Merge branch 'merge-pcre' into 10.1

pcre/AUTHORS

@@ -8,7 +8,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2019 University of Cambridge
+Copyright (c) 1997-2020 University of Cambridge
 All rights reserved
 
 
@@ -19,7 +19,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2010-2019 Zoltan Herczeg
+Copyright(c) 2010-2020 Zoltan Herczeg
 All rights reserved.
 
 
@@ -30,7 +30,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2009-2019 Zoltan Herczeg
+Copyright(c) 2009-2020 Zoltan Herczeg
 All rights reserved.
 
 

pcre/ChangeLog

@@ -5,6 +5,35 @@ Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All
 development is happening in the PCRE2 10.xx series.
 
 
+Version 8.44 12 February-2020
+-----------------------------
+
+1. Setting --enable-jit=auto for an out-of-tree build failed because the
+source directory wasn't in the search path for AC_TRY_COMPILE always. Patch
+from Ross Burton.
+
+2. Applied a patch from Michael Shigorin to fix 8.43 build on e2k arch
+with lcc compiler (EDG frontend based); the problem it fixes is:
+
+  lcc: "pcrecpp.cc", line 74: error: declaration aliased to undefined entity
+       "_ZN7pcrecpp2RE6no_argE" [-Werror]
+
+3. Change 2 for 8.43 omitted (*LF) from the list of start-of-pattern items. Now
+added.
+
+4. Fix ARMv5 JIT improper handling of labels right after a constant pool.
+
+5. Small patch to pcreposix.c to set the erroroffset field to -1 immediately
+after a successful compile, instead of at the start of matching to avoid a
+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
 -----------------------------
 

pcre/LICENCE

@@ -25,7 +25,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2019 University of Cambridge
+Copyright (c) 1997-2020 University of Cambridge
 All rights reserved.
 
 
@@ -36,7 +36,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Email domain:     freemail.hu
 
-Copyright(c) 2010-2019 Zoltan Herczeg
+Copyright(c) 2010-2020 Zoltan Herczeg
 All rights reserved.
 
 
@@ -47,7 +47,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Email domain:     freemail.hu
 
-Copyright(c) 2009-2019 Zoltan Herczeg
+Copyright(c) 2009-2020 Zoltan Herczeg
 All rights reserved.
 
 

pcre/NEWS

@@ -5,6 +5,12 @@ Note that this library (now called PCRE1) is now being maintained for bug fixes
 only. New projects are advised to use the new PCRE2 libraries.
 
 
+Release 8.44 12-February-2020
+-----------------------------
+
+This is a bug-fix release.
+
+
 Release 8.43 23-February-2019
 -----------------------------
 

pcre/README

@@ -13,9 +13,10 @@ libraries.
 The latest release of PCRE1 is always available in three alternative formats
 from:
 
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.gz
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.bz2
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.zip
+
 
 There is a mailing list for discussion about the development of PCRE at
 pcre-dev@exim.org. You can access the archives and subscribe or manage your
@@ -999,4 +1000,4 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
 Philip Hazel
 Email local part: ph10
 Email domain: cam.ac.uk
-Last updated: 10 February 2015
+Last updated: 12 February 2020

pcre/configure.ac

@@ -9,19 +9,19 @@ dnl The PCRE_PRERELEASE feature is for identifying release candidates. It might
 dnl be defined as -RC2, for example. For real releases, it should be empty.
 
 m4_define(pcre_major, [8])
-m4_define(pcre_minor, [43])
+m4_define(pcre_minor, [44])
 m4_define(pcre_prerelease, [])
-m4_define(pcre_date, [2019-02-23])
+m4_define(pcre_date, [2020-02-12])
 
 # NOTE: The CMakeLists.txt file searches for the above variables in the first
 # 50 lines of this file. Please update that if the variables above are moved.
 
