bpo-36673: Implement comment/PI parsing support for the TreeBuilder in ElementTree. (#12883)

* bpo-36673: Implement comment/PI parsing support for the TreeBuilder in ElementTree.

* bpo-36673: Rewrite the comment/PI factory handling for the TreeBuilder in "_elementtree" to make it use the same factories as the ElementTree module, and to make it explicit when the comments/PIs are inserted into the tree and when they are not (which is the default).

Doc/library/xml.etree.elementtree.rst

@@ -523,8 +523,9 @@ Functions
    Parses an XML section into an element tree incrementally, and reports what's
    going on to the user.  *source* is a filename or :term:`file object`
    containing XML data.  *events* is a sequence of events to report back.  The
-   supported events are the strings ``"start"``, ``"end"``, ``"start-ns"`` and
+   supported events are the strings ``"start"``, ``"end"``, ``"comment"``,
-   ``"end-ns"`` (the "ns" events are used to get detailed namespace
+   ``"pi"``, ``"start-ns"`` and ``"end-ns"``
+   (the "ns" events are used to get detailed namespace
    information).  If *events* is omitted, only ``"end"`` events are reported.
    *parser* is an optional parser instance.  If not given, the standard
    :class:`XMLParser` parser is used.  *parser* must be a subclass of
@@ -549,6 +550,10 @@ Functions
    .. deprecated:: 3.4
       The *parser* argument.
 
+   .. versionchanged:: 3.8
+      The ``comment`` and ``pi`` events were added.
+
+
 .. function:: parse(source, parser=None)
 
    Parses an XML section into an element tree.  *source* is a filename or file
@@ -1021,14 +1026,24 @@ TreeBuilder Objects
 ^^^^^^^^^^^^^^^^^^^
 
 
-.. class:: TreeBuilder(element_factory=None)
+.. class:: TreeBuilder(element_factory=None, *, comment_factory=None, \
+                       pi_factory=None, insert_comments=False, insert_pis=False)
 
    Generic element structure builder.  This builder converts a sequence of
-   start, data, and end method calls to a well-formed element structure.  You
+   start, data, end, comment and pi method calls to a well-formed element
-   can use this class to build an element structure using a custom XML parser,
+   structure.  You can use this class to build an element structure using
-   or a parser for some other XML-like format.  *element_factory*, when given,
+   a custom XML parser, or a parser for some other XML-like format.
-   must be a callable accepting two positional arguments: a tag and
+
-   a dict of attributes.  It is expected to return a new element instance.
+   *element_factory*, when given, must be a callable accepting two positional
+   arguments: a tag and a dict of attributes.  It is expected to return a new
+   element instance.
+
+   The *comment_factory* and *pi_factory* functions, when given, should behave
+   like the :func:`Comment` and :func:`ProcessingInstruction` functions to
+   create comments and processing instructions.  When not given, the default
+   factories will be used.  When *insert_comments* and/or *insert_pis* is true,
+   comments/pis will be inserted into the tree if they appear within the root
+   element (but not outside of it).
 
    .. method:: close()
 
@@ -1054,6 +1069,22 @@ TreeBuilder Objects
       containing element attributes.  Returns the opened element.
 
 
+   .. method:: comment(text)
+
+      Creates a comment with the given *text*.  If ``insert_comments`` is true,
+      this will also add it to the tree.
+
+      .. versionadded:: 3.8
+
+
+   .. method:: pi(target, text)
+
+      Creates a comment with the given *target* name and *text*.  If
+      ``insert_pis`` is true, this will also add it to the tree.
+
+      .. versionadded:: 3.8
+
+
    In addition, a custom :class:`TreeBuilder` object can provide the
    following method:
 
@@ -1150,9 +1181,9 @@ XMLPullParser Objects
    callback target, :class:`XMLPullParser` collects an internal list of parsing
    events and lets the user read from it. *events* is a sequence of events to
    report back.  The supported events are the strings ``"start"``, ``"end"``,
-   ``"start-ns"`` and ``"end-ns"`` (the "ns" events are used to get detailed
+   ``"comment"``, ``"pi"``, ``"start-ns"`` and ``"end-ns"`` (the "ns" events
-   namespace information).  If *events* is omitted, only ``"end"`` events are
+   are used to get detailed namespace information).  If *events* is omitted,
-   reported.
+   only ``"end"`` events are reported.
 
    .. method:: feed(data)
 
@@ -1171,7 +1202,13 @@ XMLPullParser Objects
       data fed to the
       parser.  The iterator yields ``(event, elem)`` pairs, where *event* is a
       string representing the type of event (e.g. ``"end"``) and *elem* is the
-      encountered :class:`Element` object.
+      encountered :class:`Element` object, or other context value as follows.
+
+      * ``start``, ``end``: the current Element.
+      * ``comment``, ``pi``: the current comment / processing instruction
+      * ``start-ns``: a tuple ``(prefix, uri)`` naming the declared namespace
+        mapping.
+      * ``end-ns``: :const:`None` (this may change in a future version)
 
       Events provided in a previous call to :meth:`read_events` will not be
       yielded again.  Events are consumed from the internal queue only when
@@ -1191,6 +1228,10 @@ XMLPullParser Objects
 
    .. versionadded:: 3.4
 
+   .. versionchanged:: 3.8
+      The ``comment`` and ``pi`` events were added.
+
+
 Exceptions
 ^^^^^^^^^^
 

Lib/test/test_xml_etree.py

@@ -1194,6 +1194,12 @@ class XMLPullParserTest(unittest.TestCase):
             for i in range(0, len(data), chunk_size):
                 parser.feed(data[i:i+chunk_size])
 
