提交: e6470192110d4890abe9761ed67d0ce7fd6060c9 - ffftp (git)

FFFTPのソースコードです。

Commit MetaInfo

• 修訂: e6470192110d4890abe9761ed67d0ce7fd6060c9 (tree)
• 時間: 2011-10-22 00:05:09
• 作者: s_kawamoto <s_kawamoto@user...>
• Commiter: s_kawamoto

Log Message

Add support for encoding multi-byte domain name to Punycode.

Change Summary

• modified: FFFTP.vc90.vcproj
• modified: FFFTP.vcproj
• modified: FFFTP_Eng_Release/FFFTP.exe
• modified: FFFTP_English.vc90.vcproj
• modified: FFFTP_English.vcproj
• modified: Release/FFFTP.exe
• add: punycode.c
• add: punycode.h
• modified: socket.c

差異

--- a/FFFTP.vc90.vcproj
+++ b/FFFTP.vc90.vcproj
@@ -311,6 +311,10 @@
 				>
 			</File>
 			<File
+				RelativePath=".\punycode.c"
+				>
+			</File>
+			<File
 				RelativePath=".\protectprocess.c"
 				>
 			</File>

--- a/FFFTP.vcproj
+++ b/FFFTP.vcproj
@@ -312,6 +312,10 @@
 				>
 			</File>
 			<File
+				RelativePath=".\punycode.c"
+				>
+			</File>
+			<File
 				RelativePath=".\protectprocess.c"
 				>
 			</File>

Binary files a/FFFTP_Eng_Release/FFFTP.exe and b/FFFTP_Eng_Release/FFFTP.exe differ

--- a/FFFTP_English.vc90.vcproj
+++ b/FFFTP_English.vc90.vcproj
@@ -311,6 +311,10 @@
 				>
 			</File>
 			<File
+				RelativePath=".\punycode.c"
+				>
+			</File>
+			<File
 				RelativePath=".\protectprocess.c"
 				>
 			</File>

--- a/FFFTP_English.vcproj
+++ b/FFFTP_English.vcproj
@@ -312,6 +312,10 @@
 				>
 			</File>
 			<File
+				RelativePath=".\punycode.c"
+				>
+			</File>
+			<File
 				RelativePath=".\protectprocess.c"
 				>
 			</File>

