Add a standalone version of hex encoding and decoding, defining the filters

in terms of these calls.

The header for the hex filter is renamed hex_filt.h. This probably
won't affect people because filters.h (included by botan.h) already
included hex.h, and now just includes hex_filt.h instead.

3 files changed, 289 insertions, 0 deletions

diff --git a/src/codec/hex/hex.cpp b/src/codec/hex/hex.cpp
new file mode 100644
index 000000000..70e819906
--- /dev/null
+++ b/src/codec/hex/hex.cpp
@@ -0,0 +1,180 @@
+/*
+* Hex Encoding and Decoding
+* (C) 2010 Jack Lloyd
+*
+* Distributed under the terms of the Botan license
+*/
+
+#include <botan/hex.h>
+#include <botan/mem_ops.h>
+#include <stdexcept>
+
+namespace Botan {
+
+void hex_encode(char output[],
+                const byte input[],
+                u32bit input_length,
+                bool uppercase)
+   {
+   static const byte BIN_TO_HEX_UPPER[16] = {
+      '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+      'A', 'B', 'C', 'D', 'E', 'F' };
+
+   static const byte BIN_TO_HEX_LOWER[16] = {
+      '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+      'a', 'b', 'c', 'd', 'e', 'f' };
+
+   const byte* tbl = uppercase ? BIN_TO_HEX_UPPER : BIN_TO_HEX_LOWER;
+
+   for(u32bit i = 0; i != input_length; ++i)
+      {
+      byte x = input[i];
+      output[2*i  ] = tbl[(x >> 4) & 0x0F];
+      output[2*i+1] = tbl[(x     ) & 0x0F];
+      }
+   }
+
+std::string hex_encode(const byte input[],
+                       u32bit input_length,
+                       bool uppercase)
+   {
+   std::string output(2 * input_length, 0);
+   hex_encode(&output[0], input, input_length, uppercase);
+   return output;
+   }
+
+u32bit hex_decode(byte output[],
+                  const char input[],
+                  u32bit input_length,
+                  u32bit& input_consumed,
+                  bool ignore_ws)
+   {
+   /*
+   * Mapping of hex characters to either their binary equivalent
+   * or to an error code.
+   *  If valid hex (0-9 A-F a-f), the value.
+   *  If whitespace, then 0x80
+   *  Otherwise 0xFF
+   * Warning: this table assumes ASCII character encodings
+   */
+
+   static const byte HEX_TO_BIN[256] = {
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x80,
+      0x80, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0x80, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x00, 0x01,
+      0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E,
+      0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x0A, 0x0B, 0x0C,
+      0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+      0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
+
+   byte* out_ptr = output;
+   bool top_nibble = true;
+
+   clear_mem(output, input_length / 2);
+
+   for(u32bit i = 0; i != input_length; ++i)
+      {
+      const byte bin = HEX_TO_BIN[(byte)input[i]];
+
+      if(bin >= 0x10)
+         {
+         if(bin == 0x80 && ignore_ws)
+            continue;
+
+         std::string bad_char(1, input[i]);
+         if(bad_char == "\t")
+           bad_char = "\\t";
+         else if(bad_char == "\n")
+           bad_char = "\\n";
+
+         throw std::invalid_argument(
+           std::string("hex_decode: invalid hex character '") +
+           bad_char + "'");
+         }
+
+      *out_ptr |= bin << (top_nibble*4);
+
+      top_nibble = !top_nibble;
+      if(top_nibble)
+         ++out_ptr;
+      }
+
+   input_consumed = input_length;
+   u32bit written = (out_ptr - output);
+
+   /*
+   * We only got half of a byte at the end; zap the half-written
+   * output and mark it as unread
+   */
+   if(!top_nibble)
+      {
+      *out_ptr = 0;
+      input_consumed -= 1;
+      }
+
+   return written;
+   }
+
+u32bit hex_decode(byte output[],
+                  const char input[],
+                  u32bit input_length,
+                  bool ignore_ws)
+   {
+   u32bit consumed = 0;
+   u32bit written = hex_decode(output, input, input_length,
+                               consumed, ignore_ws);
+
+   if(consumed != input_length)
+      throw std::invalid_argument("hex_decode: input did not have full bytes");
+
+   return written;
+   }
+
+u32bit hex_decode(byte output[],
+                  const std::string& input,
+                  bool ignore_ws)
+   {
+   return hex_decode(output, &input[0], input.length(), ignore_ws);
+   }
+
+SecureVector<byte> hex_decode(const char input[],
+                              u32bit input_length,
+                              bool ignore_ws)
