Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

refactor doc mapper #5522

Merged
merged 2 commits into from
Oct 24, 2024
Merged

refactor doc mapper #5522

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9525d50
refactor doc mapper
PSeitz Oct 24, 2024
dcc9170
use base64 for bytes
PSeitz Oct 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
118 changes: 5 additions & 113 deletions quickwit/quickwit-doc-mapper/src/doc_mapper/doc_mapper_impl.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ use std::num::NonZeroU32;

use anyhow::{bail, Context};
use fnv::FnvHashSet;
use quickwit_common::PathHasher;
use quickwit_proto::types::DocMappingUid;
use quickwit_query::create_default_quickwit_tokenizer_manager;
use quickwit_query::query_ast::QueryAst;
Expand All @@ -31,13 +30,12 @@ use serde::{Deserialize, Serialize};
use serde_json::{self, Value as JsonValue};
use serde_json_borrow::Map as BorrowedJsonMap;
use tantivy::query::Query;
use tantivy::schema::document::{ReferenceValue, ReferenceValueLeaf};
use tantivy::schema::{
Field, FieldType, OwnedValue as TantivyValue, Schema, Value, INDEXED, STORED,
};
use tantivy::schema::{Field, FieldType, OwnedValue as TantivyValue, Schema, INDEXED, STORED};
use tantivy::TantivyDocument as Document;

use super::field_mapping_entry::RAW_TOKENIZER_NAME;
use super::field_presence::populate_field_presence;
use super::tantivy_val_to_json::tantivy_value_to_json;
use super::DocMapperBuilder;
use crate::doc_mapper::mapping_tree::{
build_field_path_from_str, build_mapping_tree, map_primitive_json_to_tantivy,
Expand Down Expand Up @@ -430,85 +428,6 @@ fn extract_single_obj(
}
}

// TODO: Formatting according to mapper if applicable
fn tantivy_value_to_json(val: TantivyValue) -> JsonValue {
match val {
TantivyValue::Null => JsonValue::Null,
TantivyValue::Str(val) => JsonValue::String(val),
TantivyValue::PreTokStr(val) => JsonValue::String(val.text),
TantivyValue::U64(val) => JsonValue::Number(val.into()),
TantivyValue::I64(val) => JsonValue::Number(val.into()),
TantivyValue::F64(val) => serde_json::json!(val),
TantivyValue::Bool(val) => JsonValue::Bool(val),
TantivyValue::Date(val) => JsonValue::String(format!("{:?}", val)),
TantivyValue::Facet(val) => JsonValue::String(val.to_string()),
TantivyValue::Bytes(val) => JsonValue::String(format!("{:?}", val)),
TantivyValue::Array(val) => val.into_iter().map(tantivy_value_to_json).collect(),
TantivyValue::Object(val) => val
.into_iter()
.map(|(key, val)| (key, tantivy_value_to_json(val)))
.collect(),
TantivyValue::IpAddr(val) => JsonValue::String(format!("{:?}", val)),
}
}

#[inline]
fn populate_field_presence_for_json_value<'a>(
json_value: impl Value<'a>,
path_hasher: &PathHasher,
is_expand_dots_enabled: bool,
output: &mut FnvHashSet<u64>,
) {
match json_value.as_value() {
ReferenceValue::Leaf(ReferenceValueLeaf::Null) => {}
ReferenceValue::Leaf(_) => {
output.insert(path_hasher.finish());
}
ReferenceValue::Array(items) => {
for item in items {
populate_field_presence_for_json_value(
item,
path_hasher,
is_expand_dots_enabled,
output,
);
}
}
ReferenceValue::Object(json_obj) => {
populate_field_presence_for_json_obj(
json_obj,
path_hasher.clone(),
is_expand_dots_enabled,
output,
);
}
}
}

fn populate_field_presence_for_json_obj<'a, Iter: Iterator<Item = (&'a str, impl Value<'a>)>>(
json_obj: Iter,
path_hasher: PathHasher,
is_expand_dots_enabled: bool,
output: &mut FnvHashSet<u64>,
) {
for (field_key, field_value) in json_obj {
let mut child_path_hasher = path_hasher.clone();
if is_expand_dots_enabled {
for segment in field_key.split('.') {
child_path_hasher.append(segment.as_bytes());
}
} else {
child_path_hasher.append(field_key.as_bytes());
};
populate_field_presence_for_json_value(
field_value,
&child_path_hasher,
is_expand_dots_enabled,
output,
);
}
}

impl DocMapper {
/// Returns the unique identifier of the doc mapping.
pub fn doc_mapping_uid(&self) -> DocMappingUid {
Expand Down Expand Up @@ -636,36 +555,9 @@ impl DocMapper {
document.add_u64(document_size_field, document_len);
}

