diff -Nru beautifulsoup4-4.9.3/beautifulsoup4.egg-info/PKG-INFO beautifulsoup4-4.10.0/beautifulsoup4.egg-info/PKG-INFO
--- beautifulsoup4-4.9.3/beautifulsoup4.egg-info/PKG-INFO 2020-10-03 15:34:15.000000000 +0000
+++ beautifulsoup4-4.10.0/beautifulsoup4.egg-info/PKG-INFO 2021-09-08 00:13:24.000000000 +0000
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: beautifulsoup4
-Version: 4.9.3
+Version: 4.10.0
Summary: Screen-scraping library
Home-page: http://www.crummy.com/software/BeautifulSoup/bs4/
Author: Leonard Richardson
@@ -62,17 +62,11 @@
# Note on Python 2 sunsetting
- Since 2012, Beautiful Soup has been developed as a Python 2 library
- which is automatically converted to Python 3 code as necessary. This
- makes it impossible to take advantage of some features of Python
- 3.
-
- For this reason, I plan to discontinue Beautiful Soup's Python 2
- support at some point after December 31, 2020: one year after the
- sunset date for Python 2 itself. Beyond that point, new Beautiful Soup
- development will exclusively target Python 3. Of course, older
- releases of Beautiful Soup, which support both versions, will continue
- to be available.
+ Beautiful Soup's support for Python 2 was discontinued on December 31,
+ 2020: one year after the sunset date for Python 2 itself. From this
+ point onward, new Beautiful Soup development will exclusively target
+ Python 3. The final release of Beautiful Soup 4 to support Python 2
+ was 4.9.3.
# Supporting the project
@@ -102,25 +96,20 @@
```
```
- $ python -m unittest discover -s bs4
+ $ python3 -m unittest discover -s bs4
```
- If you checked out the source tree, you should see a script in the
- home directory called test-all-versions. This script will run the unit
- tests under Python 2, then create a temporary Python 3 conversion of
- the source and run the unit tests again under Python 3.
-
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Markup :: HTML
Classifier: Topic :: Text Processing :: Markup :: XML
Classifier: Topic :: Text Processing :: Markup :: SGML
Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >3.0.0
Description-Content-Type: text/markdown
Provides-Extra: html5lib
Provides-Extra: lxml
diff -Nru beautifulsoup4-4.9.3/beautifulsoup4.egg-info/requires.txt beautifulsoup4-4.10.0/beautifulsoup4.egg-info/requires.txt
--- beautifulsoup4-4.9.3/beautifulsoup4.egg-info/requires.txt 2020-10-03 15:34:15.000000000 +0000
+++ beautifulsoup4-4.10.0/beautifulsoup4.egg-info/requires.txt 2021-09-08 00:13:24.000000000 +0000
@@ -1,8 +1,3 @@
-
-[:python_version < "3.0"]
-soupsieve<2.0,>1.2
-
-[:python_version >= "3.0"]
soupsieve>1.2
[html5lib]
diff -Nru beautifulsoup4-4.9.3/beautifulsoup4.egg-info/SOURCES.txt beautifulsoup4-4.10.0/beautifulsoup4.egg-info/SOURCES.txt
--- beautifulsoup4-4.9.3/beautifulsoup4.egg-info/SOURCES.txt 2020-10-03 15:34:15.000000000 +0000
+++ beautifulsoup4-4.10.0/beautifulsoup4.egg-info/SOURCES.txt 2021-09-08 00:13:24.000000000 +0000
@@ -4,7 +4,7 @@
NEWS.txt
README.md
TODO.txt
-convert-py3k
+parse.txt
setup.cfg
setup.py
test-all-versions
diff -Nru beautifulsoup4-4.9.3/bs4/builder/_html5lib.py beautifulsoup4-4.10.0/bs4/builder/_html5lib.py
--- beautifulsoup4-4.9.3/bs4/builder/_html5lib.py 2020-09-26 14:36:10.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/builder/_html5lib.py 2021-09-07 23:36:46.000000000 +0000
@@ -33,7 +33,7 @@
# Pre-0.99999999
from html5lib.treebuilders import _base as treebuilder_base
new_html5lib = False
-except ImportError, e:
+except ImportError as e:
# 0.99999999 and up
from html5lib.treebuilders import base as treebuilder_base
new_html5lib = True
@@ -79,7 +79,7 @@
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
self.underlying_builder.parser = parser
extra_kwargs = dict()
- if not isinstance(markup, unicode):
+ if not isinstance(markup, str):
if new_html5lib:
extra_kwargs['override_encoding'] = self.user_specified_encoding
else:
@@ -87,13 +87,13 @@
doc = parser.parse(markup, **extra_kwargs)
# Set the character encoding detected by the tokenizer.
- if isinstance(markup, unicode):
+ if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
original_encoding = parser.tokenizer.stream.charEncoding[0]
- if not isinstance(original_encoding, basestring):
+ if not isinstance(original_encoding, str):
# In 0.99999999 and up, the encoding is an html5lib
# Encoding object. We want to use a string for compatibility
# with other tree builders.
@@ -110,7 +110,7 @@
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
- return u'%s' % fragment
+ return '%s' % fragment
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
@@ -217,7 +217,7 @@
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
- for name, value in element.attrs.items():
+ for name, value in list(element.attrs.items()):
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace], name.name)
if isinstance(value, list):
@@ -272,7 +272,7 @@
def appendChild(self, node):
string_child = child = None
- if isinstance(node, basestring):
+ if isinstance(node, str):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
@@ -289,7 +289,7 @@
child = node.element
node.parent = self
- if not isinstance(child, basestring) and child.parent is not None:
+ if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child is not None and self.element.contents
@@ -302,7 +302,7 @@
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
- if isinstance(node, basestring):
+ if isinstance(node, str):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
@@ -340,7 +340,7 @@
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
- for name, value in attributes.items():
+ for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
diff -Nru beautifulsoup4-4.9.3/bs4/builder/_htmlparser.py beautifulsoup4-4.10.0/bs4/builder/_htmlparser.py
--- beautifulsoup4-4.9.3/bs4/builder/_htmlparser.py 2020-09-26 14:36:05.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/builder/_htmlparser.py 2021-09-07 23:36:46.000000000 +0000
@@ -8,11 +8,11 @@
'HTMLParserTreeBuilder',
]
-from HTMLParser import HTMLParser
+from html.parser import HTMLParser
try:
- from HTMLParser import HTMLParseError
-except ImportError, e:
+ from html.parser import HTMLParseError
+except ImportError as e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
@@ -219,19 +219,19 @@
continue
try:
data = bytearray([real_name]).decode(encoding)
- except UnicodeDecodeError, e:
+ except UnicodeDecodeError as e:
pass
if not data:
try:
- data = unichr(real_name)
- except (ValueError, OverflowError), e:
+ data = chr(real_name)
+ except (ValueError, OverflowError) as e:
pass
- data = data or u"\N{REPLACEMENT CHARACTER}"
+ data = data or "\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
"""Handle a named entity reference by converting it to the
- corresponding Unicode character and treating it as textual
+ corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
@@ -353,15 +353,30 @@
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
- if isinstance(markup, unicode):
+ if isinstance(markup, str):
# Parse Unicode as-is.
yield (markup, None, None, False)
return
# Ask UnicodeDammit to sniff the most likely encoding.
+
+ # This was provided by the end-user; treat it as a known
+ # definite encoding per the algorithm laid out in the HTML5
+ # spec. (See the EncodingDetector class for details.)
+ known_definite_encodings = [user_specified_encoding]
+
+ # This was found in the document; treat it as a slightly lower-priority
+ # user encoding.
+ user_encodings = [document_declared_encoding]
+
try_encodings = [user_specified_encoding, document_declared_encoding]
- dammit = UnicodeDammit(markup, try_encodings, is_html=True,
- exclude_encodings=exclude_encodings)
+ dammit = UnicodeDammit(
+ markup,
+ known_definite_encodings=known_definite_encodings,
+ user_encodings=user_encodings,
+ is_html=True,
+ exclude_encodings=exclude_encodings
+ )
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
@@ -376,7 +391,7 @@
try:
parser.feed(markup)
parser.close()
- except HTMLParseError, e:
+ except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
diff -Nru beautifulsoup4-4.9.3/bs4/builder/__init__.py beautifulsoup4-4.10.0/bs4/builder/__init__.py
--- beautifulsoup4-4.9.3/bs4/builder/__init__.py 2020-05-30 18:17:21.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/builder/__init__.py 2021-09-07 23:36:46.000000000 +0000
@@ -234,7 +234,8 @@
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
- in this encoding.
+ in this encoding. NOTE: This argument is not used by the
+ calling code and can probably be removed.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
@@ -300,13 +301,13 @@
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
- for attr in attrs.keys():
+ for attr in list(attrs.keys()):
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
- if isinstance(value, basestring):
+ if isinstance(value, str):
values = nonwhitespace_re.findall(value)
else:
# html5lib sometimes calls setAttributes twice
@@ -496,7 +497,7 @@
"""
if isinstance(message_or_exception, Exception):
e = message_or_exception
- message_or_exception = "%s: %s" % (e.__class__.__name__, unicode(e))
+ message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
super(ParserRejectedMarkup, self).__init__(message_or_exception)
# Builders are registered in reverse order of priority, so that custom
diff -Nru beautifulsoup4-4.9.3/bs4/builder/_lxml.py beautifulsoup4-4.10.0/bs4/builder/_lxml.py
--- beautifulsoup4-4.9.3/bs4/builder/_lxml.py 2020-09-07 11:13:41.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/builder/_lxml.py 2021-09-07 23:36:46.000000000 +0000
@@ -8,11 +8,11 @@
try:
from collections.abc import Callable # Python 3.6
-except ImportError , e:
+except ImportError as e:
from collections import Callable
from io import BytesIO
-from StringIO import StringIO
+from io import StringIO
from lxml import etree
from bs4.element import (
Comment,
@@ -35,7 +35,7 @@
def _invert(d):
"Invert a dictionary."
- return dict((v,k) for k, v in d.items())
+ return dict((v,k) for k, v in list(d.items()))
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
@@ -81,7 +81,7 @@
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
- for key, value in mapping.items():
+ for key, value in list(mapping.items()):
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
@@ -169,27 +169,37 @@
else:
self.processing_instruction_class = XMLProcessingInstruction
- if isinstance(markup, unicode):
+ if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
yield markup, None, document_declared_encoding, False
- if isinstance(markup, unicode):
+ if isinstance(markup, str):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
- try_encodings = [user_specified_encoding, document_declared_encoding]
+ # This was provided by the end-user; treat it as a known
+ # definite encoding per the algorithm laid out in the HTML5
+ # spec. (See the EncodingDetector class for details.)
+ known_definite_encodings = [user_specified_encoding]
+
+ # This was found in the document; treat it as a slightly lower-priority
+ # user encoding.
+ user_encodings = [document_declared_encoding]
detector = EncodingDetector(
- markup, try_encodings, is_html, exclude_encodings)
+ markup, known_definite_encodings=known_definite_encodings,
+ user_encodings=user_encodings, is_html=is_html,
+ exclude_encodings=exclude_encodings
+ )
for encoding in detector.encodings:
yield (detector.markup, encoding, document_declared_encoding, False)
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
- elif isinstance(markup, unicode):
+ elif isinstance(markup, str):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
@@ -204,7 +214,7 @@
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
- except (UnicodeDecodeError, LookupError, etree.ParserError), e:
+ except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def close(self):
@@ -233,7 +243,7 @@
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
- for prefix, namespace in nsmap.items():
+ for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
@@ -242,7 +252,7 @@
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
- for attr, value in attrs.items():
+ for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
@@ -302,7 +312,7 @@
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
- return u'\n%s' % fragment
+ return '\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
@@ -323,10 +333,10 @@
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
- except (UnicodeDecodeError, LookupError, etree.ParserError), e:
+ except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
- return u'%s' % fragment
+ return '%s' % fragment
diff -Nru beautifulsoup4-4.9.3/bs4/dammit.py beautifulsoup4-4.10.0/bs4/dammit.py
--- beautifulsoup4-4.9.3/bs4/dammit.py 2020-05-17 17:56:04.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/dammit.py 2021-09-07 23:36:46.000000000 +0000
@@ -9,8 +9,9 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
+from html.entities import codepoint2name
+from collections import defaultdict
import codecs
-from htmlentitydefs import codepoint2name
import re
import logging
import string
@@ -22,7 +23,7 @@
# PyPI package: cchardet
import cchardet
def chardet_dammit(s):
- if isinstance(s, unicode):
+ if isinstance(s, str):
return None
return cchardet.detect(s)['encoding']
except ImportError:
@@ -32,7 +33,7 @@
# PyPI package: chardet
import chardet
def chardet_dammit(s):
- if isinstance(s, unicode):
+ if isinstance(s, str):
return None
return chardet.detect(s)['encoding']
#import chardet.constants
@@ -53,46 +54,2380 @@
# Build bytestring and Unicode versions of regular expressions for finding
# a declared encoding inside an XML or HTML document.
-xml_encoding = u'^\\s*<\\?.*encoding=[\'"](.*?)[\'"].*\\?>'
-html_meta = u'<\\s*meta[^>]+charset\\s*=\\s*["\']?([^>]*?)[ /;\'">]'
+xml_encoding = '^\\s*<\\?.*encoding=[\'"](.*?)[\'"].*\\?>'
+html_meta = '<\\s*meta[^>]+charset\\s*=\\s*["\']?([^>]*?)[ /;\'">]'
encoding_res = dict()
encoding_res[bytes] = {
'html' : re.compile(html_meta.encode("ascii"), re.I),
'xml' : re.compile(xml_encoding.encode("ascii"), re.I),
}
-encoding_res[unicode] = {
+encoding_res[str] = {
'html' : re.compile(html_meta, re.I),
'xml' : re.compile(xml_encoding, re.I)
}
+try:
+ from html.entities import html5
+except ImportError:
+ # This is a copy of html.entities.html5 from Python 3.9. There's
+ # no equivalent table in Python 2, so we'll just provide a copy
+ # here.
