Add new upcase and downcase verbs

docs/src/manpage.md

@@ -191,13 +191,14 @@ MILLER(1)                                                            MILLER(1)
 
 1mVERB LIST0m
        altkv bar bootstrap cat check clean-whitespace count-distinct count
-       count-similar cut decimate fill-down fill-empty filter flatten format-values
-       fraction gap grep group-by group-like having-fields head histogram json-parse
-       json-stringify join label latin1-to-utf8 least-frequent merge-fields
-       most-frequent nest nothing put regularize remove-empty-columns rename reorder
-       repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle skip-trivial-records
-       sort sort-within-records split stats1 stats2 step summary tac tail tee
-       template top utf8-to-latin1 unflatten uniq unspace unsparsify
+       count-similar cut decimate downcase fill-down fill-empty filter flatten
+       format-values fraction gap grep group-by group-like having-fields head
+       histogram json-parse json-stringify join label latin1-to-utf8 least-frequent
+       merge-fields most-frequent nest nothing put regularize remove-empty-columns
+       rename reorder repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle
+       skip-trivial-records sort sort-within-records split stats1 stats2 step summary
+       tac tail tee template top utf8-to-latin1 unflatten uniq unspace unsparsify
+       upcase
 
 1mFUNCTION LIST0m
        abs acos acosh any append apply arrayify asin asinh asserting_absent
@@ -1002,6 +1003,14 @@ MILLER(1)                                                            MILLER(1)
         -n {n} Decimation factor (default 10).
        -h|--help Show this message.
 
+   1mdowncase0m
+       Usage: mlr downcase [options]
+       Lowercases strings in record keys and/or values.
+       Options:
+       -k        Downcase only keys, not keys and values.
+       -v        Downcase only values, not keys and values.
+       -h|--help Show this message.
+
    1mfill-down0m
        Usage: mlr fill-down [options]
        If a given record has a missing value for a given field, fill that from
@@ -2107,6 +2116,14 @@ MILLER(1)                                                            MILLER(1)
        being 'b=3,c=4', then the output is the two records 'a=1,b=2,c=' and
        'a=,b=3,c=4'.
 
+   1mupcase0m
+       Usage: mlr upcase [options]
+       Uppercases strings in record keys and/or values.
+       Options:
+       -k        Upcase only keys, not keys and values.
+       -v        Upcase only values, not keys and values.
+       -h|--help Show this message.
+
 1mFUNCTIONS FOR FILTER/PUT0m
    1mabs0m
         (class=math #args=1) Absolute value.
@@ -3314,5 +3331,5 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-03-02                         MILLER(1)
+                                  2023-03-04                         MILLER(1)
 </pre>

docs/src/manpage.txt

@@ -170,13 +170,14 @@ MILLER(1)                                                            MILLER(1)
 
 1mVERB LIST0m
        altkv bar bootstrap cat check clean-whitespace count-distinct count
-       count-similar cut decimate fill-down fill-empty filter flatten format-values
-       fraction gap grep group-by group-like having-fields head histogram json-parse
-       json-stringify join label latin1-to-utf8 least-frequent merge-fields
-       most-frequent nest nothing put regularize remove-empty-columns rename reorder
-       repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle skip-trivial-records
-       sort sort-within-records split stats1 stats2 step summary tac tail tee
-       template top utf8-to-latin1 unflatten uniq unspace unsparsify
+       count-similar cut decimate downcase fill-down fill-empty filter flatten
+       format-values fraction gap grep group-by group-like having-fields head
+       histogram json-parse json-stringify join label latin1-to-utf8 least-frequent
+       merge-fields most-frequent nest nothing put regularize remove-empty-columns
+       rename reorder repeat reshape sample sec2gmtdate sec2gmt seqgen shuffle
+       skip-trivial-records sort sort-within-records split stats1 stats2 step summary
+       tac tail tee template top utf8-to-latin1 unflatten uniq unspace unsparsify
+       upcase
 
 1mFUNCTION LIST0m
        abs acos acosh any append apply arrayify asin asinh asserting_absent
@@ -981,6 +982,14 @@ MILLER(1)                                                            MILLER(1)
         -n {n} Decimation factor (default 10).
        -h|--help Show this message.
 
