XML 1.1 Document Grammar

The following grammar provides the EBNF productions for the XML 1.1 recommendation.

EBNF Grammar for XML 1.1

[1] document ::= prolog 22 element 39 Misc 27 * - Char 2 * RestrictedChar 2a Char 2 *

[2] Char ::= [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] /* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */

[2a] RestrictedChar ::= [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]

[3] S ::= (#x20 | #x9 | #xD | #xA)+

[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]

[4a] NameChar ::= NameStartChar 4 | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]

[5] Name ::= NameStartChar 4 ( NameChar 4a )*

[6] Names ::= Name 5 (#x20 Name 5 )*

[7] Nmtoken ::= ( NameChar 4a )+

[8] Nmtokens ::= Nmtoken 7 (#x20 Nmtoken 7 )*

[9] EntityValue ::= '"' ([^%&"] | PEReference 69 | Reference 67 )* '"' | "'" ([^%&'] | PEReference 69 | Reference 67 )* "'"

[10] AttValue ::= '"' ([^<&"] | Reference 67 )* '"' | "'" ([^<&'] | Reference 67 )* "'"

[11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")

[12] PubidLiteral ::= '"' PubidChar 13 * '"' | "'" ( PubidChar 13 - "'")* "'"

[13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'( )+,./:=?;!*#@$_%]

[14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)

[15] Comment ::= '<!--' (( Char 2 - '-') | ('-' ( Char 2 - '-')))* '-->'

[16] PI ::= '<?' PITarget 17 ( S 3 ( Char 2 * - ( Char 2 * '?>' Char 2 *)))? '?>'

[17] PITarget ::= Name 5 - (('X' | 'x') ('M' | 'm') ('L' | 'l'))

[18] CDSect ::= CDStart 19 CData 20 CDEnd 21

[19] CDStart ::= '<![CDATA['

[20] CData ::= ( Char 2 * - ( Char 2 * ']]>' Char 2 *))

[21] CDEnd ::= ']]>'

[22] prolog ::= XMLDecl 23 Misc 27 * ( doctypedecl 28 Misc 27 *)?

[23] XMLDecl ::= '<?xml' VersionInfo 24 EncodingDecl 80 ? SDDecl 32 ? S 3 ?'?>'

[24] VersionInfo ::= S 3 'version' Eq 25 ("'" VersionNum 26 "'" | '"' VersionNum 26 '"')

[25] Eq ::= S 3 ? '=' S 3 ?

[26] VersionNum ::= '1.1'

[27] Misc ::= Comment 15 | PI 16 | S 3

[28] doctypedecl ::= '<!DOCTYPE' S 3 Name 5 ( S 3 ExternalID)? S 3 ? ('[' intSubset 28b']' S 3 ?)? '>'

[28a] DeclSep ::= PEReference 69 | S 3

[28b] intSubset ::= ( markupdecl 29 | DeclSep 28a )*

[29] markupdecl ::= elementdecl 45 | AttlistDecl 52 | EntityDecl 70 | NotationDecl 82 | PI 16 | Comment 15

[30] extSubset ::= TextDecl 77 ? extSubsetDecl 31

[31] extSubsetDecl ::= ( markupdecl 29 | conditionalSect 61 | DeclSep 28a )*

[32] SDDecl ::= #x20+ 'standalone' Eq 25 (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))

[39] element ::= EmptyElemTag 44 | STag 40 content 43 ETag 42

[40] STag ::= '<' Name 5 ( S 3 Attribute 41 )* S 3 ? '>'

[41] Attribute ::= Name Eq AttValue

[42] ETag ::= '</' Name 5 S 3 ? '>'

[43] content ::= CharData 14 ? (( element 39 | Reference 67 | CDSect 18 | PI 16 | Comment 15 ) CharData 14 ?)*

[44] EmptyElemTag ::= '<' Name 5 ( S 3 Attribute 41 )* S 3 ? '/>'

[45] elementdecl ::= '<!ELEMENT' S 3 Name 5 S 3 contentspec 46 S 3 ? '>'

[46] contentspec ::= 'EMPTY' | 'ANY' | Mixed 51 | children 47

[47] children ::= ( choice 49 | seq 50 ) ('?' | '*' | '+')?