+ html5 = {
+ 'Aacute': '\xc1',
+ 'aacute': '\xe1',
+ 'Aacute;': '\xc1',
+ 'aacute;': '\xe1',
+ 'Abreve;': '\u0102',
+ 'abreve;': '\u0103',
+ 'ac;': '\u223e',
+ 'acd;': '\u223f',
+ 'acE;': '\u223e\u0333',
+ 'Acirc': '\xc2',
+ 'acirc': '\xe2',
+ 'Acirc;': '\xc2',
+ 'acirc;': '\xe2',
+ 'acute': '\xb4',
+ 'acute;': '\xb4',
+ 'Acy;': '\u0410',
+ 'acy;': '\u0430',
+ 'AElig': '\xc6',
+ 'aelig': '\xe6',
+ 'AElig;': '\xc6',
+ 'aelig;': '\xe6',
+ 'af;': '\u2061',
+ 'Afr;': '\U0001d504',
+ 'afr;': '\U0001d51e',
+ 'Agrave': '\xc0',
+ 'agrave': '\xe0',
+ 'Agrave;': '\xc0',
+ 'agrave;': '\xe0',
+ 'alefsym;': '\u2135',
+ 'aleph;': '\u2135',
+ 'Alpha;': '\u0391',
+ 'alpha;': '\u03b1',
+ 'Amacr;': '\u0100',
+ 'amacr;': '\u0101',
+ 'amalg;': '\u2a3f',
+ 'AMP': '&',
+ 'amp': '&',
+ 'AMP;': '&',
+ 'amp;': '&',
+ 'And;': '\u2a53',
+ '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;': '\u0104',
+ 'aogon;': '\u0105',
+ 'Aopf;': '\U0001d538',
+ 'aopf;': '\U0001d552',
+ 'ap;': '\u2248',
+ 'apacir;': '\u2a6f',
+ 'apE;': '\u2a70',
+ 'ape;': '\u224a',
+ 'apid;': '\u224b',
+ 'apos;': "'",
+ 'ApplyFunction;': '\u2061',
+ 'approx;': '\u2248',
+ 'approxeq;': '\u224a',
+ 'Aring': '\xc5',
+ 'aring': '\xe5',
+ 'Aring;': '\xc5',
+ 'aring;': '\xe5',
+ 'Ascr;': '\U0001d49c',
+ 'ascr;': '\U0001d4b6',
+ 'Assign;': '\u2254',
+ 'ast;': '*',
+ 'asymp;': '\u2248',
+ 'asympeq;': '\u224d',
+ 'Atilde': '\xc3',
+ 'atilde': '\xe3',
+ 'Atilde;': '\xc3',
+ 'atilde;': '\xe3',
+ 'Auml': '\xc4',
+ 'auml': '\xe4',
+ 'Auml;': '\xc4',
+ 'auml;': '\xe4',
+ 'awconint;': '\u2233',
+ 'awint;': '\u2a11',
+ 'backcong;': '\u224c',
+ 'backepsilon;': '\u03f6',
+ 'backprime;': '\u2035',
+ 'backsim;': '\u223d',
+ 'backsimeq;': '\u22cd',
+ 'Backslash;': '\u2216',
+ 'Barv;': '\u2ae7',
+ 'barvee;': '\u22bd',
+ 'Barwed;': '\u2306',
+ 'barwed;': '\u2305',
+ 'barwedge;': '\u2305',
+ 'bbrk;': '\u23b5',
+ 'bbrktbrk;': '\u23b6',
+ 'bcong;': '\u224c',
+ 'Bcy;': '\u0411',
+ 'bcy;': '\u0431',
+ 'bdquo;': '\u201e',
+ 'becaus;': '\u2235',
+ 'Because;': '\u2235',
+ 'because;': '\u2235',
+ 'bemptyv;': '\u29b0',
+ 'bepsi;': '\u03f6',
+ 'bernou;': '\u212c',
+ 'Bernoullis;': '\u212c',
+ 'Beta;': '\u0392',
+ 'beta;': '\u03b2',
+ 'beth;': '\u2136',
+ 'between;': '\u226c',
+ 'Bfr;': '\U0001d505',
+ '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;': '\u2aed',
+ 'bnot;': '\u2310',
+ 'Bopf;': '\U0001d539',
+ 'bopf;': '\U0001d553',
+ 'bot;': '\u22a5',
+ 'bottom;': '\u22a5',
+ 'bowtie;': '\u22c8',
+ 'boxbox;': '\u29c9',
+ 'boxDL;': '\u2557',
+ 'boxDl;': '\u2556',
+ 'boxdL;': '\u2555',
+ 'boxdl;': '\u2510',
+ 'boxDR;': '\u2554',
+ 'boxDr;': '\u2553',
+ 'boxdR;': '\u2552',
+ 'boxdr;': '\u250c',
+ 'boxH;': '\u2550',
+ 'boxh;': '\u2500',
+ 'boxHD;': '\u2566',
+ 'boxHd;': '\u2564',
+ 'boxhD;': '\u2565',
+ 'boxhd;': '\u252c',
+ 'boxHU;': '\u2569',
+ 'boxHu;': '\u2567',
+ 'boxhU;': '\u2568',
+ 'boxhu;': '\u2534',
+ 'boxminus;': '\u229f',
+ 'boxplus;': '\u229e',
+ 'boxtimes;': '\u22a0',
+ 'boxUL;': '\u255d',
+ 'boxUl;': '\u255c',
+ 'boxuL;': '\u255b',
+ 'boxul;': '\u2518',
+ 'boxUR;': '\u255a',
+ 'boxUr;': '\u2559',
+ 'boxuR;': '\u2558',
+ 'boxur;': '\u2514',
+ 'boxV;': '\u2551',
+ 'boxv;': '\u2502',
+ 'boxVH;': '\u256c',
+ 'boxVh;': '\u256b',
+ 'boxvH;': '\u256a',
+ 'boxvh;': '\u253c',
+ 'boxVL;': '\u2563',
+ 'boxVl;': '\u2562',
+ 'boxvL;': '\u2561',
+ 'boxvl;': '\u2524',
+ 'boxVR;': '\u2560',
+ 'boxVr;': '\u255f',
+ 'boxvR;': '\u255e',
+ 'boxvr;': '\u251c',
+ 'bprime;': '\u2035',
+ 'Breve;': '\u02d8',
+ 'breve;': '\u02d8',
+ 'brvbar': '\xa6',
+ 'brvbar;': '\xa6',
+ 'Bscr;': '\u212c',
+ 'bscr;': '\U0001d4b7',
+ 'bsemi;': '\u204f',
+ 'bsim;': '\u223d',
+ 'bsime;': '\u22cd',
+ 'bsol;': '\\',
+ 'bsolb;': '\u29c5',
+ 'bsolhsub;': '\u27c8',
+ 'bull;': '\u2022',
+ 'bullet;': '\u2022',
+ 'bump;': '\u224e',
+ 'bumpE;': '\u2aae',
+ 'bumpe;': '\u224f',
+ 'Bumpeq;': '\u224e',
+ 'bumpeq;': '\u224f',
+ 'Cacute;': '\u0106',
+ 'cacute;': '\u0107',
+ 'Cap;': '\u22d2',
+ 'cap;': '\u2229',
+ 'capand;': '\u2a44',
+ 'capbrcup;': '\u2a49',
+ 'capcap;': '\u2a4b',
+ 'capcup;': '\u2a47',
+ 'capdot;': '\u2a40',
+ 'CapitalDifferentialD;': '\u2145',
+ 'caps;': '\u2229\ufe00',
+ 'caret;': '\u2041',
+ 'caron;': '\u02c7',
+ 'Cayleys;': '\u212d',
+ 'ccaps;': '\u2a4d',
+ 'Ccaron;': '\u010c',
+ 'ccaron;': '\u010d',
+ 'Ccedil': '\xc7',
+ 'ccedil': '\xe7',
+ 'Ccedil;': '\xc7',
+ 'ccedil;': '\xe7',
+ 'Ccirc;': '\u0108',
+ 'ccirc;': '\u0109',
+ 'Cconint;': '\u2230',
+ 'ccups;': '\u2a4c',
+ 'ccupssm;': '\u2a50',
+ 'Cdot;': '\u010a',
+ 'cdot;': '\u010b',
+ 'cedil': '\xb8',
+ 'cedil;': '\xb8',
+ 'Cedilla;': '\xb8',
+ 'cemptyv;': '\u29b2',
+ 'cent': '\xa2',
+ 'cent;': '\xa2',
+ 'CenterDot;': '\xb7',
+ 'centerdot;': '\xb7',
+ 'Cfr;': '\u212d',
+ 'cfr;': '\U0001d520',
+ 'CHcy;': '\u0427',
+ 'chcy;': '\u0447',
+ 'check;': '\u2713',
+ 'checkmark;': '\u2713',
+ 'Chi;': '\u03a7',
+ 'chi;': '\u03c7',
+ 'cir;': '\u25cb',
+ 'circ;': '\u02c6',
+ 'circeq;': '\u2257',
+ 'circlearrowleft;': '\u21ba',
+ 'circlearrowright;': '\u21bb',
+ 'circledast;': '\u229b',
+ 'circledcirc;': '\u229a',
+ 'circleddash;': '\u229d',
+ 'CircleDot;': '\u2299',
+ 'circledR;': '\xae',
+ 'circledS;': '\u24c8',
+ 'CircleMinus;': '\u2296',
+ 'CirclePlus;': '\u2295',
+ 'CircleTimes;': '\u2297',
+ 'cirE;': '\u29c3',
+ 'cire;': '\u2257',
+ 'cirfnint;': '\u2a10',
+ 'cirmid;': '\u2aef',
+ 'cirscir;': '\u29c2',
+ 'ClockwiseContourIntegral;': '\u2232',
+ 'CloseCurlyDoubleQuote;': '\u201d',
+ 'CloseCurlyQuote;': '\u2019',
+ 'clubs;': '\u2663',
+ 'clubsuit;': '\u2663',
+ 'Colon;': '\u2237',
+ 'colon;': ':',
+ 'Colone;': '\u2a74',
+ 'colone;': '\u2254',
+ 'coloneq;': '\u2254',
+ 'comma;': ',',
+ 'commat;': '@',
+ 'comp;': '\u2201',
+ 'compfn;': '\u2218',
+ 'complement;': '\u2201',
+ 'complexes;': '\u2102',
+ 'cong;': '\u2245',
+ 'congdot;': '\u2a6d',
+ 'Congruent;': '\u2261',
+ 'Conint;': '\u222f',
+ 'conint;': '\u222e',
+ 'ContourIntegral;': '\u222e',
+ 'Copf;': '\u2102',
+ 'copf;': '\U0001d554',
+ 'coprod;': '\u2210',
+ 'Coproduct;': '\u2210',
+ 'COPY': '\xa9',
+ 'copy': '\xa9',
+ 'COPY;': '\xa9',
+ 'copy;': '\xa9',
+ 'copysr;': '\u2117',
+ 'CounterClockwiseContourIntegral;': '\u2233',
+ 'crarr;': '\u21b5',
+ 'Cross;': '\u2a2f',
+ 'cross;': '\u2717',
+ 'Cscr;': '\U0001d49e',
+ '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;': '\u22d3',
+ 'cup;': '\u222a',
+ 'cupbrcap;': '\u2a48',
+ 'CupCap;': '\u224d',
+ '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',
+ 'Dagger;': '\u2021',
+ 'dagger;': '\u2020',
+ 'daleth;': '\u2138',
+ 'Darr;': '\u21a1',
+ 'dArr;': '\u21d3',
+ 'darr;': '\u2193',
+ 'dash;': '\u2010',
+ 'Dashv;': '\u2ae4',
+ 'dashv;': '\u22a3',
+ 'dbkarow;': '\u290f',
+ 'dblac;': '\u02dd',
+ 'Dcaron;': '\u010e',
+ 'dcaron;': '\u010f',
+ 'Dcy;': '\u0414',
+ 'dcy;': '\u0434',
+ 'DD;': '\u2145',
+ 'dd;': '\u2146',
+ 'ddagger;': '\u2021',
+ 'ddarr;': '\u21ca',
+ 'DDotrahd;': '\u2911',
+ 'ddotseq;': '\u2a77',
+ 'deg': '\xb0',
+ 'deg;': '\xb0',
+ 'Del;': '\u2207',
+ 'Delta;': '\u0394',
+ 'delta;': '\u03b4',
+ 'demptyv;': '\u29b1',
+ 'dfisht;': '\u297f',
+ 'Dfr;': '\U0001d507',
+ 'dfr;': '\U0001d521',
+ 'dHar;': '\u2965',
+ 'dharl;': '\u21c3',
+ 'dharr;': '\u21c2',
+ 'DiacriticalAcute;': '\xb4',
+ 'DiacriticalDot;': '\u02d9',
+ 'DiacriticalDoubleAcute;': '\u02dd',
+ 'DiacriticalGrave;': '`',
+ 'DiacriticalTilde;': '\u02dc',
+ 'diam;': '\u22c4',
+ 'Diamond;': '\u22c4',
+ 'diamond;': '\u22c4',
+ 'diamondsuit;': '\u2666',
+ 'diams;': '\u2666',
+ 'die;': '\xa8',
+ 'DifferentialD;': '\u2146',
+ 'digamma;': '\u03dd',
+ 'disin;': '\u22f2',
+ 'div;': '\xf7',
+ 'divide': '\xf7',
+ 'divide;': '\xf7',
+ 'divideontimes;': '\u22c7',
+ 'divonx;': '\u22c7',
+ 'DJcy;': '\u0402',
+ 'djcy;': '\u0452',
+ 'dlcorn;': '\u231e',
+ 'dlcrop;': '\u230d',
+ 'dollar;': '$',
+ 'Dopf;': '\U0001d53b',
+ 'dopf;': '\U0001d555',
+ 'Dot;': '\xa8',
+ 'dot;': '\u02d9',
+ 'DotDot;': '\u20dc',
+ 'doteq;': '\u2250',
+ 'doteqdot;': '\u2251',
+ 'DotEqual;': '\u2250',
+ 'dotminus;': '\u2238',
+ 'dotplus;': '\u2214',
+ 'dotsquare;': '\u22a1',
+ 'doublebarwedge;': '\u2306',
+ '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',
+ 'Downarrow;': '\u21d3',
+ 'downarrow;': '\u2193',
+ 'DownArrowBar;': '\u2913',
+ 'DownArrowUpArrow;': '\u21f5',
+ 'DownBreve;': '\u0311',
+ 'downdownarrows;': '\u21ca',
+ 'downharpoonleft;': '\u21c3',
+ 'downharpoonright;': '\u21c2',
+ 'DownLeftRightVector;': '\u2950',
+ 'DownLeftTeeVector;': '\u295e',
+ 'DownLeftVector;': '\u21bd',
+ 'DownLeftVectorBar;': '\u2956',
+ 'DownRightTeeVector;': '\u295f',
+ 'DownRightVector;': '\u21c1',
+ 'DownRightVectorBar;': '\u2957',
+ 'DownTee;': '\u22a4',
+ 'DownTeeArrow;': '\u21a7',
+ 'drbkarow;': '\u2910',
+ 'drcorn;': '\u231f',
+ 'drcrop;': '\u230c',
+ 'Dscr;': '\U0001d49f',
+ 'dscr;': '\U0001d4b9',
+ 'DScy;': '\u0405',
+ 'dscy;': '\u0455',
+ 'dsol;': '\u29f6',
+ 'Dstrok;': '\u0110',
+ 'dstrok;': '\u0111',
+ 'dtdot;': '\u22f1',
+ 'dtri;': '\u25bf',
+ 'dtrif;': '\u25be',
+ 'duarr;': '\u21f5',
+ 'duhar;': '\u296f',
+ 'dwangle;': '\u29a6',
+ 'DZcy;': '\u040f',
+ 'dzcy;': '\u045f',
+ 'dzigrarr;': '\u27ff',
+ 'Eacute': '\xc9',
+ 'eacute': '\xe9',
+ 'Eacute;': '\xc9',
+ 'eacute;': '\xe9',
+ 'easter;': '\u2a6e',
+ 'Ecaron;': '\u011a',
+ 'ecaron;': '\u011b',
+ 'ecir;': '\u2256',
+ 'Ecirc': '\xca',
+ 'ecirc': '\xea',
+ 'Ecirc;': '\xca',
+ 'ecirc;': '\xea',
+ 'ecolon;': '\u2255',
+ 'Ecy;': '\u042d',
+ 'ecy;': '\u044d',
