walkero
/
pcre2
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Implement PCRE2_NEWLINE_NUL.

This commit is contained in:
Philip.Hazel 2017-05-26 17:14:36 +00:00
parent 772d857f69
commit 3d80fa4fc2
40 changed files with 1274 additions and 1105 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
CMakeLists.txt
View File

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

1
ChangeLog
View File

@ -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 33. Implement extra compile options in the compile context and add the first
one: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES. one: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES.
34. Implement newline type PCRE2_NEWLINE_NUL.
Version 10.23 14-February-2017 Version 10.23 14-February-2017

5
RunGrepTest
View File

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

7
configure.ac
View File

@ -189,6 +189,10 @@ AC_ARG_ENABLE(newline-is-any,
AS_HELP_STRING([--enable-newline-is-any], AS_HELP_STRING([--enable-newline-is-any],
[use any valid Unicode newline sequence]), [use any valid Unicode newline sequence]),
ac_pcre2_newline=any) 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="$ac_pcre2_newline" enable_newline="$ac_pcre2_newline"
# Handle --enable-bsr-anycrlf # Handle --enable-bsr-anycrlf
@ -360,6 +364,7 @@ case "$enable_newline" in
crlf) ac_pcre2_newline_value=3 ;; crlf) ac_pcre2_newline_value=3 ;;
any) ac_pcre2_newline_value=4 ;; any) ac_pcre2_newline_value=4 ;;
anycrlf) ac_pcre2_newline_value=5 ;; anycrlf) ac_pcre2_newline_value=5 ;;
nul) ac_pcre2_newline_value=6 ;;
*) *)
AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option]) 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 The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values 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), 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 "$enable_bsr_anycrlf" = "yes"; then if test "$enable_bsr_anycrlf" = "yes"; then
AC_DEFINE([BSR_ANYCRLF], [], [ AC_DEFINE([BSR_ANYCRLF], [], [

1
doc/html/pcre2_config.html
View File

@ -57,6 +57,7 @@ point to a uint32_t integer variable. The available codes are:
PCRE2_NEWLINE_CRLF PCRE2_NEWLINE_CRLF
PCRE2_NEWLINE_ANY PCRE2_NEWLINE_ANY
PCRE2_NEWLINE_ANYCRLF PCRE2_NEWLINE_ANYCRLF
PCRE2_NEWLINE_NUL
PCRE2_CONFIG_PARENSLIMIT Default parentheses nesting limit PCRE2_CONFIG_PARENSLIMIT Default parentheses nesting limit
PCRE2_CONFIG_RECURSIONLIMIT Obsolete: use PCRE2_CONFIG_DEPTHLIMIT PCRE2_CONFIG_RECURSIONLIMIT Obsolete: use PCRE2_CONFIG_DEPTHLIMIT
PCRE2_CONFIG_STACKRECURSE Obsolete: always returns 0 PCRE2_CONFIG_STACKRECURSE Obsolete: always returns 0

1
doc/html/pcre2_pattern_info.html
View File

@ -71,6 +71,7 @@ request are as follows:
PCRE2_NEWLINE_CRLF PCRE2_NEWLINE_CRLF
PCRE2_NEWLINE_ANY PCRE2_NEWLINE_ANY
PCRE2_NEWLINE_ANYCRLF PCRE2_NEWLINE_ANYCRLF
PCRE2_NEWLINE_NUL
PCRE2_INFO_RECURSIONLIMIT Obsolete synonym for PCRE2_INFO_DEPTHLIMIT PCRE2_INFO_RECURSIONLIMIT Obsolete synonym for PCRE2_INFO_DEPTHLIMIT
PCRE2_INFO_SIZE Size of compiled pattern PCRE2_INFO_SIZE Size of compiled pattern
</pre> </pre>

1
doc/html/pcre2_set_newline.html
View File

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

9
doc/html/pcre2api.html
View File

@ -783,8 +783,9 @@ PCRE2_SIZE variable can hold, which is effectively unlimited.
This specifies which characters or character sequences are to be recognized as 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), newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character
sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above),
PCRE2_NEWLINE_ANY (any Unicode newline sequence). PCRE2_NEWLINE_ANY (any Unicode newline sequence), or PCRE2_NEWLINE_NUL (the
NUL character, that is a binary zero).
</P> </P>
<P> <P>
A pattern can override the value set in the compile context by starting with a A pattern can override the value set in the compile context by starting with a
@ -1106,6 +1107,7 @@ sequence that is recognized as meaning "newline". The values are:
PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF) PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF)
PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
PCRE2_NEWLINE_NUL The NUL character (binary zero)
</pre> </pre>
The default should normally correspond to the standard sequence for your The default should normally correspond to the standard sequence for your
operating system. operating system.
@ -2121,6 +2123,7 @@ The output is one of the following <b>uint32_t</b> values:
PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF) PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF)
PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
PCRE2_NEWLINE_NUL The NUL character (binary zero)
</pre> </pre>
This identifies the character sequence that will be recognized as meaning This identifies the character sequence that will be recognized as meaning
"newline" while matching. "newline" while matching.
@ -3468,7 +3471,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC42" href="#TOC1">REVISION</a><br> <br><a name="SEC42" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 17 May 2017 Last updated: 26 May 2017
<br> <br>
Copyright &copy; 1997-2017 University of Cambridge. Copyright &copy; 1997-2017 University of Cambridge.
<br> <br>

