SSR: Stringify VNodes (II)

ci/run_tests.sh

@@ -3,9 +3,10 @@ set -euxo pipefail # https://vaneyckt.io/posts/safer_bash_scripts_with_set_euxo_
 
 (cd yew \
   && cargo test --target wasm32-unknown-unknown --features wasm_test \
+  && cargo test --target wasm32-unknown-unknown --features wasm_test,sans_mount_render \
   && cargo test --doc --features doc_test,wasm_test,yaml,msgpack,cbor,toml \
   && cargo test --doc --features doc_test,wasm_test,yaml,msgpack,cbor,toml \
-    --features std_web,agent,services --no-default-features)
+    --features std_web,agent,services,sans_mount_render --no-default-features)
 
 (cd yew-functional && cargo test --target wasm32-unknown-unknown)
 

yew-stdweb/Cargo.toml

@@ -30,6 +30,7 @@ gloo = { version = "0.2.1", optional = true }
 http = "0.2"
 indexmap = "1.0.2"
 js-sys = { version = "0.3", optional = true }
+lazy_static = "1.3.0"
 log = "0.4"
 proc-macro-hack = "0.5"
 proc-macro-nested = "0.1"
@@ -78,7 +79,7 @@ msgpack = ["rmp-serde"]
 cbor = ["serde_cbor"]
 
 [package.metadata.docs.rs]
-features = ["yaml", "cbor", "toml", "msgpack", "doc_test"]
+features = ["yaml", "cbor", "toml", "msgpack", "doc_test", "sans_mount_render"]
 
 [workspace]
 members = [

yew/Cargo.toml

@@ -28,9 +28,11 @@ console_error_panic_hook = { version = "0.1", optional = true }
 futures = { version = "0.3", optional = true }
 gloo = { version = "0.2.1", optional = true }
 http = "0.2"
+htmlescape = { version = "0.3.1", optional = true }
 indexmap = "1.0.2"
 js-sys = { version = "0.3", optional = true }
 log = "0.4"
+lazy_static = "1.3.0"
 proc-macro-hack = "0.5"
 proc-macro-nested = "0.1"
 rmp-serde = { version = "0.14.0", optional = true }
@@ -133,10 +135,11 @@ web_sys = ["console_error_panic_hook", "futures", "gloo", "js-sys", "web-sys", "
 doc_test = []
 wasm_test = []
 services = []
+sans_mount_render = ["htmlescape"]
 agent = ["bincode"]
 yaml = ["serde_yaml"]
 msgpack = ["rmp-serde"]
 cbor = ["serde_cbor"]
 
 [package.metadata.docs.rs]
-features = ["yaml", "cbor", "toml", "msgpack", "doc_test"]
+features = ["yaml", "cbor", "toml", "msgpack", "doc_test", "sans_mount_render"]

yew/src/lib.rs

@@ -120,6 +120,8 @@ mod scheduler;
 pub mod utils;
 pub mod virtual_dom;
 
+pub mod sgml_tags;
+
 #[cfg(feature = "agent")]
 pub mod agent;
 #[cfg(feature = "services")]

yew/src/sgml_tags.rs

@@ -0,0 +1,230 @@
+//! This module contains utilities for parsing or validating strings relating
+//! to tags.
+
+use lazy_static::lazy_static;
+use std::collections::HashSet;
+use std::iter::FromIterator;
+
+lazy_static! {
+    static ref DISALLOWED_CUSTOM_ELEMENT_TAGS: HashSet<&'static str> = HashSet::from_iter(
+        vec![
+            "annotation-xml",
+            "color-profile",
+            "font-face",
+            "font-face-src",
+            "font-face-uri",
+            "font-face-format",
+            "font-face-name",
+            "missing-glyph",
+        ]
+        .iter()
+        .map(|tag| tag.clone())
+    );
+}
+
+/// Returns true when the character provided is a "control" as defined
+/// in [the WhatWG spec](https://infra.spec.whatwg.org/#control)
+fn is_control(c: char) -> bool {
+    match c {
+        '\u{007F}'..='\u{009F}' => true,
+        _ => is_c0_control(c),
+    }
+}
+
+/// Returns true when the character provided is a "c0 control" as defined
+/// in [the WhatWG spec](https://infra.spec.whatwg.org/#c0-control)
+fn is_c0_control(c: char) -> bool {
+    match c {
+        '\u{0000}'..='\u{001F}' => true,
+        _ => false,
+    }
+}
+
+/// Returns true when the string provided is a "noncharacter" as defined
+/// in [the WhatWG spec](https://infra.spec.whatwg.org/#noncharacter)
+fn is_noncharacter(c: char) -> bool {
+    match c {
+        '\u{FDD0}'..='\u{FDEF}' => true,
+        '\u{FFFE}' | '\u{FFFF}' | '\u{1FFFE}' | '\u{1FFFF}' | '\u{2FFFE}' | '\u{2FFFF}'
+        | '\u{3FFFE}' | '\u{3FFFF}' | '\u{4FFFE}' | '\u{4FFFF}' | '\u{5FFFE}' | '\u{5FFFF}'
+        | '\u{6FFFE}' | '\u{6FFFF}' | '\u{7FFFE}' | '\u{7FFFF}' | '\u{8FFFE}' | '\u{8FFFF}'
+        | '\u{9FFFE}' | '\u{9FFFF}' | '\u{AFFFE}' | '\u{AFFFF}' | '\u{BFFFE}' | '\u{BFFFF}'
+        | '\u{CFFFE}' | '\u{CFFFF}' | '\u{DFFFE}' | '\u{DFFFF}' | '\u{EFFFE}' | '\u{EFFFF}'
+        | '\u{FFFFE}' | '\u{FFFFF}' | '\u{10FFFE}' | '\u{10FFFF}' => true,
+        _ => false,
+    }
+}
+
+/// Returns true when the string provided is a valid "attribute name" as defined
+/// in [the WhatWG spec](https://html.spec.whatwg.org/multipage/syntax.html#syntax-attribute-name)
+pub fn is_valid_html_attribute_name(attr: &str) -> bool {
+    for c in attr.chars() {
+        if is_noncharacter(c)
+            || is_control(c)
+            || c == '\u{0020}'
+            || c == '\u{0022}'
+            || c == '\u{0027}'
+            || c == '\u{003E}'
+            || c == '\u{002F}'
+            || c == '\u{003D}'
+        {
+            return false;
+        }
+    }
+    true
+}
+
+/// Returns true when the character provided is a valid PCENChar as defined
+/// in [the WhatWG spec](https://html.spec.whatwg.org/multipage/custom-elements.html#prod-pcenchar)
+fn is_pcen_char(c: char) -> bool {
+    match c {
+        '-' | '.' | '0'..='9' | 'a'..='z' | '_' => true,
+        '\u{B7}' => true,
+        '\u{C0}'..='\u{D6}' => true,
+        '\u{D8}'..='\u{F6}' => true,
+        '\u{F8}'..='\u{37D}' => true,
+        '\u{37F}'..='\u{1FFF}' => true,
+        '\u{200C}'..='\u{200D}' => true,
+        '\u{203F}'..='\u{2040}' => true,
+        '\u{2070}'..='\u{218F}' => true,
+        '\u{2C00}'..='\u{2FEF}' => true,
+        '\u{3001}'..='\u{D7FF}' => true,
+        '\u{F900}'..='\u{FDCF}' => true,
+        '\u{FDF0}'..='\u{FFFD}' => true,
+        '\u{10000}'..='\u{EFFFF}' => true,
+        _ => false,
+    }
+}
+
+/// Returns true when the tag name provided would be a valid "custom element" per
+/// [the WhatWG spec](https://html.spec.whatwg.org/multipage/custom-elements.html#valid-custom-element-name)
+fn is_valid_html_custom_element_name(tag: &str) -> bool {
+    if DISALLOWED_CUSTOM_ELEMENT_TAGS.contains(&tag) {
+        return false;
+    }
+
+    let mut chars = tag.chars();
+    let first_char = chars.next();
+
+    match first_char {
+        None => false,
+        Some(first_char) => {
+            // must begin with [a-z]
+            if first_char < 'a' || first_char > 'z' {
+                return false;
+            }
+
+            let mut seen_hyphen = false;
+            for c in chars {
+                if c == '-' {
