com.itextpdf.styledxmlparser.jsoup.parser.Tokeniser Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of styled-xml-parser Show documentation
Show all versions of styled-xml-parser Show documentation
Styled XML parser is used by iText modules to parse HTML and XML
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2021 iText Group NV
Authors: iText Software.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License version 3
as published by the Free Software Foundation with the addition of the
following permission added to Section 15 as permitted in Section 7(a):
FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
ITEXT GROUP. ITEXT GROUP DISCLAIMS THE WARRANTY OF NON INFRINGEMENT
OF THIRD PARTY RIGHTS
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program; if not, see http://www.gnu.org/licenses or write to
the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
Boston, MA, 02110-1301 USA, or download the license from the following URL:
http://itextpdf.com/terms-of-use/
The interactive user interfaces in modified source and object code versions
of this program must display Appropriate Legal Notices, as required under
Section 5 of the GNU Affero General Public License.
In accordance with Section 7(b) of the GNU Affero General Public License,
a covered work must retain the producer line in every PDF that is created
or manipulated using iText.
You can be released from the requirements of the license by purchasing
a commercial license. Buying such a license is mandatory as soon as you
develop commercial activities involving the iText software without
disclosing the source code of your own applications.
These activities include: offering paid services to customers as an ASP,
serving PDFs on the fly in a web application, shipping iText with a closed
source product.
For more information, please contact iText Software Corp. at this
address: [email protected]
*/
package com.itextpdf.styledxmlparser.jsoup.parser;
import com.itextpdf.styledxmlparser.jsoup.helper.Validate;
import com.itextpdf.styledxmlparser.jsoup.PortUtil;
import com.itextpdf.styledxmlparser.jsoup.nodes.Entities;
import com.itextpdf.io.util.MessageFormatUtil;
import java.util.Arrays;
/**
* Readers the input stream into tokens.
*/
final class Tokeniser {
static final char replacementChar = '\uFFFD'; // replaces null character
private static final char[] notCharRefCharsSorted = new char[]{'\t', '\n', '\r', '\f', ' ', '<', '&'};
static {
Arrays.sort(notCharRefCharsSorted);
}
private CharacterReader reader; // html input
private ParseErrorList errors; // errors found while tokenising
private TokeniserState state = TokeniserState.Data; // current tokenisation state
private Token emitPending; // the token we are about to emit on next read
private boolean isEmitPending = false;
private String charsString = null; // characters pending an emit. Will fall to charsBuilder if more than one
private StringBuilder charsBuilder = new StringBuilder(1024); // buffers characters to output as one token, if more than one emit per read
StringBuilder dataBuffer = new StringBuilder(1024); // buffers data looking for
Token.Tag tagPending; // tag we are building up
Token.StartTag startPending = new Token.StartTag();
Token.EndTag endPending = new Token.EndTag();
Token.Character charPending = new Token.Character();
Token.Doctype doctypePending = new Token.Doctype(); // doctype building up
Token.Comment commentPending = new Token.Comment(); // comment building up
private String lastStartTag; // the last start tag emitted, to test appropriate end tag
private boolean selfClosingFlagAcknowledged = true;
Tokeniser(CharacterReader reader, ParseErrorList errors) {
this.reader = reader;
this.errors = errors;
}
Token read() {
if (!selfClosingFlagAcknowledged) {
error("Self closing flag not acknowledged");
selfClosingFlagAcknowledged = true;
}
while (!isEmitPending)
state.read(this, reader);
// if emit is pending, a non-character token was found: return any chars in buffer, and leave token for next read:
if (charsBuilder.length() > 0) {
String str = charsBuilder.toString();
charsBuilder.delete(0, charsBuilder.length());
charsString = null;
return charPending.data(str);
} else if (charsString != null) {
Token token = charPending.data(charsString);
charsString = null;
return token;
} else {
isEmitPending = false;
return emitPending;
}
}
void emit(Token token) {
Validate.isFalse(isEmitPending, "There is an unread token pending!");
emitPending = token;
isEmitPending = true;
if (token.type == Token.TokenType.StartTag) {
Token.StartTag startTag = (Token.StartTag) token;
lastStartTag = startTag.tagName;
if (startTag.selfClosing)
selfClosingFlagAcknowledged = false;
} else if (token.type == Token.TokenType.EndTag) {
Token.EndTag endTag = (Token.EndTag) token;
if (endTag.attributes != null)
error("Attributes incorrectly present on end tag");
}
}
void emit(final String str) {
// buffer strings up until last string token found, to emit only one token for a run of character refs etc.
