SUP-302 (FeatureBaseDB#2243)

* add ability to use Θ in all field names & with PQL

Author: jrbrinlee1

idk/header.go

@@ -32,7 +32,7 @@ const (
 
 var (
 	ErrNoFieldSpec      = errors.New("no field spec in this header")
-	ErrInvalidFieldName = errors.New("field name must match [a-z][a-z0-9_-]{0,229}")
+	ErrInvalidFieldName = errors.New("field name must match [a-z][a-z0-9Θ_-]{0,229}")
 	ErrParsingEpoch     = "parsing epoch for "
 	ErrDecodingConfig   = "decoding config for field "
 )

idk/header_test.go

@@ -351,6 +351,11 @@ func TestHeaderToField(t *testing.T) {
 			input: "a__LookupText",
 			exp:   LookupTextField{NameVal: "a", DestNameVal: "a"},
 		},
+		{
+			name:  "theta",
+			input: "fldΘnameΘ__String",
+			exp:   StringField{NameVal: "fldΘnameΘ", DestNameVal: "fldΘnameΘ"},
+		},
 	}
 
 	for _, test := range tests {

pilosa.go

@@ -47,7 +47,7 @@ var (
 	ErrInvalidView      = errors.New("invalid view")
 	ErrInvalidCacheType = errors.New("invalid cache type")
 
-	ErrName = errors.New("invalid index or field name, must match [a-z][a-z0-9_-]* and contain at most 230 characters")
+	ErrName = errors.New("invalid index or field name, must match [a-z][a-z0-9Θ_-]* and contain at most 230 characters")
 
 	// ErrFragmentNotFound is returned when a fragment does not exist.
 	ErrFragmentNotFound = errors.New("fragment not found")
@@ -135,7 +135,7 @@ func newPreconditionFailedError(err error) PreconditionFailedError {
 }
 
 // Regular expression to validate index and field names.
-var nameRegexp = regexp.MustCompile(`^[a-z][a-z0-9_-]{0,229}$`)
+var nameRegexp = regexp.MustCompile(`^[a-z][a-z0-9Θ_-]{0,229}$`)
 
 // TimeFormat is the go-style time format used to parse string dates.
 const TimeFormat = "2006-01-02T15:04"

pilosa_test.go

@@ -3,6 +3,7 @@
 package pilosa_test
 
 import (
+	"fmt"
 	"strings"
 	"testing"
 
@@ -43,3 +44,28 @@ func TestAddressWithDefaults(t *testing.T) {
 		}
 	}
 }
+
+func TestValidateName(t *testing.T) {
+	tests := []struct {
+		name string
+		err  error
+	}{
+		{name: "a_name", err: nil},
+		{name: "a-name", err: nil},
+		{name: "a-name-10", err: nil},
+		{name: "A-name", err: fmt.Errorf("'A-name': %s", pilosa.ErrName)},
+		{name: "-a-name", err: fmt.Errorf("'-a-name': %s", pilosa.ErrName)},
+		{name: "8th_name", err: fmt.Errorf("'8th_name': %s", pilosa.ErrName)},
+		{name: "Θ_name", err: fmt.Errorf("'Θ_name': %s", pilosa.ErrName)},
+		{name: "a_NaMe", err: fmt.Errorf("'a_NaMe': %s", pilosa.ErrName)},
+		{name: "indexΘname", err: nil},
+	}
+	for _, test := range tests {
+		err := pilosa.ValidateName(test.name)
+		if !(err == nil && test.err == nil) {
+			if err.Error() != test.err.Error() {
+				t.Errorf("expected error: %v, but got: %v", test.err, err)
+			}
+		}
+	}
+}

pql/parser_test.go

@@ -307,6 +307,20 @@ func TestParser_Parse(t *testing.T) {
 			}
 		}
 	})
+
+	t.Run("ParseTheta", func(t *testing.T) {
+		q, err := pql.ParseString(`Row(fldΘname=fldΘval)`)
+		if err != nil {
+			t.Fatal(err)
+		} else if !reflect.DeepEqual(q.Calls[0],
+			&pql.Call{
+				Name: "Row",
+				Args: map[string]interface{}{"fldΘname": "fldΘval"},
+			},
+		) {
+			t.Fatalf("unexpected call: %#v", q.Calls[0])
+		}
+	})
 }
 
