Plugin/reader each interval

docs/DATA_FORMATS_INPUT.md

@@ -9,6 +9,7 @@ Telegraf is able to parse the following input data formats into metrics:
 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)
+1. [Grok](https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#grok)
 
 Telegraf metrics, like InfluxDB
 [points](https://docs.influxdata.com/influxdb/v0.10/write_protocols/line/),
@@ -657,5 +658,106 @@ For more information about the dropwizard json format see
   # [inputs.exec.dropwizard_tag_paths]
   #   tag1 = "tags.tag1"
   #   tag2 = "tags.tag2"
+```
 
+#### Grok
+Parse logstash-style "grok" patterns. Patterns can be added to patterns, or custom patterns read from custom_pattern_files.
+
+# View logstash grok pattern docs here:
+#   https://www.elastic.co/guide/en/logstash/current/plugins-filters-grok.html
+# All default logstash patterns are supported, these can be viewed here:
+#   https://github.com/logstash-plugins/logstash-patterns-core/blob/master/patterns/grok-patterns
+
+# Available modifiers:
+#   string   (default if nothing is specified)
+#   int
+#   float
+#   duration (ie, 5.23ms gets converted to int nanoseconds)
+#   tag      (converts the field into a tag)
+#   drop     (drops the field completely)
+# Timestamp modifiers:
+#   ts-ansic         ("Mon Jan _2 15:04:05 2006")
+#   ts-unix          ("Mon Jan _2 15:04:05 MST 2006")
+#   ts-ruby          ("Mon Jan 02 15:04:05 -0700 2006")
+#   ts-rfc822        ("02 Jan 06 15:04 MST")
+#   ts-rfc822z       ("02 Jan 06 15:04 -0700")
+#   ts-rfc850        ("Monday, 02-Jan-06 15:04:05 MST")
+#   ts-rfc1123       ("Mon, 02 Jan 2006 15:04:05 MST")
+#   ts-rfc1123z      ("Mon, 02 Jan 2006 15:04:05 -0700")
+#   ts-rfc3339       ("2006-01-02T15:04:05Z07:00")
+#   ts-rfc3339nano   ("2006-01-02T15:04:05.999999999Z07:00")
+#   ts-httpd         ("02/Jan/2006:15:04:05 -0700")
+#   ts-epoch         (seconds since unix epoch)
+#   ts-epochnano     (nanoseconds since unix epoch)
+#   ts-"CUSTOM"
+# CUSTOM time layouts must be within quotes and be the representation of the
+# "reference time", which is Mon Jan 2 15:04:05 -0700 MST 2006
+# See https://golang.org/pkg/time/#Parse for more details.
+
+# Example log file pattern, example log looks like this:
+#   [04/Jun/2016:12:41:45 +0100] 1.25 200 192.168.1.1 5.432µs
+# Breakdown of the DURATION pattern below:
+#   NUMBER  is a builtin logstash grok pattern matching float & int numbers.
+#   [nuµm]? is a regex specifying 0 or 1 of the characters within brackets.
+#   s       is also regex, this pattern must end in "s".
+# so DURATION will match something like '5.324ms' or '6.1µs' or '10s'
+DURATION %{NUMBER}[nuµm]?s
+RESPONSE_CODE %{NUMBER:response_code:tag}
+RESPONSE_TIME %{DURATION:response_time_ns:duration}
+EXAMPLE_LOG \[%{HTTPDATE:ts:ts-httpd}\] %{NUMBER:myfloat:float} %{RESPONSE_CODE} %{IPORHOST:clientip} %{RESPONSE_TIME}
+
+# Wider-ranging username matching vs. logstash built-in %{USER}
+NGUSERNAME [a-zA-Z0-9\.\@\-\+_%]+
+NGUSER %{NGUSERNAME}
+# Wider-ranging client IP matching
+CLIENT (?:%{IPORHOST}|%{HOSTPORT}|::1)
+
+##
+## COMMON LOG PATTERNS
+##
+
+# apache & nginx logs, this is also known as the "common log format"
+#   see https://en.wikipedia.org/wiki/Common_Log_Format
+COMMON_LOG_FORMAT %{CLIENT:client_ip} %{NOTSPACE:ident} %{NOTSPACE:auth} \[%{HTTPDATE:ts:ts-httpd}\] "(?:%{WORD:verb:tag} %{NOTSPACE:request}(?: HTTP/%{NUMBER:http_version:float})?|%{DATA})" %{NUMBER:resp_code:tag} (?:%{NUMBER:resp_bytes:int}|-)
+
+# Combined log format is the same as the common log format but with the addition
+# of two quoted strings at the end for "referrer" and "agent"
+#   See Examples at http://httpd.apache.org/docs/current/mod/mod_log_config.html
+COMBINED_LOG_FORMAT %{COMMON_LOG_FORMAT} %{QS:referrer} %{QS:agent}
+
+# HTTPD log formats
+HTTPD20_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[%{LOGLEVEL:loglevel:tag}\] (?:\[client %{IPORHOST:clientip}\] ){0,1}%{GREEDYDATA:errormsg}
+HTTPD24_ERRORLOG \[%{HTTPDERROR_DATE:timestamp}\] \[%{WORD:module}:%{LOGLEVEL:loglevel:tag}\] \[pid %{POSINT:pid:int}:tid %{NUMBER:tid:int}\]( \(%{POSINT:proxy_errorcode:int}\)%{DATA:proxy_errormessage}:)?( \[client %{IPORHOST:client}:%{POSINT:clientport}\])? %{DATA:errorcode}: %{GREEDYDATA:message}
+HTTPD_ERRORLOG %{HTTPD20_ERRORLOG}|%{HTTPD24_ERRORLOG}
+
+#### Grok Configuration:
+```toml
+[[inputs.reader]]
+  ## This is a list of patterns to check the given log file(s) for.
