mirrors/poky
1
0
Fork 0
mirror of https://git.yoctoproject.org/poky synced 2026-05-30 00:20:08 +00:00
Code Issues Projects Releases Wiki Activity

bitbake: bitbake/bs4: Upgrade 4.3.2 -> 4.4.1 (python 3 version)

Browse Source 
Upgrade to 4.4.1 which has been run through 2to3 as per the maintainers
recommendation for v3 use.

(Bitbake rev: 2f4b98af93c971a8c466ffaf3c09cca0edb6e3ad)

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
This commit is contained in:
Richard Purdie
2016-05-06 09:06:51 +01:00
parent 4f8959324d
commit 822eabf32d
15 changed files with 972 additions and 361 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bitbake/lib/bs4/builder/_html5lib.py
+59 -12
View File
@@ -2,6 +2,7 @@ __all__ = [
'HTML5TreeBuilder',
]
from pdb import set_trace
import warnings
from bs4.builder import (
PERMISSIVE,
@@ -9,7 +10,10 @@ from bs4.builder import (
HTML_5,
HTMLTreeBuilder,
)
from bs4.element import NamespacedAttribute
from bs4.element import (
NamespacedAttribute,
whitespace_re,
)
import html5lib
from html5lib.constants import namespaces
from bs4.element import (
@@ -22,11 +26,20 @@ from bs4.element import (
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree."""
features = ['html5lib', PERMISSIVE, HTML_5, HTML]
NAME = "html5lib"
def prepare_markup(self, markup, user_specified_encoding):
features = [NAME, PERMISSIVE, HTML_5, HTML]
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
# document_declared_encoding and exclude_encodings aren't used
# ATM because the html5lib TreeBuilder doesn't use
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
yield (markup, None, None, False)
# These methods are defined by Beautiful Soup.
@@ -37,7 +50,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
doc = parser.parse(markup, encoding=self.user_specified_encoding)
# 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
@@ -51,7 +64,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><head></head><body>%s</body></html>' % fragment
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
@@ -101,7 +114,16 @@ class AttrList(object):
def __iter__(self):
return list(self.attrs.items()).__iter__()
def __setitem__(self, name, value):
"set attr", name, value
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = HTML5TreeBuilder.cdata_list_attributes
if (name in list_attr['*']
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = whitespace_re.split(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
@@ -124,7 +146,7 @@ class Element(html5lib.treebuilders._base.Node):
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.
@@ -139,7 +161,7 @@ class Element(html5lib.treebuilders._base.Node):
else:
child = node.element
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 and self.element.contents
@@ -152,7 +174,7 @@ class Element(html5lib.treebuilders._base.Node):
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)
@@ -161,6 +183,12 @@ class Element(html5lib.treebuilders._base.Node):
# immediately after the parent, if it has no children.)
if self.element.contents:
most_recent_element = self.element._last_descendant(False)
elif self.element.next_element is not None:
# Something from further ahead in the parse tree is
# being inserted into this earlier element. This is
# very annoying because it means an expensive search
# for the last element in the tree.
most_recent_element = self.soup._last_descendant()
else:
most_recent_element = self.element
@@ -172,6 +200,7 @@ class Element(html5lib.treebuilders._base.Node):
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
@@ -183,7 +212,7 @@ class Element(html5lib.treebuilders._base.Node):
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.
@@ -218,6 +247,9 @@ class Element(html5lib.treebuilders._base.Node):
def reparentChildren(self, new_parent):
"""Move all of this tag's children into another tag."""
# print "MOVE", self.element.contents
# print "FROM", self.element
# print "TO", new_parent.element
element = self.element
new_parent_element = new_parent.element
# Determine what this tag's next_element will be once all the children
@@ -236,17 +268,28 @@ class Element(html5lib.treebuilders._base.Node):
new_parents_last_descendant_next_element = new_parent_element.next_element
to_append = element.contents
append_after = new_parent.element.contents
append_after = new_parent_element.contents
if len(to_append) > 0:
# Set the first child's previous_element and previous_sibling
# to elements within the new parent
first_child = to_append[0]
first_child.previous_element = new_parents_last_descendant
if new_parents_last_descendant:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child:
new_parents_last_child.next_sibling = first_child
# Fix the last child's next_element and next_sibling
last_child = to_append[-1]
last_child.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element:
new_parents_last_descendant_next_element.previous_element = last_child
last_child.next_sibling = None
for child in to_append:
@@ -257,6 +300,10 @@ class Element(html5lib.treebuilders._base.Node):
element.contents = []
element.next_element = final_next_element
# print "DONE WITH MOVE"
# print "FROM", self.element
# print "TO", new_parent_element
def cloneNode(self):
tag = self.soup.new_tag(self.element.name, self.namespace)
node = Element(tag, self.soup, self.namespace)