org.apache.camel.xml.io.util.XmlStreamReader Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright 2004 Sun Microsystems, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
*/
package org.apache.camel.xml.io.util;
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;
import java.text.MessageFormat;
import java.util.Locale;
import java.util.Map;
import java.util.Map.Entry;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* Character stream that handles (or at least attempts to) all the necessary Voodoo to figure out the charset encoding
* of the XML document within the stream.
*
* IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a character stream.
*
* All this has to be done without consuming characters from the stream, if not the XML parser will not recognized the
* document as a valid XML. This is not 100% true, but it's close enough (UTF-8 BOM is not handled by all parsers right
* now, XmlReader handles it and things work in all parsers).
*
* The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP streams by offering
* a wide set of constructors.
*
* By default the charset encoding detection is lenient, the constructor with the lenient flag can be used for an script
* (following HTTP MIME and XML specifications). All this is nicely explained by Mark Pilgrim in his blog,
*
* Determining the character encoding of a feed.
*/
public class XmlStreamReader extends Reader {
private static final int BUFFER_SIZE = 4096;
private static final String US_ASCII = "US-ASCII";
private static final String UTF_8 = "UTF-8";
private static final String UTF_16BE = "UTF-16BE";
private static final String UTF_16LE = "UTF-16LE";
private static final String UTF_16 = "UTF-16";
private static final String CP1047 = "CP1047";
private static final Pattern CHARSET_PATTERN = Pattern.compile("charset=([.[^; ]]*)");
private static final Pattern ENCODING_PATTERN
= Pattern.compile("<\\?xml.*encoding[\\s]*=[\\s]*(\".[^\"]*\"|'.[^']*')", Pattern.MULTILINE);
private static final MessageFormat RAW_EX_1
= new MessageFormat("Invalid encoding, BOM [{0}] XML guess [{1}] XML prolog [{2}] encoding mismatch");
private static final MessageFormat RAW_EX_2
= new MessageFormat("Invalid encoding, BOM [{0}] XML guess [{1}] XML prolog [{2}] unknown BOM");
private static final MessageFormat HTTP_EX_1 = new MessageFormat(
"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], BOM must be NULL");
private static final MessageFormat HTTP_EX_2 = new MessageFormat(
"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], encoding mismatch");
private static final MessageFormat HTTP_EX_3 = new MessageFormat(
"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], Invalid MIME");
private static String staticDefaultEncoding = null;
private final String defaultEncoding;
private Reader reader;
private String encoding;
/**
* Creates a Reader for a File.
*
* It looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also missing defaults to
* UTF-8.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param file File to create a Reader from.
* @throws IOException thrown if there is a problem reading the file.
*/
public XmlStreamReader(final File file) throws IOException {
this(new FileInputStream(file));
}
/**
* Creates a Reader for a raw InputStream.
*
* It follows the same logic used for files.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param is InputStream to create a Reader from.
* @throws IOException thrown if there is a problem reading the stream.
*/
public XmlStreamReader(final InputStream is) throws IOException {
this(is, true);
}
/**
* Creates a Reader for a raw InputStream and uses the provided default encoding if none is determined.
*
* It follows the same logic used for files.
*
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the
* following:
*
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
*
* Else if the XML prolog had a charset encoding that encoding is used.
*
* Else if the content type had a charset encoding that encoding is used.
*
* Else 'UTF-8' is used.
*
* If lenient detection is indicated an XmlStreamReaderException is never thrown.
*
*
* @param is InputStream to create a Reader from.
* @param lenient indicates if the charset encoding detection should be relaxed.
* @param defaultEncoding default encoding to use if one cannot be detected.
* @throws IOException thrown if there is a problem reading the stream.
* @throws XmlStreamReaderException thrown if the charset encoding could not be determined according to the specs.
*/
public XmlStreamReader(final InputStream is, final boolean lenient, final String defaultEncoding) throws IOException,
XmlStreamReaderException {
if (defaultEncoding == null) {
this.defaultEncoding = staticDefaultEncoding;
} else {
this.defaultEncoding = defaultEncoding;
}
try {
doRawStream(is, lenient);
} catch (final XmlStreamReaderException ex) {
if (!lenient) {
throw ex;
} else {
doLenientDetection(null, ex);
}
}
}
/**
* Creates a Reader for a raw InputStream.
*
* It follows the same logic used for files.
*
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the
* following:
*
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
*
* Else if the XML prolog had a charset encoding that encoding is used.
*
* Else if the content type had a charset encoding that encoding is used.
*
* Else 'UTF-8' is used.
*
* If lenient detection is indicated an XmlStreamReaderException is never thrown.