10
doc/html/pcre2grep.html
View File

@ -142,9 +142,11 @@ standard input is always so treated.
<br><a name="SEC4" href="#TOC1">BINARY FILES</a><br> <br><a name="SEC4" href="#TOC1">BINARY FILES</a><br>
<P> <P>
By default, a file that contains a binary zero byte within the first 1024 bytes 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 is identified as a binary file, and is processed specially. (GNU grep
identifies binary files in this manner.) See the <b>--binary-files</b> option identifies binary files in this manner.) However, if the newline type is
for a means of changing the way binary files are handled. 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> </P>
<br><a name="SEC5" href="#TOC1">OPTIONS</a><br> <br><a name="SEC5" href="#TOC1">OPTIONS</a><br>
<P> <P>
@ -934,7 +936,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC15" href="#TOC1">REVISION</a><br> <br><a name="SEC15" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 11 April 2017 Last updated: 26 May 2017
<br> <br>
Copyright &copy; 1997-2017 University of Cambridge. Copyright &copy; 1997-2017 University of Cambridge.
<br> <br>

11
doc/html/pcre2pattern.html
View File

@ -214,10 +214,10 @@ amount of system stack that is used.
Newline conventions Newline conventions
</b><br> </b><br>
<P> <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) strings: a single CR (carriage return) character, a single LF (linefeed)
character, the two-character sequence CRLF, any of the three preceding, or any character, the two-character sequence CRLF, any of the three preceding, any
Unicode newline sequence. The Unicode newline sequence, or the NUL character (binary zero). The
<a href="pcre2api.html"><b>pcre2api</b></a> <a href="pcre2api.html"><b>pcre2api</b></a>
page has page has
<a href="pcre2api.html#newlines">further discussion</a> <a href="pcre2api.html#newlines">further discussion</a>
@ -226,13 +226,14 @@ about newlines, and shows how to set the newline convention when calling
</P> </P>
<P> <P>
It is also possible to specify a newline convention by starting a pattern 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> <pre>
(*CR) carriage return (*CR) carriage return
(*LF) linefeed (*LF) linefeed
(*CRLF) carriage return, followed by linefeed (*CRLF) carriage return, followed by linefeed
(*ANYCRLF) any of the three above (*ANYCRLF) any of the three above
(*ANY) all Unicode newline sequences (*ANY) all Unicode newline sequences
(*NUL) the NUL character (binary zero)
</pre> </pre>
These override the default and the options given to the compiling function. For 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 example, on a Unix system where LF is the default newline sequence, the pattern
@ -3444,7 +3445,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC30" href="#TOC1">REVISION</a><br> <br><a name="SEC30" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 18 April 2017 Last updated: 26 May 2017
<br> <br>
Copyright &copy; 1997-2017 University of Cambridge. Copyright &copy; 1997-2017 University of Cambridge.
<br> <br>

3
doc/html/pcre2syntax.html
View File

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

10
doc/html/pcre2test.html
View File

@ -182,7 +182,7 @@ following options output the value and set the exit code as indicated:
linksize the configured internal link size (2, 3, or 4) linksize the configured internal link size (2, 3, or 4)
exit code is set to the link size exit code is set to the link size
newline the default newline setting: newline the default newline setting:
CR, LF, CRLF, ANYCRLF, or ANY CR, LF, CRLF, ANYCRLF, ANY, or NUL
exit code is always 0 exit code is always 0
bsr the default setting for what \R matches: bsr the default setting for what \R matches:
ANYCRLF or ANY ANYCRLF or ANY
@ -367,8 +367,8 @@ when PCRE2 is compiled with either CR or CRLF as the default newline.
</P> </P>
<P> <P>
The #newline_default command specifies a list of newline types that are 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 acceptable as the default. The types must be one of CR, LF, CRLF, ANYCRLF,
ANY (in upper or lower case), for example: ANY, or NUL (in upper or lower case), for example:
<pre> <pre>
#newline_default LF Any anyCRLF #newline_default LF Any anyCRLF
</pre> </pre>
@ -655,7 +655,7 @@ is built, with the default default being Unicode.
<P> <P>
The <b>newline</b> modifier specifies which characters are to be interpreted as 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, 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> </P>
<br><b> <br><b>
Information about a pattern Information about a pattern
@ -1816,7 +1816,7 @@ Cambridge, England.
</P> </P>
<br><a name="SEC21" href="#TOC1">REVISION</a><br> <br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 17 May 2017 Last updated: 26 May 2017
<br> <br>
Copyright &copy; 1997-2017 University of Cambridge. Copyright &copy; 1997-2017 University of Cambridge.
<br> <br>

