feat: decode common symbolic named references

README.md

@@ -79,8 +79,10 @@ See [`fixtures/sample`](fixtures/sample) for working examples.
 
 Conversion decodes semicolon-terminated named references used by the bundled
 fixtures, including common currency (`£`, `¢`, `¥`) and mathematical
-(`∉`, `≤`, `≥`) references. The complete HTML Latin-1 set is
-supported, so `½`, `×`, and `÷` become `½`, `×`, and `÷`.
+(`∉`, `≤`, `≥`) references. It also supports the HTML 4 Greek-letter
+set, common mathematical operators and relations, and directional arrows (for
+example, `α`, `∑`, `≠`, and `→`). The complete HTML Latin-1
+set is supported, so `½`, `×`, and `÷` become `½`, `×`, and `÷`.
 Named references are case-sensitive: defined aliases such as `Á` decode,
 while undefined spellings such as `Á` remain unchanged. Unknown named references remain
 unchanged so fixture comparisons do not silently discard source text.
@@ -113,9 +115,10 @@ hexadecimal forms may omit the trailing semicolon, null, surrogate, and
 out-of-range values become `�`, and the HTML C1 replacement table is applied.
 Common named references, including HTML Latin-1 names such as `ç` and
 `é`, `½`, `×`, and `÷` and symbols such as `™`,
-`€`, and `“`, are decoded only
-when the trailing semicolon is present and the name's case exactly matches a
-defined reference. Unknown or differently cased named references are preserved.
+`€`, and `“`, are supported alongside Greek letters, mathematical
+operators and relations, and arrows. Named references are decoded only when
+the trailing semicolon is present and the name's case exactly matches a defined
+reference. Unknown or differently cased named references are preserved.
 
 ## Safety boundaries
 

src/html.js

@@ -18,7 +18,21 @@ const ENTITIES = new Map([
   ['agrave', 'à'], ['aacute', 'á'], ['acirc', 'â'], ['atilde', 'ã'], ['auml', 'ä'], ['aring', 'å'], ['aelig', 'æ'], ['ccedil', 'ç'],
   ['egrave', 'è'], ['eacute', 'é'], ['ecirc', 'ê'], ['euml', 'ë'], ['igrave', 'ì'], ['iacute', 'í'], ['icirc', 'î'], ['iuml', 'ï'],
   ['eth', 'ð'], ['ntilde', 'ñ'], ['ograve', 'ò'], ['oacute', 'ó'], ['ocirc', 'ô'], ['otilde', 'õ'], ['ouml', 'ö'], ['oslash', 'ø'],
-  ['ugrave', 'ù'], ['uacute', 'ú'], ['ucirc', 'û'], ['uuml', 'ü'], ['yacute', 'ý'], ['thorn', 'þ'], ['yuml', 'ÿ']
+  ['ugrave', 'ù'], ['uacute', 'ú'], ['ucirc', 'û'], ['uuml', 'ü'], ['yacute', 'ý'], ['thorn', 'þ'], ['yuml', 'ÿ'],
+  ['Alpha', 'Α'], ['Beta', 'Β'], ['Gamma', 'Γ'], ['Delta', 'Δ'], ['Epsilon', 'Ε'], ['Zeta', 'Ζ'], ['Eta', 'Η'], ['Theta', 'Θ'],
+  ['Iota', 'Ι'], ['Kappa', 'Κ'], ['Lambda', 'Λ'], ['Mu', 'Μ'], ['Nu', 'Ν'], ['Xi', 'Ξ'], ['Omicron', 'Ο'], ['Pi', 'Π'],
+  ['Rho', 'Ρ'], ['Sigma', 'Σ'], ['Tau', 'Τ'], ['Upsilon', 'Υ'], ['Phi', 'Φ'], ['Chi', 'Χ'], ['Psi', 'Ψ'], ['Omega', 'Ω'],
+  ['alpha', 'α'], ['beta', 'β'], ['gamma', 'γ'], ['delta', 'δ'], ['epsilon', 'ε'], ['zeta', 'ζ'], ['eta', 'η'], ['theta', 'θ'],
+  ['iota', 'ι'], ['kappa', 'κ'], ['lambda', 'λ'], ['mu', 'μ'], ['nu', 'ν'], ['xi', 'ξ'], ['omicron', 'ο'], ['pi', 'π'],
+  ['rho', 'ρ'], ['sigmaf', 'ς'], ['sigma', 'σ'], ['tau', 'τ'], ['upsilon', 'υ'], ['phi', 'φ'], ['chi', 'χ'], ['psi', 'ψ'],
+  ['omega', 'ω'], ['thetasym', 'ϑ'], ['upsih', 'ϒ'], ['piv', 'ϖ'],
+  ['forall', '∀'], ['part', '∂'], ['exist', '∃'], ['empty', '∅'], ['nabla', '∇'], ['isin', '∈'], ['ni', '∋'], ['prod', '∏'],
+  ['sum', '∑'], ['minus', '−'], ['lowast', '∗'], ['radic', '√'], ['prop', '∝'], ['infin', '∞'], ['ang', '∠'], ['and', '∧'],
+  ['or', '∨'], ['cap', '∩'], ['cup', '∪'], ['int', '∫'], ['there4', '∴'], ['sim', '∼'], ['cong', '≅'], ['asymp', '≈'],
+  ['ne', '≠'], ['equiv', '≡'], ['sub', '⊂'], ['sup', '⊃'], ['nsub', '⊄'], ['sube', '⊆'], ['supe', '⊇'], ['oplus', '⊕'],
+  ['otimes', '⊗'], ['perp', '⊥'], ['sdot', '⋅'],
+  ['larr', '←'], ['uarr', '↑'], ['rarr', '→'], ['darr', '↓'], ['harr', '↔'], ['crarr', '↵'],
+  ['lArr', '⇐'], ['uArr', '⇑'], ['rArr', '⇒'], ['dArr', '⇓'], ['hArr', '⇔']
 ]);
 
 const NUMERIC_REFERENCE_REPLACEMENTS = new Map([

test/html.test.js

@@ -13,6 +13,24 @@ test('decodeEntities handles common currency and math references', () => {
   assert.equal(decodeEntities('£ ¢ ¥ ∉ ≤ ≥'), '£ ¢ ¥ ∉ ≤ ≥');
 });
 
+test('decodeEntities handles common Greek, mathematical, and arrow references', () => {
+  const cases = [
+    ['Greek letters', 'Α Ω α β ω', 'Α Ω α β ω'],
+    ['mathematical operators', '∀ ∂ ∏ ∑ √ ∫', '∀ ∂ ∏ ∑ √ ∫'],
+    ['mathematical relations', '∈ ∉ ≠ ≡ ⊆ ⊥', '∈ ∉ ≠ ≡ ⊆ ⊥'],
+    ['directional arrows', '← ↑ → ↓ ↔ ⇒', '← ↑ → ↓ ↔ ⇒']
+  ];
+
+  for (const [name, input, expected] of cases) assert.equal(decodeEntities(input), expected, name);
+});
+
+test('convertHtmlToText exposes common named-reference symbols', () => {
+  assert.equal(
+    convertHtmlToText('<p>&alpha; + &beta; &ne; &sum; &rarr; &Omega;</p>').text,
+    'α + β ≠ ∑ → Ω'
+  );
+});
+
 test('decodeEntities preserves undefined reference spellings case-sensitively', () => {
   assert.equal(decodeEntities('&Aacute; &aacute; &AACUTE; &POUND; &NotIn; &madeup;'), 'Á á &AACUTE; &POUND; &NotIn; &madeup;');
 });