com.itextpdf.io.font.cmap.CMapContentParser Maven / Gradle / Ivy
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2023 Apryse Group NV
Authors: Apryse Software.
This program is offered under a commercial and under the AGPL license.
For commercial licensing, contact us at https://itextpdf.com/sales. For AGPL licensing, see below.
AGPL licensing:
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
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 ls) throws java.io.IOException {
ls.clear();
CMapObject ob;
while ((ob = readObject()) != null) {
ls.add(ob);
// TokenType.Other or CMapObject.Literal means a command
if (ob.isLiteral())
break;
}
}
/**
* Reads a dictionary. The tokeniser must be positioned past the {@code "<<"} token.
* @return the dictionary
* @throws java.io.IOException on error
*/
public CMapObject readDictionary() throws java.io.IOException {
Map dic = new HashMap<>();
while (true) {
if (!nextValidToken())
throw new IOException("Unexpected end of file.");
if (tokeniser.getTokenType() == TokenType.EndDic)
break;
if (tokeniser.getTokenType() == TokenType.Other && "def".equals(tokeniser.getStringValue()))
continue;
if (tokeniser.getTokenType() != TokenType.Name)
throw new IOException("Dictionary key {0} is not a name.").setMessageParams(tokeniser.getStringValue());
String name = tokeniser.getStringValue();
CMapObject obj = readObject();
if (obj.isToken()) {
if (obj.toString().equals(">>")) {
tokeniser.throwError(IoExceptionMessageConstant.UNEXPECTED_GT_GT);
}
if (obj.toString().equals("]")) {
tokeniser.throwError(IoExceptionMessageConstant.UNEXPECTED_CLOSE_BRACKET);
}
}
dic.put(name, obj);
}
return new CMapObject(CMapObject.DICTIONARY, dic);
}
/**
* Reads an array. The tokeniser must be positioned past the "[" token.
* @return an array
* @throws java.io.IOException on error
*/
public CMapObject readArray() throws java.io.IOException {
List array = new ArrayList();
while (true) {
CMapObject obj = readObject();
if (obj.isToken()) {
if (obj.toString().equals("]")) {
break;
}
if (obj.toString().equals(">>")) {
tokeniser.throwError(IoExceptionMessageConstant.UNEXPECTED_GT_GT);
}
}
array.add(obj);
}
return new CMapObject(CMapObject.ARRAY, array);
}
/**
* Reads a pdf object.
* @return the pdf object
* @throws java.io.IOException on error
*/
public CMapObject readObject() throws java.io.IOException {
if (!nextValidToken())
return null;
TokenType type = tokeniser.getTokenType();
switch (type) {
case StartDic:
return readDictionary();
case StartArray:
return readArray();
case String:
CMapObject obj;
if (tokeniser.isHexString()) {
obj = new CMapObject(CMapObject.HEX_STRING, PdfTokenizer.decodeStringContent(tokeniser.getByteContent(), true));
} else {
obj = new CMapObject(CMapObject.STRING, PdfTokenizer.decodeStringContent(tokeniser.getByteContent(), false));
}
return obj;
case Name:
return new CMapObject(CMapObject.NAME, decodeName(tokeniser.getByteContent()));
case Number:
CMapObject numObject = new CMapObject(CMapObject.NUMBER, null);
try {
numObject.setValue((int)java.lang.Double.parseDouble(tokeniser.getStringValue()));
} catch (NumberFormatException e) {
numObject.setValue(Integer.MIN_VALUE);
}
return numObject;
case Other:
return new CMapObject(CMapObject.LITERAL, tokeniser.getStringValue());
case EndArray:
return new CMapObject(CMapObject.TOKEN, "]");
case EndDic:
return new CMapObject(CMapObject.TOKEN, ">>");
default:
return new CMapObject(0, "");
}
}
/**
* Reads the next token skipping over the comments.
* @return {@code true} if a token was read, {@code false} if the end of content was reached.
* @throws java.io.IOException on error.
*/
public boolean nextValidToken() throws java.io.IOException {
while (tokeniser.nextToken()) {
if (tokeniser.getTokenType() == TokenType.Comment)
continue;
return true;
}
return false;
}
// TODO: Duplicates PdfName.generateValue (REFACTOR)
protected static String decodeName(byte[] content) {
StringBuilder buf = new StringBuilder();
try {
for (int k = 0; k < content.length; ++k) {
char c = (char) content[k];
if (c == '#') {
byte c1 = content[k + 1];
byte c2 = content[k + 2];
c = (char) ((ByteBuffer.getHex(c1) << 4) + ByteBuffer.getHex(c2));
k += 2;
}
buf.append(c);
}
} catch (IndexOutOfBoundsException e) {
// empty on purpose
}
return buf.toString();
}
private static String toHex4(int n) {
String s = "0000" + Integer.toHexString(n);
return s.substring(s.length() - 4);
}
/**
* Gets an hex string in the format "<HHHH>".
*
* @param n the number
* @return the hex string
*/
public static String toHex(int n) {
if (n < 0x10000)
return "<" + toHex4(n) + ">";
n -= 0x10000;
int high = n / 0x400 + 0xd800;
int low = n % 0x400 + 0xdc00;
return "[<" + toHex4(high) + toHex4(low) + ">]";
}
public static String decodeCMapObject(CMapObject cMapObject) {
if (cMapObject.isHexString()) {
return PdfEncodings.convertToString(((String) cMapObject.getValue()).getBytes(), PdfEncodings.UNICODE_BIG_UNMARKED);
} else {
return (String) cMapObject.getValue();
}
}
}