New format DSL function (#869)

* New format DSL function

* Updated affected test cases involving on-line help on "for" prefix

* doc-build artifacts for previous commit

* regression-test cases

docs/src/manpage.md

@@ -207,9 +207,9 @@ FUNCTION LIST
        asserting_present asserting_string atan atan2 atanh bitcount boolean
        capitalize cbrt ceil clean_whitespace collapse_whitespace concat cos cosh
        depth dhms2fsec dhms2sec erf erfc every exp expm1 flatten float floor fmtnum
-       fold fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub haskey
-       hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array is_bool
-       is_boolean is_empty is_empty_map is_error is_float is_int is_map
+       fold format fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub
+       haskey hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array
+       is_bool is_boolean is_empty is_empty_map is_error is_float is_int is_map
        is_nonempty_map is_not_array is_not_empty is_not_map is_not_null is_null
        is_numeric is_present is_string joink joinkv joinv json_parse json_stringify
        leafcount length localtime2gmt localtime2sec log log10 log1p logifit lstrip
@@ -2139,6 +2139,13 @@ FUNCTIONS FOR FILTER/PUT
        Array example: fold([1,2,3,4,5], func(acc,e) {return acc + e**3}, 10000) returns 10225.
        Map example: fold({"a":1, "b":3, "c": 5}, func(acck,accv,ek,ev) {return {"sum": accv+ev**2}}, {"sum":10000}) returns 10035.
 
+   format
+        (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+       Examples:
+       format("{}:{}:{}", 1,2)     gives "1:2:".
+       format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+       format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
+
    fsec2dhms
         (class=time #args=1) Formats floating-point seconds as in fsec2dhms(500000.25) = "5d18h53m20.250000s"
 

docs/src/manpage.txt

@@ -186,9 +186,9 @@ FUNCTION LIST
        asserting_present asserting_string atan atan2 atanh bitcount boolean
        capitalize cbrt ceil clean_whitespace collapse_whitespace concat cos cosh
        depth dhms2fsec dhms2sec erf erfc every exp expm1 flatten float floor fmtnum
-       fold fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub haskey
-       hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array is_bool
-       is_boolean is_empty is_empty_map is_error is_float is_int is_map
+       fold format fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub
+       haskey hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array
+       is_bool is_boolean is_empty is_empty_map is_error is_float is_int is_map
        is_nonempty_map is_not_array is_not_empty is_not_map is_not_null is_null
        is_numeric is_present is_string joink joinkv joinv json_parse json_stringify
        leafcount length localtime2gmt localtime2sec log log10 log1p logifit lstrip
@@ -2118,6 +2118,13 @@ FUNCTIONS FOR FILTER/PUT
        Array example: fold([1,2,3,4,5], func(acc,e) {return acc + e**3}, 10000) returns 10225.
        Map example: fold({"a":1, "b":3, "c": 5}, func(acck,accv,ek,ev) {return {"sum": accv+ev**2}}, {"sum":10000}) returns 10035.
 
+   format
+        (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+       Examples:
+       format("{}:{}:{}", 1,2)     gives "1:2:".
+       format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+       format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
+
    fsec2dhms
         (class=time #args=1) Formats floating-point seconds as in fsec2dhms(500000.25) = "5d18h53m20.250000s"
 

docs/src/reference-dsl-builtin-functions.md

@@ -74,7 +74,7 @@ is 2. Unary operators such as `!` and `~` show argument-count of 1; the ternary
 * [**Hashing functions**](#hashing-functions):  [md5](#md5),  [sha1](#sha1),  [sha256](#sha256),  [sha512](#sha512).
 * [**Higher-order-functions functions**](#higher-order-functions-functions):  [any](#any),  [apply](#apply),  [every](#every),  [fold](#fold),  [reduce](#reduce),  [select](#select),  [sort](#sort).
 * [**Math functions**](#math-functions):  [abs](#abs),  [acos](#acos),  [acosh](#acosh),  [asin](#asin),  [asinh](#asinh),  [atan](#atan),  [atan2](#atan2),  [atanh](#atanh),  [cbrt](#cbrt),  [ceil](#ceil),  [cos](#cos),  [cosh](#cosh),  [erf](#erf),  [erfc](#erfc),  [exp](#exp),  [expm1](#expm1),  [floor](#floor),  [invqnorm](#invqnorm),  [log](#log),  [log10](#log10),  [log1p](#log1p),  [logifit](#logifit),  [max](#max),  [min](#min),  [qnorm](#qnorm),  [round](#round),  [roundm](#roundm),  [sgn](#sgn),  [sin](#sin),  [sinh](#sinh),  [sqrt](#sqrt),  [tan](#tan),  [tanh](#tanh),  [urand](#urand),  [urand32](#urand32),  [urandelement](#urandelement),  [urandint](#urandint),  [urandrange](#urandrange).
-* [**String functions**](#string-functions):  [capitalize](#capitalize),  [clean_whitespace](#clean_whitespace),  [collapse_whitespace](#collapse_whitespace),  [gsub](#gsub),  [lstrip](#lstrip),  [regextract](#regextract),  [regextract_or_else](#regextract_or_else),  [rstrip](#rstrip),  [ssub](#ssub),  [strip](#strip),  [strlen](#strlen),  [sub](#sub),  [substr](#substr),  [substr0](#substr0),  [substr1](#substr1),  [tolower](#tolower),  [toupper](#toupper),  [truncate](#truncate),  [\.](#dot).
+* [**String functions**](#string-functions):  [capitalize](#capitalize),  [clean_whitespace](#clean_whitespace),  [collapse_whitespace](#collapse_whitespace),  [format](#format),  [gsub](#gsub),  [lstrip](#lstrip),  [regextract](#regextract),  [regextract_or_else](#regextract_or_else),  [rstrip](#rstrip),  [ssub](#ssub),  [strip](#strip),  [strlen](#strlen),  [sub](#sub),  [substr](#substr),  [substr0](#substr0),  [substr1](#substr1),  [tolower](#tolower),  [toupper](#toupper),  [truncate](#truncate),  [\.](#dot).
 * [**System functions**](#system-functions):  [hostname](#hostname),  [os](#os),  [system](#system),  [version](#version).
 * [**Time functions**](#time-functions):  [dhms2fsec](#dhms2fsec),  [dhms2sec](#dhms2sec),  [fsec2dhms](#fsec2dhms),  [fsec2hms](#fsec2hms),  [gmt2localtime](#gmt2localtime),  [gmt2sec](#gmt2sec),  [hms2fsec](#hms2fsec),  [hms2sec](#hms2sec),  [localtime2gmt](#localtime2gmt),  [localtime2sec](#localtime2sec),  [sec2dhms](#sec2dhms),  [sec2gmt](#sec2gmt),  [sec2gmtdate](#sec2gmtdate),  [sec2hms](#sec2hms),  [sec2localdate](#sec2localdate),  [sec2localtime](#sec2localtime),  [strftime](#strftime),  [strftime_local](#strftime_local),  [strptime](#strptime),  [strptime_local](#strptime_local),  [systime](#systime),  [systimeint](#systimeint),  [uptime](#uptime).
 * [**Typing functions**](#typing-functions):  [asserting_absent](#asserting_absent),  [asserting_array](#asserting_array),  [asserting_bool](#asserting_bool),  [asserting_boolean](#asserting_boolean),  [asserting_empty](#asserting_empty),  [asserting_empty_map](#asserting_empty_map),  [asserting_error](#asserting_error),  [asserting_float](#asserting_float),  [asserting_int](#asserting_int),  [asserting_map](#asserting_map),  [asserting_nonempty_map](#asserting_nonempty_map),  [asserting_not_array](#asserting_not_array),  [asserting_not_empty](#asserting_not_empty),  [asserting_not_map](#asserting_not_map),  [asserting_not_null](#asserting_not_null),  [asserting_null](#asserting_null),  [asserting_numeric](#asserting_numeric),  [asserting_present](#asserting_present),  [asserting_string](#asserting_string),  [is_absent](#is_absent),  [is_array](#is_array),  [is_bool](#is_bool),  [is_boolean](#is_boolean),  [is_empty](#is_empty),  [is_empty_map](#is_empty_map),  [is_error](#is_error),  [is_float](#is_float),  [is_int](#is_int),  [is_map](#is_map),  [is_nonempty_map](#is_nonempty_map),  [is_not_array](#is_not_array),  [is_not_empty](#is_not_empty),  [is_not_map](#is_not_map),  [is_not_null](#is_not_null),  [is_null](#is_null),  [is_numeric](#is_numeric),  [is_present](#is_present),  [is_string](#is_string),  [typeof](#typeof).
@@ -927,6 +927,16 @@ collapse_whitespace  (class=string #args=1) Strip repeated whitespace from strin
 </pre>
 
 
+### format
+<pre class="pre-non-highlight-non-pair">
+format  (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+Examples:
+format("{}:{}:{}", 1,2)     gives "1:2:".
+format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
+</pre>
+
+
 ### gsub
 <pre class="pre-non-highlight-non-pair">
 gsub  (class=string #args=3) '$name=gsub($name, "old", "new")' (replace all).

