File: count.go

package info (click to toggle)
miller 6.16.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 87,928 kB
  • sloc: ruby: 162; sh: 119; makefile: 87
file content (244 lines) | stat: -rw-r--r-- 7,003 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
package transformers

import (
	"container/list"
	"fmt"
	"os"
	"strings"

	"github.com/johnkerl/miller/v6/pkg/cli"
	"github.com/johnkerl/miller/v6/pkg/lib"
	"github.com/johnkerl/miller/v6/pkg/mlrval"
	"github.com/johnkerl/miller/v6/pkg/types"
)

// ----------------------------------------------------------------
const verbNameCount = "count"

var CountSetup = TransformerSetup{
	Verb:         verbNameCount,
	UsageFunc:    transformerCountUsage,
	ParseCLIFunc: transformerCountParseCLI,
	IgnoresInput: false,
}

func transformerCountUsage(
	o *os.File,
) {
	fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameCount)
	fmt.Fprint(o,
		`Prints number of records, optionally grouped by distinct values for specified field names.
`)
	fmt.Fprintf(o, "Options:\n")
	fmt.Fprintf(o, "-g {a,b,c} Optional group-by-field names for counts, e.g. a,b,c\n")
	fmt.Fprintf(o, "-n {n} Show only the number of distinct values. Not interesting without -g.\n")
	fmt.Fprintf(o, "-o {name} Field name for output-count. Default \"count\".\n")
	fmt.Fprintf(o, "-h|--help Show this message.\n")
}

func transformerCountParseCLI(
	pargi *int,
	argc int,
	args []string,
	_ *cli.TOptions,
	doConstruct bool, // false for first pass of CLI-parse, true for second pass
) IRecordTransformer {

	// Skip the verb name from the current spot in the mlr command line
	argi := *pargi
	verb := args[argi]
	argi++

	var groupByFieldNames []string = nil
	showCountsOnly := false
	outputFieldName := "count"

	for argi < argc /* variable increment: 1 or 2 depending on flag */ {
		opt := args[argi]
		if !strings.HasPrefix(opt, "-") {
			break // No more flag options to process
		}
		if args[argi] == "--" {
			break // All transformers must do this so main-flags can follow verb-flags
		}
		argi++

		if opt == "-h" || opt == "--help" {
			transformerCountUsage(os.Stdout)
			os.Exit(0)

		} else if opt == "-g" {
			groupByFieldNames = cli.VerbGetStringArrayArgOrDie(verb, opt, args, &argi, argc)

		} else if opt == "-n" {
			showCountsOnly = true

		} else if opt == "-o" {
			outputFieldName = cli.VerbGetStringArgOrDie(verb, opt, args, &argi, argc)

		} else {
			transformerCountUsage(os.Stderr)
			os.Exit(1)
		}
	}

	*pargi = argi
	if !doConstruct { // All transformers must do this for main command-line parsing
		return nil
	}

	transformer, err := NewTransformerCount(
		groupByFieldNames,
		showCountsOnly,
		outputFieldName,
	)
	if err != nil {
		fmt.Fprintln(os.Stderr, err)
		os.Exit(1)
	}

	return transformer
}

// ----------------------------------------------------------------
type TransformerCount struct {
	// input
	groupByFieldNames []string
	showCountsOnly    bool
	outputFieldName   string

	// state
	recordTransformerFunc RecordTransformerFunc
	ungroupedCount        int64
	// Example:
	// * Suppose group-by fields are a,b.
	// * One record has a=foo,b=bar
	// * Another record has a=baz,b=quux
	// * Map keys are strings "foo,bar" and "baz,quux".
	// * groupedCounts maps "foo,bar" to 1 and "baz,quux" to 1.
	// * groupByValues maps "foo,bar" to ["foo", "bar"] and "baz,quux" to ["baz", "quux"].
	groupedCounts  *lib.OrderedMap
	groupingValues *lib.OrderedMap
}

