rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-06-05 01:50:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Returning Result in some of the API (#880)

Browse Source 
* Returning Result in some of the API

* Introducing `.writer_for_test(..)`
This commit is contained in:
Paul Masurel
2020-09-07 15:52:34 +09:00
committed by GitHub
parent 6530bf0eae
commit 439d6956a9
35 changed files with 339 additions and 356 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
src/collector/facet_collector.rs
View File

@@ -472,7 +472,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let num_facets: usize = 3 * 4 * 5;
let facets: Vec<Facet> = (0..num_facets)
.map(|mut n| {
@@ -531,7 +531,7 @@ mod tests {
let facet_field = schema_builder.add_facet_field("facets");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/subjects/A/a"),
facet_field => Facet::from_text(&"/subjects/B/a"),
@@ -550,12 +550,12 @@ mod tests {
}
#[test]
fn test_doc_search_by_facet() {
fn test_doc_search_by_facet() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/A"),
));
@@ -568,8 +568,8 @@ mod tests {
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/D/C/A"),
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 4);
@@ -586,17 +586,17 @@ mod tests {
assert_eq!(count_facet("/A/C"), 1);
assert_eq!(count_facet("/A/C/A"), 1);
assert_eq!(count_facet("/C/A"), 0);
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query = query_parser.parse_query("facet:/A/B").unwrap();
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A").unwrap();
assert_eq!(3, searcher.search(&query, &Count).unwrap());
}
let query = query_parser.parse_query("facet:/A/B")?;
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A")?;
assert_eq!(3, searcher.search(&query, &Count)?);
}
Ok(())
}
#[test]
@@ -631,7 +631,7 @@ mod tests {
.collect();
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for doc in docs {
index_writer.add_document(doc);
}
@@ -684,7 +684,7 @@ mod bench {
// 40425 docs
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for doc in docs {
index_writer.add_document(doc);
}

2
src/collector/int_facet_collector.rs
View File

@@ -89,7 +89,7 @@ mod tests {
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
for i in 0u64..10u64 {
index_writer.add_document(doc!(

2
src/collector/multi_collector.rs
View File

@@ -259,7 +259,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text=>"abc"));
index_writer.add_document(doc!(text=>"abc abc abc"));
index_writer.add_document(doc!(text=>"abc abc"));

14
src/collector/top_score_collector.rs
View File

@@ -38,7 +38,7 @@ use std::fmt;
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
/// let mut index_writer = index.writer_for_tests().unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
@@ -123,7 +123,7 @@ impl TopDocs {
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
/// let mut index_writer = index.writer_for_tests().unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
@@ -163,7 +163,7 @@ impl TopDocs {
/// # let schema = schema_builder.build();
/// #
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # let mut index_writer = index.writer_for_tests()?;
/// # index_writer.add_document(doc!(title => "The Name of the Wind", rating => 92u64));
/// # index_writer.add_document(doc!(title => "The Diary of Muadib", rating => 97u64));
/// # index_writer.add_document(doc!(title => "A Dairy Cow", rating => 63u64));
@@ -264,7 +264,7 @@ impl TopDocs {
/// fn create_index() -> tantivy::Result<Index> {
/// let schema = create_schema();
/// let index = Index::create_in_ram(schema);
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// let mut index_writer = index.writer_for_tests()?;
/// let product_name = index.schema().get_field("product_name").unwrap();
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// index_writer.add_document(doc!(product_name => "The Diary of Muadib", popularity => 1u64));
@@ -371,7 +371,7 @@ impl TopDocs {
/// # fn main() -> tantivy::Result<()> {
/// # let schema = create_schema();
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # let mut index_writer = index.writer_for_tests()?;
/// # let product_name = index.schema().get_field("product_name").unwrap();
/// #
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
@@ -561,7 +561,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"Hello happy tax payer."));
index_writer.add_document(doc!(text_field=>"Droopy says hello happy tax payer"));
index_writer.add_document(doc!(text_field=>"I like Droopy"));
@@ -821,7 +821,7 @@ mod tests {
) -> (Index, Box<dyn Query>) {
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
doc_adder(&mut index_writer);
index_writer.commit().unwrap();
let query_parser = QueryParser::for_index(&index, vec![query_field]);

13
src/core/index.rs
View File

@@ -300,6 +300,15 @@ impl Index {
)
}
/// Helper to create an index writer for tests.
///
/// That index writer only simply has a single thread and a heap of 5 MB.
/// Using a single thread gives us a deterministic allocation of DocId.
#[cfg(test)]
pub fn writer_for_tests(&self) -> crate::Result<IndexWriter> {
self.writer_with_num_threads(1, 10_000_000)
}
/// Creates a multithreaded writer
///
/// Tantivy will automatically define the number of threads to use.
@@ -502,7 +511,7 @@ mod tests {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let mut index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut writer = index.writer_for_tests().unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
@@ -545,7 +554,7 @@ mod tests {
let _watch_handle = reader_index.directory_mut().watch(Box::new(move || {
let _ = sender.send(());
}));
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut writer = index.writer_for_tests().unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
writer.commit().unwrap();

6
src/core/inverted_index_reader.rs
View File

@@ -3,7 +3,6 @@ use crate::directory::ReadOnlySource;
use crate::positions::PositionReader;
use crate::postings::TermInfo;
use crate::postings::{BlockSegmentPostings, SegmentPostings};
use crate::schema::FieldType;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::termdict::TermDictionary;
@@ -54,10 +53,7 @@ impl InvertedIndexReader {
/// Creates an empty `InvertedIndexReader` object, which
/// contains no terms at all.
pub fn empty(field_type: &FieldType) -> InvertedIndexReader {
let record_option = field_type
.get_index_record_option()
.unwrap_or(IndexRecordOption::Basic);
pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
InvertedIndexReader {
termdict: TermDictionary::empty(),
postings_source: ReadOnlySource::empty(),

