SF.net SVN: docutils:[9735 ] trunk/docutils

Revision: 9735
          http://sourceforge.net/p/docutils/code/9735
Author:   milde
Date:     2024-06-06 14:01:46 +0000 (Thu, 06 Jun 2024)
Log Message:
-----------
xml-parser: new optional argument `document` for `parse_node()`.

The default is a new "dummy" `nodes.document` instance.

* Passed to the auxiliary `element2node()` function.
* Fixes ``parse_node('<document></document>)`` (instantiating
  `nodes.document` requires additional arguments).
* Provides a "reporter" instance.
* Provides a configuration settings instance.

Use `parse_node()` to simplify `Parser.parse()`.

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

Modified: trunk/docutils/docutils/parsers/docutils_xml.py
===================================================================
--- trunk/docutils/docutils/parsers/docutils_xml.py	2024-06-06 14:01:35 UTC (rev 9734)
+++ trunk/docutils/docutils/parsers/docutils_xml.py	2024-06-06 14:01:46 UTC (rev 9735)
@@ -21,7 +21,7 @@
 
 import xml.etree.ElementTree as ET
 
-from docutils import nodes, parsers
+from docutils import frontend, nodes, parsers, utils
 
 
 class Parser(parsers.Parser):
@@ -45,24 +45,22 @@
         """
         self.setup_parse(inputstring, document)
 
-        # get ElementTree
-        root = ET.fromstring(inputstring)
-        # convert ElementTree to Docutils Document Tree
-        if root.tag == 'document':
-            convert_attribs(document, root.attrib)
-            for element in root:
-                document.append(element2node(element))
-        else:
-            document.append(element2node(root))
+        node = parse_element(inputstring, document)
+        if not isinstance(node, nodes.document):
+            document.append(node)
 
         self.finish_parse()
 
 
-def parse_element(inputstring):
+def parse_element(inputstring, document=None):
     """
     Parse `inputstring` as "Docutils XML", return `nodes.Element` instance.
 
     :inputstring: XML source.
+    :document: `nodes.document` instance (default: a new dummy instance).
+               Provides settings and reporter.
+               Populated and returned, if the inputstring's root element
+               is <document>.
 
     Caution:
       The function does not detect invalid XML.
@@ -75,10 +73,10 @@
 
     Provisional.
     """
-    return element2node(ET.fromstring(inputstring))
+    return element2node(ET.fromstring(inputstring), document)
 
 
-def element2node(element):
+def element2node(element, document=None):
     """
     Convert an `etree` element and its children to Docutils doctree nodes.
 
@@ -86,12 +84,22 @@
 
     Internal.
     """
+    if document is None:
+        document = utils.new_document('xml input',
+                                      frontend.get_default_settings(Parser))
+
     # Get the corresponding `nodes.Element` instance:
     nodeclass = getattr(nodes, element.tag)
-    node = nodeclass()
+    if nodeclass == nodes.document:
+        node = document
+    else:
+        node = nodeclass()
 
     # Attributes: convert and add to `node.attributes`.
-    convert_attribs(node, element.attrib)
+    for key, value in element.items():
+        if key.startswith('{'):
+            continue  # skip duplicate attributes with namespace URL
+        node.attributes[key] = nodes.ATTRIBUTE_VALIDATORS[key](value)
 
     # Append text (wrapped in a `nodes.Text` instance)
     append_text(node, element.text)
@@ -98,7 +106,7 @@
 
     # Append children and their tailing text
     for child in element:
-        node.append(element2node(child))
+        node.append(element2node(child, document))
         # Text after a child node
         append_text(node, child.tail)
 
@@ -105,14 +113,6 @@
     return node
 
 
-def convert_attribs(node, a):
-    # Convert doctree element attribute values from string to their datatype,
-    for key, value in a.items():
-        if key.startswith('{'):
-            continue  # skip duplicate attributes with namespace URL
-        node.attributes[key] = nodes.ATTRIBUTE_VALIDATORS[key](value)
-
-
 def append_text(node, text):
     if not text:
         return

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 14:01:35 UTC (rev 9734)
+++ trunk/docutils/test/test_parsers/test_docutils_xml/test_parse_element.py	2024-06-06 14:01:46 UTC (rev 9735)
@@ -195,8 +195,14 @@
     # 'suffix': CDATA (str) → test_enumtype
 
     def test_title(self):  # CDATA (str)
-        ...
-        # TODO: <document> does not work with parse_element()
+        xml = (r'<document ids="test-document" names="test\ document"'
+               r'          source="/tmp/foo.rst" title="Test Document" />')
+        expected = {'ids': ['test-document'],
+                    'names': ['test document'],
+                    'source': '/tmp/foo.rst',
+                    'title': 'Test Document'}
+        node = docutils_xml.parse_element(xml)
+        self.assertEqual(node.attributes, self.common_attributes | expected)
 
     # 'uri': CDATA (str)                → test_alt
     # 'width' measure (str)             → test_alt

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