Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

M1452: Initial Step of Integrate an XML parser #3718

Merged
merged 1 commit into from Oct 29, 2014
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
10 changes: 10 additions & 0 deletions components/script/dom/servohtmlparser.rs
Expand Up @@ -14,6 +14,7 @@ use dom::bindings::utils::{Reflectable, Reflector, reflect_dom_object};
use dom::node::TrustedNodeAddress;
use dom::document::{Document, DocumentHelpers};
use parse::html::JSMessage;
use parse::Parser;

use servo_util::task_state;

Expand Down Expand Up @@ -43,6 +44,15 @@ pub struct ServoHTMLParser {
tokenizer: DOMRefCell<Tokenizer>,
}

impl Parser for ServoHTMLParser{
fn parse_chunk(&self, input: String) {
self.tokenizer().borrow_mut().feed(input);
}
fn finish(&self){
self.tokenizer().borrow_mut().end();
}
}

impl ServoHTMLParser {
#[allow(unrooted_must_root)]
pub fn new(js_chan: Sender<JSMessage>, base_url: Option<Url>, document: JSRef<Document>)
Expand Down
4 changes: 1 addition & 3 deletions components/script/lib.rs
Expand Up @@ -211,9 +211,7 @@ pub mod dom {
pub mod testbinding;
}

pub mod parse {
pub mod html;
}
pub mod parse;

pub mod layout_interface;
pub mod page;
Expand Down
9 changes: 5 additions & 4 deletions components/script/parse/html.rs
Expand Up @@ -18,6 +18,7 @@ use dom::servohtmlparser;
use dom::servohtmlparser::ServoHTMLParser;
use dom::types::*;
use page::Page;
use parse::Parser;

use encoding::all::UTF_8;
use encoding::types::{Encoding, DecodeReplace};
Expand Down Expand Up @@ -486,22 +487,22 @@ pub fn parse_html(page: &Page,

match input {
InputString(s) => {
parser.tokenizer().borrow_mut().feed(s);
parser.parse_chunk(s);
}
InputUrl(url) => {
let load_response = load_response.unwrap();
match load_response.metadata.content_type {
Some((ref t, _)) if t.as_slice().eq_ignore_ascii_case("image") => {
let page = format!("<html><body><img src='{:s}' /></body></html>", base_url.as_ref().unwrap().serialize());
parser.tokenizer().borrow_mut().feed(page);
parser.parse_chunk(page);
},
_ => {
for msg in load_response.progress_port.iter() {
match msg {
Payload(data) => {
// FIXME: use Vec<u8> (html5ever #34)
let data = UTF_8.decode(data.as_slice(), DecodeReplace).unwrap();
parser.tokenizer().borrow_mut().feed(data);
parser.parse_chunk(data);
}
Done(Err(err)) => {
fail!("Failed to load page URL {:s}, error: {:s}", url.serialize(), err);
Expand All @@ -514,7 +515,7 @@ pub fn parse_html(page: &Page,
}
}

parser.tokenizer().borrow_mut().end();
parser.finish();

task_state::exit(InHTMLParser);

Expand Down
10 changes: 10 additions & 0 deletions components/script/parse/mod.rs
@@ -0,0 +1,10 @@
/* This Source Code Form is subject to the terms of the Mozilla Public
* 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/. */

pub mod html;

pub trait Parser {
fn parse_chunk(&self,input: String);
fn finish(&self);
}