From f06ff492f18d7c9cdf861a79293279e5ed55823f Mon Sep 17 00:00:00 2001 From: Michal Srb Date: Fri, 26 Apr 2013 07:32:04 +0200 Subject: [PATCH 2/2] Replace bundled gdata-java-client classes with commons-codec --- .../gdata/util/common/base/Escaper.java | 97 ---- .../util/common/base/PercentEscaper.java | 281 ---------- .../util/common/base/UnicodeEscaper.java | 506 ------------------ .../org/yaml/snakeyaml/util/UriEncoder.java | 37 +- 4 files changed, 28 insertions(+), 893 deletions(-) delete mode 100644 src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/Escaper.java delete mode 100644 src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/PercentEscaper.java delete mode 100644 src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/UnicodeEscaper.java diff --git a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/Escaper.java b/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/Escaper.java deleted file mode 100644 index c26e3cb..0000000 --- a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/Escaper.java +++ /dev/null @@ -1,97 +0,0 @@ -/* Copyright (c) 2008 Google 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.yaml.snakeyaml.external.com.google.gdata.util.common.base; - -/** - * An object that converts literal text into a format safe for inclusion in a - * particular context (such as an XML document). Typically (but not always), the - * inverse process of "unescaping" the text is performed automatically by the - * relevant parser. - * - *

- * For example, an XML escaper would convert the literal string - * {@code "Foo"} into {@code "Foo<Bar>"} to prevent {@code ""} - * from being confused with an XML tag. When the resulting XML document is - * parsed, the parser API will return this text as the original literal string - * {@code "Foo"}. - * - *

- * An {@code Escaper} instance is required to be stateless, and safe when used - * concurrently by multiple threads. - * - *

- * Several popular escapers are defined as constants in the class - * {@link CharEscapers}. To create your own escapers, use - * {@link CharEscaperBuilder}, or extend {@link CharEscaper} or - * {@code UnicodeEscaper}. - * - * - */ -public interface Escaper { - /** - * Returns the escaped form of a given literal string. - * - *

- * Note that this method may treat input characters differently depending on - * the specific escaper implementation. - *

- * - * @param string - * the literal string to be escaped - * @return the escaped form of {@code string} - * @throws NullPointerException - * if {@code string} is null - * @throws IllegalArgumentException - * if {@code string} contains badly formed UTF-16 or cannot be - * escaped for any other reason - */ - public String escape(String string); - - /** - * Returns an {@code Appendable} instance which automatically escapes all - * text appended to it before passing the resulting text to an underlying - * {@code Appendable}. - * - *

- * Note that this method may treat input characters differently depending on - * the specific escaper implementation. - *

- * - * @param out - * the underlying {@code Appendable} to append escaped output to - * @return an {@code Appendable} which passes text to {@code out} after - * escaping it. - */ - public Appendable escape(Appendable out); -} diff --git a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/PercentEscaper.java b/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/PercentEscaper.java deleted file mode 100644 index 5e2f902..0000000 --- a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/PercentEscaper.java +++ /dev/null @@ -1,281 +0,0 @@ -/* Copyright (c) 2008 Google 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.yaml.snakeyaml.external.com.google.gdata.util.common.base; - -/** - * A {@code UnicodeEscaper} that escapes some set of Java characters using the - * URI percent encoding scheme. The set of safe characters (those which remain - * unescaped) can be specified on construction. - * - *

- * For details on escaping URIs for use in web pages, see section 2.4 of RFC 3986. - * - *

- * In most cases this class should not need to be used directly. If you have no - * special requirements for escaping your URIs, you should use either - * {@link CharEscapers#uriEscaper()} or {@link CharEscapers#uriEscaper(boolean)}. - * - *

- * When encoding a String, the following rules apply: - *

- * - *

- * RFC 2396 specifies the set of unreserved characters as "-", "_", ".", "!", - * "~", "*", "'", "(" and ")". It goes on to state: - * - *

- * Unreserved characters can be escaped without changing the semantics of the - * URI, but this should not be done unless the URI is being used in a context - * that does not allow the unescaped character to appear. - * - *

- * For performance reasons the only currently supported character encoding of - * this class is UTF-8. - * - *