+    def assert_events(self, parser, expected):
+        self.assertEqual(
+            [(event, (elem.tag, elem.text))
+             for event, elem in parser.read_events()],
+            expected)
+
     def assert_event_tags(self, parser, expected):
         events = parser.read_events()
         self.assertEqual([(action, elem.tag) for action, elem in events],
@@ -1276,8 +1282,10 @@ class XMLPullParserTest(unittest.TestCase):
         self.assert_event_tags(parser, [])
 
         parser = ET.XMLPullParser(events=('start', 'end'))
-        self._feed(parser, "<!-- comment -->\n")
+        self._feed(parser, "<!-- text here -->\n")
-        self.assert_event_tags(parser, [])
+        self.assert_events(parser, [])
+
+        parser = ET.XMLPullParser(events=('start', 'end'))
         self._feed(parser, "<root>\n")
         self.assert_event_tags(parser, [('start', 'root')])
         self._feed(parser, "<element key='value'>text</element")
@@ -1314,6 +1322,33 @@ class XMLPullParserTest(unittest.TestCase):
         self._feed(parser, "</root>")
         self.assertIsNone(parser.close())
 
+    def test_events_comment(self):
+        parser = ET.XMLPullParser(events=('start', 'comment', 'end'))
+        self._feed(parser, "<!-- text here -->\n")
+        self.assert_events(parser, [('comment', (ET.Comment, ' text here '))])
+        self._feed(parser, "<!-- more text here -->\n")
+        self.assert_events(parser, [('comment', (ET.Comment, ' more text here '))])
+        self._feed(parser, "<root-tag>text")
+        self.assert_event_tags(parser, [('start', 'root-tag')])
+        self._feed(parser, "<!-- inner comment-->\n")
+        self.assert_events(parser, [('comment', (ET.Comment, ' inner comment'))])
+        self._feed(parser, "</root-tag>\n")
+        self.assert_event_tags(parser, [('end', 'root-tag')])
+        self._feed(parser, "<!-- outer comment -->\n")
+        self.assert_events(parser, [('comment', (ET.Comment, ' outer comment '))])
+
+        parser = ET.XMLPullParser(events=('comment',))
+        self._feed(parser, "<!-- text here -->\n")
+        self.assert_events(parser, [('comment', (ET.Comment, ' text here '))])
+
+    def test_events_pi(self):
+        parser = ET.XMLPullParser(events=('start', 'pi', 'end'))
+        self._feed(parser, "<?pitarget?>\n")
+        self.assert_events(parser, [('pi', (ET.PI, 'pitarget'))])
+        parser = ET.XMLPullParser(events=('pi',))
+        self._feed(parser, "<?pitarget some text ?>\n")
+        self.assert_events(parser, [('pi', (ET.PI, 'pitarget some text '))])
+
     def test_events_sequence(self):
         # Test that events can be some sequence that's not just a tuple or list
         eventset = {'end', 'start'}
@@ -1333,7 +1368,6 @@ class XMLPullParserTest(unittest.TestCase):
         self._feed(parser, "<foo>bar</foo>")
         self.assert_event_tags(parser, [('start', 'foo'), ('end', 'foo')])
 
-
     def test_unknown_event(self):
         with self.assertRaises(ValueError):
             ET.XMLPullParser(events=('start', 'end', 'bogus'))
@@ -2741,6 +2775,33 @@ class TreeBuilderTest(unittest.TestCase):
         parser.feed(self.sample1)
         self.assertIsNone(parser.close())
 
+    def test_treebuilder_comment(self):
+        b = ET.TreeBuilder()
+        self.assertEqual(b.comment('ctext').tag, ET.Comment)
+        self.assertEqual(b.comment('ctext').text, 'ctext')
+
+        b = ET.TreeBuilder(comment_factory=ET.Comment)
+        self.assertEqual(b.comment('ctext').tag, ET.Comment)
+        self.assertEqual(b.comment('ctext').text, 'ctext')
+
+        b = ET.TreeBuilder(comment_factory=len)
+        self.assertEqual(b.comment('ctext'), len('ctext'))
+
+    def test_treebuilder_pi(self):
+        b = ET.TreeBuilder()
+        self.assertEqual(b.pi('target', None).tag, ET.PI)
+        self.assertEqual(b.pi('target', None).text, 'target')
+
+        b = ET.TreeBuilder(pi_factory=ET.PI)
+        self.assertEqual(b.pi('target').tag, ET.PI)
+        self.assertEqual(b.pi('target').text, "target")
+        self.assertEqual(b.pi('pitarget', ' text ').tag, ET.PI)
+        self.assertEqual(b.pi('pitarget', ' text ').text, "pitarget  text ")
+
+        b = ET.TreeBuilder(pi_factory=lambda target, text: (len(target), text))
+        self.assertEqual(b.pi('target'), (len('target'), None))
+        self.assertEqual(b.pi('pitarget', ' text '), (len('pitarget'), ' text '))
+
     def test_treebuilder_elementfactory_none(self):
         parser = ET.XMLParser(target=ET.TreeBuilder(element_factory=None))
         parser.feed(self.sample1)
@@ -2761,6 +2822,21 @@ class TreeBuilderTest(unittest.TestCase):
         e = parser.close()
         self._check_sample1_element(e)
 
