@xmldom/xmldom 0.9.0-beta.1 → 0.9.0-beta.11

package/lib/grammar.js

@@ -0,0 +1,528 @@
+'use strict';
+
+/**
+ * Detects relevant unicode support for regular expressions in the runtime.
+ * Should the runtime not accepts the flag `u` or unicode ranges,
+ * character classes without unicode handling will be used.
+ *
+ * @param {typeof RegExp} [RegExpImpl=RegExp]
+ * For testing: the RegExp class.
+ * @returns {boolean}
+ * @see https://node.green/#ES2015-syntax-RegExp--y--and--u--flags
+ */
+function detectUnicodeSupport(RegExpImpl) {
+	try {
+		if (typeof RegExpImpl !== 'function') {
+			RegExpImpl = RegExp;
+		}
+		// eslint-disable-next-line es5/no-unicode-regex,es5/no-unicode-code-point-escape
+		var match = new RegExpImpl('\u{1d306}', 'u').exec('𝌆');
+		return !!match && match[0].length === 2;
+	} catch (error) {}
+	return false;
+}
+var UNICODE_SUPPORT = detectUnicodeSupport();
+
+/**
+ * Removes `[`, `]` and any trailing quantifiers from the source of a RegExp.
+ *
+ * @param {RegExp} regexp
+ */
+function chars(regexp) {
+	if (regexp.source[0] !== '[') {
+		throw new Error(regexp + ' can not be used with chars');
+	}
+	return regexp.source.slice(1, regexp.source.lastIndexOf(']'));
+}
+
+/**
+ * Creates a new character list regular expression,
+ * by removing `search` from the source of `regexp`.
+ *
+ * @param {RegExp} regexp
+ * @param {string} search
+ * The character(s) to remove.
+ * @returns {RegExp}
+ */
+function chars_without(regexp, search) {
+	if (regexp.source[0] !== '[') {
+		throw new Error('/' + regexp.source + '/ can not be used with chars_without');
+	}
+	if (!search || typeof search !== 'string') {
+		throw new Error(JSON.stringify(search) + ' is not a valid search');
+	}
+	if (regexp.source.indexOf(search) === -1) {
+		throw new Error('"' + search + '" is not is /' + regexp.source + '/');
+	}
+	if (search === '-' && regexp.source.indexOf(search) !== 1) {
+		throw new Error('"' + search + '" is not at the first postion of /' + regexp.source + '/');
+	}
+	return new RegExp(regexp.source.replace(search, ''), UNICODE_SUPPORT ? 'u' : '');
+}
+
+/**
+ * Combines and Regular expressions correctly by using `RegExp.source`.
+ *
+ * @param {...(RegExp | string)[]} args
+ * @returns {RegExp}
+ */
+function reg(args) {
+	var self = this;
+	return new RegExp(
+		Array.prototype.slice
+			.call(arguments)
+			.map(function (part) {
+				var isStr = typeof part === 'string';
+				if (isStr && self === undefined && part === '|') {
+					throw new Error('use regg instead of reg to wrap expressions with `|`!');
+				}
+				return isStr ? part : part.source;
+			})
+			.join(''),
+		UNICODE_SUPPORT ? 'mu' : 'm'
+	);
+}
+
+/**
+ * Like `reg` but wraps the expression in `(?:`,`)` to create a non tracking group.
+ *
+ * @param {...(RegExp | string)[]} args
+ * @returns {RegExp}
+ */
+function regg(args) {
+	if (arguments.length === 0) {
+		throw new Error('no parameters provided');
+	}
+	return reg.apply(regg, ['(?:'].concat(Array.prototype.slice.call(arguments), [')']));
+}
+
+// /**
+//  * Append ^ to the beginning of the expression.
+//  * @param {...(RegExp | string)[]} args
+//  * @returns {RegExp}
+//  */
+// function reg_start(args) {
+// 	if (arguments.length === 0) {
+// 		throw new Error('no parameters provided');
+// 	}
+// 	return reg.apply(reg_start, ['^'].concat(Array.prototype.slice.call(arguments)));
+// }
+
+// https://www.w3.org/TR/xml/#document
+// `[1] document ::= prolog element Misc*`
+// https://www.w3.org/TR/xml11/#NT-document
+// `[1] document ::= ( prolog element Misc* ) - ( Char* RestrictedChar Char* )`
+
+/**
+ * A character usually appearing in wrongly converted strings.
