summaryrefslogtreecommitdiff
path: root/server/util.c
diff options
context:
space:
mode:
Diffstat (limited to 'server/util.c')
-rw-r--r--server/util.c340
1 files changed, 316 insertions, 24 deletions
diff --git a/server/util.c b/server/util.c
index 2b603000..06da7897 100644
--- a/server/util.c
+++ b/server/util.c
@@ -96,7 +96,6 @@
#undef APLOG_MODULE_INDEX
#define APLOG_MODULE_INDEX AP_CORE_MODULE_INDEX
-
/*
* Examine a field value (such as a media-/content-type) string and return
* it sans any parameters; e.g., strip off any ';charset=foo' and the like.
@@ -252,7 +251,7 @@ AP_DECLARE(int) ap_os_is_path_absolute(apr_pool_t *p, const char *dir)
AP_DECLARE(int) ap_is_matchexp(const char *str)
{
- register int x;
+ int x;
for (x = 0; str[x]; x++)
if ((str[x] == '*') || (str[x] == '?'))
@@ -528,7 +527,7 @@ AP_DECLARE(void) ap_getparents(char *name)
while (name[l] != '\0') {
if (name[l] == '.' && name[l + 1] == '.' && IS_SLASH(name[l + 2])
&& (l == 0 || IS_SLASH(name[l - 1]))) {
- register int m = l + 3, n;
+ int m = l + 3, n;
l = l - 2;
if (l >= 0) {
@@ -654,7 +653,7 @@ AP_DECLARE(char *) ap_make_dirstr_parent(apr_pool_t *p, const char *s)
AP_DECLARE(int) ap_count_dirs(const char *path)
{
- register int x, n;
+ int x, n;
for (x = 0, n = 0; path[x]; x++)
if (path[x] == '/')
@@ -821,6 +820,60 @@ AP_DECLARE(char *) ap_getword_conf(apr_pool_t *p, const char **line)
return res;
}
+AP_DECLARE(char *) ap_getword_conf2_nc(apr_pool_t *p, char **line)
+{
+ return ap_getword_conf2(p, (const char **) line);
+}
+
+AP_DECLARE(char *) ap_getword_conf2(apr_pool_t *p, const char **line)
+{
+ const char *str = *line, *strend;
+ char *res;
+ char quote;
+ int count = 1;
+
+ while (apr_isspace(*str))
+ ++str;
+
+ if (!*str) {
+ *line = str;
+ return "";
+ }
+
+ if ((quote = *str) == '"' || quote == '\'')
+ return ap_getword_conf(p, line);
+
+ if (quote == '{') {
+ strend = str + 1;
+ while (*strend) {
+ if (*strend == '}' && !--count)
+ break;
+ if (*strend == '{')
+ ++count;
+ if (*strend == '\\' && strend[1] && strend[1] == '\\') {
+ ++strend;
+ }
+ ++strend;
+ }
+ res = substring_conf(p, str + 1, strend - str - 1, 0);
+
+ if (*strend == '}')
+ ++strend;
+ }
+ else {
+ strend = str;
+ while (*strend && !apr_isspace(*strend))
+ ++strend;
+
+ res = substring_conf(p, str, strend - str, 0);
+ }
+
+ while (apr_isspace(*strend))
+ ++strend;
+ *line = strend;
+ return res;
+}
+
AP_DECLARE(int) ap_cfg_closefile(ap_configfile_t *cfp)
{
#ifdef DEBUG
@@ -970,20 +1023,20 @@ AP_DECLARE(const char *) ap_pcfg_strerror(apr_pool_t *p, ap_configfile_t *cfp,
/* Read one line from open ap_configfile_t, strip LF, increase line number */
/* If custom handler does not define a getstr() function, read char by char */
static apr_status_t ap_cfg_getline_core(char *buf, apr_size_t bufsize,
- ap_configfile_t *cfp)
+ apr_size_t offset, ap_configfile_t *cfp)
{
apr_status_t rc;
/* If a "get string" function is defined, use it */
if (cfp->getstr != NULL) {
char *cp;
- char *cbuf = buf;
- apr_size_t cbufsize = bufsize;
+ char *cbuf = buf + offset;
+ apr_size_t cbufsize = bufsize - offset;
while (1) {
++cfp->line_number;
