mooncakes.io

analysis
→
cmd
→
core
→
index
→
query
→
schema
→
store
→
tests
→
README
U
AnalysisError
U
Bm25Scorer
U
BooleanClause
U
BooleanQuery
U
BoostQuery
U
ChineseDictionary
U
ChineseDictionaryResourceError
U
ChineseHmmModel
U
ChineseHmmModelError
U
ChineseHmmState
U
ChineseLexicon
U
ChineseLexiconEntry
U
ChineseLexiconError
U
ChineseSearchModeFilter
U
ChineseTokenizer
U
ChineseWordMatch
U
Directory
U
DocAddress
U
DocId
U
Document
U
EnglishStemmerFilter
U
FieldId
U
FsDirectory
U
IndexReader
U
IndexWriter
U
LowerCaseFilter
U
MemoryDirectory
U
NgramTokenizer
U
Occur
U
PersistenceError
U
PhraseQuery
U
Posting
U
Query
U
QueryParser
U
RawTokenizer
U
RemoveLongFilter
U
Schema
U
SchemaBuilder
U
Scorer
U
SearchHit
U
SearchStatistics
U
Searcher
U
Segment
U
SegmentWriter
U
SimpleTokenizer
U
StopWordFilter
U
StoredDocument
U
TableChineseHmmModel
U
Term
U
TermQuery
U
TextAnalyzer
U
TextOptions
U
Token
U
TokenFilter
U
TokenGraph
U
TokenGraphPath
U
TokenStream
U
Tokenizer
U
TokenizerManager
U
TopKCollector
U
Weight
U
WhitespaceAnalyzer
U
WhitespaceTokenizer
V
chinese_analyzer
V
chinese_dag_analyzer
V
chinese_dag_hmm_analyzer
V
chinese_dag_hmm_search_analyzer
V
chinese_dag_hmm_search_index_analyzer
V
chinese_dag_search_analyzer
V
chinese_dag_search_index_analyzer
V
chinese_search_analyzer
V
chinese_search_index_analyzer
V
english_stem_analyzer

README

Lucius646/MoonSearch/index does not have a README file

#
FieldLength

type FieldLength

#
FieldStats

source

type FieldStats

#
Posting

source

pub(all) struct Posting {
  doc_id : @Lucius646/MoonSearch/core.DocId
DocId
  term_freq : Int
  positions : ReadOnlyArray[Int]
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

One document occurrence in a posting list.

#
Segment

source

pub struct Segment {
  schema : @Lucius646/MoonSearch/schema.Schema
Schema?
  indexed_terms : ReadOnlyArray[@Lucius646/MoonSearch/core.Term
Term]
  posting_lists : ReadOnlyArray[ReadOnlyArray[Posting]]
  stored_documents : ReadOnlyArray[@Lucius646/MoonSearch/core.StoredDocument
StoredDocument]
  document_field_lengths : ReadOnlyArray[ReadOnlyArray[FieldLength]]
  field_stats : ReadOnlyArray[FieldStats]
  document_count : Int
}

Immutable in-memory index for one batch of documents.

#
Segment::average_field_length

source

fn Segment::average_field_length(self : Segment, field_id : @Lucius646/MoonSearch/core.FieldId
FieldId) -> Double

Average analyzed token count among documents that contain the field.

#
Segment::doc

source

fn Segment::doc(self : Segment, doc_id : @Lucius646/MoonSearch/core.DocId
DocId) -> @Lucius646/MoonSearch/core.StoredDocument
StoredDocument?

Returns the immutable stored document for a segment-local document ID.

#
Segment::doc_count

source

fn Segment::doc_count(self : Segment) -> Int

#
Segment::field_doc_count

source

fn Segment::field_doc_count(self : Segment, field_id : @Lucius646/MoonSearch/core.FieldId
FieldId) -> Int

Number of documents that contain the field, including empty field values.

#
Segment::field_length

source

fn Segment::field_length(self : Segment, doc_id : @Lucius646/MoonSearch/core.DocId
DocId, field_id : @Lucius646/MoonSearch/core.FieldId
FieldId) -> Int

Returns the analyzed token count for one document field.

#
Segment::has_field

source

fn Segment::has_field(self : Segment, doc_id : @Lucius646/MoonSearch/core.DocId
DocId, field_id : @Lucius646/MoonSearch/core.FieldId
FieldId) -> Bool

#
Segment::postings_for

source

fn Segment::postings_for(self : Segment, term : @Lucius646/MoonSearch/core.Term
Term) -> ReadOnlyArray[Posting]

Looks up a field-qualified term in this segment.

#
Segment::schema

source

fn Segment::schema(self : Segment) -> @Lucius646/MoonSearch/schema.Schema
Schema?

Returns the schema used by this segment, if it was built with one.

#
Segment::terms

source

fn Segment::terms(self : Segment) -> ReadOnlyArray[@Lucius646/MoonSearch/core.Term
Term]

Returns all indexed terms in deterministic first-seen order.

