Add character property expression (Meet RL1.2 of UTS #18 partially)

\p{property name=property value} matches a character has the property.
When the property name is General_Category, it can be omitted.
That is, \p{Letter} equals \p{General_Category=Letter}.
Currently, only General_Category is supported.
This feature meets RL1.2 of UTS #18 partially.

RL1.2 Properties: https://unicode.org/reports/tr18/#RL1.2

1 files changed, 72 insertions, 1 deletions

diff --git a/compiler/parser_test.go b/compiler/parser_test.go
index c636d8b..5a138ab 100644
--- a/compiler/parser_test.go
+++ b/compiler/parser_test.go
@@ -29,6 +29,11 @@ func TestParser_parse(t *testing.T) {
 		pattern     string
 		ast         astNode
 		syntaxError *SyntaxError
+
+		// When an AST is large, as patterns containing a character property expression,
+		// this test only checks that the pattern is parsable.
+		// The check of the validity of such AST is performed by checking that it can be matched correctly using the driver.
+		skipTestAST bool
 	}{
 		{
 			pattern: "a",
@@ -84,6 +89,10 @@ func TestParser_parse(t *testing.T) {
 			),
 		},
 		{
+			pattern:     "\\p{Letter}?",
+			skipTestAST: true,
+		},
+		{
 			pattern: "(a)?",
 			ast: genConcatNode(
 				newOptionNode(
@@ -186,6 +195,10 @@ func TestParser_parse(t *testing.T) {
 			),
 		},
 		{
+			pattern:     "\\p{Letter}*",
+			skipTestAST: true,
+		},
+		{
 			pattern: "((a*)*)*",
 			ast: genConcatNode(
 				newRepeatNode(
@@ -290,6 +303,10 @@ func TestParser_parse(t *testing.T) {
 			),
 		},
 		{
+			pattern:     "\\p{Letter}+",
+			skipTestAST: true,
+		},
+		{
 			pattern: "((a+)+)+",
 			ast: genConcatNode(
 				genConcatNode(
@@ -838,6 +855,58 @@ func TestParser_parse(t *testing.T) {
 			syntaxError: synErrCPExpInvalidForm,
 		},
 		{
+			pattern:     "\\p{Letter}",
+			skipTestAST: true,
+		},
+		{
+			pattern:     "\\p{General_Category=Letter}",
+			skipTestAST: true,
+		},
+		{
+			pattern:     "\\p{ Letter }",
+			skipTestAST: true,
+		},
+		{
+			pattern:     "\\p{ General_Category = Letter }",
+			skipTestAST: true,
+		},
+		{
+			pattern:     "\\p",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{Letter",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{General_Category=}",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{General_Category=  }",
+			syntaxError: synErrCharPropInvalidSymbol,
+		},
+		{
+			pattern:     "\\p{=Letter}",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{  =Letter}",
+			syntaxError: synErrCharPropInvalidSymbol,
+		},
+		{
+			pattern:     "\\p{=}",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
+			pattern:     "\\p{}",
+			syntaxError: synErrCharPropExpInvalidForm,
+		},
+		{
 			pattern: "(a)",
 			ast: newConcatNode(
 				newSymbolNodeWithPos(byte('a'), symPos(1)),
@@ -1031,7 +1100,9 @@ func TestParser_parse(t *testing.T) {
 					t.Fatal("AST is nil")
 				}
 				// printAST(os.Stdout, ast, "", "", false)
-				testAST(t, tt.ast, ast)
+				if !tt.skipTestAST {
+					testAST(t, tt.ast, ast)
+				}
 			}
 		})
 	}