Refactor to move more things to `util/`

6 files changed, 3292 insertions, 3 deletions

diff --git a/src/util/classify_character.rs b/src/util/classify_character.rs
index b938502..79ed46a 100644
--- a/src/util/classify_character.rs
+++ b/src/util/classify_character.rs
@@ -1,6 +1,6 @@
 //! Utilities to classify characters as whitespace, punctuation, or rest.
 
-use crate::unicode::PUNCTUATION;
+use crate::util::unicode::PUNCTUATION;
 
 /// Character kinds.
 #[derive(Debug, PartialEq, Eq)]
diff --git a/src/util/constant.rs b/src/util/constant.rs
new file mode 100644
index 0000000..0c82378
--- /dev/null
+++ b/src/util/constant.rs
@@ -0,0 +1,2449 @@
+//! Constants needed to parse markdown.
+//!
+//! Most of these constants are magic numbers, such as the number of markers
+//! needed to parse [code (fenced)][code_fenced]
+//! ([`CODE_FENCED_SEQUENCE_SIZE_MIN`][]) or the max number of allowed markers
+//! in a [heading (atx)][heading_atx]
+//! ([`HEADING_ATX_OPENING_FENCE_SIZE_MAX`][]).
+//!
+//! Some constants are instead lists of things, such as the list of tag names
+//! considered in the **raw** production of [HTML (flow)][html_flow]
+//! ([`HTML_RAW_NAMES`][]), or the list of named character references
+//! ([`CHARACTER_REFERENCES`][]).
+//!
+//! [code_fenced]: crate::construct::code_fenced
+//! [heading_atx]: crate::construct::heading_atx
+//! [html_flow]: crate::construct::html_flow
+
+/// The number of characters allowed in a protocol of an [autolink][].
+///
+/// The protocol part is the `xxx` in `<xxx://example.com>`.
+/// 32 characters is fine, 33 is too many.
+///
+/// [autolink]: crate::construct::autolink
+pub const AUTOLINK_SCHEME_SIZE_MAX: usize = 32;
+
+/// The number of characters allowed in a domain of an email [autolink][].
+///
+/// There can be multiple “domains”.
+/// A domain part is each `xxx` in `<example@xxx.xxx.xxx>`.
+/// 63 characters is fine, 64 is too many.
+///
+/// [autolink]: crate::construct::autolink
+pub const AUTOLINK_DOMAIN_SIZE_MAX: usize = 63;
+
+/// The max number of characters in a decimal numeric
+/// [character reference][character_reference].
+///
+/// To illustrate, this allows `&#9999999;` and disallows `&#99999990;`.
+/// This limit is imposed because all bigger numbers are invalid.
+///
+/// [character_reference]: crate::construct::character_reference
+pub const CHARACTER_REFERENCE_DECIMAL_SIZE_MAX: usize = 7;
+
+/// The max number of characters in a hexadecimal numeric
+/// [character reference][character_reference].
+///
+/// To illustrate, this allows `&#xff9999;` and disallows `&#xff99990;`.
+/// This limit is imposed because all bigger numbers are invalid.
+///
+/// [character_reference]: crate::construct::character_reference
+pub const CHARACTER_REFERENCE_HEXADECIMAL_SIZE_MAX: usize = 6;
+
+/// The max number of characters in a named
+/// [character reference][character_reference].
+///
+/// This is the number of the longest name in [`CHARACTER_REFERENCES`][].
+/// It allows `&CounterClockwiseContourIntegral;` and prevents the parser from
+/// continuing for eons.
+///
+/// [character_reference]: crate::construct::character_reference
+pub const CHARACTER_REFERENCE_NAMED_SIZE_MAX: usize = 31;
+
+/// The number of markers needed for [code (fenced)][code_fenced] to form.
+///
+/// Like many things in markdown, the number is `3`.
+///
+/// [code_fenced]: crate::construct::code_fenced
+pub const CODE_FENCED_SEQUENCE_SIZE_MIN: usize = 3;
+
+/// The number of markers needed for [frontmatter][] to form.
+///
+/// Like many things in markdown, the number is `3`.
+///
+/// [frontmatter]: crate::construct::frontmatter
+pub const FRONTMATTER_SEQUENCE_SIZE: usize = 3;
+
+/// The number of preceding spaces needed for a [hard break
+/// (trailing)][whitespace] to form.
+///
+/// [whitespace]: crate::construct::partial_whitespace
+pub const HARD_BREAK_PREFIX_SIZE_MIN: usize = 2;
+
+/// The max number of markers allowed to form a [heading (atx)][heading_atx].
+///
+/// This limitation is imposed by HTML, which imposes a max heading rank of
+/// `6`.
+///
+/// [heading_atx]: crate::construct::heading_atx
+pub const HEADING_ATX_OPENING_FENCE_SIZE_MAX: usize = 6;
+
+/// List of HTML tag names that form the **basic** production of
+/// [HTML (flow)][html_flow].
+///
+/// The **basic** production allows interleaving HTML and markdown with blank
+/// lines and allows flow (block) elements to interrupt definitions, paragraphs,
+/// and heading (setext).
+/// Tag name matching must be performed insensitive to case, and thus this list
+/// includes lowercase tag names.
+///
+/// Tag names not on this list result in the **complete** production.
+///
+/// > 👉 **Note**: `source` was removed on `main` of the `CommonMark` spec and
+/// > is slated to be released in `CommonMark@0.31`.
+///
+/// ## References
+///
+/// *   [*§ 4.6 HTML blocks* in `CommonMark`](https://spec.commonmark.org/0.30/#html-blocks)
+/// *   [*Remove source element as HTML block start condition* as `commonmark/commonmark-spec#710`](https://github.com/commonmark/commonmark-spec/pull/710)
+///
+/// [html_flow]: crate::construct::html_flow
+pub const HTML_BLOCK_NAMES: [&str; 61] = [
+    "address",
+    "article",
+    "aside",
+    "base",
+    "basefont",
+    "blockquote",
+    "body",
+    "caption",
+    "center",
+    "col",
+    "colgroup",
+    "dd",
+    "details",
+    "dialog",
+    "dir",
+    "div",
+    "dl",
+    "dt",
+    "fieldset",
+    "figcaption",
+    "figure",
+    "footer",
+    "form",
+    "frame",
+    "frameset",
+    "h1",
+    "h2",
+    "h3",
+    "h4",
+    "h5",
+    "h6",
+    "head",
+    "header",
+    "hr",
+    "html",
+    "iframe",
+    "legend",
+    "li",
+    "link",
+    "main",
+    "menu",
+    "menuitem",
+    "nav",
+    "noframes",
+    "ol",
+    "optgroup",
+    "option",
+    "p",
+    "param",
+    "section",
+    "summary",
+    "table",
+    "tbody",
+    "td",
+    "tfoot",
+    "th",
+    "thead",
+    "title",
+    "tr",
+    "track",
+    "ul",
+];
+
+/// Magic string of CDATA (after `<![`).
+///
+/// Used in the **cdata** production of [HTML (flow)][html_flow] and
+/// [HTML (text)][html_text].
+///
+/// [html_flow]: crate::construct::html_flow
+/// [html_text]: crate::construct::html_text
+pub const HTML_CDATA_PREFIX: [u8; 6] = [b'C', b'D', b'A', b'T', b'A', b'['];
+
+/// List of HTML tag names that form the **raw** production of
+/// [HTML (flow)][html_flow].
+///
+/// The **raw** production allows blank lines and thus no interleaving with
+/// markdown.
+/// Tag name matching must be performed insensitive to case, and thus this list
+/// includes lowercase tag names.
+///
+/// The number of the longest tag name is also stored as a constant in
+/// [`HTML_RAW_SIZE_MAX`][].
+///
+/// > 👉 **Note**: `textarea` was added in `CommonMark@0.30`.
+///
+/// ## References
+///
+/// *   [*§ 4.6 HTML blocks* in `CommonMark`](https://spec.commonmark.org/0.30/#html-blocks)
+///
+/// [html_flow]: crate::construct::html_flow
+pub const HTML_RAW_NAMES: [&str; 4] = ["pre", "script", "style", "textarea"];
+
+/// The number of the longest tag name in [`HTML_RAW_NAMES`][].
+///
+/// This is currently the size of `textarea`.
+pub const HTML_RAW_SIZE_MAX: usize = 8;
+
+/// To safeguard performance, labels are capped at a large number: `999`.
+pub const LINK_REFERENCE_SIZE_MAX: usize = 999;
+
+/// The max number of decimals allowed to form an (ordered)
+/// [list item][list-item].
+///
+/// `CommonMark` caps this at 10 digits (9 is fine, 10 not).
+/// This limit is imposed because bigger numbers result in integer overflows
+/// in some browsers.
+///
+/// ## References
+///
+/// *   [*§ 5.2 List items* in `CommonMark`](https://spec.commonmark.org/0.30/#ordered-list-marker)
+///
+/// [list-item]: crate::construct::list_item
+pub const LIST_ITEM_VALUE_SIZE_MAX: usize = 10;
+
+/// Maximum allowed unbalanced parens in destination.
+///
+/// There can be many balanced parens, but if there are 33 opens that were not
+/// yet closed, the destination does not parse.
+/// `CommonMark` requires that at least 3 opening parens are allowed.
+/// See: <https://spec.commonmark.org/0.30/#link-destination>,
+/// In practice, this is quite low, and several places instead cap it at 32.
+/// See: <https://github.com/remarkjs/react-markdown/issues/658#issuecomment-984345577>.
+pub const RESOURCE_DESTINATION_BALANCE_MAX: usize = 32;
+
+/// List of protocols allowed, when operating safely, as `href` on `a`.
+///
+/// This list is based on what is allowed by GitHub.
+pub const SAFE_PROTOCOL_HREF: [&str; 6] = ["http", "https", "irc", "ircs", "mailto", "xmpp"];
+
+/// List of protocols allowed, when operating safely, as `src` on `img`.
+///
+/// This list is based on what is allowed by GitHub.
+pub const SAFE_PROTOCOL_SRC: [&str; 2] = ["http", "https"];
+
+/// The number of characters that form a tab stop.
+///
+/// This relates to the number of whitespace characters needed to form certain
+/// constructs in markdown, most notable the whitespace required to form
+/// [code (indented)][code_indented].
+///
+/// [code_indented]: crate::construct::code_indented
+pub const TAB_SIZE: usize = 4;
+
+/// The number of markers needed for a [thematic break][thematic_break] to form.
+///
+/// Like many things in markdown, the number is `3`.
+///
+/// [thematic_break]: crate::construct::thematic_break
+pub const THEMATIC_BREAK_MARKER_COUNT_MIN: usize = 3;
+
+// Important: please touch the below lists as few times as possible to keep Git small.
+
+/// List of names and values that form named [character reference][character_reference]s.
+///
+/// This list is sensitive to casing.
+///
+/// The number of the longest name (`CounterClockwiseContourIntegral`) is also
+/// stored as a constant in [`CHARACTER_REFERENCE_NAMED_SIZE_MAX`][].
