From 4b9f9085b1de8f57a81a00547b4f99f9a8f78e0f Mon Sep 17 00:00:00 2001 From: Nicholas Wilson Date: Sun, 5 Jan 2025 21:20:14 +0000 Subject: [PATCH] WIP for some real EBCDIC tests --- .github/workflows/dev.yml | 21 + CMakeLists.txt | 64 +- Makefile.am | 17 +- README | 25 +- RunTest | 132 ++- config-cmake.h.in | 1 + configure.ac | 36 +- doc/html/README.txt | 21 +- doc/html/pcre2build.html | 39 +- doc/html/pcre2test.html | 2 + doc/pcre2.txt | 161 +-- doc/pcre2build.3 | 37 +- doc/pcre2test.1 | 2 + doc/pcre2test.txt | 1187 ++++++++++++----------- maint/PrepareRelease | 2 + maint/manifest-tarball | 2 + src/config.h.generic | 7 +- src/pcre2_chartables.c.ebcdic-1047-nl15 | 196 ++++ src/pcre2_chartables.c.ebcdic-1047-nl25 | 196 ++++ src/pcre2_compile.c | 125 ++- src/pcre2_convert.c | 6 + src/pcre2_dftables.c | 48 +- src/pcre2_error.c | 7 +- src/pcre2_internal.h | 321 ++++-- src/pcre2_maketables.c | 54 +- src/pcre2_tables.c | 71 +- src/pcre2test.c | 187 ++-- testdata/testinputEBC | 118 +-- testdata/testoutputEBC | 154 ++- 29 files changed, 2108 insertions(+), 1131 deletions(-) create mode 100644 src/pcre2_chartables.c.ebcdic-1047-nl15 create mode 100644 src/pcre2_chartables.c.ebcdic-1047-nl25 diff --git a/.github/workflows/dev.yml b/.github/workflows/dev.yml index 13c75a5dc..c01c7d2f8 100644 --- a/.github/workflows/dev.yml +++ b/.github/workflows/dev.yml @@ -337,6 +337,27 @@ jobs: - name: Test run: bazelisk test //... --enable_runfiles --incompatible_strict_action_env --test_output=all + ebcdic: + # Tests the full support for EBCDIC on a non-EBCDIC platform, using a + # hardcoded EBCDIC-1047 codepage. + name: EBCDIC + runs-on: ubuntu-24.04 + steps: + - name: Checkout + uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 + with: + submodules: true + + - name: Configure + # TODO: Add the new CFLAGS_GCC when merging with the other PR + run: cmake -DPCRE2_SUPPORT_JIT=OFF -DPCRE2_SUPPORT_UNICODE=OFF -DPCRE2_EBCDIC=ON -DPCRE2_EBCDIC_IGNORING_COMPILER=ON -DPCRE2_DEBUG=ON -DCMAKE_COMPILE_WARNING_AS_ERROR=ON -DCMAKE_BUILD_TYPE=Release -B build + + - name: Build + run: cd build && make -j3 + + - name: Test + run: cd build && ../RunTest + heron: # Job to verify that the tasks performed by PrepareRelease have been done. It is # the committer's responsibility (currently) to run PrepareRelease themselves when diff --git a/CMakeLists.txt b/CMakeLists.txt index 9e9161743..39fe7c237 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -265,6 +265,10 @@ set( set(PCRE2_EBCDIC_NL25 OFF CACHE BOOL "Use 0x25 as EBCDIC NL character instead of 0x15; implies EBCDIC.") +set(PCRE2_EBCDIC_IGNORING_COMPILER OFF CACHE BOOL "Force EBCDIC 1047 using numeric literals rather than C character literals; implies EBCDIC.") + +option(PCRE2_REBUILD_CHARTABLES "Rebuild char tables" OFF) + set( PCRE2_LINK_SIZE "2" @@ -572,13 +576,42 @@ if(NEWLINE_DEFAULT STREQUAL "") ) endif() +set(REBUILD_CHARTABLES OFF) +if(PCRE2_REBUILD_CHARTABLES) + set(REBUILD_CHARTABLES ON) +endif() + +set(EBCDIC OFF) if(PCRE2_EBCDIC) - set(EBCDIC 1) + set(EBCDIC ON) endif() if(PCRE2_EBCDIC_NL25) - set(EBCDIC 1) - set(EBCDIC_NL25 1) + set(EBCDIC ON) + set(EBCDIC_NL25 ON) +endif() + +if(PCRE2_EBCDIC_IGNORING_COMPILER) + set(EBCDIC ON) + set(EBCDIC_IGNORING_COMPILER ON) +endif() + +# Make sure that if EBCDIC is set (without EBCDIC_IGNORING_COMPILER), then +# REBUILD_CHARTABLES is also enabled. +# Also check that UTF support is not requested, because PCRE2 cannot handle +# EBCDIC and UTF in the same build. To do so it would need to use different +# character constants depending on the mode. +# Also, EBCDIC cannot be used with 16-bit and 32-bit libraries. +if(EBCDIC) + if(NOT EBCDIC_IGNORING_COMPILER) + set(REBUILD_CHARTABLES ON) + endif() + if(PCRE2_SUPPORT_UNICODE) + message(FATAL_ERROR "Support for EBCDIC and Unicode cannot be enabled at the same time") + endif() + if(PCRE2_BUILD_PCRE2_16 OR PCRE2_BUILD_PCRE2_32) + message(FATAL_ERROR "EBCDIC support is available only for the 8-bit library") + endif() endif() # Output files @@ -652,8 +685,7 @@ endif() # Character table generation -option(PCRE2_REBUILD_CHARTABLES "Rebuild char tables" OFF) -if(PCRE2_REBUILD_CHARTABLES) +if(REBUILD_CHARTABLES) add_executable(pcre2_dftables src/pcre2_dftables.c) add_custom_command( OUTPUT ${PROJECT_BINARY_DIR}/pcre2_chartables.c @@ -663,8 +695,12 @@ if(PCRE2_REBUILD_CHARTABLES) COMMENT "Generating character tables (pcre2_chartables.c) for current locale" VERBATIM ) -else() +elseif(NOT PCRE2_EBCDIC) configure_file(${PROJECT_SOURCE_DIR}/src/pcre2_chartables.c.dist ${PROJECT_BINARY_DIR}/pcre2_chartables.c COPYONLY) +elseif(PCRE2_EBCDIC_NL25) + configure_file(${PROJECT_SOURCE_DIR}/src/pcre2_chartables.c.ebcdic-1047-nl25 ${PROJECT_BINARY_DIR}/pcre2_chartables.c COPYONLY) +else() + configure_file(${PROJECT_SOURCE_DIR}/src/pcre2_chartables.c.ebcdic-1047-nl15 ${PROJECT_BINARY_DIR}/pcre2_chartables.c COPYONLY) endif() # Source code @@ -1342,9 +1378,19 @@ if(PCRE2_SHOW_REPORT) message(STATUS " Newline char/sequence ............. : ${PCRE2_NEWLINE}") message(STATUS " \\R matches only ANYCRLF ........... : ${PCRE2_SUPPORT_BSR_ANYCRLF}") message(STATUS " \\C is disabled .................... : ${PCRE2_NEVER_BACKSLASH_C}") - message(STATUS " EBCDIC coding ..................... : ${PCRE2_EBCDIC}") - message(STATUS " EBCDIC coding with NL=0x25 ........ : ${PCRE2_EBCDIC_NL25}") - message(STATUS " Rebuild char tables ............... : ${PCRE2_REBUILD_CHARTABLES}") + + if(NOT EBCDIC) + set(EBCDIC_NL_CODE "n/a") + elseif(EBCDIC_NL25) + set(EBCDIC_NL_CODE "0x25") + else() + set(EBCDIC_NL_CODE "0x15") + endif() + message(STATUS " EBCDIC coding ..................... : ${EBCDIC}") + message(STATUS " EBCDIC code for NL ................ : ${EBCDIC_NL_CODE}") + message(STATUS " EBCDIC coding ignoring compiler ... : ${PCRE2_EBCDIC_IGNORING_COMPILER}") + message(STATUS " Rebuild char tables ............... : ${REBUILD_CHARTABLES}") + message(STATUS " Internal link size ................ : ${PCRE2_LINK_SIZE}") message(STATUS " Maximum variable lookbehind ....... : ${PCRE2_MAX_VARLOOKBEHIND}") message(STATUS " Parentheses nest limit ............ : ${PCRE2_PARENS_NEST_LIMIT}") diff --git a/Makefile.am b/Makefile.am index 8aaa0cc5b..9510962fe 100644 --- a/Makefile.am +++ b/Makefile.am @@ -362,9 +362,21 @@ src/pcre2_chartables.c: pcre2_dftables$(EXEEXT) rm -f $@ ./pcre2_dftables$(EXEEXT) $@ else +if WITH_EBCDIC +if WITH_EBCDIC_NL25 +src/pcre2_chartables.c: $(srcdir)/src/pcre2_chartables.c.ebcdic-1047-nl25 + rm -f $@ + $(LN_S) $(abs_srcdir)/src/pcre2_chartables.c.ebcdic-1047-nl25 $(abs_builddir)/src/pcre2_chartables.c +else # WITH_EBCDIC_NL25 +src/pcre2_chartables.c: $(srcdir)/src/pcre2_chartables.c.ebcdic-1047-nl15 + rm -f $@ + $(LN_S) $(abs_srcdir)/src/pcre2_chartables.c.ebcdic-1047-nl15 $(abs_builddir)/src/pcre2_chartables.c +endif # WITH_EBCDIC_NL25 +else # WITH_EBCDIC src/pcre2_chartables.c: $(srcdir)/src/pcre2_chartables.c.dist rm -f $@ $(LN_S) $(abs_srcdir)/src/pcre2_chartables.c.dist $(abs_builddir)/src/pcre2_chartables.c +endif # WITH_EBCDIC endif # WITH_REBUILD_CHARTABLES BUILT_SOURCES = src/pcre2_chartables.c @@ -460,7 +472,10 @@ endif # WITH_PCRE2_32 # The pcre2_chartables.c.dist file is the default version of # pcre2_chartables.c, used unless --enable-rebuild-chartables is specified. -EXTRA_DIST += src/pcre2_chartables.c.dist +EXTRA_DIST += \ + src/pcre2_chartables.c.dist \ + src/pcre2_chartables.c.ebcdic-1047-nl15 \ + src/pcre2_chartables.c.ebcdic-1047-nl25 CLEANFILES += src/pcre2_chartables.c # The JIT compiler lives in a separate directory, but its files are #included diff --git a/README b/README index 5a50f7f11..ce335c83c 100644 --- a/README +++ b/README @@ -309,11 +309,22 @@ library. They are also documented in the pcre2build man page. --enable-ebcdic --disable-unicode - This automatically implies --enable-rebuild-chartables (see above). However, - when PCRE2 is built this way, it always operates in EBCDIC. It cannot support - both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, - which specifies that the code value for the EBCDIC NL character is 0x25 - instead of the default 0x15. + This automatically implies --enable-rebuild-chartables (see above), in order + to ensure that you have the correct default character tables for your system's + codepage. There is an exception when you set --enable-ebcdic-ignoring-compiler + (see below), which allows using a default set of EBCDIC 1047 character tables + rather than forcing use of --enable-rebuild-chartables. + + When PCRE2 is built with EBCDIC support, it always operates in EBCDIC. It + cannot support both EBCDIC and ASCII or UTF-8/16/32. + + There is a second option, --enable-ebcdic-nl25, which specifies that the code + value for the EBCDIC NL character is 0x25 instead of the default 0x15. + + There is a third option, --enable-ebcdic-ignoring-compiler, which disregards + the compiler's codepage for determining the numeric value of C character + constants such as 'z', and instead forces PCRE2 to use numeric constants for + the EBCDIC 1047 codepage instead. . If you specify --enable-debug, additional debugging code is included in the build. This option is intended for use by the PCRE2 maintainers. @@ -822,6 +833,10 @@ The distribution should contain the files listed below. src/pcre2_chartables.c.dist a default set of character tables that assume ASCII coding; unless --enable-rebuild-chartables is specified, used by copying to pcre2_chartables.c + src/pcre2_chartables.c.ebcdic-1047-{nl15,nl25} a default set of character + tables for EBCDIC 1047; used if + --enable-ebcdic-ignoring-compiler is specified + without --enable-rebuild-chartables src/pcre2posix.c ) src/pcre2_auto_possess.c ) diff --git a/RunTest b/RunTest index dafef3e23..be910d6c3 100755 --- a/RunTest +++ b/RunTest @@ -45,15 +45,9 @@ # very much more stack than normal. In environments where the stack can be # set at runtime, -bigstack sets a gigantic stack. # -# There are two special cases where only one argument is allowed: -# -# If the first and only argument is "ebcdic", the script runs the special -# EBCDIC test that can be useful for checking certain EBCDIC features, even -# when run in an ASCII environment. PCRE2 must be built with EBCDIC support for -# this test to be run. -# -# If the script is obeyed as "RunTest list", a list of available tests is -# output, but none of them are run. +# Special cases where only one argument is allowed: +# - If the script is invoked as "RunTest list", a list of available tests is +# output, but none of them are run. ############################################################################### # Define test titles in variables so that they can be output as a list. Some @@ -92,6 +86,7 @@ title26="Test 26: Unicode property tests (compatible with Perl >= 5.38)" title27="Test 27: Auto-generated unicode property tests" maxtest=27 titleheap="Test 'heap': Environment-specific heap tests" +titleEBC="Test 'ebcdic': EBCDIC-specific tests" if [ $# -eq 1 -a "$1" = "list" ]; then echo $title0 @@ -124,6 +119,7 @@ if [ $# -eq 1 -a "$1" = "list" ]; then echo $title27 echo "" echo $titleheap + echo $titleEBC echo "" echo "Numbered tests are automatically run if nothing selected." echo "Named tests must be explicitly selected." @@ -357,6 +353,12 @@ support32=$? $sim $pcre2test -C backslash-C >/dev/null supportBSC=$? +# Check if compiled in EBCDIC mode, and whether we have EBCDIC I/O +$sim $pcre2test -C ebcdic >/dev/null +ebcdic=$? +$sim $pcre2test -C ebcdic-io >/dev/null +ebcdic_io=$? + # Initialize all bitsizes skipped test8=skip @@ -435,34 +437,38 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \ $do24 = no -a $do25 = no -a $do26 = no -a $do27 = no -a \ $doheap = no -a $doebcdic = no \ ]; then - do0=yes - do1=yes - do2=yes - do3=yes - do4=yes - do5=yes - do6=yes - do7=yes - do8=yes - do9=yes - do10=yes - do11=yes - do12=yes - do13=yes - do14=yes - do15=yes - do16=yes - do17=yes - do18=yes - do19=yes - do20=yes - do21=yes - do22=yes - do23=yes - do24=yes - do25=yes - do26=yes - do27=yes + if [ $ebcdic -eq 0 ] ; then + do0=yes + do1=yes + do2=yes + do3=yes + do4=yes + do5=yes + do6=yes + do7=yes + do8=yes + do9=yes + do10=yes + do11=yes + do12=yes + do13=yes + do14=yes + do15=yes + do16=yes + do17=yes + do18=yes + do19=yes + do20=yes + do21=yes + do22=yes + do23=yes + do24=yes + do25=yes + do26=yes + do27=yes + else + doebcdic=yes + fi fi # Handle any explicit skips at this stage, so that an argument list may consist @@ -921,24 +927,44 @@ for bmode in "$test8" "$test16" "$test32"; do checkresult $? heap-$bits "" fi -# End of loop for 8/16/32-bit tests -done - - -# ------ Special EBCDIC Test ------- + # Special EBCDIC tests -if [ $doebcdic = yes ] ; then - $sim $valgrind $pcre2test -C ebcdic >/dev/null - ebcdic=$? - if [ $ebcdic -ne 1 ] ; then - echo "Cannot run EBCDIC tests: EBCDIC support not compiled" - exit 1 + if [ $doebcdic = yes ] ; then + echo $titleEBC + if [ $ebcdic -ne 1 ] ; then + echo "Cannot run EBCDIC tests: EBCDIC support not compiled" + exit 1 + fi + if [ $ebcdic_io -eq 0 ] ; then + # Our testdata files are in ASCII, and the pcre2test program is using + # ASCII input: all easy. + for opt in "" "-dfa"; do + $sim $valgrind $pcre2test -q $setstack $bmode $opt $testdata/testinputEBC >testtry + checkresult $? EBC "$opt" + done + else + echo "Cannot run EBCDIC tests:" + echo " Ironically we do not support running these tests on an actual" + echo " EBCDIC system. The testdata files shipped with PCRE2 are in ASCII." + echo " You may be able to run the tests manually if you know which" + echo " EBCDIC codepage you used when compiling PCRE2, and then convert" + echo " the testdata to match. For example, if the C compiler used to build" + echo " PCRE2 was using IBM-1047:" + echo "" + echo " iconv -f ISO8859-1 -t IBM-1047 testinputEBC-native" + echo " pcre2test -q -$bmode testinputEBC-native >testoutputEBC-native" + echo " [ $? -eq 0 ] || echo 'pcre2test failed'" + echo " iconv -f IBM-1047 -t ISO8859-1 testoutputEBC-ascii" + echo " $cf testdata/testoutputEBC testoutputEBC-ascii" + echo "" + echo "This is speculative. The PCRE2 maintainers do not have access to an" + echo "EBCDIC system to test this. Please report back if you try it." + exit 1 + fi fi - for opt in "" "-dfa"; do - $sim $valgrind $pcre2test -q $opt $testdata/testinputEBC >testtry - checkresult $? EBC "$opt" - done -fi + +# End of loop for 8/16/32-bit tests +done # Clean up local working files diff --git a/config-cmake.h.in b/config-cmake.h.in index 0eff0e0f7..22f28547c 100644 --- a/config-cmake.h.in +++ b/config-cmake.h.in @@ -38,6 +38,7 @@ #cmakedefine BSR_ANYCRLF 1 #cmakedefine EBCDIC 1 #cmakedefine EBCDIC_NL25 1 +#cmakedefine EBCDIC_IGNORING_COMPILER 1 #cmakedefine HEAP_MATCH_RECURSE 1 #cmakedefine NEVER_BACKSLASH_C 1 diff --git a/configure.ac b/configure.ac index 6b8cb0846..480432966 100644 --- a/configure.ac +++ b/configure.ac @@ -315,7 +315,7 @@ AC_ARG_ENABLE(never-backslash-C, # Handle --enable-ebcdic AC_ARG_ENABLE(ebcdic, AS_HELP_STRING([--enable-ebcdic], - [assume EBCDIC coding rather than ASCII; incompatible with --enable-unicode; use only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]), + [assume EBCDIC coding rather than ASCII; incompatible with --enable-unicode; use only in (uncommon) EBCDIC environments]), , enable_ebcdic=no) # Handle --enable-ebcdic-nl25 @@ -324,6 +324,12 @@ AC_ARG_ENABLE(ebcdic-nl25, [set EBCDIC code for NL to 0x25 instead of 0x15; it implies --enable-ebcdic]), , enable_ebcdic_nl25=no) +# Handle --enable-ebcdic-ignoring-compiler +AC_ARG_ENABLE(ebcdic-ignoring-compiler, + AS_HELP_STRING([--enable-ebcdic-ignoring-compiler], + [force EBCDIC 1047 using numeric literals rather than C character literals; it implies --enable-ebcdic]), + , enable_ebcdic_ignoring_compiler=no) + # Handle --enable-pcre2grep-libz AC_ARG_ENABLE(pcre2grep-libz, AS_HELP_STRING([--enable-pcre2grep-libz], @@ -493,19 +499,21 @@ case "$enable_newline" in ;; esac -# --enable-ebcdic-nl25 implies --enable-ebcdic -if test "x$enable_ebcdic_nl25" = "xyes"; then +# --enable-ebcdic-nl25 and --enable-ebcdic-ignoring-compiler imply --enable-ebcdic +if test "x$enable_ebcdic_nl25" = "xyes" -o "x$enable_ebcdic_ignoring_compiler" = "xyes"; then enable_ebcdic=yes fi -# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# Make sure that if enable_ebcdic is set (without +# enable_ebcdic_ignoring_compiler), rebuild_chartables is also enabled. # Also check that UTF support is not requested, because PCRE2 cannot handle # EBCDIC and UTF in the same build. To do so it would need to use different -# character constants depending on the mode. Also, EBCDIC cannot be used with -# 16-bit and 32-bit libraries. -# +# character constants depending on the mode. +# Also, EBCDIC cannot be used with 16-bit and 32-bit libraries. if test "x$enable_ebcdic" = "xyes"; then - enable_rebuild_chartables=yes + if test "x$enable_ebcdic_ignoring_compiler" != "xyes"; then + enable_rebuild_chartables=yes + fi if test "x$enable_unicode" = "xyes"; then AC_MSG_ERROR([support for EBCDIC and Unicode cannot be enabled at the same time]) fi @@ -563,6 +571,8 @@ AM_CONDITIONAL(WITH_DEBUG, test "x$enable_debug" = "xyes") AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes") AM_CONDITIONAL(WITH_JIT, test "x$enable_jit" = "xyes") AM_CONDITIONAL(WITH_UNICODE, test "x$enable_unicode" = "xyes") +AM_CONDITIONAL(WITH_EBCDIC, test "x$enable_ebcdic" = "xyes") +AM_CONDITIONAL(WITH_EBCDIC_NL25, test "x$enable_ebcdic_nl25" = "xyes") AM_CONDITIONAL(WITH_VALGRIND, test "x$enable_valgrind" = "xyes") AM_CONDITIONAL(WITH_FUZZ_SUPPORT, test "x$enable_fuzz_support" = "xyes") AM_CONDITIONAL(WITH_DIFF_FUZZ_SUPPORT, test "x$enable_diff_fuzz_support" = "xyes") @@ -943,7 +953,7 @@ if test "$enable_ebcdic" = "yes"; then assumes that all input strings are in EBCDIC. If you do not define this macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It is not possible to build a version of PCRE2 that supports both EBCDIC and - UTF-8/16/32.]) + ASCII or UTF-8/16/32.]) fi if test "$enable_ebcdic_nl25" = "yes"; then @@ -953,6 +963,13 @@ if test "$enable_ebcdic_nl25" = "yes"; then that LF does in an ASCII/Unicode environment.]) fi +if test "$enable_ebcdic_ignoring_compiler" = "yes"; then + AC_DEFINE_UNQUOTED([EBCDIC_IGNORING_COMPILER], [], [ + To force an EBCDIC environment, define this macro to make the core PCRE2 + library functions use EBCDIC codepage 1047, regardless of whether the + compiler supports it using C character literals.]) +fi + if test "$enable_valgrind" = "yes"; then AC_DEFINE_UNQUOTED([SUPPORT_VALGRIND], [], [ Define to any value for valgrind support to find invalid memory reads.]) @@ -1191,6 +1208,7 @@ $PACKAGE-$VERSION configuration summary: \C is disabled ..................... : ${enable_never_backslash_C} EBCDIC coding ...................... : ${enable_ebcdic} EBCDIC code for NL ................. : ${ebcdic_nl_code} + EBCDIC coding ignoring compiler .... : ${enable_ebcdic_ignoring_compiler} Rebuild char tables ................ : ${enable_rebuild_chartables} Internal link size ................. : ${with_link_size} Maximum variable lookbehind ........ : ${with_max_varlookbehind} diff --git a/doc/html/README.txt b/doc/html/README.txt index 5a50f7f11..941c4e280 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -309,11 +309,22 @@ library. They are also documented in the pcre2build man page. --enable-ebcdic --disable-unicode - This automatically implies --enable-rebuild-chartables (see above). However, - when PCRE2 is built this way, it always operates in EBCDIC. It cannot support - both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, - which specifies that the code value for the EBCDIC NL character is 0x25 - instead of the default 0x15. + This automatically implies --enable-rebuild-chartables (see above), in order + to ensure that you have the correct default character tables for your system's + codepage. There is an exception when you set --enable-ebcdic-ignoring-compiler + (see below), which allows using a default set of EBCDIC 1047 character tables + rather than forcing use of --enable-rebuild-chartables. + + When PCRE2 is built with EBCDIC support, it always operates in EBCDIC. It + cannot support both EBCDIC and ASCII or UTF-8/16/32. + + There is a second option, --enable-ebcdic-nl25, which specifies that the code + value for the EBCDIC NL character is 0x25 instead of the default 0x15. + + There is a third option, --enable-ebcdic-ignoring-compiler, which disregards + the compiler's codepage for determining the numeric value of C character + constants such as 'z', and instead forces PCRE2 to use numeric constants for + the EBCDIC 1047 codepage instead. . If you specify --enable-debug, additional debugging code is included in the build. This option is intended for use by the PCRE2 maintainers. diff --git a/doc/html/pcre2build.html b/doc/html/pcre2build.html index f4e127f14..77a0b2069 100644 --- a/doc/html/pcre2build.html +++ b/doc/html/pcre2build.html @@ -398,14 +398,21 @@

