Revision: 1274
http://www.exim.org/viewvc/pcre2?view=rev&revision=1274
Author: ph10
Date: 2020-10-04 17:34:31 +0100 (Sun, 04 Oct 2020)
Log Message:
-----------
pcre2grep update: -m and $x{..}, $o{..} escapes. Also some doc updates.
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/README
code/trunk/RunGrepTest
code/trunk/doc/html/README.txt
code/trunk/doc/html/pcre2grep.html
code/trunk/doc/html/pcre2test.html
code/trunk/doc/pcre2.txt
code/trunk/doc/pcre2grep.1
code/trunk/doc/pcre2grep.txt
code/trunk/doc/pcre2test.txt
code/trunk/src/pcre2grep.c
code/trunk/testdata/grepoutput
code/trunk/testdata/grepoutput8
code/trunk/testdata/grepoutputC
code/trunk/testdata/grepoutputCN
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/ChangeLog 2020-10-04 16:34:31 UTC (rev 1274)
@@ -76,7 +76,17 @@
14. Fixed a bug in character set matching when JIT is enabled and both unicode
scripts and unicode classes are present at the same time.
+15. Added GNU grep's -m (aka --max-count) option to pcre2grep.
+16. Refactored substitution processing in pcre2grep strings, both for the -O
+option and when dealing with callouts. There is now a single function that
+handles $ expansion in all cases (instead of multiple copies of almost
+identical code). This means that the same escape sequences are available
+everywhere, which was not previously the case. At the same time, the escape
+sequences $x{...} and $o{...} have been introduced, to allow for characters
+whose code points are greater than 255 in Unicode mode.
+
+
Version 10.35 09-May-2020
---------------------------
Modified: code/trunk/README
===================================================================
--- code/trunk/README 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/README 2020-10-04 16:34:31 UTC (rev 1274)
@@ -892,6 +892,6 @@
) environments
Philip Hazel
-Email local part: ph10
-Email domain: cam.ac.uk
-Last updated: 20 March 2020
+Email local part: Philip.Hazel
+Email domain: gmail.com
+Last updated: 22 September 2020
Modified: code/trunk/RunGrepTest
===================================================================
--- code/trunk/RunGrepTest 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/RunGrepTest 2020-10-04 16:34:31 UTC (rev 1274)
@@ -661,6 +661,26 @@
(cd $srcdir; $valgrind $vjs $pcre2grep -o1 --om-capture=0 'pattern()()()()' testdata/grepinput) >>testtrygrep 2>&1
echo "RC=$?" >>testtrygrep
+echo "---------------------------- Test 129 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m 2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 130 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -o -m2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 131 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -oc -m2 'fox' testdata/grepinput) >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 132 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m1 -A3 '^match'; echo '---'; head -1) <testdata/grepinput >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
+echo "---------------------------- Test 133 -----------------------------" >>testtrygrep
+(cd $srcdir; $valgrind $vjs $pcre2grep -m1 -O '=$x{41}$x423$o{103}$o1045=' 'fox') <testdata/grepinputv >>testtrygrep 2>&1
+echo "RC=$?" >>testtrygrep
+
# Now compare the results.
$cf $srcdir/testdata/grepoutput testtrygrep
@@ -694,6 +714,10 @@
(cd $srcdir; $valgrind $vjs $pcre2grep -U -o '....' $builddir/testtemp1grep) >>testtrygrep
echo "RC=$?" >>testtrygrep
+ echo "---------------------------- Test U6 -----------------------------" >>testtrygrep
+ (cd $srcdir; $valgrind $vjs $pcre2grep -u -m1 -O '=$x{1d3}$o{744}=' 'fox') <testdata/grepinputv >>testtrygrep 2>&1
+ echo "RC=$?" >>testtrygrep
+
$cf $srcdir/testdata/grepoutput8 testtrygrep
if [ $? != 0 ] ; then exit 1; fi
@@ -764,6 +788,7 @@
$valgrind $vjs $pcre2grep '(T)(..(.))()()()()()()()(..)(?C"/bin/echo|Arg1: [$11] [${11}]")' $srcdir/testdata/grepinputv >>testtrygrep
$valgrind $vjs $pcre2grep '(T)(?C"|$0:$1$n")' $srcdir/testdata/grepinputv >>testtrygrep
$valgrind $vjs $pcre2grep '(T)(?C"|$1$n")(*F)' $srcdir/testdata/grepinputv >>testtrygrep
+ $valgrind $vjs $pcre2grep -m1 '(T)(?C"|$0:$1:$x{41}$o{101}$n")' $srcdir/testdata/grepinputv >>testtrygrep
if $valgrind $vjs $pcre2grep --help | $valgrind $vjs $pcre2grep -q 'Non-fork callout scripts in patterns are supported'; then
$cf $srcdir/testdata/grepoutputCN testtrygrep
Modified: code/trunk/doc/html/README.txt
===================================================================
--- code/trunk/doc/html/README.txt 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/html/README.txt 2020-10-04 16:34:31 UTC (rev 1274)
@@ -892,6 +892,6 @@
) environments
Philip Hazel
-Email local part: ph10
-Email domain: cam.ac.uk
-Last updated: 20 March 2020
+Email local part: Philip.Hazel
+Email domain: gmail.com
+Last updated: 22 September 2020
Modified: code/trunk/doc/html/pcre2grep.html
===================================================================
--- code/trunk/doc/html/pcre2grep.html 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/html/pcre2grep.html 2020-10-04 16:34:31 UTC (rev 1274)
@@ -111,8 +111,8 @@
(either shown literally, or as an offset), scanning resumes immediately
following the match, so that further matches on the same line can be found. If
there are multiple patterns, they are all tried on the remainder of the line,
-but patterns that follow the one that matched are not tried on the earlier part
-of the line.
+but patterns that follow the one that matched are not tried on the earlier
+matched part of the line.
</P>
<P>
This behaviour means that the order in which multiple patterns are specified
@@ -146,11 +146,10 @@
<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
-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.
+is identified as a binary file, and is processed specially. 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">BINARY ZEROS IN PATTERNS</a><br>
<P>
@@ -443,8 +442,8 @@
<P>
<b>--include</b>=<i>pattern</i>
If any <b>--include</b> patterns are specified, the only files that are
-processed are those that match one of the patterns (and do not match an
-<b>--exclude</b> pattern). This option does not affect directories, but it
+processed are those whose names match one of the patterns and do not match an
+<b>--exclude</b> pattern. This option does not affect directories, but it
applies to all files, whether listed on the command line, obtained from
<b>--file-list</b>, or by scanning a directory. The pattern is a PCRE2 regular
expression, and is matched against the final component of the file name, not
@@ -463,8 +462,8 @@
<P>
<b>--include-dir</b>=<i>pattern</i>
If any <b>--include-dir</b> patterns are specified, the only directories that
-are processed are those that match one of the patterns (and do not match an
-<b>--exclude-dir</b> pattern). This applies to all directories, whether listed
+are processed are those whose names match one of the patterns and do not match
+an <b>--exclude-dir</b> pattern. This applies to all directories, whether listed
on the command line, obtained from <b>--file-list</b>, or by scanning a parent
directory. The pattern is a PCRE2 regular expression, and is matched against
the final component of the directory name, not the entire path. The <b>-F</b>,
@@ -487,8 +486,9 @@
in a file. However, if the <b>-c</b> (count) option is also used, matching
continues in order to obtain the correct count, and those files that have at
least one match are listed along with their counts. Using this option with
-<b>-c</b> is a way of suppressing the listing of files with no matches. This
-opeion overrides any previous <b>-H</b>, <b>-h</b>, or <b>-L</b> options.
+<b>-c</b> is a way of suppressing the listing of files with no matches that
+occurs with <b>-c</b> on its own. This option overrides any previous <b>-H</b>,
+<b>-h</b>, or <b>-L</b> options.
</P>
<P>
<b>--label</b>=<i>name</i>
@@ -501,8 +501,8 @@
When this option is given, non-compressed input is read and processed line by
line, and the output is flushed after each write. By default, input is read in
large chunks, unless <b>pcre2grep</b> can determine that it is reading from a
-terminal (which is currently possible only in Unix-like environments or
-Windows). Output to terminal is normally automatically flushed by the operating
+terminal, which is currently possible only in Unix-like environments or
+Windows. Output to terminal is normally automatically flushed by the operating
system. This option can be useful when the input or output is attached to a
pipe and you do not want <b>pcre2grep</b> to buffer up large amounts of data.
However, its use will affect performance, and the <b>-M</b> (multiline) option
@@ -528,6 +528,49 @@
used. There is no short form for this option.
</P>
<P>
+<b>-M</b>, <b>--multiline</b>
+Allow patterns to match more than one line. When this option is set, the PCRE2
+library is called in "multiline" mode. This allows a matched string to extend
+past the end of a line and continue on one or more subsequent lines. Patterns
+used with <b>-M</b> may usefully contain literal newline characters and internal
+occurrences of ^ and $ characters. The output for a successful match may
+consist of more than one line. The first line is the line in which the match
+started, and the last line is the line in which the match ended. If the matched
+string ends with a newline sequence, the output ends at the end of that line.
+If <b>-v</b> is set, none of the lines in a multi-line match are output. Once a
+match has been handled, scanning restarts at the beginning of the line after
+the one in which the match ended.
+<br>
+<br>
+The newline sequence that separates multiple lines must be matched as part of
+the pattern. For example, to find the phrase "regular expression" in a file
+where "regular" might be at the end of a line and "expression" at the start of
+the next line, you could use this command:
+<pre>
+ pcre2grep -M 'regular\s+expression' <file>
+</pre>
+The \s escape sequence matches any white space character, including newlines,
+and is followed by + so as to match trailing white space on the first line as
+well as possibly handling a two-character newline sequence.
+<br>
+<br>
+There is a limit to the number of lines that can be matched, imposed by the way
+that <b>pcre2grep</b> buffers the input file as it scans it. With a sufficiently
+large processing buffer, this should not be a problem, but the <b>-M</b> option
+does not work when input is read line by line (see <b>--line-buffered</b>.)
+</P>
+<P>
+<b>-m</b> <i>number</i>, <b>--max-count</b>=<i>number</i>
+Stop processing after finding <i>number</i> matching lines, or non-matching
+lines if <b>-v</b> is also set. Any trailing context lines are output after the
+final match. In multiline mode, each multiline match counts as just one line
+for this purpose. If this limit is reached when reading the standard input from
+a regular file, the file is left positioned just after the last matching line.
+If <b>-c</b> is also set, the count that is output is never greater than
+<i>number</i>. This option has no effect if used with <b>-L</b>, <b>-l</b>, or
+<b>-q</b>, or when just checking for a match in a binary file.
+</P>
+<P>
<b>--match-limit</b>=<i>number</i>
Processing some regular expression patterns may take a very long time to search
for all possible matching strings. Others may require a very large amount of
@@ -568,38 +611,6 @@
smaller than the starting buffer size.
</P>
<P>
-<b>-M</b>, <b>--multiline</b>
-Allow patterns to match more than one line. When this option is set, the PCRE2
-library is called in "multiline" mode. This allows a matched string to extend
-past the end of a line and continue on one or more subsequent lines. Patterns
-used with <b>-M</b> may usefully contain literal newline characters and internal
-occurrences of ^ and $ characters. The output for a successful match may
-consist of more than one line. The first line is the line in which the match
-started, and the last line is the line in which the match ended. If the matched
-string ends with a newline sequence, the output ends at the end of that line.
-If <b>-v</b> is set, none of the lines in a multi-line match are output. Once a
-match has been handled, scanning restarts at the beginning of the line after
-the one in which the match ended.
-<br>
-<br>
-The newline sequence that separates multiple lines must be matched as part of
-the pattern. For example, to find the phrase "regular expression" in a file
-where "regular" might be at the end of a line and "expression" at the start of
-the next line, you could use this command:
-<pre>
- pcre2grep -M 'regular\s+expression' <file>
-</pre>
-The \s escape sequence matches any white space character, including newlines,
-and is followed by + so as to match trailing white space on the first line as
-well as possibly handling a two-character newline sequence.
-<br>
-<br>
-There is a limit to the number of lines that can be matched, imposed by the way
-that <b>pcre2grep</b> buffers the input file as it scans it. With a sufficiently
-large processing buffer, this should not be a problem, but the <b>-M</b> option
-does not work when input is read line by line (see <b>--line-buffered</b>.)
-</P>
-<P>
<b>-N</b> <i>newline-type</i>, <b>--newline</b>=<i>newline-type</i>
Six different conventions for indicating the ends of lines in scanned files are
supported. For example:
@@ -648,31 +659,41 @@
</P>
<P>
<b>-O</b> <i>text</i>, <b>--output</b>=<i>text</i>
-When there is a match, instead of outputting the whole line that matched,
-output just the given text, followed by an operating-system standard newline.
-The <b>--newline</b> option has no effect on this option, which is mutually
-exclusive with <b>--only-matching</b>, <b>--file-offsets</b>, and
-<b>--line-offsets</b>. Escape sequences starting with a dollar character may be
-used to insert the contents of the matched part of the line and/or captured
-substrings into the text.
+When there is a match, instead of outputting the line that matched, output just
+the text specified in this option, followed by an operating-system standard
+newline. In this mode, no context is shown. That is, the <b>-A</b>, <b>-B</b>,
+and <b>-C</b> options are ignored. The <b>--newline</b> option has no effect on
+this option, which is mutually exclusive with <b>--only-matching</b>,
+<b>--file-offsets</b>, and <b>--line-offsets</b>. However, like
+<b>--only-matching</b>, if there is more than one match in a line, each of them
+causes a line of output.
<br>
<br>
-$<digits> or ${<digits>} is replaced by the captured
-substring of the given decimal number; zero substitutes the whole match. If
-the number is greater than the number of capturing substrings, or if the
-capture is unset, the replacement is empty.
+Escape sequences starting with a dollar character may be used to insert the
+contents of the matched part of the line and/or captured substrings into the
+text.
<br>
<br>
+$<digits> or ${<digits>} is replaced by the captured substring of the given
+decimal number; zero substitutes the whole match. If the number is greater than
+the number of capturing substrings, or if the capture is unset, the replacement
+is empty.
+<br>
+<br>
$a is replaced by bell; $b by backspace; $e by escape; $f by form feed; $n by
newline; $r by carriage return; $t by tab; $v by vertical tab.
<br>
<br>
-$o<digits> is replaced by the character represented by the given octal
-number; up to three digits are processed.
+$o<digits> or $o{<digits>} is replaced by the character whose code point is the
+given octal number. In the first form, up to three octal digits are processed.
+When more digits are needed in Unicode mode to specify a wide character, the
+second form must be used.
<br>
<br>
-$x<digits> is replaced by the character represented by the given hexadecimal
-number; up to two digits are processed.
+$x<digits> or $x{<digits>} is replaced by the character represented by the
+given hexadecimal number. In the first form, up to two hexadecimal digits are
+processed. When more digits are needed in Unicode mode to specify a wide
+character, the second form must be used.
<br>
<br>
Any other character is substituted by itself. In particular, $$ is replaced by
@@ -741,7 +762,8 @@
</P>
<P>
<b>--recursion-limit</b>=<i>number</i>
-See <b>--match-limit</b> above.
+This is an obsolete synonym for <b>--depth-limit</b>. See <b>--match-limit</b>
+above for details.
</P>
<P>
<b>-s</b>, <b>--no-messages</b>
@@ -765,15 +787,18 @@
<b>-u</b>, <b>--utf</b>
Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
with UTF-8 support. All patterns (including those for any <b>--exclude</b> and
-<b>--include</b> options) and all subject lines that are scanned must be valid
-strings of UTF-8 characters.
+<b>--include</b> options) and all lines that are scanned must be valid strings
+of UTF-8 characters. If an invalid UTF-8 string is encountered, an error
+occurs.
</P>
<P>
<b>-U</b>, <b>--utf-allow-invalid</b>
As <b>--utf</b>, but in addition subject lines may contain invalid UTF-8 code
-unit sequences. These can never form part of any pattern match. This facility
-allows valid UTF-8 strings to be sought in executable or other binary files.
-For more details about matching in non-valid UTF-8 strings, see the
+unit sequences. These can never form part of any pattern match. Patterns
+themselves, however, must still be valid UTF-8 strings. This facility allows
+valid UTF-8 strings to be sought within arbitrary byte sequences in executable
+or other binary files. For more details about matching in non-valid UTF-8
+strings, see the
<a href="pcre2unicode.html"><b>pcre2unicode</b>(3)</a>
documentation.
</P>
@@ -786,7 +811,9 @@
<P>
<b>-v</b>, <b>--invert-match</b>
Invert the sense of the match, so that lines which do <i>not</i> match any of
-the patterns are the ones that are found.
+the patterns are the ones that are found. When this option is set, options such
+as <b>--only-matching</b> and <b>--output</b>, which specify parts of a match
+that are to be output, are ignored.
</P>
<P>
<b>-w</b>, <b>--word-regex</b>, <b>--word-regexp</b>
@@ -909,12 +936,36 @@
only callouts with string arguments are useful.
</P>
<br><b>
+Echoing a specific string
+</b><br>
+<P>
+Starting the callout string with a pipe character invokes an echoing facility
+that avoids calling an external program or script. This facility is always
+available, provided that callouts were not completely disabled when
+<b>pcre2grep</b> was built. The rest of the callout string is processed as a
+zero-terminated string, which means it should not contain any internal binary
+zeros. It is written to the output, having first been passed through the same
+escape processing as text from the <b>--output</b> (<b>-O</b>) option (see
+above). However, $0 cannot be used to insert a matched substring because the
+match is still in progress. Instead, the single character '0' is inserted. Any
+syntax errors in the string (for example, a dollar not followed by another
+character) causes the callout to be ignored. No terminator is added to the
+output string, so if you want a newline, you must include it explicitly using
+the escape $n. For example:
+<pre>
+ pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' <some file>
+</pre>
+Matching continues normally after the string is output. If you want to see only
+the callout output but not any output from an actual match, you should end the
+pattern with (*FAIL).
+</P>
+<br><b>
Calling external programs or scripts
</b><br>
<P>
This facility can be independently disabled when <b>pcre2grep</b> is built. It
is supported for Windows, where a call to <b>_spawnvp()</b> is used, for VMS,
-where <b>lib$spawn()</b> is used, and for any other Unix-like environment where
+where <b>lib$spawn()</b> is used, and for any Unix-like environment where
<b>fork()</b> and <b>execv()</b> are available.
</P>
<P>
@@ -926,14 +977,11 @@
executable_name|arg1|arg2|...
</pre>
Any substring (including the executable name) may contain escape sequences
-started by a dollar character: $<digits> or ${<digits>} is replaced by the
-captured substring of the given decimal number, which must be greater than
-zero. If the number is greater than the number of capturing substrings, or if
-the capture is unset, the replacement is empty.
-</P>
-<P>
-Any other character is substituted by itself. In particular, $$ is replaced by
-a single dollar and $| is replaced by a pipe character. Here is an example:
+started by a dollar character. These are the same as for the <b>--output</b>
+(<b>-O</b>) option documented above, except that $0 cannot insert the matched
+string because the match is still in progress. Instead, the character '0'
+is inserted. If you need a literal dollar or pipe character in any
+substring, use $$ or $| respectively. Here is an example:
<pre>
echo -e "abcde\n12345" | pcre2grep \
'(?x)(.)(..(.))
@@ -946,29 +994,15 @@
Arg1: [1] [234] [4] Arg2: |1| ()
12345
</pre>
-The parameters for the system call that is used to run the
-program or script are zero-terminated strings. This means that binary zero
-characters in the callout argument will cause premature termination of their
-substrings, and therefore should not be present. Any syntax errors in the
-string (for example, a dollar not followed by another character) cause the
-callout to be ignored. If running the program fails for any reason (including
-the non-existence of the executable), a local matching failure occurs and the
-matcher backtracks in the normal way.
+The parameters for the system call that is used to run the program or script
+are zero-terminated strings. This means that binary zero characters in the
+callout argument will cause premature termination of their substrings, and
+therefore should not be present. Any syntax errors in the string (for example,
+a dollar not followed by another character) causes the callout to be ignored.
+If running the program fails for any reason (including the non-existence of the
+executable), a local matching failure occurs and the matcher backtracks in the
+normal way.
</P>
-<br><b>
-Echoing a specific string
-</b><br>
-<P>
-This facility is always available, provided that callouts were not completely
-disabled when <b>pcre2grep</b> was built. If the callout string starts with a
-pipe (vertical bar) character, the rest of the string is written to the output,
-having been passed through the same escape processing as text from the --output
-option. This provides a simple echoing facility that avoids calling an external
-program or script. No terminator is added to the string, so if you want a
-newline, you must include it explicitly. Matching continues normally after the
-string is output. If you want to see only the callout output but not any output
-from an actual match, you should end the relevant pattern with (*FAIL).
-</P>
<br><a name="SEC12" href="#TOC1">MATCHING ERRORS</a><br>
<P>
It is possible to supply a regular expression that takes a very long time to
@@ -999,7 +1033,8 @@
</P>
<br><a name="SEC14" href="#TOC1">SEE ALSO</a><br>
<P>
-<b>pcre2pattern</b>(3), <b>pcre2syntax</b>(3), <b>pcre2callout</b>(3).
+<b>pcre2pattern</b>(3), <b>pcre2syntax</b>(3), <b>pcre2callout</b>(3),
+<b>pcre2unicode</b>(3).
</P>
<br><a name="SEC15" href="#TOC1">AUTHOR</a><br>
<P>
@@ -1012,7 +1047,7 @@
</P>
<br><a name="SEC16" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 25 January 2020
+Last updated: 04 October 2020
<br>
Copyright © 1997-2020 University of Cambridge.
<br>
Modified: code/trunk/doc/html/pcre2test.html
===================================================================
--- code/trunk/doc/html/pcre2test.html 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/html/pcre2test.html 2020-10-04 16:34:31 UTC (rev 1274)
@@ -323,7 +323,7 @@
some restrictions, can also be processed by the <b>perltest.sh</b> script that
is distributed with PCRE2 as a means of checking that the behaviour of PCRE2
and Perl is the same. For a specification of <b>perltest.sh</b>, see the
-comments near its beginning.
+comments near its beginning. See also the #perltest command below.
</P>
<P>
When the input is a terminal, <b>pcre2test</b> prompts for each line of input,
@@ -420,14 +420,20 @@
<pre>
#perltest
</pre>
-The appearance of this line causes all subsequent modifier settings to be
-checked for compatibility with the <b>perltest.sh</b> script, which is used to
-confirm that Perl gives the same results as PCRE2. Also, apart from comment
-lines, #pattern commands, and #subject commands that set or unset "mark", no
-command lines are permitted, because they and many of the modifiers are
-specific to <b>pcre2test</b>, and should not be used in test files that are also
-processed by <b>perltest.sh</b>. The <b>#perltest</b> command helps detect tests
-that are accidentally put in the wrong file.
+This line is used in test files that can also be processed by <b>perltest.sh</b>
+to confirm that Perl gives the same results as PCRE2. Subsequent tests are
+checked for the use of <b>pcre2test</b> features that are incompatible with the
+<b>perltest.sh</b> script.
+</P>
+<P>
+Patterns must use '/' as their delimiter, and only certain modifiers are
+supported. Comment lines, #pattern commands, and #subject commands that set or
+unset "mark" are recognized and acted on. The #perltest, #forbid_utf, and
+#newline_default commands, which are needed in the relevant pcre2test files,
+are silently ignored. All other command lines are ignored, but give a warning
+message. The <b>#perltest</b> command helps detect tests that are accidentally
+put in the wrong file or use the wrong delimiter. For more details of the
+<b>perltest.sh</b> script see the comments it contains.
<pre>
#pop [<modifiers>]
#popcopy [<modifiers>]
@@ -2113,7 +2119,7 @@
</P>
<br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P>
-Last updated: 20 March 2020
+Last updated: 14 September 2020
<br>
Copyright © 1997-2020 University of Cambridge.
<br>
Modified: code/trunk/doc/pcre2.txt
===================================================================
--- code/trunk/doc/pcre2.txt 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/pcre2.txt 2020-10-04 16:34:31 UTC (rev 1274)
@@ -180,8 +180,8 @@
Last updated: 17 September 2018
Copyright (c) 1997-2018 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2API(3) Library Functions Manual PCRE2API(3)
@@ -3796,8 +3796,8 @@
Last updated: 19 March 2020
Copyright (c) 1997-2020 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3)
@@ -4390,8 +4390,8 @@
Last updated: 20 March 2020
Copyright (c) 1997-2020 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3)
@@ -4820,8 +4820,8 @@
Last updated: 03 February 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3)
@@ -5029,8 +5029,8 @@
Last updated: 13 July 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2JIT(3) Library Functions Manual PCRE2JIT(3)
@@ -5454,8 +5454,8 @@
Last updated: 23 May 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3)
@@ -5524,8 +5524,8 @@
Last updated: 02 February 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3)
@@ -5748,8 +5748,8 @@
Last updated: 23 May 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3)
@@ -6128,8 +6128,8 @@
Last updated: 04 September 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PATTERN(3) Library Functions Manual PCRE2PATTERN(3)
@@ -9562,8 +9562,8 @@
Last updated: 24 February 2020
Copyright (c) 1997-2020 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2PERFORM(3) Library Functions Manual PCRE2PERFORM(3)
@@ -9797,8 +9797,8 @@
Last updated: 03 February 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2POSIX(3) Library Functions Manual PCRE2POSIX(3)
@@ -10127,8 +10127,8 @@
Last updated: 30 January 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2SAMPLE(3) Library Functions Manual PCRE2SAMPLE(3)
@@ -10406,8 +10406,8 @@
Last updated: 27 June 2018
Copyright (c) 1997-2018 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2SYNTAX(3) Library Functions Manual PCRE2SYNTAX(3)
@@ -10922,8 +10922,8 @@
Last updated: 28 December 2019
Copyright (c) 1997-2019 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3)
@@ -11357,5 +11357,5 @@
Last updated: 23 February 2020
Copyright (c) 1997-2020 University of Cambridge.
------------------------------------------------------------------------------
-
-
+
+
Modified: code/trunk/doc/pcre2grep.1
===================================================================
--- code/trunk/doc/pcre2grep.1 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/pcre2grep.1 2020-10-04 16:34:31 UTC (rev 1274)
@@ -1,4 +1,4 @@
-.TH PCRE2GREP 1 "25 January 2020" "PCRE2 10.35"
+.TH PCRE2GREP 1 "04 October 2020" "PCRE2 10.36"
.SH NAME
pcre2grep - a grep with Perl-compatible regular expressions.
.SH SYNOPSIS
@@ -79,8 +79,8 @@
(either shown literally, or as an offset), scanning resumes immediately
following the match, so that further matches on the same line can be found. If
there are multiple patterns, they are all tried on the remainder of the line,
-but patterns that follow the one that matched are not tried on the earlier part
-of the line.
+but patterns that follow the one that matched are not tried on the earlier
+matched part of the line.
.P
This behaviour means that the order in which multiple patterns are specified
can affect the output when one of the above options is used. This is no longer
@@ -115,11 +115,10 @@
.rs
.sp
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
-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 \fB--binary-files\fP option for a means
-of changing the way binary files are handled.
+is identified as a binary file, and is processed specially. 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 \fB--binary-files\fP
+option for a means of changing the way binary files are handled.
.
.
.SH "BINARY ZEROS IN PATTERNS"
@@ -383,8 +382,8 @@
.TP
\fB--include\fP=\fIpattern\fP
If any \fB--include\fP patterns are specified, the only files that are
-processed are those that match one of the patterns (and do not match an
-\fB--exclude\fP pattern). This option does not affect directories, but it
+processed are those whose names match one of the patterns and do not match an
+\fB--exclude\fP pattern. This option does not affect directories, but it
applies to all files, whether listed on the command line, obtained from
\fB--file-list\fP, or by scanning a directory. The pattern is a PCRE2 regular
expression, and is matched against the final component of the file name, not
@@ -401,8 +400,8 @@
.TP
\fB--include-dir\fP=\fIpattern\fP
If any \fB--include-dir\fP patterns are specified, the only directories that
-are processed are those that match one of the patterns (and do not match an
-\fB--exclude-dir\fP pattern). This applies to all directories, whether listed
+are processed are those whose names match one of the patterns and do not match
+an \fB--exclude-dir\fP pattern. This applies to all directories, whether listed
on the command line, obtained from \fB--file-list\fP, or by scanning a parent
directory. The pattern is a PCRE2 regular expression, and is matched against
the final component of the directory name, not the entire path. The \fB-F\fP,
@@ -423,8 +422,9 @@
in a file. However, if the \fB-c\fP (count) option is also used, matching
continues in order to obtain the correct count, and those files that have at
least one match are listed along with their counts. Using this option with
-\fB-c\fP is a way of suppressing the listing of files with no matches. This
-opeion overrides any previous \fB-H\fP, \fB-h\fP, or \fB-L\fP options.
+\fB-c\fP is a way of suppressing the listing of files with no matches that
+occurs with \fB-c\fP on its own. This option overrides any previous \fB-H\fP,
+\fB-h\fP, or \fB-L\fP options.
.TP
\fB--label\fP=\fIname\fP
This option supplies a name to be used for the standard input when file names
@@ -435,8 +435,8 @@
When this option is given, non-compressed input is read and processed line by
line, and the output is flushed after each write. By default, input is read in
large chunks, unless \fBpcre2grep\fP can determine that it is reading from a
-terminal (which is currently possible only in Unix-like environments or
-Windows). Output to terminal is normally automatically flushed by the operating
+terminal, which is currently possible only in Unix-like environments or
+Windows. Output to terminal is normally automatically flushed by the operating
system. This option can be useful when the input or output is attached to a
pipe and you do not want \fBpcre2grep\fP to buffer up large amounts of data.
However, its use will affect performance, and the \fB-M\fP (multiline) option
@@ -459,6 +459,45 @@
locale is specified, the PCRE2 library's default (usually the "C" locale) is
used. There is no short form for this option.
.TP
+\fB-M\fP, \fB--multiline\fP
+Allow patterns to match more than one line. When this option is set, the PCRE2
+library is called in "multiline" mode. This allows a matched string to extend
+past the end of a line and continue on one or more subsequent lines. Patterns
+used with \fB-M\fP may usefully contain literal newline characters and internal
+occurrences of ^ and $ characters. The output for a successful match may
+consist of more than one line. The first line is the line in which the match
+started, and the last line is the line in which the match ended. If the matched
+string ends with a newline sequence, the output ends at the end of that line.
+If \fB-v\fP is set, none of the lines in a multi-line match are output. Once a
+match has been handled, scanning restarts at the beginning of the line after
+the one in which the match ended.
+.sp
+The newline sequence that separates multiple lines must be matched as part of
+the pattern. For example, to find the phrase "regular expression" in a file
+where "regular" might be at the end of a line and "expression" at the start of
+the next line, you could use this command:
+.sp
+ pcre2grep -M 'regular\es+expression' <file>
+.sp
+The \es escape sequence matches any white space character, including newlines,
+and is followed by + so as to match trailing white space on the first line as
+well as possibly handling a two-character newline sequence.
+.sp
+There is a limit to the number of lines that can be matched, imposed by the way
+that \fBpcre2grep\fP buffers the input file as it scans it. With a sufficiently
+large processing buffer, this should not be a problem, but the \fB-M\fP option
+does not work when input is read line by line (see \fB--line-buffered\fP.)
+.TP
+\fB-m\fP \fInumber\fP, \fB--max-count\fP=\fInumber\fP
+Stop processing after finding \fInumber\fP matching lines, or non-matching
+lines if \fB-v\fP is also set. Any trailing context lines are output after the
+final match. In multiline mode, each multiline match counts as just one line
+for this purpose. If this limit is reached when reading the standard input from
+a regular file, the file is left positioned just after the last matching line.
+If \fB-c\fP is also set, the count that is output is never greater than
+\fInumber\fP. This option has no effect if used with \fB-L\fP, \fB-l\fP, or
+\fB-q\fP, or when just checking for a match in a binary file.
+.TP
\fB--match-limit\fP=\fInumber\fP
Processing some regular expression patterns may take a very long time to search
for all possible matching strings. Others may require a very large amount of
@@ -493,35 +532,6 @@
set by \fB--buffer-size\fP. The maximum buffer size is silently forced to be no
smaller than the starting buffer size.
.TP
-\fB-M\fP, \fB--multiline\fP
-Allow patterns to match more than one line. When this option is set, the PCRE2
-library is called in "multiline" mode. This allows a matched string to extend
-past the end of a line and continue on one or more subsequent lines. Patterns
-used with \fB-M\fP may usefully contain literal newline characters and internal
-occurrences of ^ and $ characters. The output for a successful match may
-consist of more than one line. The first line is the line in which the match
-started, and the last line is the line in which the match ended. If the matched
-string ends with a newline sequence, the output ends at the end of that line.
-If \fB-v\fP is set, none of the lines in a multi-line match are output. Once a
-match has been handled, scanning restarts at the beginning of the line after
-the one in which the match ended.
-.sp
-The newline sequence that separates multiple lines must be matched as part of
-the pattern. For example, to find the phrase "regular expression" in a file
-where "regular" might be at the end of a line and "expression" at the start of
-the next line, you could use this command:
-.sp
- pcre2grep -M 'regular\es+expression' <file>
-.sp
-The \es escape sequence matches any white space character, including newlines,
-and is followed by + so as to match trailing white space on the first line as
-well as possibly handling a two-character newline sequence.
-.sp
-There is a limit to the number of lines that can be matched, imposed by the way
-that \fBpcre2grep\fP buffers the input file as it scans it. With a sufficiently
-large processing buffer, this should not be a problem, but the \fB-M\fP option
-does not work when input is read line by line (see \fB--line-buffered\fP.)
-.TP
\fB-N\fP \fInewline-type\fP, \fB--newline\fP=\fInewline-type\fP
Six different conventions for indicating the ends of lines in scanned files are
supported. For example:
@@ -565,27 +575,36 @@
It should never be needed in normal use.
.TP
\fB-O\fP \fItext\fP, \fB--output\fP=\fItext\fP
-When there is a match, instead of outputting the whole line that matched,
-output just the given text, followed by an operating-system standard newline.
-The \fB--newline\fP option has no effect on this option, which is mutually
-exclusive with \fB--only-matching\fP, \fB--file-offsets\fP, and
-\fB--line-offsets\fP. Escape sequences starting with a dollar character may be
-used to insert the contents of the matched part of the line and/or captured
-substrings into the text.
+When there is a match, instead of outputting the line that matched, output just
+the text specified in this option, followed by an operating-system standard
+newline. In this mode, no context is shown. That is, the \fB-A\fP, \fB-B\fP,
+and \fB-C\fP options are ignored. The \fB--newline\fP option has no effect on
+this option, which is mutually exclusive with \fB--only-matching\fP,
+\fB--file-offsets\fP, and \fB--line-offsets\fP. However, like
+\fB--only-matching\fP, if there is more than one match in a line, each of them
+causes a line of output.
.sp
-$<digits> or ${<digits>} is replaced by the captured
-substring of the given decimal number; zero substitutes the whole match. If
-the number is greater than the number of capturing substrings, or if the
-capture is unset, the replacement is empty.
+Escape sequences starting with a dollar character may be used to insert the
+contents of the matched part of the line and/or captured substrings into the
+text.
.sp
+$<digits> or ${<digits>} is replaced by the captured substring of the given
+decimal number; zero substitutes the whole match. If the number is greater than
+the number of capturing substrings, or if the capture is unset, the replacement
+is empty.
+.sp
$a is replaced by bell; $b by backspace; $e by escape; $f by form feed; $n by
newline; $r by carriage return; $t by tab; $v by vertical tab.
.sp
-$o<digits> is replaced by the character represented by the given octal
-number; up to three digits are processed.
+$o<digits> or $o{<digits>} is replaced by the character whose code point is the
+given octal number. In the first form, up to three octal digits are processed.
+When more digits are needed in Unicode mode to specify a wide character, the
+second form must be used.
.sp
-$x<digits> is replaced by the character represented by the given hexadecimal
-number; up to two digits are processed.
+$x<digits> or $x{<digits>} is replaced by the character represented by the
+given hexadecimal number. In the first form, up to two hexadecimal digits are
+processed. When more digits are needed in Unicode mode to specify a wide
+character, the second form must be used.
.sp
Any other character is substituted by itself. In particular, $$ is replaced by
a single dollar.
@@ -644,7 +663,8 @@
option to "recurse".
.TP
\fB--recursion-limit\fP=\fInumber\fP
-See \fB--match-limit\fP above.
+This is an obsolete synonym for \fB--depth-limit\fP. See \fB--match-limit\fP
+above for details.
.TP
\fB-s\fP, \fB--no-messages\fP
Suppress error messages about non-existent or unreadable files. Such files are
@@ -665,14 +685,17 @@
\fB-u\fP, \fB--utf\fP
Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
with UTF-8 support. All patterns (including those for any \fB--exclude\fP and
-\fB--include\fP options) and all subject lines that are scanned must be valid
-strings of UTF-8 characters.
+\fB--include\fP options) and all lines that are scanned must be valid strings
+of UTF-8 characters. If an invalid UTF-8 string is encountered, an error
+occurs.
.TP
\fB-U\fP, \fB--utf-allow-invalid\fP
As \fB--utf\fP, but in addition subject lines may contain invalid UTF-8 code
-unit sequences. These can never form part of any pattern match. This facility
-allows valid UTF-8 strings to be sought in executable or other binary files.
-For more details about matching in non-valid UTF-8 strings, see the
+unit sequences. These can never form part of any pattern match. Patterns
+themselves, however, must still be valid UTF-8 strings. This facility allows
+valid UTF-8 strings to be sought within arbitrary byte sequences in executable
+or other binary files. For more details about matching in non-valid UTF-8
+strings, see the
.\" HREF
\fBpcre2unicode\fP(3)
.\"
@@ -685,7 +708,9 @@
.TP
\fB-v\fP, \fB--invert-match\fP
Invert the sense of the match, so that lines which do \fInot\fP match any of
-the patterns are the ones that are found.
+the patterns are the ones that are found. When this option is set, options such
+as \fB--only-matching\fP and \fB--output\fP, which specify parts of a match
+that are to be output, are ignored.
.TP
\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP
Force the patterns only to match "words". That is, there must be a word
@@ -812,12 +837,36 @@
only callouts with string arguments are useful.
.
.
+.SS "Echoing a specific string"
+.rs
+.sp
+Starting the callout string with a pipe character invokes an echoing facility
+that avoids calling an external program or script. This facility is always
+available, provided that callouts were not completely disabled when
+\fBpcre2grep\fP was built. The rest of the callout string is processed as a
+zero-terminated string, which means it should not contain any internal binary
+zeros. It is written to the output, having first been passed through the same
+escape processing as text from the \fB--output\fP (\fB-O\fP) option (see
+above). However, $0 cannot be used to insert a matched substring because the
+match is still in progress. Instead, the single character '0' is inserted. Any
+syntax errors in the string (for example, a dollar not followed by another
+character) causes the callout to be ignored. No terminator is added to the
+output string, so if you want a newline, you must include it explicitly using
+the escape $n. For example:
+.sp
+ pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' <some file>
+.sp
+Matching continues normally after the string is output. If you want to see only
+the callout output but not any output from an actual match, you should end the
+pattern with (*FAIL).
+.
+.
.SS "Calling external programs or scripts"
.rs
.sp
This facility can be independently disabled when \fBpcre2grep\fP is built. It
is supported for Windows, where a call to \fB_spawnvp()\fP is used, for VMS,
-where \fBlib$spawn()\fP is used, and for any other Unix-like environment where
+where \fBlib$spawn()\fP is used, and for any Unix-like environment where
\fBfork()\fP and \fBexecv()\fP are available.
.P
If the callout string does not start with a pipe (vertical bar) character, it
@@ -828,13 +877,11 @@
executable_name|arg1|arg2|...
.sp
Any substring (including the executable name) may contain escape sequences
-started by a dollar character: $<digits> or ${<digits>} is replaced by the
-captured substring of the given decimal number, which must be greater than
-zero. If the number is greater than the number of capturing substrings, or if
-the capture is unset, the replacement is empty.
-.P
-Any other character is substituted by itself. In particular, $$ is replaced by
-a single dollar and $| is replaced by a pipe character. Here is an example:
+started by a dollar character. These are the same as for the \fB--output\fP
+(\fB-O\fP) option documented above, except that $0 cannot insert the matched
+string because the match is still in progress. Instead, the character '0'
+is inserted. If you need a literal dollar or pipe character in any
+substring, use $$ or $| respectively. Here is an example:
.sp
echo -e "abcde\en12345" | pcre2grep \e
'(?x)(.)(..(.))
@@ -847,30 +894,16 @@
Arg1: [1] [234] [4] Arg2: |1| ()
12345
.sp
-The parameters for the system call that is used to run the
-program or script are zero-terminated strings. This means that binary zero
-characters in the callout argument will cause premature termination of their
-substrings, and therefore should not be present. Any syntax errors in the
-string (for example, a dollar not followed by another character) cause the
-callout to be ignored. If running the program fails for any reason (including
-the non-existence of the executable), a local matching failure occurs and the
-matcher backtracks in the normal way.
+The parameters for the system call that is used to run the program or script
+are zero-terminated strings. This means that binary zero characters in the
+callout argument will cause premature termination of their substrings, and
+therefore should not be present. Any syntax errors in the string (for example,
+a dollar not followed by another character) causes the callout to be ignored.
+If running the program fails for any reason (including the non-existence of the
+executable), a local matching failure occurs and the matcher backtracks in the
+normal way.
.
.
