From db1d539d499afd04234f19dd63b2029713261791 Mon Sep 17 00:00:00 2001
From: Johnothan King <johnothanking@protonmail.com>
Date: Thu, 2 Jul 2020 10:40:15 -0700
Subject: [PATCH] Fix ERE repetition expressions in [[ ... =~ ERE{x,y} ]] (#54)

Regular expressions that combine a repetition expression with
a parenthesized sub-expression throw a garbled syntax error:

$ [[ AATAAT =~ (AAT){2} ]]
ksh: syntax error: `~(E)(AAT){2} ]]
:'%Cred%h%Creseksh: syntax error: `~(E)(AAT){2} ]]
:'%Cred%h%Creseksh: syntax' unexpected

The syntax error occurs because ksh is not fully
accounting for '=~' when it runs into a curly bracket.
This fix disables the syntax error when the operator
is '=~' and adds handling for '(str){x}' (to allow for
more than one sub-expression). This bugfix and the
regression tests for it were backported from ksh93v-
2014-12-24-beta.

src/cmd/ksh93/sh/lex.c:
- Do not trigger a syntax error for '{x}' when the operator
  is '=~' and add handling for multiple parentheses when
  combined with '{x}'.

src/cmd/ksh93/tests/bracket.sh:
- Add two tests from ksh93v- to test sub-expressions
  combined with the '{x}' quantifier.
---
 NEWS                           | 3 +++
 src/cmd/ksh93/sh/lex.c         | 8 +++++++-
 src/cmd/ksh93/tests/bracket.sh | 5 +++++
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/NEWS b/NEWS
index 9ab5949a6..bf83cd421 100644
--- a/NEWS
+++ b/NEWS
@@ -8,6 +8,9 @@ Any uppercase BUG_* names are modernish shell bug IDs.
 - 'read -u' will no longer crash with a memory fault when given an out of
   range or negative file descriptor.
 
+- The '=~' operator no longer raises an error if a regular expression
+  combines the '{x}' quantifier with a sub-expression.
+
 2020-06-28:
 
 - Variables created with 'typeset -RF' no longer cause a memory fault
diff --git a/src/cmd/ksh93/sh/lex.c b/src/cmd/ksh93/sh/lex.c
index b6c504daf..916561b57 100644
--- a/src/cmd/ksh93/sh/lex.c
+++ b/src/cmd/ksh93/sh/lex.c
@@ -388,6 +388,12 @@ int sh_lex(Lex_t* lp)
 		switch(n)
 		{
 			case S_BREAK:
+				if(lp->lex.incase>TEST_RE && mode==ST_NORM && c==LPAREN)
+				{
+					pushlevel(lp,RPAREN,mode);
+					mode = ST_NESTED;
+					continue;
+				}
 				fcseek(-LEN);
 				goto breakloop;
 			case S_EOF:
@@ -1163,7 +1169,7 @@ int sh_lex(Lex_t* lp)
 				}
 				if(mode==ST_NONE)
 					return(0);
-				if(c!=n)
+				if(c!=n && lp->lex.incase<TEST_RE)
 				{
 					lp->token = c;
 					sh_syntax(lp);
diff --git a/src/cmd/ksh93/tests/bracket.sh b/src/cmd/ksh93/tests/bracket.sh
index 7447aa5f5..5b7745fe2 100755
--- a/src/cmd/ksh93/tests/bracket.sh
+++ b/src/cmd/ksh93/tests/bracket.sh
@@ -388,5 +388,10 @@ var=$(echo begin; exec >/dev/tty; [ -t 1 ] && test -t 1 && [[ -t 1 ]]) \
 test 123 -eq 123x 2>/dev/null
 [[ $? -ge 2 ]] || err_exit 'test builtin should return value greater than 1 on error'
 
+# ======
+# The '=~' operator should work with curly brackets
+$SHELL -c '[[ AATAAT =~ (AAT){2} ]]' || err_exit '[[ AATAAT =~ (AAT){2} ]] does not match'
+$SHELL -c '[[ AATAATCCCAATAAT =~ (AAT){2}CCC(AAT){2} ]]' || err_exit '[[ AATAATCCCAATAAT =~ (AAT){2}CCC(AAT){2} ]] does not match'
+
 # ======
 exit $((Errors<125?Errors:125))