*
*
* @param is InputStream to create a Reader from.
* @param lenient indicates if the charset encoding detection should be relaxed.
* @throws IOException thrown if there is a problem reading the stream.
* @throws XmlStreamReaderException thrown if the charset encoding could not be determined according to the specs.
*/
public XmlStreamReader(final InputStream is, final boolean lenient) throws IOException, XmlStreamReaderException {
this(is, lenient, null);
}
/**
* Creates a Reader using the InputStream of a URL.
*
* If the URL is not of type HTTP and there is not 'content-type' header in the fetched data it uses the same logic
* used for Files.
*
* If the URL is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic used for
* an InputStream with content-type.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param url URL to create a Reader from.
* @throws IOException thrown if there is a problem reading the stream of the URL.
*/
public XmlStreamReader(final URL url) throws IOException {
this(url, null);
}
/**
* Creates a Reader using the InputStream of a URL.
*
* If the URL is not of type HTTP and there is not 'content-type' header in the fetched data it uses the same logic
* used for Files.
*
* If the URL is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic used for
* an InputStream with content-type.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param url URL to create a Reader from.
* @param requestHeaders optional Map of headers to set on http request.
* @throws IOException thrown if there is a problem reading the stream of the URL.
*/
public XmlStreamReader(final URL url, final Map requestHeaders) throws IOException {
this(url.openConnection(), requestHeaders);
}
/**
* Creates a Reader using the InputStream of a URLConnection.
*
* If the URLConnection is not of type HttpURLConnection and there is not 'content-type' header in the fetched data
* it uses the same logic used for files.
*
* If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic
* used for an InputStream with content-type.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param conn URLConnection to create a Reader from.
* @throws IOException thrown if there is a problem reading the stream of the URLConnection.
*/
public XmlStreamReader(final URLConnection conn) throws IOException {
this(conn, null);
}
/**
* Creates a Reader using the InputStream of a URLConnection.
*
* If the URLConnection is not of type HttpURLConnection and there is not 'content-type' header in the fetched data
* it uses the same logic used for files.
*
* If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic
* used for an InputStream with content-type.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param conn URLConnection to create a Reader from.
* @param requestHeaders optional Map of headers to set on http request.
* @throws IOException thrown if there is a problem reading the stream of the URLConnection.
*/
public XmlStreamReader(final URLConnection conn, final Map requestHeaders) throws IOException {
defaultEncoding = staticDefaultEncoding;
final boolean lenient = true;
if (conn instanceof HttpURLConnection) {
setRequestHeader(conn, requestHeaders);
try {
doHttpStream(conn.getInputStream(), conn.getContentType(), lenient);
} catch (final XmlStreamReaderException ex) {
doLenientDetection(conn.getContentType(), ex);
}
} else if (conn.getContentType() != null) {
try {
doHttpStream(conn.getInputStream(), conn.getContentType(), lenient);
} catch (final XmlStreamReaderException ex) {
doLenientDetection(conn.getContentType(), ex);
}
} else {
try {
doRawStream(conn.getInputStream(), lenient);
} catch (final XmlStreamReaderException ex) {
doLenientDetection(null, ex);
}
}
}
/**
* Creates a Reader using an InputStream and the associated content-type header.
*
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. If there is not
* content-type encoding checks the XML prolog encoding. If there is not XML prolog encoding uses the default
* encoding mandated by the content-type MIME type.
*
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
*
*
* @param is InputStream to create the reader from.
* @param httpContentType content-type header to use for the resolution of the charset encoding.
* @throws IOException thrown if there is a problem reading the file.
*/
public XmlStreamReader(final InputStream is, final String httpContentType) throws IOException {
this(is, httpContentType, true);
}
/**
* Creates a Reader using an InputStream and the associated content-type header.
*
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. If there is not
* content-type encoding checks the XML prolog encoding. If there is not XML prolog encoding uses the default
* encoding mandated by the content-type MIME type.
*
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the
* following:
*
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
*
* Else if the XML prolog had a charset encoding that encoding is used.
*
* Else if the content type had a charset encoding that encoding is used.
*
* Else 'UTF-8' is used.
*
* If lenient detection is indicated and XmlStreamReaderException is never thrown.
*
*
* @param is InputStream to create the reader from.
* @param httpContentType content-type header to use for the resolution of the charset encoding.
* @param lenient indicates if the charset encoding detection should be relaxed.
* @param defaultEncoding default encoding to use if one cannot be detected.
* @throws IOException thrown if there is a problem reading the file.
* @throws XmlStreamReaderException thrown if the charset encoding could not be determined according to the specs.
