Add serialization functions and tests with updated pcre2test. Fix

PCRE2_INFO_SIZE issues.
This commit is contained in:
Philip.Hazel 2015-01-23 16:51:47 +00:00
parent d4daaf966d
commit 5438fc8a6a
40 changed files with 3144 additions and 975 deletions

View File

@ -1,8 +1,8 @@
Change Log for PCRE2 Change Log for PCRE2
-------------------- --------------------
Version 10.10 13-January-2015 Version 10.10 xx-xxx-2015
----------------------------- -------------------------
1. When a pattern is compiled, it remembers the highest back reference so that 1. When a pattern is compiled, it remembers the highest back reference so that
when matching, if the ovector is too small, extra memory can be obtained to when matching, if the ovector is too small, extra memory can be obtained to
@ -16,6 +16,19 @@ bug was that the condition was always treated as FALSE when the capture could
not be consulted, leading to a incorrect behaviour by pcre2_match(). This bug not be consulted, leading to a incorrect behaviour by pcre2_match(). This bug
has been fixed. has been fixed.
2. Functions for serialization and deserialization of sets of compiled patterns
have been added.
3. The value that is returned by PCRE2_INFO_SIZE has been corrected to remove
excess code units at the end of the data block that may occasionally occur if
the code for calculating the size over-estimates. This change stops the
serialization code copying uninitialized data, to which valgrind objects. The
documentation of PCRE2_INFO_SIZE was incorrect in stating that the size did not
include the general overhead. This has been corrected.
4. All code units in every slot in the table of group names are now set, again
in order to avoid accessing uninitialized data when serializing.
Version 10.00 05-January-2015 Version 10.00 05-January-2015
----------------------------- -----------------------------
@ -30,8 +43,9 @@ logged. In addition to the API changes, the following changes were made. They
are either new functionality, or bug fixes and other noticeable changes of are either new functionality, or bug fixes and other noticeable changes of
behaviour that were implemented after the code had been forked. behaviour that were implemented after the code had been forked.
1. Unicode support is now enabled by default, but it can optionally be 1. Including Unicode support at build time is now enabled by default, but it
disabled. can optionally be disabled. It is not enabled by default at run time (no
change).
2. The test program, now called pcre2test, was re-specified and almost 2. The test program, now called pcre2test, was re-specified and almost
completely re-written. Its input is not compatible with input for pcretest. completely re-written. Its input is not compatible with input for pcretest.

View File

@ -54,6 +54,10 @@ dist_html_DATA = \
doc/html/pcre2_match_data_create_from_pattern.html \ doc/html/pcre2_match_data_create_from_pattern.html \
doc/html/pcre2_match_data_free.html \ doc/html/pcre2_match_data_free.html \
doc/html/pcre2_pattern_info.html \ doc/html/pcre2_pattern_info.html \
doc/html/pcre2_serialize_decode.html \
doc/html/pcre2_serialize_encode.html \
doc/html/pcre2_serialize_free.html \
doc/html/pcre2_serialize_get_number_of_codes.html \
doc/html/pcre2_set_bsr.html \ doc/html/pcre2_set_bsr.html \
doc/html/pcre2_set_callout.html \ doc/html/pcre2_set_callout.html \
doc/html/pcre2_set_character_tables.html \ doc/html/pcre2_set_character_tables.html \
@ -89,6 +93,7 @@ dist_html_DATA = \
doc/html/pcre2perform.html \ doc/html/pcre2perform.html \
doc/html/pcre2posix.html \ doc/html/pcre2posix.html \
doc/html/pcre2sample.html \ doc/html/pcre2sample.html \
doc/html/pcre2serialize.html \
doc/html/pcre2stack.html \ doc/html/pcre2stack.html \
doc/html/pcre2syntax.html \ doc/html/pcre2syntax.html \
doc/html/pcre2test.html \ doc/html/pcre2test.html \
@ -127,6 +132,10 @@ dist_man_MANS = \
doc/pcre2_match_data_create_from_pattern.3 \ doc/pcre2_match_data_create_from_pattern.3 \
doc/pcre2_match_data_free.3 \ doc/pcre2_match_data_free.3 \
doc/pcre2_pattern_info.3 \ doc/pcre2_pattern_info.3 \
doc/pcre2_serialize_decode.3 \
doc/pcre2_serialize_encode.3 \
doc/pcre2_serialize_free.3 \
doc/pcre2_serialize_get_number_of_codes.3 \
doc/pcre2_set_bsr.3 \ doc/pcre2_set_bsr.3 \
doc/pcre2_set_callout.3 \ doc/pcre2_set_callout.3 \
doc/pcre2_set_character_tables.3 \ doc/pcre2_set_character_tables.3 \
@ -162,6 +171,7 @@ dist_man_MANS = \
doc/pcre2perform.3 \ doc/pcre2perform.3 \
doc/pcre2posix.3 \ doc/pcre2posix.3 \
doc/pcre2sample.3 \ doc/pcre2sample.3 \
doc/pcre2serialize.3 \
doc/pcre2stack.3 \ doc/pcre2stack.3 \
doc/pcre2syntax.3 \ doc/pcre2syntax.3 \
doc/pcre2test.1 \ doc/pcre2test.1 \
@ -316,6 +326,7 @@ COMMON_SOURCES = \
src/pcre2_newline.c \ src/pcre2_newline.c \
src/pcre2_ord2utf.c \ src/pcre2_ord2utf.c \
src/pcre2_pattern_info.c \ src/pcre2_pattern_info.c \
src/pcre2_serialize.c \
src/pcre2_string_utils.c \ src/pcre2_string_utils.c \
src/pcre2_study.c \ src/pcre2_study.c \
src/pcre2_substitute.c \ src/pcre2_substitute.c \
@ -573,6 +584,7 @@ EXTRA_DIST += \
testdata/testinput16 \ testdata/testinput16 \
testdata/testinput17 \ testdata/testinput17 \
testdata/testinput18 \ testdata/testinput18 \
testdata/testinput19 \
testdata/testinputEBC \ testdata/testinputEBC \
testdata/testoutput1 \ testdata/testoutput1 \
testdata/testoutput2 \ testdata/testoutput2 \
@ -598,6 +610,7 @@ EXTRA_DIST += \
testdata/testoutput16 \ testdata/testoutput16 \
testdata/testoutput17 \ testdata/testoutput17 \
testdata/testoutput18 \ testdata/testoutput18 \
testdata/testoutput19 \
testdata/testoutputEBC \ testdata/testoutputEBC \
perltest.sh perltest.sh

View File

@ -108,6 +108,7 @@ can skip ahead to the CMake section.
pcre2_newline.c pcre2_newline.c
pcre2_ord2utf.c pcre2_ord2utf.c
pcre2_pattern_info.c pcre2_pattern_info.c
pcre2_serialize.c
pcre2_string_utils.c pcre2_string_utils.c
pcre2_study.c pcre2_study.c
pcre2_substitute.c pcre2_substitute.c
@ -391,4 +392,4 @@ The site currently has ports for PCRE1 releases, but PCRE2 should follow in due
course. course.
============================= =============================
Last Updated: 05 January 2015 Last Updated: 19 January 2015

101
README
View File

@ -527,11 +527,10 @@ Testing PCRE2
------------ ------------
To test the basic PCRE2 library on a Unix-like system, run the RunTest script. To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the options of the There is another script called RunGrepTest that tests the pcre2grep command.
pcre2grep command. When JIT support is enabled, a third test program called When JIT support is enabled, a third test program called pcre2_jit_test is
pcre2_jit_test is built. Both the scripts and all the program tests are run if built. Both the scripts and all the program tests are run if you obey "make
you obey "make check". For other environments, see the instructions in check". For other environments, see the instructions in NON-AUTOTOOLS-BUILD.
NON-AUTOTOOLS-BUILD.
The RunTest script runs the pcre2test test program (which is documented in its The RunTest script runs the pcre2test test program (which is documented in its
own man page) on each of the relevant testinput files in the testdata own man page) on each of the relevant testinput files in the testdata
@ -544,9 +543,9 @@ Some tests are relevant only when certain build-time options were selected. For
example, the tests for UTF-8/16/32 features are run only when Unicode support example, the tests for UTF-8/16/32 features are run only when Unicode support
is available. RunTest outputs a comment when it skips a test. is available. RunTest outputs a comment when it skips a test.
Many of the tests that are not skipped are run twice if JIT support is Many (but not all) of the tests that are not skipped are run twice if JIT
available. On the second run, JIT compilation is forced. This testing can be support is available. On the second run, JIT compilation is forced. This
suppressed by putting "nojit" on the RunTest command line. testing can be suppressed by putting "nojit" on the RunTest command line.
The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit
libraries that are enabled. If you want to run just one set of tests, call libraries that are enabled. If you want to run just one set of tests, call
@ -570,14 +569,20 @@ in numerical order.
You can also call RunTest with the single argument "list" to cause it to output You can also call RunTest with the single argument "list" to cause it to output
a list of tests. a list of tests.
The first two tests can always be run, as they expect only plain text strings The test sequence starts with "test 0", which is a special test that has no
(not UTF) and make no use of Unicode properties. The first test file can be fed input file, and whose output is not checked. This is because it will be
different on different hardware and with different configurations. The test
exists in order to exercise some of pcre2test's code that would not otherwise
be run.
Tests 1 and 2 can always be run, as they expect only plain text strings (not
UTF) and make no use of Unicode properties. The first test file can be fed
directly into the perltest.sh script to check that Perl gives the same results. directly into the perltest.sh script to check that Perl gives the same results.
The only difference you should see is in the first few lines, where the Perl The only difference you should see is in the first few lines, where the Perl
version is given instead of the PCRE2 version. The second set of tests check version is given instead of the PCRE2 version. The second set of tests check
auxiliary functions, error detection, and run-time flags that are specific to auxiliary functions, error detection, and run-time flags that are specific to
PCRE2, as well as the POSIX wrapper API. It also uses the debugging flags to PCRE2. It also uses the debugging flags to check some of the internals of
check some of the internals of pcre2_compile(). pcre2_compile().
If you build PCRE2 with a locale setting that is not the standard C locale, the If you build PCRE2 with a locale setting that is not the standard C locale, the
character tables may be different (see next paragraph). In some cases, this may character tables may be different (see next paragraph). In some cases, this may
@ -585,18 +590,17 @@ cause failures in the second set of tests. For example, in a locale where the
isprint() function yields TRUE for characters in the range 128-255, the use of isprint() function yields TRUE for characters in the range 128-255, the use of
[:isascii:] inside a character class defines a different set of characters, and [:isascii:] inside a character class defines a different set of characters, and
this shows up in this test as a difference in the compiled code, which is being this shows up in this test as a difference in the compiled code, which is being
listed for checking. Where the comparison test output contains [\x00-\x7f] the listed for checking. For example, where the comparison test output contains
test will contain [\x00-\xff], and similarly in some other cases. This is not a [\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other
bug in PCRE2. cases. This is not a bug in PCRE2.
The third set of tests checks pcre2_maketables(), the facility for building a Test 3 checks pcre2_maketables(), the facility for building a set of character
set of character tables for a specific locale and using them instead of the tables for a specific locale and using them instead of the default tables. The
default tables. The script uses the "locale" command to check for the script uses the "locale" command to check for the availability of the "fr_FR",
availability of the "fr_FR", "french", or "fr" locale, and uses the first one "french", or "fr" locale, and uses the first one that it finds. If the "locale"
that it finds. If the "locale" command fails, or if its output doesn't include command fails, or if its output doesn't include "fr_FR", "french", or "fr" in
"fr_FR", "french", or "fr" in the list of available locales, the third test the list of available locales, the third test cannot be run, and a comment is
cannot be run, and a comment is output to say why. If running this test output to say why. If running this test produces an error like this:
produces an error like this
** Failed to set locale "fr_FR" ** Failed to set locale "fr_FR"
@ -606,33 +610,37 @@ alternative output files for the third test, because three different versions
of the French locale have been encountered. The test passes if its output of the French locale have been encountered. The test passes if its output
matches any one of them. matches any one of them.
The fourth and fifth tests check UTF and Unicode property support, the fourth Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible
being compatible with the perltest.sh script, and the fifth checking with the perltest.sh script, and test 5 checking PCRE2-specific things.
PCRE2-specific things.
The sixth and seventh tests check the pcre2_dfa_match() alternative matching Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
function, in non-UTF mode and UTF-mode with Unicode property support, non-UTF mode and UTF-mode with Unicode property support, respectively.
respectively.
The eighth test checks some internal offsets and code size features; it is Test 8 checks some internal offsets and code size features; it is run only when
run only when the default "link size" of 2 is set (in other cases the sizes the default "link size" of 2 is set (in other cases the sizes change) and when
change) and when Unicode support is enabled. Unicode support is enabled.
The ninth and tenth tests are run only in 8-bit mode, and the eleventh and Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
twelfth tests are run only in 16-bit and 32-bit modes. These are tests that 16-bit and 32-bit modes. These are tests that generate different output in
generate different output in 8-bit mode. Each pair are for general cases and 8-bit mode. Each pair are for general cases and Unicode support, respectively.
Unicode support, respectively. The thirteenth test checks the handling of Test 13 checks the handling of non-UTF characters greater than 255 by
non-UTF characters greater than 255 by pcre2_dfa_match() in 16-bit and 32-bit pcre2_dfa_match() in 16-bit and 32-bit modes.
modes.
The fourteenth test is run only when JIT support is not available, and the Test 14 contains a number of tests that must not be run with JIT. They check,
fifteenth test is run only when JIT support is available. They test some among other non-JIT things, the match-limiting features of the intepretive
JIT-specific features such as information output from pcre2test about JIT matcher.
compilation.
The sixteenth and seventeenth tests are run only in 8-bit mode. They check the Test 15 is run only when JIT support is not available. It checks that an
POSIX interface to the 8-bit library, without and with Unicode support, attempt to use JIT has the expected behaviour.
respectively.
Test 16 is run only when JIT support is available. It checks JIT complete and
partial modes, match-limiting under JIT, and other JIT-specific features.
Tests 17 and 18 are run only in 8-bit mode. They check the POSIX interface to
the 8-bit library, without and with Unicode support, respectively.
Test 19 checks the serialization functions by writing a set of compiled
patterns to a file, and then reloading and checking them.
Character tables Character tables
@ -718,6 +726,7 @@ The distribution should contain the files listed below.
src/pcre2_newline.c ) src/pcre2_newline.c )
src/pcre2_ord2utf.c ) src/pcre2_ord2utf.c )
src/pcre2_pattern_info.c ) src/pcre2_pattern_info.c )
src/pcre2_serialize.c )
src/pcre2_string_utils.c ) src/pcre2_string_utils.c )
src/pcre2_study.c ) src/pcre2_study.c )
src/pcre2_substitute.c ) src/pcre2_substitute.c )
@ -816,4 +825,4 @@ The distribution should contain the files listed below.
Philip Hazel Philip Hazel
Email local part: ph10 Email local part: ph10
Email domain: cam.ac.uk Email domain: cam.ac.uk
Last updated: 05 January 2015 Last updated: 20 January 2015

17
RunTest
View File

@ -65,6 +65,7 @@ title15="Test 15: JIT-specific features when JIT is not available"
title16="Test 16: JIT-specific features when JIT is available" title16="Test 16: JIT-specific features when JIT is available"
title17="Test 17: Tests of the POSIX interface, excluding UTF/UCP" title17="Test 17: Tests of the POSIX interface, excluding UTF/UCP"
title18="Test 18: Tests of the POSIX interface with UTF/UCP" title18="Test 18: Tests of the POSIX interface with UTF/UCP"
title19="Test 19: Serialization tests"
maxtest=18 maxtest=18
if [ $# -eq 1 -a "$1" = "list" ]; then if [ $# -eq 1 -a "$1" = "list" ]; then
@ -87,6 +88,7 @@ if [ $# -eq 1 -a "$1" = "list" ]; then
echo $title16 echo $title16
echo $title17 echo $title17
echo $title18 echo $title18
echo $title19
exit 0 exit 0
fi fi
@ -207,6 +209,7 @@ do15=no
do16=no do16=no
do17=no do17=no
do18=no do18=no
do19=no
while [ $# -gt 0 ] ; do while [ $# -gt 0 ] ; do
case $1 in case $1 in
@ -229,6 +232,7 @@ while [ $# -gt 0 ] ; do
16) do16=yes;; 16) do16=yes;;
17) do17=yes;; 17) do17=yes;;
18) do18=yes;; 18) do18=yes;;
19) do19=yes;;
-8) arg8=yes;; -8) arg8=yes;;
-16) arg16=yes;; -16) arg16=yes;;
-32) arg32=yes;; -32) arg32=yes;;
@ -364,7 +368,7 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
$do4 = no -a $do5 = no -a $do6 = no -a $do7 = no -a \ $do4 = no -a $do5 = no -a $do6 = no -a $do7 = no -a \
$do8 = no -a $do9 = no -a $do10 = no -a $do11 = no -a \ $do8 = no -a $do9 = no -a $do10 = no -a $do11 = no -a \
$do12 = no -a $do13 = no -a $do14 = no -a $do15 = no -a \ $do12 = no -a $do13 = no -a $do14 = no -a $do15 = no -a \
$do16 = no -a $do17 = no -a $do18 = no \ $do16 = no -a $do17 = no -a $do18 = no -a $do19 = no \
]; then ]; then
do0=yes do0=yes
do1=yes do1=yes
@ -385,6 +389,7 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \
do16=yes do16=yes
do17=yes do17=yes
do18=yes do18=yes
do19=yes
fi fi
# Handle any explicit skips at this stage, so that an argument list may consist # Handle any explicit skips at this stage, so that an argument list may consist
@ -721,10 +726,18 @@ for bmode in "$test8" "$test16" "$test32"; do
fi fi
fi fi
# Serialization tests
if [ $do19 = yes ] ; then
echo $title19
$sim $valgrind ./pcre2test -q $bmode $testdata/testinput19 testtry
checkresult $? 19 ""
fi
# End of loop for 8/16/32-bit tests # End of loop for 8/16/32-bit tests
done done
# Clean up local working files # Clean up local working files
rm -f testSinput test3input test3output test3outputA test3outputB teststdout testtry rm -f testSinput test3input testsaved1 testsaved2 test3output test3outputA test3outputB teststdout testtry
# End # End

View File

@ -108,6 +108,7 @@ can skip ahead to the CMake section.
pcre2_newline.c pcre2_newline.c
pcre2_ord2utf.c pcre2_ord2utf.c
pcre2_pattern_info.c pcre2_pattern_info.c
pcre2_serialize.c
pcre2_string_utils.c pcre2_string_utils.c
pcre2_study.c pcre2_study.c
pcre2_substitute.c pcre2_substitute.c
@ -391,4 +392,4 @@ The site currently has ports for PCRE1 releases, but PCRE2 should follow in due
course. course.
============================= =============================
Last Updated: 05 January 2015 Last Updated: 19 January 2015