+    def test_subclass_comment_pi(self):
+        class MyTreeBuilder(ET.TreeBuilder):
+            def foobar(self, x):
+                return x * 2
+
+        tb = MyTreeBuilder(comment_factory=ET.Comment, pi_factory=ET.PI)
+        self.assertEqual(tb.foobar(10), 20)
+
+        parser = ET.XMLParser(target=tb)
+        parser.feed(self.sample1)
+        parser.feed('<!-- a comment--><?and a pi?>')
+
+        e = parser.close()
+        self._check_sample1_element(e)
+
     def test_element_factory(self):
         lst = []
         def myfactory(tag, attrib):
@@ -3418,6 +3494,12 @@ def test_main(module=None):
     # Copy the path cache (should be empty)
     path_cache = ElementPath._cache
     ElementPath._cache = path_cache.copy()
+    # Align the Comment/PI factories.
+    if hasattr(ET, '_set_factories'):
+        old_factories = ET._set_factories(ET.Comment, ET.PI)
+    else:
+        old_factories = None
+
     try:
         support.run_unittest(*test_classes)
     finally:
@@ -3426,6 +3508,8 @@ def test_main(module=None):
         nsmap.clear()
         nsmap.update(nsmap_copy)
         ElementPath._cache = path_cache
+        if old_factories is not None:
+            ET._set_factories(*old_factories)
         # don't interfere with subsequent tests
         ET = pyET = None
 

Lib/xml/etree/ElementTree.py

@@ -1374,12 +1374,30 @@ class TreeBuilder:
     *element_factory* is an optional element factory which is called
     to create new Element instances, as necessary.
 
+    *comment_factory* is a factory to create comments to be used instead of
+    the standard factory.  If *insert_comments* is false (the default),
+    comments will not be inserted into the tree.
+
+    *pi_factory* is a factory to create processing instructions to be used
+    instead of the standard factory.  If *insert_pis* is false (the default),
+    processing instructions will not be inserted into the tree.
     """
-    def __init__(self, element_factory=None):
+    def __init__(self, element_factory=None, *,
+                 comment_factory=None, pi_factory=None,
+                 insert_comments=False, insert_pis=False):
         self._data = [] # data collector
         self._elem = [] # element stack
         self._last = None # last element
+        self._root = None # root element
         self._tail = None # true if we're after an end tag
+        if comment_factory is None:
+            comment_factory = Comment
+        self._comment_factory = comment_factory
+        self.insert_comments = insert_comments
+        if pi_factory is None:
+            pi_factory = ProcessingInstruction
+        self._pi_factory = pi_factory
+        self.insert_pis = insert_pis
         if element_factory is None:
             element_factory = Element
         self._factory = element_factory
@@ -1387,8 +1405,8 @@ class TreeBuilder:
     def close(self):
         """Flush builder buffers and return toplevel document Element."""
         assert len(self._elem) == 0, "missing end tags"
-        assert self._last is not None, "missing toplevel element"
+        assert self._root is not None, "missing toplevel element"
-        return self._last
+        return self._root
 
     def _flush(self):
         if self._data:
@@ -1417,6 +1435,8 @@ class TreeBuilder:
         self._last = elem = self._factory(tag, attrs)
         if self._elem:
             self._elem[-1].append(elem)
+        elif self._root is None:
+            self._root = elem
         self._elem.append(elem)
         self._tail = 0
         return elem
@@ -1435,6 +1455,33 @@ class TreeBuilder:
         self._tail = 1
         return self._last
 
+    def comment(self, text):
+        """Create a comment using the comment_factory.
+
+        *text* is the text of the comment.
+        """
+        return self._handle_single(
+            self._comment_factory, self.insert_comments, text)
+
+    def pi(self, target, text=None):
+        """Create a processing instruction using the pi_factory.
+
+        *target* is the target name of the processing instruction.
+        *text* is the data of the processing instruction, or ''.
+        """
+        return self._handle_single(
+            self._pi_factory, self.insert_pis, target, text)
+
+    def _handle_single(self, factory, insert, *args):
+        elem = factory(*args)
+        if insert:
+            self._flush()
+            self._last = elem
+            if self._elem:
+                self._elem[-1].append(elem)
+            self._tail = 1
+        return elem
+
 
 # also see ElementTree and TreeBuilder
 class XMLParser:
@@ -1519,6 +1566,15 @@ class XMLParser:
                 def handler(prefix, event=event_name, append=append):
                     append((event, None))
                 parser.EndNamespaceDeclHandler = handler
+            elif event_name == 'comment':
+                def handler(text, event=event_name, append=append, self=self):
+                    append((event, self.target.comment(text)))
+                parser.CommentHandler = handler
+            elif event_name == 'pi':
+                def handler(pi_target, data, event=event_name, append=append,
+                            self=self):
+                    append((event, self.target.pi(pi_target, data)))
+                parser.ProcessingInstructionHandler = handler
             else:
                 raise ValueError("unknown event %r" % event_name)
 
@@ -1640,7 +1696,10 @@ try:
     # (see tests)
     _Element_Py = Element
 
-    # Element, SubElement, ParseError, TreeBuilder, XMLParser
+    # Element, SubElement, ParseError, TreeBuilder, XMLParser, _set_factories
     from _elementtree import *
+    from _elementtree import _set_factories
 except ImportError:
     pass
+else:
+    _set_factories(Comment, ProcessingInstruction)

Misc/NEWS.d/next/Library/2019-04-20-09-50-32.bpo-36673.XF4Egb.rst

@@ -0,0 +1,3 @@
+The TreeBuilder and XMLPullParser in xml.etree.ElementTree gained support
+for parsing comments and processing instructions.
+Patch by Stefan Behnel.

