Merge pull request #463 from cbowman0/issue462

Support a rewrite syntax with form \g{n} to allow for integers to follow

Makefile.am

@@ -126,6 +126,7 @@ CRTESTS = \
 	issue357 \
 	issue369 \
 	issue448 \
+	issue462 \
 	server-type \
 	basic \
 	metriclimits \

carbon-c-relay.md

@@ -486,10 +486,11 @@ needed aggregation instances.
 ### REWRITES
 Rewrite rules take a regular expression as input to match incoming
 metrics, and transform them into the desired new metric name.  In the
-replacement,
-backreferences are allowed to match capture groups defined in the input
-regular expression.  A match of `server\.(x|y|z)\.` allows to use e.g.
-`role.\1.` in the substitution.  A few caveats apply to the current
+replacement, backreferences are allowed to match capture groups
+defined in the input regular expression.  A match of `server\.(x|y|z)\.`
+allows to use e.g.  `role.\1.` in the substitution. If needed, a notation
+of `\g{n}` can be used instead of `\n` where the backreference is followed
+by an integer, such as `\g{1}100`.  A few caveats apply to the current
 implementation of rewrite rules.  First, their location in the config
 file determines when the rewrite is performed.  The rewrite is done
 in-place, as such a match rule before the rewrite would match the
@@ -555,7 +556,7 @@ Given the input expression, the following match groups are available:
 something like `carbon.relays.\_2` for certain scenarios, to always use
 the lowercased short hostname, which following the expression doesn't
 contain a dot.  By default, the metrics are submitted every 60 seconds,
-this can be changed using the `submit every <interval> seconds` clause.  
+this can be changed using the `submit every <interval> seconds` clause
 To obtain a more compatible set of values to carbon-cache.py, use the
 `reset counters after interval` clause to make values non-cumulative,
 that is, they will report the change compared to the previous value.
@@ -818,6 +819,18 @@ matters.  Hence to build on top of the old/new cluster example done
 earlier, the following would store the original metric name in the old
 cluster, and the new metric name in the new cluster:
 
+```
+rewrite ^server\.(.+)\.(.+)\.([a-zA-Z]+)([0-9]+)
+    into server.\_1.\2.\3.\3\4
+    ;
+rewrite ^server\.(.+)\.(.+)\.([a-zA-Z]+)([0-9]+)
+    into server.\g{_1}.\g{2}.\g{3}.\g{3}\g{4}
+    ;
+```
+
+The alternate syntax for backreference notation using `g\{n}` instead of `\n`
+notation shown above.  Both rewrite rules are identical.
+
 ```
 match * send to old;
 
@@ -936,7 +949,8 @@ without the `send to`, the metric name can't be kept its original name,
 for the output now directly goes to the cluster.
 
 
-When configuring cluster you might want to check how the metrics will be routed and hashed. That's what the `-t` flag is for. For the following configuration: 
+When configuring cluster you might want to check how the metrics will be routed
+and hashed. That's what the `-t` flag is for. For the following configuration:
 
 ```
 cluster graphite_swarm_odd
@@ -962,7 +976,8 @@ match *
 ;
 ```
 
-Running the command: `echo "my.super.metric" | carbon-c-relay -f config.conf  -t`, will result in: 
+Running the command:
+`echo "my.super.metric" | carbon-c-relay -f config.conf  -t`, will result in:
 