+ 'eDDot;': '\u2a77',
+ 'Edot;': '\u0116',
+ 'eDot;': '\u2251',
+ 'edot;': '\u0117',
+ 'ee;': '\u2147',
+ 'efDot;': '\u2252',
+ 'Efr;': '\U0001d508',
+ 'efr;': '\U0001d522',
+ 'eg;': '\u2a9a',
+ 'Egrave': '\xc8',
+ 'egrave': '\xe8',
+ 'Egrave;': '\xc8',
+ 'egrave;': '\xe8',
+ 'egs;': '\u2a96',
+ 'egsdot;': '\u2a98',
+ 'el;': '\u2a99',
+ 'Element;': '\u2208',
+ 'elinters;': '\u23e7',
+ 'ell;': '\u2113',
+ 'els;': '\u2a95',
+ 'elsdot;': '\u2a97',
+ 'Emacr;': '\u0112',
+ 'emacr;': '\u0113',
+ 'empty;': '\u2205',
+ 'emptyset;': '\u2205',
+ 'EmptySmallSquare;': '\u25fb',
+ 'emptyv;': '\u2205',
+ 'EmptyVerySmallSquare;': '\u25ab',
+ 'emsp13;': '\u2004',
+ 'emsp14;': '\u2005',
+ 'emsp;': '\u2003',
+ 'ENG;': '\u014a',
+ 'eng;': '\u014b',
+ 'ensp;': '\u2002',
+ 'Eogon;': '\u0118',
+ 'eogon;': '\u0119',
+ 'Eopf;': '\U0001d53c',
+ 'eopf;': '\U0001d556',
+ 'epar;': '\u22d5',
+ 'eparsl;': '\u29e3',
+ 'eplus;': '\u2a71',
+ 'epsi;': '\u03b5',
+ 'Epsilon;': '\u0395',
+ 'epsilon;': '\u03b5',
+ 'epsiv;': '\u03f5',
+ 'eqcirc;': '\u2256',
+ 'eqcolon;': '\u2255',
+ 'eqsim;': '\u2242',
+ 'eqslantgtr;': '\u2a96',
+ 'eqslantless;': '\u2a95',
+ 'Equal;': '\u2a75',
+ 'equals;': '=',
+ 'EqualTilde;': '\u2242',
+ 'equest;': '\u225f',
+ 'Equilibrium;': '\u21cc',
+ 'equiv;': '\u2261',
+ 'equivDD;': '\u2a78',
+ 'eqvparsl;': '\u29e5',
+ 'erarr;': '\u2971',
+ 'erDot;': '\u2253',
+ 'Escr;': '\u2130',
+ 'escr;': '\u212f',
+ 'esdot;': '\u2250',
+ 'Esim;': '\u2a73',
+ 'esim;': '\u2242',
+ 'Eta;': '\u0397',
+ 'eta;': '\u03b7',
+ 'ETH': '\xd0',
+ 'eth': '\xf0',
+ 'ETH;': '\xd0',
+ 'eth;': '\xf0',
+ 'Euml': '\xcb',
+ 'euml': '\xeb',
+ 'Euml;': '\xcb',
+ 'euml;': '\xeb',
+ 'euro;': '\u20ac',
+ 'excl;': '!',
+ 'exist;': '\u2203',
+ 'Exists;': '\u2203',
+ 'expectation;': '\u2130',
+ 'ExponentialE;': '\u2147',
+ 'exponentiale;': '\u2147',
+ 'fallingdotseq;': '\u2252',
+ 'Fcy;': '\u0424',
+ 'fcy;': '\u0444',
+ 'female;': '\u2640',
+ 'ffilig;': '\ufb03',
+ 'fflig;': '\ufb00',
+ 'ffllig;': '\ufb04',
+ 'Ffr;': '\U0001d509',
+ 'ffr;': '\U0001d523',
+ 'filig;': '\ufb01',
+ 'FilledSmallSquare;': '\u25fc',
+ 'FilledVerySmallSquare;': '\u25aa',
+ 'fjlig;': 'fj',
+ 'flat;': '\u266d',
+ 'fllig;': '\ufb02',
+ 'fltns;': '\u25b1',
+ 'fnof;': '\u0192',
+ 'Fopf;': '\U0001d53d',
+ 'fopf;': '\U0001d557',
+ 'ForAll;': '\u2200',
+ 'forall;': '\u2200',
+ 'fork;': '\u22d4',
+ 'forkv;': '\u2ad9',
+ 'Fouriertrf;': '\u2131',
+ '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;': '\u2131',
+ 'fscr;': '\U0001d4bb',
+ 'gacute;': '\u01f5',
+ 'Gamma;': '\u0393',
+ 'gamma;': '\u03b3',
+ 'Gammad;': '\u03dc',
+ 'gammad;': '\u03dd',
+ 'gap;': '\u2a86',
+ 'Gbreve;': '\u011e',
+ 'gbreve;': '\u011f',
+ 'Gcedil;': '\u0122',
+ 'Gcirc;': '\u011c',
+ 'gcirc;': '\u011d',
+ 'Gcy;': '\u0413',
+ 'gcy;': '\u0433',
+ 'Gdot;': '\u0120',
+ 'gdot;': '\u0121',
+ 'gE;': '\u2267',
+ 'ge;': '\u2265',
+ 'gEl;': '\u2a8c',
+ 'gel;': '\u22db',
+ 'geq;': '\u2265',
+ 'geqq;': '\u2267',
+ 'geqslant;': '\u2a7e',
+ 'ges;': '\u2a7e',
+ 'gescc;': '\u2aa9',
+ 'gesdot;': '\u2a80',
+ 'gesdoto;': '\u2a82',
+ 'gesdotol;': '\u2a84',
+ 'gesl;': '\u22db\ufe00',
+ 'gesles;': '\u2a94',
+ 'Gfr;': '\U0001d50a',
+ 'gfr;': '\U0001d524',
+ 'Gg;': '\u22d9',
+ 'gg;': '\u226b',
+ 'ggg;': '\u22d9',
+ 'gimel;': '\u2137',
+ 'GJcy;': '\u0403',
+ 'gjcy;': '\u0453',
+ 'gl;': '\u2277',
+ 'gla;': '\u2aa5',
+ 'glE;': '\u2a92',
+ 'glj;': '\u2aa4',
+ 'gnap;': '\u2a8a',
+ 'gnapprox;': '\u2a8a',
+ 'gnE;': '\u2269',
+ 'gne;': '\u2a88',
+ 'gneq;': '\u2a88',
+ 'gneqq;': '\u2269',
+ 'gnsim;': '\u22e7',
+ 'Gopf;': '\U0001d53e',
+ 'gopf;': '\U0001d558',
+ 'grave;': '`',
+ 'GreaterEqual;': '\u2265',
+ 'GreaterEqualLess;': '\u22db',
+ 'GreaterFullEqual;': '\u2267',
+ 'GreaterGreater;': '\u2aa2',
+ 'GreaterLess;': '\u2277',
+ 'GreaterSlantEqual;': '\u2a7e',
+ 'GreaterTilde;': '\u2273',
+ 'Gscr;': '\U0001d4a2',
+ 'gscr;': '\u210a',
+ 'gsim;': '\u2273',
+ 'gsime;': '\u2a8e',
+ 'gsiml;': '\u2a90',
+ 'GT': '>',
+ 'gt': '>',
+ 'GT;': '>',
+ 'Gt;': '\u226b',
+ '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',
+ 'Hacek;': '\u02c7',
+ 'hairsp;': '\u200a',
+ 'half;': '\xbd',
+ 'hamilt;': '\u210b',
+ 'HARDcy;': '\u042a',
+ 'hardcy;': '\u044a',
+ 'hArr;': '\u21d4',
+ 'harr;': '\u2194',
+ 'harrcir;': '\u2948',
+ 'harrw;': '\u21ad',
+ 'Hat;': '^',
+ 'hbar;': '\u210f',
+ 'Hcirc;': '\u0124',
+ 'hcirc;': '\u0125',
+ 'hearts;': '\u2665',
+ 'heartsuit;': '\u2665',
+ 'hellip;': '\u2026',
+ 'hercon;': '\u22b9',
+ 'Hfr;': '\u210c',
+ 'hfr;': '\U0001d525',
+ 'HilbertSpace;': '\u210b',
+ 'hksearow;': '\u2925',
+ 'hkswarow;': '\u2926',
+ 'hoarr;': '\u21ff',
+ 'homtht;': '\u223b',
+ 'hookleftarrow;': '\u21a9',
+ 'hookrightarrow;': '\u21aa',
+ 'Hopf;': '\u210d',
+ 'hopf;': '\U0001d559',
+ 'horbar;': '\u2015',
+ 'HorizontalLine;': '\u2500',
+ 'Hscr;': '\u210b',
+ 'hscr;': '\U0001d4bd',
+ 'hslash;': '\u210f',
+ 'Hstrok;': '\u0126',
+ 'hstrok;': '\u0127',
+ 'HumpDownHump;': '\u224e',
+ 'HumpEqual;': '\u224f',
+ 'hybull;': '\u2043',
+ 'hyphen;': '\u2010',
+ 'Iacute': '\xcd',
+ 'iacute': '\xed',
+ 'Iacute;': '\xcd',
+ 'iacute;': '\xed',
+ 'ic;': '\u2063',
+ 'Icirc': '\xce',
+ 'icirc': '\xee',
+ 'Icirc;': '\xce',
+ 'icirc;': '\xee',
+ 'Icy;': '\u0418',
+ 'icy;': '\u0438',
+ 'Idot;': '\u0130',
+ 'IEcy;': '\u0415',
+ 'iecy;': '\u0435',
+ 'iexcl': '\xa1',
+ 'iexcl;': '\xa1',
+ 'iff;': '\u21d4',
+ 'Ifr;': '\u2111',
+ 'ifr;': '\U0001d526',
+ 'Igrave': '\xcc',
+ 'igrave': '\xec',
+ 'Igrave;': '\xcc',
+ 'igrave;': '\xec',
+ 'ii;': '\u2148',
+ 'iiiint;': '\u2a0c',
+ 'iiint;': '\u222d',
+ 'iinfin;': '\u29dc',
+ 'iiota;': '\u2129',
+ 'IJlig;': '\u0132',
+ 'ijlig;': '\u0133',
+ 'Im;': '\u2111',
+ 'Imacr;': '\u012a',
+ 'imacr;': '\u012b',
+ 'image;': '\u2111',
+ 'ImaginaryI;': '\u2148',
+ 'imagline;': '\u2110',
+ 'imagpart;': '\u2111',
+ 'imath;': '\u0131',
+ 'imof;': '\u22b7',
+ 'imped;': '\u01b5',
+ 'Implies;': '\u21d2',
+ 'in;': '\u2208',
+ 'incare;': '\u2105',
+ 'infin;': '\u221e',
+ 'infintie;': '\u29dd',
+ 'inodot;': '\u0131',
+ 'Int;': '\u222c',
+ 'int;': '\u222b',
+ 'intcal;': '\u22ba',
+ 'integers;': '\u2124',
+ 'Integral;': '\u222b',
+ 'intercal;': '\u22ba',
+ 'Intersection;': '\u22c2',
+ 'intlarhk;': '\u2a17',
+ 'intprod;': '\u2a3c',
+ 'InvisibleComma;': '\u2063',
+ 'InvisibleTimes;': '\u2062',
+ 'IOcy;': '\u0401',
+ 'iocy;': '\u0451',
+ 'Iogon;': '\u012e',
+ 'iogon;': '\u012f',
+ 'Iopf;': '\U0001d540',
+ 'iopf;': '\U0001d55a',
+ 'Iota;': '\u0399',
+ 'iota;': '\u03b9',
+ 'iprod;': '\u2a3c',
+ 'iquest': '\xbf',
+ 'iquest;': '\xbf',
+ 'Iscr;': '\u2110',
+ 'iscr;': '\U0001d4be',
+ 'isin;': '\u2208',
+ 'isindot;': '\u22f5',
+ 'isinE;': '\u22f9',
+ 'isins;': '\u22f4',
+ 'isinsv;': '\u22f3',
+ 'isinv;': '\u2208',
+ 'it;': '\u2062',
+ 'Itilde;': '\u0128',
+ 'itilde;': '\u0129',
+ 'Iukcy;': '\u0406',
+ 'iukcy;': '\u0456',
+ 'Iuml': '\xcf',
+ 'iuml': '\xef',
+ 'Iuml;': '\xcf',
+ 'iuml;': '\xef',
+ 'Jcirc;': '\u0134',
+ 'jcirc;': '\u0135',
+ 'Jcy;': '\u0419',
+ 'jcy;': '\u0439',
+ 'Jfr;': '\U0001d50d',
+ 'jfr;': '\U0001d527',
+ 'jmath;': '\u0237',
+ 'Jopf;': '\U0001d541',
+ 'jopf;': '\U0001d55b',
+ 'Jscr;': '\U0001d4a5',
+ 'jscr;': '\U0001d4bf',
+ 'Jsercy;': '\u0408',
+ 'jsercy;': '\u0458',
+ 'Jukcy;': '\u0404',
+ 'jukcy;': '\u0454',
+ 'Kappa;': '\u039a',
+ 'kappa;': '\u03ba',
+ 'kappav;': '\u03f0',
+ 'Kcedil;': '\u0136',
+ 'kcedil;': '\u0137',
+ 'Kcy;': '\u041a',
+ 'kcy;': '\u043a',
+ 'Kfr;': '\U0001d50e',
+ 'kfr;': '\U0001d528',
+ 'kgreen;': '\u0138',
+ 'KHcy;': '\u0425',
+ 'khcy;': '\u0445',
+ 'KJcy;': '\u040c',
+ 'kjcy;': '\u045c',
+ 'Kopf;': '\U0001d542',
+ 'kopf;': '\U0001d55c',
+ 'Kscr;': '\U0001d4a6',
+ 'kscr;': '\U0001d4c0',
+ 'lAarr;': '\u21da',
+ 'Lacute;': '\u0139',
+ 'lacute;': '\u013a',
+ 'laemptyv;': '\u29b4',
+ 'lagran;': '\u2112',
+ 'Lambda;': '\u039b',
+ 'lambda;': '\u03bb',
+ 'Lang;': '\u27ea',
+ 'lang;': '\u27e8',
+ 'langd;': '\u2991',
+ 'langle;': '\u27e8',
+ 'lap;': '\u2a85',
+ 'Laplacetrf;': '\u2112',
+ 'laquo': '\xab',
+ 'laquo;': '\xab',
+ 'Larr;': '\u219e',
+ 'lArr;': '\u21d0',
+ 'larr;': '\u2190',
+ 'larrb;': '\u21e4',
+ 'larrbfs;': '\u291f',
+ 'larrfs;': '\u291d',
+ 'larrhk;': '\u21a9',
+ 'larrlp;': '\u21ab',
+ 'larrpl;': '\u2939',
+ 'larrsim;': '\u2973',
+ 'larrtl;': '\u21a2',
+ 'lat;': '\u2aab',
+ 'lAtail;': '\u291b',
+ 'latail;': '\u2919',
+ 'late;': '\u2aad',
+ 'lates;': '\u2aad\ufe00',
+ 'lBarr;': '\u290e',
+ 'lbarr;': '\u290c',
+ 'lbbrk;': '\u2772',
+ 'lbrace;': '{',
+ 'lbrack;': '[',
+ 'lbrke;': '\u298b',
+ 'lbrksld;': '\u298f',
+ 'lbrkslu;': '\u298d',
+ 'Lcaron;': '\u013d',
+ 'lcaron;': '\u013e',
+ 'Lcedil;': '\u013b',
+ 'lcedil;': '\u013c',
+ 'lceil;': '\u2308',
+ 'lcub;': '{',
+ 'Lcy;': '\u041b',
+ 'lcy;': '\u043b',
+ 'ldca;': '\u2936',
+ 'ldquo;': '\u201c',
+ 'ldquor;': '\u201e',
+ 'ldrdhar;': '\u2967',
+ 'ldrushar;': '\u294b',
+ 'ldsh;': '\u21b2',
+ 'lE;': '\u2266',
+ 'le;': '\u2264',
+ 'LeftAngleBracket;': '\u27e8',
+ 'LeftArrow;': '\u2190',
+ 'Leftarrow;': '\u21d0',
+ 'leftarrow;': '\u2190',
+ 'LeftArrowBar;': '\u21e4',
+ 'LeftArrowRightArrow;': '\u21c6',
+ 'leftarrowtail;': '\u21a2',
+ 'LeftCeiling;': '\u2308',
+ 'LeftDoubleBracket;': '\u27e6',
+ 'LeftDownTeeVector;': '\u2961',
+ 'LeftDownVector;': '\u21c3',
+ 'LeftDownVectorBar;': '\u2959',
+ 'LeftFloor;': '\u230a',
+ 'leftharpoondown;': '\u21bd',
+ 'leftharpoonup;': '\u21bc',
+ 'leftleftarrows;': '\u21c7',
+ 'LeftRightArrow;': '\u2194',
+ 'Leftrightarrow;': '\u21d4',
