Compare commits

...

2 Commits

Author SHA1 Message Date
Paul Masurel
2267722d01 Added SegmentFruit 2018-12-13 08:58:00 +09:00
Paul Masurel
279a9eb5e3 Closes #449 (#450)
Clippy working on stable.
Clippy warnings addressed
2018-12-10 12:20:59 +09:00
44 changed files with 305 additions and 280 deletions

View File

@@ -106,37 +106,37 @@ fn main() -> tantivy::Result<()> {
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// Multivalued field just need to be repeated.
index_writer.add_document(doc!(
title => "Frankenstein",
title => "The Modern Prometheus",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
title => "Frankenstein",
title => "The Modern Prometheus",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
));
// This is an example, so we will only index 3 documents

View File

@@ -70,6 +70,8 @@ impl Collector for StatsCollector {
// Our standard deviation will be a float.
type Fruit = Option<Stats>;
type SegmentFruit = Self::Fruit;
type Child = StatsSegmentCollector;
fn for_segment(

View File

@@ -68,12 +68,12 @@ fn main() -> tantivy::Result<()> {
// heap for the indexer can increase its throughput.
let mut index_writer = index.writer(50_000_000)?;
index_writer.add_document(doc!(
title => "The Old Man and the Sea",
body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."
title => "The Old Man and the Sea",
body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
title => "Of Mice and Men",
body => r#"A few miles south of Soledad, the Salinas River drops in close to the hillside
bank and runs deep and green. The water is warm too, for it has slipped twinkling
over the yellow sands in the sunlight before reaching the narrow pool. On one
@@ -84,7 +84,7 @@ fn main() -> tantivy::Result<()> {
limbs and branches that arch over the pool"#
));
index_writer.add_document(doc!(
title => "Frankenstein",
title => "Frankenstein",
body => r#"You will rejoice to hear that no disaster has accompanied the commencement of an
enterprise which you have regarded with such evil forebodings. I arrived here
yesterday, and my first task is to assure my dear sister of my welfare and

View File

@@ -35,15 +35,15 @@ fn main() -> tantivy::Result<()> {
// we'll only need one doc for this example.
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// ...
index_writer.commit()?;
@@ -56,7 +56,7 @@ fn main() -> tantivy::Result<()> {
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
let snippet_generator = SnippetGenerator::new(&searcher, &*query, body)?;
let snippet_generator = SnippetGenerator::create(&searcher, &*query, body)?;
for (score, doc_address) in top_docs {
let doc = searcher.doc(doc_address)?;

View File

@@ -72,26 +72,26 @@ fn main() -> tantivy::Result<()> {
title => "The Old Man and the Sea",
body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."
));
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winters flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Frankenstein",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
title => "Frankenstein",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
));
index_writer.commit()?;

View File

@@ -58,6 +58,7 @@ pub struct Count;
impl Collector for Count {
type Fruit = usize;
type SegmentFruit = usize;
type Child = SegmentCountCollector;

View File

@@ -258,6 +258,8 @@ impl FacetCollector {
impl Collector for FacetCollector {
type Fruit = FacetCounts;
type SegmentFruit = FacetCounts;
type Child = FacetSegmentCollector;
fn for_segment(
@@ -474,7 +476,8 @@ mod tests {
n /= 4;
let leaf = n % 5;
Facet::from(&format!("/top{}/mid{}/leaf{}", top, mid, leaf))
}).collect();
})
.collect();
for i in 0..num_facets * 10 {
let mut doc = Document::new();
doc.add_facet(facet_field, facets[i % num_facets].clone());
@@ -500,18 +503,16 @@ mod tests {
("/top1/mid2", 50),
("/top1/mid3", 50),
]
.iter()
.map(|&(facet_str, count)| (String::from(facet_str), count))
.collect::<Vec<_>>()
.iter()
.map(|&(facet_str, count)| (String::from(facet_str), count))
.collect::<Vec<_>>()
);
}
}
#[test]
#[should_panic(
expected = "Tried to add a facet which is a descendant of \
an already added facet."
)]
#[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")]
fn test_misused_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field(0));
facet_collector.add_facet(Facet::from("/country"));
@@ -563,13 +564,15 @@ mod tests {
let facet = Facet::from(&format!("/facet/{}", c));
let doc = doc!(facet_field => facet);
iter::repeat(doc).take(count)
}).map(|mut doc| {
})
.map(|mut doc| {
doc.add_facet(
facet_field,
&format!("/facet/{}", thread_rng().sample(&uniform)),
);
doc
}).collect();
})
.collect();
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();

View File

@@ -136,8 +136,10 @@ pub trait Collector: Sync {
/// e.g. `usize` for the `Count` collector.
type Fruit: Fruit;
type SegmentFruit: Fruit;
/// Type of the `SegmentCollector` associated to this collector.
type Child: SegmentCollector<Fruit = Self::Fruit>;
type Child: SegmentCollector<Fruit = Self::SegmentFruit>;
/// `set_segment` is called before beginning to enumerate
/// on this segment.
@@ -152,7 +154,7 @@ pub trait Collector: Sync {
/// Combines the fruit associated to the collection of each segments
/// into one fruit.
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit>;
fn merge_fruits(&self, segment_fruits: Vec<Self::SegmentFruit>) -> Result<Self::Fruit>;
}
/// The `SegmentCollector` is the trait in charge of defining the
@@ -181,6 +183,9 @@ where
Right: Collector,
{
type Fruit = (Left::Fruit, Right::Fruit);
type SegmentFruit = (Left::SegmentFruit, Right::SegmentFruit);
type Child = (Left::Child, Right::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
@@ -195,7 +200,7 @@ where
fn merge_fruits(
&self,
children: Vec<(Left::Fruit, Right::Fruit)>,
children: Vec<(Left::SegmentFruit, Right::SegmentFruit)>,
) -> Result<(Left::Fruit, Right::Fruit)> {
let mut left_fruits = vec![];
let mut right_fruits = vec![];
@@ -236,6 +241,7 @@ where
Three: Collector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
type SegmentFruit = (One::SegmentFruit, Two::SegmentFruit, Three::SegmentFruit);
type Child = (One::Child, Two::Child, Three::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
@@ -249,7 +255,7 @@ where
self.0.requires_scoring() || self.1.requires_scoring() || self.2.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(&self, children: Vec<Self::SegmentFruit>) -> Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
@@ -295,6 +301,7 @@ where
Four: Collector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
type SegmentFruit = (One::SegmentFruit, Two::SegmentFruit, Three::SegmentFruit, Four::SegmentFruit);
type Child = (One::Child, Two::Child, Three::Child, Four::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
@@ -312,7 +319,7 @@ where
|| self.3.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(&self, children: Vec<Self::SegmentFruit>) -> Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];