2075
doc/pcre2.txt
View File

File diff suppressed because it is too large Load Diff

3
doc/pcre2_config.3
View File

@ -1,4 +1,4 @@
.TH PCRE2_CONFIG 3 "11 April 2017" "PCRE2 10.30" .TH PCRE2_CONFIG 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS .SH SYNOPSIS
@ -47,6 +47,7 @@ point to a uint32_t integer variable. The available codes are:
PCRE2_NEWLINE_CRLF PCRE2_NEWLINE_CRLF
PCRE2_NEWLINE_ANY PCRE2_NEWLINE_ANY
PCRE2_NEWLINE_ANYCRLF PCRE2_NEWLINE_ANYCRLF
PCRE2_NEWLINE_NUL
PCRE2_CONFIG_PARENSLIMIT Default parentheses nesting limit PCRE2_CONFIG_PARENSLIMIT Default parentheses nesting limit
PCRE2_CONFIG_RECURSIONLIMIT Obsolete: use PCRE2_CONFIG_DEPTHLIMIT PCRE2_CONFIG_RECURSIONLIMIT Obsolete: use PCRE2_CONFIG_DEPTHLIMIT
PCRE2_CONFIG_STACKRECURSE Obsolete: always returns 0 PCRE2_CONFIG_STACKRECURSE Obsolete: always returns 0

3
doc/pcre2_pattern_info.3
View File

@ -1,4 +1,4 @@
.TH PCRE2_PATTERN_INFO 3 "11 April 2017" "PCRE2 10.30" .TH PCRE2_PATTERN_INFO 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS .SH SYNOPSIS
@ -71,6 +71,7 @@ request are as follows:
PCRE2_NEWLINE_CRLF PCRE2_NEWLINE_CRLF
PCRE2_NEWLINE_ANY PCRE2_NEWLINE_ANY
PCRE2_NEWLINE_ANYCRLF PCRE2_NEWLINE_ANYCRLF
PCRE2_NEWLINE_NUL
PCRE2_INFO_RECURSIONLIMIT Obsolete synonym for PCRE2_INFO_DEPTHLIMIT PCRE2_INFO_RECURSIONLIMIT Obsolete synonym for PCRE2_INFO_DEPTHLIMIT
PCRE2_INFO_SIZE Size of compiled pattern PCRE2_INFO_SIZE Size of compiled pattern
.sp .sp

3
doc/pcre2_set_newline.3
View File

@ -1,4 +1,4 @@
.TH PCRE2_SET_NEWLINE 3 "22 October 2014" "PCRE2 10.00" .TH PCRE2_SET_NEWLINE 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS .SH SYNOPSIS
@ -23,6 +23,7 @@ matching patterns. The second argument must be one of:
PCRE2_NEWLINE_CRLF CR followed by LF only PCRE2_NEWLINE_CRLF CR followed by LF only
PCRE2_NEWLINE_ANYCRLF Any of the above PCRE2_NEWLINE_ANYCRLF Any of the above
PCRE2_NEWLINE_ANY Any Unicode newline sequence PCRE2_NEWLINE_ANY Any Unicode newline sequence
PCRE2_NEWLINE_NUL The NUL character (binary zero)
.sp .sp
The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is The result is zero for success or PCRE2_ERROR_BADDATA if the second argument is
invalid. invalid.

11
doc/pcre2api.3
View File

@ -1,4 +1,4 @@
.TH PCRE2API 3 "17 May 2017" "PCRE2 10.30" .TH PCRE2API 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.sp .sp
@ -724,8 +724,9 @@ PCRE2_SIZE variable can hold, which is effectively unlimited.
This specifies which characters or character sequences are to be recognized as 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), newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character
sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above),
PCRE2_NEWLINE_ANY (any Unicode newline sequence). 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 A pattern can override the value set in the compile context by starting with a
sequence such as (*CRLF). See the sequence such as (*CRLF). See the
@ -1039,6 +1040,7 @@ sequence that is recognized as meaning "newline". The values are:
PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF) PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF)
PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
PCRE2_NEWLINE_NUL The NUL character (binary zero)
.sp .sp
The default should normally correspond to the standard sequence for your The default should normally correspond to the standard sequence for your
operating system. operating system.
@ -2090,6 +2092,7 @@ The output is one of the following \fBuint32_t\fP values:
PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF) PCRE2_NEWLINE_CRLF Carriage return, linefeed (CRLF)
PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANY Any Unicode line ending
PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF
PCRE2_NEWLINE_NUL The NUL character (binary zero)
.sp .sp
This identifies the character sequence that will be recognized as meaning This identifies the character sequence that will be recognized as meaning
"newline" while matching. "newline" while matching.
@ -3488,6 +3491,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 17 May 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.
.fi .fi

12
doc/pcre2grep.1
View File

@ -1,4 +1,4 @@
.TH PCRE2GREP 1 "11 April 2017" "PCRE2 10.30" .TH PCRE2GREP 1 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
pcre2grep - a grep with Perl-compatible regular expressions. pcre2grep - a grep with Perl-compatible regular expressions.
.SH SYNOPSIS .SH SYNOPSIS
@ -112,9 +112,11 @@ standard input is always so treated.
.rs .rs
.sp .sp
By default, a file that contains a binary zero byte within the first 1024 bytes 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 is identified as a binary file, and is processed specially. (GNU grep
identifies binary files in this manner.) See the \fB--binary-files\fP option identifies binary files in this manner.) However, if the newline type is
for a means of changing the way binary files are handled. specified as "nul", that is, the line terminator is a binary zero, the test for
a binary file is not applied. See the \fB--binary-files\fP option for a means
of changing the way binary files are handled.
. .
. .
.SH OPTIONS .SH OPTIONS
@ -848,6 +850,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 11 April 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.
.fi .fi