*/
public XmlStreamReader(final InputStream is, final String httpContentType, final boolean lenient,
final String defaultEncoding) throws IOException, XmlStreamReaderException {
if (defaultEncoding == null) {
this.defaultEncoding = staticDefaultEncoding;
} else {
this.defaultEncoding = defaultEncoding;
}
try {
doHttpStream(is, httpContentType, lenient);
} catch (final XmlStreamReaderException ex) {
if (!lenient) {
throw ex;
} else {
doLenientDetection(httpContentType, ex);
}
}
}
/**
* Creates a Reader using an InputStream and the associated content-type header.
*
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. If there is not
* content-type encoding checks the XML prolog encoding. If there is not XML prolog encoding uses the default
* encoding mandated by the content-type MIME type.
*
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the
* following:
*
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
*
* Else if the XML prolog had a charset encoding that encoding is used.
*
* Else if the content type had a charset encoding that encoding is used.
*
* Else 'UTF-8' is used.
*
* If lenient detection is indicated and XmlStreamReaderException is never thrown.
*
*
* @param is InputStream to create the reader from.
* @param httpContentType content-type header to use for the resolution of the charset encoding.
* @param lenient indicates if the charset encoding detection should be relaxed.
* @throws IOException thrown if there is a problem reading the file.
* @throws XmlStreamReaderException thrown if the charset encoding could not be determined according to the specs.
*/
public XmlStreamReader(final InputStream is, final String httpContentType, final boolean lenient) throws IOException,
XmlStreamReaderException {
this(is, httpContentType, lenient, null);
}
/**
* Returns the default encoding to use if none is set in HTTP content-type, XML prolog and the rules based on
* content-type are not adequate.
*
* If it is NULL the content-type based rules are used.
*
*
* @return the default encoding to use.
*/
public static String getDefaultEncoding() {
return staticDefaultEncoding;
}
/**
* Sets the default encoding to use if none is set in HTTP content-type, XML prolog and the rules based on
* content-type are not adequate.
*
* If it is set to NULL the content-type based rules are used.
*
* By default it is NULL.
*
*
* @param encoding charset encoding to default to.
*/
public static void setDefaultEncoding(final String encoding) {
staticDefaultEncoding = encoding;
}
/**
* Returns the charset encoding of the XmlReader.
*
*
* @return charset encoding.
*/
public String getEncoding() {
return encoding;
}
private void doLenientDetection(String httpContentType, XmlStreamReaderException ex) throws IOException {
if (httpContentType != null) {
if (httpContentType.startsWith("text/html")) {
httpContentType = httpContentType.substring("text/html".length());
httpContentType = "text/xml" + httpContentType;
try {
doHttpStream(ex.getInputStream(), httpContentType, true);
ex = null;
} catch (final XmlStreamReaderException ex2) {
ex = ex2;
}
}
}
if (ex != null) {
String xmlEncoding = ex.getXmlEncoding();
if (xmlEncoding == null) {
xmlEncoding = ex.getContentTypeEncoding();
}
if (xmlEncoding == null) {
if (defaultEncoding == null) {
xmlEncoding = UTF_8;
} else {
xmlEncoding = defaultEncoding;
}
}
prepareReader(ex.getInputStream(), xmlEncoding);
}
}
@Override
public int read(final char[] buf, final int offset, final int len) throws IOException {
return reader.read(buf, offset, len);
}
/**
* Closes the XmlReader stream.
*
*
* @throws IOException thrown if there was a problem closing the stream.