- * Note: This escaper produces uppercase hexidecimal sequences. From RFC 3986:
- * "URI producers and normalizers should use uppercase hexadecimal digits for - * all percent-encodings." - * - * - */ -public class PercentEscaper extends UnicodeEscaper { - /** - * A string of safe characters that mimics the behavior of - * {@link java.net.URLEncoder}. - * - */ - public static final String SAFECHARS_URLENCODER = "-_.*"; - - /** - * A string of characters that do not need to be encoded when used in URI - * path segments, as specified in RFC 3986. Note that some of these - * characters do need to be escaped when used in other parts of the URI. - */ - public static final String SAFEPATHCHARS_URLENCODER = "-_.!~*'()@:$&,;="; - - /** - * A string of characters that do not need to be encoded when used in URI - * query strings, as specified in RFC 3986. Note that some of these - * characters do need to be escaped when used in other parts of the URI. - */ - public static final String SAFEQUERYSTRINGCHARS_URLENCODER = "-_.!~*'()@:$,;/?:"; - - // In some uri escapers spaces are escaped to '+' - private static final char[] URI_ESCAPED_SPACE = { '+' }; - - private static final char[] UPPER_HEX_DIGITS = "0123456789ABCDEF".toCharArray(); - - /** - * If true we should convert space to the {@code +} character. - */ - private final boolean plusForSpace; - - /** - * An array of flags where for any {@code char c} if {@code safeOctets[c]} - * is true then {@code c} should remain unmodified in the output. If - * {@code c > safeOctets.length} then it should be escaped. - */ - private final boolean[] safeOctets; - - /** - * Constructs a URI escaper with the specified safe characters and optional - * handling of the space character. - * - * @param safeChars - * a non null string specifying additional safe characters for - * this escaper (the ranges 0..9, a..z and A..Z are always safe - * and should not be specified here) - * @param plusForSpace - * true if ASCII space should be escaped to {@code +} rather than - * {@code %20} - * @throws IllegalArgumentException - * if any of the parameters were invalid - */ - public PercentEscaper(String safeChars, boolean plusForSpace) { - // Avoid any misunderstandings about the behavior of this escaper - if (safeChars.matches(".*[0-9A-Za-z].*")) { - throw new IllegalArgumentException( - "Alphanumeric characters are always 'safe' and should not be " - + "explicitly specified"); - } - // Avoid ambiguous parameters. Safe characters are never modified so if - // space is a safe character then setting plusForSpace is meaningless. - if (plusForSpace && safeChars.contains(" ")) { - throw new IllegalArgumentException( - "plusForSpace cannot be specified when space is a 'safe' character"); - } - if (safeChars.contains("%")) { - throw new IllegalArgumentException("The '%' character cannot be specified as 'safe'"); - } - this.plusForSpace = plusForSpace; - this.safeOctets = createSafeOctets(safeChars); - } - - /** - * Creates a boolean[] with entries corresponding to the character values - * for 0-9, A-Z, a-z and those specified in safeChars set to true. The array - * is as small as is required to hold the given character information. - */ - private static boolean[] createSafeOctets(String safeChars) { - int maxChar = 'z'; - char[] safeCharArray = safeChars.toCharArray(); - for (char c : safeCharArray) { - maxChar = Math.max(c, maxChar); - } - boolean[] octets = new boolean[maxChar + 1]; - for (int c = '0'; c <= '9'; c++) { - octets[c] = true; - } - for (int c = 'A'; c <= 'Z'; c++) { - octets[c] = true; - } - for (int c = 'a'; c <= 'z'; c++) { - octets[c] = true; - } - for (char c : safeCharArray) { - octets[c] = true; - } - return octets; - } - - /* - * Overridden for performance. For unescaped strings this improved the - * performance of the uri escaper from ~760ns to ~400ns as measured by - * {@link CharEscapersBenchmark}. - */ - @Override - protected int nextEscapeIndex(CharSequence csq, int index, int end) { - for (; index < end; index++) { - char c = csq.charAt(index); - if (c >= safeOctets.length || !safeOctets[c]) { - break; - } - } - return index; - } - - /* - * Overridden for performance. For unescaped strings this improved the - * performance of the uri escaper from ~400ns to ~170ns as measured by - * {@link CharEscapersBenchmark}. - */ - @Override - public String escape(String s) { - int slen = s.length(); - for (int index = 0; index < slen; index++) { - char c = s.charAt(index); - if (c >= safeOctets.length || !safeOctets[c]) { - return escapeSlow(s, index); - } - } - return s; - } - - /** - * Escapes the given Unicode code point in UTF-8. - */ - @Override - protected char[] escape(int cp) { - // We should never get negative values here but if we do it will throw - // an - // IndexOutOfBoundsException, so at least it will get spotted. - if (cp < safeOctets.length && safeOctets[cp]) { - return null; - } else if (cp == ' ' && plusForSpace) { - return URI_ESCAPED_SPACE; - } else if (cp <= 0x7F) { - // Single byte UTF-8 characters - // Start with "%--" and fill in the blanks - char[] dest = new char[3]; - dest[0] = '%'; - dest[2] = UPPER_HEX_DIGITS[cp & 0xF]; - dest[1] = UPPER_HEX_DIGITS[cp >>> 4]; - return dest; - } else if (cp <= 0x7ff) { - // Two byte UTF-8 characters [cp >= 0x80 && cp <= 0x7ff] - // Start with "%--%--" and fill in the blanks - char[] dest = new char[6]; - dest[0] = '%'; - dest[3] = '%'; - dest[5] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[4] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[2] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[1] = UPPER_HEX_DIGITS[0xC | cp]; - return dest; - } else if (cp <= 0xffff) { - // Three byte UTF-8 characters [cp >= 0x800 && cp <= 0xffff] - // Start with "%E-%--%--" and fill in the blanks - char[] dest = new char[9]; - dest[0] = '%'; - dest[1] = 'E'; - dest[3] = '%'; - dest[6] = '%'; - dest[8] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[7] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[5] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[4] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[2] = UPPER_HEX_DIGITS[cp]; - return dest; - } else if (cp <= 0x10ffff) { - char[] dest = new char[12]; - // Four byte UTF-8 characters [cp >= 0xffff && cp <= 0x10ffff] - // Start with "%F-%--%--%--" and fill in the blanks - dest[0] = '%'; - dest[1] = 'F'; - dest[3] = '%'; - dest[6] = '%'; - dest[9] = '%'; - dest[11] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[10] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[8] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[7] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[5] = UPPER_HEX_DIGITS[cp & 0xF]; - cp >>>= 4; - dest[4] = UPPER_HEX_DIGITS[0x8 | (cp & 0x3)]; - cp >>>= 2; - dest[2] = UPPER_HEX_DIGITS[cp & 0x7]; - return dest; - } else { - // If this ever happens it is due to bug in UnicodeEscaper, not bad - // input. - throw new IllegalArgumentException("Invalid unicode character value " + cp); - } - } -} diff --git a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/UnicodeEscaper.java b/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/UnicodeEscaper.java deleted file mode 100644 index 5403185..0000000 --- a/src/main/java/org/yaml/snakeyaml/external/com/google/gdata/util/common/base/UnicodeEscaper.java +++ /dev/null @@ -1,506 +0,0 @@ -/* Copyright (c) 2008 Google 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.yaml.snakeyaml.external.com.google.gdata.util.common.base; - -import java.io.IOException; - -/** - * An {@link Escaper} that converts literal text into a format safe for - * inclusion in a particular context (such as an XML document). Typically (but - * not always), the inverse process of "unescaping" the text is performed - * automatically by the relevant parser. - * - *

