Implement PCRE2_NEWLINE_NUL.

CMakeLists.txt

@@ -160,7 +160,7 @@ SET(PCRE2GREP_MAX_BUFSIZE "1048576" CACHE STRING
     "Buffer maximum size parameter for pcre2grep. See PCRE2GREP_MAX_BUFSIZE in config.h.in for details.")
 
 SET(PCRE2_NEWLINE "LF" CACHE STRING
-    "What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF).")
+    "What to recognize as a newline (one of CR, LF, CRLF, ANY, ANYCRLF, NUL).")
 
 SET(PCRE2_HEAP_MATCH_RECURSE OFF CACHE BOOL
     "Obsolete option: do not use")
@@ -344,6 +344,9 @@ ENDIF(PCRE2_NEWLINE STREQUAL "ANY")
 IF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
         SET(NEWLINE_DEFAULT "5")
 ENDIF(PCRE2_NEWLINE STREQUAL "ANYCRLF")
+IF(PCRE2_NEWLINE STREQUAL "NUL")
+        SET(NEWLINE_DEFAULT "6")
+ENDIF(PCRE2_NEWLINE STREQUAL "NUL")
 
 IF(NEWLINE_DEFAULT STREQUAL "")
         MESSAGE(FATAL_ERROR "The PCRE2_NEWLINE variable must be set to one of the following values: \"LF\", \"CR\", \"CRLF\", \"ANY\", \"ANYCRLF\".")

ChangeLog

@@ -169,6 +169,7 @@ all the tests can run with clang's sanitizing options.
 33. Implement extra compile options in the compile context and add the first 
 one: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES.
 
+34. Implement newline type PCRE2_NEWLINE_NUL.
 
 
 Version 10.23 14-February-2017

RunGrepTest

@@ -662,6 +662,11 @@ $valgrind $vjs $pcre2grep -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >
 printf "%c--------------------------- Test N6 ------------------------------\r\n" - >>testtrygrep
 $valgrind $vjs $pcre2grep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep
 
+printf "abc\0def" >testNinputgrep
+
+printf "%c--------------------------- Test N7 ------------------------------\r\n" - >>testtrygrep
+$valgrind $vjs $pcre2grep -na --newline=nul "^(abc|def)" testNinputgrep | sed 's/\x00/ZERO/' >>testtrygrep
+
 $cf $srcdir/testdata/grepoutputN testtrygrep
 if [ $? != 0 ] ; then exit 1; fi
 

configure.ac

@@ -189,6 +189,10 @@ AC_ARG_ENABLE(newline-is-any,
               AS_HELP_STRING([--enable-newline-is-any],
                              [use any valid Unicode newline sequence]),
               ac_pcre2_newline=any)
+AC_ARG_ENABLE(newline-is-nul,
+              AS_HELP_STRING([--enable-newline-is-nul],
+                             [use NUL (binary zero) as newline character]),
+              ac_pcre2_newline=nul)
 enable_newline="$ac_pcre2_newline"
 
 # Handle --enable-bsr-anycrlf
@@ -360,6 +364,7 @@ case "$enable_newline" in
   crlf)    ac_pcre2_newline_value=3 ;;
   any)     ac_pcre2_newline_value=4 ;;
   anycrlf) ac_pcre2_newline_value=5 ;;
+  nul)     ac_pcre2_newline_value=6 ;; 
   *)
   AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option])
   ;;
@@ -658,7 +663,7 @@ AC_DEFINE_UNQUOTED([NEWLINE_DEFAULT], [$ac_pcre2_newline_value], [
   The value of NEWLINE_DEFAULT determines the default newline character
   sequence. PCRE2 client programs can override this by selecting other values
   at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY),
-  and 5 (ANYCRLF).])
+  5 (ANYCRLF), and 6 (NUL).])
 