*/
@Override
public void close() throws IOException {
reader.close();
}
private void doRawStream(final InputStream is, final boolean lenient) throws IOException {
final BufferedInputStream pis = new BufferedInputStream(is, BUFFER_SIZE);
final String bomEnc = getBOMEncoding(pis);
final String xmlGuessEnc = getXMLGuessEncoding(pis);
final String xmlEnc = getXmlProlog(pis, xmlGuessEnc);
final String calculatedEncoding = calculateRawEncoding(bomEnc, xmlGuessEnc, xmlEnc, pis);
prepareReader(pis, calculatedEncoding);
}
private void doHttpStream(final InputStream is, final String httpContentType, final boolean lenient) throws IOException {
final BufferedInputStream pis = new BufferedInputStream(is, BUFFER_SIZE);
final String cTMime = getContentTypeMime(httpContentType);
final String cTEnc = getContentTypeEncoding(httpContentType);
final String bomEnc = getBOMEncoding(pis);
final String xmlGuessEnc = getXMLGuessEncoding(pis);
final String xmlEnc = getXmlProlog(pis, xmlGuessEnc);
final String calculatedHttpEncoding = calculateHttpEncoding(cTMime, cTEnc, bomEnc, xmlGuessEnc, xmlEnc, pis, lenient);
prepareReader(pis, calculatedHttpEncoding);
}
private void prepareReader(final InputStream is, final String encoding) throws IOException {
reader = new InputStreamReader(is, encoding);
this.encoding = encoding;
}
// InputStream is passed for XmlStreamReaderException creation only
private String calculateRawEncoding(
final String bomEnc, final String xmlGuessEnc, final String xmlEnc, final InputStream is)
throws IOException {
String retEncoding;
if (bomEnc == null) {
if (xmlGuessEnc == null || xmlEnc == null) {
if (defaultEncoding == null) {
retEncoding = UTF_8;
} else {
retEncoding = defaultEncoding;
}
} else if (xmlEnc.equals(UTF_16) && (xmlGuessEnc.equals(UTF_16BE) || xmlGuessEnc.equals(UTF_16LE))) {
retEncoding = xmlGuessEnc;
} else {
retEncoding = xmlEnc;
}
} else if (bomEnc.equals(UTF_8)) {
if (xmlGuessEnc != null && !xmlGuessEnc.equals(UTF_8)) {
throw new XmlStreamReaderException(
RAW_EX_1.format(new Object[] { bomEnc, xmlGuessEnc, xmlEnc }), bomEnc, xmlGuessEnc, xmlEnc, is);
}
if (xmlEnc != null && !xmlEnc.equals(UTF_8)) {
throw new XmlStreamReaderException(
RAW_EX_1.format(new Object[] { bomEnc, xmlGuessEnc, xmlEnc }), bomEnc, xmlGuessEnc, xmlEnc, is);
}
retEncoding = UTF_8;
} else if (bomEnc.equals(UTF_16BE) || bomEnc.equals(UTF_16LE)) {
if (xmlGuessEnc != null && !xmlGuessEnc.equals(bomEnc)) {
throw new IOException(RAW_EX_1.format(new Object[] { bomEnc, xmlGuessEnc, xmlEnc }));
}
if (xmlEnc != null && !xmlEnc.equals(UTF_16) && !xmlEnc.equals(bomEnc)) {
throw new XmlStreamReaderException(
RAW_EX_1.format(new Object[] { bomEnc, xmlGuessEnc, xmlEnc }), bomEnc, xmlGuessEnc, xmlEnc, is);
}
retEncoding = bomEnc;
} else {
throw new XmlStreamReaderException(
RAW_EX_2.format(new Object[] { bomEnc, xmlGuessEnc, xmlEnc }), bomEnc, xmlGuessEnc, xmlEnc, is);
}
return retEncoding;
}
private void setRequestHeader(final URLConnection conn, final Map requestHeaders) {
final Package pckg = this.getClass().getPackage();
if (pckg.getImplementationTitle() != null && pckg.getImplementationVersion() != null) {
conn.setRequestProperty("User-Agent", pckg.getImplementationTitle() + "/" + pckg.getImplementationVersion());
} else {
conn.setRequestProperty("User-Agent", "ROME");
}
if (requestHeaders != null) {
for (final Entry requestHeader : requestHeaders.entrySet()) {
conn.setRequestProperty(requestHeader.getKey(), requestHeader.getValue());
}
}
}
// InputStream is passed for XmlStreamReaderException creation only
private String calculateHttpEncoding(
final String cTMime, final String cTEnc, final String bomEnc, final String xmlGuessEnc, final String xmlEnc,
final InputStream is,
final boolean lenient)
throws IOException {
String retEncoding;
if (lenient && xmlEnc != null) {
retEncoding = xmlEnc;
} else {
final boolean appXml = isAppXml(cTMime);
final boolean textXml = isTextXml(cTMime);
if (appXml || textXml) {
if (cTEnc == null) {
if (appXml) {
retEncoding = calculateRawEncoding(bomEnc, xmlGuessEnc, xmlEnc, is);
} else {
if (defaultEncoding == null) {
retEncoding = US_ASCII;
} else {
retEncoding = defaultEncoding;
}
}
} else if (bomEnc != null && (cTEnc.equals(UTF_16BE) || cTEnc.equals(UTF_16LE))) {
