From 3c50ea4303ad58785e7f5058cdd353c6d0140ee4 Mon Sep 17 00:00:00 2001 From: Fred Drake Date: Sat, 17 May 2008 22:02:32 +0000 Subject: rename HTMLParser to html.parser and htmlentitydefs to html.entities; includes merge of trunk revision 63432 --- Doc/library/htmllib.rst | 10 +- Doc/library/htmlparser.rst | 14 +- Lib/HTMLParser.py | 387 ------------------------------- Lib/html/__init__.py | 1 + Lib/html/entities.py | 270 ++++++++++++++++++++++ Lib/html/parser.py | 388 ++++++++++++++++++++++++++++++++ Lib/htmlentitydefs.py | 270 ---------------------- Lib/htmllib.py | 2 +- Lib/test/test_codeccallbacks.py | 4 +- Lib/test/test_multibytecodec_support.py | 2 +- Lib/test/test_sundry.py | 2 +- 11 files changed, 676 insertions(+), 674 deletions(-) delete mode 100644 Lib/HTMLParser.py create mode 100644 Lib/html/__init__.py create mode 100644 Lib/html/entities.py create mode 100644 Lib/html/parser.py delete mode 100644 Lib/htmlentitydefs.py diff --git a/Doc/library/htmllib.rst b/Doc/library/htmllib.rst index e1f2447..34423a0 100644 --- a/Doc/library/htmllib.rst +++ b/Doc/library/htmllib.rst @@ -75,12 +75,12 @@ The module defines a parser class and an exception: Interface definition for transforming an abstract flow of formatting events into specific output events on writer objects. - Module :mod:`HTMLParser` + Module :mod:`html.parser` Alternate HTML parser that offers a slightly lower-level view of the input, but is designed to work with XHTML, and does not implement some of the SGML syntax not used in "HTML as deployed" and which isn't legal for XHTML. - Module :mod:`htmlentitydefs` + Module :mod:`html.entities` Definition of replacement text for XHTML 1.0 entities. Module :mod:`sgmllib` @@ -147,10 +147,10 @@ additional methods and instance variables for use within tag methods. :meth:`save_bgn` will raise a :exc:`TypeError` exception. -:mod:`htmlentitydefs` --- Definitions of HTML general entities -============================================================== +:mod:`html.entities` --- Definitions of HTML general entities +============================================================= -.. module:: htmlentitydefs +.. module:: html.entities :synopsis: Definitions of HTML general entities. .. sectionauthor:: Fred L. Drake, Jr. diff --git a/Doc/library/htmlparser.rst b/Doc/library/htmlparser.rst index 5cfe04e..4bfb287 100644 --- a/Doc/library/htmlparser.rst +++ b/Doc/library/htmlparser.rst @@ -1,8 +1,8 @@ -:mod:`HTMLParser` --- Simple HTML and XHTML parser -================================================== +:mod:`html.parser` --- Simple HTML and XHTML parser +=================================================== -.. module:: HTMLParser +.. module:: html.parser :synopsis: A simple parser that can handle HTML and XHTML. @@ -18,7 +18,7 @@ in :mod:`sgmllib`. The :class:`HTMLParser` class is instantiated without arguments. - An HTMLParser instance is fed HTML data and calls handler functions when tags + An :class:`HTMLParser` instance is fed HTML data and calls handler functions when tags begin and end. The :class:`HTMLParser` class is meant to be overridden by the user to provide a desired behavior. @@ -87,8 +87,8 @@ An exception is defined as well: HREF="http://www.cwi.nl/">``, this method would be called as ``handle_starttag('a', [('href', 'http://www.cwi.nl/')])``. - All entity references from htmlentitydefs are replaced in the attribute - values. + All entity references from :mod:`html.entities` are replaced in the + attribute values. .. method:: HTMLParser.handle_startendtag(tag, attrs) @@ -166,7 +166,7 @@ Example HTML Parser Application As a basic example, below is a very basic HTML parser that uses the :class:`HTMLParser` class to print out tags as they are encountered:: - from HTMLParser import HTMLParser + from html.parser import HTMLParser class MyHTMLParser(HTMLParser): diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py deleted file mode 100644 index 9979195..0000000 --- a/Lib/HTMLParser.py +++ /dev/null @@ -1,387 +0,0 @@ -"""A parser for HTML and XHTML.""" - -# This file is based on sgmllib.py, but the API is slightly different. - -# XXX There should be a way to distinguish between PCDATA (parsed -# character data -- the normal case), RCDATA (replaceable character -# data -- only char and entity references and end tags are special) -# and CDATA (character data -- only end tags are special). - - -import _markupbase -import re - -# Regular expressions used for parsing - -interesting_normal = re.compile('[&<]') -interesting_cdata = re.compile(r'<(/|\Z)') -incomplete = re.compile('&[a-zA-Z#]') - -entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') -charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]') - -starttagopen = re.compile('<[a-zA-Z]') -piclose = re.compile('>') -commentclose = re.compile(r'--\s*>') -tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') -attrfind = re.compile( - r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' - r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?') - -locatestarttagend = re.compile(r""" - <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name - (?:\s+ # whitespace before attribute name - (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name - (?:\s*=\s* # value indicator - (?:'[^']*' # LITA-enclosed value - |\"[^\"]*\" # LIT-enclosed value - |[^'\">\s]+ # bare value - ) - )? - ) - )* - \s* # trailing whitespace -""", re.VERBOSE) -endendtag = re.compile('>') -endtagfind = re.compile('') - - -class HTMLParseError(Exception): - """Exception raised for all parse errors.""" - - def __init__(self, msg, position=(None, None)): - assert msg - self.msg = msg - self.lineno = position[0] - self.offset = position[1] - - def __str__(self): - result = self.msg - if self.lineno is not None: - result = result + ", at line %d" % self.lineno - if self.offset is not None: - result = result + ", column %d" % (self.offset + 1) - return result - - -class HTMLParser(_markupbase.ParserBase): - """Find tags and other markup and call handler functions. - - Usage: - p = HTMLParser() - p.feed(data) - ... - p.close() - - Start tags are handled by calling self.handle_starttag() or - self.handle_startendtag(); end tags by self.handle_endtag(). The - data between tags is passed from the parser to the derived class - by calling self.handle_data() with the data as argument (the data - may be split up in arbitrary chunks). Entity references are - passed by calling self.handle_entityref() with the entity - reference as the argument. Numeric character references are - passed to self.handle_charref() with the string containing the - reference as the argument. - """ - - CDATA_CONTENT_ELEMENTS = ("script", "style") - - - def __init__(self): - """Initialize and reset this instance.""" - self.reset() - - def reset(self): - """Reset this instance. Loses all unprocessed data.""" - self.rawdata = '' - self.lasttag = '???' - self.interesting = interesting_normal - _markupbase.ParserBase.reset(self) - - def feed(self, data): - """Feed data to the parser. - - Call this as often as you want, with as little or as much text - as you want (may include '\n'). - """ - self.rawdata = self.rawdata + data - self.goahead(0) - - def close(self): - """Handle any buffered data.""" - self.goahead(1) - - def error(self, message): - raise HTMLParseError(message, self.getpos()) - - __starttag_text = None - - def get_starttag_text(self): - """Return full source of start tag: '<...