pcre2build man page

   --enable-ebcdic --disable-unicode
-to the configure command. This setting implies ---enable-rebuild-chartables. You should only use it if you know that you are in -an EBCDIC environment (for example, an IBM mainframe operating system). +to the configure command. You should only use it if you know that you are +in an EBCDIC environment (for example, an IBM mainframe operating system).

-It is not possible to support both EBCDIC and UTF-8 codes in the same version -of the library. Consequently, --enable-unicode and --enable-ebcdic are mutually -exclusive. +This setting implies --enable-rebuild-chartables, in order to ensure that you +have the correct default character tables for your system's codepage. There is +an exception when you set --enable-ebcdic-ignoring-compiler (see below), which +allows using a default set of EBCDIC 1047 character tables rather than forcing +use of --enable-rebuild-chartables. +

+

+It is not supported to enable both EBCDIC input and either ASCII or UTF-8/16/32 +in the same build of the library. When PCRE2 is built with EBCDIC support, it +always operates in EBCDIC, and consequently --enable-unicode and --enable-ebcdic +are mutually exclusive.

The EBCDIC character that corresponds to an ASCII LF is assumed to have the @@ -414,16 +421,28 @@

pcre2build man page

   --enable-ebcdic-nl25
-as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the -same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is not -chosen as LF is made to correspond to the Unicode NEL character (which, in -Unicode, is 0x85). +(which implies --enable-ebcdic). The EBCDIC character for CR has the same value +as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is not chosen as LF +is made to correspond to the Unicode NEL character (which, in Unicode, is 0x85).

The options that select newline behaviour, such as --enable-newline-is-cr, and equivalent run-time options, refer to these character values in an EBCDIC environment.

+

+On systems requiring an EBCDIC build of PCRE2, the compiler should be set to use +the correct codepage, so that C character literals such as 'z' use the correct +numeric value for whichever EBCDIC codpage is in use. (PCRE2 cannot support +multiple EBCDIC codepages dynamically.) However, if this not possible, then you +can use +

+  --enable-ebcdic-ignoring-compiler
+
+in order to disregard the compiler's codepage, and instead force PCRE2 to use +numeric constants corresponding to the EBCDIC 1047 codepage instead. This can be +used to build (or test) EBCDIC support on an ASCII/UTF-8 system such as Linux. +


PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS

By default pcre2grep supports the use of callouts with string arguments diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index db9073f0e..02477f223 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -194,6 +194,8 @@

pcre2test man page

   backslash-C  \C is supported (not locked out)
   ebcdic       compiled for an EBCDIC environment
+  ebcdic-io    if PCRE2 is compiled for EBCDIC, whether pcre2test's input and
+                 output is EBCDIC or ASCII
   jit          just-in-time support is available
   pcre2-16     the 16-bit library was built
   pcre2-32     the 32-bit library was built
diff --git a/doc/pcre2.txt b/doc/pcre2.txt
index 7e402b29e..2b8c889f5 100644
--- a/doc/pcre2.txt
+++ b/doc/pcre2.txt
@@ -4668,74 +4668,95 @@ USING EBCDIC CODE
 
          --enable-ebcdic --disable-unicode
 
-       to the configure command. This setting implies --enable-rebuild-charta-
-       bles.  You should only use it if you know that you are in an EBCDIC en-
-       vironment (for example, an IBM mainframe operating system).
-
-       It is not possible to support both EBCDIC and UTF-8 codes in  the  same
-       version  of  the  library. Consequently, --enable-unicode and --enable-
-       ebcdic are mutually exclusive.
+       to  the  configure command. You should only use it if you know that you
+       are in an EBCDIC environment (for example, an IBM  mainframe  operating
+       system).
+
+       This  setting  implies  --enable-rebuild-chartables, in order to ensure
+       that you have the correct default character tables  for  your  system's
+       codepage.  There is an exception when you set --enable-ebcdic-ignoring-
+       compiler (see below), which allows using a default set of  EBCDIC  1047
+       character  tables  rather  than forcing use of --enable-rebuild-charta-
+       bles.
+
+       It is not supported to enable both EBCDIC input  and  either  ASCII  or
+       UTF-8/16/32  in the same build of the library. When PCRE2 is built with
+       EBCDIC support, it always operates in EBCDIC,  and  consequently  --en-
+       able-unicode and --enable-ebcdic are mutually exclusive.
 
        The EBCDIC character that corresponds to an ASCII LF is assumed to have
-       the value 0x15 by default. However, in some EBCDIC  environments,  0x25
+       the  value  0x15 by default. However, in some EBCDIC environments, 0x25
        is used. In such an environment you should use
 
          --enable-ebcdic-nl25
 
-       as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR
-       has  the  same  value  as in ASCII, namely, 0x0d. Whichever of 0x15 and
-       0x25 is not chosen as LF is made to correspond to the Unicode NEL char-
-       acter (which, in Unicode, is 0x85).
+       (which implies --enable-ebcdic). The EBCDIC character for  CR  has  the
+       same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is not
+       chosen as LF is made to correspond to the Unicode NEL character (which,
+       in Unicode, is 0x85).
 
        The options that select newline behaviour, such as --enable-newline-is-
        cr, and equivalent run-time options, refer to these character values in
        an EBCDIC environment.
 
+       On  systems  requiring an EBCDIC build of PCRE2, the compiler should be
+       set to use the correct codepage, so that C character literals  such  as
+       'z'  use  the  correct numeric value for whichever EBCDIC codpage is in
+       use. (PCRE2 cannot support multiple EBCDIC codepages dynamically.) How-
+       ever, if this not possible, then you can use
+
+         --enable-ebcdic-ignoring-compiler
+
+       in order to disregard the compiler's codepage, and instead force  PCRE2
+       to  use numeric constants corresponding to the EBCDIC 1047 codepage in-
+       stead. This can be used  to  build  (or  test)  EBCDIC  support  on  an
+       ASCII/UTF-8 system such as Linux.
+
 
 PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
 
        By default pcre2grep supports the use of callouts with string arguments
-       within the patterns it is matching. There are two kinds: one that  gen-
+       within  the patterns it is matching. There are two kinds: one that gen-
        erates output using local code, and another that calls an external pro-
-       gram  or  script.   If --disable-pcre2grep-callout-fork is added to the
-       configure command, only the first kind  of  callout  is  supported;  if
-       --disable-pcre2grep-callout  is  used,  all callouts are completely ig-
-       nored. For more details of pcre2grep callouts, see the pcre2grep  docu-
+       gram or script.  If --disable-pcre2grep-callout-fork is  added  to  the
+       configure  command,  only  the  first  kind of callout is supported; if
+       --disable-pcre2grep-callout is used, all callouts  are  completely  ig-
+       nored.  For more details of pcre2grep callouts, see the pcre2grep docu-
        mentation.
 
 
 PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
 
-       By  default,  pcre2grep reads all files as plain text. You can build it
-       so that it recognizes files whose names end in .gz or .bz2,  and  reads
+       By default, pcre2grep reads all files as plain text. You can  build  it
+       so  that  it recognizes files whose names end in .gz or .bz2, and reads
        them with libz or libbz2, respectively, by adding one or both of
 
          --enable-pcre2grep-libz
          --enable-pcre2grep-libbz2
 
        to the configure command. These options naturally require that the rel-
-       evant  libraries  are installed on your system. Configuration will fail
+       evant libraries are installed on your system. Configuration  will  fail
        if they are not.
 
 
 PCRE2GREP BUFFER SIZE
 
-       pcre2grep uses an internal buffer to hold a "window" on the file it  is
+       pcre2grep  uses an internal buffer to hold a "window" on the file it is
        scanning, in order to be able to output "before" and "after" lines when
        it finds a match. The default starting size of the buffer is 20KiB. The
-       buffer  itself  is  three times this size, but because of the way it is
+       buffer itself is three times this size, but because of the  way  it  is
        used for holding "before" lines, the longest line that is guaranteed to
        be processable is the notional buffer size. If a longer line is encoun-
-       tered, pcre2grep automatically expands the buffer, up  to  a  specified
-       maximum  size, whose default is 1MiB or the starting size, whichever is
-       the larger. You can change the default parameter values by adding,  for
+       tered,  pcre2grep  automatically  expands the buffer, up to a specified
+       maximum size, whose default is 1MiB or the starting size, whichever  is
+       the  larger. You can change the default parameter values by adding, for
        example,
 
          --with-pcre2grep-bufsize=51200
          --with-pcre2grep-max-bufsize=2097152
 
-       to  the  configure  command. The caller of pcre2grep can override these
-       values by using --buffer-size  and  --max-buffer-size  on  the  command
+       to the configure command. The caller of pcre2grep  can  override  these
+       values  by  using  --buffer-size  and  --max-buffer-size on the command
        line.
 
