/usr/lib/python2.7/dist-packages/openpyxl/develop/classify.py is in python-openpyxl 2.3.0-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | from __future__ import absolute_import, print_function
# Copyright (c) 2010-2015 openpyxl
"""
Generate Python classes from XML Schema
Disclaimer: this is really shabby, "works well enough" code.
The spyne library does a much better job of interpreting the schema.
"""
import argparse
import re
import logging
logging.basicConfig(filename="classify.log", level=logging.DEBUG)
from openpyxl.tests.schema import (
sheet_src,
chart_src,
drawing_main_src,
drawing_src,
shared_src,
)
from lxml.etree import parse
XSD = "http://www.w3.org/2001/XMLSchema"
simple_mapping = {
'xsd:boolean':'Bool',
'xsd:unsignedInt':'Integer',
'xsd:int':'Integer',
'xsd:double':'Float',
'xsd:string':'String',
'xsd:unsignedByte':'Integer',
'xsd:byte':'Integer',
'xsd:long':'Float',
'xsd:token':'String',
's:ST_Panose':'HexBinary',
's:ST_Lang':'String',
'ST_Percentage':'String',
'ST_PositivePercentage':'Percentage',
'ST_TextPoint':'TextPoint',
'ST_UniversalMeasure':'UniversalMeasure',
'ST_Coordinate32':'Coordinate',
'ST_Coordinate':'Coordinate',
'ST_Coordinate32Unqualified':'Coordinate',
's:ST_Xstring':'String',
'ST_Angle':'Integer',
}
complex_mapping = {
'Boolean':'Bool',
'Double':'Float',
'Long':'Integer',
}
ST_REGEX = re.compile("(?P<schema>[a-z]:)?(?P<typename>ST_[A-Za-z]+)")
def get_attribute_group(schema, tagname):
for node in schema.iterfind("{%s}attributeGroup" % XSD):
if node.get("ref") == tagname:
break
attrs = node.findall("{%s}attribute" % XSD)
return attrs
def get_element_group(schema, tagname):
for node in schema.iterfind("{%s}group" % XSD):
if node.get("name") == tagname:
break
seq = node.findall("{%s}sequence/{%s}element" % (XSD, XSD))
choice = node.findall("{%s}choice/{%s}element" % (XSD, XSD))
return seq + choice
def classify(tagname, src=sheet_src, schema=None):
"""
Generate a Python-class based on the schema definition
"""
if schema is None:
schema = parse(src)
nodes = schema.iterfind("{%s}complexType" % XSD)
tag = None
for node in nodes:
if node.get('name') == tagname:
tag = tagname
break
if tag is None:
pass
raise ValueError("Tag {0} not found".format(tagname))
types = set()
s = """\n\nclass %s(Serialisable):\n\n""" % tagname[3:]
attrs = []
# attributes
attributes = node.findall("{%s}attribute" % XSD)
_group = node.find("{%s}attributeGroup" % XSD)
if _group is not None:
s += " #Using attribute group{0}\n".format(_group.get('ref'))
attributes.extend(get_attribute_group(schema, _group.get('ref')))
for el in attributes:
attr = el.attrib
if 'ref' in attr:
continue
attrs.append(attr['name'])
if attr.get("use") == "optional":
attr["use"] = "allow_none=True"
else:
attr["use"] = ""
if attr.get("type").startswith("ST_"):
attr['type'] = simple(attr.get("type"), schema, attr['use'])
types.add(attr['type'].split("(")[0])
s += " {name} = {type}\n".format(**attr)
else:
if attr['type'] in simple_mapping:
attr['type'] = simple_mapping[attr['type']]
types.add(attr['type'])
s += " {name} = {type}({use})\n".format(**attr)
else:
s += " {name} = Typed(expected_type={type}, {use})\n".format(**attr)
children = []
element_names =[]
elements = node.findall("{%s}sequence/{%s}element" % (XSD, XSD))
choice = node.findall("{%s}choice/{%s}element" % (XSD, XSD))
if choice:
s += """ # some elements are choice\n"""
elements.extend(choice)
groups = node.findall("{%s}sequence/{%s}group" % (XSD, XSD))
for group in groups:
ref = group.get("ref")
s += """ # uses element group {0}\n""".format(ref)
