quick_xml/
escape.rs

1//! Manage xml character escapes
2
3use memchr::{memchr, memchr2_iter, memchr3};
4use std::borrow::Cow;
5use std::num::ParseIntError;
6use std::ops::Range;
7
8/// Error of parsing character reference (`&#<dec-number>;` or `&#x<hex-number>;`).
9#[derive(Clone, Debug, PartialEq)]
10pub enum ParseCharRefError {
11    /// Number contains sign character (`+` or `-`) which is not allowed.
12    UnexpectedSign,
13    /// Number cannot be parsed due to non-number characters or a numeric overflow.
14    InvalidNumber(ParseIntError),
15    /// Character reference represents not a valid unicode codepoint.
16    InvalidCodepoint(u32),
17    /// Character reference expanded to a not permitted character for an XML.
18    ///
19    /// Currently, only `0x0` character produces this error.
20    IllegalCharacter(u32),
21}
22
23impl std::fmt::Display for ParseCharRefError {
24    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
25        match self {
26            Self::UnexpectedSign => f.write_str("unexpected number sign"),
27            Self::InvalidNumber(e) => e.fmt(f),
28            Self::InvalidCodepoint(n) => write!(f, "`{}` is not a valid codepoint", n),
29            Self::IllegalCharacter(n) => write!(f, "0x{:x} character is not permitted in XML", n),
30        }
31    }
32}
33
34impl std::error::Error for ParseCharRefError {
35    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
36        match self {
37            Self::InvalidNumber(e) => Some(e),
38            _ => None,
39        }
40    }
41}
42
43/// Error for XML escape / unescape.
44#[derive(Clone, Debug, PartialEq)]
45pub enum EscapeError {
46    /// Referenced entity in unknown to the parser.
47    UnrecognizedEntity(Range<usize>, String),
48    /// Cannot find `;` after `&`
49    UnterminatedEntity(Range<usize>),
50    /// Attempt to parse character reference (`&#<dec-number>;` or `&#x<hex-number>;`)
51    /// was unsuccessful, not all characters are decimal or hexadecimal numbers.
52    InvalidCharRef(ParseCharRefError),
53}
54
55impl std::fmt::Display for EscapeError {
56    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
57        match self {
58            Self::UnrecognizedEntity(rge, res) => {
59                write!(f, "at {:?}: unrecognized entity `{}`", rge, res)
60            }
61            Self::UnterminatedEntity(e) => write!(
62                f,
63                "Error while escaping character at range {:?}: Cannot find ';' after '&'",
64                e
65            ),
66            Self::InvalidCharRef(e) => {
67                write!(f, "invalid character reference: {}", e)
68            }
69        }
70    }
71}
72
73impl std::error::Error for EscapeError {
74    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
75        match self {
76            Self::InvalidCharRef(e) => Some(e),
77            _ => None,
78        }
79    }
80}
81
82/// Escapes an `&str` and replaces all xml special characters (`<`, `>`, `&`, `'`, `"`)
83/// with their corresponding xml escaped value.
84///
85/// This function performs following replacements:
86///
87/// | Character | Replacement
88/// |-----------|------------
89/// | `<`       | `&lt;`
90/// | `>`       | `&gt;`
91/// | `&`       | `&amp;`
92/// | `'`       | `&apos;`
93/// | `"`       | `&quot;`
94///
95/// This function performs following replacements:
96///
97/// | Character | Replacement
98/// |-----------|------------
99/// | `<`       | `&lt;`
100/// | `>`       | `&gt;`
101/// | `&`       | `&amp;`
102/// | `'`       | `&apos;`
103/// | `"`       | `&quot;`
104pub fn escape<'a>(raw: impl Into<Cow<'a, str>>) -> Cow<'a, str> {
105    _escape(raw, |ch| matches!(ch, b'<' | b'>' | b'&' | b'\'' | b'\"'))
106}
107
108/// Escapes an `&str` and replaces xml special characters (`<`, `>`, `&`)
109/// with their corresponding xml escaped value.
110///
111/// Should only be used for escaping text content. In XML text content, it is allowed
112/// (though not recommended) to leave the quote special characters `"` and `'` unescaped.
113///
114/// This function performs following replacements:
115///
116/// | Character | Replacement
117/// |-----------|------------
118/// | `<`       | `&lt;`
119/// | `>`       | `&gt;`
120/// | `&`       | `&amp;`
121///
122/// This function performs following replacements:
123///
124/// | Character | Replacement
125/// |-----------|------------
126/// | `<`       | `&lt;`
127/// | `>`       | `&gt;`
128/// | `&`       | `&amp;`
129pub fn partial_escape<'a>(raw: impl Into<Cow<'a, str>>) -> Cow<'a, str> {
130    _escape(raw, |ch| matches!(ch, b'<' | b'>' | b'&'))
131}
132
133/// XML standard [requires] that only `<` and `&` was escaped in text content or
134/// attribute value. All other characters not necessary to be escaped, although
135/// for compatibility with SGML they also should be escaped. Practically, escaping
136/// only those characters is enough.
137///
138/// This function performs following replacements:
139///
140/// | Character | Replacement
141/// |-----------|------------
142/// | `<`       | `&lt;`
143/// | `&`       | `&amp;`
144///
145/// [requires]: https://www.w3.org/TR/xml11/#syntax
146pub fn minimal_escape<'a>(raw: impl Into<Cow<'a, str>>) -> Cow<'a, str> {
147    _escape(raw, |ch| matches!(ch, b'<' | b'&'))
148}
149
150/// Escapes an `&str` and replaces a subset of xml special characters (`<`, `>`,
151/// `&`, `'`, `"`) with their corresponding xml escaped value.
152pub(crate) fn _escape<'a, F: Fn(u8) -> bool>(
153    raw: impl Into<Cow<'a, str>>,
154    escape_chars: F,
155) -> Cow<'a, str> {
156    let raw = raw.into();
157    let bytes = raw.as_bytes();
158    let mut escaped = None;
159    let mut iter = bytes.iter();
160    let mut pos = 0;
161    while let Some(i) = iter.position(|&b| escape_chars(b)) {
162        if escaped.is_none() {
163            escaped = Some(Vec::with_capacity(raw.len()));
164        }
165        let escaped = escaped.as_mut().expect("initialized");
166        let new_pos = pos + i;
167        escaped.extend_from_slice(&bytes[pos..new_pos]);
168        match bytes[new_pos] {
169            b'<' => escaped.extend_from_slice(b"&lt;"),
170            b'>' => escaped.extend_from_slice(b"&gt;"),
171            b'\'' => escaped.extend_from_slice(b"&apos;"),
172            b'&' => escaped.extend_from_slice(b"&amp;"),
173            b'"' => escaped.extend_from_slice(b"&quot;"),
174
175            // This set of escapes handles characters that should be escaped
176            // in elements of xs:lists, because those characters works as
177            // delimiters of list elements
178            b'\t' => escaped.extend_from_slice(b"&#9;"),
179            b'\n' => escaped.extend_from_slice(b"&#10;"),
180            b'\r' => escaped.extend_from_slice(b"&#13;"),
181            b' ' => escaped.extend_from_slice(b"&#32;"),
182            _ => unreachable!(
183                "Only '<', '>','\', '&', '\"', '\\t', '\\r', '\\n', and ' ' are escaped"
184            ),
185        }
186        pos = new_pos + 1;
187    }
188
189    if let Some(mut escaped) = escaped {
190        if let Some(raw) = bytes.get(pos..) {
191            escaped.extend_from_slice(raw);
192        }
193        // SAFETY: we operate on UTF-8 input and search for an one byte chars only,
194        // so all slices that was put to the `escaped` is a valid UTF-8 encoded strings
195        // TODO: Can be replaced with `unsafe { String::from_utf8_unchecked() }`
196        // if unsafe code will be allowed
197        Cow::Owned(String::from_utf8(escaped).unwrap())
198    } else {
199        raw
200    }
201}
202
203/// Unescape an `&str` and replaces all xml escaped characters (`&...;`) into
204/// their corresponding value.
205///
206/// If feature [`escape-html`] is enabled, then recognizes all [HTML5 escapes].
207///
208/// [`escape-html`]: ../index.html#escape-html
209/// [HTML5 escapes]: https://dev.w3.org/html5/html-author/charref
210pub fn unescape(raw: &str) -> Result<Cow<str>, EscapeError> {
211    unescape_with(raw, resolve_predefined_entity)
212}
213
214/// Unescape an `&str` and replaces all xml escaped characters (`&...;`) into
215/// their corresponding value, using a resolver function for custom entities.
216///
217/// If feature [`escape-html`] is enabled, then recognizes all [HTML5 escapes].
218///
219/// Predefined entities will be resolved _after_ trying to resolve with `resolve_entity`,
220/// which allows you to override default behavior which required in some XML dialects.
221///
222/// Character references (`&#hh;`) cannot be overridden, they are resolved before
223/// calling `resolve_entity`.
224///
225/// Note, that entities will not be resolved recursively. In order to satisfy the
226/// XML [requirements] you should unescape nested entities by yourself.
227///
228/// # Example
229///
230/// ```
231/// use quick_xml::escape::resolve_xml_entity;
232/// # use quick_xml::escape::unescape_with;
233/// # use pretty_assertions::assert_eq;
234/// let override_named_entities = |entity: &str| match entity {
235///     // Override standard entities
236///     "lt" => Some("FOO"),
237///     "gt" => Some("BAR"),
238///     // Resolve custom entities
239///     "baz" => Some("&lt;"),
240///     // Delegate other entities to the default implementation
241///     _ => resolve_xml_entity(entity),
242/// };
243///
244/// assert_eq!(
245///     unescape_with("&amp;&lt;test&gt;&baz;", override_named_entities).unwrap(),
246///     "&FOOtestBAR&lt;"
247/// );
248/// ```
249///
250/// [`escape-html`]: ../index.html#escape-html
251/// [HTML5 escapes]: https://dev.w3.org/html5/html-author/charref
252/// [requirements]: https://www.w3.org/TR/xml11/#intern-replacement
253pub fn unescape_with<'input, 'entity, F>(
254    raw: &'input str,
255    mut resolve_entity: F,
256) -> Result<Cow<'input, str>, EscapeError>
257where
258    // the lifetime of the output comes from a capture or is `'static`
259    F: FnMut(&str) -> Option<&'entity str>,
260{
261    let bytes = raw.as_bytes();
262    let mut unescaped = None;
263    let mut last_end = 0;
264    let mut iter = memchr2_iter(b'&', b';', bytes);
265    while let Some(start) = iter.by_ref().find(|p| bytes[*p] == b'&') {
266        match iter.next() {
267            Some(end) if bytes[end] == b';' => {
268                // append valid data
269                if unescaped.is_none() {
270                    unescaped = Some(String::with_capacity(raw.len()));
271                }
272                let unescaped = unescaped.as_mut().expect("initialized");
273                unescaped.push_str(&raw[last_end..start]);
274
275                // search for character correctness
276                let pat = &raw[start + 1..end];
277                if let Some(entity) = pat.strip_prefix('#') {
278                    let codepoint = parse_number(entity).map_err(EscapeError::InvalidCharRef)?;
279                    unescaped.push_str(codepoint.encode_utf8(&mut [0u8; 4]));
280                } else if let Some(value) = resolve_entity(pat) {
281                    unescaped.push_str(value);
282                } else {
283                    return Err(EscapeError::UnrecognizedEntity(
284                        start + 1..end,
285                        pat.to_string(),
286                    ));
287                }
288
289                last_end = end + 1;
290            }
291            _ => return Err(EscapeError::UnterminatedEntity(start..raw.len())),
292        }
293    }
294
295    if let Some(mut unescaped) = unescaped {
296        if let Some(raw) = raw.get(last_end..) {
297            unescaped.push_str(raw);
298        }
299        Ok(Cow::Owned(unescaped))
300    } else {
301        Ok(Cow::Borrowed(raw))
302    }
303}
304
305////////////////////////////////////////////////////////////////////////////////////////////////////
306
307// TODO: It would be better to reuse buffer after decoding if possible
308pub(crate) fn normalize_xml_eols<'input>(text: &'input str) -> Cow<'input, str> {
309    let bytes = text.as_bytes();
310
311    // The following sequences of UTF-8 encoded input should be translated into
312    // a single `\n` (U+000a) character to normalize EOLs:
313    //
314    // |UTF-8   |String|
315    // |--------|------|
316    // |0d 0a   |\r\n  |
317    // |0d c2 85|\r\x85|
318    // |0d      |\r    |
319    // |c2 85   |\x85  |
320    // |e2 80 a8|\u2028|
321    if let Some(i) = memchr3(b'\r', 0xC2, 0xE2, bytes) {
322        // We found a character that requires normalization, so create new normalized
323        // string, put the prefix as is and then put normalized character
324        let mut normalized = String::with_capacity(text.len());
325        // NOTE: unsafe { text.get_unchecked(0..i) } could be used because
326        // we are sure that index within string
327        normalized.push_str(&text[0..i]);
328
329        let mut pos = normalize_xml_eol_step(&mut normalized, text, i, '\n');
330        while let Some(i) = memchr3(b'\r', 0xC2, 0xE2, &bytes[pos..]) {
331            let index = pos + i;
332            // NOTE: unsafe { text.get_unchecked(pos..index) } could be used because
333            // we are sure that index within string
334            normalized.push_str(&text[pos..index]);
335            pos = normalize_xml_eol_step(&mut normalized, text, index, '\n');
336        }
337        if let Some(rest) = text.get(pos..) {
338            normalized.push_str(rest);
339        }
340        return normalized.into();
341    }
342    Cow::Borrowed(text)
343}
344
345/// All line breaks MUST have been normalized on input to #xA as described
346/// in [2.11 End-of-Line Handling][eof], so the rest of this algorithm operates
347/// on text normalized in this way.
348///
349/// To simplify the tasks of applications, the XML processor MUST behave
350/// as if it normalized all line breaks in external parsed entities
351/// (including the document entity) on input, before parsing, by translating
352/// all of the following to a single #xA character (_which attribute normalization
353/// routine will replace by #x20 character_):
354///
355/// 1. the two-character sequence #xD #xA
356/// 2. the two-character sequence #xD #x85
357/// 3. the single character #x85
358/// 4. the single character #x2028
359/// 5. any #xD character that is not immediately followed by #xA or #x85.
