libcpp: add function to check XID properties

libcpp/ChangeLog:

	* charset.cc (check_xid_property):new function to check XID_Start and XID_Continue
	* include/cpplib.h (check_xid_property):add enum representing XID properties

Signed-off-by: Raiki Tamura <[email protected]>

Author: tamaroning

libcpp/charset.cc

@@ -1256,6 +1256,42 @@ _cpp_uname2c_uax44_lm2 (const char *name, size_t len, char *canon_name)
   return result;
 }
 
+/* Returns flags representing the XID properties of the given codepoint.  */
+unsigned int
+check_xid_property (cppchar_t c)
+{
+  // fast path for ASCII
+  if (c < 0x80)
+  {
+    if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
+  return XID_START | XID_CONTINUE;
+    if (('0' <= c && c <= '9') || c == '_')
+  return XID_CONTINUE;
+  }
+
+  if (c > UCS_LIMIT)
+    return 0;
+
+  int mn, mx, md;
+  mn = 0;
+  mx = ARRAY_SIZE (ucnranges) - 1;
+  while (mx != mn)
+    {
+      md = (mn + mx) / 2;
+      if (c <= ucnranges[md].end)
+  mx = md;
+      else
+  mn = md + 1;
+    }
+
+  unsigned short flags = ucnranges[mn].flags;
+
+  if (flags & CXX23)
+    return XID_START | XID_CONTINUE;
+  if (flags & NXX23)
+    return XID_CONTINUE;
+  return 0;
+}
 
 /* Returns 1 if C is valid in an identifier, 2 if C is valid except at
    the start of an identifier, and 0 if C is not valid in an

libcpp/include/cpplib.h

@@ -1602,4 +1602,11 @@ bool cpp_input_conversion_is_trivial (const char *input_charset);
 int cpp_check_utf8_bom (const char *data, size_t data_length);
 bool cpp_valid_utf8_p (const char *data, size_t num_bytes);
 
+enum {
+   XID_START = 1,
+   XID_CONTINUE = 2
+};
+
+unsigned int check_xid_property (cppchar_t c);
+
 #endif /* ! LIBCPP_CPPLIB_H */