elements.extend(get_element_group(schema, ref))
for el in elements:
attr = {'name': el.get("name"),}
typename = el.get("type")
match = ST_REGEX.match(typename)
if typename.startswith("xsd:"):
attr['type'] = simple_mapping[typename]
types.add(attr['type'])
elif match is not None:
src = srcs_mapping.get(match.group('schema'))
if src is not None:
schema = parse(src)
typename = match.group('typename')
attr['type'] = simple(typename, schema)
else:
if (typename.startswith("a:")
or typename.startswith("s:")
):
attr['type'] = typename[5:]
else:
attr['type'] = typename[3:]
children.append(typename)
element_names.append(attr['name'])
attr['use'] = ""
if el.get("minOccurs") == "0" or el in choice:
attr['use'] = "allow_none=True"
attrs.append(attr['name'])
if attr['type'] in complex_mapping:
attr['type'] = complex_mapping[attr['type']]
s += " {name} = {type}(nested=True, {use})\n".format(**attr)
else:
s += " {name} = Typed(expected_type={type}, {use})\n".format(**attr)
if element_names:
names = (c for c in element_names)
s += "\n __elements__ = {0}\n".format(tuple(names))
if attrs:
s += "\n def __init__(self,\n"
for a in attrs:
s += " %s=None,\n" % a
s += " ):\n"
else:
s += " pass"
for attr in attrs:
s += " self.{0} = {0}\n".format(attr)
return s, types, children
def simple(tagname, schema, use=""):
for node in schema.iterfind("{%s}simpleType" % XSD):
if node.get("name") == tagname:
break
constraint = node.find("{%s}restriction" % XSD)
if constraint is None:
return "unknown defintion for {0}".format(tagname)
typ = constraint.get("base")
typ = "{0}()".format(simple_mapping.get(typ, typ))
values = constraint.findall("{%s}enumeration" % XSD)
values = [v.get('value') for v in values]
if values:
s = "Set"
if "none" in values:
idx = values.index("none")
del values[idx]
s = "NoneSet"
typ = s + "(values=({0}))".format(values)
return typ
srcs_mapping = {'a:':drawing_main_src, 's:':shared_src}
class ClassMaker:
"""
Generate
"""
def __init__(self, tagname, src=chart_src, classes=set()):
self.schema=parse(src)
self.types = set()
self.classes = classes
self.body = ""
self.create(tagname)
def create(self, tagname):
body, types, children = classify(tagname, schema=self.schema)
self.body = body + self.body
self.types = self.types.union(types)
for child in children:
if (child.startswith("a:")
or child.startswith("s:")
):
src = srcs_mapping[child[:2]]
tagname = child[2:]
if tagname not in self.classes:
cm = ClassMaker(tagname, src=src, classes=self.classes)
self.body = cm.body + self.body # prepend dependent types
self.types.union(cm.types)
self.classes.add(tagname)
self.classes.union(cm.classes)
continue
if child not in self.classes:
self.create(child)
self.classes.add(child)
def __str__(self):
s = """#Autogenerated schema
from openpyxl.descriptors.serialisable import Serialisable
from openpyxl.descriptors import (\n Typed,"""
for t in self.types:
s += "\n {0},".format(t)
s += (")\n")
s += self.body
return s
def make(element, schema=sheet_src):
cm = ClassMaker(element, schema)
print(cm)
commands = argparse.ArgumentParser(description="Generate Python classes for a specific scheme element")
commands.add_argument('element', help='The XML type to be converted')
commands.add_argument('--schema',
help='The relevant schema. The default is for worksheets',
choices=["sheet_src", "chart_src", "shared_src", "drawing_src", "drawing_main_src"],
default="sheet_src",
)
if __name__ == "__main__":
args = commands.parse_args()
schema = globals().get(args.schema)
make(args.element, schema)
|