Add grok function

Closes #4140

docs/language/functions/grok.md

@@ -0,0 +1,44 @@
+### Function
+
+  **grok** — parse a string using a grok pattern
+
+### Synopsis
+
+```
+grok(pattern: string, s: string) -> any
+grok(extra: string, pattern: string, s: string) -> any
+```
+
+### Description
+
+The _grok_ function parses a string using a grok pattern and returns
+a record containing the parsed fields. The syntax for a grok pattern
+is `{%pattern:field_name}` where _pattern_ is a the name of the pattern
+to match text with and _field_name_ is resultant field name of the capture
+value.
+
+When provided with three arguments, the first argument, extra is a list
+of named patterns seperated by new lines in the format `PATTERN_NAME PATTERN`. 
+The named patterns can then be used in the grok pattern.
+
+#### Included Patterns
+
+The _grok_ function by default includes a set of builtin named patterns
+that can be referenced in any pattern. The included named patterns can be seen
+[here](https://raw.githubusercontent.com/brimdata/zed/main/pkg/grok/grok-patterns).
+
+### Examples
+
+Parsing a simple log line using the builtin named patterns:
+```mdtest-command
+echo '"2020-09-16T04:20:42.45+01:00 DEBUG This is a sample debug log message"' \
+  | zq -Z 'yield grok("%{TIMESTAMP_ISO8601:timestamp} %{LOGLEVEL:level} %{GREEDYDATA:message}", this)' -
+```
+=>
+```mdtest-output
+{
+    timestamp: "2020-09-16T04:20:42.45+01:00",
+    level: "DEBUG",
+    message: "This is a sample debug log message"
+}
+```

pkg/grok/gen.go

@@ -0,0 +1,58 @@
+//go:build ignore
+
+package main
+
+import (
+	"bufio"
+	_ "embed"
+	"os"
+	"regexp"
+	"strings"
+	"text/template"
+)
+
+//go:embed grok-patterns
+var grokPatterns string
+
+const baseTemplate = `// Code generated by gen.go; DO NOT EDIT.
+
+package grok
+
+func NewBase() Host {
+    h := New()
+    {{range .}}h.Must({{printf "%q" .Name}}, {{printf "%q" .Pattern}})
+    {{end}}
+    return h
+}
+`
+
+type namedPattern struct {
+	Name    string
+	Pattern string
+}
+
+func must(err error) {
+	if err != nil {
+		panic(err)
+	}
+}
+
+var lineRegexp = regexp.MustCompile(`^(\w+)\s+(.+)$`)
+
+func main() {
+	var patterns []namedPattern
+	scanner := bufio.NewScanner(strings.NewReader(grokPatterns))
+	for scanner.Scan() {
+		sub := lineRegexp.FindStringSubmatch(scanner.Text())
+		if len(sub) == 0 { // not match
+			continue
+		}
+		patterns = append(patterns, namedPattern{Name: sub[1], Pattern: sub[2]})
+	}
+	must(scanner.Err())
+	f, err := os.Create("base.go")
+	must(err)
+	defer f.Close()
+	t := template.Must(template.New("base").Parse(baseTemplate))
+	must(t.Execute(f, patterns))
+}

