Add support for dropwizard format

Godeps

@@ -72,6 +72,8 @@ github.com/StackExchange/wmi f3e2bae1e0cb5aef83e319133eabfee30013a4a5
 github.com/streadway/amqp 63795daa9a446c920826655f26ba31c81c860fd6
 github.com/stretchr/objx 1a9d0bb9f541897e62256577b352fdbc1fb4fd94
 github.com/stretchr/testify 4d4bfba8f1d1027c4fdbe371823030df51419987
+github.com/tidwall/gjson 0623bd8fbdbf97cc62b98d15108832851a658e59
+github.com/tidwall/match 173748da739a410c5b0b813b956f89ff94730b4c
 github.com/vjeantet/grok d73e972b60935c7fec0b4ffbc904ed39ecaf7efe
 github.com/wvanbergen/kafka bc265fedb9ff5b5c5d3c0fdcef4a819b3523d3ee
 github.com/wvanbergen/kazoo-go 968957352185472eacb69215fa3dbfcfdbac1096

README.md

@@ -256,6 +256,7 @@ formats may be used with input plugins supporting the `data_format` option:
 * [Value](./docs/DATA_FORMATS_INPUT.md#value)
 * [Nagios](./docs/DATA_FORMATS_INPUT.md#nagios)
 * [Collectd](./docs/DATA_FORMATS_INPUT.md#collectd)
+* [Dropwizard](./docs/DATA_FORMATS_INPUT.md#dropwizard)
 
 ## Processor Plugins
 

docs/DATA_FORMATS_INPUT.md

@@ -8,6 +8,7 @@ Telegraf is able to parse the following input data formats into metrics:
 1. [Value](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#value), ie: 45 or "booyah"
 1. [Nagios](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#nagios) (exec input only)
 1. [Collectd](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#collectd)
+1. [Dropwizard](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#dropwizard)
 
 Telegraf metrics, like InfluxDB
 [points](https://docs.influxdata.com/influxdb/v0.10/write_protocols/line/),
@@ -479,3 +480,176 @@ You can also change the path to the typesdb or add additional typesdb using
   ## Path of to TypesDB specifications
   collectd_typesdb = ["/usr/share/collectd/types.db"]
 ```
+
+# Dropwizard:
+
+The dropwizard format can parse the JSON representation of a single dropwizard metric registry. By default, tags are parsed from metric names as if they were actual influxdb line protocol keys (`measurement<,tag_set>`) which can be overriden by defining custom [measurement & tag templates](./DATA_FORMATS_INPUT.md#measurement--tag-templates). All field values are collected as float64 fields.
+
+A typical JSON of a dropwizard metric registry:
+
+```json
+{
+	"version": "3.0.0",
+	"counters" : {
+		"measurement,tag1=green" : {
+			"count" : 1
+		}
+	},
+	"meters" : {
+		"measurement" : {
+			"count" : 1,
+			"m15_rate" : 1.0,
+			"m1_rate" : 1.0,
+			"m5_rate" : 1.0,
+			"mean_rate" : 1.0,
+			"units" : "events/second"
+		}
+	},
+	"gauges" : {
+		"measurement" : {
+			"value" : 1
+		}
+	},
+	"histograms" : {
+		"measurement" : {
+			"count" : 1,
+			"max" : 1.0,
+			"mean" : 1.0,
+			"min" : 1.0,
+			"p50" : 1.0,
+			"p75" : 1.0,
+			"p95" : 1.0,
+			"p98" : 1.0,
+			"p99" : 1.0,
+			"p999" : 1.0,
+			"stddev" : 1.0
+		}
+	},
+	"timers" : {
+		"measurement" : {
+			"count" : 1,
+			"max" : 1.0,
+			"mean" : 1.0,
+			"min" : 1.0,
+			"p50" : 1.0,
+			"p75" : 1.0,
+			"p95" : 1.0,
+			"p98" : 1.0,
+			"p99" : 1.0,
+			"p999" : 1.0,
+			"stddev" : 1.0,
+			"m15_rate" : 1.0,
+			"m1_rate" : 1.0,
+			"m5_rate" : 1.0,
+			"mean_rate" : 1.0,
+			"duration_units" : "seconds",
+			"rate_units" : "calls/second"
+		}
+	}
+}
+```
+
+Would get translated into 4 different measurements:
+
+```
+measurement,metric_type=counter,tag1=green count=1
+measurement,metric_type=meter count=1,m15_rate=1.0,m1_rate=1.0,m5_rate=1.0,mean_rate=1.0
+measurement,metric_type=gauge value=1
+measurement,metric_type=histogram count=1,max=1.0,mean=1.0,min=1.0,p50=1.0,p75=1.0,p95=1.0,p98=1.0,p99=1.0,p999=1.0
+measurement,metric_type=timer count=1,max=1.0,mean=1.0,min=1.0,p50=1.0,p75=1.0,p95=1.0,p98=1.0,p99=1.0,p999=1.0,stddev=1.0,m15_rate=1.0,m1_rate=1.0,m5_rate=1.0,mean_rate=1.0
+```
+
+You may also parse a dropwizard registry from any JSON document which contains a dropwizard registry in some inner field. 
+Eg. to parse the following JSON document:
+
+```json
+{
+	"time" : "2017-02-22T14:33:03.662+02:00",
+	"tags" : {
+		"tag1" : "green",
+		"tag2" : "yellow"
+	},
+	"metrics" : {
+		"counters" : 	{ 
+			"measurement" : {
+				"count" : 1
+			}
+		},
+		"meters" : {},
+		"gauges" : {},
+		"histograms" : {},
+		"timers" : {}
+	}
+}
+```
+and translate it into:
+
+```
+measurement,metric_type=counter,tag1=green,tag2=yellow count=1 1487766783662000000
+```
+
+you simply need to use the following additional configuration properties:
+
+```toml
+dropwizard_metric_registry_path = "metrics"
+dropwizard_time_path = "time"
+dropwizard_time_format = "2006-01-02T15:04:05Z07:00"
+dropwizard_tags_path = "tags"
+## tag paths per tag are supported too, eg.
+#[inputs.yourinput.dropwizard_tag_paths]
+#  tag1 = "tags.tag1"
+#  tag2 = "tags.tag2"
+```
+
+
+For more information about the dropwizard json format see
+[here](http://metrics.dropwizard.io/3.1.0/manual/json/).
+
+#### Dropwizard Configuration:
+
+```toml
+[[inputs.exec]]
+  ## Commands array
+  commands = ["curl http://localhost:8080/sys/metrics"]
+  timeout = "5s"
+
+  ## Data format to consume.
+  ## Each data format has its own unique set of configuration options, read
+  ## more about them here:
+  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
+  data_format = "dropwizard"
+
+  ## Used by the templating engine to join matched values when cardinality is > 1
+  separator = "_"
+
+  ## Each template line requires a template pattern. It can have an optional
+  ## filter before the template and separated by spaces. It can also have optional extra
+  ## tags following the template. Multiple tags should be separated by commas and no spaces
+  ## similar to the line protocol format. There can be only one default template.
+  ## Templates support below format:
+  ## 1. filter + template
+  ## 2. filter + template + extra tag(s)
+  ## 3. filter + template with field key
+  ## 4. default template
+  ## By providing an empty template array, templating is disabled and measurements are parsed as influxdb line protocol keys (measurement<,tag_set>)
+  templates = []
+
+  ## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax) 