View File

@@ -18,6 +18,7 @@ pub struct CollectorWrapper<TCollector: Collector>(TCollector);
impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
type Fruit = Box<Fruit>;
type SegmentFruit = Box<Fruit>;
type Child = Box<BoxableSegmentCollector>;
fn for_segment(
@@ -34,16 +35,17 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
}
fn merge_fruits(&self, children: Vec<<Self as Collector>::Fruit>) -> Result<Box<Fruit>> {
let typed_fruit: Vec<TCollector::Fruit> = children
let typed_fruit: Vec<TCollector::SegmentFruit> = children
.into_iter()
.map(|untyped_fruit| {
Downcast::<TCollector::Fruit>::downcast(untyped_fruit)
Downcast::<TCollector::SegmentFruit>::downcast(untyped_fruit)
.map(|boxed_but_typed| *boxed_but_typed)
.map_err(|e| {
let err_msg = format!("Failed to cast child collector fruit. {:?}", e);
TantivyError::InvalidArgument(err_msg)
})
}).collect::<Result<_>>()?;
})
.collect::<Result<_>>()?;
let merged_fruit = self.0.merge_fruits(typed_fruit)?;
Ok(Box::new(merged_fruit))
}
@@ -147,17 +149,17 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
/// Ok(())
/// }
/// ```
#[allow(clippy::type_complexity)]
#[derive(Default)]
pub struct MultiCollector<'a> {
collector_wrappers:
Vec<Box<Collector<Child = Box<BoxableSegmentCollector>, Fruit = Box<Fruit>> + 'a>>,
Vec<Box<Collector<Child = Box<BoxableSegmentCollector>, Fruit = Box<Fruit>, SegmentFruit = Box<Fruit>> + 'a>>,
}
impl<'a> MultiCollector<'a> {
/// Create a new `MultiCollector`
pub fn new() -> MultiCollector<'a> {
MultiCollector {
collector_wrappers: Vec::new(),
}
pub fn new() -> Self {
Default::default()
}
/// Add a new collector to our `MultiCollector`.
@@ -176,7 +178,9 @@ impl<'a> MultiCollector<'a> {
}
impl<'a> Collector for MultiCollector<'a> {
type Fruit = MultiFruit;
type SegmentFruit = MultiFruit;
type Child = MultiCollectorChild;
fn for_segment(
@@ -213,7 +217,8 @@ impl<'a> Collector for MultiCollector<'a> {
.zip(segment_fruits_list)
.map(|(child_collector, segment_fruits)| {
Ok(Some(child_collector.merge_fruits(segment_fruits)?))
}).collect::<Result<_>>()?;
})
.collect::<Result<_>>()?;
Ok(MultiFruit { sub_fruits })
}
}

View File

@@ -40,6 +40,7 @@ impl TestFruit {
impl Collector for TestCollector {
type Fruit = TestFruit;
type SegmentFruit = Self::Fruit;
type Child = TestSegmentCollector;
fn for_segment(
@@ -109,6 +110,8 @@ impl FastFieldTestCollector {
impl Collector for FastFieldTestCollector {
type Fruit = Vec<u64>;
type SegmentFruit = Self::Fruit;
type Child = FastFieldSegmentCollector;
fn for_segment(
@@ -165,6 +168,7 @@ impl BytesFastFieldTestCollector {
impl Collector for BytesFastFieldTestCollector {
type Fruit = Vec<u8>;
type SegmentFruit = Self::Fruit;
type Child = BytesFastFieldSegmentCollector;
fn for_segment(

View File

@@ -84,11 +84,9 @@ where
for (feature, doc) in child_fruit {
if top_collector.len() < self.limit {
top_collector.push(ComparableDoc { feature, doc });
} else {
if let Some(mut head) = top_collector.peek_mut() {
if head.feature < feature {
*head = ComparableDoc { feature, doc };
}
} else if let Some(mut head) = top_collector.peek_mut() {
if head.feature < feature {
*head = ComparableDoc { feature, doc };
}
}
}
@@ -142,7 +140,8 @@ impl<T: PartialOrd + Clone> TopSegmentCollector<T> {
comparable_doc.feature,
DocAddress(segment_id, comparable_doc.doc),
)
}).collect()
})
.collect()
}
/// Return true iff at least K documents have gone through

View File

@@ -88,6 +88,7 @@ impl<T: FastValue + PartialOrd + Clone> TopDocsByField<T> {
impl<T: FastValue + PartialOrd + Send + Sync + 'static> Collector for TopDocsByField<T> {
type Fruit = Vec<(T, DocAddress)>;
type SegmentFruit = Vec<(T, DocAddress)>;
type Child = TopFieldSegmentCollector<T>;

View File

@@ -89,6 +89,7 @@ impl TopDocs {
impl Collector for TopDocs {
type Fruit = Vec<(Score, DocAddress)>;
type SegmentFruit = Vec<(Score, DocAddress)>;
type Child = TopScoreSegmentCollector;