+ *
+ * @type {string}
+ * @see https://en.wikipedia.org/wiki/Specials_(Unicode_block)#Replacement_character
+ * @see https://nodejs.dev/en/api/v18/buffer/#buffers-and-character-encodings
+ * @see https://www.unicode.org/faq/utf_bom.html#BOM
+ * @readonly
+ */
+var UNICODE_REPLACEMENT_CHARACTER = '\uFFFD';
+// https://www.w3.org/TR/xml/#NT-Char
+// any Unicode character, excluding the surrogate blocks, FFFE, and FFFF.
+// `[2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]`
+// https://www.w3.org/TR/xml11/#NT-Char
+// `[2] Char ::= [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]`
+// https://www.w3.org/TR/xml11/#NT-RestrictedChar
+// `[2a] RestrictedChar ::= [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]`
+// https://www.w3.org/TR/xml11/#charsets
+var Char = /[-\x09\x0A\x0D\x20-\x2C\x2E-\uD7FF\uE000-\uFFFD]/; // without \u10000-\uEFFFF
+if (UNICODE_SUPPORT) {
+	// eslint-disable-next-line es5/no-unicode-code-point-escape
+	Char = reg('[', chars(Char), '\\u{10000}-\\u{10FFFF}', ']');
+}
+
+var _SChar = /[\x20\x09\x0D\x0A]/;
+var SChar_s = chars(_SChar);
+// https://www.w3.org/TR/xml11/#NT-S
+// `[3] S ::= (#x20 | #x9 | #xD | #xA)+`
+var S = reg(_SChar, '+');
+// optional whitespace described as `S?` in the grammar,
+// simplified to 0-n occurrences of the character class
+// instead of 0-1 occurrences of a non-capturing group around S
+var S_OPT = reg(_SChar, '*');
+
+// https://www.w3.org/TR/xml11/#NT-NameStartChar
+// `[4] NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] | [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF]`
+var NameStartChar =
+	/[:_a-zA-Z\xC0-\xD6\xD8-\xF6\xF8-\u02FF\u0370-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]/; // without \u10000-\uEFFFF
+if (UNICODE_SUPPORT) {
+	// eslint-disable-next-line es5/no-unicode-code-point-escape
+	NameStartChar = reg('[', chars(NameStartChar), '\\u{10000}-\\u{10FFFF}', ']');
+}
+var NameStartChar_s = chars(NameStartChar);
+
+// https://www.w3.org/TR/xml11/#NT-NameChar
+// `[4a] NameChar ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]`
+var NameChar = reg('[', NameStartChar_s, chars(/[-.0-9\xB7]/), chars(/[\u0300-\u036F\u203F-\u2040]/), ']');
+// https://www.w3.org/TR/xml11/#NT-Name
+// `[5] Name ::= NameStartChar (NameChar)*`
+var Name = reg(NameStartChar, NameChar, '*');
+/*
+https://www.w3.org/TR/xml11/#NT-Names
+`[6] Names ::= Name (#x20 Name)*`
+*/
+
+// https://www.w3.org/TR/xml11/#NT-Nmtoken
+// `[7] Nmtoken ::= (NameChar)+`
+var Nmtoken = reg(NameChar, '+');
+/*
+https://www.w3.org/TR/xml11/#NT-Nmtokens
+`[8] Nmtokens ::= Nmtoken (#x20 Nmtoken)*`
+var Nmtokens = reg(Nmtoken, regg(/\x20/, Nmtoken), '*');
+*/
+
+// https://www.w3.org/TR/xml11/#NT-EntityRef
+// `[68] EntityRef ::= '&' Name ';'` [WFC: Entity Declared] [VC: Entity Declared] [WFC: Parsed Entity] [WFC: No Recursion]
