From bcf460622d869c36f13214a52757433f338eb39a Mon Sep 17 00:00:00 2001
From: ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069>
Date: Fri, 7 Apr 2017 08:46:29 +0000
Subject: [PATCH] Extend auto-anchoring to ignore "never-obeyed" groups at the
 start.

---
 ChangeLog            |  5 +++++
 src/pcre2_compile.c  | 12 ++++++++++++
 testdata/testinput2  | 16 ++++++++++++++++
 testdata/testoutput2 | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 65 insertions(+)

diff --git a/ChangeLog b/ChangeLog
index fe2a2d8..486ee88 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -116,6 +116,11 @@ a message, and abandon the run (this would have detected #13 above).
 20. Applied Jason Hood's patches (slightly modified) to pcre2grep, to implement 
 the --output=text (-O) option and the inbuilt callout echo.
 
+21. Extend auto-anchoring etc. to ignore groups with a zero qualifier and 
+single-branch conditions with a false condition (e.g. DEFINE) at the start of a 
+branch. For example, /(?(DEFINE)...)^A/ and /(...){0}^B/ are now flagged as
+anchored.
+
 
 Version 10.23 14-February-2017
 ------------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 0b6175b..bab1494 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -4164,6 +4164,18 @@ for (;;)
     case OP_CALLOUT_STR:
     code += GET(code, 1 + 2*LINK_SIZE);
     break;
+    
+    case OP_SKIPZERO:
+    code += 2 + GET(code, 2) + LINK_SIZE;
+    break;   
+    
+    case OP_COND:
+    case OP_SCOND:
+    if (code[1+LINK_SIZE] != OP_FALSE ||   /* Not DEFINE */
+        code[GET(code, 1)] != OP_KET)      /* More than one branch */
+      return code;
+    code += GET(code, 1) + 1 + LINK_SIZE;
+    break;    
 
     default:
     return code;
diff --git a/testdata/testinput2 b/testdata/testinput2
index cd1cbfa..c49c26b 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5040,4 +5040,20 @@ a)"xI
 
 #subject -no_jit
 
+# Check auto-anchoring when there is a group that is never obeyed at
+# the start of a branch.
+
+/(?(DEFINE)(a))^bc/I
+
+/(a){0}.*bc/sI
+
+# This should be anchored, as the condition is always false and there is
+# no alternative branch.
+
+/(?(VERSION>=999)yes)^bc/I
+
+# This should not be anchored.
+
+/(?(VERSION>=999)yes|no)^bc/I
+
 # End of testinput2 
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 5251a0e..539f853 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -15576,6 +15576,38 @@ No match
 
 #subject -no_jit
 
+# Check auto-anchoring when there is a group that is never obeyed at
+# the start of a branch.
+
+/(?(DEFINE)(a))^bc/I
+Capturing subpattern count = 1
+Compile options: <none>
+Overall options: anchored
+Subject length lower bound = 2
+
+/(a){0}.*bc/sI
+Capturing subpattern count = 1
+Compile options: dotall
+Overall options: anchored dotall
+Last code unit = 'c'
+Subject length lower bound = 2
+
+# This should be anchored, as the condition is always false and there is
+# no alternative branch.
+
+/(?(VERSION>=999)yes)^bc/I
+Capturing subpattern count = 0
+Compile options: <none>
+Overall options: anchored
+Subject length lower bound = 2
+
+# This should not be anchored.
+
+/(?(VERSION>=999)yes|no)^bc/I
+Capturing subpattern count = 0
+Last code unit = 'c'
+Subject length lower bound = 4
+
 # End of testinput2 
 Error -63: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data