 
@@ -4746,26 +4767,26 @@ PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
          --enable-pcre2test-libreadline
          --enable-pcre2test-libedit
 
-       to  the configure command, pcre2test is linked with the libreadline or-
-       libedit library, respectively, and when its input is from  a  terminal,
-       it  reads  it using the readline() function. This provides line-editing
-       and history facilities. Note that libreadline is  GPL-licensed,  so  if
-       you  distribute  a binary of pcre2test linked in this way, there may be
+       to the configure command, pcre2test is linked with the libreadline  or-
+       libedit  library,  respectively, and when its input is from a terminal,
+       it reads it using the readline() function. This  provides  line-editing
+       and  history  facilities.  Note that libreadline is GPL-licensed, so if
+       you distribute a binary of pcre2test linked in this way, there  may  be
        licensing issues. These can be avoided by linking instead with libedit,
        which has a BSD licence.
 
-       Setting --enable-pcre2test-libreadline causes the -lreadline option  to
-       be  added to the pcre2test build. In many operating environments with a
-       system-installed readline library this is sufficient. However, in  some
+       Setting  --enable-pcre2test-libreadline causes the -lreadline option to
+       be added to the pcre2test build. In many operating environments with  a
+       system-installed  readline library this is sufficient. However, in some
        environments (e.g. if an unmodified distribution version of readline is
-       in  use),  some  extra configuration may be necessary. The INSTALL file
+       in use), some extra configuration may be necessary.  The  INSTALL  file
        for libreadline says this:
 
          "Readline uses the termcap functions, but does not link with
          the termcap or curses library itself, allowing applications
          which link with readline the to choose an appropriate library."
 
-       If your environment has not been set up so that an appropriate  library
+       If  your environment has not been set up so that an appropriate library
        is automatically included, you may need to add something like
 
          LIBS="-ncurses"
@@ -4779,7 +4800,7 @@ INCLUDING DEBUGGING CODE
 
          --enable-debug
 
-       to  the configure command, additional debugging code is included in the
+       to the configure command, additional debugging code is included in  the
        build. This feature is intended for use by the PCRE2 maintainers.
 
 
@@ -4789,14 +4810,14 @@ DEBUGGING WITH VALGRIND SUPPORT
 
          --enable-valgrind
 
-       to the configure command, PCRE2 will use valgrind annotations  to  mark
-       certain  memory  regions as unaddressable. This allows it to detect in-
+       to  the  configure command, PCRE2 will use valgrind annotations to mark
+       certain memory regions as unaddressable. This allows it to  detect  in-
        valid memory accesses, and is mostly useful for debugging PCRE2 itself.
 
 
 CODE COVERAGE REPORTING
 
-       If your C compiler is gcc, you can build a version of  PCRE2  that  can
+       If  your  C  compiler is gcc, you can build a version of PCRE2 that can
        generate a code coverage report for its test suite. To enable this, you
        must install lcov version 1.6 or above. Then specify
 
@@ -4805,20 +4826,20 @@ CODE COVERAGE REPORTING
        to the configure command and build PCRE2 in the usual way.
 
        Note that using ccache (a caching C compiler) is incompatible with code
-       coverage  reporting. If you have configured ccache to run automatically
+       coverage reporting. If you have configured ccache to run  automatically
        on your system, you must set the environment variable
 
          CCACHE_DISABLE=1
 
        before running make to build PCRE2, so that ccache is not used.
 
-       When --enable-coverage is used,  the  following  addition  targets  are
+       When  --enable-coverage  is  used,  the  following addition targets are
        added to the Makefile:
 
          make coverage
 
-       This  creates  a  fresh coverage report for the PCRE2 test suite. It is
-       equivalent to running "make coverage-reset", "make  coverage-baseline",
+       This creates a fresh coverage report for the PCRE2 test  suite.  It  is
+       equivalent  to running "make coverage-reset", "make coverage-baseline",
        "make check", and then "make coverage-report".
 
          make coverage-reset
@@ -4835,73 +4856,73 @@ CODE COVERAGE REPORTING
 
          make coverage-clean-report
 
-       This  removes the generated coverage report without cleaning the cover-
+       This removes the generated coverage report without cleaning the  cover-
        age data itself.
 
          make coverage-clean-data
 
-       This removes the captured coverage data without removing  the  coverage
+       This  removes  the captured coverage data without removing the coverage
        files created at compile time (*.gcno).
 
          make coverage-clean
 
-       This  cleans all coverage data including the generated coverage report.
-       For more information about code coverage, see the gcov and  lcov  docu-
+       This cleans all coverage data including the generated coverage  report.
+       For  more  information about code coverage, see the gcov and lcov docu-
        mentation.
 
 
 DISABLING THE Z AND T FORMATTING MODIFIERS
 
-       The  C99  standard  defines formatting modifiers z and t for size_t and
-       ptrdiff_t values, respectively. By default, PCRE2 uses these  modifiers
+       The C99 standard defines formatting modifiers z and t  for  size_t  and
+       ptrdiff_t  values, respectively. By default, PCRE2 uses these modifiers
        in environments other than old versions of Microsoft Visual Studio when
-       __STDC_VERSION__  is  defined  and has a value greater than or equal to
-       199901L (indicating support for C99).  However, there is at  least  one
+       __STDC_VERSION__ is defined and has a value greater than  or  equal  to
+       199901L  (indicating  support for C99).  However, there is at least one
        environment that claims to be C99 but does not support these modifiers.
        If
 
          --disable-percent-zt
 
        is specified, no use is made of the z or t modifiers. Instead of %td or
-       %zu,  a  suitable  format is used depending in the size of long for the
+       %zu, a suitable format is used depending in the size of  long  for  the
        platform.
 
 
 SUPPORT FOR FUZZERS
 
-       There is a special option for use by people who  want  to  run  fuzzing
+       There  is  a  special  option for use by people who want to run fuzzing
        tests on PCRE2:
 
          --enable-fuzz-support
 
        At present this applies only to the 8-bit library. If set, it causes an
-       extra  library  called  libpcre2-fuzzsupport.a to be built, but not in-
-       stalled. This contains a single  function  called  LLVMFuzzerTestOneIn-
-       put()  whose  arguments are a pointer to a string and the length of the
-       string. When called, this function tries to compile  the  string  as  a
-       pattern,  and if that succeeds, to match it.  This is done both with no
-       options and with some random options bits that are generated  from  the
+       extra library called libpcre2-fuzzsupport.a to be built,  but  not  in-
+       stalled.  This  contains  a single function called LLVMFuzzerTestOneIn-
+       put() whose arguments are a pointer to a string and the length  of  the
+       string.  When  called,  this  function tries to compile the string as a
+       pattern, and if that succeeds, to match it.  This is done both with  no
+       options  and  with some random options bits that are generated from the
        string.
 
-       Setting  --enable-fuzz-support  also  causes  a binary called pcre2fuz-
-       zcheck to be created. This is normally run under valgrind or used  when
+       Setting --enable-fuzz-support also causes  a  binary  called  pcre2fuz-
+       zcheck  to be created. This is normally run under valgrind or used when
        PCRE2 is compiled with address sanitizing enabled. It calls the fuzzing
-       function  and  outputs  information  about  what it is doing. The input
-       strings are specified by arguments: if an argument starts with "="  the
-       rest  of it is a literal input string. Otherwise, it is assumed to be a
+       function and outputs information about what  it  is  doing.  The  input
+       strings  are specified by arguments: if an argument starts with "=" the
+       rest of it is a literal input string. Otherwise, it is assumed to be  a
        file name, and the contents of the file are the test string.
 
 
 OBSOLETE OPTION
 
-       In versions of PCRE2 prior to 10.30, there were two  ways  of  handling
-       backtracking  in the pcre2_match() function. The default was to use the
+       In  versions  of  PCRE2 prior to 10.30, there were two ways of handling
+       backtracking in the pcre2_match() function. The default was to use  the
        system stack, but if
 
          --disable-stack-for-recursion
 
-       was set, memory on the heap was used. From release 10.30  onwards  this
-       has  changed  (the  stack  is  no longer used) and this option now does
+       was  set,  memory on the heap was used. From release 10.30 onwards this
+       has changed (the stack is no longer used)  and  this  option  now  does
        nothing except give a warning.
 
 
diff --git a/doc/pcre2build.3 b/doc/pcre2build.3
index 13d2438da..d81b537a0 100644
--- a/doc/pcre2build.3
+++ b/doc/pcre2build.3
@@ -395,13 +395,19 @@ most computer operating systems. PCRE2 can, however, be compiled to run in an
 .sp
   --enable-ebcdic --disable-unicode
 .sp
-to the \fBconfigure\fP command. This setting implies
---enable-rebuild-chartables. You should only use it if you know that you are in
-an EBCDIC environment (for example, an IBM mainframe operating system).
+to the \fBconfigure\fP command. You should only use it if you know that you are
+in an EBCDIC environment (for example, an IBM mainframe operating system).
 .P
-It is not possible to support both EBCDIC and UTF-8 codes in the same version
-of the library. Consequently, --enable-unicode and --enable-ebcdic are mutually
-exclusive.
+This setting implies --enable-rebuild-chartables, in order to ensure that you
+have the correct default character tables for your system's codepage. There is
+an exception when you set --enable-ebcdic-ignoring-compiler (see below), which
+allows using a default set of EBCDIC 1047 character tables rather than forcing
+use of --enable-rebuild-chartables.
+.P
+It is not supported to enable both EBCDIC input and either ASCII or UTF-8/16/32
+in the same build of the library. When PCRE2 is built with EBCDIC support, it
+always operates in EBCDIC, and consequently --enable-unicode and --enable-ebcdic
+are mutually exclusive.
 .P
 The EBCDIC character that corresponds to an ASCII LF is assumed to have the
 value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In
@@ -409,14 +415,25 @@ such an environment you should use
 .sp
   --enable-ebcdic-nl25
 .sp
-as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the
-same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP
-chosen as LF is made to correspond to the Unicode NEL character (which, in
-Unicode, is 0x85).
+(which implies --enable-ebcdic). The EBCDIC character for CR has the same value
+as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP chosen as LF
+is made to correspond to the Unicode NEL character (which, in Unicode, is 0x85).
 .P
 The options that select newline behaviour, such as --enable-newline-is-cr,
 and equivalent run-time options, refer to these character values in an EBCDIC
 environment.
+.P
+On systems requiring an EBCDIC build of PCRE2, the compiler should be set to use
+the correct codepage, so that C character literals such as 'z' use the correct
+numeric value for whichever EBCDIC codpage is in use. (PCRE2 cannot support
+multiple EBCDIC codepages dynamically.) However, if this not possible, then you
+can use
+.sp
+  --enable-ebcdic-ignoring-compiler
+.sp
+in order to disregard the compiler's codepage, and instead force PCRE2 to use
+numeric constants corresponding to the EBCDIC 1047 codepage instead. This can be
+used to build (or test) EBCDIC support on an ASCII/UTF-8 system such as Linux.
 .
 .
 .SH "PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS"
diff --git a/doc/pcre2test.1 b/doc/pcre2test.1
index e2325b4d8..98e21adce 100644
--- a/doc/pcre2test.1
+++ b/doc/pcre2test.1
@@ -161,6 +161,8 @@ to the same value:
 .sp
   backslash-C  \eC is supported (not locked out)
   ebcdic       compiled for an EBCDIC environment
+  ebcdic-io    if PCRE2 is compiled for EBCDIC, whether pcre2test's input and
+                 output is EBCDIC or ASCII
   jit          just-in-time support is available
   pcre2-16     the 16-bit library was built
   pcre2-32     the 32-bit library was built
diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt
index 4e229148c..61d8a1e13 100644
--- a/doc/pcre2test.txt
+++ b/doc/pcre2test.txt
@@ -150,6 +150,9 @@ COMMAND LINE OPTIONS
 
                    backslash-C  \C is supported (not locked out)
                    ebcdic       compiled for an EBCDIC environment
+                   ebcdic-io     if  PCRE2  is  compiled  for  EBCDIC, whether
+                 pcre2test's input and
+                                  output is EBCDIC or ASCII
                    jit          just-in-time support is available
                    pcre2-16     the 16-bit library was built
                    pcre2-32     the 32-bit library was built
@@ -157,9 +160,9 @@ COMMAND LINE OPTIONS
                    unicode      Unicode support is available
 
                  Note that the availability of JIT support in the library does
-                 not  guarantee  that  it can actually be used because in some
-                 environments it is unable to allocate executable memory.  The
-                 option  "jitusable"  gives  more detailed information. It re-
+                 not guarantee that it can actually be used  because  in  some
+                 environments  it is unable to allocate executable memory. The
+                 option "jitusable" gives more detailed  information.  It  re-
                  turns one of the following values:
 
                    0  JIT is available and usable
@@ -167,56 +170,56 @@ COMMAND LINE OPTIONS
                    2  JIT is not available
                    3  Unexpected return from test call to pcre2_jit_compile()
 
-                 If an unknown option is given, an error  message  is  output;
+                 If  an  unknown  option is given, an error message is output;
                  the exit code is 0.
 
-       -d        Behave  as if each pattern has the debug modifier; the inter-
+       -d        Behave as if each pattern has the debug modifier; the  inter-
                  nal form and information about the compiled pattern is output
                  after compilation; -d is equivalent to -b -i.
 
        -dfa      Behave as if each subject line has the dfa modifier; matching
-                 is done using the pcre2_dfa_match() function instead  of  the
+                 is  done  using the pcre2_dfa_match() function instead of the
                  default pcre2_match().
 
        -error number[,number,...]
-                 Call  pcre2_get_error_message() for each of the error numbers
-                 in the comma-separated list, display the  resulting  messages
-                 on  the  standard  output, then exit with zero exit code. The
-                 numbers may be positive or negative. This  is  a  convenience
+                 Call pcre2_get_error_message() for each of the error  numbers
+                 in  the  comma-separated list, display the resulting messages
+                 on the standard output, then exit with zero  exit  code.  The
+                 numbers  may  be  positive or negative. This is a convenience
                  facility for PCRE2 maintainers.
 
        -help     Output a brief summary these options and then exit.
 
-       -i        Behave  as if each pattern has the info modifier; information
+       -i        Behave as if each pattern has the info modifier;  information
                  about the compiled pattern is given after compilation.
 
-       -jit      Behave as if each pattern line has the  jit  modifier;  after
-                 successful  compilation,  each pattern is passed to the just-
+       -jit      Behave  as  if  each pattern line has the jit modifier; after
+                 successful compilation, each pattern is passed to  the  just-
                  in-time compiler, if available.
 
-       -jitfast  Behave as if each pattern line has the jitfast modifier;  af-
-                 ter  successful  compilation,  each  pattern is passed to the
+       -jitfast  Behave  as if each pattern line has the jitfast modifier; af-
+                 ter successful compilation, each pattern  is  passed  to  the
                  just-in-time compiler, if available, and each subject line is
                  passed directly to the JIT matcher via its "fast path".
 
        -jitverify
-                 Behave as if each pattern line has  the  jitverify  modifier;
-                 after  successful  compilation, each pattern is passed to the
-                 just-in-time compiler, if available, and the use of  JIT  for
+                 Behave  as  if  each pattern line has the jitverify modifier;
+                 after successful compilation, each pattern is passed  to  the
+                 just-in-time  compiler,  if available, and the use of JIT for
                  matching is verified.
 
        -LM       List modifiers: write a list of available pattern and subject
-                 modifiers  to  the  standard output, then exit with zero exit
-                 code. All other options are ignored.  If both -C and any  -Lx
+                 modifiers to the standard output, then exit  with  zero  exit
+                 code.  All other options are ignored.  If both -C and any -Lx
                  options are present, whichever is first is recognized.
 
-       -LP       List  properties:  write a list of recognized Unicode proper-
-                 ties to the standard output, then exit with zero  exit  code.
+       -LP       List properties: write a list of recognized  Unicode  proper-
+                 ties  to  the standard output, then exit with zero exit code.
                  All other options are ignored. If both -C and any -Lx options
                  are present, whichever is first is recognized.
 
        -LS       List scripts: write a list of recognized Unicode script names
-                 to  the  standard  output, then exit with zero exit code. All
+                 to the standard output, then exit with zero  exit  code.  All
                  other options are ignored. If both -C and any -Lx options are
                  present, whichever is first is recognized.
 