+///
+/// ## References
+///
+/// *   [*§ 2.5 Entity and numeric character references* in `CommonMark`](https://spec.commonmark.org/0.30/#entity-and-numeric-character-references)
+///
+/// [character_reference]: crate::construct::character_reference
+pub const CHARACTER_REFERENCES: [(&str, &str); 2125] = [
+    ("AElig", "Æ"),
+    ("AMP", "&"),
+    ("Aacute", "Á"),
+    ("Abreve", "Ă"),
+    ("Acirc", "Â"),
+    ("Acy", "А"),
+    ("Afr", "𝔄"),
+    ("Agrave", "À"),
+    ("Alpha", "Α"),
+    ("Amacr", "Ā"),
+    ("And", "⩓"),
+    ("Aogon", "Ą"),
+    ("Aopf", "𝔸"),
+    ("ApplyFunction", "⁡"),
+    ("Aring", "Å"),
+    ("Ascr", "𝒜"),
+    ("Assign", "≔"),
+    ("Atilde", "Ã"),
+    ("Auml", "Ä"),
+    ("Backslash", "∖"),
+    ("Barv", "⫧"),
+    ("Barwed", "⌆"),
+    ("Bcy", "Б"),
+    ("Because", "∵"),
+    ("Bernoullis", "ℬ"),
+    ("Beta", "Β"),
+    ("Bfr", "𝔅"),
+    ("Bopf", "𝔹"),
+    ("Breve", "˘"),
+    ("Bscr", "ℬ"),
+    ("Bumpeq", "≎"),
+    ("CHcy", "Ч"),
+    ("COPY", "©"),
+    ("Cacute", "Ć"),
+    ("Cap", "⋒"),
+    ("CapitalDifferentialD", "ⅅ"),
+    ("Cayleys", "ℭ"),
+    ("Ccaron", "Č"),
+    ("Ccedil", "Ç"),
+    ("Ccirc", "Ĉ"),
+    ("Cconint", "∰"),
+    ("Cdot", "Ċ"),
+    ("Cedilla", "¸"),
+    ("CenterDot", "·"),
+    ("Cfr", "ℭ"),
+    ("Chi", "Χ"),
+    ("CircleDot", "⊙"),
+    ("CircleMinus", "⊖"),
+    ("CirclePlus", "⊕"),
+    ("CircleTimes", "⊗"),
+    ("ClockwiseContourIntegral", "∲"),
+    ("CloseCurlyDoubleQuote", "”"),
+    ("CloseCurlyQuote", "’"),
+    ("Colon", "∷"),
+    ("Colone", "⩴"),
+    ("Congruent", "≡"),
+    ("Conint", "∯"),
+    ("ContourIntegral", "∮"),
+    ("Copf", "ℂ"),
+    ("Coproduct", "∐"),
+    ("CounterClockwiseContourIntegral", "∳"),
+    ("Cross", "⨯"),
+    ("Cscr", "𝒞"),
+    ("Cup", "⋓"),
+    ("CupCap", "≍"),
+    ("DD", "ⅅ"),
+    ("DDotrahd", "⤑"),
+    ("DJcy", "Ђ"),
+    ("DScy", "Ѕ"),
+    ("DZcy", "Џ"),
+    ("Dagger", "‡"),
+    ("Darr", "↡"),
+    ("Dashv", "⫤"),
+    ("Dcaron", "Ď"),
+    ("Dcy", "Д"),
+    ("Del", "∇"),
+    ("Delta", "Δ"),
+    ("Dfr", "𝔇"),
+    ("DiacriticalAcute", "´"),
+    ("DiacriticalDot", "˙"),
+    ("DiacriticalDoubleAcute", "˝"),
+    ("DiacriticalGrave", "`"),
+    ("DiacriticalTilde", "˜"),
+    ("Diamond", "⋄"),
+    ("DifferentialD", "ⅆ"),
+    ("Dopf", "𝔻"),
+    ("Dot", "¨"),
+    ("DotDot", "⃜"),
+    ("DotEqual", "≐"),
+    ("DoubleContourIntegral", "∯"),
+    ("DoubleDot", "¨"),
+    ("DoubleDownArrow", "⇓"),
+    ("DoubleLeftArrow", "⇐"),
+    ("DoubleLeftRightArrow", "⇔"),
+    ("DoubleLeftTee", "⫤"),
+    ("DoubleLongLeftArrow", "⟸"),
+    ("DoubleLongLeftRightArrow", "⟺"),
+    ("DoubleLongRightArrow", "⟹"),
+    ("DoubleRightArrow", "⇒"),
+    ("DoubleRightTee", "⊨"),
+    ("DoubleUpArrow", "⇑"),
+    ("DoubleUpDownArrow", "⇕"),
+    ("DoubleVerticalBar", "∥"),
+    ("DownArrow", "↓"),
+    ("DownArrowBar", "⤓"),
+    ("DownArrowUpArrow", "⇵"),
+    ("DownBreve", "̑"),
+    ("DownLeftRightVector", "⥐"),
+    ("DownLeftTeeVector", "⥞"),
+    ("DownLeftVector", "↽"),
+    ("DownLeftVectorBar", "⥖"),
+    ("DownRightTeeVector", "⥟"),
+    ("DownRightVector", "⇁"),
+    ("DownRightVectorBar", "⥗"),
+    ("DownTee", "⊤"),
+    ("DownTeeArrow", "↧"),
+    ("Downarrow", "⇓"),
+    ("Dscr", "𝒟"),
+    ("Dstrok", "Đ"),
+    ("ENG", "Ŋ"),
+    ("ETH", "Ð"),
+    ("Eacute", "É"),
+    ("Ecaron", "Ě"),
+    ("Ecirc", "Ê"),
+    ("Ecy", "Э"),
+    ("Edot", "Ė"),
+    ("Efr", "𝔈"),
+    ("Egrave", "È"),
+    ("Element", "∈"),
+    ("Emacr", "Ē"),
+    ("EmptySmallSquare", "◻"),
+    ("EmptyVerySmallSquare", "▫"),
+    ("Eogon", "Ę"),
+    ("Eopf", "𝔼"),
+    ("Epsilon", "Ε"),
+    ("Equal", "⩵"),
+    ("EqualTilde", "≂"),
+    ("Equilibrium", "⇌"),
+    ("Escr", "ℰ"),
+    ("Esim", "⩳"),
+    ("Eta", "Η"),
+    ("Euml", "Ë"),
+    ("Exists", "∃"),
+    ("ExponentialE", "ⅇ"),
+    ("Fcy", "Ф"),
+    ("Ffr", "𝔉"),
+    ("FilledSmallSquare", "◼"),
+    ("FilledVerySmallSquare", "▪"),
+    ("Fopf", "𝔽"),
+    ("ForAll", "∀"),
+    ("Fouriertrf", "ℱ"),
+    ("Fscr", "ℱ"),
+    ("GJcy", "Ѓ"),
+    ("GT", ">"),
+    ("Gamma", "Γ"),
+    ("Gammad", "Ϝ"),
+    ("Gbreve", "Ğ"),
+    ("Gcedil", "Ģ"),
+    ("Gcirc", "Ĝ"),
+    ("Gcy", "Г"),
+    ("Gdot", "Ġ"),
+    ("Gfr", "𝔊"),
+    ("Gg", "⋙"),
+    ("Gopf", "𝔾"),
+    ("GreaterEqual", "≥"),
+    ("GreaterEqualLess", "⋛"),
+    ("GreaterFullEqual", "≧"),
+    ("GreaterGreater", "⪢"),
+    ("GreaterLess", "≷"),
+    ("GreaterSlantEqual", "⩾"),
+    ("GreaterTilde", "≳"),
+    ("Gscr", "𝒢"),
+    ("Gt", "≫"),
+    ("HARDcy", "Ъ"),
+    ("Hacek", "ˇ"),
+    ("Hat", "^"),
+    ("Hcirc", "Ĥ"),
+    ("Hfr", "ℌ"),
+    ("HilbertSpace", "ℋ"),
+    ("Hopf", "ℍ"),
+    ("HorizontalLine", "─"),
+    ("Hscr", "ℋ"),
+    ("Hstrok", "Ħ"),
+    ("HumpDownHump", "≎"),
+    ("HumpEqual", "≏"),
+    ("IEcy", "Е"),
+    ("IJlig", "IJ"),
+    ("IOcy", "Ё"),
+    ("Iacute", "Í"),
+    ("Icirc", "Î"),
+    ("Icy", "И"),
+    ("Idot", "İ"),
+    ("Ifr", "ℑ"),
+    ("Igrave", "Ì"),
+    ("Im", "ℑ"),
+    ("Imacr", "Ī"),
+    ("ImaginaryI", "ⅈ"),
+    ("Implies", "⇒"),
+    ("Int", "∬"),
+    ("Integral", "∫"),
+    ("Intersection", "⋂"),
+    ("InvisibleComma", "⁣"),
+    ("InvisibleTimes", "⁢"),
+    ("Iogon", "Į"),
+    ("Iopf", "𝕀"),
+    ("Iota", "Ι"),
+    ("Iscr", "ℐ"),
+    ("Itilde", "Ĩ"),
+    ("Iukcy", "І"),
+    ("Iuml", "Ï"),
+    ("Jcirc", "Ĵ"),
+    ("Jcy", "Й"),
+    ("Jfr", "𝔍"),
+    ("Jopf", "𝕁"),
+    ("Jscr", "𝒥"),
+    ("Jsercy", "Ј"),
+    ("Jukcy", "Є"),
+    ("KHcy", "Х"),
+    ("KJcy", "Ќ"),
+    ("Kappa", "Κ"),
+    ("Kcedil", "Ķ"),
+    ("Kcy", "К"),
+    ("Kfr", "𝔎"),
+    ("Kopf", "𝕂"),
+    ("Kscr", "𝒦"),
+    ("LJcy", "Љ"),
+    ("LT", "<"),
+    ("Lacute", "Ĺ"),
+    ("Lambda", "Λ"),
+    ("Lang", "⟪"),
+    ("Laplacetrf", "ℒ"),
+    ("Larr", "↞"),
+    ("Lcaron", "Ľ"),
+    ("Lcedil", "Ļ"),
+    ("Lcy", "Л"),
+    ("LeftAngleBracket", "⟨"),
+    ("LeftArrow", "←"),
+    ("LeftArrowBar", "⇤"),
+    ("LeftArrowRightArrow", "⇆"),
+    ("LeftCeiling", "⌈"),
+    ("LeftDoubleBracket", "⟦"),
+    ("LeftDownTeeVector", "⥡"),
+    ("LeftDownVector", "⇃"),
+    ("LeftDownVectorBar", "⥙"),
+    ("LeftFloor", "⌊"),
+    ("LeftRightArrow", "↔"),
+    ("LeftRightVector", "⥎"),
+    ("LeftTee", "⊣"),
+    ("LeftTeeArrow", "↤"),
+    ("LeftTeeVector", "⥚"),
+    ("LeftTriangle", "⊲"),
+    ("LeftTriangleBar", "⧏"),
+    ("LeftTriangleEqual", "⊴"),
+    ("LeftUpDownVector", "⥑"),
+    ("LeftUpTeeVector", "⥠"),
+    ("LeftUpVector", "↿"),
+    ("LeftUpVectorBar", "⥘"),
+    ("LeftVector", "↼"),
+    ("LeftVectorBar", "⥒"),
+    ("Leftarrow", "⇐"),
+    ("Leftrightarrow", "⇔"),
+    ("LessEqualGreater", "⋚"),
+    ("LessFullEqual", "≦"),
+    ("LessGreater", "≶"),
+    ("LessLess", "⪡"),
+    ("LessSlantEqual", "⩽"),
+    ("LessTilde", "≲"),
+    ("Lfr", "𝔏"),
+    ("Ll", "⋘"),
+    ("Lleftarrow", "⇚"),
+    ("Lmidot", "Ŀ"),
+    ("LongLeftArrow", "⟵"),
+    ("LongLeftRightArrow", "⟷"),
+    ("LongRightArrow", "⟶"),
+    ("Longleftarrow", "⟸"),
+    ("Longleftrightarrow", "⟺"),
+    ("Longrightarrow", "⟹"),
+    ("Lopf", "𝕃"),
+    ("LowerLeftArrow", "↙"),
+    ("LowerRightArrow", "↘"),
+    ("Lscr", "ℒ"),
+    ("Lsh", "↰"),
+    ("Lstrok", "Ł"),
+    ("Lt", "≪"),
+    ("Map", "⤅"),
+    ("Mcy", "М"),
+    ("MediumSpace", " "),
+    ("Mellintrf", "ℳ"),
+    ("Mfr", "𝔐"),
+    ("MinusPlus", "∓"),
+    ("Mopf", "𝕄"),
+    ("Mscr", "ℳ"),
+    ("Mu", "Μ"),
+    ("NJcy", "Њ"),
+    ("Nacute", "Ń"),
+    ("Ncaron", "Ň"),
+    ("Ncedil", "Ņ"),
+    ("Ncy", "Н"),
+    ("NegativeMediumSpace", "\u{200B}"),
+    ("NegativeThickSpace", "\u{200B}"),
+    ("NegativeThinSpace", "\u{200B}"),
+    ("NegativeVeryThinSpace", "\u{200B}"),
+    ("NestedGreaterGreater", "≫"),
+    ("NestedLessLess", "≪"),
+    ("NewLine", "\n"),
+    ("Nfr", "𝔑"),
+    ("NoBreak", "\u{2060}"),
+    ("NonBreakingSpace", " "),
+    ("Nopf", "ℕ"),
+    ("Not", "⫬"),
+    ("NotCongruent", "≢"),
+    ("NotCupCap", "≭"),
+    ("NotDoubleVerticalBar", "∦"),
+    ("NotElement", "∉"),
+    ("NotEqual", "≠"),
+    ("NotEqualTilde", "≂̸"),
+    ("NotExists", "∄"),
+    ("NotGreater", "≯"),
+    ("NotGreaterEqual", "≱"),
+    ("NotGreaterFullEqual", "≧̸"),
+    ("NotGreaterGreater", "≫̸"),
+    ("NotGreaterLess", "≹"),
+    ("NotGreaterSlantEqual", "⩾̸"),
+    ("NotGreaterTilde", "≵"),
+    ("NotHumpDownHump", "≎̸"),
+    ("NotHumpEqual", "≏̸"),
+    ("NotLeftTriangle", "⋪"),
+    ("NotLeftTriangleBar", "⧏̸"),
+    ("NotLeftTriangleEqual", "⋬"),
+    ("NotLess", "≮"),
+    ("NotLessEqual", "≰"),
+    ("NotLessGreater", "≸"),
+    ("NotLessLess", "≪̸"),
+    ("NotLessSlantEqual", "⩽̸"),
+    ("NotLessTilde", "≴"),
+    ("NotNestedGreaterGreater", "⪢̸"),
+    ("NotNestedLessLess", "⪡̸"),
+    ("NotPrecedes", "⊀"),
+    ("NotPrecedesEqual", "⪯̸"),
+    ("NotPrecedesSlantEqual", "⋠"),
+    ("NotReverseElement", "∌"),
+    ("NotRightTriangle", "⋫"),
+    ("NotRightTriangleBar", "⧐̸"),
+    ("NotRightTriangleEqual", "⋭"),
+    ("NotSquareSubset", "⊏̸"),
+    ("NotSquareSubsetEqual", "⋢"),
+    ("NotSquareSuperset", "⊐̸"),
+    ("NotSquareSupersetEqual", "⋣"),
+    ("NotSubset", "⊂⃒"),
+    ("NotSubsetEqual", "⊈"),
+    ("NotSucceeds", "⊁"),
+    ("NotSucceedsEqual", "⪰̸"),
+    ("NotSucceedsSlantEqual", "⋡"),
+    ("NotSucceedsTilde", "≿̸"),
+    ("NotSuperset", "⊃⃒"),
+    ("NotSupersetEqual", "⊉"),
+    ("NotTilde", "≁"),
+    ("NotTildeEqual", "≄"),
+    ("NotTildeFullEqual", "≇"),
+    ("NotTildeTilde", "≉"),
+    ("NotVerticalBar", "∤"),
+    ("Nscr", "𝒩"),
+    ("Ntilde", "Ñ"),
+    ("Nu", "Ν"),
+    ("OElig", "Œ"),
+    ("Oacute", "Ó"),
+    ("Ocirc", "Ô"),
+    ("Ocy", "О"),
+    ("Odblac", "Ő"),
+    ("Ofr", "𝔒"),
+    ("Ograve", "Ò"),
+    ("Omacr", "Ō"),
+    ("Omega", "Ω"),
+    ("Omicron", "Ο"),
+    ("Oopf", "𝕆"),
+    ("OpenCurlyDoubleQuote", "“"),
+    ("OpenCurlyQuote", "‘"),
+    ("Or", "⩔"),
+    ("Oscr", "𝒪"),
+    ("Oslash", "Ø"),
+    ("Otilde", "Õ"),
+    ("Otimes", "⨷"),
+    ("Ouml", "Ö"),
