I would like to do a interface change in pgcrypto. (Good

timing, I know :))  At the moment the digest() function returns
hexadecimal coded hash, but I want it to return pure binary.  I
have also included functions encode() and decode() which support
'base64' and 'hex' encodings, so if anyone needs digest() in hex
he can do encode(digest(...), 'hex').

Main reason for it is "to do one thing and do it well" :)

Another reason is if someone needs really lot of digesting, in
the end he wants to store the binary not the hexadecimal result.
It is really silly to convert it to hex then back to binary
again.  As I said if someone needs hex he can get it.

Well, and the real reason that I am doing encrypt()/decrypt()
functions and _they_ return binary.  For testing I like to see
it in hex occasionally, but it is really wrong to let them
return hex.  Only now it caught my eye that hex-coding in
digest() is wrong.  When doing digest() I thought about 'common
case' but hacking with psql is probably _not_ the common case :)

Marko Kreen

contrib/pgcrypto/Makefile

 #
-# $Header: /cvsroot/pgsql/contrib/pgcrypto/Makefile,v 1.1 2000/10/31 13:11:28 petere Exp $
+# $Header: /cvsroot/pgsql/contrib/pgcrypto/Makefile,v 1.2 2001/01/24 03:46:16 momjian Exp $
 #
 
 subdir = contrib/pgcrypto
@@ -34,7 +34,7 @@ SRCS=krb.c
 endif
 
 NAME	:= pgcrypto
-SRCS	+= pgcrypto.c
+SRCS	+= pgcrypto.c encode.c
 OBJS	:= $(SRCS:.c=.o)
 SO_MAJOR_VERSION = 0
 SO_MINOR_VERSION = 1

contrib/pgcrypto/README.pgcrypto

 
 DESCRIPTION
 
-  Here is a implementation of crypto hashes for PostgreSQL.
-  It exports 2 functions to SQL level:
+  Here are various cryptographic and otherwise useful
+  functions for PostgreSQL.
+
+    encode(data, type)
+        encodes binary data into ASCII-only representation.
+	Types supported are 'hex' and 'base64'.
+
+    decode(data, type)
+    	decodes the data processed by encode()
 
     digest(data::text, hash_name::text)
-	which returns hexadecimal coded hash over data by
+	which returns cryptographic checksum over data by
 	specified algorithm. eg
 
-	> select digest('blah', 'sha1');
+	> select encode(digest('blah', 'sha1'), 'hex');
 	5bf1fd927dfb8679496a2e6cf00cbe50c1c87145
 
