[binutils-gdb] Turn wchar iterator into a class

[Tom Tromey <tromey at sourceware dot org>]

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=cda6c55bd399a8892d62178d4daeb074def909e0

commit cda6c55bd399a8892d62178d4daeb074def909e0
Author: Tom Tromey <tom@tromey.com>
Date:   Thu Sep 22 21:16:53 2016 -0600

    Turn wchar iterator into a class
    
    This changes wchar_iterator from charset.c into a real C++ class, then
    updates the users to use the class.  This lets us remove some cleanups
    in favor of the class' destructor.
    
    2016-10-12  Tom Tromey  <tom@tromey.com>
    
    	* valprint.c (generic_emit_char, count_next_character)
    	(generic_printstr): Update.
    	* charset.c (struct wchar_iterator): Move to charset.h.
    	(wchar_iterator::wchar_iterator): Rename from
    	make_wchar_iterator, turn into a constructor.
    	(wchar_iterator::~wchar_iterator): Rename from
    	do_cleanup_iterator, turn into a destructor.
    	(make_cleanup_wchar_iterator): Remove.
    	(wchar_iterator::iterate): Rename from wchar_iterate.  Remove
    	"iter" argument.  Update.
    	* charset.h: Include <vector>.
    	(class wchar_iterator): New class, from old struct
    	wchar_iterator.
    	(make_wchar_iterator, make_cleanup_wchar_iterator): Don't
    	declare.

Diff:
---
 gdb/ChangeLog  |  18 ++++++++++
 gdb/charset.c  | 110 +++++++++++++++++----------------------------------------
 gdb/charset.h  |  95 ++++++++++++++++++++++++++++---------------------
 gdb/valprint.c |  25 ++++++-------
 4 files changed, 116 insertions(+), 132 deletions(-)

diff --git a/gdb/ChangeLog b/gdb/ChangeLog
index 7507648..5d83d59 100644
--- a/gdb/ChangeLog
+++ b/gdb/ChangeLog
@@ -1,5 +1,23 @@
 2016-10-12  Tom Tromey  <tom@tromey.com>
 
+	* valprint.c (generic_emit_char, count_next_character)
+	(generic_printstr): Update.
+	* charset.c (struct wchar_iterator): Move to charset.h.
+	(wchar_iterator::wchar_iterator): Rename from
+	make_wchar_iterator, turn into a constructor.
+	(wchar_iterator::~wchar_iterator): Rename from
+	do_cleanup_iterator, turn into a destructor.
+	(make_cleanup_wchar_iterator): Remove.
+	(wchar_iterator::iterate): Rename from wchar_iterate.  Remove
+	"iter" argument.  Update.
+	* charset.h: Include <vector>.
+	(class wchar_iterator): New class, from old struct
+	wchar_iterator.
+	(make_wchar_iterator, make_cleanup_wchar_iterator): Don't
+	declare.
+
+2016-10-12  Tom Tromey  <tom@tromey.com>
+
 	* selftest.c: Include <vector>, not "vec.h".
 	(self_test_function_ptr): Remove.
 	(tests): Now a std::vector.
diff --git a/gdb/charset.c b/gdb/charset.c
index abad901..3eb8fac 100644
--- a/gdb/charset.c
+++ b/gdb/charset.c
@@ -589,71 +589,30 @@ convert_between_encodings (const char *from, const char *to,
 
 
 
-/* An iterator that returns host wchar_t's from a target string.  */
-struct wchar_iterator
-{
-  /* The underlying iconv descriptor.  */
-  iconv_t desc;
-
-  /* The input string.  This is updated as convert characters.  */
-  const gdb_byte *input;
-  /* The number of bytes remaining in the input.  */
-  size_t bytes;
-
-  /* The width of an input character.  */
-  size_t width;
-
-  /* The output buffer and its size.  */
-  gdb_wchar_t *out;
-  size_t out_size;
-};
-
 /* Create a new iterator.  */
-struct wchar_iterator *
-make_wchar_iterator (const gdb_byte *input, size_t bytes, 
-		     const char *charset, size_t width)
+wchar_iterator::wchar_iterator (const gdb_byte *input, size_t bytes, 
+				const char *charset, size_t width)
+: m_input (input),
+  m_bytes (bytes),
+  m_width (width),
+  m_out (1)
 {
-  struct wchar_iterator *result;
-  iconv_t desc;
-
-  desc = iconv_open (INTERMEDIATE_ENCODING, charset);
-  if (desc == (iconv_t) -1)
+  m_desc = iconv_open (INTERMEDIATE_ENCODING, charset);
+  if (m_desc == (iconv_t) -1)
     perror_with_name (_("Converting character sets"));
-
-  result = XNEW (struct wchar_iterator);
-  result->desc = desc;
-  result->input = input;
-  result->bytes = bytes;
-  result->width = width;
-
-  result->out = XNEW (gdb_wchar_t);
-  result->out_size = 1;
-
-  return result;
-}
-
-static void
-do_cleanup_iterator (void *p)
-{
-  struct wchar_iterator *iter = (struct wchar_iterator *) p;
-
-  iconv_close (iter->desc);
-  xfree (iter->out);
-  xfree (iter);
 }
 
