vendor: update github.com/VictoriaMetrics/metricsql from v0.50.0 to v0.51.0

Updates https://github.com/VictoriaMetrics/metricsql/pull/7
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3589

app/vmselect/promql/exec_test.go

@@ -7367,7 +7367,7 @@ func TestExecSuccess(t *testing.T) {
 	})
 	t.Run(`rollup_scrape_interval()`, func(t *testing.T) {
 		t.Parallel()
-		q := `sort_by_label(rollup_scrape_interval(1[5m:10s]), "rollup")`
+		q := `sort_by_label(rollup_scrape_interval(1[5M:10s]), "rollup")`
 		r1 := netstorage.Result{
 			MetricName: metricNameExpected,
 			Values:     []float64{10, 10, 10, 10, 10, 10},

docs/CHANGELOG.md

@@ -18,6 +18,7 @@ The following tip changes can be tested by building VictoriaMetrics components f
 * FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent.html): add support for aggregation of incoming [samples](https://docs.victoriametrics.com/keyConcepts.html#raw-samples) by time and by labels. See [these docs](https://docs.victoriametrics.com/stream-aggregation.html) and [this feature request](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3460).
 * FEATURE: [vmui](https://docs.victoriametrics.com/#vmui): add ability to explore metrics exported by a particular `job` / `instance`. See [these docs](https://docs.victoriametrics.com/#metrics-explorer) and [this feature request](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3386).
 * FEATURE: allow passing partial `RFC3339` date/time to `time`, `start` and `end` query args at [querying APIs](https://docs.victoriametrics.com/#prometheus-querying-api-usage) and [export APIs](https://docs.victoriametrics.com/#how-to-export-time-series). For example, `2022` is equivalent to `2022-01-01T00:00:00Z`, while `2022-01-30T14` is equivalent to `2022-01-30T14:00:00Z`. See [these docs](https://docs.victoriametrics.com/#timestamp-formats).
+* FEATURE: [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html): allow using unicode letters in identifiers. For example, `температура{город="Киев"}` is a valid MetricsQL expression now. Previously every non-ascii letters should be escaped with `\` char when used inside MetricsQL expression: `\т\е\м\п\е\р\а\т\у\р\а{\г\о\р\о\д="Киев"}`. Now both expressions are equivalent. Thanks to @hzwwww for the [pull request](https://github.com/VictoriaMetrics/metricsql/pull/7).
 * FEATURE: [relabeling](https://docs.victoriametrics.com/vmagent.html#relabeling): add support for `keepequal` and `dropequal` relabeling actions, which are supported by Prometheus starting from [v2.41.0](https://github.com/prometheus/prometheus/releases/tag/v2.41.0). These relabeling actions are almost identical to `keep_if_equal` and `drop_if_equal` relabeling actions supported by VictoriaMetrics since `v1.38.0` - see [these docs](https://docs.victoriametrics.com/vmagent.html#relabeling-enhancements) - so it is recommended sticking to `keep_if_equal` and `drop_if_equal` actions instead of switching to `keepequal` and `dropequal`.
 * FEATURE: [csvimport](https://docs.victoriametrics.com/#how-to-import-csv-data): support empty values for imported metrics. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3540).
 * FEATURE: [vmalert](httpпоs://docs.victoriametrics.com/vmalert.html): allow configuring the default number of stored rule's update states in memory via global `-rule.updateEntriesLimit` command-line flag or per-rule via rule's `update_entries_limit` configuration param. See [these docs](https://docs.victoriametrics.com/vmalert.html#rules) and [this pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/3556).
@@ -25,6 +26,7 @@ The following tip changes can be tested by building VictoriaMetrics components f
 * BUGFIX: [vmui](https://docs.victoriametrics.com/#vmui): properly update the `step` value in url after the `step` input field has been manually changed. This allows preserving the proper `step` when copy-n-pasting the url to another instance of web browser. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3513).
 * BUGFIX: [vmui](https://docs.victoriametrics.com/#vmui): properly update tooltip when quickly hovering multiple lines on the graph. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3530).
 * BUGFIX: properly parse floating-point numbers without integer or fractional parts such as `.123` and `20.` during [data import](https://docs.victoriametrics.com/#how-to-import-time-series-data). See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3544).
+* BUGFIX: [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html): properly parse durations with uppercase suffixes such as `10S`, `5MS`, `1W`, etc. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3589).
 