-.SS "Echoing a specific string"
-.rs
-.sp
-This facility is always available, provided that callouts were not completely
-disabled when \fBpcre2grep\fP was built. If the callout string starts with a
-pipe (vertical bar) character, the rest of the string is written to the output,
-having been passed through the same escape processing as text from the --output
-option. This provides a simple echoing facility that avoids calling an external
-program or script. No terminator is added to the string, so if you want a
-newline, you must include it explicitly. Matching continues normally after the
-string is output. If you want to see only the callout output but not any output
-from an actual match, you should end the relevant pattern with (*FAIL).
-.
-.
.SH "MATCHING ERRORS"
.rs
.sp
@@ -904,7 +937,8 @@
.SH "SEE ALSO"
.rs
.sp
-\fBpcre2pattern\fP(3), \fBpcre2syntax\fP(3), \fBpcre2callout\fP(3).
+\fBpcre2pattern\fP(3), \fBpcre2syntax\fP(3), \fBpcre2callout\fP(3),
+\fBpcre2unicode\fP(3).
.
.
.SH AUTHOR
@@ -921,6 +955,6 @@
.rs
.sp
.nf
-Last updated: 25 January 2020
+Last updated: 04 October 2020
Copyright (c) 1997-2020 University of Cambridge.
.fi
Modified: code/trunk/doc/pcre2grep.txt
===================================================================
--- code/trunk/doc/pcre2grep.txt 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/pcre2grep.txt 2020-10-04 16:34:31 UTC (rev 1274)
@@ -80,7 +80,7 @@
following the match, so that further matches on the same line can be
found. If there are multiple patterns, they are all tried on the re-
mainder of the line, but patterns that follow the one that matched are
- not tried on the earlier part of the line.
+ not tried on the earlier matched part of the line.
This behaviour means that the order in which multiple patterns are
specified can affect the output when one of the above options is used.
@@ -115,10 +115,10 @@
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 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 handled.
+ 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 --binary-files option for a means of changing the way binary
+ files are handled.
BINARY ZEROS IN PATTERNS
@@ -413,17 +413,17 @@
--include=pattern
If any --include patterns are specified, the only files that
- are processed are those that match one of the patterns (and
- do not match an --exclude pattern). This option does not af-
- fect directories, but it applies to all files, whether listed
- on the command line, obtained from --file-list, or by scan-
- ning a directory. The pattern is a PCRE2 regular expression,
- and is matched against the final component of the file name,
- not the entire path. The -F, -w, and -x options do not apply
- to this pattern. The option may be given any number of times.
- If a file name matches both an --include and an --exclude
- pattern, it is excluded. There is no short form for this op-
- tion.
+ are processed are those whose names match one of the patterns
+ and do not match an --exclude pattern. This option does not
+ affect directories, but it applies to all files, whether
+ listed on the command line, obtained from --file-list, or by
+ scanning a directory. The pattern is a PCRE2 regular expres-
+ sion, and is matched against the final component of the file
+ name, not the entire path. The -F, -w, and -x options do not
+ apply to this pattern. The option may be given any number of
+ times. If a file name matches both an --include and an --ex-
+ clude pattern, it is excluded. There is no short form for
+ this option.
--include-from=filename
Treat each non-empty line of the file as the data for an
@@ -434,8 +434,8 @@
--include-dir=pattern
If any --include-dir patterns are specified, the only direc-
- tories that are processed are those that match one of the
- patterns (and do not match an --exclude-dir pattern). This
+ tories that are processed are those whose names match one of
+ the patterns and do not match an --exclude-dir pattern. This
applies to all directories, whether listed on the command
line, obtained from --file-list, or by scanning a parent di-
rectory. The pattern is a PCRE2 regular expression, and is
@@ -461,8 +461,9 @@
matching continues in order to obtain the correct count, and
those files that have at least one match are listed along
with their counts. Using this option with -c is a way of sup-
- pressing the listing of files with no matches. This opeion
- overrides any previous -H, -h, or -L options.
+ pressing the listing of files with no matches that occurs
+ with -c on its own. This option overrides any previous -H,
+ -h, or -L options.
--label=name
This option supplies a name to be used for the standard input
@@ -470,37 +471,84 @@
input)" is used. There is no short form for this option.
--line-buffered
- When this option is given, non-compressed input is read and
- processed line by line, and the output is flushed after each
- write. By default, input is read in large chunks, unless
- pcre2grep can determine that it is reading from a terminal
- (which is currently possible only in Unix-like environments
- or Windows). Output to terminal is normally automatically
- flushed by the operating system. This option can be useful
- when the input or output is attached to a pipe and you do not
- want pcre2grep to buffer up large amounts of data. However,
- its use will affect performance, and the -M (multiline) op-
- tion ceases to work. When input is from a compressed .gz or
- .bz2 file, --line-buffered is ignored.
+ When this option is given, non-compressed input is read and
+ processed line by line, and the output is flushed after each
+ write. By default, input is read in large chunks, unless
+ pcre2grep can determine that it is reading from a terminal,
+ which is currently possible only in Unix-like environments or
+ Windows. Output to terminal is normally automatically flushed
+ by the operating system. This option can be useful when the
+ input or output is attached to a pipe and you do not want
+ pcre2grep to buffer up large amounts of data. However, its
+ use will affect performance, and the -M (multiline) option
+ ceases to work. When input is from a compressed .gz or .bz2
+ file, --line-buffered is ignored.
--line-offsets
- Instead of showing lines or parts of lines that match, show
+ Instead of showing lines or parts of lines that match, show
each match as a line number, the offset from the start of the
- line, and a length. The line number is terminated by a colon
- (as usual; see the -n option), and the offset and length are
- separated by a comma. In this mode, no context is shown.
- That is, the -A, -B, and -C options are ignored. If there is
- more than one match in a line, each of them is shown sepa-
- rately. This option is mutually exclusive with --output,
+ line, and a length. The line number is terminated by a colon
+ (as usual; see the -n option), and the offset and length are
+ separated by a comma. In this mode, no context is shown.
+ That is, the -A, -B, and -C options are ignored. If there is
+ more than one match in a line, each of them is shown sepa-
+ rately. This option is mutually exclusive with --output,
--file-offsets, and --only-matching.
--locale=locale-name
- This option specifies a locale to be used for pattern match-
- ing. It overrides the value in the LC_ALL or LC_CTYPE envi-
- ronment variables. If no locale is specified, the PCRE2 li-
+ This option specifies a locale to be used for pattern match-
+ ing. It overrides the value in the LC_ALL or LC_CTYPE envi-
+ ronment variables. If no locale is specified, the PCRE2 li-
brary's default (usually the "C" locale) is used. There is no
short form for this option.
+ -M, --multiline
+ Allow patterns to match more than one line. When this option
+ is set, the PCRE2 library is called in "multiline" mode. This
+ allows a matched string to extend past the end of a line and
+ continue on one or more subsequent lines. Patterns used with
+ -M may usefully contain literal newline characters and inter-
+ nal occurrences of ^ and $ characters. The output for a suc-
+ cessful match may consist of more than one line. The first
+ line is the line in which the match started, and the last
+ line is the line in which the match ended. If the matched
+ string ends with a newline sequence, the output ends at the
+ end of that line. If -v is set, none of the lines in a
+ multi-line match are output. Once a match has been handled,
+ scanning restarts at the beginning of the line after the one
+ in which the match ended.
+
+ The newline sequence that separates multiple lines must be
+ matched as part of the pattern. For example, to find the
+ phrase "regular expression" in a file where "regular" might
+ be at the end of a line and "expression" at the start of the
+ next line, you could use this command:
+
+ pcre2grep -M 'regular\s+expression' <file>
+
+ The \s escape sequence matches any white space character, in-
+ cluding newlines, and is followed by + so as to match trail-
+ ing white space on the first line as well as possibly han-
+ dling a two-character newline sequence.
+
+ There is a limit to the number of lines that can be matched,
+ imposed by the way that pcre2grep buffers the input file as
+ it scans it. With a sufficiently large processing buffer,
+ this should not be a problem, but the -M option does not work
+ when input is read line by line (see --line-buffered.)
+
+ -m number, --max-count=number
+ Stop processing after finding number matching lines, or non-
+ matching lines if -v is also set. Any trailing context lines
+ are output after the final match. In multiline mode, each
+ multiline match counts as just one line for this purpose. If
+ this limit is reached when reading the standard input from a
+ regular file, the file is left positioned just after the last
+ matching line. If -c is also set, the count that is output
+ is never greater than number. This option has no effect if
+ used with -L, -l, or -q, or when just checking for a match in
+ a binary file.
+
--match-limit=number
Processing some regular expression patterns may take a very
long time to search for all possible matching strings. Others
@@ -542,41 +590,6 @@
size is silently forced to be no smaller than the starting
buffer size.
- -M, --multiline
- Allow patterns to match more than one line. When this option
- is set, the PCRE2 library is called in "multiline" mode. This
- allows a matched string to extend past the end of a line and
- continue on one or more subsequent lines. Patterns used with
- -M may usefully contain literal newline characters and inter-
- nal occurrences of ^ and $ characters. The output for a suc-
- cessful match may consist of more than one line. The first
- line is the line in which the match started, and the last
- line is the line in which the match ended. If the matched
- string ends with a newline sequence, the output ends at the
- end of that line. If -v is set, none of the lines in a
- multi-line match are output. Once a match has been handled,
- scanning restarts at the beginning of the line after the one
- in which the match ended.
-
- The newline sequence that separates multiple lines must be
- matched as part of the pattern. For example, to find the
- phrase "regular expression" in a file where "regular" might
- be at the end of a line and "expression" at the start of the
- next line, you could use this command:
-
- pcre2grep -M 'regular\s+expression' <file>
-
- The \s escape sequence matches any white space character, in-
- cluding newlines, and is followed by + so as to match trail-
- ing white space on the first line as well as possibly han-
- dling a two-character newline sequence.
-
- There is a limit to the number of lines that can be matched,
- imposed by the way that pcre2grep buffers the input file as
- it scans it. With a sufficiently large processing buffer,
- this should not be a problem, but the -M option does not work
- when input is read line by line (see --line-buffered.)
-
-N newline-type, --newline=newline-type
Six different conventions for indicating the ends of lines in
scanned files are supported. For example:
@@ -625,97 +638,109 @@
lems. It should never be needed in normal use.
-O text, --output=text
- When there is a match, instead of outputting the whole line
- that matched, output just the given text, followed by an op-
- erating-system standard newline. The --newline option has no
- effect on this option, which is mutually exclusive with
- --only-matching, --file-offsets, and --line-offsets. Escape
- sequences starting with a dollar character may be used to in-
- sert the contents of the matched part of the line and/or cap-
- tured substrings into the text.
+ When there is a match, instead of outputting the line that
+ matched, output just the text specified in this option, fol-
+ lowed by an operating-system standard newline. In this mode,
+ no context is shown. That is, the -A, -B, and -C options are
+ ignored. The --newline option has no effect on this option,
+ which is mutually exclusive with --only-matching, --file-off-
+ sets, and --line-offsets. However, like --only-matching, if
+ there is more than one match in a line, each of them causes a
+ line of output.
- $<digits> or ${<digits>} is replaced by the captured sub-
- string of the given decimal number; zero substitutes the
+ Escape sequences starting with a dollar character may be used
+ to insert the contents of the matched part of the line and/or
+ captured substrings into the text.
+
+ $<digits> or ${<digits>} is replaced by the captured sub-
+ string of the given decimal number; zero substitutes the
whole match. If the number is greater than the number of cap-
- turing substrings, or if the capture is unset, the replace-
+ turing substrings, or if the capture is unset, the replace-
ment is empty.
- $a is replaced by bell; $b by backspace; $e by escape; $f by
- form feed; $n by newline; $r by carriage return; $t by tab;
+ $a is replaced by bell; $b by backspace; $e by escape; $f by
+ form feed; $n by newline; $r by carriage return; $t by tab;
$v by vertical tab.
- $o<digits> is replaced by the character represented by the
- given octal number; up to three digits are processed.
+ $o<digits> or $o{<digits>} is replaced by the character whose
+ code point is the given octal number. In the first form, up
+ to three octal digits are processed. When more digits are
+ needed in Unicode mode to specify a wide character, the sec-
+ ond form must be used.
- $x<digits> is replaced by the character represented by the
- given hexadecimal number; up to two digits are processed.
+ $x<digits> or $x{<digits>} is replaced by the character rep-
+ resented by the given hexadecimal number. In the first form,
+ up to two hexadecimal digits are processed. When more digits
+ are needed in Unicode mode to specify a wide character, the
+ second form must be used.
- Any other character is substituted by itself. In particular,
+ Any other character is substituted by itself. In particular,
$$ is replaced by a single dollar.
-o, --only-matching
Show only the part of the line that matched a pattern instead
- of the whole line. In this mode, no context is shown. That
- is, the -A, -B, and -C options are ignored. If there is more
- than one match in a line, each of them is shown separately,
- on a separate line of output. If -o is combined with -v (in-
- vert the sense of the match to find non-matching lines), no
- output is generated, but the return code is set appropri-
- ately. If the matched portion of the line is empty, nothing
- is output unless the file name or line number are being
- printed, in which case they are shown on an otherwise empty
+ of the whole line. In this mode, no context is shown. That
+ is, the -A, -B, and -C options are ignored. If there is more
+ than one match in a line, each of them is shown separately,
+ on a separate line of output. If -o is combined with -v (in-
+ vert the sense of the match to find non-matching lines), no
+ output is generated, but the return code is set appropri-
+ ately. If the matched portion of the line is empty, nothing
+ is output unless the file name or line number are being
+ printed, in which case they are shown on an otherwise empty
line. This option is mutually exclusive with --output,
--file-offsets and --line-offsets.
-onumber, --only-matching=number
- Show only the part of the line that matched the capturing
+ Show only the part of the line that matched the capturing
parentheses of the given number. Up to 50 capturing parenthe-
- ses are supported by default. This limit can be changed via
- the --om-capture option. A pattern may contain any number of
- capturing parentheses, but only those whose number is within
- the limit can be accessed by -o. An error occurs if the num-
+ ses are supported by default. This limit can be changed via
+ the --om-capture option. A pattern may contain any number of
+ capturing parentheses, but only those whose number is within
+ the limit can be accessed by -o. An error occurs if the num-
ber specified by -o is greater than the limit.
-o0 is the same as -o without a number. Because these options
- can be given without an argument (see above), if an argument
- is present, it must be given in the same shell item, for ex-
- ample, -o3 or --only-matching=2. The comments given for the
- non-argument case above also apply to this option. If the
- specified capturing parentheses do not exist in the pattern,
- or were not set in the match, nothing is output unless the
+ can be given without an argument (see above), if an argument
+ is present, it must be given in the same shell item, for ex-
+ ample, -o3 or --only-matching=2. The comments given for the
+ non-argument case above also apply to this option. If the
+ specified capturing parentheses do not exist in the pattern,
+ or were not set in the match, nothing is output unless the
file name or line number are being output.
- If this option is given multiple times, multiple substrings
- are output for each match, in the order the options are
- given, and all on one line. For example, -o3 -o1 -o3 causes
- the substrings matched by capturing parentheses 3 and 1 and
- then 3 again to be output. By default, there is no separator
+ If this option is given multiple times, multiple substrings
+ are output for each match, in the order the options are
+ given, and all on one line. For example, -o3 -o1 -o3 causes
+ the substrings matched by capturing parentheses 3 and 1 and
+ then 3 again to be output. By default, there is no separator
(but see the next but one option).
--om-capture=number
- Set the number of capturing parentheses that can be accessed
+ Set the number of capturing parentheses that can be accessed
by -o. The default is 50.
--om-separator=text
- Specify a separating string for multiple occurrences of -o.
- The default is an empty string. Separating strings are never
+ Specify a separating string for multiple occurrences of -o.
+ The default is an empty string. Separating strings are never
coloured.
-q, --quiet
Work quietly, that is, display nothing except error messages.
- The exit status indicates whether or not any matches were
+ The exit status indicates whether or not any matches were
found.
-r, --recursive
- If any given path is a directory, recursively scan the files
- it contains, taking note of any --include and --exclude set-
- tings. By default, a directory is read as a normal file; in
- some operating systems this gives an immediate end-of-file.
- This option is a shorthand for setting the -d option to "re-
+ If any given path is a directory, recursively scan the files
+ it contains, taking note of any --include and --exclude set-
+ tings. By default, a directory is read as a normal file; in
+ some operating systems this gives an immediate end-of-file.
+ This option is a shorthand for setting the -d option to "re-
curse".
--recursion-limit=number
- See --match-limit above.
+ This is an obsolete synonym for --depth-limit. See --match-
+ limit above for details.
-s, --no-messages
Suppress error messages about non-existent or unreadable
@@ -737,26 +762,30 @@
-u, --utf Operate in UTF-8 mode. This option is available only if PCRE2
has been compiled with UTF-8 support. All patterns (including
- those for any --exclude and --include options) and all sub-
- ject lines that are scanned must be valid strings of UTF-8
- characters.
+ those for any --exclude and --include options) and all lines
+ that are scanned must be valid strings of UTF-8 characters.
+ If an invalid UTF-8 string is encountered, an error occurs.
-U, --utf-allow-invalid
As --utf, but in addition subject lines may contain invalid
UTF-8 code unit sequences. These can never form part of any
- pattern match. This facility allows valid UTF-8 strings to be
- sought in executable or other binary files. For more details
- about matching in non-valid UTF-8 strings, see the pcre2uni-
- code(3) documentation.
+ pattern match. Patterns themselves, however, must still be
+ valid UTF-8 strings. This facility allows valid UTF-8 strings
+ to be sought within arbitrary byte sequences in executable or
+ other binary files. For more details about matching in non-
+ valid UTF-8 strings, see the pcre2unicode(3) documentation.
-V, --version
- Write the version numbers of pcre2grep and the PCRE2 library
- to the standard output and then exit. Anything else on the
+ Write the version numbers of pcre2grep and the PCRE2 library
+ to the standard output and then exit. Anything else on the
command line is ignored.
-v, --invert-match
- Invert the sense of the match, so that lines which do not
- match any of the patterns are the ones that are found.
+ Invert the sense of the match, so that lines which do not
+ match any of the patterns are the ones that are found. When
+ this option is set, options such as --only-matching and
+ --output, which specify parts of a match that are to be out-
+ put, are ignored.
-w, --word-regex, --word-regexp
Force the patterns only to match "words". That is, there must
@@ -878,31 +907,50 @@
mentation for details). Numbered callouts are ignored by pcre2grep;
only callouts with string arguments are useful.
+ Echoing a specific string
+
+ Starting the callout string with a pipe character invokes an echoing
+ facility that avoids calling an external program or script. This facil-
+ ity is always available, provided that callouts were not completely
+ disabled when pcre2grep was built. The rest of the callout string is
+ processed as a zero-terminated string, which means it should not con-
+ tain any internal binary zeros. It is written to the output, having
+ first been passed through the same escape processing as text from the
+ --output (-O) option (see above). However, $0 cannot be used to insert
+ a matched substring because the match is still in progress. Instead,
+ the single character '0' is inserted. Any syntax errors in the string
+ (for example, a dollar not followed by another character) causes the
+ callout to be ignored. No terminator is added to the output string, so
+ if you want a newline, you must include it explicitly using the escape
+ $n. For example:
+
+ pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' <some file>
+
+ Matching continues normally after the string is output. If you want to
+ see only the callout output but not any output from an actual match,
+ you should end the pattern with (*FAIL).
+
Calling external programs or scripts
This facility can be independently disabled when pcre2grep is built. It
- is supported for Windows, where a call to _spawnvp() is used, for VMS,
- where lib$spawn() is used, and for any other Unix-like environment
- where fork() and execv() are available.
+ is supported for Windows, where a call to _spawnvp() is used, for VMS,
+ where lib$spawn() is used, and for any Unix-like environment where
+ fork() and execv() are available.
If the callout string does not start with a pipe (vertical bar) charac-
- ter, it is parsed into a list of substrings separated by pipe charac-
- ters. The first substring must be an executable name, with the follow-
+ ter, it is parsed into a list of substrings separated by pipe charac-
+ ters. The first substring must be an executable name, with the follow-
ing substrings specifying arguments:
executable_name|arg1|arg2|...
- Any substring (including the executable name) may contain escape se-
- quences started by a dollar character: $<digits> or ${<digits>} is re-
- placed by the captured substring of the given decimal number, which
- must be greater than zero. If the number is greater than the number of
- capturing substrings, or if the capture is unset, the replacement is
- empty.
+ Any substring (including the executable name) may contain escape se-
+ quences started by a dollar character. These are the same as for the
+ --output (-O) option documented above, except that $0 cannot insert the
+ matched string because the match is still in progress. Instead, the
+ character '0' is inserted. If you need a literal dollar or pipe charac-
+ ter in any substring, use $$ or $| respectively. Here is an example:
- Any other character is substituted by itself. In particular, $$ is re-
- placed by a single dollar and $| is replaced by a pipe character. Here
- is an example:
-
echo -e "abcde\n12345" | pcre2grep \
'(?x)(.)(..(.))
