css_ast 0.0.31

pub use css_lexer::AtomSet;
use derive_atom_set::AtomSet as DeriveAtomSet;

/// Every label in the [Encoding Standard], matched ASCII case-insensitively.
///
/// A label names an encoding, and an encoding has several labels. [EncodingLabel::compact] gives
/// the shortest label of an encoding, so compare compacted labels to compare encodings.
///
/// Variant names spell their label with `-` written as `_`. The labels that hold `_`, `.` or
/// `:` cannot be spelled that way, so they mangle those bytes to `_u_`, `_d_` and `_c_` and
/// carry an explicit `#[atom]`.
///
/// [Encoding Standard]: https://encoding.spec.whatwg.org/#names-and-labels
#[allow(non_camel_case_types)]
#[derive(DeriveAtomSet, Debug, Default, Copy, Clone, PartialEq, Eq)]
pub enum EncodingLabel {
	#[default]
	Unknown,

	_866,
	#[atom("ansi_x3.4-1968")]
	Ansi_u_x3_d_4_1968,
	Arabic,
	Ascii,
	Asmo_708,
	Big5,
	Big5_hkscs,
	Chinese,
	Cn_big5,
	Cp1250,
	Cp1251,
	Cp1252,
	Cp1253,
	Cp1254,
	Cp1255,
	Cp1256,
	Cp1257,
	Cp1258,
	Cp819,
	Cp866,
	Csbig5,
	Cseuckr,
	Cseucpkdfmtjapanese,
	Csgb2312,
	Csibm866,
	Csiso2022jp,
	Csiso2022kr,
	Csiso58gb231280,
	Csiso88596e,
	Csiso88596i,
	Csiso88598e,
	Csiso88598i,
	Csisolatin1,
	Csisolatin2,
	Csisolatin3,
	Csisolatin4,
	Csisolatin5,
	Csisolatin6,
	Csisolatin9,
	Csisolatinarabic,
	Csisolatincyrillic,
	Csisolatingreek,
	Csisolatinhebrew,
	Cskoi8r,
	Csksc56011987,
	Csmacintosh,
	Csshiftjis,
	Csunicode,
	Cyrillic,
	Dos_874,
	Ecma_114,
	Ecma_118,
	#[atom("elot_928")]
	Elot_u_928,
	Euc_jp,
	Euc_kr,
	Gb18030,
	Gb2312,
	#[atom("gb_2312")]
	Gb_u_2312,
	#[atom("gb_2312-80")]
	Gb_u_2312_80,
	Gbk,
	Greek,
	Greek8,
	Hebrew,
	Hz_gb_2312,
	Ibm819,
	Ibm866,
	Iso_10646_ucs_2,
	Iso_2022_cn,
	Iso_2022_cn_ext,
	Iso_2022_jp,
	Iso_2022_kr,
	Iso_8859_1,
	Iso_8859_10,
	Iso_8859_11,
	Iso_8859_13,
	Iso_8859_14,
	Iso_8859_15,
	Iso_8859_16,
	Iso_8859_2,
	Iso_8859_3,
	Iso_8859_4,
	Iso_8859_5,
	Iso_8859_6,
	Iso_8859_6_e,
	Iso_8859_6_i,
	Iso_8859_7,
	Iso_8859_8,
	Iso_8859_8_e,
	Iso_8859_8_i,
	Iso_8859_9,
	Iso_ir_100,
	Iso_ir_101,
	Iso_ir_109,
	Iso_ir_110,
	Iso_ir_126,
	Iso_ir_127,
	Iso_ir_138,
	Iso_ir_144,
	Iso_ir_148,
	Iso_ir_149,
	Iso_ir_157,
	Iso_ir_58,
	Iso8859_1,
	Iso8859_10,
