Searched defs:indexedDocument (Results 1 – 6 of 6) sorted by relevance
| /external/licenseclassifier/v2/ |
| D | document.go | 39 type indexedDocument struct { struct
40 Norm string // The normalized token sequence
41 Tokens []indexedToken // ordered tokens of the document
42 …// these are matches identified while processing the original, untokenized text via regexp matching
43 f *frequencyTable // frequencies computed for this document
44 dict *dictionary // The corpus dictionary for this document
45 s *searchSet // The searchset for this document
46 runes []rune
49 func (d *indexedDocument) generateSearchSet(q int) {
53 func (d *indexedDocument) size() int {
[all …]
|
| D | diff.go | 48 func docDiff(id string, doc1 *indexedDocument, doc1Start, doc1End int, doc2 *indexedDocument, doc2S…
60 func diffWordsToRunes(doc *indexedDocument, start, end int) []rune {
|
| D | frequencies.go | 41 func (d *indexedDocument) tokenSimilarity(o *indexedDocument) float64 {
|
| D | scoring.go | 36 func (c *Classifier) score(id string, unknown, known *indexedDocument, unknownStart, unknownEnd int…
|
| D | tokenizer.go | 240 func appendToDoc(doc *indexedDocument, dict *dictionary, line int, in []tokenID, ld *dictionary, no…
|
| D | searchset.go | 58 func newSearchSet(s *indexedDocument, q int) *searchSet {
|