1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # cnseg.pm --
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program is free software; you can redistribute it and/or modify
|
---|
11 | # it under the terms of the GNU General Public License as published by
|
---|
12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
13 | # (at your option) any later version.
|
---|
14 | #
|
---|
15 | # This program is distributed in the hope that it will be useful,
|
---|
16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | # GNU General Public License for more details.
|
---|
19 | #
|
---|
20 | # You should have received a copy of the GNU General Public License
|
---|
21 | # along with this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 |
|
---|
27 | # this package segments a chinese UTF-8 encoded Unicode
|
---|
28 | # string into words.
|
---|
29 |
|
---|
30 | package cnseg;
|
---|
31 |
|
---|
32 | use strict;
|
---|
33 | use unicode;
|
---|
34 |
|
---|
35 |
|
---|
36 | # 'segment' takes a UTF-8 encoded Unicode Chinese-language
|
---|
37 | # string and places U-200B between words -- the ZERO
|
---|
38 | # WIDTH SPACE. Each line is treated as a separate
|
---|
39 | # paragraph, so lines in one paragraph should
|
---|
40 | # be joined before using this method (normally a single
|
---|
41 | # word might span more than one line within a paragraph).
|
---|
42 | #
|
---|
43 | # 'segment' is currently written in Perl, however, I (Rodger)
|
---|
44 | # plan to use C++ (via pipes) once a more complex (and useful!)
|
---|
45 | # algorithm is being used. Currently, each Chinese character
|
---|
46 | # is treated as a seperate word.
|
---|
47 |
|
---|
48 | sub segment {
|
---|
49 | my ($in) = @_;
|
---|
50 | my ($c);
|
---|
51 |
|
---|
52 | my $uniin = &unicode::utf82unicode($in);
|
---|
53 | my $out = [];
|
---|
54 |
|
---|
55 | my $space = 1; # start doesn't need a space
|
---|
56 | foreach $c (@$uniin) {
|
---|
57 | if (($c >= 0x2e80 && $c <= 0xd7a3) ||
|
---|
58 | ( $c >= 0xf900 && $c <= 0xfa6a)) { # main east asian codes
|
---|
59 | # currently c++ receptionist code can't handle these large numbers
|
---|
60 | # search terms need to be segmented the same way. Add these back
|
---|
61 | # in when fix up c++
|
---|
62 | # ($c >= 0x20000 && $c <= 0x2a6d6) || # cjk unified ideographs ext B
|
---|
63 | # ($c >= 0x2f800 && $c <= 0x2fa1d)) { #cjk compatibility ideographs supplement
|
---|
64 | # CJK character
|
---|
65 | push (@$out, 0x200b) unless $space;
|
---|
66 | push (@$out, $c);
|
---|
67 | push (@$out, 0x200b);
|
---|
68 | $space = 1;
|
---|
69 |
|
---|
70 | } else {
|
---|
71 | # non-Chinese character
|
---|
72 | push (@$out, $c);
|
---|
73 | $space = 0;
|
---|
74 | }
|
---|
75 | }
|
---|
76 |
|
---|
77 | return &unicode::unicode2utf8($out);
|
---|
78 | }
|
---|
79 |
|
---|
80 | 1;
|
---|