360///
361/// The characters #x85 and #x2028 cannot be reliably recognized and translated
362/// until an entity's encoding declaration (if present) has been read.
363/// Therefore, it is a fatal error to use them within the XML declaration or text declaration.
364///
365/// Note, that this function cannot be used to normalize HTML values. The text in HTML
366/// normally is not normalized in any way; normalization is performed only in limited
367/// contexts and [only for] `\r\n` and `\r`.
368///
369/// # Parameters
370///
371/// - `normalized`: the string with the result of normalization
372/// - `input`: UTF-8 bytes of the string to be normalized
373/// - `index`: a byte index into `input` of character which is processed right now.
374///   It always points to the first byte of character in UTF-8 encoding
375/// - `ch`: a character that should be put to the string instead of newline sequence
376///
377/// Returns the index of next unprocessed byte in the `input`.
378///
379/// [eof]: https://www.w3.org/TR/xml11/#sec-line-ends
380/// [only for]: https://html.spec.whatwg.org/#normalize-newlines
381fn normalize_xml_eol_step(normalized: &mut String, text: &str, index: usize, ch: char) -> usize {
382    let input = text.as_bytes();
383    match input[index] {
384        b'\r' => {
385            if index + 1 < input.len() {
386                let next = input[index + 1];
387                if next == b'\n' {
388                    normalized.push(ch);
389                    return index + 2; // skip \r\n
390                }
391                // Because input is correct UTF-8 and in UTF-8 every character has
392                // an unique prefix, byte C2 means only start of #x85 character
393                if next == 0xC2 {
394                    if index + 2 < input.len() && input[index + 2] == 0x85 {
395                        normalized.push(ch);
396                    } else {
397                        // NOTE: unsafe { text.get_unchecked(index..index + 3) } could be used because
398                        // we are sure that index within string
399                        normalized.push_str(&text[index..index + 3]);
400                    }
401                    return index + 3; // skip \r + UTF-8 encoding of character (c2 xx)
402                }
403            }
404            normalized.push(ch);
405            index + 1 // skip \r
406        }
407        b'\n' => {
408            normalized.push(ch);
409            index + 1 // skip \n
410        }
411        // Start of UTF-8 encoding of #x85 character (c2 85)
412        0xC2 => {
413            if index + 1 < input.len() && input[index + 1] == 0x85 {
414                normalized.push(ch);
415            } else {
416                // NOTE: unsafe { text.get_unchecked(index..index + 2) } could be used because
417                // we are sure that index within string
418                normalized.push_str(&text[index..index + 2]);
419            }
420            index + 2 // skip UTF-8 encoding of character (c2 xx)
421        }
422        // Start of UTF-8 encoding of #x2028 character (e2 80 a8)
423        0xE2 => {
424            if index + 2 < input.len() && input[index + 1] == 0x80 && input[index + 2] == 0xA8 {
425                normalized.push(ch);
426            } else {
427                // NOTE: unsafe { text.get_unchecked(index..index + 3) } could be used because
428                // we are sure that index within string
429                normalized.push_str(&text[index..index + 3]);
430            }
431            index + 3 // skip UTF-8 encoding of character (e2 xx xx)
432        }
433
434        x => unreachable!(
435            "at {}: expected ''\\n', '\\r', '\\xC2', or '\\xE2', found '{}' / {} / `0x{:X}`",
436            index, x as char, x, x
437        ),
438    }
439}
440
441////////////////////////////////////////////////////////////////////////////////////////////////////
442
443// TODO: It would be better to reuse buffer after decoding if possible
444pub(crate) fn normalize_html_eols<'input>(text: &'input str) -> Cow<'input, str> {
445    let bytes = text.as_bytes();
446
447    // The following sequences of UTF-8 encoded input should be translated into
448    // a single `\n` (U+000a) character to normalize EOLs:
449    //
450    // |UTF-8   |String|
451    // |--------|------|
452    // |0d 0a   |\r\n  |
453    // |0d      |\r    |
454    if let Some(i) = memchr(b'\r', bytes) {
455        // We found a character that requires normalization, so create new normalized
456        // string, put the prefix as is and then put normalized character
457        let mut normalized = String::with_capacity(text.len());
458        // NOTE: unsafe { text.get_unchecked(0..i) } could be used because
459        // we are sure that index within string
460        normalized.push_str(&text[0..i]);
461
462        let mut pos = normalize_html_eol_step(&mut normalized, bytes, i, '\n');
463        while let Some(i) = memchr(b'\r', &bytes[pos..]) {
464            let index = pos + i;
465            // NOTE: unsafe { text.get_unchecked(pos..index) } could be used because
466            // we are sure that index within string
467            normalized.push_str(&text[pos..index]);
468            pos = normalize_html_eol_step(&mut normalized, bytes, index, '\n');
469        }
470        if let Some(rest) = text.get(pos..) {
471            normalized.push_str(rest);
472        }
473        return normalized.into();
474    }
475    Cow::Borrowed(text)
476}
477
478/// The text in HTML normally is not normalized in any way; normalization is
479/// performed only in limited contexts and [only for] `\r\n` and `\r`.
480///
481/// # Parameters
482///
483/// - `normalized`: the string with the result of normalization
484/// - `input`: UTF-8 bytes of the string to be normalized
485/// - `index`: a byte index into `input` of character which is processed right now.
486///   It always points to the first byte of character in UTF-8 encoding
487/// - `ch`: a character that should be put to the string instead of newline sequence
488///
489/// [only for]: https://html.spec.whatwg.org/#normalize-newlines
490fn normalize_html_eol_step(normalized: &mut String, input: &[u8], index: usize, ch: char) -> usize {
491    match input[index] {
492        b'\r' => {
493            normalized.push(ch);
494            if index + 1 < input.len() && input[index + 1] == b'\n' {
495                return index + 2; // skip \r\n
496            }
497            index + 1 // skip \r
498        }
499        b'\n' => {
500            normalized.push(ch);
501            index + 1 // skip \n
502        }
503
504        x => unreachable!(
505            "at {}: expected ''\\n' or '\\r', found '{}' / {} / `0x{:X}`",
506            index, x as char, x, x
507        ),
508    }
509}
510
511////////////////////////////////////////////////////////////////////////////////////////////////////
512
513/// Resolves predefined XML entities or all HTML5 entities depending on the feature
514/// [`escape-html`](https://docs.rs/quick-xml/latest/quick_xml/#escape-html).
515///
516/// Behaves like [`resolve_xml_entity`] if feature is not enabled and as
517/// [`resolve_html5_entity`] if enabled.
518#[inline]
519pub const fn resolve_predefined_entity(entity: &str) -> Option<&'static str> {
520    #[cfg(not(feature = "escape-html"))]
521    {
522        resolve_xml_entity(entity)
523    }
524
525    #[cfg(feature = "escape-html")]
526    {
527        resolve_html5_entity(entity)
528    }
529}
530
531/// Resolves predefined XML entities. If specified entity is not a predefined XML
532/// entity, `None` is returned.
533///
534/// The complete list of predefined entities are defined in the [specification].
535///
536/// ```
537/// # use quick_xml::escape::resolve_xml_entity;
538/// # use pretty_assertions::assert_eq;
539/// assert_eq!(resolve_xml_entity("lt"), Some("<"));
540/// assert_eq!(resolve_xml_entity("gt"), Some(">"));
541/// assert_eq!(resolve_xml_entity("amp"), Some("&"));
542/// assert_eq!(resolve_xml_entity("apos"), Some("'"));
543/// assert_eq!(resolve_xml_entity("quot"), Some("\""));
544///
545/// assert_eq!(resolve_xml_entity("foo"), None);
546/// ```
547///
548/// [specification]: https://www.w3.org/TR/xml11/#sec-predefined-ent
549pub const fn resolve_xml_entity(entity: &str) -> Option<&'static str> {
550    // match over strings are not allowed in const functions
551    let s = match entity.as_bytes() {
552        b"lt" => "<",
553        b"gt" => ">",
554        b"amp" => "&",
555        b"apos" => "'",
556        b"quot" => "\"",
557        _ => return None,
558    };
559    Some(s)
560}
561
562/// Resolves all HTML5 entities. For complete list see <https://dev.w3.org/html5/html-author/charref>.
563#[cfg(feature = "escape-html")]
564pub const fn resolve_html5_entity(entity: &str) -> Option<&'static str> {
565    // imported from https://dev.w3.org/html5/html-author/charref
566    // match over strings are not allowed in const functions
567    //TODO: automate up-to-dating using https://html.spec.whatwg.org/entities.json
568    //TODO: building this function increases compilation time by 10+ seconds (or 5x times)
569    // Maybe this is because of very long match
570    // See https://github.com/tafia/quick-xml/issues/763
571    let s = match entity.as_bytes() {
572        b"Tab" => "\u{09}",
573        b"NewLine" => "\u{0A}",
574        b"excl" => "\u{21}",
575        b"quot" | b"QUOT" => "\u{22}",
576        b"num" => "\u{23}",
577        b"dollar" => "\u{24}",
578        b"percnt" => "\u{25}",
579        b"amp" | b"AMP" => "\u{26}",
580        b"apos" => "\u{27}",
581        b"lpar" => "\u{28}",
582        b"rpar" => "\u{29}",
583        b"ast" | b"midast" => "\u{2A}",
584        b"plus" => "\u{2B}",
585        b"comma" => "\u{2C}",
586        b"period" => "\u{2E}",
587        b"sol" => "\u{2F}",
588        b"colon" => "\u{3A}",
589        b"semi" => "\u{3B}",
590        b"lt" | b"LT" => "\u{3C}",
591        b"equals" => "\u{3D}",
592        b"gt" | b"GT" => "\u{3E}",
593        b"quest" => "\u{3F}",
594        b"commat" => "\u{40}",
595        b"lsqb" | b"lbrack" => "\u{5B}",
596        b"bsol" => "\u{5C}",
597        b"rsqb" | b"rbrack" => "\u{5D}",
598        b"Hat" => "\u{5E}",
599        b"lowbar" => "\u{5F}",
600        b"grave" | b"DiacriticalGrave" => "\u{60}",
601        b"lcub" | b"lbrace" => "\u{7B}",
602        b"verbar" | b"vert" | b"VerticalLine" => "\u{7C}",
603        b"rcub" | b"rbrace" => "\u{7D}",
604        b"nbsp" | b"NonBreakingSpace" => "\u{A0}",
605        b"iexcl" => "\u{A1}",
606        b"cent" => "\u{A2}",
607        b"pound" => "\u{A3}",
608        b"curren" => "\u{A4}",
609        b"yen" => "\u{A5}",
610        b"brvbar" => "\u{A6}",
611        b"sect" => "\u{A7}",
612        b"Dot" | b"die" | b"DoubleDot" | b"uml" => "\u{A8}",
613        b"copy" | b"COPY" => "\u{A9}",
614        b"ordf" => "\u{AA}",
615        b"laquo" => "\u{AB}",
616        b"not" => "\u{AC}",
617        b"shy" => "\u{AD}",
618        b"reg" | b"circledR" | b"REG" => "\u{AE}",
619        b"macr" | b"OverBar" | b"strns" => "\u{AF}",
620        b"deg" => "\u{B0}",
621        b"plusmn" | b"pm" | b"PlusMinus" => "\u{B1}",
622        b"sup2" => "\u{B2}",
623        b"sup3" => "\u{B3}",
