crates/clawhdf5-format/src/filter_registry.rs

@@ -9,7 +9,11 @@
 //!   [`builtin_filters`] lists them.
 //! * **Registered filters** (`std` only) — codecs the application supplies
 //!   for any other ID with [`register_filter`] (a [`FilterCodec`], or just a
-//!   decoding closure). A registered codec cannot shadow a built-in one.
+//!   decoding closure). A registered codec cannot shadow a built-in one,
+//!   except under 32023: that ID belongs to Granular BitRound, and the
+//!   built-in entry there only reads the pcodec chunks clawhdf5 <= 2.7.0
+//!   wrote (filter name `"pcodec"`), so a codec registered for 32023 handles
+//!   every other chunk with that ID, and writes.
 //!
 //! An ID in neither tier fails with [`FormatError::UnsupportedFilter`], as it
 //! always has.
@@ -118,6 +122,19 @@ impl BuiltinFilter {
     pub fn can_encode(&self) -> bool {
         self.encode.is_some()
     }
+
+    /// Whether the built-in entry only borrows its ID for some chunks, so a
+    /// registered codec may take the rest: the legacy pcodec entry under
+    /// Granular BitRound's 32023, which claims only chunks named `"pcodec"`.
+    fn is_shared(&self) -> bool {
+        self.id == crate::filter_pipeline::FILTER_PCODEC_LEGACY
+    }
+
+    /// Whether this entry decodes chunks written with `filter`.
+    fn claims(&self, filter: &crate::filter_pipeline::FilterDescription) -> bool {
+        !self.is_shared()
+            || filter.name.as_deref() == Some(crate::filter_pipeline::FILTER_PCODEC_LEGACY_NAME)
+    }
 }
 
 /// The filters compiled into this build, in ID order.
@@ -198,7 +215,11 @@ mod custom {
 /// A plain closure `Fn(&[u8], &FilterContext) -> Result<Vec<u8>, FormatError>`
 /// registers a decoder. Replaces (and returns) an earlier registration for
 /// the same ID. Fails with [`FormatError::FilterError`] if `id` is a built-in
-/// filter of this build: those cannot be overridden.
+/// filter of this build: those cannot be overridden. The exception is 32023
+/// (Granular BitRound): with the `pcodec` feature the built-in entry there
+/// reads only chunks whose filter is named `"pcodec"` (clawhdf5 <= 2.7.0's
+/// files); a codec registered for 32023 decodes every other chunk with that
+/// ID and does all the writing.
 #[cfg(feature = "std")]
 pub fn register_filter<C>(
     id: u16,
@@ -207,7 +228,7 @@ pub fn register_filter<C>(
 where
     C: FilterCodec + 'static,
 {
-    if let Some(builtin) = builtin_filter(id) {
+    if let Some(builtin) = builtin_filter(id).filter(|b| !b.is_shared()) {
         return Err(FormatError::FilterError(format!(
             "filter {id} ({}) is built in and cannot be re-registered",
             builtin.name
@@ -229,11 +250,13 @@ pub fn registered(id: u16) -> Option<std::sync::Arc<dyn FilterCodec>> {
     custom::with_read(|r| r.get(&id).cloned())
 }
 
-/// Undo filter `ctx.filter` on `input`: the built-in decoder if there is one,
-/// else a registered one, else [`FormatError::UnsupportedFilter`].
+/// Undo filter `ctx.filter` on `input`: the built-in decoder if there is one
+/// that claims the chunk, else a registered one, else the built-in decoder's
+/// own refusal or [`FormatError::UnsupportedFilter`].
 pub(crate) fn decode(input: &[u8], ctx: &FilterContext<'_>) -> Result<Vec<u8>, FormatError> {
     let id = ctx.filter.filter_id;
-    if let Some(builtin) = builtin_filter(id) {
+    let builtin = builtin_filter(id);
+    if let Some(builtin) = builtin.filter(|b| b.claims(ctx.filter)) {
         return (builtin.decode)(input, ctx);
     }
     #[cfg(feature = "std")]
@@ -250,12 +273,21 @@ pub(crate) fn decode(input: &[u8], ctx: &FilterContext<'_>) -> Result<Vec<u8>, F
         }
         return Ok(out);
     }
-    Err(FormatError::UnsupportedFilter(id))
+    match builtin {
+        Some(builtin) => (builtin.decode)(input, ctx),
+        None => Err(FormatError::UnsupportedFilter(id)),
+    }
 }
 