View File

@ -527,11 +527,10 @@ Testing PCRE2
------------ ------------
To test the basic PCRE2 library on a Unix-like system, run the RunTest script. To test the basic PCRE2 library on a Unix-like system, run the RunTest script.
There is another script called RunGrepTest that tests the options of the There is another script called RunGrepTest that tests the pcre2grep command.
pcre2grep command. When JIT support is enabled, a third test program called When JIT support is enabled, a third test program called pcre2_jit_test is
pcre2_jit_test is built. Both the scripts and all the program tests are run if built. Both the scripts and all the program tests are run if you obey "make
you obey "make check". For other environments, see the instructions in check". For other environments, see the instructions in NON-AUTOTOOLS-BUILD.
NON-AUTOTOOLS-BUILD.
The RunTest script runs the pcre2test test program (which is documented in its The RunTest script runs the pcre2test test program (which is documented in its
own man page) on each of the relevant testinput files in the testdata own man page) on each of the relevant testinput files in the testdata
@ -544,9 +543,9 @@ Some tests are relevant only when certain build-time options were selected. For
example, the tests for UTF-8/16/32 features are run only when Unicode support example, the tests for UTF-8/16/32 features are run only when Unicode support
is available. RunTest outputs a comment when it skips a test. is available. RunTest outputs a comment when it skips a test.
Many of the tests that are not skipped are run twice if JIT support is Many (but not all) of the tests that are not skipped are run twice if JIT
available. On the second run, JIT compilation is forced. This testing can be support is available. On the second run, JIT compilation is forced. This
suppressed by putting "nojit" on the RunTest command line. testing can be suppressed by putting "nojit" on the RunTest command line.
The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit
libraries that are enabled. If you want to run just one set of tests, call libraries that are enabled. If you want to run just one set of tests, call
@ -570,14 +569,20 @@ in numerical order.
You can also call RunTest with the single argument "list" to cause it to output You can also call RunTest with the single argument "list" to cause it to output
a list of tests. a list of tests.
The first two tests can always be run, as they expect only plain text strings The test sequence starts with "test 0", which is a special test that has no
(not UTF) and make no use of Unicode properties. The first test file can be fed input file, and whose output is not checked. This is because it will be
different on different hardware and with different configurations. The test
exists in order to exercise some of pcre2test's code that would not otherwise
be run.
Tests 1 and 2 can always be run, as they expect only plain text strings (not
UTF) and make no use of Unicode properties. The first test file can be fed
directly into the perltest.sh script to check that Perl gives the same results. directly into the perltest.sh script to check that Perl gives the same results.
The only difference you should see is in the first few lines, where the Perl The only difference you should see is in the first few lines, where the Perl
version is given instead of the PCRE2 version. The second set of tests check version is given instead of the PCRE2 version. The second set of tests check
auxiliary functions, error detection, and run-time flags that are specific to auxiliary functions, error detection, and run-time flags that are specific to
PCRE2, as well as the POSIX wrapper API. It also uses the debugging flags to PCRE2. It also uses the debugging flags to check some of the internals of
check some of the internals of pcre2_compile(). pcre2_compile().
If you build PCRE2 with a locale setting that is not the standard C locale, the If you build PCRE2 with a locale setting that is not the standard C locale, the
character tables may be different (see next paragraph). In some cases, this may character tables may be different (see next paragraph). In some cases, this may
@ -585,18 +590,17 @@ cause failures in the second set of tests. For example, in a locale where the
isprint() function yields TRUE for characters in the range 128-255, the use of isprint() function yields TRUE for characters in the range 128-255, the use of
[:isascii:] inside a character class defines a different set of characters, and [:isascii:] inside a character class defines a different set of characters, and
this shows up in this test as a difference in the compiled code, which is being this shows up in this test as a difference in the compiled code, which is being
listed for checking. Where the comparison test output contains [\x00-\x7f] the listed for checking. For example, where the comparison test output contains
test will contain [\x00-\xff], and similarly in some other cases. This is not a [\x00-\x7f] the test might contain [\x00-\xff], and similarly in some other
bug in PCRE2. cases. This is not a bug in PCRE2.
The third set of tests checks pcre2_maketables(), the facility for building a Test 3 checks pcre2_maketables(), the facility for building a set of character
set of character tables for a specific locale and using them instead of the tables for a specific locale and using them instead of the default tables. The
default tables. The script uses the "locale" command to check for the script uses the "locale" command to check for the availability of the "fr_FR",
availability of the "fr_FR", "french", or "fr" locale, and uses the first one "french", or "fr" locale, and uses the first one that it finds. If the "locale"
that it finds. If the "locale" command fails, or if its output doesn't include command fails, or if its output doesn't include "fr_FR", "french", or "fr" in
"fr_FR", "french", or "fr" in the list of available locales, the third test the list of available locales, the third test cannot be run, and a comment is
cannot be run, and a comment is output to say why. If running this test output to say why. If running this test produces an error like this:
produces an error like this
** Failed to set locale "fr_FR" ** Failed to set locale "fr_FR"
@ -606,33 +610,37 @@ alternative output files for the third test, because three different versions
of the French locale have been encountered. The test passes if its output of the French locale have been encountered. The test passes if its output
matches any one of them. matches any one of them.
The fourth and fifth tests check UTF and Unicode property support, the fourth Tests 4 and 5 check UTF and Unicode property support, test 4 being compatible
being compatible with the perltest.sh script, and the fifth checking with the perltest.sh script, and test 5 checking PCRE2-specific things.
PCRE2-specific things.
The sixth and seventh tests check the pcre2_dfa_match() alternative matching Tests 6 and 7 check the pcre2_dfa_match() alternative matching function, in
function, in non-UTF mode and UTF-mode with Unicode property support, non-UTF mode and UTF-mode with Unicode property support, respectively.
respectively.
The eighth test checks some internal offsets and code size features; it is Test 8 checks some internal offsets and code size features; it is run only when
run only when the default "link size" of 2 is set (in other cases the sizes the default "link size" of 2 is set (in other cases the sizes change) and when
change) and when Unicode support is enabled. Unicode support is enabled.
The ninth and tenth tests are run only in 8-bit mode, and the eleventh and Tests 9 and 10 are run only in 8-bit mode, and tests 11 and 12 are run only in
twelfth tests are run only in 16-bit and 32-bit modes. These are tests that 16-bit and 32-bit modes. These are tests that generate different output in
generate different output in 8-bit mode. Each pair are for general cases and 8-bit mode. Each pair are for general cases and Unicode support, respectively.
Unicode support, respectively. The thirteenth test checks the handling of Test 13 checks the handling of non-UTF characters greater than 255 by
non-UTF characters greater than 255 by pcre2_dfa_match() in 16-bit and 32-bit pcre2_dfa_match() in 16-bit and 32-bit modes.
modes.
The fourteenth test is run only when JIT support is not available, and the Test 14 contains a number of tests that must not be run with JIT. They check,
fifteenth test is run only when JIT support is available. They test some among other non-JIT things, the match-limiting features of the intepretive
JIT-specific features such as information output from pcre2test about JIT matcher.
compilation.
The sixteenth and seventeenth tests are run only in 8-bit mode. They check the Test 15 is run only when JIT support is not available. It checks that an
POSIX interface to the 8-bit library, without and with Unicode support, attempt to use JIT has the expected behaviour.
respectively.
Test 16 is run only when JIT support is available. It checks JIT complete and
partial modes, match-limiting under JIT, and other JIT-specific features.
Tests 17 and 18 are run only in 8-bit mode. They check the POSIX interface to
the 8-bit library, without and with Unicode support, respectively.
Test 19 checks the serialization functions by writing a set of compiled
patterns to a file, and then reloading and checking them.
Character tables Character tables
@ -718,6 +726,7 @@ The distribution should contain the files listed below.
src/pcre2_newline.c ) src/pcre2_newline.c )
src/pcre2_ord2utf.c ) src/pcre2_ord2utf.c )
src/pcre2_pattern_info.c ) src/pcre2_pattern_info.c )
src/pcre2_serialize.c )
src/pcre2_string_utils.c ) src/pcre2_string_utils.c )
src/pcre2_study.c ) src/pcre2_study.c )
src/pcre2_substitute.c ) src/pcre2_substitute.c )
@ -816,4 +825,4 @@ The distribution should contain the files listed below.
Philip Hazel Philip Hazel
Email local part: ph10 Email local part: ph10
Email domain: cam.ac.uk Email domain: cam.ac.uk
Last updated: 05 January 2015 Last updated: 20 January 2015

View File

@ -65,6 +65,9 @@ first.
<tr><td><a href="pcre2sample.html">pcre2sample</a></td> <tr><td><a href="pcre2sample.html">pcre2sample</a></td>
<td>&nbsp;&nbsp;Discussion of the pcre2demo program</td></tr> <td>&nbsp;&nbsp;Discussion of the pcre2demo program</td></tr>
<tr><td><a href="pcre2serialize.html">pcre2serialize</a></td>
<td>&nbsp;&nbsp;Serializing functions for saving precompiled patterns</td></tr>
<tr><td><a href="pcre2stack.html">pcre2stack</a></td> <tr><td><a href="pcre2stack.html">pcre2stack</a></td>
<td>&nbsp;&nbsp;Discussion of PCRE2's stack usage</td></tr> <td>&nbsp;&nbsp;Discussion of PCRE2's stack usage</td></tr>
@ -177,6 +180,18 @@ in the library.
<tr><td><a href="pcre2_pattern_info.html">pcre2_pattern_info</a></td> <tr><td><a href="pcre2_pattern_info.html">pcre2_pattern_info</a></td>
<td>&nbsp;&nbsp;Extract information about a pattern</td></tr> <td>&nbsp;&nbsp;Extract information about a pattern</td></tr>
<tr><td><a href="pcre2_serialize_decode.html">pcre2_serialize_decode</a></td>
<td>&nbsp;&nbsp;Decode serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_serialize_encode.html">pcre2_serialize_encode</a></td>
<td>&nbsp;&nbsp;Serialize compiled patterns for save/restore</td></tr>
<tr><td><a href="pcre2_serialize_free.html">pcre2_serialize_free</a></td>
<td>&nbsp;&nbsp;Free serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_serialize_get_number_of_codes.html">pcre2_serialize_get_number_of_codes</a></td>
<td>&nbsp;&nbsp;Get number of serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_set_bsr.html">pcre2_set_bsr</a></td> <tr><td><a href="pcre2_set_bsr.html">pcre2_set_bsr</a></td>
<td>&nbsp;&nbsp;Set \R convention</td></tr> <td>&nbsp;&nbsp;Set \R convention</td></tr>

View File

@ -0,0 +1,62 @@
<html>
<head>
<title>pcre2_serialize_decode specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2_serialize_decode man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<br><b>
SYNOPSIS
</b><br>
<P>
<b>#include &#60;pcre2.h&#62;</b>
</P>
<P>
<b>int32_t pcre2_serialize_decode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, const uint32_t *<i>bytes</i>,</b>
<b> pcre2_general_context *<i>gcontext</i>);</b>
</P>
<br><b>
DESCRIPTION
</b><br>
<P>
This function decodes a serialized set of compiled patterns back into a list of
individual patterns. Its arguments are:
<pre>
<i>codes</i> pointer to a vector in which to build the list
<i>number_of_codes</i> number of slots in the vector
<i>bytes</i> the serialized byte stream
<i>gcontext</i> pointer to a general context or NULL
</pre>
The <i>bytes</i> argument must point to a block of data that was originally
created by <b>pcre2_serialize_encode()</b>, though it may have been saved on
disc or elsewhere in the meantime. If there are more codes in the serialized
data than slots in the list, only those compiled patterns that will fit are
decoded. The yield of the function is the number of decoded patterns, or one of
the following negative error codes:
<pre>
PCRE2_ERROR_BADDATA <i>number_of_codes</i> is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in <i>bytes</i>
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE version
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_NULL <i>codes</i> or <i>bytes</i> is NULL
</pre>
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
</P>
<P>
There is a complete description of the PCRE2 native API in the
<a href="pcre2api.html"><b>pcre2api</b></a>
page and a description of the POSIX API in the
<a href="pcre2posix.html"><b>pcre2posix</b></a>
page.
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>

View File

@ -0,0 +1,61 @@
<html>
<head>
<title>pcre2_serialize_encode specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2_serialize_encode man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<br><b>
SYNOPSIS
</b><br>
<P>
<b>#include &#60;pcre2.h&#62;</b>
</P>
<P>
<b>int32_t pcre2_serialize_encode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, uint32_t **<i>serialized_bytes</i>,</b>
<b> PCRE2_SIZE *<i>serialized_size</i>, pcre2_general_context *<i>gcontext</i>);</b>
</P>
<br><b>
DESCRIPTION
</b><br>
<P>
This function encodes a list of compiled patterns into a byte stream that can
be saved on disc or elsewhere. Its arguments are:
<pre>
<i>codes</i> pointer to a vector containing the list
<i>number_of_codes</i> number of slots in the vector
<i>serialized_bytes</i> set to point to the serialized byte stream
<i>serialized_size</i> set to the number of bytes in the byte stream
<i>gcontext</i> pointer to a general context or NULL
</pre>
The context argument is used to obtain memory for the byte stream. When the
serialized data is no longer needed, it must be freed by calling
<b>pcre2_serialize_free()</b>. The yield of the function is the number of
serialized patterns, or one of the following negative error codes:
<pre>
PCRE2_ERROR_BADDATA <i>number_of_codes</i> is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in one of the patterns
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_MIXEDTABLES the patterns do not all use the same tables
PCRE2_ERROR_NULL an argument other than <i>gcontext</i> is NULL
</pre>
PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
that a slot in the vector does not point to a compiled pattern.
</P>
<P>
There is a complete description of the PCRE2 native API in the
<a href="pcre2api.html"><b>pcre2api</b></a>
page and a description of the POSIX API in the
<a href="pcre2posix.html"><b>pcre2posix</b></a>
page.
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>

View File

@ -0,0 +1,40 @@
<html>
<head>
<title>pcre2_serialize_free specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2_serialize_free man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<br><b>
SYNOPSIS
</b><br>
<P>
<b>#include &#60;pcre2.h&#62;</b>
</P>
<P>
<b>void pcre2_serialize_free(uint8_t *<i>bytes</i>);</b>
</P>
<br><b>
DESCRIPTION
</b><br>
<P>
This function frees the memory that was obtained by
<b>pcre2_serialize_encode()</b> to hold a serialized byte stream. The argument
must point to such a byte stream.
</P>
<P>
There is a complete description of the PCRE2 native API in the
<a href="pcre2api.html"><b>pcre2api</b></a>
page and a description of the POSIX API in the
<a href="pcre2posix.html"><b>pcre2posix</b></a>
page.
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>

View File

@ -0,0 +1,49 @@
<html>
<head>
<title>pcre2_serialize_get_number_of_codes specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2_serialize_get_number_of_codes man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<br><b>
SYNOPSIS
</b><br>
<P>
<b>#include &#60;pcre2.h&#62;</b>
</P>
<P>
<b>int32_t pcre2_serialize_get_number_of_codes(const uint8_t *<i>bytes</i>);</b>
</P>
<br><b>
DESCRIPTION
</b><br>
<P>
The <i>bytes</i> argument must point to a serialized byte stream that was
originally created by <b>pcre2_serialize_encode()</b> (though it may have been
saved on disc or elsewhere in the meantime). The function returns the number of
serialized patterns in the byte stream, or one of the following negative error
codes:
<pre>
PCRE2_ERROR_BADMAGIC mismatch of id bytes in <i>bytes</i>
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE version
PCRE2_ERROR_NULL the argument is NULL
</pre>
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
</P>
<P>
There is a complete description of the PCRE2 native API in the
<a href="pcre2api.html"><b>pcre2api</b></a>
page and a description of the POSIX API in the
<a href="pcre2posix.html"><b>pcre2posix</b></a>
page.
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>

