Skip to content
This repository

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
branch: master
Fetching contributors…

Octocat-spinner-32-eaf2f5

Cannot retrieve contributors at this time

file 408 lines (333 sloc) 13.514 kb
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
# encoding: utf-8
"""
structured.py - handle structured data/dicts/objects

Created by Maximillian Dornseif on 2009-12-27.
Copyright (c) 2009, 2010, 2011 HUDORA. All rights reserved.
"""
import xml.etree.cElementTree as ET
from StringIO import StringIO


# Basic conversation goal here is converting a dict to an object allowing
# more comfortable access. `Struct()` and `make_struct()` are used to archive
# this goal.
# See http://stackoverflow.com/questions/1305532/convert-python-dict-to-object for the inital Idea
#
# The reasoning for this is the observation that we ferry arround hundreds of dicts via JSON
# and accessing them as `obj['key']` is tiresome after some time. `obj.key` is much nicer.
class Struct(object):
    """Emulate a cross over between a dict() and an object()."""
    def __init__(self, entries, default=None, nodefault=False):
        # ensure all keys are strings and nothing else
        entries = dict([(str(x), y) for x, y in entries.items()])
        self.__dict__.update(entries)
        self.__default = default
        self.__nodefault = nodefault

    def __getattr__(self, name):
        """Emulate Object access.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.a
'b'
>>> obj.foobar
'c'

`hasattr` results in strange behaviour if you give a default value. This might change in the future.
>>> hasattr(obj, 'a')
True
>>> hasattr(obj, 'foobar')
True
"""
        if name.startswith('_'):
            # copy expects __deepcopy__, __getnewargs__ to raise AttributeError
            # see http://groups.google.com/group/comp.lang.python/browse_thread/thread/6ac8a11de4e2526f/
            # e76b9fbb1b2ee171?#e76b9fbb1b2ee171
            raise AttributeError("'<Struct>' object has no attribute '%s'" % name)
        if self.__nodefault:
            raise AttributeError("'<Struct>' object has no attribute '%s'" % name)
        return self.__default

    def __getitem__(self, key):
        """Emulate dict like access.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj['a']
'b'

While the standard dict access via [key] uses the default given when creating the struct,
access via get(), results in None for keys not set. This might be considered a bug and
should change in the future.
>>> obj['foobar']
'c'
>>> obj.get('foobar')
'c'
"""
        # warnings.warn("dict_accss[foo] on a Struct, use object_access.foo instead",
        # DeprecationWarning, stacklevel=2)
        if self.__nodefault:
            return self.__dict__[key]
        return self.__dict__.get(key, self.__default)

    def get(self, key, default=None):
        """Emulate dictionary access.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.get('a')
'b'
>>> obj.get('foobar')
'c'
"""
        if key in self.__dict__:
            return self.__dict__[key]
        if not self.__nodefault:
            return self.__default
        return default

    def __contains__(self, item):
        """Emulate dict 'in' functionality.

>>> obj = Struct({'a': 'b'}, default='c')
>>> 'a' in obj
True
>>> 'foobar' in obj
False
"""
        return item in self.__dict__

    def __nonzero__(self):
        """Returns whether the instance evaluates to False"""
        return bool(self.items())

    def has_key(self, item):
        """Emulate dict.has_key() functionality.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.has_key('a')
True
>>> obj.has_key('foobar')
False
"""
        return item in self

    def items(self):
        """Emulate dict.items() functionality.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.items()
[('a', 'b')]
"""
        return [(k, v) for (k, v) in self.__dict__.items() if not k.startswith('_Struct__')]

    def keys(self):
        """Emulate dict.keys() functionality.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.keys()
['a']
"""
        return [k for (k, _v) in self.__dict__.items() if not k.startswith('_Struct__')]

    def values(self):
        """Emulate dict.values() functionality.

>>> obj = Struct({'a': 'b'}, default='c')
>>> obj.values()
['b']
"""
        return [v for (k, v) in self.__dict__.items() if not k.startswith('_Struct__')]

    def __repr__(self):
        return "<Struct: %r>" % dict(self.items())

    def as_dict(self):
        """Return a dict representing the content of this struct."""
        return self.__dict__


def make_struct(obj, default=None, nodefault=False):
    """Converts a dict to an object, leaves objects untouched.

Someting like obj.vars() = dict() - Read Only!

