Skip to content

Refactor gcp-fixture multipart parser #125828

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

Merged
merged 21 commits into from
Apr 15, 2025
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
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@

import fixture.gcs.FakeOAuth2HttpHandler;
import fixture.gcs.GoogleCloudStorageHttpHandler;
import fixture.gcs.MultipartUpload;

import com.google.api.client.http.HttpExecuteInterceptor;
import com.google.api.client.http.HttpRequestInitializer;
Expand Down Expand Up @@ -43,7 +44,6 @@
import org.elasticsearch.core.Nullable;
import org.elasticsearch.core.SuppressForbidden;
import org.elasticsearch.core.TimeValue;
import org.elasticsearch.core.Tuple;
import org.elasticsearch.http.ResponseInjectingHttpHandler;
import org.elasticsearch.repositories.blobstore.AbstractBlobContainerRetriesTestCase;
import org.elasticsearch.repositories.blobstore.ESMockAPIBasedRepositoryIntegTestCase;
Expand All @@ -62,15 +62,13 @@
import java.util.Locale;
import java.util.Map;
import java.util.Objects;
import java.util.Optional;
import java.util.Queue;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentLinkedQueue;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.concurrent.atomic.AtomicReference;

import static fixture.gcs.GoogleCloudStorageHttpHandler.parseMultipartRequestBody;
import static fixture.gcs.TestUtils.createServiceAccount;
import static java.nio.charset.StandardCharsets.UTF_8;
import static org.elasticsearch.repositories.blobstore.BlobStoreTestUtil.randomPurpose;
Expand All @@ -80,7 +78,6 @@
import static org.elasticsearch.repositories.gcs.GoogleCloudStorageClientSettings.ENDPOINT_SETTING;
import static org.elasticsearch.repositories.gcs.GoogleCloudStorageClientSettings.READ_TIMEOUT_SETTING;
import static org.elasticsearch.repositories.gcs.GoogleCloudStorageClientSettings.TOKEN_URI_SETTING;
import static org.elasticsearch.test.hamcrest.OptionalMatchers.isPresent;
import static org.hamcrest.Matchers.anyOf;
import static org.hamcrest.Matchers.containsString;
import static org.hamcrest.Matchers.equalTo;
Expand Down Expand Up @@ -268,17 +265,16 @@ public void testWriteBlobWithRetries() throws Exception {
final CountDown countDown = new CountDown(maxRetries);

final BlobContainer blobContainer = blobContainerBuilder().maxRetries(maxRetries).build();
final byte[] bytes = randomBlobContent();
final byte[] bytes = randomBlobContent(0);
httpServer.createContext("/upload/storage/v1/b/bucket/o", safeHandler(exchange -> {
assertThat(exchange.getRequestURI().getQuery(), containsString("uploadType=multipart"));
if (countDown.countDown()) {
Optional<Tuple<String, BytesReference>> content = parseMultipartRequestBody(exchange.getRequestBody());
assertThat(content, isPresent());
assertThat(content.get().v1(), equalTo(blobContainer.path().buildAsString() + "write_blob_max_retries"));
if (Objects.deepEquals(bytes, BytesReference.toBytes(content.get().v2()))) {
MultipartUpload multipartUpload = MultipartUpload.parseBody(exchange, exchange.getRequestBody());
assertEquals(multipartUpload.name(), blobContainer.path().buildAsString() + "write_blob_max_retries");
if (multipartUpload.content().equals(new BytesArray(bytes))) {
byte[] response = Strings.format("""
{"bucket":"bucket","name":"%s"}
""", content.get().v1()).getBytes(UTF_8);
""", multipartUpload.name()).getBytes(UTF_8);
exchange.getResponseHeaders().add("Content-Type", "application/json");
exchange.sendResponseHeaders(RestStatus.OK.getStatus(), response.length);
exchange.getResponseBody().write(response);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@
import org.elasticsearch.common.io.Streams;
import org.elasticsearch.common.regex.Regex;
import org.elasticsearch.core.SuppressForbidden;
import org.elasticsearch.core.Tuple;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.rest.RestUtils;
import org.elasticsearch.test.fixture.HttpHeaderParser;
Expand All @@ -27,26 +26,17 @@
import org.elasticsearch.xcontent.XContentFactory;
import org.elasticsearch.xcontent.XContentType;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URLDecoder;
import java.util.HashMap;
import java.util.Locale;
import java.util.Map;
import java.util.Objects;
import java.util.Optional;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
import java.util.zip.GZIPInputStream;

import static fixture.gcs.MockGcsBlobStore.failAndThrow;
import static java.nio.charset.StandardCharsets.UTF_8;
import static java.util.stream.Collectors.joining;
import static org.elasticsearch.core.Strings.format;

/**
* Minimal HTTP handler that acts as a Google Cloud Storage compliant server
Expand Down Expand Up @@ -183,26 +173,18 @@ public void handle(final HttpExchange exchange) throws IOException {
exchange.getResponseBody().write(response);

