summaryrefslogtreecommitdiff
path: root/strings/apr_cpystrn.c
blob: eb057111ef95ea0ec1e5ea34285ab30dc4ce36cf (plain)
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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2000-2002 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact apache@apache.org.
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

#include "apr.h"
#include "apr_strings.h"
#include "apr_private.h"
#include "apr_lib.h"

#if APR_HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif
#if APR_HAVE_STRING_H
#include <string.h>
#endif
#if APR_HAVE_CTYPE_H
#include <ctype.h>
#endif

/*
 * Apache's "replacement" for the strncpy() function. We roll our
 * own to implement these specific changes:
 *   (1) strncpy() doesn't always null terminate and we want it to.
 *   (2) strncpy() null fills, which is bogus, esp. when copy 8byte
 *       strings into 8k blocks.
 *   (3) Instead of returning the pointer to the beginning of
 *       the destination string, we return a pointer to the
 *       terminating '\0' to allow us to "check" for truncation
 *
 * apr_cpystrn() follows the same call structure as strncpy().
 */

APR_DECLARE(char *) apr_cpystrn(char *dst, const char *src, apr_size_t dst_size)
{

    char *d, *end;

    if (dst_size == 0) {
        return (dst);
    }

    d = dst;
    end = dst + dst_size - 1;

    for (; d < end; ++d, ++src) {
	if (!(*d = *src)) {
	    return (d);
	}
    }

    *d = '\0';	/* always null terminate */

    return (d);
}


/*
 * This function provides a way to parse a generic argument string
 * into a standard argv[] form of argument list. It respects the 
 * usual "whitespace" and quoteing rules. In the future this could
 * be expanded to include support for the apr_call_exec command line
 * string processing (including converting '+' to ' ' and doing the 
 * url processing. It does not currently support this function.
 *
 *    token_context: Context from which pool allocations will occur.
 *    arg_str:       Input argument string for conversion to argv[].
 *    argv_out:      Output location. This is a pointer to an array
 *                   of pointers to strings (ie. &(char *argv[]).
 *                   This value will be allocated from the contexts
 *                   pool and filled in with copies of the tokens
 *                   found during parsing of the arg_str. 
 */
APR_DECLARE(apr_status_t) apr_tokenize_to_argv(const char *arg_str, 
                                            char ***argv_out,
                                            apr_pool_t *token_context)
{
    const char *cp;
    const char *ct;
    int isquoted, numargs = 0;

#define SKIP_WHITESPACE(cp) \
    for ( ; *cp == ' ' || *cp == '\t'; ) { \
        cp++; \
    };

#define CHECK_QUOTATION(cp,isquoted) \
    isquoted = 0; \
    if (*cp == '"') { \
        isquoted = 1; \
        cp++; \
    }

/* DETERMINE_NEXTSTRING:
 * At exit, cp will point to one of the following:  NULL, SPACE, TAB or QUOTE.
 * NULL implies the argument string has been fully traversed.
 */
#define DETERMINE_NEXTSTRING(cp,isquoted) \
    for ( ; *cp != '\0'; cp++) { \
        if (   (isquoted    && (*cp     == ' ' || *cp     == '\t')) \
            || (*cp == '\\' && (*(cp+1) == ' ' || *(cp+1) == '\t'))) { \
            cp++; \
            continue; \
        } \
        if (   (!isquoted && (*cp == ' ' || *cp == '\t')) \
            || (isquoted  && *cp == '"')                  ) { \
            break; \
        } \
    }

    cp = arg_str;
    SKIP_WHITESPACE(cp);
    ct = cp;

    /* This is ugly and expensive, but if anyone wants to figure a
     * way to support any number of args without counting and 
     * allocating, please go ahead and change the code.
     *
     * Must account for the trailing NULL arg.
     */
    numargs = 1;
    while (*ct != '\0') {
        CHECK_QUOTATION(ct, isquoted);
        DETERMINE_NEXTSTRING(ct, isquoted);
        ct++;
        numargs++;
        SKIP_WHITESPACE(ct);
    }
    *argv_out = apr_palloc(token_context, numargs * sizeof(char*));

