File tidies for 10.23-RC1

AUTHORS

@@ -8,7 +8,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2016 University of Cambridge
+Copyright (c) 1997-2017 University of Cambridge
 All rights reserved
 
 
@@ -19,7 +19,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2010-2016 Zoltan Herczeg
+Copyright(c) 2010-2017 Zoltan Herczeg
 All rights reserved.
 
 
@@ -30,7 +30,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2009-2016 Zoltan Herczeg
+Copyright(c) 2009-2017 Zoltan Herczeg
 All rights reserved.
 
 ####

ChangeLog

@@ -2,8 +2,8 @@ Change Log for PCRE2
 --------------------
 
 
-Version 10.23 xx-xxxxxx-2016
+Version 10.23 16-January-2017
-----------------------------
+-----------------------------
 
 1. Extended pcre2test with the utf8_input modifier so that it is able to
 generate all possible 16-bit and 32-bit code unit values in non-UTF modes.

LICENCE

@@ -25,7 +25,7 @@ Email domain:     cam.ac.uk
 University of Cambridge Computing Service,
 Cambridge, England.
 
-Copyright (c) 1997-2016 University of Cambridge
+Copyright (c) 1997-2017 University of Cambridge
 All rights reserved.
 
 
@@ -36,7 +36,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2010-2016 Zoltan Herczeg
+Copyright(c) 2010-2017 Zoltan Herczeg
 All rights reserved.
 
 
@@ -47,7 +47,7 @@ Written by:       Zoltan Herczeg
 Email local part: hzmester
 Emain domain:     freemail.hu
 
-Copyright(c) 2009-2016 Zoltan Herczeg
+Copyright(c) 2009-2017 Zoltan Herczeg
 All rights reserved.
 
 

Makefile.am

@@ -3,6 +3,10 @@
 AUTOMAKE_OPTIONS = subdir-objects
 ACLOCAL_AMFLAGS = -I m4
 
+## This seems to have become necessary for building in non-source directory.
+
+AM_CPPFLAGS="-I$(srcdir)/src"
+
 ## Specify the documentation files that are distributed.
 
 dist_doc_DATA = \

NEWS

@@ -1,6 +1,42 @@
 News about PCRE2 releases
 -------------------------
 
+Version 10.23 16-January-2017
+-----------------------------
+
+1. ChangeLog has the details of a lot of bug fixes and tidies.
+
+2. There has been a major re-factoring of the pcre2_compile.c file. Most syntax
+checking is now done in the pre-pass that identifies capturing groups. This has
+reduced the amount of duplication and made the code tidier. While doing this,
+some minor bugs and Perl incompatibilities were fixed (see ChangeLog for
+details.)
+
+3. Back references are now permitted in lookbehind assertions when there are
+no duplicated group numbers (that is, (?| has not been used), and, if the
+reference is by name, there is only one group of that name. The referenced
+group must, of course be of fixed length.
+
+4. \g{+<number>} (e.g. \g{+2} ) is now supported. It is a "forward back
+reference" and can be useful in repetitions (compare \g{-<number>} ). Perl does
+not recognize this syntax.
+
+5. pcre2grep now automatically expands its buffer up to a maximum set by
+--max-buffer-size.
+
+6. The -t option (grand total) has been added to pcre2grep.
+
+7. A new function called pcre2_code_copy_with_tables() exists to copy a
+compiled pattern along with a private copy of the character tables that is
+uses.
+
+8. A user supplied a number of patches to upgrade pcre2grep under Windows and
+tidy the code.
+
+9. Several updates have been made to pcre2test and test scripts (see
+ChangeLog).
+
+
 Version 10.22 29-July-2016
 --------------------------
 

RunTest

@@ -520,7 +520,7 @@ for bmode in "$test8" "$test16" "$test32"; do
         echo $title2 "(excluding UTF-$bits) (64M stack)"
         $sim $valgrind ${opt:+$vjs} ./pcre2test -q -S 64 $bmode $opt $testdata/testinput2 testtry
         if [ $? = 0 ] ; then
-          $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189 >>testtry
+          $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -63,-62,-2,-1,0,100,188,189,190,191 >>testtry
           checkresult $? 2 "$opt"
         else
           echo " "

configure.ac

@@ -11,16 +11,16 @@ dnl be defined as -RC2, for example. For real releases, it should be empty.
 m4_define(pcre2_major, [10])
 m4_define(pcre2_minor, [23])
 m4_define(pcre2_prerelease, [-RC1])
-m4_define(pcre2_date, [2016-08-01])
+m4_define(pcre2_date, [2017-01-16])
 
 # 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(libpcre2_8_version,     [4:0:4])
+m4_define(libpcre2_8_version,     [5:0:5])
-m4_define(libpcre2_16_version,    [4:0:4])
+m4_define(libpcre2_16_version,    [5:0:5])
-m4_define(libpcre2_32_version,    [4:0:4])
+m4_define(libpcre2_32_version,    [5:0:5])
-m4_define(libpcre2_posix_version, [1:0:0])
+m4_define(libpcre2_posix_version, [1:1:0])
 
 AC_PREREQ(2.57)
 AC_INIT(PCRE2, pcre2_major.pcre2_minor[]pcre2_prerelease, , pcre2)

doc/html/pcre2_dfa_match.html

@@ -45,8 +45,8 @@ is <b>pcre2_match()</b>.) The arguments for this function are:
   <i>wscount</i>      Number of elements in the vector
 </pre>
 For <b>pcre2_dfa_match()</b>, a match context is needed only if you want to set
-up a callout function. The <i>length</i> and <i>startoffset</i> values are code
+up a callout function or specify the recursion limit. The <i>length</i> and
-units, not characters. The options are:
+<i>startoffset</i> values are code units, not characters. The options are:
 <pre>
   PCRE2_ANCHORED          Match only at the first position
   PCRE2_NOTBOL            Subject is not the beginning of a line