@@ -226,25 +229,25 @@ COMMAND LINE OPTIONS
        -q        Do not output the version number of pcre2test at the start of
                  execution.
 
-       -S size   On Unix-like systems, set the size of the run-time  stack  to
+       -S size   On  Unix-like  systems, set the size of the run-time stack to
                  size mebibytes (units of 1024*1024 bytes).
 
        -subject modifier-list
                  Behave as if each subject line contains the given modifiers.
 
-       -t        Run  each compile and match many times with a timer, and out-
-                 put the resulting times per compile or  match.  When  JIT  is
-                 used,  separate  times  are given for the initial compile and
-                 the JIT compile. You can control  the  number  of  iterations
-                 that  are used for timing by following -t with a number (as a
-                 separate item on the command line). For  example,  "-t  1000"
+       -t        Run each compile and match many times with a timer, and  out-
+                 put  the  resulting  times  per compile or match. When JIT is
+                 used, separate times are given for the  initial  compile  and
+                 the  JIT  compile.  You  can control the number of iterations
+                 that are used for timing by following -t with a number (as  a
+                 separate  item  on  the command line). For example, "-t 1000"
                  iterates 1000 times. The default is to iterate 500,000 times.
 
        -tm       This is like -t except that it times only the matching phase,
                  not the compile phase.
 
-       -T -TM    These  behave like -t and -tm, but in addition, at the end of
-                 a run, the total times for all compiles and matches are  out-
+       -T -TM    These behave like -t and -tm, but in addition, at the end  of
+                 a  run, the total times for all compiles and matches are out-
                  put.
 
        -version  Output the PCRE2 version number and then exit.
@@ -252,153 +255,153 @@ COMMAND LINE OPTIONS
 
 DESCRIPTION
 
-       If  pcre2test  is given two filename arguments, it reads from the first
+       If pcre2test 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 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
        writes to stdout.
 
-       When  pcre2test  is  built,  a configuration option can specify that it
-       should be linked with the libreadline or libedit library. When this  is
-       done,  if the input is from a terminal, it is read using the readline()
+       When pcre2test is built, a configuration option  can  specify  that  it
+       should  be linked with the libreadline or libedit library. When this is
+       done, if the input is from a terminal, it is read using the  readline()
        function. This provides line-editing and history facilities. The output
        from the -help option states whether or not readline() will be used.
 
-       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,
+       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 number of subject lines to be matched against that pat-
        tern. In between sets of test data, command lines that begin with # may
        appear. This file format, with some restrictions, can also be processed
-       by the perltest.sh script that is distributed with PCRE2 as a means  of
+       by  the perltest.sh script that is distributed with PCRE2 as a means of
        checking that the behaviour of PCRE2 and Perl is the same. For a speci-
-       fication  of perltest.sh, see the comments near its beginning. See also
+       fication of perltest.sh, see the comments near its beginning. See  also
        the #perltest command below.
 
        When the input is a terminal, pcre2test prompts for each line of input,
-       using "re>" to prompt for regular expression patterns, and  "data>"  to
-       prompt  for subject lines. Command lines starting with # can be entered
+       using  "re>"  to prompt for regular expression patterns, and "data>" to
+       prompt for subject lines. Command lines starting with # can be  entered
        only in response to the "re>" prompt.
 
-       Each subject line is matched separately and independently. If you  want
+       Each  subject line is matched separately and independently. If you want
        to do multi-line matches, you have to use the \n escape sequence (or \r
-       or  \r\n,  etc.,  depending on the newline setting) in a single line of
-       input to encode the newline sequences. There is no limit on the  length
-       of  subject  lines; the input buffer is automatically extended if it is
-       too small. There are replication features that  makes  it  possible  to
-       generate  long  repetitive  pattern  or subject lines without having to
+       or \r\n, etc., depending on the newline setting) in a  single  line  of
+       input  to encode the newline sequences. There is no limit on the length
+       of subject lines; the input buffer is automatically extended if  it  is
+       too  small.  There  are  replication features that makes it possible to
+       generate long repetitive pattern or subject  lines  without  having  to
        supply them explicitly.
 
-       An empty line or the end of the file signals the  end  of  the  subject
-       lines  for  a test, at which point a new pattern or command line is ex-
+       An  empty  line  or  the end of the file signals the end of the subject
+       lines for a test, at which point a new pattern or command line  is  ex-
        pected if there is still input to be read.
 
 
 COMMAND LINES
 
-       In between sets of test data, a line that begins with # is  interpreted
+       In  between sets of test data, a line that begins with # is interpreted
        as a command line. If the first character is followed by white space or
-       an  exclamation  mark,  the  line is treated as a comment, and ignored.
+       an exclamation mark, the line is treated as  a  comment,  and  ignored.
        Otherwise, the following commands are recognized:
 
          #forbid_utf
 
-       Subsequent  patterns  automatically  have   the   PCRE2_NEVER_UTF   and
-       PCRE2_NEVER_UCP  options  set, which locks out the use of the PCRE2_UTF
-       and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start  of
-       patterns.  This  command  also  forces an error if a subsequent pattern
-       contains any occurrences of \P, \p, or \X, which  are  still  supported
-       when  PCRE2_UTF  is not set, but which require Unicode property support
+       Subsequent   patterns   automatically   have  the  PCRE2_NEVER_UTF  and
+       PCRE2_NEVER_UCP options set, which locks out the use of  the  PCRE2_UTF
+       and  PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
+       patterns. This command also forces an error  if  a  subsequent  pattern
+       contains  any  occurrences  of \P, \p, or \X, which are still supported
+       when PCRE2_UTF is not set, but which require Unicode  property  support
        to be included in the library.
 
-       This is a trigger guard that is used in test files to ensure  that  UTF
-       or  Unicode property tests are not accidentally added to files that are
-       used when Unicode support is  not  included  in  the  library.  Setting
-       PCRE2_NEVER_UTF  and  PCRE2_NEVER_UCP as a default can also be obtained
-       by the use of #pattern; the difference is that  #forbid_utf  cannot  be
-       unset,  and the automatic options are not displayed in pattern informa-
+       This  is  a trigger guard that is used in test files to ensure that UTF
+       or Unicode property tests are not accidentally added to files that  are
+       used  when  Unicode  support  is  not  included in the library. Setting
+       PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also  be  obtained
+       by  the  use  of #pattern; the difference is that #forbid_utf cannot be
+       unset, and the automatic options are not displayed in pattern  informa-
        tion, to avoid cluttering up test output.
 
          #load 
 
        This command is used to load a set of precompiled patterns from a file,
-       as described in the section entitled  "Saving  and  restoring  compiled
+       as  described  in  the  section entitled "Saving and restoring compiled
        patterns" below.
 
          #loadtables 
 
-       This  command is used to load a set of binary character tables that can
-       be accessed by the tables=3 qualifier. Such tables can  be  created  by
+       This command is used to load a set of binary character tables that  can
+       be  accessed  by  the tables=3 qualifier. Such tables can be created by
        the pcre2_dftables program with the -b option.
 
          #newline_default []
 
-       When  PCRE2  is  built,  a default newline convention can be specified.
-       This determines which characters and/or character pairs are  recognized
+       When PCRE2 is built, a default newline  convention  can  be  specified.
+       This  determines which characters and/or character pairs are recognized
        as indicating a newline in a pattern or subject string. The default can
-       be  overridden when a pattern is compiled. The standard test files con-
-       tain tests of various newline conventions,  but  the  majority  of  the
-       tests  expect  a  single  linefeed to be recognized as a newline by de-
-       fault. Without special action the tests would fail when PCRE2  is  com-
+       be overridden when a pattern is compiled. The standard test files  con-
+       tain  tests  of  various  newline  conventions, but the majority of the
+       tests expect a single linefeed to be recognized as  a  newline  by  de-
+       fault.  Without  special action the tests would fail when PCRE2 is com-
        piled with either CR or CRLF as the default newline.
 
        The #newline_default command specifies a list of newline types that are
-       acceptable  as the default. The types must be one of CR, LF, CRLF, ANY-
+       acceptable as the default. The types must be one of CR, LF, CRLF,  ANY-
        CRLF, ANY, or NUL (in upper or lower case), for example:
 
          #newline_default LF Any anyCRLF
 
        If the default newline is in the list, this command has no effect. Oth-
-       erwise, except when testing the POSIX  API,  a  newline  modifier  that
+       erwise,  except  when  testing  the  POSIX API, a newline modifier that
        specifies the first newline convention in the list (LF in the above ex-
-       ample)  is  added  to  any pattern that does not already have a newline
+       ample) is added to any pattern that does not  already  have  a  newline
        modifier. If the newline list is empty, the feature is turned off. This
        command is present in a number of the standard test input files.
 
-       When the POSIX API is being tested there is no way to override the  de-
+       When  the POSIX API is being tested there is no way to override the de-
        fault newline convention, though it is possible to set the newline con-
-       vention  from  within  the  pattern. A warning is given if the posix or
-       posix_nosub modifier is used when #newline_default would set a  default
+       vention from within the pattern. A warning is given  if  the  posix  or
+       posix_nosub  modifier is used when #newline_default would set a default
        for the non-POSIX API.
 
          #pattern 
 
-       This  command  sets  a default modifier list that applies to all subse-
+       This command sets a default modifier list that applies  to  all  subse-
        quent patterns. Modifiers on a pattern can change these settings.
 
          #perltest
 
-       This line is used in test files that can also  be  processed  by  perl-
-       test.sh  to  confirm  that Perl gives the same results as PCRE2. Subse-
-       quent tests are checked for the use of pcre2test features that are  in-
+       This  line  is  used  in test files that can also be processed by perl-
+       test.sh to confirm that Perl gives the same results  as  PCRE2.  Subse-
+       quent  tests are checked for the use of pcre2test features that are in-
        compatible with the perltest.sh script.
 
-       Patterns  must  use  '/' as their delimiter, and only certain modifiers
-       are supported. Comment lines, #pattern commands, and #subject  commands
-       that  set  or  unset "mark" are recognized and acted on. The #perltest,
-       #forbid_utf, and #newline_default commands, which  are  needed  in  the
+       Patterns must use '/' as their delimiter, and  only  certain  modifiers
+       are  supported. Comment lines, #pattern commands, and #subject commands
+       that set or unset "mark" are recognized and acted  on.  The  #perltest,
+       #forbid_utf,  and  #newline_default  commands,  which are needed in the
        relevant pcre2test files, are silently ignored. All other command lines
-       are  ignored,  but  give a warning message. The #perltest command helps
-       detect tests that are accidentally put in the wrong  file  or  use  the
-       wrong  delimiter.  For  more  details of the perltest.sh script see the
+       are ignored, but give a warning message. The  #perltest  command  helps
+       detect  tests  that  are  accidentally put in the wrong file or use the
+       wrong delimiter. For more details of the  perltest.sh  script  see  the
        comments it contains.
 
          #pop []
          #popcopy []
 
-       These commands are used to manipulate the stack of  compiled  patterns,
-       as  described  in  the  section entitled "Saving and restoring compiled
+       These  commands  are used to manipulate the stack of compiled patterns,
+       as described in the section entitled  "Saving  and  restoring  compiled
        patterns" below.
 
          #save 
 
-       This command is used to save a set of compiled patterns to a  file,  as
-       described  in  the section entitled "Saving and restoring compiled pat-
+       This  command  is used to save a set of compiled patterns to a file, as
+       described in the section entitled "Saving and restoring  compiled  pat-
        terns" below.
 
          #subject 
 
-       This command sets a default modifier list that applies  to  all  subse-
-       quent  subject lines. Modifiers on a subject line can change these set-
+       This  command  sets  a default modifier list that applies to all subse-
+       quent subject lines. Modifiers on a subject line can change these  set-
        tings.
 
 
@@ -406,47 +409,47 @@ MODIFIER SYNTAX
 
        Modifier lists are used with both pattern and subject lines. Items in a
        list are separated by commas followed by optional white space. Trailing
-       whitespace in a modifier list is ignored. Some modifiers may  be  given
-       for  both patterns and subject lines, whereas others are valid only for
-       one or the other. Each modifier has  a  long  name,  for  example  "an-
-       chored",  and  some  of  them  must be followed by an equals sign and a
-       value, for example, "offset=12". Values cannot  contain  comma  charac-
-       ters,  but may contain spaces. Modifiers that do not take values may be
+       whitespace  in  a modifier list is ignored. Some modifiers may be given
+       for both patterns and subject lines, whereas others are valid only  for
+       one  or  the  other.  Each  modifier  has a long name, for example "an-
+       chored", and some of them must be followed by  an  equals  sign  and  a
+       value,  for  example,  "offset=12". Values cannot contain comma charac-
+       ters, but may contain spaces. Modifiers that do not take values may  be
        preceded by a minus sign to turn off a previous setting.
 
        A few of the more common modifiers can also be specified as single let-
-       ters, for example "i" for "caseless". In documentation,  following  the
+       ters,  for  example "i" for "caseless". In documentation, following the
        Perl convention, these are written with a slash ("the /i modifier") for
-       clarity.  Abbreviated  modifiers  must all be concatenated in the first
-       item of a modifier list. If the first item is not recognized as a  long
-       modifier  name, it is interpreted as a sequence of these abbreviations.
+       clarity. Abbreviated modifiers must all be concatenated  in  the  first
+       item  of a modifier list. If the first item is not recognized as a long
+       modifier name, it is interpreted as a sequence of these  abbreviations.
        For example:
 
          /abc/ig,newline=cr,jit=3
 
-       This is a pattern line whose modifier list starts with  two  one-letter
-       modifiers  (/i  and  /g).  The lower-case abbreviated modifiers are the
+       This  is  a pattern line whose modifier list starts with two one-letter
+       modifiers (/i and /g). The lower-case  abbreviated  modifiers  are  the
        same as used in Perl.
 
 
 PATTERN SYNTAX
 
-       A pattern line must start with one of the following characters  (common
+       A  pattern line must start with one of the following characters (common
        symbols, excluding pattern meta-characters):
 
          / ! " ' ` - = _ : ; , % & @ ~
 
-       This  is  interpreted  as the pattern's delimiter. A regular expression
-       may be continued over several input lines, in which  case  the  newline
+       This is interpreted as the pattern's delimiter.  A  regular  expression
+       may  be  continued  over several input lines, in which case the newline
        characters are included within it. It is possible to include the delim-
-       iter  as  a literal within the pattern by escaping it with a backslash,
+       iter as a literal within the pattern by escaping it with  a  backslash,
        for example
 
          /abc\/def/
 
-       If you do this, the escape and the delimiter form part of the  pattern,
+       If  you do this, the escape and the delimiter form part of the pattern,
        but since the delimiters are all non-alphanumeric, the inclusion of the
-       backslash  does not affect the pattern's interpretation. Note, however,
+       backslash does not affect the pattern's interpretation. Note,  however,
        that this trick does not work within \Q...\E literal bracketing because
        the backslash will itself be interpreted as a literal. If the terminat-
        ing delimiter is immediately followed by a backslash, for example,
@@ -454,13 +457,13 @@ PATTERN SYNTAX
          /abc/\
 
        a backslash is added to the end of the pattern. This is done to provide
-       a way of testing the error condition that arises if a pattern  finishes
+       a  way of testing the error condition that arises if a pattern finishes
        with a backslash, because
 
          /abc\/
 
-       is  interpreted as the first line of a pattern that starts with "abc/",
-       causing pcre2test to read the next line as a continuation of the  regu-
+       is interpreted as the first line of a pattern that starts with  "abc/",
+       causing  pcre2test to read the next line as a continuation of the regu-
        lar expression.
 
        A pattern can be followed by a modifier list (details below).
@@ -469,9 +472,9 @@ PATTERN SYNTAX
 SUBJECT LINE SYNTAX
 
        Before each subject line is passed to pcre2_match(), pcre2_dfa_match(),
-       or  pcre2_jit_match(), leading and trailing white space is removed, and
-       the line is scanned for backslash escapes, unless  the  subject_literal
-       modifier  was set for the pattern. The following provide a means of en-
+       or pcre2_jit_match(), leading and trailing white space is removed,  and
+       the  line  is scanned for backslash escapes, unless the subject_literal
+       modifier was set for the pattern. The following provide a means of  en-
        coding non-printing characters in a visible way:
 
          \a          alarm (BEL, \x07)
@@ -484,7 +487,7 @@ SUBJECT LINE SYNTAX
          \t          tab (\x09)
          \v          vertical tab (\x0b)
          \ddd        octal number (up to 3 octal digits); represent a single
-                       code point unless larger than 255 with  the  8-bit  li-
+                       code  point  unless  larger than 255 with the 8-bit li-
        brary
          \o{dd...}   octal number (any number of octal digits} representing a
                        character in UTF mode or a code point
@@ -492,28 +495,28 @@ SUBJECT LINE SYNTAX
          \x{hh...}   hexadecimal number (up to 8 hex digits) representing a
                        character in UTF mode or a code point
 
-       Invoking  \N{U+hh...}  or  \x{hh...} doesn't require the use of the utf
+       Invoking \N{U+hh...} or \x{hh...} doesn't require the use  of  the  utf
        modifier on the pattern. It is always recognized. There may be any num-
        ber of hexadecimal digits inside the braces; invalid values provoke er-
        ror messages but when using \N{U+hh...} with some invalid unicode char-
        acters they will be accepted with a warning instead.
 