+ 'leftrightarrow;': '\u2194',
+ 'leftrightarrows;': '\u21c6',
+ 'leftrightharpoons;': '\u21cb',
+ 'leftrightsquigarrow;': '\u21ad',
+ 'LeftRightVector;': '\u294e',
+ 'LeftTee;': '\u22a3',
+ 'LeftTeeArrow;': '\u21a4',
+ 'LeftTeeVector;': '\u295a',
+ 'leftthreetimes;': '\u22cb',
+ 'LeftTriangle;': '\u22b2',
+ 'LeftTriangleBar;': '\u29cf',
+ 'LeftTriangleEqual;': '\u22b4',
+ 'LeftUpDownVector;': '\u2951',
+ 'LeftUpTeeVector;': '\u2960',
+ 'LeftUpVector;': '\u21bf',
+ 'LeftUpVectorBar;': '\u2958',
+ 'LeftVector;': '\u21bc',
+ 'LeftVectorBar;': '\u2952',
+ 'lEg;': '\u2a8b',
+ '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',
+ 'LessEqualGreater;': '\u22da',
+ 'LessFullEqual;': '\u2266',
+ 'LessGreater;': '\u2276',
+ 'lessgtr;': '\u2276',
+ 'LessLess;': '\u2aa1',
+ 'lesssim;': '\u2272',
+ 'LessSlantEqual;': '\u2a7d',
+ 'LessTilde;': '\u2272',
+ 'lfisht;': '\u297c',
+ 'lfloor;': '\u230a',
+ 'Lfr;': '\U0001d50f',
+ 'lfr;': '\U0001d529',
+ 'lg;': '\u2276',
+ 'lgE;': '\u2a91',
+ 'lHar;': '\u2962',
+ 'lhard;': '\u21bd',
+ 'lharu;': '\u21bc',
+ 'lharul;': '\u296a',
+ 'lhblk;': '\u2584',
+ 'LJcy;': '\u0409',
+ 'ljcy;': '\u0459',
+ 'Ll;': '\u22d8',
+ 'll;': '\u226a',
+ 'llarr;': '\u21c7',
+ 'llcorner;': '\u231e',
+ 'Lleftarrow;': '\u21da',
+ 'llhard;': '\u296b',
+ 'lltri;': '\u25fa',
+ 'Lmidot;': '\u013f',
+ 'lmidot;': '\u0140',
+ 'lmoust;': '\u23b0',
+ 'lmoustache;': '\u23b0',
+ 'lnap;': '\u2a89',
+ 'lnapprox;': '\u2a89',
+ 'lnE;': '\u2268',
+ 'lne;': '\u2a87',
+ 'lneq;': '\u2a87',
+ 'lneqq;': '\u2268',
+ 'lnsim;': '\u22e6',
+ 'loang;': '\u27ec',
+ 'loarr;': '\u21fd',
+ 'lobrk;': '\u27e6',
+ 'LongLeftArrow;': '\u27f5',
+ 'Longleftarrow;': '\u27f8',
+ 'longleftarrow;': '\u27f5',
+ 'LongLeftRightArrow;': '\u27f7',
+ 'Longleftrightarrow;': '\u27fa',
+ 'longleftrightarrow;': '\u27f7',
+ 'longmapsto;': '\u27fc',
+ 'LongRightArrow;': '\u27f6',
+ 'Longrightarrow;': '\u27f9',
+ 'longrightarrow;': '\u27f6',
+ 'looparrowleft;': '\u21ab',
+ 'looparrowright;': '\u21ac',
+ 'lopar;': '\u2985',
+ 'Lopf;': '\U0001d543',
+ 'lopf;': '\U0001d55d',
+ 'loplus;': '\u2a2d',
+ 'lotimes;': '\u2a34',
+ 'lowast;': '\u2217',
+ 'lowbar;': '_',
+ 'LowerLeftArrow;': '\u2199',
+ 'LowerRightArrow;': '\u2198',
+ 'loz;': '\u25ca',
+ 'lozenge;': '\u25ca',
+ 'lozf;': '\u29eb',
+ 'lpar;': '(',
+ 'lparlt;': '\u2993',
+ 'lrarr;': '\u21c6',
+ 'lrcorner;': '\u231f',
+ 'lrhar;': '\u21cb',
+ 'lrhard;': '\u296d',
+ 'lrm;': '\u200e',
+ 'lrtri;': '\u22bf',
+ 'lsaquo;': '\u2039',
+ 'Lscr;': '\u2112',
+ 'lscr;': '\U0001d4c1',
+ 'Lsh;': '\u21b0',
+ 'lsh;': '\u21b0',
+ 'lsim;': '\u2272',
+ 'lsime;': '\u2a8d',
+ 'lsimg;': '\u2a8f',
+ 'lsqb;': '[',
+ 'lsquo;': '\u2018',
+ 'lsquor;': '\u201a',
+ 'Lstrok;': '\u0141',
+ 'lstrok;': '\u0142',
+ 'LT': '<',
+ 'lt': '<',
+ 'LT;': '<',
+ 'Lt;': '\u226a',
+ 'lt;': '<',
+ 'ltcc;': '\u2aa6',
+ 'ltcir;': '\u2a79',
+ 'ltdot;': '\u22d6',
+ 'lthree;': '\u22cb',
+ 'ltimes;': '\u22c9',
+ 'ltlarr;': '\u2976',
+ 'ltquest;': '\u2a7b',
+ 'ltri;': '\u25c3',
+ 'ltrie;': '\u22b4',
+ 'ltrif;': '\u25c2',
+ 'ltrPar;': '\u2996',
+ 'lurdshar;': '\u294a',
+ 'luruhar;': '\u2966',
+ 'lvertneqq;': '\u2268\ufe00',
+ 'lvnE;': '\u2268\ufe00',
+ 'macr': '\xaf',
+ 'macr;': '\xaf',
+ 'male;': '\u2642',
+ 'malt;': '\u2720',
+ 'maltese;': '\u2720',
+ 'Map;': '\u2905',
+ 'map;': '\u21a6',
+ 'mapsto;': '\u21a6',
+ 'mapstodown;': '\u21a7',
+ 'mapstoleft;': '\u21a4',
+ 'mapstoup;': '\u21a5',
+ 'marker;': '\u25ae',
+ 'mcomma;': '\u2a29',
+ 'Mcy;': '\u041c',
+ 'mcy;': '\u043c',
+ 'mdash;': '\u2014',
+ 'mDDot;': '\u223a',
+ 'measuredangle;': '\u2221',
+ 'MediumSpace;': '\u205f',
+ 'Mellintrf;': '\u2133',
+ 'Mfr;': '\U0001d510',
+ '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',
+ 'MinusPlus;': '\u2213',
+ 'mlcp;': '\u2adb',
+ 'mldr;': '\u2026',
+ 'mnplus;': '\u2213',
+ 'models;': '\u22a7',
+ 'Mopf;': '\U0001d544',
+ 'mopf;': '\U0001d55e',
+ 'mp;': '\u2213',
+ 'Mscr;': '\u2133',
+ 'mscr;': '\U0001d4c2',
+ 'mstpos;': '\u223e',
+ 'Mu;': '\u039c',
+ 'mu;': '\u03bc',
+ 'multimap;': '\u22b8',
+ 'mumap;': '\u22b8',
+ 'nabla;': '\u2207',
+ 'Nacute;': '\u0143',
+ '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;': '\u0147',
+ 'ncaron;': '\u0148',
+ 'Ncedil;': '\u0145',
+ 'ncedil;': '\u0146',
+ 'ncong;': '\u2247',
+ 'ncongdot;': '\u2a6d\u0338',
+ 'ncup;': '\u2a42',
+ 'Ncy;': '\u041d',
+ 'ncy;': '\u043d',
+ 'ndash;': '\u2013',
+ 'ne;': '\u2260',
+ 'nearhk;': '\u2924',
+ 'neArr;': '\u21d7',
+ 'nearr;': '\u2197',
+ 'nearrow;': '\u2197',
+ 'nedot;': '\u2250\u0338',
+ 'NegativeMediumSpace;': '\u200b',
+ 'NegativeThickSpace;': '\u200b',
+ 'NegativeThinSpace;': '\u200b',
+ 'NegativeVeryThinSpace;': '\u200b',
+ 'nequiv;': '\u2262',
+ 'nesear;': '\u2928',
+ 'nesim;': '\u2242\u0338',
+ 'NestedGreaterGreater;': '\u226b',
+ 'NestedLessLess;': '\u226a',
+ 'NewLine;': '\n',
+ 'nexist;': '\u2204',
+ 'nexists;': '\u2204',
+ 'Nfr;': '\U0001d511',
+ 'nfr;': '\U0001d52b',
+ 'ngE;': '\u2267\u0338',
+ 'nge;': '\u2271',
+ 'ngeq;': '\u2271',
+ 'ngeqq;': '\u2267\u0338',
+ 'ngeqslant;': '\u2a7e\u0338',
+ 'nges;': '\u2a7e\u0338',
+ 'nGg;': '\u22d9\u0338',
+ 'ngsim;': '\u2275',
+ 'nGt;': '\u226b\u20d2',
+ 'ngt;': '\u226f',
+ 'ngtr;': '\u226f',
+ 'nGtv;': '\u226b\u0338',
+ 'nhArr;': '\u21ce',
+ 'nharr;': '\u21ae',
+ 'nhpar;': '\u2af2',
+ 'ni;': '\u220b',
+ 'nis;': '\u22fc',
+ 'nisd;': '\u22fa',
+ 'niv;': '\u220b',
+ 'NJcy;': '\u040a',
+ 'njcy;': '\u045a',
+ 'nlArr;': '\u21cd',
+ 'nlarr;': '\u219a',
+ 'nldr;': '\u2025',
+ 'nlE;': '\u2266\u0338',
+ 'nle;': '\u2270',
+ 'nLeftarrow;': '\u21cd',
+ 'nleftarrow;': '\u219a',
+ 'nLeftrightarrow;': '\u21ce',
+ 'nleftrightarrow;': '\u21ae',
+ 'nleq;': '\u2270',
+ 'nleqq;': '\u2266\u0338',
+ 'nleqslant;': '\u2a7d\u0338',
+ 'nles;': '\u2a7d\u0338',
+ 'nless;': '\u226e',
+ 'nLl;': '\u22d8\u0338',
+ 'nlsim;': '\u2274',
+ 'nLt;': '\u226a\u20d2',
+ 'nlt;': '\u226e',
+ 'nltri;': '\u22ea',
+ 'nltrie;': '\u22ec',
+ 'nLtv;': '\u226a\u0338',
+ 'nmid;': '\u2224',
+ 'NoBreak;': '\u2060',
+ 'NonBreakingSpace;': '\xa0',
+ 'Nopf;': '\u2115',
+ 'nopf;': '\U0001d55f',
+ 'not': '\xac',
+ 'Not;': '\u2aec',
+ 'not;': '\xac',
+ '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',
+ 'notin;': '\u2209',
+ 'notindot;': '\u22f5\u0338',
+ 'notinE;': '\u22f9\u0338',
+ 'notinva;': '\u2209',
+ 'notinvb;': '\u22f7',
+ 'notinvc;': '\u22f6',
+ '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',
+ 'notni;': '\u220c',
+ 'notniva;': '\u220c',
+ 'notnivb;': '\u22fe',
+ 'notnivc;': '\u22fd',
+ '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',
+ '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;': '\u21cf',
+ 'nrightarrow;': '\u219b',
+ 'nrtri;': '\u22eb',
+ 'nrtrie;': '\u22ed',
+ 'nsc;': '\u2281',
+ 'nsccue;': '\u22e1',
+ 'nsce;': '\u2ab0\u0338',
+ 'Nscr;': '\U0001d4a9',
+ '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': '\xd1',
+ 'ntilde': '\xf1',
+ 'Ntilde;': '\xd1',
+ 'ntilde;': '\xf1',
+ 'ntlg;': '\u2278',
+ 'ntriangleleft;': '\u22ea',
+ 'ntrianglelefteq;': '\u22ec',
+ 'ntriangleright;': '\u22eb',
+ 'ntrianglerighteq;': '\u22ed',
+ 'Nu;': '\u039d',
+ 'nu;': '\u03bd',
+ 'num;': '#',
+ 'numero;': '\u2116',
+ 'numsp;': '\u2007',
+ 'nvap;': '\u224d\u20d2',
+ 'nVDash;': '\u22af',
+ 'nVdash;': '\u22ae',
+ 'nvDash;': '\u22ad',
+ 'nvdash;': '\u22ac',
+ 'nvge;': '\u2265\u20d2',
+ 'nvgt;': '>\u20d2',
+ 'nvHarr;': '\u2904',
+ 'nvinfin;': '\u29de',
+ 'nvlArr;': '\u2902',
+ 'nvle;': '\u2264\u20d2',
+ 'nvlt;': '<\u20d2',
+ 'nvltrie;': '\u22b4\u20d2',
+ 'nvrArr;': '\u2903',
+ 'nvrtrie;': '\u22b5\u20d2',
+ 'nvsim;': '\u223c\u20d2',
+ 'nwarhk;': '\u2923',
+ 'nwArr;': '\u21d6',
+ 'nwarr;': '\u2196',
+ 'nwarrow;': '\u2196',
+ 'nwnear;': '\u2927',
+ 'Oacute': '\xd3',
+ 'oacute': '\xf3',
+ 'Oacute;': '\xd3',
+ 'oacute;': '\xf3',
+ 'oast;': '\u229b',
+ 'ocir;': '\u229a',
+ 'Ocirc': '\xd4',
+ 'ocirc': '\xf4',
+ 'Ocirc;': '\xd4',
+ 'ocirc;': '\xf4',
+ 'Ocy;': '\u041e',
+ 'ocy;': '\u043e',
+ 'odash;': '\u229d',
+ 'Odblac;': '\u0150',
+ 'odblac;': '\u0151',
+ 'odiv;': '\u2a38',
+ 'odot;': '\u2299',
+ 'odsold;': '\u29bc',
+ 'OElig;': '\u0152',
+ 'oelig;': '\u0153',
+ 'ofcir;': '\u29bf',
+ 'Ofr;': '\U0001d512',
+ 'ofr;': '\U0001d52c',
+ 'ogon;': '\u02db',
+ 'Ograve': '\xd2',
+ 'ograve': '\xf2',
+ 'Ograve;': '\xd2',
+ 'ograve;': '\xf2',
+ 'ogt;': '\u29c1',
+ 'ohbar;': '\u29b5',
+ 'ohm;': '\u03a9',
+ 'oint;': '\u222e',
+ 'olarr;': '\u21ba',
+ 'olcir;': '\u29be',
+ 'olcross;': '\u29bb',
+ 'oline;': '\u203e',
+ 'olt;': '\u29c0',
+ 'Omacr;': '\u014c',
+ 'omacr;': '\u014d',
+ 'Omega;': '\u03a9',
+ 'omega;': '\u03c9',
+ 'Omicron;': '\u039f',
+ 'omicron;': '\u03bf',
+ 'omid;': '\u29b6',
+ 'ominus;': '\u2296',
+ 'Oopf;': '\U0001d546',
+ 'oopf;': '\U0001d560',
+ 'opar;': '\u29b7',
+ 'OpenCurlyDoubleQuote;': '\u201c',
+ 'OpenCurlyQuote;': '\u2018',
+ 'operp;': '\u29b9',
+ 'oplus;': '\u2295',
+ 'Or;': '\u2a54',
+ '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',
+ 'oS;': '\u24c8',
+ 'Oscr;': '\U0001d4aa',
+ 'oscr;': '\u2134',
+ 'Oslash': '\xd8',
+ 'oslash': '\xf8',
+ 'Oslash;': '\xd8',
+ 'oslash;': '\xf8',
+ 'osol;': '\u2298',
+ 'Otilde': '\xd5',
+ 'otilde': '\xf5',
+ 'Otilde;': '\xd5',
+ 'otilde;': '\xf5',
+ 'Otimes;': '\u2a37',
+ 'otimes;': '\u2297',
+ 'otimesas;': '\u2a36',
+ 'Ouml': '\xd6',
+ 'ouml': '\xf6',
+ 'Ouml;': '\xd6',
+ 'ouml;': '\xf6',
+ 'ovbar;': '\u233d',
+ 'OverBar;': '\u203e',
+ 'OverBrace;': '\u23de',
