MINOR: sample: add new converters to hash input

From time to time it's useful to hash input data (scramble input, or
reduce the space needed in a stick table). This patch provides 3 simple
converters allowing use of the available hash functions to hash input
data. The output is an unsigned integer which can be passed into a header,
a log or used as an index for a stick table. One nice usage is to scramble
source IP addresses before logging when there are requirements to hide them.

doc/configuration.txt

@@ -9959,6 +9959,17 @@ base64
   transfer binary content in a way that can be reliably transferred (eg:
   an SSL ID can be copied in a header).
 
+djb2([<avalanche>])
+  Hashes a binary input sample into an unsigned 32-bit quantity using the DJB2
+  hash function. Optionally, it is possible to apply a full avalanche hash
+  function to the output if the optional <avalanche> argument equals 1. This
+  converter uses the same functions as used by the various hash-based load
+  balancing algorithms, so it will provide exactly the same results. It is
+  mostly intended for debugging, but can be used as a stick-table entry to
+  collect rough statistics. It must not be used for security purposes as a
+  32-bit hash is trivial to break. See also "sdbm", "wt6" and the "hash-type"
+  directive.
+
 hex
   Converts a binary input sample to an hex string containing two hex digits per
   input byte. It is used to log or transfer hex dumps of some binary input data
@@ -10089,6 +10100,17 @@ map_<match_type>_<output_type>(<map_file>[,<default_value>])
       |       `---------------------------- key
       `------------------------------------ leading spaces ignored
 
+sdbm([<avalanche>])
+  Hashes a binary input sample into an unsigned 32-bit quantity using the SDBM
+  hash function. Optionally, it is possible to apply a full avalanche hash
+  function to the output if the optional <avalanche> argument equals 1. This
+  converter uses the same functions as used by the various hash-based load
+  balancing algorithms, so it will provide exactly the same results. It is
+  mostly intended for debugging, but can be used as a stick-table entry to
+  collect rough statistics. It must not be used for security purposes as a
+  32-bit hash is trivial to break. See also "djb2", "wt6" and the "hash-type"
+  directive.
+
 table_bytes_in_rate(<table>)
   Uses the string representation of the input sample to perform a look up in
   the specified table. If the key is not found in the table, integer value zero
@@ -10247,6 +10269,17 @@ utime(<format>[,<offset>])
       # Eg:  20140710162350 127.0.0.1:57325
       log-format %[date,utime(%Y%m%d%H%M%S)]\ %ci:%cp
 
+wt6([<avalanche>])
+  Hashes a binary input sample into an unsigned 32-bit quantity using the WT6
+  hash function. Optionally, it is possible to apply a full avalanche hash
+  function to the output if the optional <avalanche> argument equals 1. This
+  converter uses the same functions as used by the various hash-based load
+  balancing algorithms, so it will provide exactly the same results. It is
+  mostly intended for debugging, but can be used as a stick-table entry to
+  collect rough statistics. It must not be used for security purposes as a
+  32-bit hash is trivial to break. See also "djb2", "sdbm", and the "hash-type"
+  directive.
+
 
 7.3.2. Fetching samples from internal states
 --------------------------------------------
@@ -11408,7 +11441,9 @@ base32 : integer
   This returns a 32-bit hash of the value returned by the "base" fetch method
   above. This is useful to track per-URL activity on high traffic sites without
   having to store all URLs. Instead a shorter hash is stored, saving a lot of
-  memory. The output type is an unsigned integer.
+  memory. The output type is an unsigned integer. The hash function used is
+  SDBM with full avalanche on the output. Technically, base32 is exactly equal
+  to "base,sdbm(1)".
 
 base32+src : binary
   This returns the concatenation of the base32 fetch above and the src fetch

src/sample.c

@@ -18,6 +18,7 @@
 #include <types/global.h>
 
 #include <common/chunk.h>
+#include <common/hash.h>
 #include <common/standard.h>
 #include <common/uri_auth.h>
 #include <common/base64.h>
@@ -1240,6 +1241,16 @@ static int sample_conv_bin2hex(const struct arg *arg_p, struct sample *smp)
 	return 1;
 }
 
+/* hashes the binary input into a 32-bit unsigned int */
+static int sample_conv_djb2(const struct arg *arg_p, struct sample *smp)
+{
+	smp->data.uint = hash_djb2(smp->data.str.str, smp->data.str.len);
+	if (arg_p && arg_p->data.uint)
+		smp->data.uint = full_hash(smp->data.uint);
+	smp->type = SMP_T_UINT;
+	return 1;
+}
+
 static int sample_conv_str2lower(const struct arg *arg_p, struct sample *smp)
 {
 	int i;
@@ -1302,6 +1313,16 @@ static int sample_conv_ltime(const struct arg *args, struct sample *smp)
 	return 1;
 }
 
+/* hashes the binary input into a 32-bit unsigned int */
+static int sample_conv_sdbm(const struct arg *arg_p, struct sample *smp)
+{
+	smp->data.uint = hash_sdbm(smp->data.str.str, smp->data.str.len);
+	if (arg_p && arg_p->data.uint)
+		smp->data.uint = full_hash(smp->data.uint);
+	smp->type = SMP_T_UINT;
+	return 1;
+}
+
 /* takes an UINT value on input supposed to represent the time since EPOCH,
  * adds an optional offset found in args[1] and emits a string representing
  * the UTC date in the format specified in args[1] using strftime().
@@ -1322,6 +1343,16 @@ static int sample_conv_utime(const struct arg *args, struct sample *smp)
 	return 1;
 }
 
+/* hashes the binary input into a 32-bit unsigned int */
+static int sample_conv_wt6(const struct arg *arg_p, struct sample *smp)
+{
+	smp->data.uint = hash_wt6(smp->data.str.str, smp->data.str.len);
+	if (arg_p && arg_p->data.uint)
+		smp->data.uint = full_hash(smp->data.uint);
+	smp->type = SMP_T_UINT;
+	return 1;
+}
+
 /************************************************************************/
 /*       All supported sample fetch functions must be declared here     */
 /************************************************************************/
@@ -1426,6 +1457,9 @@ static struct sample_conv_kw_list sample_conv_kws = {ILH, {
 	{ "ipmask", sample_conv_ipmask,    ARG1(1,MSK4), NULL, SMP_T_IPV4, SMP_T_IPV4 },
 	{ "ltime",  sample_conv_ltime,     ARG2(1,STR,SINT), NULL, SMP_T_UINT, SMP_T_STR },
 	{ "utime",  sample_conv_utime,     ARG2(1,STR,SINT), NULL, SMP_T_UINT, SMP_T_STR },
+	{ "djb2",   sample_conv_djb2,      ARG1(0,UINT), NULL, SMP_T_BIN,  SMP_T_UINT },
+	{ "sdbm",   sample_conv_sdbm,      ARG1(0,UINT), NULL, SMP_T_BIN,  SMP_T_UINT },
+	{ "wt6",    sample_conv_wt6,       ARG1(0,UINT), NULL, SMP_T_BIN,  SMP_T_UINT },
 	{ NULL, NULL, 0, 0, 0 },
 }};