Mirrors/servo
1
0
Fork 0
mirror of https://github.com/servo/servo.git synced 2025-08-03 04:30:10 +01:00
Code Issues Projects Releases Packages Wiki Activity

Migrate mime_classifier top-level string to enum.

Browse source
This commit is contained in:
Corey Farwell 2016-07-02 16:42:29 -04:00
parent 9d3fc76463
commit 66303e40b5
3 changed files with 89 additions and 84 deletions
Download patch file Download diff file Expand all files Collapse all files

168
components/net/mime_classifier.rs
View file

@ -2,6 +2,7 @@
* License, v. 2.0. If a copy of the MPL was not distributed with this * License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
use hyper::mime::TopLevel;
use net_traits::LoadContext; use net_traits::LoadContext;
use std::borrow::ToOwned; use std::borrow::ToOwned;
@ -48,7 +49,8 @@ pub enum NoSniffFlag {
OFF OFF
} }
pub type MimeType = (String, String); pub type MimeType = (TopLevel, String);
impl MimeClassifier { impl MimeClassifier {
//Performs MIME Type Sniffing Algorithm (sections 7 and 8) //Performs MIME Type Sniffing Algorithm (sections 7 and 8)
@ -59,7 +61,7 @@ impl MimeClassifier {
supplied_type: &Option<MimeType>, supplied_type: &Option<MimeType>,
data: &[u8]) -> MimeType { data: &[u8]) -> MimeType {
let supplied_type_or_octet_stream = supplied_type.clone() let supplied_type_or_octet_stream = supplied_type.clone()
.unwrap_or(("application".to_owned(), .unwrap_or((TopLevel::Application,
"octet-stream".to_owned())); "octet-stream".to_owned()));
match context { match context {
LoadContext::Browsing => match *supplied_type { LoadContext::Browsing => match *supplied_type {
@ -105,7 +107,7 @@ impl MimeClassifier {
// This section was *not* finalized in the specs at the time // This section was *not* finalized in the specs at the time
// of this implementation. // of this implementation.
match *supplied_type { match *supplied_type {
None => ("application".to_owned(), "octet-stream".to_owned()), None => (TopLevel::Application, "octet-stream".to_owned()),
_ => supplied_type_or_octet_stream, _ => supplied_type_or_octet_stream,
} }
}, },
@ -115,7 +117,7 @@ impl MimeClassifier {
// This section was *not* finalized in the specs at the time // This section was *not* finalized in the specs at the time
// of this implementation. // of this implementation.
match *supplied_type { match *supplied_type {
None => ("text".to_owned(), "css".to_owned()), None => (TopLevel::Text, "css".to_owned()),
_ => supplied_type_or_octet_stream, _ => supplied_type_or_octet_stream,
} }
}, },
@ -125,7 +127,7 @@ impl MimeClassifier {
// This section was *not* finalized in the specs at the time // This section was *not* finalized in the specs at the time
// of this implementation. // of this implementation.
match *supplied_type { match *supplied_type {
None => ("text".to_owned(), "javascript".to_owned()), None => (TopLevel::Text, "javascript".to_owned()),
_ => supplied_type_or_octet_stream, _ => supplied_type_or_octet_stream,
} }
}, },
@ -141,14 +143,14 @@ impl MimeClassifier {
// //
// This section was *not* finalized in the specs at the time // This section was *not* finalized in the specs at the time
// of this implementation. // of this implementation.
("text".to_owned(), "vtt".to_owned()) (TopLevel::Text, "vtt".to_owned())
}, },
LoadContext::CacheManifest => { LoadContext::CacheManifest => {
// 8.9 Sniffing in a cache manifest context // 8.9 Sniffing in a cache manifest context
// //
// This section was *not* finalized in the specs at the time // This section was *not* finalized in the specs at the time
// of this implementation. // of this implementation.