6
doc/pcre2grep.txt
View File

@ -114,7 +114,9 @@ BINARY FILES
By default, a file that contains a binary zero byte within the first 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. 1024 bytes is identified as a binary file, and is processed specially.
(GNU grep also identifies binary files in this manner.) See the (GNU grep identifies binary files in this manner.) However, if the new-
line 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
--binary-files option for a means of changing the way binary files are --binary-files option for a means of changing the way binary files are
handled. handled.
@ -915,5 +917,5 @@ AUTHOR
REVISION REVISION
Last updated: 11 April 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.

13
doc/pcre2pattern.3
View File

@ -1,4 +1,4 @@
.TH PCRE2PATTERN 3 "18 April 2017" "PCRE2 10.30" .TH PCRE2PATTERN 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION DETAILS" .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@ -180,10 +180,10 @@ amount of system stack that is used.
.SS "Newline conventions" .SS "Newline conventions"
.rs .rs
.sp .sp
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) strings: a single CR (carriage return) character, a single LF (linefeed)
character, the two-character sequence CRLF, any of the three preceding, or any character, the two-character sequence CRLF, any of the three preceding, any
Unicode newline sequence. The Unicode newline sequence, or the NUL character (binary zero). The
.\" HREF .\" HREF
\fBpcre2api\fP \fBpcre2api\fP
.\" .\"
@ -196,13 +196,14 @@ about newlines, and shows how to set the newline convention when calling
\fBpcre2_compile()\fP. \fBpcre2_compile()\fP.
.P .P
It is also possible to specify a newline convention by starting a pattern 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:
.sp .sp
(*CR) carriage return (*CR) carriage return
(*LF) linefeed (*LF) linefeed
(*CRLF) carriage return, followed by linefeed (*CRLF) carriage return, followed by linefeed
(*ANYCRLF) any of the three above (*ANYCRLF) any of the three above
(*ANY) all Unicode newline sequences (*ANY) all Unicode newline sequences
(*NUL) the NUL character (binary zero)
.sp .sp
These override the default and the options given to the compiling function. For 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 example, on a Unix system where LF is the default newline sequence, the pattern
@ -3474,6 +3475,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 18 April 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.
.fi .fi

5
doc/pcre2syntax.3
View File

@ -1,4 +1,4 @@
.TH PCRE2SYNTAX 3 "18 April 2017" "PCRE2 10.30" .TH PCRE2SYNTAX 3 "26 May 2017" "PCRE2 10.30"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY" .SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@ -447,6 +447,7 @@ settings with a similar syntax.
(*CRLF) carriage return followed by linefeed (*CRLF) carriage return followed by linefeed
(*ANYCRLF) all three of the above (*ANYCRLF) all three of the above
(*ANY) any Unicode newline sequence (*ANY) any Unicode newline sequence
(*NUL) the NUL character (binary zero)
. .
. .
.SH "WHAT \eR MATCHES" .SH "WHAT \eR MATCHES"
@ -587,6 +588,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 18 April 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.
.fi .fi

12
doc/pcre2test.1
View File

@ -1,4 +1,4 @@
.TH PCRE2TEST 1 "17 May 2017" "PCRE 10.30" .TH PCRE2TEST 1 "26 May 2017" "PCRE 10.30"
.SH NAME .SH NAME
pcre2test - a program for testing Perl-compatible regular expressions. pcre2test - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS .SH SYNOPSIS
@ -150,7 +150,7 @@ following options output the value and set the exit code as indicated:
linksize the configured internal link size (2, 3, or 4) linksize the configured internal link size (2, 3, or 4)
exit code is set to the link size exit code is set to the link size
newline the default newline setting: newline the default newline setting:
CR, LF, CRLF, ANYCRLF, or ANY CR, LF, CRLF, ANYCRLF, ANY, or NUL
exit code is always 0 exit code is always 0
bsr the default setting for what \eR matches: bsr the default setting for what \eR matches:
ANYCRLF or ANY ANYCRLF or ANY
@ -320,8 +320,8 @@ recognized as a newline by default. Without special action the tests would fail
when PCRE2 is compiled with either CR or CRLF as the default newline. when PCRE2 is compiled with either CR or CRLF as the default newline.
.P .P
The #newline_default command specifies a list of newline types that are 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 acceptable as the default. The types must be one of CR, LF, CRLF, ANYCRLF,
ANY (in upper or lower case), for example: ANY, or NUL (in upper or lower case), for example:
.sp .sp
#newline_default LF Any anyCRLF #newline_default LF Any anyCRLF
.sp .sp
@ -617,7 +617,7 @@ is built, with the default default being Unicode.
.P .P
The \fBnewline\fP modifier specifies which characters are to be interpreted as The \fBnewline\fP 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, 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).
. .
. .
.SS "Information about a pattern" .SS "Information about a pattern"
@ -1792,6 +1792,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 17 May 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.
.fi .fi

