fix(format): write fill times with libhdf5's codes; add fill values

FillTime::to_byte had the fill-time field rotated against libhdf5
(H5D_FILL_TIME_ALLOC = 0, NEVER = 1, IFSET = 2): Never was written as
ALLOC, Alloc as IFSET and IfSet as NEVER, as h5py reported. The flags
byte is now late allocation plus the right code, and FillTime::from_byte
decodes it.

The default becomes IfSet, which is libhdf5's default and exactly the
byte (0x0a) every dataset was already written with, so default output
does not change; `Alloc` was documented as the C library's default but
never was. DatasetCreateProps follows.

DatasetBuilder::with_fill_value sets a user-defined fill value (one
element's stored bytes, checked against the datatype size), written as a
defined value in the fill value message. h5py reports it, and extending
the dataset in h5py fills the new elements with it.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-25 21:11:07 -05:00
co-authored by Claude Opus 5.5
parent 74fdf0582b
commit 8c3ef996ea
4 changed files with 193 additions and 35 deletions
+21 -19
View File
@@ -19,7 +19,7 @@ use crate::metadata_index::{DatasetMetadata, MetadataBlock, MetadataIndex};
use crate::object_header_writer::ObjectHeaderWriter;
use crate::superblock::Superblock;
use crate::type_builders::{
DatasetBuilder, FillTime, FinishedGroup, GroupBuilder, build_attr_message,
DatasetBuilder, FinishedGroup, GroupBuilder, build_attr_message, fill_value_message,
};
// Re-export public types that moved to type_builders for API compatibility.
@@ -80,12 +80,12 @@ pub(crate) fn build_chunked_dataset_oh(
pipeline_message: Option<&[u8]>,
attrs: &[AttributeMessage],
dense_blob: Option<&DenseAttrBlob>,
fill_time: FillTime,
fill_message: &[u8],
) -> Result<Vec<u8>, FormatError> {
let mut w = ObjectHeaderWriter::new();
w.add_message_with_flags(MessageType::Datatype, dt.serialize(), 0x01);
w.add_message(MessageType::Dataspace, ds.serialize(LENGTH_SIZE));
w.add_message_with_flags(MessageType::FillValue, vec![3, fill_time.to_byte()], 0x01);
w.add_message_with_flags(MessageType::FillValue, fill_message.to_vec(), 0x01);
w.add_message(MessageType::DataLayout, layout_message.to_vec());
if let Some(pm) = pipeline_message {
w.add_message(MessageType::FilterPipeline, pm.to_vec());
@@ -107,12 +107,12 @@ pub(crate) fn build_dataset_oh(
data_size: u64,
attrs: &[AttributeMessage],
dense_blob: Option<&DenseAttrBlob>,
fill_time: FillTime,
fill_message: &[u8],
) -> Result<Vec<u8>, FormatError> {
let mut w = ObjectHeaderWriter::new();
w.add_message_with_flags(MessageType::Datatype, dt.serialize(), 0x01);
w.add_message(MessageType::Dataspace, ds.serialize(LENGTH_SIZE));
w.add_message_with_flags(MessageType::FillValue, vec![3, fill_time.to_byte()], 0x01);
w.add_message_with_flags(MessageType::FillValue, fill_message.to_vec(), 0x01);
let mut dl = Vec::new();
dl.push(4); // version
dl.push(1); // class = contiguous
@@ -142,12 +142,12 @@ pub(crate) fn build_compact_dataset_oh(
data: &[u8],
attrs: &[AttributeMessage],
dense_blob: Option<&DenseAttrBlob>,
fill_time: FillTime,
fill_message: &[u8],
) -> Result<Vec<u8>, FormatError> {
let mut w = ObjectHeaderWriter::new();
w.add_message_with_flags(MessageType::Datatype, dt.serialize(), 0x01);
