Merge branch 'feature/UpdateHtml5lib' into dev

CHANGES.md

@@ -1,5 +1,6 @@
 ### 3.28.0 (2023-xx-xx xx:xx:00 UTC)
 
+* Update html5lib 1.1 (f87487a) to 1.2-dev (3e500bb)
 * Update package resource API 63.2.0 (3ae44cd) to 67.3.2 (b9bf2ec)
 * Change remove calls to legacy py2 fix encoding function
 * Change requirements for pure py3

lib/html5lib/__init__.py

@@ -32,4 +32,4 @@ __all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
 
 # this has to be at the top level, see how setup.py parses this
 #: Distribution version number.
-__version__ = "1.1"
+__version__ = "1.2-dev"

lib/html5lib/_ihatexml.py

@@ -104,18 +104,15 @@ def charStringToList(chars):
     charRanges = [item.strip() for item in chars.split(" | ")]
     rv = []
     for item in charRanges:
-        foundMatch = False
         for regexp in (reChar, reCharRange):
             match = regexp.match(item)
             if match is not None:
                 rv.append([hexToInt(item) for item in match.groups()])
                 if len(rv[-1]) == 1:
                     rv[-1] = rv[-1] * 2
-                foundMatch = True
                 break
-        if not foundMatch:
+        else:
             assert len(item) == 1
-
             rv.append([ord(item)] * 2)
     rv = normaliseCharList(rv)
     return rv

lib/html5lib/_inputstream.py

@@ -324,7 +324,7 @@ class HTMLUnicodeInputStream(object):
         except KeyError:
             if __debug__:
                 for c in characters:
-                    assert(ord(c) < 128)
+                    assert ord(c) < 128
             regex = "".join(["\\x%02x" % ord(c) for c in characters])
             if not opposite:
                 regex = "^%s" % regex

lib/html5lib/constants.py

@@ -557,23 +557,36 @@ headingElements = (
 )
 
 voidElements = frozenset([
+    "area",
     "base",
-    "command",
+    "br",
-    "event-source",
+    "col",
+    "command",  # removed ^1
+    "embed",
+    "event-source",  # renamed and later removed ^2
+    "hr",
+    "img",
+    "input",
     "link",
     "meta",
-    "hr",
+    "param",  # deprecated ^3
-    "br",
-    "img",
-    "embed",
-    "param",
-    "area",
-    "col",
-    "input",
     "source",
-    "track"
+    "track",
+    "wbr",
 ])
 
+# Removals and deprecations in the HTML 5 spec:
+# ^1: command
+#     http://lists.whatwg.org/pipermail/whatwg-whatwg.org/2012-December/038472.html
+#     https://github.com/whatwg/html/commit/9e2e25f4ae90969a7c64e0763c98548a35b50af8
+# ^2: event-source
+#     renamed to eventsource in 7/2008:
+#     https://github.com/whatwg/html/commit/d157945d0285b4463a04b57318da0c4b300a99e7
+#     removed entirely in 2/2009:
+#     https://github.com/whatwg/html/commit/43cbdbfbb7eb74b0d65e0f4caab2020c0b2a16ff
+# ^3: param
+#     https://developer.mozilla.org/en-US/docs/Web/HTML/Element/param
+
 cdataElements = frozenset(['title', 'textarea'])
 
 rcdataElements = frozenset([
@@ -604,6 +617,7 @@ booleanAttributes = {
     "button": frozenset(["disabled", "autofocus"]),
     "input": frozenset(["disabled", "readonly", "required", "autofocus", "checked", "ismap"]),
     "select": frozenset(["disabled", "readonly", "autofocus", "multiple"]),
+    "ol": frozenset(["reversed"]),
     "output": frozenset(["disabled", "readonly"]),
     "iframe": frozenset(["seamless"]),
 }

