1 /* Measure strcoll execution time in different locales.
2 Copyright (C) 2015 Free Software Foundation, Inc.
3 This file is part of the GNU C Library.
5 The GNU C Library is free software; you can redistribute it and/or
6 modify it under the terms of the GNU Lesser General Public
7 License as published by the Free Software Foundation; either
8 version 2.1 of the License, or (at your option) any later version.
10 The GNU C Library is distributed in the hope that it will be useful,
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 Lesser General Public License for more details.
15 You should have received a copy of the GNU Lesser General Public
16 License along with the GNU C Library; if not, see
17 <http://www.gnu.org/licenses/>. */
26 #include "bench-timing.h"
28 /* Many thanks to http://generator.lorem-ipsum.info/ */
29 #define INPUT_PREFIX "strcoll-inputs/"
31 static const char *const input_files
[] = {
33 "filelist#en_US.UTF-8",
34 "lorem_ipsum#vi_VN.UTF-8",
35 "lorem_ipsum#ar_SA.UTF-8",
36 "lorem_ipsum#en_US.UTF-8",
37 "lorem_ipsum#zh_CN.UTF-8",
38 "lorem_ipsum#cs_CZ.UTF-8",
39 "lorem_ipsum#en_GB.UTF-8",
40 "lorem_ipsum#da_DK.UTF-8",
41 "lorem_ipsum#pl_PL.UTF-8",
42 "lorem_ipsum#fr_FR.UTF-8",
43 "lorem_ipsum#pt_PT.UTF-8",
44 "lorem_ipsum#el_GR.UTF-8",
45 "lorem_ipsum#ru_RU.UTF-8",
46 "lorem_ipsum#iw_IL.UTF-8",
47 "lorem_ipsum#es_ES.UTF-8",
48 "lorem_ipsum#hi_IN.UTF-8",
49 "lorem_ipsum#sv_SE.UTF-8",
50 "lorem_ipsum#hu_HU.UTF-8",
51 "lorem_ipsum#tr_TR.UTF-8",
52 "lorem_ipsum#is_IS.UTF-8",
53 "lorem_ipsum#it_IT.UTF-8",
54 "lorem_ipsum#sr_RS.UTF-8",
55 "lorem_ipsum#ja_JP.UTF-8"
58 #define TEXTFILE_DELIMITER " \n\r\t.,?!"
61 read_file (const char *filename
)
65 int fd
= open (filename
, O_CLOEXEC
);
69 if (fstat (fd
, &stats
) == 0)
71 buffer
= malloc (stats
.st_size
+ 1);
74 if (read (fd
, buffer
, stats
.st_size
) == stats
.st_size
)
75 buffer
[stats
.st_size
] = '\0';
90 count_words (const char *text
, const char *delim
)
93 char *tmp
= strdup (text
);
95 char *token
= strtok (tmp
, delim
);
100 token
= strtok (NULL
, delim
);
114 new_word_list (size_t size
)
116 word_list
*list
= malloc (sizeof (word_list
));
117 assert (list
!= NULL
);
119 list
->words
= malloc (size
* sizeof (char *));
120 assert (list
->words
!= NULL
);
125 str_word_list (const char *str
, const char *delim
)
128 word_list
*list
= new_word_list (count_words (str
, delim
));
130 char *toks
= strdup (str
);
131 char *word
= strtok (toks
, delim
);
132 while (word
!= NULL
&& n
< list
->size
)
135 list
->words
[n
++] = strdup (word
);
136 word
= strtok (NULL
, delim
);
144 copy_word_list (const word_list
*list
)
147 word_list
*copy
= new_word_list (list
->size
);
149 for (i
= 0; i
< list
->size
; i
++)
150 copy
->words
[i
] = strdup (list
->words
[i
]);
156 free_word_list (word_list
*list
)
159 for (i
= 0; i
< list
->size
; i
++)
160 free (list
->words
[i
]);
167 compare_words (const void *a
, const void *b
)
169 const char *s1
= *(char **) a
;
170 const char *s2
= *(char **) b
;
171 return strcoll (s1
, s2
);
174 #undef INNER_LOOP_ITERS
175 #define INNER_LOOP_ITERS 16
178 bench_list (json_ctx_t
*json_ctx
, word_list
*list
)
181 timing_t start
, stop
, cur
;
183 word_list
**tests
= malloc (INNER_LOOP_ITERS
* sizeof (word_list
*));
184 assert (tests
!= NULL
);
185 for (i
= 0; i
< INNER_LOOP_ITERS
; i
++)
186 tests
[i
] = copy_word_list (list
);
189 for (i
= 0; i
< INNER_LOOP_ITERS
; i
++)
190 qsort (tests
[i
]->words
, tests
[i
]->size
, sizeof (char *), compare_words
);
193 TIMING_DIFF (cur
, start
, stop
);
194 setlocale (LC_ALL
, "en_US.UTF-8");
195 json_attr_double (json_ctx
, "duration", cur
);
196 json_attr_double (json_ctx
, "iterations", i
);
197 json_attr_double (json_ctx
, "mean", (double) cur
/ i
);
199 for (i
= 0; i
< INNER_LOOP_ITERS
; i
++)
200 free_word_list (tests
[i
]);
213 bench_file (json_ctx_t
*json_ctx
, const char *testname
, const char *filename
,
216 if (setlocale (LC_ALL
, locale
) == NULL
)
219 char *text
= read_file (filename
);
223 word_list
*list
= str_word_list (text
, TEXTFILE_DELIMITER
);
225 json_attr_object_begin (json_ctx
, testname
);
226 bench_list (json_ctx
, list
);
227 json_attr_object_end (json_ctx
);
229 free_word_list (list
);
240 json_ctx_t
*json_ctx
= malloc (sizeof (json_ctx_t
));
241 assert (json_ctx
!= NULL
);
242 json_init (json_ctx
, 2, stdout
);
243 json_attr_object_begin (json_ctx
, "strcoll");
246 result_t result
= OK
;
247 for (i
= 0; i
< (sizeof (input_files
) / sizeof (input_files
[0])); i
++)
249 char *locale
= strchr (input_files
[i
], '#');
252 printf ("Failed to get locale from filename %s, aborting!\n",
254 return ERROR_FILENAME
;
258 asprintf (&filename
, INPUT_PREFIX
"%s", input_files
[i
]);
259 result
= bench_file (json_ctx
, input_files
[i
], filename
, locale
+ 1);
263 if (result
== ERROR_LOCALE
)
264 printf ("Failed to set locale %s, aborting!\n", locale
);
265 else if (result
== ERROR_IO
)
266 printf ("Failed to read file %s, aborting!\n", filename
);
274 json_attr_object_end (json_ctx
);