	Iso8859_11,
	Iso8859_13,
	Iso8859_14,
	Iso8859_15,
	Iso8859_2,
	Iso8859_3,
	Iso8859_4,
	Iso8859_5,
	Iso8859_6,
	Iso8859_7,
	Iso8859_8,
	Iso8859_9,
	Iso88591,
	Iso885910,
	Iso885911,
	Iso885913,
	Iso885914,
	Iso885915,
	Iso88592,
	Iso88593,
	Iso88594,
	Iso88595,
	Iso88596,
	Iso88597,
	Iso88598,
	Iso88599,
	#[atom("iso_8859-1")]
	Iso_u_8859_1,
	#[atom("iso_8859-15")]
	Iso_u_8859_15,
	#[atom("iso_8859-1:1987")]
	Iso_u_8859_1_c_1987,
	#[atom("iso_8859-2")]
	Iso_u_8859_2,
	#[atom("iso_8859-2:1987")]
	Iso_u_8859_2_c_1987,
	#[atom("iso_8859-3")]
	Iso_u_8859_3,
	#[atom("iso_8859-3:1988")]
	Iso_u_8859_3_c_1988,
	#[atom("iso_8859-4")]
	Iso_u_8859_4,
	#[atom("iso_8859-4:1988")]
	Iso_u_8859_4_c_1988,
	#[atom("iso_8859-5")]
	Iso_u_8859_5,
	#[atom("iso_8859-5:1988")]
	Iso_u_8859_5_c_1988,
	#[atom("iso_8859-6")]
	Iso_u_8859_6,
	#[atom("iso_8859-6:1987")]
	Iso_u_8859_6_c_1987,
	#[atom("iso_8859-7")]
	Iso_u_8859_7,
	#[atom("iso_8859-7:1987")]
	Iso_u_8859_7_c_1987,
	#[atom("iso_8859-8")]
	Iso_u_8859_8,
	#[atom("iso_8859-8:1988")]
	Iso_u_8859_8_c_1988,
	#[atom("iso_8859-9")]
	Iso_u_8859_9,
	#[atom("iso_8859-9:1989")]
	Iso_u_8859_9_c_1989,
	Koi,
	Koi8,
	Koi8_r,
	Koi8_ru,
	Koi8_u,
	#[atom("koi8_r")]
	Koi8_u_r,
	Korean,
	#[atom("ks_c_5601-1987")]
	Ks_u_c_u_5601_1987,
	#[atom("ks_c_5601-1989")]
	Ks_u_c_u_5601_1989,
	Ksc5601,
	#[atom("ksc_5601")]
	Ksc_u_5601,
	L1,
	L2,
	L3,
	L4,
	L5,
	L6,
	L9,
	Latin1,
	Latin2,
	Latin3,
	Latin4,
	Latin5,
	Latin6,
	Logical,
	Mac,
	Macintosh,
	Ms932,
	#[atom("ms_kanji")]
	Ms_u_kanji,
	Replacement,
	Shift_jis,
	#[atom("shift_jis")]
	Shift_u_jis,
	Sjis,
	#[atom("sun_eu_greek")]
	Sun_u_eu_u_greek,
	Tis_620,
	Ucs_2,
	Unicode,
	Unicode_1_1_utf_8,
	Unicode11utf8,
	Unicode20utf8,
	Unicodefeff,
	Unicodefffe,
	Us_ascii,
	Utf_16,
	Utf_16be,
	Utf_16le,
	Utf_8,
	Utf8,
	Visual,
	Windows_1250,
	Windows_1251,
	Windows_1252,
	Windows_1253,
	Windows_1254,
	Windows_1255,
	Windows_1256,
	Windows_1257,
	Windows_1258,
	Windows_31j,
	Windows_874,
	Windows_949,
	X_cp1250,
	X_cp1251,
	X_cp1252,
	X_cp1253,
	X_cp1254,
	X_cp1255,
	X_cp1256,
	X_cp1257,
	X_cp1258,
	X_euc_jp,
	X_gbk,
	X_mac_cyrillic,
	X_mac_roman,
	X_mac_ukrainian,
	X_sjis,
	X_unicode20utf8,
	X_user_defined,
	X_x_big5,
}