Modules/_elementtree.c

@@ -92,6 +92,8 @@ typedef struct {
     PyObject *parseerror_obj;
     PyObject *deepcopy_obj;
     PyObject *elementpath_obj;
+    PyObject *comment_factory;
+    PyObject *pi_factory;
 } elementtreestate;
 
 static struct PyModuleDef elementtreemodule;
@@ -114,6 +116,8 @@ elementtree_clear(PyObject *m)
     Py_CLEAR(st->parseerror_obj);
     Py_CLEAR(st->deepcopy_obj);
     Py_CLEAR(st->elementpath_obj);
+    Py_CLEAR(st->comment_factory);
+    Py_CLEAR(st->pi_factory);
     return 0;
 }
 
@@ -124,6 +128,8 @@ elementtree_traverse(PyObject *m, visitproc visit, void *arg)
     Py_VISIT(st->parseerror_obj);
     Py_VISIT(st->deepcopy_obj);
     Py_VISIT(st->elementpath_obj);
+    Py_VISIT(st->comment_factory);
+    Py_VISIT(st->pi_factory);
     return 0;
 }
 
@@ -2385,6 +2391,8 @@ typedef struct {
     Py_ssize_t index; /* current stack size (0 means empty) */
 
     PyObject *element_factory;
+    PyObject *comment_factory;
+    PyObject *pi_factory;
 
     /* element tracing */
     PyObject *events_append; /* the append method of the list of events, or NULL */
@@ -2392,6 +2400,11 @@ typedef struct {
     PyObject *end_event_obj;
     PyObject *start_ns_event_obj;
     PyObject *end_ns_event_obj;
+    PyObject *comment_event_obj;
+    PyObject *pi_event_obj;
+
+    char insert_comments;
+    char insert_pis;
 } TreeBuilderObject;
 
 #define TreeBuilder_CheckExact(op) (Py_TYPE(op) == &TreeBuilder_Type)
@@ -2413,6 +2426,8 @@ treebuilder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
 
         t->data = NULL;
         t->element_factory = NULL;
+        t->comment_factory = NULL;
+        t->pi_factory = NULL;
         t->stack = PyList_New(20);
         if (!t->stack) {
             Py_DECREF(t->this);
@@ -2425,6 +2440,8 @@ treebuilder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
         t->events_append = NULL;
         t->start_event_obj = t->end_event_obj = NULL;
         t->start_ns_event_obj = t->end_ns_event_obj = NULL;
+        t->comment_event_obj = t->pi_event_obj = NULL;
+        t->insert_comments = t->insert_pis = 0;
     }
     return (PyObject *)t;
 }
@@ -2433,17 +2450,53 @@ treebuilder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
 _elementtree.TreeBuilder.__init__
 
     element_factory: object = NULL
+    *
+    comment_factory: object = NULL
+    pi_factory: object = NULL
+    insert_comments: bool = False
+    insert_pis: bool = False
 
 [clinic start generated code]*/
 
 static int
 _elementtree_TreeBuilder___init___impl(TreeBuilderObject *self,
-                                       PyObject *element_factory)
+                                       PyObject *element_factory,
-/*[clinic end generated code: output=91cfa7558970ee96 input=1b424eeefc35249c]*/
+                                       PyObject *comment_factory,
+                                       PyObject *pi_factory,
+                                       int insert_comments, int insert_pis)
+/*[clinic end generated code: output=8571d4dcadfdf952 input=1f967b5c245e0a71]*/
 {
-    if (element_factory) {
+    if (element_factory && element_factory != Py_None) {
         Py_INCREF(element_factory);
         Py_XSETREF(self->element_factory, element_factory);
+    } else {
+        Py_CLEAR(self->element_factory);
+    }
+
+    if (!comment_factory || comment_factory == Py_None) {
+        elementtreestate *st = ET_STATE_GLOBAL;
+        comment_factory = st->comment_factory;
+    }
+    if (comment_factory) {
+        Py_INCREF(comment_factory);
+        Py_XSETREF(self->comment_factory, comment_factory);
+        self->insert_comments = insert_comments;
+    } else {
+        Py_CLEAR(self->comment_factory);
+        self->insert_comments = 0;
+    }
+
+    if (!pi_factory || pi_factory == Py_None) {
+        elementtreestate *st = ET_STATE_GLOBAL;
+        pi_factory = st->pi_factory;
+    }
+    if (pi_factory) {
+        Py_INCREF(pi_factory);
+        Py_XSETREF(self->pi_factory, pi_factory);
+        self->insert_pis = insert_pis;
+    } else {
+        Py_CLEAR(self->pi_factory);
+        self->insert_pis = 0;
     }
 
