Implement md5(bytea), update regression tests and documentation. Patch

from Abhijit Menon-Sen, minor editorialization from Neil Conway. Also,
improve md5(text) to allocate a constant-sized buffer on the stack
rather than via palloc.

Catalog version bumped.

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 27cbab9291b412f374d513592ebf44833b547947..cb7f3ac3d27e8e86e491f763cf4e5f150fe69bd8 100644 (file)
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -2328,6 +2328,17 @@ PostgreSQL documentation
       <entry><literal>5</literal></entry>
      </row>
 
+     <row>
+      <entry><literal><function>md5</function>(<parameter>string</parameter>)</literal></entry>
+      <entry><type>text</type></entry>
+      <entry>
+       Calculates the MD5 hash of <parameter>string</parameter>,
+       returning the result in hexadecimal.
+      </entry>
+      <entry><literal>md5('Th\\000omas'::bytea)</literal></entry>
+      <entry><literal>8ab2d3c9689aaf18 b4958c334c82d8b1</literal></entry>
+     </row>
+
      <row>
       <entry>
        <literal><function>decode</function>(<parameter>string</parameter> <type>text</type>,

diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index e37192fa643d9fc7342243377e7981bf57b5ec4b..f9b50d0267476fd5dc27f0549d24e14ef60e019f 100644 (file)
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -2308,15 +2308,12 @@ md5_text(PG_FUNCTION_ARGS)
 {
        text       *in_text = PG_GETARG_TEXT_P(0);
        size_t          len;
-       char       *hexsum;
+       char        hexsum[MD5_HASH_LEN + 1];
        text       *result_text;
 
        /* Calculate the length of the buffer using varlena metadata */
        len = VARSIZE(in_text) - VARHDRSZ;
 
-       /* leave room for the terminating '\0' */
-       hexsum = (char *) palloc(MD5_HASH_LEN + 1);
-
        /* get the hash result */
        if (md5_hash(VARDATA(in_text), len, hexsum) == false)
                ereport(ERROR,
@@ -2327,3 +2324,25 @@ md5_text(PG_FUNCTION_ARGS)
        result_text = PG_STR_GET_TEXT(hexsum);
        PG_RETURN_TEXT_P(result_text);
 }
+
+/*
+ * Create an md5 hash of a bytea field and return it as a hex string:
+ * 16-byte md5 digest is represented in 32 hex characters.
+ */
+Datum
+md5_bytea(PG_FUNCTION_ARGS)
+{
+       bytea      *in = PG_GETARG_BYTEA_P(0);
+       size_t          len;
+       char            hexsum[MD5_HASH_LEN + 1];
+       text       *result_text;
+
+       len = VARSIZE(in) - VARHDRSZ;
+       if (md5_hash(VARDATA(in), len, hexsum) == false)
+               ereport(ERROR,
+                               (errcode(ERRCODE_OUT_OF_MEMORY),
+                                errmsg("out of memory")));
+
+       result_text = PG_STR_GET_TEXT(hexsum);
+       PG_RETURN_TEXT_P(result_text);
+}

diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index 4d558d9ef1c7e134f9b12a835c46ec260f1455b1..7d0e65aceb5d13c3e45d53df14a8838bf9f1e08c 100644 (file)
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -53,6 +53,6 @@
  */
 
 /*                                                     yyyymmddN */
-#define CATALOG_VERSION_NO     200505171
+#define CATALOG_VERSION_NO     200505201
 
 #endif

diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index d14fcbc90b5bea6e2440cd1f3260e714ed1bddb0..aec5b180ef64db98c4832510197e268b9df0f390 100644 (file)
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -3269,6 +3269,8 @@ DESCR("I/O");
 /* cryptographic */
 DATA(insert OID =  2311 (  md5    PGNSP PGUID 12 f f t f i 1 25 "25" _null_ _null_ _null_  md5_text - _null_ ));
 DESCR("calculates md5 hash");
+DATA(insert OID =  2321 (  md5    PGNSP PGUID 12 f f t f i 1 25 "17" _null_ _null_ _null_  md5_bytea - _null_ ));
+DESCR("calculates md5 hash");
 