impl EncodingLabel {
	/// The shortest label naming the same encoding as each variant, indexed by discriminant.
	const COMPACT: [Self; 229] = [
		Self::Unknown,
		Self::_866,
		Self::L1,
		Self::Arabic,
		Self::L1,
		Self::Arabic,
		Self::Big5,
		Self::Big5,
		Self::Gbk,
		Self::Big5,
		Self::Cp1250,
		Self::Cp1251,
		Self::L1,
		Self::Cp1253,
		Self::L5,
		Self::Cp1255,
		Self::Cp1256,
		Self::Cp1257,
		Self::Cp1258,
		Self::L1,
		Self::_866,
		Self::Big5,
		Self::Euc_kr,
		Self::Euc_jp,
		Self::Gbk,
		Self::_866,
		Self::Csiso2022jp,
		Self::Hz_gb_2312,
		Self::Gbk,
		Self::Arabic,
		Self::Arabic,
		Self::Hebrew,
		Self::Logical,
		Self::L1,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::L5,
		Self::L6,
		Self::L9,
		Self::Arabic,
		Self::Cyrillic,
		Self::Greek,
		Self::Hebrew,
		Self::Koi,
		Self::Euc_kr,
		Self::Mac,
		Self::Sjis,
		Self::Unknown,
		Self::Cyrillic,
		Self::Dos_874,
		Self::Arabic,
		Self::Greek,
		Self::Greek,
		Self::Euc_jp,
		Self::Euc_kr,
		Self::Gb18030,
		Self::Gbk,
		Self::Gbk,
		Self::Gbk,
		Self::Gbk,
		Self::Greek,
		Self::Greek,
		Self::Hebrew,
		Self::Hz_gb_2312,
		Self::L1,
		Self::_866,
		Self::Unknown,
		Self::Hz_gb_2312,
		Self::Hz_gb_2312,
		Self::Csiso2022jp,
		Self::Hz_gb_2312,
		Self::L1,
		Self::L6,
		Self::Dos_874,
		Self::Iso885913,
		Self::Iso885914,
		Self::L9,
		Self::Iso_8859_16,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::Cyrillic,
		Self::Arabic,
		Self::Arabic,
		Self::Arabic,
		Self::Greek,
		Self::Hebrew,
		Self::Hebrew,
		Self::Logical,
		Self::L5,
		Self::L1,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::Greek,
		Self::Arabic,
		Self::Hebrew,
		Self::Cyrillic,
		Self::L5,
		Self::Euc_kr,
		Self::L6,
		Self::Gbk,
		Self::L1,
		Self::L6,
		Self::Dos_874,
		Self::Iso885913,
		Self::Iso885914,
		Self::L9,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::Cyrillic,
		Self::Arabic,
		Self::Greek,
		Self::Hebrew,
		Self::L5,
		Self::L1,
		Self::L6,
		Self::Dos_874,
		Self::Iso885913,
		Self::Iso885914,
		Self::L9,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::Cyrillic,
		Self::Arabic,
		Self::Greek,
		Self::Hebrew,
		Self::L5,
		Self::L1,
		Self::L9,
		Self::L1,
		Self::L2,
		Self::L2,
		Self::L3,
		Self::L3,
		Self::L4,
		Self::L4,
		Self::Cyrillic,
		Self::Cyrillic,
		Self::Arabic,
		Self::Arabic,
		Self::Greek,
		Self::Greek,
		Self::Hebrew,
		Self::Hebrew,
		Self::L5,
		Self::L5,
		Self::Koi,
		Self::Koi,
		Self::Koi,
		Self::Koi8_u,
		Self::Koi8_u,
		Self::Koi,
		Self::Euc_kr,
		Self::Euc_kr,
		Self::Euc_kr,
		Self::Euc_kr,
		Self::Euc_kr,
		Self::L1,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::L5,
		Self::L6,
		Self::L9,
		Self::L1,
		Self::L2,
		Self::L3,
		Self::L4,
		Self::L5,
		Self::L6,
		Self::Logical,
		Self::Mac,
		Self::Mac,
		Self::Sjis,
		Self::Sjis,
		Self::Hz_gb_2312,
		Self::Sjis,
		Self::Sjis,
		Self::Sjis,
		Self::Greek,
		Self::Dos_874,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::L1,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Unknown,
		Self::Hebrew,
		Self::Cp1250,
		Self::Cp1251,
		Self::L1,
		Self::Cp1253,
		Self::L5,
		Self::Cp1255,
		Self::Cp1256,
		Self::Cp1257,
		Self::Cp1258,
		Self::Sjis,
		Self::Dos_874,
		Self::Euc_kr,
		Self::Cp1250,
		Self::Cp1251,
		Self::L1,
		Self::Cp1253,
		Self::L5,
		Self::Cp1255,
		Self::Cp1256,
		Self::Cp1257,
		Self::Cp1258,
		Self::Euc_jp,
		Self::Gbk,
		Self::X_mac_cyrillic,
		Self::Mac,
		Self::X_mac_cyrillic,
		Self::Sjis,
		Self::Unknown,
		Self::X_user_defined,
		Self::Big5,
	];