-struct cleanup *
-make_cleanup_wchar_iterator (struct wchar_iterator *iter)
+wchar_iterator::~wchar_iterator ()
 {
-  return make_cleanup (do_cleanup_iterator, iter);
+  if (m_desc != (iconv_t) -1)
+    iconv_close (m_desc);
 }
 
 int
-wchar_iterate (struct wchar_iterator *iter,
-	       enum wchar_iterate_result *out_result,
-	       gdb_wchar_t **out_chars,
-	       const gdb_byte **ptr,
-	       size_t *len)
+wchar_iterator::iterate (enum wchar_iterate_result *out_result,
+			 gdb_wchar_t **out_chars,
+			 const gdb_byte **ptr,
+			 size_t *len)
 {
   size_t out_request;
 
@@ -663,17 +622,17 @@ wchar_iterate (struct wchar_iterator *iter,
      invalid input sequence -- but we want to reliably report this to
      our caller so it can emit an escape sequence.  */
   out_request = 1;
-  while (iter->bytes > 0)
+  while (m_bytes > 0)
     {
-      ICONV_CONST char *inptr = (ICONV_CONST char *) iter->input;
-      char *outptr = (char *) &iter->out[0];
-      const gdb_byte *orig_inptr = iter->input;
-      size_t orig_in = iter->bytes;
+      ICONV_CONST char *inptr = (ICONV_CONST char *) m_input;
+      char *outptr = (char *) m_out.data ();
+      const gdb_byte *orig_inptr = m_input;
+      size_t orig_in = m_bytes;
       size_t out_avail = out_request * sizeof (gdb_wchar_t);
       size_t num;
-      size_t r = iconv (iter->desc, &inptr, &iter->bytes, &outptr, &out_avail);
+      size_t r = iconv (m_desc, &inptr, &m_bytes, &outptr, &out_avail);
 
-      iter->input = (gdb_byte *) inptr;
+      m_input = (gdb_byte *) inptr;
 
       if (r == (size_t) -1)
 	{
@@ -688,10 +647,10 @@ wchar_iterate (struct wchar_iterator *iter,
 	      /* Otherwise skip the first invalid character, and let
 		 the caller know about it.  */
 	      *out_result = wchar_iterate_invalid;
-	      *ptr = iter->input;
-	      *len = iter->width;
-	      iter->input += iter->width;
-	      iter->bytes -= iter->width;
+	      *ptr = m_input;
+	      *len = m_width;
+	      m_input += m_width;
+	      m_bytes -= m_width;
 	      return 0;
 
 	    case E2BIG:
@@ -702,20 +661,17 @@ wchar_iterate (struct wchar_iterator *iter,
 		break;
 
 	      ++out_request;
-	      if (out_request > iter->out_size)
-		{
-		  iter->out_size = out_request;
-		  iter->out = XRESIZEVEC (gdb_wchar_t, iter->out, out_request);
-		}
+	      if (out_request > m_out.size ())
+		m_out.reserve (out_request);
 	      continue;
 
 	    case EINVAL:
 	      /* Incomplete input sequence.  Let the caller know, and
 		 arrange for future calls to see EOF.  */
 	      *out_result = wchar_iterate_incomplete;
-	      *ptr = iter->input;
-	      *len = iter->bytes;
-	      iter->bytes = 0;
+	      *ptr = m_input;
+	      *len = m_bytes;
+	      m_bytes = 0;
 	      return 0;
 
 	    default:
@@ -727,9 +683,9 @@ wchar_iterate (struct wchar_iterator *iter,
       /* We converted something.  */
       num = out_request - out_avail / sizeof (gdb_wchar_t);
       *out_result = wchar_iterate_ok;
-      *out_chars = iter->out;
+      *out_chars = m_out.data ();
       *ptr = orig_inptr;
-      *len = orig_in - iter->bytes;
+      *len = orig_in - m_bytes;
       return num;
     }
 
diff --git a/gdb/charset.h b/gdb/charset.h
index 559b328..64aa58d 100644
--- a/gdb/charset.h
+++ b/gdb/charset.h
@@ -19,6 +19,8 @@
 #ifndef CHARSET_H
 #define CHARSET_H
 
