Added rule to ecpg lexer to accept "Unicode surrogate pair in extended quoted

string". This is not really needed because the string gets copied to the output
untranslated anyway, but by adding this rule the lexer stays in sync with the
backend lexer.

diff --git a/src/interfaces/ecpg/preproc/pgc.l b/src/interfaces/ecpg/preproc/pgc.l
index b7e4686..f528f21 100644 (file)
--- a/src/interfaces/ecpg/preproc/pgc.l
+++ b/src/interfaces/ecpg/preproc/pgc.l
@@ -146,6 +146,7 @@ xeinside            [^\\']+
 xeescape               [\\][^0-7]
 xeoctesc               [\\][0-7]{1,3}
 xehexesc               [\\]x[0-9A-Fa-f]{1,2}
+xeunicode              [\\](u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})
 
 /* C version of hex number */
 xch                            0[xX][0-9A-Fa-f]*
@@ -505,6 +506,7 @@ cppline                     {space}*#([^i][A-Za-z]*|{if}|{ifdef}|{ifndef}|{import})(.*\\{space})*.
                        }
 <xq,xqc,xn,xus>{xqinside}      { addlit(yytext, yyleng); }
 <xe>{xeinside}         { addlit(yytext, yyleng); }
+<xe>{xeunicode}                { addlit(yytext, yyleng); }
 <xe>{xeescape}         { addlit(yytext, yyleng); }
 <xe>{xeoctesc}         { addlit(yytext, yyleng); }
 <xe>{xehexesc}         { addlit(yytext, yyleng); }