searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-23 13:10:06 +01:00
Code Issues Releases Wiki Activity

Fix index_documents_check_exists_database

Browse Source
This commit is contained in:
ManyTheFish 2024-11-20 09:44:23 +01:00 committed by Clément Renault
parent ba7f091db3
commit b1f8aec348
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
3 changed files with 103 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
crates/milli/src/update/new/extract/faceted/facet_document.rs
View File

@ -24,25 +24,46 @@ pub fn extract_document_facets<'doc>(
};
// if the current field is searchable or contains a searchable attribute
if perm_json_p::select_field(field_name, Some(attributes_to_extract), &[]) {
let selection = perm_json_p::select_field(field_name, Some(attributes_to_extract), &[]);
if selection != perm_json_p::Selection::Skip {
// parse json.
match serde_json::value::to_value(value).map_err(InternalError::SerdeJson)? {
Value::Object(object) => perm_json_p::seek_leaf_values_in_object(
&object,
Some(attributes_to_extract),
&[], // skip no attributes
field_name,
perm_json_p::Depth::OnBaseKey,
&mut tokenize_field,
)?,
Value::Array(array) => perm_json_p::seek_leaf_values_in_array(
&array,
Some(attributes_to_extract),
&[], // skip no attributes
field_name,
perm_json_p::Depth::OnBaseKey,
&mut tokenize_field,
)?,
Value::Object(object) => {
perm_json_p::seek_leaf_values_in_object(
&object,
Some(attributes_to_extract),
&[], // skip no attributes
field_name,
perm_json_p::Depth::OnBaseKey,
&mut tokenize_field,
)?;
if selection == perm_json_p::Selection::Select {
tokenize_field(
field_name,
perm_json_p::Depth::OnBaseKey,
&Value::Object(object),
)?;
}
}
Value::Array(array) => {
perm_json_p::seek_leaf_values_in_array(
&array,
Some(attributes_to_extract),
&[], // skip no attributes
field_name,
perm_json_p::Depth::OnBaseKey,
&mut tokenize_field,
)?;
if selection == perm_json_p::Selection::Select {
tokenize_field(
field_name,
perm_json_p::Depth::OnBaseKey,
&Value::Array(array),
)?;
}
}
value => tokenize_field(field_name, perm_json_p::Depth::OnBaseKey, &value)?,
}
}

86
crates/milli/src/update/new/extract/mod.rs
View File

@ -88,25 +88,37 @@ pub mod perm_json_p {
// here if the user only specified `doggo` we need to iterate in all the fields of `doggo`
// so we check the contained_in on both side
let should_continue = select_field(&base_key, selectors, skip_selectors);
if should_continue {
let selection = select_field(&base_key, selectors, skip_selectors);
if selection != Selection::Skip {
match value {
Value::Object(object) => seek_leaf_values_in_object(
object,
selectors,
skip_selectors,
&base_key,
Depth::OnBaseKey,
seeker,
),
Value::Array(array) => seek_leaf_values_in_array(
array,
selectors,
skip_selectors,
&base_key,
Depth::OnBaseKey,
seeker,
),
Value::Object(object) => {
if selection == Selection::Select {
seeker(&base_key, Depth::OnBaseKey, value)?;
}
seek_leaf_values_in_object(
object,
selectors,
skip_selectors,
&base_key,
Depth::OnBaseKey,
seeker,
)
}
Value::Array(array) => {
if selection == Selection::Select {
seeker(&base_key, Depth::OnBaseKey, value)?;
}
seek_leaf_values_in_array(
array,
selectors,
skip_selectors,
&base_key,
Depth::OnBaseKey,
seeker,
)
}
value => seeker(&base_key, Depth::OnBaseKey, value),
}?;
}
@ -156,13 +168,37 @@ pub mod perm_json_p {
field_name: &str,
selectors: Option<&[&str]>,
skip_selectors: &[&str],
) -> bool {
selectors.map_or(true, |selectors| {
selectors.iter().any(|selector| {
contained_in(selector, field_name) || contained_in(field_name, selector)
})
}) && !skip_selectors.iter().any(|skip_selector| {
) -> Selection {
if skip_selectors.iter().any(|skip_selector| {
contained_in(skip_selector, field_name) || contained_in(field_name, skip_selector)
})
}) {
Selection::Skip
} else if let Some(selectors) = selectors {
selectors
.iter()
.filter_map(|selector| {
if contained_in(field_name, selector) {
Some(Selection::Select)
} else if contained_in(selector, field_name) {
Some(Selection::Parent)
} else {
None
}
})
.next()
.unwrap_or(Selection::Skip)
} else {
Selection::Select
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Selection {
/// The field is a parent of the of a nested field that must be selected
Parent,
/// The field must be selected
Select,
/// The field must be skipped
Skip,
}
}

6
crates/milli/src/update/new/extract/searchable/tokenize_document.rs
View File

@ -5,7 +5,7 @@ use serde_json::Value;
use crate::update::new::document::Document;
use crate::update::new::extract::perm_json_p::{
seek_leaf_values_in_array, seek_leaf_values_in_object, select_field, Depth,
seek_leaf_values_in_array, seek_leaf_values_in_object, select_field, Depth, Selection,
};
use crate::{
FieldId, GlobalFieldsIdsMap, InternalError, LocalizedAttributesRule, Result, UserError,
@ -88,7 +88,9 @@ impl<'a> DocumentTokenizer<'a> {
};
// if the current field is searchable or contains a searchable attribute
if select_field(field_name, self.attribute_to_extract, self.attribute_to_skip) {
if select_field(field_name, self.attribute_to_extract, self.attribute_to_skip)
!= Selection::Skip
{
// parse json.
match serde_json::to_value(value).map_err(InternalError::SerdeJson)? {
Value::Object(object) => seek_leaf_values_in_object(