+var EntityRef = reg('&', Name, ';');
+// https://www.w3.org/TR/xml11/#NT-CharRef
+// `[66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'` [WFC: Legal Character]
+var CharRef = regg(/&#[0-9]+;|&#x[0-9a-fA-F]+;/);
+
+/*
+https://www.w3.org/TR/xml11/#NT-Reference
+- `[67] Reference ::= EntityRef | CharRef`
+- `[66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'` [WFC: Legal Character]
+- `[68] EntityRef ::= '&' Name ';'` [WFC: Entity Declared] [VC: Entity Declared] [WFC: Parsed Entity] [WFC: No Recursion]
+*/
+var Reference = regg(EntityRef, '|', CharRef);
+
+// https://www.w3.org/TR/xml11/#NT-PEReference
+// `[69] PEReference ::= '%' Name ';'`
+// [VC: Entity Declared] [WFC: No Recursion] [WFC: In DTD]
+var PEReference = reg('%', Name, ';');
+
+// https://www.w3.org/TR/xml11/#NT-EntityValue
+// `[9] EntityValue ::= '"' ([^%&"] | PEReference | Reference)* '"' | "'" ([^%&'] | PEReference | Reference)* "'"`
+var EntityValue = regg(
+	reg('"', regg(/[^%&"]/, '|', PEReference, '|', Reference), '*', '"'),
+	'|',
+	reg("'", regg(/[^%&']/, '|', PEReference, '|', Reference), '*', "'")
+);
+
+// https://www.w3.org/TR/xml11/#NT-AttValue
+// `[10] AttValue ::= '"' ([^<&"] | Reference)* '"' | "'" ([^<&'] | Reference)* "'"`
+var AttValue = regg('"', regg(/[^<&"]/, '|', Reference), '*', '"', '|', "'", regg(/[^<&']/, '|', Reference), '*', "'");
+
+// https://www.w3.org/TR/xml-names/#ns-decl
+// https://www.w3.org/TR/xml-names/#ns-qualnames
+// NameStartChar without ":"
+var NCNameStartChar = chars_without(NameStartChar, ':');
+// https://www.w3.org/TR/xml-names/#orphans
+// `[5] NCNameChar ::= NameChar - ':'`
+// An XML NameChar, minus the ":"
+var NCNameChar = chars_without(NameChar, ':');
+// https://www.w3.org/TR/xml-names/#NT-NCName
+// `[4] NCName ::= Name - (Char* ':' Char*)`
+// An XML Name, minus the ":"
+var NCName = reg(NCNameStartChar, NCNameChar, '*');
+
+/**
+https://www.w3.org/TR/xml-names/#ns-qualnames
+
+```
+[7] QName ::= PrefixedName | UnprefixedName
+				  === (NCName ':' NCName) | NCName
+				  === NCName (':' NCName)?
+[8] PrefixedName ::= Prefix ':' LocalPart
+								 === NCName ':' NCName
+[9] UnprefixedName ::= LocalPart
+									 === NCName
+[10] Prefix ::= NCName
+[11] LocalPart ::= NCName
+```
+*/
+var QName = reg(NCName, regg(':', NCName), '?');
+var QName_exact = reg('^', QName, '$');
+var QName_group = reg('(', QName, ')');
+
+// https://www.w3.org/TR/xml11/#NT-SystemLiteral
+// `[11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")`
+var SystemLiteral = regg(/"[^"]*"|'[^']*'/);
+
+/*
+ https://www.w3.org/TR/xml11/#NT-PI
+ ```
+ [17] PITarget    ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l'))
+ [16] PI    ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>'
+ ```
+ target /xml/i is not excluded!