 if test "$enable_bsr_anycrlf" = "yes"; then
   AC_DEFINE([BSR_ANYCRLF], [], [

doc/html/pcre2_config.html

@@ -57,6 +57,7 @@ <h1>pcre2_config man page</h1>
                                  PCRE2_NEWLINE_CRLF
                                  PCRE2_NEWLINE_ANY
                                  PCRE2_NEWLINE_ANYCRLF
+                                 PCRE2_NEWLINE_NUL 
   PCRE2_CONFIG_PARENSLIMIT     Default parentheses nesting limit
   PCRE2_CONFIG_RECURSIONLIMIT  Obsolete: use PCRE2_CONFIG_DEPTHLIMIT
   PCRE2_CONFIG_STACKRECURSE    Obsolete: always returns 0

doc/html/pcre2_pattern_info.html

@@ -71,6 +71,7 @@ <h1>pcre2_pattern_info man page</h1>
                                PCRE2_NEWLINE_CRLF
                                PCRE2_NEWLINE_ANY
                                PCRE2_NEWLINE_ANYCRLF
+                               PCRE2_NEWLINE_NUL 
   PCRE2_INFO_RECURSIONLIMIT  Obsolete synonym for PCRE2_INFO_DEPTHLIMIT
   PCRE2_INFO_SIZE            Size of compiled pattern
 </pre>

doc/html/pcre2_set_newline.html

@@ -35,6 +35,7 @@ <h1>pcre2_set_newline man page</h1>
   PCRE2_NEWLINE_CRLF      CR followed by LF only
   PCRE2_NEWLINE_ANYCRLF   Any of the above
   PCRE2_NEWLINE_ANY       Any Unicode newline sequence
+  PCRE2_NEWLINE_NUL       The NUL character (binary zero) 
 </pre>
 The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
 invalid.

doc/html/pcre2api.html

@@ -783,8 +783,9 @@ <h1>pcre2api man page</h1>
 This specifies which characters or character sequences are to be recognized as
 newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
 PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character
-sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or
-PCRE2_NEWLINE_ANY (any Unicode newline sequence).
+sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), 
+PCRE2_NEWLINE_ANY (any Unicode newline sequence), or PCRE2_NEWLINE_NUL (the 
+NUL character, that is a binary zero).
 </P>
 <P>
 A pattern can override the value set in the compile context by starting with a
@@ -1106,6 +1107,7 @@ <h1>pcre2api man page</h1>
   PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
   PCRE2_NEWLINE_ANY      Any Unicode line ending
   PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+  PCRE2_NEWLINE_NUL      The NUL character (binary zero) 
 </pre>
 The default should normally correspond to the standard sequence for your
 operating system.
@@ -2121,6 +2123,7 @@ <h1>pcre2api man page</h1>
   PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
   PCRE2_NEWLINE_ANY      Any Unicode line ending
   PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
+  PCRE2_NEWLINE_NUL      The NUL character (binary zero) 
 </pre>
 This identifies the character sequence that will be recognized as meaning
 "newline" while matching.
@@ -3468,7 +3471,7 @@ <h1>pcre2api man page</h1>
 </P>
 <br><a name="SEC42" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 17 May 2017
+Last updated: 26 May 2017
 <br>
 Copyright &copy; 1997-2017 University of Cambridge.
 <br>

doc/html/pcre2grep.html

@@ -142,9 +142,11 @@ <h1>pcre2grep man page</h1>
 <br><a name="SEC4" href="#TOC1">BINARY FILES</a><br>
 <P>
 By default, a file that contains a binary zero byte within the first 1024 bytes
-is identified as a binary file, and is processed specially. (GNU grep also
-identifies binary files in this manner.) See the <b>--binary-files</b> option
-for a means of changing the way binary files are handled.
+is identified as a binary file, and is processed specially. (GNU grep
+identifies binary files in this manner.) However, if the newline type is
+specified as "nul", that is, the line terminator is a binary zero, the test for
+a binary file is not applied. See the <b>--binary-files</b> option for a means
+of changing the way binary files are handled.
 </P>
 <br><a name="SEC5" href="#TOC1">OPTIONS</a><br>
 <P>
@@ -934,7 +936,7 @@ <h1>pcre2grep man page</h1>
 </P>
 <br><a name="SEC15" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 11 April 2017
+Last updated: 26 May 2017
 <br>
 Copyright &copy; 1997-2017 University of Cambridge.
 <br>