     return 0;
@@ -2452,6 +2505,8 @@ _elementtree_TreeBuilder___init___impl(TreeBuilderObject *self,
 static int
 treebuilder_gc_traverse(TreeBuilderObject *self, visitproc visit, void *arg)
 {
+    Py_VISIT(self->pi_event_obj);
+    Py_VISIT(self->comment_event_obj);
     Py_VISIT(self->end_ns_event_obj);
     Py_VISIT(self->start_ns_event_obj);
     Py_VISIT(self->end_event_obj);
@@ -2462,6 +2517,8 @@ treebuilder_gc_traverse(TreeBuilderObject *self, visitproc visit, void *arg)
     Py_VISIT(self->last);
     Py_VISIT(self->data);
     Py_VISIT(self->stack);
+    Py_VISIT(self->pi_factory);
+    Py_VISIT(self->comment_factory);
     Py_VISIT(self->element_factory);
     return 0;
 }
@@ -2469,6 +2526,8 @@ treebuilder_gc_traverse(TreeBuilderObject *self, visitproc visit, void *arg)
 static int
 treebuilder_gc_clear(TreeBuilderObject *self)
 {
+    Py_CLEAR(self->pi_event_obj);
+    Py_CLEAR(self->comment_event_obj);
     Py_CLEAR(self->end_ns_event_obj);
     Py_CLEAR(self->start_ns_event_obj);
     Py_CLEAR(self->end_event_obj);
@@ -2478,6 +2537,8 @@ treebuilder_gc_clear(TreeBuilderObject *self)
     Py_CLEAR(self->data);
     Py_CLEAR(self->last);
     Py_CLEAR(self->this);
+    Py_CLEAR(self->pi_factory);
+    Py_CLEAR(self->comment_factory);
     Py_CLEAR(self->element_factory);
     Py_CLEAR(self->root);
     return 0;
@@ -2494,6 +2555,57 @@ treebuilder_dealloc(TreeBuilderObject *self)
 /* -------------------------------------------------------------------- */
 /* helpers for handling of arbitrary element-like objects */
 
+/*[clinic input]
+_elementtree._set_factories
+
+    comment_factory: object
+    pi_factory: object
+    /
+
+Change the factories used to create comments and processing instructions.
+
+For internal use only.
+[clinic start generated code]*/
+
+static PyObject *
+_elementtree__set_factories_impl(PyObject *module, PyObject *comment_factory,
+                                 PyObject *pi_factory)
+/*[clinic end generated code: output=813b408adee26535 input=99d17627aea7fb3b]*/
+{
+    elementtreestate *st = ET_STATE_GLOBAL;
+    PyObject *old;
+
+    if (!PyCallable_Check(comment_factory) && comment_factory != Py_None) {
+        PyErr_Format(PyExc_TypeError, "Comment factory must be callable, not %.100s",
+                     Py_TYPE(comment_factory)->tp_name);
+        return NULL;
+    }
+    if (!PyCallable_Check(pi_factory) && pi_factory != Py_None) {
+        PyErr_Format(PyExc_TypeError, "PI factory must be callable, not %.100s",
+                     Py_TYPE(pi_factory)->tp_name);
+        return NULL;
+    }
+
+    old = PyTuple_Pack(2,
+        st->comment_factory ? st->comment_factory : Py_None,
+        st->pi_factory ? st->pi_factory : Py_None);
+
+    if (comment_factory == Py_None) {
+        Py_CLEAR(st->comment_factory);
+    } else {
+        Py_INCREF(comment_factory);
+        Py_XSETREF(st->comment_factory, comment_factory);
+    }
+    if (pi_factory == Py_None) {
+        Py_CLEAR(st->pi_factory);
+    } else {
+        Py_INCREF(pi_factory);
+        Py_XSETREF(st->pi_factory, pi_factory);
+    }
+
+    return old;
+}
+
 static int
 treebuilder_set_element_text_or_tail(PyObject *element, PyObject **data,
                                      PyObject **dest, _Py_Identifier *name)
@@ -2569,7 +2681,7 @@ treebuilder_append_event(TreeBuilderObject *self, PyObject *action,
         PyObject *event = PyTuple_Pack(2, action, node);
         if (event == NULL)
             return -1;
-        res = PyObject_CallFunctionObjArgs(self->events_append, event, NULL);
+        res = _PyObject_FastCall(self->events_append, &event, 1);
         Py_DECREF(event);
         if (res == NULL)
             return -1;
@@ -2593,7 +2705,7 @@ treebuilder_handle_start(TreeBuilderObject* self, PyObject* tag,
         return NULL;
     }
 
-    if (!self->element_factory || self->element_factory == Py_None) {
+    if (!self->element_factory) {
         node = create_new_element(tag, attrib);
     } else if (attrib == Py_None) {
         attrib = PyDict_New();
@@ -2721,6 +2833,84 @@ treebuilder_handle_end(TreeBuilderObject* self, PyObject* tag)
     return (PyObject*) self->last;
 }
 
+LOCAL(PyObject*)
+treebuilder_handle_comment(TreeBuilderObject* self, PyObject* text)
+{
+    PyObject* comment = NULL;
+    PyObject* this;
+
+    if (treebuilder_flush_data(self) < 0) {
+        return NULL;
+    }
+
+    if (self->comment_factory) {
+        comment = _PyObject_FastCall(self->comment_factory, &text, 1);
+        if (!comment)
+            return NULL;
+
+        this = self->this;
+        if (self->insert_comments && this != Py_None) {
+            if (treebuilder_add_subelement(this, comment) < 0)
+                goto error;
+        }
+    } else {
+        Py_INCREF(text);
+        comment = text;
+    }
+
+    if (self->events_append && self->comment_event_obj) {
+        if (treebuilder_append_event(self, self->comment_event_obj, comment) < 0)
+            goto error;
+    }
+
+    return comment;
+
+  error:
+    Py_DECREF(comment);
+    return NULL;
+}
+
+LOCAL(PyObject*)
+treebuilder_handle_pi(TreeBuilderObject* self, PyObject* target, PyObject* text)
+{
+    PyObject* pi = NULL;
+    PyObject* this;
+    PyObject* stack[2] = {target, text};
+
+    if (treebuilder_flush_data(self) < 0) {
+        return NULL;
+    }
+
+    if (self->pi_factory) {
+        pi = _PyObject_FastCall(self->pi_factory, stack, 2);
+        if (!pi) {
+            return NULL;
+        }
+
+        this = self->this;
+        if (self->insert_pis && this != Py_None) {
+            if (treebuilder_add_subelement(this, pi) < 0)
+                goto error;
+        }
+    } else {
+        pi = PyTuple_Pack(2, target, text);
+        if (!pi) {
+            return NULL;
+        }
+    }
+
+    if (self->events_append && self->pi_event_obj) {
+        if (treebuilder_append_event(self, self->pi_event_obj, pi) < 0)
+            goto error;
+    }
+
+    return pi;
+
+  error:
+    Py_DECREF(pi);
+    return NULL;
+}
+
 /* -------------------------------------------------------------------- */
 /* methods (in alphabetical order) */
 
