support hexadecimal numeric html entities, fixes #13

Author: Mario Hros

go.mod

@@ -0,0 +1,5 @@
+module github.com/k3a/html2text
+
+go 1.16
+
+require github.com/smartystreets/goconvey v1.6.4 // indirect

go.sum

@@ -0,0 +1,13 @@
+github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
+github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
+github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
+github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
+github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d h1:zE9ykElWQ6/NYmHa3jpm/yHnI4xSofP+UP6SpjHcSeM=
+github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
+github.com/smartystreets/goconvey v1.6.4 h1:fv0U8FUIMPNf1L9lnHLvLhgicrIVChEkdzIKYqbNC9s=
+github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=

html2text.go

@@ -17,16 +17,26 @@ var badTagnamesRE = regexp.MustCompile(`^(head|script|style|a)($|\s+)`)
 var linkTagRE = regexp.MustCompile(`a.*href=('([^']*?)'|"([^"]*?)")`)
 var badLinkHrefRE = regexp.MustCompile(`javascript:`)
 var headersRE = regexp.MustCompile(`^(\/)?h[1-6]`)
-var numericEntityRE = regexp.MustCompile(`^#([0-9]+)$`)
+var numericEntityRE = regexp.MustCompile(`(?i)^#(x?[a-f0-9]+)$`)
 
 func parseHTMLEntity(entName string) (string, bool) {
 	if r, ok := entity[entName]; ok {
 		return string(r), true
 	}
 
 	if match := numericEntityRE.FindStringSubmatch(entName); len(match) == 2 {
-		digits := match[1]
-		n, err := strconv.Atoi(digits)
+		var (
+			err    error
+			n      int64
+			digits = match[1]
+		)
+
+		if digits != "" && (digits[0] == 'x' || digits[0] == 'X') {
+			n, err = strconv.ParseInt(digits[1:], 16, 64)
+		} else {
+			n, err = strconv.ParseInt(digits, 10, 64)
+		}
+
 		if err == nil && (n == 9 || n == 10 || n == 13 || n > 31) {
 			return string(rune(n)), true
 		}

html2text_test.go

@@ -61,6 +61,7 @@ func TestHTML2Text(t *testing.T) {
 			So(HTML2Text(`fish & chips`), ShouldEqual, "fish & chips")
 			So(HTML2Text(`"I'm sorry, Dave. I'm afraid I can't do that." – HAL, 2001: A Space Odyssey`), ShouldEqual, "\"I'm sorry, Dave. I'm afraid I can't do that.\" – HAL, 2001: A Space Odyssey")
 			So(HTML2Text(`Google ®`), ShouldEqual, "Google ®")
+			So(HTML2Text(`⁌ decimal and hex entities supported ⁍`), ShouldEqual, "⁌ decimal and hex entities supported ⁍")
 		})
 
 		Convey("Large Entity", func() {