;": "\u2116", + "numsp;": "\u2007", + "nvDash;": "\u22ad", + "nvHarr;": "\u2904", + "nvap;": "\u224d\u20d2", + "nvdash;": "\u22ac", + "nvge;": "\u2265\u20d2", + "nvgt;": ">\u20d2", + "nvinfin;": "\u29de", + "nvlArr;": "\u2902", + "nvle;": "\u2264\u20d2", + "nvlt;": "<\u20d2", + "nvltrie;": "\u22b4\u20d2", + "nvrArr;": "\u2903", + "nvrtrie;": "\u22b5\u20d2", + "nvsim;": "\u223c\u20d2", + "nwArr;": "\u21d6", + "nwarhk;": "\u2923", + "nwarr;": "\u2196", + "nwarrow;": "\u2196", + "nwnear;": "\u2927", + "oS;": "\u24c8", + "oacute": "\xf3", + "oacute;": "\xf3", + "oast;": "\u229b", + "ocir;": "\u229a", + "ocirc": "\xf4", + "ocirc;": "\xf4", + "ocy;": "\u043e", + "odash;": "\u229d", + "odblac;": "\u0151", + "odiv;": "\u2a38", + "odot;": "\u2299", + "odsold;": "\u29bc", + "oelig;": "\u0153", + "ofcir;": "\u29bf", + "ofr;": "\U0001d52c", + "ogon;": "\u02db", + "ograve": "\xf2", + "ograve;": "\xf2", + "ogt;": "\u29c1", + "ohbar;": "\u29b5", + "ohm;": "\u03a9", + "oint;": "\u222e", + "olarr;": "\u21ba", + "olcir;": "\u29be", + "olcross;": "\u29bb", + "oline;": "\u203e", + "olt;": "\u29c0", + "omacr;": "\u014d", + "omega;": "\u03c9", + "omicron;": "\u03bf", + "omid;": "\u29b6", + "ominus;": "\u2296", + "oopf;": "\U0001d560", + "opar;": "\u29b7", + "operp;": "\u29b9", + "oplus;": "\u2295", + "or;": "\u2228", + "orarr;": "\u21bb", + "ord;": "\u2a5d", + "order;": "\u2134", + "orderof;": "\u2134", + "ordf": "\xaa", + "ordf;": "\xaa", + "ordm": "\xba", + "ordm;": "\xba", + "origof;": "\u22b6", + "oror;": "\u2a56", + "orslope;": "\u2a57", + "orv;": "\u2a5b", + "oscr;": "\u2134", + "oslash": "\xf8", + "oslash;": "\xf8", + "osol;": "\u2298", + "otilde": "\xf5", + "otilde;": "\xf5", + "otimes;": "\u2297", + "otimesas;": "\u2a36", + "ouml": "\xf6", + "ouml;": "\xf6", + "ovbar;": "\u233d", + "par;": "\u2225", + "para": "\xb6", + "para;": "\xb6", + "parallel;": "\u2225", + "parsim;": "\u2af3", + "parsl;": "\u2afd", + "part;": "\u2202", + "pcy;": "\u043f", + "percnt;": "%", + "period;": ".", + "permil;": "\u2030", + "perp;": "\u22a5", + "pertenk;": "\u2031", + "pfr;": "\U0001d52d", + "phi;": "\u03c6", + "phiv;": "\u03d5", + "phmmat;": "\u2133", + "phone;": "\u260e", + "pi;": "\u03c0", + "pitchfork;": "\u22d4", + "piv;": "\u03d6", + "planck;": "\u210f", + "planckh;": "\u210e", + "plankv;": "\u210f", + "plus;": "+", + "plusacir;": "\u2a23", + "plusb;": "\u229e", + "pluscir;": "\u2a22", + "plusdo;": "\u2214", + "plusdu;": "\u2a25", + "pluse;": "\u2a72", + "plusmn": "\xb1", + "plusmn;": "\xb1", + "plussim;": "\u2a26", + "plustwo;": "\u2a27", + "pm;": "\xb1", + "pointint;": "\u2a15", + "popf;": "\U0001d561", + "pound": "\xa3", + "pound;": "\xa3", + "pr;": "\u227a", + "prE;": "\u2ab3", + "prap;": "\u2ab7", + "prcue;": "\u227c", + "pre;": "\u2aaf", + "prec;": "\u227a", + "precapprox;": "\u2ab7", + "preccurlyeq;": "\u227c", + "preceq;": "\u2aaf", + "precnapprox;": "\u2ab9", + "precneqq;": "\u2ab5", + "precnsim;": "\u22e8", + "precsim;": "\u227e", + "prime;": "\u2032", + "primes;": "\u2119", + "prnE;": "\u2ab5", + "prnap;": "\u2ab9", + "prnsim;": "\u22e8", + "prod;": "\u220f", + "profalar;": "\u232e", + "profline;": "\u2312", + "profsurf;": "\u2313", + "prop;": "\u221d", + "propto;": "\u221d", + "prsim;": "\u227e", + "prurel;": "\u22b0", + "pscr;": "\U0001d4c5", + "psi;": "\u03c8", + "puncsp;": "\u2008", + "qfr;": "\U0001d52e", + "qint;": "\u2a0c", + "qopf;": "\U0001d562", + "qprime;": "\u2057", + "qscr;": "\U0001d4c6", + "quaternions;": "\u210d", + "quatint;": "\u2a16", + "quest;": "?", + "questeq;": "\u225f", + "quot": "\"", + "quot;": "\"", + "rAarr;": "\u21db", + "rArr;": "\u21d2", + "rAtail;": "\u291c", + "rBarr;": "\u290f", + "rHar;": "\u2964", + "race;": "\u223d\u0331", + "racute;": "\u0155", + "radic;": "\u221a", + "raemptyv;": "\u29b3", + "rang;": "\u27e9", + "rangd;": "\u2992", + "range;": "\u29a5", + "rangle;": "\u27e9", + "raquo": "\xbb", + "raquo;": "\xbb", + "rarr;": "\u2192", + "rarrap;": "\u2975", + "rarrb;": "\u21e5", + "rarrbfs;": "\u2920", + "rarrc;": "\u2933", + "rarrfs;": "\u291e", + "rarrhk;": "\u21aa", + "rarrlp;": "\u21ac", + "rarrpl;": "\u2945", + "rarrsim;": "\u2974", + "rarrtl;": "\u21a3", + "rarrw;": "\u219d", + "ratail;": "\u291a", + "ratio;": "\u2236", + "rationals;": "\u211a", + "rbarr;": "\u290d", + "rbbrk;": "\u2773", + "rbrace;": "}", + "rbrack;": "]", + "rbrke;": "\u298c", + "rbrksld;": "\u298e", + "rbrkslu;": "\u2990", + "rcaron;": "\u0159", + "rcedil;": "\u0157", + "rceil;": "\u2309", + "rcub;": "}", + "rcy;": "\u0440", + "rdca;": "\u2937", + "rdldhar;": "\u2969", + "rdquo;": "\u201d", + "rdquor;": "\u201d", + "rdsh;": "\u21b3", + "real;": "\u211c", + "realine;": "\u211b", + "realpart;": "\u211c", + "reals;": "\u211d", + "rect;": "\u25ad", + "reg": "\xae", + "reg;": "\xae", + "rfisht;": "\u297d", + "rfloor;": "\u230b", + "rfr;": "\U0001d52f", + "rhard;": "\u21c1", + "rharu;": "\u21c0", + "rharul;": "\u296c", + "rho;": "\u03c1", + "rhov;": "\u03f1", + "rightarrow;": "\u2192", + "rightarrowtail;": "\u21a3", + "rightharpoondown;": "\u21c1", + "rightharpoonup;": "\u21c0", + "rightleftarrows;": "\u21c4", + "rightleftharpoons;": "\u21cc", + "rightrightarrows;": "\u21c9", + "rightsquigarrow;": "\u219d", + "rightthreetimes;": "\u22cc", + "ring;": "\u02da", + "risingdotseq;": "\u2253", + "rlarr;": "\u21c4", + "rlhar;": "\u21cc", + "rlm;": "\u200f", + "rmoust;": "\u23b1", + "rmoustache;": "\u23b1", + "rnmid;": "\u2aee", + "roang;": "\u27ed", + "roarr;": "\u21fe", + "robrk;": "\u27e7", + "ropar;": "\u2986", + "ropf;": "\U0001d563", + "roplus;": "\u2a2e", + "rotimes;": "\u2a35", + "rpar;": ")", + "rpargt;": "\u2994", + "rppolint;": "\u2a12", + "rrarr;": "\u21c9", + "rsaquo;": "\u203a", + "rscr;": "\U0001d4c7", + "rsh;": "\u21b1", + "rsqb;": "]", + "rsquo;": "\u2019", + "rsquor;": "\u2019", + "rthree;": "\u22cc", + "rtimes;": "\u22ca", + "rtri;": "\u25b9", + "rtrie;": "\u22b5", + "rtrif;": "\u25b8", + "rtriltri;": "\u29ce", + "ruluhar;": "\u2968", + "rx;": "\u211e", + "sacute;": "\u015b", + "sbquo;": "\u201a", + "sc;": "\u227b", + "scE;": "\u2ab4", + "scap;": "\u2ab8", + "scaron;": "\u0161", + "sccue;": "\u227d", + "sce;": "\u2ab0", + "scedil;": "\u015f", + "scirc;": "\u015d", + "scnE;": "\u2ab6", + "scnap;": "\u2aba", + "scnsim;": "\u22e9", + "scpolint;": "\u2a13", + "scsim;": "\u227f", + "scy;": "\u0441", + "sdot;": "\u22c5", + "sdotb;": "\u22a1", + "sdote;": "\u2a66", + "seArr;": "\u21d8", + "searhk;": "\u2925", + "searr;": "\u2198", + "searrow;": "\u2198", + "sect": "\xa7", + "sect;": "\xa7", + "semi;": ";", + "seswar;": "\u2929", + "setminus;": "\u2216", + "setmn;": "\u2216", + "sext;": "\u2736", + "sfr;": "\U0001d530", + "sfrown;": "\u2322", + "sharp;": "\u266f", + "shchcy;": "\u0449", + "shcy;": "\u0448", + "shortmid;": "\u2223", + "shortparallel;": "\u2225", + "shy": "\xad", + "shy;": "\xad", + "sigma;": "\u03c3", + "sigmaf;": "\u03c2", + "sigmav;": "\u03c2", + "sim;": "\u223c", + "simdot;": "\u2a6a", + "sime;": "\u2243", + "simeq;": "\u2243", + "simg;": "\u2a9e", + "simgE;": "\u2aa0", + "siml;": "\u2a9d", + "simlE;": "\u2a9f", + "simne;": "\u2246", + "simplus;": "\u2a24", + "simrarr;": "\u2972", + "slarr;": "\u2190", + "smallsetminus;": "\u2216", + "smashp;": "\u2a33", + "smeparsl;": "\u29e4", + "smid;": "\u2223", + "smile;": "\u2323", + "smt;": "\u2aaa", + "smte;": "\u2aac", + "smtes;": "\u2aac\ufe00", + "softcy;": "\u044c", + "sol;": "/", + "solb;": "\u29c4", + "solbar;": "\u233f", + "sopf;": "\U0001d564", + "spades;": "\u2660", + "spadesuit;": "\u2660", + "spar;": "\u2225", + "sqcap;": "\u2293", + "sqcaps;": "\u2293\ufe00", + "sqcup;": "\u2294", + "sqcups;": "\u2294\ufe00", + "sqsub;": "\u228f", + "sqsube;": "\u2291", + "sqsubset;": "\u228f", + "sqsubseteq;": "\u2291", + "sqsup;": "\u2290", + "sqsupe;": "\u2292", + "sqsupset;": "\u2290", + "sqsupseteq;": "\u2292", + "squ;": "\u25a1", + "square;": "\u25a1", + "squarf;": "\u25aa", + "squf;": "\u25aa", + "srarr;": "\u2192", + "sscr;": "\U0001d4c8", + "ssetmn;": "\u2216", + "ssmile;": "\u2323", + "sstarf;": "\u22c6", + "star;": "\u2606", + "starf;": "\u2605", + "straightepsilon;": "\u03f5", + "straightphi;": "\u03d5", + "strns;": "\xaf", + "sub;": "\u2282", + "subE;": "\u2ac5", + "subdot;": "\u2abd", + "sube;": "\u2286", + "subedot;": "\u2ac3", + "submult;": "\u2ac1", + "subnE;": "\u2acb", + "subne;": "\u228a", + "subplus;": "\u2abf", + "subrarr;": "\u2979", + "subset;": "\u2282", + "subseteq;": "\u2286", + "subseteqq;": "\u2ac5", + "subsetneq;": "\u228a", + "subsetneqq;": "\u2acb", + "subsim;": "\u2ac7", + "subsub;": "\u2ad5", + "subsup;": "\u2ad3", + "succ;": "\u227b", + "succapprox;": "\u2ab8", + "succcurlyeq;": "\u227d", + "succeq;": "\u2ab0", + "succnapprox;": "\u2aba", + "succneqq;": "\u2ab6", + "succnsim;": "\u22e9", + "succsim;": "\u227f", + "sum;": "\u2211", + "sung;": "\u266a", + "sup1": "\xb9", + "sup1;": "\xb9", + "sup2": "\xb2", + "sup2;": "\xb2", + "sup3": "\xb3", + "sup3;": "\xb3", + "sup;": "\u2283", + "supE;": "\u2ac6", + "supdot;": "\u2abe", + "supdsub;": "\u2ad8", + "supe;": "\u2287", + "supedot;": "\u2ac4", + "suphsol;": "\u27c9", + "suphsub;": "\u2ad7", + "suplarr;": "\u297b", + "supmult;": "\u2ac2", + "supnE;": "\u2acc", + "supne;": "\u228b", + "supplus;": "\u2ac0", + "supset;": "\u2283", + "supseteq;": "\u2287", + "supseteqq;": "\u2ac6", + "supsetneq;": "\u228b", + "supsetneqq;": "\u2acc", + "supsim;": "\u2ac8", + "supsub;": "\u2ad4", + "supsup;": "\u2ad6", + "swArr;": "\u21d9", + "swarhk;": "\u2926", + "swarr;": "\u2199", + "swarrow;": "\u2199", + "swnwar;": "\u292a", + "szlig": "\xdf", + "szlig;": "\xdf", + "target;": "\u2316", + "tau;": "\u03c4", + "tbrk;": "\u23b4", + "tcaron;": "\u0165", + "tcedil;": "\u0163", + "tcy;": "\u0442", + "tdot;": "\u20db", + "telrec;": "\u2315", + "tfr;": "\U0001d531", + "there4;": "\u2234", + "therefore;": "\u2234", + "theta;": "\u03b8", + "thetasym;": "\u03d1", + "thetav;": "\u03d1", + "thickapprox;": "\u2248", + "thicksim;": "\u223c", + "thinsp;": "\u2009", + "thkap;": "\u2248", + "thksim;": "\u223c", + "thorn": "\xfe", + "thorn;": "\xfe", + "tilde;": "\u02dc", + "times": "\xd7", + "times;": "\xd7", + "timesb;": "\u22a0", + "timesbar;": "\u2a31", + "timesd;": "\u2a30", + "tint;": "\u222d", + "toea;": "\u2928", + "top;": "\u22a4", + "topbot;": "\u2336", + "topcir;": "\u2af1", + "topf;": "\U0001d565", + "topfork;": "\u2ada", + "tosa;": "\u2929", + "tprime;": "\u2034", + "trade;": "\u2122", + "triangle;": "\u25b5", + "triangledown;": "\u25bf", + "triangleleft;": "\u25c3", + "trianglelefteq;": "\u22b4", + "triangleq;": "\u225c", + "triangleright;": "\u25b9", + "trianglerighteq;": "\u22b5", + "tridot;": "\u25ec", + "trie;": "\u225c", + "triminus;": "\u2a3a", + "triplus;": "\u2a39", + "trisb;": "\u29cd", + "tritime;": "\u2a3b", + "trpezium;": "\u23e2", + "tscr;": "\U0001d4c9", + "tscy;": "\u0446", + "tshcy;": "\u045b", + "tstrok;": "\u0167", + "twixt;": "\u226c", + "twoheadleftarrow;": "\u219e", + "twoheadrightarrow;": "\u21a0", + "uArr;": "\u21d1", + "uHar;": "\u2963", + "uacute": "\xfa", + "uacute;": "\xfa", + "uarr;": "\u2191", + "ubrcy;": "\u045e", + "ubreve;": "\u016d", + "ucirc": "\xfb", + "ucirc;": "\xfb", + "ucy;": "\u0443", + "udarr;": "\u21c5", + "udblac;": "\u0171", + "udhar;": "\u296e", + "ufisht;": "\u297e", + "ufr;": "\U0001d532", + "ugrave": "\xf9", + "ugrave;": "\xf9", + "uharl;": "\u21bf", + "uharr;": "\u21be", + "uhblk;": "\u2580", + "ulcorn;": "\u231c", + "ulcorner;": "\u231c", + "ulcrop;": "\u230f", + "ultri;": "\u25f8", + "umacr;": "\u016b", + "uml": "\xa8", + "uml;": "\xa8", + "uogon;": "\u0173", + "uopf;": "\U0001d566", + "uparrow;": "\u2191", + "updownarrow;": "\u2195", + "upharpoonleft;": "\u21bf", + "upharpoonright;": "\u21be", + "uplus;": "\u228e", + "upsi;": "\u03c5", + "upsih;": "\u03d2", + "upsilon;": "\u03c5", + "upuparrows;": "\u21c8", + "urcorn;": "\u231d", + "urcorner;": "\u231d", + "urcrop;": "\u230e", + "uring;": "\u016f", + "urtri;": "\u25f9", + "uscr;": "\U0001d4ca", + "utdot;": "\u22f0", + "utilde;": "\u0169", + "utri;": "\u25b5", + "utrif;": "\u25b4", + "uuarr;": "\u21c8", + "uuml": "\xfc", + "uuml;": "\xfc", + "uwangle;": "\u29a7", + "vArr;": "\u21d5", + "vBar;": "\u2ae8", + "vBarv;": "\u2ae9", + "vDash;": "\u22a8", + "vangrt;": "\u299c", + "varepsilon;": "\u03f5", + "varkappa;": "\u03f0", + "varnothing;": "\u2205", + "varphi;": "\u03d5", + "varpi;": "\u03d6", + "varpropto;": "\u221d", + "varr;": "\u2195", + "varrho;": "\u03f1", + "varsigma;": "\u03c2", + "varsubsetneq;": "\u228a\ufe00", + "varsubsetneqq;": "\u2acb\ufe00", + "varsupsetneq;": "\u228b\ufe00", + "varsupsetneqq;": "\u2acc\ufe00", + "vartheta;": "\u03d1", + "vartriangleleft;": "\u22b2", + "vartriangleright;": "\u22b3", + "vcy;": "\u0432", + "vdash;": "\u22a2", + "vee;": "\u2228", + "veebar;": "\u22bb", + "veeeq;": "\u225a", + "vellip;": "\u22ee", + "verbar;": "|", + "vert;": "|", + "vfr;": "\U0001d533", + "vltri;": "\u22b2", + "vnsub;": "\u2282\u20d2", + "vnsup;": "\u2283\u20d2", + "vopf;": "\U0001d567", + "vprop;": "\u221d", + "vrtri;": "\u22b3", + "vscr;": "\U0001d4cb", + "vsubnE;": "\u2acb\ufe00", + "vsubne;": "\u228a\ufe00", + "vsupnE;": "\u2acc\ufe00", + "vsupne;": "\u228b\ufe00", + "vzigzag;": "\u299a", + "wcirc;": "\u0175", + "wedbar;": "\u2a5f", + "wedge;": "\u2227", + "wedgeq;": "\u2259", + "weierp;": "\u2118", + "wfr;": "\U0001d534", + "wopf;": "\U0001d568", + "wp;": "\u2118", + "wr;": "\u2240", + "wreath;": "\u2240", + "wscr;": "\U0001d4cc", + "xcap;": "\u22c2", + "xcirc;": "\u25ef", + "xcup;": "\u22c3", + "xdtri;": "\u25bd", + "xfr;": "\U0001d535", + "xhArr;": "\u27fa", + "xharr;": "\u27f7", + "xi;": "\u03be", + "xlArr;": "\u27f8", + "xlarr;": "\u27f5", + "xmap;": "\u27fc", + "xnis;": "\u22fb", + "xodot;": "\u2a00", + "xopf;": "\U0001d569", + "xoplus;": "\u2a01", + "xotime;": "\u2a02", + "xrArr;": "\u27f9", + "xrarr;": "\u27f6", + "xscr;": "\U0001d4cd", + "xsqcup;": "\u2a06", + "xuplus;": "\u2a04", + "xutri;": "\u25b3", + "xvee;": "\u22c1", + "xwedge;": "\u22c0", + "yacute": "\xfd", + "yacute;": "\xfd", + "yacy;": "\u044f", + "ycirc;": "\u0177", + "ycy;": "\u044b", + "yen": "\xa5", + "yen;": "\xa5", + "yfr;": "\U0001d536", + "yicy;": "\u0457", + "yopf;": "\U0001d56a", + "yscr;": "\U0001d4ce", + "yucy;": "\u044e", + "yuml": "\xff", + "yuml;": "\xff", + "zacute;": "\u017a", + "zcaron;": "\u017e", + "zcy;": "\u0437", + "zdot;": "\u017c", + "zeetrf;": "\u2128", + "zeta;": "\u03b6", + "zfr;": "\U0001d537", + "zhcy;": "\u0436", + "zigrarr;": "\u21dd", + "zopf;": "\U0001d56b", + "zscr;": "\U0001d4cf", + "zwj;": "\u200d", + "zwnj;": "\u200c", +} + +replacementCharacters = { + 0x0: "\uFFFD", + 0x0d: "\u000D", + 0x80: "\u20AC", + 0x81: "\u0081", + 0x81: "\u0081", + 0x82: "\u201A", + 0x83: "\u0192", + 0x84: "\u201E", + 0x85: "\u2026", + 0x86: "\u2020", + 0x87: "\u2021", + 0x88: "\u02C6", + 0x89: "\u2030", + 0x8A: "\u0160", + 0x8B: "\u2039", + 0x8C: "\u0152", + 0x8D: "\u008D", + 0x8E: "\u017D", + 0x8F: "\u008F", + 0x90: "\u0090", + 0x91: "\u2018", + 0x92: "\u2019", + 0x93: "\u201C", + 0x94: "\u201D", + 0x95: "\u2022", + 0x96: "\u2013", + 0x97: "\u2014", + 0x98: "\u02DC", + 0x99: "\u2122", + 0x9A: "\u0161", + 0x9B: "\u203A", + 0x9C: "\u0153", + 0x9D: "\u009D", + 0x9E: "\u017E", + 0x9F: "\u0178", +} + +encodings = { + '437': 'cp437', + '850': 'cp850', + '852': 'cp852', + '855': 'cp855', + '857': 'cp857', + '860': 'cp860', + '861': 'cp861', + '862': 'cp862', + '863': 'cp863', + '865': 'cp865', + '866': 'cp866', + '869': 'cp869', + 'ansix341968': 'ascii', + 'ansix341986': 'ascii', + 'arabic': 'iso8859-6', + 'ascii': 'ascii', + 'asmo708': 'iso8859-6', + 'big5': 'big5', + 'big5hkscs': 'big5hkscs', + 'chinese': 'gbk', + 'cp037': 'cp037', + 'cp1026': 'cp1026', + 'cp154': 'ptcp154', + 'cp367': 'ascii', + 'cp424': 'cp424', + 'cp437': 'cp437', + 'cp500': 'cp500', + 'cp775': 'cp775', + 'cp819': 'windows-1252', + 'cp850': 'cp850', + 'cp852': 'cp852', + 'cp855': 'cp855', + 'cp857': 'cp857', + 'cp860': 'cp860', + 'cp861': 'cp861', + 'cp862': 'cp862', + 'cp863': 'cp863', + 'cp864': 'cp864', + 'cp865': 'cp865', + 'cp866': 'cp866', + 'cp869': 'cp869', + 'cp936': 'gbk', + 'cpgr': 'cp869', + 'cpis': 'cp861', + 'csascii': 'ascii', + 'csbig5': 'big5', + 'cseuckr': 'cp949', + 'cseucpkdfmtjapanese': 'euc_jp', + 'csgb2312': 'gbk', + 'cshproman8': 'hp-roman8', + 'csibm037': 'cp037', + 'csibm1026': 'cp1026', + 'csibm424': 'cp424', + 'csibm500': 'cp500', + 'csibm855': 'cp855', + 'csibm857': 'cp857', + 'csibm860': 'cp860', + 'csibm861': 'cp861', + 'csibm863': 'cp863', + 'csibm864': 'cp864', + 'csibm865': 'cp865', + 'csibm866': 'cp866', + 'csibm869': 'cp869', + 'csiso2022jp': 'iso2022_jp', + 'csiso2022jp2': 'iso2022_jp_2', + 'csiso2022kr': 'iso2022_kr', + 'csiso58gb231280': 'gbk', + 'csisolatin1': 'windows-1252', + 'csisolatin2': 'iso8859-2', + 'csisolatin3': 'iso8859-3', + 'csisolatin4': 'iso8859-4', + 'csisolatin5': 'windows-1254', + 'csisolatin6': 'iso8859-10', + 'csisolatinarabic': 'iso8859-6', + 'csisolatincyrillic': 'iso8859-5', + 'csisolatingreek': 'iso8859-7', + 'csisolatinhebrew': 'iso8859-8', + 'cskoi8r': 'koi8-r', + 'csksc56011987': 'cp949', + 'cspc775baltic': 'cp775', + 'cspc850multilingual': 'cp850', + 'cspc862latinhebrew': 'cp862', + 'cspc8codepage437': 'cp437', + 'cspcp852': 'cp852', + 'csptcp154': 'ptcp154', + 'csshiftjis': 'shift_jis', + 'csunicode11utf7': 'utf-7', + 'cyrillic': 'iso8859-5', + 'cyrillicasian': 'ptcp154', + 'ebcdiccpbe': 'cp500', + 'ebcdiccpca': 'cp037', + 'ebcdiccpch': 'cp500', + 'ebcdiccphe': 'cp424', + 'ebcdiccpnl': 'cp037', + 'ebcdiccpus': 'cp037', + 'ebcdiccpwt': 'cp037', + 'ecma114': 'iso8859-6', + 'ecma118': 'iso8859-7', + 'elot928': 'iso8859-7', + 'eucjp': 'euc_jp', + 'euckr': 'cp949', + 'extendedunixcodepackedformatforjapanese': 'euc_jp', + 'gb18030': 'gb18030', + 'gb2312': 'gbk', + 'gb231280': 'gbk', + 'gbk': 'gbk', + 'greek': 'iso8859-7', + 'greek8': 'iso8859-7', + 'hebrew': 'iso8859-8', + 'hproman8': 'hp-roman8', + 'hzgb2312': 'hz', + 'ibm037': 'cp037', + 'ibm1026': 'cp1026', + 'ibm367': 'ascii', + 'ibm424': 'cp424', + 'ibm437': 'cp437', + 'ibm500': 'cp500', + 'ibm775': 'cp775', + 