org.apache.http.client.utils.URLEncodedUtilsHC4 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.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
*
* This is typically useful while parsing an HTTP PUT.
*
* This API is currently only used for testing.
*
* @param uri
* URI to parse
* @param charset
* Charset name to use while parsing the query
* @return a list of {@link NameValuePair} as built from the URI's query portion.
*/
public static List parse(final URI uri, final String charset) {
final String query = uri.getRawQuery();
if (query != null && query.length() > 0) {
final List result = new ArrayList();
final Scanner scanner = new Scanner(query);
parse(result, scanner, QP_SEP_PATTERN, charset);
return result;
}
return Collections.emptyList();
}
/**
* Returns a list of {@link NameValuePair NameValuePairs} as parsed from an {@link HttpEntity}. The encoding is
* taken from the entity's Content-Encoding header.
*
* This is typically used while parsing an HTTP POST.
*
* @param entity
* The entity to parse
* @return a list of {@link NameValuePair} as built from the URI's query portion.
* @throws IOException
* If there was an exception getting the entity's data.
*/
public static List parse(
final HttpEntity entity) throws IOException {
final ContentType contentType = ContentType.get(entity);
if (contentType != null && contentType.getMimeType().equalsIgnoreCase(CONTENT_TYPE)) {
final String content = EntityUtilsHC4.toString(entity, Consts.ASCII);
if (content != null && content.length() > 0) {
Charset charset = contentType.getCharset();
if (charset == null) {
charset = Charset.forName(HTTP.DEFAULT_CONTENT_CHARSET);
}
return parse(content, charset, QP_SEPS);
}
}
return Collections.emptyList();
}
/**
* Returns true if the entity's Content-Type header is
* application/x-www-form-urlencoded.
*/
public static boolean isEncoded(final HttpEntity entity) {
final Header h = entity.getContentType();
if (h != null) {
final HeaderElement[] elems = h.getElements();
if (elems.length > 0) {
final String contentType = elems[0].getName();
return contentType.equalsIgnoreCase(CONTENT_TYPE);
}
}
return false;
}
/**
* Adds all parameters within the Scanner to the list of parameters, as encoded by
* encoding. For example, a scanner containing the string a=1&b=2&c=3 would add the
* {@link NameValuePair NameValuePairs} a=1, b=2, and c=3 to the list of parameters. By convention, {@code '&'} and
* {@code ';'} are accepted as parameter separators.
*
* @param parameters
* List to add parameters to.
* @param scanner
* Input that contains the parameters to parse.
* @param charset
* Encoding to use when decoding the parameters.
*/
public static void parse(
final List parameters,
final Scanner scanner,
final String charset) {
parse(parameters, scanner, QP_SEP_PATTERN, charset);
}
/**
* Adds all parameters within the Scanner to the list of
* parameters, as encoded by encoding. For
* example, a scanner containing the string a=1&b=2&c=3 would
* add the {@link NameValuePair NameValuePairs} a=1, b=2, and c=3 to the
* list of parameters.
*
* @param parameters
* List to add parameters to.
* @param scanner
* Input that contains the parameters to parse.
* @param parameterSepartorPattern
* The Pattern string for parameter separators, by convention {@code "[&;]"}
* @param charset
* Encoding to use when decoding the parameters.
*/
public static void parse(
final List parameters,
final Scanner scanner,
final String parameterSepartorPattern,
final String charset) {
scanner.useDelimiter(parameterSepartorPattern);
while (scanner.hasNext()) {
String name = null;
String value = null;
final String token = scanner.next();
final int i = token.indexOf(NAME_VALUE_SEPARATOR);
if (i != -1) {
name = decodeFormFields(token.substring(0, i).trim(), charset);
value = decodeFormFields(token.substring(i + 1).trim(), charset);
} else {
name = decodeFormFields(token.trim(), charset);
}
parameters.add(new BasicNameValuePair(name, value));
}
}
/**
* Query parameter separators.
*/
private static final char[] QP_SEPS = new char[] { QP_SEP_A, QP_SEP_S };
/**
* Query parameter separator pattern.
*/
private static final String QP_SEP_PATTERN = "[" + new String(QP_SEPS) + "]";
/**
* Returns a list of {@link NameValuePair NameValuePairs} as parsed from the given string using the given character
* encoding. By convention, {@code '&'} and {@code ';'} are accepted as parameter separators.