("text".to_owned(), "cache-manifest".to_owned()) (TopLevel::Text, "cache-manifest".to_owned())
}, },
} }
} }
@ -199,39 +201,41 @@ impl MimeClassifier {
self.binary_or_plaintext.classify(data).expect("BinaryOrPlaintextClassifier always succeeds") self.binary_or_plaintext.classify(data).expect("BinaryOrPlaintextClassifier always succeeds")
} }
fn is_xml(tp: &str, sub_tp: &str) -> bool { fn is_xml(tp: &TopLevel, sub_tp: &str) -> bool {
sub_tp.ends_with("+xml") || sub_tp.ends_with("+xml") ||
match (tp, sub_tp) { match (tp, sub_tp) {
("application", "xml") | ("text", "xml") => true, (&TopLevel::Application, "xml") | (&TopLevel::Text, "xml") => true,
_ => false _ => false
} }
} }
fn is_html(tp: &str, sub_tp: &str) -> bool { fn is_html(tp: &TopLevel, sub_tp: &str) -> bool {
tp == "text" && sub_tp == "html" *tp == TopLevel::Text && sub_tp == "html"
} }
fn is_image(tp: &str) -> bool { fn is_image(tp: &TopLevel) -> bool {
tp == "image" *tp == TopLevel::Image
} }
fn is_audio_video(tp: &str, sub_tp: &str) -> bool { fn is_audio_video(tp: &TopLevel, sub_tp: &str) -> bool {
tp == "audio" || *tp == TopLevel::Audio ||
tp == "video" || *tp == TopLevel::Video ||
(tp == "application" && sub_tp == "ogg") (*tp == TopLevel::Application && sub_tp == "ogg")
} }
fn is_explicit_unknown(tp: &str, sub_tp: &str) -> bool { fn is_explicit_unknown(tp: &TopLevel, sub_tp: &str) -> bool {
match(tp, sub_tp) { if let TopLevel::Ext(ref e) = *tp {
("unknown", "unknown") | return e == "unknown" && sub_tp == "unknown";
("application", "unknown") | }
("*", "*") => true, match (tp, sub_tp) {
(&TopLevel::Application, "unknown") |
(&TopLevel::Star, "*") => true,
_ => false _ => false
} }
} }
fn get_media_type(media_type: &str, fn get_media_type(media_type: &TopLevel,
media_subtype: &str) -> Option<MediaType> { media_subtype: &str) -> Option<MediaType> {
if MimeClassifier::is_xml(media_type, media_subtype) { if MimeClassifier::is_xml(media_type, media_subtype) {
Some(MediaType::Xml) Some(MediaType::Xml)
} else if MimeClassifier::is_html(media_type, media_subtype) { } else if MimeClassifier::is_html(media_type, media_subtype) {
@ -252,7 +256,7 @@ impl MimeClassifier {
} }
} }
pub fn as_string_option(tup: Option<(&'static str, &'static str)>) -> Option<MimeType> { pub fn as_string_option(tup: Option<(TopLevel, &'static str)>) -> Option<MimeType> {
tup.map(|(a, b)| (a.to_owned(), b.to_owned())) tup.map(|(a, b)| (a.to_owned(), b.to_owned()))
} }
@ -299,7 +303,7 @@ struct ByteMatcher {
pattern: &'static [u8], pattern: &'static [u8],
mask: &'static [u8], mask: &'static [u8],
leading_ignore: &'static [u8], leading_ignore: &'static [u8],
content_type: (&'static str, &'static str) content_type: (TopLevel, &'static str)
} }
impl ByteMatcher { impl ByteMatcher {
@ -403,7 +407,7 @@ impl Mp4Matcher {
impl MIMEChecker for Mp4Matcher { impl MIMEChecker for Mp4Matcher {
fn classify(&self, data: &[u8]) -> Option<MimeType> { fn classify(&self, data: &[u8]) -> Option<MimeType> {
if self.matches(data) { if self.matches(data) {
Some(("video".to_owned(), "mp4".to_owned())) Some((TopLevel::Video, "mp4".to_owned()))
} else { } else {
None None
} }
@ -417,19 +421,19 @@ impl MIMEChecker for Mp4Matcher {
struct BinaryOrPlaintextClassifier; struct BinaryOrPlaintextClassifier;
impl BinaryOrPlaintextClassifier { impl BinaryOrPlaintextClassifier {
fn classify_impl(&self, data: &[u8]) -> (&'static str, &'static str) { fn classify_impl(&self, data: &[u8]) -> (TopLevel, &'static str) {
if data.starts_with(&[0xFFu8, 0xFEu8]) || if data.starts_with(&[0xFFu8, 0xFEu8]) ||
data.starts_with(&[0xFEu8, 0xFFu8]) || data.starts_with(&[0xFEu8, 0xFFu8]) ||
data.starts_with(&[0xEFu8, 0xBBu8, 0xBFu8]) data.starts_with(&[0xEFu8, 0xBBu8, 0xBFu8])
{ {
("text", "plain") (TopLevel::Text, "plain")
} else if data.iter().any(|&x| x <= 0x08u8 || } else if data.iter().any(|&x| x <= 0x08u8 ||
x == 0x0Bu8 || x == 0x0Bu8 ||
(x >= 0x0Eu8 && x <= 0x1Au8) || (x >= 0x0Eu8 && x <= 0x1Au8) ||
(x >= 0x1Cu8 && x <= 0x1Fu8)) { (x >= 0x1Cu8 && x <= 0x1Fu8)) {
("application", "octet-stream") (TopLevel::Application, "octet-stream")
} else { } else {
("text", "plain") (TopLevel::Text, "plain")
} }
} }
} }
@ -587,7 +591,7 @@ where T: Iterator<Item=&'a u8> + Clone {
struct FeedsClassifier; struct FeedsClassifier;
impl FeedsClassifier { impl FeedsClassifier {
// Implements sniffing for mislabeled feeds (https://mimesniff.spec.whatwg.org/#sniffing-a-mislabeled-feed) // Implements sniffing for mislabeled feeds (https://mimesniff.spec.whatwg.org/#sniffing-a-mislabeled-feed)
fn classify_impl(&self, data: &[u8]) -> Option<(&'static str, &'static str)> { fn classify_impl(&self, data: &[u8]) -> Option<(TopLevel, &'static str)> {
// Step 4: can not be feed unless length is > 3 // Step 4: can not be feed unless length is > 3
if data.len() < 3 { if data.len() < 3 {
return None; return None;