// The capacity is inexact here.

if self.index_field_presence {
let mut field_presence_hashes: FnvHashSet<u64> =
FnvHashSet::with_capacity_and_hasher(document.len(), Default::default());
for (field, value) in document.field_values() {
let field_entry = self.schema.get_field_entry(field);
if !field_entry.is_indexed() || field_entry.is_fast() {
// We are using an tantivy's ExistsQuery for fast fields.
continue;
}
let mut path_hasher: PathHasher = PathHasher::default();
path_hasher.append(&field.field_id().to_le_bytes()[..]);
if let Some(json_obj) = value.as_object() {
let is_expand_dots_enabled: bool =
if let FieldType::JsonObject(json_options) = field_entry.field_type() {
json_options.is_expand_dots_enabled()
} else {
false
};
populate_field_presence_for_json_obj(
json_obj,
path_hasher,
is_expand_dots_enabled,
&mut field_presence_hashes,
);
} else {
field_presence_hashes.insert(path_hasher.finish());
}
}
let field_presence_hashes: FnvHashSet<u64> =
populate_field_presence(&document, &self.schema);
for field_presence_hash in field_presence_hashes {
document.add_field_value(FIELD_PRESENCE_FIELD, &field_presence_hash);
}
Expand Down
121 changes: 121 additions & 0 deletions quickwit/quickwit-doc-mapper/src/doc_mapper/field_presence.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,121 @@
// Copyright (C) 2024 Quickwit, Inc.
//
// Quickwit is offered under the AGPL v3.0 and as commercial software.
// For commercial licensing, contact us at [email protected].
//
// AGPL:
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.

use fnv::FnvHashSet;
use quickwit_common::PathHasher;
use tantivy::schema::document::{ReferenceValue, ReferenceValueLeaf};
use tantivy::schema::{FieldType, Schema, Value};
use tantivy::Document;

/// Populates the field presence for a document.
///
/// The field presence is a set of hashes that represent the fields that are present in the
/// document. Each hash is computed from the field path.
///
/// It is only added if the field is indexed and not fast.
pub(crate) fn populate_field_presence<D: Document>(
document: &D,
schema: &Schema,
) -> FnvHashSet<u64> {
let mut field_presence_hashes: FnvHashSet<u64> =
FnvHashSet::with_capacity_and_hasher(schema.num_fields(), Default::default());
for (field, value) in document.iter_fields_and_values() {
let field_entry = schema.get_field_entry(field);
if !field_entry.is_indexed() || field_entry.is_fast() {
// We are using an tantivy's ExistsQuery for fast fields.
continue;
}
let mut path_hasher: PathHasher = PathHasher::default();
path_hasher.append(&field.field_id().to_le_bytes()[..]);
if let Some(json_obj) = value.as_object() {
let is_expand_dots_enabled: bool =
if let FieldType::JsonObject(json_options) = field_entry.field_type() {
json_options.is_expand_dots_enabled()
} else {
false
};
populate_field_presence_for_json_obj(
json_obj,
path_hasher,
is_expand_dots_enabled,
&mut field_presence_hashes,
);
} else {
field_presence_hashes.insert(path_hasher.finish());
}
}
field_presence_hashes
}

#[inline]
fn populate_field_presence_for_json_value<'a>(
json_value: impl Value<'a>,
path_hasher: &PathHasher,
is_expand_dots_enabled: bool,
output: &mut FnvHashSet<u64>,
) {
match json_value.as_value() {
ReferenceValue::Leaf(ReferenceValueLeaf::Null) => {}
ReferenceValue::Leaf(_) => {
output.insert(path_hasher.finish());
}
ReferenceValue::Array(items) => {
for item in items {
populate_field_presence_for_json_value(
item,
path_hasher,
is_expand_dots_enabled,
output,
);
}
}
ReferenceValue::Object(json_obj) => {
populate_field_presence_for_json_obj(
json_obj,
path_hasher.clone(),
is_expand_dots_enabled,
output,
);
}
}
}

fn populate_field_presence_for_json_obj<'a, Iter: Iterator<Item = (&'a str, impl Value<'a>)>>(
json_obj: Iter,
path_hasher: PathHasher,
is_expand_dots_enabled: bool,
output: &mut FnvHashSet<u64>,
) {
for (field_key, field_value) in json_obj {
let mut child_path_hasher = path_hasher.clone();
if is_expand_dots_enabled {
for segment in field_key.split('.') {
child_path_hasher.append(segment.as_bytes());
}
} else {
child_path_hasher.append(field_key.as_bytes());
};
populate_field_presence_for_json_value(
field_value,
&child_path_hasher,
is_expand_dots_enabled,
output,
);
}
}
Loading
Loading