Correct the Big5-HKSCS converter to preserve low order state bits (bug 25744)

Message ID f4a05c37-d242-bc38-1b12-78175c43d6c6@honermann.net
State Superseded
Headers
Series Correct the Big5-HKSCS converter to preserve low order state bits (bug 25744) |

Commit Message

Tom Honermann April 7, 2020, 5:40 a.m. UTC
  Enclosed is a patch for bug 25744 [1] that 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].

This patch depends on Carlos O'Donell's patch for bug 25734 [2] as 
posted at [3].

The code changes are styled to match how these bits are maintained by 
other 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.

Carlos, assuming you have no objections to this patch, would you be so 
kind as to commit it on my behalf?  Thank you in advance.

ChangeLog:
	Correct Big5-HKSCS to preserve low order state bits (Bug 25744)

	* iconvdata/big5hkscs.c: Modified.
  	* iconvdata/tst-iconv-big5-hkscs-to-2ucs4.c: Modified.

Tom.

[1]: https://sourceware.org/bugzilla/show_bug.cgi?id=25744
[2]: https://sourceware.org/bugzilla/show_bug.cgi?id=25734
[3]: https://sourceware.org/pipermail/libc-alpha/2020-April/112551.html
  

Patch

diff --git a/iconvdata/big5hkscs.c b/iconvdata/big5hkscs.c
index ef325119b1..b4e556be98 100644
--- a/iconvdata/big5hkscs.c
+++ b/iconvdata/big5hkscs.c
@@ -17771,7 +17771,7 @@  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)						      \
 	{								      \
@@ -17780,7 +17780,7 @@  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.  */	      \
@@ -17794,7 +17794,7 @@  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.  */	      \
@@ -17880,7 +17880,7 @@  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;							      \
@@ -17897,7 +17897,7 @@  static struct
       }									      \
     else								      \
       /* Clear the queue and proceed to output the saved character.  */	      \
-      *statep = 0;							      \
+      *statep &= 7;							      \
 									      \
     put32 (outptr, ch);							      \
     outptr += 4;							      \
@@ -17948,7 +17948,7 @@  static struct
 	  }								      \
 	*outptr++ = (ch >> 8) & 0xff;					      \
 	*outptr++ = ch & 0xff;						      \
-	*statep = 0;							      \
+	*statep &= 7;							      \
 	inptr += 4;							      \
 	continue;							      \
 									      \
@@ -17961,7 +17961,7 @@  static struct
 	  }								      \
 	*outptr++ = (lasttwo >> 8) & 0xff;				      \
 	*outptr++ = lasttwo & 0xff;					      \
-	*statep = 0;							      \
+	*statep &= 7;							      \
 	continue;							      \
       }									      \
 									      \
@@ -17998,7 +17998,7 @@  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 8389adebf2..8141722595 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;
 }