756: support for / test with python 3.13

.github/workflows/verify.yml

@@ -39,7 +39,7 @@ jobs:
       # Run all matrix jobs even if one of them fails.
       fail-fast: false
       matrix:
-        python: ['3.10', '3.11', '3.12']
+        python: ['3.10', '3.11', '3.12', '3.13']
         os: [ubuntu-latest, macos-latest, windows-latest]
         include:
           - os: windows-latest

README.rst

@@ -7,7 +7,7 @@ pyxform
 .. |pypi| image:: https://badge.fury.io/py/pyxform.svg
     :target: https://badge.fury.io/py/pyxform
 
-.. |python| image:: https://img.shields.io/badge/python-3.10,3.11,3.12-blue.svg
+.. |python| image:: https://img.shields.io/badge/python-3.10,3.11,3.12,3.13-blue.svg
     :target: https://www.python.org/downloads
 
 ``pyxform`` is a Python library that simplifies writing forms for ODK Collect and Enketo by converting spreadsheets that follow the `XLSForm standard <http://xlsform.org/>`_ into `ODK XForms <https://github.com/opendatakit/xforms-spec>`_. The XLSForms format is used in a `number of tools <http://xlsform.org/en/#tools-that-support-xlsforms>`_.
@@ -44,7 +44,7 @@ The ``xls2xform`` command can then be used::
 
     xls2xform path_to_XLSForm [output_path]
 
-The currently supported Python versions for ``pyxform`` are 3.10, 3.11 and 3.12.
+The currently supported Python versions for ``pyxform`` are 3.10, 3.11, 3.12, and 3.13.
 
 Running pyxform from local source
 ---------------------------------

pyproject.toml

@@ -16,7 +16,7 @@ dependencies = [
 [project.optional-dependencies]
 # Install with `pip install pyxform[dev]`.
 dev = [
-  "formencode==2.1.0",  # Compare XML
+  "formencode==2.1.1",  # Compare XML
   "lxml==5.3.0",        # XPath test expressions
   "psutil==6.1.0",      # Process info for performance tests
   "ruff==0.7.1",        # Format and lint

pyxform/utils.py

@@ -12,7 +12,7 @@
 from itertools import chain
 from json.decoder import JSONDecodeError
 from xml.dom import Node
-from xml.dom.minidom import Element, Text, _write_data
+from xml.dom.minidom import Element, Text
 
 from defusedxml.minidom import parseString
 
@@ -29,6 +29,8 @@
 SPACE_TRANS_TABLE = str.maketrans({" ": "_"})
 XML_TEXT_SUBS = {"&": "&amp;", "<": "&lt;", ">": "&gt;"}
 XML_TEXT_TABLE = str.maketrans(XML_TEXT_SUBS)
+XML_ATTR_SUBS = {'"': "&quot;", "\r": "&#13;", "\n": "&#10;", "\t": "&#9;"}
+XML_ATTR_TABLE = str.maketrans(XML_ATTR_SUBS)
 
 
 class DetachableElement(Element):
@@ -54,9 +56,8 @@ def writexml(self, writer, indent="", addindent="", newl=""):
 
         if self._attrs:
             for k, v in self._attrs.items():
-                writer.write(f' {k}="')
-                _write_data(writer, v.value)
-                writer.write('"')
+                # First space prefix separates attr from tagName, then it separates attrs.
+                writer.write(f' {k}="{escape_text_for_xml(v.value, attribute=True)}"')
         if self.childNodes:
             writer.write(">")
             # For text or mixed content, write without adding indents or newlines.
@@ -80,11 +81,13 @@ def writexml(self, writer, indent="", addindent="", newl=""):
 
 
 @lru_cache(maxsize=64)
-def escape_text_for_xml(text: str) -> str:
-    if any(c in set(text) for c in XML_TEXT_SUBS):
-        return text.translate(XML_TEXT_TABLE)
-    else:
-        return text
+def escape_text_for_xml(text: str, attribute: bool = False) -> str:
+    chars = set(text)
+    if any(c in chars for c in XML_TEXT_SUBS):
+        text = text.translate(XML_TEXT_TABLE)
+    if attribute and any(c in chars for c in XML_ATTR_SUBS):
+        text = text.translate(XML_ATTR_TABLE)
+    return text
 
 
 class PatchedText(Text):

tests/xform_test_case/test_xml.py

@@ -2,6 +2,7 @@
 Test XForm XML syntax.
 """
 
+from sys import version_info
 from unittest import TestCase
 from xml.dom.minidom import getDOMImplementation
 
@@ -86,20 +87,30 @@ def test_to_xml(self):
 
 
 class MinidomTextWriterMonkeyPatchTest(TestCase):
+    maxDiff = None
+
     def test_patch_lets_node_func_escape_only_necessary(self):
-        """Should only escape text chars that should be: ["<", ">", "&"]."""
-        text = "' \" & < >"
-        expected = "<root>' \" &amp; &lt; &gt;</root>"
-        observed = node("root", text).toprettyxml(indent="", newl="")
+        """Should find that pyxform escapes ["&<>\r\n\t] in attrs and [&<>] in text."""
+        replaceable_chars = "' \" & < > \r \n \t"
+        expected = """<root attr="' &quot; &amp; &lt; &gt; &#13; &#10; &#9;">' " &amp; &lt; &gt; \r \n \t</root>"""
+        observed = node("root", replaceable_chars, attr=replaceable_chars).toprettyxml(
+            indent="", newl=""
+        )
         self.assertEqual(expected, observed)
 
     def test_original_escape_escapes_more_than_necessary(self):
         """Should fail if the original is updated (the patch can be removed)."""
-        text = "' \" & < >"
-        expected = "<root>' &quot; &amp; &lt; &gt;</root>"
+        replaceable_chars = "' \" & < > \r \n \t"
         document = getDOMImplementation().createDocument(None, "root", None)
         root = document.documentElement
-        text_node = document.createTextNode(text)
-        root.appendChild(text_node)
+        root.appendChild(document.createTextNode(replaceable_chars))
+        root.setAttribute("attr", replaceable_chars)
         observed = root.toprettyxml(indent="", newl="")
-        self.assertEqual(expected, observed)
+        if version_info.major == 3 and version_info.minor >= 13:
+            # In 3.13, minidom was updated to only escape " in attrs, and also escape \r\n\t.
+            expected = """<root attr="' &quot; &amp; &lt; &gt; &#13; &#10; &#9;">' " &amp; &lt; &gt; \r \n \t</root>"""
+            self.assertEqual(expected, observed)
+        else:
+            # Prior to 3.13 " was escaped in text unnecessarily, and \r\n\t not escaped in attrs.
+            expected = """<root attr="' &quot; &amp; &lt; &gt; \r \n \t">' &quot; &amp; &lt; &gt; \r \n \t</root>"""
+            self.assertEqual(expected, observed)