mirror of
https://github.com/meilisearch/MeiliSearch
synced 2025-07-04 20:37:15 +02:00
Implement documents format
document reader transform remove update format support document sequences fix document transform clean transform improve error handling add documents! macro fix transform bug fix tests remove csv dependency Add comments on the transform process replace search cli fmt review edits fix http ui fix clippy warnings Revert "fix clippy warnings" This reverts commit a1ce3cd96e603633dbf43e9e0b12b2453c9c5620. fix review comments remove smallvec in transform loop review edits
This commit is contained in:
parent
94764e5c7c
commit
aa6c5df0bc
25 changed files with 5114 additions and 713 deletions
|
@ -2,10 +2,9 @@ use UpdateIndexingStep::*;
|
|||
|
||||
#[derive(Debug, Clone, Copy)]
|
||||
pub enum UpdateIndexingStep {
|
||||
/// Transform from the original user given format (CSV, JSON, JSON lines)
|
||||
/// into a generic format based on the obkv and grenad crates. This step also
|
||||
/// deduplicate potential documents in this batch update by merging or replacing them.
|
||||
TransformFromUserIntoGenericFormat { documents_seen: usize },
|
||||
/// Remap document addition fields the one present in the database, adding new fields in to the
|
||||
/// schema on the go.
|
||||
RemapDocumentAddition { documents_seen: usize },
|
||||
|
||||
/// This step check the external document id, computes the internal ids and merge
|
||||
/// the documents that are already present in the database.
|
||||
|
@ -23,7 +22,7 @@ pub enum UpdateIndexingStep {
|
|||
impl UpdateIndexingStep {
|
||||
pub const fn step(&self) -> usize {
|
||||
match self {
|
||||
TransformFromUserIntoGenericFormat { .. } => 0,
|
||||
RemapDocumentAddition { .. } => 0,
|
||||
ComputeIdsAndMergeDocuments { .. } => 1,
|
||||
IndexDocuments { .. } => 2,
|
||||
MergeDataIntoFinalDatabase { .. } => 3,
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue