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.

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

[7.17](backport #32767) allow for json/ndjson content type with charset #32834

Merged
merged 2 commits into from
Aug 25, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions CHANGELOG.next.asciidoc
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ https://github.com/elastic/beats/compare/v7.0.0-alpha2...master[Check the HEAD d
*Filebeat*

- Fix file.path field in cloudtrail fileset to use json.digestS3Object. {pull}32759[32759]
- Fix not parsing as json when `json` and `ndjson` content types have charset information in `aws-s3` input {pull}32767[32767]

*Heartbeat*

Expand Down
19 changes: 12 additions & 7 deletions x-pack/filebeat/input/awss3/input_integration_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ import (
"io/ioutil"
"os"
"path/filepath"
"strings"
"testing"
"time"

Expand Down Expand Up @@ -86,7 +87,6 @@ file_selectors:
-
regex: 'events-array.json$'
expand_event_list_from_field: Events
content_type: application/json
include_s3_metadata:
- last-modified
- x-amz-version-id
Expand All @@ -95,7 +95,6 @@ file_selectors:
- Content-Type
-
regex: '\.(?:nd)?json(\.gz)?$'
content_type: application/json
-
regex: 'multiline.txt$'
parsers:
Expand All @@ -115,7 +114,6 @@ file_selectors:
-
regex: 'events-array.json$'
expand_event_list_from_field: Events
content_type: application/json
include_s3_metadata:
- last-modified
- x-amz-version-id
Expand All @@ -124,7 +122,6 @@ file_selectors:
- Content-Type
-
regex: '\.(?:nd)?json(\.gz)?$'
content_type: application/json
-
regex: 'multiline.txt$'
parsers:
Expand Down Expand Up @@ -324,11 +321,19 @@ func uploadS3TestFiles(t *testing.T, region, bucket string, filenames ...string)
t.Fatalf("Failed to open file %q, %v", filename, err)
}

contentType := ""
if strings.HasSuffix(filename, "ndjson") || strings.HasSuffix(filename, "ndjson.gz") {
contentType = contentTypeNDJSON + "; charset=UTF-8"
} else if strings.HasSuffix(filename, "json") || strings.HasSuffix(filename, "json.gz") {
contentType = contentTypeJSON + "; charset=UTF-8"
}

// Upload the file to S3.
result, err := uploader.Upload(&s3manager.UploadInput{
Bucket: aws.String(bucket),
Key: aws.String(filepath.Base(filename)),
Body: bytes.NewReader(data),
Bucket: aws.String(bucket),
Key: aws.String(filepath.Base(filename)),
Body: bytes.NewReader(data),
ContentType: aws.String(contentType),
})
if err != nil {
t.Fatalf("Failed to upload file %q: %v", filename, err)
Expand Down
2 changes: 1 addition & 1 deletion x-pack/filebeat/input/awss3/s3_objects.go
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ func (p *s3ObjectProcessor) ProcessS3Object() error {

// Process object content stream.
switch {
case contentType == contentTypeJSON || contentType == contentTypeNDJSON:
case strings.HasPrefix(contentType, contentTypeJSON) || strings.HasPrefix(contentType, contentTypeNDJSON):
err = p.readJSON(reader)
default:
err = p.readFile(reader)
Expand Down