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
|
#!/usr/bin/python
# coding=utf-8
# -*- encoding: utf-8 -*-
import sys
def processWord(c):
lemma = ''
tags = ''
c = sys.stdin.read(1)
while c != '<':
if c == '*':
while c and c != '$':
lemma += c
c = sys.stdin.read(1)
sys.stdout.write(lemma.replace(' ', '~') + ' ')
return
lemma += c
c = sys.stdin.read(1)
while c != '$':
tags += c
c = sys.stdin.read(1)
sys.stdout.write(lemma.replace(' ', '~') + tags.replace(' ', '~') + ' ')
c = sys.stdin.read(1)
while c:
# Beginning of a lexical unit
if c == '^':
processWord(c)
if c == '[':
while c and c != ']':
if c == '\n':
sys.stdout.write('\n')
c = sys.stdin.read(1)
# Newline is newline
if c == '\n':
sys.stdout.write('\n')
c = sys.stdin.read(1)
|