 # Libtool shared library interface versions (current:revision:age)
-m4_define(libpcre_version, [3:11:2])
-m4_define(libpcre16_version, [2:11:2])
-m4_define(libpcre32_version, [0:11:0])
-m4_define(libpcreposix_version, [0:6:0])
-m4_define(libpcrecpp_version, [0:1:0])
+m4_define(libpcre_version, [3:12:2])
+m4_define(libpcre16_version, [2:12:2])
+m4_define(libpcre32_version, [0:12:0])
+m4_define(libpcreposix_version, [0:7:0])
+m4_define(libpcrecpp_version, [0:2:0])
 
 AC_PREREQ(2.57)
 AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre)
@@ -159,12 +159,15 @@ AC_ARG_ENABLE(jit,
 
 if test "$enable_jit" = "auto"; then
   AC_LANG(C)
+  SAVE_CPPFLAGS=$CPPFLAGS
+  CPPFLAGS=-I$srcdir
   AC_COMPILE_IFELSE([AC_LANG_SOURCE([[
   #define SLJIT_CONFIG_AUTO 1
   #include "sljit/sljitConfigInternal.h"
   #if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED)
   #error unsupported
   #endif]])], enable_jit=yes, enable_jit=no)
+  CPPFLAGS=$SAVE_CPPFLAGS
 fi
 
 # Handle --disable-pcregrep-jit (enabled by default)

pcre/doc/html/README.txt

@@ -13,9 +13,10 @@ libraries.
 The latest release of PCRE1 is always available in three alternative formats
 from:
 
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2
-  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.gz
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.bz2
+  https://ftp.pcre.org/pub/pcre/pcre-x.xx.tar.zip
+
 
 There is a mailing list for discussion about the development of PCRE at
 pcre-dev@exim.org. You can access the archives and subscribe or manage your
@@ -999,4 +1000,4 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx.
 Philip Hazel
 Email local part: ph10
 Email domain: cam.ac.uk
-Last updated: 10 February 2015
+Last updated: 12 February 2020

pcre/doc/html/pcre.html

@@ -143,7 +143,7 @@ performance.
 One way of guarding against this possibility is to use the
 <b>pcre_fullinfo()</b> function to check the compiled pattern's options for UTF.
 Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at
-compile time. This causes an compile time error if a pattern contains a
+compile time. This causes a compile time error if a pattern contains a
 UTF-setting sequence.
 </P>
 <P>

pcre/doc/html/pcreapi.html

@@ -1246,7 +1246,7 @@ the following negative numbers:
   PCRE_ERROR_BADOPTION      the value of <i>what</i> was invalid
   PCRE_ERROR_UNSET          the requested field is not set
 </pre>
-The "magic number" is placed at the start of each compiled pattern as an simple
+The "magic number" is placed at the start of each compiled pattern as a simple
 check against passing an arbitrary memory pointer. The endianness error can
 occur if a compiled pattern is saved and reloaded on a different host. Here is
 a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled
@@ -1318,7 +1318,7 @@ returned. For anchored patterns, -2 is returned.
 </pre>
 Return the value of the first data unit (non-UTF character) of any matched
 string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
-otherwise return 0. The fourth argument should point to an <b>uint_t</b>
+otherwise return 0. The fourth argument should point to a <b>uint_t</b>
 variable.
 </P>
 <P>
@@ -1577,7 +1577,7 @@ returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
 </pre>
 Return the value of the rightmost literal data unit that must exist in any
 matched string, other than at its start, if such a value has been recorded. The
-fourth argument should point to an <b>uint32_t</b> variable. If there is no such
+fourth argument should point to a <b>uint32_t</b> variable. If there is no such
 value, 0 is returned.
 </P>
 <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>

