gdb

	PR fortran/10036:
	* valprint.h (generic_emit_char, generic_printstr): Declare.
	* valprint.c (wchar_printable, append_string_as_wide)
	(print_wchar): Move from c-lang.c.
	(generic_emit_char): New function; mostly taken from c_emit_char.
	(generic_printstr): New function; mostly taken from c_printstr.
	* f-valprint.c (f_val_print) <TYPE_CODE_ARRAY>: Handle strings
	represented as arrays.
	<TYPE_CODE_CHAR>: Treat as TYPE_CODE_INT; recognize as character
	type.
	* f-typeprint.c (f_type_print_base) <TYPE_CODE_CHAR>: Treat
	identically to TYPE_CODE_INT.
	* f-lang.c (f_get_encoding): New function.
	(f_emit_char): Use generic_emit_char.
	(f_printchar): Replace comment.
	(f_printstr): Use generic_printstr.
	* dwarf2read.c (read_base_type) <DW_ATE_unsigned>: Handle Fortran
	"character" types specially.
	<DW_ATE_signed_char, DW_ATE_unsigned_char>: Make TYPE_CODE_CHAR
	for Fortran.
	* c-lang.c (wchar_printable, append_string_as_wide, print_wchar):
	Move to valprint.c
	(c_emit_char): Call generic_emit_char.
	(c_printstr): Call generic_printstr.
gdb/testsuite
	* gdb.fortran/charset.exp: New file.
	* gdb.fortran/charset.f90: New file.

1 files changed, 8 insertions, 404 deletions

diff --git a/gdb/c-lang.c b/gdb/c-lang.c
index 255fabe2bfd..3a35a782057 100644
--- a/gdb/c-lang.c
+++ b/gdb/c-lang.c
@@ -140,123 +140,6 @@ classify_type (struct type *elttype, struct gdbarch *gdbarch,
   return result;
 }
 
-/* Return true if print_wchar can display W without resorting to a
-   numeric escape, false otherwise.  */
-
-static int
-wchar_printable (gdb_wchar_t w)
-{
-  return (gdb_iswprint (w)
-	  || w == LCST ('\a') || w == LCST ('\b')
-	  || w == LCST ('\f') || w == LCST ('\n')
-	  || w == LCST ('\r') || w == LCST ('\t')
-	  || w == LCST ('\v'));
-}
-
-/* A helper function that converts the contents of STRING to wide
-   characters and then appends them to OUTPUT.  */
-
-static void
-append_string_as_wide (const char *string,
-		       struct obstack *output)
-{
-  for (; *string; ++string)
-    {
-      gdb_wchar_t w = gdb_btowc (*string);
-      obstack_grow (output, &w, sizeof (gdb_wchar_t));
-    }
-}
-
-/* Print a wide character W to OUTPUT.  ORIG is a pointer to the
-   original (target) bytes representing the character, ORIG_LEN is the
-   number of valid bytes.  WIDTH is the number of bytes in a base
-   characters of the type.  OUTPUT is an obstack to which wide
-   characters are emitted.  QUOTER is a (narrow) character indicating
-   the style of quotes surrounding the character to be printed.
-   NEED_ESCAPE is an in/out flag which is used to track numeric
-   escapes across calls.  */
-
-static void
-print_wchar (gdb_wint_t w, const gdb_byte *orig,
-	     int orig_len, int width,
-	     enum bfd_endian byte_order,
-	     struct obstack *output,
-	     int quoter, int *need_escapep)
-{
-  int need_escape = *need_escapep;
-
-  *need_escapep = 0;
-  if (gdb_iswprint (w) && (!need_escape || (!gdb_iswdigit (w)
-					    && w != LCST ('8')
-					    && w != LCST ('9'))))
-    {
-      gdb_wchar_t wchar = w;
-
-      if (w == gdb_btowc (quoter) || w == LCST ('\\'))
-	obstack_grow_wstr (output, LCST ("\\"));
-      obstack_grow (output, &wchar, sizeof (gdb_wchar_t));
-    }
-  else
-    {
-      switch (w)
-	{
-	case LCST ('\a'):
-	  obstack_grow_wstr (output, LCST ("\\a"));
-	  break;
-	case LCST ('\b'):
-	  obstack_grow_wstr (output, LCST ("\\b"));
-	  break;
-	case LCST ('\f'):
-	  obstack_grow_wstr (output, LCST ("\\f"));
-	  break;
-	case LCST ('\n'):
-	  obstack_grow_wstr (output, LCST ("\\n"));
-	  break;
-	case LCST ('\r'):
-	  obstack_grow_wstr (output, LCST ("\\r"));
-	  break;
-	case LCST ('\t'):
-	  obstack_grow_wstr (output, LCST ("\\t"));
-	  break;
-	case LCST ('\v'):
-	  obstack_grow_wstr (output, LCST ("\\v"));
-	  break;
-	default:
-	  {
-	    int i;
-
-	    for (i = 0; i + width <= orig_len; i += width)
-	      {
-		char octal[30];
-		ULONGEST value;
-
-		value = extract_unsigned_integer (&orig[i], width,
-						  byte_order);
-		/* If the value fits in 3 octal digits, print it that
-		   way.  Otherwise, print it as a hex escape.  */
-		if (value <= 0777)
-		  sprintf (octal, "\\%.3o", (int) (value & 0777));
-		else
-		  sprintf (octal, "\\x%lx", (long) value);
-		append_string_as_wide (octal, output);
-	      }
-	    /* If we somehow have extra bytes, print them now.  */
-	    while (i < orig_len)
-	      {
-		char octal[5];
-
-		sprintf (octal, "\\%.3o", orig[i] & 0xff);
-		append_string_as_wide (octal, output);
-		++i;
-	      }
-
-	    *need_escapep = 1;
-	  }
-	  break;
-	}
-    }
-}
-
 /* Print the character C on STREAM as part of the contents of a
    literal string whose delimiter is QUOTER.  Note that that format
    for printing characters and strings is language specific.  */
@@ -265,85 +148,10 @@ void
 c_emit_char (int c, struct type *type,
 	     struct ui_file *stream, int quoter)
 {
-  enum bfd_endian byte_order
-    = gdbarch_byte_order (get_type_arch (type));
-  struct obstack wchar_buf, output;
-  struct cleanup *cleanups;
   const char *encoding;
-  gdb_byte *buf;
-  struct wchar_iterator *iter;
-  int need_escape = 0;
 
   classify_type (type, get_type_arch (type), &encoding);
-
-  buf = alloca (TYPE_LENGTH (type));
-  pack_long (buf, type, c);
-
-  iter = make_wchar_iterator (buf, TYPE_LENGTH (type),
-			      encoding, TYPE_LENGTH (type));
-  cleanups = make_cleanup_wchar_iterator (iter);
-
-  /* This holds the printable form of the wchar_t data.  */
-  obstack_init (&wchar_buf);
-  make_cleanup_obstack_free (&wchar_buf);
-
-  while (1)
-    {
-      int num_chars;
-      gdb_wchar_t *chars;
-      const gdb_byte *buf;
-      size_t buflen;
-      int print_escape = 1;
-      enum wchar_iterate_result result;
-
-      num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
-      if (num_chars < 0)
-	break;
-      if (num_chars > 0)
-	{
-	  /* If all characters are printable, print them.  Otherwise,
-	     we're going to have to print an escape sequence.  We
-	     check all characters because we want to print the target
-	     bytes in the escape sequence, and we don't know character
-	     boundaries there.  */
-	  int i;
-
-	  print_escape = 0;
-	  for (i = 0; i < num_chars; ++i)
-	    if (!wchar_printable (chars[i]))
-	      {
-		print_escape = 1;
-		break;
-	      }
-
-	  if (!print_escape)
-	    {
-	      for (i = 0; i < num_chars; ++i)
-		print_wchar (chars[i], buf, buflen,
-			     TYPE_LENGTH (type), byte_order,
-			     &wchar_buf, quoter, &need_escape);
-	    }
-	}
-
-      /* This handles the NUM_CHARS == 0 case as well.  */
-      if (print_escape)
-	print_wchar (gdb_WEOF, buf, buflen, TYPE_LENGTH (type),
-		     byte_order, &wchar_buf, quoter, &need_escape);
-    }
-
-  /* The output in the host encoding.  */
-  obstack_init (&output);
-  make_cleanup_obstack_free (&output);
-
-  convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
-			     obstack_base (&wchar_buf),
-			     obstack_object_size (&wchar_buf),
-			     1, &output, translit_char);
-  obstack_1grow (&output, '\0');
-
-  fputs_filtered (obstack_base (&output), stream);
-
-  do_cleanups (cleanups);
+  generic_emit_char (c, type, stream, quoter, encoding);
 }
 
 void
@@ -385,6 +193,10 @@ c_printstr (struct ui_file *stream, struct type *type,
 	    const char *user_encoding, int force_ellipses,
 	    const struct value_print_options *options)
 {
+  enum c_string_type str_type;
+  const char *type_encoding;
+  const char *encoding;
+
   enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
   unsigned int i;
   unsigned int things_printed = 0;
@@ -393,35 +205,10 @@ c_printstr (struct ui_file *stream, struct type *type,
   int width = TYPE_LENGTH (type);
   struct obstack wchar_buf, output;
   struct cleanup *cleanup;
-  enum c_string_type str_type;
-  const char *type_encoding;
-  const char *encoding;
   struct wchar_iterator *iter;
   int finished = 0;
   int need_escape = 0;
 
-  if (length == -1)
-    {
-      unsigned long current_char = 1;
-
-      for (i = 0; current_char; ++i)
-	{
-	  QUIT;
-	  current_char = extract_unsigned_integer (string + i * width,
-						   width, byte_order);
-	}
-      length = i;
-    }
-
-  /* If the string was not truncated due to `set print elements', and
-     the last byte of it is a null, we don't print that, in
-     traditional C style.  */
-  if (!force_ellipses
-      && length > 0
-      && (extract_unsigned_integer (string + (length - 1) * width,
-				    width, byte_order) == 0))
-    length--;
-
   str_type = (classify_type (type, get_type_arch (type), &type_encoding)
 	      & ~C_CHAR);
   switch (str_type)
@@ -439,193 +226,10 @@ c_printstr (struct ui_file *stream, struct type *type,
       break;
     }
 