@ -618,11 +622,11 @@ impl FeedsClassifier {
// Step 5.2.5 // Step 5.2.5
if matcher.matches(b"rss") { if matcher.matches(b"rss") {
return Some(("application", "rss+xml")); return Some((TopLevel::Application, "rss+xml"));
} }
// Step 5.2.6 // Step 5.2.6
if matcher.matches(b"feed") { if matcher.matches(b"feed") {
return Some(("application", "atom+xml")); return Some((TopLevel::Application, "atom+xml"));
} }
// Step 5.2.7 // Step 5.2.7
if matcher.matches(b"rdf:RDF") { if matcher.matches(b"rdf:RDF") {
@ -633,7 +637,7 @@ impl FeedsClassifier {
.chain(|| eats_until(&mut matcher, .chain(|| eats_until(&mut matcher,
b"http://www.w3.org/1999/02/22-rdf-syntax-ns#", b"http://www.w3.org/1999/02/22-rdf-syntax-ns#",
b"http://purl.org/rss/1.0/")) { b"http://purl.org/rss/1.0/")) {
Match::StartAndEnd => return Some(("application", "rss+xml")), Match::StartAndEnd => return Some((TopLevel::Application, "rss+xml")),
Match::DidNotMatch => {}, Match::DidNotMatch => {},
Match::Start => return None Match::Start => return None
} }
@ -662,7 +666,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x00\x00\x01\x00", pattern: b"\x00\x00\x01\x00",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("image", "x-icon"), content_type: (TopLevel::Image, "x-icon"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -671,7 +675,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x00\x00\x02\x00", pattern: b"\x00\x00\x02\x00",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("image", "x-icon"), content_type: (TopLevel::Image, "x-icon"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -680,7 +684,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"BM", pattern: b"BM",
mask: b"\xFF\xFF", mask: b"\xFF\xFF",
content_type: ("image", "bmp"), content_type: (TopLevel::Image, "bmp"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -689,7 +693,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"GIF89a", pattern: b"GIF89a",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("image", "gif"), content_type: (TopLevel::Image, "gif"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -698,7 +702,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"GIF87a", pattern: b"GIF87a",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("image", "gif"), content_type: (TopLevel::Image, "gif"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -707,7 +711,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"RIFF\x00\x00\x00\x00WEBPVP", pattern: b"RIFF\x00\x00\x00\x00WEBPVP",
mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("image", "webp"), content_type: (TopLevel::Image, "webp"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -717,7 +721,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x89PNG\r\n\x1A\n", pattern: b"\x89PNG\r\n\x1A\n",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("image", "png"), content_type: (TopLevel::Image, "png"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -726,7 +730,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\xFF\xD8\xFF", pattern: b"\xFF\xD8\xFF",
mask: b"\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF",
content_type: ("image", "jpeg"), content_type: (TopLevel::Image, "jpeg"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -735,7 +739,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x1A\x45\xDF\xA3", pattern: b"\x1A\x45\xDF\xA3",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("video", "webm"), content_type: (TopLevel::Video, "webm"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -744,7 +748,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b".snd", pattern: b".snd",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("audio", "basic"), content_type: (TopLevel::Audio, "basic"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -753,7 +757,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"FORM\x00\x00\x00\x00AIFF", pattern: b"FORM\x00\x00\x00\x00AIFF",
mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF",
content_type: ("audio", "aiff"), content_type: (TopLevel::Audio, "aiff"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -762,7 +766,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"ID3", pattern: b"ID3",
mask: b"\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF",
content_type: ("audio", "mpeg"), content_type: (TopLevel::Audio, "mpeg"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -771,7 +775,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"OggS\x00", pattern: b"OggS\x00",
mask: b"\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF",
content_type: ("application", "ogg"), content_type: (TopLevel::Application, "ogg"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -781,7 +785,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"MThd\x00\x00\x00\x06", pattern: b"MThd\x00\x00\x00\x06",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("audio", "midi"), content_type: (TopLevel::Audio, "midi"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -790,7 +794,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"RIFF\x00\x00\x00\x00AVI ", pattern: b"RIFF\x00\x00\x00\x00AVI ",
mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF",
content_type: ("video", "avi"), content_type: (TopLevel::Video, "avi"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -799,7 +803,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"RIFF\x00\x00\x00\x00WAVE", pattern: b"RIFF\x00\x00\x00\x00WAVE",
mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\x00\x00\x00\x00\xFF\xFF\xFF\xFF",
content_type: ("audio", "wave"), content_type: (TopLevel::Audio, "wave"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -809,7 +813,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<!DOCTYPE HTML", pattern: b"<!DOCTYPE HTML",
mask: b"\xFF\xFF\xDF\xDF\xDF\xDF\xDF\xDF\xDF\xFF\xDF\xDF\xDF\xDF", mask: b"\xFF\xFF\xDF\xDF\xDF\xDF\xDF\xDF\xDF\xFF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -821,7 +825,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<HTML", pattern: b"<HTML",
mask: b"\xFF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -833,7 +837,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<HEAD", pattern: b"<HEAD",
mask: b"\xFF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -845,7 +849,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<SCRIPT", pattern: b"<SCRIPT",
mask: b"\xFF\xDF\xDF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -857,7 +861,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<IFRAME", pattern: b"<IFRAME",
mask: b"\xFF\xDF\xDF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -869,7 +873,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<H1", pattern: b"<H1",
mask: b"\xFF\xDF\xFF", mask: b"\xFF\xDF\xFF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -881,7 +885,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<DIV", pattern: b"<DIV",
mask: b"\xFF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -893,7 +897,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<FONT", pattern: b"<FONT",
mask: b"\xFF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -905,7 +909,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<TABLE", pattern: b"<TABLE",
mask: b"\xFF\xDF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -917,7 +921,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<A", pattern: b"<A",
mask: b"\xFF\xDF", mask: b"\xFF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -929,7 +933,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<STYLE", pattern: b"<STYLE",
mask: b"\xFF\xDF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -941,7 +945,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<TITLE", pattern: b"<TITLE",
mask: b"\xFF\xDF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -953,7 +957,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<B", pattern: b"<B",
mask: b"\xFF\xDF", mask: b"\xFF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -965,7 +969,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<BODY", pattern: b"<BODY",
mask: b"\xFF\xDF\xDF\xDF\xDF", mask: b"\xFF\xDF\xDF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -977,7 +981,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<BR", pattern: b"<BR",
mask: b"\xFF\xDF\xDF", mask: b"\xFF\xDF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -989,7 +993,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<P", pattern: b"<P",
mask: b"\xFF\xDF", mask: b"\xFF\xDF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -1001,7 +1005,7 @@ impl ByteMatcher {
matcher: ByteMatcher { matcher: ByteMatcher {
pattern: b"<!--", pattern: b"<!--",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("text", "html"), content_type: (TopLevel::Text, "html"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -1012,7 +1016,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"<?xml", pattern: b"<?xml",
mask: b"\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF",
content_type: ("text", "xml"), content_type: (TopLevel::Text, "xml"),
leading_ignore: b"\t\n\x0C\r " leading_ignore: b"\t\n\x0C\r "
} }
} }
@ -1021,7 +1025,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"%PDF-", pattern: b"%PDF-",
mask: b"\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF",
content_type: ("application", "pdf"), content_type: (TopLevel::Application, "pdf"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1034,7 +1038,7 @@ impl ByteMatcher {
mask: b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\ mask: b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\
\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\ \x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\
\x00\x00\xFF\xFF", \x00\x00\xFF\xFF",
