Merge remote-tracking branch 'upstream/3.10' into backport-f04bea4-3.10

Author: hartwork

Doc/Makefile

@@ -155,10 +155,20 @@ venv:
 		echo "The venv has been created in the $(VENVDIR) directory"; \
 	fi
 
+.PHONY: dist-no-html
+dist-no-html: dist-text dist-epub dist-texinfo
+
 dist:
 	rm -rf dist
 	mkdir -p dist
-
+	$(MAKE) dist-html
+	$(MAKE) dist-text
+	$(MAKE) dist-pdf
+	$(MAKE) dist-epub
+	$(MAKE) dist-texinfo
+
+.PHONY: dist-html
+dist-html:
 	# archive the HTML
 	make html
 	cp -pPR build/html dist/python-$(DISTVERSION)-docs-html
@@ -168,6 +178,8 @@ dist:
 	rm -r dist/python-$(DISTVERSION)-docs-html
 	rm dist/python-$(DISTVERSION)-docs-html.tar
 
+.PHONY: dist-text
+dist-text:
 	# archive the text build
 	make text
 	cp -pPR build/text dist/python-$(DISTVERSION)-docs-text
@@ -177,6 +189,8 @@ dist:
 	rm -r dist/python-$(DISTVERSION)-docs-text
 	rm dist/python-$(DISTVERSION)-docs-text.tar
 
+.PHONY: dist-pdf
+dist-pdf:
 	# archive the A4 latex
 	rm -rf build/latex
 	make latex PAPER=a4
@@ -193,11 +207,15 @@ dist:
 	cp build/latex/docs-pdf.zip dist/python-$(DISTVERSION)-docs-pdf-letter.zip
 	cp build/latex/docs-pdf.tar.bz2 dist/python-$(DISTVERSION)-docs-pdf-letter.tar.bz2
 
+.PHONY: dist-epub
+dist-epub:
 	# copy the epub build
 	rm -rf build/epub
 	make epub
 	cp -pPR build/epub/Python.epub dist/python-$(DISTVERSION)-docs.epub
 
+.PHONY: dist-texinfo
+dist-texinfo:
 	# archive the texinfo build
 	rm -rf build/texinfo
 	make texinfo
@@ -225,11 +243,11 @@ serve:
 
 # for development releases: always build
 autobuild-dev:
-	make dist SPHINXOPTS='$(SPHINXOPTS) -Ea -A daily=1'
+	make dist-no-html SPHINXOPTS='$(SPHINXOPTS) -Ea -A daily=1'
 
 # for quick rebuilds (HTML only)
 autobuild-dev-html:
-	make html SPHINXOPTS='$(SPHINXOPTS) -Ea -A daily=1'
+	make dist-html SPHINXOPTS='$(SPHINXOPTS) -Ea -A daily=1'
 
 # for stable releases: only build if not in pre-release stage (alpha, beta)
 # release candidate downloads are okay, since the stable tree can be in that stage

Doc/library/html.parser.rst

@@ -15,14 +15,18 @@
 This module defines a class :class:`HTMLParser` which serves as the basis for
 parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.
 
-.. class:: HTMLParser(*, convert_charrefs=True)
+.. class:: HTMLParser(*, convert_charrefs=True, scripting=False)
 
    Create a parser instance able to parse invalid markup.
 
-   If *convert_charrefs* is ``True`` (the default), all character
-   references (except the ones in ``script``/``style`` elements) are
+   If *convert_charrefs* is true (the default), all character
+   references (except the ones in elements like ``script`` and ``style``) are
    automatically converted to the corresponding Unicode characters.
 
+   If *scripting* is false (the default), the content of the ``noscript``
+   element is parsed normally; if it's true, it's returned as is without
+   being parsed.
+
    An :class:`.HTMLParser` instance is fed HTML data and calls handler methods
    when start tags, end tags, text, comments, and other markup elements are
    encountered.  The user should subclass :class:`.HTMLParser` and override its
@@ -37,6 +41,9 @@ parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.
    .. versionchanged:: 3.5
       The default value for argument *convert_charrefs* is now ``True``.
 