624        b"acute" | b"DiacriticalAcute" => "\u{B4}",
625        b"micro" => "\u{B5}",
626        b"para" => "\u{B6}",
627        b"middot" | b"centerdot" | b"CenterDot" => "\u{B7}",
628        b"cedil" | b"Cedilla" => "\u{B8}",
629        b"sup1" => "\u{B9}",
630        b"ordm" => "\u{BA}",
631        b"raquo" => "\u{BB}",
632        b"frac14" => "\u{BC}",
633        b"frac12" | b"half" => "\u{BD}",
634        b"frac34" => "\u{BE}",
635        b"iquest" => "\u{BF}",
636        b"Agrave" => "\u{C0}",
637        b"Aacute" => "\u{C1}",
638        b"Acirc" => "\u{C2}",
639        b"Atilde" => "\u{C3}",
640        b"Auml" => "\u{C4}",
641        b"Aring" => "\u{C5}",
642        b"AElig" => "\u{C6}",
643        b"Ccedil" => "\u{C7}",
644        b"Egrave" => "\u{C8}",
645        b"Eacute" => "\u{C9}",
646        b"Ecirc" => "\u{CA}",
647        b"Euml" => "\u{CB}",
648        b"Igrave" => "\u{CC}",
649        b"Iacute" => "\u{CD}",
650        b"Icirc" => "\u{CE}",
651        b"Iuml" => "\u{CF}",
652        b"ETH" => "\u{D0}",
653        b"Ntilde" => "\u{D1}",
654        b"Ograve" => "\u{D2}",
655        b"Oacute" => "\u{D3}",
656        b"Ocirc" => "\u{D4}",
657        b"Otilde" => "\u{D5}",
658        b"Ouml" => "\u{D6}",
659        b"times" => "\u{D7}",
660        b"Oslash" => "\u{D8}",
661        b"Ugrave" => "\u{D9}",
662        b"Uacute" => "\u{DA}",
663        b"Ucirc" => "\u{DB}",
664        b"Uuml" => "\u{DC}",
665        b"Yacute" => "\u{DD}",
666        b"THORN" => "\u{DE}",
667        b"szlig" => "\u{DF}",
668        b"agrave" => "\u{E0}",
669        b"aacute" => "\u{E1}",
670        b"acirc" => "\u{E2}",
671        b"atilde" => "\u{E3}",
672        b"auml" => "\u{E4}",
673        b"aring" => "\u{E5}",
674        b"aelig" => "\u{E6}",
675        b"ccedil" => "\u{E7}",
676        b"egrave" => "\u{E8}",
677        b"eacute" => "\u{E9}",
678        b"ecirc" => "\u{EA}",
679        b"euml" => "\u{EB}",
680        b"igrave" => "\u{EC}",
681        b"iacute" => "\u{ED}",
682        b"icirc" => "\u{EE}",
683        b"iuml" => "\u{EF}",
684        b"eth" => "\u{F0}",
685        b"ntilde" => "\u{F1}",
686        b"ograve" => "\u{F2}",
687        b"oacute" => "\u{F3}",
688        b"ocirc" => "\u{F4}",
689        b"otilde" => "\u{F5}",
690        b"ouml" => "\u{F6}",
691        b"divide" | b"div" => "\u{F7}",
692        b"oslash" => "\u{F8}",
693        b"ugrave" => "\u{F9}",
694        b"uacute" => "\u{FA}",
695        b"ucirc" => "\u{FB}",
696        b"uuml" => "\u{FC}",
697        b"yacute" => "\u{FD}",
698        b"thorn" => "\u{FE}",
699        b"yuml" => "\u{FF}",
700        b"Amacr" => "\u{10}",
701        b"amacr" => "\u{10}",
702        b"Abreve" => "\u{10}",
703        b"abreve" => "\u{10}",
704        b"Aogon" => "\u{10}",
705        b"aogon" => "\u{10}",
706        b"Cacute" => "\u{10}",
707        b"cacute" => "\u{10}",
708        b"Ccirc" => "\u{10}",
709        b"ccirc" => "\u{10}",
710        b"Cdot" => "\u{10}",
711        b"cdot" => "\u{10}",
712        b"Ccaron" => "\u{10}",
713        b"ccaron" => "\u{10}",
714        b"Dcaron" => "\u{10}",
715        b"dcaron" => "\u{10}",
716        b"Dstrok" => "\u{11}",
717        b"dstrok" => "\u{11}",
718        b"Emacr" => "\u{11}",
719        b"emacr" => "\u{11}",
720        b"Edot" => "\u{11}",
721        b"edot" => "\u{11}",
722        b"Eogon" => "\u{11}",
723        b"eogon" => "\u{11}",
724        b"Ecaron" => "\u{11}",
725        b"ecaron" => "\u{11}",
726        b"Gcirc" => "\u{11}",
727        b"gcirc" => "\u{11}",
728        b"Gbreve" => "\u{11}",
729        b"gbreve" => "\u{11}",
730        b"Gdot" => "\u{12}",
731        b"gdot" => "\u{12}",
732        b"Gcedil" => "\u{12}",
733        b"Hcirc" => "\u{12}",
734        b"hcirc" => "\u{12}",
735        b"Hstrok" => "\u{12}",
736        b"hstrok" => "\u{12}",
737        b"Itilde" => "\u{12}",
738        b"itilde" => "\u{12}",
739        b"Imacr" => "\u{12}",
740        b"imacr" => "\u{12}",
741        b"Iogon" => "\u{12}",
742        b"iogon" => "\u{12}",
743        b"Idot" => "\u{13}",
744        b"imath" | b"inodot" => "\u{13}",
745        b"IJlig" => "\u{13}",
746        b"ijlig" => "\u{13}",
747        b"Jcirc" => "\u{13}",
748        b"jcirc" => "\u{13}",
749        b"Kcedil" => "\u{13}",
750        b"kcedil" => "\u{13}",
751        b"kgreen" => "\u{13}",
752        b"Lacute" => "\u{13}",
753        b"lacute" => "\u{13}",
754        b"Lcedil" => "\u{13}",
755        b"lcedil" => "\u{13}",
756        b"Lcaron" => "\u{13}",
757        b"lcaron" => "\u{13}",
758        b"Lmidot" => "\u{13}",
759        b"lmidot" => "\u{14}",
760        b"Lstrok" => "\u{14}",
761        b"lstrok" => "\u{14}",
762        b"Nacute" => "\u{14}",
763        b"nacute" => "\u{14}",
764        b"Ncedil" => "\u{14}",
765        b"ncedil" => "\u{14}",
766        b"Ncaron" => "\u{14}",
767        b"ncaron" => "\u{14}",
768        b"napos" => "\u{14}",
769        b"ENG" => "\u{14}",
770        b"eng" => "\u{14}",
771        b"Omacr" => "\u{14}",
772        b"omacr" => "\u{14}",
773        b"Odblac" => "\u{15}",
774        b"odblac" => "\u{15}",
775        b"OElig" => "\u{15}",
776        b"oelig" => "\u{15}",
777        b"Racute" => "\u{15}",
778        b"racute" => "\u{15}",
779        b"Rcedil" => "\u{15}",
780        b"rcedil" => "\u{15}",
781        b"Rcaron" => "\u{15}",
782        b"rcaron" => "\u{15}",
783        b"Sacute" => "\u{15}",
784        b"sacute" => "\u{15}",
785        b"Scirc" => "\u{15}",
786        b"scirc" => "\u{15}",
787        b"Scedil" => "\u{15}",
788        b"scedil" => "\u{15}",
789        b"Scaron" => "\u{16}",
790        b"scaron" => "\u{16}",
791        b"Tcedil" => "\u{16}",
792        b"tcedil" => "\u{16}",
793        b"Tcaron" => "\u{16}",
794        b"tcaron" => "\u{16}",
795        b"Tstrok" => "\u{16}",
796        b"tstrok" => "\u{16}",
797        b"Utilde" => "\u{16}",
798        b"utilde" => "\u{16}",
799        b"Umacr" => "\u{16}",
800        b"umacr" => "\u{16}",
801        b"Ubreve" => "\u{16}",
802        b"ubreve" => "\u{16}",
803        b"Uring" => "\u{16}",
804        b"uring" => "\u{16}",
805        b"Udblac" => "\u{17}",
806        b"udblac" => "\u{17}",
807        b"Uogon" => "\u{17}",
808        b"uogon" => "\u{17}",
809        b"Wcirc" => "\u{17}",
810        b"wcirc" => "\u{17}",
811        b"Ycirc" => "\u{17}",
812        b"ycirc" => "\u{17}",
813        b"Yuml" => "\u{17}",
814        b"Zacute" => "\u{17}",
815        b"zacute" => "\u{17}",
816        b"Zdot" => "\u{17}",
817        b"zdot" => "\u{17}",
818        b"Zcaron" => "\u{17}",
819        b"zcaron" => "\u{17}",
820        b"fnof" => "\u{19}",
821        b"imped" => "\u{1B}",
822        b"gacute" => "\u{1F}",
823        b"jmath" => "\u{23}",
824        b"circ" => "\u{2C}",
825        b"caron" | b"Hacek" => "\u{2C}",
826        b"breve" | b"Breve" => "\u{2D}",
827        b"dot" | b"DiacriticalDot" => "\u{2D}",
828        b"ring" => "\u{2D}",
829        b"ogon" => "\u{2D}",
830        b"tilde" | b"DiacriticalTilde" => "\u{2D}",
831        b"dblac" | b"DiacriticalDoubleAcute" => "\u{2D}",
832        b"DownBreve" => "\u{31}",
833        b"UnderBar" => "\u{33}",
834        b"Alpha" => "\u{39}",
835        b"Beta" => "\u{39}",
836        b"Gamma" => "\u{39}",
837        b"Delta" => "\u{39}",
838        b"Epsilon" => "\u{39}",
839        b"Zeta" => "\u{39}",
840        b"Eta" => "\u{39}",
841        b"Theta" => "\u{39}",
842        b"Iota" => "\u{39}",
843        b"Kappa" => "\u{39}",
844        b"Lambda" => "\u{39}",
845        b"Mu" => "\u{39}",
846        b"Nu" => "\u{39}",
847        b"Xi" => "\u{39}",
848        b"Omicron" => "\u{39}",
849        b"Pi" => "\u{3A}",
850        b"Rho" => "\u{3A}",
851        b"Sigma" => "\u{3A}",
852        b"Tau" => "\u{3A}",
853        b"Upsilon" => "\u{3A}",
854        b"Phi" => "\u{3A}",
855        b"Chi" => "\u{3A}",
856        b"Psi" => "\u{3A}",
857        b"Omega" => "\u{3A}",
858        b"alpha" => "\u{3B}",
859        b"beta" => "\u{3B}",
860        b"gamma" => "\u{3B}",
861        b"delta" => "\u{3B}",
862        b"epsiv" | b"varepsilon" | b"epsilon" => "\u{3B}",
863        b"zeta" => "\u{3B}",
864        b"eta" => "\u{3B}",
865        b"theta" => "\u{3B}",
866        b"iota" => "\u{3B}",
867        b"kappa" => "\u{3B}",
868        b"lambda" => "\u{3B}",
869        b"mu" => "\u{3B}",
870        b"nu" => "\u{3B}",
871        b"xi" => "\u{3B}",
872        b"omicron" => "\u{3B}",
873        b"pi" => "\u{3C}",
874        b"rho" => "\u{3C}",
875        b"sigmav" | b"varsigma" | b"sigmaf" => "\u{3C}",
876        b"sigma" => "\u{3C}",
877        b"tau" => "\u{3C}",
878        b"upsi" | b"upsilon" => "\u{3C}",
879        b"phi" | b"phiv" | b"varphi" => "\u{3C}",
880        b"chi" => "\u{3C}",
881        b"psi" => "\u{3C}",
882        b"omega" => "\u{3C}",
883        b"thetav" | b"vartheta" | b"thetasym" => "\u{3D}",
884        b"Upsi" | b"upsih" => "\u{3D}",
885        b"straightphi" => "\u{3D}",
886        b"piv" | b"varpi" => "\u{3D}",
887        b"Gammad" => "\u{3D}",
888        b"gammad" | b"digamma" => "\u{3D}",
889        b"kappav" | b"varkappa" => "\u{3F}",
890        b"rhov" | b"varrho" => "\u{3F}",
891        b"epsi" | b"straightepsilon" => "\u{3F}",
892        b"bepsi" | b"backepsilon" => "\u{3F}",
893        b"IOcy" => "\u{40}",
894        b"DJcy" => "\u{40}",
895        b"GJcy" => "\u{40}",
896        b"Jukcy" => "\u{40}",
897        b"DScy" => "\u{40}",
898        b"Iukcy" => "\u{40}",
899        b"YIcy" => "\u{40}",
900        b"Jsercy" => "\u{40}",
901        b"LJcy" => "\u{40}",
902        b"NJcy" => "\u{40}",
903        b"TSHcy" => "\u{40}",
904        b"KJcy" => "\u{40}",
905        b"Ubrcy" => "\u{40}",
906        b"DZcy" => "\u{40}",
907        b"Acy" => "\u{41}",
908        b"Bcy" => "\u{41}",
909        b"Vcy" => "\u{41}",
910        b"Gcy" => "\u{41}",
911        b"Dcy" => "\u{41}",
912        b"IEcy" => "\u{41}",
913        b"ZHcy" => "\u{41}",
914        b"Zcy" => "\u{41}",
915        b"Icy" => "\u{41}",
916        b"Jcy" => "\u{41}",
917        b"Kcy" => "\u{41}",
918        b"Lcy" => "\u{41}",
919        b"Mcy" => "\u{41}",
920        b"Ncy" => "\u{41}",
921        b"Ocy" => "\u{41}",
922        b"Pcy" => "\u{41}",
923        b"Rcy" => "\u{42}",
924        b"Scy" => "\u{42}",
925        b"Tcy" => "\u{42}",
926        b"Ucy" => "\u{42}",
927        b"Fcy" => "\u{42}",
928        b"KHcy" => "\u{42}",
929        b"TScy" => "\u{42}",
930        b"CHcy" => "\u{42}",
931        b"SHcy" => "\u{42}",
932        b"SHCHcy" => "\u{42}",
933        b"HARDcy" => "\u{42}",
934        b"Ycy" => "\u{42}",
935        b"SOFTcy" => "\u{42}",
936        b"Ecy" => "\u{42}",
937        b"YUcy" => "\u{42}",
938        b"YAcy" => "\u{42}",
939        b"acy" => "\u{43}",
940        b"bcy" => "\u{43}",
941        b"vcy" => "\u{43}",
942        b"gcy" => "\u{43}",
943        b"dcy" => "\u{43}",
944        b"iecy" => "\u{43}",
945        b"zhcy" => "\u{43}",
946        b"zcy" => "\u{43}",
947        b"icy" => "\u{43}",
948        b"jcy" => "\u{43}",
949        b"kcy" => "\u{43}",
950        b"lcy" => "\u{43}",
951        b"mcy" => "\u{43}",
952        b"ncy" => "\u{43}",
953        b"ocy" => "\u{43}",
954        b"pcy" => "\u{43}",
955        b"rcy" => "\u{44}",
956        b"scy" => "\u{44}",
957        b"tcy" => "\u{44}",