 
 ## [v1.85.3](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.85.3)

docs/MetricsQL.md

@@ -77,9 +77,12 @@ The list of MetricsQL features:
 * Trailing commas on all the lists are allowed - label filters, function args and with expressions.
   For instance, the following queries are valid: `m{foo="bar",}`, `f(a, b,)`, `WITH (x=y,) x`.
   This simplifies maintenance of multi-line queries.
-* Metric names and metric labels may contain escaped chars. For instance, `foo\-bar{baz\=aa="b"}` is valid expression.
+* Metric names and label names may contain any unicode letter. For example `температура{город="Киев"}` is a value MetricsQL expression.
+* Metric names and labels names may contain escaped chars. For example, `foo\-bar{baz\=aa="b"}` is valid expression.
   It returns time series with name `foo-bar` containing label `baz=aa` with value `b`.
-  Additionally, `\xXX` escape sequence is supported, where `XX` is hexadecimal representation of escaped char.
+  Additionally, the following escape sequences are supported:
+  - `\xXX`, where `XX` is hexadecimal representation of the escaped ascii char.
+  - `\uXXXX`, where `XXXX` is a hexadecimal representation of the escaped unicode char.
 * Aggregate functions support optional `limit N` suffix in order to limit the number of output series.
   For example, `sum(x) by (y) limit 3` limits the number of output time series after the aggregation to 3.
   All the other time series are dropped.

go.mod

@@ -12,7 +12,7 @@ require (
 	// like https://github.com/valyala/fasthttp/commit/996610f021ff45fdc98c2ce7884d5fa4e7f9199b
 	github.com/VictoriaMetrics/fasthttp v1.1.0
 	github.com/VictoriaMetrics/metrics v1.23.0
-	github.com/VictoriaMetrics/metricsql v0.50.0
+	github.com/VictoriaMetrics/metricsql v0.51.1
 	github.com/aws/aws-sdk-go-v2 v1.17.3
 	github.com/aws/aws-sdk-go-v2/config v1.18.7
 	github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.11.46

go.sum

@@ -69,8 +69,8 @@ github.com/VictoriaMetrics/fasthttp v1.1.0/go.mod h1:/7DMcogqd+aaD3G3Hg5kFgoFwlR
 github.com/VictoriaMetrics/metrics v1.18.1/go.mod h1:ArjwVz7WpgpegX/JpB0zpNF2h2232kErkEnzH1sxMmA=
 github.com/VictoriaMetrics/metrics v1.23.0 h1:WzfqyzCaxUZip+OBbg1+lV33WChDSu4ssYII3nxtpeA=
 github.com/VictoriaMetrics/metrics v1.23.0/go.mod h1:rAr/llLpEnAdTehiNlUxKgnjcOuROSzpw0GvjpEbvFc=
-github.com/VictoriaMetrics/metricsql v0.50.0 h1:MCBhjn1qlfMqPGP6HiR9JgmEw7oTRGm/O8YwSeoaI1E=
-github.com/VictoriaMetrics/metricsql v0.50.0/go.mod h1:6pP1ZeLVJHqJrHlF6Ij3gmpQIznSsgktEcZgsAWYel0=
+github.com/VictoriaMetrics/metricsql v0.51.1 h1:gmh3ZGCDrqUTdhUrr87eJOXMOputDYs1PtLwTfySTsI=
+github.com/VictoriaMetrics/metricsql v0.51.1/go.mod h1:6pP1ZeLVJHqJrHlF6Ij3gmpQIznSsgktEcZgsAWYel0=
 github.com/VividCortex/ewma v1.1.1/go.mod h1:2Tkkvm3sRDVXaiyucHiACn4cqf7DpdyLvmxzcbUokwA=
 github.com/VividCortex/ewma v1.2.0 h1:f58SaIzcDXrSy3kWaHNvuJgJ3Nmz59Zji6XoJR/q1ow=
 github.com/VividCortex/ewma v1.2.0/go.mod h1:nz4BbCtbLyFDeC9SUHbtcT5644juEuWfUAUnGx7j5l4=

