Add support for org-entities (e.g. ndash, mdash, \Aacute)

README.org

@@ -4,8 +4,6 @@ A basic org-mode parser in go
 - have a org-mode AST to play around with building an org-mode language server
 - hopefully add reasonable org-mode support to hugo - sadly [[https://github.com/chaseadamsio/goorgeous][goorgeous]] is broken & abandoned
 * next
-*** TODO [[https://github.com/chaseadamsio/goorgeous/issues/46][#46]]: Support for symbols like ndash and mdash
-- see org-entities replacement: see org-entities-help
 *** TODO [[https://github.com/chaseadamsio/goorgeous/issues/10][#10]]: Support noexport
 *** TODO [[https://github.com/chaseadamsio/goorgeous/issues/31][#31]]: Support #+INCLUDE
 - see https://orgmode.org/manual/Include-files.html

org/html.go

@@ -58,6 +58,13 @@ func (w *HTMLWriter) before(d *Document) {}
 
 func (w *HTMLWriter) after(d *Document) {
 	w.writeFootnotes(d)
+	w.replaceHTMLEntities(d)
+}
+
+func (w *HTMLWriter) replaceHTMLEntities(d *Document) {
+	s := w.stringBuilder.String()
+	w.stringBuilder.Reset()
+	w.stringBuilder.WriteString(htmlEntityReplacer.Replace(s))
 }
 
