Auto merge of #15552 - servo:cssparserup, r=nox

Update cssparser to 0.9

<!-- Please describe your changes on the following line: -->

---
<!-- Thank you for contributing to Servo! Please replace each `[ ]` by `[X]` when the step is complete, and replace `__` with appropriate data: -->
- [x] `./mach build -d` does not report any errors
- [x] `./mach test-tidy` does not report any errors
- [ ] These changes fix #__ (github issue number if applicable).

<!-- Either: -->
- [ ] There are tests for these changes OR
- [ ] These changes do not require tests because _____

<!-- Pull requests that do not address these steps are welcome, but they will require additional verification as part of the review process. -->

<!-- Reviewable:start -->
---
This change is [<img src="https://reviewable.io/review_button.svg" height="34" align="absmiddle" alt="Reviewable"/>](https://reviewable.io/reviews/servo/servo/15552)
<!-- Reviewable:end -->

components/canvas/Cargo.toml

@@ -12,7 +12,7 @@ path = "lib.rs"
 [dependencies]
 azure = {git = "https://github.com/servo/rust-azure", features = ["plugins"]}
 canvas_traits = {path = "../canvas_traits"}
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 euclid = "0.10.1"
 gleam = "0.2.8"
 ipc-channel = "0.5"

components/canvas_traits/Cargo.toml

@@ -10,7 +10,7 @@ name = "canvas_traits"
 path = "lib.rs"
 
 [dependencies]
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 euclid = "0.10.1"
 heapsize = "0.3.0"
 heapsize_derive = "0.1"

components/layout/Cargo.toml

@@ -14,7 +14,7 @@ app_units = "0.3"
 atomic_refcell = "0.1"
 bitflags = "0.7"
 canvas_traits = {path = "../canvas_traits"}
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 euclid = "0.10.1"
 fnv = "1.0"
 gfx = {path = "../gfx"}

components/msg/Cargo.toml

@@ -11,7 +11,7 @@ path = "lib.rs"
 
 [dependencies]
 bitflags = "0.7"
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 heapsize = "0.3.0"
 heapsize_derive = "0.1"
 plugins = {path = "../plugins"}

components/script/Cargo.toml

@@ -34,7 +34,7 @@ byteorder = "1.0"
 canvas_traits = {path = "../canvas_traits"}
 caseless = "0.1.0"
 cookie = {version = "0.2.5", features = ["serialize-rustc"]}
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 deny_public_fields = {path = "../deny_public_fields"}
 devtools_traits = {path = "../devtools_traits"}
 domobject_derive = {path = "../domobject_derive"}

components/script_layout_interface/Cargo.toml

@@ -13,7 +13,7 @@ path = "lib.rs"
 app_units = "0.3"
 atomic_refcell = "0.1"
 canvas_traits = {path = "../canvas_traits"}
-cssparser = {version = "0.8", features = ["heap_size", "serde-serialization"]}
+cssparser = {version = "0.9", features = ["heap_size", "serde-serialization"]}
 euclid = "0.10.1"
 gfx_traits = {path = "../gfx_traits"}
 heapsize = "0.3.0"

components/selectors/Cargo.toml

@@ -18,5 +18,5 @@ path = "lib.rs"
 [dependencies]
 bitflags = "0.7"
 matches = "0.1"
-cssparser = ">=0.6, <0.9"
+cssparser = "0.9"
 fnv = "1.0"

components/style/Cargo.toml

@@ -26,7 +26,7 @@ app_units = "0.3"
 atomic_refcell = "0.1"
 bitflags = "0.7"
 cfg-if = "0.1.0"
-cssparser = "0.8"
+cssparser = "0.9"
 encoding = "0.2"
 euclid = "0.10.1"
 fnv = "1.0"