rc = cfp->getstr(cbuf, cbufsize, cfp->param);
if (rc == APR_EOF) {
- if (cbuf != buf) {
+ if (cbuf != buf + offset) {
*cbuf = '\0';
break;
}
@@ -1001,11 +1054,11 @@ static apr_status_t ap_cfg_getline_core(char *buf, apr_size_t bufsize,
*/
cp = cbuf;
cp += strlen(cp);
- if (cp > cbuf && cp[-1] == LF) {
+ if (cp > buf && cp[-1] == LF) {
cp--;
- if (cp > cbuf && cp[-1] == CR)
+ if (cp > buf && cp[-1] == CR)
cp--;
- if (cp > cbuf && cp[-1] == '\\') {
+ if (cp > buf && cp[-1] == '\\') {
cp--;
/*
* line continuation requested -
@@ -1023,19 +1076,19 @@ static apr_status_t ap_cfg_getline_core(char *buf, apr_size_t bufsize,
}
} else {
/* No "get string" function defined; read character by character */
- apr_size_t i = 0;
+ apr_size_t i = offset;
if (bufsize < 2) {
/* too small, assume caller is crazy */
return APR_EINVAL;
}
- buf[0] = '\0';
+ buf[offset] = '\0';
while (1) {
char c;
rc = cfp->getch(&c, cfp->param);
if (rc == APR_EOF) {
- if (i > 0)
+ if (i > offset)
break;
else
return APR_EOF;
@@ -1053,11 +1106,11 @@ static apr_status_t ap_cfg_getline_core(char *buf, apr_size_t bufsize,
break;
}
}
- else if (i >= bufsize - 2) {
- return APR_ENOSPC;
- }
buf[i] = c;
++i;
+ if (i >= bufsize - 1) {
+ return APR_ENOSPC;
+ }
}
buf[i] = '\0';
}
@@ -1091,7 +1144,7 @@ static int cfg_trim_line(char *buf)
AP_DECLARE(apr_status_t) ap_cfg_getline(char *buf, apr_size_t bufsize,
ap_configfile_t *cfp)
{
- apr_status_t rc = ap_cfg_getline_core(buf, bufsize, cfp);
+ apr_status_t rc = ap_cfg_getline_core(buf, bufsize, 0, cfp);
if (rc == APR_SUCCESS)
cfg_trim_line(buf);
return rc;
@@ -1118,7 +1171,7 @@ AP_DECLARE(apr_status_t) ap_varbuf_cfg_getline(struct ap_varbuf *vb,
}
for (;;) {
- rc = ap_cfg_getline_core(vb->buf + vb->strlen, vb->avail - vb->strlen, cfp);
+ rc = ap_cfg_getline_core(vb->buf, vb->avail, vb->strlen, cfp);
if (rc == APR_ENOSPC || rc == APR_SUCCESS)
vb->strlen += strlen(vb->buf + vb->strlen);
if (rc != APR_ENOSPC)
@@ -1451,6 +1504,95 @@ AP_DECLARE(int) ap_find_etag_weak(apr_pool_t *p, const char *line,
return find_list_item(p, line, tok, AP_ETAG_WEAK);
}
+/* Grab a list of tokens of the format 1#token (from RFC7230) */
+AP_DECLARE(const char *) ap_parse_token_list_strict(apr_pool_t *p,
+ const char *str_in,
+ apr_array_header_t **tokens,
+ int skip_invalid)
+{
+ int in_leading_space = 1;
+ int in_trailing_space = 0;
+ int string_end = 0;
+ const char *tok_begin;
+ const char *cur;
+
+ if (!str_in) {
+ return NULL;
+ }
+
+ tok_begin = cur = str_in;
+
+ while (!string_end) {
+ const unsigned char c = (unsigned char)*cur;
+
+ if (!TEST_CHAR(c, T_HTTP_TOKEN_STOP) && c != '\0') {
+ /* Non-separator character; we are finished with leading
+ * whitespace. We must never have encountered any trailing
+ * whitespace before the delimiter (comma) */
+ in_leading_space = 0;
+ if (in_trailing_space) {
+ return "Encountered illegal whitespace in token";
+ }
+ }
+ else if (c == ' ' || c == '\t') {
+ /* "Linear whitespace" only includes ASCII CRLF, space, and tab;
+ * we can't get a CRLF since headers are split on them already,
+ * so only look for a space or a tab */
+ if (in_leading_space) {
+ /* We're still in leading whitespace */