29
src/core/segment_reader.rs
View File

@@ -9,9 +9,9 @@ use crate::fastfield::DeleteBitSet;
use crate::fastfield::FacetReader;
use crate::fastfield::FastFieldReaders;
use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
use crate::schema::Field;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::schema::{Field, IndexRecordOption};
use crate::space_usage::SegmentSpaceUsage;
use crate::store::StoreReader;
use crate::termdict::TermDictionary;
@@ -125,17 +125,15 @@ impl SegmentReader {
///
/// They are simply stored as a fast field, serialized in
/// the `.fieldnorm` file of the segment.
pub fn get_fieldnorms_reader(&self, field: Field) -> FieldNormReader {
if let Some(fieldnorm_reader) = self.fieldnorm_readers.get_field(field) {
fieldnorm_reader
} else {
pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
self.fieldnorm_readers.get_field(field).ok_or_else(|| {
let field_name = self.schema.get_field_name(field);
let err_msg = format!(
"Field norm not found for field {:?}. Was it market as indexed during indexing.",
field_name
);
panic!(err_msg);
}
crate::TantivyError::SchemaError(err_msg)
})
}
/// Accessor to the segment's `StoreReader`.
@@ -212,6 +210,11 @@ impl SegmentReader {
/// The field reader is in charge of iterating through the
/// term dictionary associated to a specific field,
/// and opening the posting list associated to any term.
///
/// If the field is marked as index, a warn is logged and an empty `InvertedIndexReader`
/// is returned.
/// Similarly if the field is marked as indexed but no term has been indexed for the given
/// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
pub fn inverted_index(&self, field: Field) -> Arc<InvertedIndexReader> {
if let Some(inv_idx_reader) = self
.inv_idx_reader_cache
@@ -226,21 +229,21 @@ impl SegmentReader {
let record_option_opt = field_type.get_index_record_option();
if record_option_opt.is_none() {
panic!("Field {:?} does not seem indexed.", field_entry.name());
warn!("Field {:?} does not seem indexed.", field_entry.name());
}
let record_option = record_option_opt.unwrap();
let postings_source_opt = self.postings_composite.open_read(field);
if postings_source_opt.is_none() {
if postings_source_opt.is_none() || record_option_opt.is_none() {
// no documents in the segment contained this field.
// As a result, no data is associated to the inverted index.
//
// Returns an empty inverted index.
return Arc::new(InvertedIndexReader::empty(field_type));
let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
return Arc::new(InvertedIndexReader::empty(record_option));
}
let record_option = record_option_opt.unwrap();
let postings_source = postings_source_opt.unwrap();
let termdict_source = self.termdict_composite.open_read(field).expect(
@@ -339,7 +342,7 @@ mod test {
let name = schema.get_field("name").unwrap();
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(name => "tantivy"));
index_writer.add_document(doc!(name => "horse"));
index_writer.add_document(doc!(name => "jockey"));

3
src/directory/mmap_directory.rs
View File

@@ -34,7 +34,6 @@ use std::sync::Mutex;
use std::sync::RwLock;
use std::sync::Weak;
use std::thread;
use tempfile;
use tempfile::TempDir;
/// Create a default io error given a string.
@@ -655,7 +654,7 @@ mod tests {
{
let index = Index::create(mmap_directory.clone(), schema).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut log_merge_policy = LogMergePolicy::default();
log_merge_policy.set_min_merge_size(3);
index_writer.set_merge_policy(Box::new(log_merge_policy));

2
src/fastfield/bytes/mod.rs
View File

@@ -15,7 +15,7 @@ mod tests {
let field = schema_builder.add_bytes_field("bytesfield");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=>vec![0u8, 1, 2, 3]));
index_writer.add_document(doc!(field=>vec![]));
index_writer.add_document(doc!(field=>vec![255u8]));

4
src/fastfield/mod.rs
View File

@@ -474,7 +474,7 @@ mod tests {
let date_field = schema_builder.add_date_field("date", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(date_field =>crate::chrono::prelude::Utc::now()));
index_writer.commit().unwrap();
@@ -511,7 +511,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(1i64.to_u64()),

8
src/fastfield/multivalued/mod.rs
View File

@@ -25,7 +25,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=>1u64, field=>3u64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=>4u64));
@@ -64,7 +64,7 @@ mod tests {
schema_builder.add_i64_field("time_stamp_i", IntOptions::default().set_stored());
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let first_time_stamp = chrono::Utc::now();
index_writer.add_document(
doc!(date_field=>first_time_stamp, date_field=>first_time_stamp, time_i=>1i64),
@@ -186,7 +186,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=> 1i64, field => 3i64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=> -4i64));
@@ -221,7 +221,7 @@ mod tests {
let field = schema_builder.add_facet_field("facetfield");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for i in 0..100_000 {
index_writer.add_document(doc!(field=> Facet::from(format!("/lang/{}", i).as_str())));
}

2
src/fastfield/multivalued/reader.rs
View File

@@ -74,7 +74,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index
.writer_with_num_threads(1, 30_000_000)
.writer_for_tests()
.expect("Failed to create index writer.");
index_writer.add_document(doc!(
facet_field => Facet::from("/category/cat2"),

