SF.net SVN: docutils:[9744 ] trunk/docutils

Revision: 9744
          http://sourceforge.net/p/docutils/code/9744
Author:   milde
Date:     2024-06-06 14:03:33 +0000 (Thu, 06 Jun 2024)
Log Message:
-----------
xml-parser: Register IDs, report duplicate IDs.

Add element IDs to `document.ids`.

Report an ERROR system message for duplicate IDs.

Improves co-operation with "rST" parser when including XML
files in an rST file.

Modified Paths:
--------------
    trunk/docutils/docutils/parsers/docutils_xml.py
    trunk/docutils/test/test_parsers/test_docutils_xml/test_parse.py
    trunk/docutils/test/test_parsers/test_docutils_xml/test_parse_element.py

Added Paths:
-----------
    trunk/docutils/test/test_parsers/test_docutils_xml/test_misc.py

Modified: trunk/docutils/docutils/parsers/docutils_xml.py
===================================================================
--- trunk/docutils/docutils/parsers/docutils_xml.py	2024-06-06 14:03:21 UTC (rev 9743)
+++ trunk/docutils/docutils/parsers/docutils_xml.py	2024-06-06 14:03:33 UTC (rev 9744)
@@ -147,6 +147,14 @@
             if key in node.list_attributes:
                 value = value.split()
             node.attributes[key] = value  # node becomes invalid!
+    # register ids, check for duplicates
+    for id in node['ids']:
+        document.ids.setdefault(id, node)
+        if document.ids[id] is not node:
+            document.reporter.error(f'Duplicate ID: "{id}" used by '
+                                    f'{document.ids[id].starttag()} '
+                                    f'and {node.starttag()}',
+                                    base_node=node)
 
     # Append content:
     # update "unindent" flag: change line indentation?

Added: trunk/docutils/test/test_parsers/test_docutils_xml/test_misc.py
===================================================================
--- trunk/docutils/test/test_parsers/test_docutils_xml/test_misc.py	                        (rev 0)
+++ trunk/docutils/test/test_parsers/test_docutils_xml/test_misc.py	2024-06-06 14:03:33 UTC (rev 9744)
@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+# :Copyright: © 2024 Günter Milde.
+# :License: Released under the terms of the `2-Clause BSD license`_, in short:
+#
+#    Copying and distribution of this file, with or without modification,
+#    are permitted in any medium without royalty provided the copyright
+#    notice and this notice are preserved.
+#    This file is offered as-is, without any warranty.
+#
+# .. _2-Clause BSD license: https://opensource.org/licenses/BSD-2-Clause
+
+"""Various tests for the XML parser.
+
+Test parsing + transformations with `publish_string()`.
+"""
+
+from pathlib import Path
+import sys
+import unittest
+
+if __name__ == '__main__':
+    # prepend the "docutils root" to the Python library path
+    # so we import the local `docutils` package.
+    sys.path.insert(0, str(Path(__file__).resolve().parents[3]))
+
+from docutils.core import publish_string
+from docutils.parsers import docutils_xml
+
+parser = docutils_xml.Parser()
+
+
+class XMLParserTests(unittest.TestCase):
+    maxDiff = None
+
+    mysettings = {'_disable_config': True,
+                  'output_encoding': 'unicode',
+                  'warning_stream': '',
+                  }
+
+    def test_publish(self):
+        for name, (settings, cases) in totest.items():
+            settings = self.mysettings | settings
+            for casenum, (case_input, case_expected) in enumerate(cases):
+                with self.subTest(id=f'totest[{name!r}][{casenum}]'):
+                    output = publish_string(case_input, parser=parser,
+                                            settings_overrides=settings)
+                    self.assertEqual(case_expected, output)
+
+
+totest = {}
+
+totest['hyperlinks'] = ({},
+[
+# resolve anonymous hyperlinks
+["""\
+<document source="test data">
+    <paragraph>A <reference anonymous="1" name="link">link</reference> to Docutils.</paragraph>
+    <target anonymous="1" ids="target-1" refuri="http://docutils.sourceforge.io"/>
+</document>
+""",
+"""\
+<document source="test data">
+    <paragraph>
+        A \n\
+        <reference anonymous="1" name="link" refuri="http://docutils.sourceforge.io">
+            link
+         to Docutils.
+    <target anonymous="1" ids="target-1" refuri="http://docutils.sourceforge.io">
+"""],
+# duplicate ids are an error
+["""\
+<tip ids="i1 i2">
+    <paragraph><strong ids="i2 i3"></strong></paragraph>
+</tip>
+""",
+"""\
+<document source="<string>">
+    <tip ids="i1 i2">
+        <paragraph>
+            <strong ids="i2 i3">
+    <section classes="system-messages">
+        <title>
+            Docutils System Messages
+        <system_message level="3" line="2" source="<string>" type="ERROR">
+            <paragraph>
+                Duplicate ID: "i2" used by <tip ids="i1 i2"> and <strong ids="i2 i3">
+"""],
+])
+
+if __name__ == '__main__':
+    unittest.main()


Property changes on: trunk/docutils/test/test_parsers/test_docutils_xml/test_misc.py
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: svn:keywords
## -0,0 +1 ##
+Author Date Id Revision
\ No newline at end of property
Modified: trunk/docutils/test/test_parsers/test_docutils_xml/test_parse.py
===================================================================
--- trunk/docutils/test/test_parsers/test_docutils_xml/test_parse.py	2024-06-06 14:03:21 UTC (rev 9743)
+++ trunk/docutils/test/test_parsers/test_docutils_xml/test_parse.py	2024-06-06 14:03:33 UTC (rev 9744)
@@ -28,13 +28,13 @@
 
 
 class XmlParserTestCase(unittest.TestCase):
-    def test_parser(self):
-        settings = get_default_settings(docutils_xml.Parser)
-        # settings.warning_stream = ''
+    def test_parse(self):
+        settings = get_default_settings(parser)
+        settings.warning_stream = ''
         for name, cases in totest.items():
             for casenum, (case_input, case_expected) in enumerate(cases):
                 with self.subTest(id=f'totest[{name!r}][{casenum}]'):
-                    document = new_document('test data', settings.copy())
+                    document = new_document('test data', settings)
                     parser.parse(case_input, document)
                     output = document.pformat()
                     self.assertEqual(case_expected, output)

Modified: trunk/docutils/test/test_parsers/test_docutils_xml/test_parse_element.py
===================================================================
--- trunk/docutils/test/test_parsers/test_docutils_xml/test_parse_element.py	2024-06-06 14:03:21 UTC (rev 9743)
+++ trunk/docutils/test/test_parsers/test_docutils_xml/test_parse_element.py	2024-06-06 14:03:33 UTC (rev 9744)
@@ -27,6 +27,7 @@
 
 class ParseElementTestCase(unittest.TestCase):
     """Test the `docutils.xml.parse_element()` function."""
+    maxDiff = None
 
     # supress warnings when passing `document` to `parse_element()`
     settings = frontend.get_default_settings(docutils_xml.Parser)

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.



_______________________________________________
Docutils-checkins mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/docutils-checkins