doc/html/pcre2pattern.html

@@ -214,10 +214,10 @@ <h1>pcre2pattern man page</h1>
 Newline conventions
 </b><br>
 <P>
-PCRE2 supports five different conventions for indicating line breaks in
+PCRE2 supports six different conventions for indicating line breaks in
 strings: a single CR (carriage return) character, a single LF (linefeed)
-character, the two-character sequence CRLF, any of the three preceding, or any
-Unicode newline sequence. The
+character, the two-character sequence CRLF, any of the three preceding, any
+Unicode newline sequence, or the NUL character (binary zero). The
 <a href="pcre2api.html"><b>pcre2api</b></a>
 page has
 <a href="pcre2api.html#newlines">further discussion</a>
@@ -226,13 +226,14 @@ <h1>pcre2pattern man page</h1>
 </P>
 <P>
 It is also possible to specify a newline convention by starting a pattern
-string with one of the following five sequences:
+string with one of the following sequences:
 <pre>
   (*CR)        carriage return
   (*LF)        linefeed
   (*CRLF)      carriage return, followed by linefeed
   (*ANYCRLF)   any of the three above
   (*ANY)       all Unicode newline sequences
+  (*NUL)       the NUL character (binary zero) 
 </pre>
 These override the default and the options given to the compiling function. For
 example, on a Unix system where LF is the default newline sequence, the pattern
@@ -3444,7 +3445,7 @@ <h1>pcre2pattern man page</h1>
 </P>
 <br><a name="SEC30" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 18 April 2017
+Last updated: 26 May 2017
 <br>
 Copyright &copy; 1997-2017 University of Cambridge.
 <br>

doc/html/pcre2syntax.html

@@ -468,6 +468,7 @@ <h1>pcre2syntax man page</h1>
   (*CRLF)         carriage return followed by linefeed
   (*ANYCRLF)      all three of the above
   (*ANY)          any Unicode newline sequence
+  (*NUL)          the NUL character (binary zero)
 </PRE>
 </P>
 <br><a name="SEC18" href="#TOC1">WHAT \R MATCHES</a><br>
@@ -598,7 +599,7 @@ <h1>pcre2syntax man page</h1>
 </P>
 <br><a name="SEC27" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 18 April 2017
+Last updated: 26 May 2017
 <br>
 Copyright &copy; 1997-2017 University of Cambridge.
 <br>

doc/html/pcre2test.html

@@ -182,7 +182,7 @@ <h1>pcre2test man page</h1>
   linksize   the configured internal link size (2, 3, or 4)
                exit code is set to the link size
   newline    the default newline setting:
-               CR, LF, CRLF, ANYCRLF, or ANY
+               CR, LF, CRLF, ANYCRLF, ANY, or NUL
                exit code is always 0
   bsr        the default setting for what \R matches:
                ANYCRLF or ANY
@@ -367,8 +367,8 @@ <h1>pcre2test man page</h1>
 </P>
 <P>
 The #newline_default command specifies a list of newline types that are
-acceptable as the default. The types must be one of CR, LF, CRLF, ANYCRLF, or
-ANY (in upper or lower case), for example:
+acceptable as the default. The types must be one of CR, LF, CRLF, ANYCRLF,
+ANY, or NUL (in upper or lower case), for example:
 <pre>
   #newline_default LF Any anyCRLF
 </pre>
@@ -655,7 +655,7 @@ <h1>pcre2test man page</h1>
 <P>
 The <b>newline</b> modifier specifies which characters are to be interpreted as
 newlines, both in the pattern and in subject lines. The type must be one of CR,
-LF, CRLF, ANYCRLF, or ANY (in upper or lower case).
+LF, CRLF, ANYCRLF, ANY, or NUL (in upper or lower case).
 </P>
 <br><b>
 Information about a pattern
@@ -1816,7 +1816,7 @@ <h1>pcre2test man page</h1>
 </P>
 <br><a name="SEC21" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 17 May 2017
+Last updated: 26 May 2017
 <br>
 Copyright &copy; 1997-2017 University of Cambridge.
 <br>