>'.""" - return self.__starttag_text - - def set_cdata_mode(self): - self.interesting = interesting_cdata - - def clear_cdata_mode(self): - self.interesting = interesting_normal - - # Internal -- handle data as far as reasonable. May leave state - # and data to be processed by a subsequent call. If 'end' is - # true, force handling all data as if followed by EOF marker. - def goahead(self, end): - rawdata = self.rawdata - i = 0 - n = len(rawdata) - while i < n: - match = self.interesting.search(rawdata, i) # < or & - if match: - j = match.start() - else: - j = n - if i < j: self.handle_data(rawdata[i:j]) - i = self.updatepos(i, j) - if i == n: break - startswith = rawdata.startswith - if startswith('<', i): - if starttagopen.match(rawdata, i): # < + letter - k = self.parse_starttag(i) - elif startswith(" - if not match: - return -1 - j = match.start() - self.handle_pi(rawdata[i+2: j]) - j = match.end() - return j - - # Internal -- handle starttag, return end or -1 if not terminated - def parse_starttag(self, i): - self.__starttag_text = None - endpos = self.check_for_whole_start_tag(i) - if endpos < 0: - return endpos - rawdata = self.rawdata - self.__starttag_text = rawdata[i:endpos] - - # Now parse the data between i+1 and j into a tag and attrs - attrs = [] - match = tagfind.match(rawdata, i+1) - assert match, 'unexpected call to parse_starttag()' - k = match.end() - self.lasttag = tag = rawdata[i+1:k].lower() - - while k < endpos: - m = attrfind.match(rawdata, k) - if not m: - break - attrname, rest, attrvalue = m.group(1, 2, 3) - if not rest: - attrvalue = None - elif attrvalue[:1] == '\'' == attrvalue[-1:] or \ - attrvalue[:1] == '"' == attrvalue[-1:]: - attrvalue = attrvalue[1:-1] - attrvalue = self.unescape(attrvalue) - attrs.append((attrname.lower(), attrvalue)) - k = m.end() - - end = rawdata[k:endpos].strip() - if end not in (">", "/>"): - lineno, offset = self.getpos() - if "\n" in self.__starttag_text: - lineno = lineno + self.__starttag_text.count("\n") - offset = len(self.__starttag_text) \ - - self.__starttag_text.rfind("\n") - else: - offset = offset + len(self.__starttag_text) - self.error("junk characters in start tag: %r" - % (rawdata[k:endpos][:20],)) - if end.endswith('/>'): - # XHTML-style empty tag: - self.handle_startendtag(tag, attrs) - else: - self.handle_starttag(tag, attrs) - if tag in self.CDATA_CONTENT_ELEMENTS: - self.set_cdata_mode() - return endpos - - # Internal -- check to see if we have a complete starttag; return end - # or -1 if incomplete. - def check_for_whole_start_tag(self, i): - rawdata = self.rawdata - m = locatestarttagend.match(rawdata, i) - if m: - j = m.end() - next = rawdata[j:j+1] - if next == ">": - return j + 1 - if next == "/": - if rawdata.startswith("/>", j): - return j + 2 - if rawdata.startswith("/", j): - # buffer boundary - return -1 - # else bogus input - self.updatepos(i, j + 1) - self.error("malformed empty start tag") - if next == "": - # end of input - return -1 - if next in ("abcdefghijklmnopqrstuvwxyz=/" - "ABCDEFGHIJKLMNOPQRSTUVWXYZ"): - # end of input in or before attribute value, or we have the - # '/' from a '/>' ending - return -1 - self.updatepos(i, j) - self.error("malformed start tag") - raise AssertionError("we should not get here!") - - # Internal -- parse endtag, return end or -1 if incomplete - def parse_endtag(self, i): - rawdata = self.rawdata - assert rawdata[i:i+2] == " - if not match: - return -1 - j = match.end() - match = endtagfind.match(rawdata, i) # - if not match: - self.error("bad end tag: %r" % (rawdata[i:j],)) - tag = match.group(1) - self.handle_endtag(tag.lower()) - self.clear_cdata_mode() - return j - - # Overridable -- finish processing of start+end tag: - def handle_startendtag(self, tag, attrs): - self.handle_starttag(tag, attrs) - self.handle_endtag(tag) - - # Overridable -- handle start tag - def handle_starttag(self, tag, attrs): - pass - - # Overridable -- handle end tag - def handle_endtag(self, tag): - pass - - # Overridable -- handle character reference - def handle_charref(self, name): - pass - - # Overridable -- handle entity reference - def handle_entityref(self, name): - pass - - # Overridable -- handle data - def handle_data(self, data): - pass - - # Overridable -- handle comment - def handle_comment(self, data): - pass - - # Overridable -- handle declaration - def handle_decl(self, decl): - pass - - # Overridable -- handle processing instruction - def handle_pi(self, data): - pass - - def unknown_decl(self, data): - self.error("unknown declaration: %r" % (data,)) - - # Internal -- helper to remove special character quoting - entitydefs = None - def unescape(self, s): - if '&' not in s: - return s - def replaceEntities(s): - s = s.groups()[0] - if s[0] == "#": - s = s[1:] - if s[0] in ['x','X']: - c = int(s[1:], 16) - else: - c = int(s) - return chr(c) - else: - # Cannot use name2codepoint directly, because HTMLParser supports apos, - # which is not part of HTML 4 - import htmlentitydefs - if HTMLParser.entitydefs is None: - entitydefs = HTMLParser.entitydefs = {'apos':"'"} - for k, v in htmlentitydefs.name2codepoint.items(): - entitydefs[k] = chr(v) - try: - return self.entitydefs[s] - except KeyError: - return '&'+s+';' - - return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s) diff --git a/Lib/html/__init__.py b/Lib/html/__init__.py new file mode 100644 index 0000000..196d378 --- /dev/null +++ b/Lib/html/__init__.py @@ -0,0 +1 @@ +# This directory is a Python package. diff --git a/Lib/html/entities.py b/Lib/html/entities.py new file mode 100644 index 0000000..e2b7bf1 --- /dev/null +++ b/Lib/html/entities.py @@ -0,0 +1,270 @@ +"""HTML character entity references.""" + +# maps the HTML entity name to the Unicode codepoint +name2codepoint = { + 'AElig': 0x00c6, # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1 + 'Aacute': 0x00c1, # latin capital letter A with acute, U+00C1 ISOlat1 + 'Acirc': 0x00c2, # latin capital letter A with circumflex, U+00C2 ISOlat1 + 'Agrave': 0x00c0, # latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1 + 'Alpha': 0x0391, # greek capital letter alpha, U+0391 + 'Aring': 0x00c5, # latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1 + 'Atilde': 0x00c3, # latin capital letter A with tilde, U+00C3 ISOlat1 + 'Auml': 0x00c4, # latin capital letter A with diaeresis, U+00C4 ISOlat1 + 'Beta': 0x0392, # greek capital letter beta, U+0392 + 'Ccedil': 0x00c7, # latin capital letter C with cedilla, U+00C7 ISOlat1 + 'Chi': 0x03a7, # greek capital letter chi, U+03A7 + 'Dagger': 0x2021, # double dagger, U+2021 ISOpub + 'Delta': 0x0394, # greek capital letter delta, U+0394 ISOgrk3 + 'ETH': 0x00d0, # latin capital letter ETH, U+00D0 ISOlat1 + 'Eacute': 0x00c9, # latin capital letter E with acute, U+00C9 