YoursFunny/TelegramTwitterMediaBot
1
0
Fork 0
mirror of https://github.com/TheFunny/TelegramTwitterMediaBot.git synced 2026-09-23 23:32:05 +00:00
Code Releases Activity

fix: cut tweet text by code points, not UTF-16 units

Browse Source
This commit is contained in:
YoursFunny
2026-08-04 23:45:54 +08:00
parent f4e60d8946
commit 2faccaac42
2 changed files with 9 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/x-media/src/site/twitter/interface.rs
+8 -12
View File
@@ -205,21 +205,17 @@ impl Tweet {
} }
/// The raw syndication `text` ends with the appended media short link /// The raw syndication `text` ends with the appended media short link
/// (" https://t.co/wmI8McgXul"). `display_text_range` (UTF-16 indices) marks /// (" https://t.co/wmI8McgXul"). `display_text_range` marks the visible text;
/// the visible text; a regex strips any remaining trailing t.co link when the /// a regex strips any remaining trailing t.co link when the range is absent
/// range is absent or a tweet ends in a URL short link. /// or a tweet ends in a URL short link.
///
/// X reports these indices in Unicode **code points**, not UTF-16 units
/// (verified against GraphQL responses containing emoji: cutting an emoji
/// tweet by UTF-16 units silently drops the character after the emoji).
fn strip_trailing_short_links(text: &str, display_text_range: Option<[usize; 2]>) -> String { fn strip_trailing_short_links(text: &str, display_text_range: Option<[usize; 2]>) -> String {
let mut out = match display_text_range { let mut out = match display_text_range {
Some([start, end]) if start < end => { Some([start, end]) if start < end => {
let units: Vec<u16> = text text.chars().skip(start).take(end - start).collect()
.encode_utf16()
.skip(start)
.take(end - start)
.collect();
// Drop the replacement char that a surrogate cut at the boundary
// would produce (the range end is a valid UTF-16 boundary in
// practice, so this is just a safety net).
String::from_utf16_lossy(&units).replace('\u{FFFD}', "")
} }
_ => text.to_string(), _ => text.to_string(),
}; };
crates/x-media/src/site/twitter/model.rs
+1 -1
View File
@@ -10,7 +10,7 @@ pub struct SyndicationTweet {
#[serde(default)] #[serde(default)]
pub possibly_sensitive: Option<bool>, pub possibly_sensitive: Option<bool>,
/// Visible-text span; the raw `text` field has the appended media short /// Visible-text span; the raw `text` field has the appended media short
/// link after it. Indices are UTF-16 code units. /// link after it. Indices are Unicode code points (not UTF-16 units).
#[serde(default, rename = "display_text_range")] #[serde(default, rename = "display_text_range")]
pub display_text_range: Option<[usize; 2]>, pub display_text_range: Option<[usize; 2]>,
#[serde(default)] #[serde(default)]