+   {
+   SecureVector<byte> bin(input_length / 2);
+
+   u32bit written = hex_decode(&bin[0],
+                               input,
+                               input_length,
+                               ignore_ws);
+
+   bin.truncate(written);
+   return bin;
+   }
+
+SecureVector<byte> hex_decode(const std::string& input,
+                              bool ignore_ws)
+   {
+   return hex_decode(&input[0], input.size(), ignore_ws);
+   }
+
+}
diff --git a/src/codec/hex/hex.h b/src/codec/hex/hex.h
new file mode 100644
index 000000000..91a743b45
--- /dev/null
+++ b/src/codec/hex/hex.h
@@ -0,0 +1,108 @@
+/*
+* Hex Encoding and Decoding
+* (C) 2010 Jack Lloyd
+*
+* Distributed under the terms of the Botan license
+*/
+
+#ifndef BOTAN_HEX_CODEC_H__
+#define BOTAN_HEX_CODEC_H__
+
+#include <botan/secmem.h>
+#include <string>
+
+namespace Botan {
+
+/**
+* Perform hex encoding
+* @param output an array of at least input_length*2 bytes
+* @param input is some binary data
+* @param input_length length of input in bytes
+* @param uppercase should output be upper or lower case?
+*/
+void BOTAN_DLL hex_encode(char output[],
+                          const byte input[],
+                          u32bit input_length,
+                          bool uppercase = true);
+
+/**
+* Perform hex encoding
+* @param input some input
+* @param input_length length of input in bytes
+* @param uppercase should output be upper or lower case?
+* @return hexadecimal representation of input
+*/
+std::string BOTAN_DLL hex_encode(const byte input[],
+                                 u32bit input_length,
+                                 bool uppercase = true);
+
+/**
+* Perform hex decoding
+* @param output an array of at least input_length/2 bytes
+* @param input some hex input
+* @param input_length length of input in bytes
+* @param input_consumed is an output parameter which says how many
+*        bytes of input were actually consumed. If less than
+*        input_length, then the range input[consumed:length]
+*        should be passed in later along with more input.
+* @param ignore_ws ignore whitespace on input; if false, throw an
+                   exception if whitespace is encountered
+* @return number of bytes written to output
+*/
+u32bit BOTAN_DLL hex_decode(byte output[],
+                            const char input[],
+                            u32bit input_length,
+                            u32bit& input_consumed,
+                            bool ignore_ws = true);
+
+/**
+* Perform hex decoding
+* @param output an array of at least input_length/2 bytes
+* @param input some hex input
+* @param input_length length of input in bytes
+* @param ignore_ws ignore whitespace on input; if false, throw an
+                   exception if whitespace is encountered
+* @return number of bytes written to output
+*/
+u32bit BOTAN_DLL hex_decode(byte output[],
+                            const char input[],
+                            u32bit input_length,
+                            bool ignore_ws = true);
+
+/**
+* Perform hex decoding
+* @param output an array of at least input_length/2 bytes
+* @param input some hex input
+* @param ignore_ws ignore whitespace on input; if false, throw an
+                   exception if whitespace is encountered
+* @return number of bytes written to output
+*/
+u32bit BOTAN_DLL hex_decode(byte output[],
+                            const std::string& input,
+                            bool ignore_ws = true);
+
+/**
+* Perform hex decoding
+* @param input some hex input
+* @param input_length the length of input in bytes
+* @param ignore_ws ignore whitespace on input; if false, throw an
+                   exception if whitespace is encountered
+* @return decoded hex output
+*/
+SecureVector<byte> BOTAN_DLL hex_decode(const char input[],
+                                        u32bit input_length,
+                                        bool ignore_ws = true);
+
+/**
+* Perform hex decoding
+* @param input some hex input
+* @param ignore_ws ignore whitespace on input; if false, throw an
+                   exception if whitespace is encountered
+* @return decoded hex output
+*/
+SecureVector<byte> BOTAN_DLL hex_decode(const std::string& input,
+                                        bool ignore_ws = true);
+
+}
+
+#endif
diff --git a/src/codec/hex/info.txt b/src/codec/hex/info.txt
new file mode 100644
index 000000000..c9eb8fb73
--- /dev/null
+++ b/src/codec/hex/info.txt
@@ -0,0 +1 @@
+define HEX_CODEC