Expose GetCurrentByteCount from expat

Author: DelusionalLogic

Doc/library/pyexpat.rst

@@ -316,6 +316,15 @@ just past the last parse event (regardless of whether there was an associated
 callback).
 
 
+.. attribute:: xmlparser.CurrentByteCount
+
+   Number of bytes in the current event.  ``0`` if the event is for the end tag
+   event for *empty-element* tags or is inside a reference to an internal
+   entity.
+
+   .. versionadded:: 3.14
+
+
 .. attribute:: xmlparser.CurrentByteIndex
 
    Current byte index in the parser input.

Lib/test/test_pyexpat.py

@@ -506,6 +506,7 @@ def EndElementHandler(self, name):
     def check_pos(self, event):
         pos = (event,
                self.parser.CurrentByteIndex,
+               self.parser.CurrentByteCount,
                self.parser.CurrentLineNumber,
                self.parser.CurrentColumnNumber)
         self.assertTrue(self.upto < len(self.expected_list),
@@ -520,8 +521,8 @@ def test(self):
         self.parser.StartElementHandler = self.StartElementHandler
         self.parser.EndElementHandler = self.EndElementHandler
         self.upto = 0
-        self.expected_list = [('s', 0, 1, 0), ('s', 5, 2, 1), ('s', 11, 3, 2),
-                              ('e', 15, 3, 6), ('e', 17, 4, 1), ('e', 22, 5, 0)]
+        self.expected_list = [('s', 0, 3, 1, 0), ('s', 5, 3, 2, 1), ('s', 11, 4, 3, 2),
+                              ('e', 15, 0, 3, 6), ('e', 17, 4, 4, 1), ('e', 22, 4, 5, 0)]
 
         xml = b'<a>\n <b>\n  <c/>\n </b>\n</a>'
         self.parser.Parse(xml, True)

Misc/ACKS

@@ -882,6 +882,7 @@ Muhammad Jehanzeb
 Drew Jenkins
 Flemming Kjær Jensen
 Philip H. Jensen
+Jesper Jensen
 Philip Jenvey
 MunSic Jeong
 Chris Jerdonek

Misc/NEWS.d/next/Library/2024-09-11-16-40-12.gh-issue-123963.TzzIY8.rst

@@ -0,0 +1,3 @@
+Expose the :attr:`xmlparser.CurrentByteCount` field for :mod:`Expat XML
+<xml.parsers.expat>` parsers.
+Patch by Jesper Jensen.

Modules/pyexpat.c

@@ -1349,6 +1349,7 @@ INT_GETTER(ErrorByteIndex)
 INT_GETTER(CurrentLineNumber)
 INT_GETTER(CurrentColumnNumber)
 INT_GETTER(CurrentByteIndex)
+INT_GETTER(CurrentByteCount)
 
 #undef INT_GETTER
 
@@ -1529,6 +1530,7 @@ static PyGetSetDef xmlparse_getsetlist[] = {
     XMLPARSE_GETTER_DEF(CurrentLineNumber)
     XMLPARSE_GETTER_DEF(CurrentColumnNumber)
     XMLPARSE_GETTER_DEF(CurrentByteIndex)
+    XMLPARSE_GETTER_DEF(CurrentByteCount)
     XMLPARSE_GETTER_SETTER_DEF(buffer_size)
     XMLPARSE_GETTER_SETTER_DEF(buffer_text)
     XMLPARSE_GETTER_DEF(buffer_used)