     digest_exists(hash_name::text)::bool

contrib/pgcrypto/encode.c

+/*
+ * encode.c
+ *		Various data encoding/decoding things.
+ * 
+ * Copyright (c) 2001 Marko Kreen
+ * 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.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS 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 AUTHOR OR 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.
+ *
+ * $Id: encode.c,v 1.1 2001/01/24 03:46:16 momjian Exp $
+ */
+
+#include <postgres.h>
+#include <fmgr.h>
+
+#include "encode.h"
+
+/*
+ * NAMEDATALEN is used for hash names
+ */
+#if NAMEDATALEN < 16
+#error "NAMEDATALEN < 16: too small"
+#endif
+
+static pg_coding *
+find_coding(pg_coding *hbuf, text *name, int silent);
+static pg_coding *
+pg_find_coding(pg_coding *res, char *name);
+
+
+/* SQL function: encode(bytea, text) returns text */
+PG_FUNCTION_INFO_V1(encode);
+
+Datum
+encode(PG_FUNCTION_ARGS)
+{
+	text *arg;
+	text *name;
+	uint len, rlen, rlen0;
+	pg_coding *c, cbuf;
+	text *res;
+	
+	if (PG_ARGISNULL(0) || PG_ARGISNULL(1))
+		PG_RETURN_NULL();
+	
+	name = PG_GETARG_TEXT_P(1);	
+	c = find_coding(&cbuf, name, 0); /* will give error if fails */
+
+	arg = PG_GETARG_TEXT_P(0);
+	len = VARSIZE(arg) - VARHDRSZ;
+	
+	rlen0 = c->encode_len(len);
+	
+	res = (text *)palloc(rlen0 + VARHDRSZ);
+	
+	rlen = c->encode(VARDATA(arg), len, VARDATA(res));
+	VARATT_SIZEP(res) = rlen + VARHDRSZ;
+
+	if (rlen > rlen0)
+		elog(FATAL, "pg_encode: overflow, encode estimate too small");
+	
+	PG_FREE_IF_COPY(arg, 0);
+	PG_FREE_IF_COPY(name, 0);
+	
+	PG_RETURN_TEXT_P(res);
+}
+
+/* SQL function: decode(text, text) returns bytea */
+PG_FUNCTION_INFO_V1(decode);
+
+Datum
+decode(PG_FUNCTION_ARGS)
+{
+	text *arg;
+	text *name;
+	uint len, rlen, rlen0;
+	pg_coding *c, cbuf;
+	text *res;
+	
+	if (PG_ARGISNULL(0) || PG_ARGISNULL(1))
+		PG_RETURN_NULL();
+	
+	name = PG_GETARG_TEXT_P(1);	
+	c = find_coding(&cbuf, name, 0); /* will give error if fails */
+
+	arg = PG_GETARG_TEXT_P(0);
+	len = VARSIZE(arg) - VARHDRSZ;
+	
+	rlen0 = c->decode_len(len);
+	
+	res = (text *)palloc(rlen0 + VARHDRSZ);
+	
+	rlen = c->decode(VARDATA(arg), len, VARDATA(res));
+	VARATT_SIZEP(res) = rlen + VARHDRSZ;
+
+	if (rlen > rlen0)
+		elog(FATAL, "pg_decode: overflow, decode estimate too small");
+	
+	PG_FREE_IF_COPY(arg, 0);
+	PG_FREE_IF_COPY(name, 0);
+	
+	PG_RETURN_TEXT_P(res);
+}
+
+static pg_coding *
+find_coding(pg_coding *dst, text *name, int silent)
+{
+	pg_coding *p;
+	char buf[NAMEDATALEN];
+	uint len;
+	
+	len = VARSIZE(name) - VARHDRSZ;
+	if (len >= NAMEDATALEN) {
+		if (silent)
+			return NULL;
+		elog(ERROR, "Encoding type does not exist (name too long)");
+	}
+		
+	memcpy(buf, VARDATA(name), len);
+	buf[len] = 0;
+	
+	p = pg_find_coding(dst, buf);
+
+	if (p == NULL && !silent)
+		elog(ERROR, "Encoding type does not exist: '%s'", buf);
+	return p;
+}
+
+static char *hextbl = "0123456789abcdef";
+
+uint
+hex_encode(uint8 *src, uint len, uint8 *dst)
+{
+	uint8 *end = src + len;
+	while (src < end) {
+		*dst++ = hextbl[(*src >> 4) & 0xF];
+		*dst++ = hextbl[*src & 0xF];
+		src++;
+	}
+	return len*2;
+}
+
+/* probably should use lookup table */
+static uint8
+get_hex(char c)
+{
+	uint8 res = 0;
+	
+	if (c >= '0' && c <= '9')
+		res = c - '0';
+	else if (c >= 'a' && c <= 'f')
+		res = c - 'a' + 10;
+	else if (c >= 'A' && c <= 'F')
+		res = c - 'A' + 10;
+	else
+		elog(ERROR, "Bad hex code: '%c'", c);
+	
+	return res;
+}
+
+uint
+hex_decode(uint8 *src, uint len, uint8 *dst)
+{
+	uint8 *s, *srcend, v1, v2, *p = dst;
+	
+	srcend = src + len;
+	s = src; p = dst;
+	while (s < srcend) {
+		if (*s == ' ' || *s == '\n' || *s == '\t' || *s == '\r') {
+			s++;
+			continue;
+		}
+		v1 = get_hex(*s++) << 4;
+		if (s >= srcend)
+			elog(ERROR, "hex_decode: invalid data");
+		v2 = get_hex(*s++);
+		*p++ = v1 | v2;
+	}
+	
+	return p - dst;
+}
+
+
+static unsigned char _base64[] =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+
+uint
+b64_encode(uint8 *src, uint len, uint8 *dst)
+{
+	uint8 *s, *p, *end = src + len, *lend = dst + 76;
+	int pos = 2;
+	unsigned long buf = 0;
+
+	s = src; p = dst;
+	
+	while (s < end) {
+		buf |= *s << (pos << 3);
+		pos--;
+		s++;
+		
+		/* write it out */
+		if (pos < 0) {
+			*p++ = _base64[(buf >> 18) & 0x3f];
+			*p++ = _base64[(buf >> 12) & 0x3f];
+			*p++ = _base64[(buf >> 6) & 0x3f];
+			*p++ = _base64[buf & 0x3f];
+
+			pos = 2;
+			buf = 0;
+		}
+		if (p >= lend) {
+			*p++ = '\n';
+			lend = p + 76;
+		}
+	}
+	if (pos != 2) {
+		*p++ = _base64[(buf >> 18) & 0x3f];
+		*p++ = _base64[(buf >> 12) & 0x3f];
+		*p++ = (pos == 0) ? _base64[(buf >> 6) & 0x3f] : '=';
+		*p++ = '=';
+	}
+
+	return p - dst;
+}
+
+/* probably should use lookup table */
+uint
+b64_decode(uint8 *src, uint len, uint8 *dst)
+{
+	char *srcend = src + len, *s = src;
+	uint8 *p = dst;
+	char c;
+	uint b = 0;
+	unsigned long buf = 0;
+	int pos = 0, end = 0;
+	
+	while (s < srcend) {
+		c = *s++;
+		if (c >= 'A' && c <= 'Z')
+			b = c - 'A';
+		else if (c >= 'a' && c <= 'z')
+			b = c - 'a' + 26;
+		else if (c >= '0' && c <= '9')
+			b = c - '0' + 52;
+		else if (c == '+')
+			b = 62;
+		else if (c == '/')
+			b = 63;
+		else if (c == '=') {
+			/* end sequence */
+			if (!end) {
+				if (pos == 2) end = 1;
+				else if (pos == 3) end = 2;
+				else
+					elog(ERROR, "base64: unexpected '='");
+			}
+			b = 0;
+		} else if (c == ' ' || c == '\t' || c == '\n' || c == '\r')
+			continue;
+		else
+			elog(ERROR, "base64: Invalid symbol");
+
+		/* add it to buffer */
+		buf = (buf << 6) + b;
+		pos++;
+		if (pos == 4) {
+			*p++ = (buf >> 16) & 255;
+			if (end == 0 || end > 1)
+				*p++ = (buf >> 8) & 255;
+			if (end == 0 || end > 2)
+				*p++ = buf & 255;
+			buf = 0;
+			pos = 0;
+		}
+	}
+
+	if (pos != 0)
+		elog(ERROR, "base64: invalid end sequence");
+
+	return p - dst;
+}
+
+
+uint
+hex_enc_len(uint srclen)
+{
+	return srclen << 1;
+}
+
+uint
+hex_dec_len(uint srclen)
+{
+	return srclen >> 1;
+}
+
+uint
+b64_enc_len(uint srclen)
+{
+	return srclen + (srclen / 3) + (srclen / (76 / 2));
+}
+
+uint
+b64_dec_len(uint srclen)
+{
+	return (srclen * 3) >> 2;
+}
+
+static pg_coding
+encoding_list [] = {
+	{ "hex", hex_enc_len, hex_dec_len, hex_encode, hex_decode},
+	{ "base64", b64_enc_len, b64_dec_len, b64_encode, b64_decode},
+	{ NULL, NULL, NULL, NULL, NULL}
+};
+
+
+static pg_coding *
+pg_find_coding(pg_coding *res, char *name)
+{
+	pg_coding *p;
+	for (p = encoding_list; p->name; p++) {
+		if (!strcasecmp(p->name, name))
+			return p;
+	}
+	return NULL;
+}
+

