New homemade XML library to replace Penlight+LuaExpat.

Author: ReFreezed

lib/markdown.lua

@@ -1196,7 +1196,7 @@ end
 setfenv(1, _G)
 M.lock(M)
 
--- Expose markdown function to the world
-markdown = M.markdown
+-- Expose markdown function to the world  @Edit: No!
+-- markdown = M.markdown
 
-return markdown
+return M.markdown

lib/pl/xml.lua

@@ -66,8 +66,8 @@ end
 -- @param text_or_file  File or string representation.
 -- @param is_file       Whether text_or_file is a file name or not.
 -- @param use_basic     Do a basic parse.
--- @return             A parsed LOM document with the document metatatables set.
--- @return nil, error  The error can either be a file error or a parse error.
+-- @return              A parsed LOM document with the document metatatables set.
+-- @return nil, error   The error can either be a file error or a parse error.
 function _M.parse(text_or_file, is_file, use_basic)
     local parser,status,lom
     if use_basic then parser = _M.basic_parse
@@ -486,15 +486,15 @@ function _M.compare(t1,t2)
     if #t1 ~= #t2 then return false, 'size '..#t1..' ~= size '..#t2..' for tag '..t1.tag end
     -- compare attributes
     for k,v in pairs(t1.attr) do
-        if t2.attr[k] ~= v then return false, 'mismatch attrib' end
+        if is_text(k) and t2.attr[k] ~= v then return false, 'mismatch attrib' end
     end
     for k,v in pairs(t2.attr) do
-        if t1.attr[k] ~= v then return false, 'mismatch attrib' end
+        if is_text(k) and t1.attr[k] ~= v then return false, 'mismatch attrib' end
     end
     -- compare children
     for i = 1,#t1 do
         local yes,err = _M.compare(t1[i],t2[i])
-        if not yes then return err end
+        if not yes then return false, err end
     end
     return true
 end
@@ -532,6 +532,7 @@ local html_empty_elements = { --lists all HTML empty (void) elements  :Edit
     isindex = true,
     link    = true,
     meta    = true,
+    option  = true,
     param   = true,
     track   = true,
     wbr     = true,
@@ -574,7 +575,8 @@ function _M.basic_parse(s,all_text,html)
 
     t_insert(stack, top)
     local ni,c,label,xarg, empty, _, istart
-    local i, j = 1, 1
+    local i = 1
+    local j
     -- we're not interested in <?xml version="1.0"?>
     _,istart = s_find(s,'^%s*<%?[^%?]+%?>%s*')
     if not istart then -- or <!DOCTYPE ...>
@@ -598,8 +600,6 @@ function _M.basic_parse(s,all_text,html)
             if html then
                 label = label:lower()
                 if html_empty_elements[label] then empty = "/" end
-                if label == 'script' then
-                end
             end
             if all_text or not s_find(text, "^%s*$") then
                 t_insert(top, unescape(text))
@@ -621,7 +621,7 @@ function _M.basic_parse(s,all_text,html)
                 t_insert(top, toclose)
             end
         end
-    i = j+1
+        i = j+1
     end
     local text = s_sub(s, i)
     if all_text or  not s_find(text, "^%s*$") then

src/app.lua2p

@@ -335,6 +335,7 @@ _G.scriptEnvironmentGlobals = {
 
 	-- Lua libraries.
 	lfs = lfs,
+	xml = xmlLib,
 
 	-- Site objects. (Create at site generation.)
 	site = nil,
@@ -450,7 +451,7 @@ _G.scriptEnvironmentGlobals = {
 			end
 		end
 