+ 'OverBracket;': '\u23b4',
+ 'OverParenthesis;': '\u23dc',
+ 'par;': '\u2225',
+ 'para': '\xb6',
+ 'para;': '\xb6',
+ 'parallel;': '\u2225',
+ 'parsim;': '\u2af3',
+ 'parsl;': '\u2afd',
+ 'part;': '\u2202',
+ 'PartialD;': '\u2202',
+ 'Pcy;': '\u041f',
+ 'pcy;': '\u043f',
+ 'percnt;': '%',
+ 'period;': '.',
+ 'permil;': '\u2030',
+ 'perp;': '\u22a5',
+ 'pertenk;': '\u2031',
+ 'Pfr;': '\U0001d513',
+ 'pfr;': '\U0001d52d',
+ 'Phi;': '\u03a6',
+ 'phi;': '\u03c6',
+ 'phiv;': '\u03d5',
+ 'phmmat;': '\u2133',
+ 'phone;': '\u260e',
+ 'Pi;': '\u03a0',
+ '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',
+ 'PlusMinus;': '\xb1',
+ 'plusmn': '\xb1',
+ 'plusmn;': '\xb1',
+ 'plussim;': '\u2a26',
+ 'plustwo;': '\u2a27',
+ 'pm;': '\xb1',
+ 'Poincareplane;': '\u210c',
+ 'pointint;': '\u2a15',
+ 'Popf;': '\u2119',
+ 'popf;': '\U0001d561',
+ 'pound': '\xa3',
+ 'pound;': '\xa3',
+ 'Pr;': '\u2abb',
+ 'pr;': '\u227a',
+ 'prap;': '\u2ab7',
+ 'prcue;': '\u227c',
+ 'prE;': '\u2ab3',
+ 'pre;': '\u2aaf',
+ 'prec;': '\u227a',
+ 'precapprox;': '\u2ab7',
+ 'preccurlyeq;': '\u227c',
+ 'Precedes;': '\u227a',
+ 'PrecedesEqual;': '\u2aaf',
+ 'PrecedesSlantEqual;': '\u227c',
+ 'PrecedesTilde;': '\u227e',
+ 'preceq;': '\u2aaf',
+ 'precnapprox;': '\u2ab9',
+ 'precneqq;': '\u2ab5',
+ 'precnsim;': '\u22e8',
+ 'precsim;': '\u227e',
+ 'Prime;': '\u2033',
+ 'prime;': '\u2032',
+ 'primes;': '\u2119',
+ 'prnap;': '\u2ab9',
+ 'prnE;': '\u2ab5',
+ 'prnsim;': '\u22e8',
+ 'prod;': '\u220f',
+ 'Product;': '\u220f',
+ 'profalar;': '\u232e',
+ 'profline;': '\u2312',
+ 'profsurf;': '\u2313',
+ 'prop;': '\u221d',
+ 'Proportion;': '\u2237',
+ 'Proportional;': '\u221d',
+ 'propto;': '\u221d',
+ 'prsim;': '\u227e',
+ 'prurel;': '\u22b0',
+ 'Pscr;': '\U0001d4ab',
+ 'pscr;': '\U0001d4c5',
+ 'Psi;': '\u03a8',
+ 'psi;': '\u03c8',
+ 'puncsp;': '\u2008',
+ 'Qfr;': '\U0001d514',
+ 'qfr;': '\U0001d52e',
+ 'qint;': '\u2a0c',
+ 'Qopf;': '\u211a',
+ 'qopf;': '\U0001d562',
+ 'qprime;': '\u2057',
+ 'Qscr;': '\U0001d4ac',
+ 'qscr;': '\U0001d4c6',
+ 'quaternions;': '\u210d',
+ 'quatint;': '\u2a16',
+ 'quest;': '?',
+ 'questeq;': '\u225f',
+ 'QUOT': '"',
+ 'quot': '"',
+ 'QUOT;': '"',
+ 'quot;': '"',
+ 'rAarr;': '\u21db',
+ 'race;': '\u223d\u0331',
+ 'Racute;': '\u0154',
+ 'racute;': '\u0155',
+ 'radic;': '\u221a',
+ 'raemptyv;': '\u29b3',
+ 'Rang;': '\u27eb',
+ 'rang;': '\u27e9',
+ 'rangd;': '\u2992',
+ 'range;': '\u29a5',
+ 'rangle;': '\u27e9',
+ 'raquo': '\xbb',
+ 'raquo;': '\xbb',
+ 'Rarr;': '\u21a0',
+ 'rArr;': '\u21d2',
+ 'rarr;': '\u2192',
+ 'rarrap;': '\u2975',
+ 'rarrb;': '\u21e5',
+ 'rarrbfs;': '\u2920',
+ 'rarrc;': '\u2933',
+ 'rarrfs;': '\u291e',
+ 'rarrhk;': '\u21aa',
+ 'rarrlp;': '\u21ac',
+ 'rarrpl;': '\u2945',
+ 'rarrsim;': '\u2974',
+ 'Rarrtl;': '\u2916',
+ 'rarrtl;': '\u21a3',
+ 'rarrw;': '\u219d',
+ 'rAtail;': '\u291c',
+ 'ratail;': '\u291a',
+ 'ratio;': '\u2236',
+ 'rationals;': '\u211a',
+ 'RBarr;': '\u2910',
+ 'rBarr;': '\u290f',
+ 'rbarr;': '\u290d',
+ 'rbbrk;': '\u2773',
+ 'rbrace;': '}',
+ 'rbrack;': ']',
+ 'rbrke;': '\u298c',
+ 'rbrksld;': '\u298e',
+ 'rbrkslu;': '\u2990',
+ 'Rcaron;': '\u0158',
+ 'rcaron;': '\u0159',
+ 'Rcedil;': '\u0156',
+ 'rcedil;': '\u0157',
+ 'rceil;': '\u2309',
+ 'rcub;': '}',
+ 'Rcy;': '\u0420',
+ 'rcy;': '\u0440',
+ 'rdca;': '\u2937',
+ 'rdldhar;': '\u2969',
+ 'rdquo;': '\u201d',
+ 'rdquor;': '\u201d',
+ 'rdsh;': '\u21b3',
+ 'Re;': '\u211c',
+ 'real;': '\u211c',
+ 'realine;': '\u211b',
+ 'realpart;': '\u211c',
+ 'reals;': '\u211d',
+ 'rect;': '\u25ad',
+ 'REG': '\xae',
+ 'reg': '\xae',
+ 'REG;': '\xae',
+ 'reg;': '\xae',
+ 'ReverseElement;': '\u220b',
+ 'ReverseEquilibrium;': '\u21cb',
+ 'ReverseUpEquilibrium;': '\u296f',
+ 'rfisht;': '\u297d',
+ 'rfloor;': '\u230b',
+ 'Rfr;': '\u211c',
+ 'rfr;': '\U0001d52f',
+ 'rHar;': '\u2964',
+ 'rhard;': '\u21c1',
+ 'rharu;': '\u21c0',
+ 'rharul;': '\u296c',
+ 'Rho;': '\u03a1',
+ 'rho;': '\u03c1',
+ 'rhov;': '\u03f1',
+ 'RightAngleBracket;': '\u27e9',
+ 'RightArrow;': '\u2192',
+ 'Rightarrow;': '\u21d2',
+ 'rightarrow;': '\u2192',
+ 'RightArrowBar;': '\u21e5',
+ 'RightArrowLeftArrow;': '\u21c4',
+ 'rightarrowtail;': '\u21a3',
+ 'RightCeiling;': '\u2309',
+ 'RightDoubleBracket;': '\u27e7',
+ 'RightDownTeeVector;': '\u295d',
+ 'RightDownVector;': '\u21c2',
+ 'RightDownVectorBar;': '\u2955',
+ 'RightFloor;': '\u230b',
+ 'rightharpoondown;': '\u21c1',
+ 'rightharpoonup;': '\u21c0',
+ 'rightleftarrows;': '\u21c4',
+ 'rightleftharpoons;': '\u21cc',
+ 'rightrightarrows;': '\u21c9',
+ 'rightsquigarrow;': '\u219d',
+ 'RightTee;': '\u22a2',
+ 'RightTeeArrow;': '\u21a6',
+ 'RightTeeVector;': '\u295b',
+ 'rightthreetimes;': '\u22cc',
+ 'RightTriangle;': '\u22b3',
+ 'RightTriangleBar;': '\u29d0',
+ 'RightTriangleEqual;': '\u22b5',
+ 'RightUpDownVector;': '\u294f',
+ 'RightUpTeeVector;': '\u295c',
+ 'RightUpVector;': '\u21be',
+ 'RightUpVectorBar;': '\u2954',
+ 'RightVector;': '\u21c0',
+ 'RightVectorBar;': '\u2953',
+ '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;': '\u211d',
+ 'ropf;': '\U0001d563',
+ 'roplus;': '\u2a2e',
+ 'rotimes;': '\u2a35',
+ 'RoundImplies;': '\u2970',
+ 'rpar;': ')',
+ 'rpargt;': '\u2994',
+ 'rppolint;': '\u2a12',
+ 'rrarr;': '\u21c9',
+ 'Rrightarrow;': '\u21db',
+ 'rsaquo;': '\u203a',
+ 'Rscr;': '\u211b',
+ 'rscr;': '\U0001d4c7',
+ 'Rsh;': '\u21b1',
+ 'rsh;': '\u21b1',
+ 'rsqb;': ']',
+ 'rsquo;': '\u2019',
+ 'rsquor;': '\u2019',
+ 'rthree;': '\u22cc',
+ 'rtimes;': '\u22ca',
+ 'rtri;': '\u25b9',
+ 'rtrie;': '\u22b5',
+ 'rtrif;': '\u25b8',
+ 'rtriltri;': '\u29ce',
+ 'RuleDelayed;': '\u29f4',
+ 'ruluhar;': '\u2968',
+ 'rx;': '\u211e',
+ 'Sacute;': '\u015a',
+ 'sacute;': '\u015b',
+ 'sbquo;': '\u201a',
+ 'Sc;': '\u2abc',
+ 'sc;': '\u227b',
+ 'scap;': '\u2ab8',
+ 'Scaron;': '\u0160',
+ 'scaron;': '\u0161',
+ 'sccue;': '\u227d',
+ 'scE;': '\u2ab4',
+ 'sce;': '\u2ab0',
+ 'Scedil;': '\u015e',
+ 'scedil;': '\u015f',
+ 'Scirc;': '\u015c',
+ 'scirc;': '\u015d',
+ 'scnap;': '\u2aba',
+ 'scnE;': '\u2ab6',
+ 'scnsim;': '\u22e9',
+ 'scpolint;': '\u2a13',
+ 'scsim;': '\u227f',
+ 'Scy;': '\u0421',
+ 'scy;': '\u0441',
+ 'sdot;': '\u22c5',
+ 'sdotb;': '\u22a1',
+ 'sdote;': '\u2a66',
+ 'searhk;': '\u2925',
+ 'seArr;': '\u21d8',
+ 'searr;': '\u2198',
+ 'searrow;': '\u2198',
+ 'sect': '\xa7',
+ 'sect;': '\xa7',
+ 'semi;': ';',
+ 'seswar;': '\u2929',
+ 'setminus;': '\u2216',
+ 'setmn;': '\u2216',
+ 'sext;': '\u2736',
+ 'Sfr;': '\U0001d516',
+ 'sfr;': '\U0001d530',
+ 'sfrown;': '\u2322',
+ 'sharp;': '\u266f',
+ 'SHCHcy;': '\u0429',
+ 'shchcy;': '\u0449',
+ 'SHcy;': '\u0428',
+ 'shcy;': '\u0448',
+ 'ShortDownArrow;': '\u2193',
+ 'ShortLeftArrow;': '\u2190',
+ 'shortmid;': '\u2223',
+ 'shortparallel;': '\u2225',
+ 'ShortRightArrow;': '\u2192',
+ 'ShortUpArrow;': '\u2191',
+ 'shy': '\xad',
+ 'shy;': '\xad',
+ 'Sigma;': '\u03a3',
+ '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',
+ 'SmallCircle;': '\u2218',
+ 'smallsetminus;': '\u2216',
+ 'smashp;': '\u2a33',
+ 'smeparsl;': '\u29e4',
+ 'smid;': '\u2223',
+ 'smile;': '\u2323',
+ 'smt;': '\u2aaa',
+ 'smte;': '\u2aac',
+ 'smtes;': '\u2aac\ufe00',
+ 'SOFTcy;': '\u042c',
+ 'softcy;': '\u044c',
+ 'sol;': '/',
+ 'solb;': '\u29c4',
+ 'solbar;': '\u233f',
+ 'Sopf;': '\U0001d54a',
+ 'sopf;': '\U0001d564',
+ 'spades;': '\u2660',
+ 'spadesuit;': '\u2660',
+ 'spar;': '\u2225',
+ 'sqcap;': '\u2293',
+ 'sqcaps;': '\u2293\ufe00',
+ 'sqcup;': '\u2294',
+ 'sqcups;': '\u2294\ufe00',
+ 'Sqrt;': '\u221a',
+ 'sqsub;': '\u228f',
+ 'sqsube;': '\u2291',
+ 'sqsubset;': '\u228f',
+ 'sqsubseteq;': '\u2291',
+ 'sqsup;': '\u2290',
+ 'sqsupe;': '\u2292',
+ 'sqsupset;': '\u2290',
+ 'sqsupseteq;': '\u2292',
+ 'squ;': '\u25a1',
+ 'Square;': '\u25a1',
+ 'square;': '\u25a1',
+ 'SquareIntersection;': '\u2293',
+ 'SquareSubset;': '\u228f',
+ 'SquareSubsetEqual;': '\u2291',
+ 'SquareSuperset;': '\u2290',
+ 'SquareSupersetEqual;': '\u2292',
+ 'SquareUnion;': '\u2294',
+ 'squarf;': '\u25aa',
+ 'squf;': '\u25aa',
+ 'srarr;': '\u2192',
+ 'Sscr;': '\U0001d4ae',
+ 'sscr;': '\U0001d4c8',
+ 'ssetmn;': '\u2216',
+ 'ssmile;': '\u2323',
+ 'sstarf;': '\u22c6',
+ 'Star;': '\u22c6',
+ 'star;': '\u2606',
+ 'starf;': '\u2605',
+ 'straightepsilon;': '\u03f5',
+ 'straightphi;': '\u03d5',
+ 'strns;': '\xaf',
+ 'Sub;': '\u22d0',
+ 'sub;': '\u2282',
+ 'subdot;': '\u2abd',
+ 'subE;': '\u2ac5',
+ 'sube;': '\u2286',
+ 'subedot;': '\u2ac3',
+ 'submult;': '\u2ac1',
+ 'subnE;': '\u2acb',
+ 'subne;': '\u228a',
+ 'subplus;': '\u2abf',
+ 'subrarr;': '\u2979',
+ 'Subset;': '\u22d0',
+ 'subset;': '\u2282',
+ 'subseteq;': '\u2286',
+ 'subseteqq;': '\u2ac5',
+ 'SubsetEqual;': '\u2286',
+ 'subsetneq;': '\u228a',
+ 'subsetneqq;': '\u2acb',
+ 'subsim;': '\u2ac7',
+ 'subsub;': '\u2ad5',
+ 'subsup;': '\u2ad3',
+ 'succ;': '\u227b',
+ 'succapprox;': '\u2ab8',
+ 'succcurlyeq;': '\u227d',
+ 'Succeeds;': '\u227b',
+ 'SucceedsEqual;': '\u2ab0',
+ 'SucceedsSlantEqual;': '\u227d',
+ 'SucceedsTilde;': '\u227f',
+ 'succeq;': '\u2ab0',
+ 'succnapprox;': '\u2aba',
+ 'succneqq;': '\u2ab6',
+ 'succnsim;': '\u22e9',
+ 'succsim;': '\u227f',
+ 'SuchThat;': '\u220b',
+ 'Sum;': '\u2211',
+ 'sum;': '\u2211',
+ 'sung;': '\u266a',
+ 'sup1': '\xb9',
+ 'sup1;': '\xb9',
+ 'sup2': '\xb2',
+ 'sup2;': '\xb2',
+ 'sup3': '\xb3',
+ 'sup3;': '\xb3',
+ 'Sup;': '\u22d1',
+ 'sup;': '\u2283',
+ 'supdot;': '\u2abe',
+ 'supdsub;': '\u2ad8',
+ 'supE;': '\u2ac6',
+ 'supe;': '\u2287',
+ 'supedot;': '\u2ac4',
+ 'Superset;': '\u2283',