-       Note that even in UTF-8 mode, \xhh (and depending of how  large,  \ddd)
-       describe  one byte rather than one character; this makes it possible to
-       construct invalid UTF-8 sequences for testing purposes.  On  the  other
+       Note  that  even in UTF-8 mode, \xhh (and depending of how large, \ddd)
+       describe one byte rather than one character; this makes it possible  to
+       construct  invalid  UTF-8  sequences for testing purposes. On the other
        hand, \x{hh...} is interpreted as a UTF-8 character in UTF-8 mode, only
-       generating  more  than  one  byte  if the value is greater than 127. To
-       avoid the ambiguity it is preferred to use \N{U+hh...} when  describing
-       characters.  When  testing  the 8-bit library not in UTF-8 mode, \x{hh}
+       generating more than one byte if the value  is  greater  than  127.  To
+       avoid  the ambiguity it is preferred to use \N{U+hh...} when describing
+       characters. When testing the 8-bit library not in  UTF-8  mode,  \x{hh}
        generates one byte for values that could fit on it, and causes an error
        for greater values.
 
-       When testing the 16-bit  library,  not  in  UTF-16  mode,  all  4-digit
-       \x{hhhh}  values  are accepted. This makes it possible to construct in-
+       When  testing  the  16-bit  library,  not  in  UTF-16 mode, all 4-digit
+       \x{hhhh} values are accepted. This makes it possible to  construct  in-
        valid UTF-16 sequences for testing purposes.
 
-       When testing the 32-bit library, not in UTF-32 mode, all 4  to  8-digit
-       \x{...}  values  are  accepted. This makes it possible to construct in-
+       When  testing  the 32-bit library, not in UTF-32 mode, all 4 to 8-digit
+       \x{...} values are accepted. This makes it possible  to  construct  in-
        valid UTF-32 sequences for testing purposes.
 
        There is a special backslash sequence that specifies replication of one
@@ -521,31 +524,31 @@ SUBJECT LINE SYNTAX
 
          \[]{}
 
-       This makes it possible to test long strings without having  to  provide
+       This  makes  it possible to test long strings without having to provide
        them as part of the file. For example:
 
          \[abc]{4}
 
-       is  converted to "abcabcabcabc". This feature does not support nesting.
+       is converted to "abcabcabcabc". This feature does not support  nesting.
        To include a closing square bracket in the characters, code it as \x5D.
 
-       A backslash followed by an equals sign marks the  end  of  the  subject
+       A  backslash  followed  by  an equals sign marks the end of the subject
        string and the start of a modifier list. For example:
 
          abc\=notbol,notempty
 
-       If  the  subject  string is empty and \= is followed by whitespace, the
-       line is treated as a comment line, and is not used  for  matching.  For
+       If the subject string is empty and \= is followed  by  whitespace,  the
+       line  is  treated  as a comment line, and is not used for matching. For
        example:
 
          \= This is a comment.
          abc\= This is an invalid modifier list.
 
-       A  backslash  followed by any other non-alphanumeric character just es-
-       capes that character. A backslash followed by anything else  causes  an
-       error.  However,  if the very last character in the line is a backslash
-       (and there is no modifier list), it is ignored. This  gives  a  way  of
-       passing  an  empty line as data, since a real empty line terminates the
+       A backslash followed by any other non-alphanumeric character  just  es-
+       capes  that  character. A backslash followed by anything else causes an
+       error. However, if the very last character in the line is  a  backslash
+       (and  there  is  no  modifier list), it is ignored. This gives a way of
+       passing an empty line as data, since a real empty line  terminates  the
        data input.
 
        If the subject_literal modifier is set for a pattern, all subject lines
@@ -556,19 +559,19 @@ SUBJECT LINE SYNTAX
 
 PATTERN MODIFIERS
 
-       There are several types of modifier that can appear in  pattern  lines.
+       There  are  several types of modifier that can appear in pattern lines.
        Except where noted below, they may also be used in #pattern commands. A
-       pattern's  modifier  list can add to or override default modifiers that
+       pattern's modifier list can add to or override default  modifiers  that
        were set by a previous #pattern command.
 
    Setting compilation options
 
-       The following modifiers set options for pcre2_compile(). Most  of  them
-       set  bits  in  the  options  argument of that function, but those whose
+       The  following  modifiers set options for pcre2_compile(). Most of them
+       set bits in the options argument of  that  function,  but  those  whose
        names start with PCRE2_EXTRA are additional options that are set in the
-       compile context.  Some of these options  have  single-letter  abbrevia-
-       tions.  There  is  special  handling  for /x: if a second x is present,
-       PCRE2_EXTENDED is converted into  PCRE2_EXTENDED_MORE  as  in  Perl.  A
+       compile  context.   Some  of these options have single-letter abbrevia-
+       tions. There is special handling for /x: if  a  second  x  is  present,
+       PCRE2_EXTENDED  is  converted  into  PCRE2_EXTENDED_MORE  as in Perl. A
        third appearance adds PCRE2_EXTENDED as well, though this makes no dif-
        ference to the way pcre2_compile() behaves. See pcre2api for a descrip-
        tion of the effects of these options.
@@ -624,13 +627,13 @@ PATTERN MODIFIERS
              utf                       set PCRE2_UTF
 
        As well as turning on the PCRE2_UTF option, the utf modifier causes all
-       non-printing  characters  in  output  strings  to  be printed using the
-       \x{hh...} notation. Otherwise, those less than 0x100 are output in  hex
-       without  the  curly brackets. Setting utf in 16-bit or 32-bit mode also
-       causes pattern and subject  strings  to  be  translated  to  UTF-16  or
+       non-printing characters in output  strings  to  be  printed  using  the
+       \x{hh...}  notation. Otherwise, those less than 0x100 are output in hex
+       without the curly brackets. Setting utf in 16-bit or 32-bit  mode  also
+       causes  pattern  and  subject  strings  to  be  translated to UTF-16 or
        UTF-32, respectively, before being passed to library functions.
 
-       The  following modifiers enable or disable performance optimizations by
+       The following modifiers enable or disable performance optimizations  by
        calling pcre2_set_optimize() before invoking the regex compiler.
 
              optimization_full      enable all optional optimizations
@@ -647,8 +650,8 @@ PATTERN MODIFIERS
 
    Setting compilation controls
 
-       The following modifiers affect the compilation process or  request  in-
-       formation  about the pattern. There are single-letter abbreviations for
+       The  following  modifiers affect the compilation process or request in-
+       formation about the pattern. There are single-letter abbreviations  for
        some that are heavily used in the test files.
 
          /B  bincode                   show binary code without lengths
@@ -692,35 +695,35 @@ PATTERN MODIFIERS
 
    Newline and \R handling
 
-       The bsr modifier specifies what \R in a pattern should match. If it  is
-       set  to  "anycrlf",  \R  matches  CR, LF, or CRLF only. If it is set to
-       "unicode", \R matches any Unicode newline sequence. The default can  be
+       The  bsr modifier specifies what \R in a pattern should match. If it is
+       set to "anycrlf", \R matches CR, LF, or CRLF only.  If  it  is  set  to
+       "unicode",  \R matches any Unicode newline sequence. The default can be
        specified when PCRE2 is built; if it is not, the default is set to Uni-
        code.
 
-       The  newline  modifier specifies which characters are to be interpreted
+       The newline modifier specifies which characters are to  be  interpreted
        as newlines, both in the pattern and in subject lines. The type must be
        one of CR, LF, CRLF, ANYCRLF, ANY, or NUL (in upper or lower case).
 
    Information about a pattern
 
-       The debug modifier is a shorthand for info,fullbincode, requesting  all
+       The  debug modifier is a shorthand for info,fullbincode, requesting all
        available information.
 
        The bincode modifier causes a representation of the compiled code to be
-       output  after compilation. This information does not contain length and
+       output after compilation. This information does not contain length  and
        offset values, which ensures that the same output is generated for dif-
-       ferent internal link sizes and different code  unit  widths.  By  using
-       bincode,  the  same  regression tests can be used in different environ-
+       ferent  internal  link  sizes  and different code unit widths. By using
+       bincode, the same regression tests can be used  in  different  environ-
        ments.
 
-       The fullbincode modifier, by contrast, does include length  and  offset
-       values.  This is used in a few special tests that run only for specific
+       The  fullbincode  modifier, by contrast, does include length and offset
+       values. This is used in a few special tests that run only for  specific
        code unit widths and link sizes, and is also useful for one-off tests.
 
-       The info modifier  requests  information  about  the  compiled  pattern
-       (whether  it  is anchored, has a fixed first character, and so on). The
-       information is obtained from the  pcre2_pattern_info()  function.  Here
+       The  info  modifier  requests  information  about  the compiled pattern
+       (whether it is anchored, has a fixed first character, and so  on).  The
+       information  is  obtained  from the pcre2_pattern_info() function. Here
        are some typical examples:
 
            re> /(?i)(^a|^b)/m,info
@@ -738,136 +741,136 @@ PATTERN MODIFIERS
          Last code unit = 'c' (caseless)
          Subject length lower bound = 3
 
-       "Compile  options"  are those specified by modifiers; "overall options"
-       have added options that are taken or deduced from the pattern. If  both
-       sets  of  options are the same, just a single "options" line is output;
-       if there are no options, the line is  omitted.  "First  code  unit"  is
-       where  any  match must start; if there is more than one they are listed
-       as "starting code units". "Last code unit" is  the  last  literal  code
-       unit  that  must  be  present in any match. This is not necessarily the
-       last character. These lines are omitted if no starting or  ending  code
-       units   are   recorded.   The  subject  length  line  is  omitted  when
-       no_start_optimize is set because the minimum length is  not  calculated
+       "Compile options" are those specified by modifiers;  "overall  options"
+       have  added options that are taken or deduced from the pattern. If both
+       sets of options are the same, just a single "options" line  is  output;
+       if  there  are  no  options,  the line is omitted. "First code unit" is
+       where any match must start; if there is more than one they  are  listed
+       as  "starting  code  units".  "Last code unit" is the last literal code
+       unit that must be present in any match. This  is  not  necessarily  the
+       last  character.  These lines are omitted if no starting or ending code
+       units  are  recorded.  The  subject  length  line   is   omitted   when
+       no_start_optimize  is  set because the minimum length is not calculated
        when it can never be used.
 
-       The  framesize modifier shows the size, in bytes, of each storage frame
-       used by pcre2_match() for handling backtracking. The  size  depends  on
-       the  number  of capturing parentheses in the pattern. A vector of these
-       frames is used at matching time; its overall size  is  shown  when  the
+       The framesize modifier shows the size, in bytes, of each storage  frame
+       used  by  pcre2_match()  for handling backtracking. The size depends on
+       the number of capturing parentheses in the pattern. A vector  of  these
+       frames  is  used  at  matching time; its overall size is shown when the
        heaframes_size subject modifier is set.
 
-       The  callout_info  modifier requests information about all the callouts
+       The callout_info modifier requests information about all  the  callouts
        in the pattern. A list of them is output at the end of any other infor-
        mation that is requested. For each callout, either its number or string
        is given, followed by the item that follows it in the pattern.
 
    Passing a NULL context
 
-       Normally, pcre2test passes a context block to pcre2_compile().  If  the
-       null_context  modifier  is  set,  however,  NULL is passed. This is for
-       testing that pcre2_compile() behaves correctly in this  case  (it  uses
+       Normally,  pcre2test  passes a context block to pcre2_compile(). If the
+       null_context modifier is set, however, NULL  is  passed.  This  is  for
+       testing  that  pcre2_compile()  behaves correctly in this case (it uses
        default values).
 
    Passing a NULL pattern
 
-       The  null_pattern  modifier  is for testing the behaviour of pcre2_com-
-       pile() when the pattern argument is NULL. The length  value  passed  is
+       The null_pattern modifier is for testing the  behaviour  of  pcre2_com-
+       pile()  when  the  pattern argument is NULL. The length value passed is
        the default PCRE2_ZERO_TERMINATED unless use_length is set.  Any length
        other than zero causes an error.
 
    Specifying pattern characters in hexadecimal
 
-       The  hex  modifier specifies that the characters of the pattern, except
-       for substrings enclosed in single or double quotes, are  to  be  inter-
-       preted  as  pairs  of hexadecimal digits. This feature is provided as a
+       The hex modifier specifies that the characters of the  pattern,  except
+       for  substrings  enclosed  in single or double quotes, are to be inter-
+       preted as pairs of hexadecimal digits. This feature is  provided  as  a
        way of creating patterns that contain binary zeros and other non-print-
-       ing characters. White space is permitted between pairs of  digits.  For
+       ing  characters.  White space is permitted between pairs of digits. For
        example, this pattern contains three characters:
 
          /ab 32 59/hex
 
-       Parts  of  such  a  pattern are taken literally if quoted. This pattern
-       contains nine characters, only two of which are specified in  hexadeci-
+       Parts of such a pattern are taken literally  if  quoted.  This  pattern
+       contains  nine characters, only two of which are specified in hexadeci-
        mal:
 
          /ab "literal" 32/hex
 
-       Either  single or double quotes may be used. There is no way of includ-
-       ing the delimiter within a substring. The hex and expand modifiers  are
+       Either single or double quotes may be used. There is no way of  includ-
+       ing  the delimiter within a substring. The hex and expand modifiers are
        mutually exclusive.
 
    Specifying the pattern's length
 
        By default, patterns are passed to the compiling functions as zero-ter-
-       minated  strings but can be passed by length instead of being zero-ter-
-       minated. The use_length modifier causes this to happen. Using a  length
-       happens  automatically  (whether  or not use_length is set) when hex is
-       set, because patterns specified in hexadecimal may contain  binary  ze-
+       minated strings but can be passed by length instead of being  zero-ter-
+       minated.  The use_length modifier causes this to happen. Using a length
+       happens automatically (whether or not use_length is set)  when  hex  is
+       set,  because  patterns specified in hexadecimal may contain binary ze-
        ros.
 
        If hex or use_length is used with the POSIX wrapper API (see "Using the
-       POSIX  wrapper  API" below), the REG_PEND extension is used to pass the
+       POSIX wrapper API" below), the REG_PEND extension is used to  pass  the
        pattern's length.
 
    Specifying a maximum for variable lookbehinds
 
-       Variable lookbehind assertions are supported only  if,  for  each  one,
+       Variable  lookbehind  assertions  are  supported only if, for each one,
        there is a maximum length (in characters) that it can match. There is a
        limit on this, whose default can be set at build time, with an ultimate
-       default    of    255.   The   max_varlookbehind   modifier   uses   the
+       default   of   255.   The   max_varlookbehind   modifier    uses    the
        pcre2_set_max_varlookbehind() function to change the limit. Lookbehinds
-       whose branches each match a fixed length are limited to  65535  charac-
+       whose  branches  each match a fixed length are limited to 65535 charac-
        ters per branch.
 
    Specifying wide characters in 16-bit and 32-bit modes
 
        In 16-bit and 32-bit modes, all input is automatically treated as UTF-8
-       and  translated  to  UTF-16 or UTF-32 when the utf modifier is set. For
+       and translated to UTF-16 or UTF-32 when the utf modifier  is  set.  For
        testing the 16-bit and 32-bit libraries in non-UTF mode, the utf8_input
-       modifier can be used. It is mutually exclusive with  utf.  Input  lines
+       modifier  can  be  used. It is mutually exclusive with utf. Input lines
        are interpreted as UTF-8 as a means of specifying wide characters. More
        details are given in "Input encoding" above.
 