*
* @param s
* text to parse.
* @param charset
* Encoding to use when decoding the parameters.
* @return a list of {@link NameValuePair} as built from the URI's query portion.
*
* @since 4.2
*/
public static List parse(final String s, final Charset charset) {
return parse(s, charset, QP_SEPS);
}
/**
* Returns a list of {@link NameValuePair NameValuePairs} as parsed from the given string using the given character
* encoding.
*
* @param s
* text to parse.
* @param charset
* Encoding to use when decoding the parameters.
* @param parameterSeparator
* The characters used to separate parameters, by convention, {@code '&'} and {@code ';'}.
* @return a list of {@link NameValuePair} as built from the URI's query portion.
*
* @since 4.3
*/
public static List parse(final String s, final Charset charset, final char... parameterSeparator) {
if (s == null) {
return Collections.emptyList();
}
final BasicHeaderValueParserHC4 parser = BasicHeaderValueParserHC4.INSTANCE;
final CharArrayBuffer buffer = new CharArrayBuffer(s.length());
buffer.append(s);
final ParserCursor cursor = new ParserCursor(0, buffer.length());
final List list = new ArrayList();
while (!cursor.atEnd()) {
final NameValuePair nvp = parser.parseNameValuePair(buffer, cursor, parameterSeparator);
if (nvp.getName().length() > 0) {
list.add(new BasicNameValuePair(
decodeFormFields(nvp.getName(), charset),
decodeFormFields(nvp.getValue(), charset)));
}
}
return list;
}
/**
* Returns a String that is suitable for use as an {@code application/x-www-form-urlencoded}
* list of parameters in an HTTP PUT or HTTP POST.
*
* @param parameters The parameters to include.
* @param charset The encoding to use.
* @return An {@code application/x-www-form-urlencoded} string
*/
public static String format(
final List parameters,
final String charset) {
return format(parameters, QP_SEP_A, charset);
}
/**
* Returns a String that is suitable for use as an {@code application/x-www-form-urlencoded}
* list of parameters in an HTTP PUT or HTTP POST.
*
* @param parameters The parameters to include.
* @param parameterSeparator The parameter separator, by convention, {@code '&'} or {@code ';'}.
* @param charset The encoding to use.
* @return An {@code application/x-www-form-urlencoded} string
*
* @since 4.3
*/
public static String format(
final List parameters,
final char parameterSeparator,
final String charset) {
final StringBuilder result = new StringBuilder();
for (final NameValuePair parameter : parameters) {
final String encodedName = encodeFormFields(parameter.getName(), charset);
final String encodedValue = encodeFormFields(parameter.getValue(), charset);
if (result.length() > 0) {
result.append(parameterSeparator);
}
result.append(encodedName);
if (encodedValue != null) {
result.append(NAME_VALUE_SEPARATOR);
result.append(encodedValue);
}
}
return result.toString();
}
/**
* Returns a String that is suitable for use as an {@code application/x-www-form-urlencoded}
* list of parameters in an HTTP PUT or HTTP POST.
*
* @param parameters The parameters to include.
* @param charset The encoding to use.
* @return An {@code application/x-www-form-urlencoded} string
*
* @since 4.2
*/
public static String format(
final Iterable parameters,
final Charset charset) {
return format(parameters, QP_SEP_A, charset);
}
/**
* Returns a String that is suitable for use as an {@code application/x-www-form-urlencoded}
* list of parameters in an HTTP PUT or HTTP POST.
*
* @param parameters The parameters to include.
* @param parameterSeparator The parameter separator, by convention, {@code '&'} or {@code ';'}.
* @param charset The encoding to use.
* @return An {@code application/x-www-form-urlencoded} string
*
* @since 4.3
*/
public static String format(
final Iterable parameters,
final char parameterSeparator,
final Charset charset) {
final StringBuilder result = new StringBuilder();
for (final NameValuePair parameter : parameters) {
final String encodedName = encodeFormFields(parameter.getName(), charset);
final String encodedValue = encodeFormFields(parameter.getValue(), charset);
if (result.length() > 0) {
result.append(parameterSeparator);
}
result.append(encodedName);
if (encodedValue != null) {
result.append(NAME_VALUE_SEPARATOR);
result.append(encodedValue);
}
}
return result.toString();
}
/**
* Unreserved characters, i.e. alphanumeric, plus: {@code _ - ! . ~ ' ( ) *}
*
* This list is the same as the {@code unreserved} list in
* RFC 2396
*/
private static final BitSet UNRESERVED = new BitSet(256);
/**
* Punctuation characters: , ; : $ & + =
*
* These are the additional characters allowed by userinfo.