 func (w *HTMLWriter) writeNodes(ns ...Node) {

org/html_entity.go

@@ -0,0 +1,437 @@
+package org
+
+import "strings"
+
+var htmlEntityReplacer *strings.Replacer
+
+func init() {
+	htmlEntities = append(htmlEntities,
+		"---", "—",
+		"--", "–",
+		"...", "…",
+	)
+	htmlEntityReplacer = strings.NewReplacer(htmlEntities...)
+}
+
+/*
+Generated & copied over using the following elisp
+(Setting up go generate seems like a waste for now - I call YAGNI on that one)
+
+(insert (mapconcat
+         (lambda (entity) (concat "`\\" (car entity) "`, `" (nth 6 entity) "`")) ; entity -> utf8
+         (remove-if-not 'listp org-entities)
+         ",\n"))
+*/
+var htmlEntities = []string{
+	`\Agrave`, `À`,
+	`\agrave`, `à`,
+	`\Aacute`, `Á`,
+	`\aacute`, `á`,
+	`\Acirc`, `Â`,
+	`\acirc`, `â`,
+	`\Amacr`, `Ã`,
+	`\amacr`, `ã`,
+	`\Atilde`, `Ã`,
+	`\atilde`, `ã`,
+	`\Auml`, `Ä`,
+	`\auml`, `ä`,
+	`\Aring`, `Å`,
+	`\AA`, `Å`,
+	`\aring`, `å`,
+	`\AElig`, `Æ`,
+	`\aelig`, `æ`,
+	`\Ccedil`, `Ç`,
+	`\ccedil`, `ç`,
+	`\Egrave`, `È`,
+	`\egrave`, `è`,
+	`\Eacute`, `É`,
+	`\eacute`, `é`,
+	`\Ecirc`, `Ê`,
+	`\ecirc`, `ê`,
+	`\Euml`, `Ë`,
+	`\euml`, `ë`,
+	`\Igrave`, `Ì`,
+	`\igrave`, `ì`,
+	`\Iacute`, `Í`,
+	`\iacute`, `í`,
+	`\Icirc`, `Î`,
+	`\icirc`, `î`,
+	`\Iuml`, `Ï`,
+	`\iuml`, `ï`,
+	`\Ntilde`, `Ñ`,
+	`\ntilde`, `ñ`,
+	`\Ograve`, `Ò`,
+	`\ograve`, `ò`,
+	`\Oacute`, `Ó`,
+	`\oacute`, `ó`,
+	`\Ocirc`, `Ô`,
+	`\ocirc`, `ô`,
+	`\Otilde`, `Õ`,
+	`\otilde`, `õ`,
+	`\Ouml`, `Ö`,
+	`\ouml`, `ö`,
+	`\Oslash`, `Ø`,
+	`\oslash`, `ø`,
+	`\OElig`, `Œ`,
+	`\oelig`, `œ`,
+	`\Scaron`, `Š`,
+	`\scaron`, `š`,
+	`\szlig`, `ß`,
+	`\Ugrave`, `Ù`,
+	`\ugrave`, `ù`,
+	`\Uacute`, `Ú`,
+	`\uacute`, `ú`,
+	`\Ucirc`, `Û`,
+	`\ucirc`, `û`,
+	`\Uuml`, `Ü`,
+	`\uuml`, `ü`,
+	`\Yacute`, `Ý`,
+	`\yacute`, `ý`,
+	`\Yuml`, `Ÿ`,
+	`\yuml`, `ÿ`,
+	`\fnof`, `ƒ`,
+	`\real`, `ℜ`,
+	`\image`, `ℑ`,
+	`\weierp`, `℘`,
+	`\ell`, `ℓ`,
+	`\imath`, `ı`,
+	`\jmath`, `ȷ`,
+	`\Alpha`, `Α`,
+	`\alpha`, `α`,
+	`\Beta`, `Β`,
+	`\beta`, `β`,
+	`\Gamma`, `Γ`,
+	`\gamma`, `γ`,
+	`\Delta`, `Δ`,
+	`\delta`, `δ`,
+	`\Epsilon`, `Ε`,
+	`\epsilon`, `ε`,
+	`\varepsilon`, `ε`,
+	`\Zeta`, `Ζ`,
+	`\zeta`, `ζ`,
+	`\Eta`, `Η`,
+	`\eta`, `η`,
+	`\Theta`, `Θ`,
+	`\theta`, `θ`,
+	`\thetasym`, `ϑ`,
+	`\vartheta`, `ϑ`,
+	`\Iota`, `Ι`,
+	`\iota`, `ι`,
+	`\Kappa`, `Κ`,
+	`\kappa`, `κ`,
+	`\Lambda`, `Λ`,
+	`\lambda`, `λ`,
+	`\Mu`, `Μ`,
+	`\mu`, `μ`,
+	`\nu`, `ν`,
+	`\Nu`, `Ν`,
+	`\Xi`, `Ξ`,
+	`\xi`, `ξ`,
+	`\Omicron`, `Ο`,
+	`\omicron`, `ο`,
+	`\Pi`, `Π`,
+	`\pi`, `π`,
+	`\Rho`, `Ρ`,
+	`\rho`, `ρ`,
+	`\Sigma`, `Σ`,
+	`\sigma`, `σ`,
+	`\sigmaf`, `ς`,
+	`\varsigma`, `ς`,
+	`\Tau`, `Τ`,
+	`\Upsilon`, `Υ`,
+	`\upsih`, `ϒ`,