(?C"/bin/echo|Arg1: [$1] [$2] [$3]|Arg2: $|${1}$| ($4)")()' -
@@ -914,29 +962,16 @@
Arg1: [1] [234] [4] Arg2: |1| ()
12345
- The parameters for the system call that is used to run the program or
+ The parameters for the system call that is used to run the program or
script are zero-terminated strings. This means that binary zero charac-
- ters in the callout argument will cause premature termination of their
- substrings, and therefore should not be present. Any syntax errors in
- the string (for example, a dollar not followed by another character)
- cause the callout to be ignored. If running the program fails for any
- reason (including the non-existence of the executable), a local match-
+ ters in the callout argument will cause premature termination of their
+ substrings, and therefore should not be present. Any syntax errors in
+ the string (for example, a dollar not followed by another character)
+ causes the callout to be ignored. If running the program fails for any
+ reason (including the non-existence of the executable), a local match-
ing failure occurs and the matcher backtracks in the normal way.
- Echoing a specific string
- This facility is always available, provided that callouts were not com-
- pletely disabled when pcre2grep was built. If the callout string starts
- with a pipe (vertical bar) character, the rest of the string is written
- to the output, having been passed through the same escape processing as
- text from the --output option. This provides a simple echoing facility
- that avoids calling an external program or script. No terminator is
- added to the string, so if you want a newline, you must include it ex-
- plicitly. Matching continues normally after the string is output. If
- you want to see only the callout output but not any output from an ac-
- tual match, you should end the relevant pattern with (*FAIL).
-
-
MATCHING ERRORS
It is possible to supply a regular expression that takes a very long
@@ -969,7 +1004,7 @@
SEE ALSO
- pcre2pattern(3), pcre2syntax(3), pcre2callout(3).
+ pcre2pattern(3), pcre2syntax(3), pcre2callout(3), pcre2unicode(3).
AUTHOR
@@ -981,5 +1016,5 @@
REVISION
- Last updated: 25 January 2020
+ Last updated: 04 October 2020
Copyright (c) 1997-2020 University of Cambridge.
Modified: code/trunk/doc/pcre2test.txt
===================================================================
--- code/trunk/doc/pcre2test.txt 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/doc/pcre2test.txt 2020-10-04 16:34:31 UTC (rev 1274)
@@ -257,127 +257,134 @@
appear. This file format, with some restrictions, can also be processed
by the perltest.sh script that is distributed with PCRE2 as a means of
checking that the behaviour of PCRE2 and Perl is the same. For a speci-
- fication of perltest.sh, see the comments near its beginning.
+ fication of perltest.sh, see the comments near its beginning. See also
+ the #perltest command below.
When the input is a terminal, pcre2test prompts for each line of input,
- using "re>" to prompt for regular expression patterns, and "data>" to
- prompt for subject lines. Command lines starting with # can be entered
+ using "re>" to prompt for regular expression patterns, and "data>" to
+ prompt for subject lines. Command lines starting with # can be entered
only in response to the "re>" prompt.
- Each subject line is matched separately and independently. If you want
+ Each subject line is matched separately and independently. If you want
to do multi-line matches, you have to use the \n escape sequence (or \r
- or \r\n, etc., depending on the newline setting) in a single line of
- input to encode the newline sequences. There is no limit on the length
- of subject lines; the input buffer is automatically extended if it is
- too small. There are replication features that makes it possible to
- generate long repetitive pattern or subject lines without having to
+ or \r\n, etc., depending on the newline setting) in a single line of
+ input to encode the newline sequences. There is no limit on the length
+ of subject lines; the input buffer is automatically extended if it is
+ too small. There are replication features that makes it possible to
+ generate long repetitive pattern or subject lines without having to
supply them explicitly.
- An empty line or the end of the file signals the end of the subject
- lines for a test, at which point a new pattern or command line is ex-
+ An empty line or the end of the file signals the end of the subject
+ lines for a test, at which point a new pattern or command line is ex-
pected if there is still input to be read.
COMMAND LINES
- In between sets of test data, a line that begins with # is interpreted
+ In between sets of test data, a line that begins with # is interpreted
as a command line. If the first character is followed by white space or
- an exclamation mark, the line is treated as a comment, and ignored.
+ an exclamation mark, the line is treated as a comment, and ignored.
Otherwise, the following commands are recognized:
#forbid_utf
- Subsequent patterns automatically have the PCRE2_NEVER_UTF and
- PCRE2_NEVER_UCP options set, which locks out the use of the PCRE2_UTF
- and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
- patterns. This command also forces an error if a subsequent pattern
- contains any occurrences of \P, \p, or \X, which are still supported
- when PCRE2_UTF is not set, but which require Unicode property support
+ Subsequent patterns automatically have the PCRE2_NEVER_UTF and
+ PCRE2_NEVER_UCP options set, which locks out the use of the PCRE2_UTF
+ and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
+ patterns. This command also forces an error if a subsequent pattern
+ contains any occurrences of \P, \p, or \X, which are still supported
+ when PCRE2_UTF is not set, but which require Unicode property support
to be included in the library.
- This is a trigger guard that is used in test files to ensure that UTF
- or Unicode property tests are not accidentally added to files that are
- used when Unicode support is not included in the library. Setting
- PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also be obtained
- by the use of #pattern; the difference is that #forbid_utf cannot be
- unset, and the automatic options are not displayed in pattern informa-
+ This is a trigger guard that is used in test files to ensure that UTF
+ or Unicode property tests are not accidentally added to files that are
+ used when Unicode support is not included in the library. Setting
+ PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also be obtained
+ by the use of #pattern; the difference is that #forbid_utf cannot be
+ unset, and the automatic options are not displayed in pattern informa-
tion, to avoid cluttering up test output.
#load <filename>
This command is used to load a set of precompiled patterns from a file,
- as described in the section entitled "Saving and restoring compiled
+ as described in the section entitled "Saving and restoring compiled
patterns" below.
#loadtables <filename>
- This command is used to load a set of binary character tables that can
- be accessed by the tables=3 qualifier. Such tables can be created by
+ This command is used to load a set of binary character tables that can
+ be accessed by the tables=3 qualifier. Such tables can be created by
the pcre2_dftables program with the -b option.
#newline_default [<newline-list>]
- When PCRE2 is built, a default newline convention can be specified.
- This determines which characters and/or character pairs are recognized
+ When PCRE2 is built, a default newline convention can be specified.
+ This determines which characters and/or character pairs are recognized
as indicating a newline in a pattern or subject string. The default can
- be overridden when a pattern is compiled. The standard test files con-
- tain tests of various newline conventions, but the majority of the
- tests expect a single linefeed to be recognized as a newline by de-
- fault. Without special action the tests would fail when PCRE2 is com-
+ be overridden when a pattern is compiled. The standard test files con-
+ tain tests of various newline conventions, but the majority of the
+ tests expect a single linefeed to be recognized as a newline by de-
+ fault. Without special action the tests would fail when PCRE2 is com-
piled with either CR or CRLF as the default newline.
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, ANY, or NUL (in upper or lower case), for example:
#newline_default LF Any anyCRLF
If the default newline is in the list, this command has no effect. Oth-
- erwise, except when testing the POSIX API, a newline modifier that
+ erwise, except when testing the POSIX API, a newline modifier that
specifies the first newline convention in the list (LF in the above ex-
- ample) is added to any pattern that does not already have a newline
+ ample) is added to any pattern that does not already have a newline
modifier. If the newline list is empty, the feature is turned off. This
command is present in a number of the standard test input files.
- When the POSIX API is being tested there is no way to override the de-
+ When the POSIX API is being tested there is no way to override the de-
fault newline convention, though it is possible to set the newline con-
- vention from within the pattern. A warning is given if the posix or
- posix_nosub modifier is used when #newline_default would set a default
+ vention from within the pattern. A warning is given if the posix or
+ posix_nosub modifier is used when #newline_default would set a default
for the non-POSIX API.
#pattern <modifier-list>
- This command sets a default modifier list that applies to all subse-
+ This command sets a default modifier list that applies to all subse-
quent patterns. Modifiers on a pattern can change these settings.
#perltest
- The appearance of this line causes all subsequent modifier settings to
- be checked for compatibility with the perltest.sh script, which is used
- to confirm that Perl gives the same results as PCRE2. Also, apart from
- comment lines, #pattern commands, and #subject commands that set or un-
- set "mark", no command lines are permitted, because they and many of
- the modifiers are specific to pcre2test, and should not be used in test
- files that are also processed by perltest.sh. The #perltest command
- helps detect tests that are accidentally put in the wrong file.
+ This line is used in test files that can also be processed by perl-
+ test.sh to confirm that Perl gives the same results as PCRE2. Subse-
+ quent tests are checked for the use of pcre2test features that are in-
+ compatible with the perltest.sh script.
+ Patterns must use '/' as their delimiter, and only certain modifiers
+ are supported. Comment lines, #pattern commands, and #subject commands
+ that set or unset "mark" are recognized and acted on. The #perltest,
+ #forbid_utf, and #newline_default commands, which are needed in the
+ relevant pcre2test files, are silently ignored. All other command lines
+ are ignored, but give a warning message. The #perltest command helps
+ detect tests that are accidentally put in the wrong file or use the
+ wrong delimiter. For more details of the perltest.sh script see the
+ comments it contains.
+
#pop [<modifiers>]
#popcopy [<modifiers>]
- These commands are used to manipulate the stack of compiled patterns,
- as described in the section entitled "Saving and restoring compiled
+ These commands are used to manipulate the stack of compiled patterns,
+ as described in the section entitled "Saving and restoring compiled
patterns" below.
#save <filename>
- This command is used to save a set of compiled patterns to a file, as
- described in the section entitled "Saving and restoring compiled pat-
+ This command is used to save a set of compiled patterns to a file, as
+ described in the section entitled "Saving and restoring compiled pat-
terns" below.
#subject <modifier-list>
- This command sets a default modifier list that applies to all subse-
- quent subject lines. Modifiers on a subject line can change these set-
+ This command sets a default modifier list that applies to all subse-
+ quent subject lines. Modifiers on a subject line can change these set-
tings.
@@ -385,58 +392,58 @@
Modifier lists are used with both pattern and subject lines. Items in a
list are separated by commas followed by optional white space. Trailing
- whitespace in a modifier list is ignored. Some modifiers may be given
- for both patterns and subject lines, whereas others are valid only for
- one or the other. Each modifier has a long name, for example "an-
- chored", and some of them must be followed by an equals sign and a
- value, for example, "offset=12". Values cannot contain comma charac-
- ters, but may contain spaces. Modifiers that do not take values may be
+ whitespace in a modifier list is ignored. Some modifiers may be given
+ for both patterns and subject lines, whereas others are valid only for
+ one or the other. Each modifier has a long name, for example "an-
+ chored", and some of them must be followed by an equals sign and a
+ value, for example, "offset=12". Values cannot contain comma charac-
+ ters, but may contain spaces. Modifiers that do not take values may be
preceded by a minus sign to turn off a previous setting.
A few of the more common modifiers can also be specified as single let-
- ters, for example "i" for "caseless". In documentation, following the
+ ters, for example "i" for "caseless". In documentation, following the
Perl convention, these are written with a slash ("the /i modifier") for
- clarity. Abbreviated modifiers must all be concatenated in the first
- item of a modifier list. If the first item is not recognized as a long
- modifier name, it is interpreted as a sequence of these abbreviations.
+ clarity. Abbreviated modifiers must all be concatenated in the first
+ item of a modifier list. If the first item is not recognized as a long
+ modifier name, it is interpreted as a sequence of these abbreviations.
For example:
/abc/ig,newline=cr,jit=3
- This is a pattern line whose modifier list starts with two one-letter
- modifiers (/i and /g). The lower-case abbreviated modifiers are the
+ This is a pattern line whose modifier list starts with two one-letter
+ modifiers (/i and /g). The lower-case abbreviated modifiers are the
same as used in Perl.
PATTERN SYNTAX
- A pattern line must start with one of the following characters (common
+ A pattern line must start with one of the following characters (common
symbols, excluding pattern meta-characters):
/ ! " ' ` - = _ : ; , % & @ ~
- This is interpreted as the pattern's delimiter. A regular expression
- may be continued over several input lines, in which case the newline
+ This is interpreted as the pattern's delimiter. A regular expression
+ may be continued over several input lines, in which case the newline
characters are included within it. It is possible to include the delim-
iter within the pattern by escaping it with a backslash, for example
/abc\/def/
- If you do this, the escape and the delimiter form part of the pattern,
+ If you do this, the escape and the delimiter form part of the pattern,
but since the delimiters are all non-alphanumeric, this does not affect
- its interpretation. If the terminating delimiter is immediately fol-
+ its interpretation. If the terminating delimiter is immediately fol-
lowed by a backslash, for example,
/abc/\
- then a backslash is added to the end of the pattern. This is done to
- provide a way of testing the error condition that arises if a pattern
+ then a backslash is added to the end of the pattern. This is done to
+ provide a way of testing the error condition that arises if a pattern
finishes with a backslash, because
/abc\/
- is interpreted as the first line of a pattern that starts with "abc/",
- causing pcre2test to read the next line as a continuation of the regu-
+ is interpreted as the first line of a pattern that starts with "abc/",
+ causing pcre2test to read the next line as a continuation of the regu-
lar expression.
A pattern can be followed by a modifier list (details below).
@@ -444,7 +451,7 @@
SUBJECT LINE SYNTAX
- Before each subject line is passed to pcre2_match() or
+ Before each subject line is passed to pcre2_match() or
pcre2_dfa_match(), leading and trailing white space is removed, and the
line is scanned for backslash escapes, unless the subject_literal modi-
fier was set for the pattern. The following provide a means of encoding
@@ -465,15 +472,15 @@
\x{hh...} hexadecimal character (any number of hex digits)
The use of \x{hh...} is not dependent on the use of the utf modifier on
- the pattern. It is recognized always. There may be any number of hexa-
- decimal digits inside the braces; invalid values provoke error mes-
+ the pattern. It is recognized always. There may be any number of hexa-
+ decimal digits inside the braces; invalid values provoke error mes-
sages.
- Note that \xhh specifies one byte rather than one character in UTF-8
- mode; this makes it possible to construct invalid UTF-8 sequences for
- testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
- character in UTF-8 mode, generating more than one byte if the value is
- greater than 127. When testing the 8-bit library not in UTF-8 mode,
+ Note that \xhh specifies one byte rather than one character in UTF-8
+ mode; this makes it possible to construct invalid UTF-8 sequences for
+ testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8
+ character in UTF-8 mode, generating more than one byte if the value is
+ greater than 127. When testing the 8-bit library not in UTF-8 mode,
\x{hh} generates one byte for values less than 256, and causes an error
for greater values.
@@ -480,8 +487,8 @@
In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it
possible to construct invalid UTF-16 sequences for testing purposes.
- In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
- makes it possible to construct invalid UTF-32 sequences for testing
+ In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This
+ makes it possible to construct invalid UTF-32 sequences for testing
purposes.
There is a special backslash sequence that specifies replication of one
@@ -489,31 +496,31 @@
\[<characters>]{<count>}
- This makes it possible to test long strings without having to provide
+ This makes it possible to test long strings without having to provide
them as part of the file. For example:
\[abc]{4}
- is converted to "abcabcabcabc". This feature does not support nesting.
+ is converted to "abcabcabcabc". This feature does not support nesting.
To include a closing square bracket in the characters, code it as \x5D.
- A backslash followed by an equals sign marks the end of the subject
+ A backslash followed by an equals sign marks the end of the subject
string and the start of a modifier list. For example:
abc\=notbol,notempty
- If the subject string is empty and \= is followed by whitespace, the
- line is treated as a comment line, and is not used for matching. For
+ If the subject string is empty and \= is followed by whitespace, the
+ line is treated as a comment line, and is not used for matching. For
example:
\= This is a comment.
abc\= This is an invalid modifier list.
- A backslash followed by any other non-alphanumeric character just es-
- capes that character. A backslash followed by anything else causes an
- error. However, if the very last character in the line is a backslash
- (and there is no modifier list), it is ignored. This gives a way of
- passing an empty line as data, since a real empty line terminates the
+ A backslash followed by any other non-alphanumeric character just es-
+ capes that character. A backslash followed by anything else causes an
+ error. However, if the very last character in the line is a backslash
+ (and there is no modifier list), it is ignored. This gives a way of
+ passing an empty line as data, since a real empty line terminates the
data input.
If the subject_literal modifier is set for a pattern, all subject lines
@@ -524,22 +531,22 @@
PATTERN MODIFIERS
- There are several types of modifier that can appear in pattern lines.
+ There are several types of modifier that can appear in pattern lines.
Except where noted below, they may also be used in #pattern commands. A
- pattern's modifier list can add to or override default modifiers that
+ pattern's modifier list can add to or override default modifiers that
were set by a previous #pattern command.
Setting compilation options
- The following modifiers set options for pcre2_compile(). Most of them
- set bits in the options argument of that function, but those whose
+ The following modifiers set options for pcre2_compile(). Most of them
+ set bits in the options argument of that function, but those whose
names start with PCRE2_EXTRA are additional options that are set in the
compile context. For the main options, there are some single-letter ab-
- breviations that are the same as Perl options. There is special han-
- dling for /x: if a second x is present, PCRE2_EXTENDED is converted
- into PCRE2_EXTENDED_MORE as in Perl. A third appearance adds PCRE2_EX-
- TENDED as well, though this makes no difference to the way pcre2_com-
- pile() behaves. See pcre2api for a description of the effects of these
+ breviations that are the same as Perl options. There is special han-
+ dling for /x: if a second x is present, PCRE2_EXTENDED is converted
+ into PCRE2_EXTENDED_MORE as in Perl. A third appearance adds PCRE2_EX-
+ TENDED as well, though this makes no difference to the way pcre2_com-
+ pile() behaves. See pcre2api for a description of the effects of these
options.
allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS
@@ -580,16 +587,16 @@
utf set PCRE2_UTF
As well as turning on the PCRE2_UTF option, the utf modifier causes all
- non-printing characters in output strings to be printed using the
- \x{hh...} notation. Otherwise, those less than 0x100 are output in hex
- without the curly brackets. Setting utf in 16-bit or 32-bit mode also
- causes pattern and subject strings to be translated to UTF-16 or
+ non-printing characters in output strings to be printed using the
+ \x{hh...} notation. Otherwise, those less than 0x100 are output in hex
+ without the curly brackets. Setting utf in 16-bit or 32-bit mode also
+ causes pattern and subject strings to be translated to UTF-16 or
UTF-32, respectively, before being passed to library functions.
Setting compilation controls
- The following modifiers affect the compilation process or request in-
- formation about the pattern. There are single-letter abbreviations for
+ The following modifiers affect the compilation process or request in-
+ formation about the pattern. There are single-letter abbreviations for
some that are heavily used in the test files.
bsr=[anycrlf|unicode] specify \R handling
@@ -627,35 +634,35 @@
Newline and \R handling
- The bsr modifier specifies what \R in a pattern should match. If it is
- set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to
- "unicode", \R matches any Unicode newline sequence. The default can be
+ The bsr modifier specifies what \R in a pattern should match. If it is
+ set to "anycrlf", \R matches CR, LF, or CRLF only. If it is set to
+ "unicode", \R matches any Unicode newline sequence. The default can be
specified when PCRE2 is built; if it is not, the default is set to Uni-
code.
- 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
one of CR, LF, CRLF, ANYCRLF, ANY, or NUL (in upper or lower case).
Information about a pattern
- The debug modifier is a shorthand for info,fullbincode, requesting all
+ The debug modifier is a shorthand for info,fullbincode, requesting all
available information.
The bincode modifier causes a representation of the compiled code to be
- output after compilation. This information does not contain length and
+ output after compilation. This information does not contain length and
offset values, which ensures that the same output is generated for dif-
- ferent internal link sizes and different code unit widths. By using
- bincode, the same regression tests can be used in different environ-
+ ferent internal link sizes and different code unit widths. By using
+ bincode, the same regression tests can be used in different environ-
ments.
- The fullbincode modifier, by contrast, does include length and offset
- values. This is used in a few special tests that run only for specific
+ The fullbincode modifier, by contrast, does include length and offset
+ values. This is used in a few special tests that run only for specific
code unit widths and link sizes, and is also useful for one-off tests.
- The info modifier requests information about the compiled pattern
- (whether it is anchored, has a fixed first character, and so on). The
- information is obtained from the pcre2_pattern_info() function. Here
+ The info modifier requests information about the compiled pattern
+ (whether it is anchored, has a fixed first character, and so on). The
+ information is obtained from the pcre2_pattern_info() function. Here
are some typical examples:
re> /(?i)(^a|^b)/m,info
@@ -673,23 +680,23 @@
Last code unit = 'c' (caseless)
Subject length lower bound = 3
- "Compile options" are those specified by modifiers; "overall options"
- have added options that are taken or deduced from the pattern. If both
- sets of options are the same, just a single "options" line is output;
- if there are no options, the line is omitted. "First code unit" is
- where any match must start; if there is more than one they are listed
- as "starting code units". "Last code unit" is the last literal code
- unit that must be present in any match. This is not necessarily the
- last character. These lines are omitted if no starting or ending code
- units are recorded. The subject length line is omitted when
- no_start_optimize is set because the minimum length is not calculated
+ "Compile options" are those specified by modifiers; "overall options"
+ have added options that are taken or deduced from the pattern. If both
+ sets of options are the same, just a single "options" line is output;
+ if there are no options, the line is omitted. "First code unit" is
+ where any match must start; if there is more than one they are listed
+ as "starting code units". "Last code unit" is the last literal code
+ unit that must be present in any match. This is not necessarily the
+ last character. These lines are omitted if no starting or ending code
+ units are recorded. The subject length line is omitted when
+ no_start_optimize is set because the minimum length is not calculated
when it can never be used.
- The framesize modifier shows the size, in bytes, of the storage frames
- used by pcre2_match() for handling backtracking. The size depends on
+ The framesize modifier shows the size, in bytes, of the storage frames
+ used by pcre2_match() for handling backtracking. The size depends on
the number of capturing parentheses in the pattern.
- The callout_info modifier requests information about all the callouts
+ The callout_info modifier requests information about all the callouts
in the pattern. A list of them is output at the end of any other infor-
mation that is requested. For each callout, either its number or string
is given, followed by the item that follows it in the pattern.
@@ -696,60 +703,60 @@
Passing a NULL context
- Normally, pcre2test passes a context block to pcre2_compile(). If the
- null_context modifier is set, however, NULL is passed. This is for
- testing that pcre2_compile() behaves correctly in this case (it uses
+ Normally, pcre2test passes a context block to pcre2_compile(). If the
+ null_context modifier is set, however, NULL is passed. This is for
+ testing that pcre2_compile() behaves correctly in this case (it uses
default values).
Specifying pattern characters in hexadecimal
- The hex modifier specifies that the characters of the pattern, except
- for substrings enclosed in single or double quotes, are to be inter-
- preted as pairs of hexadecimal digits. This feature is provided as a
+ The hex modifier specifies that the characters of the pattern, except
+ for substrings enclosed in single or double quotes, are to be inter-
+ preted as pairs of hexadecimal digits. This feature is provided as a
way of creating patterns that contain binary zeros and other non-print-
- ing characters. White space is permitted between pairs of digits. For
+ ing characters. White space is permitted between pairs of digits. For
example, this pattern contains three characters:
/ab 32 59/hex
- Parts of such a pattern are taken literally if quoted. This pattern
- contains nine characters, only two of which are specified in hexadeci-
+ Parts of such a pattern are taken literally if quoted. This pattern
+ contains nine characters, only two of which are specified in hexadeci-
mal:
/ab "literal" 32/hex
- Either single or double quotes may be used. There is no way of includ-
- ing the delimiter within a substring. The hex and expand modifiers are
+ Either single or double quotes may be used. There is no way of includ-
+ ing the delimiter within a substring. The hex and expand modifiers are
mutually exclusive.
Specifying the pattern's length
By default, patterns are passed to the compiling functions as zero-ter-
- minated strings but can be passed by length instead of being zero-ter-
- minated. The use_length modifier causes this to happen. Using a length
- happens automatically (whether or not use_length is set) when hex is
- set, because patterns specified in hexadecimal may contain binary ze-
+ minated strings but can be passed by length instead of being zero-ter-
+ minated. The use_length modifier causes this to happen. Using a length
+ happens automatically (whether or not use_length is set) when hex is
+ set, because patterns specified in hexadecimal may contain binary ze-
ros.
If hex or use_length is used with the POSIX wrapper API (see "Using the
- POSIX wrapper API" below), the REG_PEND extension is used to pass the
+ POSIX wrapper API" below), the REG_PEND extension is used to pass the
pattern's length.
Specifying wide characters in 16-bit and 32-bit modes
In 16-bit and 32-bit modes, all input is automatically treated as UTF-8
- and translated to UTF-16 or UTF-32 when the utf modifier is set. For
+ and translated to UTF-16 or UTF-32 when the utf modifier is set. For
testing the 16-bit and 32-bit libraries in non-UTF mode, the utf8_input
- modifier can be used. It is mutually exclusive with utf. Input lines
+ modifier can be used. It is mutually exclusive with utf. Input lines
are interpreted as UTF-8 as a means of specifying wide characters. More
details are given in "Input encoding" above.
Generating long repetitive patterns
- Some tests use long patterns that are very repetitive. Instead of cre-
- ating a very long input line for such a pattern, you can use a special
- repetition feature, similar to the one described for subject lines
- above. If the expand modifier is present on a pattern, parts of the
+ Some tests use long patterns that are very repetitive. Instead of cre-
+ ating a very long input line for such a pattern, you can use a special
+ repetition feature, similar to the one described for subject lines
+ above. If the expand modifier is present on a pattern, parts of the
pattern that have the form
\[<characters>]{<count>}
@@ -756,34 +763,34 @@
are expanded before the pattern is passed to pcre2_compile(). For exam-
ple, \[AB]{6000} is expanded to "ABAB..." 6000 times. This construction
- cannot be nested. An initial "\[" sequence is recognized only if "]{"
- followed by decimal digits and "}" is found later in the pattern. If
+ cannot be nested. An initial "\[" sequence is recognized only if "]{"
+ followed by decimal digits and "}" is found later in the pattern. If
not, the characters remain in the pattern unaltered. The expand and hex
modifiers are mutually exclusive.
- If part of an expanded pattern looks like an expansion, but is really
+ If part of an expanded pattern looks like an expansion, but is really
part of the actual pattern, unwanted expansion can be avoided by giving
two values in the quantifier. For example, \[AB]{6000,6000} is not rec-
ognized as an expansion item.
- If the info modifier is set on an expanded pattern, the result of the
+ If the info modifier is set on an expanded pattern, the result of the
expansion is included in the information that is output.
JIT compilation
- Just-in-time (JIT) compiling is a heavyweight optimization that can
- greatly speed up pattern matching. See the pcre2jit documentation for
- details. JIT compiling happens, optionally, after a pattern has been
- successfully compiled into an internal form. The JIT compiler converts
+ Just-in-time (JIT) compiling is a heavyweight optimization that can
+ greatly speed up pattern matching. See the pcre2jit documentation for
+ details. JIT compiling happens, optionally, after a pattern has been
+ successfully compiled into an internal form. The JIT compiler converts
this to optimized machine code. It needs to know whether the match-time
options PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT are going to be used,
- because different code is generated for the different cases. See the
- partial modifier in "Subject Modifiers" below for details of how these
+ because different code is generated for the different cases. See the
+ partial modifier in "Subject Modifiers" below for details of how these
options are specified for each match attempt.
JIT compilation is requested by the jit pattern modifier, which may op-
- tionally be followed by an equals sign and a number in the range 0 to
- 7. The three bits that make up the number specify which of the three
+ tionally be followed by an equals sign and a number in the range 0 to
+ 7. The three bits that make up the number specify which of the three
JIT operating modes are to be compiled:
1 compile JIT code for non-partial matching
@@ -800,31 +807,31 @@
6 soft and hard partial matching only
7 all three modes
- If no number is given, 7 is assumed. The phrase "partial matching"
+ If no number is given, 7 is assumed. The phrase "partial matching"
means a call to pcre2_match() with either the PCRE2_PARTIAL_SOFT or the
- PCRE2_PARTIAL_HARD option set. Note that such a call may return a com-
+ PCRE2_PARTIAL_HARD option set. Note that such a call may return a com-
plete match; the options enable the possibility of a partial match, but
- do not require it. Note also that if you request JIT compilation only
- for partial matching (for example, jit=2) but do not set the partial
- modifier on a subject line, that match will not use JIT code because
+ do not require it. Note also that if you request JIT compilation only
+ for partial matching (for example, jit=2) but do not set the partial
+ modifier on a subject line, that match will not use JIT code because
none was compiled for non-partial matching.
- If JIT compilation is successful, the compiled JIT code will automati-
+ If JIT compilation is successful, the compiled JIT code will automati-
cally be used when an appropriate type of match is run, except when in-
- compatible run-time options are specified. For more details, see the
- pcre2jit documentation. See also the jitstack modifier below for a way
+ compatible run-time options are specified. For more details, see the
+ pcre2jit documentation. See also the jitstack modifier below for a way
of setting the size of the JIT stack.
- If the jitfast modifier is specified, matching is done using the JIT
- "fast path" interface, pcre2_jit_match(), which skips some of the san-
- ity checks that are done by pcre2_match(), and of course does not work
- when JIT is not supported. If jitfast is specified without jit, jit=7
+ If the jitfast modifier is specified, matching is done using the JIT
+ "fast path" interface, pcre2_jit_match(), which skips some of the san-
+ ity checks that are done by pcre2_match(), and of course does not work
+ when JIT is not supported. If jitfast is specified without jit, jit=7
is assumed.
- If the jitverify modifier is specified, information about the compiled
- pattern shows whether JIT compilation was or was not successful. If
- jitverify is specified without jit, jit=7 is assumed. If JIT compila-
- tion is successful when jitverify is set, the text "(JIT)" is added to
+ If the jitverify modifier is specified, information about the compiled
+ pattern shows whether JIT compilation was or was not successful. If
+ jitverify is specified without jit, jit=7 is assumed. If JIT compila-
+ tion is successful when jitverify is set, the text "(JIT)" is added to
the first output line after a match or non match when JIT-compiled code
was actually used in the match.
@@ -835,19 +842,19 @@
/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
+ 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
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-
+ 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 hold
- the compiled pattern to be output. This does not include the size of
- the pcre2_code block; it is just the actual compiled data. If the pat-
- tern is subsequently passed to the JIT compiler, the size of the JIT
+ the compiled pattern to be output. This does not include the size of
+ the pcre2_code block; it is just the actual compiled data. If the pat-
+ 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
@@ -857,27 +864,27 @@
Limiting nested parentheses
- The parens_nest_limit modifier sets a limit on the depth of nested
- parentheses in a pattern. Breaching the limit causes a compilation er-
- ror. The default for the library is set when PCRE2 is built, but
- pcre2test sets its own default of 220, which is required for running
+ The parens_nest_limit modifier sets a limit on the depth of nested
+ parentheses in a pattern. Breaching the limit causes a compilation er-
+ ror. The default for the library is set when PCRE2 is built, but
+ pcre2test sets its own default of 220, which is required for running
the standard test suite.
Limiting the pattern length
- The max_pattern_length modifier sets a limit, in code units, to the
+ The max_pattern_length modifier sets a limit, in code units, to the
length of pattern that pcre2_compile() will accept. Breaching the limit
- causes a compilation error. The default is the largest number a
+ causes a compilation error. The default is the largest number a
PCRE2_SIZE variable can hold (essentially unlimited).
Using the POSIX wrapper API
- The posix and posix_nosub modifiers cause pcre2test to call PCRE2 via
- the POSIX wrapper API rather than its native API. When posix_nosub is
- used, the POSIX option REG_NOSUB is passed to regcomp(). The POSIX
- wrapper supports only the 8-bit library. Note that it does not imply
+ The posix and posix_nosub modifiers cause pcre2test to call PCRE2 via
+ the POSIX wrapper API rather than its native API. When posix_nosub is
+ used, the POSIX option REG_NOSUB is passed to regcomp(). The POSIX
+ wrapper supports only the 8-bit library. Note that it does not imply
POSIX matching semantics; for more detail see the pcre2posix documenta-
- tion. The following pattern modifiers set options for the regcomp()
+ tion. The following pattern modifiers set options for the regcomp()
function:
caseless REG_ICASE
@@ -887,42 +894,42 @@
ucp REG_UCP ) the POSIX standard
utf REG_UTF8 )
- The regerror_buffsize modifier specifies a size for the error buffer
- that is passed to regerror() in the event of a compilation error. For
+ The regerror_buffsize modifier specifies a size for the error buffer
+ that is passed to regerror() in the event of a compilation error. For
example:
/abc/posix,regerror_buffsize=20
- This provides a means of testing the behaviour of regerror() when the
- buffer is too small for the error message. If this modifier has not
+ This provides a means of testing the behaviour of regerror() when the
+ buffer is too small for the error message. If this modifier has not
been set, a large buffer is used.
- The aftertext and allaftertext subject modifiers work as described be-
+ The aftertext and allaftertext subject modifiers work as described be-
low. All other modifiers are either ignored, with a warning message, or
cause an error.
- The pattern is passed to regcomp() as a zero-terminated string by de-
+ The pattern is passed to regcomp() as a zero-terminated string by de-
fault, but if the use_length or hex modifiers are set, the REG_PEND ex-
tension is used to pass it by length.
Testing the stack guard feature
- 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
+ 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
greater than zero, pcre2_set_compile_recursion_guard() is called to set
- up callback from pcre2_compile() to a local function. The argument it
- receives is the current nesting parenthesis depth; if this is greater
+ up callback from pcre2_compile() to a local function. The argument it
+ receives is the current nesting parenthesis depth; if this is greater
than the value given by the modifier, non-zero is returned, causing the
compilation to be aborted.
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, 2, or 3. 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
- behaviour with different character tables. The digit specifies the ta-
+ be passed to pcre2_compile(). This is used in the PCRE2 tests to check
+ behaviour with different character tables. The digit specifies the ta-
bles as follows:
0 do not pass any special character tables
@@ -933,15 +940,15 @@
In tables 2, some characters whose codes are greater than 128 are iden-
tified as letters, digits, spaces, etc. Tables 3 can be used only after
- a #loadtables command has loaded them from a binary file. Setting al-
+ a #loadtables command has loaded them from a binary file. Setting al-
ternate character tables and a locale are mutually exclusive.
Setting certain match controls
The following modifiers are really subject modifiers, and are described
- under "Subject Modifiers" below. However, they may be included in a
- pattern's modifier list, in which case they are applied to every sub-
- ject line that is processed with that pattern. These modifiers do not
+ under "Subject Modifiers" below. However, they may be included in a
+ pattern's modifier list, in which case they are applied to every sub-
+ ject line that is processed with that pattern. These modifiers do not
affect the compilation process.
aftertext show text after match
@@ -966,39 +973,39 @@
substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET
substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY
- These modifiers may not appear in a #pattern command. If you want them
+ These modifiers may not appear in a #pattern command. If you want them
as defaults, set them in a #subject command.
Specifying literal subject lines
- If the subject_literal modifier is present on a pattern, all the sub-
+ If the subject_literal modifier is present on a pattern, all the sub-
ject lines that it matches are taken as literal strings, with no inter-
- pretation of backslashes. It is not possible to set subject modifiers
- on such lines, but any that are set as defaults by a #subject command
+ pretation of backslashes. It is not possible to set subject modifiers
+ on such lines, but any that are set as defaults by a #subject command
are recognized.
Saving a compiled pattern
- When a pattern with the push modifier is successfully compiled, it is
- pushed onto a stack of compiled patterns, and pcre2test expects the
- next line to contain a new pattern (or a command) instead of a subject
+ When a pattern with the push modifier is successfully compiled, it is
+ pushed onto a stack of compiled patterns, and pcre2test expects the
+ next line to contain a new pattern (or a command) instead of a subject
line. This facility is used when saving compiled patterns to a file, as
- described in the section entitled "Saving and restoring compiled pat-
- terns" below. If pushcopy is used instead of push, a copy of the com-
- piled pattern is stacked, leaving the original as current, ready to
- match the following input lines. This provides a way of testing the
- pcre2_code_copy() function. The push and pushcopy modifiers are in-
- compatible with compilation modifiers such as global that act at match
+ described in the section entitled "Saving and restoring compiled pat-
+ terns" below. If pushcopy is used instead of push, a copy of the com-
+ piled pattern is stacked, leaving the original as current, ready to
+ match the following input lines. This provides a way of testing the
+ pcre2_code_copy() function. The push and pushcopy modifiers are in-
+ compatible with compilation modifiers such as global that act at match
time. Any that are specified are ignored (for the stacked copy), with a
- warning message, except for replace, which causes an error. Note that
- jitverify, which is allowed, does not carry through to any subsequent
+ warning message, except for replace, which causes an error. Note that
+ jitverify, which is allowed, does not carry through to any subsequent
matching that uses a stacked pattern.
Testing foreign pattern conversion
- The experimental foreign pattern conversion functions in PCRE2 can be
- tested by setting the convert modifier. Its argument is a colon-sepa-
- rated list of options, which set the equivalent option for the
+ The experimental foreign pattern conversion functions in PCRE2 can be
+ tested by setting the convert modifier. Its argument is a colon-sepa-
+ rated list of options, which set the equivalent option for the
pcre2_pattern_convert() function:
glob PCRE2_CONVERT_GLOB
@@ -1010,19 +1017,19 @@
The "unset" value is useful for turning off a default that has been set
by a #pattern command. When one of these options is set, the input pat-
- tern is passed to pcre2_pattern_convert(). If the conversion is suc-
- cessful, the result is reflected in the output and then passed to
+ tern is passed to pcre2_pattern_convert(). If the conversion is suc-
+ cessful, the result is reflected in the output and then passed to
pcre2_compile(). The normal utf and no_utf_check options, if set, cause
- the PCRE2_CONVERT_UTF and PCRE2_CONVERT_NO_UTF_CHECK options to be
+ the PCRE2_CONVERT_UTF and PCRE2_CONVERT_NO_UTF_CHECK options to be
passed to pcre2_pattern_convert().
By default, the conversion function is allowed to allocate a buffer for
- its output. However, if the convert_length modifier is set to a value
- greater than zero, pcre2test passes a buffer of the given length. This
+ its output. However, if the convert_length modifier is set to a value
+ greater than zero, pcre2test passes a buffer of the given length. This
makes it possible to test the length check.
- The convert_glob_escape and convert_glob_separator modifiers can be
- used to specify the escape and separator characters for glob process-
+ The convert_glob_escape and convert_glob_separator modifiers can be
+ used to specify the escape and separator characters for glob process-
ing, overriding the defaults, which are operating-system dependent.
@@ -1033,7 +1040,7 @@
Setting match options
- The following modifiers set options for pcre2_match() or
+ The following modifiers set options for pcre2_match() or
pcre2_dfa_match(). See pcreapi for a description of their effects.
anchored set PCRE2_ANCHORED
@@ -1049,34 +1056,34 @@
partial_hard (or ph) set PCRE2_PARTIAL_HARD
partial_soft (or ps) set PCRE2_PARTIAL_SOFT
- The partial matching modifiers are provided with abbreviations because
+ The partial matching modifiers are provided with abbreviations because
they appear frequently in tests.
- If the posix or posix_nosub modifier was present on the pattern, caus-
+ If the posix or posix_nosub modifier was present on the pattern, caus-
ing the POSIX wrapper API to be used, the only option-setting modifiers
that have any effect are notbol, notempty, and noteol, causing REG_NOT-
- BOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to
+ BOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to
regexec(). The other modifiers are ignored, with a warning message.
- There is one additional modifier that can be used with the POSIX wrap-
+ There is one additional modifier that can be used with the POSIX wrap-
per. It is ignored (with a warning) if used for non-POSIX matching.
posix_startend=<n>[:<m>]
- This causes the subject string to be passed to regexec() using the
- REG_STARTEND option, which uses offsets to specify which part of the
- string is searched. If only one number is given, the end offset is
- passed as the end of the subject string. For more detail of REG_STAR-
- TEND, see the pcre2posix documentation. If the subject string contains
- binary zeros (coded as escapes such as \x{00} because pcre2test does
+ This causes the subject string to be passed to regexec() using the
+ REG_STARTEND option, which uses offsets to specify which part of the
+ string is searched. If only one number is given, the end offset is
+ passed as the end of the subject string. For more detail of REG_STAR-
+ TEND, see the pcre2posix documentation. If the subject string contains
+ binary zeros (coded as escapes such as \x{00} because pcre2test does
not support actual binary zeros in its input), you must use posix_star-
tend to specify its length.
Setting match controls
- The following modifiers affect the matching process or request addi-
- tional information. Some of them may also be specified on a pattern
- line (see above), in which case they apply to every subject line that
+ The following modifiers affect the matching process or request addi-
+ tional information. Some of them may also be specified on a pattern
+ line (see above), in which case they apply to every subject line that
is matched against that pattern.
aftertext show text after match
@@ -1125,29 +1132,29 @@
zero_terminate pass the subject as zero-terminated
The effects of these modifiers are described in the following sections.
- When matching via the POSIX wrapper API, the aftertext, allaftertext,
- and ovector subject modifiers work as described below. All other modi-
+ When matching via the POSIX wrapper API, the aftertext, allaftertext,
+ and ovector subject modifiers work as described below. All other modi-
fiers are either ignored, with a warning message, or cause an error.
Showing more text
- The aftertext modifier requests that as well as outputting the part of
+ The aftertext modifier requests that as well as outputting the part of
the subject string that matched the entire pattern, pcre2test should in
addition output the remainder of the subject string. This is useful for
tests where the subject contains multiple copies of the same substring.
- The allaftertext modifier requests the same action for captured sub-
+ The allaftertext modifier requests the same action for captured sub-
strings as well as the main matched substring. In each case the remain-
der is output on the following line with a plus character following the
capture number.
- The allusedtext modifier requests that all the text that was consulted
- during a successful pattern match by the interpreter should be shown,
- for both full and partial matches. This feature is not supported for
- JIT matching, and if requested with JIT it is ignored (with a warning
- message). Setting this modifier affects the output if there is a look-
- behind at the start of a match, or, for a complete match, a lookahead
+ The allusedtext modifier requests that all the text that was consulted
+ during a successful pattern match by the interpreter should be shown,
+ for both full and partial matches. This feature is not supported for
+ JIT matching, and if requested with JIT it is ignored (with a warning
+ message). Setting this modifier affects the output if there is a look-
+ behind at the start of a match, or, for a complete match, a lookahead
at the end, or if \K is used in the pattern. Characters that precede or
- follow the start and end of the actual match are indicated in the out-
+ follow the start and end of the actual match are indicated in the out-
put by '<' or '>' characters underneath them. Here is an example:
re> /(?<=pqr)abc(?=xyz)/
@@ -1158,16 +1165,16 @@
Partial match: pqrabcxy
<<<
- The first, complete match shows that the matched string is "abc", with
- the preceding and following strings "pqr" and "xyz" having been con-
- sulted during the match (when processing the assertions). The partial
+ The first, complete match shows that the matched string is "abc", with
+ the preceding and following strings "pqr" and "xyz" having been con-
+ sulted during the match (when processing the assertions). The partial
match can indicate only the preceding string.
- The startchar modifier requests that the starting character for the
- match be indicated, if it is different to the start of the matched
+ The startchar modifier requests that the starting character for the
+ match be indicated, if it is different to the start of the matched
string. The only time when this occurs is when \K has been processed as
part of the match. In this situation, the output for the matched string
- is displayed from the starting character instead of from the match
+ is displayed from the starting character instead of from the match
point, with circumflex characters under the earlier characters. For ex-
ample:
@@ -1176,7 +1183,7 @@
0: abcxyz
^^^
- Unlike allusedtext, the startchar modifier can be used with JIT. How-
+ Unlike allusedtext, the startchar modifier can be used with JIT. How-
ever, these two modifiers are mutually exclusive.
Showing the value of all capture groups
@@ -1184,9 +1191,9 @@
The allcaptures modifier requests that the values of all potential cap-
tured parentheses be output after a match. By default, only those up to
the highest one actually used in the match are output (corresponding to
- the return code from pcre2_match()). Groups that did not take part in
- the match are output as "<unset>". This modifier is not relevant for
- DFA matching (which does no capturing) and does not apply when replace
+ the return code from pcre2_match()). Groups that did not take part in
+ the match are output as "<unset>". This modifier is not relevant for
+ DFA matching (which does no capturing) and does not apply when replace
is specified; it is ignored, with a warning message, if present.
Showing the entire ovector, for all outcomes
@@ -1193,53 +1200,53 @@
The allvector modifier requests that the entire ovector be shown, what-
ever the outcome of the match. Compare allcaptures, which shows only up
- to the maximum number of capture groups for the pattern, and then only
- for a successful complete non-DFA match. This modifier, which acts af-
- ter any match result, and also for DFA matching, provides a means of
- checking that there are no unexpected modifications to ovector fields.
- Before each match attempt, the ovector is filled with a special value,
- and if this is found in both elements of a capturing pair, "<un-
- changed>" is output. After a successful match, this applies to all
- groups after the maximum capture group for the pattern. In other cases
- it applies to the entire ovector. After a partial match, the first two
- elements are the only ones that should be set. After a DFA match, the
- amount of ovector that is used depends on the number of matches that
+ to the maximum number of capture groups for the pattern, and then only
+ for a successful complete non-DFA match. This modifier, which acts af-
+ ter any match result, and also for DFA matching, provides a means of
+ checking that there are no unexpected modifications to ovector fields.
+ Before each match attempt, the ovector is filled with a special value,
+ and if this is found in both elements of a capturing pair, "<un-
+ changed>" is output. After a successful match, this applies to all
+ groups after the maximum capture group for the pattern. In other cases
+ it applies to the entire ovector. After a partial match, the first two
+ elements are the only ones that should be set. After a DFA match, the
+ amount of ovector that is used depends on the number of matches that
were found.
Testing pattern callouts
- A callout function is supplied when pcre2test calls the library match-
- ing functions, unless callout_none is specified. Its behaviour can be
- controlled by various modifiers listed above whose names begin with
- callout_. Details are given in the section entitled "Callouts" below.
- Testing callouts from pcre2_substitute() is decribed separately in
+ A callout function is supplied when pcre2test calls the library match-
+ ing functions, unless callout_none is specified. Its behaviour can be
+ controlled by various modifiers listed above whose names begin with
+ callout_. Details are given in the section entitled "Callouts" below.
+ Testing callouts from pcre2_substitute() is decribed separately in
"Testing the substitution function" below.
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
- 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
- searching at a new point within the entire string (which is what Perl
+ 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
+ searching at a new point within the entire string (which is what Perl
does), whereas the latter passes over a shortened subject. This makes a
difference to the matching process if the pattern begins with a lookbe-
hind assertion (including \b or \B).
- If an empty string is matched, the next match is done with the
+ If an empty string is matched, the next match is done with the
PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search
for another, non-empty, match at the same point in the subject. If this
- match fails, the start offset is advanced, and the normal match is re-
- tried. This imitates the way Perl handles such cases when using the /g
- modifier or the split() function. Normally, the start offset is ad-
- vanced by one character, but if the newline convention recognizes CRLF
- as a newline, and the current character is CR followed by LF, an ad-
+ match fails, the start offset is advanced, and the normal match is re-
+ tried. This imitates the way Perl handles such cases when using the /g
+ modifier or the split() function. Normally, the start offset is ad-
+ vanced by one character, but if the newline convention recognizes CRLF
+ as a newline, and the current character is CR followed by LF, an ad-
vance of two characters occurs.
Testing substring extraction functions
- The copy and get modifiers can be used to test the pcre2_sub-
+ The copy and get modifiers can be used to test the pcre2_sub-
string_copy_xxx() and pcre2_substring_get_xxx() functions. They can be
given more than once, and each can specify a capture group name or num-
ber, for example:
@@ -1246,37 +1253,37 @@
abcd\=copy=1,copy=3,get=G1
- If the #subject command is used to set default copy and/or get lists,
- these can be unset by specifying a negative number to cancel all num-
+ If the #subject command is used to set default copy and/or get lists,
+ these can be unset by specifying a negative number to cancel all num-
bered groups and an empty name to cancel all named groups.
- The getall modifier tests pcre2_substring_list_get(), which extracts
+ The getall modifier tests pcre2_substring_list_get(), which extracts
all captured substrings.
- If the subject line is successfully matched, the substrings extracted
- by the convenience functions are output with C, G, or L after the
- string number instead of a colon. This is in addition to the normal
- full list. The string length (that is, the return from the extraction
+ If the subject line is successfully matched, the substrings extracted
+ by the convenience functions are output with C, G, or L after the
+ string number instead of a colon. This is in addition to the normal
+ full list. The string length (that is, the return from the extraction
function) is given in parentheses after each substring, followed by the
name when the extraction was by name.
Testing the substitution function
- If the replace modifier is set, the pcre2_substitute() function is
- called instead of one of the matching functions (or after one call of
- pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note that re-
- placement strings cannot contain commas, because a comma signifies the
- end of a modifier. This is not thought to be an issue in a test pro-
+ If the replace modifier is set, the pcre2_substitute() function is
+ called instead of one of the matching functions (or after one call of
+ pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note that re-
+ placement strings cannot contain commas, because a comma signifies the
+ end of a modifier. This is not thought to be an issue in a test pro-
gram.
- Unlike subject strings, pcre2test does not process replacement strings
- for escape sequences. In UTF mode, a replacement string is checked to
- see if it is a valid UTF-8 string. If so, it is correctly converted to
- a UTF string of the appropriate code unit width. If it is not a valid
- UTF-8 string, the individual code units are copied directly. This pro-
+ Unlike subject strings, pcre2test does not process replacement strings
+ for escape sequences. In UTF mode, a replacement string is checked to
+ see if it is a valid UTF-8 string. If so, it is correctly converted to
+ a UTF string of the appropriate code unit width. If it is not a valid
+ UTF-8 string, the individual code units are copied directly. This pro-
vides a means of passing an invalid UTF-8 string for testing purposes.
- The following modifiers set options (in additional to the normal match
+ The following modifiers set options (in additional to the normal match
options) for pcre2_substitute():
global PCRE2_SUBSTITUTE_GLOBAL
@@ -1290,8 +1297,8 @@
See the pcre2api documentation for details of these options.
- After a successful substitution, the modified string is output, pre-
- ceded by the number of replacements. This may be zero if there were no
+ After a successful substitution, the modified string is output, pre-
+ ceded by the number of replacements. This may be zero if there were no
matches. Here is a simple example of a substitution test:
/abc/replace=xxx
@@ -1300,12 +1307,12 @@
=abc=abc=\=global
2: =xxx=xxx=
- Subject and replacement strings should be kept relatively short (fewer
- than 256 characters) for substitution tests, as fixed-size buffers are
- used. To make it easy to test for buffer overflow, if the replacement
- string starts with a number in square brackets, that number is passed
- to pcre2_substitute() as the size of the output buffer, with the re-
- placement string starting at the next character. Here is an example
+ Subject and replacement strings should be kept relatively short (fewer
+ than 256 characters) for substitution tests, as fixed-size buffers are
+ used. To make it easy to test for buffer overflow, if the replacement
+ string starts with a number in square brackets, that number is passed
+ to pcre2_substitute() as the size of the output buffer, with the re-
+ placement string starting at the next character. Here is an example
that tests the edge case:
/abc/
@@ -1315,12 +1322,12 @@
Failed: error -47: no more memory
The default action of pcre2_substitute() is to return PCRE2_ER-
- ROR_NOMEMORY when the output buffer is too small. However, if the
- PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the substi-
+ ROR_NOMEMORY when the output buffer is too small. However, if the
+ PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the substi-
tute_overflow_length modifier), pcre2_substitute() continues to go
- through the motions of matching and substituting (but not doing any
- callouts), in order to compute the size of buffer that is required.
- When this happens, pcre2test shows the required buffer length (which
+ through the motions of matching and substituting (but not doing any
+ callouts), in order to compute the size of buffer that is required.
+ When this happens, pcre2test shows the required buffer length (which
includes space for the trailing zero) as part of the error message. For
example:
@@ -1329,15 +1336,15 @@
Failed: error -47: no more memory: 10 code units are needed
A replacement string is ignored with POSIX and DFA matching. Specifying
- partial matching provokes an error return ("bad option value") from
+ partial matching provokes an error return ("bad option value") from
pcre2_substitute().
Testing substitute callouts
If the substitute_callout modifier is set, a substitution callout func-
- tion is set up. The null_context modifier must not be set, because the
- address of the callout function is passed in a match context. When the
- callout function is called (after each substitution), details of the
+ tion is set up. The null_context modifier must not be set, because the
+ address of the callout function is passed in a match context. When the
+ callout function is called (after each substitution), details of the
the input and output strings are output. For example:
/abc/g,replace=<$0>,substitute_callout
@@ -1346,19 +1353,19 @@
2(1) Old 6 9 "abc" New 8 13 "<abc>"
2: <abc>def<abc>pqr
- The first number on each callout line is the count of matches. The
+ The first number on each callout line is the count of matches. The
parenthesized number is the number of pairs that are set in the ovector
- (that is, one more than the number of capturing groups that were set).
+ (that is, one more than the number of capturing groups that were set).
Then are listed the offsets of the old substring, its contents, and the
same for the replacement.
- By default, the substitution callout function returns zero, which ac-
- cepts the replacement and causes matching to continue if /g was used.
- Two further modifiers can be used to test other return values. If sub-
- stitute_skip is set to a value greater than zero the callout function
- returns +1 for the match of that number, and similarly substitute_stop
- returns -1. These cause the replacement to be rejected, and -1 causes
- no further matching to take place. If either of them are set, substi-
+ By default, the substitution callout function returns zero, which ac-
+ cepts the replacement and causes matching to continue if /g was used.
+ Two further modifiers can be used to test other return values. If sub-
+ stitute_skip is set to a value greater than zero the callout function
+ returns +1 for the match of that number, and similarly substitute_stop
+ returns -1. These cause the replacement to be rejected, and -1 causes
+ no further matching to take place. If either of them are set, substi-
tute_callout is assumed. For example:
/abc/g,replace=<$0>,substitute_skip=1
@@ -1376,55 +1383,55 @@
Setting the JIT stack size
- The jitstack modifier provides a way of setting the maximum stack size
- that is used by the just-in-time optimization code. It is ignored if
- JIT optimization is not being used. The value is a number of kibibytes
- (units of 1024 bytes). Setting zero reverts to the default of 32KiB.
+ The jitstack modifier provides a way of setting the maximum stack size
+ that is used by the just-in-time optimization code. It is ignored if
+ JIT optimization is not being used. The value is a number of kibibytes
+ (units of 1024 bytes). Setting zero reverts to the default of 32KiB.
Providing a stack that is larger than the default is necessary only for
- very complicated patterns. If jitstack is set non-zero on a subject
+ very complicated patterns. If jitstack is set non-zero on a subject
line it overrides any value that was set on the pattern.
Setting heap, match, and depth limits
- The heap_limit, match_limit, and depth_limit modifiers set the appro-
- priate limits in the match context. These values are ignored when the
+ The heap_limit, match_limit, and depth_limit modifiers set the appro-
+ priate limits in the match context. These values are ignored when the
find_limits modifier is specified.
Finding minimum limits
- If the find_limits modifier is present on a subject line, pcre2test
- calls the relevant matching function several times, setting different
- values in the match context via pcre2_set_heap_limit(),
- pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds the
- minimum values for each parameter that allows the match to complete
+ If the find_limits modifier is present on a subject line, pcre2test
+ calls the relevant matching function several times, setting different
+ values in the match context via pcre2_set_heap_limit(),
+ pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds the
+ minimum values for each parameter that allows the match to complete
without error. If JIT is being used, only the match limit is relevant.
When using this modifier, the pattern should not contain any limit set-
- tings such as (*LIMIT_MATCH=...) within it. If such a setting is
+ tings such as (*LIMIT_MATCH=...) within it. If such a setting is
present and is lower than the minimum matching value, the minimum value
- cannot be found because pcre2_set_match_limit() etc. are only able to
+ cannot be found because pcre2_set_match_limit() etc. are only able to
reduce the value of an in-pattern limit; they cannot increase it.
- For non-DFA matching, the minimum depth_limit number is a measure of
+ For non-DFA matching, the minimum depth_limit number is a measure of
how much nested backtracking happens (that is, how deeply the pattern's
- tree is searched). In the case of DFA matching, depth_limit controls
- the depth of recursive calls of the internal function that is used for
+ tree is searched). In the case of DFA matching, depth_limit controls
+ the depth of recursive calls of the internal function that is used for
handling pattern recursion, lookaround assertions, and atomic groups.
For non-DFA matching, the match_limit number is a measure of the amount
of backtracking that takes place, and learning the minimum value can be
- instructive. For most simple matches, the number is quite small, but
- for patterns with very large numbers of matching possibilities, it can
- become large very quickly with increasing length of subject string. In
- the case of DFA matching, match_limit controls the total number of
+ instructive. For most simple matches, the number is quite small, but
+ for patterns with very large numbers of matching possibilities, it can
+ become large very quickly with increasing length of subject string. In
+ the case of DFA matching, match_limit controls the total number of
calls, both recursive and non-recursive, to the internal matching func-
tion, thus controlling the overall amount of computing resource that is
used.
- For both kinds of matching, the heap_limit number, which is in
- kibibytes (units of 1024 bytes), limits the amount of heap memory used
+ For both kinds of matching, the heap_limit number, which is in
+ kibibytes (units of 1024 bytes), limits the amount of heap memory used
for matching. A value of zero disables the use of any heap memory; many
- simple pattern matches can be done without using the heap, so zero is
+ simple pattern matches can be done without using the heap, so zero is
not an unreasonable setting.
Showing MARK names
@@ -1431,50 +1438,50 @@
The mark modifier causes the names from backtracking control verbs that
- are returned from calls to pcre2_match() to be displayed. If a mark is
- returned for a match, non-match, or partial match, pcre2test shows it.
- For a match, it is on a line by itself, tagged with "MK:". Otherwise,
+ are returned from calls to pcre2_match() to be displayed. If a mark is
+ returned for a match, non-match, or partial match, pcre2test shows it.
+ For a match, it is on a line by itself, tagged with "MK:". Otherwise,
it is added to the non-match message.
Showing memory usage
- The memory modifier causes pcre2test to log the sizes of all heap mem-
- ory allocation and freeing calls that occur during a call to
- pcre2_match() or pcre2_dfa_match(). These occur only when a match re-
- quires a bigger vector than the default for remembering backtracking
- points (pcre2_match()) or for internal workspace (pcre2_dfa_match()).
- In many cases there will be no heap memory used and therefore no addi-
+ The memory modifier causes pcre2test to log the sizes of all heap mem-
+ ory allocation and freeing calls that occur during a call to
+ pcre2_match() or pcre2_dfa_match(). These occur only when a match re-
+ quires a bigger vector than the default for remembering backtracking
+ points (pcre2_match()) or for internal workspace (pcre2_dfa_match()).
+ In many cases there will be no heap memory used and therefore no addi-
tional output. No heap memory is allocated during matching with JIT, so
- in that case the memory modifier never has any effect. For this modi-
- fier to work, the null_context modifier must not be set on both the
+ in that case the memory modifier never has any effect. For this modi-
+ fier to work, the null_context modifier must not be set on both the
pattern and the subject, though it can be set on one or the other.
Setting a starting offset
- The offset modifier sets an offset in the subject string at which
+ The offset modifier sets an offset in the subject string at which
matching starts. Its value is a number of code units, not characters.
Setting an offset limit
- The offset_limit modifier sets a limit for unanchored matches. If a
+ The offset_limit modifier sets a limit for unanchored matches. If a
match cannot be found starting at or before this offset in the subject,
a "no match" return is given. The data value is a number of code units,
- not characters. When this modifier is used, the use_offset_limit modi-
+ not characters. When this modifier is used, the use_offset_limit modi-
fier must have been set for the pattern; if not, an error is generated.
Setting the size of the output vector
- The ovector modifier applies only to the subject line in which it ap-
+ The ovector modifier applies only to the subject line in which it ap-
pears, though of course it can also be used to set a default in a #sub-
- ject command. It specifies the number of pairs of offsets that are
+ ject command. It specifies the number of pairs of offsets that are
available for storing matching information. The default is 15.
- A value of zero is useful when testing the POSIX API because it causes
+ A value of zero is useful when testing the POSIX API because it causes
regexec() to be called with a NULL capture vector. When not testing the
- POSIX API, a value of zero is used to cause pcre2_match_data_cre-
- ate_from_pattern() to be called, in order to create a match block of
+ POSIX API, a value of zero is used to cause pcre2_match_data_cre-
+ ate_from_pattern() to be called, in order to create a match block of
exactly the right size for the pattern. (It is not possible to create a
- match block with a zero-length ovector; there is always at least one
+ match block with a zero-length ovector; there is always at least one
pair of offsets.)
Passing the subject as zero-terminated
@@ -1481,55 +1488,55 @@
By default, the subject string is passed to a native API matching func-
tion with its correct length. In order to test the facility for passing
- a zero-terminated string, the zero_terminate modifier is provided. It
- causes the length to be passed as PCRE2_ZERO_TERMINATED. When matching
+ a zero-terminated string, the zero_terminate modifier is provided. It
+ causes the length to be passed as PCRE2_ZERO_TERMINATED. When matching
via the POSIX interface, this modifier is ignored, with a warning.
- When testing pcre2_substitute(), this modifier also has the effect of
+ When testing pcre2_substitute(), this modifier also has the effect of
passing the replacement string as zero-terminated.
Passing a NULL context
- Normally, pcre2test passes a context block to pcre2_match(),
- pcre2_dfa_match(), pcre2_jit_match() or pcre2_substitute(). If the
- null_context modifier is set, however, NULL is passed. This is for
- testing that the matching and substitution functions behave correctly
- in this case (they use default values). This modifier cannot be used
+ Normally, pcre2test passes a context block to pcre2_match(),
+ pcre2_dfa_match(), pcre2_jit_match() or pcre2_substitute(). If the
+ null_context modifier is set, however, NULL is passed. This is for
+ testing that the matching and substitution functions behave correctly
+ in this case (they use default values). This modifier cannot be used
with the find_limits or substitute_callout modifiers.