>>> obj = make_struct(dict(foo='bar'))
>>> obj.foo
'bar'

`make_struct` leaves objects alone.
>>> class MyObj(object): pass
>>> data = MyObj()
>>> data.foo = 'bar'
>>> obj = make_struct(data)
>>> obj.foo
'bar'

`make_struct` also is idempotent
>>> obj = make_struct(make_struct(dict(foo='bar')))
>>> obj.foo
'bar'

`make_struct` recursively handles dicts and lists of dicts
>>> obj = make_struct(dict(foo=dict(bar='baz')))
>>> obj.foo.bar
'baz'

>>> obj = make_struct([dict(foo='baz')])
>>> obj
[<Struct: {'foo': 'baz'}>]
>>> obj[0].foo
'baz'

>>> obj = make_struct(dict(foo=dict(bar=dict(baz='end'))))
>>> obj.foo.bar.baz
'end'

>>> obj = make_struct(dict(foo=[dict(bar='baz')]))
>>> obj.foo[0].bar
'baz'
>>> obj.items()
[('foo', [<Struct: {'bar': 'baz'}>])]
"""
    if type(obj) == type(Struct):
        return obj
    if (not hasattr(obj, '__dict__')) and hasattr(obj, 'iterkeys'):
        # this should be a dict
        struc = Struct(obj, default, nodefault)
        # handle recursive sub-dicts
        for key, val in obj.items():
            setattr(struc, key, make_struct(val, default, nodefault))
        return struc
    elif hasattr(obj, '__delslice__') and hasattr(obj, '__getitem__'):
        #
        return [make_struct(v, default, nodefault) for v in obj]
    else:
        return obj


# Code is based on http://code.activestate.com/recipes/573463/
def _convert_dict_to_xml_recurse(parent, dictitem, listnames, sort=True):
    """Helper Function for XML conversion."""

    if isinstance(dictitem, list):
        raise TypeError('Unable to convert bare lists')

    if isinstance(dictitem, dict):
        items = dictitem.iteritems()
        if sort:
            items = sorted(items)
        for (tag, child) in items:
            if isinstance(child, list):
                # iterate through the array and convert
                itemname = listnames.get(tag, 'item')
                if itemname is not None:
                    listelem = ET.SubElement(parent, tag)
                else:
                    listelem = parent

                for listchild in child:
                    if itemname is not None:
                        elem = ET.SubElement(listelem, itemname)
                    else:
                        elem = ET.SubElement(listelem, tag)

                    _convert_dict_to_xml_recurse(elem, listchild, listnames, sort=sort)
            else:
                if tag.startswith('@'):
                    parent.attrib[tag[1:]] = child
                else:
                    elem = ET.Element(tag)
                    parent.append(elem)
                    _convert_dict_to_xml_recurse(elem, child, listnames, sort=sort)
    elif not dictitem is None:
        parent.text = unicode(dictitem)


def dict2et(xmldict, roottag='data', listnames=None, sort=True):
    """Converts a dict to an ElementTree.

Converts a dictionary to an XML ElementTree Element::

>>> data = {"nr": "xq12", "positionen": [{"m": 12}, {"m": 2}]}
>>> root = dict2et(data)
>>> ET.tostring(root)
'<data><nr>xq12</nr><positionen><item><m>12</m></item><item><m>2</m></item></positionen></data>'

Per default everything is put in an enclosing '<data>' element. Also per default lists are converted
to collections of `<item>` elements. By provding a mapping between list names and element names,
you can generate different elements:

>>> data = {"positionen": [{"m": 12}, {"m": 2}]}
>>> root = dict2et(data, roottag='xml')
>>> ET.tostring(root)
'<xml><positionen><item><m>12</m></item><item><m>2</m></item></positionen></xml>'

>>> root = dict2et(data, roottag='xml', listnames={'positionen': 'position'})
>>> ET.tostring(root)
'<xml><positionen><position><m>12</m></position><position><m>2</m></position></positionen></xml>'

If you explictly set the elementname to None, a flat list is created:
>>> root = dict2et(data, roottag='flat', listnames={'positionen': None})
>>> ET.tostring(root)
'<flat><positionen><m>12</m></positionen><positionen><m>2</m></positionen></flat>'

