Merge pull request #607 from JackDandy/feature/UpdateXmltodict

Update xmltodict library 0.9.2 (579a005) to 0.9.2 (eac0031).

CHANGES.md

@@ -1,6 +1,6 @@
 ### 0.12.0 (2016-xx-xx xx:xx:xx UTC)
 
-*
+* Update xmltodict library 0.9.2 (579a005) to 0.9.2 (eac0031)
 
 
 ### 0.11.0 (2016-01-10 22:30:00 UTC)

lib/xmltodict.py

@@ -50,10 +50,11 @@ class _DictSAXHandler(object):
                  dict_constructor=OrderedDict,
                  strip_whitespace=True,
                  namespace_separator=':',
-                 namespaces=None):
+                 namespaces=None,
+                 force_list=()):
         self.path = []
         self.stack = []
-        self.data = None
+        self.data = []
         self.item = None
         self.item_depth = item_depth
         self.xml_attribs = xml_attribs
@@ -67,6 +68,7 @@ class _DictSAXHandler(object):
         self.strip_whitespace = strip_whitespace
         self.namespace_separator = namespace_separator
         self.namespaces = namespaces
+        self.force_list = force_list
 
     def _build_name(self, full_name):
         if not self.namespaces:
@@ -99,21 +101,25 @@ class _DictSAXHandler(object):
             else:
                 attrs = None
             self.item = attrs or None
-            self.data = None
+            self.data = []
 
     def endElement(self, full_name):
         name = self._build_name(full_name)
         if len(self.path) == self.item_depth:
             item = self.item
             if item is None:
-                item = self.data
+                item = (None if not self.data
+                        else self.cdata_separator.join(self.data))
+
             should_continue = self.item_callback(self.path, item)
             if not should_continue:
                 raise ParsingInterrupted()
         if len(self.stack):
-            item, data = self.item, self.data
+            data = (None if not self.data
+                    else self.cdata_separator.join(self.data))
+            item = self.item
             self.item, self.data = self.stack.pop()
-            if self.strip_whitespace and data is not None:
+            if self.strip_whitespace and data:
                 data = data.strip() or None
             if data and self.force_cdata and item is None:
                 item = self.dict_constructor()
@@ -124,14 +130,15 @@ class _DictSAXHandler(object):
             else:
                 self.item = self.push_data(self.item, name, data)
         else:
-            self.item = self.data = None
+            self.item = None
+            self.data = []
         self.path.pop()
 
     def characters(self, data):
         if not self.data:
-            self.data = data
+            self.data = [data]
         else:
-            self.data += self.cdata_separator + data
+            self.data.append(data)
 
     def push_data(self, item, key, data):
         if self.postprocessor is not None:
@@ -148,7 +155,10 @@ class _DictSAXHandler(object):
             else:
                 item[key] = [value, data]
         except KeyError:
-            item[key] = data
+            if key in self.force_list:
+                item[key] = [data]
+            else:
+                item[key] = data
         return item
 
 
@@ -220,6 +230,37 @@ def parse(xml_input, encoding=None, expat=expat, process_namespaces=False,
         >>> xmltodict.parse('<a>hello</a>', expat=defusedexpat.pyexpat)
         OrderedDict([(u'a', u'hello')])
 
+    You can use the force_list argument to force lists to be created even
+    when there is only a single child of a given level of hierarchy. The
+    force_list argument is a tuple of keys. If the key for a given level
+    of hierarchy is in the force_list argument, that level of hierarchy
+    will have a list as a child (even if there is only one sub-element).
+    The index_keys operation takes precendence over this. This is applied
+    after any user-supplied postprocessor has already run.
+
+        For example, given this input:
+        <servers>
+          <server>
+            <name>host1</name>
+            <os>Linux</os>
+            <interfaces>
+              <interface>
+                <name>em0</name>
+                <ip_address>10.0.0.1</ip_address>
+              </interface>
+            </interfaces>
+          </server>
+        </servers>
+
+        If called with force_list=('interface',), it will produce
+        this dictionary:
+        {'servers':
+          {'server':
+            {'name': 'host1',
+             'os': 'Linux'},
+             'interfaces':
+              {'interface':
+                [ {'name': 'em0', 'ip_address': '10.0.0.1' } ] } } }
     """
     handler = _DictSAXHandler(namespace_separator=namespace_separator,
                               **kwargs)