4 Commits (1cdc58722cdbd60f70a48c83d6ead45cebb3562d)

Author	SHA1	Message	Date
Bruce Momjian	8aa538cfd5	* When postgres.h does not define BYTE_ENDIAN pgcrypto ... produces garbage. I learned the hard way that #if UNDEFINED_1 == UNDEFINED_2 #error "gcc is idiot" #endif prints "gcc is idiot" ... Affected are MD5/SHA1 in internal library, and also HMAC-MD5/HMAC-SHA1/ crypt-md5 which use them. Blowfish is ok, also Rijndael on at least x86. Big thanks to Daniel Holtzman who send me a build log which contained warning: md5.c:246: warning: `X' defined but not used Yes, gcc is that helpful... Please apply this. -- marko	24 years ago
Bruce Momjian	b81844b173	pgindent run on all C files. Java run to follow. initdb/regression ... tests pass.	24 years ago
Tom Lane	77f27d5ec3	Fix some portability problems (get it to compile, at least, on HP's cc)	24 years ago
Bruce Momjian	ab56022864	Big thanks to Solar Designer who pointed out a bug in bcrypt ... salt generation code. He also urged using better random source and making possible to choose using bcrypt and xdes rounds more easily. So, here's patch: * For all salt generation, use Solar Designer's own code. This is mostly due fact that his code is more fit for get_random_bytes() style interface. * New function: gen_salt(type, rounds). This lets specify iteration count for algorithm. * random.c: px_get_random_bytes() function. Supported randomness soure: /dev/urandom, OpenSSL PRNG, libc random() Default: /dev/urandom. * Draft description of C API for pgcrypto functions. New files: API, crypt-gensalt.c, random.c Marko Kreen	24 years ago