Add support for WebVTT (#223)

* Add support for WebVTT

Use <https://www.iana.org/assignments/media-types/text/vtt> for magic
numbers.

* Add VTT signatures that include EOF

* Remove pointy brackets around URL

* Simplify Vtt

* delete bytePointer

internal/magic/text.go

@@ -348,3 +348,28 @@ func Srt(in []byte, _ uint32) bool {
 	// A third line must exist and not be empty. This is the actual subtitle text.
 	return s.Scan() && len(s.Bytes()) != 0
 }
+
+// Vtt matches a Web Video Text Tracks (WebVTT) file. See
+// https://www.iana.org/assignments/media-types/text/vtt.
+func Vtt(raw []byte, limit uint32) bool {
+	// Prefix match.
+	prefixes := [][]byte{
+		{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0A}, // UTF-8 BOM, "WEBVTT" and a line feed
+		{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0D}, // UTF-8 BOM, "WEBVTT" and a carriage return
+		{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x20}, // UTF-8 BOM, "WEBVTT" and a space
+		{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x09}, // UTF-8 BOM, "WEBVTT" and a horizontal tab
+		{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0A},                   // "WEBVTT" and a line feed
+		{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x0D},                   // "WEBVTT" and a carriage return
+		{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x20},                   // "WEBVTT" and a space
+		{0x57, 0x45, 0x42, 0x56, 0x54, 0x54, 0x09},                   // "WEBVTT" and a horizontal tab
+	}
+	for _, p := range prefixes {
+		if bytes.HasPrefix(raw, p) {
+			return true
+		}
+	}
+
+	// Exact match.
+	return bytes.Equal(raw, []byte{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) || // UTF-8 BOM and "WEBVTT"
+		bytes.Equal(raw, []byte{0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) // "WEBVTT"
+}

mimetype_test.go

@@ -197,6 +197,10 @@ var files = map[string]string{
 	"vcf.dos.vcf":     "text/vcard",
 	"vcf.vcf":         "text/vcard",
 	"voc.voc":         "audio/x-unknown",
+	"vtt.vtt":         "text/vtt",
+	"vtt.space.vtt":   "text/vtt",
+	"vtt.tab.vtt":     "text/vtt",
+	"vtt.eof.vtt":     "text/vtt",
 	"warc.warc":       "application/warc",
 	"wasm.wasm":       "application/wasm",
 	"wav.wav":         "audio/wav",

supported_mimes.md

@@ -1,4 +1,4 @@
-## 167 Supported MIME types
+## 168 Supported MIME types
 This file is automatically generated when running tests. Do not edit manually.
 
 Extension | MIME type | Aliases
@@ -170,3 +170,4 @@ Extension | MIME type | Aliases
 **.vcf** | text/vcard | -
 **.ics** | text/calendar | -
 **.warc** | application/warc | -
+**.vtt** | text/vtt | -

testdata/vtt.eof.vtt

@@ -0,0 +1 @@
+WEBVTT

testdata/vtt.space.vtt

@@ -0,0 +1 @@
+WEBVTT 

testdata/vtt.tab.vtt

@@ -0,0 +1 @@
+WEBVTT	

testdata/vtt.vtt

@@ -0,0 +1,45 @@
+WEBVTT 
+Kind: captions
+Language: en
+
+00:09.000 --> 00:11.000
+<v Roger Bingham>We are in New York City
+
+00:11.000 --> 00:13.000
+<v Roger Bingham>We are in New York City
+
+00:13.000 --> 00:16.000
+<v Roger Bingham>We're actually at the Lucern Hotel, just down the street
+
+00:16.000 --> 00:18.000
+<v Roger Bingham>from the American Museum of Natural History
+
+00:18.000 --> 00:20.000
+<v Roger Bingham>And with me is Neil deGrasse Tyson
+
+00:20.000 --> 00:22.000
+<v Roger Bingham>Astrophysicist, Director of the Hayden Planetarium
+
+00:22.000 --> 00:24.000
+<v Roger Bingham>at the AMNH.
+
+00:24.000 --> 00:26.000
+<v Roger Bingham>Thank you for walking down here.
+
+00:27.000 --> 00:30.000
+<v Roger Bingham>And I want to do a follow-up on the last conversation we did.
+
+00:30.000 --> 00:31.500 align:end size:50%
+<v Roger Bingham>When we e-mailed—
+
+00:30.500 --> 00:32.500 align:start size:50%
+<v Neil deGrasse Tyson>Didn't we talk about enough in that conversation?
+
+00:32.000 --> 00:35.500 align:end size:50%
+<v Roger Bingham>No! No no no no; 'cos 'cos obviously 'cos
+
+00:32.500 --> 00:33.500 align:start size:50%
+<v Neil deGrasse Tyson><i>Laughs</i>
+
+00:35.500 --> 00:38.000
+<v Roger Bingham>You know I'm so excited my glasses are falling off here.

tree.go

@@ -76,7 +76,7 @@ var (
 		alias("application/x-ogg")
 	oggAudio = newMIME("audio/ogg", ".oga", magic.OggAudio)
 	oggVideo = newMIME("video/ogg", ".ogv", magic.OggVideo)
-	text     = newMIME("text/plain", ".txt", magic.Text, html, svg, xml, php, js, lua, perl, python, json, ndJSON, rtf, srt, tcl, csv, tsv, vCard, iCalendar, warc)
+	text     = newMIME("text/plain", ".txt", magic.Text, html, svg, xml, php, js, lua, perl, python, json, ndJSON, rtf, srt, tcl, csv, tsv, vCard, iCalendar, warc, vtt)
 	xml      = newMIME("text/xml", ".xml", magic.XML, rss, atom, x3d, kml, xliff, collada, gml, gpx, tcx, amf, threemf, xfdf, owl2)
 	json     = newMIME("application/json", ".json", magic.JSON, geoJSON, har)
 	har      = newMIME("application/json", ".har", magic.HAR)
@@ -87,10 +87,11 @@ var (
 	html     = newMIME("text/html", ".html", magic.HTML)
 	php      = newMIME("text/x-php", ".php", magic.Php)
 	rtf      = newMIME("text/rtf", ".rtf", magic.Rtf)
-	srt      = newMIME("text/x-subrip", ".srt", magic.Srt).
-			alias("text/x-srt")
-	js = newMIME("application/javascript", ".js", magic.Js).
-		alias("application/x-javascript", "text/javascript")
+	js       = newMIME("application/javascript", ".js", magic.Js).
+			alias("application/x-javascript", "text/javascript")
+	srt = newMIME("text/x-subrip", ".srt", magic.Srt).
+		alias("text/x-srt")
+	vtt    = newMIME("text/vtt", ".vtt", magic.Vtt)
 	lua    = newMIME("text/x-lua", ".lua", magic.Lua)
 	perl   = newMIME("text/x-perl", ".pl", magic.Perl)
 	python = newMIME("application/x-python", ".py", magic.Python)