prometheus/model/textparse/promlex.l.go
Owen Williams a28d7865ad UTF-8: Add support for parsing UTF8 metric and label names
This adds support for the new grammar of `{"metric_name", "l1"="val"}` to promql and some of the exposition formats.
This grammar will also be valid for non-UTF-8 names.
UTF-8 names will not be considered valid unless model.NameValidationScheme is changed.

This does not update the go expfmt parser in text_parse.go, which will be addressed by https://github.com/prometheus/common/issues/554/.

Part of https://github.com/prometheus/prometheus/issues/13095

Signed-off-by: Owen Williams <owen.williams@grafana.com>
2024-02-15 14:34:37 -05:00

657 lines
9.9 KiB
Go

// Code generated by golex. DO NOT EDIT.
// Copyright 2017 The Prometheus Authors
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package textparse
import (
"fmt"
)
const (
sInit = iota
sComment
sMeta1
sMeta2
sLabels
sLValue
sValue
sTimestamp
sExemplar
sEValue
sETimestamp
)
// Lex is called by the parser generated by "go tool yacc" to obtain each
// token. The method is opened before the matching rules block and closed at
// the end of the file.
func (l *promlexer) Lex() token {
if l.i >= len(l.b) {
return tEOF
}
c := l.b[l.i]
l.start = l.i
yystate0:
switch yyt := l.state; yyt {
default:
panic(fmt.Errorf(`invalid start condition %d`, yyt))
case 0: // start condition: INITIAL
goto yystart1
case 1: // start condition: sComment
goto yystart9
case 2: // start condition: sMeta1
goto yystart20
case 3: // start condition: sMeta2
goto yystart25
case 4: // start condition: sLabels
goto yystart28
case 5: // start condition: sLValue
goto yystart36
case 6: // start condition: sValue
goto yystart40
case 7: // start condition: sTimestamp
goto yystart43
}
yystate1:
c = l.next()
yystart1:
switch {
default:
goto yyabort
case c == '#':
goto yystate5
case c == ':' || c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate7
case c == '\n':
goto yystate4
case c == '\t' || c == ' ':
goto yystate3
case c == '\x00':
goto yystate2
case c == '{':
goto yystate8
}
yystate2:
c = l.next()
goto yyrule1
yystate3:
c = l.next()
switch {
default:
goto yyrule3
case c == '\t' || c == ' ':
goto yystate3
}
yystate4:
c = l.next()
goto yyrule2
yystate5:
c = l.next()
switch {
default:
goto yyrule5
case c == '\t' || c == ' ':
goto yystate6
}
yystate6:
c = l.next()
switch {
default:
goto yyrule4
case c == '\t' || c == ' ':
goto yystate6
}
yystate7:
c = l.next()
switch {
default:
goto yyrule11
case c >= '0' && c <= ':' || c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate7
}
yystate8:
c = l.next()
goto yyrule13
yystate9:
c = l.next()
yystart9:
switch {
default:
goto yyabort
case c == 'H':
goto yystate10
case c == 'T':
goto yystate15
case c == '\t' || c == ' ':
goto yystate3
}
yystate10:
c = l.next()
switch {
default:
goto yyabort
case c == 'E':
goto yystate11
}
yystate11:
c = l.next()
switch {
default:
goto yyabort
case c == 'L':
goto yystate12
}
yystate12:
c = l.next()
switch {
default:
goto yyabort
case c == 'P':
goto yystate13
}
yystate13:
c = l.next()
switch {
default:
goto yyabort
case c == '\t' || c == ' ':
goto yystate14
}
yystate14:
c = l.next()
switch {
default:
goto yyrule6
case c == '\t' || c == ' ':
goto yystate14
}
yystate15:
c = l.next()
switch {
default:
goto yyabort
case c == 'Y':
goto yystate16
}
yystate16:
c = l.next()
switch {
default:
goto yyabort
case c == 'P':
goto yystate17
}
yystate17:
c = l.next()
switch {
default:
goto yyabort
case c == 'E':
goto yystate18
}
yystate18:
c = l.next()
switch {
default:
goto yyabort
case c == '\t' || c == ' ':
goto yystate19
}
yystate19:
c = l.next()
switch {
default:
goto yyrule7
case c == '\t' || c == ' ':
goto yystate19
}
yystate20:
c = l.next()
yystart20:
switch {
default:
goto yyabort
case c == '"':
goto yystate21
case c == ':' || c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate24
case c == '\t' || c == ' ':
goto yystate3
}
yystate21:
c = l.next()
switch {
default:
goto yyabort
case c == '"':
goto yystate22
case c == '\\':
goto yystate23
case c >= '\x01' && c <= '!' || c >= '#' && c <= '[' || c >= ']' && c <= 'ÿ':
goto yystate21
}
yystate22:
c = l.next()
goto yyrule8
yystate23:
c = l.next()
switch {
default:
goto yyabort
case c >= '\x01' && c <= '\t' || c >= '\v' && c <= 'ÿ':
goto yystate21
}
yystate24:
c = l.next()
switch {
default:
goto yyrule9
case c >= '0' && c <= ':' || c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate24
}
yystate25:
c = l.next()
yystart25:
switch {
default:
goto yyrule10
case c == '\t' || c == ' ':
goto yystate27
case c >= '\x01' && c <= '\b' || c >= '\v' && c <= '\x1f' || c >= '!' && c <= 'ÿ':
goto yystate26
}
yystate26:
c = l.next()
switch {
default:
goto yyrule10
case c >= '\x01' && c <= '\t' || c >= '\v' && c <= 'ÿ':
goto yystate26
}
yystate27:
c = l.next()
switch {
default:
goto yyrule3
case c == '\t' || c == ' ':
goto yystate27
case c >= '\x01' && c <= '\b' || c >= '\v' && c <= '\x1f' || c >= '!' && c <= 'ÿ':
goto yystate26
}
yystate28:
c = l.next()
yystart28:
switch {
default:
goto yyabort
case c == '"':
goto yystate29
case c == ',':
goto yystate32
case c == '=':
goto yystate33
case c == '\t' || c == ' ':
goto yystate3
case c == '}':
goto yystate35
case c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate34
}
yystate29:
c = l.next()
switch {
default:
goto yyabort
case c == '"':
goto yystate30
case c == '\\':
goto yystate31
case c >= '\x01' && c <= '!' || c >= '#' && c <= '[' || c >= ']' && c <= 'ÿ':
goto yystate29
}
yystate30:
c = l.next()
goto yyrule15
yystate31:
c = l.next()
switch {
default:
goto yyabort
case c >= '\x01' && c <= '\t' || c >= '\v' && c <= 'ÿ':
goto yystate29
}
yystate32:
c = l.next()
goto yyrule18
yystate33:
c = l.next()
goto yyrule17
yystate34:
c = l.next()
switch {
default:
goto yyrule14
case c >= '0' && c <= '9' || c >= 'A' && c <= 'Z' || c == '_' || c >= 'a' && c <= 'z':
goto yystate34
}
yystate35:
c = l.next()
goto yyrule16
yystate36:
c = l.next()
yystart36:
switch {
default:
goto yyabort
case c == '"':
goto yystate37
case c == '\t' || c == ' ':
goto yystate3
}
yystate37:
c = l.next()
switch {
default:
goto yyabort
case c == '"':
goto yystate38
case c == '\\':
goto yystate39
case c >= '\x01' && c <= '!' || c >= '#' && c <= '[' || c >= ']' && c <= 'ÿ':
goto yystate37
}
yystate38:
c = l.next()
goto yyrule19
yystate39:
c = l.next()
switch {
default:
goto yyabort
