github.com/m3db/m3@v1.5.1-0.20231129193456-75a402aa583b/src/m3ninx/postings/pilosa/codec.go (about)

     1  // Copyright (c) 2018 Uber Technologies, Inc.
     2  //
     3  // Permission is hereby granted, free of charge, to any person obtaining a copy
     4  // of this software and associated documentation files (the "Software"), to deal
     5  // in the Software without restriction, including without limitation the rights
     6  // to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
     7  // copies of the Software, and to permit persons to whom the Software is
     8  // furnished to do so, subject to the following conditions:
     9  //
    10  // The above copyright notice and this permission notice shall be included in
    11  // all copies or substantial portions of the Software.
    12  //
    13  // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
    14  // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
    15  // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
    16  // AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
    17  // LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
    18  // OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
    19  // THE SOFTWARE.
    20  
    21  package pilosa
    22  
    23  import (
    24  	"bytes"
    25  
    26  	"github.com/m3db/m3/src/m3ninx/postings"
    27  	idxroaring "github.com/m3db/m3/src/m3ninx/postings/roaring"
    28  	"github.com/m3dbx/pilosa/roaring"
    29  )
    30  
    31  // Encoder helps serialize a Pilosa RoaringBitmap
    32  type Encoder struct {
    33  	scratchBuffer bytes.Buffer
    34  }
    35  
    36  // NewEncoder returns a new Encoder.
    37  func NewEncoder() *Encoder {
    38  	return &Encoder{}
    39  }
    40  
    41  // Reset resets the internal state of the encoder to allow
    42  // for re-use.
    43  func (e *Encoder) Reset() {
    44  	e.scratchBuffer.Reset()
    45  }
    46  
    47  // Encode encodes the provided postings list in serialized form.
    48  // The bytes returned are invalidate on a subsequent call to Encode(),
    49  // or Reset().
    50  func (e *Encoder) Encode(pl postings.List) ([]byte, error) {
    51  	e.scratchBuffer.Reset()
    52  
    53  	// Optimistically try to see if we can extract from the postings list itself
    54  	bitmap, ok := idxroaring.BitmapFromPostingsList(pl)
    55  	if !ok {
    56  		var err error
    57  		bitmap, err = toPilosa(pl)
    58  		if err != nil {
    59  			return nil, err
    60  		}
    61  	}
    62  
    63  	if _, err := bitmap.WriteTo(&e.scratchBuffer); err != nil {
    64  		return nil, err
    65  	}
    66  
    67  	return e.scratchBuffer.Bytes(), nil
    68  }
    69  
    70  func toPilosa(pl postings.List) (*roaring.Bitmap, error) {
    71  	bitmap := roaring.NewBitmap()
    72  	iter := pl.Iterator()
    73  
    74  	for iter.Next() {
    75  		_, err := bitmap.Add(uint64(iter.Current()))
    76  		if err != nil {
    77  			return nil, err
    78  		}
    79  	}
    80  
    81  	if err := iter.Err(); err != nil {
    82  		return nil, err
    83  	}
    84  
    85  	return bitmap, nil
    86  }
    87  
    88  // Unmarshal unmarshals the provided bytes into a postings.List.
    89  func Unmarshal(data []byte) (postings.List, error) {
    90  	bitmap := roaring.NewBitmap()
    91  	err := bitmap.UnmarshalBinary(data)
    92  	if err != nil {
    93  		return nil, err
    94  	}
    95  	return idxroaring.NewPostingsListFromBitmap(bitmap), nil
    96  }