vendor/github.com/VictoriaMetrics/metricsql/lexer.go

@@ -331,19 +331,22 @@ func scanNumMultiplier(s string) int {
 func scanIdent(s string) string {
 	i := 0
 	for i < len(s) {
-		if isIdentChar(s[i]) {
-			i++
+		r, size := utf8.DecodeRuneInString(s[i:])
+		if i == 0 && isFirstIdentChar(r) || i > 0 && isIdentChar(r) {
+			i += size
 			continue
 		}
-		if s[i] != '\\' {
+		if r != '\\' {
 			break
 		}
-		i++
-
-		// Do not verify the next char, since it is escaped.
-		// The next char may be encoded as multi-byte UTF8 sequence. See https://en.wikipedia.org/wiki/UTF-8#Encoding
-		_, size := utf8.DecodeRuneInString(s[i:])
 		i += size
+		r, n := decodeEscapeSequence(s[i:])
+		if r == utf8.RuneError {
+			// Invalid escape sequence
+			i -= size
+			break
+		}
+		i += n
 	}
 	if i == 0 {
 		panic("BUG: scanIdent couldn't find a single ident char; make sure isIdentPrefix called before scanIdent")
@@ -360,23 +363,12 @@ func unescapeIdent(s string) string {
 	for {
 		dst = append(dst, s[:n]...)
 		s = s[n+1:]
-		if len(s) == 0 {
-			return string(dst)
-		}
-		if s[0] == 'x' && len(s) >= 3 {
-			h1 := fromHex(s[1])
-			h2 := fromHex(s[2])
-			if h1 >= 0 && h2 >= 0 {
-				dst = append(dst, byte((h1<<4)|h2))
-				s = s[3:]
-			} else {
-				dst = append(dst, s[0])
-				s = s[1:]
-			}
+		r, size := decodeEscapeSequence(s)
+		if r == utf8.RuneError {
+			// Cannot decode escape sequence. Put it in the output as is
+			dst = append(dst, '\\')
 		} else {
-			// UTF8 char. See https://en.wikipedia.org/wiki/UTF-8#Encoding
-			_, size := utf8.DecodeRuneInString(s)
-			dst = append(dst, s[:size]...)
+			dst = utf8.AppendRune(dst, r)
 			s = s[size:]
 		}
 		n = strings.IndexByte(s, '\\')
@@ -387,49 +379,16 @@ func unescapeIdent(s string) string {
 	}
 }
 
-func fromHex(ch byte) int {
-	if ch >= '0' && ch <= '9' {
-		return int(ch - '0')
-	}
-	if ch >= 'a' && ch <= 'f' {
-		return int((ch - 'a') + 10)
-	}
-	if ch >= 'A' && ch <= 'F' {
-		return int((ch - 'A') + 10)
-	}
-	return -1
-}
-
-func toHex(n byte) byte {
-	if n < 10 {
-		return '0' + n
-	}
-	return 'a' + (n - 10)
-}
-
 func appendEscapedIdent(dst []byte, s string) []byte {
-	for i := 0; i < len(s); i++ {
-		ch := s[i]
-		if isIdentChar(ch) {
-			if i == 0 && !isFirstIdentChar(ch) {
-				// hex-encode the first char
-				dst = append(dst, '\\', 'x', toHex(ch>>4), toHex(ch&0xf))
-			} else {
-				dst = append(dst, ch)
-			}
-			continue
-		}
-
-		// escape ch
-		dst = append(dst, '\\')
+	i := 0
+	for i < len(s) {
 		r, size := utf8.DecodeRuneInString(s[i:])
-		if r != utf8.RuneError && unicode.IsPrint(r) {
-			dst = append(dst, s[i:i+size]...)
-			i += size - 1
+		if i == 0 && isFirstIdentChar(r) || i > 0 && isIdentChar(r) {
+			dst = utf8.AppendRune(dst, r)
 		} else {
-			// hex-encode non-printable chars
-			dst = append(dst, 'x', toHex(ch>>4), toHex(ch&0xf))
+			dst = appendEscapeSequence(dst, r)
 		}
+		i += size
 	}
 	return dst
 }
@@ -597,6 +556,7 @@ func DurationValue(s string, step int64) (int64, error) {
 }
 
 func parseSingleDuration(s string, step int64) (float64, error) {
+	s = strings.ToLower(s)
 	numPart := s[:len(s)-1]
 	if strings.HasSuffix(numPart, "m") {
 		// Duration in ms
@@ -656,6 +616,7 @@ func scanSingleDuration(s string, canBeNegative bool) int {
 	if len(s) == 0 {
 		return -1
 	}
+	s = strings.ToLower(s)
 	i := 0
 	if s[0] == '-' && canBeNegative {
 		i++
@@ -703,25 +664,26 @@ func isIdentPrefix(s string) bool {
 	if len(s) == 0 {
 		return false
 	}
-	if s[0] == '\\' {
-		// Assume this is an escape char for the next char.
-		return true
+	r, size := utf8.DecodeRuneInString(s)
+	if r == '\\' {
+		r, _ = decodeEscapeSequence(s[size:])
+		return r != utf8.RuneError
 	}
-	return isFirstIdentChar(s[0])
+	return isFirstIdentChar(r)
 }
 