958        b"ucy" => "\u{44}",
959        b"fcy" => "\u{44}",
960        b"khcy" => "\u{44}",
961        b"tscy" => "\u{44}",
962        b"chcy" => "\u{44}",
963        b"shcy" => "\u{44}",
964        b"shchcy" => "\u{44}",
965        b"hardcy" => "\u{44}",
966        b"ycy" => "\u{44}",
967        b"softcy" => "\u{44}",
968        b"ecy" => "\u{44}",
969        b"yucy" => "\u{44}",
970        b"yacy" => "\u{44}",
971        b"iocy" => "\u{45}",
972        b"djcy" => "\u{45}",
973        b"gjcy" => "\u{45}",
974        b"jukcy" => "\u{45}",
975        b"dscy" => "\u{45}",
976        b"iukcy" => "\u{45}",
977        b"yicy" => "\u{45}",
978        b"jsercy" => "\u{45}",
979        b"ljcy" => "\u{45}",
980        b"njcy" => "\u{45}",
981        b"tshcy" => "\u{45}",
982        b"kjcy" => "\u{45}",
983        b"ubrcy" => "\u{45}",
984        b"dzcy" => "\u{45}",
985        b"ensp" => "\u{2002}",
986        b"emsp" => "\u{2003}",
987        b"emsp13" => "\u{2004}",
988        b"emsp14" => "\u{2005}",
989        b"numsp" => "\u{2007}",
990        b"puncsp" => "\u{2008}",
991        b"thinsp" | b"ThinSpace" => "\u{2009}",
992        b"hairsp" | b"VeryThinSpace" => "\u{200A}",
993        b"ZeroWidthSpace"
994        | b"NegativeVeryThinSpace"
995        | b"NegativeThinSpace"
996        | b"NegativeMediumSpace"
997        | b"NegativeThickSpace" => "\u{200B}",
998        b"zwnj" => "\u{200C}",
999        b"zwj" => "\u{200D}",
1000        b"lrm" => "\u{200E}",
1001        b"rlm" => "\u{200F}",
1002        b"hyphen" | b"dash" => "\u{2010}",
1003        b"ndash" => "\u{2013}",
1004        b"mdash" => "\u{2014}",
1005        b"horbar" => "\u{2015}",
1006        b"Verbar" | b"Vert" => "\u{2016}",
1007        b"lsquo" | b"OpenCurlyQuote" => "\u{2018}",
1008        b"rsquo" | b"rsquor" | b"CloseCurlyQuote" => "\u{2019}",
1009        b"lsquor" | b"sbquo" => "\u{201A}",
1010        b"ldquo" | b"OpenCurlyDoubleQuote" => "\u{201C}",
1011        b"rdquo" | b"rdquor" | b"CloseCurlyDoubleQuote" => "\u{201D}",
1012        b"ldquor" | b"bdquo" => "\u{201E}",
1013        b"dagger" => "\u{2020}",
1014        b"Dagger" | b"ddagger" => "\u{2021}",
1015        b"bull" | b"bullet" => "\u{2022}",
1016        b"nldr" => "\u{2025}",
1017        b"hellip" | b"mldr" => "\u{2026}",
1018        b"permil" => "\u{2030}",
1019        b"pertenk" => "\u{2031}",
1020        b"prime" => "\u{2032}",
1021        b"Prime" => "\u{2033}",
1022        b"tprime" => "\u{2034}",
1023        b"bprime" | b"backprime" => "\u{2035}",
1024        b"lsaquo" => "\u{2039}",
1025        b"rsaquo" => "\u{203A}",
1026        b"oline" => "\u{203E}",
1027        b"caret" => "\u{2041}",
1028        b"hybull" => "\u{2043}",
1029        b"frasl" => "\u{2044}",
1030        b"bsemi" => "\u{204F}",
1031        b"qprime" => "\u{2057}",
1032        b"MediumSpace" => "\u{205F}",
1033        b"NoBreak" => "\u{2060}",
1034        b"ApplyFunction" | b"af" => "\u{2061}",
1035        b"InvisibleTimes" | b"it" => "\u{2062}",
1036        b"InvisibleComma" | b"ic" => "\u{2063}",
1037        b"euro" => "\u{20AC}",
1038        b"tdot" | b"TripleDot" => "\u{20DB}",
1039        b"DotDot" => "\u{20DC}",
1040        b"Copf" | b"complexes" => "\u{2102}",
1041        b"incare" => "\u{2105}",
1042        b"gscr" => "\u{210A}",
1043        b"hamilt" | b"HilbertSpace" | b"Hscr" => "\u{210B}",
1044        b"Hfr" | b"Poincareplane" => "\u{210C}",
1045        b"quaternions" | b"Hopf" => "\u{210D}",
1046        b"planckh" => "\u{210E}",
1047        b"planck" | b"hbar" | b"plankv" | b"hslash" => "\u{210F}",
1048        b"Iscr" | b"imagline" => "\u{2110}",
1049        b"image" | b"Im" | b"imagpart" | b"Ifr" => "\u{2111}",
1050        b"Lscr" | b"lagran" | b"Laplacetrf" => "\u{2112}",
1051        b"ell" => "\u{2113}",
1052        b"Nopf" | b"naturals" => "\u{2115}",
1053        b"numero" => "\u{2116}",
1054        b"copysr" => "\u{2117}",
1055        b"weierp" | b"wp" => "\u{2118}",
1056        b"Popf" | b"primes" => "\u{2119}",
1057        b"rationals" | b"Qopf" => "\u{211A}",
1058        b"Rscr" | b"realine" => "\u{211B}",
1059        b"real" | b"Re" | b"realpart" | b"Rfr" => "\u{211C}",
1060        b"reals" | b"Ropf" => "\u{211D}",
1061        b"rx" => "\u{211E}",
1062        b"trade" | b"TRADE" => "\u{2122}",
1063        b"integers" | b"Zopf" => "\u{2124}",
1064        b"ohm" => "\u{2126}",
1065        b"mho" => "\u{2127}",
1066        b"Zfr" | b"zeetrf" => "\u{2128}",
1067        b"iiota" => "\u{2129}",
1068        b"angst" => "\u{212B}",
1069        b"bernou" | b"Bernoullis" | b"Bscr" => "\u{212C}",
1070        b"Cfr" | b"Cayleys" => "\u{212D}",
1071        b"escr" => "\u{212F}",
1072        b"Escr" | b"expectation" => "\u{2130}",
1073        b"Fscr" | b"Fouriertrf" => "\u{2131}",
1074        b"phmmat" | b"Mellintrf" | b"Mscr" => "\u{2133}",
1075        b"order" | b"orderof" | b"oscr" => "\u{2134}",
1076        b"alefsym" | b"aleph" => "\u{2135}",
1077        b"beth" => "\u{2136}",
1078        b"gimel" => "\u{2137}",
1079        b"daleth" => "\u{2138}",
1080        b"CapitalDifferentialD" | b"DD" => "\u{2145}",
1081        b"DifferentialD" | b"dd" => "\u{2146}",
1082        b"ExponentialE" | b"exponentiale" | b"ee" => "\u{2147}",
1083        b"ImaginaryI" | b"ii" => "\u{2148}",
1084        b"frac13" => "\u{2153}",
1085        b"frac23" => "\u{2154}",
1086        b"frac15" => "\u{2155}",
1087        b"frac25" => "\u{2156}",
1088        b"frac35" => "\u{2157}",
1089        b"frac45" => "\u{2158}",
1090        b"frac16" => "\u{2159}",
1091        b"frac56" => "\u{215A}",
1092        b"frac18" => "\u{215B}",
1093        b"frac38" => "\u{215C}",
1094        b"frac58" => "\u{215D}",
1095        b"frac78" => "\u{215E}",
1096        b"larr" | b"leftarrow" | b"LeftArrow" | b"slarr" | b"ShortLeftArrow" => "\u{2190}",
1097        b"uarr" | b"uparrow" | b"UpArrow" | b"ShortUpArrow" => "\u{2191}",
1098        b"rarr" | b"rightarrow" | b"RightArrow" | b"srarr" | b"ShortRightArrow" => "\u{2192}",
1099        b"darr" | b"downarrow" | b"DownArrow" | b"ShortDownArrow" => "\u{2193}",
1100        b"harr" | b"leftrightarrow" | b"LeftRightArrow" => "\u{2194}",
1101        b"varr" | b"updownarrow" | b"UpDownArrow" => "\u{2195}",
1102        b"nwarr" | b"UpperLeftArrow" | b"nwarrow" => "\u{2196}",
1103        b"nearr" | b"UpperRightArrow" | b"nearrow" => "\u{2197}",
1104        b"searr" | b"searrow" | b"LowerRightArrow" => "\u{2198}",
1105        b"swarr" | b"swarrow" | b"LowerLeftArrow" => "\u{2199}",
1106        b"nlarr" | b"nleftarrow" => "\u{219A}",
1107        b"nrarr" | b"nrightarrow" => "\u{219B}",
1108        b"rarrw" | b"rightsquigarrow" => "\u{219D}",
1109        b"Larr" | b"twoheadleftarrow" => "\u{219E}",
1110        b"Uarr" => "\u{219F}",
1111        b"Rarr" | b"twoheadrightarrow" => "\u{21A0}",
1112        b"Darr" => "\u{21A1}",
1113        b"larrtl" | b"leftarrowtail" => "\u{21A2}",
1114        b"rarrtl" | b"rightarrowtail" => "\u{21A3}",
1115        b"LeftTeeArrow" | b"mapstoleft" => "\u{21A4}",
1116        b"UpTeeArrow" | b"mapstoup" => "\u{21A5}",
1117        b"map" | b"RightTeeArrow" | b"mapsto" => "\u{21A6}",
1118        b"DownTeeArrow" | b"mapstodown" => "\u{21A7}",
1119        b"larrhk" | b"hookleftarrow" => "\u{21A9}",
1120        b"rarrhk" | b"hookrightarrow" => "\u{21AA}",
1121        b"larrlp" | b"looparrowleft" => "\u{21AB}",
1122        b"rarrlp" | b"looparrowright" => "\u{21AC}",
1123        b"harrw" | b"leftrightsquigarrow" => "\u{21AD}",
1124        b"nharr" | b"nleftrightarrow" => "\u{21AE}",
1125        b"lsh" | b"Lsh" => "\u{21B0}",
1126        b"rsh" | b"Rsh" => "\u{21B1}",
1127        b"ldsh" => "\u{21B2}",
1128        b"rdsh" => "\u{21B3}",
1129        b"crarr" => "\u{21B5}",
1130        b"cularr" | b"curvearrowleft" => "\u{21B6}",
1131        b"curarr" | b"curvearrowright" => "\u{21B7}",
1132        b"olarr" | b"circlearrowleft" => "\u{21BA}",
1133        b"orarr" | b"circlearrowright" => "\u{21BB}",
1134        b"lharu" | b"LeftVector" | b"leftharpoonup" => "\u{21BC}",
1135        b"lhard" | b"leftharpoondown" | b"DownLeftVector" => "\u{21BD}",
1136        b"uharr" | b"upharpoonright" | b"RightUpVector" => "\u{21BE}",
1137        b"uharl" | b"upharpoonleft" | b"LeftUpVector" => "\u{21BF}",
1138        b"rharu" | b"RightVector" | b"rightharpoonup" => "\u{21C0}",
1139        b"rhard" | b"rightharpoondown" | b"DownRightVector" => "\u{21C1}",
1140        b"dharr" | b"RightDownVector" | b"downharpoonright" => "\u{21C2}",
1141        b"dharl" | b"LeftDownVector" | b"downharpoonleft" => "\u{21C3}",
1142        b"rlarr" | b"rightleftarrows" | b"RightArrowLeftArrow" => "\u{21C4}",
1143        b"udarr" | b"UpArrowDownArrow" => "\u{21C5}",
1144        b"lrarr" | b"leftrightarrows" | b"LeftArrowRightArrow" => "\u{21C6}",
1145        b"llarr" | b"leftleftarrows" => "\u{21C7}",
1146        b"uuarr" | b"upuparrows" => "\u{21C8}",
1147        b"rrarr" | b"rightrightarrows" => "\u{21C9}",
1148        b"ddarr" | b"downdownarrows" => "\u{21CA}",
1149        b"lrhar" | b"ReverseEquilibrium" | b"leftrightharpoons" => "\u{21CB}",
1150        b"rlhar" | b"rightleftharpoons" | b"Equilibrium" => "\u{21CC}",
1151        b"nlArr" | b"nLeftarrow" => "\u{21CD}",
1152        b"nhArr" | b"nLeftrightarrow" => "\u{21CE}",
1153        b"nrArr" | b"nRightarrow" => "\u{21CF}",
1154        b"lArr" | b"Leftarrow" | b"DoubleLeftArrow" => "\u{21D0}",
1155        b"uArr" | b"Uparrow" | b"DoubleUpArrow" => "\u{21D1}",
1156        b"rArr" | b"Rightarrow" | b"Implies" | b"DoubleRightArrow" => "\u{21D2}",
1157        b"dArr" | b"Downarrow" | b"DoubleDownArrow" => "\u{21D3}",
1158        b"hArr" | b"Leftrightarrow" | b"DoubleLeftRightArrow" | b"iff" => "\u{21D4}",
1159        b"vArr" | b"Updownarrow" | b"DoubleUpDownArrow" => "\u{21D5}",
1160        b"nwArr" => "\u{21D6}",
1161        b"neArr" => "\u{21D7}",
1162        b"seArr" => "\u{21D8}",
1163        b"swArr" => "\u{21D9}",
1164        b"lAarr" | b"Lleftarrow" => "\u{21DA}",
1165        b"rAarr" | b"Rrightarrow" => "\u{21DB}",
1166        b"zigrarr" => "\u{21DD}",
1167        b"larrb" | b"LeftArrowBar" => "\u{21E4}",
1168        b"rarrb" | b"RightArrowBar" => "\u{21E5}",
1169        b"duarr" | b"DownArrowUpArrow" => "\u{21F5}",
1170        b"loarr" => "\u{21FD}",
1171        b"roarr" => "\u{21FE}",
1172        b"hoarr" => "\u{21FF}",
1173        b"forall" | b"ForAll" => "\u{2200}",
1174        b"comp" | b"complement" => "\u{2201}",
1175        b"part" | b"PartialD" => "\u{2202}",
1176        b"exist" | b"Exists" => "\u{2203}",
1177        b"nexist" | b"NotExists" | b"nexists" => "\u{2204}",
1178        b"empty" | b"emptyset" | b"emptyv" | b"varnothing" => "\u{2205}",
1179        b"nabla" | b"Del" => "\u{2207}",
1180        b"isin" | b"isinv" | b"Element" | b"in" => "\u{2208}",
1181        b"notin" | b"NotElement" | b"notinva" => "\u{2209}",
1182        b"niv" | b"ReverseElement" | b"ni" | b"SuchThat" => "\u{220B}",
1183        b"notni" | b"notniva" | b"NotReverseElement" => "\u{220C}",
1184        b"prod" | b"Product" => "\u{220F}",
1185        b"coprod" | b"Coproduct" => "\u{2210}",
1186        b"sum" | b"Sum" => "\u{2211}",
1187        b"minus" => "\u{2212}",
1188        b"mnplus" | b"mp" | b"MinusPlus" => "\u{2213}",
1189        b"plusdo" | b"dotplus" => "\u{2214}",
