From 65b9f236b777ff70dabb066d9b1dfb4da2cacab8 Mon Sep 17 00:00:00 2001
From: guqing <38999863+guqing@users.noreply.github.com>
Date: Mon, 16 Dec 2024 17:06:58 +0800
Subject: [PATCH] fix: missing enclosure attribute length (#49)

---
 .../java/run/halo/feed/RssCacheManager.java   |  5 ++-
 .../java/run/halo/feed/RssXmlBuilder.java     | 44 ++++++++++++++++++-
 2 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/app/src/main/java/run/halo/feed/RssCacheManager.java b/app/src/main/java/run/halo/feed/RssCacheManager.java
index 7193fec..02d9a7b 100644
--- a/app/src/main/java/run/halo/feed/RssCacheManager.java
+++ b/app/src/main/java/run/halo/feed/RssCacheManager.java
@@ -49,7 +49,10 @@ private Mono<String> generateRssXml(Mono<RSS2> loader) {
             .doOnNext(prop -> builder.withExtractRssTags(prop.getRssExtraTags()));
 
         return Mono.when(rssMono, generatorMono, extractTagsMono)
-            .then(Mono.fromSupplier(builder::toXmlString));
+            // toXmlString is a blocking operation
+            .then(Mono.fromCallable(builder::toXmlString)
+                .subscribeOn(Schedulers.boundedElastic())
+            );
     }
 
     @EventListener(PluginConfigUpdatedEvent.class)
diff --git a/app/src/main/java/run/halo/feed/RssXmlBuilder.java b/app/src/main/java/run/halo/feed/RssXmlBuilder.java
index 5305b5e..0d9b732 100644
--- a/app/src/main/java/run/halo/feed/RssXmlBuilder.java
+++ b/app/src/main/java/run/halo/feed/RssXmlBuilder.java
@@ -15,13 +15,28 @@
 import org.dom4j.DocumentHelper;
 import org.dom4j.Element;
 import org.dom4j.io.SAXReader;
+import org.springframework.http.HttpEntity;
+import org.springframework.http.HttpHeaders;
+import org.springframework.http.client.reactive.ReactorClientHttpConnector;
+import org.springframework.lang.NonNull;
 import org.springframework.util.CollectionUtils;
+import org.springframework.web.reactive.function.client.WebClient;
 import org.springframework.web.util.UriComponentsBuilder;
 import org.springframework.web.util.UriUtils;
+import reactor.netty.http.client.HttpClient;
 import run.halo.feed.telemetry.TelemetryEndpoint;
 
 @Slf4j
 public class RssXmlBuilder {
+    static final String UA =
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) "
+            + "Chrome/131.0.0.0 Safari/537.36";
+    private final WebClient webClient = WebClient.builder()
+        .clientConnector(new ReactorClientHttpConnector(HttpClient.create()
+            .followRedirect(true))
+        )
+        .build();
+
     private RSS2 rss2;
     private String generator = "Halo v2.0";
     private String extractRssTags;
@@ -174,10 +189,17 @@ private void createItemElementToChannel(Element channel, RSS2.Item item) {
         }
 
         if (StringUtils.isNotBlank(item.getEnclosureUrl())) {
-            itemElement.addElement("enclosure")
+            var enclosureElement = itemElement.addElement("enclosure")
                 .addAttribute("url", item.getEnclosureUrl())
-                .addAttribute("length", item.getEnclosureLength())
                 .addAttribute("type", item.getEnclosureType());
+
+            var enclosureLength = item.getEnclosureLength();
+            if (StringUtils.isBlank(enclosureLength)) {
+                // https://www.rssboard.org/rss-validator/docs/error/MissingAttribute.html
+                var fileBytes = getFileSizeBytes(item.getEnclosureUrl());
+                enclosureLength = String.valueOf(fileBytes);
+            }
+            enclosureElement.addAttribute("length", enclosureLength);
         }
 
         nullSafeList(item.getCategories())
@@ -258,4 +280,22 @@ static String instantToString(Instant instant) {
         return instant.atOffset(ZoneOffset.UTC)
             .format(DateTimeFormatter.RFC_1123_DATE_TIME);
     }
+
+    @NonNull
+    private Long getFileSizeBytes(String url) {
+        return webClient.get()
+            .uri(url)
+            .header(HttpHeaders.USER_AGENT, UA)
+            .retrieve()
+            .toBodilessEntity()
+            .map(HttpEntity::getHeaders)
+            .mapNotNull(headers -> headers.getFirst(HttpHeaders.CONTENT_LENGTH))
+            .map(Long::parseLong)
+            .doOnError(e -> log.debug("Failed to get file size from url: {}", url,
+                Throwables.getRootCause(e))
+            )
+            .onErrorReturn(0L)
+            .blockOptional()
+            .orElseThrow();
+    }
 }