View File

@ -21,35 +21,37 @@ please consult the man page, in case the conversion went wrong.
<li><a name="TOC6" href="#SEC6">PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS</a> <li><a name="TOC6" href="#SEC6">PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS</a>
<li><a name="TOC7" href="#SEC7">PCRE2 NATIVE API STRING SUBSTITUTION FUNCTION</a> <li><a name="TOC7" href="#SEC7">PCRE2 NATIVE API STRING SUBSTITUTION FUNCTION</a>
<li><a name="TOC8" href="#SEC8">PCRE2 NATIVE API JIT FUNCTIONS</a> <li><a name="TOC8" href="#SEC8">PCRE2 NATIVE API JIT FUNCTIONS</a>
<li><a name="TOC9" href="#SEC9">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a> <li><a name="TOC9" href="#SEC9">PCRE2 NATIVE API SERIALIZATION FUNCTIONS</a>
<li><a name="TOC10" href="#SEC10">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a> <li><a name="TOC10" href="#SEC10">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a>
<li><a name="TOC11" href="#SEC11">PCRE2 API OVERVIEW</a> <li><a name="TOC11" href="#SEC11">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a>
<li><a name="TOC12" href="#SEC12">STRING LENGTHS AND OFFSETS</a> <li><a name="TOC12" href="#SEC12">PCRE2 API OVERVIEW</a>
<li><a name="TOC13" href="#SEC13">NEWLINES</a> <li><a name="TOC13" href="#SEC13">STRING LENGTHS AND OFFSETS</a>
<li><a name="TOC14" href="#SEC14">MULTITHREADING</a> <li><a name="TOC14" href="#SEC14">NEWLINES</a>
<li><a name="TOC15" href="#SEC15">PCRE2 CONTEXTS</a> <li><a name="TOC15" href="#SEC15">MULTITHREADING</a>
<li><a name="TOC16" href="#SEC16">CHECKING BUILD-TIME OPTIONS</a> <li><a name="TOC16" href="#SEC16">PCRE2 CONTEXTS</a>
<li><a name="TOC17" href="#SEC17">COMPILING A PATTERN</a> <li><a name="TOC17" href="#SEC17">CHECKING BUILD-TIME OPTIONS</a>
<li><a name="TOC18" href="#SEC18">COMPILATION ERROR CODES</a> <li><a name="TOC18" href="#SEC18">COMPILING A PATTERN</a>
<li><a name="TOC19" href="#SEC19">JUST-IN-TIME (JIT) COMPILATION</a> <li><a name="TOC19" href="#SEC19">COMPILATION ERROR CODES</a>
<li><a name="TOC20" href="#SEC20">LOCALE SUPPORT</a> <li><a name="TOC20" href="#SEC20">JUST-IN-TIME (JIT) COMPILATION</a>
<li><a name="TOC21" href="#SEC21">INFORMATION ABOUT A COMPILED PATTERN</a> <li><a name="TOC21" href="#SEC21">LOCALE SUPPORT</a>
<li><a name="TOC22" href="#SEC22">THE MATCH DATA BLOCK</a> <li><a name="TOC22" href="#SEC22">INFORMATION ABOUT A COMPILED PATTERN</a>
<li><a name="TOC23" href="#SEC23">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a> <li><a name="TOC23" href="#SEC23">SERIALIZATION AND PRECOMPILING</a>
<li><a name="TOC24" href="#SEC24">NEWLINE HANDLING WHEN MATCHING</a> <li><a name="TOC24" href="#SEC24">THE MATCH DATA BLOCK</a>
<li><a name="TOC25" href="#SEC25">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a> <li><a name="TOC25" href="#SEC25">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a>
<li><a name="TOC26" href="#SEC26">OTHER INFORMATION ABOUT A MATCH</a> <li><a name="TOC26" href="#SEC26">NEWLINE HANDLING WHEN MATCHING</a>
<li><a name="TOC27" href="#SEC27">ERROR RETURNS FROM <b>pcre2_match()</b></a> <li><a name="TOC27" href="#SEC27">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a>
<li><a name="TOC28" href="#SEC28">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a> <li><a name="TOC28" href="#SEC28">OTHER INFORMATION ABOUT A MATCH</a>
<li><a name="TOC29" href="#SEC29">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a> <li><a name="TOC29" href="#SEC29">ERROR RETURNS FROM <b>pcre2_match()</b></a>
<li><a name="TOC30" href="#SEC30">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a> <li><a name="TOC30" href="#SEC30">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a>
<li><a name="TOC31" href="#SEC31">CREATING A NEW STRING WITH SUBSTITUTIONS</a> <li><a name="TOC31" href="#SEC31">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a>
<li><a name="TOC32" href="#SEC32">DUPLICATE SUBPATTERN NAMES</a> <li><a name="TOC32" href="#SEC32">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
<li><a name="TOC33" href="#SEC33">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a> <li><a name="TOC33" href="#SEC33">CREATING A NEW STRING WITH SUBSTITUTIONS</a>
<li><a name="TOC34" href="#SEC34">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a> <li><a name="TOC34" href="#SEC34">DUPLICATE SUBPATTERN NAMES</a>
<li><a name="TOC35" href="#SEC35">SEE ALSO</a> <li><a name="TOC35" href="#SEC35">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a>
<li><a name="TOC36" href="#SEC36">AUTHOR</a> <li><a name="TOC36" href="#SEC36">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
<li><a name="TOC37" href="#SEC37">REVISION</a> <li><a name="TOC37" href="#SEC37">SEE ALSO</a>
<li><a name="TOC38" href="#SEC38">AUTHOR</a>
<li><a name="TOC39" href="#SEC39">REVISION</a>
</ul> </ul>
<P> <P>
<b>#include &#60;pcre2.h&#62;</b> <b>#include &#60;pcre2.h&#62;</b>
@ -260,7 +262,24 @@ document for an overview of all the PCRE2 documentation.
<br> <br>
<b>void pcre2_jit_stack_free(pcre2_jit_stack *<i>jit_stack</i>);</b> <b>void pcre2_jit_stack_free(pcre2_jit_stack *<i>jit_stack</i>);</b>
</P> </P>
<br><a name="SEC9" href="#TOC1">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a><br> <br><a name="SEC9" href="#TOC1">PCRE2 NATIVE API SERIALIZATION FUNCTIONS</a><br>
<P>
<b>int32_t pcre2_serialize_decode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, const uint32_t *<i>bytes</i>,</b>
<b> pcre2_general_context *<i>gcontext</i>);</b>
<br>
<br>
<b>int32_t pcre2_serialize_encode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, uint32_t **<i>serialized_bytes</i>,</b>
<b> PCRE2_SIZE *<i>serialized_size</i>, pcre2_general_context *<i>gcontext</i>);</b>
<br>
<br>
<b>void pcre2_serialize_free(uint8_t *<i>bytes</i>);</b>
<br>
<br>
<b>int32_t pcre2_serialize_get_number_of_codes(const uint8_t *<i>bytes</i>);</b>
</P>
<br><a name="SEC10" href="#TOC1">PCRE2 NATIVE API AUXILIARY FUNCTIONS</a><br>
<P> <P>
<b>int pcre2_get_error_message(int <i>errorcode</i>, PCRE2_UCHAR *<i>buffer</i>,</b> <b>int pcre2_get_error_message(int <i>errorcode</i>, PCRE2_UCHAR *<i>buffer</i>,</b>
<b> PCRE2_SIZE <i>bufflen</i>);</b> <b> PCRE2_SIZE <i>bufflen</i>);</b>
@ -274,7 +293,7 @@ document for an overview of all the PCRE2 documentation.
<br> <br>
<b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b> <b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b>
</P> </P>
<br><a name="SEC10" href="#TOC1">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br> <br><a name="SEC11" href="#TOC1">PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
<P> <P>
There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code
units, respectively. However, there is just one header file, <b>pcre2.h</b>. units, respectively. However, there is just one header file, <b>pcre2.h</b>.
@ -335,7 +354,7 @@ In the function summaries above, and in the rest of this document and other
PCRE2 documents, functions and data types are described using their generic PCRE2 documents, functions and data types are described using their generic
names, without the 8, 16, or 32 suffix. names, without the 8, 16, or 32 suffix.
</P> </P>
<br><a name="SEC11" href="#TOC1">PCRE2 API OVERVIEW</a><br> <br><a name="SEC12" href="#TOC1">PCRE2 API OVERVIEW</a><br>
<P> <P>
PCRE2 has its own native API, which is described in this document. There are PCRE2 has its own native API, which is described in this document. There are
also some wrapper functions for the 8-bit library that correspond to the also some wrapper functions for the 8-bit library that correspond to the
@ -426,7 +445,7 @@ Finally, there are functions for finding out information about a compiled
pattern (<b>pcre2_pattern_info()</b>) and about the configuration with which pattern (<b>pcre2_pattern_info()</b>) and about the configuration with which
PCRE2 was built (<b>pcre2_config()</b>). PCRE2 was built (<b>pcre2_config()</b>).
</P> </P>
<br><a name="SEC12" href="#TOC1">STRING LENGTHS AND OFFSETS</a><br> <br><a name="SEC13" href="#TOC1">STRING LENGTHS AND OFFSETS</a><br>
<P> <P>
The PCRE2 API uses string lengths and offsets into strings of code units in The PCRE2 API uses string lengths and offsets into strings of code units in
several places. These values are always of type PCRE2_SIZE, which is an several places. These values are always of type PCRE2_SIZE, which is an
@ -436,7 +455,7 @@ as a special indicator for zero-terminated strings and unset offsets.
Therefore, the longest string that can be handled is one less than this Therefore, the longest string that can be handled is one less than this
maximum. maximum.
<a name="newlines"></a></P> <a name="newlines"></a></P>
<br><a name="SEC13" href="#TOC1">NEWLINES</a><br> <br><a name="SEC14" href="#TOC1">NEWLINES</a><br>
<P> <P>
PCRE2 supports five different conventions for indicating line breaks in PCRE2 supports five different conventions for indicating line breaks in
strings: a single CR (carriage return) character, a single LF (linefeed) strings: a single CR (carriage return) character, a single LF (linefeed)
@ -471,7 +490,7 @@ The choice of newline convention does not affect the interpretation of
the \n or \r escape sequences, nor does it affect what \R matches; this has the \n or \r escape sequences, nor does it affect what \R matches; this has
its own separate convention. its own separate convention.
</P> </P>
<br><a name="SEC14" href="#TOC1">MULTITHREADING</a><br> <br><a name="SEC15" href="#TOC1">MULTITHREADING</a><br>
<P> <P>
In a multithreaded application it is important to keep thread-specific data In a multithreaded application it is important to keep thread-specific data
separate from data that can be shared between threads. The PCRE2 library code separate from data that can be shared between threads. The PCRE2 library code
@ -516,7 +535,7 @@ storing the results of a match. This includes details of what was matched, as
well as additional information such as the name of a (*MARK) setting. Each well as additional information such as the name of a (*MARK) setting. Each
thread must provide its own version of this memory. thread must provide its own version of this memory.
</P> </P>
<br><a name="SEC15" href="#TOC1">PCRE2 CONTEXTS</a><br> <br><a name="SEC16" href="#TOC1">PCRE2 CONTEXTS</a><br>
<P> <P>
Some PCRE2 functions have a lot of parameters, many of which are used only by Some PCRE2 functions have a lot of parameters, many of which are used only by
specialist applications, for example, those that use custom memory management specialist applications, for example, those that use custom memory management
@ -797,7 +816,7 @@ exit so that they can be re-used when possible during the match. In the absence
of these functions, the normal custom memory management functions are used, if of these functions, the normal custom memory management functions are used, if
supplied, otherwise the system functions. supplied, otherwise the system functions.
</P> </P>
<br><a name="SEC16" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br> <br><a name="SEC17" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br>
<P> <P>
<b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b> <b>int pcre2_config(uint32_t <i>what</i>, void *<i>where</i>);</b>
</P> </P>
@ -929,7 +948,7 @@ the PCRE2 version string, zero-terminated. The number of code units used is
returned. This is the length of the string plus one unit for the terminating returned. This is the length of the string plus one unit for the terminating
zero. zero.
<a name="compiling"></a></P> <a name="compiling"></a></P>
<br><a name="SEC17" href="#TOC1">COMPILING A PATTERN</a><br> <br><a name="SEC18" href="#TOC1">COMPILING A PATTERN</a><br>
<P> <P>
<b>pcre2_code *pcre2_compile(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b> <b>pcre2_code *pcre2_compile(PCRE2_SPTR <i>pattern</i>, PCRE2_SIZE <i>length</i>,</b>
<b> uint32_t <i>options</i>, int *<i>errorcode</i>, PCRE2_SIZE *<i>erroroffset,</i></b> <b> uint32_t <i>options</i>, int *<i>errorcode</i>, PCRE2_SIZE *<i>erroroffset,</i></b>
@ -1305,7 +1324,7 @@ the behaviour of PCRE2 are given in the
<a href="pcre2unicode.html"><b>pcre2unicode</b></a> <a href="pcre2unicode.html"><b>pcre2unicode</b></a>
page. page.
</P> </P>
<br><a name="SEC18" href="#TOC1">COMPILATION ERROR CODES</a><br> <br><a name="SEC19" href="#TOC1">COMPILATION ERROR CODES</a><br>
<P> <P>
There are over 80 positive error codes that <b>pcre2_compile()</b> may return if There are over 80 positive error codes that <b>pcre2_compile()</b> may return if
it finds an error in the pattern. There are also some negative error codes that it finds an error in the pattern. There are also some negative error codes that
@ -1315,7 +1334,7 @@ are used for invalid UTF strings. These are the same as given by
page. The <b>pcre2_get_error_message()</b> function can be called to obtain a page. The <b>pcre2_get_error_message()</b> function can be called to obtain a
textual error message from any error code. textual error message from any error code.
</P> </P>
<br><a name="SEC19" href="#TOC1">JUST-IN-TIME (JIT) COMPILATION</a><br> <br><a name="SEC20" href="#TOC1">JUST-IN-TIME (JIT) COMPILATION</a><br>
<P> <P>
<b>int pcre2_jit_compile(pcre2_code *<i>code</i>, uint32_t <i>options</i>);</b> <b>int pcre2_jit_compile(pcre2_code *<i>code</i>, uint32_t <i>options</i>);</b>
<br> <br>
@ -1353,7 +1372,7 @@ patterns to be analyzed, and for one-off matches and simple patterns the
benefit of faster execution might be offset by a much slower compilation time. benefit of faster execution might be offset by a much slower compilation time.
Most, but not all patterns can be optimized by the JIT compiler. Most, but not all patterns can be optimized by the JIT compiler.
<a name="localesupport"></a></P> <a name="localesupport"></a></P>
<br><a name="SEC20" href="#TOC1">LOCALE SUPPORT</a><br> <br><a name="SEC21" href="#TOC1">LOCALE SUPPORT</a><br>
<P> <P>
PCRE2 handles caseless matching, and determines whether characters are letters, PCRE2 handles caseless matching, and determines whether characters are letters,
digits, or whatever, by reference to a set of tables, indexed by character code digits, or whatever, by reference to a set of tables, indexed by character code
@ -1409,7 +1428,7 @@ is saved with the compiled pattern, and the same tables are used by
compilation, and matching all happen in the same locale, but different patterns compilation, and matching all happen in the same locale, but different patterns
can be processed in different locales. can be processed in different locales.
<a name="infoaboutpattern"></a></P> <a name="infoaboutpattern"></a></P>
<br><a name="SEC21" href="#TOC1">INFORMATION ABOUT A COMPILED PATTERN</a><br> <br><a name="SEC22" href="#TOC1">INFORMATION ABOUT A COMPILED PATTERN</a><br>
<P> <P>
<b>int pcre2_pattern_info(const pcre2 *<i>code</i>, uint32_t <i>what</i>, void *<i>where</i>);</b> <b>int pcre2_pattern_info(const pcre2 *<i>code</i>, uint32_t <i>what</i>, void *<i>where</i>);</b>
</P> </P>
@ -1478,8 +1497,12 @@ options returned for PCRE2_INFO_ALLOPTIONS.
PCRE2_INFO_BACKREFMAX PCRE2_INFO_BACKREFMAX
</pre> </pre>
Return the number of the highest back reference in the pattern. The third Return the number of the highest back reference in the pattern. The third
argument should point to an <b>uint32_t</b> variable. Zero is returned if there argument should point to an <b>uint32_t</b> variable. Named subpatterns acquire
are no back references. numbers as well as names, and these count towards the highest back reference.
Back references such as \4 or \g{12} match the captured characters of the
given group, but in addition, the check that a capturing group is set in a
conditional subpattern such as (?(3)a|b) is also a back reference. Zero is
returned if there are no back references.
<pre> <pre>
PCRE2_INFO_BSR PCRE2_INFO_BSR
</pre> </pre>
@ -1689,14 +1712,24 @@ set, the call to <b>pcre2_pattern_info()</b> returns the error PCRE2_ERROR_UNSET
PCRE2_INFO_SIZE PCRE2_INFO_SIZE
</pre> </pre>
Return the size of the compiled pattern in bytes (for all three libraries). The Return the size of the compiled pattern in bytes (for all three libraries). The
third argument should point to a <b>size_t</b> variable. This value does not third argument should point to a <b>size_t</b> variable. This value includes the
include the size of the <b>pcre2_code</b> structure that is returned by size of the general data block that precedes the code units of the compiled
<b>pcre_compile()</b>. The value that is used when <b>pcre2_compile()</b> is pattern itself. The value that is used when <b>pcre2_compile()</b> is getting
getting memory in which to place the compiled data is the value returned by memory in which to place the compiled pattern may be slightly larger than the
this option plus the size of the <b>pcre2_code</b> structure. Processing a value returned by this option, because there are cases where the code that
pattern with the JIT compiler does not alter the value returned by this option. calculates the size has to over-estimate. Processing a pattern with the JIT
compiler does not alter the value returned by this option.
</P>
<br><a name="SEC23" href="#TOC1">SERIALIZATION AND PRECOMPILING</a><br>
<P>
It is possible to save compiled patterns on disc or elsewhere, and reload them
later, subject to a number of restrictions. The functions whose names begin
with <b>pcre2_serialize_</b> are used for this purpose. They are described in
the
<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
documentation.
<a name="matchdatablock"></a></P> <a name="matchdatablock"></a></P>
<br><a name="SEC22" href="#TOC1">THE MATCH DATA BLOCK</a><br> <br><a name="SEC24" href="#TOC1">THE MATCH DATA BLOCK</a><br>
<P> <P>
<b>pcre2_match_data_create(uint32_t <i>ovecsize</i>,</b> <b>pcre2_match_data_create(uint32_t <i>ovecsize</i>,</b>
<b> pcre2_general_context *<i>gcontext</i>);</b> <b> pcre2_general_context *<i>gcontext</i>);</b>
@ -1767,7 +1800,7 @@ match data block (for that match) have taken place.
When a match data block itself is no longer needed, it should be freed by When a match data block itself is no longer needed, it should be freed by
calling <b>pcre2_match_data_free()</b>. calling <b>pcre2_match_data_free()</b>.
</P> </P>
<br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br> <br><a name="SEC25" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
<P> <P>
<b>int pcre2_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b> <b>int pcre2_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b> <b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
@ -1981,7 +2014,7 @@ examples, in the
<a href="pcre2partial.html"><b>pcre2partial</b></a> <a href="pcre2partial.html"><b>pcre2partial</b></a>
documentation. documentation.
</P> </P>
<br><a name="SEC24" href="#TOC1">NEWLINE HANDLING WHEN MATCHING</a><br> <br><a name="SEC26" href="#TOC1">NEWLINE HANDLING WHEN MATCHING</a><br>
<P> <P>
When PCRE2 is built, a default newline convention is set; this is usually the When PCRE2 is built, a default newline convention is set; this is usually the
standard convention for the operating system. The default can be overridden in standard convention for the operating system. The default can be overridden in
@ -2016,7 +2049,7 @@ LF in the characters that it matches.
Notwithstanding the above, anomalous effects may still occur when CRLF is a Notwithstanding the above, anomalous effects may still occur when CRLF is a
valid newline sequence and explicit \r or \n escapes appear in the pattern. valid newline sequence and explicit \r or \n escapes appear in the pattern.
<a name="matchedstrings"></a></P> <a name="matchedstrings"></a></P>
<br><a name="SEC25" href="#TOC1">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a><br> <br><a name="SEC27" href="#TOC1">HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS</a><br>
<P> <P>
<b>uint32_t pcre2_get_ovector_count(pcre2_match_data *<i>match_data</i>);</b> <b>uint32_t pcre2_get_ovector_count(pcre2_match_data *<i>match_data</i>);</b>
<br> <br>
@ -2118,7 +2151,7 @@ parentheses, no more than <i>ovector[0]</i> to <i>ovector[2n+1]</i> are set by
<b>pcre2_match()</b>. The other elements retain whatever values they previously <b>pcre2_match()</b>. The other elements retain whatever values they previously
had. had.
<a name="matchotherdata"></a></P> <a name="matchotherdata"></a></P>
<br><a name="SEC26" href="#TOC1">OTHER INFORMATION ABOUT A MATCH</a><br> <br><a name="SEC28" href="#TOC1">OTHER INFORMATION ABOUT A MATCH</a><br>
<P> <P>
<b>PCRE2_SPTR pcre2_get_mark(pcre2_match_data *<i>match_data</i>);</b> <b>PCRE2_SPTR pcre2_get_mark(pcre2_match_data *<i>match_data</i>);</b>
<br> <br>
@ -2162,7 +2195,7 @@ the code unit offset of the invalid UTF character. Details are given in the
<a href="pcre2unicode.html"><b>pcre2unicode</b></a> <a href="pcre2unicode.html"><b>pcre2unicode</b></a>
page. page.
<a name="errorlist"></a></P> <a name="errorlist"></a></P>
<br><a name="SEC27" href="#TOC1">ERROR RETURNS FROM <b>pcre2_match()</b></a><br> <br><a name="SEC29" href="#TOC1">ERROR RETURNS FROM <b>pcre2_match()</b></a><br>
<P> <P>
If <b>pcre2_match()</b> fails, it returns a negative number. This can be If <b>pcre2_match()</b> fails, it returns a negative number. This can be
converted to a text string by calling <b>pcre2_get_error_message()</b>. Negative converted to a text string by calling <b>pcre2_get_error_message()</b>. Negative
@ -2271,7 +2304,7 @@ is attempted.
</pre> </pre>
The internal recursion limit was reached. The internal recursion limit was reached.
<a name="extractbynumber"></a></P> <a name="extractbynumber"></a></P>
<br><a name="SEC28" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br> <br><a name="SEC30" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
<P> <P>
<b>int pcre2_substring_length_bynumber(pcre2_match_data *<i>match_data</i>,</b> <b>int pcre2_substring_length_bynumber(pcre2_match_data *<i>match_data</i>,</b>
<b> uint32_t <i>number</i>, PCRE2_SIZE *<i>length</i>);</b> <b> uint32_t <i>number</i>, PCRE2_SIZE *<i>length</i>);</b>
@ -2368,7 +2401,7 @@ The substring did not participate in the match. For example, if the pattern is
(abc)|(def) and the subject is "def", and the ovector contains at least two (abc)|(def) and the subject is "def", and the ovector contains at least two
capturing slots, substring number 1 is unset. capturing slots, substring number 1 is unset.
</P> </P>
<br><a name="SEC29" href="#TOC1">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a><br> <br><a name="SEC31" href="#TOC1">EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS</a><br>
<P> <P>
<b>int pcre2_substring_list_get(pcre2_match_data *<i>match_data</i>,</b> <b>int pcre2_substring_list_get(pcre2_match_data *<i>match_data</i>,</b>
<b>" PCRE2_UCHAR ***<i>listptr</i>, PCRE2_SIZE **<i>lengthsptr</i>);</b> <b>" PCRE2_UCHAR ***<i>listptr</i>, PCRE2_SIZE **<i>lengthsptr</i>);</b>
@ -2407,7 +2440,7 @@ can be distinguished from a genuine zero-length substring by inspecting the
appropriate offset in the ovector, which contain PCRE2_UNSET for unset appropriate offset in the ovector, which contain PCRE2_UNSET for unset
substrings, or by calling <b>pcre2_substring_length_bynumber()</b>. substrings, or by calling <b>pcre2_substring_length_bynumber()</b>.
<a name="extractbyname"></a></P> <a name="extractbyname"></a></P>
<br><a name="SEC30" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br> <br><a name="SEC32" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
<P> <P>
<b>int pcre2_substring_number_from_name(const pcre2_code *<i>code</i>,</b> <b>int pcre2_substring_number_from_name(const pcre2_code *<i>code</i>,</b>
<b> PCRE2_SPTR <i>name</i>);</b> <b> PCRE2_SPTR <i>name</i>);</b>
@ -2467,7 +2500,7 @@ names are not included in the compiled code. The matching process uses only
numbers. For this reason, the use of different names for subpatterns of the numbers. For this reason, the use of different names for subpatterns of the
same number causes an error at compile time. same number causes an error at compile time.
</P> </P>
<br><a name="SEC31" href="#TOC1">CREATING A NEW STRING WITH SUBSTITUTIONS</a><br> <br><a name="SEC33" href="#TOC1">CREATING A NEW STRING WITH SUBSTITUTIONS</a><br>
<P> <P>
<b>int pcre2_substitute(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b> <b>int pcre2_substitute(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b> <b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
@ -2528,7 +2561,7 @@ straight back. PCRE2_ERROR_BADREPLACEMENT is returned for an invalid
replacement string (unrecognized sequence following a dollar sign), and replacement string (unrecognized sequence following a dollar sign), and
PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough.
</P> </P>
<br><a name="SEC32" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br> <br><a name="SEC34" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
<P> <P>
<b>int pcre2_substring_nametable_scan(const pcre2_code *<i>code</i>,</b> <b>int pcre2_substring_nametable_scan(const pcre2_code *<i>code</i>,</b>
<b> PCRE2_SPTR <i>name</i>, PCRE2_SPTR *<i>first</i>, PCRE2_SPTR *<i>last</i>);</b> <b> PCRE2_SPTR <i>name</i>, PCRE2_SPTR *<i>first</i>, PCRE2_SPTR *<i>last</i>);</b>
@ -2573,7 +2606,7 @@ The format of the name table is described above in the section entitled
Given all the relevant entries for the name, you can extract each of their Given all the relevant entries for the name, you can extract each of their
numbers, and hence the captured data. numbers, and hence the captured data.
</P> </P>
<br><a name="SEC33" href="#TOC1">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a><br> <br><a name="SEC35" href="#TOC1">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a><br>
<P> <P>
The traditional matching function uses a similar algorithm to Perl, which stops The traditional matching function uses a similar algorithm to Perl, which stops
when it finds the first match at a given point in the subject. If you want to when it finds the first match at a given point in the subject. If you want to
@ -2591,7 +2624,7 @@ substring. Then return 1, which forces <b>pcre2_match()</b> to backtrack and try
other alternatives. Ultimately, when it runs out of matches, other alternatives. Ultimately, when it runs out of matches,
<b>pcre2_match()</b> will yield PCRE2_ERROR_NOMATCH. <b>pcre2_match()</b> will yield PCRE2_ERROR_NOMATCH.
<a name="dfamatch"></a></P> <a name="dfamatch"></a></P>
<br><a name="SEC34" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br> <br><a name="SEC36" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
<P> <P>
<b>int pcre2_dfa_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b> <b>int pcre2_dfa_match(const pcre2_code *<i>code</i>, PCRE2_SPTR <i>subject</i>,</b>
<b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b> <b> PCRE2_SIZE <i>length</i>, PCRE2_SIZE <i>startoffset</i>,</b>
@ -2786,13 +2819,13 @@ some plausibility checks are made on the contents of the workspace, which
should contain data about the previous partial match. If any of these checks should contain data about the previous partial match. If any of these checks
fail, this error is given. fail, this error is given.
</P> </P>
<br><a name="SEC35" href="#TOC1">SEE ALSO</a><br> <br><a name="SEC37" href="#TOC1">SEE ALSO</a><br>
<P> <P>
<b>pcre2build</b>(3), <b>pcre2callout</b>(3), <b>pcre2demo(3)</b>, <b>pcre2build</b>(3), <b>pcre2callout</b>(3), <b>pcre2demo(3)</b>,
<b>pcre2matching</b>(3), <b>pcre2partial</b>(3), <b>pcre2posix</b>(3), <b>pcre2matching</b>(3), <b>pcre2partial</b>(3), <b>pcre2posix</b>(3),
<b>pcre2sample</b>(3), <b>pcre2stack</b>(3), <b>pcre2unicode</b>(3). <b>pcre2sample</b>(3), <b>pcre2stack</b>(3), <b>pcre2unicode</b>(3).
</P> </P>
<br><a name="SEC36" href="#TOC1">AUTHOR</a><br> <br><a name="SEC38" href="#TOC1">AUTHOR</a><br>
<P> <P>
Philip Hazel Philip Hazel
<br> <br>
@ -2801,9 +2834,9 @@ University Computing Service
Cambridge, England. Cambridge, England.
<br> <br>
</P> </P>
<br><a name="SEC37" href="#TOC1">REVISION</a><br> <br><a name="SEC39" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 02 January 2015 Last updated: 23 January 2015
<br> <br>
Copyright &copy; 1997-2015 University of Cambridge. Copyright &copy; 1997-2015 University of Cambridge.
<br> <br>

View File

@ -0,0 +1,184 @@
<html>
<head>
<title>pcre2serialize specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2serialize man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<ul>
<li><a name="TOC1" href="#SEC1">SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS</a>
<li><a name="TOC2" href="#SEC2">SAVING COMPILED PATTERNS</a>
<li><a name="TOC3" href="#SEC3">RE-USING PRECOMPILED PATTERNS</a>
<li><a name="TOC4" href="#SEC4">AUTHOR</a>
<li><a name="TOC5" href="#SEC5">REVISION</a>
</ul>
<br><a name="SEC1" href="#TOC1">SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS</a><br>
<P>
<b>int32_t pcre2_serialize_decode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, const uint32_t *<i>bytes</i>,</b>
<b> pcre2_general_context *<i>gcontext</i>);</b>
<br>
<br>
<b>int32_t pcre2_serialize_encode(pcre2_code **<i>codes</i>,</b>
<b> int32_t <i>number_of_codes</i>, uint32_t **<i>serialized_bytes</i>,</b>
<b> PCRE2_SIZE *<i>serialized_size</i>, pcre2_general_context *<i>gcontext</i>);</b>
<br>
<br>
<b>void pcre2_serialize_free(uint8_t *<i>bytes</i>);</b>
<br>
<br>
<b>int32_t pcre2_serialize_get_number_of_codes(const uint8_t *<i>bytes</i>);</b>
<br>
<br>
If you are running an application that uses a large number of regular
expression patterns, it may be useful to store them in a precompiled form
instead of having to compile them every time the application is run. However,
if you are using the just-in-time optimization feature, it is not possible to
save and reload the JIT data, because it is position-dependent. In addition,
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. For example, patterns compiled on a 32-bit
system using PCRE2's 16-bit library cannot be reloaded on a 64-bit system, nor
can they be reloaded using the 8-bit library.
</P>
<br><a name="SEC2" href="#TOC1">SAVING COMPILED PATTERNS</a><br>
<P>
Before compiled patterns can be saved they must be serialized, that is,
converted to a stream of bytes. A single byte stream may contain any number of
compiled patterns, but they must all use the same character tables. A single
copy of the tables is included in the byte stream (its size is 1088 bytes). For
more details of character tables, see the
<a href="pcre2api.html#localesupport">section on locale support</a>
in the
<a href="pcre2api.html"><b>pcre2api</b></a>
documentation.
</P>
<P>
The function <b>pcre2_serialize_encode()</b> creates a serialized byte stream
from a list of compiled patterns. Its first two arguments specify the list,
being a pointer to a vector of pointers to compiled patterns, and the length of
the vector. The third and fourth arguments point to variables which are set to
point to the created byte stream and its length, respectively. The final
argument is a pointer to a general context, which can be used to specify custom
memory mangagement functions. If this argument is NULL, <b>malloc()</b> is used
to obtain memory for the byte stream. The yield of the function is the number
of serialized patterns, or one of the following negative error codes:
<pre>
PCRE2_ERROR_BADDATA the number of patterns is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in one of the patterns
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_MIXEDTABLES the patterns do not all use the same tables
PCRE2_ERROR_NULL the 1st, 3rd, or 4th argument is NULL
</pre>
PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
that a slot in the vector does not point to a compiled pattern.
</P>
<P>
Once a set of patterns has been serialized you can save the data in any
appropriate manner. Here is sample code that compiles two patterns and writes
them to a file. It assumes that the variable <i>fd</i> refers to a file that is
open for output. The error checking that should be present in a real
application has been omitted for simplicity.
<pre>
int errorcode;
uint8_t *bytes;
PCRE2_SIZE erroroffset;
PCRE2_SIZE bytescount;
pcre2_code *list_of_codes[2];
list_of_codes[0] = pcre2_compile("first pattern",
PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
list_of_codes[1] = pcre2_compile("second pattern",
PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
errorcode = pcre2_serialize_encode(list_of_codes, 2, &bytes,
&bytescount, NULL);
errorcode = fwrite(bytes, 1, bytescount, fd);
</pre>
Note that the serialized data is binary data that may contain any of the 256
possible byte values. On systems that make a distinction between binary and
non-binary data, be sure that the file is opened for binary output.
</P>
<P>
Serializing a set of patterns leaves the original data untouched, so they can
still be used for matching. Their memory must eventually be freed in the usual
way by calling <b>pcre2_code_free()</b>. When you have finished with the byte
stream, it too must be freed by calling <b>pcre2_serialize_free()</b>.
</P>
<br><a name="SEC3" href="#TOC1">RE-USING PRECOMPILED PATTERNS</a><br>
<P>
In order to re-use a set of saved patterns you must first make the serialized
byte stream available in main memory (for example, by reading from a file). The
management of this memory block is up to the application. You can use the
<b>pcre2_serialize_get_number_of_codes()</b> function to find out how many
compiled patterns are in the serialized data without actually decoding the
patterns:
<pre>
uint8_t *bytes = &#60;serialized data&#62;;
int32_t number_of_codes = pcre2_serialize_get_number_of_codes(bytes);
</pre>
The <b>pcre2_serialize_decode()</b> function reads a byte stream and recreates
the compiled patterns in new memory blocks, setting pointers to them in a
vector. The first two arguments are a pointer to a suitable vector and its
length, and the third argument points to a byte stream. The final argument is a
pointer to a general context, which can be used to specify custom memory
mangagement functions for the decoded patterns. If this argument is NULL,
<b>malloc()</b> and <b>free()</b> are used. After deserialization, the byte
stream is no longer needed and can be discarded.
<pre>
int32_t number_of_codes;
pcre2_code *list_of_codes[2];
uint8_t *bytes = &#60;serialized data&#62;;
int32_t number_of_codes =
pcre2_serialize_decode(list_of_codes, 2, bytes, NULL);
</pre>
If the vector is not large enough for all the patterns in the byte stream, it
is filled with those that fit, and the remainder are ignored. The yield of the
function is the number of decoded patterns, or one of the following negative
error codes:
<pre>
PCRE2_ERROR_BADDATA second argument is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in the data
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE2 version
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_NULL first or third argument is NULL
</pre>
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
</P>
<P>
Decoded patterns can be used for matching in the usual way, and must be freed
by calling <b>pcre2_code_free()</b> as normal. A single copy of the character
tables is used by all the decoded patterns. A reference count is used to
arrange for its memory to be automatically freed when the last pattern is
freed.
</P>
<P>
If a pattern was processed by <b>pcre2_jit_compile()</b> before being
serialized, the JIT data is discarded and so is no longer available after a
save/restore cycle. You can, however, process a restored pattern with
<b>pcre2_jit_compile()</b> if you wish.
</P>
<br><a name="SEC4" href="#TOC1">AUTHOR</a><br>
<P>
Philip Hazel
<br>
University Computing Service
<br>
Cambridge, England.
<br>
</P>
<br><a name="SEC5" href="#TOC1">REVISION</a><br>
<P>
Last updated: 20 January 2015
<br>
Copyright &copy; 1997-2015 University of Cambridge.
<br>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>