'ibm819': 'windows-1252', + 'ibm850': 'cp850', + 'ibm852': 'cp852', + 'ibm855': 'cp855', + 'ibm857': 'cp857', + 'ibm860': 'cp860', + 'ibm861': 'cp861', + 'ibm862': 'cp862', + 'ibm863': 'cp863', + 'ibm864': 'cp864', + 'ibm865': 'cp865', + 'ibm866': 'cp866', + 'ibm869': 'cp869', + 'iso2022jp': 'iso2022_jp', + 'iso2022jp2': 'iso2022_jp_2', + 'iso2022kr': 'iso2022_kr', + 'iso646irv1991': 'ascii', + 'iso646us': 'ascii', + 'iso88591': 'windows-1252', + 'iso885910': 'iso8859-10', + 'iso8859101992': 'iso8859-10', + 'iso885911987': 'windows-1252', + 'iso885913': 'iso8859-13', + 'iso885914': 'iso8859-14', + 'iso8859141998': 'iso8859-14', + 'iso885915': 'iso8859-15', + 'iso885916': 'iso8859-16', + 'iso8859162001': 'iso8859-16', + 'iso88592': 'iso8859-2', + 'iso885921987': 'iso8859-2', + 'iso88593': 'iso8859-3', + 'iso885931988': 'iso8859-3', + 'iso88594': 'iso8859-4', + 'iso885941988': 'iso8859-4', + 'iso88595': 'iso8859-5', + 'iso885951988': 'iso8859-5', + 'iso88596': 'iso8859-6', + 'iso885961987': 'iso8859-6', + 'iso88597': 'iso8859-7', + 'iso885971987': 'iso8859-7', + 'iso88598': 'iso8859-8', + 'iso885981988': 'iso8859-8', + 'iso88599': 'windows-1254', + 'iso885991989': 'windows-1254', + 'isoceltic': 'iso8859-14', + 'isoir100': 'windows-1252', + 'isoir101': 'iso8859-2', + 'isoir109': 'iso8859-3', + 'isoir110': 'iso8859-4', + 'isoir126': 'iso8859-7', + 'isoir127': 'iso8859-6', + 'isoir138': 'iso8859-8', + 'isoir144': 'iso8859-5', + 'isoir148': 'windows-1254', + 'isoir149': 'cp949', + 'isoir157': 'iso8859-10', + 'isoir199': 'iso8859-14', + 'isoir226': 'iso8859-16', + 'isoir58': 'gbk', + 'isoir6': 'ascii', + 'koi8r': 'koi8-r', + 'koi8u': 'koi8-u', + 'korean': 'cp949', + 'ksc5601': 'cp949', + 'ksc56011987': 'cp949', + 'ksc56011989': 'cp949', + 'l1': 'windows-1252', + 'l10': 'iso8859-16', + 'l2': 'iso8859-2', + 'l3': 'iso8859-3', + 'l4': 'iso8859-4', + 'l5': 'windows-1254', + 'l6': 'iso8859-10', + 'l8': 'iso8859-14', + 'latin1': 'windows-1252', + 'latin10': 'iso8859-16', + 'latin2': 'iso8859-2', + 'latin3': 'iso8859-3', + 'latin4': 'iso8859-4', + 'latin5': 'windows-1254', + 'latin6': 'iso8859-10', + 'latin8': 'iso8859-14', + 'latin9': 'iso8859-15', + 'ms936': 'gbk', + 'mskanji': 'shift_jis', + 'pt154': 'ptcp154', + 'ptcp154': 'ptcp154', + 'r8': 'hp-roman8', + 'roman8': 'hp-roman8', + 'shiftjis': 'shift_jis', + 'tis620': 'cp874', + 'unicode11utf7': 'utf-7', + 'us': 'ascii', + 'usascii': 'ascii', + 'utf16': 'utf-16', + 'utf16be': 'utf-16-be', + 'utf16le': 'utf-16-le', + 'utf8': 'utf-8', + 'windows1250': 'cp1250', + 'windows1251': 'cp1251', + 'windows1252': 'cp1252', + 'windows1253': 'cp1253', + 'windows1254': 'cp1254', + 'windows1255': 'cp1255', + 'windows1256': 'cp1256', + 'windows1257': 'cp1257', + 'windows1258': 'cp1258', + 'windows936': 'gbk', + 'x-x-big5': 'big5'} + +tokenTypes = { + "Doctype": 0, + "Characters": 1, + "SpaceCharacters": 2, + "StartTag": 3, + "EndTag": 4, + "EmptyTag": 5, + "Comment": 6, + "ParseError": 7 +} + +tagTokenTypes = frozenset((tokenTypes["StartTag"], tokenTypes["EndTag"], + tokenTypes["EmptyTag"])) + + +prefixes = dict([(v, k) for k, v in namespaces.items()]) +prefixes["http://www.w3.org/1998/Math/MathML"] = "math" + + +class DataLossWarning(UserWarning): + pass + + +class ReparseException(Exception): + pass diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/__init__.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/_base.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/_base.py new file mode 100644 index 0000000..c7dbaed --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/_base.py @@ -0,0 +1,12 @@ +from __future__ import absolute_import, division, unicode_literals + + +class Filter(object): + def __init__(self, source): + self.source = source + + def __iter__(self): + return iter(self.source) + + def __getattr__(self, name): + return getattr(self.source, name) diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.py new file mode 100644 index 0000000..fed6996 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/alphabeticalattributes.py @@ -0,0 +1,20 @@ +from __future__ import absolute_import, division, unicode_literals + +from . import _base + +try: + from collections import OrderedDict +except ImportError: + from ordereddict import OrderedDict + + +class Filter(_base.Filter): + def __iter__(self): + for token in _base.Filter.__iter__(self): + if token["type"] in ("StartTag", "EmptyTag"): + attrs = OrderedDict() + for name, value in sorted(token["data"].items(), + key=lambda x: x[0]): + attrs[name] = value + token["data"] = attrs + yield token diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.py new file mode 100644 index 0000000..ca33b70 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/inject_meta_charset.py @@ -0,0 +1,65 @@ +from __future__ import absolute_import, division, unicode_literals + +from . import _base + + +class Filter(_base.Filter): + def __init__(self, source, encoding): + _base.Filter.__init__(self, source) + self.encoding = encoding + + def __iter__(self): + state = "pre_head" + meta_found = (self.encoding is None) + pending = [] + + for token in _base.Filter.__iter__(self): + type = token["type"] + if type == "StartTag": + if token["name"].lower() == "head": + state = "in_head" + + elif type == "EmptyTag": + if token["name"].lower() == "meta": + # replace charset with actual encoding + has_http_equiv_content_type = False + for (namespace, name), value in token["data"].items(): + if namespace is not None: + continue + elif name.lower() == 'charset': + token["data"][(namespace, name)] = self.encoding + meta_found = True + break + elif name == 'http-equiv' and value.lower() == 'content-type': + has_http_equiv_content_type = True + else: + if has_http_equiv_content_type and (None, "content") in token["data"]: + token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding + meta_found = True + + elif token["name"].lower() == "head" and not meta_found: + # insert meta into empty head + yield {"type": "StartTag", "name": "head", + "data": token["data"]} + yield {"type": "EmptyTag", "name": "meta", + "data": {(None, "charset"): self.encoding}} + yield {"type": "EndTag", "name": "head"} + meta_found = True + continue + + elif type == "EndTag": + if token["name"].lower() == "head" and pending: + # insert meta into head (if necessary) and flush pending queue + yield pending.pop(0) + if not meta_found: + yield {"type": "EmptyTag", "name": "meta", + "data": {(None, "charset"): self.encoding}} + while pending: + yield pending.pop(0) + meta_found = True + state = "post_head" + + if state == "in_head": + pending.append(token) + else: + yield token diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/lint.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/lint.py new file mode 100644 index 0000000..83ad639 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/lint.py @@ -0,0 +1,93 @@ +from __future__ import absolute_import, division, unicode_literals + +from gettext import gettext +_ = gettext + +from . import _base +from ..constants import cdataElements, rcdataElements, voidElements + +from ..constants import spaceCharacters +spaceCharacters = "".join(spaceCharacters) + + +class LintError(Exception): + pass + + +class Filter(_base.Filter): + def __iter__(self): + open_elements = [] + contentModelFlag = "PCDATA" + for token in _base.Filter.__iter__(self): + type = token["type"] + if type in ("StartTag", "EmptyTag"): + name = token["name"] + if contentModelFlag != "PCDATA": + raise LintError(_("StartTag not in PCDATA content model flag: %s") % name) + if not isinstance(name, str): + raise LintError(_("Tag name is not a string: %r") % name) + if not name: + raise LintError(_("Empty tag name")) + if type == "StartTag" and name in voidElements: + raise LintError(_("Void element reported as StartTag token: %s") % name) + elif type == "EmptyTag" and name not in voidElements: + raise LintError(_("Non-void element reported as EmptyTag token: %s") % token["name"]) + if type == "StartTag": + open_elements.append(name) + for name, value in token["data"]: + if not isinstance(name, str): + raise LintError(_("Attribute name is not a string: %r") % name) + if not name: + raise LintError(_("Empty attribute name")) + if not isinstance(value, str): + raise LintError(_("Attribute value is not a string: %r") % value) + if name in cdataElements: + contentModelFlag = "CDATA" + elif name in rcdataElements: + contentModelFlag = "RCDATA" + elif name == "plaintext": + contentModelFlag = "PLAINTEXT" + + elif type == "EndTag": + name = token["name"] + if not isinstance(name, str): + raise LintError(_("Tag name is not a string: %r") % name) + if not name: + raise LintError(_("Empty tag name")) + if name in voidElements: + raise LintError(_("Void element reported as EndTag token: %s") % name) + start_name = open_elements.pop() + if start_name != name: + raise LintError(_("EndTag (%s) does not match StartTag (%s)") % (name, start_name)) + contentModelFlag = "PCDATA" + + elif type == "Comment": + if contentModelFlag != "PCDATA": + raise LintError(_("Comment not in PCDATA content model flag")) + + elif type in ("Characters", "SpaceCharacters"): + data = token["data"] + if not isinstance(data, str): + raise LintError(_("Attribute name is not a string: %r") % data) + if not data: + raise LintError(_("%s token with empty data") % type) + if type == "SpaceCharacters": + data = data.strip(spaceCharacters) + if data: + raise LintError(_("Non-space character(s) found in SpaceCharacters token: ") % data) + + elif type == "Doctype": + name = token["name"] + if contentModelFlag != "PCDATA": + raise LintError(_("Doctype not in PCDATA content model flag: %s") % name) + if not isinstance(name, str): + raise LintError(_("Tag name is not a string: %r") % name) + # XXX: what to do with token["data"] ? + + elif type in ("ParseError", "SerializeError"): + pass + + else: + raise LintError(_("Unknown token type: %s") % type) + + yield token diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/optionaltags.