1
|
#!/usr/bin/env python
|
2
|
# Converts a CSV dataset to XML using a mappings spreadsheet
|
3
|
|
4
|
import csv
|
5
|
import re
|
6
|
import sys
|
7
|
from copy import deepcopy
|
8
|
from xml.dom.minidom import getDOMImplementation
|
9
|
|
10
|
from XpathParser import XpathParser, XpathElem
|
11
|
from xml_dom import by_path
|
12
|
|
13
|
def main():
|
14
|
prog_name = sys.argv.pop(0)
|
15
|
try:
|
16
|
dest = sys.argv.pop(0)
|
17
|
mappings_path = sys.argv.pop(0)
|
18
|
except IndexError: raise Exception('Usage: '+prog_name
|
19
|
+' dest_mappings_column mappings_path <dataset')
|
20
|
|
21
|
# Get mappings
|
22
|
mappings = {}
|
23
|
stream = open(mappings_path, 'rb')
|
24
|
reader = csv.reader(stream, delimiter=',', quotechar='"')
|
25
|
fieldnames = reader.next()
|
26
|
src = fieldnames[0]
|
27
|
dest_idx = fieldnames.index(dest)
|
28
|
for row in reader:
|
29
|
name = row[0]
|
30
|
path = row[dest_idx]
|
31
|
if path != '':
|
32
|
if path.startswith('?'): path = path[1:]
|
33
|
path = path.replace('<name>', name)
|
34
|
path = re.sub(r'(?<=/)\*(?=s/(\w+))', r'\1', path)
|
35
|
mappings[name] = XpathParser(path).parse()
|
36
|
stream.close()
|
37
|
|
38
|
# Process dataset
|
39
|
doc = getDOMImplementation().createDocument(None, dest, None)
|
40
|
stream = sys.stdin
|
41
|
reader = csv.reader(stream, delimiter=',', quotechar='"')
|
42
|
fieldnames = reader.next()
|
43
|
row_idx = 0
|
44
|
for row in reader:
|
45
|
row_id = src+'_'+str(row_idx)
|
46
|
for idx, name in enumerate(fieldnames):
|
47
|
value = row[idx]
|
48
|
if value and name in mappings:
|
49
|
path = deepcopy(mappings[name]) # don't modify main value!
|
50
|
path[1].attrs.append([XpathElem('id', row_id, is_attr=True)])
|
51
|
path[-1].value = value
|
52
|
by_path(doc, path, True)
|
53
|
row_idx += 1
|
54
|
doc.writexml(sys.stdout, addindent=' ', newl='\n')
|
55
|
|
56
|
main()
|