org.json.XMLTokener Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of aem-sdk-api Show documentation
Show all versions of aem-sdk-api Show documentation
The Adobe Experience Manager SDK
package org.json;
import java.util.HashMap;
/**
* The XMLTokener extends the JSONTokener to provide additional methods
* for the parsing of XML texts.
* @author JSON.org
* @version 2009-02-11
* @deprecated Use javax.json or other other json libraries instead
*/
@Deprecated
public class XMLTokener extends JSONTokener {
public static final HashMap entity = new HashMap<>(8);
static {
entity.put("amp", XML.AMP);
entity.put("apos", XML.APOS);
entity.put("gt", XML.GT);
entity.put("lt", XML.LT);
entity.put("quot", XML.QUOT);
}
/**
* Construct an XMLTokener from a string.
* @param s A source string.
*/
public XMLTokener(String s) {
super(s);
}
/**
* Get the text in the CDATA block.
* @return The string up to the ]]>.
* @throws JSONException If the ]]> is not found.
*/
public String nextCDATA() throws JSONException {
StringBuffer sb = new StringBuffer();
int i;
do {
char c = next();
if (end()) {
throw syntaxError("Unclosed CDATA");
}
sb.append(c);
i = sb.length() - 3;
} while ((i < 0) || (sb.charAt(i) != ']') || (sb.charAt(i + 1) != ']') || (sb.charAt(i + 2) != '>'));
sb.setLength(i);
return sb.toString();
}
/**
* Get the next XML outer token, trimming whitespace. There are two kinds
* of tokens: the '<' character which begins a markup tag, and the content
* text between markup tags.
*
* @return A string, or a '<' Character, or null if there is no more
* source text.
* @throws JSONException
*/
public Object nextContent() throws JSONException {
char c;
do {
c = next();
} while (Character.isWhitespace(c));
if (c == 0) {
return null;
}
if (c == '<') {
return XML.LT;
}
StringBuffer sb = new StringBuffer();
for (;;) {
if ((c == '<') || (c == 0)) {
back();
return sb.toString().trim();
}
if (c == '&') {
sb.append(nextEntity(c));
} else {
sb.append(c);
}
c = next();
}
}
/**
* Return the next entity. These entities are translated to Characters:
* & ' > < ".
* @param ampersand An ampersand character.
* @return A Character or an entity String if the entity is not recognized.
* @throws JSONException If missing ';' in XML entity.
*/
public Object nextEntity(char ampersand) throws JSONException {
StringBuffer sb = new StringBuffer();
char c;
do {
c = next();
if (!Character.isLetterOrDigit(c) && c != '#')
break;
sb.append(Character.toLowerCase(c));
} while (true);
if (c != ';') {
throw syntaxError((new StringBuilder()).append("Missing ';' in XML entity: &").append(sb).toString());
} else {
String string = sb.toString();
Object object = entity.get(string);
return object == null
? (new StringBuilder()).append(ampersand).append(string).append(";").toString()
: object;
}
}
/**
* Returns the next XML meta token. This is used for skipping over
* and structures.
* @return Syntax characters (< > / = ! ?) are returned as
* Character, and strings and names are returned as Boolean. We don't care
* what the values actually are.
* @throws JSONException If a string is not properly closed or if the XML
* is badly structured.
*/
public Object nextMeta() throws JSONException {
char c;
do {
c = next();
} while (Character.isWhitespace(c));
switch (c) {
case '\000' :
throw syntaxError("Misshaped meta tag");
case '<' :
return XML.LT;
case '>' :
return XML.GT;
case '/' :
return XML.SLASH;
case '=' :
return XML.EQ;
case '!' :
return XML.BANG;
case '?' :
return XML.QUEST;
case '"' :
case '\'' :
char q = c;
do {
c = next();
if (c == 0) {
throw syntaxError("Unterminated string");
}
} while (c != q);
return Boolean.TRUE;
}
for (;;) {
c = next();
if (Character.isWhitespace(c)) {
return Boolean.TRUE;
}
switch (c) {
case '\000' :
case '!' :
case '"' :
case '\'' :
case '/' :
case '<' :
case '=' :
case '>' :
case '?' :
back();
return Boolean.TRUE;
}
}
}
/**
* Get the next XML Token. These tokens are found inside of angle
* brackets. It may be one of these characters: / > = ! ? or it
* may be a string wrapped in single quotes or double quotes, or it may be a
* name.
* @return a String or a Character.
* @throws JSONException If the XML is not well formed.
*/
public Object nextToken() throws JSONException {
char c;
do {
c = next();
} while (Character.isWhitespace(c));
switch (c) {
case '\000' :
throw syntaxError("Misshaped element");
case '<' :
throw syntaxError("Misplaced '<'");
case '>' :
return XML.GT;
case '/' :
return XML.SLASH;
case '=' :
return XML.EQ;
case '!' :
return XML.BANG;
case '?' :
return XML.QUEST;
case '"' :
case '\'' :
char q = c;
StringBuffer sb = new StringBuffer();
for (;;) {
c = next();
if (c == 0) {
throw syntaxError("Unterminated string");
}
if (c == q) {
return sb.toString();
}
if (c == '&') {
sb.append(nextEntity(c));
} else {
sb.append(c);
}
}
}
StringBuffer sb = new StringBuffer();
for (;;) {
sb.append(c);
c = next();
if (Character.isWhitespace(c)) {
return sb.toString();
}
switch (c) {
case '\000' :
return sb.toString();
case '!' :
case '/' :
case '=' :
case '>' :
case '?' :
case '[' :
case ']' :
back();
return sb.toString();
case '"' :
case '\'' :
case '<' :
throw syntaxError("Bad character in a name");
}
}
}
/**
* Skip characters until past the requested string.
* If it is not found, we are left at the end of the source with a result of false.
* @param to A string to skip past.
*/
public boolean skipPast(String to) throws JSONException {
int offset = 0;
int length = to.length();
char[] circle = new char[length];
for (int i = 0; i < length; i++) {
char c = next();
if (c == 0) {
return false;
}
circle[i] = c;
}
for (;;) {
int j = offset;
boolean b = true;
for (int i = 0; i < length; i++) {
if (circle[j] != to.charAt(i)) {
b = false;
break;
}
j++;
if (j >= length) {
j -= length;
}
}
if (b) {
return true;
}
char c = next();
if (c == 0) {
return false;
}
circle[offset] = c;
offset++;
if (offset >= length) {
offset -= length;
}
}
}
}