+*/
+var PI = reg(/^<\?/, '(', Name, ')', regg(S, '(', Char, '*?)'), '?', /\?>/);
+
+// https://www.w3.org/TR/xml11/#NT-PubidChar
+// `[13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]`
+var PubidChar = /[\x20\x0D\x0Aa-zA-Z0-9-'()+,./:=?;!*#@$_%]/;
+
+// https://www.w3.org/TR/xml11/#NT-PubidLiteral
+// `[12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"`
+var PubidLiteral = regg('"', PubidChar, '*"', '|', "'", chars_without(PubidChar, "'"), "*'");
+
+// https://www.w3.org/TR/xml11/#NT-CharData
+// `[14] CharData    ::= [^<&]* - ([^<&]* ']]>' [^<&]*)`
+
+var COMMENT_START = '<!--';
+var COMMENT_END = '-->';
+// https://www.w3.org/TR/xml11/#NT-Comment
+// `[15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'`
+var Comment = reg(COMMENT_START, regg(chars_without(Char, '-'), '|', reg('-', chars_without(Char, '-'))), '*', COMMENT_END);
+
+var PCDATA = '#PCDATA';
+// https://www.w3.org/TR/xml11/#NT-Mixed
+// `[51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' | '(' S? '#PCDATA' S? ')'`
+// https://www.w3.org/TR/xml-names/#NT-Mixed
+// `[51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? QName)* S? ')*' | '(' S? '#PCDATA' S? ')'`
+// [VC: Proper Group/PE Nesting] [VC: No Duplicate Types]
+var Mixed = regg(
+	reg(/\(/, S_OPT, PCDATA, regg(S_OPT, /\|/, S_OPT, QName), '*', S_OPT, /\)\*/),
+	'|',
+	reg(/\(/, S_OPT, PCDATA, S_OPT, /\)/)
+);
+
+var _children_quantity = /[?*+]?/;
+/*
+ `[49] choice ::= '(' S? cp ( S? '|' S? cp )+ S? ')'` [VC: Proper Group/PE Nesting]
+ `[50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')'` [VC: Proper Group/PE Nesting]
+ simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting"
+ var _choice_or_seq = reg('[', NameChar_s, SChar_s, chars(_children_quantity), '()|,]*');
+ ```
+ [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')?
+         === (Name | '(' S? cp ( S? '|' S? cp )+ S? ')' | '(' S? cp ( S? ',' S? cp )* S? ')') ('?' | '*' | '+')?
+         !== (Name | [_choice_or_seq]*) ('?' | '*' | '+')?
+ ```
+ simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting"
+ var cp = reg(regg(Name, '|', _choice_or_seq), _children_quantity);
+*/
+/*
+Inefficient regular expression (High)
+This part of the regular expression may cause exponential backtracking on strings starting with '(|' and containing many repetitions of '|'.
+https://github.com/xmldom/xmldom/security/code-scanning/91
+var choice = regg(/\(/, S_OPT, cp, regg(S_OPT, /\|/, S_OPT, cp), '+', S_OPT, /\)/);
+*/
+/*
+Inefficient regular expression (High)
+This part of the regular expression may cause exponential backtracking on strings starting with '(,' and containing many repetitions of ','.
+https://github.com/xmldom/xmldom/security/code-scanning/92
+var seq = regg(/\(/, S_OPT, cp, regg(S_OPT, /,/, S_OPT, cp), '*', S_OPT, /\)/);
+*/
+
+// `[47] children ::= (choice | seq) ('?' | '*' | '+')?`
+// simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting"
+var children = reg(/\([^>]+\)/, _children_quantity /*regg(choice, '|', seq), _children_quantity*/);
+
+// https://www.w3.org/TR/xml11/#NT-contentspec
+// `[46] contentspec ::= 'EMPTY' | 'ANY' | Mixed | children`
+var contentspec = regg('EMPTY', '|', 'ANY', '|', Mixed, '|', children);
+
+var ELEMENTDECL_START = '<!ELEMENT';
+// https://www.w3.org/TR/xml11/#NT-elementdecl
+// `[45] elementdecl ::= '<!ELEMENT' S Name S contentspec S? '>'`
