Skip to content

fix(druid): sniff HTML error body before JSON parse (second leg) #20152

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
shoemoney wants to merge 1 commit into
base: master
Choose a base branch
from
+63 −0
Open

fix(druid): sniff HTML error body before JSON parse (second leg) #20152

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
63 changes: 63 additions & 0 deletions server/src/main/java/org/apache/druid/client/DirectDruidClient.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@
import org.apache.druid.java.util.http.client.response.StatusResponseHolder;
import org.apache.druid.query.Queries;
import org.apache.druid.query.Query;
import org.apache.druid.query.QueryCapacityExceededException;
import org.apache.druid.query.QueryContext;
import org.apache.druid.query.QueryMetrics;
import org.apache.druid.query.QueryPlus;
Expand Down Expand Up @@ -243,6 +244,68 @@ public ClientResponse<InputStream> handleResponse(HttpResponse response, Traffic
{
trafficCopRef.set(trafficCop);
checkQueryTimeout();
// Handle 429/503 HTML before JSON parse to avoid JsonParseException 0x3c ('<')
final int statusCode = response.getStatus().getCode();
final String contentType = response.headers().get(HttpHeaders.Names.CONTENT_TYPE);
final ChannelBuffer contentBuffer = response.getContent();
boolean isHtmlContentType = contentType != null && StringUtils.toLowerCase(contentType).contains("text/html");
boolean isHtmlBody = false;
if (contentBuffer.readableBytes() > 0) {
int readerIndex = contentBuffer.readerIndex();
int readable = contentBuffer.readableBytes();
for (int i = 0; i < readable; i++) {
byte b = contentBuffer.getByte(readerIndex + i);
if (b == ' ' || b == '\n' || b == '\r' || b == '\t') {
continue;
}
if (b == '<') {
isHtmlBody = true;
} else if (b != '{' && b != '[') {
// Not JSON start, but only treat '<' as HTML indicator
}
break;
}
}
if (statusCode == 429 || statusCode == 503) {
String msg = StringUtils.format(
"Query[%s] url[%s] failed with status[%s] [%s]",
query.getId(),
url,
statusCode,
response.getStatus().getReasonPhrase()
);
if (contentBuffer.readableBytes() > 0) {
int len = Math.min(contentBuffer.readableBytes(), 512);
byte[] previewBytes = new byte[len];
contentBuffer.getBytes(contentBuffer.readerIndex(), previewBytes);
String preview = StringUtils.fromUtf8(previewBytes);
preview = preview.substring(0, Math.min(preview.length(), 256));
msg = StringUtils.format("%s: %s", msg, preview);
}
throw QueryCapacityExceededException.withErrorMessageAndResolvedHost(msg);
}
if (isHtmlContentType || isHtmlBody) {
int len = Math.min(contentBuffer.readableBytes(), 512);
byte[] previewBytes = new byte[len];
if (len > 0) {
contentBuffer.getBytes(contentBuffer.readerIndex(), previewBytes);
}
String preview = len > 0 ? StringUtils.fromUtf8(previewBytes) : "";
preview = preview.substring(0, Math.min(preview.length(), 256));
throw new org.apache.druid.query.QueryInterruptedException(
org.apache.druid.query.QueryException.UNKNOWN_EXCEPTION_ERROR_CODE,
StringUtils.format(
"Query[%s] url[%s] returned HTML response instead of JSON with status[%s] contentType[%s] preview[%s]",
query.getId(),
url,
statusCode,
contentType,
preview
),
org.apache.druid.query.QueryInterruptedException.class.getName(),
host
);
}
checkTotalBytesLimit(response.getContent().readableBytes());

log.debug("Initial response from url[%s] for queryId[%s]", url, query.getId());
Expand Down