View File

@@ -94,7 +94,8 @@ mod tests {
panic!("panic should propagate");
},
vec![0].into_iter(),
).unwrap();
)
.unwrap();
}
#[test]
@@ -106,7 +107,8 @@ mod tests {
panic!("panic should propagate");
},
vec![0].into_iter(),
).unwrap();
)
.unwrap();
}
#[test]

View File

@@ -135,7 +135,7 @@ impl Index {
/// Creates a new index given an implementation of the trait `Directory`
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
let directory = ManagedDirectory::new(dir)?;
let directory = ManagedDirectory::wrap(dir)?;
Index::from_directory(directory, schema)
}
@@ -199,7 +199,7 @@ impl Index {
/// Open the index using the provided directory
pub fn open<D: Directory>(directory: D) -> Result<Index> {
let directory = ManagedDirectory::new(directory)?;
let directory = ManagedDirectory::wrap(directory)?;
let metas = load_metas(&directory)?;
Index::create_from_metas(directory, &metas)
}

View File

@@ -32,10 +32,7 @@ pub struct InvertedIndexReader {
}
impl InvertedIndexReader {
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::needless_pass_by_value)
)] // for symetry
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symetry
pub(crate) fn new(
termdict: TermDictionary,
postings_source: ReadOnlySource,

View File

@@ -23,7 +23,7 @@ fn collect_segment<C: Collector>(
weight: &Weight,
segment_ord: u32,
segment_reader: &SegmentReader,
) -> Result<C::Fruit> {
) -> Result<C::SegmentFruit> {
let mut scorer = weight.scorer(segment_reader)?;
let mut segment_collector = collector.for_segment(segment_ord as u32, segment_reader)?;
if let Some(delete_bitset) = segment_reader.delete_bitset() {
@@ -104,7 +104,8 @@ impl Searcher {
.iter()
.map(|segment_reader| {
u64::from(segment_reader.inverted_index(term.field()).doc_freq(term))
}).sum::<u64>()
})
.sum::<u64>()
}
/// Return the list of segment readers

View File

@@ -59,7 +59,7 @@ fn save_managed_paths(
impl ManagedDirectory {
/// Wraps a directory as managed directory.
pub fn new<Dir: Directory>(directory: Dir) -> Result<ManagedDirectory> {
pub fn wrap<Dir: Directory>(directory: Dir) -> Result<ManagedDirectory> {
match directory.atomic_read(&MANAGED_FILEPATH) {
Ok(data) => {
let managed_files_json = String::from_utf8_lossy(&data);
@@ -260,7 +260,7 @@ mod tests {
let tempdir_path = PathBuf::from(tempdir.path());
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::new(mmap_directory).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
{
let mut write_file = managed_directory.open_write(*TEST_PATH1).unwrap();
write_file.flush().unwrap();
@@ -286,7 +286,7 @@ mod tests {
}
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::new(mmap_directory).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
{
assert!(managed_directory.exists(*TEST_PATH1));
assert!(!managed_directory.exists(*TEST_PATH2));
@@ -310,7 +310,7 @@ mod tests {
let living_files = HashSet::new();
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::new(mmap_directory).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
managed_directory
.atomic_write(*TEST_PATH1, &vec![0u8, 1u8])
.unwrap();

View File

@@ -100,7 +100,8 @@ impl InnerDirectory {
);
let io_err = make_io_err(msg);
OpenReadError::IOError(IOError::with_path(path.to_owned(), io_err))
}).and_then(|readable_map| {
})
.and_then(|readable_map| {
readable_map
.get(path)
.ok_or_else(|| OpenReadError::FileDoesNotExist(PathBuf::from(path)))
@@ -120,7 +121,8 @@ impl InnerDirectory {
);
let io_err = make_io_err(msg);
DeleteError::IOError(IOError::with_path(path.to_owned(), io_err))
}).and_then(|mut writable_map| match writable_map.remove(path) {
})
.and_then(|mut writable_map| match writable_map.remove(path) {
Some(_) => Ok(()),
None => Err(DeleteError::FileDoesNotExist(PathBuf::from(path))),
})

View File

@@ -191,10 +191,7 @@ impl DeleteCursor {
}
}
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::wrong_self_convention)
)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::wrong_self_convention))]
fn is_behind_opstamp(&mut self, target_opstamp: u64) -> bool {
self.get()
.map(|operation| operation.opstamp < target_opstamp)

View File

@@ -61,7 +61,8 @@ fn initial_table_size(per_thread_memory_budget: usize) -> usize {
"Per thread memory is too small: {}",
per_thread_memory_budget
)
}).min(19) // we cap it at 512K
})
.min(19) // we cap it at 512K
}
/// `IndexWriter` is the user entry-point to add document to an index.
@@ -139,7 +140,7 @@ pub fn open_index_writer(
let stamper = Stamper::new(current_opstamp);
let segment_updater =
SegmentUpdater::new(index.clone(), stamper.clone(), &delete_queue.cursor())?;
SegmentUpdater::create(index.clone(), stamper.clone(), &delete_queue.cursor())?;
let mut index_writer = IndexWriter {
_directory_lock: Some(directory_lock),
@@ -390,7 +391,8 @@ impl IndexWriter {
.name(format!(
"thrd-tantivy-index{}-gen{}",
self.worker_id, generation
)).spawn(move || {
))
.spawn(move || {
loop {
let mut document_iterator =
document_receiver_clone.clone().into_iter().peekable();
@@ -465,10 +467,8 @@ impl IndexWriter {
///
/// Returns the former segment_ready channel.
fn recreate_document_channel(&mut self) -> DocumentReceiver {
let (mut document_sender, mut document_receiver): (
DocumentSender,
DocumentReceiver,
) = channel::bounded(PIPELINE_MAX_SIZE_IN_DOCS);
let (mut document_sender, mut document_receiver): (DocumentSender, DocumentReceiver) =
channel::bounded(PIPELINE_MAX_SIZE_IN_DOCS);
swap(&mut self.document_sender, &mut document_sender);
swap(&mut self.document_receiver, &mut document_receiver);
document_receiver

