回答編集履歴
2
追加
test
CHANGED
|
@@ -87,3 +87,179 @@
|
|
|
87
87
|
$str = encode('UTF-8', $str);
|
|
88
88
|
|
|
89
89
|
```
|
|
90
|
+
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
サンプルを添付しました。UTF8の場合
|
|
94
|
+
|
|
95
|
+
```perl
|
|
96
|
+
|
|
97
|
+
use Encode 'decode';
|
|
98
|
+
|
|
99
|
+
use Encode 'encode';
|
|
100
|
+
|
|
101
|
+
@species1 = ();
|
|
102
|
+
|
|
103
|
+
@species2 = ();
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
#ファイルから読み込み
|
|
108
|
+
|
|
109
|
+
while ($line = <>) {
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
chomp $line;
|
|
114
|
+
|
|
115
|
+
$line = decode('UTF-8', $line);
|
|
116
|
+
|
|
117
|
+
($sp1, $sp2) = split (/\s+/, $line);
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
print encode('UTF-8',$sp1), "\n"; #ここで問題発覚
|
|
122
|
+
|
|
123
|
+
push @species1, $sp1;
|
|
124
|
+
|
|
125
|
+
push @species2, $sp2;
|
|
126
|
+
|
|
127
|
+
}
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
|
|
131
|
+
|
|
132
|
+
|
|
133
|
+
($ref_common, $ref_only_in1, $ref_only_in2) = &find_common(\@species1, \@species2);
|
|
134
|
+
|
|
135
|
+
|
|
136
|
+
|
|
137
|
+
print "common species\n";
|
|
138
|
+
|
|
139
|
+
foreach $sp (@$ref_common) {
|
|
140
|
+
|
|
141
|
+
$sp = encode('UTF-8', $sp);
|
|
142
|
+
|
|
143
|
+
print $sp, "\n";
|
|
144
|
+
|
|
145
|
+
}
|
|
146
|
+
|
|
147
|
+
print "\n";
|
|
148
|
+
|
|
149
|
+
|
|
150
|
+
|
|
151
|
+
print "only in the first group\n";
|
|
152
|
+
|
|
153
|
+
foreach $sp (@$ref_only_in1) {
|
|
154
|
+
|
|
155
|
+
$sp = encode('UTF-8', $sp);
|
|
156
|
+
|
|
157
|
+
print $sp, "\n"
|
|
158
|
+
|
|
159
|
+
}
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
|
|
163
|
+
print "\n";
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
|
|
167
|
+
print "only in the second group\n";
|
|
168
|
+
|
|
169
|
+
foreach $sp (@$ref_only_in2) {
|
|
170
|
+
|
|
171
|
+
$sp = encode('UTF-8', $sp);
|
|
172
|
+
|
|
173
|
+
print $sp, "\n";
|
|
174
|
+
|
|
175
|
+
}
|
|
176
|
+
|
|
177
|
+
|
|
178
|
+
|
|
179
|
+
sub find_common
|
|
180
|
+
|
|
181
|
+
{
|
|
182
|
+
|
|
183
|
+
my ($ref1, $ref2) = @_;
|
|
184
|
+
|
|
185
|
+
|
|
186
|
+
|
|
187
|
+
my @common = ();
|
|
188
|
+
|
|
189
|
+
my @only_in1 = ();
|
|
190
|
+
|
|
191
|
+
my @only_in2 = ();
|
|
192
|
+
|
|
193
|
+
|
|
194
|
+
|
|
195
|
+
my $found;
|
|
196
|
+
|
|
197
|
+
|
|
198
|
+
|
|
199
|
+
foreach my $sp1 (@$ref1) {
|
|
200
|
+
|
|
201
|
+
foreach my $sp2 (@$ref2) {
|
|
202
|
+
|
|
203
|
+
$found = 0;
|
|
204
|
+
|
|
205
|
+
if ($sp1 eq $sp2) {
|
|
206
|
+
|
|
207
|
+
$found = 1;
|
|
208
|
+
|
|
209
|
+
last;
|
|
210
|
+
|
|
211
|
+
}
|
|
212
|
+
|
|
213
|
+
}
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
|
|
217
|
+
if ($found == 1) {
|
|
218
|
+
|
|
219
|
+
push @common, $sp1;
|
|
220
|
+
|
|
221
|
+
}
|
|
222
|
+
|
|
223
|
+
else {
|
|
224
|
+
|
|
225
|
+
push @only_in1, $sp1;
|
|
226
|
+
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
}
|
|
230
|
+
|
|
231
|
+
|
|
232
|
+
|
|
233
|
+
foreach my $sp2 (@$ref2) {
|
|
234
|
+
|
|
235
|
+
foreach my $sp_common (@common) {
|
|
236
|
+
|
|
237
|
+
$found = 0;
|
|
238
|
+
|
|
239
|
+
if ($sp2 eq $sp_common) {
|
|
240
|
+
|
|
241
|
+
$found = 1;
|
|
242
|
+
|
|
243
|
+
last;
|
|
244
|
+
|
|
245
|
+
}
|
|
246
|
+
|
|
247
|
+
}
|
|
248
|
+
|
|
249
|
+
if ($found == 0) {
|
|
250
|
+
|
|
251
|
+
push @only_in2, $sp2;
|
|
252
|
+
|
|
253
|
+
}
|
|
254
|
+
|
|
255
|
+
}
|
|
256
|
+
|
|
257
|
+
|
|
258
|
+
|
|
259
|
+
return (\@common, \@only_in1, \@only_in2);
|
|
260
|
+
|
|
261
|
+
}
|
|
262
|
+
|
|
263
|
+
```
|
|
264
|
+
|
|
265
|
+
|
1
追加
test
CHANGED
|
@@ -57,3 +57,33 @@
|
|
|
57
57
|
グンテ
|
|
58
58
|
|
|
59
59
|
```
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
perlには内部コードなるものが有りますので全角の文字列の場合変換されると良いです
|
|
64
|
+
|
|
65
|
+
「UTF-8バイト文字列」を「内部文字列」に変換する
|
|
66
|
+
|
|
67
|
+
```perl
|
|
68
|
+
|
|
69
|
+
use Encode 'decode';
|
|
70
|
+
|
|
71
|
+
# バイト文字列(外部からの入力)を内部文字列に変換($strがUTF-8の場合)
|
|
72
|
+
|
|
73
|
+
$str = decode('UTF-8', $str);
|
|
74
|
+
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
面倒ですが出力する場合は逆にします。
|
|
80
|
+
|
|
81
|
+
```perl
|
|
82
|
+
|
|
83
|
+
use Encode 'encode';
|
|
84
|
+
|
|
85
|
+
# 内部文字列をUTF-8バイト文字列に変換する場合
|
|
86
|
+
|
|
87
|
+
$str = encode('UTF-8', $str);
|
|
88
|
+
|
|
89
|
+
```
|