ISOlat1 + 'Ecirc': 0x00ca, # latin capital letter E with circumflex, U+00CA ISOlat1 + 'Egrave': 0x00c8, # latin capital letter E with grave, U+00C8 ISOlat1 + 'Epsilon': 0x0395, # greek capital letter epsilon, U+0395 + 'Eta': 0x0397, # greek capital letter eta, U+0397 + 'Euml': 0x00cb, # latin capital letter E with diaeresis, U+00CB ISOlat1 + 'Gamma': 0x0393, # greek capital letter gamma, U+0393 ISOgrk3 + 'Iacute': 0x00cd, # latin capital letter I with acute, U+00CD ISOlat1 + 'Icirc': 0x00ce, # latin capital letter I with circumflex, U+00CE ISOlat1 + 'Igrave': 0x00cc, # latin capital letter I with grave, U+00CC ISOlat1 + 'Iota': 0x0399, # greek capital letter iota, U+0399 + 'Iuml': 0x00cf, # latin capital letter I with diaeresis, U+00CF ISOlat1 + 'Kappa': 0x039a, # greek capital letter kappa, U+039A + 'Lambda': 0x039b, # greek capital letter lambda, U+039B ISOgrk3 + 'Mu': 0x039c, # greek capital letter mu, U+039C + 'Ntilde': 0x00d1, # latin capital letter N with tilde, U+00D1 ISOlat1 + 'Nu': 0x039d, # greek capital letter nu, U+039D + 'OElig': 0x0152, # latin capital ligature OE, U+0152 ISOlat2 + 'Oacute': 0x00d3, # latin capital letter O with acute, U+00D3 ISOlat1 + 'Ocirc': 0x00d4, # latin capital letter O with circumflex, U+00D4 ISOlat1 + 'Ograve': 0x00d2, # latin capital letter O with grave, U+00D2 ISOlat1 + 'Omega': 0x03a9, # greek capital letter omega, U+03A9 ISOgrk3 + 'Omicron': 0x039f, # greek capital letter omicron, U+039F + 'Oslash': 0x00d8, # latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1 + 'Otilde': 0x00d5, # latin capital letter O with tilde, U+00D5 ISOlat1 + 'Ouml': 0x00d6, # latin capital letter O with diaeresis, U+00D6 ISOlat1 + 'Phi': 0x03a6, # greek capital letter phi, U+03A6 ISOgrk3 + 'Pi': 0x03a0, # greek capital letter pi, U+03A0 ISOgrk3 + 'Prime': 0x2033, # double prime = seconds = inches, U+2033 ISOtech + 'Psi': 0x03a8, # greek capital letter psi, U+03A8 ISOgrk3 + 'Rho': 0x03a1, # greek capital letter rho, U+03A1 + 'Scaron': 0x0160, # latin capital letter S with caron, U+0160 ISOlat2 + 'Sigma': 0x03a3, # greek capital letter sigma, U+03A3 ISOgrk3 + 'THORN': 0x00de, # latin capital letter THORN, U+00DE ISOlat1 + 'Tau': 0x03a4, # greek capital letter tau, U+03A4 + 'Theta': 0x0398, # greek capital letter theta, U+0398 ISOgrk3 + 'Uacute': 0x00da, # latin capital letter U with acute, U+00DA ISOlat1 + 'Ucirc': 0x00db, # latin capital letter U with circumflex, U+00DB ISOlat1 + 'Ugrave': 0x00d9, # latin capital letter U with grave, U+00D9 ISOlat1 + 'Upsilon': 0x03a5, # greek capital letter upsilon, U+03A5 ISOgrk3 + 'Uuml': 0x00dc, # latin capital letter U with diaeresis, U+00DC ISOlat1 + 'Xi': 0x039e, # greek capital letter xi, U+039E ISOgrk3 + 'Yacute': 0x00dd, # latin capital letter Y with acute, U+00DD ISOlat1 + 'Yuml': 0x0178, # latin capital letter Y with diaeresis, U+0178 ISOlat2 + 'Zeta': 0x0396, # greek capital letter zeta, U+0396 + 'aacute': 0x00e1, # latin small letter a with acute, U+00E1 ISOlat1 + 'acirc': 0x00e2, # latin small letter a with circumflex, U+00E2 ISOlat1 + 'acute': 0x00b4, # acute accent = spacing acute, U+00B4 ISOdia + 'aelig': 0x00e6, # latin small letter ae = latin small ligature ae, U+00E6 ISOlat1 + 'agrave': 0x00e0, # latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1 + 'alefsym': 0x2135, # alef symbol = first transfinite cardinal, U+2135 NEW + 'alpha': 0x03b1, # greek small letter alpha, U+03B1 ISOgrk3 + 'amp': 0x0026, # ampersand, U+0026 ISOnum + 'and': 0x2227, # logical and = wedge, U+2227 ISOtech + 'ang': 0x2220, # angle, U+2220 ISOamso + 'aring': 0x00e5, # latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1 + 'asymp': 0x2248, # almost equal to = asymptotic to, U+2248 ISOamsr + 'atilde': 0x00e3, # latin small letter a with tilde, U+00E3 ISOlat1 + 'auml': 0x00e4, # latin small letter a with diaeresis, U+00E4 ISOlat1 + 'bdquo': 0x201e, # double low-9 quotation mark, U+201E NEW + 'beta': 0x03b2, # greek small letter beta, U+03B2 ISOgrk3 + 'brvbar': 0x00a6, # broken bar = broken vertical bar, U+00A6 ISOnum + 'bull': 0x2022, # bullet = black small circle, U+2022 ISOpub + 'cap': 0x2229, # intersection = cap, U+2229 ISOtech + 'ccedil': 0x00e7, # latin small letter c with cedilla, U+00E7 ISOlat1 + 'cedil': 0x00b8, # cedilla = spacing cedilla, U+00B8 ISOdia + 'cent': 0x00a2, # cent sign, U+00A2 ISOnum + 'chi': 0x03c7, # greek small letter chi, U+03C7 ISOgrk3 + 'circ': 0x02c6, # modifier letter circumflex accent, U+02C6 ISOpub + 'clubs': 0x2663, # black club suit = shamrock, U+2663 ISOpub + 'cong': 0x2245, # approximately equal to, U+2245 ISOtech + 'copy': 0x00a9, # copyright sign, U+00A9 ISOnum + 'crarr': 0x21b5, # downwards arrow with corner leftwards = carriage return, U+21B5 NEW + 'cup': 0x222a, # union = cup, U+222A ISOtech + 'curren': 0x00a4, # currency sign, U+00A4 ISOnum + 'dArr': 0x21d3, # downwards double arrow, U+21D3 ISOamsa + 'dagger': 0x2020, # dagger, U+2020 ISOpub + 'darr': 0x2193, # downwards arrow, U+2193 ISOnum + 'deg': 0x00b0, # degree sign, U+00B0 ISOnum + 'delta': 0x03b4, # greek small letter delta, U+03B4 ISOgrk3 + 'diams': 0x2666, # black diamond suit, U+2666 ISOpub + 'divide': 0x00f7, # division sign, U+00F7 ISOnum + 'eacute': 0x00e9, # latin small letter e with acute, U+00E9 ISOlat1 + 'ecirc': 0x00ea, # latin small letter e with circumflex, U+00EA ISOlat1 + 'egrave': 0x00e8, # latin small letter e with grave, U+00E8 ISOlat1 + 'empty': 0x2205, # empty set = null set = diameter, U+2205 ISOamso + 'emsp': 0x2003, # em space, U+2003 ISOpub + 'ensp': 0x2002, # en space, U+2002 ISOpub + 'epsilon': 0x03b5, # greek small letter epsilon, U+03B5 ISOgrk3 + 'equiv': 0x2261, # identical to, U+2261 ISOtech + 'eta': 0x03b7, # greek small letter eta, U+03B7 ISOgrk3 + 'eth': 0x00f0, # latin small letter eth, U+00F0 ISOlat1 + 'euml': 0x00eb, # latin small letter e with diaeresis, U+00EB ISOlat1 + 'euro': 0x20ac, # euro sign, U+20AC NEW + 'exist': 0x2203, # there exists, U+2203 ISOtech + 'fnof': 0x0192, # latin small f with hook = function = florin, U+0192 ISOtech + 'forall': 0x2200, # for all, U+2200 ISOtech + 'frac12': 0x00bd, # vulgar fraction one half = fraction one half, U+00BD ISOnum + 'frac14': 0x00bc, # vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum + 'frac34': 0x00be, # vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum + 'frasl': 0x2044, # fraction slash, U+2044 NEW + 'gamma': 0x03b3, # greek small letter gamma, U+03B3 ISOgrk3 + 'ge': 0x2265, # greater-than or equal to, U+2265 ISOtech + 'gt': 0x003e, # greater-than sign, U+003E ISOnum + 'hArr': 0x21d4, # left right double arrow, U+21D4 ISOamsa + 'harr': 0x2194, # left right arrow, U+2194 ISOamsa + 'hearts': 0x2665, # black heart suit = valentine, U+2665 ISOpub + 'hellip': 0x2026, # horizontal ellipsis = three dot leader, U+2026 ISOpub + 'iacute': 0x00ed, # latin small letter i with acute, U+00ED ISOlat1 + 'icirc': 0x00ee, # latin small letter i with circumflex, U+00EE ISOlat1 + 'iexcl': 0x00a1, # inverted exclamation mark, U+00A1 ISOnum + 'igrave': 0x00ec, # latin small letter i with grave, U+00EC ISOlat1 + 'image': 