diff options
Diffstat (limited to 'import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py')
| -rw-r--r-- | import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py | 47 |
1 files changed, 31 insertions, 16 deletions
diff --git a/import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py b/import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py index fa5d49875..9c6c14ee6 100644 --- a/import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py +++ b/import-layers/yocto-poky/bitbake/lib/bs4/builder/_lxml.py @@ -4,10 +4,15 @@ __all__ = [ ] from io import BytesIO -from StringIO import StringIO +from io import StringIO import collections from lxml import etree -from bs4.element import Comment, Doctype, NamespacedAttribute +from bs4.element import ( + Comment, + Doctype, + NamespacedAttribute, + ProcessingInstruction, +) from bs4.builder import ( FAST, HTML, @@ -25,8 +30,11 @@ class LXMLTreeBuilderForXML(TreeBuilder): is_xml = True + NAME = "lxml-xml" + ALTERNATE_NAMES = ["xml"] + # Well, it's permissive by XML parser standards. - features = [LXML, XML, FAST, PERMISSIVE] + features = [NAME, LXML, XML, FAST, PERMISSIVE] CHUNK_SIZE = 512 @@ -70,6 +78,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): return (None, tag) def prepare_markup(self, markup, user_specified_encoding=None, + exclude_encodings=None, document_declared_encoding=None): """ :yield: A series of 4-tuples. @@ -78,12 +87,12 @@ class LXMLTreeBuilderForXML(TreeBuilder): Each 4-tuple represents a strategy for parsing the document. """ - 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", @@ -95,14 +104,15 @@ class LXMLTreeBuilderForXML(TreeBuilder): # the document as each one in turn. is_html = not self.is_xml try_encodings = [user_specified_encoding, document_declared_encoding] - detector = EncodingDetector(markup, try_encodings, is_html) + detector = EncodingDetector( + markup, try_encodings, is_html, 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, @@ -117,7 +127,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): 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(str(e)) def close(self): @@ -135,12 +145,12 @@ class LXMLTreeBuilderForXML(TreeBuilder): self.nsmaps.append(None) elif len(nsmap) > 0: # A new namespace mapping has come into play. - inverted_nsmap = dict((value, key) for key, value in nsmap.items()) + inverted_nsmap = dict((value, key) for key, value in list(nsmap.items())) self.nsmaps.append(inverted_nsmap) # 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 @@ -149,7 +159,7 @@ class LXMLTreeBuilderForXML(TreeBuilder): # 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 @@ -189,7 +199,9 @@ class LXMLTreeBuilderForXML(TreeBuilder): self.nsmaps.pop() def pi(self, target, data): - pass + self.soup.endData() + self.soup.handle_data(target + ' ' + data) + self.soup.endData(ProcessingInstruction) def data(self, content): self.soup.handle_data(content) @@ -207,12 +219,15 @@ class LXMLTreeBuilderForXML(TreeBuilder): def test_fragment_to_document(self, fragment): """See `TreeBuilder`.""" - return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment + return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): - features = [LXML, HTML, FAST, PERMISSIVE] + NAME = LXML + ALTERNATE_NAMES = ["lxml-html"] + + features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE] is_xml = False def default_parser(self, encoding): @@ -224,10 +239,10 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML): 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(str(e)) def test_fragment_to_document(self, fragment): """See `TreeBuilder`.""" - return u'<html><body>%s</body></html>' % fragment + return '<html><body>%s</body></html>' % fragment |