+                    seen_hyphen = true
+                }
+
+                // all characters must be valid PCENChar's
+                if !is_pcen_char(c) {
+                    return false;
+                }
+            }
+
+            // must contain at least one hyphen
+            seen_hyphen
+        }
+    }
+}
+
+/// Returns true when the tag name provided looks like a valid non-custom HTML element or valid SVG element.
+/// There's no official spec here, it's just arbitrary.
+fn is_valid_html_standard_ish_element_name(tag: &str) -> bool {
+    // must contain at least one character
+    if tag.is_empty() {
+        return false;
+    }
+
+    let mut saw_non_hyphen = false;
+    for c in tag.chars() {
+        match c {
+            'a'..='z' |'A'..='Z' | '0'..='9' => {
+                saw_non_hyphen = true
+            }
+            '-' => {}
+            _ => {
+                return false;
+            }
+        }
+    }
+
+    saw_non_hyphen
+}
+
+/// Returns true when you could validly construct a tag using this name in an HTML document
+pub fn is_valid_sgml_tag(tag: &str) -> bool {
+    is_valid_html_standard_ish_element_name(tag) || is_valid_html_custom_element_name(tag)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[cfg(feature = "wasm_test")]
+    use wasm_bindgen_test::{wasm_bindgen_test as test, wasm_bindgen_test_configure};
+
+    #[cfg(feature = "wasm_test")]
+    wasm_bindgen_test_configure!(run_in_browser);
+
+    #[test]
+    fn valid_custom_element() {
+        assert_eq!(is_valid_html_custom_element_name("foo-bar"), true);
+        assert_eq!(is_valid_html_custom_element_name("foo-"), true);
+        assert_eq!(is_valid_html_custom_element_name("bar-baz"), true);
+    }
+
+    #[test]
+    fn invalid_custom_element() {
+        assert_eq!(is_valid_html_custom_element_name("foobar"), false);
+        assert_eq!(is_valid_html_custom_element_name("-bar"), false);
+        assert_eq!(is_valid_html_custom_element_name("foo bar"), false);
+        assert_eq!(is_valid_html_custom_element_name(""), false);
+        assert_eq!(is_valid_html_custom_element_name("foo\nbar"), false);
+        assert_eq!(is_valid_html_custom_element_name("-"), false);
+    }
+
+    #[test]
+    fn valid_html_element() {
+        assert_eq!(is_valid_html_standard_ish_element_name("section"), true);
+        assert_eq!(is_valid_html_standard_ish_element_name("h2"), true);
+        assert_eq!(is_valid_html_standard_ish_element_name("applet"), true);
+        assert_eq!(is_valid_html_standard_ish_element_name("appLET"), true);
+        assert_eq!(is_valid_html_standard_ish_element_name("aPPlet"), true);
+        assert_eq!(is_valid_html_standard_ish_element_name("foo-bar"), true);
+    }
+
+    #[test]
+    fn invalid_html_element() {
+        assert_eq!(is_valid_html_standard_ish_element_name(" foo"), false);
+        assert_eq!(is_valid_html_standard_ish_element_name("foo "), false);
+        assert_eq!(is_valid_html_standard_ish_element_name("-"), false);
+        assert_eq!(is_valid_html_standard_ish_element_name("!doctype"), false);
+    }
+
+    #[test]
+    fn valid_html_attribute() {
+        assert_eq!(is_valid_html_attribute_name("-foo-bar"), true);
+        assert_eq!(is_valid_html_attribute_name("data-foobar"), true);
+        assert_eq!(is_valid_html_attribute_name("foo<bar"), true); // shocking but true
+    }
+
+    #[test]
+    fn invalid_html_attribute() {
+        assert_eq!(is_valid_html_attribute_name("foo=bar"), false);
+        assert_eq!(is_valid_html_attribute_name("\"foo\""), false);
+        assert_eq!(is_valid_html_attribute_name("foo bar"), false);
+        assert_eq!(is_valid_html_attribute_name("foo>bar"), false);
+    }
+
+    #[test]
+    fn invalid_sgml_tag() {
+        assert_eq!(is_valid_sgml_tag("f>bar"), false);
+        assert_eq!(is_valid_sgml_tag("f<bar"), false);
+        assert_eq!(is_valid_sgml_tag("/>"), false);
+    }
+}

yew/src/virtual_dom/mod.rs

@@ -11,6 +11,9 @@ pub mod vtag;
 #[doc(hidden)]
 pub mod vtext;
 
+#[cfg(feature = "sans_mount_render")]
+pub mod smr;
+
 use crate::html::{AnyScope, NodeRef};
 use cfg_if::cfg_if;
 use indexmap::set::IndexSet;