1190        b"setmn" | b"setminus" | b"Backslash" | b"ssetmn" | b"smallsetminus" => "\u{2216}",
1191        b"lowast" => "\u{2217}",
1192        b"compfn" | b"SmallCircle" => "\u{2218}",
1193        b"radic" | b"Sqrt" => "\u{221A}",
1194        b"prop" | b"propto" | b"Proportional" | b"vprop" | b"varpropto" => "\u{221D}",
1195        b"infin" => "\u{221E}",
1196        b"angrt" => "\u{221F}",
1197        b"ang" | b"angle" => "\u{2220}",
1198        b"angmsd" | b"measuredangle" => "\u{2221}",
1199        b"angsph" => "\u{2222}",
1200        b"mid" | b"VerticalBar" | b"smid" | b"shortmid" => "\u{2223}",
1201        b"nmid" | b"NotVerticalBar" | b"nsmid" | b"nshortmid" => "\u{2224}",
1202        b"par" | b"parallel" | b"DoubleVerticalBar" | b"spar" | b"shortparallel" => "\u{2225}",
1203        b"npar" | b"nparallel" | b"NotDoubleVerticalBar" | b"nspar" | b"nshortparallel" => {
1204            "\u{2226}"
1205        }
1206        b"and" | b"wedge" => "\u{2227}",
1207        b"or" | b"vee" => "\u{2228}",
1208        b"cap" => "\u{2229}",
1209        b"cup" => "\u{222A}",
1210        b"int" | b"Integral" => "\u{222B}",
1211        b"Int" => "\u{222C}",
1212        b"tint" | b"iiint" => "\u{222D}",
1213        b"conint" | b"oint" | b"ContourIntegral" => "\u{222E}",
1214        b"Conint" | b"DoubleContourIntegral" => "\u{222F}",
1215        b"Cconint" => "\u{2230}",
1216        b"cwint" => "\u{2231}",
1217        b"cwconint" | b"ClockwiseContourIntegral" => "\u{2232}",
1218        b"awconint" | b"CounterClockwiseContourIntegral" => "\u{2233}",
1219        b"there4" | b"therefore" | b"Therefore" => "\u{2234}",
1220        b"becaus" | b"because" | b"Because" => "\u{2235}",
1221        b"ratio" => "\u{2236}",
1222        b"Colon" | b"Proportion" => "\u{2237}",
1223        b"minusd" | b"dotminus" => "\u{2238}",
1224        b"mDDot" => "\u{223A}",
1225        b"homtht" => "\u{223B}",
1226        b"sim" | b"Tilde" | b"thksim" | b"thicksim" => "\u{223C}",
1227        b"bsim" | b"backsim" => "\u{223D}",
1228        b"ac" | b"mstpos" => "\u{223E}",
1229        b"acd" => "\u{223F}",
1230        b"wreath" | b"VerticalTilde" | b"wr" => "\u{2240}",
1231        b"nsim" | b"NotTilde" => "\u{2241}",
1232        b"esim" | b"EqualTilde" | b"eqsim" => "\u{2242}",
1233        b"sime" | b"TildeEqual" | b"simeq" => "\u{2243}",
1234        b"nsime" | b"nsimeq" | b"NotTildeEqual" => "\u{2244}",
1235        b"cong" | b"TildeFullEqual" => "\u{2245}",
1236        b"simne" => "\u{2246}",
1237        b"ncong" | b"NotTildeFullEqual" => "\u{2247}",
1238        b"asymp" | b"ap" | b"TildeTilde" | b"approx" | b"thkap" | b"thickapprox" => "\u{2248}",
1239        b"nap" | b"NotTildeTilde" | b"napprox" => "\u{2249}",
1240        b"ape" | b"approxeq" => "\u{224A}",
1241        b"apid" => "\u{224B}",
1242        b"bcong" | b"backcong" => "\u{224C}",
1243        b"asympeq" | b"CupCap" => "\u{224D}",
1244        b"bump" | b"HumpDownHump" | b"Bumpeq" => "\u{224E}",
1245        b"bumpe" | b"HumpEqual" | b"bumpeq" => "\u{224F}",
1246        b"esdot" | b"DotEqual" | b"doteq" => "\u{2250}",
1247        b"eDot" | b"doteqdot" => "\u{2251}",
1248        b"efDot" | b"fallingdotseq" => "\u{2252}",
1249        b"erDot" | b"risingdotseq" => "\u{2253}",
1250        b"colone" | b"coloneq" | b"Assign" => "\u{2254}",
1251        b"ecolon" | b"eqcolon" => "\u{2255}",
1252        b"ecir" | b"eqcirc" => "\u{2256}",
1253        b"cire" | b"circeq" => "\u{2257}",
1254        b"wedgeq" => "\u{2259}",
1255        b"veeeq" => "\u{225A}",
1256        b"trie" | b"triangleq" => "\u{225C}",
1257        b"equest" | b"questeq" => "\u{225F}",
1258        b"ne" | b"NotEqual" => "\u{2260}",
1259        b"equiv" | b"Congruent" => "\u{2261}",
1260        b"nequiv" | b"NotCongruent" => "\u{2262}",
1261        b"le" | b"leq" => "\u{2264}",
1262        b"ge" | b"GreaterEqual" | b"geq" => "\u{2265}",
1263        b"lE" | b"LessFullEqual" | b"leqq" => "\u{2266}",
1264        b"gE" | b"GreaterFullEqual" | b"geqq" => "\u{2267}",
1265        b"lnE" | b"lneqq" => "\u{2268}",
1266        b"gnE" | b"gneqq" => "\u{2269}",
1267        b"Lt" | b"NestedLessLess" | b"ll" => "\u{226A}",
1268        b"Gt" | b"NestedGreaterGreater" | b"gg" => "\u{226B}",
1269        b"twixt" | b"between" => "\u{226C}",
1270        b"NotCupCap" => "\u{226D}",
1271        b"nlt" | b"NotLess" | b"nless" => "\u{226E}",
1272        b"ngt" | b"NotGreater" | b"ngtr" => "\u{226F}",
1273        b"nle" | b"NotLessEqual" | b"nleq" => "\u{2270}",
1274        b"nge" | b"NotGreaterEqual" | b"ngeq" => "\u{2271}",
1275        b"lsim" | b"LessTilde" | b"lesssim" => "\u{2272}",
1276        b"gsim" | b"gtrsim" | b"GreaterTilde" => "\u{2273}",
1277        b"nlsim" | b"NotLessTilde" => "\u{2274}",
1278        b"ngsim" | b"NotGreaterTilde" => "\u{2275}",
1279        b"lg" | b"lessgtr" | b"LessGreater" => "\u{2276}",
1280        b"gl" | b"gtrless" | b"GreaterLess" => "\u{2277}",
1281        b"ntlg" | b"NotLessGreater" => "\u{2278}",
1282        b"ntgl" | b"NotGreaterLess" => "\u{2279}",
1283        b"pr" | b"Precedes" | b"prec" => "\u{227A}",
1284        b"sc" | b"Succeeds" | b"succ" => "\u{227B}",
1285        b"prcue" | b"PrecedesSlantEqual" | b"preccurlyeq" => "\u{227C}",
1286        b"sccue" | b"SucceedsSlantEqual" | b"succcurlyeq" => "\u{227D}",
1287        b"prsim" | b"precsim" | b"PrecedesTilde" => "\u{227E}",
1288        b"scsim" | b"succsim" | b"SucceedsTilde" => "\u{227F}",
1289        b"npr" | b"nprec" | b"NotPrecedes" => "\u{2280}",
1290        b"nsc" | b"nsucc" | b"NotSucceeds" => "\u{2281}",
1291        b"sub" | b"subset" => "\u{2282}",
1292        b"sup" | b"supset" | b"Superset" => "\u{2283}",
1293        b"nsub" => "\u{2284}",
1294        b"nsup" => "\u{2285}",
1295        b"sube" | b"SubsetEqual" | b"subseteq" => "\u{2286}",
1296        b"supe" | b"supseteq" | b"SupersetEqual" => "\u{2287}",
1297        b"nsube" | b"nsubseteq" | b"NotSubsetEqual" => "\u{2288}",
1298        b"nsupe" | b"nsupseteq" | b"NotSupersetEqual" => "\u{2289}",
1299        b"subne" | b"subsetneq" => "\u{228A}",
1300        b"supne" | b"supsetneq" => "\u{228B}",
1301        b"cupdot" => "\u{228D}",
1302        b"uplus" | b"UnionPlus" => "\u{228E}",
1303        b"sqsub" | b"SquareSubset" | b"sqsubset" => "\u{228F}",
1304        b"sqsup" | b"SquareSuperset" | b"sqsupset" => "\u{2290}",
1305        b"sqsube" | b"SquareSubsetEqual" | b"sqsubseteq" => "\u{2291}",
1306        b"sqsupe" | b"SquareSupersetEqual" | b"sqsupseteq" => "\u{2292}",
1307        b"sqcap" | b"SquareIntersection" => "\u{2293}",
1308        b"sqcup" | b"SquareUnion" => "\u{2294}",
1309        b"oplus" | b"CirclePlus" => "\u{2295}",
1310        b"ominus" | b"CircleMinus" => "\u{2296}",
1311        b"otimes" | b"CircleTimes" => "\u{2297}",
1312        b"osol" => "\u{2298}",
1313        b"odot" | b"CircleDot" => "\u{2299}",
1314        b"ocir" | b"circledcirc" => "\u{229A}",
1315        b"oast" | b"circledast" => "\u{229B}",
1316        b"odash" | b"circleddash" => "\u{229D}",
1317        b"plusb" | b"boxplus" => "\u{229E}",
1318        b"minusb" | b"boxminus" => "\u{229F}",
1319        b"timesb" | b"boxtimes" => "\u{22A0}",
1320        b"sdotb" | b"dotsquare" => "\u{22A1}",
1321        b"vdash" | b"RightTee" => "\u{22A2}",
1322        b"dashv" | b"LeftTee" => "\u{22A3}",
1323        b"top" | b"DownTee" => "\u{22A4}",
1324        b"bottom" | b"bot" | b"perp" | b"UpTee" => "\u{22A5}",
1325        b"models" => "\u{22A7}",
1326        b"vDash" | b"DoubleRightTee" => "\u{22A8}",
1327        b"Vdash" => "\u{22A9}",
1328        b"Vvdash" => "\u{22AA}",
1329        b"VDash" => "\u{22AB}",
1330        b"nvdash" => "\u{22AC}",
1331        b"nvDash" => "\u{22AD}",
1332        b"nVdash" => "\u{22AE}",
1333        b"nVDash" => "\u{22AF}",
1334        b"prurel" => "\u{22B0}",
1335        b"vltri" | b"vartriangleleft" | b"LeftTriangle" => "\u{22B2}",
1336        b"vrtri" | b"vartriangleright" | b"RightTriangle" => "\u{22B3}",
1337        b"ltrie" | b"trianglelefteq" | b"LeftTriangleEqual" => "\u{22B4}",
1338        b"rtrie" | b"trianglerighteq" | b"RightTriangleEqual" => "\u{22B5}",
1339        b"origof" => "\u{22B6}",
1340        b"imof" => "\u{22B7}",
1341        b"mumap" | b"multimap" => "\u{22B8}",
1342        b"hercon" => "\u{22B9}",
1343        b"intcal" | b"intercal" => "\u{22BA}",
1344        b"veebar" => "\u{22BB}",
1345        b"barvee" => "\u{22BD}",
1346        b"angrtvb" => "\u{22BE}",
1347        b"lrtri" => "\u{22BF}",
1348        b"xwedge" | b"Wedge" | b"bigwedge" => "\u{22C0}",
1349        b"xvee" | b"Vee" | b"bigvee" => "\u{22C1}",
1350        b"xcap" | b"Intersection" | b"bigcap" => "\u{22C2}",
1351        b"xcup" | b"Union" | b"bigcup" => "\u{22C3}",
1352        b"diam" | b"diamond" | b"Diamond" => "\u{22C4}",
1353        b"sdot" => "\u{22C5}",
1354        b"sstarf" | b"Star" => "\u{22C6}",
1355        b"divonx" | b"divideontimes" => "\u{22C7}",
1356        b"bowtie" => "\u{22C8}",
1357        b"ltimes" => "\u{22C9}",
1358        b"rtimes" => "\u{22CA}",
1359        b"lthree" | b"leftthreetimes" => "\u{22CB}",
1360        b"rthree" | b"rightthreetimes" => "\u{22CC}",
1361        b"bsime" | b"backsimeq" => "\u{22CD}",
1362        b"cuvee" | b"curlyvee" => "\u{22CE}",
1363        b"cuwed" | b"curlywedge" => "\u{22CF}",
1364        b"Sub" | b"Subset" => "\u{22D0}",
1365        b"Sup" | b"Supset" => "\u{22D1}",
1366        b"Cap" => "\u{22D2}",
1367        b"Cup" => "\u{22D3}",
1368        b"fork" | b"pitchfork" => "\u{22D4}",
1369        b"epar" => "\u{22D5}",
1370        b"ltdot" | b"lessdot" => "\u{22D6}",
1371        b"gtdot" | b"gtrdot" => "\u{22D7}",
1372        b"Ll" => "\u{22D8}",
1373        b"Gg" | b"ggg" => "\u{22D9}",
1374        b"leg" | b"LessEqualGreater" | b"lesseqgtr" => "\u{22DA}",
1375        b"gel" | b"gtreqless" | b"GreaterEqualLess" => "\u{22DB}",
1376        b"cuepr" | b"curlyeqprec" => "\u{22DE}",
1377        b"cuesc" | b"curlyeqsucc" => "\u{22DF}",
1378        b"nprcue" | b"NotPrecedesSlantEqual" => "\u{22E0}",
1379        b"nsccue" | b"NotSucceedsSlantEqual" => "\u{22E1}",
1380        b"nsqsube" | b"NotSquareSubsetEqual" => "\u{22E2}",
1381        b"nsqsupe" | b"NotSquareSupersetEqual" => "\u{22E3}",
1382        b"lnsim" => "\u{22E6}",
1383        b"gnsim" => "\u{22E7}",
1384        b"prnsim" | b"precnsim" => "\u{22E8}",
1385        b"scnsim" | b"succnsim" => "\u{22E9}",
1386        b"nltri" | b"ntriangleleft" | b"NotLeftTriangle" => "\u{22EA}",
1387        b"nrtri" | b"ntriangleright" | b"NotRightTriangle" => "\u{22EB}",
1388        b"nltrie" | b"ntrianglelefteq" | b"NotLeftTriangleEqual" => "\u{22EC}",
1389        b"nrtrie" | b"ntrianglerighteq" | b"NotRightTriangleEqual" => "\u{22ED}",
1390        b"vellip" => "\u{22EE}",
1391        b"ctdot" => "\u{22EF}",
1392        b"utdot" => "\u{22F0}",
1393        b"dtdot" => "\u{22F1}",
1394        b"disin" => "\u{22F2}",
1395        b"isinsv" => "\u{22F3}",
1396        b"isins" => "\u{22F4}",
1397        b"isindot" => "\u{22F5}",
1398        b"notinvc" => "\u{22F6}",
1399        b"notinvb" => "\u{22F7}",
1400        b"isinE" => "\u{22F9}",
1401        b"nisd" => "\u{22FA}",
1402        b"xnis" => "\u{22FB}",
1403        b"nis" => "\u{22FC}",
1404        b"notnivc" => "\u{22FD}",
1405        b"notnivb" => "\u{22FE}",