+    ("OverBar", "‾"),
+    ("OverBrace", "⏞"),
+    ("OverBracket", "⎴"),
+    ("OverParenthesis", "⏜"),
+    ("PartialD", "∂"),
+    ("Pcy", "П"),
+    ("Pfr", "𝔓"),
+    ("Phi", "Φ"),
+    ("Pi", "Π"),
+    ("PlusMinus", "±"),
+    ("Poincareplane", "ℌ"),
+    ("Popf", "ℙ"),
+    ("Pr", "⪻"),
+    ("Precedes", "≺"),
+    ("PrecedesEqual", "⪯"),
+    ("PrecedesSlantEqual", "≼"),
+    ("PrecedesTilde", "≾"),
+    ("Prime", "″"),
+    ("Product", "∏"),
+    ("Proportion", "∷"),
+    ("Proportional", "∝"),
+    ("Pscr", "𝒫"),
+    ("Psi", "Ψ"),
+    ("QUOT", "\""),
+    ("Qfr", "𝔔"),
+    ("Qopf", "ℚ"),
+    ("Qscr", "𝒬"),
+    ("RBarr", "⤐"),
+    ("REG", "®"),
+    ("Racute", "Ŕ"),
+    ("Rang", "⟫"),
+    ("Rarr", "↠"),
+    ("Rarrtl", "⤖"),
+    ("Rcaron", "Ř"),
+    ("Rcedil", "Ŗ"),
+    ("Rcy", "Р"),
+    ("Re", "ℜ"),
+    ("ReverseElement", "∋"),
+    ("ReverseEquilibrium", "⇋"),
+    ("ReverseUpEquilibrium", "⥯"),
+    ("Rfr", "ℜ"),
+    ("Rho", "Ρ"),
+    ("RightAngleBracket", "⟩"),
+    ("RightArrow", "→"),
+    ("RightArrowBar", "⇥"),
+    ("RightArrowLeftArrow", "⇄"),
+    ("RightCeiling", "⌉"),
+    ("RightDoubleBracket", "⟧"),
+    ("RightDownTeeVector", "⥝"),
+    ("RightDownVector", "⇂"),
+    ("RightDownVectorBar", "⥕"),
+    ("RightFloor", "⌋"),
+    ("RightTee", "⊢"),
+    ("RightTeeArrow", "↦"),
+    ("RightTeeVector", "⥛"),
+    ("RightTriangle", "⊳"),
+    ("RightTriangleBar", "⧐"),
+    ("RightTriangleEqual", "⊵"),
+    ("RightUpDownVector", "⥏"),
+    ("RightUpTeeVector", "⥜"),
+    ("RightUpVector", "↾"),
+    ("RightUpVectorBar", "⥔"),
+    ("RightVector", "⇀"),
+    ("RightVectorBar", "⥓"),
+    ("Rightarrow", "⇒"),
+    ("Ropf", "ℝ"),
+    ("RoundImplies", "⥰"),
+    ("Rrightarrow", "⇛"),
+    ("Rscr", "ℛ"),
+    ("Rsh", "↱"),
+    ("RuleDelayed", "⧴"),
+    ("SHCHcy", "Щ"),
+    ("SHcy", "Ш"),
+    ("SOFTcy", "Ь"),
+    ("Sacute", "Ś"),
+    ("Sc", "⪼"),
+    ("Scaron", "Š"),
+    ("Scedil", "Ş"),
+    ("Scirc", "Ŝ"),
+    ("Scy", "С"),
+    ("Sfr", "𝔖"),
+    ("ShortDownArrow", "↓"),
+    ("ShortLeftArrow", "←"),
+    ("ShortRightArrow", "→"),
+    ("ShortUpArrow", "↑"),
+    ("Sigma", "Σ"),
+    ("SmallCircle", "∘"),
+    ("Sopf", "𝕊"),
+    ("Sqrt", "√"),
+    ("Square", "□"),
+    ("SquareIntersection", "⊓"),
+    ("SquareSubset", "⊏"),
+    ("SquareSubsetEqual", "⊑"),
+    ("SquareSuperset", "⊐"),
+    ("SquareSupersetEqual", "⊒"),
+    ("SquareUnion", "⊔"),
+    ("Sscr", "𝒮"),
+    ("Star", "⋆"),
+    ("Sub", "⋐"),
+    ("Subset", "⋐"),
+    ("SubsetEqual", "⊆"),
+    ("Succeeds", "≻"),
+    ("SucceedsEqual", "⪰"),
+    ("SucceedsSlantEqual", "≽"),
+    ("SucceedsTilde", "≿"),
+    ("SuchThat", "∋"),
+    ("Sum", "∑"),
+    ("Sup", "⋑"),
+    ("Superset", "⊃"),
+    ("SupersetEqual", "⊇"),
+    ("Supset", "⋑"),
+    ("THORN", "Þ"),
+    ("TRADE", "™"),
+    ("TSHcy", "Ћ"),
+    ("TScy", "Ц"),
+    ("Tab", "\t"),
+    ("Tau", "Τ"),
+    ("Tcaron", "Ť"),
+    ("Tcedil", "Ţ"),
+    ("Tcy", "Т"),
+    ("Tfr", "𝔗"),
+    ("Therefore", "∴"),
+    ("Theta", "Θ"),
+    ("ThickSpace", "  "),
+    ("ThinSpace", " "),
+    ("Tilde", "∼"),
+    ("TildeEqual", "≃"),
+    ("TildeFullEqual", "≅"),
+    ("TildeTilde", "≈"),
+    ("Topf", "𝕋"),
+    ("TripleDot", "⃛"),
+    ("Tscr", "𝒯"),
+    ("Tstrok", "Ŧ"),
+    ("Uacute", "Ú"),
+    ("Uarr", "↟"),
+    ("Uarrocir", "⥉"),
+    ("Ubrcy", "Ў"),
+    ("Ubreve", "Ŭ"),
+    ("Ucirc", "Û"),
+    ("Ucy", "У"),
+    ("Udblac", "Ű"),
+    ("Ufr", "𝔘"),
+    ("Ugrave", "Ù"),
+    ("Umacr", "Ū"),
+    ("UnderBar", "_"),
+    ("UnderBrace", "⏟"),
+    ("UnderBracket", "⎵"),
+    ("UnderParenthesis", "⏝"),
+    ("Union", "⋃"),
+    ("UnionPlus", "⊎"),
+    ("Uogon", "Ų"),
+    ("Uopf", "𝕌"),
+    ("UpArrow", "↑"),
+    ("UpArrowBar", "⤒"),
+    ("UpArrowDownArrow", "⇅"),
+    ("UpDownArrow", "↕"),
+    ("UpEquilibrium", "⥮"),
+    ("UpTee", "⊥"),
+    ("UpTeeArrow", "↥"),
+    ("Uparrow", "⇑"),
+    ("Updownarrow", "⇕"),
+    ("UpperLeftArrow", "↖"),
+    ("UpperRightArrow", "↗"),
+    ("Upsi", "ϒ"),
+    ("Upsilon", "Υ"),
+    ("Uring", "Ů"),
+    ("Uscr", "𝒰"),
+    ("Utilde", "Ũ"),
+    ("Uuml", "Ü"),
+    ("VDash", "⊫"),
+    ("Vbar", "⫫"),
+    ("Vcy", "В"),
+    ("Vdash", "⊩"),
+    ("Vdashl", "⫦"),
+    ("Vee", "⋁"),
+    ("Verbar", "‖"),
+    ("Vert", "‖"),
+    ("VerticalBar", "∣"),
+    ("VerticalLine", "|"),
+    ("VerticalSeparator", "❘"),
+    ("VerticalTilde", "≀"),
+    ("VeryThinSpace", " "),
+    ("Vfr", "𝔙"),
+    ("Vopf", "𝕍"),
+    ("Vscr", "𝒱"),
+    ("Vvdash", "⊪"),
+    ("Wcirc", "Ŵ"),
+    ("Wedge", "⋀"),
+    ("Wfr", "𝔚"),
+    ("Wopf", "𝕎"),
+    ("Wscr", "𝒲"),
+    ("Xfr", "𝔛"),
+    ("Xi", "Ξ"),
+    ("Xopf", "𝕏"),
+    ("Xscr", "𝒳"),
+    ("YAcy", "Я"),
+    ("YIcy", "Ї"),
+    ("YUcy", "Ю"),
+    ("Yacute", "Ý"),
+    ("Ycirc", "Ŷ"),
+    ("Ycy", "Ы"),
+    ("Yfr", "𝔜"),
+    ("Yopf", "𝕐"),
+    ("Yscr", "𝒴"),
+    ("Yuml", "Ÿ"),
+    ("ZHcy", "Ж"),
+    ("Zacute", "Ź"),
+    ("Zcaron", "Ž"),
+    ("Zcy", "З"),
+    ("Zdot", "Ż"),
+    ("ZeroWidthSpace", "\u{200B}"),
+    ("Zeta", "Ζ"),
+    ("Zfr", "ℨ"),
+    ("Zopf", "ℤ"),
+    ("Zscr", "𝒵"),
+    ("aacute", "á"),
+    ("abreve", "ă"),
+    ("ac", "∾"),
+    ("acE", "∾̳"),
+    ("acd", "∿"),
+    ("acirc", "â"),
+    ("acute", "´"),
+    ("acy", "а"),
+    ("aelig", "æ"),
+    ("af", "⁡"),
+    ("afr", "𝔞"),
+    ("agrave", "à"),
+    ("alefsym", "ℵ"),
+    ("aleph", "ℵ"),
+    ("alpha", "α"),
+    ("amacr", "ā"),
+    ("amalg", "⨿"),
+    ("amp", "&"),
+    ("and", "∧"),
+    ("andand", "⩕"),
+    ("andd", "⩜"),
+    ("andslope", "⩘"),
+    ("andv", "⩚"),
+    ("ang", "∠"),
+    ("ange", "⦤"),
+    ("angle", "∠"),
+    ("angmsd", "∡"),
+    ("angmsdaa", "⦨"),
+    ("angmsdab", "⦩"),
+    ("angmsdac", "⦪"),
+    ("angmsdad", "⦫"),
+    ("angmsdae", "⦬"),
+    ("angmsdaf", "⦭"),
+    ("angmsdag", "⦮"),
+    ("angmsdah", "⦯"),
+    ("angrt", "∟"),
+    ("angrtvb", "⊾"),
+    ("angrtvbd", "⦝"),
+    ("angsph", "∢"),
+    ("angst", "Å"),
+    ("angzarr", "⍼"),
+    ("aogon", "ą"),
+    ("aopf", "𝕒"),
+    ("ap", "≈"),
+    ("apE", "⩰"),
+    ("apacir", "⩯"),
+    ("ape", "≊"),
+    ("apid", "≋"),
+    ("apos", "'"),
+    ("approx", "≈"),
+    ("approxeq", "≊"),
+    ("aring", "å"),
+    ("ascr", "𝒶"),
+    ("ast", "*"),
+    ("asymp", "≈"),
+    ("asympeq", "≍"),
+    ("atilde", "ã"),
+    ("auml", "ä"),
+    ("awconint", "∳"),
+    ("awint", "⨑"),
+    ("bNot", "⫭"),
+    ("backcong", "≌"),
+    ("backepsilon", "϶"),
+    ("backprime", "‵"),
+    ("backsim", "∽"),
+    ("backsimeq", "⋍"),
+    ("barvee", "⊽"),
+    ("barwed", "⌅"),
+    ("barwedge", "⌅"),
+    ("bbrk", "⎵"),
+    ("bbrktbrk", "⎶"),
+    ("bcong", "≌"),
+    ("bcy", "б"),
+    ("bdquo", "„"),
+    ("becaus", "∵"),
+    ("because", "∵"),
+    ("bemptyv", "⦰"),
+    ("bepsi", "϶"),
+    ("bernou", "ℬ"),
+    ("beta", "β"),
+    ("beth", "ℶ"),
+    ("between", "≬"),
+    ("bfr", "𝔟"),
+    ("bigcap", "⋂"),
+    ("bigcirc", "◯"),
+    ("bigcup", "⋃"),
+    ("bigodot", "⨀"),
+    ("bigoplus", "⨁"),
+    ("bigotimes", "⨂"),
+    ("bigsqcup", "⨆"),
+    ("bigstar", "★"),
+    ("bigtriangledown", "▽"),
+    ("bigtriangleup", "△"),
+    ("biguplus", "⨄"),
+    ("bigvee", "⋁"),
+    ("bigwedge", "⋀"),
+    ("bkarow", "⤍"),
+    ("blacklozenge", "⧫"),
+    ("blacksquare", "▪"),
+    ("blacktriangle", "▴"),
+    ("blacktriangledown", "▾"),
+    ("blacktriangleleft", "◂"),
+    ("blacktriangleright", "▸"),
+    ("blank", "␣"),
+    ("blk12", "▒"),
+    ("blk14", "░"),
+    ("blk34", "▓"),
+    ("block", "█"),
+    ("bne", "=⃥"),
+    ("bnequiv", "≡⃥"),
+    ("bnot", "⌐"),
+    ("bopf", "𝕓"),
+    ("bot", "⊥"),
+    ("bottom", "⊥"),
+    ("bowtie", "⋈"),
+    ("boxDL", "╗"),
+    ("boxDR", "╔"),
+    ("boxDl", "╖"),
+    ("boxDr", "╓"),
+    ("boxH", "═"),
+    ("boxHD", "╦"),
+    ("boxHU", "╩"),
+    ("boxHd", "╤"),
+    ("boxHu", "╧"),
+    ("boxUL", "╝"),
+    ("boxUR", "╚"),
+    ("boxUl", "╜"),
+    ("boxUr", "╙"),
+    ("boxV", "║"),
+    ("boxVH", "╬"),
+    ("boxVL", "╣"),
+    ("boxVR", "╠"),
+    ("boxVh", "╫"),
+    ("boxVl", "╢"),
+    ("boxVr", "╟"),
+    ("boxbox", "⧉"),
+    ("boxdL", "╕"),
+    ("boxdR", "╒"),
+    ("boxdl", "┐"),
+    ("boxdr", "┌"),
+    ("boxh", "─"),
+    ("boxhD", "╥"),
+    ("boxhU", "╨"),
+    ("boxhd", "┬"),
+    ("boxhu", "┴"),
+    ("boxminus", "⊟"),
+    ("boxplus", "⊞"),
+    ("boxtimes", "⊠"),
+    ("boxuL", "╛"),
+    ("boxuR", "╘"),
+    ("boxul", "┘"),
+    ("boxur", "└"),
+    ("boxv", "│"),
+    ("boxvH", "╪"),
+    ("boxvL", "╡"),
+    ("boxvR", "╞"),
+    ("boxvh", "┼"),
+    ("boxvl", "┤"),
+    ("boxvr", "├"),
+    ("bprime", "‵"),
+    ("breve", "˘"),
+    ("brvbar", "¦"),
+    ("bscr", "𝒷"),
+    ("bsemi", "⁏"),
+    ("bsim", "∽"),
+    ("bsime", "⋍"),
+    ("bsol", "\\"),
+    ("bsolb", "⧅"),
+    ("bsolhsub", "⟈"),
+    ("bull", "•"),
+    ("bullet", "•"),
+    ("bump", "≎"),
+    ("bumpE", "⪮"),
+    ("bumpe", "≏"),
+    ("bumpeq", "≏"),
+    ("cacute", "ć"),
+    ("cap", "∩"),
+    ("capand", "⩄"),
+    ("capbrcup", "⩉"),
+    ("capcap", "⩋"),
+    ("capcup", "⩇"),
+    ("capdot", "⩀"),
+    ("caps", "∩︀"),
+    ("caret", "⁁"),
+    ("caron", "ˇ"),
+    ("ccaps", "⩍"),
+    ("ccaron", "č"),
+    ("ccedil", "ç"),
+    ("ccirc", "ĉ"),
+    ("ccups", "⩌"),
+    ("ccupssm", "⩐"),
+    ("cdot", "ċ"),
+    ("cedil", "¸"),
+    ("cemptyv", "⦲"),
+    ("cent", "¢"),
+    ("centerdot", "·"),
+    ("cfr", "𝔠"),
+    ("chcy", "ч"),
+    ("check", "✓"),
+    ("checkmark", "✓"),
+    ("chi", "χ"),
+    ("cir", "○"),
+    ("cirE", "⧃"),
+    ("circ", "ˆ"),
+    ("circeq", "≗"),
+    ("circlearrowleft", "↺"),
+    ("circlearrowright", "↻"),
+    ("circledR", "®"),
+    ("circledS", "Ⓢ"),
+    ("circledast", "⊛"),
+    ("circledcirc", "⊚"),
+    ("circleddash", "⊝"),
+    ("cire", "≗"),
+    ("cirfnint", "⨐"),
+    ("cirmid", "⫯"),
+    ("cirscir", "⧂"),
+    ("clubs", "♣"),
+    ("clubsuit", "♣"),
+    ("colon", ":"),
+    ("colone", "≔"),
+    ("coloneq", "≔"),