- * For example, an XML escaper would convert the literal string - * {@code "Foo"} into {@code "Foo<Bar>"} to prevent {@code ""} - * from being confused with an XML tag. When the resulting XML document is - * parsed, the parser API will return this text as the original literal string - * {@code "Foo"}. - * - *

- * Note: This class is similar to {@link CharEscaper} but with one very - * important difference. A CharEscaper can only process Java UTF16 characters in isolation - * and may not cope when it encounters surrogate pairs. This class facilitates - * the correct escaping of all Unicode characters. - * - *

- * As there are important reasons, including potential security issues, to - * handle Unicode correctly if you are considering implementing a new escaper - * you should favor using UnicodeEscaper wherever possible. - * - *

- * A {@code UnicodeEscaper} instance is required to be stateless, and safe when - * used concurrently by multiple threads. - * - *

- * Several popular escapers are defined as constants in the class - * {@link CharEscapers}. To create your own escapers extend this class and - * implement the {@link #escape(int)} method. - * - * - */ -public abstract class UnicodeEscaper implements Escaper { - /** The amount of padding (chars) to use when growing the escape buffer. */ - private static final int DEST_PAD = 32; - - /** - * Returns the escaped form of the given Unicode code point, or {@code null} - * if this code point does not need to be escaped. When called as part of an - * escaping operation, the given code point is guaranteed to be in the range - * {@code 0 <= cp <= Character#MAX_CODE_POINT}. - * - *

- * If an empty array is returned, this effectively strips the input - * character from the resulting text. - * - *

- * If the character does not need to be escaped, this method should return - * {@code null}, rather than an array containing the character - * representation of the code point. This enables the escaping algorithm to - * perform more efficiently. - * - *

- * If the implementation of this method cannot correctly handle a particular - * code point then it should either throw an appropriate runtime exception - * or return a suitable replacement character. It must never silently - * discard invalid input as this may constitute a security risk. - * - * @param cp - * the Unicode code point to escape if necessary - * @return the replacement characters, or {@code null} if no escaping was - * needed - */ - protected abstract char[] escape(int cp); - - /** - * Scans a sub-sequence of characters from a given {@link CharSequence}, - * returning the index of the next character that requires escaping. - * - *

- * Note: When implementing an escaper, it is a good idea to override - * this method for efficiency. The base class implementation determines - * successive Unicode code points and invokes {@link #escape(int)} for each - * of them. If the semantics of your escaper are such that code points in - * the supplementary range are either all escaped or all unescaped, this - * method can be implemented more efficiently using - * {@link CharSequence#charAt(int)}. - * - *

- * Note however that if your escaper does not escape characters in the - * supplementary range, you should either continue to validate the - * correctness of any surrogate characters encountered or provide a clear - * warning to users that your escaper does not validate its input. - * - *

- * See {@link PercentEscaper} for an example. - * - * @param csq - * a sequence of characters - * @param start - * the index of the first character to be scanned - * @param end - * the index immediately after the last character to be scanned - * @throws IllegalArgumentException - * if the scanned sub-sequence of {@code csq} contains invalid - * surrogate pairs - */ - protected int nextEscapeIndex(CharSequence csq, int start, int end) { - int index = start; - while (index < end) { - int cp = codePointAt(csq, index, end); - if (cp < 0 || escape(cp) != null) { - break; - } - index += Character.isSupplementaryCodePoint(cp) ? 2 : 1; - } - return index; - } - - /** - * Returns the escaped form of a given literal string. - * - *

- * If you are escaping input in arbitrary successive chunks, then it is not - * generally safe to use this method. If an input string ends with an - * unmatched high surrogate character, then this method will throw - * {@link IllegalArgumentException}. You should either ensure your input is - * valid UTF-16 before - * calling this method or use an escaped {@link Appendable} (as returned by - * {@link #escape(Appendable)}) which can cope with arbitrarily split input. - * - *

- * Note: When implementing an escaper it is a good idea to override - * this method for efficiency by inlining the implementation of - * {@link #nextEscapeIndex(CharSequence, int, int)} directly. Doing this for - * {@link PercentEscaper} more than doubled the performance for unescaped - * strings (as measured by {@link CharEscapersBenchmark}). - * - * @param string - * the literal string to be escaped - * @return the escaped form of {@code string} - * @throws NullPointerException - * if {@code string} is null - * @throws IllegalArgumentException - * if invalid surrogate characters are encountered - */ - public String escape(String string) { - int end = string.length(); - int index = nextEscapeIndex(string, 0, end); - return index == end ? string : escapeSlow(string, index); - } - - /** - * Returns the escaped form of a given literal string, starting at the given - * index. This method is called by the {@link #escape(String)} method when - * it discovers that escaping is required. It is protected to allow - * subclasses to override the fastpath escaping function to inline their - * escaping test. See {@link CharEscaperBuilder} for an example usage. - * - *