+	`\upsilon`, `υ`,
+	`\Phi`, `Φ`,
+	`\phi`, `ɸ`,
+	`\varphi`, `φ`,
+	`\Chi`, `Χ`,
+	`\chi`, `χ`,
+	`\acutex`, `𝑥́`,
+	`\Psi`, `Ψ`,
+	`\psi`, `ψ`,
+	`\tau`, `τ`,
+	`\Omega`, `Ω`,
+	`\omega`, `ω`,
+	`\piv`, `ϖ`,
+	`\varpi`, `ϖ`,
+	`\partial`, `∂`,
+	`\alefsym`, `ℵ`,
+	`\aleph`, `ℵ`,
+	`\gimel`, `ℷ`,
+	`\beth`, `ב`,
+	`\dalet`, `ד`,
+	`\ETH`, `Ð`,
+	`\eth`, `ð`,
+	`\THORN`, `Þ`,
+	`\thorn`, `þ`,
+	`\dots`, `…`,
+	`\cdots`, `⋯`,
+	`\hellip`, `…`,
+	`\middot`, `·`,
+	`\iexcl`, `¡`,
+	`\iquest`, `¿`,
+	`\shy`, ``,
+	`\ndash`, `–`,
+	`\mdash`, `—`,
+	`\quot`, `"`,
+	`\acute`, `´`,
+	`\ldquo`, `“`,
+	`\rdquo`, `”`,
+	`\bdquo`, `„`,
+	`\lsquo`, `‘`,
+	`\rsquo`, `’`,
+	`\sbquo`, `‚`,
+	`\laquo`, `«`,
+	`\raquo`, `»`,
+	`\lsaquo`, `‹`,
+	`\rsaquo`, `›`,
+	`\circ`, `∘`,
+	`\vert`, `|`,
+	`\vbar`, `|`,
+	`\brvbar`, `¦`,
+	`\S`, `§`,
+	`\sect`, `§`,
+	`\amp`, `&`,
+	`\lt`, `<`,
+	`\gt`, `>`,
+	`\tilde`, `~`,
+	`\slash`, `/`,
+	`\plus`, `+`,
+	`\under`, `_`,
+	`\equal`, `=`,
+	`\asciicirc`, `^`,
+	`\dagger`, `†`,
+	`\dag`, `†`,
+	`\Dagger`, `‡`,
+	`\ddag`, `‡`,
+	`\nbsp`, ` `,
+	`\ensp`, ` `,
+	`\emsp`, ` `,
+	`\thinsp`, ` `,
+	`\curren`, `¤`,
+	`\cent`, `¢`,
+	`\pound`, `£`,
+	`\yen`, `¥`,
+	`\euro`, `€`,
+	`\EUR`, `€`,
+	`\dollar`, `$`,
+	`\USD`, `$`,
+	`\copy`, `©`,
+	`\reg`, `®`,
+	`\trade`, `™`,
+	`\minus`, `−`,
+	`\pm`, `±`,
+	`\plusmn`, `±`,
+	`\times`, `×`,
+	`\frasl`, `⁄`,
+	`\colon`, `:`,
+	`\div`, `÷`,
+	`\frac12`, `½`,
+	`\frac14`, `¼`,
+	`\frac34`, `¾`,
+	`\permil`, `‰`,
+	`\sup1`, `¹`,
+	`\sup2`, `²`,
+	`\sup3`, `³`,
+	`\radic`, `√`,
+	`\sum`, `∑`,
+	`\prod`, `∏`,
+	`\micro`, `µ`,
+	`\macr`, `¯`,
+	`\deg`, `°`,
+	`\prime`, `′`,
+	`\Prime`, `″`,
+	`\infin`, `∞`,
+	`\infty`, `∞`,
+	`\prop`, `∝`,
+	`\propto`, `∝`,
+	`\not`, `¬`,
+	`\neg`, `¬`,
+	`\land`, `∧`,
+	`\wedge`, `∧`,
+	`\lor`, `∨`,
+	`\vee`, `∨`,
+	`\cap`, `∩`,
+	`\cup`, `∪`,
+	`\smile`, `⌣`,
+	`\frown`, `⌢`,
+	`\int`, `∫`,
+	`\therefore`, `∴`,
+	`\there4`, `∴`,
+	`\because`, `∵`,
+	`\sim`, `∼`,
+	`\cong`, `≅`,
+	`\simeq`, `≅`,
+	`\asymp`, `≈`,
+	`\approx`, `≈`,
+	`\ne`, `≠`,
+	`\neq`, `≠`,
+	`\equiv`, `≡`,
+	`\triangleq`, `≜`,
+	`\le`, `≤`,
+	`\leq`, `≤`,
+	`\ge`, `≥`,
+	`\geq`, `≥`,
+	`\lessgtr`, `≶`,
+	`\lesseqgtr`, `⋚`,
+	`\ll`, `≪`,
+	`\Ll`, `⋘`,
+	`\lll`, `⋘`,
+	`\gg`, `≫`,
+	`\Gg`, `⋙`,
+	`\ggg`, `⋙`,
+	`\prec`, `≺`,
+	`\preceq`, `≼`,
+	`\preccurlyeq`, `≼`,
+	`\succ`, `≻`,
+	`\succeq`, `≽`,
+	`\succcurlyeq`, `≽`,
+	`\sub`, `⊂`,
+	`\subset`, `⊂`,
+	`\sup`, `⊃`,
+	`\supset`, `⊃`,
+	`\nsub`, `⊄`,
+	`\sube`, `⊆`,
+	`\nsup`, `⊅`,
+	`\supe`, `⊇`,
+	`\setminus`, `⧵`,
+	`\forall`, `∀`,
+	`\exist`, `∃`,
+	`\exists`, `∃`,
+	`\nexist`, `∄`,
+	`\nexists`, `∄`,
+	`\empty`, `∅`,