+ 'SupersetEqual;': '\u2287',
+ 'suphsol;': '\u27c9',
+ 'suphsub;': '\u2ad7',
+ 'suplarr;': '\u297b',
+ 'supmult;': '\u2ac2',
+ 'supnE;': '\u2acc',
+ 'supne;': '\u228b',
+ 'supplus;': '\u2ac0',
+ 'Supset;': '\u22d1',
+ 'supset;': '\u2283',
+ 'supseteq;': '\u2287',
+ 'supseteqq;': '\u2ac6',
+ 'supsetneq;': '\u228b',
+ 'supsetneqq;': '\u2acc',
+ 'supsim;': '\u2ac8',
+ 'supsub;': '\u2ad4',
+ 'supsup;': '\u2ad6',
+ 'swarhk;': '\u2926',
+ 'swArr;': '\u21d9',
+ 'swarr;': '\u2199',
+ 'swarrow;': '\u2199',
+ 'swnwar;': '\u292a',
+ 'szlig': '\xdf',
+ 'szlig;': '\xdf',
+ 'Tab;': '\t',
+ 'target;': '\u2316',
+ 'Tau;': '\u03a4',
+ 'tau;': '\u03c4',
+ 'tbrk;': '\u23b4',
+ 'Tcaron;': '\u0164',
+ 'tcaron;': '\u0165',
+ 'Tcedil;': '\u0162',
+ 'tcedil;': '\u0163',
+ 'Tcy;': '\u0422',
+ 'tcy;': '\u0442',
+ 'tdot;': '\u20db',
+ 'telrec;': '\u2315',
+ 'Tfr;': '\U0001d517',
+ 'tfr;': '\U0001d531',
+ 'there4;': '\u2234',
+ 'Therefore;': '\u2234',
+ 'therefore;': '\u2234',
+ 'Theta;': '\u0398',
+ 'theta;': '\u03b8',
+ 'thetasym;': '\u03d1',
+ 'thetav;': '\u03d1',
+ 'thickapprox;': '\u2248',
+ 'thicksim;': '\u223c',
+ 'ThickSpace;': '\u205f\u200a',
+ 'thinsp;': '\u2009',
+ 'ThinSpace;': '\u2009',
+ 'thkap;': '\u2248',
+ 'thksim;': '\u223c',
+ 'THORN': '\xde',
+ 'thorn': '\xfe',
+ 'THORN;': '\xde',
+ 'thorn;': '\xfe',
+ 'Tilde;': '\u223c',
+ 'tilde;': '\u02dc',
+ 'TildeEqual;': '\u2243',
+ 'TildeFullEqual;': '\u2245',
+ 'TildeTilde;': '\u2248',
+ 'times': '\xd7',
+ 'times;': '\xd7',
+ 'timesb;': '\u22a0',
+ 'timesbar;': '\u2a31',
+ 'timesd;': '\u2a30',
+ 'tint;': '\u222d',
+ 'toea;': '\u2928',
+ 'top;': '\u22a4',
+ 'topbot;': '\u2336',
+ 'topcir;': '\u2af1',
+ 'Topf;': '\U0001d54b',
+ 'topf;': '\U0001d565',
+ 'topfork;': '\u2ada',
+ 'tosa;': '\u2929',
+ 'tprime;': '\u2034',
+ 'TRADE;': '\u2122',
+ 'trade;': '\u2122',
+ 'triangle;': '\u25b5',
+ 'triangledown;': '\u25bf',
+ 'triangleleft;': '\u25c3',
+ 'trianglelefteq;': '\u22b4',
+ 'triangleq;': '\u225c',
+ 'triangleright;': '\u25b9',
+ 'trianglerighteq;': '\u22b5',
+ 'tridot;': '\u25ec',
+ 'trie;': '\u225c',
+ 'triminus;': '\u2a3a',
+ 'TripleDot;': '\u20db',
+ 'triplus;': '\u2a39',
+ 'trisb;': '\u29cd',
+ 'tritime;': '\u2a3b',
+ 'trpezium;': '\u23e2',
+ 'Tscr;': '\U0001d4af',
+ 'tscr;': '\U0001d4c9',
+ 'TScy;': '\u0426',
+ 'tscy;': '\u0446',
+ 'TSHcy;': '\u040b',
+ 'tshcy;': '\u045b',
+ 'Tstrok;': '\u0166',
+ 'tstrok;': '\u0167',
+ 'twixt;': '\u226c',
+ 'twoheadleftarrow;': '\u219e',
+ 'twoheadrightarrow;': '\u21a0',
+ 'Uacute': '\xda',
+ 'uacute': '\xfa',
+ 'Uacute;': '\xda',
+ 'uacute;': '\xfa',
+ 'Uarr;': '\u219f',
+ 'uArr;': '\u21d1',
+ 'uarr;': '\u2191',
+ 'Uarrocir;': '\u2949',
+ 'Ubrcy;': '\u040e',
+ 'ubrcy;': '\u045e',
+ 'Ubreve;': '\u016c',
+ 'ubreve;': '\u016d',
+ 'Ucirc': '\xdb',
+ 'ucirc': '\xfb',
+ 'Ucirc;': '\xdb',
+ 'ucirc;': '\xfb',
+ 'Ucy;': '\u0423',
+ 'ucy;': '\u0443',
+ 'udarr;': '\u21c5',
+ 'Udblac;': '\u0170',
+ 'udblac;': '\u0171',
+ 'udhar;': '\u296e',
+ 'ufisht;': '\u297e',
+ 'Ufr;': '\U0001d518',
+ 'ufr;': '\U0001d532',
+ 'Ugrave': '\xd9',
+ 'ugrave': '\xf9',
+ 'Ugrave;': '\xd9',
+ 'ugrave;': '\xf9',
+ 'uHar;': '\u2963',
+ 'uharl;': '\u21bf',
+ 'uharr;': '\u21be',
+ 'uhblk;': '\u2580',
+ 'ulcorn;': '\u231c',
+ 'ulcorner;': '\u231c',
+ 'ulcrop;': '\u230f',
+ 'ultri;': '\u25f8',
+ 'Umacr;': '\u016a',
+ 'umacr;': '\u016b',
+ 'uml': '\xa8',
+ 'uml;': '\xa8',
+ 'UnderBar;': '_',
+ 'UnderBrace;': '\u23df',
+ 'UnderBracket;': '\u23b5',
+ 'UnderParenthesis;': '\u23dd',
+ 'Union;': '\u22c3',
+ 'UnionPlus;': '\u228e',
+ 'Uogon;': '\u0172',
+ 'uogon;': '\u0173',
+ 'Uopf;': '\U0001d54c',
+ 'uopf;': '\U0001d566',
+ 'UpArrow;': '\u2191',
+ 'Uparrow;': '\u21d1',
+ 'uparrow;': '\u2191',
+ 'UpArrowBar;': '\u2912',
+ 'UpArrowDownArrow;': '\u21c5',
+ 'UpDownArrow;': '\u2195',
+ 'Updownarrow;': '\u21d5',
+ 'updownarrow;': '\u2195',
+ 'UpEquilibrium;': '\u296e',
+ 'upharpoonleft;': '\u21bf',
+ 'upharpoonright;': '\u21be',
+ 'uplus;': '\u228e',
+ 'UpperLeftArrow;': '\u2196',
+ 'UpperRightArrow;': '\u2197',
+ 'Upsi;': '\u03d2',
+ 'upsi;': '\u03c5',
+ 'upsih;': '\u03d2',
+ 'Upsilon;': '\u03a5',
+ 'upsilon;': '\u03c5',
+ 'UpTee;': '\u22a5',
+ 'UpTeeArrow;': '\u21a5',
+ 'upuparrows;': '\u21c8',
+ 'urcorn;': '\u231d',
+ 'urcorner;': '\u231d',
+ 'urcrop;': '\u230e',
+ 'Uring;': '\u016e',
+ 'uring;': '\u016f',
+ 'urtri;': '\u25f9',
+ 'Uscr;': '\U0001d4b0',
+ 'uscr;': '\U0001d4ca',
+ 'utdot;': '\u22f0',
+ 'Utilde;': '\u0168',
+ 'utilde;': '\u0169',
+ 'utri;': '\u25b5',
+ 'utrif;': '\u25b4',
+ 'uuarr;': '\u21c8',
+ 'Uuml': '\xdc',
+ 'uuml': '\xfc',
+ 'Uuml;': '\xdc',
+ 'uuml;': '\xfc',
+ 'uwangle;': '\u29a7',
+ 'vangrt;': '\u299c',
+ 'varepsilon;': '\u03f5',
+ 'varkappa;': '\u03f0',
+ 'varnothing;': '\u2205',
+ 'varphi;': '\u03d5',
+ 'varpi;': '\u03d6',
+ 'varpropto;': '\u221d',
+ 'vArr;': '\u21d5',
+ 'varr;': '\u2195',
+ 'varrho;': '\u03f1',
+ 'varsigma;': '\u03c2',
+ 'varsubsetneq;': '\u228a\ufe00',
+ 'varsubsetneqq;': '\u2acb\ufe00',
+ 'varsupsetneq;': '\u228b\ufe00',
+ 'varsupsetneqq;': '\u2acc\ufe00',
+ 'vartheta;': '\u03d1',
+ 'vartriangleleft;': '\u22b2',
+ 'vartriangleright;': '\u22b3',
+ 'Vbar;': '\u2aeb',
+ 'vBar;': '\u2ae8',
+ 'vBarv;': '\u2ae9',
+ 'Vcy;': '\u0412',
+ 'vcy;': '\u0432',
+ 'VDash;': '\u22ab',
+ 'Vdash;': '\u22a9',
+ 'vDash;': '\u22a8',
+ 'vdash;': '\u22a2',
+ 'Vdashl;': '\u2ae6',
+ 'Vee;': '\u22c1',
+ 'vee;': '\u2228',
+ 'veebar;': '\u22bb',
+ 'veeeq;': '\u225a',
+ 'vellip;': '\u22ee',
+ 'Verbar;': '\u2016',
+ 'verbar;': '|',
+ 'Vert;': '\u2016',
+ 'vert;': '|',
+ 'VerticalBar;': '\u2223',
+ 'VerticalLine;': '|',
+ 'VerticalSeparator;': '\u2758',
+ 'VerticalTilde;': '\u2240',
+ 'VeryThinSpace;': '\u200a',
+ 'Vfr;': '\U0001d519',
+ 'vfr;': '\U0001d533',
+ 'vltri;': '\u22b2',
+ 'vnsub;': '\u2282\u20d2',
+ 'vnsup;': '\u2283\u20d2',
+ 'Vopf;': '\U0001d54d',
+ 'vopf;': '\U0001d567',
+ 'vprop;': '\u221d',
+ 'vrtri;': '\u22b3',
+ 'Vscr;': '\U0001d4b1',
+ 'vscr;': '\U0001d4cb',
+ 'vsubnE;': '\u2acb\ufe00',
+ 'vsubne;': '\u228a\ufe00',
+ 'vsupnE;': '\u2acc\ufe00',
+ 'vsupne;': '\u228b\ufe00',
+ 'Vvdash;': '\u22aa',
+ 'vzigzag;': '\u299a',
+ 'Wcirc;': '\u0174',
+ 'wcirc;': '\u0175',
+ 'wedbar;': '\u2a5f',
+ 'Wedge;': '\u22c0',
+ 'wedge;': '\u2227',
+ 'wedgeq;': '\u2259',
+ 'weierp;': '\u2118',
+ 'Wfr;': '\U0001d51a',
+ 'wfr;': '\U0001d534',
+ 'Wopf;': '\U0001d54e',
+ 'wopf;': '\U0001d568',
+ 'wp;': '\u2118',
+ 'wr;': '\u2240',
+ 'wreath;': '\u2240',
+ 'Wscr;': '\U0001d4b2',
+ 'wscr;': '\U0001d4cc',
+ 'xcap;': '\u22c2',
+ 'xcirc;': '\u25ef',
+ 'xcup;': '\u22c3',
+ 'xdtri;': '\u25bd',
+ 'Xfr;': '\U0001d51b',
+ 'xfr;': '\U0001d535',
+ 'xhArr;': '\u27fa',
+ 'xharr;': '\u27f7',
+ 'Xi;': '\u039e',
+ 'xi;': '\u03be',
+ 'xlArr;': '\u27f8',
+ 'xlarr;': '\u27f5',
+ 'xmap;': '\u27fc',
+ 'xnis;': '\u22fb',
+ 'xodot;': '\u2a00',
+ 'Xopf;': '\U0001d54f',
+ 'xopf;': '\U0001d569',
+ 'xoplus;': '\u2a01',
+ 'xotime;': '\u2a02',
+ 'xrArr;': '\u27f9',
+ 'xrarr;': '\u27f6',
+ 'Xscr;': '\U0001d4b3',
+ 'xscr;': '\U0001d4cd',
+ 'xsqcup;': '\u2a06',
+ 'xuplus;': '\u2a04',
+ 'xutri;': '\u25b3',
+ 'xvee;': '\u22c1',
+ 'xwedge;': '\u22c0',
+ 'Yacute': '\xdd',
+ 'yacute': '\xfd',
+ 'Yacute;': '\xdd',
+ 'yacute;': '\xfd',
+ 'YAcy;': '\u042f',
+ 'yacy;': '\u044f',
+ 'Ycirc;': '\u0176',
+ 'ycirc;': '\u0177',
+ 'Ycy;': '\u042b',
+ 'ycy;': '\u044b',
+ 'yen': '\xa5',
+ 'yen;': '\xa5',
+ 'Yfr;': '\U0001d51c',
+ 'yfr;': '\U0001d536',
+ 'YIcy;': '\u0407',
+ 'yicy;': '\u0457',
+ 'Yopf;': '\U0001d550',
+ 'yopf;': '\U0001d56a',
+ 'Yscr;': '\U0001d4b4',
+ 'yscr;': '\U0001d4ce',
+ 'YUcy;': '\u042e',
+ 'yucy;': '\u044e',
+ 'yuml': '\xff',
+ 'Yuml;': '\u0178',
+ 'yuml;': '\xff',
+ 'Zacute;': '\u0179',
+ 'zacute;': '\u017a',
+ 'Zcaron;': '\u017d',
+ 'zcaron;': '\u017e',
+ 'Zcy;': '\u0417',
+ 'zcy;': '\u0437',
+ 'Zdot;': '\u017b',
+ 'zdot;': '\u017c',
+ 'zeetrf;': '\u2128',
+ 'ZeroWidthSpace;': '\u200b',
+ 'Zeta;': '\u0396',
+ 'zeta;': '\u03b6',
+ 'Zfr;': '\u2128',
+ 'zfr;': '\U0001d537',
+ 'ZHcy;': '\u0416',
+ 'zhcy;': '\u0436',
+ 'zigrarr;': '\u21dd',
+ 'Zopf;': '\u2124',
+ 'zopf;': '\U0001d56b',
+ 'Zscr;': '\U0001d4b5',
+ 'zscr;': '\U0001d4cf',
+ 'zwj;': '\u200d',
+ 'zwnj;': '\u200c',
+}
+
+
class EntitySubstitution(object):
"""The ability to substitute XML or HTML entities for certain characters."""
def _populate_class_variables():
- lookup = {}
- reverse_lookup = {}
- characters_for_re = []
-
- # &apos is an XHTML entity and an HTML 5, but not an HTML 4
- # entity. We don't want to use it, but we want to recognize it on the way in.
- #
- # TODO: Ideally we would be able to recognize all HTML 5 named
- # entities, but that's a little tricky.
- extra = [(39, 'apos')]
- for codepoint, name in list(codepoint2name.items()) + extra:
- character = unichr(codepoint)
- if codepoint not in (34, 39):
- # There's no point in turning the quotation mark into
- # " or the single quote into ', unless it
- # happens within an attribute value, which is handled
- # elsewhere.
- characters_for_re.append(character)
- lookup[character] = name
- # But we do want to recognize those entities on the way in and
- # convert them to Unicode characters.
- reverse_lookup[name] = character
- re_definition = "[%s]" % "".join(characters_for_re)
- return lookup, reverse_lookup, re.compile(re_definition)
+ """Initialize variables used by this class to manage the plethora of
+ HTML5 named entities.
