github.com/m3db/m3@v1.5.0/src/m3ninx/index/segment/builder/multi_segments_terms_iter_test.go (about)

     1  // Copyright (c) 2019 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 builder
    22  
    23  import (
    24  	"fmt"
    25  	"strconv"
    26  	"strings"
    27  	"testing"
    28  
    29  	"github.com/m3db/m3/src/m3ninx/doc"
    30  	"github.com/m3db/m3/src/m3ninx/index/segment"
    31  	"github.com/m3db/m3/src/m3ninx/postings"
    32  
    33  	"github.com/stretchr/testify/require"
    34  )
    35  
    36  func TestTermsIterFromSegmentsDeduplicates(t *testing.T) {
    37  	segments := []segment.Segment{
    38  		newTestSegmentWithDocs(t, []doc.Metadata{
    39  			{
    40  				ID: []byte("foo"),
    41  				Fields: []doc.Field{
    42  					{Name: []byte("fruit"), Value: []byte("apple")},
    43  					{Name: []byte("vegetable"), Value: []byte("carrot")},
    44  				},
    45  			},
    46  		}),
    47  		newTestSegmentWithDocs(t, []doc.Metadata{
    48  			{
    49  				ID: []byte("bar"),
    50  				Fields: []doc.Field{
    51  					{Name: []byte("fruit"), Value: []byte("apple")},
    52  					{Name: []byte("color"), Value: []byte("blue")},
    53  					{Name: []byte("alpha"), Value: []byte("1.0")},
    54  				},
    55  			},
    56  			{
    57  				ID: []byte("foo"),
    58  				Fields: []doc.Field{
    59  					{Name: []byte("fruit"), Value: []byte("apple")},
    60  					{Name: []byte("vegetable"), Value: []byte("carrot")},
    61  				},
    62  			},
    63  			{
    64  				ID: []byte("baz"),
    65  				Fields: []doc.Field{
    66  					{Name: []byte("fruit"), Value: []byte("watermelon")},
    67  					{Name: []byte("color"), Value: []byte("green")},
    68  					{Name: []byte("alpha"), Value: []byte("0.5")},
    69  				},
    70  			},
    71  			{
    72  				ID: []byte("bux"),
    73  				Fields: []doc.Field{
    74  					{Name: []byte("fruit"), Value: []byte("watermelon")},
    75  					{Name: []byte("color"), Value: []byte("red")},
    76  					{Name: []byte("alpha"), Value: []byte("0.1")},
    77  				},
    78  			},
    79  		}),
    80  	}
    81  
    82  	builder := NewBuilderFromSegments(testOptions)
    83  	builder.Reset()
    84  	require.NoError(t, builder.AddSegments(segments))
    85  	iter, err := builder.Terms([]byte("fruit"))
    86  	require.NoError(t, err)
    87  
    88  	assertTermsPostings(t, builder.Docs(), iter, termPostings{
    89  		"apple":      []int{0, 1},
    90  		"watermelon": []int{2, 3},
    91  	})
    92  }
    93  
    94  func assertTermsPostings(
    95  	t *testing.T,
    96  	docs []doc.Metadata,
    97  	iter segment.TermsIterator,
    98  	expected termPostings,
    99  ) {
   100  	actual := toTermPostings(t, iter)
   101  	require.Equal(t, expected, actual,
   102  		fmt.Sprintf("actual terms postings:\n%s",
   103  			termsPostingsString(docs, actual)))
   104  }
   105  
   106  func termsPostingsString(docs []doc.Metadata, tp termPostings) string {
   107  	str := strings.Builder{}
   108  	for k, ids := range tp {
   109  		str.WriteString(k)
   110  		str.WriteString(":\n")
   111  		for _, id := range ids {
   112  			str.WriteString("id=")
   113  			str.WriteString(strconv.Itoa(id))
   114  			str.WriteString(", doc=")
   115  
   116  			if id >= len(docs) {
   117  				msg := fmt.Sprintf("cannot find doc: postingsID=%d, numDocs=%d", id, len(docs))
   118  				panic(msg)
   119  			}
   120  
   121  			doc := docs[postings.ID(id)]
   122  			str.WriteString(doc.String())
   123  			str.WriteString("\n")
   124  		}
   125  		str.WriteString("\n")
   126  	}
   127  	return str.String()
   128  }