Upgrade the HTML parser foundation

Cargo.lock

@@ -640,7 +640,7 @@ dependencies = [
  "cssparser-macros",
  "dtoa-short",
  "itoa",
- "phf",
+ "phf 0.11.3",
  "smallvec",
 ]
 
@@ -1036,16 +1036,6 @@ version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6d5a32815ae3f33302d95fdcb2ce17862f8c65363dcfd29360480ba1001fc9c"
 
-[[package]]
-name = "futf"
-version = "0.1.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
-dependencies = [
- "mac",
- "new_debug_unreachable",
-]
-
 [[package]]
 name = "futures"
 version = "0.3.32"
@@ -1289,14 +1279,12 @@ dependencies = [
 
 [[package]]
 name = "html5ever"
-version = "0.29.1"
+version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b7410cae13cbc75623c98ac4cbfd1f0bedddf3227afc24f370cf0f50a44a11c"
+checksum = "46a1761807faccc9a19e86944bbf40610014066306f96edcdedc2fb714bcb7b8"
 dependencies = [
  "log",
- "mac",
  "markup5ever",
- "match_token",
 ]
 
 [[package]]
@@ -1729,35 +1717,15 @@ version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154"
 
-[[package]]
-name = "mac"
-version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
-
 [[package]]
 name = "markup5ever"
-version = "0.14.1"
+version = "0.39.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7a7213d12e1864c0f002f52c2923d4556935a43dec5e71355c2760e0f6e7a18"
+checksum = "7122d987ec5f704ee56f6e5b41a7d93722e9aae27ae07cafa4036c4d3f9757de"
 dependencies = [
  "log",
- "phf",
- "phf_codegen",
- "string_cache",
- "string_cache_codegen",
  "tendril",
-]
-
-[[package]]
-name = "match_token"
-version = "0.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88a9689d8d44bf9964484516275f5cd4c9b59457a6940c1d5d0ecbb94510a36b"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
+ "web_atoms",
 ]
 
 [[package]]
@@ -2160,7 +2128,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
 dependencies = [
  "phf_macros",
- "phf_shared",
+ "phf_shared 0.11.3",
+]
+
+[[package]]
+name = "phf"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1562dc717473dbaa4c1f85a36410e03c047b2e7df7f45ee938fbef64ae7fadf"
+dependencies = [
+ "phf_shared 0.13.1",
+ "serde",
 ]
 
 [[package]]
@@ -2169,8 +2147,18 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aef8048c789fa5e851558d709946d6d79a8ff88c0440c587967f8e94bfb1216a"
 dependencies = [
- "phf_generator",
- "phf_shared",
+ "phf_generator 0.11.3",
+ "phf_shared 0.11.3",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
+dependencies = [
+ "phf_generator 0.13.1",
+ "phf_shared 0.13.1",
 ]
 
 [[package]]
@@ -2179,18 +2167,28 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
 dependencies = [
- "phf_shared",
+ "phf_shared 0.11.3",
  "rand 0.8.6",
 ]
 
+[[package]]
+name = "phf_generator"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "135ace3a761e564ec88c03a77317a7c6b80bb7f7135ef2544dbe054243b89737"
+dependencies = [
+ "fastrand",
+ "phf_shared 0.13.1",
+]
+
 [[package]]
 name = "phf_macros"
 version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
 dependencies = [
- "phf_generator",
- "phf_shared",
+ "phf_generator 0.11.3",
+ "phf_shared 0.11.3",
  "proc-macro2",
  "quote",
  "syn",
@@ -2205,6 +2203,15 @@ dependencies = [
  "siphasher",
 ]
 
+[[package]]
+name = "phf_shared"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e57fef6bc5981e38c2ce2d63bfa546861309f875b8a75f092d1d54ae2d64f266"
+dependencies = [
+ "siphasher",
+]
+
 [[package]]
 name = "pico-args"
 version = "0.5.0"
@@ -2783,8 +2790,8 @@ dependencies = [
  "fxhash",
  "log",
  "new_debug_unreachable",
- "phf",
- "phf_codegen",
+ "phf 0.11.3",
+ "phf_codegen 0.11.3",
  "precomputed-hash",
  "servo_arc",
  "smallvec",
@@ -3043,25 +3050,24 @@ dependencies = [
 
 [[package]]
 name = "string_cache"
-version = "0.8.9"
+version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf776ba3fa74f83bf4b63c3dcbbf82173db2632ed8452cb2d891d33f459de70f"
+checksum = "a18596f8c785a729f2819c0f6a7eae6ebeebdfffbfe4214ae6b087f690e31901"
 dependencies = [
  "new_debug_unreachable",
  "parking_lot",
- "phf_shared",
+ "phf_shared 0.13.1",
  "precomputed-hash",
- "serde",
 ]
 
 [[package]]
 name = "string_cache_codegen"
-version = "0.5.4"
+version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c711928715f1fe0fe509c53b43e993a9a557babc2d0a3567d0a3006f1ac931a0"
+checksum = "585635e46db231059f76c5849798146164652513eb9e8ab2685939dd90f29b69"
 dependencies = [
- "phf_generator",
- "phf_shared",
+ "phf_generator 0.13.1",
+ "phf_shared 0.13.1",
  "proc-macro2",
  "quote",
 ]
@@ -3217,13 +3223,11 @@ dependencies = [
 
 [[package]]
 name = "tendril"
-version = "0.4.3"
+version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
+checksum = "5fed54709c5b3a53d09bb1c113ea4f5ceafd1e772ddcb0030a82e1d56c087b08"
 dependencies = [
- "futf",
- "mac",
- "utf-8",
+ "new_debug_unreachable",
 ]
 
 [[package]]
@@ -3976,6 +3980,18 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "web_atoms"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "075474b12bcb3d2e3d4546580e9de478eeeead668a1761e2a8860c836b7ef297"
+dependencies = [
+ "phf 0.13.1",
+ "phf_codegen 0.13.1",
+ "string_cache",
+ "string_cache_codegen",
+]
+
 [[package]]
 name = "webpki-root-certs"
 version = "1.0.7"

Cargo.toml

@@ -27,8 +27,8 @@ obscura-js = { path = "crates/obscura-js" }
 obscura-mcp = { path = "crates/obscura-mcp" }
 obscura-render = { path = "crates/obscura-render" }
 
-html5ever = "0.29"
-markup5ever = "0.14"
+html5ever = "0.39"
+markup5ever = "0.39"
 selectors = "0.26"
 servo_arc = "0.4"
 cssparser = "0.34"

crates/obscura-dom/src/tree_sink.rs

@@ -275,7 +275,11 @@ pub fn parse_fragment_with_context(html: &str, context_name: QualName) -> DomTre
     use html5ever::tendril::TendrilSink;
     use html5ever::{parse_fragment, ParseOpts};
     let tree = DomTree::new();
-    parse_fragment(tree, ParseOpts::default(), context_name, vec![])
+    // Obscura's fragment parser backs innerHTML in a scripting-enabled
+    // document. html5ever 0.39 makes that context flag explicit; keeping it
+    // true preserves browser parsing for context-sensitive content such as
+    // <noscript>.
+    parse_fragment(tree, ParseOpts::default(), context_name, vec![], true)
         .from_utf8()
         .one(html.as_bytes())
 }

crates/obscura-js/src/lib.rs

@@ -1,6 +1,3 @@
-#[macro_use]
-extern crate html5ever;
-
 pub mod cdp_watchdog;
 pub mod module_loader;
 pub mod runtime;