Skip to content

fix: parse quoted PostgreSQL string arrays #737

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

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

fix: parse quoted PostgreSQL string arrays #737

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
58 changes: 47 additions & 11 deletions events-processor/utils/string.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ import (
"encoding/json"
"fmt"
"strings"
"unicode"
)

type StringArray []string
Expand Down Expand Up @@ -52,22 +53,57 @@ func parsePostgresArray(s string) []string {
return []string{}
}

// Remove curly braces
s = strings.TrimPrefix(s, "{")
s = strings.TrimSuffix(s, "}")
if !strings.HasPrefix(s, "{") || !strings.HasSuffix(s, "}") {
Copy link
Copy Markdown
Contributor

@lovrocolic lovrocolic May 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For inputs without braces this changes behavior compared to the old code.

Old code would return two elements for hello,world but new logic would return one element.

Can you please explain if this was made on purpose?

Copy link
Copy Markdown
Contributor

@groyoh groyoh May 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Side note: I guess we're lacking tests for such cases.

return []string{strings.Trim(s, "\"")}
}

s = strings.TrimSuffix(strings.TrimPrefix(s, "{"), "}")
result := make([]string, 0)
var current strings.Builder
inQuotes := false
escaped := false
quoted := false
tokenStarted := false

// Split by comma and clean up quotes
parts := strings.Split(s, ",")
result := make([]string, 0, len(parts))
appendValue := func() {
value := current.String()
if !quoted {
value = strings.TrimSpace(value)
}
if quoted || value != "" {
result = append(result, value)
}
current.Reset()
quoted = false
tokenStarted = false
}

for _, part := range parts {
part = strings.TrimSpace(part)
part = strings.Trim(part, "\"")
if part != "" {
result = append(result, part)
for _, char := range s {
switch {
case escaped:
current.WriteRune(char)
escaped = false
tokenStarted = true
case char == '\\' && inQuotes:
escaped = true
case char == '"':
inQuotes = !inQuotes
quoted = true
tokenStarted = true
case char == ',' && !inQuotes:
appendValue()
case !inQuotes && quoted && unicode.IsSpace(char):
continue
case !inQuotes && !tokenStarted && unicode.IsSpace(char):
continue
default:
current.WriteRune(char)
tokenStarted = true
}
}

appendValue()

return result
}

Expand Down
12 changes: 12 additions & 0 deletions events-processor/utils/string_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,18 @@ func TestStringArray_Scan(t *testing.T) {
expected: StringArray{"plain string"},
wantErr: false,
},
{
name: "postgres array with quoted comma",
input: `{"value,1","value2"}`,
expected: StringArray{"value,1", "value2"},
wantErr: false,
},
{
name: "postgres array with empty string",
input: `{"","value2"}`,
expected: StringArray{"", "value2"},
wantErr: false,
},
}

for _, tt := range tests {
Expand Down