8
doc/pcre2test.txt
View File

@ -141,7 +141,7 @@ COMMAND LINE OPTIONS
linksize the configured internal link size (2, 3, or 4) linksize the configured internal link size (2, 3, or 4)
exit code is set to the link size exit code is set to the link size
newline the default newline setting: newline the default newline setting:
CR, LF, CRLF, ANYCRLF, or ANY CR, LF, CRLF, ANYCRLF, ANY, or NUL
exit code is always 0 exit code is always 0
bsr the default setting for what \R matches: bsr the default setting for what \R matches:
ANYCRLF or ANY ANYCRLF or ANY
@ -306,7 +306,7 @@ COMMAND LINES
The #newline_default command specifies a list of newline types that are 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, ANY- acceptable as the default. The types must be one of CR, LF, CRLF, ANY-
CRLF, or ANY (in upper or lower case), for example: CRLF, ANY, or NUL (in upper or lower case), for example:
#newline_default LF Any anyCRLF #newline_default LF Any anyCRLF
@ -594,7 +594,7 @@ PATTERN MODIFIERS
The newline modifier specifies which characters are to be interpreted The newline modifier specifies which characters are to be interpreted
as newlines, both in the pattern and in subject lines. The type must be 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). one of CR, LF, CRLF, ANYCRLF, ANY, or NUL (in upper or lower case).
Information about a pattern Information about a pattern
@ -1650,5 +1650,5 @@ AUTHOR
REVISION REVISION
Last updated: 17 May 2017 Last updated: 26 May 2017
Copyright (c) 1997-2017 University of Cambridge. Copyright (c) 1997-2017 University of Cambridge.

4
src/config.h.in
View File

@ -179,8 +179,8 @@ sure both macros are undefined; an emulation function will then be used. */
/* The value of NEWLINE_DEFAULT determines the default newline character /* The value of NEWLINE_DEFAULT determines the default newline character
sequence. PCRE2 client programs can override this by selecting other values 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 at run time. The valid values are 1 (CR), 2 (LF), 3 (CRLF), 4 (ANY), 5
(ANYCRLF). */ (ANYCRLF), and 6 (NUL). */
#undef NEWLINE_DEFAULT #undef NEWLINE_DEFAULT
/* Name of package */ /* Name of package */

1
src/pcre2.h
View File

@ -201,6 +201,7 @@ greater than zero. */
#define PCRE2_NEWLINE_CRLF 3 #define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4 #define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5 #define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1 #define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2 #define PCRE2_BSR_ANYCRLF 2

1
src/pcre2.h.in
View File

@ -201,6 +201,7 @@ greater than zero. */
#define PCRE2_NEWLINE_CRLF 3 #define PCRE2_NEWLINE_CRLF 3
#define PCRE2_NEWLINE_ANY 4 #define PCRE2_NEWLINE_ANY 4
#define PCRE2_NEWLINE_ANYCRLF 5 #define PCRE2_NEWLINE_ANYCRLF 5
#define PCRE2_NEWLINE_NUL 6
#define PCRE2_BSR_UNICODE 1 #define PCRE2_BSR_UNICODE 1
#define PCRE2_BSR_ANYCRLF 2 #define PCRE2_BSR_ANYCRLF 2

