From fdd94791086e466835ed61640cf31380efd1fbc5 Mon Sep 17 00:00:00 2001
From: Philip Hazel <Philip.Hazel@gmail.com>
Date: Wed, 26 Jan 2022 08:37:18 +0000
Subject: [PATCH] Fix incorrect compiling when [Aa] etc. are quantified

---
 ChangeLog            |  6 ++++++
 src/pcre2_compile.c  | 21 +++++++++++++--------
 testdata/testinput2  |  9 +++++++++
 testdata/testoutput2 | 44 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 72 insertions(+), 8 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 4eb3fa7..f0eab7b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -86,6 +86,12 @@ Clarke PR#72.
 21. A user discovered that the library names in CMakeLists.txt for MSVC 
 debugger (PDB) files were incorrect - perhaps never tried for PCRE2?
 
+22. An item such as [Aa] is optimized into a caseless single character match.
+When this was quantified (e.g. [Aa]{2}) and was also the last literal item in a
+pattern, the optimizing "must be present for a match" character check was not
+being flagged as caseless, causing some matches that should have succeeded to
+fail.
+
 
 Version 10.39 29-October-2021
 -----------------------------
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index fe2bf69..de259c9 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -2115,17 +2115,17 @@ if (c == CHAR_LEFT_CURLY_BRACKET)
     {
     if (ptr >= cb->end_pattern) goto ERROR_RETURN;
     c = *ptr++;
-    while (c == '_' || c == '-' || isspace(c)) 
+    while (c == '_' || c == '-' || isspace(c))
       {
       if (ptr >= cb->end_pattern) goto ERROR_RETURN;
       c = *ptr++;
-      } 
+      }
     if (c == CHAR_NUL) goto ERROR_RETURN;
     if (c == CHAR_RIGHT_CURLY_BRACKET) break;
     name[i] = tolower(c);
     if ((c == ':' || c == '=') && vptr == NULL) vptr = name + i;
     }
-     
+
   if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN;
   name[i] = 0;
   }
@@ -2159,16 +2159,16 @@ another property can be diagnosed. */
 if (vptr != NULL)
   {
   int offset = 0;
-  PCRE2_UCHAR sname[8]; 
+  PCRE2_UCHAR sname[8];
 
   *vptr = 0;   /* Terminate property name */
   if (PRIV(strcmp_c8)(name, STRING_bidiclass) == 0 ||
       PRIV(strcmp_c8)(name, STRING_bc) == 0)
     {
     offset = 4;
-    sname[0] = CHAR_b; 
+    sname[0] = CHAR_b;
     sname[1] = CHAR_i;  /* There is no strcpy_c8 function */
-    sname[2] = CHAR_d;  
+    sname[2] = CHAR_d;
     sname[3] = CHAR_i;
     }
 
@@ -7023,14 +7023,19 @@ for (;; pptr++)
 #endif  /* MAYBE_UTF_MULTI */
 
       /* Handle the case of a single code unit - either with no UTF support, or
-      with UTF disabled, or for a single-code-unit UTF character. */
+      with UTF disabled, or for a single-code-unit UTF character. In the latter
+      case, for a repeated positive match, get the caseless flag for the
+      required code unit from the previous character, because a class like [Aa]
+      sets a caseless A but by now the req_caseopt flag has been reset. */
+
         {
         mcbuffer[0] = code[-1];
         mclength = 1;
         if (op_previous <= OP_CHARI && repeat_min > 1)
           {
           reqcu = mcbuffer[0];
-          reqcuflags = req_caseopt | cb->req_varyopt;
+          reqcuflags = cb->req_varyopt;
+          if (op_previous == OP_CHARI) reqcuflags |= REQ_CASELESS;
           }
         }
       goto OUTPUT_SINGLE_REPEAT;  /* Code shared with single character types */
diff --git a/testdata/testinput2 b/testdata/testinput2
index 849bc2e..d37d8f3 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -5923,4 +5923,13 @@ a)"xI
 
 # --------- 
 
+/[Aa]{2}/BI
+    aabcd
+
+/A{2}/iBI
+    aabcd
+
+/[Aa]{2,3}/BI
+    aabcd
+
 # End of testinput2
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index ce10f2b..ce090f8 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -17702,6 +17702,50 @@ Failed: error -51: NULL argument passed with non-zero length
 
 # --------- 
 
+/[Aa]{2}/BI
+------------------------------------------------------------------
+        Bra
+     /i A{2}
+        Ket
+        End
+------------------------------------------------------------------
+Capture group count = 0
+First code unit = 'A' (caseless)
+Last code unit = 'A' (caseless)
+Subject length lower bound = 2
+    aabcd
+ 0: aa
+
+/A{2}/iBI
+------------------------------------------------------------------
+        Bra
+     /i A{2}
+        Ket
+        End
+------------------------------------------------------------------
+Capture group count = 0
+Options: caseless
+First code unit = 'A' (caseless)
+Last code unit = 'A' (caseless)
+Subject length lower bound = 2
+    aabcd
+ 0: aa
+
+/[Aa]{2,3}/BI
+------------------------------------------------------------------
+        Bra
+     /i A{2}
+     /i A?+
+        Ket
+        End
+------------------------------------------------------------------
+Capture group count = 0
+First code unit = 'A' (caseless)
+Last code unit = 'A' (caseless)
+Subject length lower bound = 2
+    aabcd
+ 0: aa
+
 # End of testinput2
 Error -70: PCRE2_ERROR_BADDATA (unknown error number)
 Error -62: bad serialized data