+
+ This function returns a 3-tuple containing two dictionaries
+ and a regular expression:
+
+ unicode_to_name - A mapping of Unicode strings like "⦨" to
+ entity names like "angmsdaa". When a single Unicode string has
+ multiple entity names, we try to choose the most commonly-used
+ name.
+
+ name_to_unicode: A mapping of entity names like "angmsdaa" to
+ Unicode strings like "⦨".
+
+ named_entity_re: A regular expression matching (almost) any
+ Unicode string that corresponds to an HTML5 named entity.
+ """
+ unicode_to_name = {}
+ name_to_unicode = {}
+
+ short_entities = set()
+ long_entities_by_first_character = defaultdict(set)
+
+ for name_with_semicolon, character in sorted(html5.items()):
+ # "It is intentional, for legacy compatibility, that many
+ # code points have multiple character reference names. For
+ # example, some appear both with and without the trailing
+ # semicolon, or with different capitalizations."
+ # - https://html.spec.whatwg.org/multipage/named-characters.html#named-character-references
+ #
+ # The parsers are in charge of handling (or not) character
+ # references with no trailing semicolon, so we remove the
+ # semicolon whenever it appears.
+ if name_with_semicolon.endswith(';'):
+ name = name_with_semicolon[:-1]
+ else:
+ name = name_with_semicolon
+
+ # When parsing HTML, we want to recognize any known named
+ # entity and convert it to a sequence of Unicode
+ # characters.
+ if name not in name_to_unicode:
+ name_to_unicode[name] = character
+
+ # When _generating_ HTML, we want to recognize special
+ # character sequences that _could_ be converted to named
+ # entities.
+ unicode_to_name[character] = name
+
+ # We also need to build a regular expression that lets us
+ # _find_ those characters in output strings so we can
+ # replace them.
+ #
+ # This is tricky, for two reasons.
+
+ if (len(character) == 1 and ord(character) < 128
+ and character not in '<>&'):
+ # First, it would be annoying to turn single ASCII
+ # characters like | into named entities like
+ # |. The exceptions are <>&, which we _must_
+ # turn into named entities to produce valid HTML.
+ continue
+
+ if len(character) > 1 and all(ord(x) < 128 for x in character):
+ # We also do not want to turn _combinations_ of ASCII
+ # characters like 'fj' into named entities like 'fj',
+ # though that's more debateable.
+ continue
+
+ # Second, some named entities have a Unicode value that's
+ # a subset of the Unicode value for some _other_ named
+ # entity. As an example, \u2267' is ≧,
+ # but '\u2267\u0338' is ≧̸. Our regular
+ # expression needs to match the first two characters of
+ # "\u2267\u0338foo", but only the first character of
+ # "\u2267foo".
+ #
+ # In this step, we build two sets of characters that
+ # _eventually_ need to go into the regular expression. But
+ # we won't know exactly what the regular expression needs
+ # to look like until we've gone through the entire list of
+ # named entities.
+ if len(character) == 1:
+ short_entities.add(character)
+ else:
+ long_entities_by_first_character[character[0]].add(character)
+
+ # Now that we've been through the entire list of entities, we
+ # can create a regular expression that matches any of them.
+ particles = set()
+ for short in short_entities:
+ long_versions = long_entities_by_first_character[short]
+ if not long_versions:
+ particles.add(short)
+ else:
+ ignore = "".join([x[1] for x in long_versions])
+ # This finds, e.g. \u2267 but only if it is _not_
+ # followed by \u0338.
+ particles.add("%s(?![%s])" % (short, ignore))
+
+ for long_entities in list(long_entities_by_first_character.values()):
+ for long_entity in long_entities:
+ particles.add(long_entity)
+
+ re_definition = "(%s)" % "|".join(particles)
+
+ # If an entity shows up in both html5 and codepoint2name, it's
+ # likely that HTML5 gives it several different names, such as
+ # 'rsquo' and 'rsquor'. When converting Unicode characters to
+ # named entities, the codepoint2name name should take
+ # precedence where possible, since that's the more easily
+ # recognizable one.
+ for codepoint, name in list(codepoint2name.items()):
+ character = chr(codepoint)
+ unicode_to_name[character] = name
+
+ return unicode_to_name, name_to_unicode, re.compile(re_definition)
(CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
@@ -113,14 +2448,14 @@
@classmethod
def _substitute_html_entity(cls, matchobj):
"""Used with a regular expression to substitute the
- appropriate HTML entity for a special character."""
+ appropriate HTML entity for a special character string."""
entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
return "&%s;" % entity
@classmethod
def _substitute_xml_entity(cls, matchobj):
"""Used with a regular expression to substitute the
- appropriate XML entity for a special character."""
+ appropriate XML entity for a special character string."""
entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
return "&%s;" % entity
@@ -228,32 +2563,65 @@
Order of precedence:
1. Encodings you specifically tell EncodingDetector to try first
- (the override_encodings argument to the constructor).
+ (the known_definite_encodings argument to the constructor).
+
+ 2. An encoding determined by sniffing the document's byte-order mark.
- 2. An encoding declared within the bytestring itself, either in an
+ 3. Encodings you specifically tell EncodingDetector to try if
+ byte-order mark sniffing fails (the user_encodings argument to the
+ constructor).
+
+ 4. An encoding declared within the bytestring itself, either in an
XML declaration (if the bytestring is to be interpreted as an XML
document), or in a tag (if the bytestring is to be
interpreted as an HTML document.)
- 3. An encoding detected through textual analysis by chardet,
+ 5. An encoding detected through textual analysis by chardet,
cchardet, or a similar external library.
4. UTF-8.
5. Windows-1252.
+
"""
- def __init__(self, markup, override_encodings=None, is_html=False,
- exclude_encodings=None):
+ def __init__(self, markup, known_definite_encodings=None,
+ is_html=False, exclude_encodings=None,
+ user_encodings=None, override_encodings=None):
"""Constructor.
:param markup: Some markup in an unknown encoding.
- :param override_encodings: These encodings will be tried first.
- :param is_html: If True, this markup is considered to be HTML. Otherwise
- it's assumed to be XML.
- :param exclude_encodings: These encodings will not be tried, even
- if they otherwise would be.
+
+ :param known_definite_encodings: When determining the encoding
+ of `markup`, these encodings will be tried first, in
+ order. In HTML terms, this corresponds to the "known
+ definite encoding" step defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#parsing-with-a-known-character-encoding
+
+ :param user_encodings: These encodings will be tried after the
+ `known_definite_encodings` have been tried and failed, and
+ after an attempt to sniff the encoding by looking at a
+ byte order mark has failed. In HTML terms, this
+ corresponds to the step "user has explicitly instructed
+ the user agent to override the document's character
+ encoding", defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
+
+ :param override_encodings: A deprecated alias for
+ known_definite_encodings. Any encodings here will be tried
+ immediately after the encodings in
+ known_definite_encodings.
+
+ :param is_html: If True, this markup is considered to be
+ HTML. Otherwise it's assumed to be XML.
+
+ :param exclude_encodings: These encodings will not be tried,
+ even if they otherwise would be.
+
"""
- self.override_encodings = override_encodings or []
+ self.known_definite_encodings = list(known_definite_encodings or [])
+ if override_encodings:
+ self.known_definite_encodings += override_encodings
+ self.user_encodings = user_encodings or []
exclude_encodings = exclude_encodings or []
self.exclude_encodings = set([x.lower() for x in exclude_encodings])
self.chardet_encoding = None
@@ -286,7 +2654,9 @@
:yield: A sequence of strings.
"""
tried = set()
- for e in self.override_encodings:
+
+ # First, try the known definite encodings
+ for e in self.known_definite_encodings:
if self._usable(e, tried):
yield e
@@ -295,6 +2665,12 @@
if self._usable(self.sniffed_encoding, tried):
yield self.sniffed_encoding
+ # Sniffing the byte-order mark did nothing; try the user
+ # encodings.
+ for e in self.user_encodings:
+ if self._usable(e, tried):
+ yield e
+
# Look within the document for an XML or HTML encoding
# declaration.
if self.declared_encoding is None:
@@ -323,7 +2699,7 @@
:return: A 2-tuple (modified data, implied encoding)
"""
encoding = None
- if isinstance(data, unicode):
+ if isinstance(data, str):
# Unicode data cannot have a byte-order mark.
return data, encoding
if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
@@ -370,7 +2746,7 @@
if isinstance(markup, bytes):
res = encoding_res[bytes]
else:
- res = encoding_res[unicode]
+ res = encoding_res[str]
xml_re = res['xml']
html_re = res['html']
@@ -405,13 +2781,33 @@
"iso-8859-2",
]
- def __init__(self, markup, override_encodings=[],
- smart_quotes_to=None, is_html=False, exclude_encodings=[]):
+ def __init__(self, markup, known_definite_encodings=[],
+ smart_quotes_to=None, is_html=False, exclude_encodings=[],
+ user_encodings=None, override_encodings=None
+ ):
"""Constructor.
:param markup: A bytestring representing markup in an unknown encoding.
- :param override_encodings: These encodings will be tried first,
- before any sniffing code is run.
+
+ :param known_definite_encodings: When determining the encoding
+ of `markup`, these encodings will be tried first, in
+ order. In HTML terms, this corresponds to the "known
+ definite encoding" step defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#parsing-with-a-known-character-encoding
+
+ :param user_encodings: These encodings will be tried after the
+ `known_definite_encodings` have been tried and failed, and
+ after an attempt to sniff the encoding by looking at a
+ byte order mark has failed. In HTML terms, this
+ corresponds to the step "user has explicitly instructed
+ the user agent to override the document's character
+ encoding", defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
+
+ :param override_encodings: A deprecated alias for
+ known_definite_encodings. Any encodings here will be tried
+ immediately after the encodings in
+ known_definite_encodings.
:param smart_quotes_to: By default, Microsoft smart quotes will, like all other characters, be converted
to Unicode characters. Setting this to 'ascii' will convert them to ASCII quotes instead.
@@ -421,6 +2817,7 @@
it's assumed to be XML.
:param exclude_encodings: These encodings will not be considered, even
if the sniffing code thinks they might make sense.
+
"""
self.smart_quotes_to = smart_quotes_to
self.tried_encodings = []
@@ -428,12 +2825,14 @@
self.is_html = is_html
self.log = logging.getLogger(__name__)
self.detector = EncodingDetector(
- markup, override_encodings, is_html, exclude_encodings)
+ markup, known_definite_encodings, is_html, exclude_encodings,
+ user_encodings, override_encodings
+ )
# Short-circuit if the data is in Unicode to begin with.
- if isinstance(markup, unicode) or markup == '':
+ if isinstance(markup, str) or markup == '':
self.markup = markup
- self.unicode_markup = unicode(markup)
+ self.unicode_markup = str(markup)
self.original_encoding = None
return
@@ -523,7 +2922,7 @@
:param encoding: The name of an encoding.
"""
- return unicode(data, encoding, errors)
+ return str(data, encoding, errors)
@property
def declared_html_encoding(self):
diff -Nru beautifulsoup4-4.9.3/bs4/diagnose.py beautifulsoup4-4.10.0/bs4/diagnose.py
--- beautifulsoup4-4.9.3/bs4/diagnose.py 2020-05-17 17:55:43.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/diagnose.py 2021-09-07 23:36:46.000000000 +0000
@@ -4,8 +4,8 @@
__license__ = "MIT"
import cProfile
-from StringIO import StringIO
-from HTMLParser import HTMLParser
+from io import StringIO
+from html.parser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
@@ -25,8 +25,8 @@
:param data: A string containing markup that needs to be explained.
:return: None; diagnostics are printed to standard output.
"""
- print("Diagnostic running on Beautiful Soup %s" % __version__)
- print("Python version %s" % sys.version)
+ print(("Diagnostic running on Beautiful Soup %s" % __version__))
+ print(("Python version %s" % sys.version))
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
@@ -35,16 +35,16 @@
break
else:
basic_parsers.remove(name)
- print(
+ print((
"I noticed that %s is not installed. Installing it may help." %
- name)
+ name))
if 'lxml' in basic_parsers:
basic_parsers.append("lxml-xml")
try:
from lxml import etree
- print("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION)))
- except ImportError, e:
+ print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
+ except ImportError as e:
print(
"lxml is not installed or couldn't be imported.")
@@ -52,21 +52,21 @@
if 'html5lib' in basic_parsers:
try:
import html5lib
- print("Found html5lib version %s" % html5lib.__version__)
- except ImportError, e:
+ print(("Found html5lib version %s" % html5lib.__version__))
+ except ImportError as e:
print(
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif data.startswith("http:") or data.startswith("https:"):
- print('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data)
+ print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
else:
try:
if os.path.exists(data):
- print('"%s" looks like a filename. Reading data from the file.' % data)
+ print(('"%s" looks like a filename. Reading data from the file.' % data))
with open(data) as fp:
data = fp.read()
except ValueError:
@@ -76,19 +76,19 @@
print("")
for parser in basic_parsers:
- print("Trying to parse your markup with %s" % parser)
+ print(("Trying to parse your markup with %s" % parser))
success = False
try:
soup = BeautifulSoup(data, features=parser)
success = True
- except Exception, e:
- print("%s could not parse the markup." % parser)
+ except Exception as e:
+ print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
- print("Here's what %s did with the markup:" % parser)
- print(soup.prettify())
+ print(("Here's what %s did with the markup:" % parser))
+ print((soup.prettify()))
- print("-" * 80)
+ print(("-" * 80))
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
@@ -104,7 +104,7 @@
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
- print("%s, %4s, %s" % (event, element.tag, element.text))
+ print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Subclass of HTMLParser that announces parse events, without doing
@@ -193,9 +193,9 @@
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
- print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
+ print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
data = rdoc(num_elements)
- print("Generated a large invalid HTML document (%d bytes)." % len(data))
+ print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
@@ -204,24 +204,24 @@
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
- except Exception, e:
- print("%s could not parse the markup." % parser)
+ except Exception as e:
+ print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
- print("BS4+%s parsed the markup in %.2fs." % (parser, b-a))
+ print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
- print("Raw lxml parsed the markup in %.2fs." % (b-a))
+ print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
- print("Raw html5lib parsed the markup in %.2fs." % (b-a))
+ print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
def profile(num_elements=100000, parser="lxml"):
"""Use Python's profiler on a randomly generated document."""
diff -Nru beautifulsoup4-4.9.3/bs4/element.py beautifulsoup4-4.10.0/bs4/element.py
--- beautifulsoup4-4.9.3/bs4/element.py 2020-10-02 22:19:12.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/element.py 2021-09-07 23:36:46.000000000 +0000
@@ -3,14 +3,14 @@
try:
from collections.abc import Callable # Python 3.6
-except ImportError , e:
+except ImportError as e:
from collections import Callable
import re
import sys
import warnings
try:
import soupsieve
-except ImportError, e:
+except ImportError as e:
soupsieve = None
warnings.warn(
'The soupsieve package is not installed. CSS selectors cannot be used.'
@@ -57,22 +57,22 @@
# Source:
# https://docs.python.org/3/library/codecs.html#python-specific-encodings
PYTHON_SPECIFIC_ENCODINGS = set([
- u"idna",
- u"mbcs",
- u"oem",
- u"palmos",
- u"punycode",
- u"raw_unicode_escape",
- u"undefined",
- u"unicode_escape",
- u"raw-unicode-escape",
- u"unicode-escape",
- u"string-escape",
- u"string_escape",
+ "idna",
+ "mbcs",
+ "oem",
+ "palmos",
+ "punycode",
+ "raw_unicode_escape",
+ "undefined",
+ "unicode_escape",
+ "raw-unicode-escape",
+ "unicode-escape",
+ "string-escape",
+ "string_escape",
])
-class NamespacedAttribute(unicode):
+class NamespacedAttribute(str):
"""A namespaced string (e.g. 'xml:lang') that remembers the namespace
('xml') and the name ('lang') that were used to create it.