View File

@ -30,9 +30,10 @@ please consult the man page, in case the conversion went wrong.
<li><a name="TOC15" href="#SEC15">RESTARTING AFTER A PARTIAL MATCH</a> <li><a name="TOC15" href="#SEC15">RESTARTING AFTER A PARTIAL MATCH</a>
<li><a name="TOC16" href="#SEC16">CALLOUTS</a> <li><a name="TOC16" href="#SEC16">CALLOUTS</a>
<li><a name="TOC17" href="#SEC17">NON-PRINTING CHARACTERS</a> <li><a name="TOC17" href="#SEC17">NON-PRINTING CHARACTERS</a>
<li><a name="TOC18" href="#SEC18">SEE ALSO</a> <li><a name="TOC18" href="#SEC18">SAVING AND RESTORING COMPILED PATTERNS</a>
<li><a name="TOC19" href="#SEC19">AUTHOR</a> <li><a name="TOC19" href="#SEC19">SEE ALSO</a>
<li><a name="TOC20" href="#SEC20">REVISION</a> <li><a name="TOC20" href="#SEC20">AUTHOR</a>
<li><a name="TOC21" href="#SEC21">REVISION</a>
</ul> </ul>
<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> <br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br>
<P> <P>
@ -51,10 +52,11 @@ documentation.
</P> </P>
<P> <P>
The input for <b>pcre2test</b> is a sequence of regular expression patterns and The input for <b>pcre2test</b> is a sequence of regular expression patterns and
subject strings to be matched. The output shows the result of each match subject strings to be matched. There are also command lines for setting
attempt. Modifiers on the command line, the patterns, and the subject lines defaults and controlling some special actions. The output shows the result of
specify PCRE2 function options, control how the subject is processed, and what each match attempt. Modifiers on external or internal command lines, the
output is produced. patterns, and the subject lines specify PCRE2 function options, control how the
subject is processed, and what output is produced.
</P> </P>
<P> <P>
As the original fairly simple PCRE library evolved, it acquired many different As the original fairly simple PCRE library evolved, it acquired many different
@ -227,9 +229,7 @@ If <b>pcre2test</b> is given two filename arguments, it reads from the first and
writes to the second. If the first name is "-", input is taken from the writes to the second. If the first name is "-", input is taken from the
standard input. If <b>pcre2test</b> is given only one argument, it reads from standard input. If <b>pcre2test</b> is given only one argument, it reads from
that file and writes to stdout. Otherwise, it reads from stdin and writes to that file and writes to stdout. Otherwise, it reads from stdin and writes to
stdout. When the input is a terminal, it prompts for each line of input, using stdout.
"re&#62;" to prompt for regular expression patterns, and "data&#62;" to prompt for
subject lines.
</P> </P>
<P> <P>
When <b>pcre2test</b> is built, a configuration option can specify that it When <b>pcre2test</b> is built, a configuration option can specify that it
@ -242,10 +242,16 @@ the <b>-help</b> option states whether or not <b>readline()</b> will be used.
The program handles any number of tests, each of which consists of a set of The program handles any number of tests, each of which consists of a set of
input lines. Each set starts with a regular expression pattern, followed by any input lines. Each set starts with a regular expression pattern, followed by any
number of subject lines to be matched against that pattern. In between sets of number of subject lines to be matched against that pattern. In between sets of
test data, command lines that begin with a hash (#) character may appear. This test data, command lines that begin with # may appear. This file format, with
file format, with some restrictions, can also be processed by the some restrictions, can also be processed by the <b>perltest.sh</b> script that
<b>perltest.sh</b> script that is distributed with PCRE2 as a means of checking is distributed with PCRE2 as a means of checking that the behaviour of PCRE2
that the behaviour of PCRE2 and Perl is the same. and Perl is the same.
</P>
<P>
When the input is a terminal, <b>pcre2test</b> prompts for each line of input,
using "re&#62;" to prompt for regular expression patterns, and "data&#62;" to prompt
for subject lines. Command lines starting with # can be entered only in
response to the "re&#62;" prompt.
</P> </P>
<P> <P>
Each subject line is matched separately and independently. If you want to do Each subject line is matched separately and independently. If you want to do
@ -263,21 +269,27 @@ still input to be read.
</P> </P>
<br><a name="SEC6" href="#TOC1">COMMAND LINES</a><br> <br><a name="SEC6" href="#TOC1">COMMAND LINES</a><br>
<P> <P>
In between sets of test data, a line that begins with a hash (#) character is In between sets of test data, a line that begins with # is interpreted as a
interpreted as a command line. If the first character is followed by white command line. If the first character is followed by white space or an
space or an exclamation mark, the line is treated as a comment, and ignored. exclamation mark, the line is treated as a comment, and ignored. Otherwise, the
Otherwise, the following commands are recognized: following commands are recognized:
<pre> <pre>
#forbid_utf #forbid_utf
</pre> </pre>
Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP
options set, which locks out the use of UTF and Unicode property features. This options set, which locks out the use of UTF and Unicode property features. This
is a trigger guard that is used in test files to ensure that UTF/Unicode tests is a trigger guard that is used in test files to ensure that UTF or Unicode
are not accidentally added to files that are used when UTF support is not property tests are not accidentally added to files that are used when Unicode
included in the library. This effect can also be obtained by the use of support is not included in the library. This effect can also be obtained by the
<b>#pattern</b>; the difference is that <b>#forbid_utf</b> cannot be unset, and use of <b>#pattern</b>; the difference is that <b>#forbid_utf</b> cannot be
the automatic options are not displayed in pattern information, to avoid unset, and the automatic options are not displayed in pattern information, to
cluttering up test output. avoid cluttering up test output.
<pre>
#load &#60;filename&#62;
</pre>
This command is used to load a set of precompiled patterns from a file, as
described in the section entitled "Saving and restoring compiled patterns"
<a href="#saverestore">below.</a>
<pre> <pre>
#pattern &#60;modifier-list&#62; #pattern &#60;modifier-list&#62;
</pre> </pre>
@ -293,6 +305,18 @@ lines, none of the other command lines are permitted, because they and many
of the modifiers are specific to <b>pcre2test</b>, and should not be used in 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> 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. command helps detect tests that are accidentally put in the wrong file.
<pre>
#pop [&#60;modifiers&#62;]
</pre>
This command is used to manipulate the stack of compiled patterns, as described
in the section entitled "Saving and restoring compiled patterns"
<a href="#saverestore">below.</a>
<pre>
#save &#60;filename&#62;
</pre>
This command is used to save a set of compiled patterns to a file, as described
in the section entitled "Saving and restoring compiled patterns"
<a href="#saverestore">below.</a>
<pre> <pre>
#subject &#60;modifier-list&#62; #subject &#60;modifier-list&#62;
</pre> </pre>
@ -428,7 +452,7 @@ There are three types of modifier that can appear in pattern lines, two of
which may also be used in a <b>#pattern</b> command. A pattern's modifier list which may also be used in a <b>#pattern</b> command. A pattern's modifier list
can add to or override default modifiers that were set by a previous can add to or override default modifiers that were set by a previous
<b>#pattern</b> command. <b>#pattern</b> command.
</P> <a name="optionmodifiers"></a></P>
<br><b> <br><b>
Setting compilation options Setting compilation options
</b><br> </b><br>
@ -465,7 +489,7 @@ As well as turning on the PCRE2_UTF option, the <b>utf</b> modifier causes all
non-printing characters in output strings to be printed using the \x{hh...} 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 notation. Otherwise, those less than 0x100 are output in hex without the curly
brackets. brackets.
</P> <a name="controlmodifiers"></a></P>
<br><b> <br><b>
Setting compilation controls Setting compilation controls
</b><br> </b><br>
@ -486,8 +510,8 @@ about the pattern:
memory show memory used memory show memory used
newline=&#60;type&#62; set newline type newline=&#60;type&#62; set newline type
parens_nest_limit=&#60;n&#62; set maximum parentheses depth parens_nest_limit=&#60;n&#62; set maximum parentheses depth
perlcompat lock out non-Perl modifiers
posix use the POSIX API posix use the POSIX API
push push compiled pattern onto the stack
stackguard=&#60;number&#62; test the stackguard feature stackguard=&#60;number&#62; test the stackguard feature
tables=[0|1|2] select internal tables tables=[0|1|2] select internal tables
</pre> </pre>
@ -726,6 +750,22 @@ not affect the compilation process.
These modifiers may not appear in a <b>#pattern</b> command. If you want them as These modifiers may not appear in a <b>#pattern</b> command. If you want them as
defaults, set them in a <b>#subject</b> command. defaults, set them in a <b>#subject</b> command.
</P> </P>
<br><b>
Saving a compiled pattern
</b><br>
<P>
When a pattern with the <b>push</b> modifier is successfully compiled, it is
pushed onto a stack of compiled patterns, and <b>pcre2test</b> 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 patterns"
<a href="#saverestore">below.</a>
The <b>push</b> modifier is incompatible with compilation modifiers such as
<b>global</b> that act at match time. Any that are specified are ignored, with a
warning message, except for <b>replace</b>, which causes an error. Note that,
<b>jitverify</b>, which is allowed, does not carry through to any subsequent
matching that uses this pattern.
</P>
<br><a name="SEC11" href="#TOC1">SUBJECT MODIFIERS</a><br> <br><a name="SEC11" href="#TOC1">SUBJECT MODIFIERS</a><br>
<P> <P>
The modifiers that can appear in subject lines and the <b>#subject</b> The modifiers that can appear in subject lines and the <b>#subject</b>
@ -1292,14 +1332,75 @@ string, it behaves in the same way, unless a different locale has been set for
the pattern (using the <b>/locale</b> modifier). In this case, the the pattern (using the <b>/locale</b> modifier). In this case, the
<b>isprint()</b> function is used to distinguish printing and non-printing <b>isprint()</b> function is used to distinguish printing and non-printing
characters. characters.
<a name="saverestore"></a></P>
<br><a name="SEC18" href="#TOC1">SAVING AND RESTORING COMPILED PATTERNS</a><br>
<P>
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 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, converted to a stream of bytes. A single byte stream may
contain any number of compiled patterns, but they must all use the same
character tables. A single copy of the tables is included in the byte stream
(its size is 1088 bytes).
</P> </P>
<br><a name="SEC18" href="#TOC1">SEE ALSO</a><br> <P>
The functions whose names begin with <b>pcre2_serialize_</b> are used
for serializing and de-serializing. They are described in the
<a href="pcre2serialize.html"><b>pcre2serialize</b></a>
documentation. In this section we describe the features of <b>pcre2test</b> that
can be used to test these functions.
</P>
<P>
When a pattern with <b>push</b> modifier is successfully compiled, it is pushed
onto a stack of compiled patterns, and <b>pcre2test</b> expects the next line to
contain a new pattern (or command) instead of a subject line. By this means, a
number of patterns can be compiled and retained. The <b>push</b> modifier is
incompatible with <b>posix</b>, and control modifiers that act at match time are
ignored (with a message). The <b>jitverify</b> modifier applies only at compile
time. The command
<pre>
#save &#60;filename&#62;
</pre>
causes all the stacked patterns to be serialized and the result written to the
named file. Afterwards, all the stacked patterns are freed. The command
<pre>
#load &#60;filename&#62;
</pre>
reads the data in the file, and then arranges for it to be de-serialized, with
the resulting compiled patterns added to the pattern stack. The pattern on the
top of the stack can be retrieved by the #pop command, 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
<a href="#controlmodifiers">control modifiers</a>
that act after a pattern has been compiled. In particular, <b>hex</b>,
<b>posix</b>, and <b>push</b> are not allowed, nor are any
<a href="#optionmodifiers">option-setting modifiers.</a>
The JIT modifiers are, however permitted. Here is an example that saves and
reloads two patterns.
<pre>
/abc/push
/xyz/push
#save tempfile
#load tempfile
#pop info
xyz
#pop jit,bincode
abc
</pre>
If <b>jitverify</b> is used with #pop, it does not automatically imply
<b>jit</b>, which is different behaviour from when it is used on a pattern.
</P>
<br><a name="SEC19" href="#TOC1">SEE ALSO</a><br>
<P> <P>
<b>pcre2</b>(3), <b>pcre2api</b>(3), <b>pcre2callout</b>(3), <b>pcre2</b>(3), <b>pcre2api</b>(3), <b>pcre2callout</b>(3),
<b>pcre2jit</b>, <b>pcre2matching</b>(3), <b>pcre2partial</b>(d), <b>pcre2jit</b>, <b>pcre2matching</b>(3), <b>pcre2partial</b>(d),
<b>pcre2pattern</b>(3). <b>pcre2pattern</b>(3), <b>pcre2serialize</b>(3).
</P> </P>
<br><a name="SEC19" href="#TOC1">AUTHOR</a><br> <br><a name="SEC20" href="#TOC1">AUTHOR</a><br>
<P> <P>
Philip Hazel Philip Hazel
<br> <br>
@ -1308,9 +1409,9 @@ University Computing Service
Cambridge, England. Cambridge, England.
<br> <br>
</P> </P>
<br><a name="SEC20" href="#TOC1">REVISION</a><br> <br><a name="SEC21" href="#TOC1">REVISION</a><br>
<P> <P>
Last updated: 02 January 2015 Last updated: 23 January 2015
<br> <br>
Copyright &copy; 1997-2015 University of Cambridge. Copyright &copy; 1997-2015 University of Cambridge.
<br> <br>

View File

@ -65,6 +65,9 @@ first.
<tr><td><a href="pcre2sample.html">pcre2sample</a></td> <tr><td><a href="pcre2sample.html">pcre2sample</a></td>
<td>&nbsp;&nbsp;Discussion of the pcre2demo program</td></tr> <td>&nbsp;&nbsp;Discussion of the pcre2demo program</td></tr>
<tr><td><a href="pcre2serialize.html">pcre2serialize</a></td>
<td>&nbsp;&nbsp;Serializing functions for saving precompiled patterns</td></tr>
<tr><td><a href="pcre2stack.html">pcre2stack</a></td> <tr><td><a href="pcre2stack.html">pcre2stack</a></td>
<td>&nbsp;&nbsp;Discussion of PCRE2's stack usage</td></tr> <td>&nbsp;&nbsp;Discussion of PCRE2's stack usage</td></tr>
@ -177,6 +180,18 @@ in the library.
<tr><td><a href="pcre2_pattern_info.html">pcre2_pattern_info</a></td> <tr><td><a href="pcre2_pattern_info.html">pcre2_pattern_info</a></td>
<td>&nbsp;&nbsp;Extract information about a pattern</td></tr> <td>&nbsp;&nbsp;Extract information about a pattern</td></tr>
<tr><td><a href="pcre2_serialize_decode.html">pcre2_serialize_decode</a></td>
<td>&nbsp;&nbsp;Decode serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_serialize_encode.html">pcre2_serialize_encode</a></td>
<td>&nbsp;&nbsp;Serialize compiled patterns for save/restore</td></tr>
<tr><td><a href="pcre2_serialize_free.html">pcre2_serialize_free</a></td>
<td>&nbsp;&nbsp;Free serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_serialize_get_number_of_codes.html">pcre2_serialize_get_number_of_codes</a></td>
<td>&nbsp;&nbsp;Get number of serialized compiled patterns</td></tr>
<tr><td><a href="pcre2_set_bsr.html">pcre2_set_bsr</a></td> <tr><td><a href="pcre2_set_bsr.html">pcre2_set_bsr</a></td>
<td>&nbsp;&nbsp;Set \R convention</td></tr> <td>&nbsp;&nbsp;Set \R convention</td></tr>

View File

@ -343,6 +343,21 @@ PCRE2 NATIVE API JIT FUNCTIONS
void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
PCRE2 NATIVE API SERIALIZATION FUNCTIONS
int32_t pcre2_serialize_decode(pcre2_code **codes,
int32_t number_of_codes, const uint32_t *bytes,
pcre2_general_context *gcontext);
int32_t pcre2_serialize_encode(pcre2_code **codes,
int32_t number_of_codes, uint32_t **serialized_bytes,
PCRE2_SIZE *serialized_size, pcre2_general_context *gcontext);
void pcre2_serialize_free(uint8_t *bytes);
int32_t pcre2_serialize_get_number_of_codes(const uint8_t *bytes);
PCRE2 NATIVE API AUXILIARY FUNCTIONS PCRE2 NATIVE API AUXILIARY FUNCTIONS
int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer, int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer,
@ -1504,8 +1519,13 @@ INFORMATION ABOUT A COMPILED PATTERN
PCRE2_INFO_BACKREFMAX PCRE2_INFO_BACKREFMAX
Return the number of the highest back reference in the pattern. The Return the number of the highest back reference in the pattern. The
third argument should point to an uint32_t variable. Zero is returned third argument should point to an uint32_t variable. Named subpatterns
if there are no back references. acquire numbers as well as names, and these count towards the highest
back reference. Back references such as \4 or \g{12} match the cap-
tured characters of the given group, but in addition, the check that a
capturing group is set in a conditional subpattern such as (?(3)a|b) is
also a back reference. Zero is returned if there are no back refer-
ences.
PCRE2_INFO_BSR PCRE2_INFO_BSR
@ -1715,12 +1735,21 @@ INFORMATION ABOUT A COMPILED PATTERN
Return the size of the compiled pattern in bytes (for all three Return the size of the compiled pattern in bytes (for all three
libraries). The third argument should point to a size_t variable. This libraries). The third argument should point to a size_t variable. This
value does not include the size of the pcre2_code structure that is value includes the size of the general data block that precedes the
returned by pcre_compile(). The value that is used when pcre2_compile() code units of the compiled pattern itself. The value that is used when
is getting memory in which to place the compiled data is the value pcre2_compile() is getting memory in which to place the compiled pat-
returned by this option plus the size of the pcre2_code structure. Pro- tern may be slightly larger than the value returned by this option,
cessing a pattern with the JIT compiler does not alter the value because there are cases where the code that calculates the size has to
returned by this option. over-estimate. Processing a pattern with the JIT compiler does not
alter the value returned by this option.
SERIALIZATION AND PRECOMPILING
It is possible to save compiled patterns on disc or elsewhere, and
reload them later, subject to a number of restrictions. The functions
whose names begin with pcre2_serialize_ are used for this purpose. They
are described in the pcre2serialize documentation.
THE MATCH DATA BLOCK THE MATCH DATA BLOCK
@ -2742,7 +2771,7 @@ AUTHOR
REVISION REVISION
Last updated: 02 January 2015 Last updated: 23 January 2015
Copyright (c) 1997-2015 University of Cambridge. Copyright (c) 1997-2015 University of Cambridge.
------------------------------------------------------------------------------ ------------------------------------------------------------------------------

View File

@ -0,0 +1,50 @@
.TH PCRE2_SERIALIZE_DECODE 3 "19 January 2015" "PCRE2 10.10"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
.rs
.sp
.B #include <pcre2.h>
.PP
.nf
.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
.B " pcre2_general_context *\fIgcontext\fP);"
.fi
.
.SH DESCRIPTION
.rs
.sp
This function decodes a serialized set of compiled patterns back into a list of
individual patterns. Its arguments are:
.sp
\fIcodes\fP pointer to a vector in which to build the list
\fInumber_of_codes\fP number of slots in the vector
\fIbytes\fP the serialized byte stream
\fIgcontext\fP pointer to a general context or NULL
.sp
The \fIbytes\fP argument must point to a block of data that was originally
created by \fBpcre2_serialize_encode()\fP, though it may have been saved on
disc or elsewhere in the meantime. If there are more codes in the serialized
data than slots in the list, only those compiled patterns that will fit are
decoded. The yield of the function is the number of decoded patterns, or one of
the following negative error codes:
.sp
PCRE2_ERROR_BADDATA \fInumber_of_codes\fP is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in \fIbytes\fP
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE version
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_NULL \fIcodes\fP or \fIbytes\fP is NULL
.sp
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
.P
There is a complete description of the PCRE2 native API in the
.\" HREF
\fBpcre2api\fP
.\"
page and a description of the POSIX API in the
.\" HREF
\fBpcre2posix\fP
.\"
page.

