rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-06-05 18:10:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix truncate, remove mutable access from term

Browse Source
This commit is contained in:
Pascal Seitz
2022-10-14 13:37:29 +08:00
parent fcfd76ec55
commit 8d75e451bd
4 changed files with 45 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/indexer/json_term_writer.rs
View File

@@ -242,10 +242,12 @@ pub(crate) fn set_string_and_get_terms(
) -> Vec<(usize, Term)> {
let mut positions_and_terms = Vec::<(usize, Term)>::new();
json_term_writer.close_path_and_set_type(Type::Str);
let term_num_bytes = json_term_writer.term_buffer.as_slice().len();
let term_num_bytes = json_term_writer.term_buffer.len_bytes();
let mut token_stream = text_analyzer.token_stream(value);
token_stream.process(&mut |token| {
json_term_writer.term_buffer.truncate(term_num_bytes);
json_term_writer
.term_buffer
.truncate_value_bytes(term_num_bytes);
json_term_writer
.term_buffer
.append_bytes(token.text.as_bytes());
@@ -260,7 +262,11 @@ pub struct JsonTermWriter<'a> {
}
impl<'a> JsonTermWriter<'a> {
pub fn from_json_path(json_path: &str, field: Field, term_buffer: &'a mut Term) -> Self {
pub fn from_field_and_json_path(
field: Field,
json_path: &str,
term_buffer: &'a mut Term,
) -> Self {
term_buffer.set_field_and_type(field, Type::Json);
let mut json_term_writer = Self::wrap(term_buffer);
for segment in json_path.split('.') {
@@ -272,7 +278,7 @@ impl<'a> JsonTermWriter<'a> {
pub fn wrap(term_buffer: &'a mut Term) -> Self {
term_buffer.clear_with_type(Type::Json);
let mut path_stack = Vec::with_capacity(10);
path_stack.push(5);
path_stack.push(0);
Self {
term_buffer,
path_stack,
@@ -281,28 +287,28 @@ impl<'a> JsonTermWriter<'a> {
fn trim_to_end_of_path(&mut self) {
let end_of_path = *self.path_stack.last().unwrap();
self.term_buffer.truncate(end_of_path);
self.term_buffer.truncate_value_bytes(end_of_path);
}
pub fn close_path_and_set_type(&mut self, typ: Type) {
self.trim_to_end_of_path();
let buffer = self.term_buffer.as_mut();
let buffer = self.term_buffer.value_bytes_mut();
let buffer_len = buffer.len();
buffer[buffer_len - 1] = JSON_END_OF_PATH;
buffer.push(typ.to_code());
self.term_buffer.append_bytes(&[typ.to_code()]);
}
pub fn push_path_segment(&mut self, segment: &str) {
// the path stack should never be empty.
self.trim_to_end_of_path();
let buffer = self.term_buffer.as_mut();
let buffer = self.term_buffer.value_bytes_mut();
let buffer_len = buffer.len();
if self.path_stack.len() > 1 {
buffer[buffer_len - 1] = JSON_PATH_SEGMENT_SEP;
}
buffer.extend(segment.as_bytes());
buffer.push(JSON_PATH_SEGMENT_SEP);
self.path_stack.push(buffer.len());
self.term_buffer.append_bytes(segment.as_bytes());
self.term_buffer.append_bytes(&[JSON_PATH_SEGMENT_SEP]);
self.path_stack.push(self.term_buffer.len_bytes());
}
pub fn pop_path_segment(&mut self) {
@@ -314,8 +320,8 @@ impl<'a> JsonTermWriter<'a> {
/// Returns the json path of the term being currently built.
#[cfg(test)]
pub(crate) fn path(&self) -> &[u8] {
let end_of_path = self.path_stack.last().cloned().unwrap_or(6);
&self.term().as_slice()[5..end_of_path - 1]
let end_of_path = self.path_stack.last().cloned().unwrap_or(1);
&self.term().value_bytes()[..end_of_path - 1]
}
pub fn set_fast_value<T: FastValue>(&mut self, val: T) {
@@ -328,14 +334,13 @@ impl<'a> JsonTermWriter<'a> {
val.to_u64()
};
self.term_buffer
.as_mut()
.extend_from_slice(value.to_be_bytes().as_slice());
.append_bytes(value.to_be_bytes().as_slice());
}
#[cfg(test)]
pub(crate) fn set_str(&mut self, text: &str) {
self.close_path_and_set_type(Type::Str);
self.term_buffer.as_mut().extend_from_slice(text.as_bytes());
self.term_buffer.append_bytes(text.as_bytes());
}
pub fn term(&self) -> &Term {