View File

@@ -40,13 +40,15 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
total_tokens += reader.inverted_index(field).total_num_tokens();
}
}
total_tokens + count
.iter()
.cloned()
.enumerate()
.map(|(fieldnorm_ord, count)| {
count as u64 * u64::from(FieldNormReader::id_to_fieldnorm(fieldnorm_ord as u8))
}).sum::<u64>()
total_tokens
+ count
.iter()
.cloned()
.enumerate()
.map(|(fieldnorm_ord, count)| {
count as u64 * u64::from(FieldNormReader::id_to_fieldnorm(fieldnorm_ord as u8))
})
.sum::<u64>()
}
pub struct IndexMerger {
@@ -523,7 +525,8 @@ impl IndexMerger {
}
}
None
}).collect();
})
.collect();
// At this point, `segment_postings` contains the posting list
// of all of the segments containing the given term.
@@ -664,7 +667,8 @@ mod tests {
TextFieldIndexing::default()
.set_tokenizer("default")
.set_index_option(IndexRecordOption::WithFreqs),
).set_stored();
)
.set_stored();
let text_field = schema_builder.add_text_field("text", text_fieldtype);
let score_fieldtype = schema::IntOptions::default().set_fast(Cardinality::SingleValue);
let score_field = schema_builder.add_u64_field("score", score_fieldtype);
@@ -803,7 +807,8 @@ mod tests {
.search(
&query,
&BytesFastFieldTestCollector::for_field(bytes_score_field),
).expect("failed to search")
)
.expect("failed to search")
};
assert_eq!(
get_fast_vals(vec![Term::from_field_text(text_field, "a")]),
@@ -823,7 +828,8 @@ mod tests {
let text_fieldtype = schema::TextOptions::default()
.set_indexing_options(
TextFieldIndexing::default().set_index_option(IndexRecordOption::WithFreqs),
).set_stored();
)
.set_stored();
let text_field = schema_builder.add_text_field("text", text_fieldtype);
let score_fieldtype = schema::IntOptions::default().set_fast(Cardinality::SingleValue);
let score_field = schema_builder.add_u64_field("score", score_fieldtype);
@@ -851,21 +857,21 @@ mod tests {
{
// a first commit
index_writer.add_document(doc!(
text_field => "a b d",
score_field => 1u64,
bytes_score_field => vec![0u8, 0, 0, 1],
));
text_field => "a b d",
score_field => 1u64,
bytes_score_field => vec![0u8, 0, 0, 1],
));
index_writer.add_document(doc!(
text_field => "b c",
score_field => 2u64,
bytes_score_field => vec![0u8, 0, 0, 2],
));
text_field => "b c",
score_field => 2u64,
bytes_score_field => vec![0u8, 0, 0, 2],
));
index_writer.delete_term(Term::from_field_text(text_field, "c"));
index_writer.add_document(doc!(
text_field => "c d",
score_field => 3u64,
bytes_score_field => vec![0u8, 0, 0, 3],
));
text_field => "c d",
score_field => 3u64,
bytes_score_field => vec![0u8, 0, 0, 3],
));
index_writer.commit().expect("committed");
index.load_searchers().unwrap();
let ref searcher = *index.searcher();
@@ -892,27 +898,27 @@ mod tests {
{
// a second commit
index_writer.add_document(doc!(
text_field => "a d e",
score_field => 4_000u64,
bytes_score_field => vec![0u8, 0, 0, 4],
));
text_field => "a d e",
score_field => 4_000u64,
bytes_score_field => vec![0u8, 0, 0, 4],
));
index_writer.add_document(doc!(
text_field => "e f",
score_field => 5_000u64,
bytes_score_field => vec![0u8, 0, 0, 5],
));
text_field => "e f",
score_field => 5_000u64,
bytes_score_field => vec![0u8, 0, 0, 5],
));
index_writer.delete_term(Term::from_field_text(text_field, "a"));
index_writer.delete_term(Term::from_field_text(text_field, "f"));
index_writer.add_document(doc!(
text_field => "f g",
score_field => 6_000u64,
bytes_score_field => vec![0u8, 0, 23, 112],
));
text_field => "f g",
score_field => 6_000u64,
bytes_score_field => vec![0u8, 0, 23, 112],
));
index_writer.add_document(doc!(
text_field => "g h",
score_field => 7_000u64,
bytes_score_field => vec![0u8, 0, 27, 88],
));
text_field => "g h",
score_field => 7_000u64,
bytes_score_field => vec![0u8, 0, 27, 88],
));
index_writer.commit().expect("committed");
index.load_searchers().unwrap();
let searcher = index.searcher();

View File

@@ -138,7 +138,7 @@ struct InnerSegmentUpdater {
}
impl SegmentUpdater {
pub fn new(
pub fn create(
index: Index,
stamper: Stamper,
delete_cursor: &DeleteCursor,
@@ -195,7 +195,8 @@ impl SegmentUpdater {
segment_updater.0.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options();
true
}).forget();
})
.forget();
true
} else {
false
@@ -249,14 +250,16 @@ impl SegmentUpdater {
opstamp,
commit_message,
directory.box_clone().borrow_mut(),
).expect("Could not save metas.");
)
.expect("Could not save metas.");
}
}
pub fn garbage_collect_files(&self) -> Result<()> {
self.run_async(move |segment_updater| {
segment_updater.garbage_collect_files_exec();
}).wait()
})
.wait()
}
fn garbage_collect_files_exec(&self) {
@@ -278,7 +281,8 @@ impl SegmentUpdater {
segment_updater.garbage_collect_files_exec();
segment_updater.consider_merge_options();
}
}).wait()
})
.wait()
}
pub fn start_merge(&self, segment_ids: &[SegmentId]) -> Result<Receiver<SegmentMeta>> {
@@ -286,7 +290,8 @@ impl SegmentUpdater {
let segment_ids_vec = segment_ids.to_vec();
self.run_async(move |segment_updater| {
segment_updater.start_merge_impl(&segment_ids_vec[..])
}).wait()?
})
.wait()?
}
// `segment_ids` is required to be non-empty.
@@ -352,7 +357,8 @@ impl SegmentUpdater {
.unwrap()
.remove(&merging_thread_id);
Ok(())
}).expect("Failed to spawn a thread.");
})
.expect("Failed to spawn a thread.");
self.0
.merging_threads
.write()
@@ -443,7 +449,8 @@ impl SegmentUpdater {
let previous_metas = segment_updater.0.index.load_metas().unwrap();
segment_updater.save_metas(previous_metas.opstamp, previous_metas.payload);
segment_updater.garbage_collect_files_exec();
}).wait()
})
.wait()
}
/// Wait for current merging threads.