"""
@@ -83,19 +83,19 @@
# per https://www.w3.org/TR/xml-names/#defaulting
name = None
- if name is None:
- obj = unicode.__new__(cls, prefix)
- elif prefix is None:
+ if not name:
+ obj = str.__new__(cls, prefix)
+ elif not prefix:
# Not really namespaced.
- obj = unicode.__new__(cls, name)
+ obj = str.__new__(cls, name)
else:
- obj = unicode.__new__(cls, prefix + ":" + name)
+ obj = str.__new__(cls, prefix + ":" + name)
obj.prefix = prefix
obj.name = name
obj.namespace = namespace
return obj
-class AttributeValueWithCharsetSubstitution(unicode):
+class AttributeValueWithCharsetSubstitution(str):
"""A stand-in object for a character encoding specified in HTML."""
class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution):
@@ -106,7 +106,7 @@
"""
def __new__(cls, original_value):
- obj = unicode.__new__(cls, original_value)
+ obj = str.__new__(cls, original_value)
obj.original_value = original_value
return obj
@@ -134,9 +134,9 @@
match = cls.CHARSET_RE.search(original_value)
if match is None:
# No substitution necessary.
- return unicode.__new__(unicode, original_value)
+ return str.__new__(str, original_value)
- obj = unicode.__new__(cls, original_value)
+ obj = str.__new__(cls, original_value)
obj.original_value = original_value
return obj
@@ -255,25 +255,67 @@
nextSibling = _alias("next_sibling") # BS3
previousSibling = _alias("previous_sibling") # BS3
- def replace_with(self, replace_with):
- """Replace this PageElement with another one, keeping the rest of the
- tree the same.
+ default = object()
+ def _all_strings(self, strip=False, types=default):
+ """Yield all strings of certain classes, possibly stripping them.
+
+ This is implemented differently in Tag and NavigableString.
+ """
+ raise NotImplementedError()
+
+ @property
+ def stripped_strings(self):
+ """Yield all strings in this PageElement, stripping them first.
+
+ :yield: A sequence of stripped strings.
+ """
+ for string in self._all_strings(True):
+ yield string
+
+ def get_text(self, separator="", strip=False,
+ types=default):
+ """Get all child strings of this PageElement, concatenated using the
+ given separator.
+
+ :param separator: Strings will be concatenated using this separator.
+
+ :param strip: If True, strings will be stripped before being
+ concatenated.
+
+ :param types: A tuple of NavigableString subclasses. Any
+ strings of a subclass not found in this list will be
+ ignored. Although there are exceptions, the default
+ behavior in most cases is to consider only NavigableString
+ and CData objects. That means no comments, processing
+ instructions, etc.
+
+ :return: A string.
+ """
+ return separator.join([s for s in self._all_strings(
+ strip, types=types)])
+ getText = get_text
+ text = property(get_text)
+
+ def replace_with(self, *args):
+ """Replace this PageElement with one or more PageElements, keeping the
+ rest of the tree the same.
- :param replace_with: A PageElement.
+ :param args: One or more PageElements.
:return: `self`, no longer part of the tree.
"""
if self.parent is None:
raise ValueError(
"Cannot replace one element with another when the "
"element to be replaced is not part of a tree.")
- if replace_with is self:
+ if len(args) == 1 and args[0] is self:
return
- if replace_with is self.parent:
+ if any(x is self.parent for x in args):
raise ValueError("Cannot replace a Tag with its parent.")
old_parent = self.parent
my_index = self.parent.index(self)
self.extract(_self_index=my_index)
- old_parent.insert(my_index, replace_with)
+ for idx, replace_with in enumerate(args, start=my_index):
+ old_parent.insert(idx, replace_with)
return self
replaceWith = replace_with # BS3
@@ -376,7 +418,7 @@
raise ValueError("Cannot insert None into a tag.")
if new_child is self:
raise ValueError("Cannot insert a tag into itself.")
- if (isinstance(new_child, basestring)
+ if (isinstance(new_child, str)
and not isinstance(new_child, NavigableString)):
new_child = NavigableString(new_child)
@@ -753,7 +795,7 @@
result = (element for element in generator
if isinstance(element, Tag))
return ResultSet(strainer, result)
- elif isinstance(name, basestring):
+ elif isinstance(name, str):
# Optimization to find all tags with a given name.
if name.count(':') == 1:
# This is a name with a prefix. If this is a namespace-aware document,
@@ -872,7 +914,7 @@
return self.parents
-class NavigableString(unicode, PageElement):
+class NavigableString(str, PageElement):
"""A Python Unicode string that is part of a parse tree.
When Beautiful Soup parses the markup penguin, it will
@@ -895,10 +937,10 @@
passed in to the superclass's __new__ or the superclass won't know
how to handle non-ASCII characters.
"""
- if isinstance(value, unicode):
- u = unicode.__new__(cls, value)
+ if isinstance(value, str):
+ u = str.__new__(cls, value)
else:
- u = unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
+ u = str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
u.setup()
return u
@@ -909,7 +951,7 @@
return type(self)(self)
def __getnewargs__(self):
- return (unicode(self),)
+ return (str(self),)
def __getattr__(self, attr):
"""text.string gives you text. This is for backwards
@@ -945,7 +987,49 @@
"""Prevent NavigableString.name from ever being set."""
raise AttributeError("A NavigableString cannot be given a name.")
-
+ def _all_strings(self, strip=False, types=PageElement.default):
+ """Yield all strings of certain classes, possibly stripping them.
+
+ This makes it easy for NavigableString to implement methods
+ like get_text() as conveniences, creating a consistent
+ text-extraction API across all PageElements.
+
+ :param strip: If True, all strings will be stripped before being
+ yielded.
+
+ :param types: A tuple of NavigableString subclasses. If this
+ NavigableString isn't one of those subclasses, the
+ sequence will be empty. By default, the subclasses
+ considered are NavigableString and CData objects. That
+ means no comments, processing instructions, etc.
+
+ :yield: A sequence that either contains this string, or is empty.
+
+ """
+ if types is self.default:
+ # This is kept in Tag because it's full of subclasses of
+ # this class, which aren't defined until later in the file.
+ types = Tag.DEFAULT_INTERESTING_STRING_TYPES
+
+ # Do nothing if the caller is looking for specific types of
+ # string, and we're of a different type.
+ my_type = type(self)
+ if types is not None:
+ if isinstance(types, type):
+ # Looking for a single type.
+ if my_type is not types:
+ return
+ elif my_type not in types:
+ # Looking for one of a list of types.
+ return
+
+ value = self
+ if strip:
+ value = value.strip()
+ if len(value) > 0:
+ yield value
+ strings = property(_all_strings)
+
class PreformattedString(NavigableString):
"""A NavigableString not subject to the normal formatting rules.
@@ -975,30 +1059,30 @@
class CData(PreformattedString):
"""A CDATA block."""
- PREFIX = u''
+ PREFIX = ''
class ProcessingInstruction(PreformattedString):
"""A SGML processing instruction."""
- PREFIX = u''
+ PREFIX = ''
class XMLProcessingInstruction(ProcessingInstruction):
"""An XML processing instruction."""
- PREFIX = u''
+ PREFIX = ''
class Comment(PreformattedString):
"""An HTML or XML comment."""
- PREFIX = u''
+ PREFIX = ''
class Declaration(PreformattedString):
"""An XML declaration."""
- PREFIX = u''
+ PREFIX = ''
class Doctype(PreformattedString):
@@ -1026,8 +1110,8 @@
return Doctype(value)
- PREFIX = u'\n'
+ PREFIX = '\n'
class Stylesheet(NavigableString):
@@ -1069,7 +1153,8 @@
prefix=None, attrs=None, parent=None, previous=None,
is_xml=None, sourceline=None, sourcepos=None,
can_be_empty_element=None, cdata_list_attributes=None,
- preserve_whitespace_tags=None
+ preserve_whitespace_tags=None,
+ interesting_string_types=None,
):
"""Basic constructor.
@@ -1095,6 +1180,13 @@
be treated as CDATA if they ever show up on this tag.
:param preserve_whitespace_tags: A list of tag names whose contents
should have their whitespace preserved.
+ :param interesting_string_types: This is a NavigableString
+ subclass or a tuple of them. When iterating over this
+ Tag's strings in methods like Tag.strings or Tag.get_text,
+ these are the types of strings that are interesting enough
+ to be considered. The default is to consider
+ NavigableString and CData the only interesting string
+ subtypes.
"""
if parser is None:
self.parser_class = None
@@ -1140,6 +1232,7 @@
self.can_be_empty_element = can_be_empty_element
self.cdata_list_attributes = cdata_list_attributes
self.preserve_whitespace_tags = preserve_whitespace_tags
+ self.interesting_string_types = interesting_string_types
else:
# Set up any substitutions for this tag, such as the charset in a META tag.
builder.set_up_substitutions(self)
@@ -1160,6 +1253,13 @@
# Keep track of the names that might cause this tag to be treated as a
# whitespace-preserved tag.
self.preserve_whitespace_tags = builder.preserve_whitespace_tags
+
+ if self.name in builder.string_containers:
+ # This sort of tag uses a special string container
+ # subclass for most of its strings. When we ask the
+ self.interesting_string_types = builder.string_containers[self.name]
+ else:
+ self.interesting_string_types = self.DEFAULT_INTERESTING_STRING_TYPES
parserClass = _alias("parser_class") # BS3
@@ -1226,65 +1326,45 @@
self.clear()
self.append(string.__class__(string))
- def _all_strings(self, strip=False, types=(NavigableString, CData)):
+ DEFAULT_INTERESTING_STRING_TYPES = (NavigableString, CData)
+ def _all_strings(self, strip=False, types=PageElement.default):
"""Yield all strings of certain classes, possibly stripping them.
:param strip: If True, all strings will be stripped before being
yielded.
- :types: A tuple of NavigableString subclasses. Any strings of
+ :param types: A tuple of NavigableString subclasses. Any strings of
a subclass not found in this list will be ignored. By
- default, this means only NavigableString and CData objects
- will be considered. So no comments, processing instructions,
- etc.
+ default, the subclasses considered are the ones found in
+ self.interesting_string_types. If that's not specified,
+ only NavigableString and CData objects will be
+ considered. That means no comments, processing
+ instructions, etc.
:yield: A sequence of strings.
+
"""
+ if types is self.default:
+ types = self.interesting_string_types
+
for descendant in self.descendants:
- if (
- (types is None and not isinstance(descendant, NavigableString))
- or
- (types is not None and type(descendant) not in types)):
+ if (types is None and not isinstance(descendant, NavigableString)):
+ continue
+ descendant_type = type(descendant)
+ if isinstance(types, type):
+ if descendant_type is not types:
+ # We're not interested in strings of this type.
+ continue
+ elif types is not None and descendant_type not in types:
+ # We're not interested in strings of this type.
continue
if strip:
descendant = descendant.strip()
if len(descendant) == 0:
continue
yield descendant
-
strings = property(_all_strings)
- @property
- def stripped_strings(self):
- """Yield all strings in the document, stripping them first.
-
- :yield: A sequence of stripped strings.
- """
- for string in self._all_strings(True):
- yield string
-
- def get_text(self, separator=u"", strip=False,
- types=(NavigableString, CData)):
- """Get all child strings, concatenated using the given separator.
-
- :param separator: Strings will be concatenated using this separator.
-
- :param strip: If True, strings will be stripped before being
- concatenated.
-
- :types: A tuple of NavigableString subclasses. Any strings of
- a subclass not found in this list will be ignored. By
- default, this means only NavigableString and CData objects
- will be considered. So no comments, processing instructions,
- stylesheets, etc.
-
- :return: A string.
- """
- return separator.join([s for s in self._all_strings(
- strip, types=types)])
- getText = get_text
- text = property(get_text)
-
def decompose(self):
"""Recursively destroys this PageElement and its children.
@@ -1416,7 +1496,7 @@
def __contains__(self, x):
return x in self.contents
- def __nonzero__(self):
+ def __bool__(self):
"A tag is non-None even if it has no contents."
return True
@@ -1565,8 +1645,8 @@
else:
if isinstance(val, list) or isinstance(val, tuple):
val = ' '.join(val)
- elif not isinstance(val, basestring):
- val = unicode(val)
+ elif not isinstance(val, str):
+ val = str(val)
elif (
isinstance(val, AttributeValueWithCharsetSubstitution)
and eventual_encoding is not None
@@ -1575,7 +1655,7 @@
text = formatter.attribute_value(val)
decoded = (
- unicode(key) + '='
+ str(key) + '='
+ formatter.quoted_attribute_value(text))
attrs.append(decoded)
close = ''
@@ -1934,7 +2014,7 @@
else:
attrs = kwargs
normalized_attrs = {}
- for key, value in attrs.items():
+ for key, value in list(attrs.items()):
normalized_attrs[key] = self._normalize_search_value(value)
self.attrs = normalized_attrs
@@ -1943,7 +2023,7 @@
def _normalize_search_value(self, value):
# Leave it alone if it's a Unicode string, a callable, a
# regular expression, a boolean, or None.
- if (isinstance(value, unicode) or isinstance(value, Callable) or hasattr(value, 'match')
+ if (isinstance(value, str) or isinstance(value, Callable) or hasattr(value, 'match')
or isinstance(value, bool) or value is None):
return value
@@ -1956,7 +2036,7 @@
new_value = []
for v in value:
if (hasattr(v, '__iter__') and not isinstance(v, bytes)
- and not isinstance(v, unicode)):
+ and not isinstance(v, str)):
# This is almost certainly the user's mistake. In the
# interests of avoiding infinite loops, we'll let
# it through as-is rather than doing a recursive call.
@@ -1968,7 +2048,7 @@
# Otherwise, convert it into a Unicode string.
# The unicode(str()) thing is so this will do the same thing on Python 2
# and Python 3.
- return unicode(str(value))
+ return str(str(value))
def __str__(self):
"""A human-readable representation of this SoupStrainer."""
@@ -1996,7 +2076,7 @@
markup = markup_name
markup_attrs = markup
- if isinstance(self.name, basestring):
+ if isinstance(self.name, str):
# Optimization for a very common case where the user is
# searching for a tag with one specific name, and we're
# looking at a tag with a different name.
@@ -2052,7 +2132,7 @@
found = None
# If given a list of items, scan it for a text element that
# matches.
- if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, basestring)):
+ if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, str)):
for element in markup:
if isinstance(element, NavigableString) \
and self.search(element):
@@ -2065,7 +2145,7 @@
found = self.search_tag(markup)
# If it's text, make sure the text matches.
elif isinstance(markup, NavigableString) or \
- isinstance(markup, basestring):
+ isinstance(markup, str):
if not self.name and not self.attrs and self._matches(markup, self.text):
found = markup
else:
@@ -2110,7 +2190,7 @@
return not match_against
if (hasattr(match_against, '__iter__')
- and not isinstance(match_against, basestring)):
+ and not isinstance(match_against, str)):
# We're asked to match against an iterable of items.
# The markup must be match at least one item in the
# iterable. We'll try each one in turn.
@@ -2137,7 +2217,7 @@
# the tag's name and once against its prefixed name.
match = False
- if not match and isinstance(match_against, unicode):
+ if not match and isinstance(match_against, str):
# Exact string match
match = markup == match_against
diff -Nru beautifulsoup4-4.9.3/bs4/formatter.py beautifulsoup4-4.10.0/bs4/formatter.py
--- beautifulsoup4-4.9.3/bs4/formatter.py 2019-12-29 15:48:17.000000000 +0000
+++ beautifulsoup4-4.10.0/bs4/formatter.py 2021-09-07 23:36:46.000000000 +0000
@@ -14,7 +14,8 @@
For HTML documents:
* 'html' - HTML entity substitution for generic HTML documents. (default)
- * 'html5' - HTML entity substitution for HTML5 documents.
+ * 'html5' - HTML entity substitution for HTML5 documents, as
+ well as some optimizations in the way tags are rendered.
* 'minimal' - Only make the substitutions necessary to guarantee
valid HTML.
* None - Do not perform any substitution. This will be faster
@@ -48,6 +49,7 @@
def __init__(
self, language=None, entity_substitution=None,
void_element_close_prefix='/', cdata_containing_tags=None,
+ empty_attributes_are_booleans=False,
):
"""Constructor.
@@ -64,6 +66,9 @@
as containing CDATA in this dialect. For example, in HTML,