Use safe-ctype.h (ISSPACE etc.) in symbol parsing & comparison

This patch avoids depending on the current locale when parsing &
comparing symbol names, by using libiberty's safe-ctype.h uppercase
TOLOWER, ISXDIGIT, etc. macros instead of the standard ctype.h
tolower, isxdigit, etc. macros/functions.

This commit:

 commit b1b60145aedb8adcb0b9dcf43a5ae735c2f03b51
 Author:     Pedro Alves <palves@redhat.com>
 AuthorDate: Tue May 22 17:35:38 2018 +0100

    Support UTF-8 identifiers in C/C++ expressions (PR gdb/22973)

did something similar, except in the expression parser.

This can improve GDB's symbol loading performance significantly.
Currently strcmp_iw_ordered can show up high on profiles (called from
sort_pst_symbols -> std::sort) because of the isspace and tolower
functions.  Hannes mentions seeing it as high as in ~24% of the
profiling samples on Windows
(https://sourceware.org/pipermail/gdb-patches/2020-May/168858.html).

I tested GDB's performance (built with "-g -O2") loading a "-g -O0"
build of gdb.

I ran GDB 10 times like:

	  /bin/time -f %e \
		    ./gdb/gdb --data-directory ./gdb/data-directory -nx \
		    -batch /tmp/gdb-g-O0

Then I computed the mean time.

The baseline mean time was

 gdb    2.515

This patch brings the number down to

 gdb    2.096

Which is an around 16% improvement.

gdb/ChangeLog:
2020-05-23  Pedro Alves  <palves@redhat.com>

	* utils.c: Include "gdbsupport/gdb-safe-ctype.h".
	(parse_escape): Use ISDIGIT instead of isdigit.
	(puts_debug): Use gdb_isprint instead of isprint.
	(fprintf_symbol_filtered): Use ISALNUM instead of isalnum.
	(cp_skip_operator_token, skip_ws, strncmp_iw_with_mode): Use
	ISSPACE instead of isspace.
	(strncmp_iw_with_mode): Use TOLOWER instead of tolower and ISSPACE
	instead of isspace.
	(strcmp_iw_ordered): Use ISSPACE instead of isspace.
	(string_to_core_addr): Use TOLOWER instead of tolower, ISXDIGIT
	instead of isxdigit and ISDIGIT instead of isdigit.

gdbsupport/ChangeLog:
2020-05-23  Pedro Alves  <palves@redhat.com>

	* gdb-safe-ctype.h: New.

1 files changed, 24 insertions, 23 deletions

diff --git a/gdb/utils.c b/gdb/utils.c
index d2290c3..102db28 100644
--- a/gdb/utils.c
+++ b/gdb/utils.c
@@ -74,6 +74,7 @@
 #include "gdbsupport/scope-exit.h"
 #include "gdbarch.h"
 #include "cli-out.h"
+#include "gdbsupport/gdb-safe-ctype.h"
 
 void (*deprecated_error_begin_hook) (void);
 
@@ -1025,7 +1026,7 @@ parse_escape (struct gdbarch *gdbarch, const char **string_ptr)
 	  while (++count < 3)
 	    {
 	      c = (**string_ptr);
-	      if (isdigit (c) && c != '8' && c != '9')
+	      if (ISDIGIT (c) && c != '8' && c != '9')
 		{
 		  (*string_ptr)++;
 		  i *= 8;
@@ -1995,7 +1996,7 @@ puts_debug (char *prefix, char *string, char *suffix)
       switch (ch)
 	{
 	default:
-	  if (isprint (ch))
+	  if (gdb_isprint (ch))
 	    fputc_unfiltered (ch, gdb_stdlog);
 
 	  else
@@ -2316,7 +2317,7 @@ fprintf_symbol_filtered (struct ui_file *stream, const char *name,
 static bool
 valid_identifier_name_char (int ch)
 {
-  return (isalnum (ch) || ch == '_');
+  return (ISALNUM (ch) || ch == '_');
 }
 
 /* Skip to end of token, or to END, whatever comes first.  Input is
@@ -2326,7 +2327,7 @@ static const char *
 cp_skip_operator_token (const char *token, const char *end)
 {
   const char *p = token;
-  while (p != end && !isspace (*p) && *p != '(')
+  while (p != end && !ISSPACE (*p) && *p != '(')
     {
       if (valid_identifier_name_char (*p))
 	{
@@ -2380,9 +2381,9 @@ cp_skip_operator_token (const char *token, const char *end)
 static void
 skip_ws (const char *&string1, const char *&string2, const char *end_str2)
 {
-  while (isspace (*string1))
+  while (ISSPACE (*string1))
     string1++;
-  while (string2 < end_str2 && isspace (*string2))
+  while (string2 < end_str2 && ISSPACE (*string2))
     string2++;
 }
 