0x2111, # blackletter capital I = imaginary part, U+2111 ISOamso + 'infin': 0x221e, # infinity, U+221E ISOtech + 'int': 0x222b, # integral, U+222B ISOtech + 'iota': 0x03b9, # greek small letter iota, U+03B9 ISOgrk3 + 'iquest': 0x00bf, # inverted question mark = turned question mark, U+00BF ISOnum + 'isin': 0x2208, # element of, U+2208 ISOtech + 'iuml': 0x00ef, # latin small letter i with diaeresis, U+00EF ISOlat1 + 'kappa': 0x03ba, # greek small letter kappa, U+03BA ISOgrk3 + 'lArr': 0x21d0, # leftwards double arrow, U+21D0 ISOtech + 'lambda': 0x03bb, # greek small letter lambda, U+03BB ISOgrk3 + 'lang': 0x2329, # left-pointing angle bracket = bra, U+2329 ISOtech + 'laquo': 0x00ab, # left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum + 'larr': 0x2190, # leftwards arrow, U+2190 ISOnum + 'lceil': 0x2308, # left ceiling = apl upstile, U+2308 ISOamsc + 'ldquo': 0x201c, # left double quotation mark, U+201C ISOnum + 'le': 0x2264, # less-than or equal to, U+2264 ISOtech + 'lfloor': 0x230a, # left floor = apl downstile, U+230A ISOamsc + 'lowast': 0x2217, # asterisk operator, U+2217 ISOtech + 'loz': 0x25ca, # lozenge, U+25CA ISOpub + 'lrm': 0x200e, # left-to-right mark, U+200E NEW RFC 2070 + 'lsaquo': 0x2039, # single left-pointing angle quotation mark, U+2039 ISO proposed + 'lsquo': 0x2018, # left single quotation mark, U+2018 ISOnum + 'lt': 0x003c, # less-than sign, U+003C ISOnum + 'macr': 0x00af, # macron = spacing macron = overline = APL overbar, U+00AF ISOdia + 'mdash': 0x2014, # em dash, U+2014 ISOpub + 'micro': 0x00b5, # micro sign, U+00B5 ISOnum + 'middot': 0x00b7, # middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum + 'minus': 0x2212, # minus sign, U+2212 ISOtech + 'mu': 0x03bc, # greek small letter mu, U+03BC ISOgrk3 + 'nabla': 0x2207, # nabla = backward difference, U+2207 ISOtech + 'nbsp': 0x00a0, # no-break space = non-breaking space, U+00A0 ISOnum + 'ndash': 0x2013, # en dash, U+2013 ISOpub + 'ne': 0x2260, # not equal to, U+2260 ISOtech + 'ni': 0x220b, # contains as member, U+220B ISOtech + 'not': 0x00ac, # not sign, U+00AC ISOnum + 'notin': 0x2209, # not an element of, U+2209 ISOtech + 'nsub': 0x2284, # not a subset of, U+2284 ISOamsn + 'ntilde': 0x00f1, # latin small letter n with tilde, U+00F1 ISOlat1 + 'nu': 0x03bd, # greek small letter nu, U+03BD ISOgrk3 + 'oacute': 0x00f3, # latin small letter o with acute, U+00F3 ISOlat1 + 'ocirc': 0x00f4, # latin small letter o with circumflex, U+00F4 ISOlat1 + 'oelig': 0x0153, # latin small ligature oe, U+0153 ISOlat2 + 'ograve': 0x00f2, # latin small letter o with grave, U+00F2 ISOlat1 + 'oline': 0x203e, # overline = spacing overscore, U+203E NEW + 'omega': 0x03c9, # greek small letter omega, U+03C9 ISOgrk3 + 'omicron': 0x03bf, # greek small letter omicron, U+03BF NEW + 'oplus': 0x2295, # circled plus = direct sum, U+2295 ISOamsb + 'or': 0x2228, # logical or = vee, U+2228 ISOtech + 'ordf': 0x00aa, # feminine ordinal indicator, U+00AA ISOnum + 'ordm': 0x00ba, # masculine ordinal indicator, U+00BA ISOnum + 'oslash': 0x00f8, # latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1 + 'otilde': 0x00f5, # latin small letter o with tilde, U+00F5 ISOlat1 + 'otimes': 0x2297, # circled times = vector product, U+2297 ISOamsb + 'ouml': 0x00f6, # latin small letter o with diaeresis, U+00F6 ISOlat1 + 'para': 0x00b6, # pilcrow sign = paragraph sign, U+00B6 ISOnum + 'part': 0x2202, # partial differential, U+2202 ISOtech + 'permil': 0x2030, # per mille sign, U+2030 ISOtech + 'perp': 0x22a5, # up tack = orthogonal to = perpendicular, U+22A5 ISOtech + 'phi': 0x03c6, # greek small letter phi, U+03C6 ISOgrk3 + 'pi': 0x03c0, # greek small letter pi, U+03C0 ISOgrk3 + 'piv': 0x03d6, # greek pi symbol, U+03D6 ISOgrk3 + 'plusmn': 0x00b1, # plus-minus sign = plus-or-minus sign, U+00B1 ISOnum + 'pound': 0x00a3, # pound sign, U+00A3 ISOnum + 'prime': 0x2032, # prime = minutes = feet, U+2032 ISOtech + 'prod': 0x220f, # n-ary product = product sign, U+220F ISOamsb + 'prop': 0x221d, # proportional to, U+221D ISOtech + 'psi': 0x03c8, # greek small letter psi, U+03C8 ISOgrk3 + 'quot': 0x0022, # quotation mark = APL quote, U+0022 ISOnum + 'rArr': 0x21d2, # rightwards double arrow, U+21D2 ISOtech + 'radic': 0x221a, # square root = radical sign, U+221A ISOtech + 'rang': 0x232a, # right-pointing angle bracket = ket, U+232A ISOtech + 'raquo': 0x00bb, # right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum + 'rarr': 0x2192, # rightwards arrow, U+2192 ISOnum + 'rceil': 0x2309, # right ceiling, U+2309 ISOamsc + 'rdquo': 0x201d, # right double quotation mark, U+201D ISOnum + 'real': 0x211c, # blackletter capital R = real part symbol, U+211C ISOamso + 'reg': 0x00ae, # registered sign = registered trade mark sign, U+00AE ISOnum + 'rfloor': 0x230b, # right floor, U+230B ISOamsc + 'rho': 0x03c1, # greek small letter rho, U+03C1 ISOgrk3 + 'rlm': 0x200f, # right-to-left mark, U+200F NEW RFC 2070 + 'rsaquo': 0x203a, # single right-pointing angle quotation mark, U+203A ISO proposed + 'rsquo': 0x2019, # right single quotation mark, U+2019 ISOnum + 'sbquo': 0x201a, # single low-9 quotation mark, U+201A NEW + 'scaron': 0x0161, # latin small letter s with caron, U+0161 ISOlat2 + 'sdot': 0x22c5, # dot operator, U+22C5 ISOamsb + 'sect': 0x00a7, # section sign, U+00A7 ISOnum + 'shy': 0x00ad, # soft hyphen = discretionary hyphen, U+00AD ISOnum + 'sigma': 0x03c3, # greek small letter sigma, U+03C3 ISOgrk3 + 'sigmaf': 0x03c2, # greek small letter final sigma, U+03C2 ISOgrk3 + 'sim': 0x223c, # tilde operator = varies with = similar to, U+223C ISOtech + 'spades': 0x2660, # black spade suit, U+2660 ISOpub + 'sub': 0x2282, # subset of, U+2282 ISOtech + 'sube': 0x2286, # subset of or equal to, U+2286 ISOtech + 'sum': 0x2211, # n-ary sumation, U+2211 ISOamsb + 'sup': 0x2283, # superset of, U+2283 ISOtech + 'sup1': 0x00b9, # superscript one = superscript digit one, U+00B9 ISOnum + 'sup2': 0x00b2, # superscript two = superscript digit two = squared, U+00B2 ISOnum + 'sup3': 0x00b3, # superscript three = superscript digit three = cubed, U+00B3 ISOnum + 'supe': 0x2287, # superset of or equal to, U+2287 ISOtech + 'szlig': 0x00df, # latin small letter sharp s = ess-zed, U+00DF ISOlat1 + 'tau': 0x03c4, # greek small letter tau, U+03C4 ISOgrk3 + 'there4': 0x2234, # therefore, U+2234 ISOtech + 'theta': 0x03b8, # greek small letter theta, U+03B8 ISOgrk3 + 'thetasym': 0x03d1, # greek small letter theta symbol, U+03D1 NEW + 'thinsp': 0x2009, # thin space, U+2009 ISOpub + 'thorn': 0x00fe, # latin small letter thorn with, U+00FE ISOlat1 + 'tilde': 0x02dc, # small tilde, U+02DC ISOdia + 'times': 0x00d7, # multiplication sign, U+00D7 ISOnum + 'trade': 0x2122, # trade mark sign, U+2122 ISOnum + 'uArr': 0x21d1, # upwards double arrow, U+21D1 ISOamsa + 'uacute': 0x00fa, # latin small letter u with acute, U+00FA ISOlat1 + 'uarr': 0x2191, # upwards arrow, U+2191 ISOnum + 'ucirc': 0x00fb, # latin small letter u with circumflex, U+00FB ISOlat1 + 'ugrave': 0x00f9, # latin small letter u with grave, U+00F9 ISOlat1 + 'uml': 0x00a8, # diaeresis = spacing diaeresis, U+00A8 ISOdia + 'upsih': 