+// https://www.w3.org/TR/xml-names/#NT-elementdecl
+// `[17] elementdecl ::= '<!ELEMENT' S QName S contentspec S? '>'`
+// because of https://www.w3.org/TR/xml11/#NT-PEReference
+// since xmldom is not supporting replacements of PEReferences in the DTD
+// this also supports PEReference in the possible places
+var elementdecl = reg(ELEMENTDECL_START, S, regg(QName, '|', PEReference), S, regg(contentspec, '|', PEReference), S_OPT, '>');
+
+// https://www.w3.org/TR/xml11/#NT-NotationType
+// `[58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')'`
+// [VC: Notation Attributes] [VC: One Notation Per Element Type] [VC: No Notation on Empty Element] [VC: No Duplicate Tokens]
+var NotationType = reg('NOTATION', S, /\(/, S_OPT, Name, regg(S_OPT, /\|/, S_OPT, Name), '*', S_OPT, /\)/);
+// https://www.w3.org/TR/xml11/#NT-Enumeration
+// `[59] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')'`
+// [VC: Enumeration] [VC: No Duplicate Tokens]
+var Enumeration = reg(/\(/, S_OPT, Nmtoken, regg(S_OPT, /\|/, S_OPT, Nmtoken), '*', S_OPT, /\)/);
+
+// https://www.w3.org/TR/xml11/#NT-EnumeratedType
+// `[57] EnumeratedType ::= NotationType | Enumeration`
+var EnumeratedType = regg(NotationType, '|', Enumeration);
+
+/*
+```
+[55] StringType ::= 'CDATA'
+[56] TokenizedType ::= 'ID' [VC: ID] [VC: One ID per Element Type] [VC: ID Attribute Default]
+   | 'IDREF' [VC: IDREF]
+   | 'IDREFS' [VC: IDREF]
+	 | 'ENTITY' [VC: Entity Name]
+	 | 'ENTITIES' [VC: Entity Name]
+	 | 'NMTOKEN' [VC: Name Token]
+	 | 'NMTOKENS' [VC: Name Token]
+ [54] AttType ::= StringType | TokenizedType | EnumeratedType
+```*/
+var AttType = regg(/CDATA|ID|IDREF|IDREFS|ENTITY|ENTITIES|NMTOKEN|NMTOKENS/, '|', EnumeratedType);
+
+// `[60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue)`
+// [WFC: No < in Attribute Values] [WFC: No External Entity References]
+// [VC: Fixed Attribute Default] [VC: Required Attribute] [VC: Attribute Default Value Syntactically Correct]
+var DefaultDecl = regg(/#REQUIRED|#IMPLIED/, '|', regg(regg('#FIXED', S), '?', AttValue));
+
+// https://www.w3.org/TR/xml11/#NT-AttDef
+// [53] AttDef ::= S Name S AttType S DefaultDecl
+// https://www.w3.org/TR/xml-names/#NT-AttDef
+// [1] NSAttName ::= PrefixedAttName | DefaultAttName
+// [2] PrefixedAttName ::= 'xmlns:' NCName [NSC: Reserved Prefixes and Namespace Names]
+// [3] DefaultAttName ::= 'xmlns'
+// [21] AttDef ::= S (QName | NSAttName) S AttType S DefaultDecl
+// 						 === S Name S AttType S DefaultDecl
+// xmldom is not distinguishing between QName and NSAttName on this level
+// to support XML without namespaces in DTD we can not restrict it to QName
+var AttDef = regg(S, Name, S, AttType, S, DefaultDecl);
+
+var ATTLIST_DECL_START = '<!ATTLIST';
+// https://www.w3.org/TR/xml11/#NT-AttlistDecl
+// `[52] AttlistDecl ::= '<!ATTLIST' S Name AttDef* S? '>'`
+// https://www.w3.org/TR/xml-names/#NT-AttlistDecl
+// `[20] AttlistDecl ::= '<!ATTLIST' S QName AttDef* S? '>'`
+// to support XML without namespaces in DTD we can not restrict it to QName
+var AttlistDecl = reg(ATTLIST_DECL_START, S, Name, AttDef, '*', S_OPT, '>');
+
+var SYSTEM = 'SYSTEM';
+var PUBLIC = 'PUBLIC';
+// https://www.w3.org/TR/xml11/#NT-ExternalID
+// `[75] ExternalID ::= 'SYSTEM' S SystemLiteral | 'PUBLIC' S PubidLiteral S SystemLiteral`
+var ExternalID = regg(regg(SYSTEM, S, SystemLiteral), '|', regg(PUBLIC, S, PubidLiteral, S, SystemLiteral));