	/// Gives the label for `label`, as [get an encoding] does: remove leading and trailing ASCII
	/// whitespace, then match ASCII case-insensitively.
	///
	/// [get an encoding]: https://encoding.spec.whatwg.org/#concept-encoding-get
	///
	/// ```rust
	/// # use css_ast::{AtomSet, EncodingLabel};
	/// assert_eq!(EncodingLabel::from_label(" \tGBK\n").to_str(), "gbk");
	/// assert_eq!(EncodingLabel::from_label("not-a-charset"), EncodingLabel::Unknown);
	/// ```
	pub fn from_label(label: &str) -> Self {
		Self::from_str(label.trim_matches(|c| matches!(c, '\t' | '\n' | '\x0C' | '\r' | ' ')))
	}

	/// Gives the shortest label naming the same encoding, or itself when it is already the shortest.
	///
	/// Gives [EncodingLabel::Unknown] for a label a `@charset` rule gains nothing from: an unknown
	/// label, and the labels of encodings that [determining the fallback encoding] resolves to UTF-8.
	/// Such a rule has no effect and you can remove it.
	///
	/// [determining the fallback encoding]: https://drafts.csswg.org/css-syntax-3/#determine-the-fallback-encoding
	///
	/// ```rust
	/// # use css_ast::{AtomSet, EncodingLabel};
	/// assert_eq!(EncodingLabel::from_label("ISO-8859-1").compact().to_str(), "l1");
	/// assert_eq!(EncodingLabel::from_label("gbk").compact().to_str(), "gbk");
	/// assert_eq!(EncodingLabel::from_label("utf-16").compact(), EncodingLabel::Unknown);
	/// ```
	pub fn compact(self) -> Self {
		Self::COMPACT[self as usize]
	}
}

#[cfg(test)]
mod tests {
	use super::{AtomSet, EncodingLabel};