View File

@ -0,0 +1,49 @@
.TH PCRE2_SERIALIZE_ENCODE 3 "19 January 2015" "PCRE2 10.10"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
.rs
.sp
.B #include <pcre2.h>
.PP
.nf
.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
.B " PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
.fi
.
.SH DESCRIPTION
.rs
.sp
This function encodes a list of compiled patterns into a byte stream that can
be saved on disc or elsewhere. Its arguments are:
.sp
\fIcodes\fP pointer to a vector containing the list
\fInumber_of_codes\fP number of slots in the vector
\fIserialized_bytes\fP set to point to the serialized byte stream
\fIserialized_size\fP set to the number of bytes in the byte stream
\fIgcontext\fP pointer to a general context or NULL
.sp
The context argument is used to obtain memory for the byte stream. When the
serialized data is no longer needed, it must be freed by calling
\fBpcre2_serialize_free()\fP. The yield of the function is the number of
serialized patterns, or one of the following negative error codes:
.sp
PCRE2_ERROR_BADDATA \fInumber_of_codes\fP is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in one of the patterns
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_MIXEDTABLES the patterns do not all use the same tables
PCRE2_ERROR_NULL an argument other than \fIgcontext\fP is NULL
.sp
PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
that a slot in the vector does not point to a compiled pattern.
.P
There is a complete description of the PCRE2 native API in the
.\" HREF
\fBpcre2api\fP
.\"
page and a description of the POSIX API in the
.\" HREF
\fBpcre2posix\fP
.\"
page.

View File

@ -0,0 +1,28 @@
.TH PCRE2_SERIALIZE_FREE 3 "19 January 2015" "PCRE2 10.10"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
.rs
.sp
.B #include <pcre2.h>
.PP
.nf
.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
.fi
.
.SH DESCRIPTION
.rs
.sp
This function frees the memory that was obtained by
\fBpcre2_serialize_encode()\fP to hold a serialized byte stream. The argument
must point to such a byte stream.
.P
There is a complete description of the PCRE2 native API in the
.\" HREF
\fBpcre2api\fP
.\"
page and a description of the POSIX API in the
.\" HREF
\fBpcre2posix\fP
.\"
page.

View File

@ -0,0 +1,37 @@
.TH PCRE2_SERIALIZE_GET_NUMBER_OF_CODES 3 "19 January 2015" "PCRE2 10.10"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH SYNOPSIS
.rs
.sp
.B #include <pcre2.h>
.PP
.nf
.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
.fi
.
.SH DESCRIPTION
.rs
.sp
The \fIbytes\fP argument must point to a serialized byte stream that was
originally created by \fBpcre2_serialize_encode()\fP (though it may have been
saved on disc or elsewhere in the meantime). The function returns the number of
serialized patterns in the byte stream, or one of the following negative error
codes:
.sp
PCRE2_ERROR_BADMAGIC mismatch of id bytes in \fIbytes\fP
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE version
PCRE2_ERROR_NULL the argument is NULL
.sp
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
.P
There is a complete description of the PCRE2 native API in the
.\" HREF
\fBpcre2api\fP
.\"
page and a description of the POSIX API in the
.\" HREF
\fBpcre2posix\fP
.\"
page.

View File

@ -1,4 +1,4 @@
.TH PCRE2API 3 "13 January 2015" "PCRE2 10.10" .TH PCRE2API 3 "23 January 2015" "PCRE2 10.10"
.SH NAME .SH NAME
PCRE2 - Perl-compatible regular expressions (revised API) PCRE2 - Perl-compatible regular expressions (revised API)
.sp .sp
@ -205,6 +205,24 @@ document for an overview of all the PCRE2 documentation.
.fi .fi
. .
. .
.SH "PCRE2 NATIVE API SERIALIZATION FUNCTIONS"
.rs
.sp
.nf
.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
.B " pcre2_general_context *\fIgcontext\fP);"
.sp
.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
.B " PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
.sp
.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
.sp
.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
.fi
.
.
.SH "PCRE2 NATIVE API AUXILIARY FUNCTIONS" .SH "PCRE2 NATIVE API AUXILIARY FUNCTIONS"
.rs .rs
.sp .sp
@ -1689,12 +1707,26 @@ set, the call to \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
PCRE2_INFO_SIZE PCRE2_INFO_SIZE
.sp .sp
Return the size of the compiled pattern in bytes (for all three libraries). The Return the size of the compiled pattern in bytes (for all three libraries). The
third argument should point to a \fBsize_t\fP variable. This value does not third argument should point to a \fBsize_t\fP variable. This value includes the
include the size of the \fBpcre2_code\fP structure that is returned by size of the general data block that precedes the code units of the compiled
\fBpcre_compile()\fP. The value that is used when \fBpcre2_compile()\fP is pattern itself. The value that is used when \fBpcre2_compile()\fP is getting
getting memory in which to place the compiled data is the value returned by memory in which to place the compiled pattern may be slightly larger than the
this option plus the size of the \fBpcre2_code\fP structure. Processing a value returned by this option, because there are cases where the code that
pattern with the JIT compiler does not alter the value returned by this option. calculates the size has to over-estimate. Processing a pattern with the JIT
compiler does not alter the value returned by this option.
.
.
.SH "SERIALIZATION AND PRECOMPILING"
.rs
.sp
It is possible to save compiled patterns on disc or elsewhere, and reload them
later, subject to a number of restrictions. The functions whose names begin
with \fBpcre2_serialize_\fP are used for this purpose. They are described in
the
.\" HREF
\fBpcre2serialize\fP
.\"
documentation.
. .
. .
.\" HTML <a name="matchdatablock"></a> .\" HTML <a name="matchdatablock"></a>
@ -2853,6 +2885,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 13 January 2015 Last updated: 23 January 2015
Copyright (c) 1997-2015 University of Cambridge. Copyright (c) 1997-2015 University of Cambridge.
.fi .fi

170
doc/pcre2serialize.3 Normal file
View File

@ -0,0 +1,170 @@
.TH PCRE2SERIALIZE 3 "20 January 2015" "PCRE2 10.10"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.SH "SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS"
.rs
.sp
.nf
.B int32_t pcre2_serialize_decode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, const uint32_t *\fIbytes\fP,"
.B " pcre2_general_context *\fIgcontext\fP);"
.sp
.B int32_t pcre2_serialize_encode(pcre2_code **\fIcodes\fP,
.B " int32_t \fInumber_of_codes\fP, uint32_t **\fIserialized_bytes\fP,"
.B " PCRE2_SIZE *\fIserialized_size\fP, pcre2_general_context *\fIgcontext\fP);"
.sp
.B void pcre2_serialize_free(uint8_t *\fIbytes\fP);
.sp
.B int32_t pcre2_serialize_get_number_of_codes(const uint8_t *\fIbytes\fP);
.fi
.sp
If you are running an application that uses a large number of regular
expression patterns, it may be useful to store them in a precompiled form
instead of having to compile them every time the application is run. However,
if you are using the just-in-time optimization feature, it is not possible to
save and reload the JIT data, because it is position-dependent. In addition,
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. For example, patterns compiled on a 32-bit
system using PCRE2's 16-bit library cannot be reloaded on a 64-bit system, nor
can they be reloaded using the 8-bit library.
.
.
.SH "SAVING COMPILED PATTERNS"
.rs
.sp
Before compiled patterns can be saved they must be serialized, that is,
converted to a stream of bytes. A single byte stream may contain any number of
compiled patterns, but they must all use the same character tables. A single
copy of the tables is included in the byte stream (its size is 1088 bytes). For
more details of character tables, see the
.\" HTML <a href="pcre2api.html#localesupport">
.\" </a>
section on locale support
.\"
in the
.\" HREF
\fBpcre2api\fP
.\"
documentation.
.P
The function \fBpcre2_serialize_encode()\fP creates a serialized byte stream
from a list of compiled patterns. Its first two arguments specify the list,
being a pointer to a vector of pointers to compiled patterns, and the length of
the vector. The third and fourth arguments point to variables which are set to
point to the created byte stream and its length, respectively. The final
argument is a pointer to a general context, which can be used to specify custom
memory mangagement functions. If this argument is NULL, \fBmalloc()\fP is used
to obtain memory for the byte stream. The yield of the function is the number
of serialized patterns, or one of the following negative error codes:
.sp
PCRE2_ERROR_BADDATA the number of patterns is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in one of the patterns
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_MIXEDTABLES the patterns do not all use the same tables
PCRE2_ERROR_NULL the 1st, 3rd, or 4th argument is NULL
.sp
PCRE2_ERROR_BADMAGIC means either that a pattern's code has been corrupted, or
that a slot in the vector does not point to a compiled pattern.
.P
Once a set of patterns has been serialized you can save the data in any
appropriate manner. Here is sample code that compiles two patterns and writes
them to a file. It assumes that the variable \fIfd\fP refers to a file that is
open for output. The error checking that should be present in a real
application has been omitted for simplicity.
.sp
int errorcode;
uint8_t *bytes;
PCRE2_SIZE erroroffset;
PCRE2_SIZE bytescount;
pcre2_code *list_of_codes[2];
list_of_codes[0] = pcre2_compile("first pattern",
PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
list_of_codes[1] = pcre2_compile("second pattern",
PCRE2_ZERO_TERMINATED, 0, &errorcode, &erroroffset, NULL);
errorcode = pcre2_serialize_encode(list_of_codes, 2, &bytes,
&bytescount, NULL);
errorcode = fwrite(bytes, 1, bytescount, fd);
.sp
Note that the serialized data is binary data that may contain any of the 256
possible byte values. On systems that make a distinction between binary and
non-binary data, be sure that the file is opened for binary output.
.P
Serializing a set of patterns leaves the original data untouched, so they can
still be used for matching. Their memory must eventually be freed in the usual
way by calling \fBpcre2_code_free()\fP. When you have finished with the byte
stream, it too must be freed by calling \fBpcre2_serialize_free()\fP.
.
.
.SH "RE-USING PRECOMPILED PATTERNS"
.rs
.sp
In order to re-use a set of saved patterns you must first make the serialized
byte stream available in main memory (for example, by reading from a file). The
management of this memory block is up to the application. You can use the
\fBpcre2_serialize_get_number_of_codes()\fP function to find out how many
compiled patterns are in the serialized data without actually decoding the
patterns:
.sp
uint8_t *bytes = <serialized data>;
int32_t number_of_codes = pcre2_serialize_get_number_of_codes(bytes);
.sp
The \fBpcre2_serialize_decode()\fP function reads a byte stream and recreates
the compiled patterns in new memory blocks, setting pointers to them in a
vector. The first two arguments are a pointer to a suitable vector and its
length, and the third argument points to a byte stream. The final argument is a
pointer to a general context, which can be used to specify custom memory
mangagement functions for the decoded patterns. If this argument is NULL,
\fBmalloc()\fP and \fBfree()\fP are used. After deserialization, the byte
stream is no longer needed and can be discarded.
.sp
int32_t number_of_codes;
pcre2_code *list_of_codes[2];
uint8_t *bytes = <serialized data>;
int32_t number_of_codes =
pcre2_serialize_decode(list_of_codes, 2, bytes, NULL);
.sp
If the vector is not large enough for all the patterns in the byte stream, it
is filled with those that fit, and the remainder are ignored. The yield of the
function is the number of decoded patterns, or one of the following negative
error codes:
.sp
PCRE2_ERROR_BADDATA second argument is zero or less
PCRE2_ERROR_BADMAGIC mismatch of id bytes in the data
PCRE2_ERROR_BADMODE mismatch of variable unit size or PCRE2 version
PCRE2_ERROR_MEMORY memory allocation failed
PCRE2_ERROR_NULL first or third argument is NULL
.sp
PCRE2_ERROR_BADMAGIC may mean that the data is corrupt, or that it was compiled
on a system with different endianness.
.P
Decoded patterns can be used for matching in the usual way, and must be freed
by calling \fBpcre2_code_free()\fP as normal. A single copy of the character
tables is used by all the decoded patterns. A reference count is used to
arrange for its memory to be automatically freed when the last pattern is
freed.
.P
If a pattern was processed by \fBpcre2_jit_compile()\fP before being
serialized, the JIT data is discarded and so is no longer available after a
save/restore cycle. You can, however, process a restored pattern with
\fBpcre2_jit_compile()\fP if you wish.
.
.
.
.SH AUTHOR
.rs
.sp
.nf
Philip Hazel
University Computing Service
Cambridge, England.
.fi
.
.
.SH REVISION
.rs
.sp
.nf
Last updated: 20 January 2015
Copyright (c) 1997-2015 University of Cambridge.
.fi

View File

@ -1,4 +1,4 @@
.TH PCRE2TEST 1 "02 January 2015" "PCRE 10.00" .TH PCRE2TEST 1 "23 January 2015" "PCRE 10.10"
.SH NAME .SH NAME
pcre2test - a program for testing Perl-compatible regular expressions. pcre2test - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS .SH SYNOPSIS
@ -21,10 +21,11 @@ options, see the
documentation. documentation.
.P .P
The input for \fBpcre2test\fP is a sequence of regular expression patterns and The input for \fBpcre2test\fP is a sequence of regular expression patterns and
subject strings to be matched. The output shows the result of each match subject strings to be matched. There are also command lines for setting
attempt. Modifiers on the command line, the patterns, and the subject lines defaults and controlling some special actions. The output shows the result of
specify PCRE2 function options, control how the subject is processed, and what each match attempt. Modifiers on external or internal command lines, the
output is produced. patterns, and the subject lines specify PCRE2 function options, control how the
subject is processed, and what output is produced.
.P .P
As the original fairly simple PCRE library evolved, it acquired many different As the original fairly simple PCRE library evolved, it acquired many different
features, and as a result, the original \fBpcretest\fP program ended up with a features, and as a result, the original \fBpcretest\fP program ended up with a
@ -185,9 +186,7 @@ If \fBpcre2test\fP is given two filename arguments, it reads from the first and
writes to the second. If the first name is "-", input is taken from the writes to the second. If the first name is "-", input is taken from the
standard input. If \fBpcre2test\fP is given only one argument, it reads from standard input. If \fBpcre2test\fP is given only one argument, it reads from
that file and writes to stdout. Otherwise, it reads from stdin and writes to that file and writes to stdout. Otherwise, it reads from stdin and writes to
stdout. When the input is a terminal, it prompts for each line of input, using stdout.
"re>" to prompt for regular expression patterns, and "data>" to prompt for
subject lines.
.P .P
When \fBpcre2test\fP is built, a configuration option can specify that it When \fBpcre2test\fP is built, a configuration option can specify that it
should be linked with the \fBlibreadline\fP or \fBlibedit\fP library. When this should be linked with the \fBlibreadline\fP or \fBlibedit\fP library. When this
@ -198,10 +197,15 @@ the \fB-help\fP option states whether or not \fBreadline()\fP will be used.
The program handles any number of tests, each of which consists of a set of The program handles any number of tests, each of which consists of a set of
input lines. Each set starts with a regular expression pattern, followed by any input lines. Each set starts with a regular expression pattern, followed by any
number of subject lines to be matched against that pattern. In between sets of number of subject lines to be matched against that pattern. In between sets of
test data, command lines that begin with a hash (#) character may appear. This test data, command lines that begin with # may appear. This file format, with
file format, with some restrictions, can also be processed by the some restrictions, can also be processed by the \fBperltest.sh\fP script that
\fBperltest.sh\fP script that is distributed with PCRE2 as a means of checking is distributed with PCRE2 as a means of checking that the behaviour of PCRE2
that the behaviour of PCRE2 and Perl is the same. and Perl is the same.
.P
When the input is a terminal, \fBpcre2test\fP 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 only in
response to the "re>" prompt.
.P .P
Each subject line is matched separately and independently. If you want to do Each subject line is matched separately and independently. If you want to do
multi-line matches, you have to use the \en escape sequence (or \er or \er\en, multi-line matches, you have to use the \en escape sequence (or \er or \er\en,
@ -219,21 +223,30 @@ still input to be read.
.SH "COMMAND LINES" .SH "COMMAND LINES"
.rs .rs
.sp .sp
In between sets of test data, a line that begins with a hash (#) character is In between sets of test data, a line that begins with # is interpreted as a
interpreted as a command line. If the first character is followed by white command line. If the first character is followed by white space or an
space or an exclamation mark, the line is treated as a comment, and ignored. exclamation mark, the line is treated as a comment, and ignored. Otherwise, the
Otherwise, the following commands are recognized: following commands are recognized:
.sp .sp
#forbid_utf #forbid_utf
.sp .sp
Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP Subsequent patterns automatically have the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP
options set, which locks out the use of UTF and Unicode property features. This options set, which locks out the use of UTF and Unicode property features. This
is a trigger guard that is used in test files to ensure that UTF/Unicode tests is a trigger guard that is used in test files to ensure that UTF or Unicode
are not accidentally added to files that are used when UTF support is not property tests are not accidentally added to files that are used when Unicode
included in the library. This effect can also be obtained by the use of support is not included in the library. This effect can also be obtained by the
\fB#pattern\fP; the difference is that \fB#forbid_utf\fP cannot be unset, and use of \fB#pattern\fP; the difference is that \fB#forbid_utf\fP cannot be
the automatic options are not displayed in pattern information, to avoid unset, and the automatic options are not displayed in pattern information, to
cluttering up test output. avoid cluttering up test output.
.sp
#load <filename>
.sp
This command is used to load a set of precompiled patterns from a file, as
described in the section entitled "Saving and restoring compiled patterns"
.\" HTML <a href="#saverestore">
.\" </a>
below.
.\"
.sp .sp
#pattern <modifier-list> #pattern <modifier-list>
.sp .sp
@ -249,6 +262,24 @@ lines, none of the other command lines are permitted, because they and many
of the modifiers are specific to \fBpcre2test\fP, and should not be used in of the modifiers are specific to \fBpcre2test\fP, and should not be used in
test files that are also processed by \fBperltest.sh\fP. The \fB#perltest\fP test files that are also processed by \fBperltest.sh\fP. The \fB#perltest\fP
command helps detect tests that are accidentally put in the wrong file. command helps detect tests that are accidentally put in the wrong file.
.sp
#pop [<modifiers>]
.sp
This command is used to manipulate the stack of compiled patterns, as described
in the section entitled "Saving and restoring compiled patterns"
.\" HTML <a href="#saverestore">
.\" </a>
below.
.\"
.sp
#save <filename>
.sp
This command is used to save a set of compiled patterns to a file, as described
in the section entitled "Saving and restoring compiled patterns"
.\" HTML <a href="#saverestore">
.\" </a>
below.
.\"
.sp .sp
#subject <modifier-list> #subject <modifier-list>
.sp .sp
@ -387,6 +418,7 @@ can add to or override default modifiers that were set by a previous
\fB#pattern\fP command. \fB#pattern\fP command.
. .
. .
.\" HTML <a name="optionmodifiers"></a>
.SS "Setting compilation options" .SS "Setting compilation options"
.rs .rs
.sp .sp
@ -426,6 +458,7 @@ notation. Otherwise, those less than 0x100 are output in hex without the curly
brackets. brackets.
. .
. .
.\" HTML <a name="controlmodifiers"></a>
.SS "Setting compilation controls" .SS "Setting compilation controls"
.rs .rs
.sp .sp
@ -445,8 +478,8 @@ about the pattern:
memory show memory used memory show memory used
newline=<type> set newline type newline=<type> set newline type
parens_nest_limit=<n> set maximum parentheses depth parens_nest_limit=<n> set maximum parentheses depth
perlcompat lock out non-Perl modifiers
posix use the POSIX API posix use the POSIX API
push push compiled pattern onto the stack
stackguard=<number> test the stackguard feature stackguard=<number> test the stackguard feature
tables=[0|1|2] select internal tables tables=[0|1|2] select internal tables
.sp .sp
@ -683,6 +716,25 @@ These modifiers may not appear in a \fB#pattern\fP command. If you want them as
defaults, set them in a \fB#subject\fP command. defaults, set them in a \fB#subject\fP command.
. .
. .
.SS "Saving a compiled pattern"
.rs
.sp
When a pattern with the \fBpush\fP modifier is successfully compiled, it is
pushed onto a stack of compiled patterns, and \fBpcre2test\fP 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 patterns"
.\" HTML <a href="#saverestore">
.\" </a>
below.
.\"
The \fBpush\fP modifier is incompatible with compilation modifiers such as
\fBglobal\fP that act at match time. Any that are specified are ignored, with a
warning message, except for \fBreplace\fP, which causes an error. Note that,
\fBjitverify\fP, which is allowed, does not carry through to any subsequent
matching that uses this pattern.
.
.
.SH "SUBJECT MODIFIERS" .SH "SUBJECT MODIFIERS"
.rs .rs
.sp .sp
@ -1253,12 +1305,83 @@ characters.
. .
. .
. .
.\" HTML <a name="saverestore"></a>
.SH "SAVING AND RESTORING COMPILED PATTERNS"
.rs
.sp
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 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, converted to a stream of bytes. A single byte stream may
contain any number of compiled patterns, but they must all use the same
character tables. A single copy of the tables is included in the byte stream
(its size is 1088 bytes).
.P
The functions whose names begin with \fBpcre2_serialize_\fP are used
for serializing and de-serializing. They are described in the
.\" HREF
\fBpcre2serialize\fP
.\"
documentation. In this section we describe the features of \fBpcre2test\fP that
can be used to test these functions.
.P
When a pattern with \fBpush\fP modifier is successfully compiled, it is pushed
onto a stack of compiled patterns, and \fBpcre2test\fP expects the next line to
contain a new pattern (or command) instead of a subject line. By this means, a
number of patterns can be compiled and retained. The \fBpush\fP modifier is
incompatible with \fBposix\fP, and control modifiers that act at match time are
ignored (with a message). The \fBjitverify\fP modifier applies only at compile
time. The command
.sp
#save <filename>
.sp
causes all the stacked patterns to be serialized and the result written to the
named file. Afterwards, all the stacked patterns are freed. The command
.sp
#load <filename>
.sp
reads the data in the file, and then arranges for it to be de-serialized, with
the resulting compiled patterns added to the pattern stack. The pattern on the
top of the stack can be retrieved by the #pop command, 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
.\" HTML <a href="#controlmodifiers">
.\" </a>
control modifiers
.\"
that act after a pattern has been compiled. In particular, \fBhex\fP,
\fBposix\fP, and \fBpush\fP are not allowed, nor are any
.\" HTML <a href="#optionmodifiers">
.\" </a>
option-setting modifiers.
.\"
The JIT modifiers are, however permitted. Here is an example that saves and
reloads two patterns.
.sp
/abc/push
/xyz/push
#save tempfile
#load tempfile
#pop info
xyz
.sp
#pop jit,bincode
abc
.sp
If \fBjitverify\fP is used with #pop, it does not automatically imply
\fBjit\fP, which is different behaviour from when it is used on a pattern.
.
.
.
.SH "SEE ALSO" .SH "SEE ALSO"
.rs .rs
.sp .sp
\fBpcre2\fP(3), \fBpcre2api\fP(3), \fBpcre2callout\fP(3), \fBpcre2\fP(3), \fBpcre2api\fP(3), \fBpcre2callout\fP(3),
\fBpcre2jit\fP, \fBpcre2matching\fP(3), \fBpcre2partial\fP(d), \fBpcre2jit\fP, \fBpcre2matching\fP(3), \fBpcre2partial\fP(d),
\fBpcre2pattern\fP(3). \fBpcre2pattern\fP(3), \fBpcre2serialize\fP(3).
. .
. .
.SH AUTHOR .SH AUTHOR
@ -1275,6 +1398,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 02 January 2015 Last updated: 23 January 2015
Copyright (c) 1997-2015 University of Cambridge. Copyright (c) 1997-2015 University of Cambridge.
.fi .fi