pcre/doc/html/pcretest.html

@@ -99,23 +99,21 @@ the 16-bit library, or <b>pcre32_xx</b> when using the 32-bit library".
 <br><a name="SEC4" href="#TOC1">COMMAND LINE OPTIONS</a><br>
 <P>
 <b>-8</b>
-If both the 8-bit library has been built, this option causes the 8-bit library
-to be used (which is the default); if the 8-bit library has not been built,
-this option causes an error.
+If the 8-bit library has been built, this option causes it to be used (this is
+the default). If the 8-bit library has not been built, this option causes an
+error.
 </P>
 <P>
 <b>-16</b>
-If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this
-option causes the 16-bit library to be used. If only the 16-bit library has been
-built, this is the default (so has no effect). If only the 8-bit or the 32-bit
-library has been built, this option causes an error.
+If the 16-bit library has been built, this option causes it to be used. If only
+the 16-bit library has been built, this is the default. If the 16-bit library
+has not been built, this option causes an error.
 </P>
 <P>
 <b>-32</b>
-If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this
-option causes the 32-bit library to be used. If only the 32-bit library has been
-built, this is the default (so has no effect). If only the 8-bit or the 16-bit
-library has been built, this option causes an error.
+If the 32-bit library has been built, this option causes it to be used. If only
+the 32-bit library has been built, this is the default. If the 32-bit library
+has not been built, this option causes an error.
 </P>
 <P>
 <b>-b</b>
@@ -1154,9 +1152,9 @@ Cambridge CB2 3QH, England.
 </P>
 <br><a name="SEC17" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 23 February 2017
+Last updated: 10 February 2020
 <br>
-Copyright &copy; 1997-2017 University of Cambridge.
+Copyright &copy; 1997-2020 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE index page</a>.

pcre/doc/pcre-config.txt

@@ -16,8 +16,8 @@ DESCRIPTION
 
        pcre-config  returns  the configuration of the installed PCRE libraries
        and the options required to compile a program to use them. Some of  the
-       options  apply  only  to  the  8-bit,  or  16-bit, or 32-bit libraries,
-       respectively, and are not available if only one of those libraries  has
+       options  apply  only  to the 8-bit, or 16-bit, or 32-bit libraries, re-
+       spectively, and are not available if only one of  those  libraries  has
        been built. If an unavailable option is encountered, the "usage" infor-
        mation is output.
 
@@ -36,37 +36,37 @@ OPTIONS
        --version Writes the version number of the installed PCRE libraries  to
                  the standard output.
 
-       --libs    Writes  to  the  standard  output  the  command  line options
-                 required to link with the 8-bit PCRE library (-lpcre on  many
+       --libs    Writes  to  the  standard output the command line options re-
+                 quired to link with the 8-bit PCRE library  (-lpcre  on  many
                  systems).
 
-       --libs16  Writes  to  the  standard  output  the  command  line options
-                 required to link with the 16-bit PCRE  library  (-lpcre16  on
-                 many systems).
+       --libs16  Writes  to  the  standard output the command line options re-
+                 quired to link with the 16-bit PCRE library (-lpcre16 on many
+                 systems).
 
-       --libs32  Writes  to  the  standard  output  the  command  line options
-                 required to link with the 32-bit PCRE  library  (-lpcre32  on
-                 many systems).
+       --libs32  Writes  to  the  standard output the command line options re-
+                 quired to link with the 32-bit PCRE library (-lpcre32 on many
+                 systems).
 
        --libs-cpp
-                 Writes  to  the  standard  output  the  command  line options
-                 required to link with PCRE's C++ wrapper  library  (-lpcrecpp
+                 Writes  to  the  standard output the command line options re-
+                 quired to link with PCRE's  C++  wrapper  library  (-lpcrecpp
                  -lpcre on many systems).
 
        --libs-posix
-                 Writes  to  the  standard  output  the  command  line options
-                 required to  link  with  PCRE's  POSIX  API  wrapper  library
+                 Writes  to  the  standard output the command line options re-
+                 quired  to  link  with  PCRE's  POSIX  API  wrapper   library
                  (-lpcreposix -lpcre on many systems).
 
