Merge pull request #14 from j3lamp/html-entities

Encode special characters as HTML entities
technosophos · Dec 31, 2015 · 7b71f0b · 7b71f0b
2 parents bae117a + 499524b
commit 7b71f0b
Showing 1 changed file with 275 additions and 1 deletion.
diff --git a/dashing.go b/dashing.go
@@ -359,6 +359,19 @@ func ignore(src string) bool {
 	return false
 }
 
+func encodeHTMLentities(orig string) string {
+	escaped := new(bytes.Buffer)
+	for _, c := range orig {
+		if point_to_entity[c] == "" {
+			escaped.WriteRune(c)
+		} else {
+			escaped.WriteString(point_to_entity[c])
+		}
+	}
+
+	return escaped.String()
+}
+
 func writeHTML(orig, dest string, root *html.Node) error {
 	dir := filepath.Dir(orig)
 	base := filepath.Base(orig)
@@ -369,7 +382,12 @@ func writeHTML(orig, dest string, root *html.Node) error {
 	}
 	defer out.Close()
 
-	return html.Render(out, root)
+	content_bytes := new(bytes.Buffer)
+	html.Render(content_bytes, root)
+	content := encodeHTMLentities(content_bytes.String())
+
+	_, err = out.WriteString(content)
+	return err
 }
 