View File

@ -17,10 +17,12 @@ SYNOPSIS
options, see the pcre2api documentation. options, see the pcre2api documentation.
The input for pcre2test is a sequence of regular expression patterns The input for pcre2test is a sequence of regular expression patterns
and subject strings to be matched. The output shows the result of each and subject strings to be matched. There are also command lines for
match attempt. Modifiers on the command line, the patterns, and the setting defaults and controlling some special actions. The output shows
subject lines specify PCRE2 function options, control how the subject the result of each match attempt. Modifiers on external or internal
is processed, and what output is produced. command lines, the patterns, and the subject lines specify PCRE2 func-
tion options, control how the subject is processed, and what output is
produced.
As the original fairly simple PCRE library evolved, it acquired many As the original fairly simple PCRE library evolved, it acquired many
different features, and as a result, the original pcretest program different features, and as a result, the original pcretest program
@ -173,9 +175,7 @@ DESCRIPTION
and writes to the second. If the first name is "-", input is taken from and writes to the second. If the first name is "-", input is taken from
the standard input. If pcre2test is given only one argument, it reads the standard input. If pcre2test is given only one argument, it reads
from that file and writes to stdout. Otherwise, it reads from stdin and from that file and writes to stdout. Otherwise, it reads from stdin and
writes to stdout. When the input is a terminal, it prompts for each writes to stdout.
line of input, using "re>" to prompt for regular expression patterns,
and "data>" to prompt for subject lines.
When pcre2test is built, a configuration option can specify that it When pcre2test is built, a configuration option can specify that it
should be linked with the libreadline or libedit library. When this is should be linked with the libreadline or libedit library. When this is
@ -186,11 +186,15 @@ DESCRIPTION
The program handles any number of tests, each of which consists of a The program handles any number of tests, each of which consists of a
set of input lines. Each set starts with a regular expression pattern, set of input lines. Each set starts with a regular expression pattern,
followed by any number of subject lines to be matched against that pat- followed by any number of subject lines to be matched against that pat-
tern. In between sets of test data, command lines that begin with a tern. In between sets of test data, command lines that begin with # may
hash (#) character may appear. This file format, with some restric- appear. This file format, with some restrictions, can also be processed
tions, can also be processed by the perltest.sh script that is distrib- by the perltest.sh script that is distributed with PCRE2 as a means of
uted with PCRE2 as a means of checking that the behaviour of PCRE2 and checking that the behaviour of PCRE2 and Perl is the same.
Perl is the same.
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
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 to do multi-line matches, you have to use the \n escape sequence (or \r
@ -207,22 +211,28 @@ DESCRIPTION
COMMAND LINES COMMAND LINES
In between sets of test data, a line that begins with a hash (#) char- In between sets of test data, a line that begins with # is interpreted
acter is interpreted as a command line. If the first character is fol- as a command line. If the first character is followed by white space or
lowed by white space or an exclamation mark, the line is treated as a an exclamation mark, the line is treated as a comment, and ignored.
comment, and ignored. Otherwise, the following commands are recog- Otherwise, the following commands are recognized:
nized:
#forbid_utf #forbid_utf
Subsequent patterns automatically have the PCRE2_NEVER_UTF and Subsequent patterns automatically have the PCRE2_NEVER_UTF and
PCRE2_NEVER_UCP options set, which locks out the use of UTF and Unicode PCRE2_NEVER_UCP options set, which locks out the use of UTF and Unicode
property features. This is a trigger guard that is used in test files property features. This is a trigger guard that is used in test files
to ensure that UTF/Unicode tests are not accidentally added to files to ensure that UTF or Unicode property tests are not accidentally added
that are used when UTF support is not included in the library. This to files that are used when Unicode support is not included in the
effect can also be obtained by the use of #pattern; the difference is library. This effect can also be obtained by the use of #pattern; the
that #forbid_utf cannot be unset, and the automatic options are not difference is that #forbid_utf cannot be unset, and the automatic
displayed in pattern information, to avoid cluttering up test output. options are not displayed in pattern information, 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
patterns" below.
#pattern <modifier-list> #pattern <modifier-list>
@ -240,6 +250,18 @@ COMMAND LINES
#perltest command helps detect tests that are accidentally put in the #perltest command helps detect tests that are accidentally put in the
wrong file. wrong file.
#pop [<modifiers>]
This command is used to manipulate the stack of compiled patterns, as
described in the section entitled "Saving and restoring compiled pat-
terns" 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-
terns" below.
#subject <modifier-list> #subject <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-
@ -432,8 +454,8 @@ PATTERN MODIFIERS
memory show memory used memory show memory used
newline=<type> set newline type newline=<type> set newline type
parens_nest_limit=<n> set maximum parentheses depth parens_nest_limit=<n> set maximum parentheses depth
perlcompat lock out non-Perl modifiers
posix use the POSIX API posix use the POSIX API
push push compiled pattern onto the stack
stackguard=<number> test the stackguard feature stackguard=<number> test the stackguard feature
tables=[0|1|2] select internal tables tables=[0|1|2] select internal tables
@ -644,6 +666,19 @@ PATTERN MODIFIERS
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. as defaults, set them in a #subject command.
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
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. The push modifier is incompatible with compilation modi-
fiers such as global that act at match time. Any that are specified are
ignored, with a 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 this pattern.
SUBJECT MODIFIERS SUBJECT MODIFIERS
@ -1171,10 +1206,69 @@ NON-PRINTING CHARACTERS
characters. characters.
SAVING AND RESTORING COMPILED PATTERNS
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
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
tables. 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
serializing and de-serializing. They are described in the pcre2serial-
ize documentation. In this section we describe the features of
pcre2test that can be used to test these functions.
When a pattern with 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 command) instead of a subject
line. By this means, a number of patterns can be compiled and retained.
The push modifier is incompatible with posix, and control modifiers
that act at match time are ignored (with a message). The jitverify mod-
ifier applies only at compile time. The command
#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
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, and push are not allowed, nor are any option-
setting modifiers. The JIT modifiers are, however permitted. Here is
an example that saves and reloads two patterns.
/abc/push
/xyz/push
#save tempfile
#load tempfile
#pop info
xyz
#pop jit,bincode
abc
If jitverify is used with #pop, it does not automatically imply jit,
which is different behaviour from when it is used on a pattern.
SEE ALSO SEE ALSO
pcre2(3), pcre2api(3), pcre2callout(3), pcre2jit, pcre2matching(3), pcre2(3), pcre2api(3), pcre2callout(3), pcre2jit, pcre2matching(3),
pcre2partial(d), pcre2pattern(3). pcre2partial(d), pcre2pattern(3), pcre2serialize(3).
AUTHOR AUTHOR
@ -1186,5 +1280,5 @@ AUTHOR
REVISION REVISION
Last updated: 02 January 2015 Last updated: 23 January 2015
Copyright (c) 1997-2015 University of Cambridge. Copyright (c) 1997-2015 University of Cambridge.

View File

@ -293,7 +293,7 @@ if [ $usevalgrind -ne 0 ]; then
for opts in \ for opts in \
"--disable-stack-for-recursion --disable-shared" \ "--disable-stack-for-recursion --disable-shared" \
"--with-link-size=3 --disable-shared" \ "--with-link-size=3 --enable-pcre2-16 --enable-pcre2-32 --disable-shared" \
"--disable-unicode --disable-shared" "--disable-unicode --disable-shared"
do do
opts="--enable-valgrind $opts" opts="--enable-valgrind $opts"

View File

@ -200,7 +200,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_NAME "PCRE2" #define PACKAGE_NAME "PCRE2"
/* Define to the full name and version of this package. */ /* Define to the full name and version of this package. */
#define PACKAGE_STRING "PCRE2 10.00" #define PACKAGE_STRING "PCRE2 10.10-RC1"
/* Define to the one symbol short name of this package. */ /* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME "pcre2" #define PACKAGE_TARNAME "pcre2"
@ -209,7 +209,7 @@ sure both macros are undefined; an emulation function will then be used. */
#define PACKAGE_URL "" #define PACKAGE_URL ""
/* Define to the version of this package. */ /* Define to the version of this package. */
#define PACKAGE_VERSION "10.00" #define PACKAGE_VERSION "10.10-RC1"
/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
parentheses (of any kind) in a pattern. This limits the amount of system parentheses (of any kind) in a pattern. This limits the amount of system
@ -287,7 +287,7 @@ sure both macros are undefined; an emulation function will then be used. */
/* #undef SUPPORT_VALGRIND */ /* #undef SUPPORT_VALGRIND */
/* Version number of package */ /* Version number of package */
#define VERSION "10.00" #define VERSION "10.10-RC1"
/* Define to empty if `const' does not conform to ANSI C. */ /* Define to empty if `const' does not conform to ANSI C. */
/* #undef const */ /* #undef const */

View File

@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
/* The current PCRE version information. */ /* The current PCRE version information. */
#define PCRE2_MAJOR 10 #define PCRE2_MAJOR 10
#define PCRE2_MINOR 00 #define PCRE2_MINOR 10
#define PCRE2_PRERELEASE #define PCRE2_PRERELEASE -RC1
#define PCRE2_DATE 2014-01-05 #define PCRE2_DATE 2014-01-13
/* When an application links to a PCRE DLL in Windows, the symbols that are /* When an application links to a PCRE DLL in Windows, the symbols that are
imported have to be identified as such. When building PCRE2, the appropriate imported have to be identified as such. When building PCRE2, the appropriate
@ -455,6 +455,18 @@ PCRE2_EXP_DECL void pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \ PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \
PCRE2_UCHAR ***, PCRE2_SIZE **); PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int pcre2_serialize_encode(const pcre2_code **, \
PCRE2_SIZE, uint8_t **, PCRE2_SIZE *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int pcre2_serialize_decode(pcre2_code **, PCRE2_SIZE, \
const uint8_t *, pcre2_general_context *); \
PCRE2_EXP_DECL int pcre2_serialize_get_number_of_codes(const uint8_t *, \
PCRE2_SIZE *); \
PCRE2_EXP_DECL void pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */ /* Convenience function for match + substitute. */
@ -560,6 +572,10 @@ pcre2_compile are called by application code. */
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_) #define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_) #define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_) #define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
#define pcre2_serialize_free PCRE2_SUFFIX(pcre2_serialize_free_)
#define pcre2_serialize_get_number_of_codes PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_) #define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_) #define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_) #define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
@ -596,8 +612,9 @@ PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \ PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \ PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \ PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_SUBSTRING_FUNCTIONS \ PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_JIT_FUNCTIONS \ PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS PCRE2_OTHER_FUNCTIONS
@ -625,6 +642,8 @@ PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS #undef PCRE2_PATTERN_INFO_FUNCTIONS
#undef PCRE2_MATCH_FUNCTIONS #undef PCRE2_MATCH_FUNCTIONS
#undef PCRE2_SUBSTRING_FUNCTIONS #undef PCRE2_SUBSTRING_FUNCTIONS
#undef PCRE2_SERIALIZE_FUNCTIONS
#undef PCRE2_SUBSTITUTE_FUNCTION
#undef PCRE2_JIT_FUNCTIONS #undef PCRE2_JIT_FUNCTIONS
#undef PCRE2_OTHER_FUNCTIONS #undef PCRE2_OTHER_FUNCTIONS
#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS #undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS

View File

@ -198,11 +198,13 @@ greater than zero. */
#define PCRE2_ERROR_UTF32_ERR1 (-27) #define PCRE2_ERROR_UTF32_ERR1 (-27)
#define PCRE2_ERROR_UTF32_ERR2 (-28) #define PCRE2_ERROR_UTF32_ERR2 (-28)
/* Error codes for pcre2[_dfa]_match(), substring extraction functions, and /* Error codes for pcre2[_dfa]_match(), substring extraction functions, context
context functions. */ functions, and serializing functions. They are in numerical order. Originally
they were in alphabetical order too, but now that PCRE2 is released, the
numbers must not be changed. */
#define PCRE2_ERROR_BADDATA (-29) #define PCRE2_ERROR_BADDATA (-29)
#define PCRE2_ERROR_BADLENGTH (-30) #define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */
#define PCRE2_ERROR_BADMAGIC (-31) #define PCRE2_ERROR_BADMAGIC (-31)
#define PCRE2_ERROR_BADMODE (-32) #define PCRE2_ERROR_BADMODE (-32)
#define PCRE2_ERROR_BADOFFSET (-33) #define PCRE2_ERROR_BADOFFSET (-33)
@ -455,6 +457,17 @@ PCRE2_EXP_DECL void pcre2_substring_list_free(PCRE2_SPTR *); \
PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \ PCRE2_EXP_DECL int pcre2_substring_list_get(pcre2_match_data *, \
PCRE2_UCHAR ***, PCRE2_SIZE **); PCRE2_UCHAR ***, PCRE2_SIZE **);
/* Functions for serializing / deserializing compiled patterns. */
#define PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_EXP_DECL int32_t pcre2_serialize_encode(const pcre2_code **, \
int32_t, uint8_t **, PCRE2_SIZE *, \
pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_decode(pcre2_code **, int32_t, \
const uint8_t *, pcre2_general_context *); \
PCRE2_EXP_DECL int32_t pcre2_serialize_get_number_of_codes(const uint8_t *); \
PCRE2_EXP_DECL void pcre2_serialize_free(uint8_t *);
/* Convenience function for match + substitute. */ /* Convenience function for match + substitute. */
@ -560,6 +573,10 @@ pcre2_compile are called by application code. */
#define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_) #define pcre2_match_data_create_from_pattern PCRE2_SUFFIX(pcre2_match_data_create_from_pattern_)
#define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_) #define pcre2_match_data_free PCRE2_SUFFIX(pcre2_match_data_free_)
#define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_) #define pcre2_pattern_info PCRE2_SUFFIX(pcre2_pattern_info_)
#define pcre2_serialize_decode PCRE2_SUFFIX(pcre2_serialize_decode_)
#define pcre2_serialize_encode PCRE2_SUFFIX(pcre2_serialize_encode_)
#define pcre2_serialize_free PCRE2_SUFFIX(pcre2_serialize_free_)
#define pcre2_serialize_get_number_of_codes PCRE2_SUFFIX(pcre2_serialize_get_number_of_codes_)
#define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_) #define pcre2_set_bsr PCRE2_SUFFIX(pcre2_set_bsr_)
#define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_) #define pcre2_set_callout PCRE2_SUFFIX(pcre2_set_callout_)
#define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_) #define pcre2_set_character_tables PCRE2_SUFFIX(pcre2_set_character_tables_)
@ -596,8 +613,9 @@ PCRE2_MATCH_CONTEXT_FUNCTIONS \
PCRE2_COMPILE_FUNCTIONS \ PCRE2_COMPILE_FUNCTIONS \
PCRE2_PATTERN_INFO_FUNCTIONS \ PCRE2_PATTERN_INFO_FUNCTIONS \
PCRE2_MATCH_FUNCTIONS \ PCRE2_MATCH_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_SUBSTRING_FUNCTIONS \ PCRE2_SUBSTRING_FUNCTIONS \
PCRE2_SERIALIZE_FUNCTIONS \
PCRE2_SUBSTITUTE_FUNCTION \
PCRE2_JIT_FUNCTIONS \ PCRE2_JIT_FUNCTIONS \
PCRE2_OTHER_FUNCTIONS PCRE2_OTHER_FUNCTIONS
@ -625,6 +643,8 @@ PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS
#undef PCRE2_PATTERN_INFO_FUNCTIONS #undef PCRE2_PATTERN_INFO_FUNCTIONS
#undef PCRE2_MATCH_FUNCTIONS #undef PCRE2_MATCH_FUNCTIONS
#undef PCRE2_SUBSTRING_FUNCTIONS #undef PCRE2_SUBSTRING_FUNCTIONS
#undef PCRE2_SERIALIZE_FUNCTIONS
#undef PCRE2_SUBSTITUTE_FUNCTION
#undef PCRE2_JIT_FUNCTIONS #undef PCRE2_JIT_FUNCTIONS
#undef PCRE2_OTHER_FUNCTIONS #undef PCRE2_OTHER_FUNCTIONS
#undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS #undef PCRE2_TYPES_STRUCTURES_AND_FUNCTIONS

View File

@ -683,10 +683,28 @@ static const uint8_t opcode_possessify[] = {
PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
pcre2_code_free(pcre2_code *code) pcre2_code_free(pcre2_code *code)
{ {
PCRE2_SIZE* ref_count;
if (code != NULL) if (code != NULL)
{ {
if (code->executable_jit != NULL) if (code->executable_jit != NULL)
PRIV(jit_free)(code->executable_jit, &code->memctl); PRIV(jit_free)(code->executable_jit, &code->memctl);
if ((code->flags & PCRE2_DEREF_TABLES) != 0)
{
/* Decoded tables belong to the codes after deserialization, and they must
be freed when there are no more reference to them. The *ref_count should
always be > 0. */
ref_count = (PCRE2_SIZE *)(code->tables + tables_length);
if (*ref_count > 0)
{
(*ref_count)--;
if (*ref_count == 0)
code->memctl.free((void *)code->tables, code->memctl.memory_data);
}
}
code->memctl.free(code, code->memctl.memory_data); code->memctl.free(code, code->memctl.memory_data);
} }
} }
@ -7317,8 +7335,14 @@ for (i = 0; i < cb->names_found; i++)
PUT2(slot, 0, groupno); PUT2(slot, 0, groupno);
memcpy(slot + IMM2_SIZE, name, CU2BYTES(length)); memcpy(slot + IMM2_SIZE, name, CU2BYTES(length));
slot[IMM2_SIZE + length] = 0;
cb->names_found++; cb->names_found++;
/* Add a terminating zero and fill the rest of the slot with zeroes so that
the memory is all initialized. Otherwise valgrind moans about uninitialized
memory when saving serialized compiled patterns. */
memset(slot + IMM2_SIZE + length, 0,
CU2BYTES(cb->name_entry_size - length - IMM2_SIZE));
} }
@ -7356,6 +7380,7 @@ PCRE2_SPTR codestart; /* Start of compiled code */
PCRE2_SPTR ptr; /* Current pointer in pattern */ PCRE2_SPTR ptr; /* Current pointer in pattern */
size_t length = 1; /* Allow or final END opcode */ size_t length = 1; /* Allow or final END opcode */
size_t usedlength; /* Actual length used */
size_t re_blocksize; /* Size of memory block */ size_t re_blocksize; /* Size of memory block */
int32_t firstcuflags, reqcuflags; /* Type of first/req code unit */ int32_t firstcuflags, reqcuflags; /* Type of first/req code unit */
@ -7754,13 +7779,16 @@ overflow. */
if (errorcode == 0 && ptr < cb.end_pattern) errorcode = ERR22; if (errorcode == 0 && ptr < cb.end_pattern) errorcode = ERR22;
*code++ = OP_END; *code++ = OP_END;
if ((size_t)(code - codestart) > length) errorcode = ERR23; usedlength = code - codestart;
if (usedlength > length) errorcode = ERR23;
/* If the estimated length exceeds the really used length, adjust the value of
re->blocksize, and if valgrind support is configured, mark the extra allocated
memory as unaddressable, so that any out-of-bound reads can be detected. */
re->blocksize -= CU2BYTES(length - usedlength);
#ifdef SUPPORT_VALGRIND #ifdef SUPPORT_VALGRIND
/* If the estimated length exceeds the really used length, mark the extra VALGRIND_MAKE_MEM_NOACCESS(code, CU2BYTES(length - usedlength));
allocated memory as unaddressable, so that any out-of-bound reads can be
detected. */
VALGRIND_MAKE_MEM_NOACCESS(code, (length - (code - codestart)) * sizeof(PCRE2_UCHAR));
#endif #endif
/* Fill in any forward references that are required. There may be repeated /* Fill in any forward references that are required. There may be repeated

View File

@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2014 University of Cambridge New API code Copyright (c) 2015 University of Cambridge
----------------------------------------------------------------------------- -----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without Redistribution and use in source and binary forms, with or without
@ -200,7 +200,7 @@ static const char match_error_texts[] =
"UTF-32 error: code points greater than 0x10ffff are not defined\0" "UTF-32 error: code points greater than 0x10ffff are not defined\0"
"bad data value\0" "bad data value\0"
/* 30 */ /* 30 */
"bad length\0" "patterns do not all use the same character tables\0"
"magic number missing\0" "magic number missing\0"
"pattern compiled in wrong mode: 8/16/32-bit error\0" "pattern compiled in wrong mode: 8/16/32-bit error\0"
"bad offset value\0" "bad offset value\0"

View File

@ -523,6 +523,7 @@ bytes in a code unit in that mode. */
#define PCRE2_NL_SET 0x00008000 /* newline was set in the pattern */ #define PCRE2_NL_SET 0x00008000 /* newline was set in the pattern */
#define PCRE2_NOTEMPTY_SET 0x00010000 /* (*NOTEMPTY) used ) keep */ #define PCRE2_NOTEMPTY_SET 0x00010000 /* (*NOTEMPTY) used ) keep */
#define PCRE2_NE_ATST_SET 0x00020000 /* (*NOTEMPTY_ATSTART) used) together */ #define PCRE2_NE_ATST_SET 0x00020000 /* (*NOTEMPTY_ATSTART) used) together */
#define PCRE2_DEREF_TABLES 0x00040000 /* Release character tables. */
#define PCRE2_MODE_MASK (PCRE2_MODE8 | PCRE2_MODE16 | PCRE2_MODE32) #define PCRE2_MODE_MASK (PCRE2_MODE8 | PCRE2_MODE16 | PCRE2_MODE32)
@ -1763,6 +1764,15 @@ typedef struct {
#define UCD_CASESET(ch) GET_UCD(ch)->caseset #define UCD_CASESET(ch) GET_UCD(ch)->caseset
#define UCD_OTHERCASE(ch) ((uint32_t)((int)ch + (int)(GET_UCD(ch)->other_case))) #define UCD_OTHERCASE(ch) ((uint32_t)((int)ch + (int)(GET_UCD(ch)->other_case)))
/* Header for serialized pcre2 codes. */
typedef struct pcre2_serialized_data {
uint32_t magic;
uint32_t version;
uint32_t config;
int32_t number_of_codes;
} pcre2_serialized_data;
/* ----------------- Items that need PCRE2_CODE_UNIT_WIDTH ----------------- */ /* ----------------- Items that need PCRE2_CODE_UNIT_WIDTH ----------------- */