- * This method is not reentrant and may only be invoked by the top level - * {@link #escape(String)} method. - * - * @param s - * the literal string to be escaped - * @param index - * the index to start escaping from - * @return the escaped form of {@code string} - * @throws NullPointerException - * if {@code string} is null - * @throws IllegalArgumentException - * if invalid surrogate characters are encountered - */ - protected final String escapeSlow(String s, int index) { - int end = s.length(); - - // Get a destination buffer and setup some loop variables. - char[] dest = DEST_TL.get(); - int destIndex = 0; - int unescapedChunkStart = 0; - - while (index < end) { - int cp = codePointAt(s, index, end); - if (cp < 0) { - throw new IllegalArgumentException("Trailing high surrogate at end of input"); - } - char[] escaped = escape(cp); - if (escaped != null) { - int charsSkipped = index - unescapedChunkStart; - - // This is the size needed to add the replacement, not the full - // size needed by the string. We only regrow when we absolutely - // must. - int sizeNeeded = destIndex + charsSkipped + escaped.length; - if (dest.length < sizeNeeded) { - int destLength = sizeNeeded + (end - index) + DEST_PAD; - dest = growBuffer(dest, destIndex, destLength); - } - // If we have skipped any characters, we need to copy them now. - if (charsSkipped > 0) { - s.getChars(unescapedChunkStart, index, dest, destIndex); - destIndex += charsSkipped; - } - if (escaped.length > 0) { - System.arraycopy(escaped, 0, dest, destIndex, escaped.length); - destIndex += escaped.length; - } - } - unescapedChunkStart = index + (Character.isSupplementaryCodePoint(cp) ? 2 : 1); - index = nextEscapeIndex(s, unescapedChunkStart, end); - } - - // Process trailing unescaped characters - no need to account for - // escaped - // length or padding the allocation. - int charsSkipped = end - unescapedChunkStart; - if (charsSkipped > 0) { - int endIndex = destIndex + charsSkipped; - if (dest.length < endIndex) { - dest = growBuffer(dest, destIndex, endIndex); - } - s.getChars(unescapedChunkStart, end, dest, destIndex); - destIndex = endIndex; - } - return new String(dest, 0, destIndex); - } - - /** - * Returns an {@code Appendable} instance which automatically escapes all - * text appended to it before passing the resulting text to an underlying - * {@code Appendable}. - * - *

- * Unlike {@link #escape(String)} it is permitted to append arbitrarily - * split input to this Appendable, including input that is split over a - * surrogate pair. In this case the pending high surrogate character will - * not be processed until the corresponding low surrogate is appended. This - * means that a trailing high surrogate character at the end of the input - * cannot be detected and will be silently ignored. This is unavoidable - * since the Appendable interface has no {@code close()} method, and it is - * impossible to determine when the last characters have been appended. - * - *

- * The methods of the returned object will propagate any exceptions thrown - * by the underlying {@code Appendable}. - * - *

- * For well formed UTF-16 - * the escaping behavior is identical to that of {@link #escape(String)} and - * the following code is equivalent to (but much slower than) - * {@code escaper.escape(string)}: - * - * 