View File

@@ -62,7 +62,8 @@ impl SegmentWriter {
segment.index().tokenizers().get(tokenizer_name)
}),
_ => None,
}).collect();
})
.collect();
Ok(SegmentWriter {
max_doc: 0,
multifield_postings,
@@ -117,7 +118,8 @@ impl SegmentWriter {
_ => {
panic!("Expected hierarchical facet");
}
}).collect();
})
.collect();
let mut term = Term::for_field(field); // we set the Term
for facet_bytes in facets {
let mut unordered_term_id_opt = None;
@@ -145,7 +147,8 @@ impl SegmentWriter {
.flat_map(|field_value| match *field_value.value() {
Value::Str(ref text) => Some(text.as_str()),
_ => None,
}).collect();
})
.collect();
if texts.is_empty() {
0
} else {

View File

@@ -1,6 +1,5 @@
#![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
#![cfg_attr(all(feature = "unstable", test), feature(test))]
#![cfg_attr(feature = "cargo-clippy", feature(tool_lints))]
#![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
#![doc(test(attr(allow(unused_variables), deny(warnings))))]
#![warn(missing_docs)]
@@ -184,10 +183,7 @@ mod macros;
pub use error::TantivyError;
#[deprecated(
since = "0.7.0",
note = "please use `tantivy::TantivyError` instead"
)]
#[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
pub use error::TantivyError as Error;
extern crate census;
@@ -217,7 +213,7 @@ pub mod store;
pub mod termdict;
mod snippet;
pub use self::snippet::{SnippetGenerator, Snippet};
pub use self::snippet::{Snippet, SnippetGenerator};
mod docset;
pub use self::docset::{DocSet, SkipResult};
@@ -514,11 +510,9 @@ mod tests {
let searcher = index.searcher();
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(text_field);
assert!(
inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none()
);
assert!(inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none());
{
let mut postings = inverted_index
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
@@ -553,11 +547,9 @@ mod tests {
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(term_abcd.field());
assert!(
inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none()
);
assert!(inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none());
{
let mut postings = inverted_index
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
@@ -591,11 +583,9 @@ mod tests {
let searcher = index.searcher();
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(term_abcd.field());
assert!(
inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none()
);
assert!(inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none());
{
let mut postings = inverted_index
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
@@ -743,11 +733,9 @@ mod tests {
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(text_field);
let term_abcd = Term::from_field_text(text_field, "abcd");
assert!(
inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none()
);
assert!(inverted_index
.read_postings(&term_abcd, IndexRecordOption::WithFreqsAndPositions)
.is_none());
let term_af = Term::from_field_text(text_field, "af");
let mut postings = inverted_index
.read_postings(&term_af, IndexRecordOption::WithFreqsAndPositions)

View File

@@ -77,10 +77,10 @@ mod test {
let likes = schema_builder.add_u64_field("num_u64", FAST);
let _schema = schema_builder.build();
let _doc = doc!(
title => "Life Aquatic",
author => "Wes Anderson",
likes => 4u64
);
title => "Life Aquatic",
author => "Wes Anderson",
likes => 4u64
);
}
#[test]
@@ -91,9 +91,9 @@ mod test {
let likes = schema_builder.add_u64_field("num_u64", FAST);
let _schema = schema_builder.build();
let _doc = doc!(
title => "Life Aquatic",
author => "Wes Anderson",
likes => 4u64,
);
title => "Life Aquatic",
author => "Wes Anderson",
likes => 4u64,
);
}
}

View File

@@ -221,12 +221,10 @@ pub mod tests {
}
{
let term_a = Term::from_field_text(text_field, "abcdef");
assert!(
segment_reader
.inverted_index(term_a.field())
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
.is_none()
);
assert!(segment_reader
.inverted_index(term_a.field())
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
.is_none());
}
{
let term_a = Term::from_field_text(text_field, "a");

View File

@@ -29,7 +29,8 @@ fn posting_from_field_entry(field_entry: &FieldEntry) -> Box<PostingsWriter> {
IndexRecordOption::WithFreqsAndPositions => {
SpecializedPostingsWriter::<TFAndPositionRecorder>::new_boxed()
}
}).unwrap_or_else(|| SpecializedPostingsWriter::<NothingRecorder>::new_boxed()),
})
.unwrap_or_else(|| SpecializedPostingsWriter::<NothingRecorder>::new_boxed()),
FieldType::U64(_) | FieldType::I64(_) | FieldType::HierarchicalFacet => {
SpecializedPostingsWriter::<NothingRecorder>::new_boxed()
}
@@ -107,10 +108,8 @@ impl MultiFieldPostingsWriter {
.map(|(key, _, _)| Term::wrap(key).field())
.enumerate();
let mut unordered_term_mappings: HashMap<
Field,
HashMap<UnorderedTermId, TermOrdinal>,
> = HashMap::new();
let mut unordered_term_mappings: HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>> =
HashMap::new();
let mut prev_field = Field(u32::max_value());
for (offset, field) in term_offsets_it {
@@ -138,7 +137,8 @@ impl MultiFieldPostingsWriter {
.enumerate()
.map(|(term_ord, unord_term_id)| {
(unord_term_id as UnorderedTermId, term_ord as TermOrdinal)
}).collect();
})
.collect();
unordered_term_mappings.insert(field, mapping);
}
FieldType::U64(_) | FieldType::I64(_) => {}