 /// Apply filter `ctx.filter` to `input`.
 pub(crate) fn encode(input: &[u8], ctx: &FilterContext<'_>) -> Result<Vec<u8>, FormatError> {
     let id = ctx.filter.filter_id;
+    #[cfg(feature = "std")]
+    if builtin_filter(id).is_some_and(|b| b.is_shared())
+        && let Some(codec) = registered(id)
+    {
+        return codec.encode(input, ctx);
+    }
     if let Some(builtin) = builtin_filter(id) {
         return match builtin.encode {
             Some(encode) => encode(input, ctx),
@@ -270,7 +302,7 @@ pub(crate) fn encode(input: &[u8], ctx: &FilterContext<'_>) -> Result<Vec<u8>, F
 }
 
 #[cfg(all(test, feature = "std"))]
-mod tests {
+pub(crate) mod tests {
     use super::*;
     use crate::filter_pipeline::{FILTER_FLETCHER32, FILTER_SHUFFLE, FilterPipeline};
     use crate::filters::{compress_chunk, decompress_chunk};
@@ -368,6 +400,55 @@ mod tests {
         assert!(builtin_filter(FILTER_SHUFFLE).is_some());
     }
 
+    /// Serialises the tests that register or read filter 32023 (the
+    /// registry is process-wide).
+    pub(crate) static ID_32023: std::sync::Mutex<()> = std::sync::Mutex::new(());
+
+    /// 32023 is Granular BitRound's ID; the `pcodec` build's built-in entry
+    /// there reads only clawhdf5 <= 2.7.0's pcodec chunks (named "pcodec"),
+    /// so a codec can be registered for the rest, and writes with it.
+    #[test]
+    fn a_codec_can_be_registered_for_granular_bitround() {
+        let _guard = ID_32023
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let named = |name: Option<&str>| FilterPipeline {
+            version: 2,
+            filters: vec![FilterDescription {
+                filter_id: 32023,
+                name: name.map(Into::into),
+                flags: 0,
+                client_data: vec![7],
+            }],
+        };
+        let prev = register_filter(32023, Xor).expect("32023 must be registrable");
+        assert!(prev.is_none());
+        let data = b"granular bitround".to_vec();
+        for name in [None, Some("granular_bitround"), Some("test")] {
+            let pl = named(name);
+            let enc = compress_chunk(&data, &pl, 1).unwrap();
+            assert_ne!(enc, data);
+            assert_eq!(decompress_chunk(&enc, &pl, data.len(), 1).unwrap(), data);
+        }
+        // clawhdf5 <= 2.7.0's pcodec chunks still go to the built-in reader.
+        #[cfg(feature = "pcodec")]
+        {
+            let raw: Vec<u8> = (0..64)
+                .flat_map(|i| (f64::from(i) * 0.5).to_le_bytes())
+                .collect();
+            let comp = crate::filters::pcodec_compress(&raw, 8).unwrap();
+            let mut pl = named(Some("pcodec"));
+            pl.filters[0].client_data = vec![8];
+            assert_eq!(decompress_chunk(&comp, &pl, raw.len(), 8).unwrap(), raw);
+        }
+        assert!(unregister_filter(32023));
+        let pl = named(None);
+        assert!(matches!(
+            decompress_chunk(&data, &pl, data.len(), 1),
+            Err(FormatError::UnsupportedFilter(32023))
+        ));
+    }
+
     #[test]
     fn unsupported_filter_error_names_the_filter() {
         let msg = FormatError::UnsupportedFilter(32026).to_string();

crates/clawhdf5-format/src/filters.rs

@@ -1446,7 +1446,7 @@ fn fletcher32_append(data: &[u8]) -> Result<Vec<u8>, FormatError> {
 // ---------------------------------------------------------------------------
 
 #[cfg(feature = "pcodec")]
-fn pcodec_compress(data: &[u8], element_size: usize) -> Result<Vec<u8>, FormatError> {
+pub(crate) fn pcodec_compress(data: &[u8], element_size: usize) -> Result<Vec<u8>, FormatError> {
     use pco::ChunkConfig;
     use pco::standalone::simple_compress;
     let config = ChunkConfig::default();
@@ -2758,6 +2758,10 @@ mod tests {
     #[cfg(feature = "pcodec")]
     fn pcodec_uses_private_id_and_reads_legacy_32023() {
         use crate::chunked_write::ChunkOptions;
+        #[cfg(feature = "std")]
+        let _guard = crate::filter_registry::tests::ID_32023
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
         let opts = ChunkOptions {
             pcodec: true,
             ..Default::default()