	/// Every label, in [EncodingLabel] declaration order.
	const ALL_LABELS: [&str; 228] = [
		"866",
		"ansi_x3.4-1968",
		"arabic",
		"ascii",
		"asmo-708",
		"big5",
		"big5-hkscs",
		"chinese",
		"cn-big5",
		"cp1250",
		"cp1251",
		"cp1252",
		"cp1253",
		"cp1254",
		"cp1255",
		"cp1256",
		"cp1257",
		"cp1258",
		"cp819",
		"cp866",
		"csbig5",
		"cseuckr",
		"cseucpkdfmtjapanese",
		"csgb2312",
		"csibm866",
		"csiso2022jp",
		"csiso2022kr",
		"csiso58gb231280",
		"csiso88596e",
		"csiso88596i",
		"csiso88598e",
		"csiso88598i",
		"csisolatin1",
		"csisolatin2",
		"csisolatin3",
		"csisolatin4",
		"csisolatin5",
		"csisolatin6",
		"csisolatin9",
		"csisolatinarabic",
		"csisolatincyrillic",
		"csisolatingreek",
		"csisolatinhebrew",
		"cskoi8r",
		"csksc56011987",
		"csmacintosh",
		"csshiftjis",
		"csunicode",
		"cyrillic",
		"dos-874",
		"ecma-114",
		"ecma-118",
		"elot_928",
		"euc-jp",
		"euc-kr",
		"gb18030",
		"gb2312",
		"gb_2312",
		"gb_2312-80",
		"gbk",
		"greek",
		"greek8",
		"hebrew",
		"hz-gb-2312",
		"ibm819",
		"ibm866",
		"iso-10646-ucs-2",
		"iso-2022-cn",
		"iso-2022-cn-ext",
		"iso-2022-jp",
		"iso-2022-kr",
		"iso-8859-1",
		"iso-8859-10",
		"iso-8859-11",
		"iso-8859-13",
		"iso-8859-14",
		"iso-8859-15",
		"iso-8859-16",
		"iso-8859-2",
		"iso-8859-3",
		"iso-8859-4",
		"iso-8859-5",
		"iso-8859-6",
		"iso-8859-6-e",
		"iso-8859-6-i",
		"iso-8859-7",
		"iso-8859-8",
		"iso-8859-8-e",
		"iso-8859-8-i",
		"iso-8859-9",
		"iso-ir-100",
		"iso-ir-101",
		"iso-ir-109",
		"iso-ir-110",
		"iso-ir-126",
		"iso-ir-127",
		"iso-ir-138",
		"iso-ir-144",
		"iso-ir-148",
		"iso-ir-149",
		"iso-ir-157",
		"iso-ir-58",
		"iso8859-1",
		"iso8859-10",
		"iso8859-11",
		"iso8859-13",
		"iso8859-14",
		"iso8859-15",
		"iso8859-2",
		"iso8859-3",
		"iso8859-4",
		"iso8859-5",
		"iso8859-6",
		"iso8859-7",
		"iso8859-8",
		"iso8859-9",
		"iso88591",
		"iso885910",
		"iso885911",
		"iso885913",
		"iso885914",
		"iso885915",
		"iso88592",
		"iso88593",
		"iso88594",
		"iso88595",
		"iso88596",
		"iso88597",
		"iso88598",
		"iso88599",
		"iso_8859-1",
		"iso_8859-15",
		"iso_8859-1:1987",
		"iso_8859-2",
		"iso_8859-2:1987",
		"iso_8859-3",
		"iso_8859-3:1988",
		"iso_8859-4",
		"iso_8859-4:1988",
		"iso_8859-5",
		"iso_8859-5:1988",
		"iso_8859-6",
		"iso_8859-6:1987",
		"iso_8859-7",
		"iso_8859-7:1987",
		"iso_8859-8",
		"iso_8859-8:1988",
		"iso_8859-9",
		"iso_8859-9:1989",
		"koi",
		"koi8",
		"koi8-r",
		"koi8-ru",
		"koi8-u",
		"koi8_r",
		"korean",
		"ks_c_5601-1987",
		"ks_c_5601-1989",
		"ksc5601",
		"ksc_5601",
		"l1",
		"l2",
		"l3",
		"l4",
		"l5",
		"l6",
		"l9",
		"latin1",
		"latin2",
		"latin3",
		"latin4",
		"latin5",
		"latin6",
		"logical",
		"mac",
		"macintosh",
		"ms932",
		"ms_kanji",
		"replacement",
		"shift-jis",
		"shift_jis",
		"sjis",
		"sun_eu_greek",
		"tis-620",
		"ucs-2",
		"unicode",
		"unicode-1-1-utf-8",
		"unicode11utf8",
		"unicode20utf8",
		"unicodefeff",
		"unicodefffe",
		"us-ascii",
		"utf-16",
		"utf-16be",
		"utf-16le",
		"utf-8",
		"utf8",
		"visual",
		"windows-1250",
		"windows-1251",
		"windows-1252",
		"windows-1253",
		"windows-1254",
		"windows-1255",
		"windows-1256",
		"windows-1257",
		"windows-1258",
		"windows-31j",
		"windows-874",
		"windows-949",
		"x-cp1250",
		"x-cp1251",
		"x-cp1252",
		"x-cp1253",
		"x-cp1254",
		"x-cp1255",
		"x-cp1256",
		"x-cp1257",
		"x-cp1258",
		"x-euc-jp",
		"x-gbk",
		"x-mac-cyrillic",
		"x-mac-roman",
		"x-mac-ukrainian",
		"x-sjis",
		"x-unicode20utf8",
		"x-user-defined",
		"x-x-big5",
	];