View File

@@ -533,7 +533,8 @@ impl BlockSegmentPostings {
} else {
BlockSegmentPostingsSkipResult::Terminated
}
}).unwrap_or(BlockSegmentPostingsSkipResult::Terminated);
})
.unwrap_or(BlockSegmentPostingsSkipResult::Terminated);
}
BlockSegmentPostingsSkipResult::Terminated
}

View File

@@ -55,7 +55,7 @@ pub struct InvertedIndexSerializer {
impl InvertedIndexSerializer {
/// Open a new `PostingsSerializer` for the given segment
fn new(
fn create(
terms_write: CompositeWrite<WritePtr>,
postings_write: CompositeWrite<WritePtr>,
positions_write: CompositeWrite<WritePtr>,
@@ -74,7 +74,7 @@ impl InvertedIndexSerializer {
/// Open a new `PostingsSerializer` for the given segment
pub fn open(segment: &mut Segment) -> Result<InvertedIndexSerializer> {
use SegmentComponent::{POSITIONS, POSITIONSSKIP, POSTINGS, TERMS};
InvertedIndexSerializer::new(
InvertedIndexSerializer::create(
CompositeWrite::wrap(segment.open_write(TERMS)?),
CompositeWrite::wrap(segment.open_write(POSTINGS)?),
CompositeWrite::wrap(segment.open_write(POSITIONS)?),
@@ -99,7 +99,7 @@ impl InvertedIndexSerializer {
let positions_write = self.positions_write.for_field(field);
let positionsidx_write = self.positionsidx_write.for_field(field);
let field_type: FieldType = (*field_entry.field_type()).clone();
FieldSerializer::new(
FieldSerializer::create(
&field_type,
term_dictionary_write,
postings_write,
@@ -130,7 +130,7 @@ pub struct FieldSerializer<'a> {
}
impl<'a> FieldSerializer<'a> {
fn new(
fn create(
field_type: &FieldType,
term_dictionary_write: &'a mut CountingWriter<WritePtr>,
postings_write: &'a mut CountingWriter<WritePtr>,
@@ -152,7 +152,7 @@ impl<'a> FieldSerializer<'a> {
_ => (false, false),
};
let term_dictionary_builder =
TermDictionaryBuilder::new(term_dictionary_write, &field_type)?;
TermDictionaryBuilder::create(term_dictionary_write, &field_type)?;
let postings_serializer =
PostingsSerializer::new(postings_write, term_freq_enabled, position_enabled);
let positions_serializer_opt = if position_enabled {

View File

@@ -63,7 +63,8 @@ impl BM25Weight {
.map(|term| {
let term_doc_freq = searcher.doc_freq(term);
idf(term_doc_freq, total_num_docs)
}).sum::<f32>();
})
.sum::<f32>();
BM25Weight::new(idf, average_fieldnorm)
}

View File

@@ -47,7 +47,8 @@ impl Query for BooleanQuery {
.iter()
.map(|&(ref occur, ref subquery)| {
Ok((*occur, subquery.weight(searcher, scoring_enabled)?))
}).collect::<Result<_>>()?;
})
.collect::<Result<_>>()?;
Ok(Box::new(BooleanWeight::new(sub_weights, scoring_enabled)))
}
@@ -68,7 +69,8 @@ impl BooleanQuery {
let term_query: Box<Query> =
Box::new(TermQuery::new(term, IndexRecordOption::WithFreqs));
(Occur::Should, term_query)
}).collect();
})
.collect();
BooleanQuery::from(occur_term_queries)
}

View File

@@ -134,7 +134,8 @@ impl<TPostings: Postings> PhraseScorer<TPostings> {
.into_iter()
.map(|(offset, postings)| {
PostingsWithOffset::new(postings, (max_offset - offset) as u32)
}).collect::<Vec<_>>();
})
.collect::<Vec<_>>();
PhraseScorer {
intersection_docset: Intersection::new(postings_with_offsets),
num_docsets,

View File

@@ -68,7 +68,8 @@ fn trim_ast(logical_ast: LogicalAST) -> Option<LogicalAST> {
.into_iter()
.flat_map(|(occur, child)| {
trim_ast(child).map(|trimmed_child| (occur, trimmed_child))
}).collect::<Vec<_>>();
})
.collect::<Vec<_>>();
if trimmed_children.is_empty() {
None
} else {
@@ -422,7 +423,8 @@ impl QueryParser {
lower: self.resolve_bound(field, &lower)?,
upper: self.resolve_bound(field, &upper)?,
})))
}).collect::<Result<Vec<_>, QueryParserError>>()?;
})
.collect::<Result<Vec<_>, QueryParserError>>()?;
let result_ast = if clauses.len() == 1 {
clauses.pop().unwrap()
} else {
@@ -598,25 +600,19 @@ mod test {
assert!(query_parser.parse_query("signed:2324").is_ok());
assert!(query_parser.parse_query("signed:\"22\"").is_ok());
assert!(query_parser.parse_query("signed:\"-2234\"").is_ok());
assert!(
query_parser
.parse_query("signed:\"-9999999999999\"")
.is_ok()
);
assert!(query_parser
.parse_query("signed:\"-9999999999999\"")
.is_ok());
assert!(query_parser.parse_query("signed:\"a\"").is_err());
assert!(query_parser.parse_query("signed:\"2a\"").is_err());
assert!(
query_parser
.parse_query("signed:\"18446744073709551615\"")
.is_err()
);
assert!(query_parser
.parse_query("signed:\"18446744073709551615\"")
.is_err());
assert!(query_parser.parse_query("unsigned:\"2\"").is_ok());
assert!(query_parser.parse_query("unsigned:\"-2\"").is_err());
assert!(
query_parser
.parse_query("unsigned:\"18446744073709551615\"")
.is_ok()
);
assert!(query_parser
.parse_query("unsigned:\"18446744073709551615\"")
.is_ok());
test_parse_query_to_logical_ast_helper(
"unsigned:2324",
"Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",

