Merge branch 'feature/UpdateBSoup' into dev

CHANGES.md

@@ -1,5 +1,6 @@
 ### 3.32.0 (2024-xx-xx xx:xx:00 UTC)
 
+* Update Beautiful Soup 4.12.2 (30c58a1) to 4.12.3 (7fb5175)
 * Update CacheControl 0.13.1 (783a338) to 0.14.0 (e2be0c2)
 * Update filelock 3.12.4 (c1163ae) to 3.14.0 (8556141)
 * Update idna library 3.4 (cab054c) to 3.7 (1d365e1)

lib/bs4/__init__.py

@@ -15,8 +15,8 @@ documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
 """
 
 __author__ = "Leonard Richardson (leonardr@segfault.org)"
-__version__ = "4.12.2"
+__version__ = "4.12.3"
-__copyright__ = "Copyright (c) 2004-2023 Leonard Richardson"
+__copyright__ = "Copyright (c) 2004-2024 Leonard Richardson"
 # Use of this source code is governed by the MIT license.
 __license__ = "MIT"
 

lib/bs4/builder/__init__.py

@@ -514,15 +514,19 @@ class DetectsXMLParsedAsHTML(object):
     XML_PREFIX_B = b'<?xml'
     
     @classmethod
-    def warn_if_markup_looks_like_xml(cls, markup):
+    def warn_if_markup_looks_like_xml(cls, markup, stacklevel=3):
         """Perform a check on some markup to see if it looks like XML
         that's not XHTML. If so, issue a warning.
 
         This is much less reliable than doing the check while parsing,
         but some of the tree builders can't do that.
 
+        :param stacklevel: The stacklevel of the code calling this
+        function.
+
         :return: True if the markup looks like non-XHTML XML, False
         otherwise.
+
         """
         if isinstance(markup, bytes):
             prefix = cls.XML_PREFIX_B
@@ -535,15 +539,16 @@ class DetectsXMLParsedAsHTML(object):
             and markup.startswith(prefix)
             and not looks_like_html.search(markup[:500])
         ):
-            cls._warn()
+            cls._warn(stacklevel=stacklevel+2)
             return True
         return False
 
     @classmethod
-    def _warn(cls):
+    def _warn(cls, stacklevel=5):
         """Issue a warning about XML being parsed as HTML."""
         warnings.warn(
-            XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
+            XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning,
+            stacklevel=stacklevel
         )
         
     def _initialize_xml_detector(self):
@@ -583,7 +588,7 @@ class DetectsXMLParsedAsHTML(object):
             # We encountered an XML declaration and then a tag other
             # than 'html'. This is a reliable indicator that a
             # non-XHTML document is being parsed as XML.
-            self._warn()
+            self._warn(stacklevel=10)
 
     
 def register_treebuilders_from(module):

lib/bs4/builder/_html5lib.py

@@ -77,7 +77,9 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
 
         # html5lib only parses HTML, so if it's given XML that's worth
         # noting.
-        DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
+        DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
+            markup, stacklevel=3
+        )
 
         yield (markup, None, None, False)
 

lib/bs4/builder/_lxml.py

@@ -179,7 +179,9 @@ class LXMLTreeBuilderForXML(TreeBuilder):
             self.processing_instruction_class = ProcessingInstruction
             # We're in HTML mode, so if we're given XML, that's worth
             # noting.
-            DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
+            DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
+                markup, stacklevel=3
+            )
         else:
             self.processing_instruction_class = XMLProcessingInstruction
 

lib/bs4/formatter.py

@@ -51,7 +51,7 @@ class Formatter(EntitySubstitution):
             void_element_close_prefix='/', cdata_containing_tags=None,
             empty_attributes_are_booleans=False, indent=1,
     ):
-        """Constructor.
+        r"""Constructor.
 
         :param language: This should be Formatter.XML if you are formatting
            XML markup and Formatter.HTML if you are formatting HTML markup.
@@ -76,7 +76,7 @@ class Formatter(EntitySubstitution):
             negative, or "" will only insert newlines. Using a
             positive integer indent indents that many spaces per
             level. If indent is a string (such as "\t"), that string
-            is used to indent each level. The default behavior to
+            is used to indent each level. The default behavior is to
             indent one space per level.
         """
         self.language = language