@@ -2444,8 +2445,8 @@ strncmp_iw_with_mode (const char *string1, const char *string2,
   while (1)
     {
       if (skip_spaces
-	  || ((isspace (*string1) && !valid_identifier_name_char (*string2))
-	      || (isspace (*string2) && !valid_identifier_name_char (*string1))))
+	  || ((ISSPACE (*string1) && !valid_identifier_name_char (*string2))
+	      || (ISSPACE (*string2) && !valid_identifier_name_char (*string1))))
 	{
 	  skip_ws (string1, string2, end_str2);
 	  skip_spaces = false;
@@ -2478,7 +2479,7 @@ strncmp_iw_with_mode (const char *string1, const char *string2,
 	  if (match_for_lcd != NULL && abi_start != string1)
 	    match_for_lcd->mark_ignored_range (abi_start, string1);
 
-	  while (isspace (*string1))
+	  while (ISSPACE (*string1))
 	    string1++;
 	}
 
@@ -2503,9 +2504,9 @@ strncmp_iw_with_mode (const char *string1, const char *string2,
 	  string1++;
 	  string2++;
 
-	  while (isspace (*string1))
+	  while (ISSPACE (*string1))
 	    string1++;
-	  while (string2 < end_str2 && isspace (*string2))
+	  while (string2 < end_str2 && ISSPACE (*string2))
 	    string2++;
 	  continue;
 	}
@@ -2599,14 +2600,14 @@ strncmp_iw_with_mode (const char *string1, const char *string2,
       if (case_sensitivity == case_sensitive_on && *string1 != *string2)
 	break;
       if (case_sensitivity == case_sensitive_off
-	  && (tolower ((unsigned char) *string1)
-	      != tolower ((unsigned char) *string2)))
+	  && (TOLOWER ((unsigned char) *string1)
+	      != TOLOWER ((unsigned char) *string2)))
 	break;
 
       /* If we see any non-whitespace, non-identifier-name character
 	 (any of "()<>*&" etc.), then skip spaces the next time
 	 around.  */
-      if (!isspace (*string1) && !valid_identifier_name_char (*string1))
+      if (!ISSPACE (*string1) && !valid_identifier_name_char (*string1))
 	skip_spaces = true;
 
       string1++;
@@ -2727,16 +2728,16 @@ strcmp_iw_ordered (const char *string1, const char *string2)
 
       while (*string1 != '\0' && *string2 != '\0')
 	{
-	  while (isspace (*string1))
+	  while (ISSPACE (*string1))
 	    string1++;
-	  while (isspace (*string2))
+	  while (ISSPACE (*string2))
 	    string2++;
 
 	  switch (case_pass)
 	  {
 	    case case_sensitive_off:
-	      c1 = tolower ((unsigned char) *string1);
-	      c2 = tolower ((unsigned char) *string2);
+	      c1 = TOLOWER ((unsigned char) *string1);
+	      c2 = TOLOWER ((unsigned char) *string2);
 	      break;
 	    case case_sensitive_on:
 	      c1 = *string1;
@@ -2924,17 +2925,17 @@ string_to_core_addr (const char *my_string)
 {
   CORE_ADDR addr = 0;
 
-  if (my_string[0] == '0' && tolower (my_string[1]) == 'x')
+  if (my_string[0] == '0' && TOLOWER (my_string[1]) == 'x')
     {
       /* Assume that it is in hex.  */
       int i;
 
       for (i = 2; my_string[i] != '\0'; i++)
 	{
-	  if (isdigit (my_string[i]))
+	  if (ISDIGIT (my_string[i]))
 	    addr = (my_string[i] - '0') + (addr * 16);
-	  else if (isxdigit (my_string[i]))
-	    addr = (tolower (my_string[i]) - 'a' + 0xa) + (addr * 16);
+	  else if (ISXDIGIT (my_string[i]))
+	    addr = (TOLOWER (my_string[i]) - 'a' + 0xa) + (addr * 16);
 	  else
 	    error (_("invalid hex \"%s\""), my_string);
 	}
@@ -2946,7 +2947,7 @@ string_to_core_addr (const char *my_string)
 
       for (i = 0; my_string[i] != '\0'; i++)
 	{
-	  if (isdigit (my_string[i]))
+	  if (ISDIGIT (my_string[i]))
 	    addr = (my_string[i] - '0') + (addr * 10);
 	  else
 	    error (_("invalid decimal \"%s\""), my_string);