6
src/postings/postings_writer.rs
View File

@@ -153,7 +153,7 @@ pub(crate) trait PostingsWriter: Send + Sync {
indexing_position: &mut IndexingPosition,
mut term_id_fast_field_writer_opt: Option<&mut MultiValuedFastFieldWriter>,
) {
let end_of_path_idx = term_buffer.as_slice().len();
let end_of_path_idx = term_buffer.len_bytes();
let mut num_tokens = 0;
let mut end_position = 0;
token_stream.process(&mut |token: &Token| {
@@ -167,7 +167,7 @@ pub(crate) trait PostingsWriter: Send + Sync {
);
return;
}
term_buffer.truncate(end_of_path_idx);
term_buffer.truncate_value_bytes(end_of_path_idx);
term_buffer.append_bytes(token.text.as_bytes());
let start_position = indexing_position.end_position + token.position as u32;
end_position = start_position + token.position_length as u32;
@@ -181,7 +181,7 @@ pub(crate) trait PostingsWriter: Send + Sync {
indexing_position.end_position = end_position + POSITION_GAP;
indexing_position.num_tokens += num_tokens;
term_buffer.truncate(end_of_path_idx);
term_buffer.truncate_value_bytes(end_of_path_idx);
}
fn total_num_tokens(&self) -> u64;

3
src/query/query_parser/query_parser.rs
View File

@@ -735,7 +735,8 @@ fn generate_literals_for_json_object(
) -> Result<Vec<LogicalLiteral>, QueryParserError> {
let mut logical_literals = Vec::new();
let mut term = Term::with_capacity(100);
let mut json_term_writer = JsonTermWriter::from_json_path(json_path, field, &mut term);
let mut json_term_writer =
JsonTermWriter::from_field_and_json_path(field, json_path, &mut term);
if let Some(term) = convert_to_fast_value_and_get_term(&mut json_term_writer, phrase) {
logical_literals.push(LogicalLiteral::Term(term));
}

38
src/schema/term.rs
View File

@@ -24,12 +24,6 @@ pub const JSON_END_OF_PATH: u8 = 0u8;
pub struct Term<B = Vec<u8>>(B)
where B: AsRef<[u8]>;
impl AsMut<Vec<u8>> for Term {
fn as_mut(&mut self) -> &mut Vec<u8> {
&mut self.0
}
}
/// The number of bytes used as metadata by `Term`.
const TERM_METADATA_LENGTH: usize = 5;
@@ -55,16 +49,16 @@ impl Term {
fn from_fast_value<T: FastValue>(field: Field, val: &T) -> Term {
let mut term = Self::with_type_and_field(T::to_type(), field);
term.set_field_and_type(field, T::to_type());
term.set_u64(val.to_u64());
term
}
/// Panics when there are byte values.
/// Panics when the term is not empty... ie: some value is set.
/// Use `clear_with_field_and_type` in that case.
///
/// Sets field and the type.
pub(crate) fn set_field_and_type(&mut self, field: Field, typ: Type) {
assert_eq!(self.0.len(), TERM_METADATA_LENGTH);
assert!(self.is_empty());
self.0[0..4].clone_from_slice(field.field_id().to_be_bytes().as_ref());
self.0[4] = typ.to_code();
}
@@ -173,11 +167,26 @@ impl Term {
}
/// Truncates the term. The new length needs to be at least 5, which is reserved for metadata.
pub fn truncate(&mut self, len: usize) {
fn truncate(&mut self, len: usize) {
assert!(len >= TERM_METADATA_LENGTH);
self.0.truncate(len);
}
/// Truncates the value bytes of the term. Value and field type stays the same.
pub fn truncate_value_bytes(&mut self, len: usize) {
self.0.truncate(len + TERM_METADATA_LENGTH);
}
/// Returns the value bytes as mutable slice
pub fn value_bytes_mut(&mut self) -> &mut [u8] {
&mut self.0[TERM_METADATA_LENGTH..]
}
/// The length of the bytes.
pub fn len_bytes(&self) -> usize {
self.0.len() - TERM_METADATA_LENGTH
}
/// Appends value bytes to the Term.
pub fn append_bytes(&mut self, bytes: &[u8]) {
self.0.extend_from_slice(bytes);
@@ -304,9 +313,6 @@ where B: AsRef<[u8]>
/// Returns `None` if the field is not of string type
/// or if the bytes are not valid utf-8.
pub fn as_str(&self) -> Option<&str> {
if self.as_slice().len() < TERM_METADATA_LENGTH {
return None;
}
if self.typ() != Type::Str {
return None;
}
@@ -318,9 +324,6 @@ where B: AsRef<[u8]>
/// Returns `None` if the field is not of facet type
/// or if the bytes are not valid utf-8.
pub fn as_facet(&self) -> Option<Facet> {
if self.as_slice().len() < TERM_METADATA_LENGTH {
return None;
}
if self.typ() != Type::Facet {
return None;
}
@@ -332,9 +335,6 @@ where B: AsRef<[u8]>
///
/// Returns `None` if the field is not of bytes type.
pub fn as_bytes(&self) -> Option<&[u8]> {
if self.as_slice().len() < TERM_METADATA_LENGTH {
return None;
}
if self.typ() != Type::Bytes {
return None;
}