0x03d2, # greek upsilon with hook symbol, U+03D2 NEW + 'upsilon': 0x03c5, # greek small letter upsilon, U+03C5 ISOgrk3 + 'uuml': 0x00fc, # latin small letter u with diaeresis, U+00FC ISOlat1 + 'weierp': 0x2118, # script capital P = power set = Weierstrass p, U+2118 ISOamso + 'xi': 0x03be, # greek small letter xi, U+03BE ISOgrk3 + 'yacute': 0x00fd, # latin small letter y with acute, U+00FD ISOlat1 + 'yen': 0x00a5, # yen sign = yuan sign, U+00A5 ISOnum + 'yuml': 0x00ff, # latin small letter y with diaeresis, U+00FF ISOlat1 + 'zeta': 0x03b6, # greek small letter zeta, U+03B6 ISOgrk3 + 'zwj': 0x200d, # zero width joiner, U+200D NEW RFC 2070 + 'zwnj': 0x200c, # zero width non-joiner, U+200C NEW RFC 2070 +} + +# maps the Unicode codepoint to the HTML entity name +codepoint2name = {} + +# maps the HTML entity name to the character +# (or a character reference if the character is outside the Latin-1 range) +entitydefs = {} + +for (name, codepoint) in name2codepoint.items(): + codepoint2name[codepoint] = name + entitydefs[name] = chr(codepoint) + +del name, codepoint diff --git a/Lib/html/parser.py b/Lib/html/parser.py new file mode 100644 index 0000000..352a788 --- /dev/null +++ b/Lib/html/parser.py @@ -0,0 +1,388 @@ +"""A parser for HTML and XHTML.""" + +# This file is based on sgmllib.py, but the API is slightly different. + +# XXX There should be a way to distinguish between PCDATA (parsed +# character data -- the normal case), RCDATA (replaceable character +# data -- only char and entity references and end tags are special) +# and CDATA (character data -- only end tags are special). + + +import _markupbase +import re + +# Regular expressions used for parsing + +interesting_normal = re.compile('[&<]') +interesting_cdata = re.compile(r'<(/|\Z)') +incomplete = re.compile('&[a-zA-Z#]') + +entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') +charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]') + +starttagopen = re.compile('<[a-zA-Z]') +piclose = re.compile('>') +commentclose = re.compile(r'--\s*>') +tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') +attrfind = re.compile( + r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' + r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?') + +locatestarttagend = re.compile(r""" + <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name + (?:\s+ # whitespace before attribute name + (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name + (?:\s*=\s* # value indicator + (?:'[^']*' # LITA-enclosed value + |\"[^\"]*\" # LIT-enclosed value + |[^'\">\s]+ # bare value + ) + )? + ) + )* + \s* # trailing whitespace +""", re.VERBOSE) +endendtag = re.compile('>') +endtagfind = re.compile('') + + +class HTMLParseError(Exception): + """Exception raised for all parse errors.""" + + def __init__(self, msg, position=(None, None)): + assert msg + self.msg = msg + self.lineno = position[0] + self.offset = position[1] + + def __str__(self): + result = self.msg + if self.lineno is not None: + result = result + ", at line %d" % self.lineno + if self.offset is not None: + result = result + ", column %d" % (self.offset + 1) + return result + + +class HTMLParser(_markupbase.ParserBase): + """Find tags and other markup and call handler functions. + + Usage: + p = HTMLParser() + p.feed(data) + ... + p.close() + + Start tags are handled by calling self.handle_starttag() or + self.handle_startendtag(); end tags by self.handle_endtag(). The + data between tags is passed from the parser to the derived class + by calling self.handle_data() with the data as argument (the data + may be split up in arbitrary chunks). Entity references are + passed by calling self.handle_entityref() with the entity + reference as the argument. Numeric character references are + passed to self.handle_charref() with the string containing the + reference as the argument. + """ + + CDATA_CONTENT_ELEMENTS = ("script", "style") + + + def __init__(self): + """Initialize and reset this instance.""" + self.reset() + + def reset(self): + """Reset this instance. Loses all unprocessed data.""" + self.rawdata = '' + self.lasttag = '???' + self.interesting = interesting_normal + _markupbase.ParserBase.reset(self) + + def feed(self, data): + """Feed data to the parser. + + Call this as often as you want, with as little or as much text + as you want (may include '\n'). + """ + self.rawdata = self.rawdata + data + self.goahead(0) + + def close(self): + """Handle any buffered data.""" + self.goahead(1) + + def error(self, message): + raise HTMLParseError(message, self.getpos()) + + __starttag_text = None + + def get_starttag_text(self): + """Return full source of start tag: '<...>'.""" + return self.__starttag_text + + def set_cdata_mode(self): + self.interesting = interesting_cdata + + def clear_cdata_mode(self): + self.interesting = interesting_normal + + # Internal -- handle data as far as reasonable. May leave state + # and data to be processed by a subsequent call. If 'end' is + # true, force handling all data as if followed by EOF marker. + def goahead(self, end): + rawdata = self.rawdata + i = 0 + n = len(rawdata) + while i < n: + match = self.interesting.search(rawdata, i) # < or & + if match: + j = match.start() + else: + j = n + if i < j: self.handle_data(rawdata[i:j]) + i = self.updatepos(i, j) + if i == n: break + startswith = rawdata.startswith + if startswith('<', i): + if starttagopen.match(rawdata, i): # < + letter + k = self.parse_starttag(i) + elif startswith(" + if not match: + return -1 + j = match.start() + self.handle_pi(rawdata[i+2: j]) + j = match.end() + return j + + # Internal -- handle starttag, return end or -1 if not terminated + def parse_starttag(self, i): + self.__starttag_text = None + endpos = self.check_for_whole_start_tag(i) + if endpos < 0: + return endpos + rawdata = self.rawdata + self.__starttag_text = rawdata[i:endpos] + + # Now parse the data between i+1 and j into a tag and attrs + attrs = [] + match = tagfind.match(rawdata, i+1) + assert match, 'unexpected call to parse_starttag()' + k = match.end() + self.lasttag = tag = rawdata[i+1:k].lower() + + while k < endpos: + m = attrfind.match(rawdata, k) + if not m: + break + attrname, rest, attrvalue = m.group(1, 2, 3) + if not rest: + attrvalue = None + elif attrvalue[:1] == '\'' == attrvalue[-1:] or \ + attrvalue[:1] == '"' == attrvalue[-1:]: + attrvalue = attrvalue[1:-1] + attrvalue = self.unescape(attrvalue) + attrs.append((attrname.lower(), attrvalue)) + k = m.end() + + end = rawdata[k:endpos].strip() + if end not in (">", "/>"): + lineno, offset = self.getpos() + if "\n" in self.__starttag_text: + lineno = lineno + self.__starttag_text.count("\n") + offset = len(self.__starttag_text) \ + - self.__starttag_text.rfind("\n") + else: + offset = offset + len(self.