-       --cflags  Writes  to  the  standard  output  the  command  line options
-                 required to compile files that use  PCRE  (this  may  include
-                 some -I options, but is blank on many systems).
+       --cflags  Writes  to  the  standard output the command line options re-
+                 quired to compile files that use PCRE (this may include  some
+                 -I options, but is blank on many systems).
 
        --cflags-posix
-                 Writes  to  the  standard  output  the  command  line options
-                 required to compile files that use PCRE's POSIX  API  wrapper
-                 library  (this  may  include some -I options, but is blank on
-                 many systems).
+                 Writes  to  the  standard output the command line options re-
+                 quired to compile files that use PCRE's POSIX API wrapper li-
+                 brary (this may include some -I options, but is blank on many
+                 systems).
 
 
 SEE ALSO

pcre/doc/pcre.3

@@ -146,7 +146,7 @@ performance.
 One way of guarding against this possibility is to use the
 \fBpcre_fullinfo()\fP function to check the compiled pattern's options for UTF.
 Alternatively, from release 8.33, you can set the PCRE_NEVER_UTF option at
-compile time. This causes an compile time error if a pattern contains a
+compile time. This causes a compile time error if a pattern contains a
 UTF-setting sequence.
 .P
 If your application is one that supports UTF, be aware that validity checking

pcre/doc/pcreapi.3

@@ -1227,7 +1227,7 @@ the following negative numbers:
   PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
   PCRE_ERROR_UNSET          the requested field is not set
 .sp
-The "magic number" is placed at the start of each compiled pattern as an simple
+The "magic number" is placed at the start of each compiled pattern as a simple
 check against passing an arbitrary memory pointer. The endianness error can
 occur if a compiled pattern is saved and reloaded on a different host. Here is
 a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
@@ -1294,7 +1294,7 @@ returned. For anchored patterns, -2 is returned.
 .sp
 Return the value of the first data unit (non-UTF character) of any matched
 string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
-otherwise return 0. The fourth argument should point to an \fBuint_t\fP
+otherwise return 0. The fourth argument should point to a \fBuint_t\fP
 variable.
 .P
 In the 8-bit library, the value is always less than 256. In the 16-bit library
@@ -1560,7 +1560,7 @@ returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
 .sp
 Return the value of the rightmost literal data unit that must exist in any
 matched string, other than at its start, if such a value has been recorded. The
-fourth argument should point to an \fBuint32_t\fP variable. If there is no such
+fourth argument should point to a \fBuint32_t\fP variable. If there is no such
 value, 0 is returned.
 .
 .

pcre/doc/pcretest.1

-.TH PCRETEST 1 "23 February 2017" "PCRE 8.41"
+.TH PCRETEST 1 "10 February 2020" "PCRE 8.44"
 .SH NAME
 pcretest - a program for testing Perl-compatible regular expressions.
 .SH SYNOPSIS
@@ -78,21 +78,19 @@ the 16-bit library, or \fBpcre32_xx\fP when using the 32-bit library".
 .rs
 .TP 10
 \fB-8\fP
-If both the 8-bit library has been built, this option causes the 8-bit library
-to be used (which is the default); if the 8-bit library has not been built,
-this option causes an error.
+If the 8-bit library has been built, this option causes it to be used (this is
+the default). If the 8-bit library has not been built, this option causes an
+error.
 .TP 10
 \fB-16\fP
-If both the 8-bit or the 32-bit, and the 16-bit libraries have been built, this
-option causes the 16-bit library to be used. If only the 16-bit library has been
-built, this is the default (so has no effect). If only the 8-bit or the 32-bit
-library has been built, this option causes an error.
+If the 16-bit library has been built, this option causes it to be used. If only
+the 16-bit library has been built, this is the default. If the 16-bit library
+has not been built, this option causes an error.
 .TP 10
 \fB-32\fP
-If both the 8-bit or the 16-bit, and the 32-bit libraries have been built, this
-option causes the 32-bit library to be used. If only the 32-bit library has been
-built, this is the default (so has no effect). If only the 8-bit or the 16-bit
-library has been built, this option causes an error.
+If the 32-bit library has been built, this option causes it to be used. If only
+the 32-bit library has been built, this is the default. If the 32-bit library
+has not been built, this option causes an error.
 .TP 10
 \fB-b\fP
 Behave as if each pattern has the \fB/B\fP (show byte code) modifier; the
@@ -1155,6 +1153,6 @@ Cambridge CB2 3QH, England.
 .rs
 .sp
 .nf
-Last updated: 23 February 2017
-Copyright (c) 1997-2017 University of Cambridge.
+Last updated: 10 February 2020
+Copyright (c) 1997-2020 University of Cambridge.
 .fi