View File

@@ -1,4 +1,3 @@
mod term_query;
mod term_scorer;
mod term_weight;

View File

@@ -55,7 +55,8 @@ where
None
}
},
).collect();
)
.collect();
Union {
docsets: non_empty_docsets,
bitsets: Box::new([TinySet::empty(); HORIZON_NUM_TINYBITSETS]),
@@ -214,10 +215,7 @@ where
// The target is outside of the buffered horizon.
// advance all docsets to a doc >= to the target.
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::clippy::collapsible_if)
)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::clippy::collapsible_if))]
unordered_drain_filter(&mut self.docsets, |docset| {
if docset.doc() < target {
if docset.skip_next(target) == SkipResult::End {

View File

@@ -232,12 +232,14 @@ impl Schema {
let field_entry = self.get_field_entry(field);
let field_type = field_entry.field_type();
match *json_value {
JsonValue::Array(ref json_items) => for json_item in json_items {
let value = field_type
.value_from_json(json_item)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
},
JsonValue::Array(ref json_items) => {
for json_item in json_items {
let value = field_type.value_from_json(json_item).map_err(|e| {
DocParsingError::ValueError(field_name.clone(), e)
})?;
doc.add(FieldValue::new(field, value));
}
}
_ => {
let value = field_type
.value_from_json(json_value)
@@ -446,7 +448,8 @@ mod tests {
"count": 4,
"popularity": 10
}"#,
).unwrap();
)
.unwrap();
assert_eq!(doc.get_first(title_field).unwrap().text(), Some("my title"));
assert_eq!(
doc.get_first(author_field).unwrap().text(),

View File

@@ -192,7 +192,8 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
item.start - fragment.start_offset,
item.stop - fragment.start_offset,
)
}).collect();
})
.collect();
Snippet {
fragments: fragment_text.to_string(),
highlighted,
@@ -242,7 +243,7 @@ fn select_best_fragment_combination(fragments: &[FragmentCandidate], text: &str)
/// let query = query_parser.parse_query("haleurs flamands").unwrap();
/// # index.load_searchers()?;
/// # let searcher = index.searcher();
/// let mut snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field)?;
/// let mut snippet_generator = SnippetGenerator::create(&searcher, &*query, text_field)?;
/// snippet_generator.set_max_num_chars(100);
/// let snippet = snippet_generator.snippet_from_doc(&doc);
/// let snippet_html: String = snippet.to_html();
@@ -259,7 +260,7 @@ pub struct SnippetGenerator {
impl SnippetGenerator {
/// Creates a new snippet generator
pub fn new(searcher: &Searcher, query: &Query, field: Field) -> Result<SnippetGenerator> {
pub fn create(searcher: &Searcher, query: &Query, field: Field) -> Result<SnippetGenerator> {
let mut terms = BTreeSet::new();
query.query_terms(&mut terms);
let terms_text: BTreeMap<String, f32> = terms
@@ -273,7 +274,8 @@ impl SnippetGenerator {
} else {
None
}
}).collect();
})
.collect();
let tokenizer = searcher.index().tokenizer_for_field(field)?;
Ok(SnippetGenerator {
terms_text,
@@ -532,12 +534,14 @@ Survey in 2016, 2017, and 2018."#;
let query_parser = QueryParser::for_index(&index, vec![text_field]);
{
let query = query_parser.parse_query("e").unwrap();
let snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field).unwrap();
let snippet_generator =
SnippetGenerator::create(&searcher, &*query, text_field).unwrap();
assert!(snippet_generator.terms_text().is_empty());
}
{
let query = query_parser.parse_query("a").unwrap();
let snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field).unwrap();
let snippet_generator =
SnippetGenerator::create(&searcher, &*query, text_field).unwrap();
assert_eq!(
&btreemap!("a".to_string() => 0.25f32),
snippet_generator.terms_text()
@@ -545,7 +549,8 @@ Survey in 2016, 2017, and 2018."#;
}
{
let query = query_parser.parse_query("a b").unwrap();
let snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field).unwrap();
let snippet_generator =
SnippetGenerator::create(&searcher, &*query, text_field).unwrap();
assert_eq!(
&btreemap!("a".to_string() => 0.25f32, "b".to_string() => 0.5),
snippet_generator.terms_text()
@@ -553,7 +558,8 @@ Survey in 2016, 2017, and 2018."#;
}
{
let query = query_parser.parse_query("a b c").unwrap();
let snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field).unwrap();
let snippet_generator =
SnippetGenerator::create(&searcher, &*query, text_field).unwrap();
assert_eq!(
&btreemap!("a".to_string() => 0.25f32, "b".to_string() => 0.5),
snippet_generator.terms_text()
@@ -585,7 +591,8 @@ Survey in 2016, 2017, and 2018."#;
let searcher = index.searcher();
let query_parser = QueryParser::for_index(&index, vec![text_field]);
let query = query_parser.parse_query("rust design").unwrap();
let mut snippet_generator = SnippetGenerator::new(&searcher, &*query, text_field).unwrap();
let mut snippet_generator =
SnippetGenerator::create(&searcher, &*query, text_field).unwrap();
{
let snippet = snippet_generator.snippet(TEST_TEXT);
assert_eq!(snippet.to_html(), "imperative-procedural paradigms. <b>Rust</b> is syntactically similar to C++[according to whom?],\nbut its <b>designers</b> intend it to provide better memory safety");