pkg/grok/grok-patterns

@@ -0,0 +1,98 @@
+# Adapted from https://github.com/vjeantet/grok/blob/master/patterns/grok-patterns
+USERNAME [a-zA-Z0-9._-]+
+USER %{USERNAME}
+INT (?:[+-]?(?:[0-9]+))
+BASE10NUM ([+-]?(?:[0-9]+(?:\.[0-9]+)?)|\.[0-9]+)
+NUMBER (?:%{BASE10NUM})
+BASE16NUM [+-]?(?:0x)?(?:[0-9A-Fa-f]+)
+BASE16FLOAT \b[+-]?(?:0x)?(?:(?:[0-9A-Fa-f]+(?:\.[0-9A-Fa-f]*)?)|(?:\.[0-9A-Fa-f]+))\b
+
+POSINT \b(?:[1-9][0-9]*)\b
+NONNEGINT \b(?:[0-9]+)\b
+WORD \b\w+\b
+NOTSPACE \S+
+SPACE \s*
+DATA .*?
+GREEDYDATA .*
+QUOTEDSTRING "([^"\\]*(\\.[^"\\]*)*)"|\'([^\'\\]*(\\.[^\'\\]*)*)\'
+UUID [A-Fa-f0-9]{8}-(?:[A-Fa-f0-9]{4}-){3}[A-Fa-f0-9]{12}
+
+# Networking
+CISCOMAC (?:(?:[A-Fa-f0-9]{4}\.){2}[A-Fa-f0-9]{4})
+WINDOWSMAC (?:(?:[A-Fa-f0-9]{2}-){5}[A-Fa-f0-9]{2})
+COMMONMAC (?:(?:[A-Fa-f0-9]{2}:){5}[A-Fa-f0-9]{2})
+MAC (?:%{CISCOMAC}|%{WINDOWSMAC}|%{COMMONMAC})
+IPV6 ((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?
+IPV4 (?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)
+IP (?:%{IPV6}|%{IPV4})
+HOSTNAME \b(?:[0-9A-Za-z][0-9A-Za-z-]{0,62})(?:\.(?:[0-9A-Za-z][0-9A-Za-z-]{0,62}))*(\.?|\b)
+HOST %{HOSTNAME}
+IPORHOST (?:%{HOSTNAME}|%{IP})
+HOSTPORT %{IPORHOST}:%{POSINT}
+
+# paths
+UNIXPATH (/[\w_%!$@:.,-]?/?)(\S+)?
+WINPATH ([A-Za-z]:|\\)(?:\\[^\\?*]*)+
+PATH (?:%{UNIXPATH}|%{WINPATH})
+TTY (?:/dev/(pts|tty([pq])?)(\w+)?/?(?:[0-9]+))
+
+URIPROTO [A-Za-z]+(\+[A-Za-z+]+)?
+URIHOST %{IPORHOST}(?::%{POSINT:port})?
+# uripath comes loosely from RFC1738, but mostly from what Firefox
+# doesn't turn into %XX
+URIPATH (?:/[A-Za-z0-9$.+!*'(){},~:;=@#%_\-]*)+
+#URIPARAM \?(?:[A-Za-z0-9]+(?:=(?:[^&]*))?(?:&(?:[A-Za-z0-9]+(?:=(?:[^&]*))?)?)*)?
+URIPARAM \?[A-Za-z0-9$.+!*'|(){},~@#%&/=:;_?\-\[\]]*
+URIPATHPARAM %{URIPATH}(?:%{URIPARAM})?
+URI %{URIPROTO}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST})?(?:%{URIPATHPARAM})?
+
+# Months: January, Feb, 3, 03, 12, December
+MONTH \b(?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?)\b
+MONTHNUM (?:0?[1-9]|1[0-2])
+MONTHDAY (?:(?:0[1-9])|(?:[12][0-9])|(?:3[01])|[1-9])
+
+# Days: Monday, Tue, Thu, etc...
+DAY (?:Mon(?:day)?|Tue(?:sday)?|Wed(?:nesday)?|Thu(?:rsday)?|Fri(?:day)?|Sat(?:urday)?|Sun(?:day)?)
+
+# Years?
+#YEAR (?>\d\d){1,2}
+#c
+YEAR (\d\d){1,2}
+
+HOUR (?:2[0123]|[01]?[0-9])
+MINUTE (?:[0-5][0-9])
+# '60' is a leap second in most time standards and thus is valid.
+SECOND (?:(?:[0-5][0-9]|60)(?:[:.,][0-9]+)?)
+#TIME (?!<[0-9])%{HOUR}:%{MINUTE}(?::%{SECOND})(?![0-9])
+#c
+TIME ([^0-9]?)%{HOUR}:%{MINUTE}(?::%{SECOND})([^0-9]?)
+# datestamp is YYYY/MM/DD-HH:MM:SS.UUUU (or something like it)
+DATE_US %{MONTHNUM}[/-]%{MONTHDAY}[/-]%{YEAR}
+DATE_EU %{MONTHDAY}[./-]%{MONTHNUM}[./-]%{YEAR}
+ISO8601_TIMEZONE (?:Z|[+-]%{HOUR}(?::?%{MINUTE}))
+ISO8601_SECOND (?:%{SECOND}|60)
+TIMESTAMP_ISO8601 %{YEAR}-%{MONTHNUM}-%{MONTHDAY}[T ]%{HOUR}:?%{MINUTE}(?::?%{SECOND})?%{ISO8601_TIMEZONE}?
+DATE %{DATE_US}|%{DATE_EU}
+DATESTAMP %{DATE}[- ]%{TIME}
+TZ (?:[PMCE][SD]T|UTC|GMT)
+DATESTAMP_RFC822 %{DAY} %{MONTH} %{MONTHDAY} %{YEAR} %{TIME} %{TZ}
+DATESTAMP_OTHER %{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{TZ} %{YEAR}
+
+# Syslog Dates: Month Day HH:MM:SS
+SYSLOGTIMESTAMP %{MONTH} +%{MONTHDAY} %{TIME}
+PROG (?:[\w._/%-]+)
+SYSLOGPROG %{PROG:program}(?:\[%{POSINT:pid}\])?
+SYSLOGHOST %{IPORHOST}
+SYSLOGFACILITY <%{NONNEGINT:facility}.%{NONNEGINT:priority}>
+HTTPDATE %{MONTHDAY}/%{MONTH}/%{YEAR}:%{TIME} %{INT}
+
+# Shortcuts
+QS %{QUOTEDSTRING}
+
+# Log formats
+SYSLOGBASE %{SYSLOGTIMESTAMP:timestamp} (?:%{SYSLOGFACILITY} )?%{SYSLOGHOST:logsource} %{SYSLOGPROG}:
+COMMONAPACHELOG %{IPORHOST:clientip} %{USER:ident} %{USER:auth} \[%{HTTPDATE:timestamp}\] "(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})" %{NUMBER:response} (?:%{NUMBER:bytes}|-)
+COMBINEDAPACHELOG %{COMMONAPACHELOG} %{QS:referrer} %{QS:agent}
+
+# Log Levels
+LOGLEVEL ([A-a]lert|ALERT|[T|t]race|TRACE|[D|d]ebug|DEBUG|[N|n]otice|NOTICE|[I|i]nfo|INFO|[W|w]arn?(?:ing)?|WARN?(?:ING)?|[E|e]rr?(?:or)?|ERR?(?:OR)?|[C|c]rit?(?:ical)?|CRIT?(?:ICAL)?|[F|f]atal|FATAL|[S|s]evere|SEVERE|EMERG(?:ENCY)?|[Ee]merg(?:ency)?)