Tidies to get rid of sanitize warnings (mostly about left shifts).

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1762 2f5784b3-3f2a-0410-8824-cb99058d5e15

6 files changed, 22 insertions, 20 deletions

diff --git a/ChangeLog b/ChangeLog
index e5aa0e5..c4b77ce 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -30,6 +30,9 @@ sanitizer complaint (regexec is supposed to be thread safe).
 6. Check the size of the number after (?C as it is read, in order to avoid 
 integer overflow.
 
+7. Tidy up left shifts to avoid sanitize warnings; also fix one NULL deference 
+in pcretest.
+
 
 Version 8.43 23-February-2019
 -----------------------------
diff --git a/pcre_compile.c b/pcre_compile.c
index 1e3d6c3..32e5b91 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -68,7 +68,7 @@ COMPILE_PCREx macro will already be appropriately set. */
 
 /* Macro for setting individual bits in class bitmaps. */
 
-#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7))
+#define SETBIT(a,b) a[(b)/8] |= (1U << ((b)&7))
 
 /* Maximum length value to check against when making sure that the integer that
 holds the compiled pattern length does not overflow. We make it a bit less than
@@ -129,8 +129,8 @@ overrun before it actually does run off the end of the data block. */
 
 /* Private flags added to firstchar and reqchar. */
 
-#define REQ_CASELESS    (1 << 0)        /* Indicates caselessness */
-#define REQ_VARY        (1 << 1)        /* Reqchar followed non-literal item */
+#define REQ_CASELESS    (1U << 0)        /* Indicates caselessness */
+#define REQ_VARY        (1U << 1)        /* Reqchar followed non-literal item */
 /* Negative values for the firstchar and reqchar flags */
 #define REQ_UNSET       (-2)
 #define REQ_NONE        (-1)
@@ -3611,7 +3611,7 @@ for(;;)
       if (chr > 255) break;
       class_bitset = (pcre_uint8 *)
         ((list_ptr == list ? code : base_end) - list_ptr[2]);
-      if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE;
+      if ((class_bitset[chr >> 3] & (1U << (chr & 7))) != 0) return FALSE;
       break;
 
 #if defined SUPPORT_UTF || !defined COMPILE_PCRE8
@@ -7458,7 +7458,7 @@ for (;; ptr++)
               {
               open_capitem *oc;
               recno = GET2(slot, 0);
-              cd->backref_map |= (recno < 32)? (1 << recno) : 1;
+              cd->backref_map |= (recno < 32)? (1U << recno) : 1;
               if (recno > cd->top_backref) cd->top_backref = recno;
 
               /* Check to see if this back reference is recursive, that it, it
@@ -8069,7 +8069,7 @@ for (;; ptr++)
         item_hwm_offset = cd->hwm - cd->start_workspace;
         *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF;
         PUT2INC(code, 0, recno);
-        cd->backref_map |= (recno < 32)? (1 << recno) : 1;
+        cd->backref_map |= (recno < 32)? (1U << recno) : 1;
         if (recno > cd->top_backref) cd->top_backref = recno;
 
         /* Check to see if this back reference is recursive, that it, it
@@ -8682,7 +8682,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
      if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE;
      }
 
@@ -8810,7 +8810,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
      if (!is_startline(scode, new_map, cd, atomcount, inassert)) return FALSE;
      }
 
diff --git a/pcre_jit_compile.c b/pcre_jit_compile.c
index bc5f9c0..4dcf8fc 100644
--- a/pcre_jit_compile.c
+++ b/pcre_jit_compile.c
@@ -3938,10 +3938,10 @@ static sljit_s32 character_to_int32(pcre_uchar chr)
 sljit_s32 value = (sljit_s32)chr;
 #if defined COMPILE_PCRE8
 #define SSE2_COMPARE_TYPE_INDEX 0
-return (value << 24) | (value << 16) | (value << 8) | value;
+return ((unsigned int)value << 24) | ((unsigned int)value << 16) | ((unsigned int)value << 8) | (unsigned int)value;
 #elif defined COMPILE_PCRE16
 #define SSE2_COMPARE_TYPE_INDEX 1
-return (value << 16) | value;
+return ((unsigned int)value << 16) | value;
 #elif defined COMPILE_PCRE32
 #define SSE2_COMPARE_TYPE_INDEX 2
 return value;
@@ -8507,7 +8507,7 @@ if (opcode == OP_ONCE)
   /* We temporarily encode the needs_control_head in the lowest bit.
      Note: on the target architectures of SLJIT the ((x << 1) >> 1) returns
      the same value for small signed numbers (including negative numbers). */
-  BACKTRACK_AS(bracket_backtrack)->u.framesize = (BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
+  BACKTRACK_AS(bracket_backtrack)->u.framesize = ((unsigned int)BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
   }
 return cc + repeat_length;
 }
diff --git a/pcretest.c b/pcretest.c
index f130303..c1ee128 100644
--- a/pcretest.c
+++ b/pcretest.c
@@ -500,7 +500,7 @@ enum {
 #if (defined (SUPPORT_PCRE8) + defined (SUPPORT_PCRE16) + \
      defined (SUPPORT_PCRE32)) >= 2
 
-#define CHAR_SIZE (1 << pcre_mode)
+#define CHAR_SIZE (1U << pcre_mode)
 
 /* There doesn't seem to be an easy way of writing these macros that can cope
 with the 3 pairs of bit sizes plus all three bit sizes. So just handle all the
@@ -4443,7 +4443,7 @@ while (!done)
 
           /* If there is study data, write it. */
 
-          if (extra != NULL)
+          if (extra != NULL && (extra->flags & PCRE_EXTRA_STUDY_DATA) != 0)
             {
             if (fwrite(extra->study_data, 1, true_study_size, f) <
                 true_study_size)
@@ -4735,7 +4735,7 @@ while (!done)
         if (isdigit(*p))    /* Set copy string */
           {
           while(isdigit(*p)) n = n * 10 + *p++ - '0';
-          copystrings |= 1 << n;
+          copystrings |= 1U << n;
           }
         else if (isalnum(*p))
           {
@@ -4798,7 +4798,7 @@ while (!done)
         if (isdigit(*p))
           {
           while(isdigit(*p)) n = n * 10 + *p++ - '0';
-          getstrings |= 1 << n;
+          getstrings |= 1U << n;
           }
         else if (isalnum(*p))
           {
@@ -5335,7 +5335,7 @@ while (!done)
 
         for (i = 0; i < 32; i++)
           {
-          if ((copystrings & (1 << i)) != 0)
+          if ((copystrings & (1U << i)) != 0)
             {
             int rc;
             char copybuffer[256];
@@ -5400,7 +5400,7 @@ while (!done)
 
         for (i = 0; i < 32; i++)
           {
-          if ((getstrings & (1 << i)) != 0)
+          if ((getstrings & (1U << i)) != 0)
             {
             int rc;
             const char *substring;
diff --git a/testdata/testinput2 b/testdata/testinput2
index 3528de1..53c9825 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -1380,7 +1380,7 @@
     1X
     123456\P
 
-//KF>testsavedregex
+//S-KF>testsavedregex
 
 /abc/IS>testsavedregex
 <testsavedregex
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 4ccda27..f5d32d6 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -5614,9 +5614,8 @@ No match
     123456\P
 No match
 
-//KF>testsavedregex
+//S-KF>testsavedregex
 Compiled pattern written to testsavedregex
-Study data written to testsavedregex
 
 /abc/IS>testsavedregex
 Capturing subpattern count = 0