doc/html/pcre2api.html

@@ -879,21 +879,23 @@ This limit is of use only if it is set smaller than <i>match_limit</i>.
 Limiting the recursion depth limits the amount of system stack that can be
 used, or, when PCRE2 has been compiled to use memory on the heap instead of the
 stack, the amount of heap memory that can be used. This limit is not relevant,
-and is ignored, when matching is done using JIT compiled code or by the
+and is ignored, when matching is done using JIT compiled code. However, it is
-<b>pcre2_dfa_match()</b> function.
+supported by <b>pcre2_dfa_match()</b>, which uses recursive function calls less
+frequently than <b>pcre2_match()</b>, but which can be caused to use a lot of
+stack by a recursive pattern such as /(.)(?1)/ matched to a very long string.
 </P>
 <P>
 The default value for <i>recursion_limit</i> can be set when PCRE2 is built; the
 default default is the same value as the default for <i>match_limit</i>. If the
-limit is exceeded, <b>pcre2_match()</b> returns PCRE2_ERROR_RECURSIONLIMIT. A
+limit is exceeded, <b>pcre2_match()</b> and <b>pcre2_dfa_match()</b> return
-value for the recursion limit may also be supplied by an item at the start of a
+PCRE2_ERROR_RECURSIONLIMIT. A value for the recursion limit may also be
-pattern of the form
+supplied by an item at the start of a pattern of the form
 <pre>
   (*LIMIT_RECURSION=ddd)
 </pre>
 where ddd is a decimal number. However, such a setting is ignored unless ddd is
-less than the limit set by the caller of <b>pcre2_match()</b> or, if no such
+less than the limit set by the caller of <b>pcre2_match()</b> or
-limit is set, less than the default.
+<b>pcre2_dfa_match()</b> or, if no such limit is set, less than the default.
 <b>int pcre2_set_recursion_memory_management(</b>
 <b>  pcre2_match_context *<i>mcontext</i>,</b>
 <b>  void *(*<i>private_malloc</i>)(PCRE2_SIZE, void *),</b>
@@ -1976,7 +1978,7 @@ Information about a successful or unsuccessful match is placed in a match
 data block, which is an opaque structure that is accessed by function calls. In
 particular, the match data block contains a vector of offsets into the subject
 string that define the matched part of the subject and any substrings that were
-captured. This is know as the <i>ovector</i>.
+captured. This is known as the <i>ovector</i>.
 </P>
 <P>
 Before calling <b>pcre2_match()</b>, <b>pcre2_dfa_match()</b>, or
@@ -3263,7 +3265,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC41" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 22 November 2016
+Last updated: 23 December 2016
 <br>
 Copyright &copy; 1997-2016 University of Cambridge.
 <br>

doc/html/pcre2grep.html

@@ -245,13 +245,23 @@ because <b>pcre2grep</b> has to search for all possible matches in a line, not
 just one, in order to colour them all.
 <br>
 <br>
-The colour that is used can be specified by setting the environment variable
+The colour that is used can be specified by setting one of the environment
-PCRE2GREP_COLOUR or PCRE2GREP_COLOR. If neither of these are set,
+variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, PCREGREP_COLOUR, or
-<b>pcre2grep</b> looks for GREP_COLOUR or GREP_COLOR. The value of the variable
+PCREGREP_COLOR, which are checked in that order. If none of these are set,
-should be a string of two numbers, separated by a semicolon. They are copied
+<b>pcre2grep</b> looks for GREP_COLORS or GREP_COLOR (in that order). The value
-directly into the control string for setting colour on a terminal, so it is
+of the variable should be a string of two numbers, separated by a semicolon,
-your responsibility to ensure that they make sense. If neither of the
+except in the case of GREP_COLORS, which must start with "ms=" or "mt="
-environment variables is set, the default is "1;31", which gives red.
+followed by two semicolon-separated colours, terminated by the end of the
+string or by a colon. If GREP_COLORS does not start with "ms=" or "mt=" it is
+ignored, and GREP_COLOR is checked.
+<br>
+<br>
+If the string obtained from one of the above variables contains any characters
+other than semicolon or digits, the setting is ignored and the default colour
+is used. The string is copied directly into the control string for setting
+colour on a terminal, so it is your responsibility to ensure that the values
+make sense. If no relevant environment variable is set, the default is "1;31",
+which gives red.
 </P>
 <P>
 <b>-D</b> <i>action</i>, <b>--devices=</b><i>action</i>
@@ -773,12 +783,12 @@ character. Otherwise <b>pcre2grep</b> will assume that it has no data.
 </P>
 <br><a name="SEC10" href="#TOC1">CALLING EXTERNAL SCRIPTS</a><br>
 <P>
-On non-Windows systems, <b>pcre2grep</b> has, by default, support for calling
+<b>pcre2grep</b> has, by default, support for calling external programs or
-external programs or scripts during matching by making use of PCRE2's callout
+scripts during matching by making use of PCRE2's callout facility. However,
-facility. However, this support can be disabled when <b>pcre2grep</b> is built.
+this support can be disabled when <b>pcre2grep</b> is built. You can find out
-You can find out whether your binary has support for callouts by running it
+whether your binary has support for callouts by running it with the <b>--help</b>
-with the <b>--help</b> option. If the support is not enabled, all callouts in
+option. If the support is not enabled, all callouts in patterns are ignored by
-patterns are ignored by <b>pcre2grep</b>.
+<b>pcre2grep</b>.
 </P>
 <P>
 A callout in a PCRE2 pattern is of the form (?C&#60;arg&#62;) where the argument is
@@ -860,7 +870,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC15" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 31 October 2016
+Last updated: 31 December 2016
 <br>
 Copyright &copy; 1997-2016 University of Cambridge.
 <br>