@@ -2754,6 +2944,38 @@ _elementtree_TreeBuilder_end(TreeBuilderObject *self, PyObject *tag)
     return treebuilder_handle_end(self, tag);
 }
 
+/*[clinic input]
+_elementtree.TreeBuilder.comment
+
+    text: object
+    /
+
+[clinic start generated code]*/
+
+static PyObject *
+_elementtree_TreeBuilder_comment(TreeBuilderObject *self, PyObject *text)
+/*[clinic end generated code: output=22835be41deeaa27 input=47e7ebc48ed01dfa]*/
+{
+    return treebuilder_handle_comment(self, text);
+}
+
+/*[clinic input]
+_elementtree.TreeBuilder.pi
+
+    target: object
+    text: object = None
+    /
+
+[clinic start generated code]*/
+
+static PyObject *
+_elementtree_TreeBuilder_pi_impl(TreeBuilderObject *self, PyObject *target,
+                                 PyObject *text)
+/*[clinic end generated code: output=21eb95ec9d04d1d9 input=349342bd79c35570]*/
+{
+    return treebuilder_handle_pi(self, target, text);
+}
+
 LOCAL(PyObject*)
 treebuilder_done(TreeBuilderObject* self)
 {
@@ -2925,7 +3147,7 @@ expat_set_error(enum XML_Error error_code, Py_ssize_t line, Py_ssize_t column,
     if (errmsg == NULL)
         return;
 
-    error = PyObject_CallFunctionObjArgs(st->parseerror_obj, errmsg, NULL);
+    error = _PyObject_FastCall(st->parseerror_obj, &errmsg, 1);
     Py_DECREF(errmsg);
     if (!error)
         return;
@@ -2988,7 +3210,7 @@ expat_default_handler(XMLParserObject* self, const XML_Char* data_in,
                 (TreeBuilderObject*) self->target, value
                 );
         else if (self->handle_data)
-            res = PyObject_CallFunctionObjArgs(self->handle_data, value, NULL);
+            res = _PyObject_FastCall(self->handle_data, &value, 1);
         else
             res = NULL;
         Py_XDECREF(res);
@@ -3099,7 +3321,7 @@ expat_data_handler(XMLParserObject* self, const XML_Char* data_in,
         /* shortcut */
         res = treebuilder_handle_data((TreeBuilderObject*) self->target, data);
     else if (self->handle_data)
-        res = PyObject_CallFunctionObjArgs(self->handle_data, data, NULL);
+        res = _PyObject_FastCall(self->handle_data, &data, 1);
     else
         res = NULL;
 
@@ -3126,7 +3348,7 @@ expat_end_handler(XMLParserObject* self, const XML_Char* tag_in)
     else if (self->handle_end) {
         tag = makeuniversal(self, tag_in);
         if (tag) {
-            res = PyObject_CallFunctionObjArgs(self->handle_end, tag, NULL);
+            res = _PyObject_FastCall(self->handle_end, &tag, 1);
             Py_DECREF(tag);
         }
     }
@@ -3176,21 +3398,31 @@ expat_end_ns_handler(XMLParserObject* self, const XML_Char* prefix_in)
 static void
 expat_comment_handler(XMLParserObject* self, const XML_Char* comment_in)
 {
-    PyObject* comment;
+    PyObject* comment = NULL;
-    PyObject* res;
+    PyObject* res = NULL;
 
     if (PyErr_Occurred())
         return;
 
-    if (self->handle_comment) {
+    if (TreeBuilder_CheckExact(self->target)) {
+        /* shortcut */
+        TreeBuilderObject *target = (TreeBuilderObject*) self->target;
+
         comment = PyUnicode_DecodeUTF8(comment_in, strlen(comment_in), "strict");
-        if (comment) {
+        if (!comment)
-            res = PyObject_CallFunctionObjArgs(self->handle_comment,
+            return; /* parser will look for errors */
-                                               comment, NULL);
+
-            Py_XDECREF(res);
+        res = treebuilder_handle_comment(target,  comment);
-            Py_DECREF(comment);
+    } else if (self->handle_comment) {
-        }
+        comment = PyUnicode_DecodeUTF8(comment_in, strlen(comment_in), "strict");
+        if (!comment)
+            return;
+
+        res = _PyObject_FastCall(self->handle_comment, &comment, 1);
     }
+
+    Py_XDECREF(res);
+    Py_DECREF(comment);
 }
 
 static void
@@ -3258,27 +3490,51 @@ static void
 expat_pi_handler(XMLParserObject* self, const XML_Char* target_in,
                  const XML_Char* data_in)
 {
-    PyObject* target;
+    PyObject* pi_target = NULL;
     PyObject* data;
     PyObject* res;
+    PyObject* stack[2];
 
     if (PyErr_Occurred())
         return;
 