-		if xmlLib.is_tag(node) then
+		if xmlLib.isElement(node) then
 			printNode(node, 0)
 		else
 			print("(xml array)")

src/entities.lua

@@ -0,0 +1,258 @@
+-- Source: https://www.freeformatter.com/html-entities.html
+return {
+	-- XML
+	["quot"] = '"', -- ' Apostrophe
+	["amp"]  = "&", -- & Ampersand
+	["apos"] = "'", -- ' Apostrophe
+	["lt"]   = "<", -- &#60; Less-than
+	["gt"]   = ">", -- &#62; Greater than
+
+	--
+	-- HTML
+	--
+
+	-- ISO-8859-1 Characters
+	["Agrave"] = "À", -- &#192; Capital a with grave accent
+	["Aacute"] = "Á", -- &#193; Capital a with acute accent
+	["Acirc"]  = "Â", -- &#194; Capital a with circumflex accent
+	["Atilde"] = "Ã", -- &#195; Capital a with tilde
+	["Auml"]   = "Ä", -- &#196; Capital a with umlaut
+	["Aring"]  = "Å", -- &#197; Capital a with ring
+	["AElig"]  = "Æ", -- &#198; Capital ae
+	["Ccedil"] = "Ç", -- &#199; Capital c with cedilla
+	["Egrave"] = "È", -- &#200; Capital e with grave accent
+	["Eacute"] = "É", -- &#201; Capital e with acute accent
+	["Ecirc"]  = "Ê", -- &#202; Capital e with circumflex accent
+	["Euml"]   = "Ë", -- &#203; Capital e with umlaut
+	["Igrave"] = "Ì", -- &#204; Capital i with grave accent
+	["Iacute"] = "Í", -- &#205; Capital i with accute accent
+	["Icirc"]  = "Î", -- &#206; Capital i with circumflex accent
+	["Iuml"]   = "Ï", -- &#207; Capital i with umlaut
+	["ETH"]    = "Ð", -- &#208; Capital eth (Icelandic)
+	["Ntilde"] = "Ñ", -- &#209; Capital n with tilde
+	["Ograve"] = "Ò", -- &#210; Capital o with grave accent
+	["Oacute"] = "Ó", -- &#211; Capital o with accute accent
+	["Ocirc"]  = "Ô", -- &#212; Capital o with circumflex accent
+	["Otilde"] = "Õ", -- &#213; Capital o with tilde
+	["Ouml"]   = "Ö", -- &#214; Capital o with umlaut
+	["Oslash"] = "Ø", -- &#216; Capital o with slash
+	["Ugrave"] = "Ù", -- &#217; Capital u with grave accent
+	["Uacute"] = "Ú", -- &#218; Capital u with acute accent
+	["Ucirc"]  = "Û", -- &#219; Capital u with circumflex accent
+	["Uuml"]   = "Ü", -- &#220; Capital u with umlaut
+	["Yacute"] = "Ý", -- &#221; Capital y with acute accent
+	["THORN"]  = "Þ", -- &#222; Capital thorn (Icelandic)
+	["szlig"]  = "ß", -- &#223; Lowercase sharp s (German)
+	["agrave"] = "à", -- &#224; Lowercase a with grave accent
+	["aacute"] = "á", -- &#225; Lowercase a with acute accent
+	["acirc"]  = "â", -- &#226; Lowercase a with circumflex accent
+	["atilde"] = "ã", -- &#227; Lowercase a with tilde
+	["auml"]   = "ä", -- &#228; Lowercase a with umlaut
+	["aring"]  = "å", -- &#229; Lowercase a with ring
+	["aelig"]  = "æ", -- &#230; Lowercase ae
+	["ccedil"] = "ç", -- &#231; Lowercase c with cedilla
+	["egrave"] = "è", -- &#232; Lowercase e with grave accent
+	["eacute"] = "é", -- &#233; Lowercase e with acute accent
+	["ecirc"]  = "ê", -- &#234; Lowercase e with circumflex accent
+	["euml"]   = "ë", -- &#235; Lowercase e with umlaut