+  ## Note that adding patterns here increases processing time. The most
+  ## efficient configuration is to have one pattern per logparser.
+  ## Other common built-in patterns are:
+  ##   %{COMMON_LOG_FORMAT}   (plain apache & nginx access logs)
+  ##   %{COMBINED_LOG_FORMAT} (access logs + referrer & agent)
+  grok_patterns = ["%{COMBINED_LOG_FORMAT}"]
+
+  ## Name of the outputted measurement name.
+  grok_name_override = "apache_access_log"
+
+  ## Full path(s) to custom pattern files.
+  grok_custom_pattern_files = []
+
+  ## Custom patterns can also be defined here. Put one pattern per line.
+  grok_custom_patterns = '''
+
+  ## Timezone allows you to provide an override for timestamps that
+  ## don't already include an offset
+  ## e.g. 04/06/2016 12:41:45 data one two 5.43µs
+  ##
+  ## Default: "" which renders UTC
+  ## Options are as follows:
+  ##   1. Local             -- interpret based on machine localtime
+  ##   2. "Canada/Eastern"  -- Unix TZ values like those found in https://en.wikipedia.org/wiki/List_of_tz_database_time_zones
+  ##   3. UTC               -- or blank/unspecified, will return timestamp in UTC
+  grok_timezone = "Canada/Eastern"
 ```

internal/config/config.go

@@ -1346,6 +1346,59 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
 		}
 	}
 
+	//for grok data_format
+	if node, ok := tbl.Fields["grok_named_patterns"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if ary, ok := kv.Value.(*ast.Array); ok {
+				for _, elem := range ary.Value {
+					if str, ok := elem.(*ast.String); ok {
+						c.NamedPatterns = append(c.NamedPatterns, str.Value)
+					}
+				}
+			}
+		}
+	}
+
+	if node, ok := tbl.Fields["grok_patterns"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if ary, ok := kv.Value.(*ast.Array); ok {
+				for _, elem := range ary.Value {
+					if str, ok := elem.(*ast.String); ok {
+						c.Patterns = append(c.Patterns, str.Value)
+					}
+				}
+			}
+		}
+	}
+
+	if node, ok := tbl.Fields["grok_custom_patterns"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.CustomPatterns = str.Value
+			}
+		}
+	}
+
+	if node, ok := tbl.Fields["grok_custom_pattern_files"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if ary, ok := kv.Value.(*ast.Array); ok {
+				for _, elem := range ary.Value {
+					if str, ok := elem.(*ast.String); ok {
+						c.CustomPatternFiles = append(c.CustomPatternFiles, str.Value)
+					}
+				}
+			}
+		}
+	}
+
+	if node, ok := tbl.Fields["grok_timezone"]; ok {
+		if kv, ok := node.(*ast.KeyValue); ok {
+			if str, ok := kv.Value.(*ast.String); ok {
+				c.TimeZone = str.Value
+			}
+		}
+	}
+
 	c.MetricName = name
 
 	delete(tbl.Fields, "data_format")
@@ -1362,6 +1415,11 @@ func buildParser(name string, tbl *ast.Table) (parsers.Parser, error) {
 	delete(tbl.Fields, "dropwizard_time_format")
 	delete(tbl.Fields, "dropwizard_tags_path")
 	delete(tbl.Fields, "dropwizard_tag_paths")
+	delete(tbl.Fields, "grok_named_patterns")
+	delete(tbl.Fields, "grok_patterns")
+	delete(tbl.Fields, "grok_custom_patterns")
+	delete(tbl.Fields, "grok_custom_pattern_files")
+	delete(tbl.Fields, "grok_timezone")
 
 	return parsers.NewParser(c)
 }

plugins/inputs/all/all.go

@@ -94,6 +94,7 @@ import (
 	_ "github.com/influxdata/telegraf/plugins/inputs/puppetagent"
 	_ "github.com/influxdata/telegraf/plugins/inputs/rabbitmq"
 	_ "github.com/influxdata/telegraf/plugins/inputs/raindrops"