10
src/pcre2_compile.c
View File

@ -760,6 +760,7 @@ static pso pso_list[] = {
{ (uint8_t *)STRING_LF_RIGHTPAR, 3, PSO_NL, PCRE2_NEWLINE_LF }, { (uint8_t *)STRING_LF_RIGHTPAR, 3, PSO_NL, PCRE2_NEWLINE_LF },
{ (uint8_t *)STRING_CRLF_RIGHTPAR, 5, PSO_NL, PCRE2_NEWLINE_CRLF }, { (uint8_t *)STRING_CRLF_RIGHTPAR, 5, PSO_NL, PCRE2_NEWLINE_CRLF },
{ (uint8_t *)STRING_ANY_RIGHTPAR, 4, PSO_NL, PCRE2_NEWLINE_ANY }, { (uint8_t *)STRING_ANY_RIGHTPAR, 4, PSO_NL, PCRE2_NEWLINE_ANY },
{ (uint8_t *)STRING_NUL_RIGHTPAR, 4, PSO_NL, PCRE2_NEWLINE_NUL },
{ (uint8_t *)STRING_ANYCRLF_RIGHTPAR, 8, PSO_NL, PCRE2_NEWLINE_ANYCRLF }, { (uint8_t *)STRING_ANYCRLF_RIGHTPAR, 8, PSO_NL, PCRE2_NEWLINE_ANYCRLF },
{ (uint8_t *)STRING_BSR_ANYCRLF_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_ANYCRLF }, { (uint8_t *)STRING_BSR_ANYCRLF_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_ANYCRLF },
{ (uint8_t *)STRING_BSR_UNICODE_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_UNICODE } { (uint8_t *)STRING_BSR_UNICODE_RIGHTPAR, 12, PSO_BSR, PCRE2_BSR_UNICODE }
@ -1911,7 +1912,7 @@ if (c == CHAR_LEFT_CURLY_BRACKET)
{ {
if (ptr >= cb->end_pattern) goto ERROR_RETURN; if (ptr >= cb->end_pattern) goto ERROR_RETURN;
c = *ptr++; c = *ptr++;
if (c == CHAR_NULL) goto ERROR_RETURN; if (c == CHAR_NUL) goto ERROR_RETURN;
if (c == CHAR_RIGHT_CURLY_BRACKET) break; if (c == CHAR_RIGHT_CURLY_BRACKET) break;
name[i] = c; name[i] = c;
} }
@ -6150,7 +6151,7 @@ for (;; pptr++)
} }
else *callout_string++ = *pp++; else *callout_string++ = *pp++;
} }
*callout_string++ = CHAR_NULL; *callout_string++ = CHAR_NUL;
/* Set the length of the entire item, the advance to its end. */ /* Set the length of the entire item, the advance to its end. */
@ -9160,6 +9161,11 @@ switch(newline)
cb.nl[0] = CHAR_NL; cb.nl[0] = CHAR_NL;
break; break;
case PCRE2_NEWLINE_NUL:
cb.nllen = 1;
cb.nl[0] = CHAR_NUL;
break;
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
cb.nllen = 2; cb.nllen = 2;
cb.nl[0] = CHAR_CR; cb.nl[0] = CHAR_CR;

1
src/pcre2_context.c
View File

@ -359,6 +359,7 @@ switch(newline)
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
case PCRE2_NEWLINE_ANY: case PCRE2_NEWLINE_ANY:
case PCRE2_NEWLINE_ANYCRLF: case PCRE2_NEWLINE_ANYCRLF:
case PCRE2_NEWLINE_NUL:
ccontext->newline_convention = newline; ccontext->newline_convention = newline;
return 0; return 0;

4
src/pcre2_convert.c
View File

@ -505,7 +505,7 @@ class_index = 0;
while (TRUE) while (TRUE)
{ {
if (*class_ptr == CHAR_NULL) return 0; if (*class_ptr == CHAR_NUL) return 0;
pattern = start; pattern = start;
@ -1021,7 +1021,7 @@ if (result == 0 || result == ERROR_NO_SLASH_Z)
if (in_atomic) if (in_atomic)
convert_glob_write(&out, CHAR_RIGHT_PARENTHESIS); convert_glob_write(&out, CHAR_RIGHT_PARENTHESIS);
convert_glob_write(&out, CHAR_NULL); convert_glob_write(&out, CHAR_NUL);
result = 0; result = 0;
if (!dummyrun && out.output_size != (PCRE2_SIZE) (out.output - use_buffer)) if (!dummyrun && out.output_size != (PCRE2_SIZE) (out.output - use_buffer))

5
src/pcre2_dfa_match.c
View File

@ -3269,6 +3269,11 @@ switch(re->newline_convention)
mb->nl[0] = CHAR_NL; mb->nl[0] = CHAR_NL;
break; break;
case PCRE2_NEWLINE_NUL:
mb->nllen = 1;
mb->nl[0] = CHAR_NUL;
break;
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
mb->nllen = 2; mb->nllen = 2;
mb->nl[0] = CHAR_CR; mb->nl[0] = CHAR_CR;

4
src/pcre2_error.c
View File

@ -307,8 +307,8 @@ else /* Invalid error number */
for (; n > 0; n--) for (; n > 0; n--)
{ {
while (*message++ != CHAR_NULL) {}; while (*message++ != CHAR_NUL) {};
if (*message == CHAR_NULL) return PCRE2_ERROR_BADDATA; if (*message == CHAR_NUL) return PCRE2_ERROR_BADDATA;
} }
for (i = 0; *message != 0; i++) for (i = 0; *message != 0; i++)

6
src/pcre2_internal.h
View File

@ -678,7 +678,7 @@ a positive value. */
/* The remaining definitions work in both environments. */ /* The remaining definitions work in both environments. */
#define CHAR_NULL '\0' #define CHAR_NUL '\0'
#define CHAR_HT '\t' #define CHAR_HT '\t'
#define CHAR_VT '\v' #define CHAR_VT '\v'
#define CHAR_FF '\f' #define CHAR_FF '\f'
@ -919,6 +919,7 @@ a positive value. */
#define STRING_CRLF_RIGHTPAR "CRLF)" #define STRING_CRLF_RIGHTPAR "CRLF)"
#define STRING_ANY_RIGHTPAR "ANY)" #define STRING_ANY_RIGHTPAR "ANY)"
#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" #define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)"
#define STRING_NUL_RIGHTPAR "NUL)"
#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" #define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)"
#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" #define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)"
#define STRING_UTF8_RIGHTPAR "UTF8)" #define STRING_UTF8_RIGHTPAR "UTF8)"
@ -956,7 +957,7 @@ only. */
#define CHAR_ESC '\033' #define CHAR_ESC '\033'
#define CHAR_DEL '\177' #define CHAR_DEL '\177'
#define CHAR_NULL '\0' #define CHAR_NUL '\0'
#define CHAR_SPACE '\040' #define CHAR_SPACE '\040'
#define CHAR_EXCLAMATION_MARK '\041' #define CHAR_EXCLAMATION_MARK '\041'
#define CHAR_QUOTATION_MARK '\042' #define CHAR_QUOTATION_MARK '\042'
@ -1194,6 +1195,7 @@ only. */
#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS #define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS #define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS
#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS #define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_NUL_RIGHTPAR STR_N STR_U STR_L STR_RIGHT_PARENTHESIS
#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS #define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS #define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS
#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS #define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS

5
src/pcre2_match.c
View File

@ -6246,6 +6246,11 @@ switch(re->newline_convention)
mb->nl[0] = CHAR_NL; mb->nl[0] = CHAR_NL;
break; break;
case PCRE2_NEWLINE_NUL:
mb->nllen = 1;
mb->nl[0] = CHAR_NUL;
break;
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
mb->nllen = 2; mb->nllen = 2;
mb->nl[0] = CHAR_CR; mb->nl[0] = CHAR_CR;

26
src/pcre2grep.c
View File

@ -404,7 +404,7 @@ static option_item optionlist[] = {
{ OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "depth-limit=number", "set PCRE2 depth limit option" }, { OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "depth-limit=number", "set PCRE2 depth limit option" },
{ OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "recursion-limit=number", "obsolete synonym for depth-limit" }, { OP_U32NUMBER, N_M_LIMIT_DEP, &depth_limit, "recursion-limit=number", "obsolete synonym for depth-limit" },
{ OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" },
{ OP_STRING, 'N', &newline_arg, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, { OP_STRING, 'N', &newline_arg, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF, ANY, or NUL)" },
{ OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" },
#ifdef SUPPORT_PCRE2GREP_JIT #ifdef SUPPORT_PCRE2GREP_JIT
{ OP_NODATA, N_NOJIT, NULL, "no-jit", "do not use just-in-time compiler optimization" }, { OP_NODATA, N_NOJIT, NULL, "no-jit", "do not use just-in-time compiler optimization" },
@ -439,7 +439,7 @@ static option_item optionlist[] = {
of PCRE2_NEWLINE_xx in pcre2.h. */ of PCRE2_NEWLINE_xx in pcre2.h. */
static const char *newlines[] = { static const char *newlines[] = {
"DEFAULT", "CR", "LF", "CRLF", "ANY", "ANYCRLF" }; "DEFAULT", "CR", "LF", "CRLF", "ANY", "ANYCRLF", "NUL" };
/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F /* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F
options. These set the 1, 2, and 4 bits in process_options, respectively. Note options. These set the 1, 2, and 4 bits in process_options, respectively. Note
@ -1337,6 +1337,16 @@ switch(endlinetype)
*lenptr = 0; *lenptr = 0;
return endptr; return endptr;
case PCRE2_NEWLINE_NUL:
while (p < endptr && *p != '\0') p++;
if (p < endptr)
{
*lenptr = 1;
return p + 1;
}
*lenptr = 0;
return endptr;
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
for (;;) for (;;)
{ {
@ -1488,6 +1498,11 @@ switch(endlinetype)
while (p > startptr && p[-1] != '\n') p--; while (p > startptr && p[-1] != '\n') p--;
return p; return p;
case PCRE2_NEWLINE_NUL:
p--;
while (p > startptr && p[-1] != '\0') p--;
return p;
case PCRE2_NEWLINE_CRLF: case PCRE2_NEWLINE_CRLF:
for (;;) for (;;)
{ {
@ -2319,12 +2334,13 @@ endptr = main_buffer + bufflength;
/* Unless binary-files=text, see if we have a binary file. This uses the same /* Unless binary-files=text, see if we have a binary file. This uses the same
rule as GNU grep, namely, a search for a binary zero byte near the start of the rule as GNU grep, namely, a search for a binary zero byte near the start of the
file. */ file. However, when the newline convention is binary zero, we can't do this. */
if (binary_files != BIN_TEXT) if (binary_files != BIN_TEXT)
{ {
binary = if (endlinetype != PCRE2_NEWLINE_NUL)
memchr(main_buffer, 0, (bufflength > 1024)? 1024 : bufflength) != NULL; binary = memchr(main_buffer, 0, (bufflength > 1024)? 1024 : bufflength)
!= NULL;
if (binary && binary_files == BIN_NOMATCH) return 1; if (binary && binary_files == BIN_NOMATCH) return 1;
} }