doc/html/pcre2pattern.html

@@ -190,6 +190,12 @@ be less than the value set (or defaulted) by the caller of <b>pcre2_match()</b>
 for it to have any effect. In other words, the pattern writer can lower the
 limits set by the programmer, but not raise them. If there is more than one
 setting of one of these limits, the lower value is used.
+</P>
+<P>
+The match limit is used (but in a different way) when JIT is being used, but it
+is not relevant, and is ignored, when matching with <b>pcre2_dfa_match()</b>.
+However, the recursion limit is relevant for DFA matching, which does use some
+function recursion, in particular, for recursions within the pattern.
 <a name="newlines"></a></P>
 <br><b>
 Newline conventions
@@ -1347,10 +1353,10 @@ or immediately after a range. For example, [b-d-z] matches letters in the range
 b to d, a hyphen character, or z.
 </P>
 <P>
-Perl treats a hyphen as a literal if it appears before a POSIX class (see
+Perl treats a hyphen as a literal if it appears before or after a POSIX class
-below) or a character type escape such as as \d, but gives a warning in its 
+(see below) or a character type escape such as as \d, but gives a warning in
-warning mode, as this is most likely a user error. As PCRE2 has no facility for
+its warning mode, as this is most likely a user error. As PCRE2 has no facility
-warning, an error is given in these cases.
+for warning, an error is given in these cases.
 </P>
 <P>
 It is not possible to have the literal character "]" as the end character of a
@@ -3446,7 +3452,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC30" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 23 October 2016
+Last updated: 27 December 2016
 <br>
 Copyright &copy; 1997-2016 University of Cambridge.
 <br>

doc/html/pcre2stack.html

@@ -57,12 +57,13 @@ assertion and "once-only" subpatterns, which are handled like subroutine calls.
 Normally, these are never very deep, and the limit on the complexity of
 <b>pcre2_dfa_match()</b> is controlled by the amount of workspace it is given.
 However, it is possible to write patterns with runaway infinite recursions;
-such patterns will cause <b>pcre2_dfa_match()</b> to run out of stack. At
+such patterns will cause <b>pcre2_dfa_match()</b> to run out of stack unless a
-present, there is no protection against this.
+limit is applied (see below).
 </P>
 <P>
-The comments that follow do NOT apply to <b>pcre2_dfa_match()</b>; they are
+The comments in the next three sections do not apply to
-relevant only for <b>pcre2_match()</b> without the JIT optimization.
+<b>pcre2_dfa_match()</b>; they are relevant only for <b>pcre2_match()</b> without
+the JIT optimization.
 </P>
 <br><b>
 Reducing <b>pcre2_match()</b>'s stack usage
@@ -115,7 +116,7 @@ entitled
 in the
 <a href="pcre2api.html"><b>pcre2api</b></a>
 documentation. Since the block sizes are always the same, it may be possible to
-implement customized a memory handler that is more efficient than the standard
+implement a customized memory handler that is more efficient than the standard
 function. The memory blocks obtained for this purpose are retained and re-used
 if possible while <b>pcre2_match()</b> is running. They are all freed just
 before it exits.
@@ -151,6 +152,15 @@ pattern to match. This is done by calling <b>pcre2_match()</b> repeatedly with
 different limits.
 </P>
 <br><b>
+Limiting <b>pcre2_dfa_match()</b>'s stack usage
+</b><br>
+<P>
+The recursion limit, as described above for <b>pcre2_match()</b>, also applies
+to <b>pcre2_dfa_match()</b>, whose use of recursive function calls for
+recursions in the pattern can lead to runaway stack usage. The non-recursive
+match limit is not relevant for DFA matching, and is ignored.
+</P>
+<br><b>
 Changing stack size in Unix-like systems
 </b><br>
 <P>
@@ -198,9 +208,9 @@ Cambridge, England.
 REVISION
 </b><br>
 <P>
-Last updated: 21 November 2014
+Last updated: 23 December 2016
 <br>
-Copyright &copy; 1997-2014 University of Cambridge.
+Copyright &copy; 1997-2016 University of Cambridge.
 <br>
 <p>
 Return to the <a href="index.html">PCRE2 index page</a>.

doc/html/pcre2syntax.html

@@ -451,9 +451,10 @@ appear.
   (*UCP)          set PCRE2_UCP (use Unicode properties for \d etc)
 </pre>
 Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the
-limits set by the caller of pcre2_match(), not increase them. The application
+limits set by the caller of <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b>, not
-can lock out the use of (*UTF) and (*UCP) by setting the PCRE2_NEVER_UTF or
+increase them. The application can lock out the use of (*UTF) and (*UCP) by
-PCRE2_NEVER_UCP options, respectively, at compile time.
+setting the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, respectively, at
+compile time.
 </P>
 <br><a name="SEC17" href="#TOC1">NEWLINE CONVENTION</a><br>
 <P>
@@ -595,7 +596,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC27" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 28 September 2016
+Last updated: 23 December 2016
 <br>
 Copyright &copy; 1997-2016 University of Cambridge.
 <br>

