| 1 | /* |
| 2 | * Copyright (C) 2011 Google Inc. All rights reserved. |
| 3 | * |
| 4 | * Redistribution and use in source and binary forms, with or without |
| 5 | * modification, are permitted provided that the following conditions are |
| 6 | * met: |
| 7 | * |
| 8 | * * Redistributions of source code must retain the above copyright |
| 9 | * notice, this list of conditions and the following disclaimer. |
| 10 | * * Redistributions in binary form must reproduce the above |
| 11 | * copyright notice, this list of conditions and the following disclaimer |
| 12 | * in the documentation and/or other materials provided with the |
| 13 | * distribution. |
| 14 | * * Neither the name of Google Inc. nor the names of its |
| 15 | * contributors may be used to endorse or promote products derived from |
| 16 | * this software without specific prior written permission. |
| 17 | * |
| 18 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 19 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 20 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 21 | * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 22 | * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 23 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 24 | * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 25 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 26 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 27 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 28 | * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 29 | */ |
| 30 | |
| 31 | #include "config.h" |
| 32 | #include "QuotedPrintable.h" |
| 33 | |
| 34 | #include <wtf/ASCIICType.h> |
| 35 | #include <wtf/Vector.h> |
| 36 | |
| 37 | namespace WebCore { |
| 38 | |
| 39 | static const size_t maximumLineLength = 76; |
| 40 | |
| 41 | static const char crlfLineEnding[] = "\r\n" ; |
| 42 | |
| 43 | static size_t lengthOfLineEndingAtIndex(const char* input, size_t inputLength, size_t index) |
| 44 | { |
| 45 | ASSERT_WITH_SECURITY_IMPLICATION(index < inputLength); |
| 46 | if (input[index] == '\n') |
| 47 | return 1; // Single LF. |
| 48 | |
| 49 | if (input[index] == '\r') { |
| 50 | if ((index + 1) == inputLength || input[index + 1] != '\n') |
| 51 | return 1; // Single CR (Classic Mac OS). |
| 52 | return 2; // CR-LF. |
| 53 | } |
| 54 | |
| 55 | return 0; |
| 56 | } |
| 57 | |
| 58 | void quotedPrintableEncode(const Vector<char>& in, Vector<char>& out) |
| 59 | { |
| 60 | quotedPrintableEncode(in.data(), in.size(), out); |
| 61 | } |
| 62 | |
| 63 | void quotedPrintableEncode(const char* input, size_t inputLength, Vector<char>& out) |
| 64 | { |
| 65 | out.clear(); |
| 66 | out.reserveCapacity(inputLength); |
| 67 | size_t currentLineLength = 0; |
| 68 | for (size_t i = 0; i < inputLength; ++i) { |
| 69 | bool isLastCharacter = (i == inputLength - 1); |
| 70 | char currentCharacter = input[i]; |
| 71 | bool requiresEncoding = false; |
| 72 | // All non-printable ASCII characters and = require encoding. |
| 73 | if ((currentCharacter < ' ' || currentCharacter > '~' || currentCharacter == '=') && currentCharacter != '\t') |
| 74 | requiresEncoding = true; |
| 75 | |
| 76 | // Space and tab characters have to be encoded if they appear at the end of a line. |
| 77 | if (!requiresEncoding && (currentCharacter == '\t' || currentCharacter == ' ') && (isLastCharacter || lengthOfLineEndingAtIndex(input, inputLength, i + 1))) |
| 78 | requiresEncoding = true; |
| 79 | |
| 80 | // End of line should be converted to CR-LF sequences. |
| 81 | if (!isLastCharacter) { |
| 82 | size_t lengthOfLineEnding = lengthOfLineEndingAtIndex(input, inputLength, i); |
| 83 | if (lengthOfLineEnding) { |
| 84 | out.append(crlfLineEnding, strlen(crlfLineEnding)); |
| 85 | currentLineLength = 0; |
| 86 | i += (lengthOfLineEnding - 1); // -1 because we'll ++ in the for() above. |
| 87 | continue; |
| 88 | } |
| 89 | } |
| 90 | |
| 91 | size_t lengthOfEncodedCharacter = 1; |
| 92 | if (requiresEncoding) |
| 93 | lengthOfEncodedCharacter += 2; |
| 94 | if (!isLastCharacter) |
| 95 | lengthOfEncodedCharacter += 1; // + 1 for the = (soft line break). |
| 96 | |
| 97 | // Insert a soft line break if necessary. |
| 98 | if (currentLineLength + lengthOfEncodedCharacter > maximumLineLength) { |
| 99 | out.append('='); |
| 100 | out.append(crlfLineEnding, strlen(crlfLineEnding)); |
| 101 | currentLineLength = 0; |
| 102 | } |
| 103 | |
| 104 | // Finally, insert the actual character(s). |
| 105 | if (requiresEncoding) { |
| 106 | out.append('='); |
| 107 | out.append(upperNibbleToASCIIHexDigit(currentCharacter)); |
| 108 | out.append(lowerNibbleToASCIIHexDigit(currentCharacter)); |
| 109 | currentLineLength += 3; |
| 110 | } else { |
| 111 | out.append(currentCharacter); |
| 112 | currentLineLength++; |
| 113 | } |
| 114 | } |
| 115 | } |
| 116 | |
| 117 | void quotedPrintableDecode(const Vector<char>& in, Vector<char>& out) |
| 118 | { |
| 119 | quotedPrintableDecode(in.data(), in.size(), out); |
| 120 | } |
| 121 | |
| 122 | void quotedPrintableDecode(const char* data, size_t dataLength, Vector<char>& out) |
| 123 | { |
| 124 | out.clear(); |
| 125 | if (!dataLength) |
| 126 | return; |
| 127 | |
| 128 | for (size_t i = 0; i < dataLength; ++i) { |
| 129 | char currentCharacter = data[i]; |
| 130 | if (currentCharacter != '=') { |
| 131 | out.append(currentCharacter); |
| 132 | continue; |
| 133 | } |
| 134 | // We are dealing with a '=xx' sequence. |
| 135 | if (dataLength - i < 3) { |
| 136 | // Unfinished = sequence, append as is. |
| 137 | out.append(currentCharacter); |
| 138 | continue; |
| 139 | } |
| 140 | char upperCharacter = data[++i]; |
| 141 | char lowerCharacter = data[++i]; |
| 142 | if (upperCharacter == '\r' && lowerCharacter == '\n') |
| 143 | continue; |
| 144 | |
| 145 | if (!isASCIIHexDigit(upperCharacter) || !isASCIIHexDigit(lowerCharacter)) { |
| 146 | // Invalid sequence, = followed by non hex digits, just insert the characters as is. |
| 147 | out.append('='); |
| 148 | out.append(upperCharacter); |
| 149 | out.append(lowerCharacter); |
| 150 | continue; |
| 151 | } |
| 152 | out.append(static_cast<char>(toASCIIHexValue(upperCharacter, lowerCharacter))); |
| 153 | } |
| 154 | } |
| 155 | |
| 156 | } |
| 157 | |