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/optionaltags.py new file mode 100644 index 0000000..fefe0b3 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/optionaltags.py @@ -0,0 +1,205 @@ +from __future__ import absolute_import, division, unicode_literals + +from . import _base + + +class Filter(_base.Filter): + def slider(self): + previous1 = previous2 = None + for token in self.source: + if previous1 is not None: + yield previous2, previous1, token + previous2 = previous1 + previous1 = token + yield previous2, previous1, None + + def __iter__(self): + for previous, token, next in self.slider(): + type = token["type"] + if type == "StartTag": + if (token["data"] or + not self.is_optional_start(token["name"], previous, next)): + yield token + elif type == "EndTag": + if not self.is_optional_end(token["name"], next): + yield token + else: + yield token + + def is_optional_start(self, tagname, previous, next): + type = next and next["type"] or None + if tagname in 'html': + # An html element's start tag may be omitted if the first thing + # inside the html element is not a space character or a comment. + return type not in ("Comment", "SpaceCharacters") + elif tagname == 'head': + # A head element's start tag may be omitted if the first thing + # inside the head element is an element. + # XXX: we also omit the start tag if the head element is empty + if type in ("StartTag", "EmptyTag"): + return True + elif type == "EndTag": + return next["name"] == "head" + elif tagname == 'body': + # A body element's start tag may be omitted if the first thing + # inside the body element is not a space character or a comment, + # except if the first thing inside the body element is a script + # or style element and the node immediately preceding the body + # element is a head element whose end tag has been omitted. + if type in ("Comment", "SpaceCharacters"): + return False + elif type == "StartTag": + # XXX: we do not look at the preceding event, so we never omit + # the body element's start tag if it's followed by a script or + # a style element. + return next["name"] not in ('script', 'style') + else: + return True + elif tagname == 'colgroup': + # A colgroup element's start tag may be omitted if the first thing + # inside the colgroup element is a col element, and if the element + # is not immediately preceeded by another colgroup element whose + # end tag has been omitted. + if type in ("StartTag", "EmptyTag"): + # XXX: we do not look at the preceding event, so instead we never + # omit the colgroup element's end tag when it is immediately + # followed by another colgroup element. See is_optional_end. + return next["name"] == "col" + else: + return False + elif tagname == 'tbody': + # A tbody element's start tag may be omitted if the first thing + # inside the tbody element is a tr element, and if the element is + # not immediately preceeded by a tbody, thead, or tfoot element + # whose end tag has been omitted. + if type == "StartTag": + # omit the thead and tfoot elements' end tag when they are + # immediately followed by a tbody element. See is_optional_end. + if previous and previous['type'] == 'EndTag' and \ + previous['name'] in ('tbody', 'thead', 'tfoot'): + return False + return next["name"] == 'tr' + else: + return False + return False + + def is_optional_end(self, tagname, next): + type = next and next["type"] or None + if tagname in ('html', 'head', 'body'): + # An html element's end tag may be omitted if the html element + # is not immediately followed by a space character or a comment. + return type not in ("Comment", "SpaceCharacters") + elif tagname in ('li', 'optgroup', 'tr'): + # A li element's end tag may be omitted if the li element is + # immediately followed by another li element or if there is + # no more content in the parent element. + # An optgroup element's end tag may be omitted if the optgroup + # element is immediately followed by another optgroup element, + # or if there is no more content in the parent element. + # A tr element's end tag may be omitted if the tr element is + # immediately followed by another tr element, or if there is + # no more content in the parent element. + if type == "StartTag": + return next["name"] == tagname + else: + return type == "EndTag" or type is None + elif tagname in ('dt', 'dd'): + # A dt element's end tag may be omitted if the dt element is + # immediately followed by another dt element or a dd element. + # A dd element's end tag may be omitted if the dd element is + # immediately followed by another dd element or a dt element, + # or if there is no more content in the parent element. + if type == "StartTag": + return next["name"] in ('dt', 'dd') + elif tagname == 'dd': + return type == "EndTag" or type is None + else: + return False + elif tagname == 'p': + # A p element's end tag may be omitted if the p element is + # immediately followed by an address, article, aside, + # blockquote, datagrid, dialog, dir, div, dl, fieldset, + # footer, form, h1, h2, h3, h4, h5, h6, header, hr, menu, + # nav, ol, p, pre, section, table, or ul, element, or if + # there is no more content in the parent element. + if type in ("StartTag", "EmptyTag"): + return next["name"] in ('address', 'article', 'aside', + 'blockquote', 'datagrid', 'dialog', + 'dir', 'div', 'dl', 'fieldset', 'footer', + 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', + 'header', 'hr', 'menu', 'nav', 'ol', + 'p', 'pre', 'section', 'table', 'ul') + else: + return type == "EndTag" or type is None + elif tagname == 'option': + # An option element's end tag may be omitted if the option + # element is immediately followed by another option element, + # or if it is immediately followed by an optgroup + # element, or if there is no more content in the parent + # element. + if type == "StartTag": + return next["name"] in ('option', 'optgroup') + else: + return type == "EndTag" or type is None + elif tagname in ('rt', 'rp'): + # An rt element's end tag may be omitted if the rt element is + # immediately followed by an rt or rp element, or if there is + # no more content in the parent element. + # An rp element's end tag may be omitted if the rp element is + # immediately followed by an rt or rp element, or if there is + # no more content in the parent element. + if type == "StartTag": + return next["name"] in ('rt', 'rp') + else: + return type == "EndTag" or type is None + elif tagname == 'colgroup': + # A colgroup element's end tag may be omitted if the colgroup + # element is not immediately followed by a space character or + # a comment. + if type in ("Comment", "SpaceCharacters"): + return False + elif type == "StartTag": + # XXX: we also look for an immediately following colgroup + # element. See is_optional_start. + return next["name"] != 'colgroup' + else: + return True + elif tagname in ('thead', 'tbody'): + # A thead element's end tag may be omitted if the thead element + # is immediately followed by a tbody or tfoot element. + # A tbody element's end tag may be omitted if the tbody element + # is immediately followed by a tbody or tfoot element, or if + # there is no more content in the parent element. + # A tfoot element's end tag may be omitted if the tfoot element + # is immediately followed by a tbody element, or if there is no + # more content in the parent element. + # XXX: we never omit the end tag when the following element is + # a tbody. See is_optional_start. + if type == "StartTag": + return next["name"] in ['tbody', 'tfoot'] + elif tagname == 'tbody': + return type == "EndTag" or type is None + else: + return False + elif tagname == 'tfoot': + # A tfoot element's end tag may be omitted if the tfoot element + # is immediately followed by a tbody element, or if there is no + # more content in the parent element. + # XXX: we never omit the end tag when the following element is + # a tbody. See is_optional_start. + if type == "StartTag": + return next["name"] == 'tbody' + else: + return type == "EndTag" or type is None + elif tagname in ('td', 'th'): + # A td element's end tag may be omitted if the td element is + # immediately followed by a td or th element, or if there is + # no more content in the parent element. + # A th element's end tag may be omitted if the th element is + # immediately followed by a td or th element, or if there is + # no more content in the parent element. + if type == "StartTag": + return next["name"] in ('td', 'th') + else: + return type == "EndTag" or type is None + return False diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/sanitizer.