-  encoding = (user_encoding && *user_encoding)
-    ? user_encoding : type_encoding;
-
-  if (length == 0)
-    {
-      fputs_filtered ("\"\"", stream);
-      return;
-    }
-
-  /* Arrange to iterate over the characters, in wchar_t form.  */
-  iter = make_wchar_iterator (string, length * width, encoding, width);
-  cleanup = make_cleanup_wchar_iterator (iter);
-
-  /* WCHAR_BUF is the obstack we use to represent the string in
-     wchar_t form.  */
-  obstack_init (&wchar_buf);
-  make_cleanup_obstack_free (&wchar_buf);
-
-  while (!finished && things_printed < options->print_max)
-    {
-      int num_chars;
-      enum wchar_iterate_result result;
-      gdb_wchar_t *chars;
-      const gdb_byte *buf;
-      size_t buflen;
-
-      QUIT;
-
-      if (need_comma)
-	{
-	  obstack_grow_wstr (&wchar_buf, LCST (", "));
-	  need_comma = 0;
-	}
-
-      num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
-      /* We only look at repetitions when we were able to convert a
-	 single character in isolation.  This makes the code simpler
-	 and probably does the sensible thing in the majority of
-	 cases.  */
-      while (num_chars == 1 && things_printed < options->print_max)
-	{
-	  /* Count the number of repetitions.  */
-	  unsigned int reps = 0;
-	  gdb_wchar_t current_char = chars[0];
-	  const gdb_byte *orig_buf = buf;
-	  int orig_len = buflen;
-
-	  if (need_comma)
-	    {
-	      obstack_grow_wstr (&wchar_buf, LCST (", "));
-	      need_comma = 0;
-	    }
-
-	  while (num_chars == 1 && current_char == chars[0])
-	    {
-	      num_chars = wchar_iterate (iter, &result, &chars,
-					 &buf, &buflen);
-	      ++reps;
-	    }
-
-	  /* Emit CURRENT_CHAR according to the repetition count and
-	     options.  */
-	  if (reps > options->repeat_count_threshold)
-	    {
-	      if (in_quotes)
-		{
-		  if (options->inspect_it)
-		    obstack_grow_wstr (&wchar_buf, LCST ("\\\", "));
-		  else
-		    obstack_grow_wstr (&wchar_buf, LCST ("\", "));
-		  in_quotes = 0;
-		}
-	      obstack_grow_wstr (&wchar_buf, LCST ("'"));
-	      need_escape = 0;
-	      print_wchar (current_char, orig_buf, orig_len, width,
-			   byte_order, &wchar_buf, '\'', &need_escape);
-	      obstack_grow_wstr (&wchar_buf, LCST ("'"));
-	      {
-		/* Painful gyrations.  */
-		int j;
-		char *s = xstrprintf (_(" <repeats %u times>"), reps);
-
-		for (j = 0; s[j]; ++j)
-		  {
-		    gdb_wchar_t w = gdb_btowc (s[j]);
-		    obstack_grow (&wchar_buf, &w, sizeof (gdb_wchar_t));
-		  }
-		xfree (s);
-	      }
-	      things_printed += options->repeat_count_threshold;
-	      need_comma = 1;
-	    }
-	  else
-	    {
-	      /* Saw the character one or more times, but fewer than
-		 the repetition threshold.  */
-	      if (!in_quotes)
-		{
-		  if (options->inspect_it)
-		    obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
-		  else
-		    obstack_grow_wstr (&wchar_buf, LCST ("\""));
-		  in_quotes = 1;
-		  need_escape = 0;
-		}
-
-	      while (reps-- > 0)
-		{
-		  print_wchar (current_char, orig_buf,
-			       orig_len, width,
-			       byte_order, &wchar_buf,
-			       '"', &need_escape);
-		  ++things_printed;
-		}
-	    }
-	}
-
-      /* NUM_CHARS and the other outputs from wchar_iterate are valid
-	 here regardless of which branch was taken above.  */
-      if (num_chars < 0)
-	{
-	  /* Hit EOF.  */
-	  finished = 1;
-	  break;
-	}
-
-      switch (result)
-	{
-	case wchar_iterate_invalid:
-	  if (!in_quotes)
-	    {
-	      if (options->inspect_it)
-		obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
-	      else
-		obstack_grow_wstr (&wchar_buf, LCST ("\""));
-	      in_quotes = 1;
-	    }
-	  need_escape = 0;
-	  print_wchar (gdb_WEOF, buf, buflen, width, byte_order,
-		       &wchar_buf, '"', &need_escape);
-	  break;
-
-	case wchar_iterate_incomplete:
-	  if (in_quotes)
-	    {
-	      if (options->inspect_it)
-		obstack_grow_wstr (&wchar_buf, LCST ("\\\","));
-	      else
-		obstack_grow_wstr (&wchar_buf, LCST ("\","));
-	      in_quotes = 0;
-	    }
-	  obstack_grow_wstr (&wchar_buf,
-			     LCST (" <incomplete sequence "));
-	  print_wchar (gdb_WEOF, buf, buflen, width,
-		       byte_order, &wchar_buf,
-		       0, &need_escape);
-	  obstack_grow_wstr (&wchar_buf, LCST (">"));
-	  finished = 1;
-	  break;
-	}
-    }
-
-  /* Terminate the quotes if necessary.  */
-  if (in_quotes)
-    {
-      if (options->inspect_it)
-	obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
-      else
-	obstack_grow_wstr (&wchar_buf, LCST ("\""));
-    }
-
-  if (force_ellipses || !finished)
-    obstack_grow_wstr (&wchar_buf, LCST ("..."));
-
-  /* OUTPUT is where we collect `char's for printing.  */
-  obstack_init (&output);
-  make_cleanup_obstack_free (&output);
-
-  convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
-			     obstack_base (&wchar_buf),
-			     obstack_object_size (&wchar_buf),
-			     1, &output, translit_char);
-  obstack_1grow (&output, '\0');
-
-  fputs_filtered (obstack_base (&output), stream);
+  encoding = (user_encoding && *user_encoding) ? user_encoding : type_encoding;
 
-  do_cleanups (cleanup);
+  generic_printstr (stream, type, string, length, encoding, force_ellipses,
+		    '"', 1, options);
 }
 
 /* Obtain a C string from the inferior storing it in a newly allocated