+var ExternalID_match = reg(
+	'^',
+	regg(
+		regg(SYSTEM, S, '(?<SystemLiteralOnly>', SystemLiteral, ')'),
+		'|',
+		regg(PUBLIC, S, '(?<PubidLiteral>', PubidLiteral, ')', S, '(?<SystemLiteral>', SystemLiteral, ')')
+	)
+);
+
+// https://www.w3.org/TR/xml11/#NT-NDataDecl
+// `[76] NDataDecl ::= S 'NDATA' S Name` [VC: Notation Declared]
+var NDataDecl = regg(S, 'NDATA', S, Name);
+
+// https://www.w3.org/TR/xml11/#NT-EntityDef
+// `[73] EntityDef ::= EntityValue | (ExternalID NDataDecl?)`
+var EntityDef = regg(EntityValue, '|', regg(ExternalID, NDataDecl, '?'));
+
+var ENTITY_DECL_START = '<!ENTITY';
+// https://www.w3.org/TR/xml11/#NT-GEDecl
+// `[71] GEDecl ::= '<!ENTITY' S Name S EntityDef S? '>'`
+var GEDecl = reg(ENTITY_DECL_START, S, Name, S, EntityDef, S_OPT, '>');
+// https://www.w3.org/TR/xml11/#NT-PEDef
+// `[74] PEDef ::= EntityValue | ExternalID`
+var PEDef = regg(EntityValue, '|', ExternalID);
+// https://www.w3.org/TR/xml11/#NT-PEDecl
+// `[72] PEDecl ::= '<!ENTITY' S '%' S Name S PEDef S? '>'`
+var PEDecl = reg(ENTITY_DECL_START, S, '%', S, Name, S, PEDef, S_OPT, '>');
+// https://www.w3.org/TR/xml11/#NT-EntityDecl
+// `[70] EntityDecl ::= GEDecl | PEDecl`
+var EntityDecl = regg(GEDecl, '|', PEDecl);
+
+// https://www.w3.org/TR/xml11/#NT-PublicID
+// `[83] PublicID    ::= 'PUBLIC' S PubidLiteral`
+var PublicID = reg(PUBLIC, S, PubidLiteral);
+// https://www.w3.org/TR/xml11/#NT-NotationDecl
+// `[82] NotationDecl    ::= '<!NOTATION' S Name S (ExternalID | PublicID) S? '>'` [VC: Unique Notation Name]
+var NotationDecl = reg('<!NOTATION', S, Name, S, regg(ExternalID, '|', PublicID), S_OPT, '>');
+
+// https://www.w3.org/TR/xml11/#NT-Eq
+// `[25] Eq ::= S? '=' S?`
+var Eq = reg(S_OPT, '=', S_OPT);
+// https://www.w3.org/TR/xml/#NT-VersionNum
+// `[26] VersionNum ::= '1.' [0-9]+`
+// https://www.w3.org/TR/xml11/#NT-VersionNum
+// `[26] VersionNum ::= '1.1'`
+var VersionNum = /1[.]\d+/;
+// https://www.w3.org/TR/xml11/#NT-VersionInfo
+// `[24] VersionInfo ::= S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"')`
+var VersionInfo = reg(S, 'version', Eq, regg("'", VersionNum, "'", '|', '"', VersionNum, '"'));
+// https://www.w3.org/TR/xml11/#NT-EncName
+// `[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*`
+var EncName = /[A-Za-z][-A-Za-z0-9._]*/;
+// https://www.w3.org/TR/xml11/#NT-EncDecl
+// `[80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'" )`
+var EncodingDecl = regg(S, 'encoding', Eq, regg('"', EncName, '"', '|', "'", EncName, "'"));
+// https://www.w3.org/TR/xml11/#NT-SDDecl
+// `[32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))`
+var SDDecl = regg(S, 'standalone', Eq, regg("'", regg('yes', '|', 'no'), "'", '|', '"', regg('yes', '|', 'no'), '"'));
+// https://www.w3.org/TR/xml11/#NT-XMLDecl
+// [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
+var XMLDecl = reg(/^<\?xml/, VersionInfo, EncodingDecl, '?', SDDecl, '?', S_OPT, /\?>/);
+
+/*
+ https://www.w3.org/TR/xml/#NT-markupdecl
+ https://www.w3.org/TR/xml11/#NT-markupdecl
+ `[29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment`
+ var markupdecl = regg(elementdecl, '|', AttlistDecl, '|', EntityDecl, '|', NotationDecl, '|', PI_unsafe, '|', Comment);
+*/
+/*
+ https://www.w3.org/TR/xml-names/#NT-doctypedecl
+`[28a] DeclSep   ::= PEReference | S`
+ https://www.w3.org/TR/xml11/#NT-intSubset
+```
