From bfad956b34fbee2f6e04584627f5d78390d6305d Mon Sep 17 00:00:00 2001
From: "Philip.Hazel" <Philip.Hazel@gmail.com>
Date: Mon, 3 Sep 2018 15:20:40 +0000
Subject: [PATCH] Treat empty-string-matching repeated conditionals the same as
 ordinary ones when checking for an anchored pattern.

---
 ChangeLog            |  6 +++
 src/pcre2_compile.c  |  2 +-
 testdata/testinput2  | 31 +++++++++++++++
 testdata/testoutput2 | 92 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/ChangeLog b/ChangeLog
index db82939..780f60c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -179,6 +179,12 @@ subpattern was treated as anchored, when it should not have been, since the
 assumed empty second branch cannot be anchored. Demonstrated by test patterns 
 such as /(?(1)^())b/ or /(?(?=^))b/.
 
+40. A repeated conditional subpattern that could match an empty string was 
+always assumed to be unanchored. Now it it checked just like any other
+repeated conditional subpattern, and can be found to be anchored if the minimum 
+quantifier is one or more. I can't see much use for a repeated anchored
+pattern, but the behaviour is now consistent.
+
 
 Version 10.31 12-February-2018
 ------------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 3df55e9..6bb1de3 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -7866,7 +7866,7 @@ do {
 
    /* Condition. If there is no second branch, it can't be anchored. */
 
-   else if (op == OP_COND)
+   else if (op == OP_COND || op == OP_SCOND)
      {
      if (scode[GET(scode,1)] != OP_ALT) return FALSE;
      if (!is_anchored(scode, bracket_map, cb, atomcount, inassert))
diff --git a/testdata/testinput2 b/testdata/testinput2
index c0f4292..fc94b35 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5474,4 +5474,35 @@ a)"xI
 
 /(?(1)^())b/I
 
+/(?(1)^())+b/I,aftertext
+    abc
+
+/(?(1)^()|^)+b/I,aftertext
+    bbc 
+\= Expect no match     
+    abc
+
+/(?(1)^()|^)*b/I,aftertext
+    bbc 
+    abc
+    xbc 
+
+/(?(1)^())+b/I,aftertext
+    abc
+
+/(?(1)^a()|^a)+b/I,aftertext
+    abc 
+\= Expect no match     
+    bbc
+
+/(?(1)^|^(a))+b/I,aftertext
+    abc 
+\= Expect no match     
+    bbc
+
+/(?(1)^a()|^a)*b/I,aftertext
+    abc 
+    bbc
+    xbc 
+
 # End of testinput2
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 6f0dd12..ecf0d80 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -16671,6 +16671,98 @@ Max back reference = 1
 Last code unit = 'b'
 Subject length lower bound = 1
 
+/(?(1)^())+b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Last code unit = 'b'
+Subject length lower bound = 1
+    abc
+ 0: b
+ 0+ c
+
+/(?(1)^()|^)+b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Compile options: <none>
+Overall options: anchored
+First code unit = 'b'
+Subject length lower bound = 1
+    bbc 
+ 0: b
+ 0+ bc
+\= Expect no match     
+    abc
+No match
+
+/(?(1)^()|^)*b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+First code unit = 'b'
+Subject length lower bound = 1
+    bbc 
+ 0: b
+ 0+ bc
+    abc
+ 0: b
+ 0+ c
+    xbc 
+ 0: b
+ 0+ c
+
+/(?(1)^())+b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Last code unit = 'b'
+Subject length lower bound = 1
+    abc
+ 0: b
+ 0+ c
+
+/(?(1)^a()|^a)+b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Compile options: <none>
+Overall options: anchored
+First code unit = 'a'
+Last code unit = 'b'
+Subject length lower bound = 2
+    abc 
+ 0: ab
+ 0+ c
+\= Expect no match     
+    bbc
+No match
+
+/(?(1)^|^(a))+b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Compile options: <none>
+Overall options: anchored
+Last code unit = 'b'
+Subject length lower bound = 1
+    abc 
+ 0: ab
+ 0+ c
+ 1: a
+\= Expect no match     
+    bbc
+No match
+
+/(?(1)^a()|^a)*b/I,aftertext
+Capturing subpattern count = 1
+Max back reference = 1
+Last code unit = 'b'
+Subject length lower bound = 1
+    abc 
+ 0: ab
+ 0+ c
+    bbc
+ 0: b
+ 0+ bc
+    xbc 
+ 0: b
+ 0+ c
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data