View File

@@ -80,6 +80,7 @@ pub struct SegmentSpaceUsage {
}
impl SegmentSpaceUsage {
#[allow(clippy::too_many_arguments)]
pub(crate) fn new(
num_docs: u32,
termdict: PerFieldSpaceUsage,

View File

@@ -95,10 +95,7 @@ impl StoreReader {
}
}
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::needless_pass_by_value)
)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))]
fn split_source(data: ReadOnlySource) -> (ReadOnlySource, ReadOnlySource, DocId) {
let data_len = data.len();
let footer_offset = data_len - size_of::<u64>() - size_of::<u32>();

View File

@@ -53,7 +53,8 @@ impl<'a> TermMerger<'a> {
.map(|(ord, streamer)| HeapItem {
streamer,
segment_ord: ord,
}).collect(),
})
.collect(),
}
}
@@ -122,10 +123,7 @@ impl<'a> TermMerger<'a> {
}
/// Iterates through terms
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::should_implement_trait)
)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::should_implement_trait))]
pub fn next(&mut self) -> Option<Term<&[u8]>> {
if self.advance() {
Some(Term::wrap(self.current_streamers[0].streamer.key()))

View File

@@ -66,7 +66,7 @@ mod tests {
let write = directory.open_write(&path).unwrap();
let field_type = FieldType::Str(TEXT);
let mut term_dictionary_builder =
TermDictionaryBuilder::new(write, &field_type).unwrap();
TermDictionaryBuilder::create(write, &field_type).unwrap();
for term in COUNTRIES.iter() {
term_dictionary_builder
.insert(term.as_bytes(), &make_term_info(0u64))
@@ -92,7 +92,7 @@ mod tests {
let write = directory.open_write(&path).unwrap();
let field_type = FieldType::Str(TEXT);
let mut term_dictionary_builder =
TermDictionaryBuilder::new(write, &field_type).unwrap();
TermDictionaryBuilder::create(write, &field_type).unwrap();
term_dictionary_builder
.insert("abc".as_bytes(), &make_term_info(34u64))
.unwrap();
@@ -180,7 +180,7 @@ mod tests {
let field_type = FieldType::Str(TEXT);
let buffer: Vec<u8> = {
let mut term_dictionary_builder =
TermDictionaryBuilder::new(vec![], &field_type).unwrap();
TermDictionaryBuilder::create(vec![], &field_type).unwrap();
for &(ref id, ref i) in &ids {
term_dictionary_builder
.insert(id.as_bytes(), &make_term_info(*i as u64))
@@ -210,7 +210,7 @@ mod tests {
let field_type = FieldType::Str(TEXT);
let buffer: Vec<u8> = {
let mut term_dictionary_builder =
TermDictionaryBuilder::new(vec![], &field_type).unwrap();
TermDictionaryBuilder::create(vec![], &field_type).unwrap();
// term requires more than 16bits
term_dictionary_builder
.insert("abcdefghijklmnopqrstuvwxy", &make_term_info(1))
@@ -245,7 +245,7 @@ mod tests {
let field_type = FieldType::Str(TEXT);
let buffer: Vec<u8> = {
let mut term_dictionary_builder =
TermDictionaryBuilder::new(vec![], &field_type).unwrap();
TermDictionaryBuilder::create(vec![], &field_type).unwrap();
for &(ref id, ref i) in &ids {
term_dictionary_builder
.insert(id.as_bytes(), &make_term_info(*i as u64))
@@ -314,7 +314,7 @@ mod tests {
let field_type = FieldType::Str(TEXT);
let buffer: Vec<u8> = {
let mut term_dictionary_builder =
TermDictionaryBuilder::new(vec![], &field_type).unwrap();
TermDictionaryBuilder::create(vec![], &field_type).unwrap();
term_dictionary_builder
.insert(&[], &make_term_info(1 as u64))
.unwrap();
@@ -338,7 +338,7 @@ mod tests {
let field_type = FieldType::Str(TEXT);
let buffer: Vec<u8> = {
let mut term_dictionary_builder =
TermDictionaryBuilder::new(vec![], &field_type).unwrap();
TermDictionaryBuilder::create(vec![], &field_type).unwrap();
for i in 0u8..10u8 {
let number_arr = [i; 1];
term_dictionary_builder
@@ -408,7 +408,7 @@ mod tests {
let write = directory.open_write(&path).unwrap();
let field_type = FieldType::Str(TEXT);
let mut term_dictionary_builder =
TermDictionaryBuilder::new(write, &field_type).unwrap();
TermDictionaryBuilder::create(write, &field_type).unwrap();
for term in COUNTRIES.iter() {
term_dictionary_builder
.insert(term.as_bytes(), &make_term_info(0u64))

View File

@@ -132,10 +132,7 @@ where
}
/// Return the next `(key, value)` pair.
#[cfg_attr(
feature = "cargo-clippy",
allow(clippy::should_implement_trait)
)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::should_implement_trait))]
pub fn next(&mut self) -> Option<(&[u8], &TermInfo)> {
if self.advance() {
Some((self.key(), self.value()))

View File

@@ -29,7 +29,7 @@ where
W: Write,
{
/// Creates a new `TermDictionaryBuilder`
pub fn new(w: W, _field_type: &FieldType) -> io::Result<Self> {
pub fn create(w: W, _field_type: &FieldType) -> io::Result<Self> {
let fst_builder = fst::MapBuilder::new(w).map_err(convert_fst_error)?;
Ok(TermDictionaryBuilder {
fst_builder,
@@ -132,7 +132,7 @@ impl TermDictionary {
/// Creates an empty term dictionary which contains no terms.
pub fn empty(field_type: &FieldType) -> Self {
let term_dictionary_data: Vec<u8> =
TermDictionaryBuilder::new(Vec::<u8>::new(), &field_type)
TermDictionaryBuilder::create(Vec::<u8>::new(), &field_type)
.expect("Creating a TermDictionaryBuilder in a Vec<u8> should never fail")
.finish()
.expect("Writing in a Vec<u8> should never fail");