// does not set isEmitPending; read checks that
if (charsString == null) {
charsString = str;
}
else {
if (charsBuilder.length() == 0) { // switching to string builder as more than one emit before read
charsBuilder.append(charsString);
}
charsBuilder.append(str);
}
}
void emit(char[] chars) {
emit(String.valueOf(chars));
}
void emit(char c) {
emit(String.valueOf(c));
}
TokeniserState getState() {
return state;
}
void transition(TokeniserState state) {
this.state = state;
}
void advanceTransition(TokeniserState state) {
reader.advance();
this.state = state;
}
void acknowledgeSelfClosingFlag() {
selfClosingFlagAcknowledged = true;
}
final private char[] charRefHolder = new char[1]; // holder to not have to keep creating arrays
char[] consumeCharacterReference(Character additionalAllowedCharacter, boolean inAttribute) {
if (reader.isEmpty())
return null;
if (additionalAllowedCharacter != null && additionalAllowedCharacter == reader.current())
return null;
if (reader.matchesAnySorted(notCharRefCharsSorted))
return null;
final char[] charRef = charRefHolder;
reader.mark();
if (reader.matchConsume("#")) { // numbered
boolean isHexMode = reader.matchConsumeIgnoreCase("X");
String numRef = isHexMode ? reader.consumeHexSequence() : reader.consumeDigitSequence();
if (numRef.length() == 0) { // didn't match anything
characterReferenceError("numeric reference with no numerals");
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
int charval = -1;
try {
int base = isHexMode ? 16 : 10;
charval = Integer.valueOf(numRef, base);
} catch (NumberFormatException e) {
} // skip
if (charval == -1 || (charval >= 0xD800 && charval <= 0xDFFF) || charval > 0x10FFFF) {
characterReferenceError("character outside of valid range");
charRef[0] = replacementChar;
return charRef;
} else {
// todo: implement number replacement table
// todo: check for extra illegal unicode points as parse errors
if (charval < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
charRef[0] = (char) charval;
return charRef;
} else
return Character.toChars(charval);
}
} else { // named
// get as many letters as possible, and look for matching entities.
String nameRef = reader.consumeLetterThenDigitSequence();
boolean looksLegit = reader.matches(';');
// found if a base named entity without a ;, or an extended entity with the ;.
boolean found = ( Entities.isBaseNamedEntity(nameRef) || (Entities.isNamedEntity(nameRef) && looksLegit));
if (!found) {
reader.rewindToMark();
if (looksLegit) // named with semicolon
characterReferenceError(MessageFormatUtil.format("invalid named referenece " + PortUtil.escapedSingleBracket + "{0}" + PortUtil.escapedSingleBracket, nameRef));
return null;
}
if (inAttribute && (reader.matchesLetter() || reader.matchesDigit() || reader.matchesAny('=', '-', '_'))) {
// don't want that to match
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
charRef[0] = Entities.getCharacterByName(nameRef);
return charRef;
}
}
Token.Tag createTagPending(boolean start) {
tagPending = (Token.Tag) (start ? startPending.reset() : endPending.reset());
return tagPending;
}
void emitTagPending() {
tagPending.finaliseTag();
emit(tagPending);
}
void createCommentPending() {
commentPending.reset();
}
void emitCommentPending() {
emit(commentPending);
}
void createDoctypePending() {
doctypePending.reset();
}
void emitDoctypePending() {
emit(doctypePending);
}
void createTempBuffer() {
Token.reset(dataBuffer);
}
boolean isAppropriateEndTagToken() {
return lastStartTag != null && tagPending.tagName.equals(lastStartTag);
}
String appropriateEndTagName() {
if (lastStartTag == null)
return null;
return lastStartTag;
}
void error(TokeniserState state) {
if (errors.canAddError())
errors.add(new ParseError(reader.pos(), "Unexpected character " + PortUtil.escapedSingleBracket + "{0}" + PortUtil.escapedSingleBracket + " in input state [{}]", reader.current(), state));
}
void eofError(TokeniserState state) {
if (errors.canAddError())
errors.add(new ParseError(reader.pos(), "Unexpectedly reached end of file (EOF) in input state [{0}]", state));
}
private void characterReferenceError(String message) {
if (errors.canAddError())
errors.add(new ParseError(reader.pos(), "Invalid character reference: {0}", message));
}
private void error(String errorMsg) {
if (errors.canAddError())
errors.add(new ParseError(reader.pos(), errorMsg));
}
boolean currentNodeInHtmlNS() {
// todo: implement namespaces correctly
return true;
// Element currentNode = currentNode();
// return currentNode != null && currentNode.namespace().equals("HTML");
}
/**
* Utility method to consume reader and unescape entities found within.
* @param inAttribute
* @return unescaped string from reader
*/
String unescapeEntities(boolean inAttribute) {
StringBuilder builder = new StringBuilder();
while (!reader.isEmpty()) {
builder.append(reader.consumeTo('&'));
if (reader.matches('&')) {
reader.consume();
char[] c = consumeCharacterReference(null, inAttribute);
if (c == null || c.length==0)
builder.append('&');
else
builder.append(c);
}
}
return builder.toString();
}
}