components/style/font_face.rs

@@ -12,6 +12,7 @@
 use computed_values::{font_style, font_weight, font_stretch};
 use computed_values::font_family::FamilyName;
 use cssparser::{AtRuleParser, DeclarationListParser, DeclarationParser, Parser};
+#[cfg(feature = "gecko")] use cssparser::UnicodeRange;
 use parser::{ParserContext, log_css_error, Parse};
 use std::fmt;
 use std::iter;
@@ -238,7 +239,7 @@ macro_rules! font_face_descriptors {
                 dest.write_str("@font-face {\n")?;
                 $(
                     dest.write_str(concat!("  ", $m_name, ": "))?;
-                    self.$m_ident.to_css(dest)?;
+                    ToCss::to_css(&self.$m_ident, dest)?;
                     dest.write_str(";\n")?;
                 )*
                 $(
@@ -247,7 +248,7 @@ macro_rules! font_face_descriptors {
                     // But it can be false for other descriptors.
                     if self.$o_ident != $o_initial {
                         dest.write_str(concat!("  ", $o_name, ": "))?;
-                        self.$o_ident.to_css(dest)?;
+                        ToCss::to_css(&self.$o_ident, dest)?;
                         dest.write_str(";\n")?;
                     }
                 )*
@@ -298,8 +299,8 @@ font_face_descriptors! {
         "font-stretch" stretch: font_stretch::T = font_stretch::T::normal,
 
         /// The ranges of code points outside of which this font face should not be used.
-        "unicode-range" unicode_range: Vec<unicode_range::Range> = vec![
-            unicode_range::Range { start: 0, end: unicode_range::MAX }
+        "unicode-range" unicode_range: Vec<UnicodeRange> = vec![
+            UnicodeRange { start: 0, end: 0x10FFFF }
         ],
     ]
 }
@@ -316,51 +317,3 @@ font_face_descriptors! {
     optional descriptors = [
     ]
 }
-
-/// https://drafts.csswg.org/css-fonts/#unicode-range-desc
-#[cfg(feature = "gecko")]
-pub mod unicode_range {
-    use cssparser::{Parser, Token};
-    use parser::{ParserContext, Parse};
-    use std::fmt;
-    use style_traits::{ToCss, OneOrMoreCommaSeparated};
-
-    /// Maximum value of the end of a range
-    pub const MAX: u32 = ::std::char::MAX as u32;
-
-    /// A single range: https://drafts.csswg.org/css-fonts/#urange-value
-    #[derive(Debug, PartialEq, Eq)]
-    pub struct Range {
-        /// Start of the range, inclusive
-        pub start: u32,
-
-        /// End of the range, inclusive
-        pub end: u32,
-    }
-
-    impl OneOrMoreCommaSeparated for Range {}
-
-    impl Parse for Range {
-        fn parse(_context: &ParserContext, input: &mut Parser) -> Result<Self, ()> {
-            // FIXME: The unicode-range token has been removed from the CSS Syntax spec,
-            // cssparser should be updated accordingly
-            // and implement https://drafts.csswg.org/css-syntax/#urange instead
-            match input.next() {
-                Ok(Token::UnicodeRange(start, end)) => {
-                    if end <= MAX && start <= end {
-                        Ok(Range { start: start, end: end })
-                    } else {
-                        Err(())
-                    }
-                }
-                _ => Err(())
-            }
-        }
-    }
-
-    impl ToCss for Range {
-        fn to_css<W>(&self, dest: &mut W) -> fmt::Result where W: fmt::Write {
-            Token::UnicodeRange(self.start, self.end).to_css(dest)
-        }
-    }
-}

components/style/parser.rs

@@ -6,7 +6,7 @@
 
 #![deny(missing_docs)]
 
-use cssparser::{Parser, SourcePosition};
+use cssparser::{Parser, SourcePosition, UnicodeRange};
 use error_reporting::ParseErrorReporter;
 #[cfg(feature = "gecko")]
 use gecko_bindings::sugar::refptr::{GeckoArcPrincipal, GeckoArcURI};
@@ -109,3 +109,9 @@ impl<T> Parse for Vec<T> where T: Parse + OneOrMoreCommaSeparated {
         input.parse_comma_separated(|input| T::parse(context, input))
     }
 }
+
+impl Parse for UnicodeRange {
+    fn parse(_context: &ParserContext, input: &mut Parser) -> Result<Self, ()> {
+        UnicodeRange::parse(input)
+    }
+}