pcre/pcre_compile.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2018 University of Cambridge
+           Copyright (c) 1997-2020 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -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)
@@ -3612,7 +3612,7 @@ 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
@@ -7133,15 +7133,17 @@ for (;; ptr++)
           int n = 0;
           ptr++;
           while(IS_DIGIT(*ptr))
+            {
             n = n * 10 + *ptr++ - CHAR_0;
-          if (*ptr != CHAR_RIGHT_PARENTHESIS)
+            if (n > 255)
               {
-            *errorcodeptr = ERR39;
+              *errorcodeptr = ERR38;
               goto FAILED;
               }
-          if (n > 255)
+            }
+          if (*ptr != CHAR_RIGHT_PARENTHESIS)
             {
-            *errorcodeptr = ERR38;
+            *errorcodeptr = ERR39;
             goto FAILED;
             }
           *code++ = n;
@@ -7459,7 +7461,7 @@ 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
@@ -8070,7 +8072,7 @@ 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
@@ -8683,7 +8685,7 @@ 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;
      }
 
@@ -8811,7 +8813,7 @@ 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;
      }
 

pcre/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;
 }

pcre/pcrecpp.cc

@@ -66,7 +66,8 @@ Arg RE::no_arg((void*)NULL);
 // inclusive test if we ever needed it.  (Note that not only the
 // __attribute__ syntax, but also __USER_LABEL_PREFIX__, are
 // gnu-specific.)
-#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) && !defined(__INTEL_COMPILER)
+#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) \
+       && !defined(__INTEL_COMPILER) && !defined(__LCC__)
 # define ULP_AS_STRING(x)            ULP_AS_STRING_INTERNAL(x)
 # define ULP_AS_STRING_INTERNAL(x)   #x
 # define USER_LABEL_PREFIX_STR       ULP_AS_STRING(__USER_LABEL_PREFIX__)
@@ -91,6 +92,7 @@ static const char *start_options[] = {
   "(*LIMIT_RECURSION=",
   "(*LIMIT_MATCH=",
   "(*CRLF)",
+  "(*LF)",
   "(*CR)",
   "(*BSR_UNICODE)",
   "(*BSR_ANYCRLF)",

pcre/pcreposix.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2018 University of Cambridge
+           Copyright (c) 1997-2020 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -298,6 +298,7 @@ if (preg->re_pcre == NULL)
 (void)pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT,
   &re_nsub);
 preg->re_nsub = (size_t)re_nsub;
+preg->re_erroffset = (size_t)(-1);  /* No meaning after successful compile */
 return 0;
 }
 
@@ -335,8 +336,6 @@ if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL;
 if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL;
 if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY;
 
-((regex_t *)preg)->re_erroffset = (size_t)(-1);  /* Only has meaning after compile */
-
 /* When no string data is being returned, or no vector has been passed in which
 to put it, ensure that nmatch is zero. Otherwise, ensure the vector for holding
 the return data is large enough. */

pcre/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;

pcre/testdata/testinput2

@@ -1380,7 +1380,7 @@
     1X
     123456\P
 
-//KF>testsavedregex
+//S-KF>testsavedregex
 
 /abc/IS>testsavedregex
 <testsavedregex

pcre/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