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/sanitizer.py new file mode 100644 index 0000000..b206b54 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/sanitizer.py @@ -0,0 +1,12 @@ +from __future__ import absolute_import, division, unicode_literals + +from . import _base +from ..sanitizer import HTMLSanitizerMixin + + +class Filter(_base.Filter, HTMLSanitizerMixin): + def __iter__(self): + for token in _base.Filter.__iter__(self): + token = self.sanitize_token(token) + if token: + yield token diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/whitespace.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/whitespace.py new file mode 100644 index 0000000..dfc60ee --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/filters/whitespace.py @@ -0,0 +1,38 @@ +from __future__ import absolute_import, division, unicode_literals + +import re + +from . import _base +from ..constants import rcdataElements, spaceCharacters +spaceCharacters = "".join(spaceCharacters) + +SPACES_REGEX = re.compile("[%s]+" % spaceCharacters) + + +class Filter(_base.Filter): + + spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements)) + + def __iter__(self): + preserve = 0 + for token in _base.Filter.__iter__(self): + type = token["type"] + if type == "StartTag" \ + and (preserve or token["name"] in self.spacePreserveElements): + preserve += 1 + + elif type == "EndTag" and preserve: + preserve -= 1 + + elif not preserve and type == "SpaceCharacters" and token["data"]: + # Test on token["data"] above to not introduce spaces where there were not + token["data"] = " " + + elif not preserve and type == "Characters": + token["data"] = collapse_spaces(token["data"]) + + yield token + + +def collapse_spaces(text): + return SPACES_REGEX.sub(' ', text) diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/html5parser.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/html5parser.py new file mode 100644 index 0000000..8a5acfe --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/pip/_vendor/html5lib/html5parser.py @@ -0,0 +1,2725 @@ +from __future__ import absolute_import, division, unicode_literals +from pip._vendor.six import with_metaclass + +import types + +from . import inputstream +from . import tokenizer + +from . import treebuilders +from .treebuilders._base import Marker + +from . import utils +from . import constants +from .constants import spaceCharacters, asciiUpper2Lower +from .constants import specialElements +from .constants import headingElements +from .constants import cdataElements, rcdataElements +from .constants import tokenTypes, ReparseException, namespaces +from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements + + +def parse(doc, treebuilder="etree", encoding=None, + namespaceHTMLElements=True): + """Parse a string or file-like object into a tree""" + tb = treebuilders.getTreeBuilder(treebuilder) + p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) + return p.parse(doc, encoding=encoding) + + +def parseFragment(doc, container="div", treebuilder="etree", encoding=None, + namespaceHTMLElements=True): + tb = treebuilders.getTreeBuilder(treebuilder) + p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements) + return p.parseFragment(doc, container=container, encoding=encoding) + + +def method_decorator_metaclass(function): + class Decorated(type): + def __new__(meta, classname, bases, classDict): + for attributeName, attribute in classDict.items(): + if isinstance(attribute, types.FunctionType): + attribute = function(attribute) + + classDict[attributeName] = attribute + return type.__new__(meta, classname, bases, classDict) + return Decorated + + +class HTMLParser(object): + """HTML parser. Generates a tree structure from a stream of (possibly + malformed) HTML""" + + def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer, + strict=False, namespaceHTMLElements=True, debug=False): + """ + strict - raise an exception when a parse error is encountered + + tree - a treebuilder class controlling the type of tree that will be + returned. Built in treebuilders can be accessed through + html5lib.treebuilders.getTreeBuilder(treeType) + + tokenizer - a class that provides a stream of tokens to the treebuilder. + This may be replaced for e.g. a sanitizer which converts some tags to + text + """ + + # Raise an exception on the first error encountered + self.strict = strict + + if tree is None: + tree = treebuilders.getTreeBuilder("etree") + self.tree = tree(namespaceHTMLElements) + self.tokenizer_class = tokenizer + self.errors = [] + + self.phases = dict([(name, cls(self, self.tree)) for name, cls in + getPhases(debug).items()]) + + def _parse(self, stream, innerHTML=False, container="div", + encoding=None, parseMeta=True, useChardet=True, **kwargs): + + self.innerHTMLMode = innerHTML + self.container = container + self.tokenizer = self.tokenizer_class(stream, encoding=encoding, + parseMeta=parseMeta, + useChardet=useChardet, + parser=self, **kwargs) + self.reset() + + while True: + try: + self.mainLoop() + break + except ReparseException: + self.reset() + + def reset(self): + self.tree.reset() + self.firstStartTag = False + self.errors = [] + self.log = [] # only used with debug mode + # "quirks" / "limited quirks" / "no quirks" + self.compatMode = "no quirks" + + if self.innerHTMLMode: + self.innerHTML = self.container.lower() + + if self.innerHTML in cdataElements: + self.tokenizer.state = self.tokenizer.rcdataState + elif self.innerHTML in rcdataElements: + self.tokenizer.state = self.tokenizer.rawtextState + elif self.innerHTML == 'plaintext': + self.tokenizer.state = self.tokenizer.plaintextState + else: + # state already is data state + # self.tokenizer.state = self.tokenizer.dataState + pass + self.phase = self.phases["beforeHtml"] + self.phase.insertHtmlElement() + self.resetInsertionMode() + else: + self.innerHTML = False + self.phase = self.phases["initial"] + + self.lastPhase = None + + self.beforeRCDataPhase = None + + self.framesetOK = True + + def isHTMLIntegrationPoint(self, element): + if (element.name == "annotation-xml" and + element.namespace == namespaces["mathml"]): + return ("encoding" in element.attributes and + element.attributes["encoding"].translate( + asciiUpper2Lower) in + ("text/html", "application/xhtml+xml")) + else: + return (element.namespace, element.name) in htmlIntegrationPointElements + + def isMathMLTextIntegrationPoint(self, element): + return (element.namespace, element.name) in mathmlTextIntegrationPointElements + + def mainLoop(self): + CharactersToken = tokenTypes["Characters"] + SpaceCharactersToken = tokenTypes["SpaceCharacters"] + StartTagToken = tokenTypes["StartTag"] + EndTagToken = tokenTypes["EndTag"] + CommentToken = tokenTypes["Comment"] + DoctypeToken = tokenTypes["Doctype"] + ParseErrorToken = tokenTypes["ParseError"] + + for token in self.normalizedTokens(): + new_token = token + while new_token is not None: + currentNode = self.tree.openElements[-1] if self.tree.openElements else None + currentNodeNamespace = currentNode.namespace if currentNode else None + currentNodeName = currentNode.name if currentNode else None + + type = new_token["type"] + + if type == ParseErrorToken: + self.parseError(new_token["data"], new_token.get("datavars", {})) + new_token = None + else: + if (len(self.tree.openElements) == 0 or + currentNodeNamespace == self.tree.defaultNamespace or + (self.isMathMLTextIntegrationPoint(currentNode) and + ((type == StartTagToken and + token["name"] not in frozenset(["mglyph", "malignmark"])) or + type in (CharactersToken, SpaceCharactersToken))) or + (currentNodeNamespace == namespaces["mathml"] and + currentNodeName == "annotation-xml" and + token["name"] == "svg") or + (self.isHTMLIntegrationPoint(currentNode) and + type in (StartTagToken, CharactersToken, SpaceCharactersToken))): + phase = self.phase + else: + phase = self.phases["inForeignContent"] + + if type == CharactersToken: + new_token = phase.processCharacters(new_token) + elif type == SpaceCharactersToken: + new_token = phase.processSpaceCharacters(new_token) + elif type == StartTagToken: + new_token = phase.processStartTag(new_token) + elif type == EndTagToken: + new_token = phase.processEndTag(new_token) + elif type == CommentToken: + new_token = phase.processComment(new_token) + elif type == DoctypeToken: + new_token = phase.processDoctype(new_token) + + if (type == StartTagToken and token["selfClosing"] + and not