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
|
# ====================================================================
# Copyright (c) 2004-2010 Open Source Applications Foundation.
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
# ====================================================================
#
from icu import UnicodeString, BreakIterator, Locale
def printTextRange(iterator, start, end):
s = iterator.getText().getText()
print("%2d %2d %s|%s|%s" %(start, end, s[:start], s[start:end], s[end:]))
#def printTextRange(iterator, start, end):
#
# u = iterator.getText().getText(UnicodeString())
# print "%2d %2d %s|%s|%s" %(start, end,
# UnicodeString(u, 0, start),
# UnicodeString(u, start, end-start),
# UnicodeString(u, end))
def printEachForward(boundary):
start = boundary.first()
for end in boundary:
printTextRange(boundary, start, end)
start = end
# Print each element in reverse order:
def printEachBackward(boundary):
end = boundary.last()
while True:
start = boundary.previous()
if start == BreakIterator.DONE:
break
printTextRange(boundary, start, end)
end = start
# Print the first element
def printFirst(boundary):
start = boundary.first()
end = boundary.next()
printTextRange(boundary, start, end)
# Print the last element
def printLast(boundary):
end = boundary.last()
start = boundary.previous()
if start != BreakIterator.DONE:
printTextRange(boundary, start, end)
# Print the element at a specified position
def printAt(boundary, pos):
end = boundary.following(pos)
start = boundary.previous()
printTextRange(boundary, start, end)
def main():
print("ICU Break Iterator Sample Program")
print("C++ Break Iteration in Python")
stringToExamine = u"Aaa bbb ccc. Ddd eee fff."
print("Examining: ", stringToExamine)
# print each sentence in forward and reverse order
boundary = BreakIterator.createSentenceInstance(Locale.getUS())
boundary.setText(stringToExamine)
print()
print("Sentence Boundaries... ")
print("----- forward: -----------")
printEachForward(boundary)
print("----- backward: ----------")
printEachBackward(boundary)
# print each word in order
print()
print("Word Boundaries...")
boundary = BreakIterator.createWordInstance(Locale.getUS())
boundary.setText(stringToExamine)
print("----- forward: -----------")
printEachForward(boundary)
# print first element
print("----- first: -------------")
printFirst(boundary)
# print last element
print("----- last: --------------")
printLast(boundary)
# print word at charpos 10
print("----- at pos 10: ---------")
printAt(boundary, 10)
print()
print("End C++ Break Iteration in Python")
if __name__ == "__main__":
main()
|