*/
private static final BitSet PUNCT = new BitSet(256);
/** Characters which are safe to use in userinfo,
* i.e. {@link #UNRESERVED} plus {@link #PUNCT}uation */
private static final BitSet USERINFO = new BitSet(256);
/** Characters which are safe to use in a path,
* i.e. {@link #UNRESERVED} plus {@link #PUNCT}uation plus / @ */
private static final BitSet PATHSAFE = new BitSet(256);
/** Characters which are safe to use in a query or a fragment,
* i.e. {@link #RESERVED} plus {@link #UNRESERVED} */
private static final BitSet URIC = new BitSet(256);
/**
* Reserved characters, i.e. {@code ;/?:@&=+$,[]}
*
* This list is the same as the {@code reserved} list in
* RFC 2396
* as augmented by
* RFC 2732
*/
private static final BitSet RESERVED = new BitSet(256);
/**
* Safe characters for x-www-form-urlencoded data, as per java.net.URLEncoder and browser behaviour,
* i.e. alphanumeric plus {@code "-", "_", ".", "*"}
*/
private static final BitSet URLENCODER = new BitSet(256);
static {
// unreserved chars
// alpha characters
for (int i = 'a'; i <= 'z'; i++) {
UNRESERVED.set(i);
}
for (int i = 'A'; i <= 'Z'; i++) {
UNRESERVED.set(i);
}
// numeric characters
for (int i = '0'; i <= '9'; i++) {
UNRESERVED.set(i);
}
UNRESERVED.set('_'); // these are the charactes of the "mark" list
UNRESERVED.set('-');
UNRESERVED.set('.');
UNRESERVED.set('*');
URLENCODER.or(UNRESERVED); // skip remaining unreserved characters
UNRESERVED.set('!');
UNRESERVED.set('~');
UNRESERVED.set('\'');
UNRESERVED.set('(');
UNRESERVED.set(')');
// punct chars
PUNCT.set(',');
PUNCT.set(';');
PUNCT.set(':');
PUNCT.set('$');
PUNCT.set('&');
PUNCT.set('+');
PUNCT.set('=');
// Safe for userinfo
USERINFO.or(UNRESERVED);
USERINFO.or(PUNCT);
// URL path safe
PATHSAFE.or(UNRESERVED);
PATHSAFE.set('/'); // segment separator
PATHSAFE.set(';'); // param separator
PATHSAFE.set(':'); // rest as per list in 2396, i.e. : @ & = + $ ,
PATHSAFE.set('@');
PATHSAFE.set('&');
PATHSAFE.set('=');
PATHSAFE.set('+');
PATHSAFE.set('$');
PATHSAFE.set(',');
RESERVED.set(';');
RESERVED.set('/');
RESERVED.set('?');
RESERVED.set(':');
RESERVED.set('@');
RESERVED.set('&');
RESERVED.set('=');
RESERVED.set('+');
RESERVED.set('$');
RESERVED.set(',');
RESERVED.set('['); // added by RFC 2732
RESERVED.set(']'); // added by RFC 2732
URIC.or(RESERVED);
URIC.or(UNRESERVED);
}
private static final int RADIX = 16;
private static String urlEncode(
final String content,
final Charset charset,
final BitSet safechars,
final boolean blankAsPlus) {
if (content == null) {
return null;
}
final StringBuilder buf = new StringBuilder();
final ByteBuffer bb = charset.encode(content);
while (bb.hasRemaining()) {
final int b = bb.get() & 0xff;
if (safechars.get(b)) {
buf.append((char) b);
} else if (blankAsPlus && b == ' ') {
buf.append('+');
} else {
buf.append("%");
final char hex1 = Character.toUpperCase(Character.forDigit((b >> 4) & 0xF, RADIX));
final char hex2 = Character.toUpperCase(Character.forDigit(b & 0xF, RADIX));
buf.append(hex1);
buf.append(hex2);
}
}
return buf.toString();
}
/**
* Decode/unescape a portion of a URL, to use with the query part ensure {@code plusAsBlank} is true.