+	`\emptyset`, `∅`,
+	`\isin`, `∈`,
+	`\in`, `∈`,
+	`\notin`, `∉`,
+	`\ni`, `∋`,
+	`\nabla`, `∇`,
+	`\ang`, `∠`,
+	`\angle`, `∠`,
+	`\perp`, `⊥`,
+	`\parallel`, `∥`,
+	`\sdot`, `⋅`,
+	`\cdot`, `⋅`,
+	`\lceil`, `⌈`,
+	`\rceil`, `⌉`,
+	`\lfloor`, `⌊`,
+	`\rfloor`, `⌋`,
+	`\lang`, `⟨`,
+	`\rang`, `⟩`,
+	`\langle`, `⟨`,
+	`\rangle`, `⟩`,
+	`\hbar`, `ℏ`,
+	`\mho`, `℧`,
+	`\larr`, `←`,
+	`\leftarrow`, `←`,
+	`\gets`, `←`,
+	`\lArr`, `⇐`,
+	`\Leftarrow`, `⇐`,
+	`\uarr`, `↑`,
+	`\uparrow`, `↑`,
+	`\uArr`, `⇑`,
+	`\Uparrow`, `⇑`,
+	`\rarr`, `→`,
+	`\to`, `→`,
+	`\rightarrow`, `→`,
+	`\rArr`, `⇒`,
+	`\Rightarrow`, `⇒`,
+	`\darr`, `↓`,
+	`\downarrow`, `↓`,
+	`\dArr`, `⇓`,
+	`\Downarrow`, `⇓`,
+	`\harr`, `↔`,
+	`\leftrightarrow`, `↔`,
+	`\hArr`, `⇔`,
+	`\Leftrightarrow`, `⇔`,
+	`\crarr`, `↵`,
+	`\hookleftarrow`, `↵`,
+	`\arccos`, `arccos`,
+	`\arcsin`, `arcsin`,
+	`\arctan`, `arctan`,
+	`\arg`, `arg`,
+	`\cos`, `cos`,
+	`\cosh`, `cosh`,
+	`\cot`, `cot`,
+	`\coth`, `coth`,
+	`\csc`, `csc`,
+	`\deg`, `deg`,
+	`\det`, `det`,
+	`\dim`, `dim`,
+	`\exp`, `exp`,
+	`\gcd`, `gcd`,
+	`\hom`, `hom`,
+	`\inf`, `inf`,
+	`\ker`, `ker`,
+	`\lg`, `lg`,
+	`\lim`, `lim`,
+	`\liminf`, `liminf`,
+	`\limsup`, `limsup`,
+	`\ln`, `ln`,
+	`\log`, `log`,
+	`\max`, `max`,
+	`\min`, `min`,
+	`\Pr`, `Pr`,
+	`\sec`, `sec`,
+	`\sin`, `sin`,
+	`\sinh`, `sinh`,
+	`\sup`, `sup`,
+	`\tan`, `tan`,
+	`\tanh`, `tanh`,
+	`\bull`, `•`,
+	`\bullet`, `•`,
+	`\star`, `⋆`,
+	`\lowast`, `∗`,
+	`\ast`, `*`,
+	`\odot`, `ʘ`,
+	`\oplus`, `⊕`,
+	`\otimes`, `⊗`,
+	`\check`, `✓`,
+	`\checkmark`, `✓`,
+	`\para`, `¶`,
+	`\ordf`, `ª`,
+	`\ordm`, `º`,
+	`\cedil`, `¸`,
+	`\oline`, `‾`,
+	`\uml`, `¨`,
+	`\zwnj`, `‌`,
+	`\zwj`, `‍`,
+	`\lrm`, `‎`,
+	`\rlm`, `‏`,
+	`\smiley`, `☺`,
+	`\blacksmile`, `☻`,
+	`\sad`, `☹`,
+	`\frowny`, `☹`,
+	`\clubs`, `♣`,
+	`\clubsuit`, `♣`,
+	`\spades`, `♠`,
+	`\spadesuit`, `♠`,
+	`\hearts`, `♥`,
+	`\heartsuit`, `♥`,
+	`\diams`, `◆`,
+	`\diamondsuit`, `◆`,
+	`\diamond`, `◆`,
+	`\Diamond`, `◆`,
+	`\loz`, `⧫`,
+	`\_ `, ` `,
+	`\_  `, `  `,
+	`\_   `, `   `,
+	`\_    `, `    `,
+	`\_     `, `     `,
+	`\_      `, `      `,
+	`\_       `, `       `,
+	`\_        `, `        `,
+	`\_         `, `         `,
+	`\_          `, `          `,
+	`\_           `, `           `,
+	`\_            `, `            `,
+	`\_             `, `             `,
+	`\_              `, `              `,
+	`\_               `, `               `,
+	`\_                `, `                `,
+	`\_                 `, `                 `,
+	`\_                  `, `                  `,
+	`\_                   `, `                   `,
+	`\_                    `, `                    `,
+}

