From a143014d738758b5558efb73fee9f351cd00cbda Mon Sep 17 00:00:00 2001
From: Guillaume Maudoux <layus.on@gmail.com>
Date: Mon, 1 May 2017 01:07:33 +0200
Subject: lexer: remove catch-all rules hiding real errors

With catch-all rules, we hide potential errors.
It turns out that a4744254 made one cath-all useless. Flex detected that
is was impossible to reach.
The other is more subtle, as it can only trigger on unfinished escapes
in unfinished strings, which only occurs at EOF.
---
 src/libexpr/lexer.l | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

(limited to 'src/libexpr/lexer.l')

diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l
index d4fae2d7da..40ca772580 100644
--- a/src/libexpr/lexer.l
+++ b/src/libexpr/lexer.l
@@ -142,18 +142,26 @@ or          { return OR_KW; }
 \{                           { return '{'; }
 <INSIDE_DOLLAR_CURLY>\{      { PUSH_STATE(INSIDE_DOLLAR_CURLY); return '{'; }
 
-<INITIAL,INSIDE_DOLLAR_CURLY>\"          { PUSH_STATE(STRING); return '"'; }
+<INITIAL,INSIDE_DOLLAR_CURLY>\" {
+                PUSH_STATE(STRING); return '"';
+              }
 <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" |
 <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ {
-              /* It is impossible to match strings ending with '$' with one
-                 regex because trailing contexts are only valid at the end
-                 of a rule. (A sane but undocumented limitation.) */
-              yylval->e = unescapeStr(data->symbols, yytext);
-              return STR;
-            }
+                /* It is impossible to match strings ending with '$' with one
+                   regex because trailing contexts are only valid at the end
+                   of a rule. (A sane but undocumented limitation.) */
+                yylval->e = unescapeStr(data->symbols, yytext);
+                return STR;
+              }
 <STRING>\$\{  { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
-<STRING>\"  { POP_STATE(); return '"'; }
-<STRING>.   return yytext[0]; /* just in case: shouldn't be reached */
+<STRING>\"    { POP_STATE(); return '"'; }
+<STRING>\$|\\|\$\\ {
+                /* This can only occur when we reach EOF, otherwise the above
+                   (...|\$[^\{\"\\]|\\.|\$\\.)+ would have triggered.
+                   This is technically invalid, but we leave the problem to the
+                   parser who fails with exact location. */
+                return STR;
+              }
 
 <INITIAL,INSIDE_DOLLAR_CURLY>\'\'(\ *\n)?     { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
 <IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
@@ -179,7 +187,6 @@ or          { return OR_KW; }
                    yylval->e = new ExprIndStr("'");
                    return IND_STR;
                  }
-<IND_STRING>.    return yytext[0]; /* just in case: shouldn't be reached */
 
 <INITIAL,INSIDE_DOLLAR_CURLY>{
 
-- 
cgit 1.4.1