質問編集履歴
2
タグ修正
test
CHANGED
File without changes
|
test
CHANGED
File without changes
|
1
実行結果とソースを追記
test
CHANGED
File without changes
|
test
CHANGED
@@ -76,3 +76,124 @@
|
|
76
76
|
|
77
77
|
出力結果は何も表示されてないようです.急ぎです.お願いします.
|
78
78
|
|
79
|
+
|
80
|
+
|
81
|
+
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
|
86
|
+
|
87
|
+
|
88
|
+
|
89
|
+
|
90
|
+
### 追記:6/2618:00
|
91
|
+
修正依頼にあったように処理の前にprintfを追加してみたバージョンのソースと実行結果を載せておきます.
|
92
|
+
|
93
|
+
おそらく/titleの処理を忘れているのではないかなと思います.
|
94
|
+
|
95
|
+
```ここに言語を入力
|
96
|
+
#include <stdio.h>
|
97
|
+
#include <stdlib.h>
|
98
|
+
#include <string.h>
|
99
|
+
#define SIZE 256 * 1024 * 1024
|
100
|
+
|
101
|
+
int main()
|
102
|
+
{
|
103
|
+
|
104
|
+
int p, pb[6];
|
105
|
+
char *line = malloc(SIZE);
|
106
|
+
char *title;
|
107
|
+
char *id;
|
108
|
+
FILE *fp = fopen("jawiki-20211220-pages-articles-multistream2.xml", "r");
|
109
|
+
FILE *fw = fopen("getX.txt", "w"); //記入先
|
110
|
+
if ((NULL == fp) || (NULL == fw))
|
111
|
+
abort();
|
112
|
+
while (p = ftell(fp), fgets(line, SIZE, fp))
|
113
|
+
{
|
114
|
+
|
115
|
+
/*
|
116
|
+
// textやpageなどの複数行にわたるとき
|
117
|
+
if (strstr(line, "<text"))
|
118
|
+
{//属性があるため<text
|
119
|
+
pb[0] = p;
|
120
|
+
}
|
121
|
+
|
122
|
+
if (strstr(line, "</text>"))
|
123
|
+
{
|
124
|
+
pb[1] = p - pb[0];
|
125
|
+
|
126
|
+
printf("%d\t%d\n", pb[0], pb[1]);
|
127
|
+
fprintf(fw, "%d\t%d\n", pb[0], pb[1]);
|
128
|
+
}
|
129
|
+
*/
|
130
|
+
|
131
|
+
if (strstr(line, "<title>"))
|
132
|
+
{
|
133
|
+
printf("title in\t 1\n");
|
134
|
+
pb[0] = p;
|
135
|
+
if ((strstr(line, "</title>")))
|
136
|
+
{
|
137
|
+
printf("/title in\t1\n");
|
138
|
+
pb[1] = p - pb[0];
|
139
|
+
pb[0] += strlen("<title>");
|
140
|
+
fseek(fp, pb[0], SEEK_SET);
|
141
|
+
fgets(title, pb[1], fp);
|
142
|
+
printf("%s\n", title);
|
143
|
+
if (strstr(line, "<title>"))
|
144
|
+
{
|
145
|
+
printf("title\tin\t22222222222\n");
|
146
|
+
pb[2] = p;
|
147
|
+
if (strstr(line, "<id>"))
|
148
|
+
{
|
149
|
+
printf("id in\t\n");
|
150
|
+
pb[2] = p;
|
151
|
+
if (strstr(line, "</id>"))
|
152
|
+
{
|
153
|
+
printf("/id in \n");
|
154
|
+
pb[3] = p - pb[2];
|
155
|
+
pb[2] += strlen("<id>");
|
156
|
+
fseek(fp, pb[2], SEEK_SET);
|
157
|
+
fgets(id, pb[3], fp);
|
158
|
+
printf("title=\t%s\nid=\t%s\n", title, id);
|
159
|
+
if (strstr(line, "<text"))
|
160
|
+
{
|
161
|
+
printf("text in ");
|
162
|
+
pb[4] = p;
|
163
|
+
if (strstr(line, "</text>"))
|
164
|
+
{
|
165
|
+
|
166
|
+
printf("/text in ");
|
167
|
+
pb[5] = p - pb[4];
|
168
|
+
printf("%s\t%s\t%d\t%d\n", title, id, pb[4], pb[5]);
|
169
|
+
}
|
170
|
+
}
|
171
|
+
}
|
172
|
+
}
|
173
|
+
}
|
174
|
+
}
|
175
|
+
}
|
176
|
+
}
|
177
|
+
|
178
|
+
printf("process ok");
|
179
|
+
free(line);
|
180
|
+
fclose(fw);
|
181
|
+
fclose(fp);
|
182
|
+
}
|
183
|
+
```
|
184
|
+
以下実行結果の一部です.
|
185
|
+
```ここに言語を入力
|
186
|
+
title in 22222222222
|
187
|
+
title in 1/title in 2(null)
|
188
|
+
title in 22222222222
|
189
|
+
title in 1/title in 2(null)
|
190
|
+
title in 22222222222
|
191
|
+
title in 1/title in 2(null)
|
192
|
+
title in 22222222222
|
193
|
+
title in 1/title in 2(null)
|
194
|
+
title in 22222222222
|
195
|
+
title in 1/title in 2(null)
|
196
|
+
title in 22222222222
|
197
|
+
process ok
|
198
|
+
```
|
199
|
+
処理のバランスおかしいですね.
|