1406        b"barwed" | b"barwedge" => "\u{2305}",
1407        b"Barwed" | b"doublebarwedge" => "\u{2306}",
1408        b"lceil" | b"LeftCeiling" => "\u{2308}",
1409        b"rceil" | b"RightCeiling" => "\u{2309}",
1410        b"lfloor" | b"LeftFloor" => "\u{230A}",
1411        b"rfloor" | b"RightFloor" => "\u{230B}",
1412        b"drcrop" => "\u{230C}",
1413        b"dlcrop" => "\u{230D}",
1414        b"urcrop" => "\u{230E}",
1415        b"ulcrop" => "\u{230F}",
1416        b"bnot" => "\u{2310}",
1417        b"profline" => "\u{2312}",
1418        b"profsurf" => "\u{2313}",
1419        b"telrec" => "\u{2315}",
1420        b"target" => "\u{2316}",
1421        b"ulcorn" | b"ulcorner" => "\u{231C}",
1422        b"urcorn" | b"urcorner" => "\u{231D}",
1423        b"dlcorn" | b"llcorner" => "\u{231E}",
1424        b"drcorn" | b"lrcorner" => "\u{231F}",
1425        b"frown" | b"sfrown" => "\u{2322}",
1426        b"smile" | b"ssmile" => "\u{2323}",
1427        b"cylcty" => "\u{232D}",
1428        b"profalar" => "\u{232E}",
1429        b"topbot" => "\u{2336}",
1430        b"ovbar" => "\u{233D}",
1431        b"solbar" => "\u{233F}",
1432        b"angzarr" => "\u{237C}",
1433        b"lmoust" | b"lmoustache" => "\u{23B0}",
1434        b"rmoust" | b"rmoustache" => "\u{23B1}",
1435        b"tbrk" | b"OverBracket" => "\u{23B4}",
1436        b"bbrk" | b"UnderBracket" => "\u{23B5}",
1437        b"bbrktbrk" => "\u{23B6}",
1438        b"OverParenthesis" => "\u{23DC}",
1439        b"UnderParenthesis" => "\u{23DD}",
1440        b"OverBrace" => "\u{23DE}",
1441        b"UnderBrace" => "\u{23DF}",
1442        b"trpezium" => "\u{23E2}",
1443        b"elinters" => "\u{23E7}",
1444        b"blank" => "\u{2423}",
1445        b"oS" | b"circledS" => "\u{24C8}",
1446        b"boxh" | b"HorizontalLine" => "\u{2500}",
1447        b"boxv" => "\u{2502}",
1448        b"boxdr" => "\u{250C}",
1449        b"boxdl" => "\u{2510}",
1450        b"boxur" => "\u{2514}",
1451        b"boxul" => "\u{2518}",
1452        b"boxvr" => "\u{251C}",
1453        b"boxvl" => "\u{2524}",
1454        b"boxhd" => "\u{252C}",
1455        b"boxhu" => "\u{2534}",
1456        b"boxvh" => "\u{253C}",
1457        b"boxH" => "\u{2550}",
1458        b"boxV" => "\u{2551}",
1459        b"boxdR" => "\u{2552}",
1460        b"boxDr" => "\u{2553}",
1461        b"boxDR" => "\u{2554}",
1462        b"boxdL" => "\u{2555}",
1463        b"boxDl" => "\u{2556}",
1464        b"boxDL" => "\u{2557}",
1465        b"boxuR" => "\u{2558}",
1466        b"boxUr" => "\u{2559}",
1467        b"boxUR" => "\u{255A}",
1468        b"boxuL" => "\u{255B}",
1469        b"boxUl" => "\u{255C}",
1470        b"boxUL" => "\u{255D}",
1471        b"boxvR" => "\u{255E}",
1472        b"boxVr" => "\u{255F}",
1473        b"boxVR" => "\u{2560}",
1474        b"boxvL" => "\u{2561}",
1475        b"boxVl" => "\u{2562}",
1476        b"boxVL" => "\u{2563}",
1477        b"boxHd" => "\u{2564}",
1478        b"boxhD" => "\u{2565}",
1479        b"boxHD" => "\u{2566}",
1480        b"boxHu" => "\u{2567}",
1481        b"boxhU" => "\u{2568}",
1482        b"boxHU" => "\u{2569}",
1483        b"boxvH" => "\u{256A}",
1484        b"boxVh" => "\u{256B}",
1485        b"boxVH" => "\u{256C}",
1486        b"uhblk" => "\u{2580}",
1487        b"lhblk" => "\u{2584}",
1488        b"block" => "\u{2588}",
1489        b"blk14" => "\u{2591}",
1490        b"blk12" => "\u{2592}",
1491        b"blk34" => "\u{2593}",
1492        b"squ" | b"square" | b"Square" => "\u{25A1}",
1493        b"squf" | b"squarf" | b"blacksquare" | b"FilledVerySmallSquare" => "\u{25AA}",
1494        b"EmptyVerySmallSquare" => "\u{25AB}",
1495        b"rect" => "\u{25AD}",
1496        b"marker" => "\u{25AE}",
1497        b"fltns" => "\u{25B1}",
1498        b"xutri" | b"bigtriangleup" => "\u{25B3}",
1499        b"utrif" | b"blacktriangle" => "\u{25B4}",
1500        b"utri" | b"triangle" => "\u{25B5}",
1501        b"rtrif" | b"blacktriangleright" => "\u{25B8}",
1502        b"rtri" | b"triangleright" => "\u{25B9}",
1503        b"xdtri" | b"bigtriangledown" => "\u{25BD}",
1504        b"dtrif" | b"blacktriangledown" => "\u{25BE}",
1505        b"dtri" | b"triangledown" => "\u{25BF}",
1506        b"ltrif" | b"blacktriangleleft" => "\u{25C2}",
1507        b"ltri" | b"triangleleft" => "\u{25C3}",
1508        b"loz" | b"lozenge" => "\u{25CA}",
1509        b"cir" => "\u{25CB}",
1510        b"tridot" => "\u{25EC}",
1511        b"xcirc" | b"bigcirc" => "\u{25EF}",
1512        b"ultri" => "\u{25F8}",
1513        b"urtri" => "\u{25F9}",
1514        b"lltri" => "\u{25FA}",
1515        b"EmptySmallSquare" => "\u{25FB}",
1516        b"FilledSmallSquare" => "\u{25FC}",
1517        b"starf" | b"bigstar" => "\u{2605}",
1518        b"star" => "\u{2606}",
1519        b"phone" => "\u{260E}",
1520        b"female" => "\u{2640}",
1521        b"male" => "\u{2642}",
1522        b"spades" | b"spadesuit" => "\u{2660}",
1523        b"clubs" | b"clubsuit" => "\u{2663}",
1524        b"hearts" | b"heartsuit" => "\u{2665}",
1525        b"diams" | b"diamondsuit" => "\u{2666}",
1526        b"sung" => "\u{266A}",
1527        b"flat" => "\u{266D}",
1528        b"natur" | b"natural" => "\u{266E}",
1529        b"sharp" => "\u{266F}",
1530        b"check" | b"checkmark" => "\u{2713}",
1531        b"cross" => "\u{2717}",
1532        b"malt" | b"maltese" => "\u{2720}",
1533        b"sext" => "\u{2736}",
1534        b"VerticalSeparator" => "\u{2758}",
1535        b"lbbrk" => "\u{2772}",
1536        b"rbbrk" => "\u{2773}",
1537        b"lobrk" | b"LeftDoubleBracket" => "\u{27E6}",
1538        b"robrk" | b"RightDoubleBracket" => "\u{27E7}",
1539        b"lang" | b"LeftAngleBracket" | b"langle" => "\u{27E8}",
1540        b"rang" | b"RightAngleBracket" | b"rangle" => "\u{27E9}",
1541        b"Lang" => "\u{27EA}",
1542        b"Rang" => "\u{27EB}",
1543        b"loang" => "\u{27EC}",
1544        b"roang" => "\u{27ED}",
1545        b"xlarr" | b"longleftarrow" | b"LongLeftArrow" => "\u{27F5}",
1546        b"xrarr" | b"longrightarrow" | b"LongRightArrow" => "\u{27F6}",
1547        b"xharr" | b"longleftrightarrow" | b"LongLeftRightArrow" => "\u{27F7}",
1548        b"xlArr" | b"Longleftarrow" | b"DoubleLongLeftArrow" => "\u{27F8}",
1549        b"xrArr" | b"Longrightarrow" | b"DoubleLongRightArrow" => "\u{27F9}",
1550        b"xhArr" | b"Longleftrightarrow" | b"DoubleLongLeftRightArrow" => "\u{27FA}",
1551        b"xmap" | b"longmapsto" => "\u{27FC}",
1552        b"dzigrarr" => "\u{27FF}",
1553        b"nvlArr" => "\u{2902}",
1554        b"nvrArr" => "\u{2903}",
1555        b"nvHarr" => "\u{2904}",
1556        b"Map" => "\u{2905}",
1557        b"lbarr" => "\u{290C}",
1558        b"rbarr" | b"bkarow" => "\u{290D}",
1559        b"lBarr" => "\u{290E}",
1560        b"rBarr" | b"dbkarow" => "\u{290F}",
1561        b"RBarr" | b"drbkarow" => "\u{2910}",
1562        b"DDotrahd" => "\u{2911}",
1563        b"UpArrowBar" => "\u{2912}",
1564        b"DownArrowBar" => "\u{2913}",
1565        b"Rarrtl" => "\u{2916}",
1566        b"latail" => "\u{2919}",
1567        b"ratail" => "\u{291A}",
1568        b"lAtail" => "\u{291B}",
1569        b"rAtail" => "\u{291C}",
1570        b"larrfs" => "\u{291D}",
1571        b"rarrfs" => "\u{291E}",
1572        b"larrbfs" => "\u{291F}",
1573        b"rarrbfs" => "\u{2920}",
1574        b"nwarhk" => "\u{2923}",
1575        b"nearhk" => "\u{2924}",
1576        b"searhk" | b"hksearow" => "\u{2925}",
1577        b"swarhk" | b"hkswarow" => "\u{2926}",
1578        b"nwnear" => "\u{2927}",
1579        b"nesear" | b"toea" => "\u{2928}",
1580        b"seswar" | b"tosa" => "\u{2929}",
1581        b"swnwar" => "\u{292A}",
1582        b"rarrc" => "\u{2933}",
1583        b"cudarrr" => "\u{2935}",
1584        b"ldca" => "\u{2936}",
1585        b"rdca" => "\u{2937}",
1586        b"cudarrl" => "\u{2938}",
1587        b"larrpl" => "\u{2939}",
1588        b"curarrm" => "\u{293C}",
1589        b"cularrp" => "\u{293D}",
1590        b"rarrpl" => "\u{2945}",
1591        b"harrcir" => "\u{2948}",
1592        b"Uarrocir" => "\u{2949}",
1593        b"lurdshar" => "\u{294A}",
1594        b"ldrushar" => "\u{294B}",
1595        b"LeftRightVector" => "\u{294E}",
1596        b"RightUpDownVector" => "\u{294F}",
1597        b"DownLeftRightVector" => "\u{2950}",
1598        b"LeftUpDownVector" => "\u{2951}",
1599        b"LeftVectorBar" => "\u{2952}",
1600        b"RightVectorBar" => "\u{2953}",
1601        b"RightUpVectorBar" => "\u{2954}",
1602        b"RightDownVectorBar" => "\u{2955}",
1603        b"DownLeftVectorBar" => "\u{2956}",
1604        b"DownRightVectorBar" => "\u{2957}",
1605        b"LeftUpVectorBar" => "\u{2958}",
1606        b"LeftDownVectorBar" => "\u{2959}",
1607        b"LeftTeeVector" => "\u{295A}",
1608        b"RightTeeVector" => "\u{295B}",
1609        b"RightUpTeeVector" => "\u{295C}",
1610        b"RightDownTeeVector" => "\u{295D}",
1611        b"DownLeftTeeVector" => "\u{295E}",
1612        b"DownRightTeeVector" => "\u{295F}",
1613        b"LeftUpTeeVector" => "\u{2960}",
1614        b"LeftDownTeeVector" => "\u{2961}",
1615        b"lHar" => "\u{2962}",
1616        b"uHar" => "\u{2963}",
1617        b"rHar" => "\u{2964}",
1618        b"dHar" => "\u{2965}",
1619        b"luruhar" => "\u{2966}",
1620        b"ldrdhar" => "\u{2967}",
1621        b"ruluhar" => "\u{2968}",
1622        b"rdldhar" => "\u{2969}",
1623        b"lharul" => "\u{296A}",
1624        b"llhard" => "\u{296B}",
1625        b"rharul" => "\u{296C}",
1626        b"lrhard" => "\u{296D}",
1627        b"udhar" | b"UpEquilibrium" => "\u{296E}",
1628        b"duhar" | b"ReverseUpEquilibrium" => "\u{296F}",
1629        b"RoundImplies" => "\u{2970}",
1630        b"erarr" => "\u{2971}",
1631        b"simrarr" => "\u{2972}",
1632        b"larrsim" => "\u{2973}",
1633        b"rarrsim" => "\u{2974}",
1634        b"rarrap" => "\u{2975}",
1635        b"ltlarr" => "\u{2976}",
1636        b"gtrarr" => "\u{2978}",
1637        b"subrarr" => "\u{2979}",
1638        b"suplarr" => "\u{297B}",
1639        b"lfisht" => "\u{297C}",
1640        b"rfisht" => "\u{297D}",
1641        b"ufisht" => "\u{297E}",
1642        b"dfisht" => "\u{297F}",
1643        b"lopar" => "\u{2985}",
1644        b"ropar" => "\u{2986}",
1645        b"lbrke" => "\u{298B}",
1646        b"rbrke" => "\u{298C}",
1647        b"lbrkslu" => "\u{298D}",
1648        b"rbrksld" => "\u{298E}",
1649        b"lbrksld" => "\u{298F}",
1650        b"rbrkslu" => "\u{2990}",
1651        b"langd" => "\u{2991}",
1652        b"rangd" => "\u{2992}",
1653        b"lparlt" => "\u{2993}",
1654        b"rpargt" => "\u{2994}",
1655        b"gtlPar" => "\u{2995}",
1656        b"ltrPar" => "\u{2996}",
1657        b"vzigzag" => "\u{299A}",
1658        b"vangrt" => "\u{299C}",
1659        b"angrtvbd" => "\u{299D}",
1660        b"ange" => "\u{29A4}",
1661        b"range" => "\u{29A5}",
1662        b"dwangle" => "\u{29A6}",
1663        b"uwangle" => "\u{29A7}",
1664        b"angmsdaa" => "\u{29A8}",
1665        b"angmsdab" => "\u{29A9}",
1666        b"angmsdac" => "\u{29AA}",
1667        b"angmsdad" => "\u{29AB}",
1668        b"angmsdae" => "\u{29AC}",
1669        b"angmsdaf" => "\u{29AD}",
1670        b"angmsdag" => "\u{29AE}",
1671        b"angmsdah" => "\u{29AF}",
1672        b"bemptyv" => "\u{29B0}",
1673        b"demptyv" => "\u{29B1}",
1674        b"cemptyv" => "\u{29B2}",