 /* crosstype operations for date vs. timestamp and timestamptz */
 DATA(insert OID = 2338 (  date_lt_timestamp               PGNSP PGUID 12 f f t f i 2 16 "1082 1114" _null_ _null_ _null_ date_lt_timestamp - _null_ ));

diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index dc2600390e4854919603a2970cb9c55302794e25..b1acc675d0c4dbd2febf238faf137d385fc1ab3a 100644 (file)
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -572,6 +572,7 @@ extern Datum array_to_text(PG_FUNCTION_ARGS);
 extern Datum to_hex32(PG_FUNCTION_ARGS);
 extern Datum to_hex64(PG_FUNCTION_ARGS);
 extern Datum md5_text(PG_FUNCTION_ARGS);
+extern Datum md5_bytea(PG_FUNCTION_ARGS);
 
 extern Datum unknownin(PG_FUNCTION_ARGS);
 extern Datum unknownout(PG_FUNCTION_ARGS);

diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
index 3421b875227e933d291cacca1d9045bed06c61a5..ab4cd6a7979b16dbd288cda61ec56dabf3b66c8d 100644 (file)
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -825,3 +825,45 @@ select md5('12345678901234567890123456789012345678901234567890123456789012345678
  t
 (1 row)
 
+select md5(''::bytea) = 'd41d8cd98f00b204e9800998ecf8427e' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('a'::bytea) = '0cc175b9c0f1b6a831c399e269772661' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('abc'::bytea) = '900150983cd24fb0d6963f7d28e17f72' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('message digest'::bytea) = 'f96b697d7cb7938d525a2f31aaf161d0' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('abcdefghijklmnopqrstuvwxyz'::bytea) = 'c3fcd3d76192e4007dfb496cca67e13b' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'::bytea) = 'd174ab98d277d9f5a5611c2c9f419d9f' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+
+select md5('12345678901234567890123456789012345678901234567890123456789012345678901234567890'::bytea) = '57edf4a22be3c955ac49da2e2107b67a' AS "TRUE";
+ TRUE 
+------
+ t
+(1 row)
+

diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
index d2368d6ba534ab537f868996e5238ed285e684dd..a59b39cf99ef5e360fb1fe1120b357a11c733c30 100644 (file)
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -331,3 +331,17 @@ select md5('abcdefghijklmnopqrstuvwxyz') = 'c3fcd3d76192e4007dfb496cca67e13b' AS
 select md5('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789') = 'd174ab98d277d9f5a5611c2c9f419d9f' AS "TRUE";
 
 select md5('12345678901234567890123456789012345678901234567890123456789012345678901234567890') = '57edf4a22be3c955ac49da2e2107b67a' AS "TRUE";
+
+select md5(''::bytea) = 'd41d8cd98f00b204e9800998ecf8427e' AS "TRUE";
+
+select md5('a'::bytea) = '0cc175b9c0f1b6a831c399e269772661' AS "TRUE";
+
+select md5('abc'::bytea) = '900150983cd24fb0d6963f7d28e17f72' AS "TRUE";
+
+select md5('message digest'::bytea) = 'f96b697d7cb7938d525a2f31aaf161d0' AS "TRUE";
+
+select md5('abcdefghijklmnopqrstuvwxyz'::bytea) = 'c3fcd3d76192e4007dfb496cca67e13b' AS "TRUE";
+
+select md5('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'::bytea) = 'd174ab98d277d9f5a5611c2c9f419d9f' AS "TRUE";
+
+select md5('12345678901234567890123456789012345678901234567890123456789012345678901234567890'::bytea) = '57edf4a22be3c955ac49da2e2107b67a' AS "TRUE";