__starttag_text) + self.error("junk characters in start tag: %r" + % (rawdata[k:endpos][:20],)) + if end.endswith('/>'): + # XHTML-style empty tag: + self.handle_startendtag(tag, attrs) + else: + self.handle_starttag(tag, attrs) + if tag in self.CDATA_CONTENT_ELEMENTS: + self.set_cdata_mode() + return endpos + + # Internal -- check to see if we have a complete starttag; return end + # or -1 if incomplete. + def check_for_whole_start_tag(self, i): + rawdata = self.rawdata + m = locatestarttagend.match(rawdata, i) + if m: + j = m.end() + next = rawdata[j:j+1] + if next == ">": + return j + 1 + if next == "/": + if rawdata.startswith("/>", j): + return j + 2 + if rawdata.startswith("/", j): + # buffer boundary + return -1 + # else bogus input + self.updatepos(i, j + 1) + self.error("malformed empty start tag") + if next == "": + # end of input + return -1 + if next in ("abcdefghijklmnopqrstuvwxyz=/" + "ABCDEFGHIJKLMNOPQRSTUVWXYZ"): + # end of input in or before attribute value, or we have the + # '/' from a '/>' ending + return -1 + self.updatepos(i, j) + self.error("malformed start tag") + raise AssertionError("we should not get here!") + + # Internal -- parse endtag, return end or -1 if incomplete + def parse_endtag(self, i): + rawdata = self.rawdata + assert rawdata[i:i+2] == " + if not match: + return -1 + j = match.end() + match = endtagfind.match(rawdata, i) # + if not match: + self.error("bad end tag: %r" % (rawdata[i:j],)) + tag = match.group(1) + self.handle_endtag(tag.lower()) + self.clear_cdata_mode() + return j + + # Overridable -- finish processing of start+end tag: + def handle_startendtag(self, tag, attrs): + self.handle_starttag(tag, attrs) + self.handle_endtag(tag) + + # Overridable -- handle start tag + def handle_starttag(self, tag, attrs): + pass + + # Overridable -- handle end tag + def handle_endtag(self, tag): + pass + + # Overridable -- handle character reference + def handle_charref(self, name): + pass + + # Overridable -- handle entity reference + def handle_entityref(self, name): + pass + + # Overridable -- handle data + def handle_data(self, data): + pass + + # Overridable -- handle comment + def handle_comment(self, data): + pass + + # Overridable -- handle declaration + def handle_decl(self, decl): + pass + + # Overridable -- handle processing instruction + def handle_pi(self, data): + pass + + def unknown_decl(self, data): + self.error("unknown declaration: %r" % (data,)) + + # Internal -- helper to remove special character quoting + entitydefs = None + def unescape(self, s): + if '&' not in s: + return s + def replaceEntities(s): + s = s.groups()[0] + if s[0] == "#": + s = s[1:] + if s[0] in ['x','X']: + c = int(s[1:], 16) + else: + c = int(s) + return chr(c) + else: + # Cannot use name2codepoint directly, because HTMLParser + # supports apos, which is not part of HTML 4 + import html.entities + if HTMLParser.entitydefs is None: + entitydefs = HTMLParser.entitydefs = {'apos':"'"} + for k, v in html.entities.name2codepoint.items(): + entitydefs[k] = unichr(v) + try: + return self.entitydefs[s] + except KeyError: + return '&'+s+';' + + return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", + replaceEntities, s) diff --git a/Lib/htmlentitydefs.py b/Lib/htmlentitydefs.py deleted file mode 100644 index e2b7bf1..0000000 --- a/Lib/htmlentitydefs.py +++ /dev/null @@ -1,270 +0,0 @@ -"""HTML character entity references.""" - -# maps the HTML entity name to the Unicode codepoint -name2codepoint = { - 'AElig': 0x00c6, # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1 - 'Aacute': 0x00c1, # latin capital letter A with acute, U+00C1 ISOlat1 - 'Acirc': 0x00c2, # latin capital letter A with circumflex, U+00C2 ISOlat1 - 'Agrave': 0x00c0, # latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1 - 'Alpha': 0x0391, # greek capital letter alpha, U+0391 - 'Aring': 0x00c5, # latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1 - 'Atilde': 0x00c3, # latin capital letter A with tilde, U+00C3 ISOlat1 - 'Auml': 0x00c4, # latin capital letter A with diaeresis, U+00C4 ISOlat1 - 'Beta': 0x0392, # greek capital letter beta, U+0392 - 'Ccedil': 0x00c7, # latin capital letter C with cedilla, U+00C7 ISOlat1 - 'Chi': 0x03a7, # greek capital letter chi, U+03A7 - 'Dagger': 0x2021, # double dagger, U+2021 ISOpub - 'Delta': 0x0394, # greek capital letter delta, U+0394 ISOgrk3 - 'ETH': 0x00d0, # latin capital letter ETH, U+00D0 ISOlat1 - 'Eacute': 0x00c9, # latin capital letter E with acute, U+00C9 ISOlat1 - 'Ecirc': 0x00ca, # latin capital letter E with circumflex, U+00CA ISOlat1 - 'Egrave': 0x00c8, # latin capital letter E with grave, U+00C8 ISOlat1 - 'Epsilon': 0x0395, # greek capital letter epsilon, U+0395 - 'Eta': 0x0397, # greek capital letter eta, U+0397 - 'Euml': 0x00cb, # latin capital letter E with diaeresis, U+00CB ISOlat1 - 'Gamma': 0x0393, # greek capital letter gamma, U+0393 ISOgrk3 - 'Iacute': 0x00cd, # latin capital letter I with acute, U+00CD ISOlat1 - 'Icirc': 0x00ce, # latin capital letter I with circumflex, U+00CE ISOlat1 - 'Igrave': 0x00cc, # latin capital letter I with grave, U+00CC ISOlat1 - 'Iota': 0x0399, # greek capital letter iota, U+0399 - 'Iuml': 0x00cf, # latin capital letter I with diaeresis, U+00CF ISOlat1 - 'Kappa': 0x039a, # greek capital letter kappa, U+039A - 'Lambda': 0x039b, # greek capital letter lambda, U+039B ISOgrk3 - 'Mu': 0x039c, # greek capital letter mu, U+039C - 'Ntilde': 0x00d1, # latin capital letter N with tilde, U+00D1 ISOlat1 - 'Nu': 0x039d, # greek capital letter nu, U+039D - 'OElig': 0x0152, # latin capital ligature OE, U+0152 ISOlat2 - 'Oacute': 0x00d3, # latin capital letter O with acute, U+00D3 ISOlat1 - 'Ocirc': 0x00d4, # latin capital letter O with circumflex, U+00D4 ISOlat1 - 'Ograve': 0x00d2, # latin capital letter O with grave, U+00D2 ISOlat1 - 'Omega': 0x03a9, # greek capital letter omega, U+03A9 ISOgrk3 - 'Omicron': 0x039f, # greek capital letter omicron, U+039F - 'Oslash': 0x00d8, # latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1 - 'Otilde': 0x00d5, # latin capital letter O with tilde, U+00D5 ISOlat1 - 'Ouml': 0x00d6, # latin capital letter O with diaeresis, U+00D6 ISOlat1 - 'Phi': 0x03a6, # greek capital letter phi, U+03A6 ISOgrk3 - 'Pi': 0x03a0, # greek capital letter pi, U+03A0 ISOgrk3 - 'Prime': 0x2033, # double prime = seconds = inches, U+2033 ISOtech - 'Psi': 0x03a8, # greek capital letter psi, U+03A8 ISOgrk3 - 'Rho': 0x03a1, # greek capital letter rho, U+03A1 - 'Scaron': 0x0160, # latin capital letter S with caron, U+0160 ISOlat2 - 'Sigma': 0x03a3, # greek capital letter sigma, U+03A3 ISOgrk3 - 'THORN': 0x00de, # latin capital letter THORN, U+00DE ISOlat1 - 'Tau': 0x03a4, # greek capital letter tau, U+03A4 - 'Theta': 0x0398, # greek capital letter theta, U+0398 ISOgrk3 - 'Uacute': 0x00da, # latin capital letter U with acute, U+00DA ISOlat1 - 'Ucirc': 0x00db, # latin capital letter U with circumflex, U+00DB ISOlat1 - 'Ugrave': 0x00d9, # latin capital letter U with grave, U+00D9 ISOlat1 - 'Upsilon': 0x03a5, # greek capital letter upsilon, U+03A5 ISOgrk3 - 'Uuml': 0x00dc, # latin capital letter U with diaeresis, U+00DC ISOlat1 - 'Xi': 0x039e, # greek capital letter xi, U+039E ISOgrk3 - 'Yacute': 0x00dd, # latin capital letter Y with acute, U+00DD ISOlat1 - 'Yuml': 0x0178, # latin capital letter Y with diaeresis, U+0178 ISOlat2 - 'Zeta': 0x0396, # greek capital letter zeta, U+0396 - 'aacute': 