1675        b"raemptyv" => "\u{29B3}",
1676        b"laemptyv" => "\u{29B4}",
1677        b"ohbar" => "\u{29B5}",
1678        b"omid" => "\u{29B6}",
1679        b"opar" => "\u{29B7}",
1680        b"operp" => "\u{29B9}",
1681        b"olcross" => "\u{29BB}",
1682        b"odsold" => "\u{29BC}",
1683        b"olcir" => "\u{29BE}",
1684        b"ofcir" => "\u{29BF}",
1685        b"olt" => "\u{29C0}",
1686        b"ogt" => "\u{29C1}",
1687        b"cirscir" => "\u{29C2}",
1688        b"cirE" => "\u{29C3}",
1689        b"solb" => "\u{29C4}",
1690        b"bsolb" => "\u{29C5}",
1691        b"boxbox" => "\u{29C9}",
1692        b"trisb" => "\u{29CD}",
1693        b"rtriltri" => "\u{29CE}",
1694        b"LeftTriangleBar" => "\u{29CF}",
1695        b"RightTriangleBar" => "\u{29D0}",
1696        b"race" => "\u{29DA}",
1697        b"iinfin" => "\u{29DC}",
1698        b"infintie" => "\u{29DD}",
1699        b"nvinfin" => "\u{29DE}",
1700        b"eparsl" => "\u{29E3}",
1701        b"smeparsl" => "\u{29E4}",
1702        b"eqvparsl" => "\u{29E5}",
1703        b"lozf" | b"blacklozenge" => "\u{29EB}",
1704        b"RuleDelayed" => "\u{29F4}",
1705        b"dsol" => "\u{29F6}",
1706        b"xodot" | b"bigodot" => "\u{2A00}",
1707        b"xoplus" | b"bigoplus" => "\u{2A01}",
1708        b"xotime" | b"bigotimes" => "\u{2A02}",
1709        b"xuplus" | b"biguplus" => "\u{2A04}",
1710        b"xsqcup" | b"bigsqcup" => "\u{2A06}",
1711        b"qint" | b"iiiint" => "\u{2A0C}",
1712        b"fpartint" => "\u{2A0D}",
1713        b"cirfnint" => "\u{2A10}",
1714        b"awint" => "\u{2A11}",
1715        b"rppolint" => "\u{2A12}",
1716        b"scpolint" => "\u{2A13}",
1717        b"npolint" => "\u{2A14}",
1718        b"pointint" => "\u{2A15}",
1719        b"quatint" => "\u{2A16}",
1720        b"intlarhk" => "\u{2A17}",
1721        b"pluscir" => "\u{2A22}",
1722        b"plusacir" => "\u{2A23}",
1723        b"simplus" => "\u{2A24}",
1724        b"plusdu" => "\u{2A25}",
1725        b"plussim" => "\u{2A26}",
1726        b"plustwo" => "\u{2A27}",
1727        b"mcomma" => "\u{2A29}",
1728        b"minusdu" => "\u{2A2A}",
1729        b"loplus" => "\u{2A2D}",
1730        b"roplus" => "\u{2A2E}",
1731        b"Cross" => "\u{2A2F}",
1732        b"timesd" => "\u{2A30}",
1733        b"timesbar" => "\u{2A31}",
1734        b"smashp" => "\u{2A33}",
1735        b"lotimes" => "\u{2A34}",
1736        b"rotimes" => "\u{2A35}",
1737        b"otimesas" => "\u{2A36}",
1738        b"Otimes" => "\u{2A37}",
1739        b"odiv" => "\u{2A38}",
1740        b"triplus" => "\u{2A39}",
1741        b"triminus" => "\u{2A3A}",
1742        b"tritime" => "\u{2A3B}",
1743        b"iprod" | b"intprod" => "\u{2A3C}",
1744        b"amalg" => "\u{2A3F}",
1745        b"capdot" => "\u{2A40}",
1746        b"ncup" => "\u{2A42}",
1747        b"ncap" => "\u{2A43}",
1748        b"capand" => "\u{2A44}",
1749        b"cupor" => "\u{2A45}",
1750        b"cupcap" => "\u{2A46}",
1751        b"capcup" => "\u{2A47}",
1752        b"cupbrcap" => "\u{2A48}",
1753        b"capbrcup" => "\u{2A49}",
1754        b"cupcup" => "\u{2A4A}",
1755        b"capcap" => "\u{2A4B}",
1756        b"ccups" => "\u{2A4C}",
1757        b"ccaps" => "\u{2A4D}",
1758        b"ccupssm" => "\u{2A50}",
1759        b"And" => "\u{2A53}",
1760        b"Or" => "\u{2A54}",
1761        b"andand" => "\u{2A55}",
1762        b"oror" => "\u{2A56}",
1763        b"orslope" => "\u{2A57}",
1764        b"andslope" => "\u{2A58}",
1765        b"andv" => "\u{2A5A}",
1766        b"orv" => "\u{2A5B}",
1767        b"andd" => "\u{2A5C}",
1768        b"ord" => "\u{2A5D}",
1769        b"wedbar" => "\u{2A5F}",
1770        b"sdote" => "\u{2A66}",
1771        b"simdot" => "\u{2A6A}",
1772        b"congdot" => "\u{2A6D}",
1773        b"easter" => "\u{2A6E}",
1774        b"apacir" => "\u{2A6F}",
1775        b"apE" => "\u{2A70}",
1776        b"eplus" => "\u{2A71}",
1777        b"pluse" => "\u{2A72}",
1778        b"Esim" => "\u{2A73}",
1779        b"Colone" => "\u{2A74}",
1780        b"Equal" => "\u{2A75}",
1781        b"eDDot" | b"ddotseq" => "\u{2A77}",
1782        b"equivDD" => "\u{2A78}",
1783        b"ltcir" => "\u{2A79}",
1784        b"gtcir" => "\u{2A7A}",
1785        b"ltquest" => "\u{2A7B}",
1786        b"gtquest" => "\u{2A7C}",
1787        b"les" | b"LessSlantEqual" | b"leqslant" => "\u{2A7D}",
1788        b"ges" | b"GreaterSlantEqual" | b"geqslant" => "\u{2A7E}",
1789        b"lesdot" => "\u{2A7F}",
1790        b"gesdot" => "\u{2A80}",
1791        b"lesdoto" => "\u{2A81}",
1792        b"gesdoto" => "\u{2A82}",
1793        b"lesdotor" => "\u{2A83}",
1794        b"gesdotol" => "\u{2A84}",
1795        b"lap" | b"lessapprox" => "\u{2A85}",
1796        b"gap" | b"gtrapprox" => "\u{2A86}",
1797        b"lne" | b"lneq" => "\u{2A87}",
1798        b"gne" | b"gneq" => "\u{2A88}",
1799        b"lnap" | b"lnapprox" => "\u{2A89}",
1800        b"gnap" | b"gnapprox" => "\u{2A8A}",
1801        b"lEg" | b"lesseqqgtr" => "\u{2A8B}",
1802        b"gEl" | b"gtreqqless" => "\u{2A8C}",
1803        b"lsime" => "\u{2A8D}",
1804        b"gsime" => "\u{2A8E}",
1805        b"lsimg" => "\u{2A8F}",
1806        b"gsiml" => "\u{2A90}",
1807        b"lgE" => "\u{2A91}",
1808        b"glE" => "\u{2A92}",
1809        b"lesges" => "\u{2A93}",
1810        b"gesles" => "\u{2A94}",
1811        b"els" | b"eqslantless" => "\u{2A95}",
1812        b"egs" | b"eqslantgtr" => "\u{2A96}",
1813        b"elsdot" => "\u{2A97}",
1814        b"egsdot" => "\u{2A98}",
1815        b"el" => "\u{2A99}",
1816        b"eg" => "\u{2A9A}",
1817        b"siml" => "\u{2A9D}",
1818        b"simg" => "\u{2A9E}",
1819        b"simlE" => "\u{2A9F}",
1820        b"simgE" => "\u{2AA0}",
1821        b"LessLess" => "\u{2AA1}",
1822        b"GreaterGreater" => "\u{2AA2}",
1823        b"glj" => "\u{2AA4}",
1824        b"gla" => "\u{2AA5}",
1825        b"ltcc" => "\u{2AA6}",
1826        b"gtcc" => "\u{2AA7}",
1827        b"lescc" => "\u{2AA8}",
1828        b"gescc" => "\u{2AA9}",
1829        b"smt" => "\u{2AAA}",
1830        b"lat" => "\u{2AAB}",
1831        b"smte" => "\u{2AAC}",
1832        b"late" => "\u{2AAD}",
1833        b"bumpE" => "\u{2AAE}",
1834        b"pre" | b"preceq" | b"PrecedesEqual" => "\u{2AAF}",
1835        b"sce" | b"succeq" | b"SucceedsEqual" => "\u{2AB0}",
1836        b"prE" => "\u{2AB3}",
1837        b"scE" => "\u{2AB4}",
1838        b"prnE" | b"precneqq" => "\u{2AB5}",
1839        b"scnE" | b"succneqq" => "\u{2AB6}",
1840        b"prap" | b"precapprox" => "\u{2AB7}",
1841        b"scap" | b"succapprox" => "\u{2AB8}",
1842        b"prnap" | b"precnapprox" => "\u{2AB9}",
1843        b"scnap" | b"succnapprox" => "\u{2ABA}",
1844        b"Pr" => "\u{2ABB}",
1845        b"Sc" => "\u{2ABC}",
1846        b"subdot" => "\u{2ABD}",
1847        b"supdot" => "\u{2ABE}",
1848        b"subplus" => "\u{2ABF}",
1849        b"supplus" => "\u{2AC0}",
1850        b"submult" => "\u{2AC1}",
1851        b"supmult" => "\u{2AC2}",
1852        b"subedot" => "\u{2AC3}",
1853        b"supedot" => "\u{2AC4}",
1854        b"subE" | b"subseteqq" => "\u{2AC5}",
1855        b"supE" | b"supseteqq" => "\u{2AC6}",
1856        b"subsim" => "\u{2AC7}",
1857        b"supsim" => "\u{2AC8}",
1858        b"subnE" | b"subsetneqq" => "\u{2ACB}",
1859        b"supnE" | b"supsetneqq" => "\u{2ACC}",
1860        b"csub" => "\u{2ACF}",
1861        b"csup" => "\u{2AD0}",
1862        b"csube" => "\u{2AD1}",
1863        b"csupe" => "\u{2AD2}",
1864        b"subsup" => "\u{2AD3}",
1865        b"supsub" => "\u{2AD4}",
1866        b"subsub" => "\u{2AD5}",
1867        b"supsup" => "\u{2AD6}",
1868        b"suphsub" => "\u{2AD7}",
1869        b"supdsub" => "\u{2AD8}",
1870        b"forkv" => "\u{2AD9}",
1871        b"topfork" => "\u{2ADA}",
1872        b"mlcp" => "\u{2ADB}",
1873        b"Dashv" | b"DoubleLeftTee" => "\u{2AE4}",
1874        b"Vdashl" => "\u{2AE6}",
1875        b"Barv" => "\u{2AE7}",
1876        b"vBar" => "\u{2AE8}",
1877        b"vBarv" => "\u{2AE9}",
1878        b"Vbar" => "\u{2AEB}",
1879        b"Not" => "\u{2AEC}",
1880        b"bNot" => "\u{2AED}",
1881        b"rnmid" => "\u{2AEE}",
1882        b"cirmid" => "\u{2AEF}",
1883        b"midcir" => "\u{2AF0}",
1884        b"topcir" => "\u{2AF1}",
1885        b"nhpar" => "\u{2AF2}",
1886        b"parsim" => "\u{2AF3}",
1887        b"parsl" => "\u{2AFD}",
1888        b"fflig" => "\u{FB00}",
1889        b"filig" => "\u{FB01}",
1890        b"fllig" => "\u{FB02}",
1891        b"ffilig" => "\u{FB03}",
1892        b"ffllig" => "\u{FB04}",
1893        b"Ascr" => "\u{1D49}",
1894        b"Cscr" => "\u{1D49}",
1895        b"Dscr" => "\u{1D49}",
1896        b"Gscr" => "\u{1D4A}",
1897        b"Jscr" => "\u{1D4A}",
1898        b"Kscr" => "\u{1D4A}",
1899        b"Nscr" => "\u{1D4A}",
1900        b"Oscr" => "\u{1D4A}",
1901        b"Pscr" => "\u{1D4A}",
1902        b"Qscr" => "\u{1D4A}",
1903        b"Sscr" => "\u{1D4A}",
1904        b"Tscr" => "\u{1D4A}",
1905        b"Uscr" => "\u{1D4B}",
1906        b"Vscr" => "\u{1D4B}",
1907        b"Wscr" => "\u{1D4B}",
1908        b"Xscr" => "\u{1D4B}",
1909        b"Yscr" => "\u{1D4B}",
1910        b"Zscr" => "\u{1D4B}",
1911        b"ascr" => "\u{1D4B}",
1912        b"bscr" => "\u{1D4B}",
1913        b"cscr" => "\u{1D4B}",
1914        b"dscr" => "\u{1D4B}",
1915        b"fscr" => "\u{1D4B}",
1916        b"hscr" => "\u{1D4B}",
1917        b"iscr" => "\u{1D4B}",
1918        b"jscr" => "\u{1D4B}",
1919        b"kscr" => "\u{1D4C}",
1920        b"lscr" => "\u{1D4C}",
1921        b"mscr" => "\u{1D4C}",
1922        b"nscr" => "\u{1D4C}",
1923        b"pscr" => "\u{1D4C}",
1924        b"qscr" => "\u{1D4C}",
1925        b"rscr" => "\u{1D4C}",
1926        b"sscr" => "\u{1D4C}",
1927        b"tscr" => "\u{1D4C}",
1928        b"uscr" => "\u{1D4C}",
1929        b"vscr" => "\u{1D4C}",
1930        b"wscr" => "\u{1D4C}",
1931        b"xscr" => "\u{1D4C}",
1932        b"yscr" => "\u{1D4C}",
1933        b"zscr" => "\u{1D4C}",
1934        b"Afr" => "\u{1D50}",
1935        b"Bfr" => "\u{1D50}",
1936        b"Dfr" => "\u{1D50}",
1937        b"Efr" => "\u{1D50}",
1938        b"Ffr" => "\u{1D50}",
1939        b"Gfr" => "\u{1D50}",
1940        b"Jfr" => "\u{1D50}",
1941        b"Kfr" => "\u{1D50}",
1942        b"Lfr" => "\u{1D50}",
1943        b"Mfr" => "\u{1D51}",
1944        b"Nfr" => "\u{1D51}",
1945        b"Ofr" => "\u{1D51}",
1946        b"Pfr" => "\u{1D51}",
1947        b"Qfr" => "\u{1D51}",
1948        b"Sfr" => "\u{1D51}",
1949        b"Tfr" => "\u{1D51}",
1950        b"Ufr" => "\u{1D51}",
1951        b"Vfr" => "\u{1D51}",
1952        b"Wfr" => "\u{1D51}",
1953        b"Xfr" => "\u{1D51}",
1954        b"Yfr" => "\u{1D51}",
1955        b"afr" => "\u{1D51}",
1956        b"bfr" => "\u{1D51}",
1957        b"cfr" => "\u{1D52}",
1958        b"dfr" => "\u{1D52}",
1959        b"efr" => "\u{1D52}",
1960        b"ffr" => "\u{1D52}",
1961        b"gfr" => "\u{1D52}",
1962        b"hfr" => "\u{1D52}",
1963        b"ifr" => "\u{1D52}",
1964        b"jfr" => "\u{1D52}",
1965        b"kfr" => "\u{1D52}",
1966        b"lfr" => "\u{1D52}",
1967        b"mfr" => "\u{1D52}",
1968        b"nfr" => "\u{1D52}",
1969        b"ofr" => "\u{1D52}",
1970        b"pfr" => "\u{1D52}",
1971        b"qfr" => "\u{1D52}",
1972        b"rfr" => "\u{1D52}",
1973        b"sfr" => "\u{1D53}",