 func htmlish(filename string) bool {
@@ -511,3 +529,259 @@ func copyFile(src, dest string) error {
 	_, err = io.Copy(out, in)
 	return err
 }
+
+
+var point_to_entity = map[rune]string{
+	8704: "&forall;",
+	8194: "&ensp;",
+	8195: "&emsp;",
+	8709: "&empty;",
+	8711: "&nabla;",
+	8712: "&isin;",
+	8201: "&thinsp;",
+	8715: "&ni;",
+	8204: "&zwnj;",
+	8205: "&zwj;",
+	8206: "&lrm;",
+	8719: "&prod;",
+	8721: "&sum;",
+	8722: "&minus;",
+	8211: "&ndash;",
+	8212: "&mdash;",
+	8727: "&lowast;",
+	8216: "&lsquo;",
+	8217: "&rsquo;",
+	8730: "&radic;",
+	175:  "&macr;",
+	8220: "&ldquo;",
+	8221: "&rdquo;",
+	8222: "&bdquo;",
+	8224: "&dagger;",
+	8225: "&Dagger;",
+	8226: "&bull;",
+	8230: "&hellip;",
+	8743: "&and;",
+	8744: "&or;",
+	8745: "&cap;",
+	8746: "&cup;",
+	8747: "&int;",
+	8240: "&permil;",
+	8242: "&prime;",
+	8243: "&Prime;",
+	8756: "&there4;",
+	8713: "&notin;",
+	8249: "&lsaquo;",
+	8250: "&rsaquo;",
+	8764: "&sim;",
+	// 62:   "&gt;",	// this is already encoded for us
+	8629: "&crarr;",
+	9824: "&spades;",
+	8260: "&frasl;",
+	8773: "&cong;",
+	8776: "&asymp;",
+	8207: "&rlm;",
+	9829: "&hearts;",
+	8800: "&ne;",
+	8801: "&equiv;",
+	9827: "&clubs;",
+	8804: "&le;",
+	8805: "&ge;",
+	9830: "&diams;",
+	// 38:   "&amp;",	// this is already encoded for us
+	8834: "&sub;",
+	8835: "&sup;",
+	8836: "&nsub;",
+	8838: "&sube;",
+	8839: "&supe;",
+	8853: "&oplus;",
+	8855: "&otimes;",
+	8734: "&infin;",
+	8218: "&sbquo;",
+	8901: "&sdot;",
+	160:  "&nbsp;",
+	161:  "&iexcl;",
+	162:  "&cent;",
+	163:  "&pound;",
+	164:  "&curren;",
+	8869: "&perp;",
+	166:  "&brvbar;",
+	167:  "&sect;",
+	168:  "&uml;",
+	169:  "&copy;",
+	170:  "&ordf;",
+	171:  "&laquo;",
+	8364: "&euro;",
+	173:  "&shy;",
+	174:  "&reg;",
+	8733: "&prop;",
+	176:  "&deg;",
+	177:  "&plusmn;",
+	178:  "&sup2;",
+	179:  "&sup3;",
+	180:  "&acute;",
+	181:  "&micro;",
+	182:  "&para;",
+	183:  "&middot;",
+	184:  "&cedil;",
+	185:  "&sup1;",
+	186:  "&ordm;",
+	187:  "&raquo;",
+	188:  "&frac14;",
+	189:  "&frac12;",
+	190:  "&frac34;",
+	191:  "&iquest;",
+	192:  "&Agrave;",
+	193:  "&Aacute;",
+	194:  "&Acirc;",
+	195:  "&Atilde;",
+	196:  "&Auml;",
+	197:  "&Aring;",
+	198:  "&AElig;",
+	199:  "&Ccedil;",
+	200:  "&Egrave;",
+	201:  "&Eacute;",
+	202:  "&Ecirc;",
+	203:  "&Euml;",
+	204:  "&Igrave;",
+	// 34:   "&quot;",	// this is already encoded
+	206:  "&Icirc;",
+	207:  "&Iuml;",
+	208:  "&ETH;",
+	209:  "&Ntilde;",
+	210:  "&Ograve;",
+	211:  "&Oacute;",
+	212:  "&Ocirc;",
+	213:  "&Otilde;",
+	214:  "&Ouml;",
+	215:  "&times;",
+	216:  "&Oslash;",
+	217:  "&Ugrave;",
+	218:  "&Uacute;",
+	219:  "&Ucirc;",
+	220:  "&Uuml;",
+	221:  "&Yacute;",
+	222:  "&THORN;",
+	223:  "&szlig;",
+	224:  "&agrave;",
+	225:  "&aacute;",
+	226:  "&acirc;",
+	227:  "&atilde;",
+	228:  "&auml;",
+	229:  "&aring;",
+	230:  "&aelig;",
+	231:  "&ccedil;",
+	232:  "&egrave;",
+	205:  "&Iacute;",
+	234:  "&ecirc;",
+	235:  "&euml;",
+	236:  "&igrave;",
+	8658: "&rArr;",
+	238:  "&icirc;",
+	239:  "&iuml;",
+	240:  "&eth;",
+	241:  "&ntilde;",
+	242:  "&ograve;",
+	243:  "&oacute;",
+	244:  "&ocirc;",
+	245:  "&otilde;",
+	246:  "&ouml;",
+	247:  "&divide;",
+	248:  "&oslash;",
+	249:  "&ugrave;",
+	250:  "&uacute;",
+	251:  "&ucirc;",
+	252:  "&uuml;",
+	253:  "&yacute;",
+	254:  "&thorn;",
+	255:  "&yuml;",
+	172:  "&not;",
+	8968: "&lceil;",
+	8969: "&rceil;",
+	8970: "&lfloor;",
+	8971: "&rfloor;",
+	8465: "&image;",
+	8472: "&weierp;",
+	8476: "&real;",
+	8482: "&trade;",
+	732:  "&tilde;",
+	9002: "&rang;",
+	8736: "&ang;",
+	402:  "&fnof;",
+	8706: "&part;",
+	8501: "&alefsym;",
+	710:  "&circ;",
+	338:  "&OElig;",
+	339:  "&oelig;",
+	352:  "&Scaron;",
+	353:  "&scaron;",
+	8593: "&uarr;",
+	// 60:   "&lt;",	// this is already encoded for us
+	8594: "&rarr;",
+	8707: "&exist;",
+	8595: "&darr;",
+	8254: "&oline;",
+	233:  "&eacute;",
+	376:  "&Yuml;",
+	916:  "&Delta;",
+	237:  "&iacute;",
+	8592: "&larr;",
+	913:  "&Alpha;",
+	914:  "&Beta;",
+	915:  "&Gamma;",
+	8596: "&harr;",
+	917:  "&Epsilon;",
+	918:  "&Zeta;",
+	919:  "&Eta;",
+	920:  "&Theta;",
+	921:  "&Iota;",
+	922:  "&Kappa;",
+	923:  "&Lambda;",
+	924:  "&Mu;",
+	925:  "&Nu;",
+	926:  "&Xi;",
+	927:  "&Omicron;",
+	928:  "&Pi;",
+	929:  "&Rho;",
+	931:  "&Sigma;",
+	932:  "&Tau;",
+	933:  "&Upsilon;",
+	934:  "&Phi;",
+	935:  "&Chi;",
+	936:  "&Psi;",
+	937:  "&Omega;",
+	945:  "&alpha;",
+	946:  "&beta;",
+	947:  "&gamma;",
+	948:  "&delta;",
+	949:  "&epsilon;",
+	950:  "&zeta;",
+	951:  "&eta;",
+	952:  "&theta;",
+	953:  "&iota;",
+	954:  "&kappa;",
+	955:  "&lambda;",
+	956:  "&mu;",
+	957:  "&nu;",
+	958:  "&xi;",
+	959:  "&omicron;",
+	960:  "&pi;",
+	961:  "&rho;",
+	962:  "&sigmaf;",
+	963:  "&sigma;",
+	964:  "&tau;",
+	965:  "&upsilon;",
+	966:  "&phi;",
+	967:  "&chi;",
+	968:  "&psi;",
+	969:  "&omega;",
+	9674: "&loz;",
+	8656: "&lArr;",
+	977:  "&thetasym;",
+	978:  "&upsih;",
+	8659: "&dArr;",
+	8660: "&hArr;",
+	982:  "&piv;",
+	165:  "&yen;",
+	8657: "&uArr;",
+	9001: "&lang;",
+}