From 8ec06c528fc75798ba1558c1896421ddf3bf5145 Mon Sep 17 00:00:00 2001
From: Apoorv Darshan <ad13dtu@gmail.com>
Date: Thu, 9 Jul 2026 22:07:26 +0530
Subject: [PATCH] Exclude annotation text from Node.__str__/__unicode__ (fixes
 #146)

Node.__str__ and Node.__unicode__ collect the string value of an element
by recursing into every child, including office:annotation (cell comment)
subtrees. As a result str(cell) on a spreadsheet cell that carries a
comment returned the comment's date and body concatenated with the cell
value, e.g. "2025-05-12T00:00:00On Day2, did thing.-CommenterCell Value"
instead of "Cell Value".

Skip office:annotation and office:annotation-end children when building
the string value so the returned text reflects only the cell's own
content. The annotation elements are untouched and still serialize to XML
via toXml(); only text extraction changes.
---
 odf/element.py          | 15 +++++++++-
 tests/testannotation.py | 61 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 1 deletion(-)
 create mode 100644 tests/testannotation.py

diff --git a/odf/element.py b/odf/element.py
index e547073..f9b8266 100644
--- a/odf/element.py
+++ b/odf/element.py
@@ -27,7 +27,7 @@
 import re
 import xml.dom
 from xml.dom.minicompat import *
-from odf.namespaces import nsdict
+from odf.namespaces import nsdict, OFFICENS
 import odf.grammar as grammar
 from odf.attrconverters import AttrConverters
 
@@ -159,6 +159,15 @@ class IllegalText(Exception):
     """ Complains if you add text or cdata to an element where it is not allowed """
 
 
+# Qualified names of annotation (cell comment) elements. Their text content is
+# metadata about the containing element rather than part of its textual value,
+# so it is skipped when collecting the string value of a node (see issue #146).
+_annotation_qnames = frozenset((
+    (OFFICENS, u'annotation'),
+    (OFFICENS, u'annotation-end'),
+))
+
+
 class Node(xml.dom.Node):
     """ super class for more specific nodes """
     parentNode = None
@@ -250,12 +259,16 @@ def removeChild(self, oldChild):
     def __str__(self):
         val = []
         for c in self.childNodes:
+            if getattr(c, "qname", None) in _annotation_qnames:
+                continue
             val.append(str(c))
         return ''.join(val)
 
     def __unicode__(self):
         val = []
         for c in self.childNodes:
+            if getattr(c, "qname", None) in _annotation_qnames:
+                continue
             val.append(unicode(c))
         return u''.join(val)
 
diff --git a/tests/testannotation.py b/tests/testannotation.py
new file mode 100644
index 0000000..2526b34
--- /dev/null
+++ b/tests/testannotation.py
@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright (C) 2007 Søren Roug, European Environment Agency
+#
+# This is free software.  You may redistribute it under the terms
+# of the Apache license and the GNU General Public License Version
+# 2 or at your option any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public
+# License along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+#
+# Contributor(s):
+#
+
+import unittest
+import sys
+from odf import office, table, text, dc
+
+if sys.version_info[0] == 3:
+    unicode = str
+
+
+class TestAnnotation(unittest.TestCase):
+
+    def _cell_with_annotation(self):
+        """ Build a table cell containing an annotation (cell comment)
+            followed by the actual cell value, as in issue #146. """
+        cell = table.TableCell(valuetype="string")
+
+        annotation = office.Annotation()
+        annotation.addElement(dc.Date(text=u"2025-05-12T00:00:00"))
+        p1 = text.P()
+        p1.addElement(text.Span(text=u"On Day2, did thing."))
+        annotation.addElement(p1)
+        p2 = text.P()
+        p2.addElement(text.Span(text=u"-Commenter"))
+        annotation.addElement(p2)
+        cell.addElement(annotation)
+
+        cell.addElement(text.P(text=u"Cell Value"))
+        return cell
+
+    def test_str_ignores_annotation(self):
+        """ str(cell) must return only the cell value, not the comment text """
+        cell = self._cell_with_annotation()
+        self.assertEqual("Cell Value", str(cell))
+
+    def test_unicode_ignores_annotation(self):
+        """ unicode(cell) must return only the cell value, not the comment """
+        cell = self._cell_with_annotation()
+        self.assertEqual(u"Cell Value", unicode(cell))
+
+
+if __name__ == '__main__':
+    unittest.main()