contrib/pgcrypto/encode.h

+/*
+ * pg_encode.h
+ *		encode.c
+ * 
+ * Copyright (c) 2001 Marko Kreen
+ * 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.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS 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 AUTHOR OR 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.
+ *
+ * $Id: encode.h,v 1.1 2001/01/24 03:46:16 momjian Exp $
+ */
+
+#ifndef __PG_ENCODE_H
+#define __PG_ENCODE_H
+
+/* exported functions */
+Datum encode(PG_FUNCTION_ARGS);
+Datum decode(PG_FUNCTION_ARGS);
+
+typedef struct _pg_coding pg_coding;
+struct _pg_coding {
+	char *name;
+	uint (*encode_len)(uint dlen);
+	uint (*decode_len)(uint dlen);
+	uint (*encode)(uint8 *data, uint dlen, uint8 *res);
+	uint (*decode)(uint8 *data, uint dlen, uint8 *res);
+};
+
+/* They are for outside usage in C code, if needed */
+uint hex_encode(uint8 *src, uint len, uint8 *dst);
+uint hex_decode(uint8 *src, uint len, uint8 *dst);
+uint b64_encode(uint8 *src, uint len, uint8 *dst);
+uint b64_decode(uint8 *src, uint len, uint8 *dst);
+
+uint hex_enc_len(uint srclen);
+uint hex_dec_len(uint srclen);
+uint b64_enc_len(uint srclen);
+uint b64_dec_len(uint srclen);
+
+#endif /* __PG_ENCODE_H */
+