internal/pkg/bifs/strings.go

@@ -1,6 +1,7 @@
 package bifs
 
 import (
+	"bytes"
 	"regexp"
 	"strconv"
 	"strings"
@@ -287,6 +288,53 @@ func BIF_clean_whitespace(input1 *mlrval.Mlrval) *mlrval.Mlrval {
 	)
 }
 
+// ================================================================
+func BIF_format(mlrvals []*mlrval.Mlrval) *mlrval.Mlrval {
+	if len(mlrvals) == 0 {
+		return mlrval.VOID
+	}
+	formatString, ok := mlrvals[0].GetStringValue()
+	if !ok { // not a string
+		return mlrval.ERROR
+	}
+
+	pieces := lib.SplitString(formatString, "{}")
+
+	var buffer bytes.Buffer
+
+	// Example: format("{}:{}", 8, 9)
+	//
+	// * piece[0] ""
+	// * piece[1] ":"
+	// * piece[2] ""
+	// * mlrval[1] 8
+	// * mlrval[2] 9
+	//
+	// So:
+	// * Write piece[0]
+	// * Write mlrvals[1]
+	// * Write piece[1]
+	// * Write mlrvals[2]
+	// * Write piece[2]
+
+	// Q: What if too few arguments for format?
+	// A: Leave them off
+	// Q: What if too many arguments for format?
+	// A: Leave them off
+
+	n := len(mlrvals)
+	for i, piece := range pieces {
+		if i > 0 {
+			if i < n {
+				buffer.WriteString(mlrvals[i].String())
+			}
+		}
+		buffer.WriteString(piece)
+	}
+
+	return mlrval.FromString(buffer.String())
+}
+
 // ================================================================
 func BIF_hexfmt(input1 *mlrval.Mlrval) *mlrval.Mlrval {
 	if input1.IsInt() {

internal/pkg/dsl/cst/builtin_function_manager.go

@@ -510,6 +510,19 @@ Arrays are new in Miller 6; the substr function is older.`,
 			binaryFunc: bifs.BIF_truncate,
 		},
 
+		{
+			name:  "format",
+			class: FUNC_CLASS_STRING,
+			help: `Using first argument as format string, interpolate remaining arguments in place of
+each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.`,
+			examples: []string{
+				`format("{}:{}:{}", 1,2)     gives "1:2:".`,
+				`format("{}:{}:{}", 1,2,3)   gives "1:2:3".`,
+				`format("{}:{}:{}", 1,2,3,4) gives "1:2:3".`,
+			},
+			variadicFunc: bifs.BIF_format,
+		},
+
 		// ----------------------------------------------------------------
 		// FUNC_CLASS_HASHING
 

man/manpage.txt

@@ -186,9 +186,9 @@ FUNCTION LIST
        asserting_present asserting_string atan atan2 atanh bitcount boolean
        capitalize cbrt ceil clean_whitespace collapse_whitespace concat cos cosh
        depth dhms2fsec dhms2sec erf erfc every exp expm1 flatten float floor fmtnum
-       fold fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub haskey
-       hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array is_bool
-       is_boolean is_empty is_empty_map is_error is_float is_int is_map
+       fold format fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub
+       haskey hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array
+       is_bool is_boolean is_empty is_empty_map is_error is_float is_int is_map
        is_nonempty_map is_not_array is_not_empty is_not_map is_not_null is_null
        is_numeric is_present is_string joink joinkv joinv json_parse json_stringify
        leafcount length localtime2gmt localtime2sec log log10 log1p logifit lstrip
@@ -2118,6 +2118,13 @@ FUNCTIONS FOR FILTER/PUT
        Array example: fold([1,2,3,4,5], func(acc,e) {return acc + e**3}, 10000) returns 10225.
        Map example: fold({"a":1, "b":3, "c": 5}, func(acck,accv,ek,ev) {return {"sum": accv+ev**2}}, {"sum":10000}) returns 10035.
 
+   format
+        (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+       Examples:
+       format("{}:{}:{}", 1,2)     gives "1:2:".
+       format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+       format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
+
    fsec2dhms
         (class=time #args=1) Formats floating-point seconds as in fsec2dhms(500000.25) = "5d18h53m20.250000s"
 