doc/html/pcre2test.html

@@ -153,8 +153,13 @@ 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>-ac</b>
+Behave as if each pattern has the <b>auto_callout</b> modifier, that is, insert
+automatic callouts into every pattern that is compiled.
+</P>
+<P>
 <b>-b</b>
-Behave as if each pattern has the <b>/fullbincode</b> modifier; the full
+Behave as if each pattern has the <b>fullbincode</b> modifier; the full
 internal binary form of the pattern is output after compilation.
 </P>
 <P>
@@ -220,7 +225,7 @@ Output a brief summary these options and then exit.
 </P>
 <P>
 <b>-i</b>
-Behave as if each pattern has the <b>/info</b> modifier; information about the
+Behave as if each pattern has the <b>info</b> modifier; information about the
 compiled pattern is given after compilation.
 </P>
 <P>
@@ -806,7 +811,7 @@ modes are to be compiled:
   2  compile JIT code for soft partial matching
   4  compile JIT code for hard partial matching
 </pre>
-The possible values for the <b>/jit</b> modifier are therefore:
+The possible values for the <b>jit</b> modifier are therefore:
 <pre>
   0  disable JIT
   1  normal matching only
@@ -852,14 +857,14 @@ code was actually used in the match.
 Setting a locale
 </b><br>
 <P>
-The <b>/locale</b> modifier must specify the name of a locale, for example:
+The <b>locale</b> modifier must specify the name of a locale, for example:
 <pre>
   /pattern/locale=fr_FR
 </pre>
 The given locale is set, <b>pcre2_maketables()</b> is called to build a set of
 character tables for the locale, and this is then passed to
 <b>pcre2_compile()</b> when compiling the regular expression. The same tables
-are used when matching the following subject lines. The <b>/locale</b> modifier
+are used when matching the following subject lines. The <b>locale</b> modifier
 applies only to the pattern on which it appears, but can be given in a
 <b>#pattern</b> command if a default is needed. Setting a locale and alternate
 character tables are mutually exclusive.
@@ -868,7 +873,7 @@ character tables are mutually exclusive.
 Showing pattern memory
 </b><br>
 <P>
-The <b>/memory</b> modifier causes the size in bytes of the memory used to hold
+The <b>memory</b> modifier causes the size in bytes of the memory used to hold
 the compiled pattern to be output. This does not include the size of the
 <b>pcre2_code</b> block; it is just the actual compiled data. If the pattern is
 subsequently passed to the JIT compiler, the size of the JIT compiled code is
@@ -937,7 +942,7 @@ an error.
 Testing the stack guard feature
 </b><br>
 <P>
-The <b>/stackguard</b> modifier is used to test the use of
+The <b>stackguard</b> modifier is used to test the use of
 <b>pcre2_set_compile_recursion_guard()</b>, a function that is provided to
 enable stack availability to be checked during compilation (see the
 <a href="pcre2api.html"><b>pcre2api</b></a>
@@ -952,7 +957,7 @@ be aborted.
 Using alternative character tables
 </b><br>
 <P>
-The value specified for the <b>/tables</b> modifier must be one of the digits 0,
+The value specified for the <b>tables</b> modifier must be one of the digits 0,
 1, or 2. It causes a specific set of built-in character tables to be passed to
 <b>pcre2_compile()</b>. This is used in the PCRE2 tests to check behaviour with
 different character tables. The digit specifies the tables as follows:
@@ -1042,7 +1047,7 @@ The partial matching modifiers are provided with abbreviations because they
 appear frequently in tests.
 </P>
 <P>
-If the <b>/posix</b> modifier was present on the pattern, causing the POSIX
+If the <b>posix</b> modifier was present on the pattern, causing the POSIX
 wrapper API to be used, the only option-setting modifiers that have any effect
 are <b>notbol</b>, <b>notempty</b>, and <b>noteol</b>, causing REG_NOTBOL,
 REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to <b>regexec()</b>.
@@ -1064,6 +1069,7 @@ pattern.
       altglobal                  alternative global matching
       callout_capture            show captures at callout time
       callout_data=&#60;n&#62;           set a value to pass via callouts
+      callout_error=&#60;n&#62;[:&#60;m&#62;]    control callout error
       callout_fail=&#60;n&#62;[:&#60;m&#62;]     control callout failure
       callout_none               do not supply a callout function
       copy=&#60;number or name&#62;      copy captured substring
@@ -1159,15 +1165,22 @@ Testing callouts
 <P>
 A callout function is supplied when <b>pcre2test</b> calls the library matching
 functions, unless <b>callout_none</b> is specified. If <b>callout_capture</b> is
-set, the current captured groups are output when a callout occurs.
+set, the current captured groups are output when a callout occurs. The default
+return from the callout function is zero, which allows matching to continue.
 </P>
 <P>
 The <b>callout_fail</b> modifier can be given one or two numbers. If there is
-only one number, 1 is returned instead of 0 when a callout of that number is
+only one number, 1 is returned instead of 0 (causing matching to backtrack)
-reached. If two numbers are given, 1 is returned when callout &#60;n&#62; is reached
+when a callout of that number is reached. If two numbers (&#60;n&#62;:&#60;m&#62;) are given, 1
-for the &#60;m&#62;th time. Note that callouts with string arguments are always given
+is returned when callout &#60;n&#62; is reached and there have been at least &#60;m&#62;
-the number zero. See "Callouts" below for a description of the output when a
+callouts. The <b>callout_error</b> modifier is similar, except that
-callout it taken.
+PCRE2_ERROR_CALLOUT is returned, causing the entire matching process to be
+aborted. If both these modifiers are set for the same callout number,
+<b>callout_error</b> takes precedence.
+</P>
+<P>
+Note that callouts with string arguments are always given the number zero. See
+"Callouts" below for a description of the output when a callout it taken.
 </P>
 <P>
 The <b>callout_data</b> modifier can be given an unsigned or a negative number.
@@ -1180,7 +1193,7 @@ Finding all matches in a string
 </b><br>
 <P>
 Searching for all possible matches within a subject can be requested by the
-<b>global</b> or <b>/altglobal</b> modifier. After finding a match, the matching
+<b>global</b> or <b>altglobal</b> modifier. After finding a match, the matching
 function is called again to search the remainder of the subject. The difference
 between <b>global</b> and <b>altglobal</b> is that the former uses the
 <i>start_offset</i> argument to <b>pcre2_match()</b> or <b>pcre2_dfa_match()</b>
@@ -1480,7 +1493,7 @@ unset substring is shown as "&#60;unset&#62;", as for the second data line.
 If the strings contain any non-printing characters, they are output as \xhh
 escapes if the value is less than 256 and UTF mode is not set. Otherwise they
 are output as \x{hh...} escapes. See below for the definition of non-printing
-characters. If the <b>/aftertext</b> modifier is set, the output for substring
+characters. If the <b>aftertext</b> modifier is set, the output for substring
 0 is followed by the the rest of the subject string, identified by "0+" like
 this:
 <pre>
@@ -1673,7 +1686,7 @@ therefore shown as hex escapes.
 <P>
 When <b>pcre2test</b> is outputting text that is a matched part of a subject
 string, it behaves in the same way, unless a different locale has been set for
-the pattern (using the <b>/locale</b> modifier). In this case, the
+the pattern (using the <b>locale</b> modifier). In this case, the
 <b>isprint()</b> function is used to distinguish printing and non-printing
 characters.
 <a name="saverestore"></a></P>
@@ -1766,7 +1779,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC21" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 04 November 2016
+Last updated: 28 December 2016
 <br>
 Copyright &copy; 1997-2016 University of Cambridge.
 <br>

doc/pcre2.txt

@@ -922,19 +922,22 @@ PCRE2 CONTEXTS
        be used, or, when PCRE2 has been compiled to use  memory  on  the  heap
        instead  of the stack, the amount of heap memory that can be used. This
        limit is not relevant, and is ignored, when matching is done using  JIT
-       compiled code or by the pcre2_dfa_match() function.
+       compiled  code.  However,  it  is supported by pcre2_dfa_match(), which
+       uses recursive function calls less frequently than  pcre2_match(),  but
+       which  can  be caused to use a lot of stack by a recursive pattern such
+       as /(.)(?1)/ matched to a very long string.
 