 func TestUnquote(t *testing.T) {

pql/pql.peg

@@ -20,7 +20,7 @@ Call <-  "Set" {p.startCall("Set")} open col comma args (comma time)? close {p.e
        / "Sum" {p.startCall("Sum")} open posfield (comma allargs)? close {p.endCall()}
        / "Range" {p.startCall("Range")} open field eq value comma 'from='? {p.addField("from")} timefmt {p.addVal(text)} comma 'to='? sp {p.addField("to")} timefmt {p.addVal(text)} close {p.endCall()}
        / < IDENT > { p.startCall(text) } open allargs comma? close { p.endCall() }
-ivyExpr <- ( '(' / '_' / '/' / '[' / ']' /'.' / '=' / '&' / '<'/ '>' /',' / ')' / '^' /  '!' / '|' / [*+] / '-' / '?' / [[A-Z]] / [0-9] / '#' / [ \t\n] )*
+ivyExpr <- ( '(' / '_' / '/' / '[' / ']' /'.' / '=' / '&' / '<'/ '>' /',' / ')' / '^' /  '!' / '|' / [*+] / '-' / '?' / [[A-Z]] / [0-9] / '#' / [ \t\n] / 'Θ')*
 ivyprogram <- '"'? <ivyExpr> '"' { p.addPosStr("_ivy", text) }
 ivyprogram2 <- '"'? <ivyExpr> '"' { p.addPosStr("_ivyReduce", text) }
 
@@ -55,16 +55,16 @@ item <-   'null' &(comma / close) { p.addVal(nil) }
          / timestampfmt { p.addTimestampVal(text) }
          / < decimal > { p.addNumVal(text) }
          / < IDENT > { p.startCall(text) } open allargs comma? close { p.addVal(p.endCall()) }
-         / < ([[A-Z]] / [0-9] / '-' / '_' / ':')+ > { p.addVal(text) }
+         / < ([[A-Z]] / [0-9] / '-' / '_' / ':' / 'Θ')+ > { p.addVal(text) }
          / < '"'  doublequotedstring '"' > { p.addVal(text) }
          / < '\''  singlequotedstring  '\'' > { p.addVal(text) }
 
 doublequotedstring <- ( '\\"' / '\\\\' / '\\n' / '\\t' / [^"\\] )*
 singlequotedstring <- ( '\\\'' / '\\\\' / '\\n' / '\\t' /  [^'\\] )*
 
-variable <- ( [[A-Z]] / '_' ) ( [[A-Z]] / [0-9] / '_' / '-' )*
+variable <- ( [[A-Z]] / '_' ) ( [[A-Z]] / [0-9] / '_' / '-' / 'Θ')*
 
-fieldExpr <- ( [[A-Z]] / '_' / '$' ) ( [[A-Z]] / [0-9] / '_' / '-' )*
+fieldExpr <- ( [[A-Z]] / '_' / '$' ) ( [[A-Z]] / [0-9] / '_' / '-' / 'Θ')*
 field <- <fieldExpr / reserved> { p.addField(text) }
 reserved <- '_row' / '_col' / '_start' / '_end' / '_timestamp' / '_field'
 posfield <- 'field='? <fieldExpr> { p.addPosStr("_field", text) }
@@ -79,7 +79,7 @@ eq <- sp '=' sp
 comma <- sp ',' sp
 lbrack <- '[' sp
 rbrack <- sp ']' sp
-IDENT <- [[A-Z]] ([[A-Z]] / [0-9])*
+IDENT <- [[A-Z]] ([[A-Z]] / [0-9] / 'Θ')*
 digits <- [0-9]+
 signedDigits <- '-'? digits
 decimal <- signedDigits ('.' digits?)?