0x00e1, # latin small letter a with acute, U+00E1 ISOlat1 - 'acirc': 0x00e2, # latin small letter a with circumflex, U+00E2 ISOlat1 - 'acute': 0x00b4, # acute accent = spacing acute, U+00B4 ISOdia - 'aelig': 0x00e6, # latin small letter ae = latin small ligature ae, U+00E6 ISOlat1 - 'agrave': 0x00e0, # latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1 - 'alefsym': 0x2135, # alef symbol = first transfinite cardinal, U+2135 NEW - 'alpha': 0x03b1, # greek small letter alpha, U+03B1 ISOgrk3 - 'amp': 0x0026, # ampersand, U+0026 ISOnum - 'and': 0x2227, # logical and = wedge, U+2227 ISOtech - 'ang': 0x2220, # angle, U+2220 ISOamso - 'aring': 0x00e5, # latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1 - 'asymp': 0x2248, # almost equal to = asymptotic to, U+2248 ISOamsr - 'atilde': 0x00e3, # latin small letter a with tilde, U+00E3 ISOlat1 - 'auml': 0x00e4, # latin small letter a with diaeresis, U+00E4 ISOlat1 - 'bdquo': 0x201e, # double low-9 quotation mark, U+201E NEW - 'beta': 0x03b2, # greek small letter beta, U+03B2 ISOgrk3 - 'brvbar': 0x00a6, # broken bar = broken vertical bar, U+00A6 ISOnum - 'bull': 0x2022, # bullet = black small circle, U+2022 ISOpub - 'cap': 0x2229, # intersection = cap, U+2229 ISOtech - 'ccedil': 0x00e7, # latin small letter c with cedilla, U+00E7 ISOlat1 - 'cedil': 0x00b8, # cedilla = spacing cedilla, U+00B8 ISOdia - 'cent': 0x00a2, # cent sign, U+00A2 ISOnum - 'chi': 0x03c7, # greek small letter chi, U+03C7 ISOgrk3 - 'circ': 0x02c6, # modifier letter circumflex accent, U+02C6 ISOpub - 'clubs': 0x2663, # black club suit = shamrock, U+2663 ISOpub - 'cong': 0x2245, # approximately equal to, U+2245 ISOtech - 'copy': 0x00a9, # copyright sign, U+00A9 ISOnum - 'crarr': 0x21b5, # downwards arrow with corner leftwards = carriage return, U+21B5 NEW - 'cup': 0x222a, # union = cup, U+222A ISOtech - 'curren': 0x00a4, # currency sign, U+00A4 ISOnum - 'dArr': 0x21d3, # downwards double arrow, U+21D3 ISOamsa - 'dagger': 0x2020, # dagger, U+2020 ISOpub - 'darr': 0x2193, # downwards arrow, U+2193 ISOnum - 'deg': 0x00b0, # degree sign, U+00B0 ISOnum - 'delta': 0x03b4, # greek small letter delta, U+03B4 ISOgrk3 - 'diams': 0x2666, # black diamond suit, U+2666 ISOpub - 'divide': 0x00f7, # division sign, U+00F7 ISOnum - 'eacute': 0x00e9, # latin small letter e with acute, U+00E9 ISOlat1 - 'ecirc': 0x00ea, # latin small letter e with circumflex, U+00EA ISOlat1 - 'egrave': 0x00e8, # latin small letter e with grave, U+00E8 ISOlat1 - 'empty': 0x2205, # empty set = null set = diameter, U+2205 ISOamso - 'emsp': 0x2003, # em space, U+2003 ISOpub - 'ensp': 0x2002, # en space, U+2002 ISOpub - 'epsilon': 0x03b5, # greek small letter epsilon, U+03B5 ISOgrk3 - 'equiv': 0x2261, # identical to, U+2261 ISOtech - 'eta': 0x03b7, # greek small letter eta, U+03B7 ISOgrk3 - 'eth': 0x00f0, # latin small letter eth, U+00F0 ISOlat1 - 'euml': 0x00eb, # latin small letter e with diaeresis, U+00EB ISOlat1 - 'euro': 0x20ac, # euro sign, U+20AC NEW - 'exist': 0x2203, # there exists, U+2203 ISOtech - 'fnof': 0x0192, # latin small f with hook = function = florin, U+0192 ISOtech - 'forall': 0x2200, # for all, U+2200 ISOtech - 'frac12': 0x00bd, # vulgar fraction one half = fraction one half, U+00BD ISOnum - 'frac14': 0x00bc, # vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum - 'frac34': 0x00be, # vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum - 'frasl': 0x2044, # fraction slash, U+2044 NEW - 'gamma': 0x03b3, # greek small letter gamma, U+03B3 ISOgrk3 - 'ge': 0x2265, # greater-than or equal to, U+2265 ISOtech - 'gt': 0x003e, # greater-than sign, U+003E ISOnum - 'hArr': 0x21d4, # left right double arrow, U+21D4 ISOamsa - 'harr': 0x2194, # left right arrow, U+2194 ISOamsa - 'hearts': 0x2665, # black heart suit = valentine, U+2665 ISOpub - 'hellip': 0x2026, # horizontal ellipsis = three dot leader, U+2026 ISOpub - 'iacute': 0x00ed, # latin small letter i with acute, U+00ED ISOlat1 - 'icirc': 0x00ee, # latin small letter i with circumflex, U+00EE ISOlat1 - 'iexcl': 0x00a1, # inverted exclamation mark, U+00A1 ISOnum - 'igrave': 0x00ec, # latin small letter i with grave, U+00EC ISOlat1 - 'image': 0x2111, # blackletter capital I = imaginary part, U+2111 ISOamso - 'infin': 0x221e, # infinity, U+221E ISOtech - 'int': 0x222b, # integral, U+222B ISOtech - 'iota': 0x03b9, # greek small letter iota, U+03B9 ISOgrk3 - 'iquest': 0x00bf, # inverted question mark = turned question mark, U+00BF ISOnum - 'isin': 0x2208, # element of, U+2208 ISOtech - 'iuml': 0x00ef, # latin small letter i with diaeresis, U+00EF ISOlat1 - 'kappa': 0x03ba, # greek small letter kappa, U+03BA ISOgrk3 - 'lArr': 0x21d0, # leftwards double arrow, U+21D0 ISOtech - 'lambda': 0x03bb, # greek small letter lambda, U+03BB ISOgrk3 - 'lang': 0x2329, # left-pointing angle bracket = bra, U+2329 ISOtech - 'laquo': 0x00ab, # left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum - 'larr': 0x2190, # leftwards arrow, U+2190 ISOnum - 'lceil': 0x2308, # left ceiling = apl upstile, U+2308 ISOamsc - 'ldquo': 0x201c, # left double quotation mark, U+201C ISOnum - 'le': 0x2264, # less-than or equal to, U+2264 ISOtech - 'lfloor': 0x230a, # left floor = apl downstile, U+230A ISOamsc - 'lowast': 0x2217, # asterisk operator, U+2217 ISOtech - 'loz': 0x25ca, # lozenge, U+25CA ISOpub - 'lrm': 0x200e, # left-to-right mark, U+200E NEW RFC 2070 - 'lsaquo': 0x2039, # single left-pointing angle quotation mark, U+2039 ISO proposed - 'lsquo': 0x2018, # left single quotation mark, U+2018 ISOnum - 'lt': 0x003c, # less-than sign, U+003C ISOnum - 'macr': 0x00af, # macron = spacing macron = overline = APL overbar, U+00AF ISOdia - 'mdash': 0x2014, # em dash, U+2014 ISOpub - 'micro': 0x00b5, # micro sign, U+00B5 ISOnum - 'middot': 0x00b7, # middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum - 'minus': 0x2212, # minus sign, U+2212 ISOtech - 'mu': 0x03bc, # greek small letter mu, U+03BC ISOgrk3 - 'nabla': 0x2207, # nabla = backward difference, U+2207 ISOtech - 'nbsp': 0x00a0, # no-break space = non-breaking space, U+00A0 ISOnum - 'ndash': 0x2013, # en dash, U+2013 ISOpub - 'ne': 0x2260, # not equal to, U+2260 ISOtech - 'ni': 0x220b, # contains as member, U+220B ISOtech - 'not': 0x00ac, # not sign, U+00AC ISOnum - 'notin': 0x2209, # not an element of, U+2209 ISOtech - 'nsub': 0x2284, # not a subset of, U+2284 ISOamsn - 'ntilde': 0x00f1, # latin small letter n with tilde, U+00F1 ISOlat1 - 'nu': 0x03bd, # greek small letter nu, U+03BD ISOgrk3 - 'oacute': 0x00f3, # latin small letter o with acute, U+00F3 ISOlat1 - 'ocirc': 0x00f4, # latin small letter o with circumflex, U+00F4 ISOlat1 - 'oelig': 0x0153, # latin small ligature oe, U+0153 ISOlat2 - 'ograve': 0x00f2, # latin small letter o with grave, U+00F2 ISOlat1 - 'oline': 0x203e, # overline = spacing overscore, U+203E NEW - 'omega': 0x03c9, # greek small letter omega, U+03C9 ISOgrk3 - 'omicron': 0x03bf, # greek small letter omicron, U+03BF NEW - 'oplus': 0x2295, # circled plus = direct sum, U+2295 ISOamsb - 'or': 0x2228, # logical or = vee, U+2228 ISOtech - 'ordf': 0x00aa, # feminine ordinal