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, 36 insertions, 0 deletions

diff --git a/compiler/ucd.go b/compiler/ucd.go
new file mode 100644
index 0000000..7432ba6
--- /dev/null
+++ b/compiler/ucd.go
@@ -0,0 +1,36 @@
+//go:generate go run ../generator/main.go
+//go:generate gofmt -w ucd_table.go
+
+package compiler
+
+import (
+	"fmt"
+
+	"github.com/nihei9/maleeni/ucd"
+)
+
+func findCodePointRanges(propName, propVal string) ([]*ucd.CodePointRange, error) {
+	name := ucd.NormalizeSymbolicValue(propName)
+	val := ucd.NormalizeSymbolicValue(propVal)
+	name, ok := propertyNameAbbs[name]
+	if !ok {
+		return nil, fmt.Errorf("unsupported character property: %v", propName)
+	}
+	val, ok = generalCategoryValueAbbs[val]
+	if !ok {
+		return nil, fmt.Errorf("unsupported character property value: %v", val)
+	}
+	vals, ok := compositGeneralCategories[val]
+	if !ok {
+		vals = []string{val}
+	}
+	var ranges []*ucd.CodePointRange
+	for _, v := range vals {
+		rs, ok := generalCategoryCodePoints[v]
+		if !ok {
+			return nil, fmt.Errorf("invalie value of the General_Category property: %v", v)
+		}
+		ranges = append(ranges, rs...)
+	}
+	return ranges, nil
+}