        The default value for recursion_limit can be set when PCRE2  is  built;
        the  default  default is the same value as the default for match_limit.
-       If  the limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSION-
+       If the limit is exceeded, pcre2_match()  and  pcre2_dfa_match()  return
-       LIMIT. A value for the recursion limit may also be supplied by an  item
+       PCRE2_ERROR_RECURSIONLIMIT. A value for the recursion limit may also be
-       at the start of a pattern of the form
+       supplied by an item at the start of a pattern of the form
 
          (*LIMIT_RECURSION=ddd)
 
        where ddd is a decimal number.  However,  such  a  setting  is  ignored
-       unless ddd is less than the limit set by the  caller  of  pcre2_match()
+       unless ddd is less than the limit set by the caller of pcre2_match() or
-       or, if no such limit is set, less than the default.
+       pcre2_dfa_match() or, if no such limit is set, less than the default.
 
        int pcre2_set_recursion_memory_management(
          pcre2_match_context *mcontext,
@@ -1986,7 +1989,7 @@ THE MATCH DATA BLOCK
        match data block, which is an opaque  structure  that  is  accessed  by
        function  calls.  In particular, the match data block contains a vector
        of offsets into the subject string that define the matched part of  the
-       subject and any substrings that were captured.  This  is  know  as  the
+       subject  and  any  substrings  that were captured. This is known as the
        ovector.
 
        Before calling pcre2_match(), pcre2_dfa_match(),  or  pcre2_jit_match()
@@ -3175,7 +3178,7 @@ AUTHOR
 
 REVISION
 
-       Last updated: 22 November 2016
+       Last updated: 23 December 2016
        Copyright (c) 1997-2016 University of Cambridge.
 ------------------------------------------------------------------------------
 
@@ -5537,6 +5540,12 @@ SPECIAL START-OF-PATTERN ITEMS
        If there is more than one setting of one of  these  limits,  the  lower
        value is used.
 
+       The  match  limit  is  used  (but in a different way) when JIT is being
+       used, but it is not  relevant,  and  is  ignored,  when  matching  with
+       pcre2_dfa_match().   However,  the  recursion limit is relevant for DFA
+       matching, which does use some function recursion,  in  particular,  for
+       recursions within the pattern.
+
    Newline conventions
 
        PCRE2 supports five different conventions for indicating line breaks in
@@ -6497,10 +6506,10 @@ SQUARE BRACKETS AND CHARACTER CLASSES
        example, [b-d-z] matches letters in the range b to d, a hyphen  charac-
        ter, or z.
 
-       Perl  treats  a  hyphen as a literal if it appears before a POSIX class
+       Perl treats a hyphen as a literal if it appears before or after a POSIX
-       (see below) or a character type escape such as as \d, but gives a warn-
+       class (see below) or a character type escape such as as \d, but gives a
-       ing  in its warning mode, as this is most likely a user error. As PCRE2
+       warning  in  its  warning mode, as this is most likely a user error. As
-       has no facility for warning, an error is given in these cases.
+       PCRE2 has no facility for warning, an error is given in these cases.
 
        It is not possible to have the literal character "]" as the end charac-
        ter  of a range. A pattern such as [W-]46] is interpreted as a class of
@@ -8487,7 +8496,7 @@ AUTHOR
 
 REVISION
 
-       Last updated: 23 October 2016
+       Last updated: 27 December 2016
        Copyright (c) 1997-2016 University of Cambridge.
 ------------------------------------------------------------------------------
 
@@ -9255,11 +9264,12 @@ PCRE2 DISCUSSION OF STACK USAGE
        limit  on  the  complexity  of  pcre2_dfa_match()  is controlled by the
        amount of workspace it is given.  However, it is possible to write pat-
        terns  with  runaway  infinite  recursions;  such  patterns  will cause
-       pcre2_dfa_match() to run out of stack. At present, there is no  protec-
+       pcre2_dfa_match() to run out of stack unless a limit  is  applied  (see
-       tion against this.
+       below).
 
-       The  comments  that  follow do NOT apply to pcre2_dfa_match(); they are
+       The   comments   in   the   next   three   sections  do  not  apply  to
-       relevant only for pcre2_match() without the JIT optimization.
+       pcre2_dfa_match(); they are relevant only for pcre2_match() without the
+       JIT optimization.
 
    Reducing pcre2_match()'s stack usage
 
@@ -9303,7 +9313,7 @@ PCRE2 DISCUSSION OF STACK USAGE
        arrange to supply your own memory management function. For details, see
        the section entitled "The match context" in the pcre2api documentation.
        Since the block sizes are always the same, it may be possible to imple-
-       ment customized a memory handler that is more efficient than the  stan-
+       ment  a customized memory handler that is more efficient than the stan-
        dard function. The memory blocks obtained for this purpose are retained
        and  re-used  if  possible while pcre2_match() is running. They are all
        freed just before it exits.
@@ -9329,6 +9339,13 @@ PCRE2 DISCUSSION OF STACK USAGE
        that allow a a pattern to match. This is done by calling  pcre2_match()
        repeatedly with different limits.
 
+   Limiting pcre2_dfa_match()'s stack usage
+
+       The recursion limit, as described above for pcre2_match(), also applies
+       to pcre2_dfa_match(), whose use of recursive function calls for  recur-
+       sions in the pattern can lead to runaway stack usage. The non-recursive
+       match limit is not relevant for DFA matching, and is ignored.
+
    Changing stack size in Unix-like systems
 
        In Unix-like environments, there is not often a problem with the  stack
@@ -9368,8 +9385,8 @@ AUTHOR
 
 REVISION
 
-       Last updated: 21 November 2014
+       Last updated: 23 December 2016
-       Copyright (c) 1997-2014 University of Cambridge.
+       Copyright (c) 1997-2016 University of Cambridge.
 ------------------------------------------------------------------------------
 
 
@@ -9667,10 +9684,10 @@ OPTION SETTING
          (*UCP)          set PCRE2_UCP (use Unicode properties for \d etc)
 
        Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value  of
-       the  limits  set by the caller of pcre2_match(), not increase them. The
+       the limits set by the caller of pcre2_match() or pcre2_dfa_match(), not
-       application can lock out the use of (*UTF) and (*UCP)  by  setting  the
+       increase them. The application can lock  out  the  use  of  (*UTF)  and
-       PCRE2_NEVER_UTF  or  PCRE2_NEVER_UCP  options, respectively, at compile
+       (*UCP)  by  setting  the  PCRE2_NEVER_UTF  or  PCRE2_NEVER_UCP options,
-       time.
+       respectively, at compile time.
 