indicator, U+00AA ISOnum - 'ordm': 0x00ba, # masculine ordinal indicator, U+00BA ISOnum - 'oslash': 0x00f8, # latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1 - 'otilde': 0x00f5, # latin small letter o with tilde, U+00F5 ISOlat1 - 'otimes': 0x2297, # circled times = vector product, U+2297 ISOamsb - 'ouml': 0x00f6, # latin small letter o with diaeresis, U+00F6 ISOlat1 - 'para': 0x00b6, # pilcrow sign = paragraph sign, U+00B6 ISOnum - 'part': 0x2202, # partial differential, U+2202 ISOtech - 'permil': 0x2030, # per mille sign, U+2030 ISOtech - 'perp': 0x22a5, # up tack = orthogonal to = perpendicular, U+22A5 ISOtech - 'phi': 0x03c6, # greek small letter phi, U+03C6 ISOgrk3 - 'pi': 0x03c0, # greek small letter pi, U+03C0 ISOgrk3 - 'piv': 0x03d6, # greek pi symbol, U+03D6 ISOgrk3 - 'plusmn': 0x00b1, # plus-minus sign = plus-or-minus sign, U+00B1 ISOnum - 'pound': 0x00a3, # pound sign, U+00A3 ISOnum - 'prime': 0x2032, # prime = minutes = feet, U+2032 ISOtech - 'prod': 0x220f, # n-ary product = product sign, U+220F ISOamsb - 'prop': 0x221d, # proportional to, U+221D ISOtech - 'psi': 0x03c8, # greek small letter psi, U+03C8 ISOgrk3 - 'quot': 0x0022, # quotation mark = APL quote, U+0022 ISOnum - 'rArr': 0x21d2, # rightwards double arrow, U+21D2 ISOtech - 'radic': 0x221a, # square root = radical sign, U+221A ISOtech - 'rang': 0x232a, # right-pointing angle bracket = ket, U+232A ISOtech - 'raquo': 0x00bb, # right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum - 'rarr': 0x2192, # rightwards arrow, U+2192 ISOnum - 'rceil': 0x2309, # right ceiling, U+2309 ISOamsc - 'rdquo': 0x201d, # right double quotation mark, U+201D ISOnum - 'real': 0x211c, # blackletter capital R = real part symbol, U+211C ISOamso - 'reg': 0x00ae, # registered sign = registered trade mark sign, U+00AE ISOnum - 'rfloor': 0x230b, # right floor, U+230B ISOamsc - 'rho': 0x03c1, # greek small letter rho, U+03C1 ISOgrk3 - 'rlm': 0x200f, # right-to-left mark, U+200F NEW RFC 2070 - 'rsaquo': 0x203a, # single right-pointing angle quotation mark, U+203A ISO proposed - 'rsquo': 0x2019, # right single quotation mark, U+2019 ISOnum - 'sbquo': 0x201a, # single low-9 quotation mark, U+201A NEW - 'scaron': 0x0161, # latin small letter s with caron, U+0161 ISOlat2 - 'sdot': 0x22c5, # dot operator, U+22C5 ISOamsb - 'sect': 0x00a7, # section sign, U+00A7 ISOnum - 'shy': 0x00ad, # soft hyphen = discretionary hyphen, U+00AD ISOnum - 'sigma': 0x03c3, # greek small letter sigma, U+03C3 ISOgrk3 - 'sigmaf': 0x03c2, # greek small letter final sigma, U+03C2 ISOgrk3 - 'sim': 0x223c, # tilde operator = varies with = similar to, U+223C ISOtech - 'spades': 0x2660, # black spade suit, U+2660 ISOpub - 'sub': 0x2282, # subset of, U+2282 ISOtech - 'sube': 0x2286, # subset of or equal to, U+2286 ISOtech - 'sum': 0x2211, # n-ary sumation, U+2211 ISOamsb - 'sup': 0x2283, # superset of, U+2283 ISOtech - 'sup1': 0x00b9, # superscript one = superscript digit one, U+00B9 ISOnum - 'sup2': 0x00b2, # superscript two = superscript digit two = squared, U+00B2 ISOnum - 'sup3': 0x00b3, # superscript three = superscript digit three = cubed, U+00B3 ISOnum - 'supe': 0x2287, # superset of or equal to, U+2287 ISOtech - 'szlig': 0x00df, # latin small letter sharp s = ess-zed, U+00DF ISOlat1 - 'tau': 0x03c4, # greek small letter tau, U+03C4 ISOgrk3 - 'there4': 0x2234, # therefore, U+2234 ISOtech - 'theta': 0x03b8, # greek small letter theta, U+03B8 ISOgrk3 - 'thetasym': 0x03d1, # greek small letter theta symbol, U+03D1 NEW - 'thinsp': 0x2009, # thin space, U+2009 ISOpub - 'thorn': 0x00fe, # latin small letter thorn with, U+00FE ISOlat1 - 'tilde': 0x02dc, # small tilde, U+02DC ISOdia - 'times': 0x00d7, # multiplication sign, U+00D7 ISOnum - 'trade': 0x2122, # trade mark sign, U+2122 ISOnum - 'uArr': 0x21d1, # upwards double arrow, U+21D1 ISOamsa - 'uacute': 0x00fa, # latin small letter u with acute, U+00FA ISOlat1 - 'uarr': 0x2191, # upwards arrow, U+2191 ISOnum - 'ucirc': 0x00fb, # latin small letter u with circumflex, U+00FB ISOlat1 - 'ugrave': 0x00f9, # latin small letter u with grave, U+00F9 ISOlat1 - 'uml': 0x00a8, # diaeresis = spacing diaeresis, U+00A8 ISOdia - 'upsih': 0x03d2, # greek upsilon with hook symbol, U+03D2 NEW - 'upsilon': 0x03c5, # greek small letter upsilon, U+03C5 ISOgrk3 - 'uuml': 0x00fc, # latin small letter u with diaeresis, U+00FC ISOlat1 - 'weierp': 0x2118, # script capital P = power set = Weierstrass p, U+2118 ISOamso - 'xi': 0x03be, # greek small letter xi, U+03BE ISOgrk3 - 'yacute': 0x00fd, # latin small letter y with acute, U+00FD ISOlat1 - 'yen': 0x00a5, # yen sign = yuan sign, U+00A5 ISOnum - 'yuml': 0x00ff, # latin small letter y with diaeresis, U+00FF ISOlat1 - 'zeta': 0x03b6, # greek small letter zeta, U+03B6 ISOgrk3 - 'zwj': 0x200d, # zero width joiner, U+200D NEW RFC 2070 - 'zwnj': 0x200c, # zero width non-joiner, U+200C NEW RFC 2070 -} - -# maps the Unicode codepoint to the HTML entity name -codepoint2name = {} - -# maps the HTML entity name to the character -# (or a character reference if the character is outside the Latin-1 range) -entitydefs = {} - -for (name, codepoint) in name2codepoint.items(): - codepoint2name[codepoint] = name - entitydefs[name] = chr(codepoint) - -del name, codepoint diff --git a/Lib/htmllib.py b/Lib/htmllib.py index 88e1df5..a580006 100644 --- a/Lib/htmllib.py +++ b/Lib/htmllib.py @@ -24,7 +24,7 @@ class HTMLParser(sgmllib.SGMLParser): """ - from htmlentitydefs import entitydefs + from html.entities import entitydefs def __init__(self, formatter, verbose=0): """Creates an instance of the HTMLParser class. diff --git a/Lib/test/test_codeccallbacks.py b/Lib/test/test_codeccallbacks.py index 12eb068..64d1645 100644 --- a/Lib/test/test_codeccallbacks.py +++ b/Lib/test/test_codeccallbacks.py @@ -1,5 +1,5 @@ import test.test_support, unittest -import sys, codecs, htmlentitydefs, unicodedata +import sys, codecs, html.entities, unicodedata class PosReturn: # this can be used for configurable callbacks @@ -86,7 +86,7 @@ class CodecCallbackTest(unittest.TestCase): l = [] for c in exc.object[exc.start:exc.end]: try: - l.append("&%s;" % htmlentitydefs.codepoint2name[ord(c)]) + l.append("&%s;" % html.entities.codepoint2name[ord(c)]) except KeyError: l.append("&#%d;" % ord(c)) return ("".join(l), exc.end) diff --git a/Lib/test/test_multibytecodec_support.py b/Lib/test/test_multibytecodec_support.py index 48e9089..5508c9d 100644 --- a/Lib/test/test_multibytecodec_support.py +++ b/Lib/test/test_multibytecodec_support.py @@ -74,7 +74,7 @@ class TestBase: if self.has_iso10646: return - from htmlentitydefs import codepoint2name + from html.entities import codepoint2name def xmlcharnamereplace(exc): if not isinstance(exc, UnicodeEncodeError): diff --git a/Lib/test/test_sundry.py b/Lib/test/test_sundry.py index dd81e5b..1b6069d 100644 --- a/Lib/test/test_sundry.py +++ b/Lib/test/test_sundry.py @@ -48,7 +48,7 @@ class TestUntestedModules(unittest.TestCase): import encodings import formatter import getpass - import htmlentitydefs + import html.entities import imghdr import keyword import linecache -- cgit v0.12