Skip to content

NUTCH-3139 protocol-okhttp: add support for zstd content-encoding #877

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

Merged
sebastian-nagel merged 1 commit into from
Dec 18, 2025
Merged

NUTCH-3139 protocol-okhttp: add support for zstd content-encoding #877

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 src/plugin/protocol-okhttp/ivy.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,8 +37,9 @@
</publications>

<dependencies>
<dependency org="com.squareup.okhttp3" name="okhttp" rev="4.9.3"/>
<dependency org="com.squareup.okhttp3" name="okhttp-brotli" rev="4.9.3"/>
<dependency org="com.squareup.okhttp3" name="okhttp" rev="5.3.2"/>
<dependency org="com.squareup.okhttp3" name="okhttp-brotli" rev="5.3.2"/>
<dependency org="com.squareup.okhttp3" name="okhttp-zstd" rev="5.3.2"/>
</dependencies>

</ivy-module>
16 changes: 9 additions & 7 deletions src/plugin/protocol-okhttp/plugin.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,13 +28,15 @@
<!-- dependencies of OkHttp -->
<library name="annotations-13.0.jar"/>
<library name="dec-0.1.2.jar"/>
<library name="kotlin-stdlib-1.4.10.jar"/>
<library name="kotlin-stdlib-common-1.4.10.jar"/>
<library name="kotlin-stdlib-jdk7-1.4.10.jar"/>
<library name="kotlin-stdlib-jdk8-1.4.10.jar"/>
<library name="okhttp-4.9.3.jar"/>
<library name="okhttp-brotli-4.9.3.jar"/>
<library name="okio-2.8.0.jar"/>
<library name="kotlin-stdlib-2.2.21.jar"/>
<library name="okhttp-5.3.2.jar"/>
<library name="okhttp-brotli-5.3.2.jar"/>
<library name="okhttp-jvm-5.3.2.jar"/>
<library name="okhttp-zstd-5.3.2.jar"/>
<library name="okio-3.16.4.jar"/>
<library name="okio-jvm-3.16.4.jar"/>
<library name="zstd-kmp-jvm-0.4.0.jar"/>
<library name="zstd-kmp-okio-jvm-0.4.0.jar"/>
<!-- end of dependencies of OkHttp -->
</runtime>

Expand Down
13 changes: 8 additions & 5 deletions src/plugin/protocol-okhttp/src/java/org/apache/nutch/protocol/okhttp/OkHttp.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,15 +52,19 @@
import org.slf4j.LoggerFactory;

import okhttp3.Authenticator;
import okhttp3.CompressionInterceptor;
import okhttp3.Connection;
import okhttp3.ConnectionPool;
import okhttp3.Gzip;
import okhttp3.Handshake;
import okhttp3.Headers;
import okhttp3.Interceptor;
import okhttp3.OkHttpClient;
import okhttp3.Protocol;
import okhttp3.Request;
import okhttp3.brotli.BrotliInterceptor;
import okhttp3.brotli.Brotli;
import okhttp3.zstd.Zstd;


public class OkHttp extends HttpBase {

Expand Down Expand Up @@ -156,13 +160,11 @@ public boolean verify(String hostname, SSLSession session) {
String proxyUsername = conf.get("http.proxy.username");
if (proxyUsername == null) {
ProxySelector selector = new ProxySelector() {
@SuppressWarnings("serial")
private final List<Proxy> noProxyList = new ArrayList<Proxy>() {
{
add(Proxy.NO_PROXY);
}
};
@SuppressWarnings("serial")
private final List<Proxy> proxyList = new ArrayList<Proxy>() {
{
add(proxy);
Expand Down Expand Up @@ -224,8 +226,9 @@ public Request authenticate(okhttp3.Route route,
builder.addNetworkInterceptor(new HTTPHeadersInterceptor());
}

// enable support for Brotli compression (Content-Encoding)
builder.addInterceptor(BrotliInterceptor.INSTANCE);
// enable support for Zstd, Brotli, Gzip Content-Encoding
builder.addInterceptor(new CompressionInterceptor(Zstd.INSTANCE,
Brotli.INSTANCE, Gzip.INSTANCE));

// instantiate connection pool(s), cf.
// https://square.github.io/okhttp/3.x/okhttp/okhttp3/ConnectionPool.html
Expand Down