>>> data = {"kommiauftragsnr":2103839, "anliefertermin":"2009-11-25", "prioritaet": 7,
... "ort": u"Hücksenwagen",
... "positionen": [{"menge": 12, "artnr": "14640/XL", "posnr": 1},],
... "versandeinweisungen": [{"guid": "2103839-XalE", "bezeichner": "avisierung48h",
... "anweisung": "48h vor Anlieferung unter 0900-LOGISTIK avisieren"},
... ]}

>>> print ET.tostring(dict2et(data, 'kommiauftrag',
... listnames={'positionen': 'position', 'versandeinweisungen': 'versandeinweisung'}))
... # doctest: +SKIP
'''<kommiauftrag>
<anliefertermin>2009-11-25</anliefertermin>
<positionen>
<position>
<posnr>1</posnr>
<menge>12</menge>
<artnr>14640/XL</artnr>
</position>
</positionen>
<ort>H&#xC3;&#xBC;cksenwagen</ort>
<versandeinweisungen>
<versandeinweisung>
<bezeichner>avisierung48h</bezeichner>
<anweisung>48h vor Anlieferung unter 0900-LOGISTIK avisieren</anweisung>
<guid>2103839-XalE</guid>
</versandeinweisung>
</versandeinweisungen>
<prioritaet>7</prioritaet>
<kommiauftragsnr>2103839</kommiauftragsnr>
</kommiauftrag>'''

Sorting can be disabled which is only useful for collections.OrderedDict.
"""

    if not listnames:
        listnames = {}
    root = ET.Element(roottag)
    _convert_dict_to_xml_recurse(root, xmldict, listnames, sort=sort)
    return root


def list2et(xmllist, root, elementname):
    """Converts a list to an ElementTree.

See also dict2et()
"""

    basexml = dict2et({root: xmllist}, 'xml', listnames={root: elementname})
    return basexml.find(root)


def dict2xml(datadict, roottag='data', listnames=None, pretty=False, sort=True):
    """Converts a dictionary to an UTF-8 encoded XML string.

See also dict2et()
"""
    root = dict2et(datadict, roottag, listnames, sort=sort)
    return to_string(root, pretty=pretty)


def list2xml(datalist, roottag, elementname, pretty=False):
    """Converts a list to an UTF-8 encoded XML string.

See also dict2et()
"""
    root = list2et(datalist, roottag, elementname)
    return to_string(root, pretty=pretty)


def to_string(root, encoding='utf-8', pretty=False):
    """Converts an ElementTree to a string"""

    if pretty:
        indent(root)

    tree = ET.ElementTree(root)
    fileobj = StringIO()
    fileobj.write('<?xml version="1.0" encoding="%s"?>' % encoding)
    if pretty:
        fileobj.write('\n')
    tree.write(fileobj, 'utf-8')
    return fileobj.getvalue()


# From http://effbot.org/zone/element-lib.htm
# prettyprint: Prints a tree with each node indented according to its depth. This is
# done by first indenting the tree (see below), and then serializing it as usual.
# indent: Adds whitespace to the tree, so that saving it as usual results in a prettyprinted tree.
# in-place prettyprint formatter

def indent(elem, level=0):
    """XML prettyprint: Prints a tree with each node indented according to its depth."""
    i = "\n" + level * " "
    if len(elem):
        if not elem.text or not elem.text.strip():
            elem.text = i + " "
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
        for child in elem:
            indent(child, level + 1)
        if child:
            if not child.tail or not child.tail.strip():
                child.tail = i
            if not elem.tail or not elem.tail.strip():
                elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i


def test():
    """Simple selftest."""

    data = {"guid": "3104247-7",
            "menge": 7,
            "artnr": "14695",
            "batchnr": "3104247"}
    xmlstr = dict2xml(data, roottag='warenzugang')
    assert xmlstr == ('<?xml version="1.0" encoding="utf-8"?><warenzugang><artnr>14695</artnr>'
                      '<batchnr>3104247</batchnr><guid>3104247-7</guid><menge>7</menge></warenzugang>')


if __name__ == '__main__':
    import doctest
    import sys
    failure_count, test_count = doctest.testmod()
    d = make_struct({
        'item1': 'string',
        'item2': ['dies', 'ist', 'eine', 'liste'],
        'item3': dict(dies=1, ist=2, ein=3, dict=4),
        'item4': 10,
        'item5': [dict(dict=1, in_einer=2, liste=3)]})
    test()
    sys.exit(failure_count)
Something went wrong with that request. Please try again.