-func isFirstIdentChar(ch byte) bool {
-	if ch >= 'a' && ch <= 'z' || ch >= 'A' && ch <= 'Z' {
+func isFirstIdentChar(r rune) bool {
+	if unicode.IsLetter(r) {
 		return true
 	}
-	return ch == '_' || ch == ':'
+	return r == '_' || r == ':'
 }
 
-func isIdentChar(ch byte) bool {
-	if isFirstIdentChar(ch) {
+func isIdentChar(r rune) bool {
+	if isFirstIdentChar(r) {
 		return true
 	}
-	return isDecimalChar(ch) || ch == '.'
+	return r < 256 && isDecimalChar(byte(r)) || r == '.'
 }
 
 func isSpaceChar(ch byte) bool {
@@ -732,3 +694,67 @@ func isSpaceChar(ch byte) bool {
 		return false
 	}
 }
+
+func appendEscapeSequence(dst []byte, r rune) []byte {
+	dst = append(dst, '\\')
+	if unicode.IsPrint(r) {
+		return utf8.AppendRune(dst, r)
+	}
+	// hex-encode non-printable chars
+	if r < 256 {
+		return append(dst, 'x', toHex(byte(r>>4)), toHex(byte(r&0xf)))
+	}
+	return append(dst, 'u', toHex(byte(r>>12)), toHex(byte((r>>8)&0xf)), toHex(byte(r>>4)), toHex(byte(r&0xf)))
+}
+
+func decodeEscapeSequence(s string) (rune, int) {
+	if strings.HasPrefix(s, "x") || strings.HasPrefix(s, "X") {
+		if len(s) >= 3 {
+			h1 := fromHex(s[1])
+			h2 := fromHex(s[2])
+			if h1 >= 0 && h2 >= 0 {
+				r := rune((h1 << 4) | h2)
+				return r, 3
+			}
+		}
+		return utf8.RuneError, 0
+	}
+	if strings.HasPrefix(s, "u") || strings.HasPrefix(s, "U") {
+		if len(s) >= 5 {
+			h1 := fromHex(s[1])
+			h2 := fromHex(s[2])
+			h3 := fromHex(s[3])
+			h4 := fromHex(s[4])
+			if h1 >= 0 && h2 >= 0 && h3 >= 0 && h4 >= 0 {
+				return rune((h1 << 12) | (h2 << 8) | (h3 << 4) | h4), 5
+			}
+		}
+		return utf8.RuneError, 0
+	}
+	r, size := utf8.DecodeRuneInString(s)
+	if unicode.IsPrint(r) {
+		return r, size
+	}
+	// Improperly escaped non-printable char
+	return utf8.RuneError, 0
+}
+
+func fromHex(ch byte) int {
+	if ch >= '0' && ch <= '9' {
+		return int(ch - '0')
+	}
+	if ch >= 'a' && ch <= 'f' {
+		return int((ch - 'a') + 10)
+	}
+	if ch >= 'A' && ch <= 'F' {
+		return int((ch - 'A') + 10)
+	}
+	return -1
+}
+
+func toHex(n byte) byte {
+	if n < 10 {
+		return '0' + n
+	}
+	return 'a' + (n - 10)
+}

vendor/modules.txt

@@ -70,7 +70,7 @@ github.com/VictoriaMetrics/fasthttp/stackless
 # github.com/VictoriaMetrics/metrics v1.23.0
 ## explicit; go 1.15
 github.com/VictoriaMetrics/metrics
-# github.com/VictoriaMetrics/metricsql v0.50.0
+# github.com/VictoriaMetrics/metricsql v0.51.1
 ## explicit; go 1.13
 github.com/VictoriaMetrics/metricsql
 github.com/VictoriaMetrics/metricsql/binaryop