-    if (self->handle_pi) {
+    if (TreeBuilder_CheckExact(self->target)) {
-        target = PyUnicode_DecodeUTF8(target_in, strlen(target_in), "strict");
+        /* shortcut */
-        data = PyUnicode_DecodeUTF8(data_in, strlen(data_in), "strict");
+        TreeBuilderObject *target = (TreeBuilderObject*) self->target;
-        if (target && data) {
+
-            res = PyObject_CallFunctionObjArgs(self->handle_pi,
+        if (target->events_append && target->pi_event_obj) {
-                                               target, data, NULL);
+            pi_target = PyUnicode_DecodeUTF8(target_in, strlen(target_in), "strict");
+            if (!pi_target)
+                goto error;
+            data = PyUnicode_DecodeUTF8(data_in, strlen(data_in), "strict");
+            if (!data)
+                goto error;
+            res = treebuilder_handle_pi(target, pi_target, data);
             Py_XDECREF(res);
             Py_DECREF(data);
-            Py_DECREF(target);
+            Py_DECREF(pi_target);
-        } else {
-            Py_XDECREF(data);
-            Py_XDECREF(target);
         }
+    } else if (self->handle_pi) {
+        pi_target = PyUnicode_DecodeUTF8(target_in, strlen(target_in), "strict");
+        if (!pi_target)
+            goto error;
+        data = PyUnicode_DecodeUTF8(data_in, strlen(data_in), "strict");
+        if (!data)
+            goto error;
+
+        stack[0] = pi_target;
+        stack[1] = data;
+        res = _PyObject_FastCall(self->handle_pi, stack, 2);
+        Py_XDECREF(res);
+        Py_DECREF(data);
+        Py_DECREF(pi_target);
     }
+
+    return;
+
+  error:
+    Py_XDECREF(pi_target);
+    return;
 }
 
 /* -------------------------------------------------------------------- */
@@ -3695,6 +3951,8 @@ _elementtree_XMLParser__setevents_impl(XMLParserObject *self,
     Py_CLEAR(target->end_event_obj);
     Py_CLEAR(target->start_ns_event_obj);
     Py_CLEAR(target->end_ns_event_obj);
+    Py_CLEAR(target->comment_event_obj);
+    Py_CLEAR(target->pi_event_obj);
 
     if (events_to_report == Py_None) {
         /* default is "end" only */
@@ -3740,6 +3998,18 @@ _elementtree_XMLParser__setevents_impl(XMLParserObject *self,
                 (XML_StartNamespaceDeclHandler) expat_start_ns_handler,
                 (XML_EndNamespaceDeclHandler) expat_end_ns_handler
                 );
+        } else if (strcmp(event_name, "comment") == 0) {
+            Py_XSETREF(target->comment_event_obj, event_name_obj);
+            EXPAT(SetCommentHandler)(
+                self->parser,
+                (XML_CommentHandler) expat_comment_handler
+                );
+        } else if (strcmp(event_name, "pi") == 0) {
+            Py_XSETREF(target->pi_event_obj, event_name_obj);
+            EXPAT(SetProcessingInstructionHandler)(
+                self->parser,
+                (XML_ProcessingInstructionHandler) expat_pi_handler
+                );
         } else {
             Py_DECREF(event_name_obj);
             Py_DECREF(events_seq);
@@ -3882,6 +4152,8 @@ static PyMethodDef treebuilder_methods[] = {
     _ELEMENTTREE_TREEBUILDER_DATA_METHODDEF
     _ELEMENTTREE_TREEBUILDER_START_METHODDEF
     _ELEMENTTREE_TREEBUILDER_END_METHODDEF
+    _ELEMENTTREE_TREEBUILDER_COMMENT_METHODDEF
+    _ELEMENTTREE_TREEBUILDER_PI_METHODDEF
     _ELEMENTTREE_TREEBUILDER_CLOSE_METHODDEF
     {NULL, NULL}
 };
@@ -3983,6 +4255,7 @@ static PyTypeObject XMLParser_Type = {
 
 static PyMethodDef _functions[] = {
     {"SubElement", (PyCFunction)(void(*)(void)) subelement, METH_VARARGS | METH_KEYWORDS},
+    _ELEMENTTREE__SET_FACTORIES_METHODDEF
     {NULL, NULL}
 };
 

Modules/clinic/_elementtree.c.h

@@ -635,19 +635,26 @@ exit:
 
 static int
 _elementtree_TreeBuilder___init___impl(TreeBuilderObject *self,
-                                       PyObject *element_factory);
+                                       PyObject *element_factory,
+                                       PyObject *comment_factory,
+                                       PyObject *pi_factory,
+                                       int insert_comments, int insert_pis);
 
 static int
 _elementtree_TreeBuilder___init__(PyObject *self, PyObject *args, PyObject *kwargs)
 {
     int return_value = -1;
-    static const char * const _keywords[] = {"element_factory", NULL};
+    static const char * const _keywords[] = {"element_factory", "comment_factory", "pi_factory", "insert_comments", "insert_pis", NULL};
     static _PyArg_Parser _parser = {NULL, _keywords, "TreeBuilder", 0};
-    PyObject *argsbuf[1];
+    PyObject *argsbuf[5];
     PyObject * const *fastargs;
     Py_ssize_t nargs = PyTuple_GET_SIZE(args);
     Py_ssize_t noptargs = nargs + (kwargs ? PyDict_GET_SIZE(kwargs) : 0) - 0;
     PyObject *element_factory = NULL;
+    PyObject *comment_factory = NULL;
+    PyObject *pi_factory = NULL;
+    int insert_comments = 0;
+    int insert_pis = 0;
 