12
src/indexer/index_writer.rs
View File

@@ -800,7 +800,7 @@ mod tests {
let mut schema_builder = schema::Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let index_writer = index.writer_for_tests().unwrap();
let operations = vec![
UserOperation::Add(doc!(text_field=>"a")),
UserOperation::Add(doc!(text_field=>"b")),
@@ -815,7 +815,7 @@ mod tests {
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "hello1"));
index_writer.add_document(doc!(text_field => "hello2"));
assert!(index_writer.commit().is_ok());
@@ -864,7 +864,7 @@ mod tests {
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let a_term = Term::from_field_text(text_field, "a");
let b_term = Term::from_field_text(text_field, "b");
let operations = vec![
@@ -926,8 +926,8 @@ mod tests {
fn test_lockfile_already_exists_error_msg() {
let schema_builder = schema::Schema::builder();
let index = Index::create_in_ram(schema_builder.build());
let _index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
match index.writer_with_num_threads(1, 3_000_000) {
let _index_writer = index.writer_for_tests().unwrap();
match index.writer_for_tests() {
Err(err) => {
let err_msg = err.to_string();
assert!(err_msg.contains("already an `IndexWriter`"));
@@ -1261,7 +1261,7 @@ mod tests {
let idfield = schema_builder.add_text_field("id", STRING);
schema_builder.add_text_field("optfield", STRING);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(idfield=>"myid"));
let commit = index_writer.commit();
assert!(commit.is_ok());

36
src/indexer/merger.rs
View File

@@ -25,14 +25,14 @@ use std::cmp;
use std::collections::HashMap;
use std::sync::Arc;
fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::Result<u64> {
let mut total_tokens = 0u64;
let mut count: [usize; 256] = [0; 256];
for reader in readers {
if reader.has_deletes() {
// if there are deletes, then we use an approximation
// using the fieldnorm
let fieldnorms_reader = reader.get_fieldnorms_reader(field);
let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
for doc in reader.doc_ids_alive() {
let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc);
count[fieldnorm_id as usize] += 1;
@@ -41,7 +41,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
total_tokens += reader.inverted_index(field).total_num_tokens();
}
}
total_tokens
Ok(total_tokens
+ count
.iter()
.cloned()
@@ -49,7 +49,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
.map(|(fieldnorm_ord, count)| {
count as u64 * u64::from(FieldNormReader::id_to_fieldnorm(fieldnorm_ord as u8))
})
.sum::<u64>()
.sum::<u64>())
}
pub struct IndexMerger {
@@ -175,7 +175,7 @@ impl IndexMerger {
for field in fields {
fieldnorms_data.clear();
for reader in &self.readers {
let fieldnorms_reader = reader.get_fieldnorms_reader(field);
let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
for doc_id in reader.doc_ids_alive() {
let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc_id);
fieldnorms_data.push(fieldnorm_id);
@@ -541,7 +541,7 @@ impl IndexMerger {
// The total number of tokens will only be exact when there has been no deletes.
//
// Otherwise, we approximate by removing deleted documents proportionally.
let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field);
let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field)?;
// Create the total list of doc ids
// by stacking the doc ids from the different segment.
@@ -751,7 +751,7 @@ mod tests {
};
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
// writing the segment
{
@@ -803,7 +803,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
}
@@ -904,7 +904,7 @@ mod tests {
let score_field = schema_builder.add_u64_field("score", score_fieldtype);
let bytes_score_field = schema_builder.add_bytes_field("score_bytes");
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let reader = index.reader().unwrap();
let search_term = |searcher: &Searcher, term: Term| {
let collector = FastFieldTestCollector::for_field(score_field);
@@ -1211,7 +1211,7 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
let reader = index.reader().unwrap();
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let index_doc = |index_writer: &mut IndexWriter, doc_facets: &[&str]| {
let mut doc = Document::default();
for facet in doc_facets {
@@ -1276,7 +1276,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
reader.reload().unwrap();
@@ -1295,7 +1295,7 @@ mod tests {
// Deleting one term
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let facet = Facet::from_path(vec!["top", "a", "firstdoc"]);
let facet_term = Term::from_facet(facet_field, &facet);
index_writer.delete_term(facet_term);
@@ -1320,7 +1320,7 @@ mod tests {
let mut schema_builder = schema::Schema::builder();
let int_field = schema_builder.add_u64_field("intvals", INDEXED);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(int_field => 1u64));
index_writer.commit().expect("commit failed");
index_writer.add_document(doc!(int_field => 1u64));
@@ -1349,7 +1349,7 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
let reader = index.reader().unwrap();
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut doc = Document::default();
doc.add_u64(int_field, 1);
index_writer.add_document(doc.clone());
@@ -1388,7 +1388,7 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let index_doc = |index_writer: &mut IndexWriter, int_vals: &[u64]| {
let mut doc = Document::default();
for &val in int_vals {
@@ -1462,7 +1462,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
assert!(block_on(index_writer.merge(&segment_ids)).is_ok());
assert!(index_writer.wait_merging_threads().is_ok());
}
@@ -1516,7 +1516,7 @@ mod tests {
let index = Index::create_in_ram(builder.build());
let mut writer = index.writer_with_num_threads(1, 3_000_000)?;
let mut writer = index.writer_for_tests()?;
// Make sure we'll attempt to merge every created segment
let mut policy = crate::indexer::LogMergePolicy::default();
@@ -1548,7 +1548,7 @@ mod tests {
let mut builder = schema::SchemaBuilder::new();
let text = builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(builder.build());
let mut writer = index.writer_with_num_threads(1, 3_000_000)?;
let mut writer = index.writer_for_tests()?;
let happy_term = Term::from_field_text(text, "happy");
let term_query = TermQuery::new(happy_term, IndexRecordOption::WithFreqs);
for _ in 0..62 {

2
src/indexer/mod.rs
View File

@@ -40,7 +40,7 @@ mod tests_mmap {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_from_tempdir(schema_builder.build()).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
// there must be one deleted document in the segment
index_writer.add_document(doc!(text_field=>"b"));
index_writer.delete_term(Term::from_field_text(text_field, "b"));

6
src/indexer/segment_updater.rs
View File

@@ -555,7 +555,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(MergeWheneverPossible));
{
@@ -608,7 +608,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
for _ in 0..100 {
@@ -679,7 +679,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
for _ in 0..100 {

