github.com/m3db/m3@v1.5.0/src/m3ninx/index/segment/fst/fst_writer.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 fst
    22  
    23  import (
    24  	"errors"
    25  	"io"
    26  
    27  	"github.com/m3dbx/vellum"
    28  )
    29  
    30  var (
    31  	errFSTWriterBuildUnset = errors.New("fst writer builer has not been Reset() before use")
    32  
    33  	// NB(r): The registry cache used by vellum is: table size * mru size * cell size
    34  	// where cell size = 16 bytes (since its an addr and a ptr)
    35  	// basically MRU size is the size of each bucket for each combination of
    36  	// a builder node
    37  	defaultVellumBuilderOpts = vellum.BuilderOpts{
    38  		Encoder:                  1,
    39  		RegistryTableSize:        10000, // 10k
    40  		RegistryMRUSize:          2,     // 4
    41  		UnfinishedNodesStackSize: 4096,
    42  		BuilderNodePoolingConfig: vellum.BuilderNodePoolingConfig{
    43  			MaxSize:           2 << 16, // ~130k
    44  			MaxTransitionSize: 2 << 7,  // 256
    45  		},
    46  	}
    47  )
    48  
    49  // fstWriter is a writer to help construct an FST.
    50  type fstWriter struct {
    51  	bytesWritten uint64
    52  	writer       io.Writer
    53  	builderOpts  *vellum.BuilderOpts
    54  	builder      *vellum.Builder
    55  }
    56  
    57  func newFSTWriter(opts WriterOptions) *fstWriter {
    58  	builderOpts := new(vellum.BuilderOpts)
    59  	*builderOpts = defaultVellumBuilderOpts
    60  	if opts.DisableRegistry {
    61  		builderOpts.RegistryTableSize = 0
    62  		builderOpts.RegistryMRUSize = 0
    63  	}
    64  	return &fstWriter{builderOpts: builderOpts}
    65  }
    66  
    67  func (f *fstWriter) Write(p []byte) (int, error) {
    68  	if f.writer == nil {
    69  		return 0, errFSTWriterBuildUnset
    70  	}
    71  	n, err := f.writer.Write(p)
    72  	if err != nil {
    73  		return 0, err
    74  	}
    75  	f.bytesWritten += uint64(n)
    76  	return n, nil
    77  }
    78  
    79  func (f *fstWriter) Reset(w io.Writer) error {
    80  	f.bytesWritten = 0
    81  	f.writer = w
    82  	if f.builder == nil {
    83  		builder, err := vellum.New(f, f.builderOpts)
    84  		if err != nil {
    85  			return err
    86  		}
    87  		f.builder = builder
    88  		return nil
    89  	}
    90  	return f.builder.Reset(f)
    91  }
    92  
    93  func (f *fstWriter) Add(b []byte, v uint64) error {
    94  	if f.builder == nil {
    95  		return errFSTWriterBuildUnset
    96  	}
    97  	return f.builder.Insert(b, v)
    98  }
    99  
   100  func (f *fstWriter) Close() (uint64, error) {
   101  	if f.builder == nil {
   102  		return 0, errFSTWriterBuildUnset
   103  	}
   104  	err := f.builder.Close()
   105  	if err != nil {
   106  		return 0, nil
   107  	}
   108  	return f.bytesWritten, nil
   109  }