+ [28b] intSubset ::= (markupdecl | DeclSep)*
+                 === (markupdecl | PEReference | S)*
+```
+ [WFC: PE Between Declarations]
+ var intSubset = reg(regg(markupdecl, '|', PEReference, '|', S), '*');
+*/
+var DOCTYPE_DECL_START = '<!DOCTYPE';
+/*
+ https://www.w3.org/TR/xml11/#NT-doctypedecl
+ `[28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S? ('[' intSubset ']' S?)? '>'`
+ https://www.afterwardsw3.org/TR/xml-names/#NT-doctypedecl
+ `[16] doctypedecl ::= '<!DOCTYPE' S QName (S ExternalID)? S? ('[' (markupdecl | PEReference | S)* ']' S?)? '>'`
+ var doctypedecl = reg('<!DOCTYPE', S, Name, regg(S, ExternalID), '?', S_OPT, regg(/\[/, intSubset, /]/, S_OPT), '?', '>');
+*/
+
+var CDATA_START = '<![CDATA[';
+var CDATA_END = ']]>';
+var CDStart = /<!\[CDATA\[/;
+var CDEnd = /\]\]>/;
+var CData = reg(Char, '*?', CDEnd);
+/*
+ https://www.w3.org/TR/xml/#dt-cdsection
+ `[18]   	CDSect	   ::=   	CDStart CData CDEnd`
+ `[19]   	CDStart	   ::=   	'<![CDATA['`
+ `[20]   	CData	   ::=   	(Char* - (Char* ']]>' Char*))`
+ `[21]   	CDEnd	   ::=   	']]>'`
+*/
+var CDSect = reg(CDStart, CData);
+
+// unit tested
+exports.chars = chars;
+exports.chars_without = chars_without;
+exports.detectUnicodeSupport = detectUnicodeSupport;
+exports.reg = reg;
+exports.regg = regg;
+exports.AttlistDecl = AttlistDecl;
+exports.CDATA_START = CDATA_START;
+exports.CDATA_END = CDATA_END;
+exports.CDSect = CDSect;
+exports.Char = Char;
+exports.Comment = Comment;
+exports.COMMENT_START = COMMENT_START;
+exports.COMMENT_END = COMMENT_END;
+exports.DOCTYPE_DECL_START = DOCTYPE_DECL_START;
+exports.elementdecl = elementdecl;
+exports.EntityDecl = EntityDecl;
+exports.EntityValue = EntityValue;
+exports.ExternalID = ExternalID;
+exports.ExternalID_match = ExternalID_match;
+exports.Name = Name;
+exports.NotationDecl = NotationDecl;
+exports.Reference = Reference;
+exports.PEReference = PEReference;
+exports.PI = PI;
+exports.PUBLIC = PUBLIC;
+exports.PubidLiteral = PubidLiteral;
+exports.QName = QName;
+exports.QName_exact = QName_exact;
+exports.QName_group = QName_group;
+exports.S = S;
+exports.SChar_s = SChar_s;
+exports.S_OPT = S_OPT;
+exports.SYSTEM = SYSTEM;
+exports.SystemLiteral = SystemLiteral;
+exports.UNICODE_REPLACEMENT_CHARACTER = UNICODE_REPLACEMENT_CHARACTER;
+exports.UNICODE_SUPPORT = UNICODE_SUPPORT;
+exports.XMLDecl = XMLDecl;

package/lib/index.js

@@ -1,6 +1,20 @@
-'use strict'
+'use strict';
 
-var dom = require('./dom')
-exports.DOMImplementation = dom.DOMImplementation
-exports.XMLSerializer = dom.XMLSerializer
-exports.DOMParser = require('./dom-parser').DOMParser
+var conventions = require('./conventions');
+exports.assign = conventions.assign;
+exports.hasDefaultHTMLNamespace = conventions.hasDefaultHTMLNamespace;
+exports.isHTMLMimeType = conventions.isHTMLMimeType;
+exports.isValidMimeType = conventions.isValidMimeType;
+exports.MIME_TYPE = conventions.MIME_TYPE;
+exports.NAMESPACE = conventions.NAMESPACE;
+exports.ParseError = conventions.ParseError;
+
+var dom = require('./dom');
+exports.DOMException = dom.DOMException;
+exports.DOMImplementation = dom.DOMImplementation;
+exports.XMLSerializer = dom.XMLSerializer;
+
+var domParser = require('./dom-parser');
+exports.DOMParser = domParser.DOMParser;
+exports.onErrorStopParsing = domParser.onErrorStopParsing;
+exports.onWarningStopParsing = domParser.onWarningStopParsing;