rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-05-26 21:20:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Uncommenting unit test

Browse Source
This commit is contained in:
Paul Masurel
2017-05-18 20:41:56 +09:00
parent e79a316e41
commit ca76fd5ba0
3 changed files with 78 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/core/searcher.rs
View File

@@ -7,7 +7,9 @@ use query::Query;
use DocId;
use DocAddress;
use schema::Term;
use datastruct::fstmap::FstMerger;
use std::fmt;
use postings::TermInfo;
/// Holds a list of `SegmentReader`s ready for search.
@@ -62,6 +64,18 @@ impl Searcher {
pub fn search<C: Collector>(&self, query: &Query, collector: &mut C) -> Result<TimerTree> {
query.search(self, collector)
}
/// Returns a Stream over all of the sorted unique terms of
/// the searcher.
///
/// This includes all of the fields from all of the segment_readers.
/// See [TermIterator](struct.TermIterator.html).
///
/// # Warning
/// This API is very likely to change in the future.
pub fn terms(&self) -> FstMerger<TermInfo> {
FstMerger::from(self.segment_readers())
}
}

7
src/core/segment_reader.rs
View File

@@ -171,7 +171,7 @@ impl SegmentReader {
}
/// Return the term dictionary datastructure.
pub fn term_infos<'b>(&'b self) -> &'b FstMap<TermInfo> {
pub fn term_infos(&self) -> &FstMap<TermInfo> {
&self.term_infos
}
@@ -227,11 +227,6 @@ impl SegmentReader {
_ => { SegmentPostingsOption::NoFreq },
};
Some(self.read_postings_from_terminfo(&term_info, possible_option))
// SegmentPostings::from_data(term_info.doc_freq,
// postings_data,
// &self.delete_bitset,
// freq_handler))
}
pub fn read_postings_from_terminfo(&self,

140
src/datastruct/fstmap/fstmerger.rs
View File

@@ -4,7 +4,7 @@ use super::FstMapStreamer;
use common::BinarySerializable;
use postings::TermInfo;
use std::cmp::Ordering;
use fst::Streamer;
pub struct HeapItem<'a, V> where V: 'a + BinarySerializable {
pub streamer: FstMapStreamer<'a, V>,
@@ -117,35 +117,6 @@ impl<'a, V> FstMerger<'a, V> where V: 'a + BinarySerializable {
/*
/// Returns the sorted list of segment ordinals
/// that include the current term.
///
/// This method may be called
/// iff advance() has been called before
/// and "true" was returned.
pub fn segment_ords(&self) -> &[usize] {
&self.current_segment_ords[..]
}
*/
/*
impl<'a, V> Streamer<'a> for FstMerger<'a, V> {
type Item = &'a Term;
fn next(&'a mut self) -> Option<Self::Item> {
if self.advance() {
Some(&self.current_term)
} else {
None
}
}
}
*/
impl<'a> From<&'a [SegmentReader]> for FstMerger<'a, TermInfo> where TermInfo: BinarySerializable {
fn from(segment_readers: &'a [SegmentReader]) -> FstMerger<'a, TermInfo> {
FstMerger::new(segment_readers
@@ -155,52 +126,67 @@ impl<'a> From<&'a [SegmentReader]> for FstMerger<'a, TermInfo> where TermInfo: B
}
}
// #[cfg(test)]
// mod tests {
// use super::*;
// use schema::{SchemaBuilder, Document, TEXT};
// use core::Index;
impl<'a, V> Streamer<'a> for FstMerger<'a, V> where V: BinarySerializable {
type Item = &'a [u8];
// #[test]
// fn test_term_iterator() {
// let mut schema_builder = SchemaBuilder::default();
// let text_field = schema_builder.add_text_field("text", TEXT);
// let index = Index::create_in_ram(schema_builder.build());
// {
// let mut index_writer = index.writer_with_num_threads(1, 40_000_000).unwrap();
// {
// {
// let mut doc = Document::default();
// doc.add_text(text_field, "a b d f");
// index_writer.add_document(doc);
// }
// index_writer.commit().unwrap();
// }
// {
// {
// let mut doc = Document::default();
// doc.add_text(text_field, "a b c d f");
// index_writer.add_document(doc);
// }
// index_writer.commit().unwrap();
// }
// {
// {
// let mut doc = Document::default();
// doc.add_text(text_field, "e f");
// index_writer.add_document(doc);
// }
// index_writer.commit().unwrap();
// }
// }
// index.load_searchers().unwrap();
// let searcher = index.searcher();
// let mut term_it = searcher.terms();
// let mut terms = String::new();
// while let Some(term) = term_it.next() {
// terms.push_str(term.text());
// }
// assert_eq!(terms, "abcdef");
// }
fn next(&'a mut self) -> Option<Self::Item> {
if self.advance() {
Some(&self.current_streamers[0].streamer.key())
}
else {
None
}
}
}
// }
#[cfg(test)]
mod tests {
use super::*;
use schema::{Term, SchemaBuilder, Document, TEXT};
use core::Index;
#[test]
fn test_term_iterator() {
let mut schema_builder = SchemaBuilder::default();
let text_field = schema_builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(schema_builder.build());
{
let mut index_writer = index.writer_with_num_threads(1, 40_000_000).unwrap();
{
{
let mut doc = Document::default();
doc.add_text(text_field, "a b d f");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
}
{
{
let mut doc = Document::default();
doc.add_text(text_field, "a b c d f");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
}
{
{
let mut doc = Document::default();
doc.add_text(text_field, "e f");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
}
}
index.load_searchers().unwrap();
let searcher = index.searcher();
let mut term_it = searcher.terms();
let mut term_string = String::new();
while term_it.advance() {
let term = Term::from_bytes(term_it.key());
term_string.push_str(term.text());
}
assert_eq!(&*term_string, "abcdef");
}
}