+	["igrave"] = "ì", -- &#236; Lowercase i with grave accent
+	["iacute"] = "í", -- &#237; Lowercase i with acute accent
+	["icirc"]  = "î", -- &#238; Lowercase i with circumflex accent
+	["iuml"]   = "ï", -- &#239; Lowercase i with umlaut
+	["eth"]    = "ð", -- &#240; Lowercase eth (Icelandic)
+	["ntilde"] = "ñ", -- &#241; Lowercase n with tilde
+	["ograve"] = "ò", -- &#242; Lowercase o with grave accent
+	["oacute"] = "ó", -- &#243; Lowercase o with acute accent
+	["ocirc"]  = "ô", -- &#244; Lowercase o with circumflex accent
+	["otilde"] = "õ", -- &#245; Lowercase o with tilde
+	["ouml"]   = "ö", -- &#246; Lowercase o with umlaut
+	["oslash"] = "ø", -- &#248; Lowercase o with slash
+	["ugrave"] = "ù", -- &#249; Lowercase u with grave accent
+	["uacute"] = "ú", -- &#250; Lowercase u with acute accent
+	["ucirc"]  = "û", -- &#251; Lowercase u with circumflex accent
+	["uuml"]   = "ü", -- &#252; Lowercase u with umlaut
+	["yacute"] = "ý", -- &#253; Lowercase y with acute accent
+	["thorn"]  = "þ", -- &#254; Lowercase thorn (Icelandic)
+	["yuml"]   = "ÿ", -- &#255; Lowercase y with umlaut
+
+	-- ISO-8859-1 Symbols
+	["nbsp"]   = " ", -- &#160; Non-breaking space
+	["iexcl"]  = "¡", -- &#161; Inverted exclamation mark
+	["cent"]   = "¢", -- &#162; Cent
+	["pound"]  = "£", -- &#163; Pound
+	["curren"] = "¤", -- &#164; Currency
+	["yen"]    = "¥", -- &#165; Yen
+	["brvbar"] = "¦", -- &#166; Broken vertical bar
+	["sect"]   = "§", -- &#167; Section
+	["uml"]    = "¨", -- &#168; Spacing diaeresis
+	["copy"]   = "©", -- &#169; Copyright
+	["ordf"]   = "ª", -- &#170; Feminine ordinal indicator
+	["laquo"]  = "«", -- &#171; Opening/Left angle quotation mark
+	["not"]    = "¬", -- &#172; Negation
+	["shy"]    = "­", -- &#173; Soft hyphen
+	["reg"]    = "®", -- &#174; Registered trademark
+	["macr"]   = "¯", -- &#175; Spacing macron
+	["deg"]    = "°", -- &#176; Degree
+	["plusmn"] = "±", -- &#177; Plus or minus
+	["sup2"]   = "²", -- &#178; Superscript 2
+	["sup3"]   = "³", -- &#179; Superscript 3
+	["acute"]  = "´", -- &#180; Spacing acute
+	["micro"]  = "µ", -- &#181; Micro
+	["para"]   = "¶", -- &#182; Paragraph
+	["cedil"]  = "¸", -- &#184; Spacing cedilla
+	["sup1"]   = "¹", -- &#185; Superscript 1
+	["ordm"]   = "º", -- &#186; Masculine ordinal indicator
+	["raquo"]  = "»", -- &#187; Closing/Right angle quotation mark
+	["frac14"] = "¼", -- &#188; Fraction 1/4
+	["frac12"] = "½", -- &#189; Fraction 1/2
+	["frac34"] = "¾", -- &#190; Fraction 3/4
+	["iquest"] = "¿", -- &#191; Inverted question mark
+	["times"]  = "×", -- &#215; Multiplication
+	["divide"] = "÷", -- &#247; Divide
+
+	-- Math Symbols
+	["forall"] = "∀", -- &#8704; For all
+	["part"]   = "∂", -- &#8706; Part
+	["exist"]  = "∃", -- &#8707; Exist
+	["empty"]  = "∅", -- &#8709; Empty
+	["nabla"]  = "∇", -- &#8711; Nabla
