From 5222cfa1cb59ef65e240053f7a93a35b1e493b97 Mon Sep 17 00:00:00 2001
From: YoursFunny <admin@yoursfunny.top>
Date: Mon, 21 Sep 2026 17:29:18 +0800
Subject: [PATCH] refactor(x-media): hoist the shared caption builder

bilibili and misskey each had a byte-identical caption() (same escaping,
same empty-text early return, differing only in a named format argument).
site::caption holds it once; both adapters call it.
---
 crates/x-media/src/site/bilibili/interface.rs | 17 ++---------------
 crates/x-media/src/site/misskey/interface.rs  | 17 ++---------------
 crates/x-media/src/site/mod.rs                | 18 ++++++++++++++++++
 3 files changed, 22 insertions(+), 30 deletions(-)

diff --git a/crates/x-media/src/site/bilibili/interface.rs b/crates/x-media/src/site/bilibili/interface.rs
index 614a3ba..fe4c69b 100644
--- a/crates/x-media/src/site/bilibili/interface.rs
+++ b/crates/x-media/src/site/bilibili/interface.rs
@@ -30,7 +30,7 @@
 use super::model;
 use crate::media::Media;
 use crate::site::{FetchError, Fetched, RenderData, Site, SiteFuture, compose_text};
-use html_escape::{encode_double_quoted_attribute, encode_text};
+use html_escape::encode_text;
 use regex::Regex;
 use std::sync::LazyLock;
 use std::sync::atomic::{AtomicBool, Ordering};
@@ -276,7 +276,7 @@ impl From<model::Item> for Fetched {
         let text = compose_text(&title, &content);
         let tags = topic_name(&item).to_string();
 
-        let caption = caption(&url, &author_url, &author, &text);
+        let caption = crate::site::caption(&url, &author_url, &author, &text);
         let media = media_of(&item);
 
         Fetched {
@@ -485,19 +485,6 @@ fn to_https(url: &str) -> String {
     }
 }
 
-fn caption(url: &str, author_url: &str, author: &str, text: &str) -> String {
-    let url = encode_double_quoted_attribute(url);
-    let author_url = encode_double_quoted_attribute(author_url);
-    let author = encode_text(author);
-    if text.is_empty() {
-        return format!("{url}\n<a href=\"{author_url}\">{author}</a>");
-    }
-    format!(
-        "{url}\n<a href=\"{author_url}\">{author}</a>: {}",
-        encode_text(text)
-    )
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
diff --git a/crates/x-media/src/site/misskey/interface.rs b/crates/x-media/src/site/misskey/interface.rs
index 4f13a79..458b98f 100644
--- a/crates/x-media/src/site/misskey/interface.rs
+++ b/crates/x-media/src/site/misskey/interface.rs
@@ -4,7 +4,7 @@
 use super::model;
 use crate::media::Media;
 use crate::site::{FetchError, Fetched, RenderData, Site, SiteFuture};
-use html_escape::{encode_double_quoted_attribute, encode_text};
+use html_escape::encode_text;
 use regex::Regex;
 use std::sync::LazyLock;
 
@@ -117,7 +117,7 @@ impl From<model::Note> for Fetched {
         text.push_str(content.text.as_deref().unwrap_or_default().trim());
         let text = text.trim().to_string();
 
-        let caption = caption(&url, &author_url, &author, &text);
+        let caption = crate::site::caption(&url, &author_url, &author, &text);
         let sensitive = content.cw.is_some() || content.files.iter().any(|f| f.is_sensitive);
         let media: Vec<Media> = content.files.iter().filter_map(media_from_file).collect();
 
@@ -143,19 +143,6 @@ impl From<model::Note> for Fetched {
     }
 }
 
-fn caption(url: &str, author_url: &str, author: &str, text: &str) -> String {
-    let url = encode_double_quoted_attribute(url);
-    let author_url = encode_double_quoted_attribute(author_url);
-    let author = encode_text(author);
-    if text.is_empty() {
-        return format!("{url}\n<a href=\"{author_url}\">{author}</a>");
-    }
-    format!(
-        "{url}\n<a href=\"{author_url}\">{author}</a>: {text}",
-        text = encode_text(text),
-    )
-}
-
 /// Maps a Misskey DriveFile to a [`Media`] item; unknown/audio/other types
 /// are skipped (twitter's `_ => {}` precedent). GIF must be matched before
 /// the generic image arm.
diff --git a/crates/x-media/src/site/mod.rs b/crates/x-media/src/site/mod.rs
index e6ce71a..76907f5 100644
--- a/crates/x-media/src/site/mod.rs
+++ b/crates/x-media/src/site/mod.rs
@@ -79,6 +79,24 @@ pub(crate) struct RenderData {
     pub tags: String,
 }
 
+/// The built-in caption for a post that has no user-supplied format: the
+/// canonical URL, the author as a link, then the post's text after a colon.
+/// The two URLs are escaped for an HTML attribute and the text as HTML text,
+/// so site-supplied content cannot inject markup. Shared by the adapters whose
+/// captions have exactly this shape (bilibili, misskey).
+pub fn caption(url: &str, author_url: &str, author: &str, text: &str) -> String {
+    let url = html_escape::encode_double_quoted_attribute(url);
+    let author_url = html_escape::encode_double_quoted_attribute(author_url);
+    let author = html_escape::encode_text(author);
+    if text.is_empty() {
+        return format!("{url}\n<a href=\"{author_url}\">{author}</a>");
+    }
+    format!(
+        "{url}\n<a href=\"{author_url}\">{author}</a>: {}",
+        html_escape::encode_text(text)
+    )
+}
+
 /// The post's text as one string: title and content joined by a line break,
 /// each only when it is non-empty. This is what the sites' built-in captions
 /// show after the author line, and what the bot quotes when it is long.