+	_ "github.com/influxdata/telegraf/plugins/inputs/reader"
 	_ "github.com/influxdata/telegraf/plugins/inputs/redis"
 	_ "github.com/influxdata/telegraf/plugins/inputs/rethinkdb"
 	_ "github.com/influxdata/telegraf/plugins/inputs/riak"

plugins/inputs/logparser/logparser.go

@@ -14,9 +14,8 @@ import (
 	"github.com/influxdata/telegraf"
 	"github.com/influxdata/telegraf/internal/globpath"
 	"github.com/influxdata/telegraf/plugins/inputs"
-
+	"github.com/influxdata/telegraf/plugins/parsers"
 	// Parsers
-	"github.com/influxdata/telegraf/plugins/inputs/logparser/grok"
 )
 
 const (
@@ -36,9 +35,10 @@ type logEntry struct {
 
 // LogParserPlugin is the primary struct to implement the interface for logparser plugin
 type LogParserPlugin struct {
-	Files         []string
-	FromBeginning bool
-	WatchMethod   string
+	Files           []string
+	FromBeginning   bool
+	WatchMethod     string
+	MeasurementName string `toml:"measurement"`
 
 	tailers map[string]*tail.Tail
 	lines   chan logEntry
@@ -49,7 +49,13 @@ type LogParserPlugin struct {
 
 	sync.Mutex
 
-	GrokParser *grok.Parser `toml:"grok"`
+	GrokParser parsers.Parser `toml:"grok"`
+
+	Patterns           []string
+	NamedPatterns      []string
+	CustomPatterns     string
+	CustomPatternFiles []string
+	TimeZone           string
 }
 
 const sampleConfig = `
@@ -132,6 +138,21 @@ func (l *LogParserPlugin) Start(acc telegraf.Accumulator) error {
 
 	// Looks for fields which implement LogParser interface
 	l.parsers = []LogParser{}
+	config := &parsers.Config{
+		Patterns:           l.Patterns,
+		NamedPatterns:      l.NamedPatterns,
+		CustomPatterns:     l.CustomPatterns,
+		CustomPatternFiles: l.CustomPatternFiles,
+		TimeZone:           l.TimeZone,
+		DataFormat:         "grok",
+	}
+
+	var err error
+	l.GrokParser, err = parsers.NewParser(config)
+	if err != nil {
+		return err
+	}
+
 	s := reflect.ValueOf(l).Elem()
 	for i := 0; i < s.NumField(); i++ {
 		f := s.Field(i)
@@ -152,13 +173,6 @@ func (l *LogParserPlugin) Start(acc telegraf.Accumulator) error {
 		return fmt.Errorf("logparser input plugin: no parser defined")
 	}
 
-	// compile log parser patterns:
-	for _, parser := range l.parsers {
-		if err := parser.Compile(); err != nil {
-			return err
-		}
-	}
-
 	l.wg.Add(1)
 	go l.parser()
 
@@ -251,8 +265,8 @@ func (l *LogParserPlugin) receiver(tailer *tail.Tail) {
 	}
 }
 
-// parser is launched as a goroutine to watch the l.lines channel.
-// when a line is available, parser parses it and adds the metric(s) to the
+// parse is launched as a goroutine to watch the l.lines channel.
+// when a line is available, parse parses it and adds the metric(s) to the
 // accumulator.
 func (l *LogParserPlugin) parser() {
 	defer l.wg.Done()
@@ -269,18 +283,17 @@ func (l *LogParserPlugin) parser() {
 				continue
 			}
 		}
-		for _, parser := range l.parsers {
-			m, err = parser.ParseLine(entry.line)
-			if err == nil {
-				if m != nil {
-					tags := m.Tags()
-					tags["path"] = entry.path
-					l.acc.AddFields(m.Name(), m.Fields(), tags, m.Time())
-				}
-			} else {
-				log.Println("E! Error parsing log line: " + err.Error())
+		m, err = l.GrokParser.ParseLine(entry.line)
+		if err == nil {
+			if m != nil {
+				tags := m.Tags()
+				tags["path"] = entry.path
+				l.acc.AddFields(l.MeasurementName, m.Fields(), tags, m.Time())
 			}
+		} else {
+			log.Println("E! Error parsing log line: " + err.Error())
 		}
+
 	}
 }