*
* @param content the portion to decode
* @param charset the charset to use
* @param plusAsBlank if {@code true}, then convert '+' to space (e.g. for www-url-form-encoded content), otherwise leave as is.
* @return encoded string
*/
private static String urlDecode(
final String content,
final Charset charset,
final boolean plusAsBlank) {
if (content == null) {
return null;
}
final ByteBuffer bb = ByteBuffer.allocate(content.length());
final CharBuffer cb = CharBuffer.wrap(content);
while (cb.hasRemaining()) {
final char c = cb.get();
if (c == '%' && cb.remaining() >= 2) {
final char uc = cb.get();
final char lc = cb.get();
final int u = Character.digit(uc, 16);
final int l = Character.digit(lc, 16);
if (u != -1 && l != -1) {
bb.put((byte) ((u << 4) + l));
} else {
bb.put((byte) '%');
bb.put((byte) uc);
bb.put((byte) lc);
}
} else if (plusAsBlank && c == '+') {
bb.put((byte) ' ');
} else {
bb.put((byte) c);
}
}
bb.flip();
return charset.decode(bb).toString();
}
/**
* Decode/unescape www-url-form-encoded content.
*
* @param content the content to decode, will decode '+' as space
* @param charset the charset to use
* @return encoded string
*/
private static String decodeFormFields (final String content, final String charset) {
if (content == null) {
return null;
}
return urlDecode(content, charset != null ? Charset.forName(charset) : Consts.UTF_8, true);
}
/**
* Decode/unescape www-url-form-encoded content.
*
* @param content the content to decode, will decode '+' as space
* @param charset the charset to use
* @return encoded string
*/
private static String decodeFormFields (final String content, final Charset charset) {
if (content == null) {
return null;
}
return urlDecode(content, charset != null ? charset : Consts.UTF_8, true);
}
/**
* Encode/escape www-url-form-encoded content.
*
* Uses the {@link #URLENCODER} set of characters, rather than
* the {@link #UNRSERVED} set; this is for compatibilty with previous
* releases, URLEncoder.encode() and most browsers.
*
* @param content the content to encode, will convert space to '+'
* @param charset the charset to use
* @return encoded string
*/
private static String encodeFormFields(final String content, final String charset) {
if (content == null) {
return null;
}
return urlEncode(content, charset != null ? Charset.forName(charset) : Consts.UTF_8, URLENCODER, true);
}
/**
* Encode/escape www-url-form-encoded content.
*
* Uses the {@link #URLENCODER} set of characters, rather than
* the {@link #UNRSERVED} set; this is for compatibilty with previous
* releases, URLEncoder.encode() and most browsers.
*
* @param content the content to encode, will convert space to '+'
* @param charset the charset to use
* @return encoded string
*/
private static String encodeFormFields (final String content, final Charset charset) {
if (content == null) {
return null;
}
return urlEncode(content, charset != null ? charset : Consts.UTF_8, URLENCODER, true);
}
/**
* Encode a String using the {@link #USERINFO} set of characters.
*
* Used by URIBuilder to encode the userinfo segment.
*
* @param content the string to encode, does not convert space to '+'
* @param charset the charset to use
* @return the encoded string
*/
static String encUserInfo(final String content, final Charset charset) {
return urlEncode(content, charset, USERINFO, false);
}
/**
* Encode a String using the {@link #URIC} set of characters.
*
* Used by URIBuilder to encode the query and fragment segments.
*
* @param content the string to encode, does not convert space to '+'
* @param charset the charset to use
* @return the encoded string
*/
static String encUric(final String content, final Charset charset) {
return urlEncode(content, charset, URIC, false);
}
/**
* Encode a String using the {@link #PATHSAFE} set of characters.
*
* Used by URIBuilder to encode path segments.
*
* @param content the string to encode, does not convert space to '+'
* @param charset the charset to use
* @return the encoded string
*/
static String encPath(final String content, final Charset charset) {
return urlEncode(content, charset, PATHSAFE, false);
}
}