remove multiple bugs

This commit is contained in:
Irevoire 2021-08-25 16:59:38 +02:00 committed by Tamo
parent b4b6ba6d82
commit 70ab2c37c5
No known key found for this signature in database
GPG Key ID: 20CD8020AFA88D69
3 changed files with 21 additions and 20 deletions

View File

@ -21,19 +21,22 @@ pub fn extract_geo_points<R: io::Read>(
})?;
// we never encountered any documents with a `_geo` field. We can skip entirely this step
if geo_field_id.is_none() {
return Ok(writer_into_reader(writer)?);
}
let geo_field_id = geo_field_id.unwrap();
let geo_field_id = match geo_field_id {
Some(geo) => geo,
None => return Ok(writer_into_reader(writer)?),
};
while let Some((docid_bytes, value)) = obkv_documents.next()? {
let obkv = obkv::KvReader::new(value);
let point = obkv.get(geo_field_id).unwrap(); // TODO: TAMO where should we handle this error?
let point = match obkv.get(geo_field_id) {
Some(point) => point,
None => continue,
};
let point: Value = serde_json::from_slice(point).map_err(InternalError::SerdeJson)?;
if let Some((lat, lng)) = point["lat"].as_f64().zip(point["lng"].as_f64()) {
// this will create an array of 16 bytes (two 8 bytes floats)
let bytes: [u8; 16] = concat_arrays![lat.to_le_bytes(), lng.to_le_bytes()];
let bytes: [u8; 16] = concat_arrays![lat.to_ne_bytes(), lng.to_ne_bytes()];
writer.insert(docid_bytes, bytes)?;
} else {
// TAMO: improve the warn

View File

@ -51,13 +51,14 @@ pub(crate) fn data_from_obkv_documents(
lmdb_writer_sx.clone(),
&searchable_fields,
&faceted_fields,
geo_field_id,
&stop_words,
)
})
.collect();
let (
(docid_word_positions_chunks),
docid_word_positions_chunks,
(docid_fid_facet_numbers_chunks, docid_fid_facet_strings_chunks),
) = result?;
@ -121,16 +122,6 @@ pub(crate) fn data_from_obkv_documents(
"field-id-facet-number-docids",
);
spawn_extraction_task(
documents_chunk,
indexer.clone(),
lmdb_writer_sx.clone(),
move |documents, indexer| extract_geo_points(documents, indexer, geo_field_id),
merge_cbo_roaring_bitmaps,
TypedChunk::GeoPoints,
"geo-points",
);
Ok(())
}
@ -181,6 +172,7 @@ fn extract_documents_data(
lmdb_writer_sx: Sender<Result<TypedChunk>>,
searchable_fields: &Option<HashSet<FieldId>>,
faceted_fields: &HashSet<FieldId>,
geo_field_id: Option<FieldId>,
stop_words: &Option<fst::Set<&[u8]>>,
) -> Result<(
grenad::Reader<CursorClonableMmap>,
@ -190,6 +182,12 @@ fn extract_documents_data(
let _ = lmdb_writer_sx.send(Ok(TypedChunk::Documents(documents_chunk.clone())));
let (documents_chunk_cloned, lmdb_writer_sx_cloned) = (documents_chunk.clone(), lmdb_writer_sx.clone());
rayon::spawn(move || {
let geo_points = extract_geo_points(documents_chunk_cloned, indexer, geo_field_id).unwrap();
lmdb_writer_sx_cloned.send(Ok(TypedChunk::GeoPoints(geo_points))).unwrap();
});
let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
rayon::join(
|| {

View File

@ -181,16 +181,16 @@ pub(crate) fn write_typed_chunk_into_index(
}
TypedChunk::GeoPoints(mut geo_points) => {
// TODO: TAMO: we should create the rtree with the `RTree::bulk_load` function
let mut rtree = index.geo_rtree(&index.read_txn()?)?.unwrap_or_default();
let mut rtree = index.geo_rtree(wtxn)?.unwrap_or_default();
while let Some((key, value)) = geo_points.next()? {
// convert the key back to a u32 (4 bytes)
let (key, _) = helpers::try_split_array_at::<u8, 4>(key).unwrap();
let key = u32::from_le_bytes(key);
let key = u32::from_be_bytes(key);
// convert the latitude and longitude back to a f64 (8 bytes)
let (lat, tail) = helpers::try_split_array_at::<u8, 8>(value).unwrap();
let (lng, _) = helpers::try_split_array_at::<u8, 8>(tail).unwrap();
let point = [f64::from_le_bytes(lat), f64::from_le_bytes(lng)];
let point = [f64::from_ne_bytes(lat), f64::from_ne_bytes(lng)];
rtree.insert(GeoPoint::new(point, key));
}
index.put_geo_rtree(wtxn, &rtree)?;