368
src/lib.rs
View File

@@ -296,7 +296,6 @@ mod tests {
use crate::schema::*;
use crate::DocAddress;
use crate::Index;
use crate::IndexWriter;
use crate::Postings;
use crate::ReloadPolicy;
use rand::distributions::Bernoulli;
@@ -361,14 +360,14 @@ mod tests {
#[test]
#[cfg(feature = "mmap")]
fn test_indexing() {
fn test_indexing() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_from_tempdir(schema).unwrap();
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
{
let doc = doc!(text_field=>"af b");
index_writer.add_document(doc);
@@ -383,29 +382,30 @@ mod tests {
}
assert!(index_writer.commit().is_ok());
}
Ok(())
}
#[test]
fn test_docfreq1() {
fn test_docfreq1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
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, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
{
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
index_writer.add_document(doc!(text_field=>"a"));
index_writer.add_document(doc!(text_field=>"a a"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
index_writer.add_document(doc!(text_field=>"c"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let term_a = Term::from_field_text(text_field, "a");
assert_eq!(searcher.doc_freq(&term_a), 3);
@@ -416,67 +416,50 @@ mod tests {
let term_d = Term::from_field_text(text_field, "d");
assert_eq!(searcher.doc_freq(&term_d), 0);
}
Ok(())
}
#[test]
fn test_fieldnorm_no_docs_with_field() {
fn test_fieldnorm_no_docs_with_field() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let title_field = schema_builder.add_text_field("title", TEXT);
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_for_tests()?;
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.commit()?;
let index_reader = index.reader()?;
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
let doc = doc!(text_field=>"a b c");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let fieldnorm_reader = reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
}
{
let index_reader = index.reader().unwrap();
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
{
let fieldnorm_reader = reader.get_fieldnorms_reader(text_field);
assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
}
{
let fieldnorm_reader = reader.get_fieldnorms_reader(title_field);
assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
}
let fieldnorm_reader = reader.get_fieldnorms_reader(title_field)?;
assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
}
Ok(())
}
#[test]
fn test_fieldnorm() {
fn test_fieldnorm() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
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, 3_000_000).unwrap();
{
let doc = doc!(text_field=>"a b c");
index_writer.add_document(doc);
}
{
let doc = doc!();
index_writer.add_document(doc);
}
{
let doc = doc!(text_field=>"a b");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
}
{
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field);
assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
}
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!());
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
Ok(())
}
fn advance_undeleted(docset: &mut dyn DocSet, reader: &SegmentReader) -> bool {
@@ -491,7 +474,7 @@ mod tests {
}
#[test]
fn test_delete_postings1() {
fn test_delete_postings1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let term_abcd = Term::from_field_text(text_field, "abcd");
@@ -507,7 +490,7 @@ mod tests {
.unwrap();
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
// 0
index_writer.add_document(doc!(text_field=>"a b"));
// 1
@@ -523,10 +506,10 @@ mod tests {
index_writer.add_document(doc!(text_field=>" b c"));
// 5
index_writer.add_document(doc!(text_field=>" a"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
let inverted_index = segment_reader.inverted_index(text_field);
@@ -554,15 +537,15 @@ mod tests {
}
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
// 0
index_writer.add_document(doc!(text_field=>"a b"));
// 1
index_writer.delete_term(Term::from_field_text(text_field, "c"));
index_writer.rollback().unwrap();
index_writer.rollback()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let seg_reader = searcher.segment_reader(0);
let inverted_index = seg_reader.inverted_index(term_abcd.field());
@@ -591,15 +574,15 @@ mod tests {
}
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.delete_term(Term::from_field_text(text_field, "c"));
index_writer.rollback().unwrap();
index_writer.rollback()?;
index_writer.delete_term(Term::from_field_text(text_field, "a"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
let inverted_index = segment_reader.inverted_index(term_abcd.field());
@@ -631,19 +614,20 @@ mod tests {
assert!(!advance_undeleted(&mut postings, segment_reader));
}
}
Ok(())
}
#[test]
fn test_indexed_u64() {
fn test_indexed_u64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let field = schema_builder.add_u64_field("value", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(field=>1u64));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_u64(field, 1u64);
let mut postings = searcher
@@ -653,20 +637,21 @@ mod tests {
.unwrap();
assert_eq!(postings.doc(), 0);
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexed_i64() {
fn test_indexed_i64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let value_field = schema_builder.add_i64_field("value", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
let negative_val = -1i64;
index_writer.add_document(doc!(value_field => negative_val));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_i64(value_field, negative_val);
let mut postings = searcher
@@ -676,20 +661,21 @@ mod tests {
.unwrap();
assert_eq!(postings.doc(), 0);
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexed_f64() {
fn test_indexed_f64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let value_field = schema_builder.add_f64_field("value", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
let val = std::f64::consts::PI;
index_writer.add_document(doc!(value_field => val));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_f64(value_field, val);
let mut postings = searcher
@@ -699,26 +685,29 @@ mod tests {
.unwrap();
assert_eq!(postings.doc(), 0);
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexedfield_not_in_documents() {
fn test_indexedfield_not_in_documents() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let absent_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a"));
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
segment_reader.inverted_index(absent_field); //< should not panic
let inverted_index = segment_reader.inverted_index(absent_field); //< should not panic
assert_eq!(inverted_index.terms().num_terms(), 0);
Ok(())
}
#[test]
fn test_delete_postings2() {
fn test_delete_postings2() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
@@ -726,53 +715,40 @@ mod tests {
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
// writing the segment
let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
let add_document = |index_writer: &mut IndexWriter, val: &'static str| {
let doc = doc!(text_field=>val);
index_writer.add_document(doc);
};
let remove_document = |index_writer: &mut IndexWriter, val: &'static str| {
let delterm = Term::from_field_text(text_field, val);
index_writer.delete_term(delterm);
