de.unkrig.commons.text.scanner.XmlScanner Maven / Gradle / Ivy
/*
* de.unkrig.commons - A general-purpose Java class library
*
* Copyright (c) 2017, Arno Unkrig
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification, are permitted provided that the
* following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this list of conditions and the
* following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the
* following disclaimer in the documentation and/or other materials provided with the distribution.
* 3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote
* products derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
* WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
package de.unkrig.commons.text.scanner;
/**
* A scanner for XML.
*/
public final
class XmlScanner {
private XmlScanner() {}
// PUBLIC INTERFACE
private
enum State { TAG }
/**
* The token types that form an XML document.
*/
public
enum TokenType {
/**
* {@code XMLDecl ::= ''}
* {@code VersionInfo ::= S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"')}
* {@code Eq ::= S? '=' S?}
* {@code VersionNum ::= '1.' [0-9]+}
* {@code EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'" )}
* {@code EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*}
* {@code SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))}
*/
XML_DECLARATION,
/** {@code Comment ::= ''} */
COMMENT,
/**
* Example:
*
* {@code }
*
*
* {@code PI ::= '' Char*)))? '?>' }
* {@code PITarget ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l'))}
*/
PROCESSING_INSTRUCTION,
/**
* {@code doctypedecl ::= ''}
* {@code ExternalID ::= 'SYSTEM' S SystemLiteral | 'PUBLIC' S PubidLiteral S SystemLiteral}
* {@code SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")}
* {@code PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"}
* {@code PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]}
* {@code intSubset ::= (markupdecl | DeclSep)*}
* {@code markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment}
* {@code elementdecl ::= ''}
* {@code contentspec ::= 'EMPTY' | 'ANY' | Mixed | children}
* {@code Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' | '(' S? '#PCDATA' S? ')'}
* {@code children ::= (choice | seq) ('?' | '*' | '+')?}
* {@code cp ::= (Name | choice | seq) ('?' | '*' | '+')?}
* {@code choice ::= '(' S? cp ( S? '|' S? cp )+ S? ')'}
* {@code seq ::= '(' S? cp ( S? ',' S? cp )* S? ')'}
*/
DOCUMENT_TYPE_DECLARATION,
/**
* The beginning of an empty element tag or a start tag (but not the beginning of an end
* tag!).
*
* {@code StartTag ::= BeginTag Attribute* EndStartTag}
* {@code EmptyElementTag ::= BeginTag Attribute* EndEmptyElementTag}
* {@code BeginTag ::= '<' Name}
* {@code Attribute ::= S AttributeName Eq AttributeValue}
*
*/
BEGIN_TAG,
/**
* {@code AttributeName ::= S Name}
*
* @see #BEGIN_TAG
*/
ATTRIBUTE_NAME,
/**
* {@code AttributeValue ::= '"' ([^<&"] | Reference)* '"' | "'" ([^<&'] | Reference)* "'"}
*
* @see #BEGIN_TAG
*/
ATTRIBUTE_VALUE,
/**
* The end of a start tag.
* {@code EndOfStartTag ::= S? '>'}
*
* @see #BEGIN_TAG
*/
END_START_TAG,
/**
* The end of an empty element tag.
* {@code EndOfEmptyElementTag ::= S? '/>'}
*
* @see #BEGIN_TAG
*/
END_EMPTY_ELEMENT_TAG,
/** {@code ETag ::= ''} */
END_TAG,
/** {@code CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)} */
CHAR_DATA,
/** {@code EntityRef ::= '&' Name ';'} */
ENTITY_REFERENCE,
/** {@code CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'} */
CHARACTER_REFERENCE,
/**
* {@code CDSect ::= CDStart CData CDEnd}
* {@code CDStart ::= '
* {@code CData ::= (Char* - (Char* ']]>' Char*))}
* {@code CDEnd ::= ']]>'}
*/
CDATA_SECTION,
}
/**
* Creates a {@link StringScanner} that scans XML documents.
*/
public static StringScanner
stringScanner() {
StatefulScanner scanner = new StatefulScanner(State.class);
final String s = "(?:[ \\t\\r\\n]+)";
final String eq = "(?:" + s + "?=" + s + "?)";
final String nameStartChar = "[:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]"; // SUPPRESS CHECKSTYLE LineLength
final String nameChar = "(?:" + nameStartChar + "|[\\-.0-9\u00B7\u0300-\u036F\u203F-\u2040])";
final String name = "(?:" + nameStartChar + nameChar + "*)";
final String entityReference = "(?:&" + name + ";)";
final String characterReference = "(?:&#[0-9]+|&#x[0-9a-zA-Z]+;)";
final String reference = "(?:" + entityReference + "|" + characterReference + ")";
final String attributeValue = "(?:'(?:[^<&\"]|" + reference + ")*'|\"(?:[^<&\"]|" + reference + ")*\")";
scanner.addRule("", TokenType.COMMENT);
// The ""
).replace("@S@", s).replace("@Eq@", eq), TokenType.XML_DECLARATION);
scanner.addRule((
""
+ "<\\?(@Name@)"
+ "(@S@.*?)?"
+ "\\?>"
).replace("@Name@", name).replace("@S@", s), TokenType.PROCESSING_INSTRUCTION);
scanner.addRule("", TokenType.DOCUMENT_TYPE_DECLARATION);
scanner.addRule("<(@Name@)".replace("@Name@", name), TokenType.BEGIN_TAG).goTo(State.TAG);
scanner.addRule(State.TAG, s + "(" + name + ")", TokenType.ATTRIBUTE_NAME).goTo(State.TAG);
scanner.addRule(State.TAG, eq + "(" + attributeValue + ")", TokenType.ATTRIBUTE_VALUE).goTo(State.TAG);
scanner.addRule(State.TAG, "@S@?>".replace("@S@", s), TokenType.END_START_TAG);
scanner.addRule(State.TAG, "@S@?/>".replace("@S@", s), TokenType.END_EMPTY_ELEMENT_TAG);
scanner.addRule((
""
+ ""
).replace("@Name@", name).replace("@S@", s), TokenType.END_TAG);
scanner.addRule("(?:[^<&](?!-->))+", TokenType.CHAR_DATA);
scanner.addRule(entityReference, TokenType.ENTITY_REFERENCE);
scanner.addRule(characterReference, TokenType.CHARACTER_REFERENCE);
scanner.addRule("(?:)", TokenType.CDATA_SECTION);
return scanner;
}
/**
* Must only be used for subpatterns that consume neither an apostrophe nor a quote, e.g. {@code
* "1\\.[0-9]+"} is ok, but {@code ".*"} is not.
*/
private static String
quoted(String subpattern) {
return (
""
+ "(?:"
+ "'(?:" + subpattern + ")*'"
+ "|"
+ "\"(?:" + subpattern + ")*\""
+ ")"
);
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy