[1/3] : C++20 P0482R6 and C2X N2653: Fix for bug 25744, mbrtowc with Big5-HKSCS

Message ID 29a48f8e-0c31-072c-ec36-8b62a0e1b430@honermann.net
State Superseded
Headers
Series : C++20 P0482R6 and C2X N2653: support for char8_t, mbrtoc8(), and c8rtomb(). |

Checks

Context Check Description
dj/TryBot-apply_patch success Patch applied to master at the time it was sent

Commit Message

Tom Honermann Feb. 27, 2022, 4:53 p.m. UTC
  This patch for bug 25744 [1] updates the Big5-HKSCS converter to 
properly maintain the lowest 3 bits of the mbstate_t __count data 
member.  This change is necessary to ensure that state is correctly 
preserved when the converter encounters an incomplete multibyte 
character.  More details are available in bug 25744 [1].

The code changes are styled to match how these bits are maintained by 
converters such as iso-2022-jp.c, ibm930.c, and others.

Running 'grep __count' in the 'iconvdata' directory suggests that a 
number of other converters, euc-jisx0213.c for example, also fail to 
preserve these bits in some cases, though it may be that negative 
effects are not observed for those converters.  This patch does not 
attempt to address such issues with other converters.

Tested on Linux x86_64.

Tom.

[1]: Bug 25744
      "mbrtowc with Big5-HKSCS returns 2 instead of 1 when consuming the
      second byte of certain double byte characters"
      https://sourceware.org/bugzilla/show_bug.cgi?id=25744
  

Patch

commit 9580fc4e7fa0ce33c049b0c2d61b98405fdd2ae3
Author: Tom Honermann <tom@honermann.net>
Date:   Wed Jan 5 18:02:24 2022 -0500

    Correct the Big5-HKSCS converter to preserve low order state bits.
    
    BZ: https://sourceware.org/bugzilla/show_bug.cgi?id=25744

diff --git a/iconvdata/big5hkscs.c b/iconvdata/big5hkscs.c
index a28b18a5ec..d12389b2e3 100644
--- a/iconvdata/big5hkscs.c
+++ b/iconvdata/big5hkscs.c
@@ -17769,7 +17769,7 @@  static struct
    the output state to the initial state.  This has to be done during the
    flushing.  */
 #define EMIT_SHIFT_TO_INIT \
-  if (data->__statep->__count != 0)					      \
+  if ((data->__statep->__count >> 3) != 0)				      \
     {									      \
       if (FROM_DIRECTION)						      \
 	{								      \
@@ -17778,7 +17778,7 @@  static struct
 	      /* Write out the last character.  */			      \
 	      *((uint32_t *) outbuf) = data->__statep->__count >> 3;	      \
 	      outbuf += sizeof (uint32_t);				      \
-	      data->__statep->__count = 0;				      \
+	      data->__statep->__count &= 7;				      \
 	    }								      \
 	  else								      \
 	    /* We don't have enough room in the output buffer.  */	      \
@@ -17792,7 +17792,7 @@  static struct
 	      uint32_t lasttwo = data->__statep->__count >> 3;		      \
 	      *outbuf++ = (lasttwo >> 8) & 0xff;			      \
 	      *outbuf++ = lasttwo & 0xff;				      \
-	      data->__statep->__count = 0;				      \
+	      data->__statep->__count &= 7;				      \
 	    }								      \
 	  else								      \
 	    /* We don't have enough room in the output buffer.  */	      \
@@ -17878,7 +17878,7 @@  static struct
 									      \
 		/* Otherwise store only the first character now, and	      \
 		   put the second one into the queue.  */		      \
-		*statep = ch2 << 3;					      \
+		*statep = (ch2 << 3) | (*statep & 7);			      \
 		/* Tell the caller why we terminate the loop.  */	      \
 		result = __GCONV_FULL_OUTPUT;				      \
 		break;							      \
@@ -17895,7 +17895,7 @@  static struct
       }									      \
     else								      \
       /* Clear the queue and proceed to output the saved character.  */	      \
-      *statep = 0;							      \
+      *statep &= 7;							      \
 									      \
     put32 (outptr, ch);							      \
     outptr += 4;							      \
@@ -17946,7 +17946,7 @@  static struct
 	  }								      \
 	*outptr++ = (ch >> 8) & 0xff;					      \
 	*outptr++ = ch & 0xff;						      \
-	*statep = 0;							      \
+	*statep &= 7;							      \
 	inptr += 4;							      \
 	continue;							      \
 									      \
@@ -17959,7 +17959,7 @@  static struct
 	  }								      \
 	*outptr++ = (lasttwo >> 8) & 0xff;				      \
 	*outptr++ = lasttwo & 0xff;					      \
-	*statep = 0;							      \
+	*statep &= 7;							      \
 	continue;							      \
       }									      \
 									      \
@@ -17996,7 +17996,7 @@  static struct
 	   /* Check for possible combining character.  */		      \
 	    if (__glibc_unlikely (ch == 0xca || ch == 0xea))		      \
 	      {								      \
-		*statep = ((cp[0] << 8) | cp[1]) << 3;			      \
+		*statep = (((cp[0] << 8) | cp[1]) << 3) | (*statep & 7);      \
 		inptr += 4;						      \
 		continue;						      \
 	      }								      \
diff --git a/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
index 9601b6c1d9..e1472dc2e2 100644
--- a/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
+++ b/iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c
@@ -128,6 +128,71 @@  check_conversion (struct testdata test)
       printf ("error: Result of third conversion was wrong.\n");
       err++;
     }
+
+  /* Now perform the same test as above consuming one byte at a time.  */
+  mbs = test.input;
+  memset (&st, 0, sizeof (st));
+
+  /* Consume the first byte; expect an incomplete multibyte character.  */
+  ret = mbrtowc (&wc, mbs, 1, &st);
+  if (ret != -2)
+    {
+      printf ("error: First byte conversion returned %zd.\n", ret);
+      err++;
+    }
+  /* Advance past the first consumed byte.  */
+  mbs += 1;
+  /* Consume the second byte; expect the first wchar_t.  */
+  ret = mbrtowc (&wc, mbs, 1, &st);
+  if (ret != 1)
+    {
+      printf ("error: Second byte conversion returned %zd.\n", ret);
+      err++;
+    }
+  /* Advance past the second consumed byte.  */
+  mbs += 1;
+  if (wc != test.expected[0])
+    {
+      printf ("error: Result of first wchar_t conversion was wrong.\n");
+      err++;
+    }
+  /* Consume no bytes; expect the second wchar_t.  */
+  ret = mbrtowc (&wc, mbs, 1, &st);
+  if (ret != 0)
+    {
+      printf ("error: First attempt of third byte conversion returned %zd.\n", ret);
+      err++;
+    }
+  /* Do not advance past the third byte.  */
+  mbs += 0;
+  if (wc != test.expected[1])
+    {
+      printf ("error: Result of second wchar_t conversion was wrong.\n");
+      err++;
+    }
+  /* After the second wchar_t conversion, the converter should be in
+     the initial state since the two input BIG5-HKSCS bytes have been
+     consumed and the two wchar_t's have been output.  */
+  if (mbsinit (&st) == 0)
+    {
+      printf ("error: Converter not in initial state.\n");
+      err++;
+    }
+  /* Consume the third byte; expect the third wchar_t.  */
+  ret = mbrtowc (&wc, mbs, 1, &st);
+  if (ret != 1)
+    {
+      printf ("error: Third byte conversion returned %zd.\n", ret);
+      err++;
+    }
+  /* Advance past the third consumed byte.  */
+  mbs += 1;
+  if (wc != test.expected[2])
+    {
+      printf ("error: Result of third wchar_t conversion was wrong.\n");
+      err++;
+    }
+
   /* Return 0 if we saw no errors.  */
   return err;
 }