+    ("comma", ","),
+    ("commat", "@"),
+    ("comp", "∁"),
+    ("compfn", "∘"),
+    ("complement", "∁"),
+    ("complexes", "ℂ"),
+    ("cong", "≅"),
+    ("congdot", "⩭"),
+    ("conint", "∮"),
+    ("copf", "𝕔"),
+    ("coprod", "∐"),
+    ("copy", "©"),
+    ("copysr", "℗"),
+    ("crarr", "↵"),
+    ("cross", "✗"),
+    ("cscr", "𝒸"),
+    ("csub", "⫏"),
+    ("csube", "⫑"),
+    ("csup", "⫐"),
+    ("csupe", "⫒"),
+    ("ctdot", "⋯"),
+    ("cudarrl", "⤸"),
+    ("cudarrr", "⤵"),
+    ("cuepr", "⋞"),
+    ("cuesc", "⋟"),
+    ("cularr", "↶"),
+    ("cularrp", "⤽"),
+    ("cup", "∪"),
+    ("cupbrcap", "⩈"),
+    ("cupcap", "⩆"),
+    ("cupcup", "⩊"),
+    ("cupdot", "⊍"),
+    ("cupor", "⩅"),
+    ("cups", "∪︀"),
+    ("curarr", "↷"),
+    ("curarrm", "⤼"),
+    ("curlyeqprec", "⋞"),
+    ("curlyeqsucc", "⋟"),
+    ("curlyvee", "⋎"),
+    ("curlywedge", "⋏"),
+    ("curren", "¤"),
+    ("curvearrowleft", "↶"),
+    ("curvearrowright", "↷"),
+    ("cuvee", "⋎"),
+    ("cuwed", "⋏"),
+    ("cwconint", "∲"),
+    ("cwint", "∱"),
+    ("cylcty", "⌭"),
+    ("dArr", "⇓"),
+    ("dHar", "⥥"),
+    ("dagger", "†"),
+    ("daleth", "ℸ"),
+    ("darr", "↓"),
+    ("dash", "‐"),
+    ("dashv", "⊣"),
+    ("dbkarow", "⤏"),
+    ("dblac", "˝"),
+    ("dcaron", "ď"),
+    ("dcy", "д"),
+    ("dd", "ⅆ"),
+    ("ddagger", "‡"),
+    ("ddarr", "⇊"),
+    ("ddotseq", "⩷"),
+    ("deg", "°"),
+    ("delta", "δ"),
+    ("demptyv", "⦱"),
+    ("dfisht", "⥿"),
+    ("dfr", "𝔡"),
+    ("dharl", "⇃"),
+    ("dharr", "⇂"),
+    ("diam", "⋄"),
+    ("diamond", "⋄"),
+    ("diamondsuit", "♦"),
+    ("diams", "♦"),
+    ("die", "¨"),
+    ("digamma", "ϝ"),
+    ("disin", "⋲"),
+    ("div", "÷"),
+    ("divide", "÷"),
+    ("divideontimes", "⋇"),
+    ("divonx", "⋇"),
+    ("djcy", "ђ"),
+    ("dlcorn", "⌞"),
+    ("dlcrop", "⌍"),
+    ("dollar", "$"),
+    ("dopf", "𝕕"),
+    ("dot", "˙"),
+    ("doteq", "≐"),
+    ("doteqdot", "≑"),
+    ("dotminus", "∸"),
+    ("dotplus", "∔"),
+    ("dotsquare", "⊡"),
+    ("doublebarwedge", "⌆"),
+    ("downarrow", "↓"),
+    ("downdownarrows", "⇊"),
+    ("downharpoonleft", "⇃"),
+    ("downharpoonright", "⇂"),
+    ("drbkarow", "⤐"),
+    ("drcorn", "⌟"),
+    ("drcrop", "⌌"),
+    ("dscr", "𝒹"),
+    ("dscy", "ѕ"),
+    ("dsol", "⧶"),
+    ("dstrok", "đ"),
+    ("dtdot", "⋱"),
+    ("dtri", "▿"),
+    ("dtrif", "▾"),
+    ("duarr", "⇵"),
+    ("duhar", "⥯"),
+    ("dwangle", "⦦"),
+    ("dzcy", "џ"),
+    ("dzigrarr", "⟿"),
+    ("eDDot", "⩷"),
+    ("eDot", "≑"),
+    ("eacute", "é"),
+    ("easter", "⩮"),
+    ("ecaron", "ě"),
+    ("ecir", "≖"),
+    ("ecirc", "ê"),
+    ("ecolon", "≕"),
+    ("ecy", "э"),
+    ("edot", "ė"),
+    ("ee", "ⅇ"),
+    ("efDot", "≒"),
+    ("efr", "𝔢"),
+    ("eg", "⪚"),
+    ("egrave", "è"),
+    ("egs", "⪖"),
+    ("egsdot", "⪘"),
+    ("el", "⪙"),
+    ("elinters", "⏧"),
+    ("ell", "ℓ"),
+    ("els", "⪕"),
+    ("elsdot", "⪗"),
+    ("emacr", "ē"),
+    ("empty", "∅"),
+    ("emptyset", "∅"),
+    ("emptyv", "∅"),
+    ("emsp13", " "),
+    ("emsp14", " "),
+    ("emsp", " "),
+    ("eng", "ŋ"),
+    ("ensp", " "),
+    ("eogon", "ę"),
+    ("eopf", "𝕖"),
+    ("epar", "⋕"),
+    ("eparsl", "⧣"),
+    ("eplus", "⩱"),
+    ("epsi", "ε"),
+    ("epsilon", "ε"),
+    ("epsiv", "ϵ"),
+    ("eqcirc", "≖"),
+    ("eqcolon", "≕"),
+    ("eqsim", "≂"),
+    ("eqslantgtr", "⪖"),
+    ("eqslantless", "⪕"),
+    ("equals", "="),
+    ("equest", "≟"),
+    ("equiv", "≡"),
+    ("equivDD", "⩸"),
+    ("eqvparsl", "⧥"),
+    ("erDot", "≓"),
+    ("erarr", "⥱"),
+    ("escr", "ℯ"),
+    ("esdot", "≐"),
+    ("esim", "≂"),
+    ("eta", "η"),
+    ("eth", "ð"),
+    ("euml", "ë"),
+    ("euro", "€"),
+    ("excl", "!"),
+    ("exist", "∃"),
+    ("expectation", "ℰ"),
+    ("exponentiale", "ⅇ"),
+    ("fallingdotseq", "≒"),
+    ("fcy", "ф"),
+    ("female", "♀"),
+    ("ffilig", "ffi"),
+    ("fflig", "ff"),
+    ("ffllig", "ffl"),
+    ("ffr", "𝔣"),
+    ("filig", "fi"),
+    ("fjlig", "fj"),
+    ("flat", "♭"),
+    ("fllig", "fl"),
+    ("fltns", "▱"),
+    ("fnof", "ƒ"),
+    ("fopf", "𝕗"),
+    ("forall", "∀"),
+    ("fork", "⋔"),
+    ("forkv", "⫙"),
+    ("fpartint", "⨍"),
+    ("frac12", "½"),
+    ("frac13", "⅓"),
+    ("frac14", "¼"),
+    ("frac15", "⅕"),
+    ("frac16", "⅙"),
+    ("frac18", "⅛"),
+    ("frac23", "⅔"),
+    ("frac25", "⅖"),
+    ("frac34", "¾"),
+    ("frac35", "⅗"),
+    ("frac38", "⅜"),
+    ("frac45", "⅘"),
+    ("frac56", "⅚"),
+    ("frac58", "⅝"),
+    ("frac78", "⅞"),
+    ("frasl", "⁄"),
+    ("frown", "⌢"),
+    ("fscr", "𝒻"),
+    ("gE", "≧"),
+    ("gEl", "⪌"),
+    ("gacute", "ǵ"),
+    ("gamma", "γ"),
+    ("gammad", "ϝ"),
+    ("gap", "⪆"),
+    ("gbreve", "ğ"),
+    ("gcirc", "ĝ"),
+    ("gcy", "г"),
+    ("gdot", "ġ"),
+    ("ge", "≥"),
+    ("gel", "⋛"),
+    ("geq", "≥"),
+    ("geqq", "≧"),
+    ("geqslant", "⩾"),
+    ("ges", "⩾"),
+    ("gescc", "⪩"),
+    ("gesdot", "⪀"),
+    ("gesdoto", "⪂"),
+    ("gesdotol", "⪄"),
+    ("gesl", "⋛︀"),
+    ("gesles", "⪔"),
+    ("gfr", "𝔤"),
+    ("gg", "≫"),
+    ("ggg", "⋙"),
+    ("gimel", "ℷ"),
+    ("gjcy", "ѓ"),
+    ("gl", "≷"),
+    ("glE", "⪒"),
+    ("gla", "⪥"),
+    ("glj", "⪤"),
+    ("gnE", "≩"),
+    ("gnap", "⪊"),
+    ("gnapprox", "⪊"),
+    ("gne", "⪈"),
+    ("gneq", "⪈"),
+    ("gneqq", "≩"),
+    ("gnsim", "⋧"),
+    ("gopf", "𝕘"),
+    ("grave", "`"),
+    ("gscr", "ℊ"),
+    ("gsim", "≳"),
+    ("gsime", "⪎"),
+    ("gsiml", "⪐"),
+    ("gt", ">"),
+    ("gtcc", "⪧"),
+    ("gtcir", "⩺"),
+    ("gtdot", "⋗"),
+    ("gtlPar", "⦕"),
+    ("gtquest", "⩼"),
+    ("gtrapprox", "⪆"),
+    ("gtrarr", "⥸"),
+    ("gtrdot", "⋗"),
+    ("gtreqless", "⋛"),
+    ("gtreqqless", "⪌"),
+    ("gtrless", "≷"),
+    ("gtrsim", "≳"),
+    ("gvertneqq", "≩︀"),
+    ("gvnE", "≩︀"),
+    ("hArr", "⇔"),
+    ("hairsp", " "),
+    ("half", "½"),
+    ("hamilt", "ℋ"),
+    ("hardcy", "ъ"),
+    ("harr", "↔"),
+    ("harrcir", "⥈"),
+    ("harrw", "↭"),
+    ("hbar", "ℏ"),
+    ("hcirc", "ĥ"),
+    ("hearts", "♥"),
+    ("heartsuit", "♥"),
+    ("hellip", "…"),
+    ("hercon", "⊹"),
+    ("hfr", "𝔥"),
+    ("hksearow", "⤥"),
+    ("hkswarow", "⤦"),
+    ("hoarr", "⇿"),
+    ("homtht", "∻"),
+    ("hookleftarrow", "↩"),
+    ("hookrightarrow", "↪"),
+    ("hopf", "𝕙"),
+    ("horbar", "―"),
+    ("hscr", "𝒽"),
+    ("hslash", "ℏ"),
+    ("hstrok", "ħ"),
+    ("hybull", "⁃"),
+    ("hyphen", "‐"),
+    ("iacute", "í"),
+    ("ic", "⁣"),
+    ("icirc", "î"),
+    ("icy", "и"),
+    ("iecy", "е"),
+    ("iexcl", "¡"),
+    ("iff", "⇔"),
+    ("ifr", "𝔦"),
+    ("igrave", "ì"),
+    ("ii", "ⅈ"),
+    ("iiiint", "⨌"),
+    ("iiint", "∭"),
+    ("iinfin", "⧜"),
+    ("iiota", "℩"),
+    ("ijlig", "ij"),
+    ("imacr", "ī"),
+    ("image", "ℑ"),
+    ("imagline", "ℐ"),
+    ("imagpart", "ℑ"),
+    ("imath", "ı"),
+    ("imof", "⊷"),
+    ("imped", "Ƶ"),
+    ("in", "∈"),
+    ("incare", "℅"),
+    ("infin", "∞"),
+    ("infintie", "⧝"),
+    ("inodot", "ı"),
+    ("int", "∫"),
+    ("intcal", "⊺"),
+    ("integers", "ℤ"),
+    ("intercal", "⊺"),
+    ("intlarhk", "⨗"),
+    ("intprod", "⨼"),
+    ("iocy", "ё"),
+    ("iogon", "į"),
+    ("iopf", "𝕚"),
+    ("iota", "ι"),
+    ("iprod", "⨼"),
+    ("iquest", "¿"),
+    ("iscr", "𝒾"),
+    ("isin", "∈"),
+    ("isinE", "⋹"),
+    ("isindot", "⋵"),
+    ("isins", "⋴"),
+    ("isinsv", "⋳"),
+    ("isinv", "∈"),
+    ("it", "⁢"),
+    ("itilde", "ĩ"),
+    ("iukcy", "і"),
+    ("iuml", "ï"),
+    ("jcirc", "ĵ"),
+    ("jcy", "й"),
+    ("jfr", "𝔧"),
+    ("jmath", "ȷ"),
+    ("jopf", "𝕛"),
+    ("jscr", "𝒿"),
+    ("jsercy", "ј"),
+    ("jukcy", "є"),
+    ("kappa", "κ"),
+    ("kappav", "ϰ"),
+    ("kcedil", "ķ"),
+    ("kcy", "к"),
+    ("kfr", "𝔨"),
+    ("kgreen", "ĸ"),
+    ("khcy", "х"),
+    ("kjcy", "ќ"),
+    ("kopf", "𝕜"),
+    ("kscr", "𝓀"),
+    ("lAarr", "⇚"),
+    ("lArr", "⇐"),
+    ("lAtail", "⤛"),
+    ("lBarr", "⤎"),
+    ("lE", "≦"),
+    ("lEg", "⪋"),
+    ("lHar", "⥢"),
+    ("lacute", "ĺ"),
+    ("laemptyv", "⦴"),
+    ("lagran", "ℒ"),
+    ("lambda", "λ"),
+    ("lang", "⟨"),
+    ("langd", "⦑"),
+    ("langle", "⟨"),
+    ("lap", "⪅"),
+    ("laquo", "«"),
+    ("larr", "←"),
+    ("larrb", "⇤"),
+    ("larrbfs", "⤟"),
+    ("larrfs", "⤝"),
+    ("larrhk", "↩"),
+    ("larrlp", "↫"),
+    ("larrpl", "⤹"),
+    ("larrsim", "⥳"),
+    ("larrtl", "↢"),
+    ("lat", "⪫"),
+    ("latail", "⤙"),
+    ("late", "⪭"),
+    ("lates", "⪭︀"),
+    ("lbarr", "⤌"),
+    ("lbbrk", "❲"),
+    ("lbrace", "{"),
+    ("lbrack", "["),
+    ("lbrke", "⦋"),
+    ("lbrksld", "⦏"),
+    ("lbrkslu", "⦍"),
+    ("lcaron", "ľ"),
+    ("lcedil", "ļ"),
+    ("lceil", "⌈"),
+    ("lcub", "{"),
+    ("lcy", "л"),
+    ("ldca", "⤶"),
+    ("ldquo", "“"),
+    ("ldquor", "„"),
+    ("ldrdhar", "⥧"),
+    ("ldrushar", "⥋"),
+    ("ldsh", "↲"),
+    ("le", "≤"),
+    ("leftarrow", "←"),
+    ("leftarrowtail", "↢"),
+    ("leftharpoondown", "↽"),
+    ("leftharpoonup", "↼"),
+    ("leftleftarrows", "⇇"),
+    ("leftrightarrow", "↔"),
+    ("leftrightarrows", "⇆"),
+    ("leftrightharpoons", "⇋"),
+    ("leftrightsquigarrow", "↭"),
+    ("leftthreetimes", "⋋"),
+    ("leg", "⋚"),
+    ("leq", "≤"),
+    ("leqq", "≦"),
+    ("leqslant", "⩽"),
+    ("les", "⩽"),
+    ("lescc", "⪨"),
+    ("lesdot", "⩿"),
+    ("lesdoto", "⪁"),
+    ("lesdotor", "⪃"),
+    ("lesg", "⋚︀"),
+    ("lesges", "⪓"),
+    ("lessapprox", "⪅"),
+    ("lessdot", "⋖"),
+    ("lesseqgtr", "⋚"),
+    ("lesseqqgtr", "⪋"),
+    ("lessgtr", "≶"),
+    ("lesssim", "≲"),
+    ("lfisht", "⥼"),
+    ("lfloor", "⌊"),
+    ("lfr", "𝔩"),
+    ("lg", "≶"),
+    ("lgE", "⪑"),
+    ("lhard", "↽"),
+    ("lharu", "↼"),
+    ("lharul", "⥪"),
+    ("lhblk", "▄"),
+    ("ljcy", "љ"),
+    ("ll", "≪"),
+    ("llarr", "⇇"),
+    ("llcorner", "⌞"),
+    ("llhard", "⥫"),
+    ("lltri", "◺"),
+    ("lmidot", "ŀ"),
+    ("lmoust", "⎰"),
+    ("lmoustache", "⎰"),
+    ("lnE", "≨"),
+    ("lnap", "⪉"),