-     * {
-     *     @code
-     *     StringBuilder sb = new StringBuilder();
-     *     escaper.escape(sb).append(string);
-     *     return sb.toString();
-     * }
-     *
- * - * @param out - * the underlying {@code Appendable} to append escaped output to - * @return an {@code Appendable} which passes text to {@code out} after - * escaping it - * @throws NullPointerException - * if {@code out} is null - * @throws IllegalArgumentException - * if invalid surrogate characters are encountered - * - */ - public Appendable escape(final Appendable out) { - assert out != null; - - return new Appendable() { - int pendingHighSurrogate = -1; - char[] decodedChars = new char[2]; - - public Appendable append(CharSequence csq) throws IOException { - return append(csq, 0, csq.length()); - } - - public Appendable append(CharSequence csq, int start, int end) throws IOException { - int index = start; - if (index < end) { - // This is a little subtle: index must never reference the - // middle of a - // surrogate pair but unescapedChunkStart can. The first - // time we enter - // the loop below it is possible that index != - // unescapedChunkStart. - int unescapedChunkStart = index; - if (pendingHighSurrogate != -1) { - // Our last append operation ended halfway through a - // surrogate pair - // so we have to do some extra work first. - char c = csq.charAt(index++); - if (!Character.isLowSurrogate(c)) { - throw new IllegalArgumentException( - "Expected low surrogate character but got " + c); - } - char[] escaped = escape(Character.toCodePoint((char) pendingHighSurrogate, - c)); - if (escaped != null) { - // Emit the escaped character and adjust - // unescapedChunkStart to - // skip the low surrogate we have consumed. - outputChars(escaped, escaped.length); - unescapedChunkStart += 1; - } else { - // Emit pending high surrogate (unescaped) but do - // not modify - // unescapedChunkStart as we must still emit the low - // surrogate. - out.append((char) pendingHighSurrogate); - } - pendingHighSurrogate = -1; - } - while (true) { - // Find and append the next subsequence of unescaped - // characters. - index = nextEscapeIndex(csq, index, end); - if (index > unescapedChunkStart) { - out.append(csq, unescapedChunkStart, index); - } - if (index == end) { - break; - } - // If we are not finished, calculate the next code - // point. - int cp = codePointAt(csq, index, end); - if (cp < 0) { - // Our sequence ended half way through a surrogate - // pair so just - // record the state and exit. - pendingHighSurrogate = -cp; - break; - } - // Escape the code point and output the characters. - char[] escaped = escape(cp); - if (escaped != null) { - outputChars(escaped, escaped.length); - } else { - // This shouldn't really happen if nextEscapeIndex - // is correct but - // we should cope with false positives. - int len = Character.toChars(cp, decodedChars, 0); - outputChars(decodedChars, len); - } - // Update our index past the escaped character and - // continue. - index += (Character.isSupplementaryCodePoint(cp) ? 2 : 1); - unescapedChunkStart = index; - } - } - return this; - } - - public Appendable append(char c) throws IOException { - if (pendingHighSurrogate != -1) { - // Our last append operation ended halfway through a - // surrogate pair - // so we have to do some extra work first. - if (!Character.isLowSurrogate(c)) { - throw new IllegalArgumentException( - "Expected low surrogate character but got '" + c + "' with value " - + (int) c); - } - char[] escaped = escape(Character.toCodePoint((char) pendingHighSurrogate, c)); - if (escaped != null) { - outputChars(escaped, escaped.length); - } else { - out.append((char) pendingHighSurrogate); - out.append(c); - } - pendingHighSurrogate = -1; - } else if (Character.isHighSurrogate(c)) { - // This is the start of a (split) surrogate pair. - pendingHighSurrogate = c; - } else { - if (Character.isLowSurrogate(c)) { - throw new IllegalArgumentException("Unexpected low surrogate character '" - + c + "' with value " + (int) c); - } - // This is a normal (non surrogate) char. - char[] escaped = escape(c); - if (escaped != null) { - outputChars(escaped, escaped.length); - } else { - out.append(c); - } - } - return this; - } - - private void outputChars(char[] chars, int len) throws IOException { - for (int n = 0; n < len; n++) { - out.append(chars[n]); - } - } - }; - } - - /** - * Returns the Unicode code point of the character at the given index. - * - *

- * Unlike {@link Character#codePointAt(CharSequence, int)} or - * {@link String#codePointAt(int)} this method will never fail silently when - * encountering an invalid surrogate pair. - * - *