+	["isin"]   = "∈", -- &#8712; Is in
+	["notin"]  = "∉", -- &#8713; Not in
+	["ni"]     = "∋", -- &#8715; Ni
+	["prod"]   = "∏", -- &#8719; Product
+	["sum"]    = "∑", -- &#8721; Sum
+	["minus"]  = "−", -- &#8722; Minus
+	["lowast"] = "∗", -- &#8727; Asterisk (Lowast)
+	["radic"]  = "√", -- &#8730; Square root
+	["prop"]   = "∝", -- &#8733; Proportional to
+	["infin"]  = "∞", -- &#8734; Infinity
+	["ang"]    = "∠", -- &#8736; Angle
+	["and"]    = "∧", -- &#8743; And
+	["or"]     = "∨", -- &#8744; Or
+	["cap"]    = "∩", -- &#8745; Cap
+	["cup"]    = "∪", -- &#8746; Cup
+	["int"]    = "∫", -- &#8747; Integral
+	["there4"] = "∴", -- &#8756; Therefore
+	["sim"]    = "∼", -- &#8764; Similar to
+	["cong"]   = "≅", -- &#8773; Congurent to
+	["asymp"]  = "≈", -- &#8776; Almost equal
+	["ne"]     = "≠", -- &#8800; Not equal
+	["equiv"]  = "≡", -- &#8801; Equivalent
+	["le"]     = "≤", -- &#8804; Less or equal
+	["ge"]     = "≥", -- &#8805; Greater or equal
+	["sub"]    = "⊂", -- &#8834; Subset of
+	["sup"]    = "⊃", -- &#8835; Superset of
+	["nsub"]   = "⊄", -- &#8836; Not subset of
+	["sube"]   = "⊆", -- &#8838; Subset or equal
+	["supe"]   = "⊇", -- &#8839; Superset or equal
+	["oplus"]  = "⊕", -- &#8853; Circled plus
+	["otimes"] = "⊗", -- &#8855; Circled times
+	["perp"]   = "⊥", -- &#8869; Perpendicular
+	["sdot"]   = "⋅", -- &#8901; Dot operator
+
+	-- Greek Letters
+	["Alpha"]    = "Α", -- &#913; Alpha
+	["Beta"]     = "Β", -- &#914; Beta
+	["Gamma"]    = "Γ", -- &#915; Gamma
+	["Delta"]    = "Δ", -- &#916; Delta
+	["Epsilon"]  = "Ε", -- &#917; Epsilon
+	["Zeta"]     = "Ζ", -- &#918; Zeta
+	["Eta"]      = "Η", -- &#919; Eta
+	["Theta"]    = "Θ", -- &#920; Theta
+	["Iota"]     = "Ι", -- &#921; Iota
+	["Kappa"]    = "Κ", -- &#922; Kappa
+	["Lambda"]   = "Λ", -- &#923; Lambda
+	["Mu"]       = "Μ", -- &#924; Mu
+	["Nu"]       = "Ν", -- &#925; Nu
+	["Xi"]       = "Ξ", -- &#926; Xi
+	["Omicron"]  = "Ο", -- &#927; Omicron
+	["Pi"]       = "Π", -- &#928; Pi
+	["Rho"]      = "Ρ", -- &#929; Rho
+	["Sigma"]    = "Σ", -- &#931; Sigma
+	["Tau"]      = "Τ", -- &#932; Tau
+	["Upsilon"]  = "Υ", -- &#933; Upsilon
+	["Phi"]      = "Φ", -- &#934; Phi
+	["Chi"]      = "Χ", -- &#935; Chi
+	["Psi"]      = "Ψ", -- &#936; Psi
+	["Omega"]    = "Ω", -- &#937; Omega
+	["alpha"]    = "α", -- &#945; alpha
+	["beta"]     = "β", -- &#946; beta
+	["gamma"]    = "γ", -- &#947; gamma
+	["delta"]    = "δ", -- &#948; delta
+	["epsilon"]  = "ε", -- &#949; epsilon
+	["zeta"]     = "ζ", -- &#950; zeta
+	["eta"]      = "η", -- &#951; eta
+	["theta"]    = "θ", -- &#952; theta
+	["iota"]     = "ι", -- &#953; iota
+	["kappa"]    = "κ", -- &#954; kappa
+	["lambda"]   = "λ", -- &#955; lambda
+	["mu"]       = "μ", -- &#956; mu
+	["nu"]       = "ν", -- &#957; nu
+	["xi"]       = "ξ", -- &#958; xi
+	["omicron"]  = "ο", -- &#959; omicron