} else if (Regex.simpleMatch("POST /upload/storage/v1/b/" + bucket + "/*uploadType=multipart*", request)) {
// Multipart upload
Optional<Tuple<String, BytesReference>> content = parseMultipartRequestBody(requestBody.streamInput());
if (content.isPresent()) {
try {
final var multipartUpload = MultipartUpload.parseBody(exchange, requestBody.streamInput());
final Long ifGenerationMatch = parseOptionalLongParameter(exchange, IF_GENERATION_MATCH);
final MockGcsBlobStore.BlobVersion newBlobVersion = mockGcsBlobStore.updateBlob(
content.get().v1(),
multipartUpload.name(),
ifGenerationMatch,
content.get().v2()
multipartUpload.content()
);
writeBlobVersionAsJson(exchange, newBlobVersion);
} else {
throw new AssertionError(
Copy link
Contributor

Choose a reason for hiding this comment

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

I would like to keep the behaviour where an invalid body causes a test failure rather than just an IllegalStateException

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Throw AssertionError errors from the MultipartUpload.parseBody now.

Copy link
Contributor

Choose a reason for hiding this comment

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

I was sort of hoping to see tests that ensured that this kind of malformed body would throw an IAE from the parser. Throwing AssertionError from the parser itself basically means you can only test the happy path (or else catch AssertionError in tests which is best avoided if possible).

"Could not read multi-part request to ["
+ request
+ "] with headers ["
+ new HashMap<>(exchange.getRequestHeaders())
+ "]"
);
} catch (IllegalArgumentException e) {
throw new AssertionError(e);
}

} else if (Regex.simpleMatch("POST /upload/storage/v1/b/" + bucket + "/*uploadType=resumable*", request)) {
// Resumable upload initialization https://cloud.google.com/storage/docs/json_api/v1/how-tos/resumable-upload
final Map<String, String> params = new HashMap<>();
Expand Down Expand Up @@ -328,81 +310,6 @@ private static String httpServerUrl(final HttpExchange exchange) {
return "http://" + exchange.getRequestHeaders().get("HOST").get(0);
}

private static final Pattern NAME_PATTERN = Pattern.compile("\"name\":\"([^\"]*)\"");

public static Optional<Tuple<String, BytesReference>> parseMultipartRequestBody(final InputStream requestBody) throws IOException {
Tuple<String, BytesReference> content = null;
final BytesReference fullRequestBody;
try (InputStream in = new GZIPInputStream(requestBody)) {
fullRequestBody = Streams.readFully(in);
}
String name = null;
boolean skippedEmptyLine = false;
int startPos = 0;
int endPos = 0;
while (startPos < fullRequestBody.length()) {
do {
endPos = fullRequestBody.indexOf((byte) '\r', endPos + 1);
} while (endPos >= 0 && fullRequestBody.get(endPos + 1) != '\n');
boolean markAndContinue = false;
final String bucketPrefix = "{\"bucket\":";
if (startPos > 0) {
startPos += 2;
}
if (name == null || skippedEmptyLine == false) {
if ((skippedEmptyLine == false && endPos == startPos)
|| (fullRequestBody.get(startPos) == '-' && fullRequestBody.get(startPos + 1) == '-')) {
markAndContinue = true;
} else {
final String start = fullRequestBody.slice(startPos, Math.min(endPos - startPos, bucketPrefix.length())).utf8ToString();
if (start.toLowerCase(Locale.ROOT).startsWith("content")) {
markAndContinue = true;
} else if (start.startsWith(bucketPrefix)) {
markAndContinue = true;
final String line = fullRequestBody.slice(
startPos + bucketPrefix.length(),
endPos - startPos - bucketPrefix.length()
).utf8ToString();
Matcher matcher = NAME_PATTERN.matcher(line);
if (matcher.find()) {
name = matcher.group(1);
}
}
}
skippedEmptyLine = markAndContinue && endPos == startPos;
startPos = endPos;
} else {
while (isEndOfPart(fullRequestBody, endPos) == false) {
endPos = fullRequestBody.indexOf((byte) '\r', endPos + 1);
}
content = Tuple.tuple(name, fullRequestBody.slice(startPos, endPos - startPos));
break;
}
}
if (content == null) {
final InputStream stream = fullRequestBody.streamInput();
logger.warn(
() -> format(
"Failed to find multi-part upload in [%s]",
new BufferedReader(new InputStreamReader(stream)).lines().collect(joining("\n"))
)
);
}
return Optional.ofNullable(content);
}

private static final byte[] END_OF_PARTS_MARKER = "\r\n--__END_OF_PART__".getBytes(UTF_8);

private static boolean isEndOfPart(BytesReference fullRequestBody, int endPos) {
for (int i = 0; i < END_OF_PARTS_MARKER.length; i++) {
final byte b = END_OF_PARTS_MARKER[i];
if (fullRequestBody.get(endPos + i) != b) {
return false;
}
}
return true;
}

private static String requireHeader(HttpExchange exchange, String headerName) {
final String headerValue = exchange.getRequestHeaders().getFirst(headerName);
if (headerValue != null) {
Expand Down
Loading