+ ++tok_begin;
+ }
+ else {
+ /* We must be in trailing whitespace */
+ ++in_trailing_space;
+ }
+ }
+ else if (c == ',' || c == '\0') {
+ if (!in_leading_space) {
+ /* If we're out of the leading space, we know we've read some
+ * characters of a token */
+ if (*tokens == NULL) {
+ *tokens = apr_array_make(p, 4, sizeof(char *));
+ }
+ APR_ARRAY_PUSH(*tokens, char *) =
+ apr_pstrmemdup((*tokens)->pool, tok_begin,
+ (cur - tok_begin) - in_trailing_space);
+ }
+ /* We're allowed to have null elements, just don't add them to the
+ * array */
+
+ tok_begin = cur + 1;
+ in_leading_space = 1;
+ in_trailing_space = 0;
+ string_end = (c == '\0');
+ }
+ else {
+ /* Encountered illegal separator char */
+ if (skip_invalid) {
+ /* Skip to the next separator */
+ const char *temp;
+ temp = ap_strchr_c(cur, ',');
+ if(!temp) {
+ temp = ap_strchr_c(cur, '\0');
+ }
+
+ /* Act like we haven't seen a token so we reset */
+ cur = temp - 1;
+ in_leading_space = 1;
+ in_trailing_space = 0;
+ }
+ else {
+ return apr_psprintf(p, "Encountered illegal separator "
+ "'\\x%.2x'", (unsigned int)c);
+ }
+ }
+
+ ++cur;
+ }
+
+ return NULL;
+}
+
/* Retrieve a token, spacing over it and returning a pointer to
* the first non-white byte afterwards. Note that these tokens
* are delimited by semis and commas; and can also be delimited
@@ -1585,7 +1727,7 @@ AP_DECLARE(char *) ap_escape_shell_cmd(apr_pool_t *p, const char *str)
static char x2c(const char *what)
{
- register char digit;
+ char digit;
#if !APR_CHARSET_EBCDIC
digit = ((what[0] >= 'A') ? ((what[0] & 0xdf) - 'A') + 10
@@ -1617,7 +1759,7 @@ static char x2c(const char *what)
static int unescape_url(char *url, const char *forbid, const char *reserved)
{
- register int badesc, badpath;
+ int badesc, badpath;
char *x, *y;
badesc = 0;
@@ -2100,11 +2242,11 @@ AP_DECLARE(char *) ap_make_full_path(apr_pool_t *a, const char *src1,
*/
AP_DECLARE(int) ap_is_url(const char *u)
{
- register int x;
+ int x;
for (x = 0; u[x] != ':'; x++) {
if ((!u[x]) ||
- ((!apr_isalpha(u[x])) && (!apr_isdigit(u[x])) &&
+ ((!apr_isalnum(u[x])) &&
(u[x] != '+') && (u[x] != '-') && (u[x] != '.'))) {
return 0;
}
@@ -2521,7 +2663,7 @@ AP_DECLARE(int) ap_parse_form_data(request_rec *r, ap_filter_t *f,
APR_BLOCK_READ, HUGE_STRING_LEN);
if (rv != APR_SUCCESS) {
apr_brigade_destroy(bb);
- return (rv == AP_FILTER_ERROR) ? rv : HTTP_BAD_REQUEST;
+ return ap_map_http_request_error(rv, HTTP_BAD_REQUEST);
}
for (bucket = APR_BRIGADE_FIRST(bb);
@@ -3005,3 +3147,153 @@ AP_DECLARE(char *) ap_get_exec_line(apr_pool_t *p,
return apr_pstrndup(p, buf, k);
}
+
+AP_DECLARE(int) ap_array_str_index(const apr_array_header_t *array,
+ const char *s,
+ int start)
+{
+ if (start >= 0) {
+ int i;
+
+ for (i = start; i < array->nelts; i++) {
+ const char *p = APR_ARRAY_IDX(array, i, const char *);
+ if (!strcmp(p, s)) {
+ return i;
+ }
+ }
+ }
+
+ return -1;
+}
+
+AP_DECLARE(int) ap_array_str_contains(const apr_array_header_t *array,
+ const char *s)
+{
+ return (ap_array_str_index(array, s, 0) >= 0);
+}
+
+#if !APR_CHARSET_EBCDIC
+/*
+ * Our own known-fast translation table for casecmp by character.
