web-html: Finish implementing the IN_HEAD and IN_HEAD_NOSCRIPT parsin…

…g states.
skift-org · Mar 26, 2024 · 3f2097c · 3f2097c
1 parent 33e96f0
commit 3f2097c
Show file tree

Hide file tree

Showing 5 changed files with 106 additions and 24 deletions.
diff --git a/src/web/web-html/lexer.cpp b/src/web/web-html/lexer.cpp
@@ -26,7 +26,7 @@ void Lexer::_raise(Str msg) {
 }
 
 void Lexer::consume(Rune rune, bool isEof) {
-    logDebug("Lexing '{#c}' {#x} in {}", rune, rune, toStr(_state));
+    // logDebug("Lexing '{#c}' {#x} in {}", rune, rune, toStr(_state));
 
     switch (_state) {
 

diff --git a/src/web/web-html/parser.cpp b/src/web/web-html/parser.cpp
@@ -406,6 +406,7 @@ void Parser::_handleBeforeHead(Token const &t) {
     // A start tag whose tag name is "head"
     else if (t.type == Token::START_TAG and t.name == "head") {
         _headElement = insertHtmlElement(*this, t);
+        _switchTo(Mode::IN_HEAD);
     }
 
     // Anything else
@@ -428,6 +429,12 @@ void Parser::_handleBeforeHead(Token const &t) {
 
 // https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inhead
 void Parser::_handleInHead(Token const &t) {
+    auto anythingElse = [&] {
+        _openElements.popBack();
+        _switchTo(Mode::AFTER_HEAD);
+        accept(t);
+    };
+
     // A character token that is one of U+0009 CHARACTER TABULATION,
     // U+000A LINE FEED (LF), U+000C FORM FEED (FF),
     // U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
@@ -520,6 +527,82 @@ void Parser::_handleInHead(Token const &t) {
 
         // 10. Switch the insertion mode to "text".
         _switchTo(Mode::TEXT);
+    } else if (t.type == Token::END_TAG and (t.name == "head")) {
+        _openElements.popBack();
+        _switchTo(Mode::AFTER_HEAD);
+    } else if (t.type == Token::END_TAG and (t.name == "body" or t.name == "html" or t.name == "br")) {
+        anythingElse();
+    } else if (t.type == Token::START_TAG and (t.name == "template")) {
+        // NOSPEC: We don't support templates
+    } else if (t.type == Token::END_TAG and (t.name == "template")) {
+        // NOSPEC: We don't support templates
+    } else if ((t.type == Token::START_TAG and (t.name == "head")) or t.type == Token::END_TAG) {
+        // ignore
+        _raise();
+    } else {
+        anythingElse();
+    }
+}
+
+// https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inheadnoscript
+void Parser::_handleInHeadNoScript(Token const &t) {
+    auto anythingElse = [&] {
+        _raise();
+        _openElements.popBack();
+        _switchTo(Mode::IN_HEAD);
+        accept(t);
+    };
+
+    // A DOCTYPE token
+    if (t.type == Token::DOCTYPE) {
+        _raise();
+    }
+
+    // A start tag whose tag name is "html"
+    else if (t.type == Token::START_TAG and (t.name == "html")) {
+        _acceptIn(Mode::IN_BODY, t);
+    }
+
+    // An end tag whose tag name is "noscript"
+    else if (t.type == Token::END_TAG and (t.name == "noscript")) {
+        _openElements.popBack();
+        _switchTo(Mode::IN_HEAD);
+    }
+
+    // A character token that is one of
+    //   - U+0009 CHARACTER TABULATION,
+    //   - U+000A LINE FEED (LF),
+    //   - U+000C FORM FEED (FF),
+    //   - U+000D CARRIAGE RETURN (CR),
+    //   - or U+0020 SPACE
+    // A comment token
+    // A start tag whose tag name is one of: "basefont", "bgsound", "link", "meta", "noframes", "style"
+    else if (
+        (t.type == Token::CHARACTER and (t.rune == '\t' or t.rune == '\n' or t.rune == '\f' or t.rune == ' ')) or
+        t.type == Token::COMMENT or
+        (t.type == Token::START_TAG and (t.name == "basefont" or t.name == "bgsound" or t.name == "link" or t.name == "meta" or t.name == "noframes" or t.name == "style"))
+    ) {
+        _acceptIn(Mode::IN_HEAD, t);
+    }
+
+    // An end tag whose tag name is "br"
+    else if (t.type == Token::END_TAG and (t.name == "br")) {
+        anythingElse();
+    }
+
+    // A start tag whose tag name is one of: "head", "noscript"
+    // Any other end tag
+    else if (
+        (t.type == Token::START_TAG and (t.name == "head" or t.name == "noscript")) or
+        t.type == Token::END_TAG
+    ) {
+        // ignore
+        _raise();
+    }
+
+    // Anything else
+    else {
+        anythingElse();
     }
 }
 