 
 NEWLINE CONVENTION
@@ -9811,7 +9828,7 @@ AUTHOR
 
 REVISION
 
-       Last updated: 28 September 2016
+       Last updated: 23 December 2016
        Copyright (c) 1997-2016 University of Cambridge.
 ------------------------------------------------------------------------------
 

doc/pcre2grep.txt

@@ -219,15 +219,25 @@ OPTIONS
                  possible matches in a line, not just one, in order to  colour
                  them all.
 
-                 The colour that is used can be specified by setting the envi-
+                 The  colour  that  is used can be specified by setting one of
-                 ronment variable PCRE2GREP_COLOUR or PCRE2GREP_COLOR. If nei-
+                 the environment variables PCRE2GREP_COLOUR,  PCRE2GREP_COLOR,
-                 ther  of  these  are  set, pcre2grep looks for GREP_COLOUR or
+                 PCREGREP_COLOUR, or PCREGREP_COLOR, which are checked in that
-                 GREP_COLOR. The value of the variable should be a  string  of
+                 order.  If  none  of  these  are  set,  pcre2grep  looks  for
-                 two  numbers,  separated  by  a  semicolon.  They  are copied
+                 GREP_COLORS  or  GREP_COLOR (in that order). The value of the
-                 directly into the control string for setting colour on a ter-
+                 variable should be a string of two numbers,  separated  by  a
-                 minal,  so it is your responsibility to ensure that they make
+                 semicolon,  except  in  the  case  of GREP_COLORS, which must
-                 sense. If neither of the environment variables  is  set,  the
+                 start with "ms=" or "mt=" followed by two semicolon-separated
-                 default is "1;31", which gives red.
+                 colours,  terminated  by the end of the string or by a colon.
+                 If GREP_COLORS does not start  with  "ms="  or  "mt="  it  is
+                 ignored, and GREP_COLOR is checked.
+
+                 If  the  string obtained from one of the above variables con-
+                 tains any characters other than semicolon or digits, the set-
+                 ting is ignored and the default colour is used. The string is
+                 copied directly into the control string for setting colour on
+                 a  terminal,  so it is your responsibility to ensure that the
+                 values make sense. If no  relevant  environment  variable  is
+                 set, the default is "1;31", which gives red.
 
        -D action, --devices=action
                  If  an  input  path  is  not  a  regular file or a directory,
@@ -763,12 +773,12 @@ OPTIONS WITH DATA
 
 CALLING EXTERNAL SCRIPTS
 
-       On non-Windows systems, pcre2grep has, by default, support for  calling
+       pcre2grep has, by default, support for  calling  external  programs  or
-       external  programs  or scripts during matching by making use of PCRE2's
+       scripts during matching by making use of PCRE2's callout facility. How-
-       callout facility. However, this support can be disabled when  pcre2grep
+       ever, this support can be disabled when pcre2grep  is  built.  You  can
-       is  built.   You can find out whether your binary has support for call-
+       find  out  whether  your  binary has support for callouts by running it
-       outs by running it with the  --help  option.  If  the  support  is  not
+       with the --help option. If the support is not enabled, all callouts  in
-       enabled, all callouts in patterns are ignored by pcre2grep.
+       patterns are ignored by pcre2grep.
 
        A  callout  in a PCRE2 pattern is of the form (?C<arg>) where the argu-
        ment is either a number or a quoted string (see the pcre2callout  docu-
@@ -852,5 +862,5 @@ AUTHOR
 
 REVISION
 
-       Last updated: 31 October 2016
+       Last updated: 31 December 2016
        Copyright (c) 1997-2016 University of Cambridge.

doc/pcre2test.txt

@@ -116,7 +116,11 @@ COMMAND LINE OPTIONS
                  is the default. If the 32-bit library  has  not  been  built,
                  this option causes an error.
 
-       -b        Behave  as if each pattern has the /fullbincode modifier; the
+       -ac       Behave as if each pattern has the auto_callout modifier, that
+                 is, insert automatic callouts into every pattern that is com-
+                 piled.
+
+       -b        Behave  as  if each pattern has the fullbincode modifier; the
                  full internal binary form of the pattern is output after com-
                  pilation.
 
@@ -174,7 +178,7 @@ COMMAND LINE OPTIONS
 
        -help     Output a brief summary these options and then exit.
 
-       -i        Behave as if each pattern has the /info modifier; information
+       -i        Behave  as if each pattern has the info modifier; information
                  about the compiled pattern is given after compilation.
 
        -jit      Behave as if each pattern line has the  jit  modifier;  after
@@ -724,7 +728,7 @@ PATTERN MODIFIERS
          2  compile JIT code for soft partial matching
          4  compile JIT code for hard partial matching
 
-       The possible values for the /jit modifier are therefore:
+       The possible values for the jit modifier are therefore:
 
          0  disable JIT
          1  normal matching only
@@ -764,24 +768,24 @@ PATTERN MODIFIERS
 
    Setting a locale
 
-       The /locale modifier must specify the name of a locale, for example:
+       The locale modifier must specify the name of a locale, for example:
 
          /pattern/locale=fr_FR
 
        The given locale is set, pcre2_maketables() is called to build a set of
        character  tables for the locale, and this is then passed to pcre2_com-
        pile() when compiling the regular expression. The same tables are  used
-       when matching the following subject lines. The /locale modifier applies
+       when  matching the following subject lines. The locale modifier applies
        only to the pattern on which it appears, but can be given in a #pattern
        command  if a default is needed. Setting a locale and alternate charac-
        ter tables are mutually exclusive.
 