token["selfClosingAcknowledged"]): + self.parseError("non-void-element-with-trailing-solidus", + {"name": token["name"]}) + + # When the loop finishes it's EOF + reprocess = True + phases = [] + while reprocess: + phases.append(self.phase) + reprocess = self.phase.processEOF() + if reprocess: + assert self.phase not in phases + + def normalizedTokens(self): + for token in self.tokenizer: + yield self.normalizeToken(token) + + def parse(self, stream, encoding=None, parseMeta=True, useChardet=True): + """Parse a HTML document into a well-formed tree + + stream - a filelike object or string containing the HTML to be parsed + + The optional encoding parameter must be a string that indicates + the encoding. If specified, that encoding will be used, + regardless of any BOM or later declaration (such as in a meta + element) + """ + self._parse(stream, innerHTML=False, encoding=encoding, + parseMeta=parseMeta, useChardet=useChardet) + return self.tree.getDocument() + + def parseFragment(self, stream, container="div", encoding=None, + parseMeta=False, useChardet=True): + """Parse a HTML fragment into a well-formed tree fragment + + container - name of the element we're setting the innerHTML property + if set to None, default to 'div' + + stream - a filelike object or string containing the HTML to be parsed + + The optional encoding parameter must be a string that indicates + the encoding. If specified, that encoding will be used, + regardless of any BOM or later declaration (such as in a meta + element) + """ + self._parse(stream, True, container=container, encoding=encoding) + return self.tree.getFragment() + + def parseError(self, errorcode="XXX-undefined-error", datavars={}): + # XXX The idea is to make errorcode mandatory. + self.errors.append((self.tokenizer.stream.position(), errorcode, datavars)) + if self.strict: + raise ParseError + + def normalizeToken(self, token): + """ HTML5 specific normalizations to the token stream """ + + if token["type"] == tokenTypes["StartTag"]: + token["data"] = dict(token["data"][::-1]) + + return token + + def adjustMathMLAttributes(self, token): + replacements = {"definitionurl": "definitionURL"} + for k, v in replacements.items(): + if k in token["data"]: + token["data"][v] = token["data"][k] + del token["data"][k] + + def adjustSVGAttributes(self, token): + replacements = { + "attributename": "attributeName", + "attributetype": "attributeType", + "basefrequency": "baseFrequency", + "baseprofile": "baseProfile", + "calcmode": "calcMode", + "clippathunits": "clipPathUnits", + "contentscripttype": "contentScriptType", + "contentstyletype": "contentStyleType", + "diffuseconstant": "diffuseConstant", + "edgemode": "edgeMode", + "externalresourcesrequired": "externalResourcesRequired", + "filterres": "filterRes", + "filterunits": "filterUnits", + "glyphref": "glyphRef", + "gradienttransform": "gradientTransform", + "gradientunits": "gradientUnits", + "kernelmatrix": "kernelMatrix", + "kernelunitlength": "kernelUnitLength", + "keypoints": "keyPoints", + "keysplines": "keySplines", + "keytimes": "keyTimes", + "lengthadjust": "lengthAdjust", + "limitingconeangle": "limitingConeAngle", + "markerheight": "markerHeight", + "markerunits": "markerUnits", + "markerwidth": "markerWidth", + "maskcontentunits": "maskContentUnits", + "maskunits": "maskUnits", + "numoctaves": "numOctaves", + "pathlength": "pathLength", + "patterncontentunits": "patternContentUnits", + "patterntransform": "patternTransform", + "patternunits": "patternUnits", + "pointsatx": "pointsAtX", + "pointsaty": "pointsAtY", + "pointsatz": "pointsAtZ", + "preservealpha": "preserveAlpha", + "preserveaspectratio": "preserveAspectRatio", + "primitiveunits": "primitiveUnits", + "refx": "refX", + "refy": "refY", + "repeatcount": "repeatCount", + "repeatdur": "repeatDur", + "requiredextensions": "requiredExtensions", + "requiredfeatures": "requiredFeatures", + "specularconstant": "specularConstant", + "specularexponent": "specularExponent", + "spreadmethod": "spreadMethod", + "startoffset": "startOffset", + "stddeviation": "stdDeviation", + "stitchtiles": "stitchTiles", + "surfacescale": "surfaceScale", + "systemlanguage": "systemLanguage", + "tablevalues": "tableValues", + "targetx": "targetX", + "targety": "targetY", + "textlength": "textLength", + "viewbox": "viewBox", + "viewtarget": "viewTarget", + "xchannelselector": "xChannelSelector", + "ychannelselector": "yChannelSelector", + "zoomandpan": "zoomAndPan" + } + for originalName in list(token["data"].keys()): + if originalName in replacements: + svgName = replacements[originalName] + token["data"][svgName] = token["data"][originalName] + del token["data"][originalName] + + def adjustForeignAttributes(self, token): + replacements = { + "xlink:actuate": ("xlink", "actuate", namespaces["xlink"]), + "xlink:arcrole": ("xlink", "arcrole", namespaces["xlink"]), + "xlink:href": ("xlink", "href", namespaces["xlink"]), + "xlink:role": ("xlink", "role", namespaces["xlink"]), + "xlink:show": ("xlink", "show", namespaces["xlink"]), + "xlink:title": ("xlink", "title", namespaces["xlink"]), + "xlink:type": ("xlink", "type", namespaces["xlink"]), + "xml:base": ("xml", "base", namespaces["xml"]), + "xml:lang": ("xml", "lang", namespaces["xml"]), + "xml:space": ("xml", "space", namespaces["xml"]), + "xmlns": (None, "xmlns", namespaces["xmlns"]), + "xmlns:xlink": ("xmlns", "xlink", namespaces["xmlns"]) + } + + for originalName in token["data"].keys(): + if originalName in replacements: + foreignName = replacements[originalName] + token["data"][foreignName] = token["data"][originalName] + del token["data"][originalName] + + def reparseTokenNormal(self, token): + self.parser.phase() + + def resetInsertionMode(self): + # The name of this method is mostly historical. (It's also used in the + # specification.) + last = False + newModes = { + "select": "inSelect", + "td": "inCell", + "th": "inCell", + "tr": "inRow", + "tbody": "inTableBody", + "thead": "inTableBody", + "tfoot": "inTableBody", + "caption": "inCaption", + "colgroup": "inColumnGroup", + "table": "inTable", + "head": "inBody", + "body": "inBody", + "frameset": "inFrameset", + "html": "beforeHead" + } + for node in self.tree.openElements[::-1]: + nodeName = node.name + new_phase = None + if node == self.tree.openElements[0]: + assert self.innerHTML + last = True + nodeName = self.innerHTML + # Check for conditions that should only happen in the innerHTML + # case + if nodeName in ("select", "colgroup", "head", "html"): + assert self.innerHTML + + if not last and node.namespace != self.tree.defaultNamespace: + continue + + if nodeName in newModes: + new_phase = self.phases[newModes[nodeName]] + break + elif last: + new_phase = self.phases["inBody"] + break + + self.phase = new_phase + + def parseRCDataRawtext(self, token, contentType): + """Generic RCDATA/RAWTEXT Parsing algorithm + contentType - RCDATA or RAWTEXT + """ + assert contentType in ("RAWTEXT", "RCDATA") + + self.tree.insertElement(token) + + if contentType == "RAWTEXT": + self.tokenizer.state = self.tokenizer.rawtextState + else: + self.tokenizer.state = self.tokenizer.rcdataState + + self.originalPhase = self.phase + + self.phase = self.phases["text"] + + +def getPhases(debug): + def log(function): + """Logger that records which phase processes each token""" + type_names = dict((value, key) for key, value in + constants.tokenTypes.items()) + + def wrapped(self, *args, **kwargs): + if function.__name__.startswith("process") and len(args) > 0: + token = args[0] + try: + info = {"type": type_names[token['type']]} + except: + raise + if token['type'] in constants.tagTokenTypes: + info["name"] = token['name'] + + self.parser.log.append((self.parser.tokenizer.state.__name__, + self.parser.phase.__class__.__name__, + self.__class__.__name__, + function.