    Generating long repetitive patterns
 
-       Some  tests use long patterns that are very repetitive. Instead of cre-
-       ating a very long input line for such a pattern, you can use a  special
-       repetition  feature,  similar  to  the  one described for subject lines
-       above. If the expand modifier is present on a  pattern,  parts  of  the
+       Some tests use long patterns that are very repetitive. Instead of  cre-
+       ating  a very long input line for such a pattern, you can use a special
+       repetition feature, similar to the  one  described  for  subject  lines
+       above.  If  the  expand  modifier is present on a pattern, parts of the
        pattern that have the form
 
          \[]{}
 
        are expanded before the pattern is passed to pcre2_compile(). For exam-
        ple, \[AB]{6000} is expanded to "ABAB..." 6000 times. This construction
-       cannot  be  nested. An initial "\[" sequence is recognized only if "]{"
-       followed by decimal digits and "}" is found later in  the  pattern.  If
+       cannot be nested. An initial "\[" sequence is recognized only  if  "]{"
+       followed  by  decimal  digits and "}" is found later in the pattern. If
        not, the characters remain in the pattern unaltered. The expand and hex
        modifiers are mutually exclusive.
 
-       If  part  of an expanded pattern looks like an expansion, but is really
+       If part of an expanded pattern looks like an expansion, but  is  really
        part of the actual pattern, unwanted expansion can be avoided by giving
        two values in the quantifier. For example, \[AB]{6000,6000} is not rec-
        ognized as an expansion item.
 
-       If the info modifier is set on an expanded pattern, the result  of  the
+       If  the  info modifier is set on an expanded pattern, the result of the
        expansion is included in the information that is output.
 
    JIT compilation
 
-       Just-in-time  (JIT)  compiling  is  a heavyweight optimization that can
-       greatly speed up pattern matching. See the pcre2jit  documentation  for
-       details.  JIT  compiling  happens, optionally, after a pattern has been
-       successfully compiled into an internal form. The JIT compiler  converts
+       Just-in-time (JIT) compiling is a  heavyweight  optimization  that  can
+       greatly  speed  up pattern matching. See the pcre2jit documentation for
+       details. JIT compiling happens, optionally, after a  pattern  has  been
+       successfully  compiled into an internal form. The JIT compiler converts
        this to optimized machine code. It needs to know whether the match-time
        options PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT are going to be used,
-       because  different  code  is generated for the different cases. See the
-       partial modifier in "Subject Modifiers" below for details of how  these
+       because different code is generated for the different  cases.  See  the
+       partial  modifier in "Subject Modifiers" below for details of how these
        options are specified for each match attempt.
 
        JIT compilation is requested by the jit pattern modifier, which may op-
-       tionally  be  followed by an equals sign and a number in the range 0 to
-       7.  The three bits that make up the number specify which of  the  three
+       tionally be followed by an equals sign and a number in the range  0  to
+       7.   The  three bits that make up the number specify which of the three
        JIT operating modes are to be compiled:
 
          1  compile JIT code for non-partial matching
@@ -884,31 +887,31 @@ PATTERN MODIFIERS
          6  soft and hard partial matching only
          7  all three modes
 
-       If  no  number  is  given,  7 is assumed. The phrase "partial matching"
+       If no number is given, 7 is  assumed.  The  phrase  "partial  matching"
        means a call to pcre2_match() with either the PCRE2_PARTIAL_SOFT or the
-       PCRE2_PARTIAL_HARD option set. Note that such a call may return a  com-
+       PCRE2_PARTIAL_HARD  option set. Note that such a call may return a com-
        plete match; the options enable the possibility of a partial match, but
-       do  not  require it. Note also that if you request JIT compilation only
-       for partial matching (for example, jit=2) but do not  set  the  partial
-       modifier  on  a  subject line, that match will not use JIT code because
+       do not require it. Note also that if you request JIT  compilation  only
+       for  partial  matching  (for example, jit=2) but do not set the partial
+       modifier on a subject line, that match will not use  JIT  code  because
        none was compiled for non-partial matching.
 
-       If JIT compilation is successful, the compiled JIT code will  automati-
+       If  JIT compilation is successful, the compiled JIT code will automati-
        cally be used when an appropriate type of match is run, except when in-
-       compatible  run-time  options  are specified. For more details, see the
-       pcre2jit documentation. See also the jitstack modifier below for a  way
+       compatible run-time options are specified. For more  details,  see  the
+       pcre2jit  documentation. See also the jitstack modifier below for a way
        of setting the size of the JIT stack.
 
-       If  the  jitfast  modifier is specified, matching is done using the JIT
-       "fast path" interface, pcre2_jit_match(), which skips some of the  san-
-       ity  checks that are done by pcre2_match(), and of course does not work
-       when JIT is not supported. If jitfast is specified without  jit,  jit=7
+       If the jitfast modifier is specified, matching is done  using  the  JIT
+       "fast  path" interface, pcre2_jit_match(), which skips some of the san-
+       ity checks that are done by pcre2_match(), and of course does not  work
+       when  JIT  is not supported. If jitfast is specified without jit, jit=7
        is assumed.
 
-       If  the jitverify modifier is specified, information about the compiled
-       pattern shows whether JIT compilation was or  was  not  successful.  If
-       jitverify  is  specified without jit, jit=7 is assumed. If JIT compila-
-       tion is successful when jitverify is set, the text "(JIT)" is added  to
+       If the jitverify modifier is specified, information about the  compiled
+       pattern  shows  whether  JIT  compilation was or was not successful. If
+       jitverify is specified without jit, jit=7 is assumed. If  JIT  compila-
+       tion  is successful when jitverify is set, the text "(JIT)" is added to
        the first output line after a match or non match when JIT-compiled code
        was actually used in the match.
 
@@ -919,19 +922,19 @@ PATTERN MODIFIERS
          /pattern/locale=fr_FR
 
        The given locale is set, pcre2_maketables() is called to build a set of
-       character  tables for the locale, and this is then passed to pcre2_com-
-       pile() when compiling the regular expression. The same tables are  used
-       when  matching the following subject lines. The locale modifier applies
+       character tables for the locale, and this is then passed to  pcre2_com-
+       pile()  when compiling the regular expression. The same tables are used
+       when matching the following subject lines. The locale modifier  applies
        only to the pattern on which it appears, but can be given in a #pattern
-       command if a default is needed. Setting a locale and alternate  charac-
+       command  if a default is needed. Setting a locale and alternate charac-
        ter tables are mutually exclusive.
 
    Showing pattern memory
 
        The memory modifier causes the size in bytes of the memory used to hold
-       the  compiled  pattern  to be output. This does not include the size of
-       the pcre2_code block; it is just the actual compiled data. If the  pat-
-       tern  is  subsequently  passed to the JIT compiler, the size of the JIT
+       the compiled pattern to be output. This does not include  the  size  of
+       the  pcre2_code block; it is just the actual compiled data. If the pat-
+       tern is subsequently passed to the JIT compiler, the size  of  the  JIT
        compiled code is also output. Here is an example:
 
            re> /a(b)c/jit,memory
@@ -941,34 +944,34 @@ PATTERN MODIFIERS
 
    Limiting nested parentheses
 
-       The parens_nest_limit modifier sets a limit  on  the  depth  of  nested
-       parentheses  in a pattern. Breaching the limit causes a compilation er-
-       ror.  The default for the library is  set  when  PCRE2  is  built,  but
-       pcre2test  sets  its  own default of 220, which is required for running
+       The  parens_nest_limit  modifier  sets  a  limit on the depth of nested
+       parentheses in a pattern. Breaching the limit causes a compilation  er-
+       ror.   The  default  for  the  library  is set when PCRE2 is built, but
+       pcre2test sets its own default of 220, which is  required  for  running
        the standard test suite.
 
    Limiting the pattern length
 
-       The max_pattern_length modifier sets a limit, in  code  units,  to  the
+       The  max_pattern_length  modifier  sets  a limit, in code units, to the
        length of pattern that pcre2_compile() will accept. Breaching the limit
-       causes  a  compilation  error.  The  default  is  the  largest number a
+       causes a compilation  error.  The  default  is  the  largest  number  a
        PCRE2_SIZE variable can hold (essentially unlimited).
 
    Limiting the size of a compiled pattern
 
        The max_pattern_compiled_length modifier sets a limit, in bytes, to the
        amount of memory used by a compiled pattern. Breaching the limit causes
-       a compilation error. The default is the  largest  number  a  PCRE2_SIZE
+       a  compilation  error.  The  default is the largest number a PCRE2_SIZE
        variable can hold (essentially unlimited).
 
    Using the POSIX wrapper API
 
-       The  posix  and posix_nosub modifiers cause pcre2test to call PCRE2 via
-       the POSIX wrapper API rather than its native API. When  posix_nosub  is
-       used,  the  POSIX  option  REG_NOSUB  is passed to regcomp(). The POSIX
-       wrapper supports only the 8-bit library. Note that it  does  not  imply
+       The posix and posix_nosub modifiers cause pcre2test to call  PCRE2  via
+       the  POSIX  wrapper API rather than its native API. When posix_nosub is
+       used, the POSIX option REG_NOSUB is  passed  to  regcomp().  The  POSIX
+       wrapper  supports  only  the 8-bit library. Note that it does not imply
        POSIX matching semantics; for more detail see the pcre2posix documenta-
-       tion.  The  following  pattern  modifiers set options for the regcomp()
+       tion. The following pattern modifiers set  options  for  the  regcomp()
        function:
 
          caseless           REG_ICASE
@@ -978,42 +981,42 @@ PATTERN MODIFIERS
          ucp                REG_UCP        )   the POSIX standard
          utf                REG_UTF8       )
 
-       The regerror_buffsize modifier specifies a size for  the  error  buffer
-       that  is  passed to regerror() in the event of a compilation error. For
+       The  regerror_buffsize  modifier  specifies a size for the error buffer
+       that is passed to regerror() in the event of a compilation  error.  For
        example:
 
          /abc/posix,regerror_buffsize=20
 
-       This provides a means of testing the behaviour of regerror()  when  the
-       buffer  is  too  small  for the error message. If this modifier has not
+       This  provides  a means of testing the behaviour of regerror() when the
+       buffer is too small for the error message. If  this  modifier  has  not
        been set, a large buffer is used.
 
-       The aftertext and allaftertext subject modifiers work as described  be-
+       The  aftertext and allaftertext subject modifiers work as described be-
        low. All other modifiers are either ignored, with a warning message, or
        cause an error.
 
-       The  pattern  is passed to regcomp() as a zero-terminated string by de-
+       The pattern is passed to regcomp() as a zero-terminated string  by  de-
        fault, but if the use_length or hex modifiers are set, the REG_PEND ex-
        tension is used to pass it by length.
 
    Testing the stack guard feature
 
-       The stackguard modifier is used  to  test  the  use  of  pcre2_set_com-
-       pile_recursion_guard(),  a  function  that  is provided to enable stack
-       availability to be checked during compilation (see the  pcre2api  docu-
-       mentation  for  details).  If  the  number specified by the modifier is
+       The  stackguard  modifier  is  used  to  test the use of pcre2_set_com-
+       pile_recursion_guard(), a function that is  provided  to  enable  stack
+       availability  to  be checked during compilation (see the pcre2api docu-
+       mentation for details). If the number  specified  by  the  modifier  is
        greater than zero, pcre2_set_compile_recursion_guard() is called to set
-       up callback from pcre2_compile() to a local function. The  argument  it
-       receives  is  the current nesting parenthesis depth; if this is greater
+       up  callback  from pcre2_compile() to a local function. The argument it
+       receives is the current nesting parenthesis depth; if this  is  greater
        than the value given by the modifier, non-zero is returned, causing the
        compilation to be aborted.
 
    Using alternative character tables
 
-       The value specified for the tables modifier must be one of  the  digits
+       The  value  specified for the tables modifier must be one of the digits
        0, 1, 2, or 3. It causes a specific set of built-in character tables to
-       be  passed to pcre2_compile(). This is used in the PCRE2 tests to check
-       behaviour with different character tables. The digit specifies the  ta-
+       be passed to pcre2_compile(). This is used in the PCRE2 tests to  check
+       behaviour  with different character tables. The digit specifies the ta-
        bles as follows:
 
          0   do not pass any special character tables
@@ -1024,15 +1027,15 @@ PATTERN MODIFIERS
 
        In tables 2, some characters whose codes are greater than 128 are iden-
        tified as letters, digits, spaces, etc. Tables 3 can be used only after
-       a  #loadtables  command has loaded them from a binary file. Setting al-
+       a #loadtables command has loaded them from a binary file.  Setting  al-
        ternate character tables and a locale are mutually exclusive.
 
    Setting certain match controls
 
        The following modifiers are really subject modifiers, and are described
-       under "Subject Modifiers" below. However, they may  be  included  in  a
-       pattern's  modifier  list, in which case they are applied to every sub-
-       ject line that is processed with that pattern. These modifiers  do  not
+       under  "Subject  Modifiers"  below.  However, they may be included in a
+       pattern's modifier list, in which case they are applied to  every  sub-
+       ject  line  that is processed with that pattern. These modifiers do not
        affect the compilation process.
 
              aftertext                   show text after match
@@ -1059,39 +1062,39 @@ PATTERN MODIFIERS
              substitute_unknown_unset    use PCRE2_SUBSTITUTE_UNKNOWN_UNSET
              substitute_unset_empty      use PCRE2_SUBSTITUTE_UNSET_EMPTY
 
-       These  modifiers may not appear in a #pattern command. If you want them
+       These modifiers may not appear in a #pattern command. If you want  them
        as defaults, set them in a #subject command.
 
    Specifying literal subject lines
 
-       If the subject_literal modifier is present on a pattern, all  the  sub-
+       If  the  subject_literal modifier is present on a pattern, all the sub-
        ject lines that it matches are taken as literal strings, with no inter-
-       pretation  of  backslashes. It is not possible to set subject modifiers
-       on such lines, but any that are set as defaults by a  #subject  command
+       pretation of backslashes. It is not possible to set  subject  modifiers
+       on  such  lines, but any that are set as defaults by a #subject command
        are recognized.
 
    Saving a compiled pattern
 
-       When  a  pattern with the push modifier is successfully compiled, it is
-       pushed onto a stack of compiled patterns,  and  pcre2test  expects  the
-       next  line to contain a new pattern (or a command) instead of a subject
+       When a pattern with the push modifier is successfully compiled,  it  is
+       pushed  onto  a  stack  of compiled patterns, and pcre2test expects the
+       next line to contain a new pattern (or a command) instead of a  subject
        line. This facility is used when saving compiled patterns to a file, as
-       described in the section entitled "Saving and restoring  compiled  pat-
-       terns"  below.  If pushcopy is used instead of push, a copy of the com-
-       piled pattern is stacked, leaving the original  as  current,  ready  to
-       match  the  following  input  lines. This provides a way of testing the
-       pcre2_code_copy() function.  The push and pushcopy  modifiers  are  in-
-       compatible  with compilation modifiers such as global that act at match
+       described  in  the section entitled "Saving and restoring compiled pat-
+       terns" below.  If pushcopy is used instead of push, a copy of the  com-
+       piled  pattern  is  stacked,  leaving the original as current, ready to
+       match the following input lines. This provides a  way  of  testing  the
+       pcre2_code_copy()  function.   The push and pushcopy  modifiers are in-
+       compatible with compilation modifiers such as global that act at  match
        time. Any that are specified are ignored (for the stacked copy), with a
-       warning message, except for replace, which causes an error.  Note  that
-       jitverify,  which  is allowed, does not carry through to any subsequent
+       warning  message,  except for replace, which causes an error. Note that
+       jitverify, which is allowed, does not carry through to  any  subsequent
        matching that uses a stacked pattern.
 
    Testing foreign pattern conversion
 
-       The experimental foreign pattern conversion functions in PCRE2  can  be
-       tested  by  setting the convert modifier. Its argument is a colon-sepa-
-       rated list  of  options,  which  set  the  equivalent  option  for  the
+       The  experimental  foreign pattern conversion functions in PCRE2 can be
+       tested by setting the convert modifier. Its argument is  a  colon-sepa-
+       rated  list  of  options,  which  set  the  equivalent  option  for the
        pcre2_pattern_convert() function:
 
          glob                    PCRE2_CONVERT_GLOB
@@ -1103,19 +1106,19 @@ PATTERN MODIFIERS
 
        The "unset" value is useful for turning off a default that has been set
        by a #pattern command. When one of these options is set, the input pat-
-       tern  is  passed  to pcre2_pattern_convert(). If the conversion is suc-
-       cessful, the result is reflected in  the  output  and  then  passed  to
+       tern is passed to pcre2_pattern_convert(). If the  conversion  is  suc-
+       cessful,  the  result  is  reflected  in  the output and then passed to
        pcre2_compile(). The normal utf and no_utf_check options, if set, cause
-       the  PCRE2_CONVERT_UTF  and  PCRE2_CONVERT_NO_UTF_CHECK  options  to be
+       the PCRE2_CONVERT_UTF  and  PCRE2_CONVERT_NO_UTF_CHECK  options  to  be
        passed to pcre2_pattern_convert().
 