+   1mdowncase0m
+       Usage: mlr downcase [options]
+       Lowercases strings in record keys and/or values.
+       Options:
+       -k        Downcase only keys, not keys and values.
+       -v        Downcase only values, not keys and values.
+       -h|--help Show this message.
+
    1mfill-down0m
        Usage: mlr fill-down [options]
        If a given record has a missing value for a given field, fill that from
@@ -2086,6 +2095,14 @@ MILLER(1)                                                            MILLER(1)
        being 'b=3,c=4', then the output is the two records 'a=1,b=2,c=' and
        'a=,b=3,c=4'.
 
+   1mupcase0m
+       Usage: mlr upcase [options]
+       Uppercases strings in record keys and/or values.
+       Options:
+       -k        Upcase only keys, not keys and values.
+       -v        Upcase only values, not keys and values.
+       -h|--help Show this message.
+
 1mFUNCTIONS FOR FILTER/PUT0m
    1mabs0m
         (class=math #args=1) Absolute value.
@@ -3293,4 +3310,4 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-03-02                         MILLER(1)
+                                  2023-03-04                         MILLER(1)

docs/src/reference-verbs.md

@@ -824,6 +824,20 @@ Options:
 -h|--help Show this message.
 </pre>
 
+## downcase
+
+<pre class="pre-highlight-in-pair">
+<b>mlr downcase --help</b>
+</pre>
+<pre class="pre-non-highlight-in-pair">
+Usage: mlr downcase [options]
+Lowercases strings in record keys and/or values.
+Options:
+-k        Downcase only keys, not keys and values.
+-v        Downcase only values, not keys and values.
+-h|--help Show this message.
+</pre>
+
 ## fill-down
 
 <pre class="pre-highlight-in-pair">
@@ -4267,3 +4281,16 @@ a b v u w x
 - - 1 - 2 -
 </pre>
 
+## upcase
+
+<pre class="pre-highlight-in-pair">
+<b>mlr upcase --help</b>
+</pre>
+<pre class="pre-non-highlight-in-pair">
+Usage: mlr upcase [options]
+Uppercases strings in record keys and/or values.
+Options:
+-k        Upcase only keys, not keys and values.
+-v        Upcase only values, not keys and values.
+-h|--help Show this message.
+</pre>

docs/src/reference-verbs.md.in

@@ -297,6 +297,12 @@ GENMD-RUN-COMMAND
 mlr decimate --help
 GENMD-EOF
 
+## downcase
+
+GENMD-RUN-COMMAND
+mlr downcase --help
+GENMD-EOF
+
 ## fill-down
 
 GENMD-RUN-COMMAND
@@ -1289,3 +1295,8 @@ GENMD-RUN-COMMAND
 mlr --ijson --opprint unsparsify -f a,b,u,v,w,x then regularize data/sparse.json
 GENMD-EOF
 
+## upcase
+
+GENMD-RUN-COMMAND
+mlr upcase --help
+GENMD-EOF

internal/pkg/transformers/aaa_transformer_table.go

@@ -22,6 +22,7 @@ var TRANSFORMER_LOOKUP_TABLE = []TransformerSetup{
 	CountSimilarSetup,
 	CutSetup,
 	DecimateSetup,
+	DowncaseSetup,
 	FillDownSetup,
 	FillEmptySetup,
 	FilterSetup,
@@ -75,6 +76,7 @@ var TRANSFORMER_LOOKUP_TABLE = []TransformerSetup{
 	UniqSetup,
 	UnspaceSetup,
 	UnsparsifySetup,
+	UpcaseSetup,
 }
 
