support C/C++ identifiers named with non-ASCII characters

[張俊芝 <zjz@zjz.name>]

[-- Attachment #1: Type: text/plain, Size: 1128 bytes --]

Hello, team.

This patch fixes the bug at
https://sourceware.org/bugzilla/show_bug.cgi?id=22973 .

Here is how to test the patch:

Step 1. If you are using Clang or any other C compilers that have 
implemented
         support for Unicode identifiers, then create a C file with the 
following
         content:

int main(int 參量, char* 參[])
{
   struct 集
   {
     int 數[3];
   } 集 = {100, 200, 300};
   int 序 = 2;
   return 0;
}

Or if you are using GCC, create a C file with the following content as a
workaround(GCC still doesn't actually support Unicode identifiers in 
2018, which
is a pity):

int main(int \u53C3\u91CF, char* \u53C3[])
{
   struct \u96C6
   {
     int \u6578[3];
   } \u96C6 = {100, 200, 300};
   int \u5E8F = 2;
   return 0;
}

Step 2. Compile the C file.

Step 3. Run GDB for the compiled executable, add a breakpoint in "return 0".

Step 4. Run until the breakpoint.

Step 5. Test the following commands to see if they work:
         p 參量
         p 參
         p 集
         p 集.數
         p 集.數[序]

Thanks for your review.

[-- Attachment #2: ChangeLog --]
[-- Type: text/plain, Size: 230 bytes --]

2018-05-20  張俊芝  <zjz@zjz.name>

	* gdb/c-exp.y (is_identifier_separator): New function.
	(lex_one_token): Now recognizes C and C++ Unicode identifiers by using
	is_identifier_separator to determine the boundary of a token.

[-- Attachment #3: diff --]
[-- Type: text/plain, Size: 2948 bytes --]

diff --git a/gdb/c-exp.y b/gdb/c-exp.y
index 5e10d2a3b4..b0dd6c7caf 100644
--- a/gdb/c-exp.y
+++ b/gdb/c-exp.y
@@ -73,6 +73,8 @@ void yyerror (const char *);
 
 static int type_aggregate_p (struct type *);
 
+static bool is_identifier_separator (char);
+
 %}
 
 /* Although the yacc "value" of an expression is not used,
@@ -1718,6 +1720,53 @@ type_aggregate_p (struct type *type)
 	      && TYPE_DECLARED_CLASS (type)));
 }
 
+/* While iterating all the characters in an identifier, an identifier separator
+   is a boundary where we know the iteration is done. */
+
+static bool
+is_identifier_separator (char c)
+{
+  switch (c)
+    {
+    case ' ':
+    case '\t':
+    case '\n':
+    case '\0':
+    case '\'':
+    case '"':
+    case '\\':
+    case '(':
+    case ')':
+    case ',':
+    case '.':
+    case '+':
+    case '-':
+    case '*':
+    case '/':
+    case '|':
+    case '&':
+    case '^':
+    case '~':
+    case '!':
+    case '@':
+    case '[':
+    case ']':
+    /* '<' should not be a token separator, because it can be an open angle
+       bracket followed by a nested template identifier in C++. */
+    case '>':
+    case '?':
+    case ':':
+    case '=':
+    case '{':
+    case '}':
+    case ';':
+      return true;
+    default:
+      break;
+    }
+  return false;
+}
+
 /* Validate a parameter typelist.  */
 
 static void
@@ -1920,7 +1969,7 @@ parse_number (struct parser_state *par_state,
 	 FIXME: This check is wrong; for example it doesn't find overflow
 	 on 0x123456789 when LONGEST is 32 bits.  */
       if (c != 'l' && c != 'u' && n != 0)
-	{	
+	{
 	  if ((unsigned_p && (ULONGEST) prevn >= (ULONGEST) n))
 	    error (_("Numeric constant too large."));
 	}
@@ -2741,16 +2790,13 @@ lex_one_token (struct parser_state *par_state, bool *is_quoted_name)
       }
     }
 
-  if (!(c == '_' || c == '$'
-	|| (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')))
+  if (is_identifier_separator(c))
     /* We must have come across a bad character (e.g. ';').  */
     error (_("Invalid character '%c' in expression."), c);
 
   /* It's a name.  See how long it is.  */
   namelen = 0;
-  for (c = tokstart[namelen];
-       (c == '_' || c == '$' || (c >= '0' && c <= '9')
-	|| (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '<');)
+  for (c = tokstart[namelen]; !is_identifier_separator(c);)
     {
       /* Template parameter lists are part of the name.
 	 FIXME: This mishandles `print $a<4&&$a>3'.  */
@@ -2932,7 +2978,7 @@ classify_name (struct parser_state *par_state, const struct block *block,
 	 filename.  However, if the name was quoted, then it is better
 	 to check for a filename or a block, since this is the only
 	 way the user has of requiring the extension to be used.  */
-      if ((is_a_field_of_this.type == NULL && !is_after_structop) 
+      if ((is_a_field_of_this.type == NULL && !is_after_structop)
 	  || is_quoted_name)
 	{
 	  /* See if it's a file name. */