func NewTransformerCount(
	groupByFieldNames []string,
	showCountsOnly bool,
	outputFieldName string,
) (*TransformerCount, error) {

	tr := &TransformerCount{
		groupByFieldNames: groupByFieldNames,
		showCountsOnly:    showCountsOnly,
		outputFieldName:   outputFieldName,

		ungroupedCount: 0,
		groupedCounts:  lib.NewOrderedMap(),
		groupingValues: lib.NewOrderedMap(),
	}

	if groupByFieldNames == nil {
		tr.recordTransformerFunc = tr.countUngrouped
	} else {
		tr.recordTransformerFunc = tr.countGrouped
	}

	return tr, nil
}

// ----------------------------------------------------------------

func (tr *TransformerCount) Transform(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) {
	HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
	tr.recordTransformerFunc(inrecAndContext, outputRecordsAndContexts, inputDownstreamDoneChannel, outputDownstreamDoneChannel)
}

// ----------------------------------------------------------------
func (tr *TransformerCount) countUngrouped(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) {
	if !inrecAndContext.EndOfStream {
		tr.ungroupedCount++
	} else {
		newrec := mlrval.NewMlrmapAsRecord()
		newrec.PutCopy(tr.outputFieldName, mlrval.FromInt(tr.ungroupedCount))
		outputRecordsAndContexts.PushBack(types.NewRecordAndContext(newrec, &inrecAndContext.Context))

		outputRecordsAndContexts.PushBack(inrecAndContext) // end-of-stream marker
	}
}

// ----------------------------------------------------------------
func (tr *TransformerCount) countGrouped(
	inrecAndContext *types.RecordAndContext,
	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
	inputDownstreamDoneChannel <-chan bool,
	outputDownstreamDoneChannel chan<- bool,
) {
	if !inrecAndContext.EndOfStream {
		inrec := inrecAndContext.Record

		groupingKey, selectedValues, ok := inrec.GetSelectedValuesAndJoined(
			tr.groupByFieldNames,
		)
		if !ok { // Current record does not have specified fields; ignore
			return
		}

		if !tr.groupedCounts.Has(groupingKey) {
			var count int64 = 1
			tr.groupedCounts.Put(groupingKey, count)
			tr.groupingValues.Put(groupingKey, selectedValues)
		} else {
			tr.groupedCounts.Put(
				groupingKey,
				tr.groupedCounts.Get(groupingKey).(int64)+1,
			)
		}

	} else {
		if tr.showCountsOnly {
			newrec := mlrval.NewMlrmapAsRecord()
			newrec.PutCopy(tr.outputFieldName, mlrval.FromInt(tr.groupedCounts.FieldCount))

			outrecAndContext := types.NewRecordAndContext(newrec, &inrecAndContext.Context)
			outputRecordsAndContexts.PushBack(outrecAndContext)

		} else {
			for outer := tr.groupedCounts.Head; outer != nil; outer = outer.Next {
				groupingKey := outer.Key
				newrec := mlrval.NewMlrmapAsRecord()

				// Example:
				// * Suppose group-by fields are a,b.
				// * Record has a=foo,b=bar
				// * Grouping key is "foo,bar"
				// * Grouping values for key is ["foo", "bar"]
				// Here we populate a record with "a=foo,b=bar".

				groupingValuesForKey := tr.groupingValues.Get(groupingKey).([]*mlrval.Mlrval)
				i := 0
				for _, groupingValueForKey := range groupingValuesForKey {
					newrec.PutCopy(tr.groupByFieldNames[i], groupingValueForKey)
					i++
				}

				countForGroup := outer.Value.(int64)
				newrec.PutCopy(tr.outputFieldName, mlrval.FromInt(countForGroup))

				outrecAndContext := types.NewRecordAndContext(newrec, &inrecAndContext.Context)
				outputRecordsAndContexts.PushBack(outrecAndContext)
			}
		}

		outputRecordsAndContexts.PushBack(inrecAndContext) // end-of-stream marker
	}
}