    Showing pattern memory
 
-       The /memory modifier causes the size in bytes of  the  memory  used  to
+       The memory modifier causes the size in bytes of the memory used to hold
-       hold  the compiled pattern to be output. This does not include the size
+       the  compiled  pattern  to be output. This does not include the size of
-       of the pcre2_code block; it is just the actual compiled  data.  If  the
+       the pcre2_code block; it is just the actual compiled data. If the  pat-
-       pattern is subsequently passed to the JIT compiler, the size of the JIT
+       tern  is  subsequently  passed to the JIT compiler, the size of the JIT
        compiled code is also output. Here is an example:
 
            re> /a(b)c/jit,memory
@@ -837,7 +841,7 @@ PATTERN MODIFIERS
 
    Testing the stack guard feature
 
-       The  /stackguard  modifier  is  used  to test the use of pcre2_set_com-
+       The  stackguard  modifier  is  used  to  test the use of pcre2_set_com-
        pile_recursion_guard(), a function that is  provided  to  enable  stack
        availability  to  be checked during compilation (see the pcre2api docu-
        mentation for details). If the number  specified  by  the  modifier  is
@@ -849,7 +853,7 @@ PATTERN MODIFIERS
 
    Using alternative character tables
 
-       The  value specified for the /tables modifier must be one of the digits
+       The  value  specified for the tables modifier must be one of the digits
        0, 1, or 2. It causes a specific set of built-in character tables to be
        passed to pcre2_compile(). This is used in the PCRE2 tests to check be-
        haviour with different character tables. The digit specifies the tables
@@ -931,7 +935,7 @@ SUBJECT MODIFIERS
        The  partial matching modifiers are provided with abbreviations because
        they appear frequently in tests.
 
-       If the /posix modifier was present on the pattern,  causing  the  POSIX
+       If the posix modifier was present on the  pattern,  causing  the  POSIX
        wrapper API to be used, the only option-setting modifiers that have any
        effect  are  notbol,  notempty,   and   noteol,   causing   REG_NOTBOL,
        REG_NOTEMPTY,  and REG_NOTEOL, respectively, to be passed to regexec().
@@ -951,6 +955,7 @@ SUBJECT MODIFIERS
              altglobal                  alternative global matching
              callout_capture            show captures at callout time
              callout_data=<n>           set a value to pass via callouts
+             callout_error=<n>[:<m>]    control callout error
              callout_fail=<n>[:<m>]     control callout failure
              callout_none               do not supply a callout function
              copy=<number or name>      copy captured substring
@@ -1042,14 +1047,22 @@ SUBJECT MODIFIERS
 
        A callout function is supplied when pcre2test calls the library  match-
        ing  functions, unless callout_none is specified. If callout_capture is
-       set, the current captured groups are output when a callout occurs.
+       set, the current captured groups are output when a callout occurs.  The
+       default return from the callout function is zero, which allows matching
+       to continue.
 
        The callout_fail modifier can be given one or two numbers. If there  is
-       only one number, 1 is returned instead of 0 when a callout of that num-
+       only  one number, 1 is returned instead of 0 (causing matching to back-
-       ber is reached. If two numbers are given, 1 is  returned  when  callout
+       track) when a callout  of  that  number  is  reached.  If  two  numbers
-       <n> is reached for the <m>th time. Note that callouts with string argu-
+       (<n>:<m>)  are  given,  1  is  returned when callout <n> is reached and
-       ments are always given the number zero.  See  "Callouts"  below  for  a
+       there have been at least <m> callouts. The  callout_error  modifier  is
-       description of the output when a callout it taken.
+       similar,  except  that  PCRE2_ERROR_CALLOUT  is  returned,  causing the
+       entire matching process to be aborted. If both these modifiers are  set
+       for the same callout number, callout_error takes precedence.
+
+       Note  that  callouts  with string arguments are always given the number
+       zero. See "Callouts" below for a description of the output when a call-
+       out it taken.
 
        The  callout_data  modifier can be given an unsigned or a negative num-
        ber.  This is set as the "user data" that is  passed  to  the  matching
@@ -1060,7 +1073,7 @@ SUBJECT MODIFIERS
    Finding all matches in a string
 
        Searching for all possible matches within a subject can be requested by
-       the global or /altglobal modifier. After finding a match, the  matching
+       the global or altglobal modifier. After finding a match,  the  matching
        function  is  called  again to search the remainder of the subject. The
        difference between global and altglobal is that  the  former  uses  the
        start_offset  argument  to  pcre2_match() or pcre2_dfa_match() to start
@@ -1329,7 +1342,7 @@ DEFAULT OUTPUT FROM pcre2test
        If  the strings contain any non-printing characters, they are output as
        \xhh escapes if the value is less than 256 and UTF  mode  is  not  set.
        Otherwise they are output as \x{hh...} escapes. See below for the defi-
-       nition of non-printing characters. If the /aftertext modifier  is  set,
+       nition of non-printing characters. If the aftertext  modifier  is  set,
        the  output  for substring 0 is followed by the the rest of the subject
        string, identified by "0+" like this:
 
@@ -1512,7 +1525,7 @@ NON-PRINTING CHARACTERS
 
        When  pcre2test  is outputting text that is a matched part of a subject
        string, it behaves in the same way, unless a different locale has  been
-       set  for  the  pattern  (using the /locale modifier). In this case, the
+       set  for  the  pattern  (using  the locale modifier). In this case, the
        isprint() function is used to  distinguish  printing  and  non-printing
        characters.
 