org/testdata/blocks.html

@@ -71,7 +71,7 @@ paragraphs
 </li>
 <li>
 <p>
-...
+…
 </p>
 </li>
 </ul>

org/testdata/headlines.html

@@ -3,5 +3,5 @@
 <h1>Headline with TODO status</h1>
 <h1>Headline with tags &amp; priority</h1>
 <p>
-this one is cheating a little as tags are ALWAYS printed right aligned to a given column number...
+this one is cheating a little as tags are ALWAYS printed right aligned to a given column number…
 </p>

org/testdata/misc.html

@@ -28,6 +28,34 @@ crazy ain't it?
 </tbody>
 </table>
 </div>
+<h3><a href="https://github.com/chaseadamsio/goorgeous/issues/46">#46</a>: Support for symbols like ndash and mdash</h3>
+<ul>
+<li>
+<p>
+ndash –
+</p>
+</li>
+<li>
+<p>
+mdash —
+</p>
+</li>
+<li>
+<p>
+ellipsis …
+</p>
+</li>
+<li>
+<p>
+acute Á and so on
+</p>
+</li>
+<li>
+<p>
+note that —— is replaced with 2 mdashes and …. becomes ellipsis+. and so on - that&#39;s how org also does it
+</p>
+</li>
+</ul>
 <h3><a href="https://github.com/chaseadamsio/goorgeous/issues/47">#47:</a> Consecutive <code>code</code> wrapped text gets joined</h3>
 <p>
 either <code>this</code> or <code>that</code> foo.
@@ -89,7 +117,7 @@ sub bullet
 </ul>
 </li>
 </ul>
-<h3><a href="https://github.com/chaseadamsio/goorgeous/issues/77">#77</a>: Recognize <code class="verbatim">code</code>--- as code plus dash</h3>
+<h3><a href="https://github.com/chaseadamsio/goorgeous/issues/77">#77</a>: Recognize <code class="verbatim">code</code>— as code plus dash</h3>
 <h3><a href="https://github.com/chaseadamsio/goorgeous/issues/78">#78</a>: Emphasis at beginning of line</h3>
 <p>
 <em>italics</em>
@@ -101,7 +129,7 @@ Text
 <h3><a href="https://github.com/chaseadamsio/goorgeous/issues/82">#82</a>: Crash on empty headline</h3>
 <h4></h4>
 <p>
-just a space as title...
+just a space as title…
 </p>
 <h3><a href="https://github.com/chaseadamsio/goorgeous/issues/84">#84</a>: Paragraphs that are not followed by an empty line are not parsed correctly</h3>
 <h4>Foo</h4>

org/testdata/misc.org

@@ -17,6 +17,15 @@ crazy ain't it?
 | *foo* | foo |
 | *bar* | bar |
 #+HTML: </div>
+*** DONE [[https://github.com/chaseadamsio/goorgeous/issues/46][#46]]: Support for symbols like ndash and mdash
+- ndash --
+- mdash ---
+- ellipsis ...
+- acute \Aacute and so on
+- note that ------ is replaced with 2 mdashes and .... becomes ellipsis+. and so on - that's how org also does it
+
+
+
 *** DONE [[https://github.com/chaseadamsio/goorgeous/issues/47][#47:]] Consecutive ~code~ wrapped text gets joined
 either ~this~ or ~that~ foo.
 either ~this~