gibheer/bleve
0
0
Fork 0
Code

changed term row encoding

Browse Source 
previously we used the format:
't' <utf-8 term> <byte separator> <16-bit field id> <utf-8 docID> <byte separator>

now we have moved the field before the term, resulting in:
't' <16-bit field id> <utf-8 term> <byte separator> <utf-8 docID> <byte separator>

this means now instead of all fields with the same term being grouped together
all terms within the same field are grouped together

this allows us to enumerate the terms used with a field

this allows us to implement prefix search, and possibly improve numeric range queries
This commit is contained in:
Marty Schoch 2014-08-07 09:39:04 -04:00
parent 0e54fbd8da
commit b16c1d7f79
2 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
index/upside_down/row.go
View File

@ -150,12 +150,12 @@ type TermFrequencyRow struct {
}
func (tfr *TermFrequencyRow) Key() []byte {
buf := make([]byte, 1+len(tfr.term)+1+2+len(tfr.doc))
buf := make([]byte, 3+len(tfr.term)+1+len(tfr.doc))
buf[0] = 't'
termLen := copy(buf[1:], tfr.term)
buf[1+termLen] = BYTE_SEPARATOR
binary.LittleEndian.PutUint16(buf[1+termLen+1:1+termLen+1+2], tfr.field)
copy(buf[1+termLen+1+2:], tfr.doc)
binary.LittleEndian.PutUint16(buf[1:3], tfr.field)
termLen := copy(buf[3:], tfr.term)
buf[3+termLen] = BYTE_SEPARATOR
copy(buf[3+termLen+1:], tfr.doc)
return buf
}
@ -211,17 +211,17 @@ func NewTermFrequencyRowKV(key, value []byte) (*TermFrequencyRow, error) {
buf.ReadByte() // type
var err error
err = binary.Read(buf, binary.LittleEndian, &rv.field)
if err != nil {
return nil, err
}
rv.term, err = buf.ReadBytes(BYTE_SEPARATOR)
if err != nil {
return nil, err
}
rv.term = rv.term[:len(rv.term)-1] // trim off separator byte
err = binary.Read(buf, binary.LittleEndian, &rv.field)
if err != nil {
return nil, err
}
doc, err := buf.ReadBytes(BYTE_SEPARATOR)
if err != io.EOF {
return nil, err

26
index/upside_down/row_test.go
View File

@ -41,17 +41,17 @@ func TestRows(t *testing.T) {
},
{
NewTermFrequencyRow([]byte{'b', 'e', 'e', 'r'}, 0, "", 3, 3.14),
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64},
},
{
NewTermFrequencyRow([]byte{'b', 'e', 'e', 'r'}, 0, "budweiser", 3, 3.14),
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64},
},
{
NewTermFrequencyRowWithTermVectors([]byte{'b', 'e', 'e', 'r'}, 0, "budweiser", 3, 3.14, []*TermVector{&TermVector{field: 0, pos: 1, start: 3, end: 11}, &TermVector{field: 0, pos: 2, start: 23, end: 31}, &TermVector{field: 0, pos: 3, start: 43, end: 51}}),
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 23, 0, 0, 0, 0, 0, 0, 0, 31, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 43, 0, 0, 0, 0, 0, 0, 0, 51, 0, 0, 0, 0, 0, 0, 0},
},
{
@ -131,49 +131,49 @@ func TestInvalidRows(t *testing.T) {
[]byte{'f', 0, 0},
[]byte{},
},
// type t, invalid key (missing term)
// type t, invalid key (missing field)
{
[]byte{'t'},
[]byte{},
},
// type t, invalid key (missing field)
// type t, invalid key (missing term)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR},
[]byte{'t', 0, 0},
[]byte{},
},
// type t, invalid key (missing id)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR},
[]byte{},
},
// type t, invalid val (misisng freq)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{},
},
// type t, invalid val (missing norm)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0},
},
// type t, invalid val (half missing tv field, full missing is valid (no term vectors))
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64, 0},
},
// type t, invalid val (missing tv pos)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64, 0, 0},
},
// type t, invalid val (missing tv start)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0},
},
// type t, invalid val (missing tv end)
{
[]byte{'t', 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 0, 0, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{'t', 0, 0, 'b', 'e', 'e', 'r', BYTE_SEPARATOR, 'b', 'u', 'd', 'w', 'e', 'i', 's', 'e', 'r'},
[]byte{3, 0, 0, 0, 0, 0, 0, 0, 195, 245, 72, 64, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0},
},
// type b, invalid key (missing id)