};
add_document(&mut index_writer, "63");
add_document(&mut index_writer, "70");
add_document(&mut index_writer, "34");
add_document(&mut index_writer, "1");
add_document(&mut index_writer, "38");
add_document(&mut index_writer, "33");
add_document(&mut index_writer, "40");
add_document(&mut index_writer, "17");
remove_document(&mut index_writer, "38");
remove_document(&mut index_writer, "34");
index_writer.commit().unwrap();
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 6);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"63"));
index_writer.add_document(doc!(text_field=>"70"));
index_writer.add_document(doc!(text_field=>"34"));
index_writer.add_document(doc!(text_field=>"1"));
index_writer.add_document(doc!(text_field=>"38"));
index_writer.add_document(doc!(text_field=>"33"));
index_writer.add_document(doc!(text_field=>"40"));
index_writer.add_document(doc!(text_field=>"17"));
index_writer.delete_term(Term::from_field_text(text_field, "38"));
index_writer.delete_term(Term::from_field_text(text_field, "34"));
index_writer.commit()?;
reader.reload()?;
assert_eq!(reader.searcher().num_docs(), 6);
Ok(())
}
#[test]
fn test_termfreq() {
fn test_termfreq() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let doc = doc!(text_field=>"af af af bc bc");
index_writer.add_document(doc);
index_writer.commit().unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af af af bc bc"));
index_writer.commit()?;
}
{
let index_reader = index.reader().unwrap();
let index_reader = index.reader()?;
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(text_field);
@@ -788,63 +764,63 @@ mod tests {
assert_eq!(postings.term_freq(), 3);
assert_eq!(postings.advance(), TERMINATED);
}
Ok(())
}
#[test]
fn test_searcher_1() {
fn test_searcher_1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let reader = index.reader().unwrap();
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"af af af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit().unwrap();
}
{
reader.reload().unwrap();
let searcher = reader.searcher();
let get_doc_ids = |terms: Vec<Term>| {
let query = BooleanQuery::new_multiterms_query(terms);
let topdocs = searcher.search(&query, &TEST_COLLECTOR_WITH_SCORE).unwrap();
topdocs.docs().to_vec()
};
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "a")]),
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "af")]),
vec![DocAddress(0, 0)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "b")]),
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "c")]),
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "d")]),
vec![DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![
Term::from_field_text(text_field, "b"),
Term::from_field_text(text_field, "a"),
]),
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
}
let reader = index.reader()?;
// writing the segment
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af af af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit()?;
reader.reload()?;
let searcher = reader.searcher();
let get_doc_ids = |terms: Vec<Term>| {
let query = BooleanQuery::new_multiterms_query(terms);
searcher
.search(&query, &TEST_COLLECTOR_WITH_SCORE)
.map(|topdocs| topdocs.docs().to_vec())
};
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "a")])?,
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "af")])?,
vec![DocAddress(0, 0)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "b")])?,
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "c")])?,
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "d")])?,
vec![DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![
Term::from_field_text(text_field, "b"),
Term::from_field_text(text_field, "a"),
])?,
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
Ok(())
}
#[test]
fn test_searcher_2() {
fn test_searcher_2() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
@@ -852,19 +828,17 @@ mod tests {
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
assert_eq!(reader.searcher().num_docs(), 0u64);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit().unwrap();
}
reader.reload().unwrap();
// writing the segment
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit()?;
reader.reload()?;
assert_eq!(reader.searcher().num_docs(), 3u64);
Ok(())
}
#[test]
@@ -886,7 +860,7 @@ mod tests {
}
#[test]
fn test_wrong_fast_field_type() {
fn test_wrong_fast_field_type() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let fast_field_unsigned = schema_builder.add_u64_field("unsigned", FAST);
let fast_field_signed = schema_builder.add_i64_field("signed", FAST);
@@ -896,14 +870,14 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
{
let document =
doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
index_writer.add_document(document);
index_writer.commit().unwrap();
index_writer.commit()?;
}
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
{
@@ -942,11 +916,12 @@ mod tests {
let fast_field_reader = fast_field_reader_opt.unwrap();
assert_eq!(fast_field_reader.get(0), 4f64)
}
Ok(())
}
// motivated by #729
#[test]
fn test_update_via_delete_insert() {
fn test_update_via_delete_insert() -> crate::Result<()> {
use crate::collector::Count;
use crate::indexer::NoMergePolicy;
use crate::query::AllQuery;
@@ -960,17 +935,17 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let index_reader = index.reader().unwrap();
let index_reader = index.reader()?;
let mut index_writer = index.writer(3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.set_merge_policy(Box::new(NoMergePolicy));
for doc_id in 0u64..DOC_COUNT {
index_writer.add_document(doc!(id => doc_id));
}
index_writer.commit().unwrap();
index_writer.commit()?;
index_reader.reload().unwrap();
index_reader.reload()?;
let searcher = index_reader.searcher();
assert_eq!(
@@ -981,12 +956,11 @@ mod tests {
// update the 10 elements by deleting and re-adding
for doc_id in 0u64..DOC_COUNT {
index_writer.delete_term(Term::from_field_u64(id, doc_id));
index_writer.commit().unwrap();
index_reader.reload().unwrap();
let doc = doc!(id => doc_id);
index_writer.add_document(doc);
index_writer.commit().unwrap();
index_reader.reload().unwrap();
index_writer.commit()?;
index_reader.reload()?;
index_writer.add_document(doc!(id => doc_id));
index_writer.commit()?;
index_reader.reload()?;
let searcher = index_reader.searcher();
// The number of document should be stable.
assert_eq!(
@@ -995,7 +969,7 @@ mod tests {
);
}
index_reader.reload().unwrap();
index_reader.reload()?;
let searcher = index_reader.searcher();
let segment_ids: Vec<SegmentId> = searcher
.segment_readers()
@@ -1004,20 +978,18 @@ mod tests {
.collect();
block_on(index_writer.merge(&segment_ids)).unwrap();
index_reader.reload().unwrap();
index_reader.reload()?;
let searcher = index_reader.searcher();
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
assert_eq!(searcher.search(&AllQuery, &Count)?, DOC_COUNT as usize);
Ok(())
}
#[test]
fn test_validate_checksum() {
fn test_validate_checksum() -> crate::Result<()> {
let index_path = tempfile::tempdir().expect("dir");
let schema = Schema::builder().build();
let index = Index::create_in_dir(&index_path, schema).expect("index");
assert!(index.validate_checksum().unwrap().is_empty());
let index = Index::create_in_dir(&index_path, schema)?;
assert!(index.validate_checksum()?.is_empty());
Ok(())
}
}