+	["pi"]       = "π", -- &#960; pi
+	["rho"]      = "ρ", -- &#961; rho
+	["sigmaf"]   = "ς", -- &#962; sigmaf
+	["sigma"]    = "σ", -- &#963; sigma
+	["tau"]      = "τ", -- &#964; tau
+	["upsilon"]  = "υ", -- &#965; upsilon
+	["phi"]      = "φ", -- &#966; phi
+	["chi"]      = "χ", -- &#967; chi
+	["psi"]      = "ψ", -- &#968; psi
+	["omega"]    = "ω", -- &#969; omega
+	["thetasym"] = "ϑ", -- &#977; Theta symbol
+	["upsih"]    = "ϒ", -- &#978; Upsilon symbol
+	["piv"]      = "ϖ", -- &#982; Pi symbol
+
+	-- Miscellaneous HTML entities
+	["OElig"]  = "Œ", -- &#338; Uppercase ligature OE
+	["oelig"]  = "œ", -- &#339; Lowercase ligature OE
+	["Scaron"] = "Š", -- &#352; Uppercase S with caron
+	["scaron"] = "š", -- &#353; Lowercase S with caron
+	["Yuml"]   = "Ÿ", -- &#376; Capital Y with diaeres
+	["fnof"]   = "ƒ", -- &#402; Lowercase with hook
+	["circ"]   = "ˆ", -- &#710; Circumflex accent
+	["tilde"]  = "˜", -- &#732; Tilde
+	["ensp"]   = " ", -- &#8194; En space
+	["emsp"]   = " ", -- &#8195; Em space
+	["thinsp"] = " ", -- &#8201; Thin space
+	["zwnj"]   = "‌", -- &#8204; Zero width non-joiner
+	["zwj"]    = "‍", -- &#8205; Zero width joiner
+	["lrm"]    = "‎", -- &#8206; Left-to-right mark
+	["rlm"]    = "‏", -- &#8207; Right-to-left mark
+	["ndash"]  = "–", -- &#8211; En dash
+	["mdash"]  = "—", -- &#8212; Em dash
+	["lsquo"]  = "‘", -- &#8216; Left single quotation mark
+	["rsquo"]  = "’", -- &#8217; Right single quotation mark
+	["sbquo"]  = "‚", -- &#8218; Single low-9 quotation mark
+	["ldquo"]  = "“", -- &#8220; Left double quotation mark
+	["rdquo"]  = "”", -- &#8221; Right double quotation mark
+	["bdquo"]  = "„", -- &#8222; Double low-9 quotation mark
+	["dagger"] = "†", -- &#8224; Dagger
+	["Dagger"] = "‡", -- &#8225; Double dagger
+	["bull"]   = "•", -- &#8226; Bullet
+	["hellip"] = "…", -- &#8230; Horizontal ellipsis
+	["permil"] = "‰", -- &#8240; Per mille
+	["prime"]  = "′", -- &#8242; Minutes (Degrees)
+	["Prime"]  = "″", -- &#8243; Seconds (Degrees)
+	["lsaquo"] = "‹", -- &#8249; Single left angle quotation
+	["rsaquo"] = "›", -- &#8250; Single right angle quotation
+	["oline"]  = "‾", -- &#8254; Overline
+	["euro"]   = "€", -- &#8364; Euro
+	["trade"]  = "™", -- &#8482; Trademark
+	["larr"]   = "←", -- &#8592; Left arrow
+	["uarr"]   = "↑", -- &#8593; Up arrow
+	["rarr"]   = "→", -- &#8594; Right arrow
+	["darr"]   = "↓", -- &#8595; Down arrow
+	["harr"]   = "↔", -- &#8596; Left right arrow
+	["crarr"]  = "↵", -- &#8629; Carriage return arrow
+	["lceil"]  = "⌈", -- &#8968; Left ceiling
+	["rceil"]  = "⌉", -- &#8969; Right ceiling
+	["lfloor"] = "⌊", -- &#8970; Left floor
+	["rfloor"] = "⌋", -- &#8971; Right floor
+	["loz"]    = "◊", -- &#9674; Lozenge
+	["spades"] = "♠", -- &#9824; Spade
+	["clubs"]  = "♣", -- &#9827; Club
+	["hearts"] = "♥", -- &#9829; Heart
+	["diams"]  = "♦", -- &#9830; Diamond
+}