refactor: 调整视频列表/视频合集的扫描逻辑，优化性能 (#342)

crates/bili_sync/src/adapter/collection.rs

@@ -44,13 +44,27 @@ impl VideoSource for collection::Model {
         true
     }
 
+    fn should_filter(
+        &self,
+        video_info: Result<VideoInfo, anyhow::Error>,
+        latest_row_at: &chrono::DateTime<Utc>,
+    ) -> Option<VideoInfo> {
+        // 由于 collection 的视频无固定时间顺序，should_take 无法提前中断拉取，因此 should_filter 环节需要进行额外过滤
+        if let Ok(video_info) = video_info {
+            if video_info.release_datetime() > latest_row_at {
+                return Some(video_info);
+            }
+        }
+        None
+    }
+
     fn log_refresh_video_start(&self) {
         info!("开始扫描{}「{}」..", CollectionType::from(self.r#type), self.name);
     }
 
     fn log_refresh_video_end(&self, count: usize) {
         info!(
-            "扫描{}「{}」完成，已拉取 {} 条视频",
+            "扫描{}「{}」完成，获取到 {} 条新视频",
             CollectionType::from(self.r#type),
             self.name,
             count,

crates/bili_sync/src/adapter/mod.rs

@@ -58,6 +58,15 @@ pub trait VideoSource {
         release_datetime > latest_row_at
     }
 
+    fn should_filter(
+        &self,
+        video_info: Result<VideoInfo, anyhow::Error>,
+        _latest_row_at: &chrono::DateTime<Utc>,
+    ) -> Option<VideoInfo> {
+        // 视频按照时间顺序拉取，should_take 已经获取了所有需要处理的视频，should_filter 无需额外处理
+        video_info.ok()
+    }
+
     /// 开始刷新视频
     fn log_refresh_video_start(&self);
 

crates/bili_sync/src/workflow.rs

@@ -76,7 +76,7 @@ pub async fn refresh_video_source<'a>(
                 }
             }
         })
-        .filter_map(|res| futures::future::ready(res.ok()))
+        .filter_map(|res| futures::future::ready(video_source.should_filter(res, &latest_row_at)))
         .chunks(10);
     let mut count = 0;
     while let Some(videos_info) = video_streams.next().await {