+ * Only ASCII alpha characters 41-5A are folded to 61-7A, other
+ * octets (such as extended latin alphabetics) are never case-folded.
+ * NOTE: Other than Alpha A-Z/a-z, each code point is unique!
+ */
+static const short ucharmap[] = {
+ 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf,
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+ 0x40, 'a', 'b', 'c', 'd', 'e', 'f', 'g',
+ 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
+ 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
+ 'x', 'y', 'z', 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+ 0x60, 'a', 'b', 'c', 'd', 'e', 'f', 'g',
+ 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
+ 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
+ 'x', 'y', 'z', 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
+ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
+ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
+ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
+ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
+ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff
+};
+#else /* APR_CHARSET_EBCDIC */
+/*
+ * Derived from apr-iconv/ccs/cp037.c for EBCDIC case comparison,
+ * provides unique identity of every char value (strict ISO-646
+ * conformance, arbitrary election of an ISO-8859-1 ordering, and
+ * very arbitrary control code assignments into C1 to achieve
+ * identity and a reversible mapping of code points),
+ * then folding the equivalences of ASCII 41-5A into 61-7A,
+ * presenting comparison results in a somewhat ISO/IEC 10646
+ * (ASCII-like) order, depending on the EBCDIC code page in use.
+ *
+ * NOTE: Other than Alpha A-Z/a-z, each code point is unique!
+ */
+static const short ucharmap[] = {
+ 0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F,
+ 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ 0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87,
+ 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
+ 0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B,
+ 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
+ 0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04,
+ 0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
+ 0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5,
+ 0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
+ 0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF,
+ 0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAC,
+ 0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5,
+ 0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
+ 0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF,
+ 0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
+ 0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ 0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
+ 0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+ 0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
+ 0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+ 0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
+ 0x5E, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC,
+ 0xBD, 0xBE, 0x5B, 0x5D, 0xAF, 0xA8, 0xB4, 0xD7,
+ 0x7B, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ 0x68, 0x69, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
+ 0x7D, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+ 0x71, 0x72, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
+ 0x5C, 0xF7, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+ 0x79, 0x7A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ 0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
+};
+#endif
+
+AP_DECLARE(int) ap_cstr_casecmp(const char *s1, const char *s2)
+{
+ const unsigned char *str1 = (const unsigned char *)s1;
+ const unsigned char *str2 = (const unsigned char *)s2;
+ for (;;)
+ {
+ const int c1 = (int)(*str1);
+ const int c2 = (int)(*str2);
+ const int cmp = ucharmap[c1] - ucharmap[c2];
+ /* Not necessary to test for !c2, this is caught by cmp */
+ if (cmp || !c1)
+ return cmp;
+ str1++;
+ str2++;
+ }
+}
+
+AP_DECLARE(int) ap_cstr_casecmpn(const char *s1, const char *s2, apr_size_t n)
+{
+ const unsigned char *str1 = (const unsigned char *)s1;
+ const unsigned char *str2 = (const unsigned char *)s2;
+ while (n--)
+ {
+ const int c1 = (int)(*str1);
+ const int c2 = (int)(*str2);
+ const int cmp = ucharmap[c1] - ucharmap[c2];
+ /* Not necessary to test for !c2, this is caught by cmp */
+ if (cmp || !c1)
+ return cmp;
+ str1++;
+ str2++;
+ }
+ return 0;
+}
+