    /*  determine first argument */
    numargs = 0;
    while (*cp != '\0') {
        CHECK_QUOTATION(cp, isquoted);
        ct = cp;
        DETERMINE_NEXTSTRING(cp, isquoted);
        cp++;
        (*argv_out)[numargs] = apr_palloc(token_context, cp - ct);
        apr_cpystrn((*argv_out)[numargs], ct, cp - ct);
        numargs++;
        SKIP_WHITESPACE(cp);
    }
    (*argv_out)[numargs] = NULL;

    return APR_SUCCESS;
}

/* Filename_of_pathname returns the final element of the pathname.
 * Using the current platform's filename syntax.
 *   "/foo/bar/gum" -> "gum"
 *   "/foo/bar/gum/" -> ""
 *   "gum" -> "gum"
 *   "wi\\n32\\stuff" -> "stuff
 *
 * Corrected Win32 to accept "a/b\\stuff", "a:stuff"
 */

APR_DECLARE(const char *) apr_filename_of_pathname(const char *pathname)
{
    const char path_separator = '/';
    const char *s = strrchr(pathname, path_separator);

#ifdef WIN32
    const char path_separator_win = '\\';
    const char drive_separator_win = ':';
    const char *s2 = strrchr(pathname, path_separator_win);

    if (s2 > s) s = s2;

    if (!s) s = strrchr(pathname, drive_separator_win);
#endif

    return s ? ++s : pathname;
}

/* length of dest assumed >= length of src
 * collapse in place (src == dest) is legal.
 * returns terminating null ptr to dest string.
 */
APR_DECLARE(char *) apr_collapse_spaces(char *dest, const char *src)
{
    while (*src) {
        if (!apr_isspace(*src)) 
            *dest++ = *src;
        ++src;
    }
    *dest = 0;
    return (dest);
}

#if !APR_HAVE_STRDUP
char *strdup(const char *str)
{
    char *sdup;
    size_t len = strlen(str) + 1;

    if (!(sdup = (char *) malloc(len))) {
        /* ### whoops! we can't call Apache logging routines here... */
#if 0
        apr_log_error(APLOG_MARK, APLOG_STARTUP | APLOG_NOERRNO, 0, NULL,
                      "Ouch! Out of memory in our strdup()!");
#endif
        return NULL;
    }
    memcpy(sdup, str, len);

    return sdup;
}
#endif

/* The following two routines were donated for SVR4 by Andreas Vogel */
#if (!APR_HAVE_STRCASECMP && !APR_HAVE_STRICMP)
int strcasecmp(const char *a, const char *b)
{
    const char *p = a;
    const char *q = b;
    for (p = a, q = b; *p && *q; p++, q++) {
        int diff = apr_tolower(*p) - apr_tolower(*q);
        if (diff)
            return diff;
    }
    if (*p)
        return 1;               /* p was longer than q */
    if (*q)
        return -1;              /* p was shorter than q */
    return 0;                   /* Exact match */
}

#endif

#if (!APR_HAVE_STRNCASECMP && !APR_HAVE_STRNICMP)
int strncasecmp(const char *a, const char *b, size_t n)
{
    const char *p = a;
    const char *q = b;

    for (p = a, q = b; /*NOTHING */ ; p++, q++) {
        int diff;
        if (p == a + n)
            return 0;           /*   Match up to n characters */
        if (!(*p && *q))
            return *p - *q;
        diff = apr_tolower(*p) - apr_tolower(*q);
        if (diff)
            return diff;
    }
    /*NOTREACHED */
}
#endif

/* The following routine was donated for UTS21 by dwd@bell-labs.com */
#if (!APR_HAVE_STRSTR)
char *strstr(char *s1, char *s2)
{
    char *p1, *p2;
    if (*s2 == '\0') {
        /* an empty s2 */
        return(s1);
    }
    while((s1 = strchr(s1, *s2)) != NULL) {
        /* found first character of s2, see if the rest matches */
        p1 = s1;
        p2 = s2;
        while (*++p1 == *++p2) {
            if (*p1 == '\0') {
                /* both strings ended together */
                return(s1);
            }
        }
        if (*p2 == '\0') {
            /* second string ended, a match */
            break;
        }
        /* didn't find a match here, try starting at next character in s1 */
        s1++;
    }
    return(s1);
}
#endif