8
src/pcre2test.c
View File

@ -390,7 +390,7 @@ static cmdstruct cmdlist[] = {
of PCRE2_NEWLINE_xx in pcre2.h. */ of PCRE2_NEWLINE_xx in pcre2.h. */
static const char *newlines[] = { static const char *newlines[] = {
"DEFAULT", "CR", "LF", "CRLF", "ANY", "ANYCRLF" }; "DEFAULT", "CR", "LF", "CRLF", "ANY", "ANYCRLF", "NUL" };
/* Structure and table for handling pattern conversion types. */ /* Structure and table for handling pattern conversion types. */
@ -4453,6 +4453,10 @@ if ((pat_patctl.control & CTL_INFO) != 0)
fprintf(outfile, "Forced newline is any Unicode newline\n"); fprintf(outfile, "Forced newline is any Unicode newline\n");
break; break;
case PCRE2_NEWLINE_NUL:
fprintf(outfile, "Forced newline is NUL\n");
break;
default: default:
break; break;
} }
@ -7635,7 +7639,7 @@ printf(" ebcdic compiled for EBCDIC character code [0,1]\n");
printf(" ebcdic-nl NL code if compiled for EBCDIC\n"); printf(" ebcdic-nl NL code if compiled for EBCDIC\n");
printf(" jit just-in-time compiler supported [0, 1]\n"); printf(" jit just-in-time compiler supported [0, 1]\n");
printf(" linksize internal link size [2, 3, 4]\n"); printf(" linksize internal link size [2, 3, 4]\n");
printf(" newline newline type [CR, LF, CRLF, ANYCRLF, ANY]\n"); printf(" newline newline type [CR, LF, CRLF, ANYCRLF, ANY, NUL]\n");
printf(" pcre2-8 8 bit library support enabled [0, 1]\n"); printf(" pcre2-8 8 bit library support enabled [0, 1]\n");
printf(" pcre2-16 16 bit library support enabled [0, 1]\n"); printf(" pcre2-16 16 bit library support enabled [0, 1]\n");
printf(" pcre2-32 32 bit library support enabled [0, 1]\n"); printf(" pcre2-32 32 bit library support enabled [0, 1]\n");

3
testdata/grepoutputN vendored
View File

@ -13,4 +13,5 @@ jkl---------------------------- Test N5 ------------------------------
4:jkl---------------------------- Test N6 ------------------------------ 4:jkl---------------------------- Test N6 ------------------------------
1:abc 2:def 1:abc 2:def
3:ghi 3:ghi
4:jkl 4:jkl---------------------------- Test N7 ------------------------------
1:abcZERO2:def

18
testdata/testinput2 vendored
View File

@ -2258,6 +2258,24 @@
/(*CRLF).*/g /(*CRLF).*/g
abc\r\ndef abc\r\ndef
/(*NUL)^.*/
a\nb\x00ccc
/(*NUL)^.*/s
a\nb\x00ccc
/^x/m,newline=NUL
ab\x00xy
/'#comment' 0d 0a 00 '^x\' 0a 'y'/x,newline=nul,hex
x\nyz
/(*NUL)^X\NY/
X\nY
X\rY
\= Expect no match
X\x00Y
/a\Rb/I,bsr=anycrlf /a\Rb/I,bsr=anycrlf
a\rb a\rb
a\nb a\nb

18
testdata/testinput6 vendored
View File

@ -4911,4 +4911,22 @@
\= Expect no match \= Expect no match
xyzabcdef xyzabcdef
/(*NUL)^.*/
a\nb\x00ccc
/(*NUL)^.*/s
a\nb\x00ccc
/^x/m,newline=nul
ab\x00xy
/'#comment' 0d 0a 00 '^x\' 0a 'y'/x,newline=nul,hex
x\nyz
/(*NUL)^X\NY/
X\nY
X\rY
\= Expect no match
X\x00Y
# End of testinput6 # End of testinput6

25
testdata/testoutput2 vendored
View File

@ -8314,6 +8314,31 @@ No match
0: def 0: def
0: 0:
/(*NUL)^.*/
a\nb\x00ccc
0: a\x0ab
/(*NUL)^.*/s
a\nb\x00ccc
0: a\x0ab\x00ccc
/^x/m,newline=NUL
ab\x00xy
0: x
/'#comment' 0d 0a 00 '^x\' 0a 'y'/x,newline=nul,hex
x\nyz
0: x\x0ay
/(*NUL)^X\NY/
X\nY
0: X\x0aY
X\rY
0: X\x0dY
\= Expect no match
X\x00Y
No match
/a\Rb/I,bsr=anycrlf /a\Rb/I,bsr=anycrlf
Capturing subpattern count = 0 Capturing subpattern count = 0
\R matches CR, LF, or CRLF \R matches CR, LF, or CRLF

25
testdata/testoutput6 vendored
View File

@ -7721,4 +7721,29 @@ Failed: error -34: bad option value
xyzabcdef xyzabcdef
No match No match
/(*NUL)^.*/
a\nb\x00ccc
0: a\x0ab
/(*NUL)^.*/s
a\nb\x00ccc
0: a\x0ab\x00ccc
/^x/m,newline=nul
ab\x00xy
0: x
/'#comment' 0d 0a 00 '^x\' 0a 'y'/x,newline=nul,hex
x\nyz
0: x\x0ay
/(*NUL)^X\NY/
X\nY
0: X\x0aY
X\rY
0: X\x0dY
\= Expect no match
X\x00Y
No match
# End of testinput6 # End of testinput6