+    ("lnapprox", "⪉"),
+    ("lne", "⪇"),
+    ("lneq", "⪇"),
+    ("lneqq", "≨"),
+    ("lnsim", "⋦"),
+    ("loang", "⟬"),
+    ("loarr", "⇽"),
+    ("lobrk", "⟦"),
+    ("longleftarrow", "⟵"),
+    ("longleftrightarrow", "⟷"),
+    ("longmapsto", "⟼"),
+    ("longrightarrow", "⟶"),
+    ("looparrowleft", "↫"),
+    ("looparrowright", "↬"),
+    ("lopar", "⦅"),
+    ("lopf", "𝕝"),
+    ("loplus", "⨭"),
+    ("lotimes", "⨴"),
+    ("lowast", "∗"),
+    ("lowbar", "_"),
+    ("loz", "◊"),
+    ("lozenge", "◊"),
+    ("lozf", "⧫"),
+    ("lpar", "("),
+    ("lparlt", "⦓"),
+    ("lrarr", "⇆"),
+    ("lrcorner", "⌟"),
+    ("lrhar", "⇋"),
+    ("lrhard", "⥭"),
+    ("lrm", "‎"),
+    ("lrtri", "⊿"),
+    ("lsaquo", "‹"),
+    ("lscr", "𝓁"),
+    ("lsh", "↰"),
+    ("lsim", "≲"),
+    ("lsime", "⪍"),
+    ("lsimg", "⪏"),
+    ("lsqb", "["),
+    ("lsquo", "‘"),
+    ("lsquor", "‚"),
+    ("lstrok", "ł"),
+    ("lt", "<"),
+    ("ltcc", "⪦"),
+    ("ltcir", "⩹"),
+    ("ltdot", "⋖"),
+    ("lthree", "⋋"),
+    ("ltimes", "⋉"),
+    ("ltlarr", "⥶"),
+    ("ltquest", "⩻"),
+    ("ltrPar", "⦖"),
+    ("ltri", "◃"),
+    ("ltrie", "⊴"),
+    ("ltrif", "◂"),
+    ("lurdshar", "⥊"),
+    ("luruhar", "⥦"),
+    ("lvertneqq", "≨︀"),
+    ("lvnE", "≨︀"),
+    ("mDDot", "∺"),
+    ("macr", "¯"),
+    ("male", "♂"),
+    ("malt", "✠"),
+    ("maltese", "✠"),
+    ("map", "↦"),
+    ("mapsto", "↦"),
+    ("mapstodown", "↧"),
+    ("mapstoleft", "↤"),
+    ("mapstoup", "↥"),
+    ("marker", "▮"),
+    ("mcomma", "⨩"),
+    ("mcy", "м"),
+    ("mdash", "—"),
+    ("measuredangle", "∡"),
+    ("mfr", "𝔪"),
+    ("mho", "℧"),
+    ("micro", "µ"),
+    ("mid", "∣"),
+    ("midast", "*"),
+    ("midcir", "⫰"),
+    ("middot", "·"),
+    ("minus", "−"),
+    ("minusb", "⊟"),
+    ("minusd", "∸"),
+    ("minusdu", "⨪"),
+    ("mlcp", "⫛"),
+    ("mldr", "…"),
+    ("mnplus", "∓"),
+    ("models", "⊧"),
+    ("mopf", "𝕞"),
+    ("mp", "∓"),
+    ("mscr", "𝓂"),
+    ("mstpos", "∾"),
+    ("mu", "μ"),
+    ("multimap", "⊸"),
+    ("mumap", "⊸"),
+    ("nGg", "⋙̸"),
+    ("nGt", "≫⃒"),
+    ("nGtv", "≫̸"),
+    ("nLeftarrow", "⇍"),
+    ("nLeftrightarrow", "⇎"),
+    ("nLl", "⋘̸"),
+    ("nLt", "≪⃒"),
+    ("nLtv", "≪̸"),
+    ("nRightarrow", "⇏"),
+    ("nVDash", "⊯"),
+    ("nVdash", "⊮"),
+    ("nabla", "∇"),
+    ("nacute", "ń"),
+    ("nang", "∠⃒"),
+    ("nap", "≉"),
+    ("napE", "⩰̸"),
+    ("napid", "≋̸"),
+    ("napos", "ʼn"),
+    ("napprox", "≉"),
+    ("natur", "♮"),
+    ("natural", "♮"),
+    ("naturals", "ℕ"),
+    ("nbsp", " "),
+    ("nbump", "≎̸"),
+    ("nbumpe", "≏̸"),
+    ("ncap", "⩃"),
+    ("ncaron", "ň"),
+    ("ncedil", "ņ"),
+    ("ncong", "≇"),
+    ("ncongdot", "⩭̸"),
+    ("ncup", "⩂"),
+    ("ncy", "н"),
+    ("ndash", "–"),
+    ("ne", "≠"),
+    ("neArr", "⇗"),
+    ("nearhk", "⤤"),
+    ("nearr", "↗"),
+    ("nearrow", "↗"),
+    ("nedot", "≐̸"),
+    ("nequiv", "≢"),
+    ("nesear", "⤨"),
+    ("nesim", "≂̸"),
+    ("nexist", "∄"),
+    ("nexists", "∄"),
+    ("nfr", "𝔫"),
+    ("ngE", "≧̸"),
+    ("nge", "≱"),
+    ("ngeq", "≱"),
+    ("ngeqq", "≧̸"),
+    ("ngeqslant", "⩾̸"),
+    ("nges", "⩾̸"),
+    ("ngsim", "≵"),
+    ("ngt", "≯"),
+    ("ngtr", "≯"),
+    ("nhArr", "⇎"),
+    ("nharr", "↮"),
+    ("nhpar", "⫲"),
+    ("ni", "∋"),
+    ("nis", "⋼"),
+    ("nisd", "⋺"),
+    ("niv", "∋"),
+    ("njcy", "њ"),
+    ("nlArr", "⇍"),
+    ("nlE", "≦̸"),
+    ("nlarr", "↚"),
+    ("nldr", "‥"),
+    ("nle", "≰"),
+    ("nleftarrow", "↚"),
+    ("nleftrightarrow", "↮"),
+    ("nleq", "≰"),
+    ("nleqq", "≦̸"),
+    ("nleqslant", "⩽̸"),
+    ("nles", "⩽̸"),
+    ("nless", "≮"),
+    ("nlsim", "≴"),
+    ("nlt", "≮"),
+    ("nltri", "⋪"),
+    ("nltrie", "⋬"),
+    ("nmid", "∤"),
+    ("nopf", "𝕟"),
+    ("not", "¬"),
+    ("notin", "∉"),
+    ("notinE", "⋹̸"),
+    ("notindot", "⋵̸"),
+    ("notinva", "∉"),
+    ("notinvb", "⋷"),
+    ("notinvc", "⋶"),
+    ("notni", "∌"),
+    ("notniva", "∌"),
+    ("notnivb", "⋾"),
+    ("notnivc", "⋽"),
+    ("npar", "∦"),
+    ("nparallel", "∦"),
+    ("nparsl", "⫽⃥"),
+    ("npart", "∂̸"),
+    ("npolint", "⨔"),
+    ("npr", "⊀"),
+    ("nprcue", "⋠"),
+    ("npre", "⪯̸"),
+    ("nprec", "⊀"),
+    ("npreceq", "⪯̸"),
+    ("nrArr", "⇏"),
+    ("nrarr", "↛"),
+    ("nrarrc", "⤳̸"),
+    ("nrarrw", "↝̸"),
+    ("nrightarrow", "↛"),
+    ("nrtri", "⋫"),
+    ("nrtrie", "⋭"),
+    ("nsc", "⊁"),
+    ("nsccue", "⋡"),
+    ("nsce", "⪰̸"),
+    ("nscr", "𝓃"),
+    ("nshortmid", "∤"),
+    ("nshortparallel", "∦"),
+    ("nsim", "≁"),
+    ("nsime", "≄"),
+    ("nsimeq", "≄"),
+    ("nsmid", "∤"),
+    ("nspar", "∦"),
+    ("nsqsube", "⋢"),
+    ("nsqsupe", "⋣"),
+    ("nsub", "⊄"),
+    ("nsubE", "⫅̸"),
+    ("nsube", "⊈"),
+    ("nsubset", "⊂⃒"),
+    ("nsubseteq", "⊈"),
+    ("nsubseteqq", "⫅̸"),
+    ("nsucc", "⊁"),
+    ("nsucceq", "⪰̸"),
+    ("nsup", "⊅"),
+    ("nsupE", "⫆̸"),
+    ("nsupe", "⊉"),
+    ("nsupset", "⊃⃒"),
+    ("nsupseteq", "⊉"),
+    ("nsupseteqq", "⫆̸"),
+    ("ntgl", "≹"),
+    ("ntilde", "ñ"),
+    ("ntlg", "≸"),
+    ("ntriangleleft", "⋪"),
+    ("ntrianglelefteq", "⋬"),
+    ("ntriangleright", "⋫"),
+    ("ntrianglerighteq", "⋭"),
+    ("nu", "ν"),
+    ("num", "#"),
+    ("numero", "№"),
+    ("numsp", " "),
+    ("nvDash", "⊭"),
+    ("nvHarr", "⤄"),
+    ("nvap", "≍⃒"),
+    ("nvdash", "⊬"),
+    ("nvge", "≥⃒"),
+    ("nvgt", ">⃒"),
+    ("nvinfin", "⧞"),
+    ("nvlArr", "⤂"),
+    ("nvle", "≤⃒"),
+    ("nvlt", "<⃒"),
+    ("nvltrie", "⊴⃒"),
+    ("nvrArr", "⤃"),
+    ("nvrtrie", "⊵⃒"),
+    ("nvsim", "∼⃒"),
+    ("nwArr", "⇖"),
+    ("nwarhk", "⤣"),
+    ("nwarr", "↖"),
+    ("nwarrow", "↖"),
+    ("nwnear", "⤧"),
+    ("oS", "Ⓢ"),
+    ("oacute", "ó"),
+    ("oast", "⊛"),
+    ("ocir", "⊚"),
+    ("ocirc", "ô"),
+    ("ocy", "о"),
+    ("odash", "⊝"),
+    ("odblac", "ő"),
+    ("odiv", "⨸"),
+    ("odot", "⊙"),
+    ("odsold", "⦼"),
+    ("oelig", "œ"),
+    ("ofcir", "⦿"),
+    ("ofr", "𝔬"),
+    ("ogon", "˛"),
+    ("ograve", "ò"),
+    ("ogt", "⧁"),
+    ("ohbar", "⦵"),
+    ("ohm", "Ω"),
+    ("oint", "∮"),
+    ("olarr", "↺"),
+    ("olcir", "⦾"),
+    ("olcross", "⦻"),
+    ("oline", "‾"),
+    ("olt", "⧀"),
+    ("omacr", "ō"),
+    ("omega", "ω"),
+    ("omicron", "ο"),
+    ("omid", "⦶"),
+    ("ominus", "⊖"),
+    ("oopf", "𝕠"),
+    ("opar", "⦷"),
+    ("operp", "⦹"),
+    ("oplus", "⊕"),
+    ("or", "∨"),
+    ("orarr", "↻"),
+    ("ord", "⩝"),
+    ("order", "ℴ"),
+    ("orderof", "ℴ"),
+    ("ordf", "ª"),
+    ("ordm", "º"),
+    ("origof", "⊶"),
+    ("oror", "⩖"),
+    ("orslope", "⩗"),
+    ("orv", "⩛"),
+    ("oscr", "ℴ"),
+    ("oslash", "ø"),
+    ("osol", "⊘"),
+    ("otilde", "õ"),
+    ("otimes", "⊗"),
+    ("otimesas", "⨶"),
+    ("ouml", "ö"),
+    ("ovbar", "⌽"),
+    ("par", "∥"),
+    ("para", "¶"),
+    ("parallel", "∥"),
+    ("parsim", "⫳"),
+    ("parsl", "⫽"),
+    ("part", "∂"),
+    ("pcy", "п"),
+    ("percnt", "%"),
+    ("period", "."),
+    ("permil", "‰"),
+    ("perp", "⊥"),
+    ("pertenk", "‱"),
+    ("pfr", "𝔭"),
+    ("phi", "φ"),
+    ("phiv", "ϕ"),
+    ("phmmat", "ℳ"),
+    ("phone", "☎"),
+    ("pi", "π"),
+    ("pitchfork", "⋔"),
+    ("piv", "ϖ"),
+    ("planck", "ℏ"),
+    ("planckh", "ℎ"),
+    ("plankv", "ℏ"),
+    ("plus", "+"),
+    ("plusacir", "⨣"),
+    ("plusb", "⊞"),
+    ("pluscir", "⨢"),
+    ("plusdo", "∔"),
+    ("plusdu", "⨥"),
+    ("pluse", "⩲"),
+    ("plusmn", "±"),
+    ("plussim", "⨦"),
+    ("plustwo", "⨧"),
+    ("pm", "±"),
+    ("pointint", "⨕"),
+    ("popf", "𝕡"),
+    ("pound", "£"),
+    ("pr", "≺"),
+    ("prE", "⪳"),
+    ("prap", "⪷"),
+    ("prcue", "≼"),
+    ("pre", "⪯"),
+    ("prec", "≺"),
+    ("precapprox", "⪷"),
+    ("preccurlyeq", "≼"),
+    ("preceq", "⪯"),
+    ("precnapprox", "⪹"),
+    ("precneqq", "⪵"),
+    ("precnsim", "⋨"),
+    ("precsim", "≾"),
+    ("prime", "′"),
+    ("primes", "ℙ"),
+    ("prnE", "⪵"),
+    ("prnap", "⪹"),
+    ("prnsim", "⋨"),
+    ("prod", "∏"),
+    ("profalar", "⌮"),
+    ("profline", "⌒"),
+    ("profsurf", "⌓"),
+    ("prop", "∝"),
+    ("propto", "∝"),
+    ("prsim", "≾"),
+    ("prurel", "⊰"),
+    ("pscr", "𝓅"),
+    ("psi", "ψ"),
+    ("puncsp", " "),
+    ("qfr", "𝔮"),
+    ("qint", "⨌"),
+    ("qopf", "𝕢"),
+    ("qprime", "⁗"),
+    ("qscr", "𝓆"),
+    ("quaternions", "ℍ"),
+    ("quatint", "⨖"),
+    ("quest", "?"),
+    ("questeq", "≟"),
+    ("quot", "\""),
+    ("rAarr", "⇛"),
+    ("rArr", "⇒"),
+    ("rAtail", "⤜"),
+    ("rBarr", "⤏"),
+    ("rHar", "⥤"),
+    ("race", "∽̱"),
+    ("racute", "ŕ"),
+    ("radic", "√"),
+    ("raemptyv", "⦳"),
+    ("rang", "⟩"),
+    ("rangd", "⦒"),
+    ("range", "⦥"),
+    ("rangle", "⟩"),
+    ("raquo", "»"),
+    ("rarr", "→"),
+    ("rarrap", "⥵"),
+    ("rarrb", "⇥"),
+    ("rarrbfs", "⤠"),
+    ("rarrc", "⤳"),
+    ("rarrfs", "⤞"),
+    ("rarrhk", "↪"),
+    ("rarrlp", "↬"),
+    ("rarrpl", "⥅"),
+    ("rarrsim", "⥴"),
+    ("rarrtl", "↣"),
+    ("rarrw", "↝"),
+    ("ratail", "⤚"),
+    ("ratio", "∶"),
+    ("rationals", "ℚ"),
+    ("rbarr", "⤍"),
+    ("rbbrk", "❳"),
+    ("rbrace", "}"),
+    ("rbrack", "]"),
+    ("rbrke", "⦌"),
+    ("rbrksld", "⦎"),
+    ("rbrkslu", "⦐"),
+    ("rcaron", "ř"),
+    ("rcedil", "ŗ"),
+    ("rceil", "⌉"),
+    ("rcub", "}"),
+    ("rcy", "р"),
+    ("rdca", "⤷"),
+    ("rdldhar", "⥩"),
+    ("rdquo", "”"),
+    ("rdquor", "”"),
+    ("rdsh", "↳"),
+    ("real", "ℜ"),
+    ("realine", "ℛ"),
+    ("realpart", "ℜ"),
+    ("reals", "ℝ"),
+    ("rect", "▭"),
+    ("reg", "®"),
+    ("rfisht", "⥽"),
+    ("rfloor", "⌋"),
+    ("rfr", "𝔯"),
+    ("rhard", "⇁"),
+    ("rharu", "⇀"),
+    ("rharul", "⥬"),
+    ("rho", "ρ"),
+    ("rhov", "ϱ"),
+    ("rightarrow", "→"),
+    ("rightarrowtail", "↣"),
+    ("rightharpoondown", "⇁"),
+    ("rightharpoonup", "⇀"),
+    ("rightleftarrows", "⇄"),
+    ("rightleftharpoons", "⇌"),
+    ("rightrightarrows", "⇉"),
+    ("rightsquigarrow", "↝"),
+    ("rightthreetimes", "⋌"),