Binary files a/Release/FFFTP.exe and b/Release/FFFTP.exe differ

--- /dev/null
+++ b/punycode.c
@@ -0,0 +1,346 @@
+/*
+punycode.c from RFC 3492
+http://www.nicemice.net/idn/
+Adam M. Costello
+http://www.nicemice.net/amc/
+
+This is ANSI C code (C89) implementing Punycode (RFC 3492).
+
+*/
+
+
+/************************************************************/
+/* Public interface (would normally go in its own .h file): */
+
+#include <limits.h>
+
+enum punycode_status {
+  punycode_success,
+  punycode_bad_input,   /* Input is invalid.                       */
+  punycode_big_output,  /* Output would exceed the space provided. */
+  punycode_overflow     /* Input needs wider integers to process.  */
+};
+
+#if UINT_MAX >= (1 << 26) - 1
+typedef unsigned int punycode_uint;
+#else
+typedef unsigned long punycode_uint;
+#endif
+
+enum punycode_status punycode_encode(
+  punycode_uint input_length,
+  const punycode_uint input[],
+  const unsigned char case_flags[],
+  punycode_uint *output_length,
+  char output[] );
+
+    /* punycode_encode() converts Unicode to Punycode.  The input     */
+    /* is represented as an array of Unicode code points (not code    */
+    /* units; surrogate pairs are not allowed), and the output        */
+    /* will be represented as an array of ASCII code points.  The     */
+    /* output string is *not* null-terminated; it will contain        */
+    /* zeros if and only if the input contains zeros.  (Of course     */
+    /* the caller can leave room for a terminator and add one if      */
+    /* needed.)  The input_length is the number of code points in     */
+    /* the input.  The output_length is an in/out argument: the       */
+    /* caller passes in the maximum number of code points that it     */
+    /* can receive, and on successful return it will contain the      */
+    /* number of code points actually output.  The case_flags array   */
+    /* holds input_length boolean values, where nonzero suggests that */
+    /* the corresponding Unicode character be forced to uppercase     */
+    /* after being decoded (if possible), and zero suggests that      */
+    /* it be forced to lowercase (if possible).  ASCII code points    */
+    /* are encoded literally, except that ASCII letters are forced    */
+    /* to uppercase or lowercase according to the corresponding       */
+    /* uppercase flags.  If case_flags is a null pointer then ASCII   */
+    /* letters are left as they are, and other code points are        */
+    /* treated as if their uppercase flags were zero.  The return     */
+    /* value can be any of the punycode_status values defined above   */
+    /* except punycode_bad_input; if not punycode_success, then       */
+    /* output_size and output might contain garbage.                  */
+
+enum punycode_status punycode_decode(
+  punycode_uint input_length,
+  const char input[],
+  punycode_uint *output_length,
+  punycode_uint output[],
+  unsigned char case_flags[] );
+
+    /* punycode_decode() converts Punycode to Unicode.  The input is  */
+    /* represented as an array of ASCII code points, and the output   */
+    /* will be represented as an array of Unicode code points.  The   */
+    /* input_length is the number of code points in the input.  The   */
+    /* output_length is an in/out argument: the caller passes in      */
+    /* the maximum number of code points that it can receive, and     */
+    /* on successful return it will contain the actual number of      */
+    /* code points output.  The case_flags array needs room for at    */
+    /* least output_length values, or it can be a null pointer if the */
+    /* case information is not needed.  A nonzero flag suggests that  */
+    /* the corresponding Unicode character be forced to uppercase     */
+    /* by the caller (if possible), while zero suggests that it be    */
+    /* forced to lowercase (if possible).  ASCII code points are      */
+    /* output already in the proper case, but their flags will be set */
+    /* appropriately so that applying the flags would be harmless.    */
+    /* The return value can be any of the punycode_status values      */
+    /* defined above; if not punycode_success, then output_length,    */
+    /* output, and case_flags might contain garbage.  On success, the */
+    /* decoder will never need to write an output_length greater than */
+    /* input_length, because of how the encoding is defined.          */
+
+/**********************************************************/
+/* Implementation (would normally go in its own .c file): */
+
+#include <string.h>
+
+/*** Bootstring parameters for Punycode ***/
+
+enum { base = 36, tmin = 1, tmax = 26, skew = 38, damp = 700,
+       initial_bias = 72, initial_n = 0x80, delimiter = 0x2D };
+
+/* basic(cp) tests whether cp is a basic code point: */
+#define basic(cp) ((punycode_uint)(cp) < 0x80)
+
+/* delim(cp) tests whether cp is a delimiter: */
+#define delim(cp) ((cp) == delimiter)
+
+/* decode_digit(cp) returns the numeric value of a basic code */
+/* point (for use in representing integers) in the range 0 to */
+/* base-1, or base if cp is does not represent a value.       */
+
+static punycode_uint decode_digit(punycode_uint cp)
+{
+  return  cp - 48 < 10 ? cp - 22 :  cp - 65 < 26 ? cp - 65 :
+          cp - 97 < 26 ? cp - 97 :  base;
+}
+
+/* encode_digit(d,flag) returns the basic code point whose value      */
+/* (when used for representing integers) is d, which needs to be in   */
+/* the range 0 to base-1.  The lowercase form is used unless flag is  */
+/* nonzero, in which case the uppercase form is used.  The behavior   */
+/* is undefined if flag is nonzero and digit d has no uppercase form. */
+
+static char encode_digit(punycode_uint d, int flag)
+{
+  return d + 22 + 75 * (d < 26) - ((flag != 0) << 5);
+  /*  0..25 map to ASCII a..z or A..Z */
+  /* 26..35 map to ASCII 0..9         */
+}
+
+/* flagged(bcp) tests whether a basic code point is flagged */
+/* (uppercase).  The behavior is undefined if bcp is not a  */
+/* basic code point.                                        */
+
+#define flagged(bcp) ((punycode_uint)(bcp) - 65 < 26)
+
+/* encode_basic(bcp,flag) forces a basic code point to lowercase */
+/* if flag is zero, uppercase if flag is nonzero, and returns    */
+/* the resulting code point.  The code point is unchanged if it  */
+/* is caseless.  The behavior is undefined if bcp is not a basic */
+/* code point.                                                   */
