lib/bs4/dammit.py

7 XML or HTML to reflect a new encoding; that's the tree builder's job.
23         return cchardet.detect(s)['encoding']
31             return chardet.detect(s)['encoding']
40     r'^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I)
177         This differs from data.encode(encoding, 'xmlcharrefreplace')
197     2. An encoding declared within the bytestring itself, either in an
202     3. An encoding detected through textual analysis by chardet,
221     def _usable(self, encoding, tried):  argument
222         if encoding is not None:
223             encoding = encoding.lower()
224             if encoding in self.exclude_encodings:
226             if encoding not in tried:
227                 tried.add(encoding)
240         # that indicated its encoding?
244         # Look within the document for an XML or HTML encoding
253         # encoding.
266         """If a byte-order mark is present, strip it and return the encoding it implies."""
267         encoding = None
270             return data, encoding
273             encoding = 'utf-16be'
277             encoding = 'utf-16le'
280             encoding = 'utf-8'
283             encoding = 'utf-32be'
286             encoding = 'utf-32le'
288         return data, encoding
292         """Given a document, tries to find its declared encoding.
294         An XML encoding is declared at the beginning of the document.
296         An HTML encoding is declared in a <meta> tag, hopefully near the
317     """A class for detecting the encoding of a *ML document and
318     converting it to a Unicode string. If the source encoding is
352         # The encoding detector may have stripped a byte-order mark.
357         for encoding in self.detector.encodings:
359             u = self._convert_from(encoding)
367             for encoding in self.detector.encodings:
368                 if encoding != "ascii":
369                     u = self._convert_from(encoding, "replace")
407         # Convert smart quotes to HTML if coming from an encoding
425         #print "Correct encoding: %s" % proposed
428     def _to_unicode(self, data, encoding, errors="strict"):  argument
429         '''Given a string and its encoding, decodes the string into Unicode.
430         %encoding is a string recognized by encodings.aliases'''
431         return str(data, encoding, errors)
773         """Fix characters from one encoding embedded in some other encoding.
793                 "UTF-8 is the only currently supported main encoding.")