Changeset 15697ff

Timestamp:

Sep 11, 2017, 5:11:40 PM (6 years ago)

Author:

Peter A. Buhr <pabuhr@…>

Branches:

ADT, aaron-thesis, arm-eh, ast-experimental, cleanup-dtors, deferred_resn, demangler, enum, forall-pointer-decay, jacob/cs343-translation, jenkins-sandbox, master, new-ast, new-ast-unique-expr, new-env, no_list, persistent-indexer, pthread-emulation, qualifiedEnum, resolv-new, with_gc

Children:

7b1d5ec

Parents:

f4b77f2

Message:

change processing of concatenated (juxtaposed) string and string encodings

File:

• src/Parser/parser.yy (modified) (5 diffs)

src/Parser/parser.yy

@@ -10 +10 @@
 // Created On       : Sat Sep  1 20:22:55 2001
 // Last Modified By : Peter A. Buhr
-// Last Modified On : Sun Sep 10 10:07:10 2017
-// Update Count     : 2752
+// Last Modified On : Mon Sep 11 08:22:25 2017
+// Update Count     : 2783
 //
 
@@ -43 +43 @@
 #define YYDEBUG_LEXER_TEXT (yylval)                                             // lexer loads this up each time
 #define YYDEBUG 1                                                                               // get the pretty debugging code to compile
+#define YYERROR_VERBOSE
 
 #undef __GNUC_MINOR__
@@ -62 +63 @@
 stack< LinkageSpec::Spec > linkageStack;
 
-void appendStr( string *to, string *from ) {
-        // "abc" "def" "ghi" => "abcdefghi", remove new text from quotes and insert before last quote in old string.
-        to->insert( to->length() - 1, from->substr( 1, from->length() - 2 ) );
+bool appendStr( string & to, string & from ) {
+        // 1. Multiple strings are concatenated into a single string but not combined internally. The reason is that
+        //    "\x12" "3" is treated as 2 characters versus 3 because "escape sequences are converted into single members of
+        //    the execution character set just prior to adjacent string literal concatenation" (C11, Section 6.4.5-8). It is
+        //    easier to let the C compiler handle this case.
+        //
+        // 2. String encodings are transformed into canonical form (one encoding at start) so the encoding can be found
+        //    without searching the string, e.g.: "abc" L"def" L"ghi" => L"abc" "def" "ghi". Multiple encodings must match,
+        //    i.e., u"a" U"b" L"c" is disallowed.
+
+        if ( from[0] != '"' ) {                                                         // encoding ?
+                if ( to[0] != '"' ) {                                                   // encoding ?
+                        if ( to[0] != from[0] ) {                                       // different encodings ?
+                                yyerror( "non-matching string encodings for string-literal concatenation" );
+                                return false;                                                   // parse error, must call YYERROR in action
+                        } // if
+                } else {
+                        to = from[0] + to;                                                      // move encoding to start
+                } // if
+                from.erase( 0, 1 );                                                             // remove 2nd encoding
+        } // if
+        to += " " + from;                                                                       // concatenated into single string
+        return true;
 } // appendStr
 
@@ -88 +109 @@
 bool forall = false;                                                                    // aggregate have one or more forall qualifiers ?
 %}
+
+%define parse.error verbose
 
 // Types declaration
@@ -391 +414 @@
         | string_literal_list STRINGliteral
                 {
-                        appendStr( $1, $2 );                                            // append 2nd juxtaposed string to 1st
+                        if ( ! appendStr( *$1, *$2 ) ) YYERROR;         // append 2nd juxtaposed string to 1st
                         delete $2;                                                                      // allocated by lexer
                         $$ = $1;                                                                        // conversion from tok to str