case c >= '\x01' && c <= '\t' || c >= '\v' && c <= 'ÿ':
goto yystate37
}
yystate40:
c = l.next()
yystart40:
switch {
default:
goto yyabort
case c == '\t' || c == ' ':
goto yystate3
case c == '{':
goto yystate42
case c >= '\x01' && c <= '\b' || c >= '\v' && c <= '\x1f' || c >= '!' && c <= 'z' || c >= '|' && c <= 'ÿ':
goto yystate41
}
yystate41:
c = l.next()
switch {
default:
goto yyrule20
case c >= '\x01' && c <= '\b' || c >= '\v' && c <= '\x1f' || c >= '!' && c <= 'z' || c >= '|' && c <= 'ÿ':
goto yystate41
}
yystate42:
c = l.next()
goto yyrule12
yystate43:
c = l.next()
yystart43:
switch {
default:
goto yyabort
case c == '\n':
goto yystate44
case c == '\t' || c == ' ':
goto yystate3
case c >= '0' && c <= '9':
goto yystate45
}
yystate44:
c = l.next()
goto yyrule22
yystate45:
c = l.next()
switch {
default:
goto yyrule21
case c >= '0' && c <= '9':
goto yystate45
}
yyrule1: // \0
{
return tEOF
}
yyrule2: // \n
{
l.state = sInit
return tLinebreak
goto yystate0
}
yyrule3: // [ \t]+
{
return tWhitespace
}
yyrule4: // #[ \t]+
{
l.state = sComment
goto yystate0
}
yyrule5: // #
{
return l.consumeComment()
}
yyrule6: // HELP[\t ]+
{
l.state = sMeta1
return tHelp
goto yystate0
}
yyrule7: // TYPE[\t ]+
{
l.state = sMeta1
return tType
goto yystate0
}
yyrule8: // \"(\\.|[^\\"])*\"
{
l.state = sMeta2
return tMName
goto yystate0
}
yyrule9: // {M}({M}|{D})*
{
l.state = sMeta2
return tMName
goto yystate0
}
yyrule10: // {C}*
{
l.state = sInit
return tText
goto yystate0
}
yyrule11: // {M}({M}|{D})*
{
l.state = sValue
return tMName
goto yystate0
}
yyrule12: // \{
{
l.state = sLabels
return tBraceOpen
goto yystate0
}
yyrule13: // \{
{
l.state = sLabels
return tBraceOpen
goto yystate0
}
yyrule14: // {L}({L}|{D})*
{
return tLName
}
yyrule15: // \"(\\.|[^\\"])*\"
{
l.state = sLabels
return tQString
goto yystate0
}
yyrule16: // \}
{
l.state = sValue
return tBraceClose
goto yystate0
}
yyrule17: // =
{
l.state = sLValue
return tEqual
goto yystate0
}
yyrule18: // ,
{
return tComma
}
yyrule19: // \"(\\.|[^\\"])*\"
{
l.state = sLabels
return tLValue
goto yystate0
}
yyrule20: // [^{ \t\n]+
{
l.state = sTimestamp
return tValue
goto yystate0
}
yyrule21: // {D}+
{
return tTimestamp
}
yyrule22: // \n
if true { // avoid go vet determining the below panic will not be reached
l.state = sInit
return tLinebreak
goto yystate0
}
panic("unreachable")
yyabort: // no lexem recognized
// silence unused label errors for build and satisfy go vet reachability analysis
{
if false {
goto yyabort
}
if false {
goto yystate0
}
if false {
goto yystate1
}
if false {
goto yystate9
}
if false {
goto yystate20
}
if false {
goto yystate25
}
if false {
goto yystate28
}
if false {
goto yystate36
}
if false {
goto yystate40
}
if false {
goto yystate43
}
}
// Workaround to gobble up comments that started with a HELP or TYPE
// prefix. We just consume all characters until we reach a newline.
// This saves us from adding disproportionate complexity to the parser.
if l.state == sComment {
return l.consumeComment()
}
return tInvalid
}
func (l *promlexer) consumeComment() token {
for c := l.cur(); ; c = l.next() {
switch c {
case 0:
return tEOF
case '\n':
l.state = sInit
return tComment
}
}
}