-
-
Notifications
You must be signed in to change notification settings - Fork 105
Add utilities to detect and replace broken links. #1366
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
base: develop
Are you sure you want to change the base?
Changes from all commits
9004e6b
7153833
d205074
c3a64e3
48c23ab
d556a33
66b8d6e
24998cf
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -4,14 +4,27 @@ | |
| import com.linkedin.urls.detection.UrlDetector; | ||
| import com.linkedin.urls.detection.UrlDetectorOptions; | ||
|
|
||
| import java.net.URI; | ||
| import java.net.http.HttpClient; | ||
| import java.net.http.HttpRequest; | ||
| import java.net.http.HttpResponse; | ||
| import java.util.List; | ||
| import java.util.Optional; | ||
| import java.util.Set; | ||
| import java.util.concurrent.CompletableFuture; | ||
|
|
||
| /** | ||
| * Utility class to detect links. | ||
| */ | ||
| public class LinkDetection { | ||
| private static final HttpClient HTTP_CLIENT = | ||
| HttpClient.newBuilder().followRedirects(HttpClient.Redirect.NORMAL).build(); | ||
|
|
||
| /** | ||
| * Default filters used when extracting links: skip suppressed URLs and non-http schemes. | ||
| */ | ||
| private static final Set<LinkFilter> DEFAULT_EXTRACT_FILTERS = | ||
| Set.of(LinkFilter.SUPPRESSED, LinkFilter.NON_HTTP_SCHEME); | ||
|
|
||
| /** | ||
| * Possible ways to filter a link. | ||
|
|
@@ -55,7 +68,120 @@ public static List<String> extractLinks(String content, Set<LinkFilter> filter) | |
| * @return true if the content contains at least one link | ||
| */ | ||
| public static boolean containsLink(String content) { | ||
| return !(new UrlDetector(content, UrlDetectorOptions.BRACKET_MATCH).detect().isEmpty()); | ||
| return !new UrlDetector(content, UrlDetectorOptions.BRACKET_MATCH).detect().isEmpty(); | ||
| } | ||
|
|
||
| /** | ||
| * Checks whether the given URL is considered broken. | ||
| * | ||
| * <p> | ||
| * A link is considered broken if: | ||
| * <ul> | ||
| * <li>An HTTP request fails</li> | ||
| * <li>The HTTP response status code is outside the 200–399 range</li> | ||
| * </ul> | ||
| * | ||
| * <p> | ||
| * Notes: | ||
| * <ul> | ||
| * <li>Status code {@code 200} is considered valid, even if the response body is empty</li> | ||
| * <li>The response body content is not inspected</li> | ||
| * </ul> | ||
| * | ||
| * @param url the URL to check | ||
| * @return a future completing with {@code true} if the link is broken | ||
| * @throws IllegalArgumentException if the given URL is not a valid URI | ||
| */ | ||
|
|
||
|
|
||
| public static CompletableFuture<Boolean> isLinkBroken(String url) { | ||
| // Quick check with HEAD "cheaper". If HEAD indicates failure some servers don't implement | ||
| // HEAD properly, | ||
| // fall back to GET to confirm the resource status. | ||
| HttpRequest headCheckRequest = HttpRequest.newBuilder(URI.create(url)) | ||
| .method("HEAD", HttpRequest.BodyPublishers.noBody()) | ||
| .build(); | ||
|
|
||
| return HTTP_CLIENT.sendAsync(headCheckRequest, HttpResponse.BodyHandlers.discarding()) | ||
| .thenApply(response -> { | ||
| int status = response.statusCode(); | ||
| return status < 200 || status >= 400; | ||
| }) | ||
| .exceptionally(_ -> true) | ||
| .thenCompose(result -> { | ||
| if (!result) { | ||
| return CompletableFuture.completedFuture(false); | ||
| } | ||
| HttpRequest getFallbackRequest = | ||
| HttpRequest.newBuilder(URI.create(url)).GET().build(); | ||
| return HTTP_CLIENT | ||
| .sendAsync(getFallbackRequest, HttpResponse.BodyHandlers.discarding()) | ||
| .thenApply(resp -> resp.statusCode() >= 400) | ||
| .exceptionally(ignored -> true); // still never null | ||
| }); | ||
| } | ||
|
|
||
| /** | ||
| * Replaces all broken links in the given text with the provided replacement string. | ||
| * | ||
| * <p> | ||
| * The link checks are performed asynchronously. | ||
| * </p> | ||
| * | ||
| * <p> | ||
| * Example: | ||
| * | ||
| * <pre>{@code | ||
| * replaceDeadLinks(""" | ||
| * Test | ||
| * http://deadlink/1 | ||
| * http://workinglink/1 | ||
| * """, "broken") | ||
| * }</pre> | ||
| * | ||
| * <p> | ||
| * Results in: | ||
| * | ||
| * <pre>{@code | ||
| * Test | ||
| * broken | ||
| * http://workinglink/1 | ||
| * }</pre> | ||
| * | ||
| * @param text the input text containing URLs | ||
| * @param replacement the string to replace broken links with | ||
| * @return a future containing the modified text | ||
| */ | ||
| public static CompletableFuture<String> replaceDeadLinks(String text, String replacement) { | ||
|
Member
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. improve naming. avoid multiple terms for the same think. you called it |
||
| List<String> links = extractLinks(text, DEFAULT_EXTRACT_FILTERS); | ||
|
|
||
| if (links.isEmpty()) { | ||
| return CompletableFuture.completedFuture(text); | ||
| } | ||
|
|
||
| List<CompletableFuture<Optional<String>>> deadLinkFutures = links.stream() | ||
| .distinct() | ||
| .map(link -> isLinkBroken(link) | ||
| .thenApply(isBroken -> isBroken ? Optional.of(link) : Optional.<String>empty())) | ||
|
Member
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. u misunderstood me. its better if u simply filter out these, skip them here instead of later. |
||
| .toList(); | ||
|
|
||
|
|
||
| return CompletableFuture.allOf(deadLinkFutures.toArray(CompletableFuture[]::new)) | ||
| .thenApply(_ -> deadLinkFutures.stream() | ||
| .map(CompletableFuture::join) | ||
| .flatMap(Optional::stream) | ||
| .toList()) | ||
| .thenApply(deadLinks -> { | ||
| StringBuilder sb = new StringBuilder(text); | ||
| for (String deadLink : deadLinks) { | ||
| int idx = sb.indexOf(deadLink); | ||
| while (idx != -1) { | ||
| sb.replace(idx, idx + deadLink.length(), replacement); | ||
| idx = sb.indexOf(deadLink, idx + replacement.length()); | ||
| } | ||
| } | ||
| return sb.toString(); | ||
| }); | ||
| } | ||
|
|
||
| private static Optional<String> toLink(Url url, Set<LinkFilter> filter) { | ||
|
|
@@ -76,7 +202,6 @@ private static Optional<String> toLink(Url url, Set<LinkFilter> filter) { | |
| // Remove trailing punctuation | ||
| link = link.substring(0, link.length() - 1); | ||
| } | ||
|
|
||
| return Optional.of(link); | ||
| } | ||
|
|
||
|
|
||
Uh oh!
There was an error while loading. Please reload this page.