throw new XmlStreamReaderException(
HTTP_EX_1.format(new Object[] { cTMime, cTEnc, bomEnc, xmlGuessEnc, xmlEnc }), cTMime, cTEnc,
bomEnc, xmlGuessEnc, xmlEnc, is);
} else if (cTEnc.equals(UTF_16)) {
if (bomEnc != null && bomEnc.startsWith(UTF_16)) {
retEncoding = bomEnc;
} else {
throw new XmlStreamReaderException(
HTTP_EX_2.format(new Object[] { cTMime, cTEnc, bomEnc, xmlGuessEnc, xmlEnc }), cTMime, cTEnc,
bomEnc, xmlGuessEnc, xmlEnc,
is);
}
} else {
retEncoding = cTEnc;
}
} else {
throw new XmlStreamReaderException(
HTTP_EX_3.format(new Object[] { cTMime, cTEnc, bomEnc, xmlGuessEnc, xmlEnc }), cTMime, cTEnc, bomEnc,
xmlGuessEnc, xmlEnc, is);
}
}
return retEncoding;
}
// returns MIME type or NULL if httpContentType is NULL
private static String getContentTypeMime(final String httpContentType) {
String mime = null;
if (httpContentType != null) {
final int i = httpContentType.indexOf(';');
if (i == -1) {
mime = httpContentType.trim();
} else {
mime = httpContentType.substring(0, i).trim();
}
}
return mime;
}
// returns charset parameter value, NULL if not present, NULL if
// httpContentType is NULL
private static String getContentTypeEncoding(final String httpContentType) {
String encoding = null;
if (httpContentType != null) {
final int i = httpContentType.indexOf(';');
if (i > -1) {
final String postMime = httpContentType.substring(i + 1);
final Matcher m = CHARSET_PATTERN.matcher(postMime);
if (m.find()) {
encoding = m.group(1);
}
if (encoding != null) {
encoding = encoding.toUpperCase(Locale.ENGLISH);
}
}
if (encoding != null && (encoding.startsWith("\"") && encoding.endsWith("\"")
|| encoding.startsWith("'") && encoding.endsWith("'"))) {
encoding = encoding.substring(1, encoding.length() - 1);
}
}
return encoding;
}
// returns the BOM in the stream, NULL if not present,
// if there was BOM the in the stream it is consumed
@SuppressWarnings("ResultOfMethodCallIgnored")
private static String getBOMEncoding(final BufferedInputStream is) throws IOException {
String encoding = null;
final int[] bytes = new int[3];
is.mark(3);
bytes[0] = is.read();
bytes[1] = is.read();
bytes[2] = is.read();
if (bytes[0] == 0xFE && bytes[1] == 0xFF) {
encoding = UTF_16BE;
is.reset();
is.read();
is.read();
} else if (bytes[0] == 0xFF && bytes[1] == 0xFE) {
encoding = UTF_16LE;
is.reset();
is.read();
is.read();
} else if (bytes[0] == 0xEF && bytes[1] == 0xBB && bytes[2] == 0xBF) {
encoding = UTF_8;
} else {
is.reset();
}
return encoding;
}
// returns the best guess for the encoding by looking the first bytes of the
// stream, ', NULL if none
static String getXmlProlog(final InputStream is, final String guessedEnc) throws IOException {
String encoding = null;
if (guessedEnc != null) {
final byte[] bytes = new byte[BUFFER_SIZE];
is.mark(BUFFER_SIZE);
int offset = 0;
int max = BUFFER_SIZE;
int c = is.read(bytes, offset, max);
int firstGT = -1;
while (c != -1 && firstGT == -1 && offset < BUFFER_SIZE) {
offset += c;
max -= c;
c = is.read(bytes, offset, max);
firstGT = new String(bytes, 0, offset, guessedEnc).indexOf('>');
}
if (firstGT == -1) {
if (c == -1) {
throw new IOException("Unexpected end of XML stream");
} else {
throw new IOException("XML prolog or ROOT element not found on first " + offset + " bytes");
}
}
final int bytesRead = offset;
if (bytesRead > 0) {
is.reset();
String prolog = new String(bytes, guessedEnc).substring(0, firstGT);
final Matcher m = ENCODING_PATTERN.matcher(prolog);
if (m.find()) {
encoding = m.group(1).toUpperCase(Locale.ENGLISH);
encoding = encoding.substring(1, encoding.length() - 1);
}
}
}
return encoding;
}
// indicates if the MIME type belongs to the APPLICATION XML family
private static boolean isAppXml(final String mime) {
return mime != null && (mime.equals("application/xml") || mime.equals("application/xml-dtd")
|| mime.equals("application/xml-external-parsed-entity")
|| mime.startsWith("application/") && mime.endsWith("+xml"));
}
// indicates if the MIME type belongs to the TEXT XML family
private static boolean isTextXml(final String mime) {
return mime != null && (mime.equals("text/xml") || mime.equals("text/xml-external-parsed-entity")
|| mime.startsWith("text/") && mime.endsWith("+xml"));
}
}