From 5b6bdbfd3a22fdb155ee9c507a02c1e888eda094 Mon Sep 17 00:00:00 2001
From: Olof hagsand <olof@hagsand.se>
Date: Wed, 20 Feb 2019 15:37:10 +0100
Subject: [PATCH] optimized string lex parsing

---
 lib/src/clixon_yang_parse.l | 43 +++++++++++++++++++++----------------
 lib/src/clixon_yang_parse.y |  6 +++---
 2 files changed, 27 insertions(+), 22 deletions(-)

diff --git a/lib/src/clixon_yang_parse.l b/lib/src/clixon_yang_parse.l
index 91cd4b33..9e0694d8 100644
--- a/lib/src/clixon_yang_parse.l
+++ b/lib/src/clixon_yang_parse.l
@@ -191,14 +191,14 @@ identifier      [A-Za-z_][A-Za-z0-9_\-\.]*
 <KEYWORD>\}               { return *yytext; }
 <KEYWORD>;                { return *yytext; }
 <KEYWORD>.                { clixon_yang_parselval.string = strdup(yytext);
-                             BEGIN(UNKNOWN); return CHAR; }
+                             BEGIN(UNKNOWN); return CHARS; }
 
 <UNKNOWN>:                { return *yytext; }
 <UNKNOWN>;                { BEGIN(KEYWORD); return *yytext; }
 <UNKNOWN>\"               { _YY->yy_lex_string_state =UNKNOWN; BEGIN(STRINGDQ); return *yytext; }
 <UNKNOWN>\{               { BEGIN(KEYWORD); return *yytext; }
 <UNKNOWN>.                { clixon_yang_parselval.string = strdup(yytext);
-                            return CHAR; }
+                            return CHARS; }
 
 <BOOLEAN>true             { clixon_yang_parselval.string = strdup(yytext);
                             return BOOL; }
@@ -211,14 +211,14 @@ identifier      [A-Za-z_][A-Za-z0-9_\-\.]*
 <INTEGER>\-?[0-9][0-9]*   { clixon_yang_parselval.string = strdup(yytext);
                             return INT; }
 <INTEGER>;                { BEGIN(KEYWORD); return *yytext; }
-<INTEGER>\{                { BEGIN(KEYWORD); return *yytext; }
+<INTEGER>\{               { BEGIN(KEYWORD); return *yytext; }
 <INTEGER>.                { return *yytext; }
 
-<STRARG>\{                 { BEGIN(KEYWORD); return *yytext; }
-<STRARG>;                  { BEGIN(KEYWORD); return *yytext; }
-<STRARG>{identifier}       { clixon_yang_parselval.string = strdup(yytext);
-                             return IDENTIFIER;}
-<STRARG>.                  { return *yytext; }
+<STRARG>\{                { BEGIN(KEYWORD); return *yytext; }
+<STRARG>;                 { BEGIN(KEYWORD); return *yytext; }
+<STRARG>{identifier}      { clixon_yang_parselval.string = strdup(yytext);
+                            return IDENTIFIER;}
+<STRARG>.                 { return *yytext; }
 
 <STRING>\{                { BEGIN(KEYWORD); return *yytext; }
 <STRING>;                 { BEGIN(KEYWORD); return *yytext; }
@@ -226,22 +226,27 @@ identifier      [A-Za-z_][A-Za-z0-9_\-\.]*
 <STRING>\'                { _YY->yy_lex_string_state =STRING; BEGIN(STRINGSQ); return SQ; }
 <STRING>\+                { return *yytext; }
 <STRING>.                 { clixon_yang_parselval.string = strdup(yytext);
-                            return CHAR;}
+                            return CHARS;}
 
-<STRINGDQ>\\                { _YY->yy_lex_state = STRINGDQ; BEGIN(ESCAPE); }
-<STRINGDQ>\"                { BEGIN(_YY->yy_lex_string_state); return *yytext; }
-<STRINGDQ>\n                { _YY->yy_linenum++; clixon_yang_parselval.string = strdup(yytext); return CHAR;}
-<STRINGDQ>.                 { clixon_yang_parselval.string = strdup(yytext);
-                              return CHAR;}
+<STRINGDQ>\\              { _YY->yy_lex_state = STRINGDQ; BEGIN(ESCAPE); }
+<STRINGDQ>\"              { BEGIN(_YY->yy_lex_string_state); return *yytext; }
+<STRINGDQ>\n              { _YY->yy_linenum++;
+                            clixon_yang_parselval.string = strdup(yytext);
+                            return CHARS;}
+<STRINGDQ>[^\\"\n]+      { clixon_yang_parselval.string = strdup(yytext);
+                            return CHARS;}
 
-<STRINGSQ>\'                { BEGIN(_YY->yy_lex_string_state); return SQ; }
-<STRINGSQ>\n                { _YY->yy_linenum++; clixon_yang_parselval.string = strdup(yytext); return CHAR;}
-<STRINGSQ>.                 { clixon_yang_parselval.string = strdup(yytext);
-                             return CHAR;}
+<STRINGSQ>\\              { _YY->yy_lex_state = STRINGSQ; BEGIN(ESCAPE); }
+<STRINGSQ>\'              { BEGIN(_YY->yy_lex_string_state); return SQ; }
+<STRINGSQ>\n              { _YY->yy_linenum++;
+                            clixon_yang_parselval.string = strdup(yytext);
+                            return CHARS;}
+<STRINGSQ>[^\\'\n]+       { clixon_yang_parselval.string = strdup(yytext);
+                            return CHARS;}
 
 <ESCAPE>.                 { BEGIN(_YY->yy_lex_state); 
                              clixon_yang_parselval.string = strdup(yytext); 
-                             return CHAR; }
+                             return CHARS; }
 <COMMENT1>[^*\n]*        /* eat anything that's not a '*' */
 <COMMENT1>"*"+[^*/\n]*   /* eat up '*'s not followed by '/'s */
 <COMMENT1>"*"+"/"        BEGIN(_YY->yy_lex_state);
diff --git a/lib/src/clixon_yang_parse.y b/lib/src/clixon_yang_parse.y
index bc80e474..cd8eab7e 100644
--- a/lib/src/clixon_yang_parse.y
+++ b/lib/src/clixon_yang_parse.y
@@ -57,7 +57,7 @@
 
 %token MY_EOF 
 %token SQ           /* Single quote: ' */
-%token <string>   CHAR
+%token <string>   CHARS
 %token <string>   IDENTIFIER
 %token <string>   BOOL
 %token <string>   INT
@@ -1726,14 +1726,14 @@ qstring        : '"' ustring '"'  { $$=$2; clicon_debug(2,"string-> \" ustring \
   ;
 
 /* unquoted string */
-ustring       : ustring CHAR 
+ustring       : ustring CHARS
                      {
 			 int len = strlen($1);
 			 $$ = realloc($1, len+strlen($2) + 1);
 			 sprintf($$+len, "%s", $2); 
 			 free($2);
 		     }
-              | CHAR 
+              | CHARS 
 	             {$$=$1; } 
               ;