        By default, the conversion function is allowed to allocate a buffer for
-       its output. However, if the convert_length modifier is set to  a  value
-       greater  than zero, pcre2test passes a buffer of the given length. This
+       its  output.  However, if the convert_length modifier is set to a value
+       greater than zero, pcre2test passes a buffer of the given length.  This
        makes it possible to test the length check.
 
-       The convert_glob_escape and  convert_glob_separator  modifiers  can  be
-       used  to  specify the escape and separator characters for glob process-
+       The  convert_glob_escape  and  convert_glob_separator  modifiers can be
+       used to specify the escape and separator characters for  glob  process-
        ing, overriding the defaults, which are operating-system dependent.
 
 
@@ -1126,7 +1129,7 @@ SUBJECT MODIFIERS
 
    Setting match options
 
-       The   following   modifiers   set   options   for   pcre2_match()    or
+       The    following   modifiers   set   options   for   pcre2_match()   or
        pcre2_dfa_match(). See pcre2api for a description of their effects.
 
              anchored                   set PCRE2_ANCHORED
@@ -1144,35 +1147,35 @@ SUBJECT MODIFIERS
              partial_hard (or ph)       set PCRE2_PARTIAL_HARD
              partial_soft (or ps)       set PCRE2_PARTIAL_SOFT
 
-       The  partial matching modifiers are provided with abbreviations because
+       The partial matching modifiers are provided with abbreviations  because
        they appear frequently in tests.
 
-       If the posix or posix_nosub modifier was present on the pattern,  caus-
+       If  the posix or posix_nosub modifier was present on the pattern, caus-
        ing the POSIX wrapper API to be used, the only option-setting modifiers
        that have any effect are notbol, notempty, and noteol, causing REG_NOT-
-       BOL,  REG_NOTEMPTY,  and  REG_NOTEOL,  respectively,  to  be  passed to
+       BOL, REG_NOTEMPTY,  and  REG_NOTEOL,  respectively,  to  be  passed  to
        regexec(). The other modifiers are ignored, with a warning message.
 
-       There is one additional modifier that can be used with the POSIX  wrap-
+       There  is one additional modifier that can be used with the POSIX wrap-
        per. It is ignored (with a warning) if used for non-POSIX matching.
 
              posix_startend=[:]
 
-       This  causes  the  subject  string  to be passed to regexec() using the
-       REG_STARTEND option, which uses offsets to specify which  part  of  the
-       string  is  searched.  If  only  one number is given, the end offset is
-       passed as the end of the subject string. For more detail  of  REG_STAR-
-       TEND,  see the pcre2posix documentation. If the subject string contains
-       binary zeros (coded as escapes such as \x{00}  because  pcre2test  does
+       This causes the subject string to be  passed  to  regexec()  using  the
+       REG_STARTEND  option,  which  uses offsets to specify which part of the
+       string is searched. If only one number is  given,  the  end  offset  is
+       passed  as  the end of the subject string. For more detail of REG_STAR-
+       TEND, see the pcre2posix documentation. If the subject string  contains
+       binary  zeros  (coded  as escapes such as \x{00} because pcre2test does
        not support actual binary zeros in its input), you must use posix_star-
        tend to specify its length.
 
    Setting match controls
 
-       The  following  modifiers  affect the matching process or request addi-
-       tional information. Some of them may also be  specified  on  a  pattern
-       line  (see  above), in which case they apply to every subject line that
-       is matched against that pattern, but can be overridden by modifiers  on
+       The following modifiers affect the matching process  or  request  addi-
+       tional  information.  Some  of  them may also be specified on a pattern
+       line (see above), in which case they apply to every subject  line  that
+       is  matched against that pattern, but can be overridden by modifiers on
        the subject.
 
              aftertext                  show text after match
@@ -1226,29 +1229,29 @@ SUBJECT MODIFIERS
              zero_terminate             pass the subject as zero-terminated
 
        The effects of these modifiers are described in the following sections.
-       When  matching  via the POSIX wrapper API, the aftertext, allaftertext,
-       and ovector subject modifiers work as described below. All other  modi-
+       When matching via the POSIX wrapper API, the  aftertext,  allaftertext,
+       and  ovector subject modifiers work as described below. All other modi-
        fiers are either ignored, with a warning message, or cause an error.
 
    Showing more text
 
-       The  aftertext modifier requests that as well as outputting the part of
+       The aftertext modifier requests that as well as outputting the part  of
        the subject string that matched the entire pattern, pcre2test should in
        addition output the remainder of the subject string. This is useful for
        tests where the subject contains multiple copies of the same substring.
-       The allaftertext modifier requests the same action  for  captured  sub-
+       The  allaftertext  modifier  requests the same action for captured sub-
        strings as well as the main matched substring. In each case the remain-
        der is output on the following line with a plus character following the
        capture number.
 
-       The  allusedtext modifier requests that all the text that was consulted
-       during a successful pattern match by the interpreter should  be  shown,
-       for  both  full  and partial matches. This feature is not supported for
-       JIT matching, and if requested with JIT it is ignored (with  a  warning
-       message).  Setting this modifier affects the output if there is a look-
-       behind at the start of a match, or, for a complete match,  a  lookahead
+       The allusedtext modifier requests that all the text that was  consulted
+       during  a  successful pattern match by the interpreter should be shown,
+       for both full and partial matches. This feature is  not  supported  for
+       JIT  matching,  and if requested with JIT it is ignored (with a warning
+       message). Setting this modifier affects the output if there is a  look-
+       behind  at  the start of a match, or, for a complete match, a lookahead
        at the end, or if \K is used in the pattern. Characters that precede or
-       follow  the start and end of the actual match are indicated in the out-
+       follow the start and end of the actual match are indicated in the  out-
        put by '<' or '>' characters underneath them.  Here is an example:
 
            re> /(?<=pqr)abc(?=xyz)/
@@ -1259,16 +1262,16 @@ SUBJECT MODIFIERS
          Partial match: pqrabcxy
                         <<<
 
-       The first, complete match shows that the matched string is "abc",  with
-       the  preceding  and  following strings "pqr" and "xyz" having been con-
-       sulted during the match (when processing the assertions).  The  partial
+       The  first, complete match shows that the matched string is "abc", with
+       the preceding and following strings "pqr" and "xyz"  having  been  con-
+       sulted  during  the match (when processing the assertions). The partial
        match can indicate only the preceding string.
 
-       The  startchar  modifier  requests  that the starting character for the
-       match be indicated, if it is different to  the  start  of  the  matched
+       The startchar modifier requests that the  starting  character  for  the
+       match  be  indicated,  if  it  is different to the start of the matched
        string. The only time when this occurs is when \K has been processed as
        part of the match. In this situation, the output for the matched string
-       is  displayed  from  the  starting  character instead of from the match
+       is displayed from the starting character  instead  of  from  the  match
        point, with circumflex characters under the earlier characters. For ex-
        ample:
 
@@ -1277,7 +1280,7 @@ SUBJECT MODIFIERS
           0: abcxyz
              ^^^
 
-       Unlike allusedtext, the startchar modifier can be used with JIT.   How-
+       Unlike  allusedtext, the startchar modifier can be used with JIT.  How-
        ever, these two modifiers are mutually exclusive.
 
    Showing the value of all capture groups
@@ -1285,104 +1288,104 @@ SUBJECT MODIFIERS
        The allcaptures modifier requests that the values of all potential cap-
        tured parentheses be output after a match. By default, only those up to
        the highest one actually used in the match are output (corresponding to
-       the  return  code from pcre2_match()). Groups that did not take part in
-       the match are output as "". This modifier is  not  relevant  for
-       DFA  matching (which does no capturing) and does not apply when replace
+       the return code from pcre2_match()). Groups that did not take  part  in
+       the  match  are  output as "". This modifier is not relevant for
+       DFA matching (which does no capturing) and does not apply when  replace
        is specified; it is ignored, with a warning message, if present.
 
    Showing the entire ovector, for all outcomes
 
        The allvector modifier requests that the entire ovector be shown, what-
        ever the outcome of the match. Compare allcaptures, which shows only up
-       to the maximum number of capture groups for the pattern, and then  only
-       for  a successful complete non-DFA match. This modifier, which acts af-
-       ter any match result, and also for DFA matching, provides  a  means  of
-       checking  that there are no unexpected modifications to ovector fields.
-       Before each match attempt, the ovector is filled with a special  value,
-       and  if  this  is  found  in  both  elements of a capturing pair, "" is output. After a successful  match,  this  applies  to  all
-       groups  after the maximum capture group for the pattern. In other cases
-       it applies to the entire ovector. After a partial match, the first  two
-       elements  are  the only ones that should be set. After a DFA match, the
-       amount of ovector that is used depends on the number  of  matches  that
+       to  the maximum number of capture groups for the pattern, and then only
+       for a successful complete non-DFA match. This modifier, which acts  af-
+       ter  any  match  result, and also for DFA matching, provides a means of
+       checking that there are no unexpected modifications to ovector  fields.
+       Before  each match attempt, the ovector is filled with a special value,
+       and if this is found in  both  elements  of  a  capturing  pair,  ""  is  output.  After  a  successful match, this applies to all
+       groups after the maximum capture group for the pattern. In other  cases
+       it  applies to the entire ovector. After a partial match, the first two
+       elements are the only ones that should be set. After a DFA  match,  the
+       amount  of  ovector  that is used depends on the number of matches that
        were found.
 
    Testing pattern callouts
 
-       A  callout function is supplied when pcre2test calls the library match-
-       ing functions, unless callout_none is specified. Its behaviour  can  be
-       controlled  by  various  modifiers  listed above whose names begin with
-       callout_. Details are given in the section entitled  "Callouts"  below.
-       Testing  callouts  from  pcre2_substitute()  is described separately in
+       A callout function is supplied when pcre2test calls the library  match-
+       ing  functions,  unless callout_none is specified. Its behaviour can be
+       controlled by various modifiers listed above  whose  names  begin  with
+       callout_.  Details  are given in the section entitled "Callouts" below.
+       Testing callouts from pcre2_substitute()  is  described  separately  in
        "Testing the substitution function" below.
 
    Finding all matches in a string
 
        Searching for all possible matches within a subject can be requested by
-       the global or altglobal modifier. After finding a match,  the  matching
-       function  is  called  again to search the remainder of the subject. The
-       difference between global and altglobal is that  the  former  uses  the
-       start_offset  argument  to  pcre2_match() or pcre2_dfa_match() to start
-       searching at a new point within the entire string (which is  what  Perl
+       the  global  or altglobal modifier. After finding a match, the matching
+       function is called again to search the remainder of  the  subject.  The
+       difference  between  global  and  altglobal is that the former uses the
+       start_offset argument to pcre2_match() or  pcre2_dfa_match()  to  start
+       searching  at  a new point within the entire string (which is what Perl
        does), whereas the latter passes over a shortened subject. This makes a
        difference to the matching process if the pattern begins with a lookbe-
        hind assertion (including \b or \B).
 
-       If  an  empty  string  is  matched,  the  next  match  is done with the
+       If an empty string  is  matched,  the  next  match  is  done  with  the
        PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set, in order to search
        for another, non-empty, match at the same point in the subject. If this
-       match fails, the start offset is advanced, and the normal match is  re-
-       tried.  This imitates the way Perl handles such cases when using the /g
-       modifier or the split() function. Normally, the  start  offset  is  ad-
-       vanced  by one character, but if the newline convention recognizes CRLF
-       as a newline, and the current character is CR followed by  LF,  an  ad-
+       match  fails, the start offset is advanced, and the normal match is re-
+       tried. This imitates the way Perl handles such cases when using the  /g
+       modifier  or  the  split()  function. Normally, the start offset is ad-
+       vanced by one character, but if the newline convention recognizes  CRLF
+       as  a  newline,  and the current character is CR followed by LF, an ad-
        vance of two characters occurs.
 
    Testing substring extraction functions
 
-       The  copy  and  get  modifiers  can  be  used  to  test  the pcre2_sub-
+       The copy  and  get  modifiers  can  be  used  to  test  the  pcre2_sub-
        string_copy_xxx() and pcre2_substring_get_xxx() functions.  They can be
        given more than once, and each can specify a capture group name or num-
        ber, for example:
 
           abcd\=copy=1,copy=3,get=G1
 
-       If the #subject command is used to set default copy and/or  get  lists,
-       these  can  be unset by specifying a negative number to cancel all num-
+       If  the  #subject command is used to set default copy and/or get lists,
+       these can be unset by specifying a negative number to cancel  all  num-
        bered groups and an empty name to cancel all named groups.
 
-       The getall modifier tests  pcre2_substring_list_get(),  which  extracts
+       The  getall  modifier  tests pcre2_substring_list_get(), which extracts
        all captured substrings.
 
-       If  the  subject line is successfully matched, the substrings extracted
-       by the convenience functions are output with  C,  G,  or  L  after  the
-       string  number  instead  of  a colon. This is in addition to the normal
-       full list. The string length (that is, the return from  the  extraction
+       If the subject line is successfully matched, the  substrings  extracted
+       by  the  convenience  functions  are  output  with C, G, or L after the
+       string number instead of a colon. This is in  addition  to  the  normal
+       full  list.  The string length (that is, the return from the extraction
        function) is given in parentheses after each substring, followed by the
        name when the extraction was by name.
 
    Testing the substitution function
 
-       If  the  replace  modifier  is  set, the pcre2_substitute() function is
-       called instead of one of the matching functions (or after one  call  of
-       pcre2_match()  in  the case of PCRE2_SUBSTITUTE_MATCHED). Note that re-
-       placement strings cannot contain commas, because a comma signifies  the
-       end  of  a  modifier. This is not thought to be an issue in a test pro-
+       If the replace modifier is  set,  the  pcre2_substitute()  function  is
+       called  instead  of one of the matching functions (or after one call of
+       pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note  that  re-
+       placement  strings cannot contain commas, because a comma signifies the
+       end of a modifier. This is not thought to be an issue in  a  test  pro-
        gram.
 
-       Specifying a completely empty replacement string  disables  this  modi-
-       fier.   However, it is possible to specify an empty replacement by pro-
-       viding a buffer length, as described below, for an otherwise empty  re-
+       Specifying  a  completely  empty replacement string disables this modi-
+       fier.  However, it is possible to specify an empty replacement by  pro-
+       viding  a buffer length, as described below, for an otherwise empty re-
        placement.
 
-       Unlike  subject strings, pcre2test does not process replacement strings
-       for escape sequences. In UTF mode, a replacement string is  checked  to
-       see  if it is a valid UTF-8 string. If so, it is correctly converted to
-       a UTF string of the appropriate code unit width. If it is not  a  valid
-       UTF-8  string, the individual code units are copied directly. This pro-
+       Unlike subject strings, pcre2test does not process replacement  strings
+       for  escape  sequences. In UTF mode, a replacement string is checked to
+       see if it is a valid UTF-8 string. If so, it is correctly converted  to
+       a  UTF  string of the appropriate code unit width. If it is not a valid
+       UTF-8 string, the individual code units are copied directly. This  pro-
        vides a means of passing an invalid UTF-8 string for testing purposes.
 
-       The following modifiers set options (in additional to the normal  match
+       The  following modifiers set options (in additional to the normal match
        options) for pcre2_substitute():
 
          global                      PCRE2_SUBSTITUTE_GLOBAL
@@ -1396,8 +1399,8 @@ SUBJECT MODIFIERS
 
        See the pcre2api documentation for details of these options.
 