+
+static char encode_basic(punycode_uint bcp, int flag)
+{
+  bcp -= (bcp - 97 < 26) << 5;
+  return bcp + ((!flag && (bcp - 65 < 26)) << 5);
+}
+
+/*** Platform-specific constants ***/
+
+/* maxint is the maximum value of a punycode_uint variable: */
+static const punycode_uint maxint = -1;
+/* Because maxint is unsigned, -1 becomes the maximum value. */
+
+/*** Bias adaptation function ***/
+
+static punycode_uint adapt(
+  punycode_uint delta, punycode_uint numpoints, int firsttime )
+{
+  punycode_uint k;
+
+  delta = firsttime ? delta / damp : delta >> 1;
+  /* delta >> 1 is a faster way of doing delta / 2 */
+  delta += delta / numpoints;
+
+  for (k = 0;  delta > ((base - tmin) * tmax) / 2;  k += base) {
+    delta /= base - tmin;
+  }
+
+  return k + (base - tmin + 1) * delta / (delta + skew);
+}
+
+/*** Main encode function ***/
+
+enum punycode_status punycode_encode(
+  punycode_uint input_length,
+  const punycode_uint input[],
+  const unsigned char case_flags[],
+  punycode_uint *output_length,
+  char output[] )
+{
+  punycode_uint n, delta, h, b, out, max_out, bias, j, m, q, k, t;
+
+  /* Initialize the state: */
+
+  n = initial_n;
+  delta = out = 0;
+  max_out = *output_length;
+  bias = initial_bias;
+
+  /* Handle the basic code points: */
+
+  for (j = 0;  j < input_length;  ++j) {
+    if (basic(input[j])) {
+      if (max_out - out < 2) return punycode_big_output;
+      output[out++] =
+        case_flags ?  encode_basic(input[j], case_flags[j]) : input[j];
+    }
+    /* else if (input[j] < n) return punycode_bad_input; */
+    /* (not needed for Punycode with unsigned code points) */
+  }
+
+  h = b = out;
+
+  /* h is the number of code points that have been handled, b is the  */
+  /* number of basic code points, and out is the number of characters */
+  /* that have been output.                                           */
+
+  if (b > 0) output[out++] = delimiter;
+
+  /* Main encoding loop: */
+
+  while (h < input_length) {
+    /* All non-basic code points < n have been     */
+    /* handled already.  Find the next larger one: */
+
+    for (m = maxint, j = 0;  j < input_length;  ++j) {
+      /* if (basic(input[j])) continue; */
+      /* (not needed for Punycode) */
+      if (input[j] >= n && input[j] < m) m = input[j];
+    }
+
+    /* Increase delta enough to advance the decoder's    */
+    /* <n,i> state to <m,0>, but guard against overflow: */
+
+    if (m - n > (maxint - delta) / (h + 1)) return punycode_overflow;
+    delta += (m - n) * (h + 1);
+    n = m;
+
+    for (j = 0;  j < input_length;  ++j) {
+      /* Punycode does not need to check whether input[j] is basic: */
+      if (input[j] < n /* || basic(input[j]) */ ) {
+        if (++delta == 0) return punycode_overflow;
+      }
+
+      if (input[j] == n) {
+        /* Represent delta as a generalized variable-length integer: */
+
+        for (q = delta, k = base;  ;  k += base) {
+          if (out >= max_out) return punycode_big_output;
+          t = k <= bias /* + tmin */ ? tmin :     /* +tmin not needed */
+              k >= bias + tmax ? tmax : k - bias;
+          if (q < t) break;
+          output[out++] = encode_digit(t + (q - t) % (base - t), 0);
+          q = (q - t) / (base - t);
+        }
+
+        output[out++] = encode_digit(q, case_flags && case_flags[j]);
+        bias = adapt(delta, h + 1, h == b);
+        delta = 0;
+        ++h;
+      }
+    }
+
+    ++delta, ++n;
+  }
+
+  *output_length = out;
+  return punycode_success;
+}
+
+/*** Main decode function ***/
+
+enum punycode_status punycode_decode(
+  punycode_uint input_length,
+  const char input[],
+  punycode_uint *output_length,
+  punycode_uint output[],
+  unsigned char case_flags[] )
+{
+  punycode_uint n, out, i, max_out, bias,
+                 b, j, in, oldi, w, k, digit, t;
+
+  /* Initialize the state: */
+
+  n = initial_n;
+  out = i = 0;
+  max_out = *output_length;
+  bias = initial_bias;
+
+  /* Handle the basic code points:  Let b be the number of input code */
+  /* points before the last delimiter, or 0 if there is none, then    */
+  /* copy the first b code points to the output.                      */
+
+  for (b = j = 0;  j < input_length;  ++j) if (delim(input[j])) b = j;
+  if (b > max_out) return punycode_big_output;
+
+  for (j = 0;  j < b;  ++j) {
+    if (case_flags) case_flags[out] = flagged(input[j]);
+    if (!basic(input[j])) return punycode_bad_input;
+    output[out++] = input[j];
+  }
+
+  /* Main decoding loop:  Start just after the last delimiter if any  */
+  /* basic code points were copied; start at the beginning otherwise. */
+
+  for (in = b > 0 ? b + 1 : 0;  in < input_length;  ++out) {
+
+    /* in is the index of the next character to be consumed, and */
+    /* out is the number of code points in the output array.     */
+
+    /* Decode a generalized variable-length integer into delta,  */
+    /* which gets added to i.  The overflow checking is easier   */
+    /* if we increase i as we go, then subtract off its starting */
+    /* value at the end to obtain delta.                         */
+
+    for (oldi = i, w = 1, k = base;  ;  k += base) {
+      if (in >= input_length) return punycode_bad_input;
+      digit = decode_digit(input[in++]);
+      if (digit >= base) return punycode_bad_input;
+      if (digit > (maxint - i) / w) return punycode_overflow;
+      i += digit * w;
+      t = k <= bias /* + tmin */ ? tmin :     /* +tmin not needed */
+          k >= bias + tmax ? tmax : k - bias;
+      if (digit < t) break;
+      if (w > maxint / (base - t)) return punycode_overflow;
+      w *= (base - t);
+    }
+
+    bias = adapt(i - oldi, out + 1, oldi == 0);
+
+    /* i was supposed to wrap around from out+1 to 0,   */
+    /* incrementing n each time, so we'll fix that now: */
+
+    if (i / (out + 1) > maxint - n) return punycode_overflow;
+    n += i / (out + 1);
+    i %= (out + 1);
+
+    /* Insert n at position i of the output: */
+
+    /* not needed for Punycode: */
+    /* if (decode_digit(n) <= base) return punycode_invalid_input; */
+    if (out >= max_out) return punycode_big_output;
+
+    if (case_flags) {
+      memmove(case_flags + i + 1, case_flags + i, out - i);
+      /* Case of last character determines uppercase flag: */
+      case_flags[i] = flagged(input[in - 1]);
+    }
+
+    memmove(output + i + 1, output + i, (out - i) * sizeof *output);
+    output[i++] = n;
+  }
+
+  *output_length = out;
+  return punycode_success;
+}
+

