add xml utility functions (#26333)

passerelle/utils/xml.py

@@ -0,0 +1,83 @@
+# passerelle - uniform access to multiple data sources and services
+# Copyright (C) 2018 Entr'ouvert
+#
+# This program is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+def text_content(node):
+    '''Extract text content from node and all its children. Equivalent to
+       xmlNodeGetContent from libxml.'''
+
+    if node is None:
+        return ''
+
+    def helper(node):
+        s = []
+        if node.text:
+            s.append(node.text)
+        for child in node:
+            s.extend(helper(child))
+            if child.tail:
+                s.append(child.tail)
+        return s
+    return u''.join(helper(node))
+
+
+def to_json(root):
+    '''Convert an XML document (a rooted tree) into dictionnary compatible with
+       JSON serialization following those rules:
+       - root is converted into a dictionnary, its children's node name are the
+         keys,
+       - all child nodes without child are considered to be only text and
+         converted to a JSON string,
+       - all child nodes with children are converted to an array with they
+         children as root of a new conversion from XML to JSON.
+
+       Ex.:
+
+         <root>
+            <child1>wtv</chidl1>
+            <rows>
+              <row>
+                 <child2>2</child2>
+              </row>
+              <row>
+                 <child3>3</child3>
+              </row>
+            </rows>
+          </root>
+
+         is converted to:
+
+         {
+            "child1": "wtv",
+            "rows": [
+                {"child2": "2"},
+                {"child3": "3"}
+            ]
+        }'''
+
+    d = {}
+    for child in root:
+        if not len(child):  # text node
+            value = text_content(child)
+            if value:
+                d[child.tag] = value
+        else:
+            d.setdefault(child.tag, [])
+            for row in child:
+                child_content = to_json(row)
+                if child_content:
+                    d[child.tag].append(child_content)
+    return d

tests/test_utils_xml.py

@@ -0,0 +1,33 @@
+import xml.etree.ElementTree as ET
+
+from passerelle.utils.xml import to_json, text_content
+
+
+def test_text_content():
+    root = ET.fromstring('<root>aa<b>bb</b>cc</root>')
+    assert text_content(root) == 'aabbcc'
+
+
+def test_to_json():
+    root = ET.fromstring('''<root>
+        <text1>1</text1>
+        <text2>2</text2>
+        <enfants>
+            <enfant>
+                <text3>3</text3>
+            </enfant>
+            <enfant>
+                <text3>4</text3>
+            </enfant>
+            <zob/>
+        </enfants>
+        <zob/>
+</root>''')
+    assert to_json(root) == {
+        'text1': '1',
+        'text2': '2',
+        'enfants': [
+            {'text3': '3'},
+            {'text3': '4'},
+        ]
+    }