__name__, + info)) + return function(self, *args, **kwargs) + else: + return function(self, *args, **kwargs) + return wrapped + + def getMetaclass(use_metaclass, metaclass_func): + if use_metaclass: + return method_decorator_metaclass(metaclass_func) + else: + return type + + class Phase(with_metaclass(getMetaclass(debug, log))): + """Base class for helper object that implements each phase of processing + """ + + def __init__(self, parser, tree): + self.parser = parser + self.tree = tree + + def processEOF(self): + raise NotImplementedError + + def processComment(self, token): + # For most phases the following is correct. Where it's not it will be + # overridden. + self.tree.insertComment(token, self.tree.openElements[-1]) + + def processDoctype(self, token): + self.parser.parseError("unexpected-doctype") + + def processCharacters(self, token): + self.tree.insertText(token["data"]) + + def processSpaceCharacters(self, token): + self.tree.insertText(token["data"]) + + def processStartTag(self, token): + return self.startTagHandler[token["name"]](token) + + def startTagHtml(self, token): + if not self.parser.firstStartTag and token["name"] == "html": + self.parser.parseError("non-html-root") + # XXX Need a check here to see if the first start tag token emitted is + # this token... If it's not, invoke self.parser.parseError(). + for attr, value in token["data"].items(): + if attr not in self.tree.openElements[0].attributes: + self.tree.openElements[0].attributes[attr] = value + self.parser.firstStartTag = False + + def processEndTag(self, token): + return self.endTagHandler[token["name"]](token) + + class InitialPhase(Phase): + def processSpaceCharacters(self, token): + pass + + def processComment(self, token): + self.tree.insertComment(token, self.tree.document) + + def processDoctype(self, token): + name = token["name"] + publicId = token["publicId"] + systemId = token["systemId"] + correct = token["correct"] + + if (name != "html" or publicId is not None or + systemId is not None and systemId != "about:legacy-compat"): + self.parser.parseError("unknown-doctype") + + if publicId is None: + publicId = "" + + self.tree.insertDoctype(token) + + if publicId != "": + publicId = publicId.translate(asciiUpper2Lower) + + if (not correct or token["name"] != "html" + or publicId.startswith( + ("+//silmaril//dtd html pro v0r11 19970101//", + "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", + "-//as//dtd html 3.0 aswedit + extensions//", + "-//ietf//dtd html 2.0 level 1//", + "-//ietf//dtd html 2.0 level 2//", + "-//ietf//dtd html 2.0 strict level 1//", + "-//ietf//dtd html 2.0 strict level 2//", + "-//ietf//dtd html 2.0 strict//", + "-//ietf//dtd html 2.0//", + "-//ietf//dtd html 2.1e//", + "-//ietf//dtd html 3.0//", + "-//ietf//dtd html 3.2 final//", + "-//ietf//dtd html 3.2//", + "-//ietf//dtd html 3//", + "-//ietf//dtd html level 0//", + "-//ietf//dtd html level 1//", + "-//ietf//dtd html level 2//", + "-//ietf//dtd html level 3//", + "-//ietf//dtd html strict level 0//", + "-//ietf//dtd html strict level 1//", + "-//ietf//dtd html strict level 2//", + "-//ietf//dtd html strict level 3//", + "-//ietf//dtd html strict//", + "-//ietf//dtd html//", + "-//metrius//dtd metrius presentational//", + "-//microsoft//dtd internet explorer 2.0 html strict//", + "-//microsoft//dtd internet explorer 2.0 html//", + "-//microsoft//dtd internet explorer 2.0 tables//", + "-//microsoft//dtd internet explorer 3.0 html strict//", + "-//microsoft//dtd internet explorer 3.0 html//", + "-//microsoft//dtd internet explorer 3.0 tables//", + "-//netscape comm. corp.//dtd html//", + "-//netscape comm. corp.//dtd strict html//", + "-//o'reilly and associates//dtd html 2.0//", + "-//o'reilly and associates//dtd html extended 1.0//", + "-//o'reilly and associates//dtd html extended relaxed 1.0//", + "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", + "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", + "-//spyglass//dtd html 2.0 extended//", + "-//sq//dtd html 2.0 hotmetal + extensions//", + "-//sun microsystems corp.//dtd hotjava html//", + "-//sun microsystems corp.//dtd hotjava strict html//", + "-//w3c//dtd html 3 1995-03-24//", + "-//w3c//dtd html 3.2 draft//", + "-//w3c//dtd html 3.2 final//", + "-//w3c//dtd html 3.2//", + "-//w3c//dtd html 3.2s draft//", + "-//w3c//dtd html 4.0 frameset//", + "-//w3c//dtd html 4.0 transitional//", + "-//w3c//dtd html experimental 19960712//", + "-//w3c//dtd html experimental 970421//", + "-//w3c//dtd w3 html//", + "-//w3o//dtd w3 html 3.0//", + "-//webtechs//dtd mozilla html 2.0//", + "-//webtechs//dtd mozilla html//")) + or publicId in + ("-//w3o//dtd w3 html strict 3.0//en//", + "-/w3c/dtd html 4.0 transitional/en", + "html") + or publicId.startswith( + ("-//w3c//dtd html 4.01 frameset//", + "-//w3c//dtd html 4.01 transitional//")) and + systemId is None + or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"): + self.parser.compatMode = "quirks" + elif (publicId.startswith( + ("-//w3c//dtd xhtml 1.0 frameset//", + "-//w3c//dtd xhtml 1.0 transitional//")) + or publicId.startswith( + ("-//w3c//dtd html 4.01 frameset//", + "-//w3c//dtd html 4.01 transitional//")) and + systemId is not None): + self.parser.compatMode = "limited quirks" + + self.parser.phase = self.parser.phases["beforeHtml"] + + def anythingElse(self): + self.parser.compatMode = "quirks" + self.parser.phase = self.parser.phases["beforeHtml"] + + def processCharacters(self, token): + self.parser.parseError("expected-doctype-but-got-chars") + self.anythingElse() + return token + + def processStartTag(self, token): + self.parser.parseError("expected-doctype-but-got-start-tag", + {"name": token["name"]}) + self.anythingElse() + return token + + def processEndTag(self, token): + self.parser.parseError("expected-doctype-but-got-end-tag", + {"name": token["name"]}) + self.anythingElse() + return token + + def processEOF(self): + self.parser.parseError("expected-doctype-but-got-eof") + self.anythingElse() + return True + + class BeforeHtmlPhase(Phase): + # helper methods + def insertHtmlElement(self): + self.tree.insertRoot(impliedTagToken("html", "StartTag")) + self.parser.phase = self.parser.phases["beforeHead"] + + # other + def processEOF(self): + self.insertHtmlElement() + return True + + def processComment(self, token): + self.tree.insertComment(token, self.tree.document) + + def processSpaceCharacters(self, token): + pass + + def processCharacters(self, token): + self.insertHtmlElement() + return token + + def processStartTag(self, token): + if token["name"] == "html": + self.parser.firstStartTag = True + self.insertHtmlElement() + return token + + def processEndTag(self, token): + if token["name"] not in ("head", "body", "html", "br"): + self.parser.parseError("unexpected-end-tag-before-html", + {"name": token["name"]}) + else: + self.insertHtmlElement() + return token + + class BeforeHeadPhase(Phase): + def __init__(self, parser, tree): + Phase.__init__(self, parser, tree) + + self.startTagHandler = utils.MethodDispatcher([ + ("html", self.startTagHtml), + ("head", self.startTagHead) + ]) + self.startTagHandler.default = self.startTagOther + + self.endTagHandler = utils.MethodDispatcher([ + (("head", "body", "html", "br"), self.endTagImplyHead) + ]) + self.endTagHandler.default = self.endTagOther + + def processEOF(self): + self.startTagHead(impliedTagToken("head", "StartTag")) + return True + + def processSpaceCharacters(self, token): + pass + + def processCharacters(self, token): + self.startTagHead(impliedTagToken("head", "StartTag")) + return token + + def startTagHtml(self, token): + return self.parser.phases["inBody"].processStartTag(token) + + def startTagHead(self, token): + self.tree.insertElement(token) + self.tree.headPointer = self.tree.openElements[-1] + self.parser.phase = self.parser.phases["inHead"] + + def startTagOther(self, token): + self.startTagHead(impliedTagToken("head", "StartTag")) + return token + + def endTagImplyHead(self, token): + self.startTagHead(impliedTagToken("head", "StartTag")) + return token + + def endTagOther(self, token): + self.parser.parseError("end-tag-after-implied-root", + {"name": token["name"]}) + + class InHeadPhase(Phase): + def __init__(self, parser, tree): + Phase.__init__(self, parser, tree) + + self.startTagHandler = utils.MethodDispatcher([ + ("html", self.startTagHtml), + ("title", self.startTagTitle), + (("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle), + ("script", self.startTagScript), + (("base", "basefont", "bgsound", "command", "link"), + self.startTagBaseLinkCommand), + ("meta", self.startTagMeta), + ("head", self.startTagHead) + ]) + self.startTagHandler.default = self.startTagOther + + self. endTagHandler = utils.MethodDispatcher([ + ("head", self.endTagHead), + (("br", "html", "body"), self.endTagHtmlBodyBr) + ]) + self.endTagHandler.default = self.endTagOther + + # the real thing + def processEOF(self): + self.anythingElse() + return True + + def processCharacters(self, token): + self.anythingElse() + return token + + def startTagHtml(self, token): + return self.parser.phases["inBody"].processStartTag(token) + + def startTagHead(self, token): + self.parser.parseError("two-heads-are-not-better-than-one") + + def startTagBaseLinkCommand(self, token): + self.tree.insertElement(token) + self.tree.openElements.pop() + token["selfClosingAcknowledged"] = True + + def startTagMeta(self, token): + self.tree.insertElement(token) + self.tree.openElements.pop() + token["selfClosingAcknowledged"] = True + + attributes = token["data"] + if self.parser.tokenizer.stream.charEncoding[1] == "tentative": + if "charset" in attributes: + self.parser.tokenizer.stream.changeEncoding(attributes["charset"]) + elif ("content" in attributes and + "http-equiv" in attributes and + attributes["http-equiv"].lower() == "content-type"): + # Encoding it as UTF-8 here is a hack, as really we should pass + # the abstract Unicode string, and just use the + # ContentAttrParser on that, but using UTF-8 allows all chars + # to be encoded and as a ASCII-superset works. + data = inputstream.EncodingBytes(attributes["content"].encode("utf-8")) + parser = inputstream.ContentAttrParser(data) + codec = parser.parse() + self.parser.tokenizer.stream.changeEncoding(codec) + + def startTagTitle(self, token): + self.parser.parseRCDataRawtext(token, "RCDATA") + + def startTagNoScriptNoFramesStyle(self, token): + # Need to decide whether to implement the scripting-disabled case + self.parser.parseRCDataRawtext(token, "RAWTEXT") + + def startTagScript(self, token): + self.tree.insertElement(token) + self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState + self.parser.originalPhase = self.parser.phase + self.parser.phase = self.parser.phases["text"] + + def startTagOther(self, token): + self.anythingElse() + return token + + def endTagHead(self, token): + node = self.parser.tree.openElements.pop() + assert node.name == "head", "Expected head got %s" % node.name + self.parser.phase = self.parser.phases["afterHead"] + + def endTagHtmlBodyBr(self, token): + self.anythingElse() + return token + + def endTagOther(self, token): + self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) + + def anythingElse(self): + self.endTagHead(impliedTagToken("head")) + + # XXX If we implement a parser for which scripting is disabled we need to + # implement this phase. + # + # class InHeadNoScriptPhase(Phase): + class AfterHeadPhase(Phase): + def __init__(self, parser, tree): + Phase.