     fastargs = _PyArg_UnpackKeywords(_PyTuple_CAST(args)->ob_item, nargs, kwargs, NULL, &_parser, 0, 1, 0, argsbuf);
     if (!fastargs) {
@@ -656,9 +663,76 @@ _elementtree_TreeBuilder___init__(PyObject *self, PyObject *args, PyObject *kwar
     if (!noptargs) {
         goto skip_optional_pos;
     }
-    element_factory = fastargs[0];
+    if (fastargs[0]) {
+        element_factory = fastargs[0];
+        if (!--noptargs) {
+            goto skip_optional_pos;
+        }
+    }
 skip_optional_pos:
-    return_value = _elementtree_TreeBuilder___init___impl((TreeBuilderObject *)self, element_factory);
+    if (!noptargs) {
+        goto skip_optional_kwonly;
+    }
+    if (fastargs[1]) {
+        comment_factory = fastargs[1];
+        if (!--noptargs) {
+            goto skip_optional_kwonly;
+        }
+    }
+    if (fastargs[2]) {
+        pi_factory = fastargs[2];
+        if (!--noptargs) {
+            goto skip_optional_kwonly;
+        }
+    }
+    if (fastargs[3]) {
+        insert_comments = PyObject_IsTrue(fastargs[3]);
+        if (insert_comments < 0) {
+            goto exit;
+        }
+        if (!--noptargs) {
+            goto skip_optional_kwonly;
+        }
+    }
+    insert_pis = PyObject_IsTrue(fastargs[4]);
+    if (insert_pis < 0) {
+        goto exit;
+    }
+skip_optional_kwonly:
+    return_value = _elementtree_TreeBuilder___init___impl((TreeBuilderObject *)self, element_factory, comment_factory, pi_factory, insert_comments, insert_pis);
+
+exit:
+    return return_value;
+}
+
+PyDoc_STRVAR(_elementtree__set_factories__doc__,
+"_set_factories($module, comment_factory, pi_factory, /)\n"
+"--\n"
+"\n"
+"Change the factories used to create comments and processing instructions.\n"
+"\n"
+"For internal use only.");
+
+#define _ELEMENTTREE__SET_FACTORIES_METHODDEF    \
+    {"_set_factories", (PyCFunction)(void(*)(void))_elementtree__set_factories, METH_FASTCALL, _elementtree__set_factories__doc__},
+
+static PyObject *
+_elementtree__set_factories_impl(PyObject *module, PyObject *comment_factory,
+                                 PyObject *pi_factory);
+
+static PyObject *
+_elementtree__set_factories(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
+{
+    PyObject *return_value = NULL;
+    PyObject *comment_factory;
+    PyObject *pi_factory;
+
+    if (!_PyArg_CheckPositional("_set_factories", nargs, 2, 2)) {
+        goto exit;
+    }
+    comment_factory = args[0];
+    pi_factory = args[1];
+    return_value = _elementtree__set_factories_impl(module, comment_factory, pi_factory);
 
 exit:
     return return_value;
@@ -680,6 +754,48 @@ PyDoc_STRVAR(_elementtree_TreeBuilder_end__doc__,
 #define _ELEMENTTREE_TREEBUILDER_END_METHODDEF    \
     {"end", (PyCFunction)_elementtree_TreeBuilder_end, METH_O, _elementtree_TreeBuilder_end__doc__},
 
+PyDoc_STRVAR(_elementtree_TreeBuilder_comment__doc__,
+"comment($self, text, /)\n"
+"--\n"
+"\n");
+
+#define _ELEMENTTREE_TREEBUILDER_COMMENT_METHODDEF    \
+    {"comment", (PyCFunction)_elementtree_TreeBuilder_comment, METH_O, _elementtree_TreeBuilder_comment__doc__},
+
+PyDoc_STRVAR(_elementtree_TreeBuilder_pi__doc__,
+"pi($self, target, text=None, /)\n"
+"--\n"
+"\n");
+
+#define _ELEMENTTREE_TREEBUILDER_PI_METHODDEF    \
+    {"pi", (PyCFunction)(void(*)(void))_elementtree_TreeBuilder_pi, METH_FASTCALL, _elementtree_TreeBuilder_pi__doc__},
+
+static PyObject *
+_elementtree_TreeBuilder_pi_impl(TreeBuilderObject *self, PyObject *target,
+                                 PyObject *text);
+
+static PyObject *
+_elementtree_TreeBuilder_pi(TreeBuilderObject *self, PyObject *const *args, Py_ssize_t nargs)
+{
+    PyObject *return_value = NULL;
+    PyObject *target;
+    PyObject *text = Py_None;
+
+    if (!_PyArg_CheckPositional("pi", nargs, 1, 2)) {
+        goto exit;
+    }
+    target = args[0];
+    if (nargs < 2) {
+        goto skip_optional;
+    }
+    text = args[1];
+skip_optional:
+    return_value = _elementtree_TreeBuilder_pi_impl(self, target, text);
+
+exit:
+    return return_value;
+}
+
 PyDoc_STRVAR(_elementtree_TreeBuilder_close__doc__,
 "close($self, /)\n"
 "--\n"
@@ -853,4 +969,4 @@ skip_optional:
 exit:
     return return_value;
 }
-/*[clinic end generated code: output=440b5d90a4b86590 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=386a68425d072b5c input=a9049054013a1b77]*/