contrib/pgcrypto/pgcrypto.c

@@ -26,7 +26,7 @@
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE.
  *
- * $Id: pgcrypto.c,v 1.3 2001/01/09 16:07:13 momjian Exp $
+ * $Id: pgcrypto.c,v 1.4 2001/01/24 03:46:16 momjian Exp $
  */
 
 #include <postgres.h>
@@ -34,11 +34,6 @@
 
 #include "pgcrypto.h"
 
-/*
- * maximum length of digest for internal buffers
- */
-#define MAX_DIGEST_LENGTH	128
-
 /*
  * NAMEDATALEN is used for hash names
  */
@@ -52,8 +47,6 @@ Datum digest(PG_FUNCTION_ARGS);
 Datum digest_exists(PG_FUNCTION_ARGS);
 
 /* private stuff */
-static char *
-to_hex(uint8 *src, uint len, char *dst);
 static pg_digest *
 find_digest(pg_digest *hbuf, text *name, int silent);
 
@@ -66,7 +59,6 @@ digest(PG_FUNCTION_ARGS)
 {
 	text *arg;
 	text *name;
-	uint8 *p, buf[MAX_DIGEST_LENGTH];
 	uint len, hlen;
 	pg_digest *h, _hbuf;
 	text *res;
@@ -78,17 +70,14 @@ digest(PG_FUNCTION_ARGS)
 	h = find_digest(&_hbuf, name, 0); /* will give error if fails */
 
 	hlen = h->length(h);
-	if (hlen > MAX_DIGEST_LENGTH)
-		elog(ERROR, "Hash length overflow: %d", hlen);
 	
-	res = (text *)palloc(hlen*2 + VARHDRSZ);
-	VARATT_SIZEP(res) = hlen*2 + VARHDRSZ;
+	res = (text *)palloc(hlen + VARHDRSZ);
+	VARATT_SIZEP(res) = hlen + VARHDRSZ;
 	
 	arg = PG_GETARG_TEXT_P(0);
 	len = VARSIZE(arg) - VARHDRSZ;
 	
-	p = h->digest(h, VARDATA(arg), len, buf);
-	to_hex(p, hlen, VARDATA(res));
+	h->digest(h, VARDATA(arg), len, VARDATA(res));
 	
 	PG_FREE_IF_COPY(arg, 0);
 	PG_FREE_IF_COPY(name, 0);
@@ -143,17 +132,3 @@ find_digest(pg_digest *hbuf, text *name, int silent)
 	return p;
 }
 
-static unsigned char *hextbl = "0123456789abcdef";
-
-/* dumps binary to hex...  Note that it does not null-terminate  */
-static char *
-to_hex(uint8 *buf, uint len, char *dst)
-{
-	uint i;
-	for (i = 0; i < len; i++) {
-		dst[i*2] = hextbl[(buf[i] >> 4) & 0xF];
-		dst[i*2 + 1] = hextbl[buf[i] & 0xF];
-	}
-	return dst;
-}
-

contrib/pgcrypto/pgcrypto.sql.in

 
 -- drop function digest(text, text);
 -- drop function digest_exists(text);
+-- drop function encode(text, text);
+-- drop function decode(text, text);
+
 
 CREATE FUNCTION digest(text, text) RETURNS text
   AS '@MODULE_FILENAME@',
@@ -10,3 +13,11 @@ CREATE FUNCTION digest_exists(text) RETURNS bool
   AS '@MODULE_FILENAME@',
   'digest_exists' LANGUAGE 'C';
 
+CREATE FUNCTION encode(text, text) RETURNS text
+  AS '@MODULE_FILENAME@',
+  'encode' LANGUAGE 'C';
+
+CREATE FUNCTION decode(text, text) RETURNS text
+  AS '@MODULE_FILENAME@',
+  'decode' LANGUAGE 'C';
+