string.go

package scrubbers

import (
	"context"
	"fmt"
	"reflect"
	"regexp"
	"strings"

	"github.com/go-playground/mold/v4"
)

var (
	emailRegex      = regexp.MustCompile("(?:(?:(?:(?:[a-zA-Z]|\\d|[!#\\$%&'\\*\\+\\-\\/=\\?\\^_`{\\|}~]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])+(?:\\.(?:[a-zA-Z]|\\d|[!#\\$%&'\\*\\+\\-\\/=\\?\\^_`{\\|}~]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])+)*)|(?:(?:\\x22)(?:(?:(?:(?:\\x20|\\x09)*(?:\\x0d\\x0a))?(?:\\x20|\\x09)+)?(?:(?:[\\x01-\\x08\\x0b\\x0c\\x0e-\\x1f\\x7f]|\\x21|[\\x23-\\x5b]|[\\x5d-\\x7e]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])|(?:\\(?:[\\x01-\\x09\\x0b\\x0c\\x0d-\\x7f]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}]))))*(?:(?:(?:\\x20|\\x09)*(?:\\x0d\\x0a))?(\\x20|\\x09)+)?(?:\\x22)))@(?:(?:(?:[a-zA-Z]|\\d|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])|(?:(?:[a-zA-Z]|\\d|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])(?:[a-zA-Z]|\\d|-|\\.|_|~|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])*(?:[a-zA-Z]|\\d|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])))\\.)+(?:(?:[a-zA-Z]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])|(?:(?:[a-zA-Z]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])(?:[a-zA-Z]|\\d|-|\\.|_|~|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])*(?:[a-zA-Z]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])))\\.?(?:[a-zA-Z]|[\\x{00A0}-\\x{D7FF}\\x{F900}-\\x{FDCF}\\x{FDF0}-\\x{FFEF}])+")
	emailSubmatchFn = func(input string) string {
		idx := strings.IndexByte(input, '@')
		scrubbed := fmt.Sprintf("<<scrubbed::email::sha1::%s>>", hashString(input[idx:]))
		return scrubbed + input[idx:]
	}
)

// emails scrubs all emails found for PII compliance
func emails(ctx context.Context, fl mold.FieldLevel) error {
	switch fl.Field().Kind() {
	case reflect.String:
		scrubbed := emailRegex.ReplaceAllStringFunc(fl.Field().String(), emailSubmatchFn)
		fl.Field().SetString(scrubbed)
	}
	return nil
}

var textFn = func(shaName string) mold.Func {
	// Text scrubs the whole text for PII compliance
	return func(ctx context.Context, fl mold.FieldLevel) error {
		switch fl.Field().Kind() {
		case reflect.String:
			scrubbed := fmt.Sprintf("<<scrubbed::%s::sha1::%s>>", shaName, hashString(fl.Field().String()))
			fl.Field().SetString(scrubbed)
		}
		return nil
	}
}