	#[test]
	fn every_label_resolves_to_its_own_variant() {
		for (i, label) in ALL_LABELS.iter().enumerate() {
			assert_eq!(
				EncodingLabel::from_label(label).as_bits() as usize,
				i + 1,
				"{label} did not resolve to its own variant",
			);
		}
	}

	#[test]
	fn compact_is_idempotent() {
		for label in EncodingLabel::COMPACT {
			assert_eq!(label.compact(), label, "{} is not its own shortest label", label.to_str());
		}
	}

	#[test]
	fn compact_never_lengthens_a_label() {
		for label in ALL_LABELS.iter().map(|l| EncodingLabel::from_label(l)) {
			let compact = label.compact();
			if compact != EncodingLabel::Unknown {
				assert!(compact.len() <= label.len(), "{} is longer than {}", compact.to_str(), label.to_str());
			}
		}
	}

	#[test]
	fn shortens_windows_1252_aliases() {
		assert_eq!(EncodingLabel::from_label("ISO-8859-1").compact().to_str(), "l1");
		assert_eq!(EncodingLabel::from_label("us-ascii").compact().to_str(), "l1");
		assert_eq!(EncodingLabel::from_label("l1").compact().to_str(), "l1");
	}

	#[test]
	fn separators_are_significant() {
		assert_eq!(EncodingLabel::from_label("iso_8859-15").compact().to_str(), "l9");
		assert_eq!(EncodingLabel::from_label("iso8859-15").compact().to_str(), "l9");
		assert_eq!(EncodingLabel::from_label("iso-8859-15").compact().to_str(), "l9");
		assert_eq!(EncodingLabel::from_label("iso-8859_15"), EncodingLabel::Unknown);
	}

	#[test]
	fn drops_utf8_and_utf16_labels() {
		assert_eq!(EncodingLabel::from_label("UTF-8").compact(), EncodingLabel::Unknown);
		assert_eq!(EncodingLabel::from_label("utf-16").compact(), EncodingLabel::Unknown);
		assert_eq!(EncodingLabel::from_label("utf-16be").compact(), EncodingLabel::Unknown);
		assert_eq!(EncodingLabel::from_label("unicode-1-1-utf-8").compact(), EncodingLabel::Unknown);
	}

	#[test]
	fn drops_unknown_labels() {
		assert_eq!(EncodingLabel::from_label("not-a-charset"), EncodingLabel::Unknown);
		assert_eq!(EncodingLabel::from_label(""), EncodingLabel::Unknown);
		assert_eq!(EncodingLabel::from_label("a-label-far-longer-than-any-real-one"), EncodingLabel::Unknown);
	}
}