@@ -548,10 +631,9 @@ void Parser::_acceptIn(Mode mode, Token const &t) {
         _handleInHead(t);
         break;
 
-    // https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inheadnoscript
-    case Mode::IN_HEAD_NOSCRIPT: {
+    case Mode::IN_HEAD_NOSCRIPT:
+        _handleInHeadNoScript(t);
         break;
-    }
 
     // https://html.spec.whatwg.org/multipage/parsing.html#the-after-head-insertion-mode
     case Mode::AFTER_HEAD: {

diff --git a/src/web/web-html/parser.h b/src/web/web-html/parser.h
@@ -66,6 +66,8 @@ struct Parser : public Sink {
 
     void _handleInHead(Token const &t);
 
+    void _handleInHeadNoScript(Token const &t);
+
     void _switchTo(Mode mode);
 
     void _acceptIn(Mode mode, Token const &t);

diff --git a/src/web/web-http/fetch.cpp b/src/web/web-http/fetch.cpp
@@ -31,11 +31,12 @@ Async::Task<usize> _fetch(Mime::Url const &url, Sys::_Connection &conn, Io::Writ
         "GET {} HTTP/1.1\r\n"
         "Host: {}\r\n"
         "Connection: close\r\n"
-        "User-Agent: Karm Web/" stringify$(__ck_version_value) "\r\n"
-                                                               "\r\n",
+        "User-Agent: Karm Web Fetch/" stringify$(__ck_version_value) "\r\n"
+                                                                     "\r\n",
         url.path,
         url.host
     ));
+
     co_try$(conn.write(req.bytes()));
 
     // Read response

diff --git a/src/web/web-json/parse.cpp b/src/web/web-json/parse.cpp
@@ -51,9 +51,8 @@ Res<String> parseStr(Io::SScan &s) {
             }
         }
 
-        if (s.next()) {
+        if (s.next())
             continue;
-        }
 
         return Error::invalidData("invalid string");
     }
@@ -76,9 +75,8 @@ Res<Object> parseObject(Io::SScan &s) {
         auto key = try$(parseStr(s));
 
         s.eat(Re::space());
-        if (not s.skip(':')) {
+        if (not s.skip(':'))
             return Error::invalidData("expected ':'");
-        }
 
         s.eat(Re::space());
 
@@ -87,24 +85,22 @@ Res<Object> parseObject(Io::SScan &s) {
 
         s.eat(Re::space());
 
-        if (s.skip('}')) {
+        if (s.skip('}'))
             return Ok(m);
-        }
-        if (not s.skip(',')) {
+
+        if (not s.skip(','))
             return Error::invalidData("expected ','");
-        }
     }
 }
 
 Res<Array> parseArray(Io::SScan &s) {
     Array v;
-    if (not s.skip('[')) {
+    if (not s.skip('['))
         return Error::invalidData("expected '['");
-    }
 
-    if (s.skip(']')) {
+    if (s.skip(']'))
         return Ok(v);
-    }
+
     while (true) {
         s.eat(Re::space());
 
@@ -113,12 +109,11 @@ Res<Array> parseArray(Io::SScan &s) {
 
         s.eat(Re::space());
 
-        if (s.skip(']')) {
+        if (s.skip(']'))
             return Ok(v);
-        }
-        if (not s.skip(',')) {
+
+        if (not s.skip(','))
             return Error::invalidData("expected ','");
-        }
     }
 }
 
@@ -136,6 +131,7 @@ Res<usize> parseDigits(Io::SScan &s) {
         s.next();
         ++digits;
     }
+
     return Ok(digits);
 }
 
@@ -152,6 +148,7 @@ Res<f64> parseDecimal(Io::SScan &s) {
         fpart += parseAsciiDecDigit(s.next()) * multiplier;
         multiplier /= 10;
     }
+
     return Ok(fpart);
 }
 
@@ -174,15 +171,15 @@ Res<isize> parseInteger(Io::SScan &s) {
     while (s.match(Re::digit()) != Match::NO) {
         ipart = ipart * 10 + parseAsciiDecDigit(s.next());
     }
+
     return Ok(sign ? -ipart : ipart);
 }
 
 Res<Value> parseNumber(Io::SScan &s) {
     isize ipart = try$(parseInteger(s));
 
-    if (s.match(Re::single('.', 'e', 'E')) == Match::NO) {
+    if (s.match(Re::single('.', 'e', 'E')) == Match::NO)
         return Ok<Value>(ipart);
-    }
 
 // NOTE: Floating point numbers are not supported in freestanding environments.
 #ifdef __ck_freestanding__