w.add_message(MessageType::Dataspace, ds.serialize(LENGTH_SIZE));
w.add_message_with_flags(MessageType::FillValue, vec![3, fill_time.to_byte()], 0x01);
w.add_message_with_flags(MessageType::FillValue, fill_message.to_vec(), 0x01);
// Compact layout message: version=4, class=0, u16 size, inline data
let mut dl = Vec::new();
dl.push(4); // version
@@ -932,12 +932,12 @@ pub(crate) fn build_vds_dataset_oh(
global_heap_addr: u64,
attrs: &[AttributeMessage],
dense_blob: Option<&DenseAttrBlob>,
fill_time: FillTime,
fill_message: &[u8],
) -> Result<Vec<u8>, FormatError> {
let mut w = ObjectHeaderWriter::new();
w.add_message_with_flags(MessageType::Datatype, dt.serialize(), 0x01);
w.add_message(MessageType::Dataspace, ds.serialize(LENGTH_SIZE));
w.add_message_with_flags(MessageType::FillValue, vec![3, fill_time.to_byte()], 0x01);
w.add_message_with_flags(MessageType::FillValue, fill_message.to_vec(), 0x01);
// VDS layout message: version=4, class=3, global_heap_address(8), global_heap_index=1(4)
let mut dl = Vec::new();
dl.push(4u8); // version
@@ -1070,7 +1070,8 @@ impl FileWriter {
attrs: Vec<AttributeMessage>,
chunk_options: ChunkOptions,
maxshape: Option<Vec<u64>>,
fill_time: FillTime,
/// Serialized Fill Value message.
fill_message: Vec<u8>,
compact: bool,
alignment: usize,
/// VDS source mappings (set for Virtual datasets).
@@ -1120,6 +1121,7 @@ impl FileWriter {
};
attrs.extend(p.build_attrs(&raw));
}
let fill_message = fill_value_message(db.fill_time, db.fill_value.as_deref(), &dt)?;
Ok(DsFlat {
name: db.name,
dt,
@@ -1128,7 +1130,7 @@ impl FileWriter {
attrs,
chunk_options: db.chunk_options,
maxshape: db.maxshape,
fill_time: db.fill_time,
fill_message,
compact: db.compact,
alignment: db.alignment,
virtual_sources: db.virtual_sources,
@@ -1274,7 +1276,7 @@ impl FileWriter {
0, // dummy address
&d.attrs,
dense_blob.as_ref(),
d.fill_time,
&d.fill_message,
)?;
// Global heap blob size is address-independent; compute it now
// so pass 2 can place it correctly.
@@ -1318,7 +1320,7 @@ impl FileWriter {
result.pipeline_message.as_deref(),
&d.attrs,
dense_blob.as_ref(),
d.fill_time,
&d.fill_message,
)?;
dummy_blobs.push(DataBlob {
data: result.data_bytes,
@@ -1337,7 +1339,7 @@ impl FileWriter {
&d.raw,
&d.attrs,
dense_blob.as_ref(),
d.fill_time,
&d.fill_message,
)?;
dummy_blobs.push(DataBlob {
data: vec![],
@@ -1357,7 +1359,7 @@ impl FileWriter {
d.raw.len() as u64,
&d.attrs,
dense_blob.as_ref(),
d.fill_time,
&d.fill_message,
)?;
dummy_blobs.push(DataBlob {
data: d.raw.clone(),
@@ -1466,7 +1468,7 @@ impl FileWriter {
heap_addr,
&d.attrs,
ds_dense_blobs[i].as_ref(),
d.fill_time,
&d.fill_message,
)?;
ds_blobs2.push(DataBlob {
data: gcol_bytes.clone(),
@@ -1493,7 +1495,7 @@ impl FileWriter {
result.pipeline_message.as_deref(),
&d.attrs,
ds_dense_blobs[i].as_ref(),
d.fill_time,
&d.fill_message,
)?;
ds_blobs2.push(DataBlob {
data: result.data_bytes,
@@ -1508,7 +1510,7 @@ impl FileWriter {
&d.raw,
&d.attrs,
ds_dense_blobs[i].as_ref(),
d.fill_time,
&d.fill_message,
)?;
ds_blobs2.push(DataBlob {
data: vec![],
@@ -1533,7 +1535,7 @@ impl FileWriter {
d.raw.len() as u64,
&d.attrs,
ds_dense_blobs[i].as_ref(),
d.fill_time,
&d.fill_message,
)?;
let mut data = vec![0u8; padding];
data.extend_from_slice(&d.raw);