--- /dev/null
+++ b/punycode.h
@@ -0,0 +1,89 @@
+/*
+punycode.c from RFC 3492
+http://www.nicemice.net/idn/
+Adam M. Costello
+http://www.nicemice.net/amc/
+
+This is ANSI C code (C89) implementing Punycode (RFC 3492).
+
+*/
+
+
+/************************************************************/
+/* Public interface (would normally go in its own .h file): */
+
+#include <limits.h>
+
+enum punycode_status {
+  punycode_success,
+  punycode_bad_input,   /* Input is invalid.                       */
+  punycode_big_output,  /* Output would exceed the space provided. */
+  punycode_overflow     /* Input needs wider integers to process.  */
+};
+
+#if UINT_MAX >= (1 << 26) - 1
+typedef unsigned int punycode_uint;
+#else
+typedef unsigned long punycode_uint;
+#endif
+
+enum punycode_status punycode_encode(
+  punycode_uint input_length,
+  const punycode_uint input[],
+  const unsigned char case_flags[],
+  punycode_uint *output_length,
+  char output[] );
+
+    /* punycode_encode() converts Unicode to Punycode.  The input     */
+    /* is represented as an array of Unicode code points (not code    */
+    /* units; surrogate pairs are not allowed), and the output        */
+    /* will be represented as an array of ASCII code points.  The     */
+    /* output string is *not* null-terminated; it will contain        */
+    /* zeros if and only if the input contains zeros.  (Of course     */
+    /* the caller can leave room for a terminator and add one if      */
+    /* needed.)  The input_length is the number of code points in     */
+    /* the input.  The output_length is an in/out argument: the       */
+    /* caller passes in the maximum number of code points that it     */
+    /* can receive, and on successful return it will contain the      */
+    /* number of code points actually output.  The case_flags array   */
+    /* holds input_length boolean values, where nonzero suggests that */
+    /* the corresponding Unicode character be forced to uppercase     */
+    /* after being decoded (if possible), and zero suggests that      */
+    /* it be forced to lowercase (if possible).  ASCII code points    */
+    /* are encoded literally, except that ASCII letters are forced    */
+    /* to uppercase or lowercase according to the corresponding       */
+    /* uppercase flags.  If case_flags is a null pointer then ASCII   */
+    /* letters are left as they are, and other code points are        */
+    /* treated as if their uppercase flags were zero.  The return     */
+    /* value can be any of the punycode_status values defined above   */
+    /* except punycode_bad_input; if not punycode_success, then       */
+    /* output_size and output might contain garbage.                  */
+
+enum punycode_status punycode_decode(
+  punycode_uint input_length,
+  const char input[],
+  punycode_uint *output_length,
+  punycode_uint output[],
+  unsigned char case_flags[] );
+
+    /* punycode_decode() converts Punycode to Unicode.  The input is  */
+    /* represented as an array of ASCII code points, and the output   */
+    /* will be represented as an array of Unicode code points.  The   */
+    /* input_length is the number of code points in the input.  The   */
+    /* output_length is an in/out argument: the caller passes in      */
+    /* the maximum number of code points that it can receive, and     */
+    /* on successful return it will contain the actual number of      */
+    /* code points output.  The case_flags array needs room for at    */
+    /* least output_length values, or it can be a null pointer if the */
+    /* case information is not needed.  A nonzero flag suggests that  */
+    /* the corresponding Unicode character be forced to uppercase     */
+    /* by the caller (if possible), while zero suggests that it be    */
+    /* forced to lowercase (if possible).  ASCII code points are      */
+    /* output already in the proper case, but their flags will be set */
+    /* appropriately so that applying the flags would be harmless.    */
+    /* The return value can be any of the punycode_status values      */
+    /* defined above; if not punycode_success, then output_length,    */
+    /* output, and case_flags might contain garbage.  On success, the */
+    /* decoder will never need to write an output_length greater than */
+    /* input_length, because of how the encoding is defined.          */
+

--- a/socket.c
+++ b/socket.c
@@ -38,6 +38,8 @@
 
 #include "common.h"
 #include "resource.h"
+// UTF-8対応
+#include "punycode.h"
 
 #define USE_THIS	1
 #define DBG_MSG		0
@@ -92,6 +94,8 @@ static int RegistAsyncTable(SOCKET s);
 static int RegistAsyncTableDbase(HANDLE Async);
 static int UnRegistAsyncTable(SOCKET s);
 static int UnRegistAsyncTableDbase(HANDLE Async);
+// UTF-8対応
+static HANDLE WSAAsyncGetHostByNameM(HWND hWnd, u_int wMsg, const char * name, char * buf, int buflen);
 
 
 /*===== 外部参照 =====*/
@@ -655,7 +659,9 @@ struct hostent *do_gethostbyname(const char *Name, char *Buf, int Len, int *Canc
 	Ret = NULL;
 	*CancelCheckWork = NO;
 
-	hAsync = WSAAsyncGetHostByName(hWndSocket, WM_ASYNC_DBASE, Name, Buf, Len);
+	// UTF-8対応
+//	hAsync = WSAAsyncGetHostByName(hWndSocket, WM_ASYNC_DBASE, Name, Buf, Len);
+	hAsync = WSAAsyncGetHostByNameM(hWndSocket, WM_ASYNC_DBASE, Name, Buf, Len);
 	if(hAsync != NULL)
 	{
 		RegistAsyncTableDbase(hAsync);
@@ -1159,3 +1165,124 @@ int CheckClosedAndReconnect(void)
 