 ```
 [...]
@@ -975,8 +990,9 @@ match
     stop
 ```
 
-You now know that your metric `my.super.metric` will be hashed and arrive on the host03 and host04 machines.
-Adding the `-d` flag will increase the amount of information by showing you the hashring
+You now know that your metric `my.super.metric` will be hashed and arrive on the
+host03 and host04 machines.  Adding the `-d` flag will increase the amount of
+information by showing you the hashring
 
 ## STATISTICS
 
@@ -1146,8 +1162,8 @@ provides a multithreaded relay which can address multiple targets and
 clusters for each and every metric based on pattern matches.
 
 There are a couple more replacement projects out there, which
-are [carbon-relay-ng](https://github.com/graphite-ng/carbon-relay-ng) and [graphite-relay](https://github.com/markchadwick/graphite-relay
-).
+are [carbon-relay-ng](https://github.com/graphite-ng/carbon-relay-ng) and
+[graphite-relay](https://github.com/markchadwick/graphite-relay).
 
 Compared to carbon-relay-ng, this project does provide carbon's
 consistent-hash routing.  graphite-relay, which does this, however

issues/issue462.conf

@@ -0,0 +1,28 @@
+cluster default
+    fnv1a_ch replication 1
+        127.0.0.1:2103 proto tcp
+    ;
+
+aggregate ^sys\.somemetric\.([A-Za-z0-9_]+)\.percentile
+    every 60 seconds
+    expire after 75 seconds
+    compute sum write to
+        sys.somemetric.\1sum
+    compute percentile50 write to
+        sys.somemetric.\g{1}50
+    compute percentile75 write to
+        sys.somemetric.\g{1}75
+    compute percentile90 write to
+        sys.somemetric.\g{^1}90
+    compute percentile99 write to
+        sys.somemetric.\g{_1}99
+    send to default
+    stop
+    ;
+
+
+match *
+    send to
+        default
+    stop
+    ;

router.c

@@ -2608,6 +2608,7 @@ router_rewrite_metric(
 	const char *t;
 	enum rewrite_case { RETAIN, LOWER, UPPER,
 	                    RETAIN_DOT, LOWER_DOT, UPPER_DOT } rcase = RETAIN;
+	enum capture_case { NUMMATCH, GMATCH, GMATCH_BRACES } ccase = NUMMATCH;
 
 	assert(pmatch != NULL);
 
@@ -2647,6 +2648,10 @@ router_rewrite_metric(
 					escape = 2;
 					ref *= 10;
 					ref += *p - '0';
+				} else if (escape && ref == 0 && *p == 'g') {
+					ccase = GMATCH;
+				} else if (escape && ref == 0 && ccase == GMATCH && *p == '{') {
+					ccase = GMATCH_BRACES;
 				} else {
 					if (escape) {
 						if (ref > 0 && ref <= nmatch
@@ -2702,9 +2707,14 @@ router_rewrite_metric(
 						}
 						ref = 0;
 					}
-					if (*p != '\\') { /* \1\2 case */
+					if (ccase == GMATCH_BRACES && *p == '}') { /* End case of \g{n} */
 						escape = 0;
 						rcase = RETAIN;
+						ccase = NUMMATCH;
+					} else if (*p != '\\') { /* \1\2 case */
+						escape = 0;
+						rcase = RETAIN;
+						ccase = NUMMATCH;
 						if (s - *newmetric + 1 < sizeof(*newmetric))
 							*s++ = *p;
 					}

test/issue462.out

@@ -0,0 +1,48 @@
+listen
+    type linemode
+        2003 proto tcp
+        2003 proto udp
+        /tmp/.s.carbon-c-relay.2003 proto unix
+    ;
+
+statistics
+    submit every 60 seconds
+    prefix with carbon.relays.test_hostname
+    ;
+
+cluster default
+    fnv1a_ch replication 1
+        127.0.0.1:2103
+    ;
+
+aggregate ^sys\.somemetric\.([A-Za-z0-9_]+)\.percentile
+    every 60 seconds
+    expire after 75 seconds
+    timestamp at end of bucket
+    compute sum write to
+        sys.somemetric.\1sum
+    compute percentile50 write to
+        sys.somemetric.\g{1}50
+    compute percentile75 write to
+        sys.somemetric.\g{1}75
+    compute percentile90 write to
+        sys.somemetric.\g{^1}90
+    compute percentile99 write to
+        sys.somemetric.\g{_1}99
+    send to default
+    stop
+    ;
+match *
+    send to default
+    stop
+    ;
+
+aggregation
+    ^sys\.somemetric\.([A-Za-z0-9_]+)\.percentile (regex) -> sys.somemetric.random.percentile
+    sum(sys.somemetric.\1sum) -> sys.somemetric.randomsum 
+    percentile50(sys.somemetric.\g{1}50) -> sys.somemetric.random50 
+    percentile75(sys.somemetric.\g{1}75) -> sys.somemetric.random75 
+    percentile90(sys.somemetric.\g{^1}90) -> sys.somemetric.RANDOM90 
+    percentile99(sys.somemetric.\g{_1}99) -> sys.somemetric.random99 
+    fnv1a_ch(default)
+    stop

test/issue462.tst

@@ -0,0 +1 @@
+sys.somemetric.random.percentile