components/style/stylesheets.rs

@@ -7,10 +7,10 @@
 #![deny(missing_docs)]
 
 use {Atom, Prefix, Namespace};
-use cssparser::{AtRuleParser, Parser, QualifiedRuleParser, decode_stylesheet_bytes};
+use cssparser::{AtRuleParser, Parser, QualifiedRuleParser, stylesheet_encoding, EncodingSupport};
 use cssparser::{AtRuleType, RuleListParser, SourcePosition, Token, parse_one_rule};
 use cssparser::ToCss as ParserToCss;
-use encoding::EncodingRef;
+use encoding::{self, EncodingRef, DecoderTrap};
 use error_reporting::ParseErrorReporter;
 use font_face::{FontFaceRule, parse_font_face_block};
 use keyframes::{Keyframe, parse_keyframe_list};
@@ -24,6 +24,7 @@ use servo_config::prefs::PREFS;
 use servo_url::ServoUrl;
 use std::cell::Cell;
 use std::fmt;
+use std::str;
 use std::sync::Arc;
 use std::sync::atomic::{AtomicBool, Ordering};
 use style_traits::ToCss;
@@ -543,6 +544,33 @@ impl ToCss for StyleRule {
     }
 }
 
+struct RustEncoding;
+
+impl EncodingSupport for RustEncoding {
+    type Encoding = EncodingRef;
+
+    fn utf8() -> Self::Encoding {
+        encoding::all::UTF_8
+    }
+
+    fn is_utf16_be_or_le(encoding: &Self::Encoding) -> bool {
+        matches!(encoding.name(), "utf-16be" | "utf-16le")
+    }
+
+    fn from_label(ascii_label: &[u8]) -> Option<Self::Encoding> {
+        str::from_utf8(ascii_label).ok().and_then(encoding::label::encoding_from_whatwg_label)
+    }
+}
+
+fn decode_stylesheet_bytes(css: &[u8], protocol_encoding_label: Option<&str>,
+                           environment_encoding: Option<EncodingRef>)
+                           -> (String, EncodingRef) {
+    let fallback_encoding = stylesheet_encoding::<RustEncoding>(
+        css, protocol_encoding_label.map(str::as_bytes), environment_encoding);
+    let (result, used_encoding) = encoding::decode(css, DecoderTrap::Replace, fallback_encoding);
+    (result.unwrap(), used_encoding)
+}
+
 impl Stylesheet {
     /// Parse a stylesheet from a set of bytes, potentially received over the
     /// network.

components/style_traits/Cargo.toml

@@ -15,7 +15,7 @@ servo = ["heapsize", "heapsize_derive", "serde", "serde_derive",
 
 [dependencies]
 app_units = "0.3"
-cssparser = "0.8"
+cssparser = "0.9"
 euclid = "0.10.1"
 heapsize = {version = "0.3.0", optional = true}
 heapsize_derive = {version = "0.1", optional = true}

components/style_traits/values.rs

@@ -5,6 +5,7 @@
 //! Helper types and traits for the handling of CSS values.
 
 use app_units::Au;
+use cssparser::UnicodeRange;
 use std::fmt;
 
 /// The real `ToCss` trait can't be implemented for types in crates that don't
@@ -27,6 +28,8 @@ pub trait ToCss {
 /// Marker trait to automatically implement ToCss for Vec<T>.
 pub trait OneOrMoreCommaSeparated {}
 
+impl OneOrMoreCommaSeparated for UnicodeRange {}
+
 impl<T> ToCss for Vec<T> where T: ToCss + OneOrMoreCommaSeparated {
     fn to_css<W>(&self, dest: &mut W) -> fmt::Result where W: fmt::Write {
         let mut iter = self.iter();
@@ -69,6 +72,7 @@ impl_to_css_for_predefined_type!(u32);
 impl_to_css_for_predefined_type!(::cssparser::Token<'a>);
 impl_to_css_for_predefined_type!(::cssparser::RGBA);
 impl_to_css_for_predefined_type!(::cssparser::Color);
+impl_to_css_for_predefined_type!(::cssparser::UnicodeRange);
 
 #[macro_export]
 macro_rules! define_css_keyword_enum {