__init__(self, parser, tree) + + self.startTagHandler = utils.MethodDispatcher([ + ("html", self.startTagHtml), + ("body", self.startTagBody), + ("frameset", self.startTagFrameset), + (("base", "basefont", "bgsound", "link", "meta", "noframes", "script", + "style", "title"), + self.startTagFromHead), + ("head", self.startTagHead) + ]) + self.startTagHandler.default = self.startTagOther + self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"), + self.endTagHtmlBodyBr)]) + self.endTagHandler.default = self.endTagOther + + def processEOF(self): + self.anythingElse() + return True + + def processCharacters(self, token): + self.anythingElse() + return token + + def startTagHtml(self, token): + return self.parser.phases["inBody"].processStartTag(token) + + def startTagBody(self, token): + self.parser.framesetOK = False + self.tree.insertElement(token) + self.parser.phase = self.parser.phases["inBody"] + + def startTagFrameset(self, token): + self.tree.insertElement(token) + self.parser.phase = self.parser.phases["inFrameset"] + + def startTagFromHead(self, token): + self.parser.parseError("unexpected-start-tag-out-of-my-head", + {"name": token["name"]}) + self.tree.openElements.append(self.tree.headPointer) + self.parser.phases["inHead"].processStartTag(token) + for node in self.tree.openElements[::-1]: + if node.name == "head": + self.tree.openElements.remove(node) + break + + def startTagHead(self, token): + self.parser.parseError("unexpected-start-tag", {"name": token["name"]}) + + def startTagOther(self, token): + self.anythingElse() + return token + + def endTagHtmlBodyBr(self, token): + self.anythingElse() + return token + + def endTagOther(self, token): + self.parser.parseError("unexpected-end-tag", {"name": token["name"]}) + + def anythingElse(self): + self.tree.insertElement(impliedTagToken("body", "StartTag")) + self.parser.phase = self.parser.phases["inBody"] + self.parser.framesetOK = True + + class InBodyPhase(Phase): + # http://www.whatwg.org/specs/web-apps/current-work/#parsing-main-inbody + # the really-really-really-very crazy mode + def __init__(self, parser, tree): + Phase.__init__(self, parser, tree) + + # Keep a ref to this for special handling of whitespace in 
+            self.processSpaceCharactersNonPre = self.processSpaceCharacters
+
+            self.startTagHandler = utils.MethodDispatcher([
+                ("html", self.startTagHtml),
+                (("base", "basefont", "bgsound", "command", "link", "meta",
+                  "noframes", "script", "style", "title"),
+                 self.startTagProcessInHead),
+                ("body", self.startTagBody),
+                ("frameset", self.startTagFrameset),
+                (("address", "article", "aside", "blockquote", "center", "details",
+                  "details", "dir", "div", "dl", "fieldset", "figcaption", "figure",
+                  "footer", "header", "hgroup", "main", "menu", "nav", "ol", "p",
+                  "section", "summary", "ul"),
+                 self.startTagCloseP),
+                (headingElements, self.startTagHeading),
+                (("pre", "listing"), self.startTagPreListing),
+                ("form", self.startTagForm),
+                (("li", "dd", "dt"), self.startTagListItem),
+                ("plaintext", self.startTagPlaintext),
+                ("a", self.startTagA),
+                (("b", "big", "code", "em", "font", "i", "s", "small", "strike",
+                  "strong", "tt", "u"), self.startTagFormatting),
+                ("nobr", self.startTagNobr),
+                ("button", self.startTagButton),
+                (("applet", "marquee", "object"), self.startTagAppletMarqueeObject),
+                ("xmp", self.startTagXmp),
+                ("table", self.startTagTable),
+                (("area", "br", "embed", "img", "keygen", "wbr"),
+                 self.startTagVoidFormatting),
+                (("param", "source", "track"), self.startTagParamSource),
+                ("input", self.startTagInput),
+                ("hr", self.startTagHr),
+                ("image", self.startTagImage),
+                ("isindex", self.startTagIsIndex),
+                ("textarea", self.startTagTextarea),
+                ("iframe", self.startTagIFrame),
+                (("noembed", "noframes", "noscript"), self.startTagRawtext),
+                ("select", self.startTagSelect),
+                (("rp", "rt"), self.startTagRpRt),
+                (("option", "optgroup"), self.startTagOpt),
+                (("math"), self.startTagMath),
+                (("svg"), self.startTagSvg),
+                (("caption", "col", "colgroup", "frame", "head",
+                  "tbody", "td", "tfoot", "th", "thead",
+                  "tr"), self.startTagMisplaced)
+            ])
+            self.startTagHandler.default = self.startTagOther
+
+            self.endTagHandler = utils.MethodDispatcher([
+                ("body", self.endTagBody),
+                ("html", self.endTagHtml),
+                (("address", "article", "aside", "blockquote", "button", "center",
+                  "details", "dialog", "dir", "div", "dl", "fieldset", "figcaption", "figure",
+                  "footer", "header", "hgroup", "listing", "main", "menu", "nav", "ol", "pre",
+                  "section", "summary", "ul"), self.endTagBlock),
+                ("form", self.endTagForm),
+                ("p", self.endTagP),
+                (("dd", "dt", "li"), self.endTagListItem),
+                (headingElements, self.endTagHeading),
+                (("a", "b", "big", "code", "em", "font", "i", "nobr", "s", "small",
+                  "strike", "strong", "tt", "u"), self.endTagFormatting),
+                (("applet", "marquee", "object"), self.endTagAppletMarqueeObject),
+                ("br", self.endTagBr),
+            ])
+            self.endTagHandler.default = self.endTagOther
+
+        def isMatchingFormattingElement(self, node1, node2):
+            if node1.name != node2.name or node1.namespace != node2.namespace:
+                return False
+            elif len(node1.attributes) != len(node2.attributes):
+                return False
+            else:
+                attributes1 = sorted(node1.attributes.items())
+                attributes2 = sorted(node2.attributes.items())
+                for attr1, attr2 in zip(attributes1, attributes2):
+                    if attr1 != attr2:
+                        return False
+            return True
+
+        # helper
+        def addFormattingElement(self, token):
+            self.tree.insertElement(token)
+            element = self.tree.openElements[-1]
+
+            matchingElements = []
+            for node in self.tree.activeFormattingElements[::-1]:
+                if node is Marker:
+                    break
+                elif self.isMatchingFormattingElement(node, element):
+                    matchingElements.append(node)
+
+            assert len(matchingElements) <= 3
+            if len(matchingElements) == 3:
+                self.tree.activeFormattingElements.remove(matchingElements[-1])
+            self.tree.activeFormattingElements.append(element)
+
+        # the real deal
+        def processEOF(self):
+            allowed_elements = frozenset(("dd", "dt", "li", "p", "tbody", "td",
+                                          "tfoot", "th", "thead", "tr", "body",
+                                          "html"))
+            for node in self.tree.openElements[::-1]:
+                if node.name not in allowed_elements:
+                    self.parser.parseError("expected-closing-tag-but-got-eof")
+                    break
+            # Stop parsing
+
+        def processSpaceCharactersDropNewline(self, token):
+            # Sometimes (start of 
, , and