 func ShowHelpForTransformer(verb string) bool {

internal/pkg/transformers/downcase.go

@@ -0,0 +1,178 @@
+package transformers
+
+import (
+	"container/list"
+	"fmt"
+	"os"
+	"strings"
+
+	"github.com/johnkerl/miller/internal/pkg/cli"
+	"github.com/johnkerl/miller/internal/pkg/mlrval"
+	"github.com/johnkerl/miller/internal/pkg/types"
+)
+
+// ----------------------------------------------------------------
+const verbNameDowncase = "downcase"
+
+var DowncaseSetup = TransformerSetup{
+	Verb:         verbNameDowncase,
+	UsageFunc:    transformerDowncaseUsage,
+	ParseCLIFunc: transformerDowncaseParseCLI,
+	IgnoresInput: false,
+}
+
+func transformerDowncaseUsage(
+	o *os.File,
+) {
+	fmt.Fprintf(o, "Usage: %s %s [options]\n", "mlr", verbNameDowncase)
+	fmt.Fprintf(o, "Lowercases strings in record keys and/or values.\n")
+	fmt.Fprintf(o, "Options:\n")
+	fmt.Fprintf(o, "-k        Downcase only keys, not keys and values.\n")
+	fmt.Fprintf(o, "-v        Downcase only values, not keys and values.\n")
+	fmt.Fprintf(o, "-h|--help Show this message.\n")
+}
+
+func transformerDowncaseParseCLI(
+	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++
+
+	which := "keys_and_values"
+
+	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" {
+			transformerDowncaseUsage(os.Stdout)
+			os.Exit(0)
+
+		} else if opt == "-k" {
+			which = "keys_only"
+
+		} else if opt == "-v" {
+			which = "values_only"
+
+		} else {
+			transformerDowncaseUsage(os.Stderr)
+			os.Exit(1)
+		}
+	}
+
+	*pargi = argi
+	if !doConstruct { // All transformers must do this for main command-line parsing
+		return nil
+	}
+
+	transformer, err := NewTransformerDowncase(which)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+
+	return transformer
+}
+
+// ----------------------------------------------------------------
+type TransformerDowncase struct {
+	recordTransformerFunc RecordTransformerFunc
+}
+
+func NewTransformerDowncase(
+	which string,
+) (*TransformerDowncase, error) {
+	tr := &TransformerDowncase{}
+	if which == "keys_only" {
+		tr.recordTransformerFunc = tr.transformKeysOnly
+	} else if which == "values_only" {
+		tr.recordTransformerFunc = tr.transformValuesOnly
+	} else {
+		tr.recordTransformerFunc = tr.transformKeysAndValues
+	}
+	return tr, nil
+}
+
+func (tr *TransformerDowncase) Transform(
+	inrecAndContext *types.RecordAndContext,
+	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
+	inputDownstreamDoneChannel <-chan bool,
+	outputDownstreamDoneChannel chan<- bool,
+) {
+	HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
+	if !inrecAndContext.EndOfStream {
+		tr.recordTransformerFunc(
+			inrecAndContext,
+			outputRecordsAndContexts,
+			inputDownstreamDoneChannel,
+			outputDownstreamDoneChannel,
+		)
+	} else { // end of record stream
+		outputRecordsAndContexts.PushBack(inrecAndContext)
+	}
+}
+
+func (tr *TransformerDowncase) transformKeysOnly(
+	inrecAndContext *types.RecordAndContext,
+	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
+	_ <-chan bool,
+	__ chan<- bool,
+) {
+	inrec := inrecAndContext.Record
+	newrec := mlrval.NewMlrmapAsRecord()
+	for pe := inrec.Head; pe != nil; pe = pe.Next {
+		newkey := strings.ToLower(pe.Key)
+		// Reference not copy since this is ownership transfer of the value from the now-abandoned inrec
+		newrec.PutReference(newkey, pe.Value)
+	}
+	outputRecordsAndContexts.PushBack(types.NewRecordAndContext(newrec, &inrecAndContext.Context))
+}
+
+func (tr *TransformerDowncase) transformValuesOnly(
+	inrecAndContext *types.RecordAndContext,
+	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
+	_ <-chan bool,
+	__ chan<- bool,
+) {
+	inrec := inrecAndContext.Record
+	for pe := inrec.Head; pe != nil; pe = pe.Next {
+		stringval, ok := pe.Value.GetStringValue()
+		if ok {
+			pe.Value = mlrval.FromString(strings.ToLower(stringval))
+		}
+	}
+	outputRecordsAndContexts.PushBack(types.NewRecordAndContext(inrec, &inrecAndContext.Context))
+}
+
+func (tr *TransformerDowncase) transformKeysAndValues(
+	inrecAndContext *types.RecordAndContext,
+	outputRecordsAndContexts *list.List, // list of *types.RecordAndContext
+	_ <-chan bool,
+	__ chan<- bool,
+) {
+	inrec := inrecAndContext.Record
+	newrec := mlrval.NewMlrmapAsRecord()
+	for pe := inrec.Head; pe != nil; pe = pe.Next {
+		newkey := strings.ToLower(pe.Key)
+		stringval, ok := pe.Value.GetStringValue()
+		if ok {
+			stringval = strings.ToLower(stringval)
+			newrec.PutReference(newkey, mlrval.FromString(stringval))
+		} else {
+			newrec.PutReference(newkey, pe.Value)
+		}
+	}
+	outputRecordsAndContexts.PushBack(types.NewRecordAndContext(newrec, &inrecAndContext.Context))
+}