+    ("ring", "˚"),
+    ("risingdotseq", "≓"),
+    ("rlarr", "⇄"),
+    ("rlhar", "⇌"),
+    ("rlm", "‏"),
+    ("rmoust", "⎱"),
+    ("rmoustache", "⎱"),
+    ("rnmid", "⫮"),
+    ("roang", "⟭"),
+    ("roarr", "⇾"),
+    ("robrk", "⟧"),
+    ("ropar", "⦆"),
+    ("ropf", "𝕣"),
+    ("roplus", "⨮"),
+    ("rotimes", "⨵"),
+    ("rpar", ")"),
+    ("rpargt", "⦔"),
+    ("rppolint", "⨒"),
+    ("rrarr", "⇉"),
+    ("rsaquo", "›"),
+    ("rscr", "𝓇"),
+    ("rsh", "↱"),
+    ("rsqb", "]"),
+    ("rsquo", "’"),
+    ("rsquor", "’"),
+    ("rthree", "⋌"),
+    ("rtimes", "⋊"),
+    ("rtri", "▹"),
+    ("rtrie", "⊵"),
+    ("rtrif", "▸"),
+    ("rtriltri", "⧎"),
+    ("ruluhar", "⥨"),
+    ("rx", "℞"),
+    ("sacute", "ś"),
+    ("sbquo", "‚"),
+    ("sc", "≻"),
+    ("scE", "⪴"),
+    ("scap", "⪸"),
+    ("scaron", "š"),
+    ("sccue", "≽"),
+    ("sce", "⪰"),
+    ("scedil", "ş"),
+    ("scirc", "ŝ"),
+    ("scnE", "⪶"),
+    ("scnap", "⪺"),
+    ("scnsim", "⋩"),
+    ("scpolint", "⨓"),
+    ("scsim", "≿"),
+    ("scy", "с"),
+    ("sdot", "⋅"),
+    ("sdotb", "⊡"),
+    ("sdote", "⩦"),
+    ("seArr", "⇘"),
+    ("searhk", "⤥"),
+    ("searr", "↘"),
+    ("searrow", "↘"),
+    ("sect", "§"),
+    ("semi", ";"),
+    ("seswar", "⤩"),
+    ("setminus", "∖"),
+    ("setmn", "∖"),
+    ("sext", "✶"),
+    ("sfr", "𝔰"),
+    ("sfrown", "⌢"),
+    ("sharp", "♯"),
+    ("shchcy", "щ"),
+    ("shcy", "ш"),
+    ("shortmid", "∣"),
+    ("shortparallel", "∥"),
+    ("shy", "\u{AD}"),
+    ("sigma", "σ"),
+    ("sigmaf", "ς"),
+    ("sigmav", "ς"),
+    ("sim", "∼"),
+    ("simdot", "⩪"),
+    ("sime", "≃"),
+    ("simeq", "≃"),
+    ("simg", "⪞"),
+    ("simgE", "⪠"),
+    ("siml", "⪝"),
+    ("simlE", "⪟"),
+    ("simne", "≆"),
+    ("simplus", "⨤"),
+    ("simrarr", "⥲"),
+    ("slarr", "←"),
+    ("smallsetminus", "∖"),
+    ("smashp", "⨳"),
+    ("smeparsl", "⧤"),
+    ("smid", "∣"),
+    ("smile", "⌣"),
+    ("smt", "⪪"),
+    ("smte", "⪬"),
+    ("smtes", "⪬︀"),
+    ("softcy", "ь"),
+    ("sol", "/"),
+    ("solb", "⧄"),
+    ("solbar", "⌿"),
+    ("sopf", "𝕤"),
+    ("spades", "♠"),
+    ("spadesuit", "♠"),
+    ("spar", "∥"),
+    ("sqcap", "⊓"),
+    ("sqcaps", "⊓︀"),
+    ("sqcup", "⊔"),
+    ("sqcups", "⊔︀"),
+    ("sqsub", "⊏"),
+    ("sqsube", "⊑"),
+    ("sqsubset", "⊏"),
+    ("sqsubseteq", "⊑"),
+    ("sqsup", "⊐"),
+    ("sqsupe", "⊒"),
+    ("sqsupset", "⊐"),
+    ("sqsupseteq", "⊒"),
+    ("squ", "□"),
+    ("square", "□"),
+    ("squarf", "▪"),
+    ("squf", "▪"),
+    ("srarr", "→"),
+    ("sscr", "𝓈"),
+    ("ssetmn", "∖"),
+    ("ssmile", "⌣"),
+    ("sstarf", "⋆"),
+    ("star", "☆"),
+    ("starf", "★"),
+    ("straightepsilon", "ϵ"),
+    ("straightphi", "ϕ"),
+    ("strns", "¯"),
+    ("sub", "⊂"),
+    ("subE", "⫅"),
+    ("subdot", "⪽"),
+    ("sube", "⊆"),
+    ("subedot", "⫃"),
+    ("submult", "⫁"),
+    ("subnE", "⫋"),
+    ("subne", "⊊"),
+    ("subplus", "⪿"),
+    ("subrarr", "⥹"),
+    ("subset", "⊂"),
+    ("subseteq", "⊆"),
+    ("subseteqq", "⫅"),
+    ("subsetneq", "⊊"),
+    ("subsetneqq", "⫋"),
+    ("subsim", "⫇"),
+    ("subsub", "⫕"),
+    ("subsup", "⫓"),
+    ("succ", "≻"),
+    ("succapprox", "⪸"),
+    ("succcurlyeq", "≽"),
+    ("succeq", "⪰"),
+    ("succnapprox", "⪺"),
+    ("succneqq", "⪶"),
+    ("succnsim", "⋩"),
+    ("succsim", "≿"),
+    ("sum", "∑"),
+    ("sung", "♪"),
+    ("sup1", "¹"),
+    ("sup2", "²"),
+    ("sup3", "³"),
+    ("sup", "⊃"),
+    ("supE", "⫆"),
+    ("supdot", "⪾"),
+    ("supdsub", "⫘"),
+    ("supe", "⊇"),
+    ("supedot", "⫄"),
+    ("suphsol", "⟉"),
+    ("suphsub", "⫗"),
+    ("suplarr", "⥻"),
+    ("supmult", "⫂"),
+    ("supnE", "⫌"),
+    ("supne", "⊋"),
+    ("supplus", "⫀"),
+    ("supset", "⊃"),
+    ("supseteq", "⊇"),
+    ("supseteqq", "⫆"),
+    ("supsetneq", "⊋"),
+    ("supsetneqq", "⫌"),
+    ("supsim", "⫈"),
+    ("supsub", "⫔"),
+    ("supsup", "⫖"),
+    ("swArr", "⇙"),
+    ("swarhk", "⤦"),
+    ("swarr", "↙"),
+    ("swarrow", "↙"),
+    ("swnwar", "⤪"),
+    ("szlig", "ß"),
+    ("target", "⌖"),
+    ("tau", "τ"),
+    ("tbrk", "⎴"),
+    ("tcaron", "ť"),
+    ("tcedil", "ţ"),
+    ("tcy", "т"),
+    ("tdot", "⃛"),
+    ("telrec", "⌕"),
+    ("tfr", "𝔱"),
+    ("there4", "∴"),
+    ("therefore", "∴"),
+    ("theta", "θ"),
+    ("thetasym", "ϑ"),
+    ("thetav", "ϑ"),
+    ("thickapprox", "≈"),
+    ("thicksim", "∼"),
+    ("thinsp", " "),
+    ("thkap", "≈"),
+    ("thksim", "∼"),
+    ("thorn", "þ"),
+    ("tilde", "˜"),
+    ("times", "×"),
+    ("timesb", "⊠"),
+    ("timesbar", "⨱"),
+    ("timesd", "⨰"),
+    ("tint", "∭"),
+    ("toea", "⤨"),
+    ("top", "⊤"),
+    ("topbot", "⌶"),
+    ("topcir", "⫱"),
+    ("topf", "𝕥"),
+    ("topfork", "⫚"),
+    ("tosa", "⤩"),
+    ("tprime", "‴"),
+    ("trade", "™"),
+    ("triangle", "▵"),
+    ("triangledown", "▿"),
+    ("triangleleft", "◃"),
+    ("trianglelefteq", "⊴"),
+    ("triangleq", "≜"),
+    ("triangleright", "▹"),
+    ("trianglerighteq", "⊵"),
+    ("tridot", "◬"),
+    ("trie", "≜"),
+    ("triminus", "⨺"),
+    ("triplus", "⨹"),
+    ("trisb", "⧍"),
+    ("tritime", "⨻"),
+    ("trpezium", "⏢"),
+    ("tscr", "𝓉"),
+    ("tscy", "ц"),
+    ("tshcy", "ћ"),
+    ("tstrok", "ŧ"),
+    ("twixt", "≬"),
+    ("twoheadleftarrow", "↞"),
+    ("twoheadrightarrow", "↠"),
+    ("uArr", "⇑"),
+    ("uHar", "⥣"),
+    ("uacute", "ú"),
+    ("uarr", "↑"),
+    ("ubrcy", "ў"),
+    ("ubreve", "ŭ"),
+    ("ucirc", "û"),
+    ("ucy", "у"),
+    ("udarr", "⇅"),
+    ("udblac", "ű"),
+    ("udhar", "⥮"),
+    ("ufisht", "⥾"),
+    ("ufr", "𝔲"),
+    ("ugrave", "ù"),
+    ("uharl", "↿"),
+    ("uharr", "↾"),
+    ("uhblk", "▀"),
+    ("ulcorn", "⌜"),
+    ("ulcorner", "⌜"),
+    ("ulcrop", "⌏"),
+    ("ultri", "◸"),
+    ("umacr", "ū"),
+    ("uml", "¨"),
+    ("uogon", "ų"),
+    ("uopf", "𝕦"),
+    ("uparrow", "↑"),
+    ("updownarrow", "↕"),
+    ("upharpoonleft", "↿"),
+    ("upharpoonright", "↾"),
+    ("uplus", "⊎"),
+    ("upsi", "υ"),
+    ("upsih", "ϒ"),
+    ("upsilon", "υ"),
+    ("upuparrows", "⇈"),
+    ("urcorn", "⌝"),
+    ("urcorner", "⌝"),
+    ("urcrop", "⌎"),
+    ("uring", "ů"),
+    ("urtri", "◹"),
+    ("uscr", "𝓊"),
+    ("utdot", "⋰"),
+    ("utilde", "ũ"),
+    ("utri", "▵"),
+    ("utrif", "▴"),
+    ("uuarr", "⇈"),
+    ("uuml", "ü"),
+    ("uwangle", "⦧"),
+    ("vArr", "⇕"),
+    ("vBar", "⫨"),
+    ("vBarv", "⫩"),
+    ("vDash", "⊨"),
+    ("vangrt", "⦜"),
+    ("varepsilon", "ϵ"),
+    ("varkappa", "ϰ"),
+    ("varnothing", "∅"),
+    ("varphi", "ϕ"),
+    ("varpi", "ϖ"),
+    ("varpropto", "∝"),
+    ("varr", "↕"),
+    ("varrho", "ϱ"),
+    ("varsigma", "ς"),
+    ("varsubsetneq", "⊊︀"),
+    ("varsubsetneqq", "⫋︀"),
+    ("varsupsetneq", "⊋︀"),
+    ("varsupsetneqq", "⫌︀"),
+    ("vartheta", "ϑ"),
+    ("vartriangleleft", "⊲"),
+    ("vartriangleright", "⊳"),
+    ("vcy", "в"),
+    ("vdash", "⊢"),
+    ("vee", "∨"),
+    ("veebar", "⊻"),
+    ("veeeq", "≚"),
+    ("vellip", "⋮"),
+    ("verbar", "|"),
+    ("vert", "|"),
+    ("vfr", "𝔳"),
+    ("vltri", "⊲"),
+    ("vnsub", "⊂⃒"),
+    ("vnsup", "⊃⃒"),
+    ("vopf", "𝕧"),
+    ("vprop", "∝"),
+    ("vrtri", "⊳"),
+    ("vscr", "𝓋"),
+    ("vsubnE", "⫋︀"),
+    ("vsubne", "⊊︀"),
+    ("vsupnE", "⫌︀"),
+    ("vsupne", "⊋︀"),
+    ("vzigzag", "⦚"),
+    ("wcirc", "ŵ"),
+    ("wedbar", "⩟"),
+    ("wedge", "∧"),
+    ("wedgeq", "≙"),
+    ("weierp", "℘"),
+    ("wfr", "𝔴"),
+    ("wopf", "𝕨"),
+    ("wp", "℘"),
+    ("wr", "≀"),
+    ("wreath", "≀"),
+    ("wscr", "𝓌"),
+    ("xcap", "⋂"),
+    ("xcirc", "◯"),
+    ("xcup", "⋃"),
+    ("xdtri", "▽"),
+    ("xfr", "𝔵"),
+    ("xhArr", "⟺"),
+    ("xharr", "⟷"),
+    ("xi", "ξ"),
+    ("xlArr", "⟸"),
+    ("xlarr", "⟵"),
+    ("xmap", "⟼"),
+    ("xnis", "⋻"),
+    ("xodot", "⨀"),
+    ("xopf", "𝕩"),
+    ("xoplus", "⨁"),
+    ("xotime", "⨂"),
+    ("xrArr", "⟹"),
+    ("xrarr", "⟶"),
+    ("xscr", "𝓍"),
+    ("xsqcup", "⨆"),
+    ("xuplus", "⨄"),
+    ("xutri", "△"),
+    ("xvee", "⋁"),
+    ("xwedge", "⋀"),
+    ("yacute", "ý"),
+    ("yacy", "я"),
+    ("ycirc", "ŷ"),
+    ("ycy", "ы"),
+    ("yen", "¥"),
+    ("yfr", "𝔶"),
+    ("yicy", "ї"),
+    ("yopf", "𝕪"),
+    ("yscr", "𝓎"),
+    ("yucy", "ю"),
+    ("yuml", "ÿ"),
+    ("zacute", "ź"),
+    ("zcaron", "ž"),
+    ("zcy", "з"),
+    ("zdot", "ż"),
+    ("zeetrf", "ℨ"),
+    ("zeta", "ζ"),
+    ("zfr", "𝔷"),
+    ("zhcy", "ж"),
+    ("zigrarr", "⇝"),
+    ("zopf", "𝕫"),
+    ("zscr", "𝓏"),
+    ("zwj", "‍"),
+    ("zwnj", "‌"),
+];
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use alloc::format;
+
+    #[test]
+    fn constants() {
+        assert_eq!(
+            CHARACTER_REFERENCE_DECIMAL_SIZE_MAX,
+            format!("{}", 0x10ffff).len(),
+            "`CHARACTER_REFERENCE_DECIMAL_SIZE_MAX`"
+        );
+
+        assert_eq!(
+            CHARACTER_REFERENCE_HEXADECIMAL_SIZE_MAX,
+            format!("{:x}", 0x10ffff).len(),
+            "`CHARACTER_REFERENCE_HEXADECIMAL_SIZE_MAX`"
+        );
+
+        assert_eq!(
+            CHARACTER_REFERENCE_NAMED_SIZE_MAX,
+            longest(&CHARACTER_REFERENCES.map(|d| d.0)).unwrap().len(),
+            "`CHARACTER_REFERENCE_NAMED_SIZE_MAX`"
+        );
+
+        assert_eq!(
+            HTML_RAW_SIZE_MAX,
+            longest(&HTML_RAW_NAMES).unwrap().len(),
+            "`HTML_RAW_SIZE_MAX`"
+        );
+    }
+
+    fn longest<'a>(list: &[&'a str]) -> Option<&'a str> {
+        let mut max = 0;
+        let mut result = None;
+        for name in list.iter() {
+            let len = name.len();
+            if len > max {
+                max = len;
+                result = Some(*name);
+            }
+        }
+
+        result
+    }
+}
diff --git a/src/util/decode_character_reference.rs b/src/util/decode_character_reference.rs
index 30b7853..d4c983a 100644
--- a/src/util/decode_character_reference.rs
+++ b/src/util/decode_character_reference.rs
@@ -1,6 +1,6 @@
 //! Decode character references.