[48] cp ::= ( Name 5 | choice 49 | seq 50 ) ('?' | '*' | '+')?

[49] choice ::= '(' S 3 ? cp 48 ( S 3 ? '|' S 3 ? cp 48 )+ S 3 ? ')'

[50] seq ::= '(' S 3 ? cp 48 ( S 3 ? ',' S 3 ? cp 48 )* S 3 ? ')'

[51] Mixed ::= '(' S 3 ? '#PCDATA' ( S 3 ? '|' S 3 ? Name 5 )* S 3 ? ')*' | '(' S 3 ? '#PCDATA' S 3 ? ')'

[52] AttlistDecl ::= '<!ATTLIST' S 3 Name 5 AttDef 53 * S 3 ? '>'

[53] AttDef ::= S 3 Name 3 S 3 AttType 3 S 3 DefaultDecl 3

[54] AttType ::= StringType 55 | TokenizedType 56 | EnumeratedType 57

[55] StringType ::= 'CDATA'

[56] TokenizedType ::= 'ID'

| 'IDREF'  
| 'IDREFS'  
| 'ENTITY' 
| 'ENTITIES' 
| 'NMTOKEN'  
| 'NMTOKENS'

[57] EnumeratedType ::= NotationType 58 | Enumeration 59

[58] NotationType ::= 'NOTATION' S 3'(' S 3 ? Name 5 ( S 3 ? '|' S 3 ? Name 5 )* S 3 ? ')'

[59] Enumeration ::= '(' S 3 ? Nmtoken 7 ( S 3 ? '|' S 3 ? Nmtoken 7 )* S 3 ? ')'

[60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S 3 )? AttValue 10 )

[61] conditionalSect ::= includeSect 62 | ignoreSect 63

[62] includeSect ::= '<![' S 3 ? 'INCLUDE' S 3 ? '[' extSubsetDecl 31']]>'

[63] ignoreSect ::= '<![' S 3 ? 'IGNORE' S 3 ? '[' ignoreSectContents 64 * ']]>'

[64] ignoreSectContents ::= Ignore 65 ('<![' ignoreSectContents 64']]>' Ignore 65 )*

[65] Ignore ::= Char 2 * - ( Char 2 * ('<![' | ']]>') Char 2 *)

[66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'

[67] Reference ::= EntityRef 68 | CharRef 66

[68] EntityRef ::= '&' Name 5';'

[69] PEReference ::= '%' Name 5';'

[70] EntityDecl ::= GEDecl 71 | PEDecl 72

[71] GEDecl ::= '<!ENTITY' S 3 Name 5 S 3 EntityDef 73 S 3 ? '>'

[72] PEDecl ::= '<!ENTITY' S 3'%' S 3 Name 5 S 3 PEDef 74 S 3 ? '>'

[73] EntityDef ::= EntityValue 9 | ( ExternalID 75 NDataDecl 76 ?)

[74] PEDef ::= EntityValue 9 | ExternalID 75

[75] ExternalID ::= 'SYSTEM' S 3 SystemLiteral 11 | 'PUBLIC' S 3 PubidLiteral 12 S 3 SystemLiteral 11

[76] NDataDecl ::= S 3 'NDATA' S 3 Name 5

[77] TextDecl ::= '<?xml' VersionInfo 24 ? EncodingDecl 80 S 3 ? '?>'

[78] extParsedEnt ::= TextDecl 77 ? content 43 - Char 2 * RestrictedChar 2a Char 2 *

[80] EncodingDecl ::= S 3 'encoding' Eq 25 ('"' EncName 81'"' | "'" EncName 81"'" )

[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')* /* Encoding name contains only Latin characters */

[82] NotationDecl ::= '<!NOTATION' S 3 Name 5 S 3 ( ExternalID 75 | PublicID 83 ) S? '>'

[83] PublicID ::= 'PUBLIC' S 3 PubidLiteral12