Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixed influx data format parsing #254

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fixed influx data format parsing #254

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions cmd/tsbs_load_influx/scan.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,12 +5,13 @@ import (
"bytes"
"strings"

"github.com/timescale/tsbs/internal/utils"
"github.com/timescale/tsbs/pkg/data"
"github.com/timescale/tsbs/pkg/data/usecases/common"
"github.com/timescale/tsbs/pkg/targets"
)

const errNotThreeTuplesFmt = "parse error: line does not have 3 tuples, has %d"
const errNotThreeTuplesFmt = "parse error: line does not have 3 tuples, has %d -> %s"

var newLine = []byte("\n")

Expand Down Expand Up @@ -47,9 +48,9 @@ func (b *batch) Append(item data.LoadedPoint) {
b.rows++
// Each influx line is format "csv-tags csv-fields timestamp", so we split by space
// and then on the middle element, we split by comma to count number of fields added
args := strings.Split(thatStr, " ")
args := utils.SplitLine(thatStr, ' ')
if len(args) != 3 {
fatal(errNotThreeTuplesFmt, len(args))
fatal(errNotThreeTuplesFmt, len(args), thatStr)
return
}
b.metrics += uint64(len(strings.Split(args[1], ",")))
Expand Down
35 changes: 35 additions & 0 deletions internal/utils/parsing.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
package utils

func SplitLine(line string, delim rune) []string {
output := make([]string, 0, 3)
beginning := 0
quoting := false
escaping := false
for index, symbol := range line {
if symbol == '\\' {
escaping = !escaping
continue
}

if symbol == delim {
if !escaping && !quoting {
item := line[beginning:index]
output = append(output, string(item))
beginning = index + 1
}
} else if symbol == '"' {
if !escaping {
quoting = !quoting
}
}

escaping = false
}

if beginning < len(line) {
item := line[beginning:]
output = append(output, string(item))
}

return output
}
144 changes: 144 additions & 0 deletions internal/utils/parsing_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,144 @@
package utils

import (
"strings"
"testing"
)

func isEquals(left []string, right []string) bool {
if len(left) != len(right) {
return false
}
for i, value := range left {
if value != right[i] {
return false
}
}
return true
}

func formatStrings(values []string) string {
if len(values) == 0 {
return "[]"
} else {
return "[\"" + strings.Join(values, "\", \"") + "\"]"
}
}

func TestInfluxLineParsing(t *testing.T) {
cases := []struct {
desc string
input string
expected []string
}{
{
desc: "simple line",
input: "measurement,tag1_name=tag1_value,tag2_name=tag2_value field1_name=field1_value,field1_name=field2_value 1556813561098000000",
expected: []string{
"measurement,tag1_name=tag1_value,tag2_name=tag2_value",
"field1_name=field1_value,field1_name=field2_value",
"1556813561098000000",
},
},
{
desc: "line with single quoted tag",
input: "measurement,\"tag1 name=tag1_value,tag2_name=tag2 value\" field1_name=field1_value,field1_name=field2_value 1556813561098000000",
expected: []string{
"measurement,\"tag1 name=tag1_value,tag2_name=tag2 value\"",
"field1_name=field1_value,field1_name=field2_value",
"1556813561098000000",
},
},
{
desc: "line with multiple quoted tags",
input: "measurement,\"tag1 name\"=tag1_value,tag2_name=\"tag2 value\" field1_name=field1_value,field1_name=field2_value 1556813561098000000",
expected: []string{
"measurement,\"tag1 name\"=tag1_value,tag2_name=\"tag2 value\"",
"field1_name=field1_value,field1_name=field2_value",
"1556813561098000000",
},
},
{
desc: "line with single quoted field",
input: "measurement,tag1_name=tag1_value,tag2_name=tag2_value \"field1 name=field1_value,field1_name=field2 value\" 1556813561098000000",
expected: []string{
"measurement,tag1_name=tag1_value,tag2_name=tag2_value",
"\"field1 name=field1_value,field1_name=field2 value\"",
"1556813561098000000",
},
},
{
desc: "line with multiple quoted fields",
input: "measurement,tag1_name=tag1_value,tag2_name=tag2_value \"field1 name\"=field1_value,field1_name=\"field2 value\" 1556813561098000000",
expected: []string{
"measurement,tag1_name=tag1_value,tag2_name=tag2_value",
"\"field1 name\"=field1_value,field1_name=\"field2 value\"",
"1556813561098000000",
},
},
{
desc: "line with escaped quotas",
input: "measurement,tag1_name=tag1_value,tag2_name=\\\"tag2_value field1_name\\\"=field1_value,field1_name=field2_value 1556813561098000000",
expected: []string{
"measurement,tag1_name=tag1_value,tag2_name=\\\"tag2_value",
"field1_name\\\"=field1_value,field1_name=field2_value",
"1556813561098000000",
},
},
}

delim := ' '
for _, c := range cases {
t.Run(c.desc, func(t *testing.T) {
actual := SplitLine(c.input, delim)
if !isEquals(actual, c.expected) {
t.Errorf("%s: expected '%s', actual: '%s'", c.desc, formatStrings(c.expected), formatStrings(actual))
}
})
}
}

func TestInfluxFieldsParsing(t *testing.T) {
cases := []struct {
desc string
input string
expected []string
}{
{
desc: "simple line",
input: "measurement,tag1_name=tag1_value,tag2_name=tag2_value",
expected: []string{
"measurement",
"tag1_name=tag1_value",
"tag2_name=tag2_value",
},
},
{
desc: "line with quoted value with delimiter",
input: "measurement,tag1_name=\"tag1_value,tag2_name=tag2_value\"",
expected: []string{
"measurement",
"tag1_name=\"tag1_value,tag2_name=tag2_value\"",
},
},
{
desc: "line with quoted value without delimiter",
input: "measurement,tag1_name=\"tag1_value\",tag2_name=tag2_value",
expected: []string{
"measurement",
"tag1_name=\"tag1_value\"",
"tag2_name=tag2_value",
},
},
}

delim := ','
for _, c := range cases {
t.Run(c.desc, func(t *testing.T) {
actual := SplitLine(c.input, delim)
if !isEquals(actual, c.expected) {
t.Errorf("%s: expected '%s', actual: '%s'", c.desc, formatStrings(c.expected), formatStrings(actual))
}
})
}
}
3 changes: 2 additions & 1 deletion pkg/targets/timescaledb/process.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ import (
"sync"
"time"

"github.com/timescale/tsbs/internal/utils"
"github.com/timescale/tsbs/pkg/targets"

"github.com/jackc/pgx/v4"
Expand Down Expand Up @@ -147,7 +148,7 @@ func (p *processor) splitTagsAndMetrics(rows []*insertData, dataCols int) ([][]s
json = subsystemTagsToJSON(strings.Split(tags[commonTagsLen], ","))
}

metrics := strings.Split(data.fields, ",")
metrics := utils.SplitLine(data.fields, ',')
numMetrics += uint64(len(metrics) - 1) // 1 field is timestamp

timeInt, err := strconv.ParseInt(metrics[0], 10, 64)
Expand Down