From: William A. Rowe Jr Date: Fri, 29 Jul 2016 22:00:52 +0000 (+0000) Subject: Replacement solution to identify VCHAR/ASCII symbols, even in EBCDIC. X-Git-Tag: 2.5.0-alpha~1351 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=4cdf495718e107bc44f816d5248947ee27baa31c;p=apache Replacement solution to identify VCHAR/ASCII symbols, even in EBCDIC. Looking for someone with an EBCDIC environment to post the output of the test_char.h generated file for verification. git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@1754579 13f79535-47bb-0310-9956-ffa450edef68 --- diff --git a/server/gen_test_char.c b/server/gen_test_char.c index 1db23b3ee5..6e065aa305 100644 --- a/server/gen_test_char.c +++ b/server/gen_test_char.c @@ -20,6 +20,7 @@ #define apr_isalpha(c) (isalpha(((unsigned char)(c)))) #define apr_iscntrl(c) (iscntrl(((unsigned char)(c)))) #define apr_isprint(c) (isprint(((unsigned char)(c)))) +#define apr_isascii(c) (isascii(((unsigned char)(c)))) #include #define APR_HAVE_STDIO_H 1 #define APR_HAVE_STRING_H 1 @@ -31,6 +32,48 @@ #endif +#if APR_CHARSET_EBCDIC +/* See util.c for complete explanation of this table */ +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 +}; +#define test_isascii_equiv(c) ((ucharmap[(unsigned char)c] & ~0x7f) == 0) +#else +#define test_isascii_equiv(c) apr_isascii(c) +#endif + + #if defined(WIN32) || defined(OS2) #define NEED_ENHANCED_ESCAPES #endif @@ -120,19 +163,20 @@ int main(int argc, char *argv[]) /* Stop for any non-'token' character, including ctrls, obs-text, * and "tspecials" (RFC2068) a.k.a. "separators" (RFC2616) - * XXX: We need to build a specific table for EBCDIC values with - * ASCII equivilants here + * XXX: We need to verify that ASCII C0 ctrls/DEL in our EBCDIC table + * are captured by apr_iscntrl() */ - if (!c || apr_iscntrl(c) || strchr(" \t()<>@,;:\\\"/[]?={}", c)) { + if (!c || apr_iscntrl(c) || strchr(" \t()<>@,;:\\\"/[]?={}", c) + || !test_isascii_equiv(c)) { flags |= T_HTTP_TOKEN_STOP; } /* Catch CTRLs other than VCHAR, HT and SP, and obs-text (RFC7230 3.2) * This includes only the C0 plane, not C1 (which is obs-text itself.) - * XXX: Need to constrain iscntrl to C0 equivilants in ASCII, - * even on EBCDIC architecture + * XXX: We need to verify that ASCII C0 ctrls/DEL in our EBCDIC table + * are captured by apr_iscntrl() */ - if (!c || (apr_iscntrl(c) && c != '\t')) { + if (!c || (apr_iscntrl(c) && c != '\t' && test_isascii_equiv(c))) { flags |= T_HTTP_CTRLS; }