 
-use crate::constant::CHARACTER_REFERENCES;
+use crate::util::constant::CHARACTER_REFERENCES;
 use alloc::string::{String, ToString};
 
 /// Decode named character references.
diff --git a/src/util/mod.rs b/src/util/mod.rs
index 022c7d6..d2ec0ed 100644
--- a/src/util/mod.rs
+++ b/src/util/mod.rs
@@ -1,6 +1,7 @@
 //! Utilities used when processing markdown.
 
 pub mod classify_character;
+pub mod constant;
 pub mod decode_character_reference;
 pub mod edit_map;
 pub mod encode;
@@ -8,3 +9,4 @@ pub mod normalize_identifier;
 pub mod sanitize_uri;
 pub mod skip;
 pub mod slice;
+pub mod unicode;
diff --git a/src/util/slice.rs b/src/util/slice.rs
index 5dcc352..0734d78 100644
--- a/src/util/slice.rs
+++ b/src/util/slice.rs
@@ -1,7 +1,7 @@
 //! Deal with bytes.
 
-use crate::constant::TAB_SIZE;
 use crate::event::{Event, Kind, Point};
+use crate::util::constant::TAB_SIZE;
 use alloc::string::String;
 use core::str;
 
diff --git a/src/util/unicode.rs b/src/util/unicode.rs
new file mode 100644
index 0000000..2b79a88
--- /dev/null
+++ b/src/util/unicode.rs
@@ -0,0 +1,838 @@
+//! Info on Unicode.
+
+/// List of characters that are considered punctuation.
+///
+/// > 👉 **Important**: this module is generated by `build.rs`.
+/// > It is generate from the latest Unicode data.
+///
+/// Rust does not contain an `is_punctuation` method on `char`, while it does
+/// support [`is_ascii_alphanumeric`](char::is_ascii_alphanumeric).
+///
+/// `CommonMark` handles attention (emphasis, strong) markers based on what
+/// comes before or after them.
+/// One such difference is if those characters are Unicode punctuation.
+///
+/// ## References
+///
+/// *   [*§ 2.1 Characters and lines* in `CommonMark`](https://spec.commonmark.org/0.30/#unicode-punctuation-character)
+pub const PUNCTUATION: [char; 819] = [
+    '\u{0021}',
+    '\u{0022}',
+    '\u{0023}',
+    '\u{0025}',
+    '\u{0026}',
+    '\u{0027}',
+    '\u{0028}',
+    '\u{0029}',
+    '\u{002A}',
+    '\u{002C}',
+    '\u{002D}',
+    '\u{002E}',
+    '\u{002F}',
+    '\u{003A}',
+    '\u{003B}',
+    '\u{003F}',
+    '\u{0040}',
+    '\u{005B}',
+    '\u{005C}',
+    '\u{005D}',
+    '\u{005F}',
+    '\u{007B}',
+    '\u{007D}',
+    '\u{00A1}',
+    '\u{00A7}',
+    '\u{00AB}',
+    '\u{00B6}',
+    '\u{00B7}',
+    '\u{00BB}',
+    '\u{00BF}',
+    '\u{037E}',
+    '\u{0387}',
+    '\u{055A}',
+    '\u{055B}',
+    '\u{055C}',
+    '\u{055D}',
+    '\u{055E}',
+    '\u{055F}',
+    '\u{0589}',
+    '\u{058A}',
+    '\u{05BE}',
+    '\u{05C0}',
+    '\u{05C3}',
+    '\u{05C6}',
+    '\u{05F3}',
+    '\u{05F4}',
+    '\u{0609}',
+    '\u{060A}',
+    '\u{060C}',
+    '\u{060D}',
+    '\u{061B}',
+    '\u{061D}',
+    '\u{061E}',
+    '\u{061F}',
+    '\u{066A}',
+    '\u{066B}',
+    '\u{066C}',
+    '\u{066D}',
+    '\u{06D4}',
+    '\u{0700}',
+    '\u{0701}',
+    '\u{0702}',
+    '\u{0703}',
+    '\u{0704}',
+    '\u{0705}',
+    '\u{0706}',
+    '\u{0707}',
+    '\u{0708}',
+    '\u{0709}',
+    '\u{070A}',
+    '\u{070B}',
+    '\u{070C}',
+    '\u{070D}',
+    '\u{07F7}',
+    '\u{07F8}',
+    '\u{07F9}',
+    '\u{0830}',
+    '\u{0831}',
+    '\u{0832}',
+    '\u{0833}',
+    '\u{0834}',
+    '\u{0835}',
+    '\u{0836}',
+    '\u{0837}',
+    '\u{0838}',
+    '\u{0839}',
+    '\u{083A}',
+    '\u{083B}',
+    '\u{083C}',
+    '\u{083D}',
+    '\u{083E}',
+    '\u{085E}',
+    '\u{0964}',
+    '\u{0965}',
+    '\u{0970}',
+    '\u{09FD}',
+    '\u{0A76}',
+    '\u{0AF0}',
+    '\u{0C77}',
+    '\u{0C84}',
+    '\u{0DF4}',
+    '\u{0E4F}',
+    '\u{0E5A}',
+    '\u{0E5B}',
+    '\u{0F04}',
+    '\u{0F05}',
+    '\u{0F06}',
+    '\u{0F07}',
+    '\u{0F08}',
+    '\u{0F09}',
+    '\u{0F0A}',
+    '\u{0F0B}',
+    '\u{0F0C}',
+    '\u{0F0D}',
+    '\u{0F0E}',
+    '\u{0F0F}',
+    '\u{0F10}',
+    '\u{0F11}',
+    '\u{0F12}',
+    '\u{0F14}',
+    '\u{0F3A}',
+    '\u{0F3B}',
+    '\u{0F3C}',
+    '\u{0F3D}',
+    '\u{0F85}',
+    '\u{0FD0}',
+    '\u{0FD1}',
+    '\u{0FD2}',
+    '\u{0FD3}',
+    '\u{0FD4}',
+    '\u{0FD9}',
+    '\u{0FDA}',
+    '\u{104A}',
+    '\u{104B}',
+    '\u{104C}',
+    '\u{104D}',
+    '\u{104E}',
+    '\u{104F}',
+    '\u{10FB}',
+    '\u{1360}',
+    '\u{1361}',
+    '\u{1362}',
+    '\u{1363}',
+    '\u{1364}',
+    '\u{1365}',
+    '\u{1366}',
+    '\u{1367}',
+    '\u{1368}',
+    '\u{1400}',
+    '\u{166E}',
+    '\u{169B}',
+    '\u{169C}',
+    '\u{16EB}',
+    '\u{16EC}',
+    '\u{16ED}',
+    '\u{1735}',
+    '\u{1736}',
+    '\u{17D4}',
+    '\u{17D5}',
+    '\u{17D6}',
+    '\u{17D8}',
+    '\u{17D9}',
+    '\u{17DA}',
+    '\u{1800}',
+    '\u{1801}',
+    '\u{1802}',
+    '\u{1803}',
+    '\u{1804}',
+    '\u{1805}',
+    '\u{1806}',
+    '\u{1807}',
+    '\u{1808}',
+    '\u{1809}',
+    '\u{180A}',
+    '\u{1944}',
+    '\u{1945}',
+    '\u{1A1E}',
+    '\u{1A1F}',
+    '\u{1AA0}',
+    '\u{1AA1}',
+    '\u{1AA2}',
+    '\u{1AA3}',
+    '\u{1AA4}',
+    '\u{1AA5}',
+    '\u{1AA6}',
+    '\u{1AA8}',
+    '\u{1AA9}',
+    '\u{1AAA}',
+    '\u{1AAB}',
+    '\u{1AAC}',
+    '\u{1AAD}',
+    '\u{1B5A}',
+    '\u{1B5B}',
+    '\u{1B5C}',
+    '\u{1B5D}',
+    '\u{1B5E}',
+    '\u{1B5F}',
+    '\u{1B60}',
+    '\u{1B7D}',
+    '\u{1B7E}',
+    '\u{1BFC}',
+    '\u{1BFD}',
+    '\u{1BFE}',
+    '\u{1BFF}',
+    '\u{1C3B}',
+    '\u{1C3C}',
+    '\u{1C3D}',
+    '\u{1C3E}',
+    '\u{1C3F}',
+    '\u{1C7E}',
+    '\u{1C7F}',
+    '\u{1CC0}',
+    '\u{1CC1}',
+    '\u{1CC2}',
+    '\u{1CC3}',
+    '\u{1CC4}',
+    '\u{1CC5}',
+    '\u{1CC6}',
+    '\u{1CC7}',
+    '\u{1CD3}',
+    '\u{2010}',
+    '\u{2011}',
+    '\u{2012}',
+    '\u{2013}',
+    '\u{2014}',
+    '\u{2015}',
+    '\u{2016}',
+    '\u{2017}',
+    '\u{2018}',
+    '\u{2019}',
+    '\u{201A}',
+    '\u{201B}',
+    '\u{201C}',
+    '\u{201D}',
+    '\u{201E}',
+    '\u{201F}',
+    '\u{2020}',
+    '\u{2021}',
+    '\u{2022}',
+    '\u{2023}',
+    '\u{2024}',
+    '\u{2025}',
+    '\u{2026}',
+    '\u{2027}',
+    '\u{2030}',
+    '\u{2031}',
+    '\u{2032}',
+    '\u{2033}',
+    '\u{2034}',
+    '\u{2035}',
+    '\u{2036}',
+    '\u{2037}',
+    '\u{2038}',
+    '\u{2039}',
+    '\u{203A}',
+    '\u{203B}',
+    '\u{203C}',
+    '\u{203D}',
+    '\u{203E}',
+    '\u{203F}',
+    '\u{2040}',
+    '\u{2041}',
+    '\u{2042}',
+    '\u{2043}',
+    '\u{2045}',
+    '\u{2046}',
+    '\u{2047}',
+    '\u{2048}',
+    '\u{2049}',
+    '\u{204A}',
+    '\u{204B}',
+    '\u{204C}',
+    '\u{204D}',
+    '\u{204E}',
+    '\u{204F}',
+    '\u{2050}',
+    '\u{2051}',
+    '\u{2053}',
+    '\u{2054}',
+    '\u{2055}',
+    '\u{2056}',
+    '\u{2057}',
+    '\u{2058}',
+    '\u{2059}',
+    '\u{205A}',
+    '\u{205B}',
+    '\u{205C}',
+    '\u{205D}',
+    '\u{205E}',
+    '\u{207D}',
+    '\u{207E}',
+    '\u{208D}',
+    '\u{208E}',
+    '\u{2308}',
+    '\u{2309}',
+    '\u{230A}',
+    '\u{230B}',
+    '\u{2329}',
+    '\u{232A}',
+    '\u{2768}',
+    '\u{2769}',
+    '\u{276A}',
+    '\u{276B}',
+    '\u{276C}',
+    '\u{276D}',
+    '\u{276E}',
+    '\u{276F}',
+    '\u{2770}',
+    '\u{2771}',
+    '\u{2772}',
+    '\u{2773}',
+    '\u{2774}',
+    '\u{2775}',
+    '\u{27C5}',
+    '\u{27C6}',
+    '\u{27E6}',
+    '\u{27E7}',
+    '\u{27E8}',
+    '\u{27E9}',
+    '\u{27EA}',
+    '\u{27EB}',
+    '\u{27EC}',
+    '\u{27ED}',
+    '\u{27EE}',
+    '\u{27EF}',
+    '\u{2983}',
+    '\u{2984}',
+    '\u{2985}',
+    '\u{2986}',
+    '\u{2987}',
+    '\u{2988}',
+    '\u{2989}',
+    '\u{298A}',
+    '\u{298B}',
+    '\u{298C}',
+    '\u{298D}',
+    '\u{298E}',
+    '\u{298F}',
+    '\u{2990}',
+    '\u{2991}',
+    '\u{2992}',
+    '\u{2993}',
+    '\u{2994}',
+    '\u{2995}',
+    '\u{2996}',
+    '\u{2997}',
+    '\u{2998}',
+    '\u{29D8}',
+    '\u{29D9}',
+    '\u{29DA}',
+    '\u{29DB}',
+    '\u{29FC}',
+    '\u{29FD}',
+    '\u{2CF9}',
+    '\u{2CFA}',
+    '\u{2CFB}',
+    '\u{2CFC}',
+    '\u{2CFE}',
+    '\u{2CFF}',
+    '\u{2D70}',
+    '\u{2E00}',
+    '\u{2E01}',
