* char in here and get it to work, because if char is signed then it
* will first be sign extended.
*/
-#define TEST_CHAR(c, f) (test_char_table[(unsigned)(c)] & (f))
+#define TEST_CHAR(c, f) (test_char_table[(unsigned char)(c)] & (f))
/* Win32/NetWare/OS2 need to check for both forward and back slashes
* in ap_getparents() and ap_escape_url.
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
if (finfo.filetype != APR_REG &&
#if defined(WIN32) || defined(OS2) || defined(NETWARE)
- ap_casecmpstr(apr_filepath_name_get(name), "nul") != 0) {
+ ap_cstr_casecmp(apr_filepath_name_get(name), "nul") != 0) {
#else
strcmp(name, "/dev/null") != 0) {
#endif /* WIN32 || OS2 */
while (!string_end) {
const unsigned char c = (unsigned char)*cur;
- if (!TEST_CHAR(c, T_HTTP_TOKEN_STOP) && c != '\0') {
+ if (!TEST_CHAR(c, T_HTTP_TOKEN_STOP)) {
/* Non-separator character; we are finished with leading
* whitespace. We must never have encountered any trailing
* whitespace before the delimiter (comma) */
return NULL;
}
+/* Scan a string for HTTP VCHAR/obs-text characters including HT and SP
+ * (as used in header values, for example, in RFC 7230 section 3.2)
+ * returning the pointer to the first non-HT ASCII ctrl character.
+ */
+AP_DECLARE(const char *) ap_scan_http_field_content(const char *ptr)
+{
+ for ( ; !TEST_CHAR(*ptr, T_HTTP_CTRLS); ++ptr) ;
+
+ return ptr;
+}
+
+/* Scan a string for HTTP token characters, returning the pointer to
+ * the first non-token character.
+ */
+AP_DECLARE(const char *) ap_scan_http_token(const char *ptr)
+{
+ for ( ; !TEST_CHAR(*ptr, T_HTTP_TOKEN_STOP); ++ptr) ;
+
+ return ptr;
+}
+
+/* Scan a string for visible ASCII (0x21-0x7E) or obstext (0x80+)
+ * and return a pointer to the first ctrl/space character encountered.
+ */
+AP_DECLARE(const char *) ap_scan_vchar_obstext(const char *ptr)
+{
+ for ( ; TEST_CHAR(*ptr, T_VCHAR_OBSTEXT); ++ptr) ;
+
+ return ptr;
+}
+
/* 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
while (*s && !TEST_CHAR(*s, T_HTTP_TOKEN_STOP)) {
++s;
}
- if (!ap_casecmpstrn((const char *)start_token, (const char *)tok,
+ if (!ap_cstr_casecmpn((const char *)start_token, (const char *)tok,
s - start_token)) {
return 1;
}
(lidx > 0 && !(apr_isspace(line[lidx - 1]) || line[lidx - 1] == ',')))
return 0;
- return (ap_casecmpstrn(&line[lidx], tok, tlen) == 0);
+ return (ap_cstr_casecmpn(&line[lidx], tok, tlen) == 0);
}
AP_DECLARE(char *) ap_escape_shell_cmd(apr_pool_t *p, const char *str)
*dest = '\0';
}
-AP_DECLARE(int) ap_has_cntrl(const char *str)
-{
- while (*str) {
- if (apr_iscntrl(*str))
- return 1;
- str++;
- }
- return 0;
-}
-
AP_DECLARE(int) ap_is_directory(apr_pool_t *p, const char *path)
{
apr_finfo_t finfo;
return has_body;
}
+/**
+ * Check whether a request is tainted by exposure to something
+ * potentially untrusted.
+ *
+ */
+AP_DECLARE(int) ap_request_tainted(request_rec *r, int flags)
+{
+ /** Potential future: a hook or callback here could serve modules
+ * like mod_security and ironbee with more complex needs.
+ */
+ return r && ((r->taint&flags)
+ || ap_request_tainted(r->main, flags)
+ || ap_request_tainted(r->prev, flags));
+}
+
AP_DECLARE_NONSTD(apr_status_t) ap_pool_cleanup_set_null(void *data_)
{
void **ptr = (void **)data_;
/* sanity check - we only support forms for now */
ct = apr_table_get(r->headers_in, "Content-Type");
- if (!ct || ap_casecmpstrn("application/x-www-form-urlencoded", ct, 33)) {
+ if (!ct || ap_cstr_casecmpn("application/x-www-form-urlencoded", ct, 33)) {
return ap_discard_request_body(r);
}
#if !APR_CHARSET_EBCDIC
/*
- * Provide our own known-fast implementation of str[n]casecmp()
- * NOTE: Only ASCII alpha characters 41-5A are folded to 61-7A,
- * other 8-bit latin alphabetics are never case-folded!
+ * 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 unsigned char ucharmap[] = {
+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,
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.
+/*
+ * 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 unsigned char 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
+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_casecmpstr(const char *s1, const char *s2)
+AP_DECLARE(int) ap_cstr_casecmp(const char *s1, const char *s2)
{
- const unsigned char *ps1 = (const unsigned char *) s1;
- const unsigned char *ps2 = (const unsigned char *) s2;
-
- while (ucharmap[*ps1] == ucharmap[*ps2]) {
- if (*ps1++ == '\0') {
- return (0);
- }
- ps2++;
+ 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++;
}
- return (ucharmap[*ps1] - ucharmap[*ps2]);
}
-AP_DECLARE(int) ap_casecmpstrn(const char *s1, const char *s2, apr_size_t n)
+AP_DECLARE(int) ap_cstr_casecmpn(const char *s1, const char *s2, apr_size_t n)
{
- const unsigned char *ps1 = (const unsigned char *) s1;
- const unsigned char *ps2 = (const unsigned char *) s2;
- while (n--) {
- if (ucharmap[*ps1] != ucharmap[*ps2]) {
- return (ucharmap[*ps1] - ucharmap[*ps2]);
- }
- if (*ps1++ == '\0') {
- break;
- }
- ps2++;
+ 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);
+ return 0;
}
+