searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-05 04:28:55 +01:00
Code Issues Releases Wiki Activity

Make sure the first document is associated to the document id 0

Browse Source
This commit is contained in:
Clément Renault 2020-08-29 10:56:40 +02:00
parent 0a44ff86ab
commit 21aafd603c
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
1 changed files with 24 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/bin/indexer.rs
View File

@ -434,18 +434,16 @@ fn index_csv(
let mut document_id: usize = 0;
let mut document = csv::StringRecord::new();
while rdr.read_record(&mut document)? {
document_id = document_id + 1;
// We skip documents that must not be indexed by this thread
if document_id % num_threads != thread_index { continue }
let document_id = DocumentId::try_from(document_id).context("generated id is too big")?;
if document_id % (ONE_MILLION as u32) == 0 {
// We skip documents that must not be indexed by this thread.
if document_id % num_threads == thread_index {
if document_id % ONE_MILLION == 0 {
debug!("We have seen {}m documents so far ({:.02?}).",
document_id / ONE_MILLION as u32, before.elapsed());
document_id / ONE_MILLION, before.elapsed());
before = Instant::now();
}
let document_id = DocumentId::try_from(document_id).context("generated id is too big")?;
for (attr, content) in document.iter().enumerate().take(MAX_ATTRIBUTES) {
for (pos, word) in lexer::break_string(&content).enumerate().take(MAX_POSITION) {
let word = word.cow_to_lowercase();
@ -462,6 +460,10 @@ fn index_csv(
store.write_document(document_id, &document)?;
}
// Compute the document id of the the next document.
document_id = document_id + 1;
}
let (reader, docs_reader) = store.finish()?;
debug!("{:?}: Store created!", thread_index);
Ok((reader, docs_reader))