+    '\u{2E02}',
+    '\u{2E03}',
+    '\u{2E04}',
+    '\u{2E05}',
+    '\u{2E06}',
+    '\u{2E07}',
+    '\u{2E08}',
+    '\u{2E09}',
+    '\u{2E0A}',
+    '\u{2E0B}',
+    '\u{2E0C}',
+    '\u{2E0D}',
+    '\u{2E0E}',
+    '\u{2E0F}',
+    '\u{2E10}',
+    '\u{2E11}',
+    '\u{2E12}',
+    '\u{2E13}',
+    '\u{2E14}',
+    '\u{2E15}',
+    '\u{2E16}',
+    '\u{2E17}',
+    '\u{2E18}',
+    '\u{2E19}',
+    '\u{2E1A}',
+    '\u{2E1B}',
+    '\u{2E1C}',
+    '\u{2E1D}',
+    '\u{2E1E}',
+    '\u{2E1F}',
+    '\u{2E20}',
+    '\u{2E21}',
+    '\u{2E22}',
+    '\u{2E23}',
+    '\u{2E24}',
+    '\u{2E25}',
+    '\u{2E26}',
+    '\u{2E27}',
+    '\u{2E28}',
+    '\u{2E29}',
+    '\u{2E2A}',
+    '\u{2E2B}',
+    '\u{2E2C}',
+    '\u{2E2D}',
+    '\u{2E2E}',
+    '\u{2E30}',
+    '\u{2E31}',
+    '\u{2E32}',
+    '\u{2E33}',
+    '\u{2E34}',
+    '\u{2E35}',
+    '\u{2E36}',
+    '\u{2E37}',
+    '\u{2E38}',
+    '\u{2E39}',
+    '\u{2E3A}',
+    '\u{2E3B}',
+    '\u{2E3C}',
+    '\u{2E3D}',
+    '\u{2E3E}',
+    '\u{2E3F}',
+    '\u{2E40}',
+    '\u{2E41}',
+    '\u{2E42}',
+    '\u{2E43}',
+    '\u{2E44}',
+    '\u{2E45}',
+    '\u{2E46}',
+    '\u{2E47}',
+    '\u{2E48}',
+    '\u{2E49}',
+    '\u{2E4A}',
+    '\u{2E4B}',
+    '\u{2E4C}',
+    '\u{2E4D}',
+    '\u{2E4E}',
+    '\u{2E4F}',
+    '\u{2E52}',
+    '\u{2E53}',
+    '\u{2E54}',
+    '\u{2E55}',
+    '\u{2E56}',
+    '\u{2E57}',
+    '\u{2E58}',
+    '\u{2E59}',
+    '\u{2E5A}',
+    '\u{2E5B}',
+    '\u{2E5C}',
+    '\u{2E5D}',
+    '\u{3001}',
+    '\u{3002}',
+    '\u{3003}',
+    '\u{3008}',
+    '\u{3009}',
+    '\u{300A}',
+    '\u{300B}',
+    '\u{300C}',
+    '\u{300D}',
+    '\u{300E}',
+    '\u{300F}',
+    '\u{3010}',
+    '\u{3011}',
+    '\u{3014}',
+    '\u{3015}',
+    '\u{3016}',
+    '\u{3017}',
+    '\u{3018}',
+    '\u{3019}',
+    '\u{301A}',
+    '\u{301B}',
+    '\u{301C}',
+    '\u{301D}',
+    '\u{301E}',
+    '\u{301F}',
+    '\u{3030}',
+    '\u{303D}',
+    '\u{30A0}',
+    '\u{30FB}',
+    '\u{A4FE}',
+    '\u{A4FF}',
+    '\u{A60D}',
+    '\u{A60E}',
+    '\u{A60F}',
+    '\u{A673}',
+    '\u{A67E}',
+    '\u{A6F2}',
+    '\u{A6F3}',
+    '\u{A6F4}',
+    '\u{A6F5}',
+    '\u{A6F6}',
+    '\u{A6F7}',
+    '\u{A874}',
+    '\u{A875}',
+    '\u{A876}',
+    '\u{A877}',
+    '\u{A8CE}',
+    '\u{A8CF}',
+    '\u{A8F8}',
+    '\u{A8F9}',
+    '\u{A8FA}',
+    '\u{A8FC}',
+    '\u{A92E}',
+    '\u{A92F}',
+    '\u{A95F}',
+    '\u{A9C1}',
+    '\u{A9C2}',
+    '\u{A9C3}',
+    '\u{A9C4}',
+    '\u{A9C5}',
+    '\u{A9C6}',
+    '\u{A9C7}',
+    '\u{A9C8}',
+    '\u{A9C9}',
+    '\u{A9CA}',
+    '\u{A9CB}',
+    '\u{A9CC}',
+    '\u{A9CD}',
+    '\u{A9DE}',
+    '\u{A9DF}',
+    '\u{AA5C}',
+    '\u{AA5D}',
+    '\u{AA5E}',
+    '\u{AA5F}',
+    '\u{AADE}',
+    '\u{AADF}',
+    '\u{AAF0}',
+    '\u{AAF1}',
+    '\u{ABEB}',
+    '\u{FD3E}',
+    '\u{FD3F}',
+    '\u{FE10}',
+    '\u{FE11}',
+    '\u{FE12}',
+    '\u{FE13}',
+    '\u{FE14}',
+    '\u{FE15}',
+    '\u{FE16}',
+    '\u{FE17}',
+    '\u{FE18}',
+    '\u{FE19}',
+    '\u{FE30}',
+    '\u{FE31}',
+    '\u{FE32}',
+    '\u{FE33}',
+    '\u{FE34}',
+    '\u{FE35}',
+    '\u{FE36}',
+    '\u{FE37}',
+    '\u{FE38}',
+    '\u{FE39}',
+    '\u{FE3A}',
+    '\u{FE3B}',
+    '\u{FE3C}',
+    '\u{FE3D}',
+    '\u{FE3E}',
+    '\u{FE3F}',
+    '\u{FE40}',
+    '\u{FE41}',
+    '\u{FE42}',
+    '\u{FE43}',
+    '\u{FE44}',
+    '\u{FE45}',
+    '\u{FE46}',
+    '\u{FE47}',
+    '\u{FE48}',
+    '\u{FE49}',
+    '\u{FE4A}',
+    '\u{FE4B}',
+    '\u{FE4C}',
+    '\u{FE4D}',
+    '\u{FE4E}',
+    '\u{FE4F}',
+    '\u{FE50}',
+    '\u{FE51}',
+    '\u{FE52}',
+    '\u{FE54}',
+    '\u{FE55}',
+    '\u{FE56}',
+    '\u{FE57}',
+    '\u{FE58}',
+    '\u{FE59}',
+    '\u{FE5A}',
+    '\u{FE5B}',
+    '\u{FE5C}',
+    '\u{FE5D}',
+    '\u{FE5E}',
+    '\u{FE5F}',
+    '\u{FE60}',
+    '\u{FE61}',
+    '\u{FE63}',
+    '\u{FE68}',
+    '\u{FE6A}',
+    '\u{FE6B}',
+    '\u{FF01}',
+    '\u{FF02}',
+    '\u{FF03}',
+    '\u{FF05}',
+    '\u{FF06}',
+    '\u{FF07}',
+    '\u{FF08}',
+    '\u{FF09}',
+    '\u{FF0A}',
+    '\u{FF0C}',
+    '\u{FF0D}',
+    '\u{FF0E}',
+    '\u{FF0F}',
+    '\u{FF1A}',
+    '\u{FF1B}',
+    '\u{FF1F}',
+    '\u{FF20}',
+    '\u{FF3B}',
+    '\u{FF3C}',
+    '\u{FF3D}',
+    '\u{FF3F}',
+    '\u{FF5B}',
+    '\u{FF5D}',
+    '\u{FF5F}',
+    '\u{FF60}',
+    '\u{FF61}',
+    '\u{FF62}',
+    '\u{FF63}',
+    '\u{FF64}',
+    '\u{FF65}',
+    '\u{10100}',
+    '\u{10101}',
+    '\u{10102}',
+    '\u{1039F}',
+    '\u{103D0}',
+    '\u{1056F}',
+    '\u{10857}',
+    '\u{1091F}',
+    '\u{1093F}',
+    '\u{10A50}',
+    '\u{10A51}',
+    '\u{10A52}',
+    '\u{10A53}',
+    '\u{10A54}',
+    '\u{10A55}',
+    '\u{10A56}',
+    '\u{10A57}',
+    '\u{10A58}',
+    '\u{10A7F}',
+    '\u{10AF0}',
+    '\u{10AF1}',
+    '\u{10AF2}',
+    '\u{10AF3}',
+    '\u{10AF4}',
+    '\u{10AF5}',
+    '\u{10AF6}',
+    '\u{10B39}',
+    '\u{10B3A}',
+    '\u{10B3B}',
+    '\u{10B3C}',
+    '\u{10B3D}',
+    '\u{10B3E}',
+    '\u{10B3F}',
+    '\u{10B99}',
+    '\u{10B9A}',
+    '\u{10B9B}',
+    '\u{10B9C}',
+    '\u{10EAD}',
+    '\u{10F55}',
+    '\u{10F56}',
+    '\u{10F57}',
+    '\u{10F58}',
+    '\u{10F59}',
+    '\u{10F86}',
+    '\u{10F87}',
+    '\u{10F88}',
+    '\u{10F89}',
+    '\u{11047}',
+    '\u{11048}',
+    '\u{11049}',
+    '\u{1104A}',
+    '\u{1104B}',
+    '\u{1104C}',
+    '\u{1104D}',
+    '\u{110BB}',
+    '\u{110BC}',
+    '\u{110BE}',
+    '\u{110BF}',
+    '\u{110C0}',
+    '\u{110C1}',
+    '\u{11140}',
+    '\u{11141}',
+    '\u{11142}',
+    '\u{11143}',
+    '\u{11174}',
+    '\u{11175}',
+    '\u{111C5}',
+    '\u{111C6}',
+    '\u{111C7}',
+    '\u{111C8}',
+    '\u{111CD}',
+    '\u{111DB}',
+    '\u{111DD}',
+    '\u{111DE}',
+    '\u{111DF}',
+    '\u{11238}',
+    '\u{11239}',
+    '\u{1123A}',
+    '\u{1123B}',
+    '\u{1123C}',
+    '\u{1123D}',
+    '\u{112A9}',
+    '\u{1144B}',
+    '\u{1144C}',
+    '\u{1144D}',
+    '\u{1144E}',
+    '\u{1144F}',
+    '\u{1145A}',
+    '\u{1145B}',
+    '\u{1145D}',
+    '\u{114C6}',
+    '\u{115C1}',
+    '\u{115C2}',
+    '\u{115C3}',
+    '\u{115C4}',
+    '\u{115C5}',
+    '\u{115C6}',
+    '\u{115C7}',
+    '\u{115C8}',
+    '\u{115C9}',
+    '\u{115CA}',
+    '\u{115CB}',
+    '\u{115CC}',
+    '\u{115CD}',
+    '\u{115CE}',
+    '\u{115CF}',
+    '\u{115D0}',
+    '\u{115D1}',
+    '\u{115D2}',
+    '\u{115D3}',
+    '\u{115D4}',
+    '\u{115D5}',
+    '\u{115D6}',
+    '\u{115D7}',
+    '\u{11641}',
+    '\u{11642}',
+    '\u{11643}',
+    '\u{11660}',
+    '\u{11661}',
+    '\u{11662}',
+    '\u{11663}',
+    '\u{11664}',
+    '\u{11665}',
+    '\u{11666}',
+    '\u{11667}',
+    '\u{11668}',
+    '\u{11669}',
+    '\u{1166A}',
+    '\u{1166B}',
+    '\u{1166C}',
+    '\u{116B9}',
+    '\u{1173C}',
+    '\u{1173D}',
+    '\u{1173E}',
+    '\u{1183B}',
+    '\u{11944}',
+    '\u{11945}',
+    '\u{11946}',
+    '\u{119E2}',
+    '\u{11A3F}',
+    '\u{11A40}',
+    '\u{11A41}',
+    '\u{11A42}',
+    '\u{11A43}',
+    '\u{11A44}',
+    '\u{11A45}',
+    '\u{11A46}',
+    '\u{11A9A}',
+    '\u{11A9B}',
+    '\u{11A9C}',
+    '\u{11A9E}',
+    '\u{11A9F}',
+    '\u{11AA0}',
+    '\u{11AA1}',
+    '\u{11AA2}',
+    '\u{11C41}',
+    '\u{11C42}',
+    '\u{11C43}',
+    '\u{11C44}',
+    '\u{11C45}',
+    '\u{11C70}',
+    '\u{11C71}',
+    '\u{11EF7}',
+    '\u{11EF8}',
+    '\u{11FFF}',
+    '\u{12470}',
+    '\u{12471}',
+    '\u{12472}',
+    '\u{12473}',
+    '\u{12474}',
+    '\u{12FF1}',
+    '\u{12FF2}',
+    '\u{16A6E}',
+    '\u{16A6F}',
+    '\u{16AF5}',
+    '\u{16B37}',
+    '\u{16B38}',
+    '\u{16B39}',
+    '\u{16B3A}',
+    '\u{16B3B}',
+    '\u{16B44}',
+    '\u{16E97}',
+    '\u{16E98}',
+    '\u{16E99}',
+    '\u{16E9A}',
+    '\u{16FE2}',
+    '\u{1BC9F}',
+    '\u{1DA87}',
+    '\u{1DA88}',
+    '\u{1DA89}',
+    '\u{1DA8A}',
+    '\u{1DA8B}',
+    '\u{1E95E}',
+    '\u{1E95F}',
+];