1
|
#!/usr/bin/env python
|
2
|
# Translates a spreadsheet column using a thesaurus.
|
3
|
# The column header is also translated. CSVs without a header are supported.
|
4
|
# Unrecognized names are left untouched, permitting successive runs on different
|
5
|
# thesauruses.
|
6
|
# Case- and punctuation-sensitive. (Use canon first for case-insensitivity.)
|
7
|
|
8
|
import csv
|
9
|
import sys
|
10
|
|
11
|
def main():
|
12
|
try: _prog_name, col_num, dict_path = sys.argv
|
13
|
except ValueError: raise SystemExit('Usage: '+sys.argv[0]
|
14
|
+' <in col# thesaurus [| '+sys.argv[0]+' col# thesaurus_2]... >out')
|
15
|
col_num = int(col_num)
|
16
|
|
17
|
# Get thesaurus
|
18
|
dict_ = {}
|
19
|
stream = open(dict_path, 'rb')
|
20
|
reader = csv.reader(stream)
|
21
|
for row in reader: dict_[row[0]] = row[1]
|
22
|
stream.close()
|
23
|
|
24
|
# Translate input
|
25
|
reader = csv.reader(sys.stdin)
|
26
|
writer = csv.writer(sys.stdout)
|
27
|
for row in reader:
|
28
|
term = row[col_num]
|
29
|
try: row[col_num] = dict_[term]
|
30
|
except KeyError: pass
|
31
|
writer.writerow(row)
|
32
|
|
33
|
main()
|