+   .. versionchanged:: 3.10.20
+      Added the *scripting* parameter.
+
 
 Example HTML Parser Application
 -------------------------------
@@ -159,24 +166,24 @@ implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`):
 .. method:: HTMLParser.handle_data(data)
 
    This method is called to process arbitrary data (e.g. text nodes and the
-   content of ``<script>...</script>`` and ``<style>...</style>``).
+   content of elements like ``script`` and ``style``).
 
 
 .. method:: HTMLParser.handle_entityref(name)
 
    This method is called to process a named character reference of the form
    ``&name;`` (e.g. ``&gt;``), where *name* is a general entity reference
-   (e.g. ``'gt'``).  This method is never called if *convert_charrefs* is
-   ``True``.
+   (e.g. ``'gt'``).
+   This method is only called if *convert_charrefs* is false.
 
 
 .. method:: HTMLParser.handle_charref(name)
 
    This method is called to process decimal and hexadecimal numeric character
    references of the form ``&#NNN;`` and ``&#xNNN;``.  For example, the decimal
    equivalent for ``&gt;`` is ``&#62;``, whereas the hexadecimal is ``&#x3E;``;
-   in this case the method will receive ``'62'`` or ``'x3E'``.  This method
-   is never called if *convert_charrefs* is ``True``.
+   in this case the method will receive ``'62'`` or ``'x3E'``.
+   This method is only called if *convert_charrefs* is false.
 
 
 .. method:: HTMLParser.handle_comment(data)
@@ -284,8 +291,8 @@ Parsing an element with a few attributes and a title::
    Data     : Python
    End tag  : h1
 
-The content of ``script`` and ``style`` elements is returned as is, without
-further parsing::
+The content of elements like ``script`` and ``style`` is returned as is,
+without further parsing::
 
    >>> parser.feed('<style type="text/css">#python { color: green }</style>')
    Start tag: style
@@ -294,10 +301,10 @@ further parsing::
    End tag  : style
 
    >>> parser.feed('<script type="text/javascript">'
-   ...             'alert("<strong>hello!</strong>");</script>')
+   ...             'alert("<strong>hello! &#9786;</strong>");</script>')
    Start tag: script
         attr: ('type', 'text/javascript')
-   Data     : alert("<strong>hello!</strong>");
+   Data     : alert("<strong>hello! &#9786;</strong>");
    End tag  : script
 
 Parsing comments::
@@ -317,7 +324,7 @@ correct char (note: these 3 references are all equivalent to ``'>'``)::
 
 Feeding incomplete chunks to :meth:`~HTMLParser.feed` works, but
 :meth:`~HTMLParser.handle_data` might be called more than once
-(unless *convert_charrefs* is set to ``True``)::
+if *convert_charrefs* is false::
 
    >>> for chunk in ['<sp', 'an>buff', 'ered ', 'text</s', 'pan>']:
    ...     parser.feed(chunk)

Include/patchlevel.h

@@ -18,12 +18,12 @@
 /*--start constants--*/
 #define PY_MAJOR_VERSION        3
 #define PY_MINOR_VERSION        10
-#define PY_MICRO_VERSION        18
+#define PY_MICRO_VERSION        19
 #define PY_RELEASE_LEVEL        PY_RELEASE_LEVEL_FINAL
 #define PY_RELEASE_SERIAL       0
 
 /* Version as a string */
-#define PY_VERSION              "3.10.18+"
+#define PY_VERSION              "3.10.19+"
 /*--end constants--*/
 
 /* Version as a single 4-byte hex number, e.g. 0x010502B2 == 1.5.2b2.

Lib/html/parser.py

@@ -109,16 +109,24 @@ class HTMLParser(_markupbase.ParserBase):
     argument.
     """
 
-    CDATA_CONTENT_ELEMENTS = ("script", "style")
+    # See the HTML5 specs section "13.4 Parsing HTML fragments".
+    # https://html.spec.whatwg.org/multipage/parsing.html#parsing-html-fragments
+    # CDATA_CONTENT_ELEMENTS are parsed in RAWTEXT mode
+    CDATA_CONTENT_ELEMENTS = ("script", "style", "xmp", "iframe", "noembed", "noframes")
     RCDATA_CONTENT_ELEMENTS = ("textarea", "title")
 
-    def __init__(self, *, convert_charrefs=True):
+    def __init__(self, *, convert_charrefs=True, scripting=False):
         """Initialize and reset this instance.
 