 
 
+// UTF-8対応
+
+static BOOL ConvertStringToPunycode(LPSTR Output, DWORD Count, LPCSTR Input)
+{
+	BOOL bResult;
+	punycode_uint* pUnicode;
+	punycode_uint* p;
+	BOOL bNeeded;
+	LPCSTR InputString;
+	punycode_uint Length;
+	punycode_uint OutputLength;
+	bResult = FALSE;
+	if(pUnicode = malloc(sizeof(punycode_uint) * strlen(Input)))
+	{
+		p = pUnicode;
+		bNeeded = FALSE;
+		InputString = Input;
+		Length = 0;
+		while(*InputString != '\0')
+		{
+			*p = 0;
+			if((*InputString & 0x80) == 0x00)
+				*p |= (punycode_uint)*InputString & 0x7f;
+			else if((*InputString & 0xe0) == 0xc0)
+				*p |= (punycode_uint)*InputString & 0x1f;
+			else if((*InputString & 0xf0) == 0xe0)
+				*p |= (punycode_uint)*InputString & 0x0f;
+			else if((*InputString & 0xf8) == 0xf0)
+				*p |= (punycode_uint)*InputString & 0x07;
+			else if((*InputString & 0xfc) == 0xf8)
+				*p |= (punycode_uint)*InputString & 0x03;
+			else if((*InputString & 0xfe) == 0xfc)
+				*p |= (punycode_uint)*InputString & 0x01;
+			InputString++;
+			while((*InputString & 0xc0) == 0x80)
+			{
+				*p = *p << 6;
+				*p |= (punycode_uint)*InputString & 0x3f;
+				InputString++;
+			}
+			if(*p >= 0x80)
+				bNeeded = TRUE;
+			p++;
+			Length++;
+		}
+		if(bNeeded)
+		{
+			if(Count >= strlen("xn--") + 1)
+			{
+				strcpy(Output, "xn--");
+				OutputLength = Count - strlen("xn--");
+				if(punycode_encode(Length, pUnicode, NULL, (punycode_uint*)&OutputLength, Output + strlen("xn--")) == punycode_success)
+				{
+					Output[strlen("xn--") + OutputLength] = '\0';
+					bResult = TRUE;
+				}
+			}
+		}
+		free(pUnicode);
+	}
+	if(!bResult)
+	{
+		if(Count >= strlen(Input) + 1)
+		{
+			strcpy(Output, Input);
+			bResult = TRUE;
+		}
+	}
+	return bResult;
+}
+
+static BOOL ConvertNameToPunycode(LPSTR Output, LPCSTR Input)
+{
+	BOOL bResult;
+	DWORD Length;
+	char* pm0;
+	char* pm1;
+	char* p;
+	char* pNext;
+	bResult = FALSE;
+	Length = strlen(Input);
+	if(pm0 = AllocateStringM(Length + 1))
+	{
+		if(pm1 = AllocateStringM(Length * 4 + 1))
+		{
+			strcpy(pm0, Input);
+			p = pm0;
+			while(p)
+			{
+				if(pNext = strchr(p, '.'))
+				{
+					*pNext = '\0';
+					pNext++;
+				}
+				if(ConvertStringToPunycode(pm1, Length * 4, p))
+					strcat(Output, pm1);
+				if(pNext)
+					strcat(Output, ".");
+				p = pNext;
+			}
+			bResult = TRUE;
+			FreeDuplicatedString(pm1);
+		}
+		FreeDuplicatedString(pm0);
+	}
+	return bResult;
+}
+
+static HANDLE WSAAsyncGetHostByNameM(HWND hWnd, u_int wMsg, const char * name, char * buf, int buflen)
+{
+	HANDLE r = NULL;
+	char* pa0 = NULL;
+	if(pa0 = AllocateStringA(strlen(name) * 4))
+	{
+		if(ConvertNameToPunycode(pa0, name))
+			r = WSAAsyncGetHostByName(hWnd, wMsg, pa0, buf, buflen);
+	}
+	FreeDuplicatedString(pa0);
+	return r;
+}
+