THE ALTERNATIVE MATCHING FUNCTION
- By default, pcre2test uses the standard PCRE2 matching function,
+ By default, pcre2test uses the standard PCRE2 matching function,
pcre2_match() to match each subject line. PCRE2 also supports an alter-
- native matching function, pcre2_dfa_match(), which operates in a dif-
- ferent way, and has some restrictions. The differences between the two
+ native matching function, pcre2_dfa_match(), which operates in a dif-
+ ferent way, and has some restrictions. The differences between the two
functions are described in the pcre2matching documentation.
- If the dfa modifier is set, the alternative matching function is used.
- This function finds all possible matches at a given point in the sub-
- ject. If, however, the dfa_shortest modifier is set, processing stops
- after the first match is found. This is always the shortest possible
+ If the dfa modifier is set, the alternative matching function is used.
+ This function finds all possible matches at a given point in the sub-
+ ject. If, however, the dfa_shortest modifier is set, processing stops
+ after the first match is found. This is always the shortest possible
match.
DEFAULT OUTPUT FROM pcre2test
- This section describes the output when the normal matching function,
+ This section describes the output when the normal matching function,
pcre2_match(), is being used.
- When a match succeeds, pcre2test outputs the list of captured sub-
- strings, starting with number 0 for the string that matched the whole
+ When a match succeeds, pcre2test outputs the list of captured sub-
+ strings, starting with number 0 for the string that matched the whole
pattern. Otherwise, it outputs "No match" when the return is PCRE2_ER-
- ROR_NOMATCH, or "Partial match:" followed by the partially matching
- substring when the return is PCRE2_ERROR_PARTIAL. (Note that this is
- the entire substring that was inspected during the partial match; it
- may include characters before the actual match start if a lookbehind
+ ROR_NOMATCH, or "Partial match:" followed by the partially matching
+ substring when the return is PCRE2_ERROR_PARTIAL. (Note that this is
+ the entire substring that was inspected during the partial match; it
+ may include characters before the actual match start if a lookbehind
assertion, \K, \b, or \B was involved.)
For any other return, pcre2test outputs the PCRE2 negative error number
- and a short descriptive phrase. If the error is a failed UTF string
- check, the code unit offset of the start of the failing character is
+ and a short descriptive phrase. If the error is a failed UTF string
+ check, the code unit offset of the start of the failing character is
also output. Here is an example of an interactive pcre2test run.
$ pcre2test
@@ -1545,8 +1552,8 @@
Unset capturing substrings that are not followed by one that is set are
not shown by pcre2test unless the allcaptures modifier is specified. In
the following example, there are two capturing substrings, but when the
- first data line is matched, the second, unset substring is not shown.
- An "internal" unset substring is shown as "<unset>", as for the second
+ first data line is matched, the second, unset substring is not shown.
+ An "internal" unset substring is shown as "<unset>", as for the second
data line.
re> /(a)|(b)/
@@ -1558,11 +1565,11 @@
1: <unset>
2: b
- 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.
+ 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,
- the output for substring 0 is followed by the the rest of the subject
+ 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:
re> /cat/aftertext
@@ -1582,8 +1589,8 @@
0: ipp
1: pp
- "No match" is output only if the first match attempt fails. Here is an
- example of a failure message (the offset 4 that is specified by the
+ "No match" is output only if the first match attempt fails. Here is an
+ example of a failure message (the offset 4 that is specified by the
offset modifier is past the end of the subject string):
re> /xyz/
@@ -1591,7 +1598,7 @@
Error -24 (bad offset value)
Note that whereas patterns can be continued over several lines (a plain
- ">" prompt is used for continuations), subject lines may not. However
+ ">" prompt is used for continuations), subject lines may not. However
newlines can be included in a subject by means of the \n escape (or \r,
\r\n, etc., depending on the newline sequence setting).
@@ -1599,7 +1606,7 @@
OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
When the alternative matching function, pcre2_dfa_match(), is used, the
- output consists of a list of all the matches that start at the first
+ output consists of a list of all the matches that start at the first
point in the subject where there is at least one match. For example:
re> /(tang|tangerine|tan)/
@@ -1608,11 +1615,11 @@
1: tang
2: tan
- Using the normal matching function on this data finds only "tang". The
- longest matching string is always given first (and numbered zero). Af-
- ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol-
+ Using the normal matching function on this data finds only "tang". The
+ longest matching string is always given first (and numbered zero). Af-
+ ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol-
lowed by the partially matching substring. Note that this is the entire
- substring that was inspected during the partial match; it may include
+ substring that was inspected during the partial match; it may include
characters before the actual match start if a lookbehind assertion, \b,
or \B was involved. (\K is not supported for DFA matching.)
@@ -1628,16 +1635,16 @@
1: tan
0: tan
- The alternative matching function does not support substring capture,
- so the modifiers that are concerned with captured substrings are not
+ The alternative matching function does not support substring capture,
+ so the modifiers that are concerned with captured substrings are not
relevant.
RESTARTING AFTER A PARTIAL MATCH
- When the alternative matching function has given the PCRE2_ERROR_PAR-
+ When the alternative matching function has given the PCRE2_ERROR_PAR-
TIAL return, indicating that the subject partially matched the pattern,
- you can restart the match with additional subject data by means of the
+ you can restart the match with additional subject data by means of the
dfa_restart modifier. For example:
re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
@@ -1646,7 +1653,7 @@
data> n05\=dfa,dfa_restart
0: n05
- For further information about partial matching, see the pcre2partial
+ For further information about partial matching, see the pcre2partial
documentation.
@@ -1653,30 +1660,30 @@
CALLOUTS
If the pattern contains any callout requests, pcre2test's callout func-
- tion is called during matching unless callout_none is specified. This
+ tion is called during matching unless callout_none is specified. This
works with both matching functions, and with JIT, though there are some
- differences in behaviour. The output for callouts with numerical argu-
+ differences in behaviour. The output for callouts with numerical argu-
ments and those with string arguments is slightly different.
Callouts with numerical arguments
By default, the callout function displays the callout number, the start
- and current positions in the subject text at the callout time, and the
+ and current positions in the subject text at the callout time, and the
next pattern item to be tested. For example:
--->pqrabcdef
0 ^ ^ \d
- This output indicates that callout number 0 occurred for a match at-
- tempt starting at the fourth character of the subject string, when the
- pointer was at the seventh character, and when the next pattern item
- was \d. Just one circumflex is output if the start and current posi-
+ This output indicates that callout number 0 occurred for a match at-
+ tempt starting at the fourth character of the subject string, when the
+ pointer was at the seventh character, and when the next pattern item
+ was \d. Just one circumflex is output if the start and current posi-
tions are the same, or if the current position precedes the start posi-
tion, which can happen if the callout is in a lookbehind assertion.
Callouts numbered 255 are assumed to be automatic callouts, inserted as
a result of the auto_callout pattern modifier. In this case, instead of
- showing the callout number, the offset in the pattern, preceded by a
+ showing the callout number, the offset in the pattern, preceded by a
plus, is output. For example:
re> /\d?[A-E]\*/auto_callout
@@ -1703,17 +1710,17 @@
+12 ^ ^
0: abc
- The mark changes between matching "a" and "b", but stays the same for
- the rest of the match, so nothing more is output. If, as a result of
- backtracking, the mark reverts to being unset, the text "<unset>" is
+ The mark changes between matching "a" and "b", but stays the same for
+ the rest of the match, so nothing more is output. If, as a result of
+ backtracking, the mark reverts to being unset, the text "<unset>" is
output.
Callouts with string arguments
The output for a callout with a string argument is similar, except that
- instead of outputting a callout number before the position indicators,
- the callout string and its offset in the pattern string are output be-
- fore the reflection of the subject string, and the subject string is
+ instead of outputting a callout number before the position indicators,
+ the callout string and its offset in the pattern string are output be-
+ fore the reflection of the subject string, and the subject string is
reflected for each callout. For example:
re> /^ab(?C'first')cd(?C"second")ef/
@@ -1729,26 +1736,26 @@
Callout modifiers
- The callout function in pcre2test returns zero (carry on matching) by
- default, but you can use a callout_fail modifier in a subject line to
+ The callout function in pcre2test returns zero (carry on matching) by
+ default, but you can use a callout_fail modifier in a subject line to
change this and other parameters of the callout (see below).
If the callout_capture modifier is set, the current captured groups are
output when a callout occurs. This is useful only for non-DFA matching,
- as pcre2_dfa_match() does not support capturing, so no captures are
+ as pcre2_dfa_match() does not support capturing, so no captures are
ever shown.
The normal callout output, showing the callout number or pattern offset
- (as described above) is suppressed if the callout_no_where modifier is
+ (as described above) is suppressed if the callout_no_where modifier is
set.
- When using the interpretive matching function pcre2_match() without
- JIT, setting the callout_extra modifier causes additional output from
- pcre2test's callout function to be generated. For the first callout in
- a match attempt at a new starting position in the subject, "New match
- attempt" is output. If there has been a backtrack since the last call-
+ When using the interpretive matching function pcre2_match() without
+ JIT, setting the callout_extra modifier causes additional output from
+ pcre2test's callout function to be generated. For the first callout in
+ a match attempt at a new starting position in the subject, "New match
+ attempt" is output. If there has been a backtrack since the last call-
out (or start of matching if this is the first callout), "Backtrack" is
- output, followed by "No other matching paths" if the backtrack ended
+ output, followed by "No other matching paths" if the backtrack ended
the previous match attempt. For example:
re> /(a+)b/auto_callout,no_start_optimize,no_auto_possess
@@ -1785,39 +1792,39 @@
+1 ^ a+
No match
- Notice that various optimizations must be turned off if you want all
- possible matching paths to be scanned. If no_start_optimize is not
- used, there is an immediate "no match", without any callouts, because
- the starting optimization fails to find "b" in the subject, which it
- knows must be present for any match. If no_auto_possess is not used,
- the "a+" item is turned into "a++", which reduces the number of back-
+ Notice that various optimizations must be turned off if you want all
+ possible matching paths to be scanned. If no_start_optimize is not
+ used, there is an immediate "no match", without any callouts, because
+ the starting optimization fails to find "b" in the subject, which it
+ knows must be present for any match. If no_auto_possess is not used,
+ the "a+" item is turned into "a++", which reduces the number of back-
tracks.
- The callout_extra modifier has no effect if used with the DFA matching
+ The callout_extra modifier has no effect if used with the DFA matching
function, or with JIT.
Return values from callouts
- The default return from the callout function is zero, which allows
+ 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 (caus-
ing matching to backtrack) when a callout of that number is reached. If
- two numbers (<n>:<m>) are given, 1 is returned when callout <n> is
- reached and there have been at least <m> callouts. The callout_error
+ two numbers (<n>:<m>) are given, 1 is returned when callout <n> is
+ reached and there have been at least <m> callouts. The callout_error
modifier is similar, except that PCRE2_ERROR_CALLOUT is returned, caus-
- ing 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
+ ing 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.
- 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
- function, and passed back when the callout function is invoked. Any
- value other than zero is used as a return from pcre2test's callout
+ 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
+ function, and passed back when the callout function is invoked. Any
+ value other than zero is used as a return from pcre2test's callout
function.
Inserting callouts can be helpful when using pcre2test to check compli-
- cated regular expressions. For further information about callouts, see
+ cated regular expressions. For further information about callouts, see
the pcre2callout documentation.
@@ -1824,12 +1831,12 @@
NON-PRINTING CHARACTERS
When pcre2test is outputting text in the compiled version of a pattern,
- bytes other than 32-126 are always treated as non-printing characters
+ bytes other than 32-126 are always treated as non-printing characters
and are therefore shown as hex escapes.
- 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 is-
+ 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 is-
print() function is used to distinguish printing and non-printing char-
acters.
@@ -1836,35 +1843,35 @@
SAVING AND RESTORING COMPILED PATTERNS
- It is possible to save compiled patterns on disc or elsewhere, and
+ It is possible to save compiled patterns on disc or elsewhere, and
reload them later, subject to a number of restrictions. JIT data cannot
- be saved. The host on which the patterns are reloaded must be running
+ be saved. The host on which the patterns are reloaded must be running
the same version of PCRE2, with the same code unit width, and must also
- have the same endianness, pointer width and PCRE2_SIZE type. Before
- compiled patterns can be saved they must be serialized, that is, con-
- verted to a stream of bytes. A single byte stream may contain any num-
- ber of compiled patterns, but they must all use the same character ta-
- bles. A single copy of the tables is included in the byte stream (its
+ have the same endianness, pointer width and PCRE2_SIZE type. Before
+ compiled patterns can be saved they must be serialized, that is, con-
+ verted to a stream of bytes. A single byte stream may contain any num-
+ ber of compiled patterns, but they must all use the same character ta-
+ bles. A single copy of the tables is included in the byte stream (its
size is 1088 bytes).
- The functions whose names begin with pcre2_serialize_ are used for se-
- rializing and de-serializing. They are described in the pcre2serialize
- documentation. In this section we describe the features of pcre2test
+ The functions whose names begin with pcre2_serialize_ are used for se-
+ rializing and de-serializing. They are described in the pcre2serialize
+ documentation. In this section we describe the features of pcre2test
that can be used to test these functions.
- Note that "serialization" in PCRE2 does not convert compiled patterns
- to an abstract format like Java or .NET. It just makes a reloadable
+ Note that "serialization" in PCRE2 does not convert compiled patterns
+ to an abstract format like Java or .NET. It just makes a reloadable
byte code stream. Hence the restrictions on reloading mentioned above.
- In pcre2test, when a pattern with push modifier is successfully com-
- piled, it is pushed onto a stack of compiled patterns, and pcre2test
- expects the next line to contain a new pattern (or command) instead of
+ In pcre2test, when a pattern with push modifier is successfully com-
+ piled, it is pushed onto a stack of compiled patterns, and pcre2test
+ expects the next line to contain a new pattern (or command) instead of
a subject line. By contrast, the pushcopy modifier causes a copy of the
- compiled pattern to be stacked, leaving the original available for im-
- mediate matching. By using push and/or pushcopy, a number of patterns
- can be compiled and retained. These modifiers are incompatible with
+ compiled pattern to be stacked, leaving the original available for im-
+ mediate matching. By using push and/or pushcopy, a number of patterns
+ can be compiled and retained. These modifiers are incompatible with
posix, and control modifiers that act at match time are ignored (with a
- message) for the stacked patterns. The jitverify modifier applies only
+ message) for the stacked patterns. The jitverify modifier applies only
at compile time.
The command
@@ -1872,21 +1879,21 @@
#save <filename>
causes all the stacked patterns to be serialized and the result written
- to the named file. Afterwards, all the stacked patterns are freed. The
+ to the named file. Afterwards, all the stacked patterns are freed. The
command
#load <filename>
- reads the data in the file, and then arranges for it to be de-serial-
- ized, with the resulting compiled patterns added to the pattern stack.
- The pattern on the top of the stack can be retrieved by the #pop com-
- mand, which must be followed by lines of subjects that are to be
- matched with the pattern, terminated as usual by an empty line or end
- of file. This command may be followed by a modifier list containing
- only control modifiers that act after a pattern has been compiled. In
- particular, hex, posix, posix_nosub, push, and pushcopy are not al-
- lowed, nor are any option-setting modifiers. The JIT modifiers are,
- however permitted. Here is an example that saves and reloads two pat-
+ reads the data in the file, and then arranges for it to be de-serial-
+ ized, with the resulting compiled patterns added to the pattern stack.
+ The pattern on the top of the stack can be retrieved by the #pop com-
+ mand, which must be followed by lines of subjects that are to be
+ matched with the pattern, terminated as usual by an empty line or end
+ of file. This command may be followed by a modifier list containing
+ only control modifiers that act after a pattern has been compiled. In
+ particular, hex, posix, posix_nosub, push, and pushcopy are not al-
+ lowed, nor are any option-setting modifiers. The JIT modifiers are,
+ however permitted. Here is an example that saves and reloads two pat-
terns.
/abc/push
@@ -1899,10 +1906,10 @@
#pop jit,bincode
abc
- If jitverify is used with #pop, it does not automatically imply jit,
+ If jitverify is used with #pop, it does not automatically imply jit,
which is different behaviour from when it is used on a pattern.
- The #popcopy command is analagous to the pushcopy modifier in that it
+ The #popcopy command is analagous to the pushcopy modifier in that it
makes current a copy of the topmost stack pattern, leaving the original
still on the stack.
@@ -1922,5 +1929,5 @@
REVISION
- Last updated: 20 March 2020
+ Last updated: 14 September 2020
Copyright (c) 1997-2020 University of Cambridge.
Modified: code/trunk/src/pcre2grep.c
===================================================================
--- code/trunk/src/pcre2grep.c 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/src/pcre2grep.c 2020-10-04 16:34:31 UTC (rev 1274)
@@ -164,6 +164,10 @@
enum { BIN_BINARY, BIN_NOMATCH, BIN_TEXT };
+/* Return values from decode_dollar_escape() */
+
+enum { DDE_ERROR, DDE_CAPTURE, DDE_CHAR };
+
/* In newer versions of gcc, with FORTIFY_SOURCE set (the default in some
environments), a warning is issued if the value of fwrite() is ignored.
Unfortunately, casting to (void) does not suppress the warning. To get round
@@ -179,15 +183,23 @@
quote for the example, as single quotes aren't usually available. */
#ifdef WIN32
-#define STDOUT_NL "\r\n"
-#define QUOT "\""
+#define STDOUT_NL "\r\n"
+#define STDOUT_NL_LEN 2
+#define QUOT "\""
#else
-#define STDOUT_NL "\n"
-#define QUOT "'"
+#define STDOUT_NL "\n"
+#define STDOUT_NL_LEN 1
+#define QUOT "'"
#endif
+/* This code is returned from decode_dollar_escape() when $n is encountered,
+and used to mean "output STDOUT_NL". It is, of course, not a valid Unicode code
+point. */
+#define STDOUT_NL_CODE 0x7fffffffu
+
+
/*************************************************
* Global variables *
*************************************************/
@@ -224,8 +236,9 @@
static int bufsize = 3*PCRE2GREP_BUFSIZE;
static int endlinetype;
+static int count_limit = -1; /* Not long, so that it works with OP_NUMBER */
+static unsigned long int counts_printed = 0;
static unsigned long int total_count = 0;
-static unsigned long int counts_printed = 0;
#ifdef WIN32
static int dee_action = dee_SKIP;
@@ -277,6 +290,9 @@
static BOOL silent = FALSE;
static BOOL utf = FALSE;
+static uint8_t utf8_buffer[8];
+
+
/* Structure for list of --only-matching capturing numbers. */
typedef struct omstr {
@@ -443,6 +459,7 @@
{ 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_NODATA, 'M', NULL, "multiline", "run in multiline mode" },
+ { OP_NUMBER, 'm', &count_limit, "max-count=number", "stop after <number> matched lines" },
{ 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" },
#ifdef SUPPORT_PCRE2GREP_JIT
@@ -482,8 +499,13 @@
static const char *newlines[] = {
"DEFAULT", "CR", "LF", "CRLF", "ANY", "ANYCRLF", "NUL" };
-/* UTF-8 tables - used only when the newline setting is "any". */
+/* UTF-8 tables */
+const int utf8_table1[] =
+ { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
+const int utf8_table1_size = sizeof(utf8_table1) / sizeof(int);
+
+const int utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
const char utf8_table4[] = {
@@ -531,7 +553,33 @@
#endif /* not VPCOMPAT && not HAVE_MEMMOVE */
+
/*************************************************
+* Convert code point to UTF-8 *
+*************************************************/
+
+/* A static buffer is used. Returns the number of bytes. */
+
+static int
+ord2utf8(uint32_t value)
+{
+int i, j;
+uint8_t *utf8bytes = utf8_buffer;
+for (i = 0; i < utf8_table1_size; i++)
+ if (value <= (uint32_t)utf8_table1[i]) break;
+utf8bytes += i;
+for (j = i; j > 0; j--)
+ {
+ *utf8bytes-- = 0x80 | (value & 0x3f);
+ value >>= 6;
+ }
+*utf8bytes = utf8_table2[i] | value;
+return i + 1;
+}
+
+
+
+/*************************************************
* Case-independent string compare *
*************************************************/
@@ -1788,6 +1836,7 @@
slen = 200;
msg = "text that starts:\n\n";
}
+
for (i = 1; p != NULL; p = p->next, i++)
{
*mrc = pcre2_match(p->compiled, (PCRE2_SPTR)matchptr, (int)length,
@@ -1823,141 +1872,255 @@
}
+
/*************************************************
-* Check output text for errors *
+* Decode dollar escape sequence *
*************************************************/
-static BOOL
-syntax_check_output_text(PCRE2_SPTR string, BOOL callout)
+/* Called from various places to decode $ escapes in output strings. The escape
+sequences are as follows:
+
+$<digits> or ${<digits>} returns a capture number. However, if callout is TRUE,
+zero is never returned; '0' is substituted.
+
+$a returns bell.
+$b returns backspace.
+$e returns escape.
+$f returns form feed.
+$n returns newline.