-        If convert_charrefs is True (the default), all character references
+        If convert_charrefs is true (the default), all character references
         are automatically converted to the corresponding Unicode characters.
+
+        If *scripting* is false (the default), the content of the
+        ``noscript`` element is parsed normally; if it's true,
+        it's returned as is without being parsed.
         """
         self.convert_charrefs = convert_charrefs
+        self.scripting = scripting
         self.reset()
 
     def reset(self):
@@ -127,6 +135,7 @@ def reset(self):
         self.lasttag = '???'
         self.interesting = interesting_normal
         self.cdata_elem = None
+        self._support_cdata = True
         self._escapable = True
         _markupbase.ParserBase.reset(self)
 
@@ -152,7 +161,9 @@ def get_starttag_text(self):
     def set_cdata_mode(self, elem, *, escapable=False):
         self.cdata_elem = elem.lower()
         self._escapable = escapable
-        if escapable and not self.convert_charrefs:
+        if self.cdata_elem == 'plaintext':
+            self.interesting = re.compile(r'\Z')
+        elif escapable and not self.convert_charrefs:
             self.interesting = re.compile(r'&|</%s(?=[\t\n\r\f />])' % self.cdata_elem,
                                           re.IGNORECASE|re.ASCII)
         else:
@@ -164,6 +175,19 @@ def clear_cdata_mode(self):
         self.cdata_elem = None
         self._escapable = True
 
+    def _set_support_cdata(self, flag=True):
+        """Enable or disable support of the CDATA sections.
+        If enabled, "<[CDATA[" starts a CDATA section which ends with "]]>".
+        If disabled, "<[CDATA[" starts a bogus comments which ends with ">".
+
+        This method is not called by default. Its purpose is to be called
+        in custom handle_starttag() and handle_endtag() methods, with
+        value that depends on the adjusted current node.
+        See https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
+        for details.
+        """
+        self._support_cdata = flag
+
     # Internal -- handle data as far as reasonable.  May leave state
     # and data to be processed by a subsequent call.  If 'end' is
     # true, force handling all data as if followed by EOF marker.
@@ -238,7 +262,7 @@ def goahead(self, end):
                                 j -= len(suffix)
                                 break
                         self.handle_comment(rawdata[i+4:j])
-                    elif startswith("<![CDATA[", i):
+                    elif startswith("<![CDATA[", i) and self._support_cdata:
                         self.unknown_decl(rawdata[i+3:])
                     elif rawdata[i:i+9].lower() == '<!doctype':
                         self.handle_decl(rawdata[i+2:])
@@ -314,15 +338,28 @@ def parse_html_declaration(self, i):
         if rawdata[i:i+4] == '<!--':
             # this case is actually already handled in goahead()
             return self.parse_comment(i)
-        elif rawdata[i:i+3] == '<![':
-            return self.parse_marked_section(i)
+        elif rawdata[i:i+9] == '<![CDATA[' and self._support_cdata:
+            j = rawdata.find(']]>', i+9)
+            if j < 0:
+                return -1
+            self.unknown_decl(rawdata[i+3: j])
+            return j + 3
         elif rawdata[i:i+9].lower() == '<!doctype':
             # find the closing >
             gtpos = rawdata.find('>', i+9)
             if gtpos == -1:
                 return -1
             self.handle_decl(rawdata[i+2:gtpos])
             return gtpos+1
+        elif rawdata[i:i+3] == '<![':
+            j = rawdata.find('>', i+3)
+            if j < 0:
+                return -1
+            if rawdata[j-1] == ']':
+                self.unknown_decl(rawdata[i+3: j-1])
+            else:
+                self.handle_comment(rawdata[i+2: j])
+            return j + 1
         else:
             return self.parse_bogus_comment(i)
 
@@ -414,8 +451,10 @@ def parse_starttag(self, i):
             self.handle_startendtag(tag, attrs)
         else:
             self.handle_starttag(tag, attrs)
-            if tag in self.CDATA_CONTENT_ELEMENTS:
-                self.set_cdata_mode(tag)
+            if (tag in self.CDATA_CONTENT_ELEMENTS or
+                (self.scripting and tag == "noscript") or
+                tag == "plaintext"):
+                self.set_cdata_mode(tag, escapable=False)
             elif tag in self.RCDATA_CONTENT_ELEMENTS:
                 self.set_cdata_mode(tag, escapable=True)
         return endpos