content_type: ("application", "vnd.ms-fontobject"), content_type: (TopLevel::Application, "vnd.ms-fontobject"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1043,7 +1047,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x00\x01\x00\x00", pattern: b"\x00\x01\x00\x00",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("application", "font-sfnt"), content_type: (TopLevel::Application, "font-sfnt"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1052,7 +1056,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"OTTO", pattern: b"OTTO",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("application", "font-sfnt"), content_type: (TopLevel::Application, "font-sfnt"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1061,7 +1065,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"ttcf", pattern: b"ttcf",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("application", "font-sfnt"), content_type: (TopLevel::Application, "font-sfnt"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1070,7 +1074,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"wOFF", pattern: b"wOFF",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("application", "font-woff"), content_type: (TopLevel::Application, "font-woff"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1079,7 +1083,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\x1F\x8B\x08", pattern: b"\x1F\x8B\x08",
mask: b"\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF",
content_type: ("application", "x-gzip"), content_type: (TopLevel::Application, "x-gzip"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1088,7 +1092,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"PK\x03\x04", pattern: b"PK\x03\x04",
mask: b"\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF",
content_type: ("application", "zip"), content_type: (TopLevel::Application, "zip"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1097,7 +1101,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"Rar \x1A\x07\x00", pattern: b"Rar \x1A\x07\x00",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("application", "x-rar-compressed"), content_type: (TopLevel::Application, "x-rar-compressed"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1106,7 +1110,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"%!PS-Adobe-", pattern: b"%!PS-Adobe-",
mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF", mask: b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF",
content_type: ("application", "postscript"), content_type: (TopLevel::Application, "postscript"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1115,7 +1119,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\xFE\xFF\x00\x00", pattern: b"\xFE\xFF\x00\x00",
mask: b"\xFF\xFF\x00\x00", mask: b"\xFF\xFF\x00\x00",
content_type: ("text", "plain"), content_type: (TopLevel::Text, "plain"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1124,7 +1128,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\xFF\xFE\x00\x00", pattern: b"\xFF\xFE\x00\x00",
mask: b"\xFF\xFF\x00\x00", mask: b"\xFF\xFF\x00\x00",
content_type: ("text", "plain"), content_type: (TopLevel::Text, "plain"),
leading_ignore: &[] leading_ignore: &[]
} }
} }
@ -1133,7 +1137,7 @@ impl ByteMatcher {
ByteMatcher { ByteMatcher {
pattern: b"\xEF\xBB\xBF\x00", pattern: b"\xEF\xBB\xBF\x00",
mask: b"\xFF\xFF\xFF\x00", mask: b"\xFF\xFF\xFF\x00",
content_type: ("text", "plain"), content_type: (TopLevel::Text, "plain"),
leading_ignore: &[] leading_ignore: &[]
} }
} }

4
components/net/resource_thread.rs
View file

@ -117,14 +117,14 @@ pub fn start_sending_sniffed_opt(start_chan: LoadConsumer, mut metadata: Metadat
let supplied_type = let supplied_type =
metadata.content_type.as_ref().map(|&Serde(ContentType(Mime(ref toplevel, ref sublevel, _)))| { metadata.content_type.as_ref().map(|&Serde(ContentType(Mime(ref toplevel, ref sublevel, _)))| {
(format!("{}", toplevel), format!("{}", sublevel)) (toplevel.to_owned(), format!("{}", sublevel))
}); });
let (toplevel, sublevel) = classifier.classify(context, let (toplevel, sublevel) = classifier.classify(context,
no_sniff, no_sniff,
check_for_apache_bug, check_for_apache_bug,
&supplied_type, &supplied_type,
&partial_body); &partial_body);
let mime_tp: TopLevel = toplevel.parse().unwrap(); let mime_tp: TopLevel = toplevel.into();
let mime_sb: SubLevel = sublevel.parse().unwrap(); let mime_sb: SubLevel = sublevel.parse().unwrap();
metadata.content_type = metadata.content_type =
Some(Serde(ContentType(Mime(mime_tp, mime_sb, vec![])))); Some(Serde(ContentType(Mime(mime_tp, mime_sb, vec![]))));

1
tests/unit/net/mime_classifier.rs
View file

@ -75,6 +75,7 @@ fn test_sniff_with_flags(filename_orig: &path::Path,
match read_result { match read_result {
Ok(data) => { Ok(data) => {
let supplied_type = supplied_type.map(|(x, y)| (x.parse().unwrap(), y));
let (parsed_type, parsed_subtp) = classifier.classify(LoadContext::Browsing, let (parsed_type, parsed_subtp) = classifier.classify(LoadContext::Browsing,
no_sniff_flag, no_sniff_flag,
apache_bug_flag, apache_bug_flag,