1974        b"tfr" => "\u{1D53}",
1975        b"ufr" => "\u{1D53}",
1976        b"vfr" => "\u{1D53}",
1977        b"wfr" => "\u{1D53}",
1978        b"xfr" => "\u{1D53}",
1979        b"yfr" => "\u{1D53}",
1980        b"zfr" => "\u{1D53}",
1981        b"Aopf" => "\u{1D53}",
1982        b"Bopf" => "\u{1D53}",
1983        b"Dopf" => "\u{1D53}",
1984        b"Eopf" => "\u{1D53}",
1985        b"Fopf" => "\u{1D53}",
1986        b"Gopf" => "\u{1D53}",
1987        b"Iopf" => "\u{1D54}",
1988        b"Jopf" => "\u{1D54}",
1989        b"Kopf" => "\u{1D54}",
1990        b"Lopf" => "\u{1D54}",
1991        b"Mopf" => "\u{1D54}",
1992        b"Oopf" => "\u{1D54}",
1993        b"Sopf" => "\u{1D54}",
1994        b"Topf" => "\u{1D54}",
1995        b"Uopf" => "\u{1D54}",
1996        b"Vopf" => "\u{1D54}",
1997        b"Wopf" => "\u{1D54}",
1998        b"Xopf" => "\u{1D54}",
1999        b"Yopf" => "\u{1D55}",
2000        b"aopf" => "\u{1D55}",
2001        b"bopf" => "\u{1D55}",
2002        b"copf" => "\u{1D55}",
2003        b"dopf" => "\u{1D55}",
2004        b"eopf" => "\u{1D55}",
2005        b"fopf" => "\u{1D55}",
2006        b"gopf" => "\u{1D55}",
2007        b"hopf" => "\u{1D55}",
2008        b"iopf" => "\u{1D55}",
2009        b"jopf" => "\u{1D55}",
2010        b"kopf" => "\u{1D55}",
2011        b"lopf" => "\u{1D55}",
2012        b"mopf" => "\u{1D55}",
2013        b"nopf" => "\u{1D55}",
2014        b"oopf" => "\u{1D56}",
2015        b"popf" => "\u{1D56}",
2016        b"qopf" => "\u{1D56}",
2017        b"ropf" => "\u{1D56}",
2018        b"sopf" => "\u{1D56}",
2019        b"topf" => "\u{1D56}",
2020        b"uopf" => "\u{1D56}",
2021        b"vopf" => "\u{1D56}",
2022        b"wopf" => "\u{1D56}",
2023        b"xopf" => "\u{1D56}",
2024        b"yopf" => "\u{1D56}",
2025        b"zopf" => "\u{1D56}",
2026        _ => return None,
2027    };
2028    Some(s)
2029}
2030
2031pub(crate) fn parse_number(num: &str) -> Result<char, ParseCharRefError> {
2032    let code = if let Some(hex) = num.strip_prefix('x') {
2033        from_str_radix(hex, 16)?
2034    } else {
2035        from_str_radix(num, 10)?
2036    };
2037    if code == 0 {
2038        return Err(ParseCharRefError::IllegalCharacter(code));
2039    }
2040    match std::char::from_u32(code) {
2041        Some(c) => Ok(c),
2042        None => Err(ParseCharRefError::InvalidCodepoint(code)),
2043    }
2044}
2045
2046#[inline]
2047fn from_str_radix(src: &str, radix: u32) -> Result<u32, ParseCharRefError> {
2048    match src.as_bytes().first().copied() {
2049        // We should not allow sign numbers, but u32::from_str_radix will accept `+`.
2050        // We also handle `-` to be consistent in returned errors
2051        Some(b'+') | Some(b'-') => Err(ParseCharRefError::UnexpectedSign),
2052        _ => u32::from_str_radix(src, radix).map_err(ParseCharRefError::InvalidNumber),
2053    }
2054}
2055
2056////////////////////////////////////////////////////////////////////////////////////////////////////
2057
2058#[cfg(test)]
2059mod normalization {
2060    use super::*;
2061
2062    mod eol {
2063        use super::*;
2064
2065        mod xml {
2066            use super::*;
2067            use pretty_assertions::assert_eq;
2068
2069            #[test]
2070            fn empty() {
2071                assert_eq!(normalize_xml_eols(""), "");
2072            }
2073
2074            #[test]
2075            fn already_normalized() {
2076                assert_eq!(
2077                    normalize_xml_eols("\nalready \n\n normalized\n"),
2078                    "\nalready \n\n normalized\n",
2079                );
2080            }
2081
2082            #[test]
2083            fn cr_lf() {
2084                assert_eq!(normalize_xml_eols("\r\nsome\r\n\r\ntext"), "\nsome\n\ntext");
2085            }
2086
2087            #[test]
2088            fn cr_u0085() {
2089                assert_eq!(
2090                    normalize_xml_eols("\r\u{0085}some\r\u{0085}\r\u{0085}text"),
2091                    "\nsome\n\ntext",
2092                );
2093            }
2094
2095            #[test]
2096            fn u0085() {
2097                assert_eq!(
2098                    normalize_xml_eols("\u{0085}some\u{0085}\u{0085}text"),
2099                    "\nsome\n\ntext",
2100                );
2101            }
2102
2103            #[test]
2104            fn u2028() {
2105                assert_eq!(
2106                    normalize_xml_eols("\u{2028}some\u{2028}\u{2028}text"),
2107                    "\nsome\n\ntext",
2108                );
2109            }
2110
2111            #[test]
2112            fn mixed() {
2113                assert_eq!(
2114                    normalize_xml_eols("\r\r\r\u{2028}\n\r\nsome\n\u{0085}\r\u{0085}text"),
2115                    "\n\n\n\n\n\nsome\n\n\ntext",
2116                );
2117            }
2118
2119            #[test]
2120            fn utf8_0xc2() {
2121                // All possible characters encoded in 2 bytes in UTF-8 which first byte is 0xC2 (0b11000010)
2122                // Second byte follows the pattern 10xxxxxx
2123                let first = str::from_utf8(&[0b11000010, 0b10000000])
2124                    .unwrap()
2125                    .chars()
2126                    .next()
2127                    .unwrap();
2128                let last = str::from_utf8(&[0b11000010, 0b10111111])
2129                    .unwrap()
2130                    .chars()
2131                    .next()
2132                    .unwrap();
2133                let mut utf8 = [0; 2];
2134                for ch in first..=last {
2135                    ch.encode_utf8(&mut utf8);
2136                    let description = format!("UTF-8 [{:02x} {:02x}] = `{}`", utf8[0], utf8[1], ch);
2137                    let input = str::from_utf8(&utf8).expect(&description);
2138
2139                    dbg!((input, &description));
2140                    if ch == '\u{0085}' {
2141                        assert_eq!(normalize_xml_eols(input), "\n", "{}", description);
2142                    } else {
2143                        assert_eq!(normalize_xml_eols(input), input, "{}", description);
2144                    }
2145                }
2146                assert_eq!((first..=last).count(), 64);
2147            }
2148
2149            #[test]
2150            fn utf8_0x0d_0xc2() {
2151                // All possible characters encoded in 2 bytes in UTF-8 which first byte is 0xC2 (0b11000010)
2152                // Second byte follows the pattern 10xxxxxx
2153                let first = str::from_utf8(&[0b11000010, 0b10000000])
2154                    .unwrap()
2155                    .chars()
2156                    .next()
2157                    .unwrap();
2158                let last = str::from_utf8(&[0b11000010, 0b10111111])
2159                    .unwrap()
2160                    .chars()
2161                    .next()
2162                    .unwrap();
2163                let mut utf8 = [b'\r', 0, 0];
2164                for ch in first..=last {
2165                    ch.encode_utf8(&mut utf8[1..]);
2166                    let description = format!(
2167                        "UTF-8 [{:02x} {:02x} {:02x}] = `{}`",
2168                        utf8[0], utf8[1], utf8[2], ch
2169                    );
2170                    let input = str::from_utf8(&utf8).expect(&description);
2171
2172                    dbg!((input, &description));
2173                    if ch == '\u{0085}' {
2174                        assert_eq!(normalize_xml_eols(input), "\n", "{}", description);
2175                    } else {
2176                        assert_eq!(normalize_xml_eols(input), input, "{}", description);
2177                    }
2178                }
2179                assert_eq!((first..=last).count(), 64);
2180            }
2181
2182            #[test]
2183            fn utf8_0xe2() {
2184                // All possible characters encoded in 3 bytes in UTF-8 which first byte is 0xE2 (0b11100010)
2185                // Second and third bytes follows the pattern 10xxxxxx
2186                let first = str::from_utf8(&[0b11100010, 0b10000000, 0b10000000])
2187                    .unwrap()
2188                    .chars()
2189                    .next()
2190                    .unwrap();
2191                let last = str::from_utf8(&[0b11100010, 0b10111111, 0b10111111])
2192                    .unwrap()
2193                    .chars()
2194                    .next()
2195                    .unwrap();
2196                let mut buf = [0; 3];
2197                for ch in first..=last {
2198                    let input = &*ch.encode_utf8(&mut buf);
2199                    let buf = input.as_bytes();
2200                    let description = format!(
2201                        "UTF-8 [{:02x} {:02x} {:02x}] = `{}`",
2202                        buf[0], buf[1], buf[2], ch
2203                    );
2204
2205                    dbg!((input, &description));
2206                    if ch == '\u{2028}' {
2207                        assert_eq!(normalize_xml_eols(input), "\n", "{}", description);
2208                    } else {
2209                        assert_eq!(normalize_xml_eols(input), input, "{}", description);
2210                    }
2211                }
2212                assert_eq!((first..=last).count(), 4096);
2213            }
2214        }
2215
2216        mod html {
2217            use super::*;
2218            use pretty_assertions::assert_eq;
2219
2220            #[test]
2221            fn empty() {
2222                assert_eq!(normalize_html_eols(""), "");
2223            }
2224
2225            #[test]
2226            fn already_normalized() {
2227                assert_eq!(
2228                    normalize_html_eols("\nalready \n\n normalized\n"),
2229                    "\nalready \n\n normalized\n",
2230                );
2231            }
2232
2233            #[test]
2234            fn cr_lf() {
2235                assert_eq!(
2236                    normalize_html_eols("\r\nsome\r\n\r\ntext"),
2237                    "\nsome\n\ntext"
2238                );
2239            }
2240
2241            #[test]
2242            fn cr_u0085() {
2243                assert_eq!(
2244                    normalize_html_eols("\r\u{0085}some\r\u{0085}\r\u{0085}text"),
2245                    "\n\u{0085}some\n\u{0085}\n\u{0085}text",
2246                );
2247            }
2248
2249            #[test]
2250            fn u0085() {
2251                assert_eq!(
2252                    normalize_html_eols("\u{0085}some\u{0085}\u{0085}text"),
2253                    "\u{0085}some\u{0085}\u{0085}text",
2254                );
2255            }
2256
2257            #[test]
2258            fn u2028() {
2259                assert_eq!(
2260                    normalize_html_eols("\u{2028}some\u{2028}\u{2028}text"),
2261                    "\u{2028}some\u{2028}\u{2028}text",
2262                );
2263            }
2264
2265            #[test]
2266            fn mixed() {
2267                assert_eq!(
2268                    normalize_html_eols("\r\r\r\u{2028}\n\r\nsome\n\u{0085}\r\u{0085}text"),
2269                    "\n\n\n\u{2028}\n\nsome\n\u{0085}\n\u{0085}text",
2270                );
2271            }
2272        }
2273    }
2274}
quick_xml/escape.rs

quick_xml/
escape.rs