+  ## to locate the metric registry within the JSON document
+  # dropwizard_metric_registry_path = "metrics"
+
+  ## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax) 
+  ## to locate the default time of the measurements within the JSON document
+  # dropwizard_time_path = "time"
+  # dropwizard_time_format = "2006-01-02T15:04:05Z07:00"
+
+  ## You may use an appropriate [gjson path](https://github.com/tidwall/gjson#path-syntax) 
+  ## to locate the tags map within the JSON document
+  # dropwizard_tags_path = "tags"
+
+  ## You may even use tag paths per tag
+  # [inputs.exec.dropwizard_tag_paths]
+  #   tag1 = "tags.tag1"
+  #   tag2 = "tags.tag2"
+
+```

internal/config/config.go

@@ -1272,6 +1272,47 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
 		}
 	}
 
+	if node, ok := tbl.Fields["dropwizard_metric_registry_path"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.DropwizardMetricRegistryPath = str.Value
+			}
+		}
+	}
+	if node, ok := tbl.Fields["dropwizard_time_path"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.DropwizardTimePath = str.Value
+			}
+		}
+	}
+	if node, ok := tbl.Fields["dropwizard_time_format"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.DropwizardTimeFormat = str.Value
+			}
+		}
+	}
+	if node, ok := tbl.Fields["dropwizard_tags_path"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.DropwizardTagsPath = str.Value
+			}
+		}
+	}
+	c.DropwizardTagPathsMap = make(map[string]string)
+	if node, ok := tbl.Fields["dropwizard_tag_paths"]; ok {
+		if subtbl, ok := node.(*ast.Table); ok {
+			for name, val := range subtbl.Fields {
+				if kv, ok := val.(*ast.KeyValue); ok {
+					if str, ok := kv.Value.(*ast.String); ok {
+						c.DropwizardTagPathsMap[name] = str.Value
+					}
+				}
+			}
+		}
+	}
+
 	c.MetricName = name
 
 	delete(tbl.Fields, "data_format")
@@ -1282,6 +1323,11 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
 	delete(tbl.Fields, "collectd_auth_file")
 	delete(tbl.Fields, "collectd_security_level")
 	delete(tbl.Fields, "collectd_typesdb")
+	delete(tbl.Fields, "dropwizard_metric_registry_path")
+	delete(tbl.Fields, "dropwizard_time_path")
+	delete(tbl.Fields, "dropwizard_time_format")
+	delete(tbl.Fields, "dropwizard_tags_path")
+	delete(tbl.Fields, "dropwizard_tag_paths")
 
 	return parsers.NewParser(c)
 }

internal/templating/engine.go

@@ -0,0 +1,86 @@
+package templating
+
+import (
+	"sort"
+	"strings"
+)
+
+const (
+	// DefaultSeparator is the default separation character to use when separating template parts.
+	DefaultSeparator = "."
+)
+
+// Engine uses a Matcher to retrieve the appropriate template and applies the template
+// to the input string
+type Engine struct {
+	joiner  string
+	matcher *matcher
+}
+
+// Apply extracts the template fields from the given line and returns the measurement
+// name, tags and field name
+func (e *Engine) Apply(line string) (string, map[string]string, string, error) {
+	return e.matcher.match(line).Apply(line, e.joiner)
+}
+
+// NewEngine creates a new templating engine
+func NewEngine(joiner string, defaultTemplate *Template, templates []string) (*Engine, error) {
+	engine := Engine{
+		joiner:  joiner,
+		matcher: newMatcher(defaultTemplate),
+	}
+	templateSpecs := parseTemplateSpecs(templates)
+
+	for _, templateSpec := range templateSpecs {
+		if err := engine.matcher.addSpec(templateSpec); err != nil {
+			return nil, err
+		}
+	}
+
+	return &engine, nil
+}
+
+func parseTemplateSpecs(templates []string) templateSpecs {
+	tmplts := templateSpecs{}
+	for _, pattern := range templates {
+		tmplt := templateSpec{
+			separator: DefaultSeparator,
+		}
+
+		// Format is [separator] [filter] <template> [tag1=value1,tag2=value2]
+		parts := strings.Fields(pattern)
+		partsLength := len(parts)
+		if partsLength < 1 {
+			// ignore
+			continue
+		}
+		if partsLength == 1 {
+			tmplt.template = pattern
+		} else if partsLength == 4 {
+			tmplt.separator = parts[0]
+			tmplt.filter = parts[1]
+			tmplt.template = parts[2]
+			tmplt.tagstring = parts[3]
+		} else {
+			hasTagstring := strings.Contains(parts[partsLength-1], "=")
+			if hasTagstring {
+				tmplt.tagstring = parts[partsLength-1]
+				tmplt.template = parts[partsLength-2]
+				if partsLength == 3 {
+					tmplt.filter = parts[0]
+				}
+			} else {
+				tmplt.template = parts[partsLength-1]
+				if partsLength == 2 {
+					tmplt.filter = parts[0]
+				} else { // length == 3
+					tmplt.separator = parts[0]
+					tmplt.filter = parts[1]
+				}
+			}
+		}
+		tmplts = append(tmplts, tmplt)
+	}
+	sort.Sort(tmplts)
+	return tmplts
+}