Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Optional force separate dict for repetitive elements #350

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Optional force separate dict for repetitive elements #350

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
340b04c
force seperate dict
austinchang-jabil Jun 17, 2024
b9ee4f7
dictToXml: Put list of children of single-keyed dict into single pare…
austinchang-jabil Jul 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 86 additions & 0 deletions tests/test_xmltodict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -475,3 +475,89 @@ def handler(path, item):
return True

parse(xml, item_depth=2, item_callback=handler)


def test_force_seperate_dict_basic(self):
xml = """
<servers>
<server>
<name>server1</name>
<os>os1</os>
</server>
<server>
<name>server2</name>
<os>os2</os>
</server>
<server>
<name>server3</name>
<os>os3</os>
</server>
</servers>
"""
expectedResult = {
'servers': [
{'server':
{ 'name': 'server1',
'os': 'os1' }
},
{'server':
{ 'name': 'server2',
'os': 'os2' }
},
{'server':
{ 'name': 'server3',
'os': 'os3' }
},
],
}
self.assertEqual(parse(xml, force_seperate_dict=('server',)), expectedResult)

def test_force_seperate_dict_with_other_elements(self):
xml = """
<config>
<servers>
<not_force_seperate_element>
<name>server0</name>
<os>os0</os>
</not_force_seperate_element>
<server>
<name>server1</name>
<os>os1</os>
</server>
<not_force_seperate_element>
<name>server2</name>
<os>os2</os>
</not_force_seperate_element>
<server>
<name>server3</name>
<os>os3</os>
</server>
</servers>
</config>
"""

expectedResult = {
'config': {
'servers': [
{'not_force_seperate_element':
{ 'name': 'server0',
'os': 'os0' }
},
{'server':
{ 'name': 'server1',
'os': 'os1' }
},
{ 'not_force_seperate_element':
{ 'name': 'server2',
'os': 'os2' }
},
{'server':
{ 'name': 'server3',
'os': 'os3' }
}
]
},
}

# only 'server' is in force_seperate_dict
self.assertEqual(parse(xml, force_seperate_dict=('server',)), expectedResult)
91 changes: 63 additions & 28 deletions xmltodict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@ def __init__(self,
namespace_separator=':',
namespaces=None,
force_list=None,
force_seperate_dict=None,
comment_key='#comment'):
self.path = []
self.stack = []
Expand All @@ -71,6 +72,7 @@ def __init__(self,
self.namespaces = namespaces
self.namespace_declarations = dict_constructor()
self.force_list = force_list
self.force_seperate_dict = force_seperate_dict
self.comment_key = comment_key

def _build_name(self, full_name):
Expand Down Expand Up @@ -170,30 +172,47 @@ def push_data(self, item, key, data):
if result is None:
return item
key, data = result

if item is None:
item = self.dict_constructor()
try:
value = item[key]
if isinstance(value, list):
value.append(data)
if self._should_force_seperate_dict(key, data):
item = []
else:
item[key] = [value, data]
except KeyError:
if self._should_force_list(key, data):
item[key] = [data]
else:
item[key] = data
item = self.dict_constructor()
elif isinstance(item, dict) and self._should_force_seperate_dict(key, data):
item = [{k: v} for k, v in item.items()]

if isinstance(item, list):
item.append({key: data})
else:
try:
value = item[key]
if isinstance(value, list):
value.append(data)
else:
item[key] = [value, data]
except KeyError:
if self._should_force_list(key, data):
item[key] = [data]
else:
item[key] = data
return item

def _should_force_list(self, key, value):
if not self.force_list:
@staticmethod
def _is_true_or_returns_true(handler, boolean_or_callable, key, value):
if not boolean_or_callable:
return False
if isinstance(self.force_list, bool):
return self.force_list
if isinstance(boolean_or_callable, bool):
return boolean_or_callable
try:
return key in self.force_list
return key in boolean_or_callable
except TypeError:
return self.force_list(self.path[:-1], key, value)
return boolean_or_callable(handler.path[:-1], key, value)

def _should_force_seperate_dict(self, key, value):
return self._is_true_or_returns_true(self, self.force_seperate_dict, key, value)

def _should_force_list(self, key, value):
return self._is_true_or_returns_true(self, self.force_list, key, value)


def parse(xml_input, encoding=None, expat=expat, process_namespaces=False,
Expand Down Expand Up @@ -409,29 +428,45 @@ def _emit(key, value, content_handler,
if result is None:
return
key, value = result
if not hasattr(value, '__iter__') or isinstance(value, (_basestring, dict)):
value = [value]

are_all_children_single_dict = False
if isinstance(value, (_basestring, dict)):
value = [value] # single child or single dict, both can be hold in single parent
elif hasattr(value, '__iter__'): # multiple childs, check if they can have single parent
value = [*value] # build a list in case the value is a generator which can only iterate once
if all(isinstance(listitem, dict) and len(listitem) == 1 for listitem in value):
are_all_children_single_dict = True
value = [value] # all are dicts with single key, can use single parent
else:
pass # other iter types CANNOT be hold in single parent node
else:
value = [value] # single child

for index, v in enumerate(value):
if full_document and depth == 0 and index > 0:
raise ValueError('document with multiple roots')

if v is None:
v = _dict()
list_key_values = []
elif are_all_children_single_dict:
list_key_values = [next(iter(item.items())) for item in v]
elif isinstance(v, bool):
if v:
v = _unicode('true')
list_key_values = [(cdata_key, _unicode('true'))]
else:
v = _unicode('false')
elif not isinstance(v, dict):
list_key_values = [(cdata_key, _unicode('false'))]
elif not isinstance(v, dict) :
if expand_iter and hasattr(v, '__iter__') and not isinstance(v, _basestring):
v = _dict(((expand_iter, v),))
list_key_values = [(expand_iter, v)]
else:
v = _unicode(v)
if isinstance(v, _basestring):
v = _dict(((cdata_key, v),))
list_key_values = [(cdata_key, _unicode(v))]
else:
list_key_values = v.items()

cdata = None
attrs = _dict()
children = []
for ik, iv in v.items():
for ik, iv in list_key_values:
if ik == cdata_key:
cdata = iv
continue
Expand Down