man/mlr.1

@@ -233,9 +233,9 @@ asserting_not_map asserting_not_null asserting_null asserting_numeric
 asserting_present asserting_string atan atan2 atanh bitcount boolean
 capitalize cbrt ceil clean_whitespace collapse_whitespace concat cos cosh
 depth dhms2fsec dhms2sec erf erfc every exp expm1 flatten float floor fmtnum
-fold fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub haskey
-hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array is_bool
-is_boolean is_empty is_empty_map is_error is_float is_int is_map
+fold format fsec2dhms fsec2hms get_keys get_values gmt2localtime gmt2sec gsub
+haskey hexfmt hms2fsec hms2sec hostname int invqnorm is_absent is_array
+is_bool is_boolean is_empty is_empty_map is_error is_float is_int is_map
 is_nonempty_map is_not_array is_not_empty is_not_map is_not_null is_null
 is_numeric is_present is_string joink joinkv joinv json_parse json_stringify
 leafcount length localtime2gmt localtime2sec log log10 log1p logifit lstrip
@@ -2963,6 +2963,19 @@ Map example: fold({"a":1, "b":3, "c": 5}, func(acck,accv,ek,ev) {return {"sum":
 .fi
 .if n \{\
 .RE
+.SS "format"
+.if n \{\
+.RS 0
+.\}
+.nf
+ (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+Examples:
+format("{}:{}:{}", 1,2)     gives "1:2:".
+format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
+.fi
+.if n \{\
+.RE
 .SS "fsec2dhms"
 .if n \{\
 .RS 0

test/cases/dsl-format/0001/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0001/expout

@@ -0,0 +1 @@
+

test/cases/dsl-format/0001/mlr

@@ -0,0 +1,3 @@
+end {
+  print format()
+}

test/cases/dsl-format/0002/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0002/expout

@@ -0,0 +1 @@
+(error)

test/cases/dsl-format/0002/mlr

@@ -0,0 +1,3 @@
+end {
+  print format(1)
+}

test/cases/dsl-format/0003/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0003/expout

@@ -0,0 +1 @@
+

test/cases/dsl-format/0003/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("")
+}

test/cases/dsl-format/0004/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0004/expout

@@ -0,0 +1 @@
+abc

test/cases/dsl-format/0004/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("abc")
+}

test/cases/dsl-format/0005/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0005/expout

@@ -0,0 +1 @@
+

test/cases/dsl-format/0005/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("{}")
+}

test/cases/dsl-format/0006/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0006/expout

@@ -0,0 +1 @@
+1

test/cases/dsl-format/0006/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("{}", 1)
+}

test/cases/dsl-format/0007/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0007/expout

@@ -0,0 +1 @@
+1

test/cases/dsl-format/0007/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("{}", 1, 2)
+}

test/cases/dsl-format/0008/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0008/expout

@@ -0,0 +1 @@
+<abc:>

test/cases/dsl-format/0008/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("<{}:{}>", "abc")
+}

test/cases/dsl-format/0009/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0009/expout

@@ -0,0 +1 @@
+<abc:def>

test/cases/dsl-format/0009/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("<{}:{}>", "abc", "def")
+}

test/cases/dsl-format/0010/cmd

@@ -0,0 +1 @@
+mlr -n put -f ${CASEDIR}/mlr

test/cases/dsl-format/0010/expout

@@ -0,0 +1 @@
+<abc:def>

test/cases/dsl-format/0010/mlr

@@ -0,0 +1,3 @@
+end {
+  print format("<{}:{}>", "abc", "def", "ghi")
+}

test/cases/help/0012/expout

@@ -28,6 +28,11 @@ Options:
                     with s in them. Undefined behavior results otherwise.
 -n                  Coerce field values autodetected as int to float, and then
                     apply the float format.
+format  (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+Examples:
+format("{}:{}:{}", 1,2)     gives "1:2:".
+format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+format("{}:{}:{}", 1,2,3,4) gives "1:2:3".
 for: defines a for-loop using one of three styles. The body statements must
 be wrapped in curly braces.
 For-loop over stream record:

test/cases/repl-help/0012/expout

@@ -13,3 +13,8 @@ For-loop over out-of-stream variables:
 C-style for-loop:
 
   Example:  'for (var i = 0, var b = 1; i < 10; i += 1, b *= 2) { ... }'
+format  (class=string #args=variadic) Using first argument as format string, interpolate remaining arguments in place of each "{}" in the format string. Too-few arguments are treated as the empty string; too-many arguments are discarded.
+Examples:
+format("{}:{}:{}", 1,2)     gives "1:2:".
+format("{}:{}:{}", 1,2,3)   gives "1:2:3".
+format("{}:{}:{}", 1,2,3,4) gives "1:2:3".

todo.txt

@@ -80,6 +80,8 @@ UX
 ! bnf fix for '[[' ']]' etc -- make it a nesting of singles. since otherwise no '[[3,4]]' literals :(
 ! broadly rethink os.Exit, especially as affecting mlr repl
 
+* ?xyz and ??xyz in repl, for :help and :help find respectively
+
 * consider expanding '(error)' to have more useful error-text
 * sync-print option; or (yuck) another xprint variant; or ...; emph dump/eprint
 * strptime w/ ...00.Z -> error