Merge pull request 'memories: restore early-era Snapchat unix-epoch filenames' (#84) from feature/snapchat-early-era-dates into master

Reviewed-on: #84

src/memories.rs

@@ -206,14 +206,20 @@ pub fn extract_date_from_filename(filename: &str) -> Option<DateTime<FixedOffset
         let timestamp_str = captures.get(1)?.as_str();
         let len = timestamp_str.len();
 
-        // Known apps whose filenames carry sequential IDs that happen to
+        // Snapchat used real unix-second filenames in its early era
-        // overlap real epoch values (e.g. `Snapchat-1021849065.mp4` parses
+        // (e.g. `Snapchat-1383929602.jpg` = 2013-11-08), then switched to
-        // as 2002-05-19, but the file was actually saved in 2021). The
+        // monotonic sequential IDs whose digits overlap plausible epoch
-        // digits alone are indistinguishable from a unix timestamp, so we
+        // ranges (`Snapchat-1021849065.mp4` truncates to 2002, actually
-        // dispatch on the source-app prefix instead.
+        // saved 2021; `Snapchat-1751031586660373917.jpg` is 19 digits,
-        const NON_TIMESTAMP_PREFIXES: &[&str] = &["snapchat-"];
+        // truncates to 2002, actually 2016). Discriminate by:
+        //   - exactly 10 captured digits AND post-2011-09-23 (launch) → real epoch
+        //   - anything else under this prefix → sequential ID, fall through
+        // The Snapchat-launch floor catches the 10-digit-2002 case; the
+        // length=10 gate catches the multi-digit sequential IDs (which
+        // get truncated to 16 by the regex above).
         let lower = filename.to_ascii_lowercase();
-        if NON_TIMESTAMP_PREFIXES.iter().any(|p| lower.starts_with(p)) {
+        let is_snapchat = lower.starts_with("snapchat-");
+        if is_snapchat && len != 10 {
             return None;
         }
 
@@ -265,6 +271,13 @@ pub fn extract_date_from_filename(filename: &str) -> Option<DateTime<FixedOffset
                 .map(|naive_dt| naive_dt.fixed_offset())
                 .and_then(plausible_filename_date)
         {
+            // Snapchat launched 2011-09-23. A 10-digit Snapchat filename
+            // dated before that is a sequential ID (e.g.
+            // `Snapchat-1021849065.mp4` parses to 2002), not a real epoch.
+            const SNAPCHAT_LAUNCH_TS: i64 = 1_316_736_000;
+            if is_snapchat && date_time.timestamp() < SNAPCHAT_LAUNCH_TS {
+                return None;
+            }
             return Some(date_time);
         }
 
@@ -652,21 +665,31 @@ mod tests {
     }
 
     #[test]
-    fn test_extract_date_from_filename_snapchat_should_not_match() {
+    fn test_extract_date_from_filename_snapchat_sequential_ids_rejected() {
-        // Snapchat-prefixed filenames carry sequential app-assigned IDs
+        // Modern Snapchat-prefixed filenames carry sequential app-assigned
-        // that happen to fall inside plausible epoch ranges. The two
+        // IDs whose digits happen to fall inside plausible epoch ranges
-        // reported cases:
+        // when truncated. Reported cases (real save dates per FileModifyDate):
-        //   Snapchat-1021849065.mp4         → 10 digits → 2002-05-19
+        //   Snapchat-1021849065.mp4         → 10 digits → 2002-05-19  (saved 2021)
-        //   Snapchat-1751031586660373917.jpg → 19 digits → 2002-09-09
+        //   Snapchat-1751031586660373917.jpg → 19 digits → 2002-09-09  (saved 2016)
-        // Real save dates are 2021 and 2016 respectively per
+        // We discriminate by length + Snapchat-launch floor: only exactly
-        // FileModifyDate; the prefix denylist forces a fall-through to
+        // 10 digits AND post-2011-09-23 (Snapchat launch) is treated as
-        // fs_time.
+        // a real unix epoch. Anything else falls through to fs_time.
         assert!(extract_date_from_filename("Snapchat-1021849065.mp4").is_none());
         assert!(extract_date_from_filename("Snapchat-1751031586660373917.jpg").is_none());
         // Case-insensitive match — lowercase variant should also reject.
         assert!(extract_date_from_filename("snapchat-1021849065.mp4").is_none());
     }
 
+    #[test]
+    fn test_extract_date_from_filename_snapchat_early_era_unix_epoch() {
+        // Early Snapchat (2013-2014ish) wrote real unix-second filenames.
+        // Snapchat-1383929602.jpg → 1383929602 = 2013-11-08 16:53:22 UTC.
+        // The blanket-prefix denial introduced for sequential IDs broke
+        // these — restore via a length=10 + post-launch sanity gate.
+        let date_time = extract_date_from_filename("Snapchat-1383929602.jpg").unwrap();
+        assert_eq!(date_time.timestamp(), 1383929602);
+    }
+
     // The obsolete `test_memory_date_priority_*` tests covered the old
     // request-time waterfall in `get_memory_date_with_priority`. Their
     // replacement lives in `crate::date_resolver::tests` (resolver