+#include <vector>
+
 /* If the target program uses a different character set than the host,
    GDB has some support for translating between the two; GDB converts
    characters and strings to the host character set before displaying
@@ -81,54 +83,67 @@ enum wchar_iterate_result
     wchar_iterate_eof
   };
 
-/* Declaration of the opaque wchar iterator type.  */
-struct wchar_iterator;
+/* An iterator that returns host wchar_t's from a target string.  */
+class wchar_iterator
+{
+ public:
 
-/* Create a new character iterator which returns wchar_t's.  INPUT is
-   the input buffer.  BYTES is the number of bytes in the input
-   buffer.  CHARSET is the name of the character set in which INPUT is
-   encoded.  WIDTH is the number of bytes in a base character of
-   CHARSET.
+  /* Create a new character iterator which returns wchar_t's.  INPUT is
+     the input buffer.  BYTES is the number of bytes in the input
+     buffer.  CHARSET is the name of the character set in which INPUT is
+     encoded.  WIDTH is the number of bytes in a base character of
+     CHARSET.
    
-   This function either returns a new character set iterator, or calls
-   error.  The result can be freed using a cleanup; see
-   make_cleanup_wchar_iterator.  */
-struct wchar_iterator *make_wchar_iterator (const gdb_byte *input,
-					    size_t bytes,
-					    const char *charset,
-					    size_t width);
-
-/* Return a new cleanup suitable for destroying the wchar iterator
-   ITER.  */
-struct cleanup *make_cleanup_wchar_iterator (struct wchar_iterator *iter);
-
-/* Perform a single iteration of a wchar_t iterator.
+     This function either returns a new character set iterator, or calls
+     error.  The result can be freed using a cleanup; see
+     make_cleanup_wchar_iterator.  */
+  wchar_iterator (const gdb_byte *input, size_t bytes, const char *charset,
+		  size_t width);
+
+  ~wchar_iterator ();
+
+  /* Perform a single iteration of a wchar_t iterator.
    
-   Returns the number of characters converted.  A negative result
-   means that EOF has been reached.  A positive result indicates the
-   number of valid wchar_ts in the result; *OUT_CHARS is updated to
-   point to the first valid character.
+     Returns the number of characters converted.  A negative result
+     means that EOF has been reached.  A positive result indicates the
+     number of valid wchar_ts in the result; *OUT_CHARS is updated to
+     point to the first valid character.
 
-   In all cases aside from EOF, *PTR is set to point to the first
-   converted target byte.  *LEN is set to the number of bytes
-   converted.
+     In all cases aside from EOF, *PTR is set to point to the first
+     converted target byte.  *LEN is set to the number of bytes
+     converted.
 
-   A zero result means one of several unusual results.  *OUT_RESULT is
-   set to indicate the type of un-ordinary return.
+     A zero result means one of several unusual results.  *OUT_RESULT is
+     set to indicate the type of un-ordinary return.
 
-   wchar_iterate_invalid means that an invalid input character was
-   seen.  The iterator is advanced by WIDTH (the argument to
-   make_wchar_iterator) bytes.
+     wchar_iterate_invalid means that an invalid input character was
+     seen.  The iterator is advanced by WIDTH (the argument to
+     the wchar_iterator constructor) bytes.
 
-   wchar_iterate_incomplete means that an incomplete character was
-   seen at the end of the input sequence.
+     wchar_iterate_incomplete means that an incomplete character was
+     seen at the end of the input sequence.
    
-   wchar_iterate_eof means that all bytes were successfully
-   converted.  The other output arguments are not set.  */
-int wchar_iterate (struct wchar_iterator *iter,
-		   enum wchar_iterate_result *out_result,
-		   gdb_wchar_t **out_chars,
-		   const gdb_byte **ptr, size_t *len);
+     wchar_iterate_eof means that all bytes were successfully
+     converted.  The other output arguments are not set.  */
+  int iterate (enum wchar_iterate_result *out_result, gdb_wchar_t **out_chars,
+	       const gdb_byte **ptr, size_t *len);
+
+ private:
+
+  /* The underlying iconv descriptor.  */
+  iconv_t m_desc;
+
+  /* The input string.  This is updated as we convert characters.  */
+  const gdb_byte *m_input;
+  /* The number of bytes remaining in the input.  */
+  size_t m_bytes;
+
+  /* The width of an input character.  */
+  size_t m_width;
+
+  /* The output buffer.  */
+  std::vector<gdb_wchar_t> m_out;
+};
 
 
 
diff --git a/gdb/valprint.c b/gdb/valprint.c
index 93607e5..ca30a7f 100644
--- a/gdb/valprint.c
+++ b/gdb/valprint.c
@@ -2404,19 +2404,16 @@ generic_emit_char (int c, struct type *type, struct ui_file *stream,
   struct obstack wchar_buf, output;
   struct cleanup *cleanups;
   gdb_byte *buf;
-  struct wchar_iterator *iter;
   int need_escape = 0;
 
   buf = (gdb_byte *) 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);
+  wchar_iterator iter (buf, TYPE_LENGTH (type), encoding, TYPE_LENGTH (type));
 
   /* This holds the printable form of the wchar_t data.  */
   obstack_init (&wchar_buf);
-  make_cleanup_obstack_free (&wchar_buf);
+  cleanups = make_cleanup_obstack_free (&wchar_buf);
 
   while (1)
     {
@@ -2427,7 +2424,7 @@ generic_emit_char (int c, struct type *type, struct ui_file *stream,
       int print_escape = 1;
       enum wchar_iterate_result result;
 
-      num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
+      num_chars = iter.iterate (&result, &chars, &buf, &buflen);
       if (num_chars < 0)
 	break;
       if (num_chars > 0)
@@ -2481,7 +2478,7 @@ generic_emit_char (int c, struct type *type, struct ui_file *stream,
    storing the result in VEC.  */
 
 static int
-count_next_character (struct wchar_iterator *iter,
+count_next_character (wchar_iterator *iter,
 		      VEC (converted_character_d) **vec)
 {
   struct converted_character *current;
@@ -2492,7 +2489,7 @@ count_next_character (struct wchar_iterator *iter,
       gdb_wchar_t *chars;
 
       tmp.num_chars
-	= wchar_iterate (iter, &tmp.result, &chars, &tmp.buf, &tmp.buflen);
+	= iter->iterate (&tmp.result, &chars, &tmp.buf, &tmp.buflen);
       if (tmp.num_chars > 0)
 	{
 	  gdb_assert (tmp.num_chars < MAX_WCHARS);
@@ -2521,8 +2518,7 @@ count_next_character (struct wchar_iterator *iter,
       while (1)
 	{
 	  /* Get the next character.  */
-	  d.num_chars
-	    = wchar_iterate (iter, &d.result, &chars, &d.buf, &d.buflen);
+	  d.num_chars = iter->iterate (&d.result, &chars, &d.buf, &d.buflen);
 
 	  /* If a character was successfully converted, save the character
 	     into the converted character.  */
@@ -2736,7 +2732,6 @@ generic_printstr (struct ui_file *stream, struct type *type,
   int width = TYPE_LENGTH (type);
   struct obstack wchar_buf, output;
   struct cleanup *cleanup;
-  struct wchar_iterator *iter;
   int finished = 0;
   struct converted_character *last;
   VEC (converted_character_d) *converted_chars;
@@ -2771,10 +2766,10 @@ generic_printstr (struct ui_file *stream, struct type *type,
     }
 
   /* 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_iterator iter (string, length * width, encoding, width);
   converted_chars = NULL;
-  make_cleanup (VEC_cleanup (converted_character_d), &converted_chars);
+  cleanup = make_cleanup (VEC_cleanup (converted_character_d),
+			  &converted_chars);
 
   /* Convert characters until the string is over or the maximum
      number of printed characters has been reached.  */
@@ -2786,7 +2781,7 @@ generic_printstr (struct ui_file *stream, struct type *type,
       QUIT;
 
       /* Grab the next character and repeat count.  */
-      r = count_next_character (iter, &converted_chars);
+      r = count_next_character (&iter, &converted_chars);
 
       /* If less than zero, the end of the input string was reached.  */
       if (r < 0)