251
src/pcre2_serialize.c Normal file
View File

@ -0,0 +1,251 @@
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2015 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains functions for serializing and deserializing
a sequence of compiled codes. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
/* Magic number to provide a small check against being handed junk. */
#define SERIALIZED_DATA_MAGIC 0x50523253u
/* Deserialization is limited to the current PCRE version and
character width. */
#define SERIALIZED_DATA_VERSION \
((PCRE2_MAJOR) | ((PCRE2_MINOR) << 16))
#define SERIALIZED_DATA_CONFIG \
(sizeof(PCRE2_UCHAR) | ((sizeof(void*)) << 8) | ((sizeof(PCRE2_SIZE)) << 16))
/*************************************************
* Serialize compiled patterns *
*************************************************/
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_encode(const pcre2_code **codes, int32_t number_of_codes,
uint8_t **serialized_bytes, PCRE2_SIZE *serialized_size,
pcre2_general_context *gcontext)
{
uint8_t *bytes;
uint8_t *dst_bytes;
int32_t i;
PCRE2_SIZE total_size;
const pcre2_real_code *re;
const uint8_t *tables;
pcre2_serialized_data *data;
const pcre2_memctl *memctl = (gcontext != NULL) ?
&gcontext->memctl : &PRIV(default_compile_context).memctl;
if (codes == NULL || serialized_bytes == NULL || serialized_size == NULL)
return PCRE2_ERROR_NULL;
if (number_of_codes <= 0) return PCRE2_ERROR_BADDATA;
/* Compute total size. */
total_size = sizeof(pcre2_serialized_data) + tables_length;
tables = NULL;
for (i = 0; i < number_of_codes; i++)
{
if (codes[i] == NULL) return PCRE2_ERROR_NULL;
re = (const pcre2_real_code *)(codes[i]);
if (re->magic_number != MAGIC_NUMBER) return PCRE2_ERROR_BADMAGIC;
if (tables == NULL)
tables = re->tables;
else if (tables != re->tables)
return PCRE2_ERROR_MIXEDTABLES;
total_size += re->blocksize;
}
/* Initialize the byte stream. */
bytes = memctl->malloc(total_size + sizeof(pcre2_memctl), memctl->memory_data);
if (bytes == NULL) return PCRE2_ERROR_NOMEMORY;
/* The controller is stored as a hidden parameter. */
memcpy(bytes, memctl, sizeof(pcre2_memctl));
bytes += sizeof(pcre2_memctl);
data = (pcre2_serialized_data *)bytes;
data->magic = SERIALIZED_DATA_MAGIC;
data->version = SERIALIZED_DATA_VERSION;
data->config = SERIALIZED_DATA_CONFIG;
data->number_of_codes = number_of_codes;
/* Copy all compiled code data. */
dst_bytes = bytes + sizeof(pcre2_serialized_data);
memcpy(dst_bytes, tables, tables_length);
dst_bytes += tables_length;
for (i = 0; i < number_of_codes; i++)
{
re = (const pcre2_real_code *)(codes[i]);
memcpy(dst_bytes, (char *)re, re->blocksize);
dst_bytes += re->blocksize;
}
*serialized_bytes = bytes;
*serialized_size = total_size;
return number_of_codes;
}
/*************************************************
* Deserialize compiled patterns *
*************************************************/
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_decode(pcre2_code **codes, int32_t number_of_codes,
const uint8_t *bytes, pcre2_general_context *gcontext)
{
const pcre2_serialized_data *data = (const pcre2_serialized_data *)bytes;
const pcre2_memctl *memctl = (gcontext != NULL) ?
&gcontext->memctl : &PRIV(default_compile_context).memctl;
const uint8_t *src_bytes;
pcre2_real_code *src_re;
pcre2_real_code *dst_re;
uint8_t *tables;
int32_t i, j;
/* Sanity checks. */
if (data == NULL || codes == NULL) return PCRE2_ERROR_NULL;
if (number_of_codes <= 0) return PCRE2_ERROR_BADDATA;
if (data->magic != SERIALIZED_DATA_MAGIC) return PCRE2_ERROR_BADMAGIC;
if (data->version != SERIALIZED_DATA_VERSION) return PCRE2_ERROR_BADMODE;
if (data->config != SERIALIZED_DATA_CONFIG) return PCRE2_ERROR_BADMODE;
if (number_of_codes > data->number_of_codes)
number_of_codes = data->number_of_codes;
src_bytes = bytes + sizeof(pcre2_serialized_data);
/* Decode tables. The reference count for the tables is stored immediately
following them. */
tables = memctl->malloc(tables_length + sizeof(PCRE2_SIZE), memctl->memory_data);
if (tables == NULL) return PCRE2_ERROR_NOMEMORY;
memcpy(tables, src_bytes, tables_length);
*(PCRE2_SIZE *)(tables + tables_length) = number_of_codes;
src_bytes += tables_length;
/* Decode byte stream. */
for (i = 0; i < number_of_codes; i++)
{
src_re = (pcre2_real_code *)src_bytes;
/* The allocator provided by gcontext replaces the original one. */
dst_re = (pcre2_real_code *)PRIV(memctl_malloc)
(src_re->blocksize, (pcre2_memctl *)gcontext);
if (dst_re == NULL)
{
memctl->free(tables, memctl->memory_data);
for (j = 0; j < i; j++)
{
memctl->free(codes[j], memctl->memory_data);
codes[j] = NULL;
}
return PCRE2_ERROR_NOMEMORY;
}
/* The new allocator must be preserved. */
memcpy(((uint8_t *)dst_re) + sizeof(pcre2_memctl),
src_bytes + sizeof(pcre2_memctl),
src_re->blocksize - sizeof(pcre2_memctl));
/* At the moment only one table is supported. */
dst_re->tables = tables;
dst_re->executable_jit = NULL;
dst_re->flags |= PCRE2_DEREF_TABLES;
codes[i] = dst_re;
src_bytes += src_re->blocksize;
}
return number_of_codes;
}
/*************************************************
* Get the number of serialized patterns *
*************************************************/
PCRE2_EXP_DECL int32_t PCRE2_CALL_CONVENTION
pcre2_serialize_get_number_of_codes(const uint8_t *bytes)
{
const pcre2_serialized_data *data = (const pcre2_serialized_data *)bytes;
if (data == NULL) return PCRE2_ERROR_NULL;
if (data->magic != SERIALIZED_DATA_MAGIC) return PCRE2_ERROR_BADMAGIC;
if (data->version != SERIALIZED_DATA_VERSION) return PCRE2_ERROR_BADMODE;
if (data->config != SERIALIZED_DATA_CONFIG) return PCRE2_ERROR_BADMODE;
return data->number_of_codes;
}
/*************************************************
* Free the allocated stream *
*************************************************/
PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION
pcre2_serialize_free(uint8_t *bytes)
{
if (bytes != NULL)
{
pcre2_memctl *memctl = (pcre2_memctl *)(bytes - sizeof(pcre2_memctl));
memctl->free(memctl, memctl->memory_data);
}
}
/* End of pcre2_serialize.c */

View File

@ -166,6 +166,7 @@ void vms_setsymbol( char *, char *, int );
#define JUNK_OFFSET 0xdeadbeef /* For initializing ovector */ #define JUNK_OFFSET 0xdeadbeef /* For initializing ovector */
#define LOCALESIZE 32 /* Size of locale name */ #define LOCALESIZE 32 /* Size of locale name */
#define LOOPREPEAT 500000 /* Default loop count for timing */ #define LOOPREPEAT 500000 /* Default loop count for timing */
#define PATSTACKSIZE 20 /* Pattern stack for save/restore testing */
#define REPLACE_MODSIZE 96 /* Field for reading 8-bit replacement */ #define REPLACE_MODSIZE 96 /* Field for reading 8-bit replacement */
#define VERSION_SIZE 64 /* Size of buffer for the version strings */ #define VERSION_SIZE 64 /* Size of buffer for the version strings */
@ -313,6 +314,26 @@ modes, so use the form of the first that is available. */
#define PCRE2_REAL_MATCH_CONTEXT pcre2_real_match_context_32 #define PCRE2_REAL_MATCH_CONTEXT pcre2_real_match_context_32
#endif #endif
/* ------------- Structure and table for handling #-commands ------------- */
typedef struct cmdstruct {
const char *name;
int value;
} cmdstruct;
enum { CMD_FORBID_UTF, CMD_LOAD, CMD_PATTERN, CMD_PERLTEST, CMD_POP, CMD_SAVE,
CMD_SUBJECT, CMD_UNKNOWN };
static cmdstruct cmdlist[] = {
{ "forbid_utf", CMD_FORBID_UTF },
{ "load", CMD_LOAD },
{ "pattern", CMD_PATTERN },
{ "perltest", CMD_PERLTEST },
{ "pop", CMD_POP },
{ "save", CMD_SAVE },
{ "subject", CMD_SUBJECT }};
#define cmdlistcount sizeof(cmdlist)/sizeof(cmdstruct)
/* ------------- Structures and tables for handling modifiers -------------- */ /* ------------- Structures and tables for handling modifiers -------------- */
@ -367,8 +388,9 @@ either on a pattern or a data line, so they must all be distinct. */
#define CTL_MARK 0x00020000u #define CTL_MARK 0x00020000u
#define CTL_MEMORY 0x00040000u #define CTL_MEMORY 0x00040000u
#define CTL_POSIX 0x00080000u #define CTL_POSIX 0x00080000u
#define CTL_STARTCHAR 0x00100000u #define CTL_PUSH 0x00100000u
#define CTL_ZERO_TERMINATE 0x00200000u #define CTL_STARTCHAR 0x00200000u
#define CTL_ZERO_TERMINATE 0x00400000u
#define CTL_BSR_SET 0x80000000u /* This is informational */ #define CTL_BSR_SET 0x80000000u /* This is informational */
#define CTL_NL_SET 0x40000000u /* This is informational */ #define CTL_NL_SET 0x40000000u /* This is informational */
@ -426,6 +448,7 @@ typedef struct datctl { /* Structure for data line modifiers. */
/* Ids for which context to modify. */ /* Ids for which context to modify. */
enum { CTX_PAT, /* Active pattern context */ enum { CTX_PAT, /* Active pattern context */
CTX_POPPAT, /* Ditto, for a popped pattern */
CTX_DEFPAT, /* Default pattern context */ CTX_DEFPAT, /* Default pattern context */
CTX_DAT, /* Active data (match) context */ CTX_DAT, /* Active data (match) context */
CTX_DEFDAT }; /* Default data (match) context */ CTX_DEFDAT }; /* Default data (match) context */
@ -513,6 +536,7 @@ static modstruct modlist[] = {
{ "ph", MOD_DAT, MOD_OPT, PCRE2_PARTIAL_HARD, DO(options) }, { "ph", MOD_DAT, MOD_OPT, PCRE2_PARTIAL_HARD, DO(options) },
{ "posix", MOD_PAT, MOD_CTL, CTL_POSIX, PO(control) }, { "posix", MOD_PAT, MOD_CTL, CTL_POSIX, PO(control) },
{ "ps", MOD_DAT, MOD_OPT, PCRE2_PARTIAL_SOFT, DO(options) }, { "ps", MOD_DAT, MOD_OPT, PCRE2_PARTIAL_SOFT, DO(options) },
{ "push", MOD_PAT, MOD_CTL, CTL_PUSH, PO(control) },
{ "recursion_limit", MOD_CTM, MOD_INT, 0, MO(recursion_limit) }, { "recursion_limit", MOD_CTM, MOD_INT, 0, MO(recursion_limit) },
{ "replace", MOD_PND, MOD_STR, REPLACE_MODSIZE, PO(replacement) }, { "replace", MOD_PND, MOD_STR, REPLACE_MODSIZE, PO(replacement) },
{ "stackguard", MOD_PAT, MOD_INT, 0, PO(stackguard_test) }, { "stackguard", MOD_PAT, MOD_INT, 0, PO(stackguard_test) },
@ -544,6 +568,20 @@ static modstruct modlist[] = {
#define EXCLUSIVE_DAT_CONTROLS (CTL_ALLUSEDTEXT|CTL_STARTCHAR) #define EXCLUSIVE_DAT_CONTROLS (CTL_ALLUSEDTEXT|CTL_STARTCHAR)
/* Control bits that are not ignored with 'push'. */
#define PUSH_SUPPORTED_COMPILE_CONTROLS ( \
CTL_BINCODE|CTL_FULLBINCODE|CTL_HEXPAT|CTL_INFO|CTL_JITVERIFY| \
CTL_MEMORY|CTL_PUSH|CTL_BSR_SET|CTL_NL_SET)
/* Controls that apply only at compile time with 'push'. */
#define PUSH_COMPILE_ONLY_CONTROLS CTL_JITVERIFY
/* Controls that are forbidden with #pop. */
#define NOTPOP_CONTROLS (CTL_HEXPAT|CTL_POSIX|CTL_PUSH)
/* Table of single-character abbreviated modifiers. The index field is /* Table of single-character abbreviated modifiers. The index field is
initialized to -1, but the first time the modifier is encountered, it is filled initialized to -1, but the first time the modifier is encountered, it is filled
in with the index of the full entry in modlist, to save repeated searching when in with the index of the full entry in modlist, to save repeated searching when
@ -671,6 +709,9 @@ static patctl pat_patctl;
static datctl def_datctl; static datctl def_datctl;
static datctl dat_datctl; static datctl dat_datctl;
static void *patstack[PATSTACKSIZE];
static int patstacknext = 0;
#ifdef SUPPORT_PCRE2_8 #ifdef SUPPORT_PCRE2_8
static regex_t preg = { NULL, NULL, 0, 0 }; static regex_t preg = { NULL, NULL, 0, 0 };
#endif #endif
@ -928,6 +969,38 @@ are supported. */
else \ else \
pcre2_printint_32(compiled_code32,outfile,a) pcre2_printint_32(compiled_code32,outfile,a)
#define PCRE2_SERIALIZE_DECODE(r,a,b,c,d) \
if (test_mode == PCRE8_MODE) \
r = pcre2_serialize_decode_8((pcre2_code_8 **)a,b,c,G(d,8)); \
else if (test_mode == PCRE16_MODE) \
r = pcre2_serialize_decode_16((pcre2_code_16 **)a,b,c,G(d,16)); \
else \
r = pcre2_serialize_decode_32((pcre2_code_32 **)a,b,c,G(d,32))
#define PCRE2_SERIALIZE_ENCODE(r,a,b,c,d,e) \
if (test_mode == PCRE8_MODE) \
r = pcre2_serialize_encode_8((const pcre2_code_8 **)a,b,c,d,G(e,8)); \
else if (test_mode == PCRE16_MODE) \
r = pcre2_serialize_encode_16((const pcre2_code_16 **)a,b,c,d,G(e,16)); \
else \
r = pcre2_serialize_encode_32((const pcre2_code_32 **)a,b,c,d,G(e,32))
#define PCRE2_SERIALIZE_FREE(a) \
if (test_mode == PCRE8_MODE) \
pcre2_serialize_free_8(a); \
else if (test_mode == PCRE16_MODE) \
pcre2_serialize_free_16(a); \
else \
pcre2_serialize_free_32(a)
#define PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(r,a) \
if (test_mode == PCRE8_MODE) \
r = pcre2_serialize_get_number_of_codes_8(a); \
else if (test_mode == PCRE16_MODE) \
r = pcre2_serialize_get_number_of_codes_16(a); \
else \
r = pcre2_serialize_get_number_of_codes_32(a); \
#define PCRE2_SET_CALLOUT(a,b,c) \ #define PCRE2_SET_CALLOUT(a,b,c) \
if (test_mode == PCRE8_MODE) \ if (test_mode == PCRE8_MODE) \
pcre2_set_callout_8(G(a,8),(int (*)(pcre2_callout_block_8 *, void *))b,c); \ pcre2_set_callout_8(G(a,8),(int (*)(pcre2_callout_block_8 *, void *))b,c); \
@ -1302,6 +1375,30 @@ the three different cases. */
else \ else \
G(pcre2_printint_,BITTWO)(G(compiled_code,BITTWO),outfile,a) G(pcre2_printint_,BITTWO)(G(compiled_code,BITTWO),outfile,a)
#define PCRE2_SERIALIZE_DECODE(r,a,b,c,d) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \
r = G(pcre2_serialize_decode_,BITONE)((G(pcre2_code_,BITONE) **)a,b,c,G(d,BITONE)); \
else \
r = G(pcre2_serialize_decode_,BITTWO)((G(pcre2_code_,BITTWO) **)a,b,c,G(d,BITTWO))
#define PCRE2_SERIALIZE_ENCODE(r,a,b,c,d,e) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \
r = G(pcre2_serialize_encode_,BITONE)((G(const pcre2_code_,BITONE) **)a,b,c,d,G(e,BITONE)); \
else \
r = G(pcre2_serialize_encode_,BITTWO)((G(const pcre2_code_,BITTWO) **)a,b,c,d,G(e,BITTWO))
#define PCRE2_SERIALIZE_FREE(a) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \
G(pcre2_serialize_free_,BITONE)(a); \
else \
G(pcre2_serialize_free_,BITTWO)(a)
#define PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(r,a) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \
r = G(pcre2_serialize_get_number_of_codes_,BITONE)(a); \
else \
r = G(pcre2_serialize_get_number_of_codes_,BITTWO)(a)
#define PCRE2_SET_CALLOUT(a,b,c) \ #define PCRE2_SET_CALLOUT(a,b,c) \
if (test_mode == G(G(PCRE,BITONE),_MODE)) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \
G(pcre2_set_callout_,BITONE)(G(a,BITONE), \ G(pcre2_set_callout_,BITONE)(G(a,BITONE), \
@ -1510,6 +1607,13 @@ the three different cases. */
#define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_8(G(a,8)) #define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_8(G(a,8))
#define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_8(G(b,8),c,d) #define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_8(G(b,8),c,d)
#define PCRE2_PRINTINT(a) pcre2_printint_8(compiled_code8,outfile,a) #define PCRE2_PRINTINT(a) pcre2_printint_8(compiled_code8,outfile,a)
#define PCRE2_SERIALIZE_DECODE(r,a,b,c,d) \
r = pcre2_serialize_decode_8((pcre2_code_8 **)a,b,c,G(d,8))
#define PCRE2_SERIALIZE_ENCODE(r,a,b,c,d,e) \
r = pcre2_serialize_encode_8((const pcre2_code_8 **)a,b,c,d,G(e,8))
#define PCRE2_SERIALIZE_FREE(a) pcre2_serialize_free_8(a)
#define PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(r,a) \
r = pcre2_serialize_get_number_of_codes_8(a)
#define PCRE2_SET_CALLOUT(a,b,c) \ #define PCRE2_SET_CALLOUT(a,b,c) \
pcre2_set_callout_8(G(a,8),(int (*)(pcre2_callout_block_8 *, void *))b,c) pcre2_set_callout_8(G(a,8),(int (*)(pcre2_callout_block_8 *, void *))b,c)
#define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_8(G(a,8),b) #define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_8(G(a,8),b)
@ -1591,6 +1695,13 @@ the three different cases. */
#define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_16(G(a,16)) #define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_16(G(a,16))
#define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_16(G(b,16),c,d) #define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_16(G(b,16),c,d)
#define PCRE2_PRINTINT(a) pcre2_printint_16(compiled_code16,outfile,a) #define PCRE2_PRINTINT(a) pcre2_printint_16(compiled_code16,outfile,a)
#define PCRE2_SERIALIZE_DECODE(r,a,b,c,d) \
r = pcre2_serialize_decode_16((pcre2_code_16 **)a,b,c,G(d,16))
#define PCRE2_SERIALIZE_ENCODE(r,a,b,c,d,e) \
r = pcre2_serialize_encode_16((const pcre2_code_16 **)a,b,c,d,G(e,16))
#define PCRE2_SERIALIZE_FREE(a) pcre2_serialize_free_16(a)
#define PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(r,a) \
r = pcre2_serialize_get_number_of_codes_16(a)
#define PCRE2_SET_CALLOUT(a,b,c) \ #define PCRE2_SET_CALLOUT(a,b,c) \
pcre2_set_callout_16(G(a,16),(int (*)(pcre2_callout_block_16 *, void *))b,c); pcre2_set_callout_16(G(a,16),(int (*)(pcre2_callout_block_16 *, void *))b,c);
#define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_16(G(a,16),b) #define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_16(G(a,16),b)
@ -1672,6 +1783,13 @@ the three different cases. */
#define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_32(G(a,32)) #define PCRE2_MATCH_DATA_FREE(a) pcre2_match_data_free_32(G(a,32))
#define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_32(G(b,32),c,d) #define PCRE2_PATTERN_INFO(a,b,c,d) a = pcre2_pattern_info_32(G(b,32),c,d)
#define PCRE2_PRINTINT(a) pcre2_printint_32(compiled_code32,outfile,a) #define PCRE2_PRINTINT(a) pcre2_printint_32(compiled_code32,outfile,a)
#define PCRE2_SERIALIZE_DECODE(r,a,b,c,d) \
r = pcre2_serialize_decode_32((pcre2_code_32 **)a,b,c,G(d,32))
#define PCRE2_SERIALIZE_ENCODE(r,a,b,c,d,e) \
r = pcre2_serialize_encode_32((const pcre2_code_32 **)a,b,c,d,G(e,32))
#define PCRE2_SERIALIZE_FREE(a) pcre2_serialize_free_32(a)
#define PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(r,a) \
r = pcre2_serialize_get_number_of_codes_32(a)
#define PCRE2_SET_CALLOUT(a,b,c) \ #define PCRE2_SET_CALLOUT(a,b,c) \
pcre2_set_callout_32(G(a,32),(int (*)(pcre2_callout_block_32 *, void *))b,c); pcre2_set_callout_32(G(a,32),(int (*)(pcre2_callout_block_32 *, void *))b,c);
#define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_32(G(a,32),b) #define PCRE2_SET_CHARACTER_TABLES(a,b) pcre2_set_character_tables_32(G(a,32),b)
@ -2792,6 +2910,7 @@ it is allowed here and find the field that is to be changed.
Arguments: Arguments:
m the modifier list entry m the modifier list entry
ctx CTX_PAT => pattern context ctx CTX_PAT => pattern context
CTX_POPPAT => pattern context for popped pattern
CTX_DEFPAT => default pattern context CTX_DEFPAT => default pattern context
CTX_DAT => data context CTX_DAT => data context
CTX_DEFDAT => default data context CTX_DEFDAT => default data context
@ -2878,6 +2997,7 @@ modifiers that apply to contexts.
Arguments: Arguments:
p point to modifier string p point to modifier string
ctx CTX_PAT => pattern context ctx CTX_PAT => pattern context
CTX_POPPAT => pattern context for popped pattern
CTX_DEFPAT => default pattern context CTX_DEFPAT => default pattern context
CTX_DAT => data context CTX_DAT => data context
CTX_DEFDAT => default data context CTX_DEFDAT => default data context
@ -2902,11 +3022,8 @@ for (;;)
int index; int index;
char *endptr; char *endptr;
/* Skip white space and commas; after a comma we have passed the first /* Skip white space and commas. */
item. */
while (isspace(*p)) p++;
if (*p == ',') first = FALSE;
while (isspace(*p) || *p == ',') p++; while (isspace(*p) || *p == ',') p++;
if (*p == 0) break; if (*p == 0) break;
@ -3163,6 +3280,17 @@ for (;;)
} }
p = pp; p = pp;
first = FALSE;
if (ctx == CTX_POPPAT &&
(pctl->options != 0 ||
pctl->tables_id != 0 ||
pctl->locale[0] != 0 ||
(pctl->control & NOTPOP_CONTROLS) != 0))
{
fprintf(outfile, "** '%s' is not valid here\n", m->name);
return FALSE;
}
} }
return TRUE; return TRUE;
@ -3246,7 +3374,7 @@ Returns: nothing
static void static void
show_controls(uint32_t controls, const char *before) show_controls(uint32_t controls, const char *before)
{ {
fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
before, before,
((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "", ((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "",
((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "", ((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "",
@ -3268,6 +3396,7 @@ fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
((controls & CTL_MARK) != 0)? " mark" : "", ((controls & CTL_MARK) != 0)? " mark" : "",
((controls & CTL_MEMORY) != 0)? " memory" : "", ((controls & CTL_MEMORY) != 0)? " memory" : "",
((controls & CTL_POSIX) != 0)? " posix" : "", ((controls & CTL_POSIX) != 0)? " posix" : "",
((controls & CTL_PUSH) != 0)? " push" : "",
((controls & CTL_STARTCHAR) != 0)? " startchar" : "", ((controls & CTL_STARTCHAR) != 0)? " startchar" : "",
((controls & CTL_ZERO_TERMINATE) != 0)? " zero_terminate" : ""); ((controls & CTL_ZERO_TERMINATE) != 0)? " zero_terminate" : "");
} }
@ -3347,6 +3476,40 @@ fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s",
/*************************************************
* Show memory usage info for a pattern *
*************************************************/
static void
show_memory_info(void)
{
uint32_t name_count, name_entry_size;
size_t size, cblock_size;
#ifdef SUPPORT_PCRE2_8
if (test_mode == 8) cblock_size = sizeof(pcre2_real_code_8);
#endif
#ifdef SUPPORT_PCRE2_16
if (test_mode == 16) cblock_size = sizeof(pcre2_real_code_16);
#endif
#ifdef SUPPORT_PCRE2_32
if (test_mode == 32) cblock_size = sizeof(pcre2_real_code_32);
#endif
(void)pattern_info(PCRE2_INFO_SIZE, &size, FALSE);
(void)pattern_info(PCRE2_INFO_NAMECOUNT, &name_count, FALSE);
(void)pattern_info(PCRE2_INFO_NAMEENTRYSIZE, &name_entry_size, FALSE);
fprintf(outfile, "Memory allocation (code space): %d\n",
(int)(size - name_count*name_entry_size*code_unit_size - cblock_size));
if (pat_patctl.jit != 0)
{
(void)pattern_info(PCRE2_INFO_JITSIZE, &size, FALSE);
fprintf(outfile, "Memory allocation (JIT code): %d\n", (int)size);
}
}
/************************************************* /*************************************************
* Show information about a pattern * * Show information about a pattern *
*************************************************/ *************************************************/
@ -3624,12 +3787,79 @@ return PR_OK;
/*************************************************
* Handle serialization error *
*************************************************/
/* Print an error message after a serialization failure.
Arguments:
rc the error code
msg an initial message for what failed
Returns: nothing
*/
static void
serial_error(int rc, const char *msg)
{
fprintf(outfile, "%s failed: error %d: ", msg, rc);
PCRE2_GET_ERROR_MESSAGE(rc, rc, pbuffer);
PCHARSV(CASTVAR(void *, pbuffer), 0, rc, FALSE, outfile);
fprintf(outfile, "\n");
}
/*************************************************
* Open file for save/load commands *
*************************************************/
/* This function decodes the file name and opens the file.
Arguments:
buffptr point after the #command
mode open mode
fptr points to the FILE variable
Returns: PR_OK or PR_ABEND
*/
static int
open_file(uint8_t *buffptr, const char *mode, FILE **fptr)
{
char *endf;
char *filename = (char *)buffptr;
while (isspace(*filename)) filename++;
endf = filename + strlen8(filename);
while (endf > filename && isspace(endf[-1])) endf--;
if (endf == filename)
{
fprintf(outfile, "** File name expected after #save\n");
return PR_ABEND;
}
*endf = 0;
*fptr = fopen((const char *)filename, mode);
if (*fptr == NULL)
{
fprintf(outfile, "** Failed to open '%s'\n", filename);
return PR_ABEND;
}
return PR_OK;
}
/************************************************* /*************************************************
* Process command line * * Process command line *
*************************************************/ *************************************************/
/* This function is called for lines beginning with # and a character that is /* This function is called for lines beginning with # and a character that is
not ! or whitespace, when encountered between tests. The line is in buffer. not ! or whitespace, when encountered between tests, which means that there is
no compiled pattern (compiled_code is NULL). The line is in buffer.
Arguments: none Arguments: none
@ -3641,33 +3871,176 @@ Returns: PR_OK continue processing next line
static int static int
process_command(void) process_command(void)
{ {
FILE *f;
PCRE2_SIZE serial_size;
size_t i;
int rc, cmd, cmdlen;
const char *cmdname;
uint8_t *argptr, *serial;
if (restrict_for_perl_test) if (restrict_for_perl_test)
{ {
fprintf(outfile, "** #-commands are not allowed after #perltest\n"); fprintf(outfile, "** #-commands are not allowed after #perltest\n");
return PR_ABEND; return PR_ABEND;
} }
if (strncmp((char *)buffer, "#forbid_utf", 11) == 0 && isspace(buffer[11])) cmd = CMD_UNKNOWN;
cmdlen = 0;
for (i = 0; i < cmdlistcount; i++)
{ {
forbid_utf = PCRE2_NEVER_UTF|PCRE2_NEVER_UCP; cmdname = cmdlist[i].name;
cmdlen = strlen(cmdname);
if (strncmp((char *)(buffer+1), cmdname, cmdlen) == 0 &&
isspace(buffer[cmdlen+1]))
{
cmd = cmdlist[i].value;
break;
} }
else if (strncmp((char *)buffer, "#pattern", 8) == 0 && isspace(buffer[8])) }
argptr = buffer + cmdlen + 1;
switch(cmd)
{ {
(void)decode_modifiers(buffer + 8, CTX_DEFPAT, &def_patctl, NULL); case CMD_UNKNOWN:
fprintf(outfile, "** Unknown command: %s", buffer);
break;
case CMD_FORBID_UTF:
forbid_utf = PCRE2_NEVER_UTF|PCRE2_NEVER_UCP;
break;
case CMD_PERLTEST:
restrict_for_perl_test = TRUE;
break;
/* Set default pattern modifiers */
case CMD_PATTERN:
(void)decode_modifiers(argptr, CTX_DEFPAT, &def_patctl, NULL);
if (def_patctl.jit == 0 && (def_patctl.control & CTL_JITVERIFY) != 0) if (def_patctl.jit == 0 && (def_patctl.control & CTL_JITVERIFY) != 0)
def_patctl.jit = 7; def_patctl.jit = 7;
} break;
else if (strncmp((char *)buffer, "#perltest", 9) == 0 && isspace(buffer[9]))
/* Set default subject modifiers */
case CMD_SUBJECT:
(void)decode_modifiers(argptr, CTX_DEFDAT, NULL, &def_datctl);
break;
/* Pop a compiled pattern off the stack. Modifiers that do not affect the
compiled pattern (e.g. to give information) are permitted. The default
pattern modifiers are ignored. */
case CMD_POP:
if (patstacknext <= 0)
{ {
restrict_for_perl_test = TRUE; fprintf(outfile, "** Can't pop off an empty stack\n");
return PR_SKIP;
} }
else if (strncmp((char *)buffer, "#subject", 8) == 0 && isspace(buffer[8])) memset(&pat_patctl, 0, sizeof(patctl)); /* Completely unset */
if (!decode_modifiers(argptr, CTX_POPPAT, &pat_patctl, NULL))
return PR_SKIP;
SET(compiled_code, patstack[--patstacknext]);
if (pat_patctl.jit != 0)
{ {
(void)decode_modifiers(buffer + 8, CTX_DEFDAT, NULL, &def_datctl); PCRE2_JIT_COMPILE(compiled_code, pat_patctl.jit);
} }
else if ((pat_patctl.control & CTL_MEMORY) != 0) show_memory_info();
if ((pat_patctl.control & CTL_ANYINFO) != 0)
{ {
fprintf(outfile, "** Unknown command: %s", buffer); rc = show_pattern_info();
if (rc != PR_OK) return rc;
}
break;
/* Save the stack of compiled patterns to a file, then empty the stack. */
case CMD_SAVE:
if (patstacknext <= 0)
{
fprintf(outfile, "** No stacked patterns to save\n");
return PR_OK;
}
rc = open_file(argptr+1, OUTPUT_MODE, &f);
if (rc != PR_OK) return rc;
PCRE2_SERIALIZE_ENCODE(rc, patstack, patstacknext, &serial, &serial_size,
general_context);
if (rc < 0)
{
serial_error(rc, "Serialization");
break;
}
/* Write the length at the start of the file to make it straightforward to
get the right memory when re-loading. This saves having to read the file size
in different operating systems. To allow for different endianness (even
though reloading with the opposite endianness does not work), write the
length byte-by-byte. */
for (i = 0; i < 4; i++) fputc((serial_size >> (i*8)) & 255, f);
if (fwrite(serial, 1, serial_size, f) != serial_size)
{
fprintf(outfile, "** Wrong return from fwrite()\n");
return PR_ABEND;
}
fclose(f);
PCRE2_SERIALIZE_FREE(serial);
while(patstacknext > 0)
{
SET(compiled_code, patstack[--patstacknext]);
SUB1(pcre2_code_free, compiled_code);
}
SET(compiled_code, NULL);
break;
/* Load a set of compiled patterns from a file onto the stack */
case CMD_LOAD:
rc = open_file(argptr+1, INPUT_MODE, &f);
if (rc != PR_OK) return rc;
serial_size = 0;
for (i = 0; i < 4; i++) serial_size |= fgetc(f) << (i*8);
serial = malloc(serial_size);
if (serial == NULL)
{
fprintf(outfile, "** Failed to get memory (size %ld) for #load\n",
serial_size);
return PR_ABEND;
}
if (fread(serial, 1, serial_size, f) != serial_size)
{
fprintf(outfile, "** Wrong return from fread()\n");
return PR_ABEND;
}
fclose(f);
PCRE2_SERIALIZE_GET_NUMBER_OF_CODES(rc, serial);
if (rc < 0) serial_error(rc, "Get number of codes"); else
{
if (rc + patstacknext > PATSTACKSIZE)
{
fprintf(outfile, "** Not enough space on pattern stack for %d pattern%s\n",
rc, (rc == 1)? "" : "s");
rc = PATSTACKSIZE - patstacknext;
fprintf(outfile, "** Decoding %d pattern%s\n", rc,
(rc == 1)? "" : "s");
}
PCRE2_SERIALIZE_DECODE(rc, patstack + patstacknext, rc, serial,
general_context);
if (rc < 0) serial_error(rc, "Deserialization");
else patstacknext += rc;
}
free(serial);
break;
} }
return PR_OK; return PR_OK;
@ -3750,6 +4123,14 @@ if (pat_patctl.jit == 0 &&
(pat_patctl.control & (CTL_JITVERIFY|CTL_JITFAST)) != 0) (pat_patctl.control & (CTL_JITVERIFY|CTL_JITFAST)) != 0)
pat_patctl.jit = 7; pat_patctl.jit = 7;
/* POSIX and 'push' do not play together. */
if ((pat_patctl.control & (CTL_POSIX|CTL_PUSH)) == (CTL_POSIX|CTL_PUSH))
{
fprintf(outfile, "** The POSIX interface is incompatible with 'push'\n");
return PR_ABEND;
}
/* Now copy the pattern to pbuffer8 for use in 8-bit testing and for reflecting /* Now copy the pattern to pbuffer8 for use in 8-bit testing and for reflecting
in callouts. Convert to binary if required. */ in callouts. Convert to binary if required. */
@ -3897,8 +4278,31 @@ if ((pat_patctl.control & CTL_POSIX) != 0)
#endif /* SUPPORT_PCRE2_8 */ #endif /* SUPPORT_PCRE2_8 */
} }
/* Handle compiling via the native interface, converting the input in non-8-bit /* Handle compiling via the native interface. Controls that act later are
modes. */ ignored with "push". Replacements are locked out. */
if ((pat_patctl.control & CTL_PUSH) != 0)
{
if (pat_patctl.replacement[0] != 0)
{
fprintf(outfile, "** Replacement text is not supported with 'push'.\n");
return PR_OK;
}
if ((pat_patctl.control & ~PUSH_SUPPORTED_COMPILE_CONTROLS) != 0)
{
show_controls(pat_patctl.control & ~PUSH_SUPPORTED_COMPILE_CONTROLS,
"** Ignored when compiled pattern is stacked with 'push':");
fprintf(outfile, "\n");
}
if ((pat_patctl.control & PUSH_COMPILE_ONLY_CONTROLS) != 0)
{
show_controls(pat_patctl.control & PUSH_COMPILE_ONLY_CONTROLS,
"** Applies only to compile when pattern is stacked with 'push':");
fprintf(outfile, "\n");
}
}
/* Convert the input in non-8-bit modes. */
#ifdef SUPPORT_PCRE2_8 #ifdef SUPPORT_PCRE2_8
if (test_mode == PCRE8_MODE) errorcode = 0; if (test_mode == PCRE8_MODE) errorcode = 0;
@ -4017,39 +4421,27 @@ if (pat_patctl.jit != 0)
/* Output code size and other information if requested. */ /* Output code size and other information if requested. */
if ((pat_patctl.control & CTL_MEMORY) != 0) if ((pat_patctl.control & CTL_MEMORY) != 0) show_memory_info();
{
uint32_t name_count, name_entry_size;
size_t size, cblock_size;
#ifdef SUPPORT_PCRE2_8
if (test_mode == 8) cblock_size = sizeof(pcre2_real_code_8);
#endif
#ifdef SUPPORT_PCRE2_16
if (test_mode == 16) cblock_size = sizeof(pcre2_real_code_16);
#endif
#ifdef SUPPORT_PCRE2_32
if (test_mode == 32) cblock_size = sizeof(pcre2_real_code_32);
#endif
(void)pattern_info(PCRE2_INFO_SIZE, &size, FALSE);
(void)pattern_info(PCRE2_INFO_NAMECOUNT, &name_count, FALSE);
(void)pattern_info(PCRE2_INFO_NAMEENTRYSIZE, &name_entry_size, FALSE);
fprintf(outfile, "Memory allocation (code space): %d\n",
(int)(size - name_count*name_entry_size*code_unit_size - cblock_size));
if (pat_patctl.jit != 0)
{
(void)pattern_info(PCRE2_INFO_JITSIZE, &size, FALSE);
fprintf(outfile, "Memory allocation (JIT code): %d\n", (int)size);
}
}
if ((pat_patctl.control & CTL_ANYINFO) != 0) if ((pat_patctl.control & CTL_ANYINFO) != 0)
{ {
int rc = show_pattern_info(); int rc = show_pattern_info();
if (rc != PR_OK) return rc; if (rc != PR_OK) return rc;
} }
/* The "push" control requests that the compiled pattern be remembered on a
stack. This is mainly for testing the serialization functionality. */
if ((pat_patctl.control & CTL_PUSH) != 0)
{
if (patstacknext >= PATSTACKSIZE)
{
fprintf(outfile, "** Too many pushed patterns (max %d)\n", PATSTACKSIZE);
return PR_ABEND;
}
patstack[patstacknext++] = PTR(compiled_code);
SET(compiled_code, NULL);
}
return PR_OK; return PR_OK;
} }
@ -6253,7 +6645,7 @@ if (argc > 1 && strcmp(argv[op], "-") != 0)
infile = fopen(argv[op], INPUT_MODE); infile = fopen(argv[op], INPUT_MODE);
if (infile == NULL) if (infile == NULL)
{ {
printf("** Failed to open %s\n", argv[op]); printf("** Failed to open '%s'\n", argv[op]);
yield = 1; yield = 1;
goto EXIT; goto EXIT;
} }
@ -6264,7 +6656,7 @@ if (argc > 2)
outfile = fopen(argv[op+1], OUTPUT_MODE); outfile = fopen(argv[op+1], OUTPUT_MODE);
if (outfile == NULL) if (outfile == NULL)
{ {
printf("** Failed to open %s\n", argv[op+1]); printf("** Failed to open '%s'\n", argv[op+1]);
yield = 1; yield = 1;
goto EXIT; goto EXIT;
} }
@ -6399,6 +6791,12 @@ free((void *)locale_tables);
PCRE2_MATCH_DATA_FREE(match_data); PCRE2_MATCH_DATA_FREE(match_data);
SUB1(pcre2_code_free, compiled_code); SUB1(pcre2_code_free, compiled_code);
while(patstacknext-- > 0)
{
SET(compiled_code, patstack[patstacknext]);
SUB1(pcre2_code_free, compiled_code);
}
PCRE2_JIT_FREE_UNUSED_MEMORY(general_context); PCRE2_JIT_FREE_UNUSED_MEMORY(general_context);
if (jit_stack != NULL) if (jit_stack != NULL)
{ {

View File

@ -6,4 +6,4 @@
/a*/I /a*/I
# End of testinput14 # End of testinput15

19
testdata/testinput16 vendored
View File

@ -161,7 +161,7 @@
# match to happen via the interpreter, but for fast JIT invalid options are # match to happen via the interpreter, but for fast JIT invalid options are
# ignored, so an unanchored match happens. # ignored, so an unanchored match happens.
/abcd/jit /abcd/
abcd\=anchored abcd\=anchored
fail abcd\=anchored fail abcd\=anchored
@ -169,4 +169,21 @@
abcd\=anchored abcd\=anchored
succeed abcd\=anchored succeed abcd\=anchored
# Push/pop does not lose the JIT information, though jitverify applies only to
# compilation, but serializing (save/load) discards JIT data completely.
/^abc\Kdef/info,push
#pop jitverify
abcdef
/^abc\Kdef/info,push
#save testsaved1
#load testsaved1
#pop jitverify
abcdef
#load testsaved1
#pop jit,jitverify
abcdef
# End of testinput16 # End of testinput16

62
testdata/testinput19 vendored Normal file
View File

@ -0,0 +1,62 @@
# This set of tests exercises the serialization/deserialization functions in
# the library. It does not use UTF or JIT.
#forbid_utf
# Compile several patterns, push them onto the stack, and then write them
# all to a file.
#pattern push
/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT))
(?(DEFINE)
(?<NAME_PAT>[a-z]+)
(?<ADDRESS_PAT>\d+)
)/x
/^(?:((.)(?1)\2|)|((.)(?3)\4|.))$/i
#save testsaved1
# Do it again for some more patterns.
/(*MARK:A)(*SKIP:B)(C|X)/mark
/(?:(?<n>foo)|(?<n>bar))\k<n>/dupnames
#save testsaved2
#pattern -push
# Reload the patterns, then pop them one by one and check them.
#load testsaved1
#load testsaved2
#pop info
foofoo
barbar
#pop mark
C
D
#pop
AmanaplanacanalPanama
#pop info
metcalfe 33
# Check for an error when different tables are used.
/abc/push,tables=1
/xyz/push,tables=2
#save testsaved1
#pop
xyz
#pop
abc
#pop should give an error
pqr
# End of testinput19

View File

@ -14,4 +14,4 @@ Capturing subpattern count = 0
May match empty string May match empty string
Subject length lower bound = 0 Subject length lower bound = 0
# End of testinput14 # End of testinput15

34
testdata/testoutput16 vendored
View File

@ -310,7 +310,7 @@ Failed: error -46: JIT stack limit reached
# match to happen via the interpreter, but for fast JIT invalid options are # match to happen via the interpreter, but for fast JIT invalid options are
# ignored, so an unanchored match happens. # ignored, so an unanchored match happens.
/abcd/jit /abcd/
abcd\=anchored abcd\=anchored
0: abcd 0: abcd
fail abcd\=anchored fail abcd\=anchored
@ -322,4 +322,36 @@ No match
succeed abcd\=anchored succeed abcd\=anchored
0: abcd (JIT) 0: abcd (JIT)
# Push/pop does not lose the JIT information, though jitverify applies only to
# compilation, but serializing (save/load) discards JIT data completely.
/^abc\Kdef/info,push
** Applied only to compile when pattern is stacked with 'push': jitverify
Capturing subpattern count = 0
Compile options: <none>
Overall options: anchored
Subject length lower bound = 6
JIT compilation was successful
#pop jitverify
abcdef
0: def (JIT)
/^abc\Kdef/info,push
** Applied only to compile when pattern is stacked with 'push': jitverify
Capturing subpattern count = 0
Compile options: <none>
Overall options: anchored
Subject length lower bound = 6
JIT compilation was successful
#save testsaved1
#load testsaved1
#pop jitverify
abcdef
0: def
#load testsaved1
#pop jit,jitverify
abcdef
0: def (JIT)
# End of testinput16 # End of testinput16

100
testdata/testoutput19 vendored Normal file
View File

@ -0,0 +1,100 @@
# This set of tests exercises the serialization/deserialization functions in
# the library. It does not use UTF or JIT.
#forbid_utf
# Compile several patterns, push them onto the stack, and then write them
# all to a file.
#pattern push
/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT))
(?(DEFINE)
(?<NAME_PAT>[a-z]+)
(?<ADDRESS_PAT>\d+)
)/x
/^(?:((.)(?1)\2|)|((.)(?3)\4|.))$/i
#save testsaved1
# Do it again for some more patterns.
/(*MARK:A)(*SKIP:B)(C|X)/mark
** Ignored when compiled pattern is stacked with 'push': mark
/(?:(?<n>foo)|(?<n>bar))\k<n>/dupnames
#save testsaved2
#pattern -push
# Reload the patterns, then pop them one by one and check them.
#load testsaved1
#load testsaved2
#pop info
Capturing subpattern count = 2
Max back reference = 2
Named capturing subpatterns:
n 1
n 2
Options: dupnames
Starting code units: b f
Subject length lower bound = 6
foofoo
0: foofoo
1: foo
barbar
0: barbar
1: <unset>
2: bar
#pop mark
C
0: C
1: C
MK: A
D
No match, mark = A
#pop
AmanaplanacanalPanama
0: AmanaplanacanalPanama
1: <unset>
2: <unset>
3: AmanaplanacanalPanama
4: A
#pop info
Capturing subpattern count = 4
Named capturing subpatterns:
ADDR 2
ADDRESS_PAT 4
NAME 1
NAME_PAT 3
Options: extended
Subject length lower bound = 3
metcalfe 33
0: metcalfe 33
1: metcalfe
2: 33
# Check for an error when different tables are used.
/abc/push,tables=1
/xyz/push,tables=2
#save testsaved1
Serialization failed: error -30: patterns do not all use the same character tables
#pop
xyz
0: xyz
#pop
abc
0: abc
#pop should give an error
** Can't pop off an empty stack
pqr
# End of testinput19