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
|
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 verbNameRegularize = "regularize"
var RegularizeSetup = TransformerSetup{
Verb: verbNameRegularize,
UsageFunc: transformerRegularizeUsage,
ParseCLIFunc: transformerRegularizeParseCLI,
IgnoresInput: false,
}
func transformerRegularizeUsage(
o *os.File,
) {
fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameRegularize)
fmt.Fprintf(o, "Outputs records sorted lexically ascending by keys.\n")
fmt.Fprintf(o, "Options:\n")
fmt.Fprintf(o, "-h|--help Show this message.\n")
}
func transformerRegularizeParseCLI(
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
argi++
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" {
transformerRegularizeUsage(os.Stdout)
os.Exit(0)
} else {
transformerRegularizeUsage(os.Stderr)
os.Exit(1)
}
}
*pargi = argi
if !doConstruct { // All transformers must do this for main command-line parsing
return nil
}
transformer, err := NewTransformerRegularize()
if err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
return transformer
}
// ----------------------------------------------------------------
type TransformerRegularize struct {
// map from string to []string
sortedToOriginal map[string][]string
}
func NewTransformerRegularize() (*TransformerRegularize, error) {
tr := &TransformerRegularize{
make(map[string][]string),
}
return tr, nil
}
// ----------------------------------------------------------------
func (tr *TransformerRegularize) Transform(
inrecAndContext *types.RecordAndContext,
outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
inputDownstreamDoneChannel <-chan bool,
outputDownstreamDoneChannel chan<- bool,
) {
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
if !inrecAndContext.EndOfStream {
inrec := inrecAndContext.Record
currentFieldNames := inrec.GetKeys()
currentSortedFieldNames := lib.SortedStrings(currentFieldNames)
currentSortedFieldNamesJoined := strings.Join(currentSortedFieldNames, ",")
previousSortedFieldNames := tr.sortedToOriginal[currentSortedFieldNamesJoined]
if previousSortedFieldNames == nil {
tr.sortedToOriginal[currentSortedFieldNamesJoined] = currentFieldNames
outputRecordsAndContexts.PushBack(inrecAndContext)
} else {
outrec := mlrval.NewMlrmapAsRecord()
for _, fieldName := range previousSortedFieldNames {
outrec.PutReference(fieldName, inrec.Get(fieldName)) // inrec will be GC'ed
}
outrecAndContext := types.NewRecordAndContext(outrec, &inrecAndContext.Context)
outputRecordsAndContexts.PushBack(outrecAndContext)
}
} else {
outputRecordsAndContexts.PushBack(inrecAndContext) // end-of-stream marker
}
}
|