#
SegmentWriter

source

pub struct SegmentWriter[A] {
  tokenizer : A
  tokenizer_manager : @Lucius646/MoonSearch/analysis.TokenizerManager
TokenizerManager?
  schema : @Lucius646/MoonSearch/schema.Schema
Schema?
  terms : Array[@Lucius646/MoonSearch/core.Term
Term]
  posting_doc_ids : Array[Array[@Lucius646/MoonSearch/core.DocId
DocId]]
  posting_term_freqs : Array[Array[Int]]
  posting_positions : Array[Array[Array[Int]]]
  stored_documents : Array[@Lucius646/MoonSearch/core.StoredDocument
StoredDocument]
  document_field_lengths : Array[Array[FieldLength]]
  field_stats : Array[FieldStats]
  next_doc_id : Int
}

Mutable builder for one in-memory segment.

#
SegmentWriter::add_document

source

fn[A : @Lucius646/MoonSearch/analysis.Tokenizer
Tokenizer] SegmentWriter::add_document(self : SegmentWriter[A], document : @Lucius646/MoonSearch/core.Document
Document) -> @Lucius646/MoonSearch/core.DocId
DocId

Adds a document and returns its sequential segment-local identifier.

#
SegmentWriter::finish

source

fn[A] SegmentWriter::finish(self : SegmentWriter[A]) -> Segment

Finishes the current batch as an immutable in-memory segment.

#
SegmentWriter::new

source

fn[A] SegmentWriter::new(tokenizer : A) -> SegmentWriter[A]

#
SegmentWriter::with_schema

source

fn[A] SegmentWriter::with_schema(schema : @Lucius646/MoonSearch/schema.Schema
Schema, tokenizer : A) -> SegmentWriter[A]

Creates a writer that applies the schema's indexed and stored text options.

#
SegmentWriter::with_schema_and_tokenizers

source

fn SegmentWriter::with_schema_and_tokenizers(schema : @Lucius646/MoonSearch/schema.Schema
Schema, tokenizer_manager : @Lucius646/MoonSearch/analysis.TokenizerManager
TokenizerManager) -> SegmentWriter[@Lucius646/MoonSearch/analysis.WhitespaceAnalyzer
WhitespaceAnalyzer] raise @Lucius646/MoonSearch/analysis.AnalysisError
AnalysisError

Creates a schema-aware writer that resolves each indexed field's Tokenizer pipeline through the supplied TokenizerManager before accepting documents.

#
SnapshotSegment

source

pub struct SnapshotSegment {
  segment : Segment
  deleted_docs : ReadOnlyArray[@Lucius646/MoonSearch/core.DocId
DocId]
}

One immutable Segment together with the tombstones captured by a manifest generation.

#
SnapshotSegment::is_deleted

source

fn SnapshotSegment::is_deleted(self : SnapshotSegment, doc_id : @Lucius646/MoonSearch/core.DocId
DocId) -> Bool

#
SnapshotSegment::live_doc_count

source

fn SnapshotSegment::live_doc_count(self : SnapshotSegment) -> Int

#
SnapshotSegment::new

source

fn SnapshotSegment::new(segment : Segment, deleted_docs : ReadOnlyArray[@Lucius646/MoonSearch/core.DocId
DocId]) -> SnapshotSegment

#
decode_segment

source

fn decode_segment(bytes : Bytes) -> Segment raise @Lucius646/MoonSearch/core.PersistenceError
PersistenceError

Decodes and validates one immutable M3 Segment container.

#
encode_segment

source

fn encode_segment(segment : Segment) -> Bytes

#
live_snapshot

source

fn live_snapshot(segment : Segment) -> SnapshotSegment

#
merge_snapshot_segments

source

fn merge_snapshot_segments(snapshots : ReadOnlyArray[SnapshotSegment]) -> Segment

Combines live documents by copying immutable index structures and assigning consecutive DocIds in Segment order. No field is re-analyzed.

Source Files

Site source Report issue Packages Build queue Skills Statistics

#FieldLength

#FieldStats

#Posting

#Segment

#Segment::average_field_length

#Segment::doc

#Segment::doc_count

#Segment::field_doc_count

#Segment::field_length

#Segment::has_field

#Segment::postings_for

#Segment::schema

#Segment::terms

#SegmentWriter

#SegmentWriter::add_document

#SegmentWriter::finish

#SegmentWriter::new

#SegmentWriter::with_schema

#SegmentWriter::with_schema_and_tokenizers

#SnapshotSegment

#SnapshotSegment::is_deleted

#SnapshotSegment::live_doc_count

#SnapshotSegment::new

#decode_segment

#encode_segment

#live_snapshot

#merge_snapshot_segments

Source Files

#
FieldLength

#
FieldStats

#
Posting

#
Segment

#
Segment::average_field_length

#
Segment::doc

#
Segment::doc_count

#
Segment::field_doc_count

#
Segment::field_length

#
Segment::has_field

#
Segment::postings_for

#
Segment::schema

#
Segment::terms

#
SegmentWriter

#
SegmentWriter::add_document

#
SegmentWriter::finish

#
SegmentWriter::new

#
SegmentWriter::with_schema

#
SegmentWriter::with_schema_and_tokenizers

#
SnapshotSegment

#
SnapshotSegment::is_deleted

#
SnapshotSegment::live_doc_count

#
SnapshotSegment::new

#
decode_segment

#
encode_segment

#
live_snapshot

#
merge_snapshot_segments