@@ -1601,5 +1614,5 @@ AUTHOR
 
 REVISION
 
-       Last updated: 04 November 2016
+       Last updated: 28 December 2016
        Copyright (c) 1997-2016 University of Cambridge.

src/config.h.generic

@@ -78,6 +78,9 @@ sure both macros are undefined; an emulation function will then be used. */
 /* Define to 1 if you have the <memory.h> header file. */
 /* #undef HAVE_MEMORY_H */
 
+/* Define to 1 if you have the `mkostemp' function. */
+/* #undef HAVE_MKOSTEMP */
+
 /* Define if you have POSIX threads libraries and header files. */
 /* #undef HAVE_PTHREAD */
 
@@ -90,6 +93,9 @@ sure both macros are undefined; an emulation function will then be used. */
 /* Define to 1 if you have the <readline/readline.h> header file. */
 /* #undef HAVE_READLINE_READLINE_H */
 
+/* Define to 1 if you have the `secure_getenv' function. */
+/* #undef HAVE_SECURE_GETENV */
+
 /* Define to 1 if you have the <stdint.h> header file. */
 /* #undef HAVE_STDINT_H */
 
@@ -308,9 +314,40 @@ sure both macros are undefined; an emulation function will then be used. */
 /* Define to any value for valgrind support to find invalid memory reads. */
 /* #undef SUPPORT_VALGRIND */
 
+/* Enable extensions on AIX 3, Interix.  */
+#ifndef _ALL_SOURCE
+# define _ALL_SOURCE 1
+#endif
+/* Enable GNU extensions on systems that have them.  */
+#ifndef _GNU_SOURCE
+# define _GNU_SOURCE 1
+#endif
+/* Enable threading extensions on Solaris.  */
+#ifndef _POSIX_PTHREAD_SEMANTICS
+# define _POSIX_PTHREAD_SEMANTICS 1
+#endif
+/* Enable extensions on HP NonStop.  */
+#ifndef _TANDEM_SOURCE
+# define _TANDEM_SOURCE 1
+#endif
+/* Enable general extensions on Solaris.  */
+#ifndef __EXTENSIONS__
+# define __EXTENSIONS__ 1
+#endif
+
 /* Version number of package */
 #define VERSION "10.23-RC1"
 
+/* Define to 1 if on MINIX. */
+/* #undef _MINIX */
+
+/* Define to 2 if the system does not provide POSIX.1 features except with
+   this defined. */
+/* #undef _POSIX_1_SOURCE */
+
+/* Define to 1 if you need to in order for `stat' and other things to work. */
+/* #undef _POSIX_SOURCE */
+
 /* Define to empty if `const' does not conform to ANSI C. */
 /* #undef const */
 

src/pcre2.h

@@ -44,7 +44,7 @@ POSSIBILITY OF SUCH DAMAGE.
 #define PCRE2_MAJOR          10
 #define PCRE2_MINOR          23
 #define PCRE2_PRERELEASE     -RC1
-#define PCRE2_DATE           2016-08-01
+#define PCRE2_DATE           2017-01-16
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE2, the appropriate

src/pcre2.h.generic

@@ -44,7 +44,7 @@ POSSIBILITY OF SUCH DAMAGE.
 #define PCRE2_MAJOR          10
 #define PCRE2_MINOR          23
 #define PCRE2_PRERELEASE     -RC1
-#define PCRE2_DATE           2016-08-01
+#define PCRE2_DATE           2017-01-16
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE2, the appropriate
@@ -465,7 +465,9 @@ PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_code_free(pcre2_code *); \
 PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
-  *pcre2_code_copy(const pcre2_code *);
+  *pcre2_code_copy(const pcre2_code *); \
+PCRE2_EXP_DECL pcre2_code PCRE2_CALL_CONVENTION \
+  *pcre2_code_copy_with_tables(const pcre2_code *);
 
 
 /* Functions that give information about a compiled pattern. */
@@ -629,6 +631,7 @@ pcre2_compile are called by application code. */
 
 #define pcre2_callout_enumerate               PCRE2_SUFFIX(pcre2_callout_enumerate_)
 #define pcre2_code_copy                       PCRE2_SUFFIX(pcre2_code_copy_)
+#define pcre2_code_copy_with_tables           PCRE2_SUFFIX(pcre2_code_copy_with_tables_)
 #define pcre2_code_free                       PCRE2_SUFFIX(pcre2_code_free_)
 #define pcre2_compile                         PCRE2_SUFFIX(pcre2_compile_)
 #define pcre2_compile_context_copy            PCRE2_SUFFIX(pcre2_compile_context_copy_)

src/pcre2_compile.c

@@ -116,9 +116,11 @@ them will be able to (i.e. assume a 64-bit world). */
 
 /* Function definitions to allow mutual recursion */
 
+#ifdef SUPPORT_UNICODE
 static unsigned int
-  add_list_to_class_internal(uint8_t *, PCRE2_UCHAR **, uint32_t, compile_block *,
+  add_list_to_class_internal(uint8_t *, PCRE2_UCHAR **, uint32_t,
-    const uint32_t *, unsigned int);
+    compile_block *, const uint32_t *, unsigned int);
+#endif
 
 static int
   compile_regex(uint32_t, PCRE2_UCHAR **, uint32_t **, int *, uint32_t,
@@ -4381,16 +4383,14 @@ return n8;    /* Number of 8-bit characters */
 
 
 
+#ifdef SUPPORT_UNICODE
 /*************************************************
 * Add a list of characters to a class (internal) *
 *************************************************/
 
 /* This function is used for adding a list of case-equivalent characters to a
-class, and also for adding a list of horizontal or vertical whitespace. If the
+class when in UTF mode. This function is called only from within
-list is in order (which it should be), ranges of characters are detected and
+add_to_class_internal(), with which it is mutually recursive.
-handled appropriately. This function is called (sometimes recursively) only
-from within the "add to class" set of functions. The external entry point is
-add_list_to_class().
 
 Arguments:
   classbits     the bit map for characters < 256
@@ -4423,6 +4423,7 @@ while (p[0] < NOTACHAR)
   }
 return n8;
 }
+#endif
 
 
 
@@ -4459,8 +4460,11 @@ return add_to_class_internal(classbits, uchardptr, options, cb, start, end);
 *   External entry point for add list to class   *
 *************************************************/
 
-/* This function sets the overall range so that the internal functions can try
+/* This function is used for adding a list of horizontal or vertical whitespace
-to avoid duplication when handling case-independence.
+characters to a class. The list must be in order so that ranges of characters
+can be detected and handled appropriately. This function sets the overall range
+so that the internal functions can try to avoid duplication when handling
+case-independence.
 
 Arguments:
   classbits     the bit map for characters < 256

src/pcre2grep.c

@@ -1937,6 +1937,8 @@ static int
 fill_buffer(void *handle, int frtype, char *buffer, int length,
   BOOL input_line_buffered)
 {
+(void)frtype;  /* Avoid warning when not used */
+
 #ifdef SUPPORT_LIBZ
 if (frtype == FR_LIBZ)
   return gzread((gzFile)handle, buffer, length);