4
src/postings/block_segment_postings.rs
View File

@@ -455,7 +455,7 @@ mod tests {
let int_field = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut last_doc = 0u32;
for &doc in docs {
for _ in last_doc..doc {
@@ -496,7 +496,7 @@ mod tests {
let int_field = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
// create two postings list, one containg even number,
// the other containing odd numbers.
for i in 0..6 {

43
src/postings/mod.rs
View File

@@ -91,7 +91,7 @@ pub mod tests {
let title = schema_builder.add_text_field("title", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 30_000_000)?;
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(title => r#"abc abc abc"#));
index_writer.add_document(doc!(title => r#"abc be be be be abc"#));
for _ in 0..1_000 {
@@ -176,7 +176,7 @@ pub mod tests {
.tokenizers()
.register("simple_no_truncation", SimpleTokenizer);
let reader = index.reader().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
{
index_writer.add_document(doc!(text_field=>exceeding_token_text));
@@ -205,7 +205,7 @@ pub mod tests {
}
#[test]
pub fn test_position_and_fieldnorm1() {
pub fn test_position_and_fieldnorm1() -> crate::Result<()> {
let mut positions = Vec::new();
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
@@ -217,42 +217,38 @@ pub mod tests {
let mut segment_writer =
SegmentWriter::for_segment(3_000_000, segment.clone(), &schema).unwrap();
{
let mut doc = Document::default();
// checking that position works if the field has two values
doc.add_text(text_field, "a b a c a d a a.");
doc.add_text(text_field, "d d d d a");
let op = AddOperation {
opstamp: 0u64,
document: doc,
document: doc!(
text_field => "a b a c a d a a.",
text_field => "d d d d a"
),
};
segment_writer.add_document(op, &schema).unwrap();
segment_writer.add_document(op, &schema)?;
}
{
let mut doc = Document::default();
doc.add_text(text_field, "b a");
let op = AddOperation {
opstamp: 1u64,
document: doc,
document: doc!(text_field => "b a"),
};
segment_writer.add_document(op, &schema).unwrap();
}
for i in 2..1000 {
let mut doc = Document::default();
let mut text = iter::repeat("e ").take(i).collect::<String>();
let mut text: String = iter::repeat("e ").take(i).collect();
text.push_str(" a");
doc.add_text(text_field, &text);
let op = AddOperation {
opstamp: 2u64,
document: doc,
document: doc!(text_field => text),
};
segment_writer.add_document(op, &schema).unwrap();
}
segment_writer.finalize().unwrap();
segment_writer.finalize()?;
}
{
let segment_reader = SegmentReader::open(&segment).unwrap();
let segment_reader = SegmentReader::open(&segment)?;
{
let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field);
let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorm_reader.fieldnorm(0), 8 + 5);
assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
for i in 2..1000 {
@@ -312,6 +308,7 @@ pub mod tests {
assert_eq!(postings_e.doc(), TERMINATED);
}
}
Ok(())
}
#[test]
@@ -322,7 +319,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "g b b d c g c"));
index_writer.add_document(doc!(text_field => "g a b b a d c g c"));
assert!(index_writer.commit().is_ok());
@@ -354,7 +351,7 @@ pub mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for i in 0u64..num_docs as u64 {
let doc = doc!(value_field => 2u64, value_field => i % 2u64);
index_writer.add_document(doc);
@@ -425,7 +422,7 @@ pub mod tests {
// delete some of the documents
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.delete_term(term_0);
assert!(index_writer.commit().is_ok());
}
@@ -479,7 +476,7 @@ pub mod tests {
// delete everything else
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.delete_term(term_1);
assert!(index_writer.commit().is_ok());
}
@@ -522,7 +519,7 @@ pub mod tests {
let index = Index::create_in_ram(schema);
let posting_list_size = 1_000_000;
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for _ in 0..posting_list_size {
let mut doc = Document::default();
if rng.gen_bool(1f64 / 15f64) {

2
src/query/all_query.rs
View File

@@ -83,7 +83,7 @@ mod tests {
let field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=>"aaa"));
index_writer.add_document(doc!(field=>"bbb"));
index_writer.commit().unwrap();

7
src/query/automaton_weight.rs
View File

@@ -5,7 +5,6 @@ use crate::query::{BitSetDocSet, Explanation};
use crate::query::{Scorer, Weight};
use crate::schema::{Field, IndexRecordOption};
use crate::termdict::{TermDictionary, TermStreamer};
use crate::Result;
use crate::TantivyError;
use crate::{DocId, Score};
use std::sync::Arc;
@@ -40,7 +39,7 @@ impl<A> Weight for AutomatonWeight<A>
where
A: Automaton + Send + Sync + 'static,
{
fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
let max_doc = reader.max_doc();
let mut doc_bitset = BitSet::with_max_value(max_doc);
let inverted_index = reader.inverted_index(self.field);
@@ -66,7 +65,7 @@ where
Ok(Box::new(const_scorer))
}
fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
let mut scorer = self.scorer(reader, 1.0)?;
if scorer.seek(doc) == doc {
Ok(Explanation::new("AutomatonScorer", 1.0))
@@ -91,7 +90,7 @@ mod tests {
let mut schema = Schema::builder();
let title = schema.add_text_field("title", STRING);
let index = Index::create_in_ram(schema.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(title=>"abc"));
index_writer.add_document(doc!(title=>"bcd"));
index_writer.add_document(doc!(title=>"abcd"));