+$r returns carriage return.
+$t returns tab.
+$v returns vertical tab.
+$o<digits> returns the character represented by the given octal
+ number; up to three digits are processed.
+$o{<digits>} does the same, up to 7 digits, but gives an error for mode-invalid
+ code points.
+$x<digits> returns the character represented by the given hexadecimal
+ number; up to two digits are processed.
+$x{<digits} does the same, up to 6 digits, but gives an error for mode-invalid
+ code points.
+Any other character is substituted by itself. E.g: $$ is replaced by a single
+dollar.
+
+Arguments:
+ begin the start of the whole string
+ string points to the $
+ callout TRUE if in a callout (inhibits error messages)
+ value where to return a value
+ last where to return pointer to the last used character
+
+Returns: DDE_ERROR after a syntax error
+ DDE_CAPTURE if *value is a capture number
+ DDE_CHAR if *value is a character code
+*/
+
+static int
+decode_dollar_escape(PCRE2_SPTR begin, PCRE2_SPTR string, BOOL callout,
+ uint32_t *value, PCRE2_SPTR *last)
{
-PCRE2_SPTR begin = string;
-for (; *string != 0; string++)
+uint32_t c = 0;
+int base = 10;
+int dcount;
+int rc = DDE_CHAR;
+BOOL brace = FALSE;
+
+switch (*(++string))
{
- if (*string == '$')
+ case 0: /* Syntax error: a character must be present after $. */
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "no character after $");
+ *last = string;
+ return DDE_ERROR;
+
+ case '{':
+ brace = TRUE;
+ string++;
+ if (!isdigit(*string)) /* Syntax error: a decimal number required. */
{
- PCRE2_SIZE capture_id = 0;
- BOOL brace = FALSE;
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
+ (int)(string - begin), "decimal number expected");
+ rc = DDE_ERROR;
+ break;
+ }
+ /* Fall through */
+
+ /* The maximum capture number is 65535, so any number greater than that will
+ always be an unknown capture number. We just stop incrementing, in order to
+ avoid overflow. */
+
+ case '0': case '1': case '2': case '3': case '4':
+ case '5': case '6': case '7': case '8': case '9':
+ do
+ {
+ if (c <= 65535) c = c * 10 + (*string - '0');
string++;
+ }
+ while (*string >= '0' && *string <= '9');
+ string--; /* Point to last digit */
- /* Syntax error: a character must be present after $. */
- if (*string == 0)
- {
- if (!callout)
- fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
- (int)(string - begin), "no character after $");
- return FALSE;
- }
+ /* In a callout, capture number 0 is not available. No error can be given,
+ so just return the character '0'. */
- if (*string == '{')
- {
- /* Must be a decimal number in braces, e.g: {5} or {38} */
- string++;
+ if (callout && c == 0)
+ {
+ *value = '0';
+ }
+ else
+ {
+ *value = c;
+ rc = DDE_CAPTURE;
+ }
+ break;
- brace = TRUE;
- }
+ /* Limit octal numbers to 3 digits without braces, or up to 7 with braces,
+ for valid Unicode code points. */
- if ((*string >= '1' && *string <= '9') || (!callout && *string == '0'))
- {
- do
- {
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
+ case 'o':
+ base = 8;
+ string++;
+ if (*string == '{')
+ {
+ brace = TRUE;
+ string++;
+ dcount = 7;
+ }
+ else dcount = 3;
+ for (; dcount > 0; dcount--)
+ {
+ if (*string < '0' || *string > '7') break;
+ c = c * 8 + (*string++ - '0');
+ }
+ *value = c;
+ string--; /* Point to last digit */
+ break;
- string++;
- }
- while (*string >= '0' && *string <= '9');
+ /* Limit hex numbers to 2 digits without braces, or up to 6 with braces,
+ for valid Unicode code points. */
- if (brace)
+ case 'x':
+ base = 16;
+ string++;
+ if (*string == '{')
+ {
+ brace = TRUE;
+ string++;
+ dcount = 6;
+ }
+ else dcount = 2;
+ for (; dcount > 0; dcount--)
+ {
+ if (!isxdigit(*string)) break;
+ if (*string >= '0' && *string <= '9')
+ c = c *16 + *string++ - '0';
+ else
+ c = c * 16 + (*string++ | 0x20) - 'a' + 10;
+ }
+ *value = c;
+ string--; /* Point to last digit */
+ break;
+
+ case 'a': *value = '\a'; break;
+ case 'b': *value = '\b'; break;
+#ifndef EBCDIC
+ case 'e': *value = '\033'; break;
+#else
+ case 'e': *value = '\047'; break;
+#endif
+ case 'f': *value = '\f'; break;
+ case 'n': *value = STDOUT_NL_CODE; break;
+ case 'r': *value = '\r'; break;
+ case 't': *value = '\t'; break;
+ case 'v': *value = '\v'; break;
+
+ default: *value = *string; break;
+ }
+
+if (brace)
+ {
+ c = string[1];
+ if (c != '}')
+ {
+ rc = DDE_ERROR;
+ if (!callout)
+ {
+ if ((base == 8 && c >= '0' && c <= '7') ||
+ (base == 16 && isxdigit(c)))
{
- /* Syntax error: closing brace is missing. */
- if (*string != '}')
- {
- if (!callout)
- fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
- (int)(string - begin), "missing closing brace");
- return FALSE;
- }
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: "
+ "too many %s digits\n", (int)(string - begin),
+ (base == 8)? "octal" : "hex");
}
else
{
- /* To negate the effect of the for. */
- string--;
- }
- }
- else if (brace)
- {
- /* Syntax error: a decimal number required. */
- if (!callout)
fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
- (int)(string - begin), "decimal number expected");
- return FALSE;
- }
- else if (*string == 'o')
- {
- string++;
-
- if (*string < '0' || *string > '7')
- {
- /* Syntax error: an octal number required. */
- if (!callout)
- fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
- (int)(string - begin), "octal number expected");
- return FALSE;
+ (int)(string - begin), "missing closing brace");
}
}
- else if (*string == 'x')
- {
- string++;
+ }
+ else string++;
+ }
- if (!isxdigit((unsigned char)*string))
- {
- /* Syntax error: a hexdecimal number required. */
- if (!callout)
- fprintf(stderr, "pcre2grep: Error in output text at offset %d: %s\n",
- (int)(string - begin), "hexadecimal number expected");
- return FALSE;
- }
- }
+/* Check maximum code point values, but take note of STDOUT_NL_CODE. */
+
+if (rc == DDE_CHAR && *value != STDOUT_NL_CODE)
+ {
+ uint32_t max = utf? 0x0010ffffu : 0xffu;
+ if (*value > max)
+ {
+ if (!callout)
+ fprintf(stderr, "pcre2grep: Error in output text at offset %d: "
+ "code point greater than 0x%x is invalid\n", (int)(string - begin), max);
+ rc = DDE_ERROR;
}
}
- return TRUE;
+*last = string;
+return rc;
}
+
/*************************************************
-* Display output text *
+* Check output text for errors *
*************************************************/
-/* Display the output text, which is assumed to have already been syntax
-checked. Output may contain escape sequences started by the dollar sign. The
-escape sequences are substituted as follows:
+/* Called early, to get errors before doing anything for -O text; also called
+from callouts to check before outputting.
- $<digits> or ${<digits>} is replaced by the captured substring of the given
- decimal number; zero will substitute the whole match. If the number is
- greater than the number of capturing substrings, or if the capture is unset,
- the replacement is empty.
+Arguments:
+ string an --output text string
+ callout TRUE if in a callout (stops printing errors)
- $a is replaced by bell.
- $b is replaced by backspace.
- $e is replaced by escape.
- $f is replaced by form feed.
- $n is replaced by newline.
- $r is replaced by carriage return.
- $t is replaced by tab.
- $v is replaced by vertical tab.
+Returns: TRUE if OK, FALSE on error
+*/
- $o<digits> is replaced by the character represented by the given octal
- number; up to three digits are processed.
+static BOOL
+syntax_check_output_text(PCRE2_SPTR string, BOOL callout)
+{
+uint32_t value;
+PCRE2_SPTR begin = string;
- $x<digits> is replaced by the character represented by the given hexadecimal
- number; up to two digits are processed.
+for (; *string != 0; string++)
+ {
+ if (*string == '$' &&
+ decode_dollar_escape(begin, string, callout, &value, &string) == DDE_ERROR)
+ return FALSE;
+ }
- Any other character is substituted by itself. E.g: $$ is replaced by a single
- dollar.
+return TRUE;
+}
+
+/*************************************************
+* Display output text *
+*************************************************/
+
+/* Display the output text, which is assumed to have already been syntax
+checked. Output may contain escape sequences started by the dollar sign.
+
Arguments:
string: the output text
callout: TRUE for the builtin callout, FALSE for --output
@@ -1973,121 +2136,54 @@
display_output_text(PCRE2_SPTR string, BOOL callout, PCRE2_SPTR subject,
PCRE2_SIZE *ovector, PCRE2_SIZE capture_top)
{
+uint32_t value;
BOOL printed = FALSE;
+PCRE2_SPTR begin = string;
for (; *string != 0; string++)
{
- int ch = EOF;
if (*string == '$')
{
- PCRE2_SIZE capture_id = 0;
- BOOL brace = FALSE;
-
- string++;
-
- if (*string == '{')
+ switch(decode_dollar_escape(begin, string, callout, &value, &string))
{
- /* Must be a decimal number in braces, e.g: {5} or {38} */
- string++;
-
- brace = TRUE;
- }
-
- if ((*string >= '1' && *string <= '9') || (!callout && *string == '0'))
- {
- do
+ case DDE_CHAR:
+ if (value == STDOUT_NL_CODE)
{
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
-
- string++;
+ fprintf(stdout, STDOUT_NL);
+ printed = FALSE;
+ continue;
}
- while (*string >= '0' && *string <= '9');
+ break; /* Will print value */
- if (!brace)
+ case DDE_CAPTURE:
+ if (value < capture_top)
{
- /* To negate the effect of the for. */
- string--;
- }
-
- if (capture_id < capture_top)
- {
PCRE2_SIZE capturesize;
- capture_id *= 2;
-
- capturesize = ovector[capture_id + 1] - ovector[capture_id];
+ value *= 2;
+ capturesize = ovector[value + 1] - ovector[value];
if (capturesize > 0)
{
- print_match(subject + ovector[capture_id], capturesize);
+ print_match(subject + ovector[value], capturesize);
printed = TRUE;
}
}
- }
- else if (*string == 'a') ch = '\a';
- else if (*string == 'b') ch = '\b';
-#ifndef EBCDIC
- else if (*string == 'e') ch = '\033';
-#else
- else if (*string == 'e') ch = '\047';
-#endif
- else if (*string == 'f') ch = '\f';
- else if (*string == 'r') ch = '\r';
- else if (*string == 't') ch = '\t';
- else if (*string == 'v') ch = '\v';
- else if (*string == 'n')
- {
- fprintf(stdout, STDOUT_NL);
- printed = FALSE;
- }
- else if (*string == 'o')
- {
- string++;
+ continue;
- ch = *string - '0';
- if (string[1] >= '0' && string[1] <= '7')
- {
- string++;
- ch = ch * 8 + (*string - '0');
- }
- if (string[1] >= '0' && string[1] <= '7')
- {
- string++;
- ch = ch * 8 + (*string - '0');
- }
+ default: /* Should not occur */
+ break;
}
- else if (*string == 'x')
- {
- string++;
+ }
- if (*string >= '0' && *string <= '9')
- ch = *string - '0';
- else
- ch = (*string | 0x20) - 'a' + 10;
- if (isxdigit((unsigned char)string[1]))
- {
- string++;
- ch *= 16;
- if (*string >= '0' && *string <= '9')
- ch += *string - '0';
- else
- ch += (*string | 0x20) - 'a' + 10;
- }
- }
- else
- {
- ch = *string;
- }
- }
- else
+ else value = *string; /* Not a $ escape */
+
+ if (utf && value <= 127) fprintf(stdout, "%c", *string); else
{
- ch = *string;
+ int i;
+ int n = ord2utf8(value);
+ for (i = 0; i < n; i++) fputc(utf8_buffer[i], stdout);
}
- if (ch != EOF)
- {
- fprintf(stdout, "%c", ch);
- printed = TRUE;
- }
+
+ printed = TRUE;
}
return printed;
@@ -2166,7 +2262,7 @@
(void)unused; /* Avoid compiler warning */
-/* Only callout with strings are supported. */
+/* Only callouts with strings are supported. */
if (string == NULL || length == 0) return 0;
@@ -2185,7 +2281,7 @@
#else
/* Checking syntax and compute the number of string fragments. Callout strings
-are ignored in case of a syntax error. */
+are silently ignored in the event of a syntax error. */
while (length > 0)
{
@@ -2192,76 +2288,36 @@
if (*string == '|')
{
argsvectorlen++;
+ if (argsvectorlen > 10000) return 0; /* Too many args */
+ }
- /* Maximum 10000 arguments allowed. */
- if (argsvectorlen > 10000) return 0;
- }
else if (*string == '$')
{
- PCRE2_SIZE capture_id = 0;
+ uint32_t value;
+ PCRE2_SPTR begin = string;
- string++;
- length--;
-
- /* Syntax error: a character must be present after $. */
- if (length == 0) return 0;
-
- if (*string >= '1' && *string <= '9')
+ switch (decode_dollar_escape(begin, string, TRUE, &value, &string))
{
- do
+ case DDE_CAPTURE:
+ if (value < capture_top)
{
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
-
- string++;
- length--;
+ value *= 2;
+ argslen += ovector[value + 1] - ovector[value];
}
- while (length > 0 && *string >= '0' && *string <= '9');
+ argslen--; /* Negate the effect of argslen++ below. */
+ break;
- /* To negate the effect of string++ below. */
- string--;
- length++;
- }
- else if (*string == '{')
- {
- /* Must be a decimal number in braces, e.g: {5} or {38} */
- string++;
- length--;
+ case DDE_CHAR:
+ if (value == STDOUT_NL_CODE) argslen += STDOUT_NL_LEN - 1;
+ else if (utf && value > 127) argslen += ord2utf8(value) - 1;
+ break;
- /* Syntax error: a decimal number required. */
- if (length == 0) return 0;
- if (*string < '1' || *string > '9') return 0;
-
- do
- {
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
-
- string++;
- length--;
-
- /* Syntax error: no more characters */
- if (length == 0) return 0;
- }
- while (*string >= '0' && *string <= '9');
-
- /* Syntax error: closing brace is missing. */
- if (*string != '}') return 0;
+ default: /* Should not occur */
+ case DDE_ERROR:
+ return 0;
}
- if (capture_id > 0)
- {
- if (capture_id < capture_top)
- {
- capture_id *= 2;
- argslen += ovector[capture_id + 1] - ovector[capture_id];
- }
-
- /* To negate the effect of argslen++ below. */
- argslen--;
- }
+ length -= (string - begin);
}
string++;
@@ -2269,6 +2325,8 @@
argslen++;
}
+/* Get memory for the argument vector and its strings. */
+
args = (char*)malloc(argslen);
if (args == NULL) return 0;
@@ -2279,9 +2337,10 @@
return 0;
}
+/* Now reprocess the string and set up the arguments. */
+
argsptr = args;
argsvectorptr = argsvector;
-
*argsvectorptr++ = argsptr;
length = calloutptr->callout_string_length;
@@ -2294,69 +2353,55 @@
*argsptr++ = '\0';
*argsvectorptr++ = argsptr;
}
+
else if (*string == '$')
{
- string++;
- length--;
+ uint32_t value;
+ PCRE2_SPTR begin = string;
- if ((*string >= '1' && *string <= '9') || *string == '{')
+ switch (decode_dollar_escape(begin, string, TRUE, &value, &string))
{
- PCRE2_SIZE capture_id = 0;
+ case DDE_CAPTURE:
+ if (value < capture_top)
+ {
+ PCRE2_SIZE capturesize;
+ value *= 2;
+ capturesize = ovector[value + 1] - ovector[value];
+ memcpy(argsptr, subject + ovector[value], capturesize);
+ argsptr += capturesize;
+ }
+ break;
- if (*string != '{')
+ case DDE_CHAR:
+ if (value == STDOUT_NL_CODE)
{
- do
- {
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
-
- string++;
- length--;
- }
- while (length > 0 && *string >= '0' && *string <= '9');
-
- /* To negate the effect of string++ below. */
- string--;
- length++;
+ memcpy(argsptr, STDOUT_NL, STDOUT_NL_LEN);
+ argsptr += STDOUT_NL_LEN;
+ }
+ else if (utf && value > 127)
+ {
+ int n = ord2utf8(value);
+ memcpy(argsptr, utf8_buffer, n);
+ argsptr += n;
}
else
{
- string++;
- length--;
-
- do
- {
- /* Maximum capture id is 65535. */
- if (capture_id <= 65535)
- capture_id = capture_id * 10 + (*string - '0');
-
- string++;
- length--;
- }
- while (*string != '}');
+ *argsptr++ = value;
}
+ break;
- if (capture_id < capture_top)
- {
- PCRE2_SIZE capturesize;
- capture_id *= 2;
+ default: /* Should not occur */
+ case DDE_ERROR:
+ return 0;
+ }
- capturesize = ovector[capture_id + 1] - ovector[capture_id];
- memcpy(argsptr, subject + ovector[capture_id], capturesize);
- argsptr += capturesize;
- }
- }
- else
- {
- *argsptr++ = *string;
- }
+ length -= (string - begin);
}
- else
- {
- *argsptr++ = *string;
- }
+ else *argsptr++ = *string;
+
+ /* Advance along the string */
+
string++;
length--;
}
@@ -2479,6 +2524,7 @@
unsigned long int linenumber = 1;
unsigned long int lastmatchnumber = 0;
unsigned long int count = 0;
+long int count_matched_lines = 0;
char *lastmatchrestart = main_buffer;
char *ptr = main_buffer;
char *endptr;
@@ -2505,7 +2551,7 @@
input_line_buffered);
#ifdef SUPPORT_LIBBZ2
-if (frtype == FR_LIBBZ2 && (int)bufflength < 0) return 2; /* Gotcha: bufflength is PCRE2_SIZE; */
+if (frtype == FR_LIBBZ2 && (int)bufflength < 0) return 2; /* Gotcha: bufflength is PCRE2_SIZE */
#endif
endptr = main_buffer + bufflength;
@@ -2533,10 +2579,23 @@
int mrc = 0;
unsigned int options = 0;
BOOL match;
+ BOOL line_matched = FALSE;
char *t = ptr;
PCRE2_SIZE length, linelength;
PCRE2_SIZE startoffset = 0;
+ /* If the -m option set a limit for the number of matched or non-matched
+ lines, check it here. A limit of zero means that no matching is ever done.
+ For stdin from a file, set the file position. */
+
+ if (count_limit >= 0 && count_matched_lines >= count_limit)
+ {
+ if (frtype == FR_PLAIN && filename == stdin_name && !is_file_tty(handle))
+ (void)fseek(handle, (long int)filepos, SEEK_SET);
+ rc = (count_limit == 0)? 1 : 0;
+ break;
+ }
+
/* At this point, ptr is at the start of a line. We need to find the length
of the subject string to pass to pcre2_match(). In multiline mode, it is the
length remainder of the data in the buffer. Otherwise, it is the length of
@@ -2686,6 +2745,10 @@
if (filenames == FN_NOMATCH_ONLY) return 1;
+ /* Remember that this line matched (for counting matched lines) */
+
+ line_matched = TRUE;
+
/* If all we want is a yes/no answer, we can return immediately. */
if (quiet) return 0;
@@ -3067,6 +3130,11 @@
filepos += (int)(linelength + endlinelength);
linenumber++;
+ /* If there was at least one match (or a non-match, as required) in the line,
+ increment the count for the -m option. */
+
+ if (line_matched) count_matched_lines++;
+
/* If input is line buffered, and the buffer is not yet full, read another
line and add it into the buffer. */
@@ -4088,6 +4156,7 @@
pcre2grep_exit(usage(2));
}
+
/* Check that there is a big enough ovector for all -o settings. */
for (om = only_matching; om != NULL; om = om->next)
Modified: code/trunk/testdata/grepoutput
===================================================================
(Binary files differ)
Modified: code/trunk/testdata/grepoutput8
===================================================================
(Binary files differ)
Modified: code/trunk/testdata/grepoutputC
===================================================================
--- code/trunk/testdata/grepoutputC 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/testdata/grepoutputC 2020-10-04 16:34:31 UTC (rev 1274)
@@ -40,3 +40,5 @@
T
T
T
+0:T:AA
+The quick brown
Modified: code/trunk/testdata/grepoutputCN
===================================================================
--- code/trunk/testdata/grepoutputCN 2020-09-19 03:49:32 UTC (rev 1273)
+++ code/trunk/testdata/grepoutputCN 2020-10-04 16:34:31 UTC (rev 1274)
@@ -28,3 +28,5 @@
T
T
T
+0:T:AA
+The quick brown