- * The behaviour of this method is as follows: - *

    - *
  1. If {@code index >= end}, {@link IndexOutOfBoundsException} is thrown. - *
  2. If the character at the specified index is not a surrogate, it is - * returned. - *
  3. If the first character was a high surrogate value, then an attempt is - * made to read the next character. - *
      - *
    1. If the end of the sequence was reached, the negated value of the - * trailing high surrogate is returned. - *
    2. If the next character was a valid low surrogate, the code point - * value of the high/low surrogate pair is returned. - *
    3. If the next character was not a low surrogate value, then - * {@link IllegalArgumentException} is thrown. - *
    - *
  4. If the first character was a low surrogate value, - * {@link IllegalArgumentException} is thrown. - *
- * - * @param seq - * the sequence of characters from which to decode the code point - * @param index - * the index of the first character to decode - * @param end - * the index beyond the last valid character to decode - * @return the Unicode code point for the given index or the negated value - * of the trailing high surrogate character at the end of the - * sequence - */ - protected static final int codePointAt(CharSequence seq, int index, int end) { - if (index < end) { - char c1 = seq.charAt(index++); - if (c1 < Character.MIN_HIGH_SURROGATE || c1 > Character.MAX_LOW_SURROGATE) { - // Fast path (first test is probably all we need to do) - return c1; - } else if (c1 <= Character.MAX_HIGH_SURROGATE) { - // If the high surrogate was the last character, return its - // inverse - if (index == end) { - return -c1; - } - // Otherwise look for the low surrogate following it - char c2 = seq.charAt(index); - if (Character.isLowSurrogate(c2)) { - return Character.toCodePoint(c1, c2); - } - throw new IllegalArgumentException("Expected low surrogate but got char '" + c2 - + "' with value " + (int) c2 + " at index " + index); - } else { - throw new IllegalArgumentException("Unexpected low surrogate character '" + c1 - + "' with value " + (int) c1 + " at index " + (index - 1)); - } - } - throw new IndexOutOfBoundsException("Index exceeds specified range"); - } - - /** - * Helper method to grow the character buffer as needed, this only happens - * once in a while so it's ok if it's in a method call. If the index passed - * in is 0 then no copying will be done. - */ - private static final char[] growBuffer(char[] dest, int index, int size) { - char[] copy = new char[size]; - if (index > 0) { - System.arraycopy(dest, 0, copy, 0, index); - } - return copy; - } - - /** - * A thread-local destination buffer to keep us from creating new buffers. - * The starting size is 1024 characters. If we grow past this we don't put - * it back in the threadlocal, we just keep going and grow as needed. - */ - private static final ThreadLocal DEST_TL = new ThreadLocal() { - @Override - protected char[] initialValue() { - return new char[1024]; - } - }; -} diff --git a/src/main/java/org/yaml/snakeyaml/util/UriEncoder.java b/src/main/java/org/yaml/snakeyaml/util/UriEncoder.java index 4cc18b4..b6a1992 100644 --- a/src/main/java/org/yaml/snakeyaml/util/UriEncoder.java +++ b/src/main/java/org/yaml/snakeyaml/util/UriEncoder.java @@ -23,27 +23,46 @@ import java.nio.charset.CharacterCodingException; import java.nio.charset.Charset; import java.nio.charset.CharsetDecoder; import java.nio.charset.CodingErrorAction; - +import java.util.BitSet; + +import org.apache.commons.codec.net.URLCodec; import org.yaml.snakeyaml.error.YAMLException; -import org.yaml.snakeyaml.external.com.google.gdata.util.common.base.Escaper; -import org.yaml.snakeyaml.external.com.google.gdata.util.common.base.PercentEscaper; public abstract class UriEncoder { private static final CharsetDecoder UTF8Decoder = Charset.forName("UTF-8").newDecoder() .onMalformedInput(CodingErrorAction.REPORT); - // Include the [] chars to the SAFEPATHCHARS_URLENCODER to avoid - // its escape as required by spec. See - // http://yaml.org/spec/1.1/#escaping%20in%20URI/ - private static final String SAFE_CHARS = PercentEscaper.SAFEPATHCHARS_URLENCODER + "[]/"; - private static final Escaper escaper = new PercentEscaper(SAFE_CHARS, false); + // default safe characters which can appear within URI and shouldn't be escaped + private static final BitSet allowedCharacters = new BitSet(256); + + static { + for (int i = 'a'; i <= 'z'; i++) { + allowedCharacters.set(i); + } + for (int i = 'A'; i <= 'Z'; i++) { + allowedCharacters.set(i); + } + for (int i = '0'; i <= '9'; i++) { + allowedCharacters.set(i); + } + // http://yaml.org/spec/1.1/#escaping%20in%20URI/ + for (char c : "-_.!~*'()@:$&,;=/[]".toCharArray()) { + allowedCharacters.set(c); + } + } /** * Escape special characters with '%' * @param uri URI to be escaped * @return encoded URI */ public static String encode(String uri) { - return escaper.escape(uri); + try { + byte[] rawdata = URLCodec.encodeUrl(allowedCharacters, + uri.getBytes("UTF-8")); + return new String(rawdata, 0, rawdata.length, "US-ASCII"); + } catch (UnsupportedEncodingException e) { + throw new YAMLException(e); + } } /** -- 2.20.1