Merge branch Generalize S_parse_ident' into blead

This series of commits documents, and generalizes this function so that
it can be called in more circumstances; the final commit calls it from
one such place, as a demonstration.

This includes adding a flag to it that allows code to be moved from
S_scan_ident to this function, and then called from a second place,
eliminating near-duplication.

The goal is to centralize to here the sort of handling of names, like
identifiers, so changes can be made in just one place, and we can get
rid of the other places which have slightly different rules from each
other.

Author: khwilliamson

embed.fnc

@@ -6142,8 +6142,7 @@ S	|char * |force_version	|NN char *s				\
 				|int guessing
 S	|char * |force_word	|NN char *start 			\
 				|int token				\
-				|int check_keyword			\
-				|int allow_pack
+				|U32 flags
 RS	|SV *	|get_and_check_backslash_N_name_wrapper 		\
 				|SPTR const char *s			\
 				|EPTRQ const char * const e
@@ -6177,12 +6176,17 @@ So	|SV *	|new_constant	|NULLOK const char *s			\
 				|NULLOK const char *type		\
 				|STRLEN typelen 			\
 				|NULLOK const char **error_msg
-S	|void	|parse_ident	|NN char **s				\
+S	|char * |parse_ident	|SPTR const char *s			\
+				|EPTRQ const char * const s_end 	\
 				|SPTR char **d				\
-				|EPTRQ char * const e			\
-				|int allow_package			\
+				|EPTR char * const e			\
+				|bool is_utf8				\
+				|U32 flags
+S	|char * |parse_ident_no_copy					\
+				|SPTR const char *s			\
+				|EPTR const char * const s_end		\
 				|bool is_utf8				\
-				|bool check_dollar
+				|U32 flags
 S	|int	|pending_ident
 RS	|char * |scan_const	|NN char *start
 RS	|char * |scan_formline	|NN char *s

embed.h

@@ -1680,7 +1680,7 @@
 #     define force_next(a)                      S_force_next(aTHX_ a)
 #     define force_strict_version(a)            S_force_strict_version(aTHX_ a)
 #     define force_version(a,b)                 S_force_version(aTHX_ a,b)
-#     define force_word(a,b,c,d)                S_force_word(aTHX_ a,b,c,d)
+#     define force_word(a,b,c)                  S_force_word(aTHX_ a,b,c)
 #     define get_and_check_backslash_N_name_wrapper(a,b) S_get_and_check_backslash_N_name_wrapper(aTHX_ a,b)
 #     define incline(a,b)                       S_incline(aTHX_ a,b)
 #     define intuit_method(a,b,c)               S_intuit_method(aTHX_ a,b,c)
@@ -1689,6 +1689,7 @@
 #     define lop(a,b,c,d)                       S_lop(aTHX_ a,b,c,d)
 #     define missingterm(a,b)                   S_missingterm(aTHX_ a,b)
 #     define parse_ident(a,b,c,d,e,f)           S_parse_ident(aTHX_ a,b,c,d,e,f)
+#     define parse_ident_no_copy(a,b,c,d)       S_parse_ident_no_copy(aTHX_ a,b,c,d)
 #     define pending_ident()                    S_pending_ident(aTHX)
 #     define scan_const(a)                      S_scan_const(aTHX_ a)
 #     define scan_formline(a)                   S_scan_formline(aTHX_ a)

parser.h

@@ -10,6 +10,7 @@
  */
 
 #define YYEMPTY		(-2)
+#define PERL_IDENTIFIER_LENGTH  (256 * MAX_UNICODE_UTF8_BYTES)
 
 typedef struct {
     YYSTYPE val;    /* semantic value */
@@ -112,7 +113,7 @@ typedef struct yy_parser {
     U8		lex_fakeeof;	/* precedence at which to fake EOF */
     U8		lex_flags;
     COP		*saved_curcop;	/* the previous PL_curcop */
-    char	tokenbuf[ 256 * MAX_UNICODE_UTF8_BYTES ];
+    char	tokenbuf[ PERL_IDENTIFIER_LENGTH ];
     line_t	herelines;	/* number of lines in here-doc */
     line_t	preambling;	/* line # when processing $ENV{PERL5DB} */