4
src/query/boolean_query/mod.rs
View File

@@ -32,7 +32,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
index_writer.add_document(doc!(text_field => "a b c"));
index_writer.add_document(doc!(text_field => "a c"));
@@ -224,7 +224,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "a b c"));
index_writer.add_document(doc!(text_field => "a c"));
index_writer.add_document(doc!(text_field => "b c"));

2
src/query/boost_query.rs
View File

@@ -144,7 +144,7 @@ mod tests {
fn test_boost_query_explain() {
let schema = Schema::builder().build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(Document::new());
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();

2
src/query/fuzzy_query.rs
View File

@@ -177,7 +177,7 @@ mod test {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(
country_field => "japan",
));

8
src/query/phrase_query/mod.rs
View File

@@ -24,7 +24,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for &text in texts {
let doc = doc!(text_field=>text);
index_writer.add_document(doc);
@@ -135,7 +135,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"a b c"));
assert!(index_writer.commit().is_ok());
}
@@ -186,7 +186,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"b"));
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.add_document(doc!(text_field=>"b a"));
@@ -217,7 +217,7 @@ pub mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"a b c d e f g h"));
assert!(index_writer.commit().is_ok());
}

14
src/query/phrase_query/phrase_weight.rs
View File

@@ -9,8 +9,8 @@ use crate::query::Weight;
use crate::query::{EmptyScorer, Explanation};
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::Score;
use crate::{DocId, DocSet};
use crate::{Result, Score};
pub struct PhraseWeight {
phrase_terms: Vec<(usize, Term)>,
@@ -32,7 +32,7 @@ impl PhraseWeight {
}
}
fn fieldnorm_reader(&self, reader: &SegmentReader) -> FieldNormReader {
fn fieldnorm_reader(&self, reader: &SegmentReader) -> crate::Result<FieldNormReader> {
let field = self.phrase_terms[0].1.field();
reader.get_fieldnorms_reader(field)
}
@@ -41,9 +41,9 @@ impl PhraseWeight {
&self,
reader: &SegmentReader,
boost: Score,
) -> Result<Option<PhraseScorer<SegmentPostings>>> {
) -> crate::Result<Option<PhraseScorer<SegmentPostings>>> {
let similarity_weight = self.similarity_weight.boost_by(boost);
let fieldnorm_reader = self.fieldnorm_reader(reader);
let fieldnorm_reader = self.fieldnorm_reader(reader)?;
if reader.has_deletes() {
let mut term_postings_list = Vec::new();
for &(offset, ref term) in &self.phrase_terms {
@@ -85,7 +85,7 @@ impl PhraseWeight {
}
impl Weight for PhraseWeight {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
if let Some(scorer) = self.phrase_scorer(reader, boost)? {
Ok(Box::new(scorer))
} else {
@@ -93,7 +93,7 @@ impl Weight for PhraseWeight {
}
}
fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
let scorer_opt = self.phrase_scorer(reader, 1.0)?;
if scorer_opt.is_none() {
return Err(does_not_match(doc));
@@ -102,7 +102,7 @@ impl Weight for PhraseWeight {
if scorer.seek(doc) != doc {
return Err(does_not_match(doc));
}
let fieldnorm_reader = self.fieldnorm_reader(reader);
let fieldnorm_reader = self.fieldnorm_reader(reader)?;
let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
let phrase_count = scorer.phrase_count();
let mut explanation = Explanation::new("Phrase Scorer", scorer.score());

19
src/query/range_query.rs
View File

@@ -9,7 +9,6 @@ use crate::query::{Query, Scorer, Weight};
use crate::schema::Type;
use crate::schema::{Field, IndexRecordOption, Term};
use crate::termdict::{TermDictionary, TermStreamer};
use crate::Result;
use crate::{DocId, Score};
use std::collections::Bound;
use std::ops::Range;
@@ -42,13 +41,13 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
/// use tantivy::query::RangeQuery;
/// use tantivy::schema::{Schema, INDEXED};
/// use tantivy::{doc, Index};
/// # fn test() -> tantivy::Result<()> {
/// # fn test() -> crate::Result<()> {
/// let mut schema_builder = Schema::builder();
/// let year_field = schema_builder.add_u64_field("year", INDEXED);
/// let schema = schema_builder.build();
///
/// let index = Index::create_in_ram(schema);
/// let mut index_writer = index.writer_with_num_threads(1, 6_000_000)?;
/// let mut index_writer = index.writer_for_tests()?;
/// for year in 1950u64..2017u64 {
/// let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
/// for _ in 0..num_docs_within_year {
@@ -246,7 +245,11 @@ impl RangeQuery {
}
impl Query for RangeQuery {
fn weight(&self, searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
fn weight(
&self,
searcher: &Searcher,
_scoring_enabled: bool,
) -> crate::Result<Box<dyn Weight>> {
let schema = searcher.schema();
let value_type = schema.get_field_entry(self.field).field_type().value_type();
if value_type != self.value_type {
@@ -289,7 +292,7 @@ impl RangeWeight {
}
impl Weight for RangeWeight {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
let max_doc = reader.max_doc();
let mut doc_bitset = BitSet::with_max_value(max_doc);
@@ -315,7 +318,7 @@ impl Weight for RangeWeight {
Ok(Box::new(ConstScorer::new(doc_bitset, boost)))
}
fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
let mut scorer = self.scorer(reader, 1.0)?;
if scorer.seek(doc) != doc {
return Err(does_not_match(doc));
@@ -342,7 +345,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for year in 1950u64..2017u64 {
let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
for _ in 0..num_docs_within_year {
@@ -485,7 +488,7 @@ mod tests {
schema_builder.add_i64_field("year", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
let mut index_writer = index.writer_for_tests()?;
let title = schema.get_field("title").unwrap();
let year = schema.get_field("year").unwrap();
index_writer.add_document(doc!(

