-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathload_data.py
192 lines (147 loc) · 6.45 KB
/
load_data.py
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
import correction
import schema
import csv
import codecs
import pprint
import re
import xml.etree.cElementTree as ET
import cerberus
OSM_PATH = "calgary_canada.osm"
NODES_PATH = "nodes.csv"
NODE_TAGS_PATH = "nodes_tags.csv"
WAYS_PATH = "ways.csv"
WAY_NODES_PATH = "ways_nodes.csv"
WAY_TAGS_PATH = "ways_tags.csv"
LOWER_COLON = re.compile(r'^([a-z]|_)+:([a-z]|_)+')
PROBLEMCHARS = re.compile(r'[=\+/&<>;\'"\?%#$@\,\. \t\r\n]')
SCHEMA = schema.schema
# Make sure the fields order in the csvs matches the column order in the sql table schema
NODE_FIELDS = ['id', 'lat', 'lon', 'user', 'uid', 'version', 'changeset', 'timestamp']
NODE_TAGS_FIELDS = ['id', 'key', 'value', 'type']
WAY_FIELDS = ['id', 'user', 'uid', 'version', 'changeset', 'timestamp']
WAY_TAGS_FIELDS = ['id', 'key', 'value', 'type']
WAY_NODES_FIELDS = ['id', 'node_id', 'position']
def shape_element(element, node_attr_fields=NODE_FIELDS, way_attr_fields=WAY_FIELDS,
problem_chars=PROBLEMCHARS, default_tag_type='regular'):
"""Clean and shape node or way XML element to Python dict"""
node_attribs = {}
way_attribs = {}
way_nodes = []
tags = [] # Handle secondary tags the same way for both node and way elements
key_format = re.compile(r'^(\w+):(.+)$')
if element.tag == 'node':
for attrib in element.attrib:
if attrib in NODE_FIELDS:
node_attribs[attrib] = element.attrib[attrib]
for tag in element.iter('tag'):
tag_dict = {}
key = tag.attrib['k']
value = tag.attrib['v']
if re.search(PROBLEMCHARS, key):
continue
elif re.match(LOWER_COLON, key):
key_match = re.match(key_format, key)
key = key_match.group(2)
type = key_match.group(1)
else:
type = default_tag_type
tag_dict['id'] = element.attrib['id']
tag_dict['key'] = key
if (type == "addr") and (key == "street"):
tag_dict['value'] = correction.update_addr(value)
elif (type == "addr") and (key == "postcode"):
tag_dict['value'] = correction.update_postal(value)
else:
tag_dict['value'] = value
tag_dict['type'] = type
tags.append(tag_dict)
return {'node': node_attribs, 'node_tags': tags}
elif element.tag == 'way':
for attrib in element.attrib:
if attrib in WAY_FIELDS:
way_attribs[attrib] = element.attrib[attrib]
for tag in element.findall('tag'):
tag_dict = {}
key = tag.attrib['k']
value = tag.attrib['v']
if re.search(PROBLEMCHARS, key):
continue
elif re.match(LOWER_COLON, key):
key_match = re.match(key_format, key)
key = key_match.group(2)
type = key_match.group(1)
else:
type = default_tag_type
tag_dict['id'] = element.attrib['id']
tag_dict['key'] = key
if (type == "addr") and (key == "street"):
tag_dict['value'] = correction.update_addr(value)
elif (type == "addr") and (key == "postcode"):
tag_dict['value'] = correction.update_postal(value)
else:
tag_dict['value'] = value
tag_dict['type'] = type
tags.append(tag_dict)
i = 0
for nd in element.findall('nd'):
nd_dict = {}
nd_dict['id'] = element.attrib['id']
nd_dict['node_id'] = nd.attrib['ref']
nd_dict['position'] = i
way_nodes.append(nd_dict)
i += 1
return {'way': way_attribs, 'way_nodes': way_nodes, 'way_tags': tags}
def get_element(osm_file, tags=('node', 'way', 'relation')):
"""Yield element if it is the right type of tag"""
context = ET.iterparse(osm_file, events=('start', 'end'))
_, root = next(context)
for event, elem in context:
if event == 'end' and elem.tag in tags:
yield elem
root.clear()
def validate_element(element, validator, schema=SCHEMA):
"""Raise ValidationError if element does not match schema"""
if validator.validate(element, schema) is not True:
field, errors = next(validator.errors.iteritems())
message_string = "\nElement of type '{0}' has the following errors:\n{1}"
error_string = pprint.pformat(errors)
raise Exception(message_string.format(field, error_string))
class UnicodeDictWriter(csv.DictWriter, object):
"""Extend csv.DictWriter to handle Unicode input"""
def writerow(self, row):
super(UnicodeDictWriter, self).writerow({
k: (v.encode('utf-8') if isinstance(v, unicode) else v) for k, v in row.iteritems()
})
def writerows(self, rows):
for row in rows:
self.writerow(row)
def process_map(file_in, validate):
"""Iteratively process each XML element and write to csv(s)"""
with codecs.open(NODES_PATH, 'w') as nodes_file, \
codecs.open(NODE_TAGS_PATH, 'w') as nodes_tags_file, \
codecs.open(WAYS_PATH, 'w') as ways_file, \
codecs.open(WAY_NODES_PATH, 'w') as way_nodes_file, \
codecs.open(WAY_TAGS_PATH, 'w') as way_tags_file:
nodes_writer = UnicodeDictWriter(nodes_file, NODE_FIELDS)
node_tags_writer = UnicodeDictWriter(nodes_tags_file, NODE_TAGS_FIELDS)
ways_writer = UnicodeDictWriter(ways_file, WAY_FIELDS)
way_nodes_writer = UnicodeDictWriter(way_nodes_file, WAY_NODES_FIELDS)
way_tags_writer = UnicodeDictWriter(way_tags_file, WAY_TAGS_FIELDS)
nodes_writer.writeheader()
node_tags_writer.writeheader()
ways_writer.writeheader()
way_nodes_writer.writeheader()
way_tags_writer.writeheader()
validator = cerberus.Validator()
for element in get_element(file_in, tags=('node', 'way')):
el = shape_element(element)
if el:
if validate is True:
validate_element(el, validator)
if element.tag == 'node':
nodes_writer.writerow(el['node'])
node_tags_writer.writerows(el['node_tags'])
elif element.tag == 'way':
ways_writer.writerow(el['way'])
way_nodes_writer.writerows(el['way_nodes'])
way_tags_writer.writerows(el['way_tags'])