lib/html5lib/filters/sanitizer.py

@@ -113,6 +113,7 @@ allowed_elements = frozenset((
     (namespaces['html'], 'strike'),
     (namespaces['html'], 'strong'),
     (namespaces['html'], 'sub'),
+    (namespaces['html'], 'summary'),
     (namespaces['html'], 'sup'),
     (namespaces['html'], 'table'),
     (namespaces['html'], 'tbody'),
@@ -128,6 +129,7 @@ allowed_elements = frozenset((
     (namespaces['html'], 'ul'),
     (namespaces['html'], 'var'),
     (namespaces['html'], 'video'),
+    (namespaces['html'], 'wbr'),
     (namespaces['mathml'], 'maction'),
     (namespaces['mathml'], 'math'),
     (namespaces['mathml'], 'merror'),
@@ -363,6 +365,7 @@ allowed_attributes = frozenset((
     (None, 'maxsize'),
     (None, 'minsize'),
     (None, 'other'),
+    (None, 'reversed'),
     (None, 'rowalign'),
     (None, 'rowalign'),
     (None, 'rowalign'),
@@ -373,6 +376,7 @@ allowed_attributes = frozenset((
     (None, 'scriptlevel'),
     (None, 'selection'),
     (None, 'separator'),
+    (None, 'start'),
     (None, 'stretchy'),
     (None, 'width'),
     (None, 'width'),
@@ -594,6 +598,10 @@ allowed_css_properties = frozenset((
     'height',
     'letter-spacing',
     'line-height',
+    'max-height',
+    'min-height',
+    'max-width',
+    'min-width',
     'overflow',
     'pause',
     'pause-after',

lib/html5lib/html5parser.py

@@ -115,6 +115,9 @@ class HTMLParser(object):
 
         if tree is None:
             tree = treebuilders.getTreeBuilder("etree")
+        elif isinstance(tree, str):
+            tree = treebuilders.getTreeBuilder(tree)
+
         self.tree = tree(namespaceHTMLElements)
         self.errors = []
 
@@ -1002,8 +1005,8 @@ def getPhases(debug):
             self.tree.insertText(token["data"])
             # This must be bad for performance
             if (self.parser.framesetOK and
-                any([char not in spaceCharacters
+                any(char not in spaceCharacters
-                     for char in token["data"]])):
+                    for char in token["data"])):
                 self.parser.framesetOK = False
 
         def processSpaceCharactersNonPre(self, token):
@@ -1850,7 +1853,7 @@ def getPhases(debug):
 
         def flushCharacters(self):
             data = "".join([item["data"] for item in self.characterTokens])
-            if any([item not in spaceCharacters for item in data]):
+            if any(item not in spaceCharacters for item in data):
                 token = {"type": tokenTypes["Characters"], "data": data}
                 self.parser.phases["inTable"].insertText(token)
             elif data:

lib/html5lib/serializer.py

@@ -222,14 +222,14 @@ class HTMLSerializer(object):
         self.strict = False
 
     def encode(self, string):
-        assert(isinstance(string, text_type))
+        assert isinstance(string, text_type)
         if self.encoding:
             return string.encode(self.encoding, "htmlentityreplace")
         else:
             return string
 
     def encodeStrict(self, string):
-        assert(isinstance(string, text_type))
+        assert isinstance(string, text_type)
         if self.encoding:
             return string.encode(self.encoding, "strict")
         else:

lib/html5lib/treebuilders/base.py

@@ -121,6 +121,7 @@ class Node(object):
 
 class ActiveFormattingElements(list):
     def append(self, node):
+        """Append node to the end of the list."""
         equalCount = 0
         if node != Marker:
             for element in self[::-1]:

lib/html5lib/treebuilders/etree.py

@@ -108,7 +108,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
             node.parent = None
 
         def insertText(self, data, insertBefore=None):
-            if not(len(self._element)):
+            if not len(self._element):
                 if not self._element.text:
                     self._element.text = ""
                 self._element.text += data
@@ -201,7 +201,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
         rv = []
 
         def serializeElement(element, indent=0):
-            if not(hasattr(element, "tag")):
+            if not hasattr(element, "tag"):
                 element = element.getroot()
             if element.tag == "<!DOCTYPE>":
                 if element.get("publicId") or element.get("systemId"):

lib/html5lib/treewalkers/etree.py

@@ -37,7 +37,7 @@ def getETreeBuilder(ElementTreeImplementation):
                 else:
                     node = elt
 
-            if not(hasattr(node, "tag")):
+            if not hasattr(node, "tag"):
                 node = node.getroot()
 
             if node.tag in ("DOCUMENT_ROOT", "DOCUMENT_FRAGMENT"):