2
src/query/regex_query.rs
View File

@@ -103,7 +103,7 @@ mod test {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(
country_field => "japan",
));

10
src/query/term_query/mod.rs
View File

@@ -25,7 +25,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let doc = doc!(text_field => "a");
index_writer.add_document(doc);
assert!(index_writer.commit().is_ok());
@@ -50,7 +50,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
let mut index_writer = index.writer_for_tests()?;
for _ in 0..COMPRESSION_BLOCK_SIZE {
let doc = doc!(text_field => "a");
index_writer.add_document(doc);
@@ -86,7 +86,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(
left_field => "left1 left2 left2 left2f2 left2f2 left3 abcde abcde abcde abcde abcde abcde abcde abcde abcde abcewde abcde abcde",
right_field => "right1 right2",
@@ -136,7 +136,7 @@ mod tests {
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 5_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.add_document(doc!(text_field=>"a c"));
index_writer.delete_term(Term::from_field_text(text_field, "b"));
@@ -153,7 +153,7 @@ mod tests {
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field=>"a"));
index_writer.add_document(doc!(text_field=>"a"));
index_writer.commit()?;

11
src/query/term_query/term_weight.rs
View File

@@ -8,7 +8,6 @@ use crate::query::weight::for_each_scorer;
use crate::query::Weight;
use crate::query::{Explanation, Scorer};
use crate::schema::IndexRecordOption;
use crate::Result;
use crate::Term;
use crate::{DocId, Score};
@@ -19,12 +18,12 @@ pub struct TermWeight {
}
impl Weight for TermWeight {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> Result<Box<dyn Scorer>> {
fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
let term_scorer = self.specialized_scorer(reader, boost)?;
Ok(Box::new(term_scorer))
}
fn explain(&self, reader: &SegmentReader, doc: DocId) -> Result<Explanation> {
fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
let mut scorer = self.specialized_scorer(reader, 1.0)?;
if scorer.seek(doc) != doc {
return Err(does_not_match(doc));
@@ -32,7 +31,7 @@ impl Weight for TermWeight {
Ok(scorer.explain())
}
fn count(&self, reader: &SegmentReader) -> Result<u32> {
fn count(&self, reader: &SegmentReader) -> crate::Result<u32> {
if let Some(delete_bitset) = reader.delete_bitset() {
Ok(self.scorer(reader, 1.0)?.count(delete_bitset))
} else {
@@ -96,10 +95,10 @@ impl TermWeight {
&self,
reader: &SegmentReader,
boost: Score,
) -> Result<TermScorer> {
) -> crate::Result<TermScorer> {
let field = self.term.field();
let inverted_index = reader.inverted_index(field);
let fieldnorm_reader = reader.get_fieldnorms_reader(field);
let fieldnorm_reader = reader.get_fieldnorms_reader(field)?;
let similarity_weight = self.similarity_weight.boost_by(boost);
let postings_opt: Option<SegmentPostings> =
inverted_index.read_postings(&self.term, self.index_record_option);

2
src/schema/mod.rs
View File

@@ -150,7 +150,7 @@ use once_cell::sync::Lazy;
use regex::Regex;
/// Regular expression representing the restriction on a valid field names.
pub const FIELD_NAME_PATTERN: &'static str = r#"^[_a-zA-Z][_\-a-zA-Z0-9]*$"#;
pub const FIELD_NAME_PATTERN: &str = r#"^[_a-zA-Z][_\-a-zA-Z0-9]*$"#;
/// Validator for a potential `field_name`.
/// Returns true iff the name can be use for a field name.

6
src/schema/value.rs
View File

@@ -221,6 +221,12 @@ impl<'a> From<&'a str> for Value {
}
}
impl<'a> From<&'a [u8]> for Value {
fn from(bytes: &'a [u8]) -> Value {
Value::Bytes(bytes.to_vec())
}
}
impl<'a> From<Facet> for Value {
fn from(facet: Facet) -> Value {
Value::Facet(facet)

6
src/snippet/mod.rs
View File

@@ -221,7 +221,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
/// # let text_field = schema_builder.add_text_field("text", TEXT);
/// # let schema = schema_builder.build();
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 30_000_000)?;
/// # let mut index_writer = index.writer_for_tests()?;
/// # let doc = doc!(text_field => r#"Comme je descendais des Fleuves impassibles,
/// # Je ne me sentis plus guidé par les haleurs :
/// # Des Peaux-Rouges criards les avaient pris pour cibles,
@@ -506,7 +506,7 @@ Survey in 2016, 2017, and 2018."#;
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "a"));
index_writer.add_document(doc!(text_field => "a"));
index_writer.add_document(doc!(text_field => "a b"));
@@ -562,7 +562,7 @@ Survey in 2016, 2017, and 2018."#;
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
let doc = doc ! (text_field => TEST_TEXT);
index_writer.add_document(doc);

8
src/space_usage/mod.rs
View File

@@ -336,7 +336,7 @@ mod test {
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(name => 1u64));
index_writer.add_document(doc!(name => 2u64));
index_writer.add_document(doc!(name => 10u64));
@@ -374,7 +374,7 @@ mod test {
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(name => "hi"));
index_writer.add_document(doc!(name => "this is a test"));
index_writer.add_document(
@@ -414,7 +414,7 @@ mod test {
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(name => "hi"));
index_writer.add_document(doc!(name => "this is a test"));
index_writer.add_document(
@@ -453,7 +453,7 @@ mod test {
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(name => 1u64));
index_writer.add_document(doc!(name => 2u64));
index_writer.add_document(doc!(name => 3u64));

2
src/termdict/mod.rs
View File

@@ -138,7 +138,7 @@ mod tests {
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, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
{
let mut doc = Document::default();