-       After  a  successful  substitution, the modified string is output, pre-
-       ceded by the number of replacements. This may be zero if there were  no
+       After a successful substitution, the modified string  is  output,  pre-
+       ceded  by the number of replacements. This may be zero if there were no
        matches. Here is a simple example of a substitution test:
 
          /abc/replace=xxx
@@ -1406,12 +1409,12 @@ SUBJECT MODIFIERS
              =abc=abc=\=global
           2: =xxx=xxx=
 
-       Subject  and replacement strings should be kept relatively short (fewer
-       than 256 characters) for substitution tests, as fixed-size buffers  are
-       used.  To  make it easy to test for buffer overflow, if the replacement
-       string starts with a number in square brackets, that number  is  passed
-       to  pcre2_substitute()  as  the size of the output buffer, with the re-
-       placement string starting at the next character.  Here  is  an  example
+       Subject and replacement strings should be kept relatively short  (fewer
+       than  256 characters) for substitution tests, as fixed-size buffers are
+       used. To make it easy to test for buffer overflow, if  the  replacement
+       string  starts  with a number in square brackets, that number is passed
+       to pcre2_substitute() as the size of the output buffer,  with  the  re-
+       placement  string  starting  at  the next character. Here is an example
        that tests the edge case:
 
          /abc/
@@ -1421,12 +1424,12 @@ SUBJECT MODIFIERS
          Failed: error -47: no more memory
 
        The  default  action  of  pcre2_substitute()  is  to  return  PCRE2_ER-
-       ROR_NOMEMORY when the output buffer  is  too  small.  However,  if  the
-       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  option  is  set (by using the substi-
+       ROR_NOMEMORY  when  the  output  buffer  is  too small. However, if the
+       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by  using  the  substi-
        tute_overflow_length  modifier),  pcre2_substitute()  continues  to  go
-       through  the  motions  of  matching and substituting (but not doing any
-       callouts), in order to compute the size of  buffer  that  is  required.
-       When  this  happens,  pcre2test shows the required buffer length (which
+       through the motions of matching and substituting  (but  not  doing  any
+       callouts),  in  order  to  compute the size of buffer that is required.
+       When this happens, pcre2test shows the required  buffer  length  (which
        includes space for the trailing zero) as part of the error message. For
        example:
 
@@ -1435,15 +1438,15 @@ SUBJECT MODIFIERS
          Failed: error -47: no more memory: 10 code units are needed
 
        A replacement string is ignored with POSIX and DFA matching. Specifying
-       partial matching provokes an error return  ("bad  option  value")  from
+       partial  matching  provokes  an  error return ("bad option value") from
        pcre2_substitute().
 
    Testing substitute callouts
 
        If the substitute_callout modifier is set, a substitution callout func-
-       tion  is set up. The null_context modifier must not be set, because the
-       address of the callout function is passed in a match context. When  the
-       callout  function  is  called (after each substitution), details of the
+       tion is set up. The null_context modifier must not be set, because  the
+       address  of the callout function is passed in a match context. When the
+       callout function is called (after each substitution),  details  of  the
        input and output strings are output. For example:
 
          /abc/g,replace=<$0>,substitute_callout
@@ -1452,19 +1455,19 @@ SUBJECT MODIFIERS
           2(1) Old 6 9 "abc" New 8 13 ""
           2: defpqr
 
-       The first number on each callout line is  the  count  of  matches.  The
+       The  first  number  on  each  callout line is the count of matches. The
        parenthesized number is the number of pairs that are set in the ovector
-       (that  is, one more than the number of capturing groups that were set).
+       (that is, one more than the number of capturing groups that were  set).
        Then are listed the offsets of the old substring, its contents, and the
        same for the replacement.
 
-       By default, the substitution callout function returns zero,  which  ac-
-       cepts  the  replacement and causes matching to continue if /g was used.
-       Two further modifiers can be used to test other return values. If  sub-
-       stitute_skip  is  set to a value greater than zero the callout function
-       returns +1 for the match of that number, and similarly  substitute_stop
-       returns  -1.  These cause the replacement to be rejected, and -1 causes
-       no further matching to take place. If either of them are  set,  substi-
+       By  default,  the substitution callout function returns zero, which ac-
+       cepts the replacement and causes matching to continue if /g  was  used.
+       Two  further modifiers can be used to test other return values. If sub-
+       stitute_skip is set to a value greater than zero the  callout  function
+       returns  +1 for the match of that number, and similarly substitute_stop
+       returns -1. These cause the replacement to be rejected, and  -1  causes
+       no  further  matching to take place. If either of them are set, substi-
        tute_callout is assumed. For example:
 
          /abc/g,replace=<$0>,substitute_skip=1
@@ -1482,193 +1485,193 @@ SUBJECT MODIFIERS
 
    Testing substitute case callouts
 
-       If  the  substitute_case_callout  modifier  is set, a substitution case
-       callout function is set up. The callout function  is  called  for  each
+       If the substitute_case_callout modifier is  set,  a  substitution  case
+       callout  function  is  set  up. The callout function is called for each
        substituted chunk which is to be case-transformed.
 
        The callout function passed is a fixed function with implementation for
-       certain  behaviours:  inputs which shrink when case-transformed; inputs
+       certain behaviours: inputs which shrink when  case-transformed;  inputs
        which grow; inputs with distinct upper/lower/titlecase forms. The char-
        acters which are not special-cased for testing purposes are left unmod-
        ified, as if they are caseless characters.
 
    Setting the JIT stack size
 
-       The jitstack modifier provides a way of setting the maximum stack  size
-       that  is  used  by the just-in-time optimization code. It is ignored if
-       JIT optimization is not being used. The value is a number of  kibibytes
-       (units  of  1024  bytes). Setting zero reverts to the default of 32KiB.
+       The  jitstack modifier provides a way of setting the maximum stack size
+       that is used by the just-in-time optimization code. It  is  ignored  if
+       JIT  optimization is not being used. The value is a number of kibibytes
+       (units of 1024 bytes). Setting zero reverts to the  default  of  32KiB.
        Providing a stack that is larger than the default is necessary only for
-       very complicated patterns. If jitstack is set  non-zero  on  a  subject
+       very  complicated  patterns.  If  jitstack is set non-zero on a subject
        line it overrides any value that was set on the pattern.
 
    Setting heap, match, and depth limits
 
-       The  heap_limit,  match_limit, and depth_limit modifiers set the appro-
-       priate limits in the match context. These values are ignored  when  the
+       The heap_limit, match_limit, and depth_limit modifiers set  the  appro-
+       priate  limits  in the match context. These values are ignored when the
        find_limits or find_limits_noheap modifier is specified.
 
    Finding minimum limits
 
-       If  the  find_limits  modifier  is present on a subject line, pcre2test
-       calls the relevant matching function several times,  setting  different
-       values    in    the    match    context   via   pcre2_set_heap_limit(),
-       pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds  the
-       smallest  value  for  each  parameter that allows the match to complete
+       If the find_limits modifier is present on  a  subject  line,  pcre2test
+       calls  the  relevant matching function several times, setting different
+       values   in   the    match    context    via    pcre2_set_heap_limit(),
+       pcre2_set_match_limit(),  or pcre2_set_depth_limit() until it finds the
+       smallest value for each parameter that allows  the  match  to  complete
        without a "limit exceeded" error. The match itself may succeed or fail.
        An alternative modifier, find_limits_noheap, omits the heap limit. This
-       is used in the standard tests, because the minimum  heap  limit  varies
-       between  systems.  If  JIT is being used, only the match limit is rele-
+       is  used  in  the standard tests, because the minimum heap limit varies
+       between systems. If JIT is being used, only the match  limit  is  rele-
        vant, and the other two are automatically omitted.
 
        When using this modifier, the pattern should not contain any limit set-
-       tings such as (*LIMIT_MATCH=...)  within  it.  If  such  a  setting  is
+       tings  such  as  (*LIMIT_MATCH=...)  within  it.  If  such a setting is
        present and is lower than the minimum matching value, the minimum value
-       cannot  be  found because pcre2_set_match_limit() etc. are only able to
+       cannot be found because pcre2_set_match_limit() etc. are only  able  to
        reduce the value of an in-pattern limit; they cannot increase it.
 
-       For non-DFA matching, the minimum depth_limit number is  a  measure  of
+       For  non-DFA  matching,  the minimum depth_limit number is a measure of
        how much nested backtracking happens (that is, how deeply the pattern's
-       tree  is  searched).  In the case of DFA matching, depth_limit controls
-       the depth of recursive calls of the internal function that is used  for
+       tree is searched). In the case of DFA  matching,  depth_limit  controls
+       the  depth of recursive calls of the internal function that is used for
        handling pattern recursion, lookaround assertions, and atomic groups.
 
        For non-DFA matching, the match_limit number is a measure of the amount
        of backtracking that takes place, and learning the minimum value can be
-       instructive.  For  most  simple matches, the number is quite small, but
-       for patterns with very large numbers of matching possibilities, it  can
-       become  large very quickly with increasing length of subject string. In
-       the case of DFA matching, match_limit  controls  the  total  number  of
+       instructive. For most simple matches, the number is  quite  small,  but
+       for  patterns with very large numbers of matching possibilities, it can
+       become large very quickly with increasing length of subject string.  In
+       the  case  of  DFA  matching,  match_limit controls the total number of
        calls, both recursive and non-recursive, to the internal matching func-
        tion, thus controlling the overall amount of computing resource that is
        used.
 
-       For  both  kinds  of  matching,  the  heap_limit  number,  which  is in
-       kibibytes (units of 1024 bytes), limits the amount of heap memory  used
+       For both  kinds  of  matching,  the  heap_limit  number,  which  is  in
+       kibibytes  (units of 1024 bytes), limits the amount of heap memory used
        for matching.
 
    Showing MARK names
 
 
        The mark modifier causes the names from backtracking control verbs that
-       are  returned from calls to pcre2_match() to be displayed. If a mark is
-       returned for a match, non-match, or partial match, pcre2test shows  it.
-       For  a  match, it is on a line by itself, tagged with "MK:". Otherwise,
+       are returned from calls to pcre2_match() to be displayed. If a mark  is
+       returned  for a match, non-match, or partial match, pcre2test shows it.
+       For a match, it is on a line by itself, tagged with  "MK:".  Otherwise,
        it is added to the non-match message.
 
    Showing memory usage
 
-       The memory modifier causes pcre2test to log the sizes of all heap  mem-
-       ory   allocation  and  freeing  calls  that  occur  during  a  call  to
-       pcre2_match() or pcre2_dfa_match(). In the latter case, heap memory  is
-       used  only  when  a match requires more internal workspace that the de-
-       fault allocation on the stack, so in many cases there will be  no  out-
-       put.  No  heap  memory  is allocated during matching with JIT. For this
+       The  memory modifier causes pcre2test to log the sizes of all heap mem-
+       ory  allocation  and  freeing  calls  that  occur  during  a  call   to
+       pcre2_match()  or pcre2_dfa_match(). In the latter case, heap memory is
+       used only when a match requires more internal workspace  that  the  de-
+       fault  allocation  on the stack, so in many cases there will be no out-
+       put. No heap memory is allocated during matching  with  JIT.  For  this
        modifier to work, the null_context modifier must not be set on both the
        pattern and the subject, though it can be set on one or the other.
 
    Showing the heap frame overall vector size
 
-       The  heapframes_size   modifier   is   relevant   for   matches   using
+       The   heapframes_size   modifier   is   relevant   for   matches  using
        pcre2_match() without JIT. After a match has run (whether successful or
-       not)  the  size,  in bytes, of the allocated heap frames vector that is
-       left attached to the match data block is shown. If the matching  action
-       involved  several  calls to pcre2_match() (for example, global matching
+       not) the size, in bytes, of the allocated heap frames  vector  that  is
+       left  attached to the match data block is shown. If the matching action
+       involved several calls to pcre2_match() (for example,  global  matching
        or for timing) only the final value is shown.
 
-       This modifier is ignored, with a warning, for POSIX  or  DFA  matching.
+       This  modifier  is  ignored, with a warning, for POSIX or DFA matching.
        JIT matching does not use the heap frames vector, so the size is always
-       zero,  unless there was a previous non-JIT match. Note that specifing a
+       zero, unless there was a previous non-JIT match. Note that specifing  a
        size of zero for the output vector (see below) causes pcre2test to free
        its match data block (and associated heap frames vector) and allocate a
        new one.
 
    Setting a starting offset
 
-       The offset modifier sets an offset  in  the  subject  string  at  which
+       The  offset  modifier  sets  an  offset  in the subject string at which
        matching starts. Its value is a number of code units, not characters.
 
    Setting an offset limit
 
-       The  offset_limit  modifier  sets  a limit for unanchored matches. If a
+       The offset_limit modifier sets a limit for  unanchored  matches.  If  a
        match cannot be found starting at or before this offset in the subject,
        a "no match" return is given. The data value is a number of code units,
-       not characters. When this modifier is used, the use_offset_limit  modi-
+       not  characters. When this modifier is used, the use_offset_limit modi-
        fier must have been set for the pattern; if not, an error is generated.
 
    Setting the size of the output vector
 
-       The  ovector  modifier applies only to the subject line in which it ap-
+       The ovector modifier applies only to the subject line in which  it  ap-
        pears, though of course it can also be used to set a default in a #sub-
-       ject command. It specifies the number of  pairs  of  offsets  that  are
+       ject  command.  It  specifies  the  number of pairs of offsets that are
        available for storing matching information. The default is 15.
 
-       A  value of zero is useful when testing the POSIX API because it causes
+       A value of zero is useful when testing the POSIX API because it  causes
        regexec() to be called with a NULL capture vector. When not testing the
-       POSIX API, a value of  zero  is  used  to  cause  pcre2_match_data_cre-
-       ate_from_pattern()  to  be called, in order to create a new match block
-       of exactly the right size for the pattern. (It is not possible to  cre-
-       ate  a match block with a zero-length ovector; there is always at least
+       POSIX  API,  a  value  of  zero  is used to cause pcre2_match_data_cre-
+       ate_from_pattern() to be called, in order to create a new  match  block
+       of  exactly the right size for the pattern. (It is not possible to cre-
+       ate a match block with a zero-length ovector; there is always at  least
        one pair of offsets.) The old match data block is freed.
 
    Passing the subject as zero-terminated
 
        By default, the subject string is passed to a native API matching func-
        tion with its correct length. In order to test the facility for passing
-       a zero-terminated string, the zero_terminate modifier is  provided.  It
-       causes  the length to be passed as PCRE2_ZERO_TERMINATED. When matching
+       a  zero-terminated  string, the zero_terminate modifier is provided. It
+       causes the length to be passed as PCRE2_ZERO_TERMINATED. When  matching
        via the POSIX interface, this modifier is ignored, with a warning.
 
-       When testing pcre2_substitute(), this modifier also has the  effect  of
+       When  testing  pcre2_substitute(), this modifier also has the effect of
        passing the replacement string as zero-terminated.
 
    Passing a NULL context, subject, or replacement
 
-       Normally,   pcre2test   passes   a   context  block  to  pcre2_match(),
-       pcre2_dfa_match(), pcre2_jit_match()  or  pcre2_substitute().   If  the
-       null_context  modifier  is  set,  however,  NULL is passed. This is for
-       testing that the matching and substitution functions  behave  correctly
-       in  this  case  (they use default values). This modifier cannot be used
-       with the find_limits, find_limits_noheap, or  substitute_callout  modi-
+       Normally,  pcre2test  passes  a   context   block   to   pcre2_match(),
+       pcre2_dfa_match(),  pcre2_jit_match()  or  pcre2_substitute().   If the
+       null_context modifier is set, however, NULL  is  passed.  This  is  for
+       testing  that  the matching and substitution functions behave correctly
+       in this case (they use default values). This modifier  cannot  be  used
+       with  the  find_limits, find_limits_noheap, or substitute_callout modi-
        fiers.
 
-       Similarly,  for  testing purposes, if the null_subject or null_replace-
-       ment modifier is set, the subject or replacement  string  pointers  are
+       Similarly, for testing purposes, if the null_subject  or  null_replace-
+       ment  modifier  is  set, the subject or replacement string pointers are
        passed as NULL, respectively, to the relevant functions.
 
 
 THE ALTERNATIVE MATCHING FUNCTION
 
-       By  default,  pcre2test  uses  the  standard  PCRE2  matching function,
+       By default,  pcre2test  uses  the  standard  PCRE2  matching  function,
        pcre2_match() to match each subject line. PCRE2 also supports an alter-
-       native matching function, pcre2_dfa_match(), which operates in  a  dif-
-       ferent  way, and has some restrictions. The differences between the two
+       native  matching  function, pcre2_dfa_match(), which operates in a dif-
+       ferent way, and has some restrictions. The differences between the  two
        functions are described in the pcre2matching documentation.
 
-       If the dfa modifier is set, the alternative matching function is  used.
-       This  function  finds all possible matches at a given point in the sub-
-       ject. If, however, the dfa_shortest modifier is set,  processing  stops
-       after  the  first  match is found. This is always the shortest possible
+       If  the dfa modifier is set, the alternative matching function is used.
+       This function finds all possible matches at a given point in  the  sub-
+       ject.  If,  however, the dfa_shortest modifier is set, processing stops
+       after the first match is found. This is always  the  shortest  possible
        match.
 
 
 DEFAULT OUTPUT FROM pcre2test
 
-       This section describes the output when the  normal  matching  function,
+       This  section  describes  the output when the normal matching function,
        pcre2_match(), is being used.
 
-       When  a  match  succeeds,  pcre2test  outputs the list of captured sub-
-       strings, starting with number 0 for the string that matched  the  whole
+       When a match succeeds, pcre2test outputs  the  list  of  captured  sub-
+       strings,  starting  with number 0 for the string that matched the whole
        pattern.  Otherwise, it outputs "No match" when the return is PCRE2_ER-
-       ROR_NOMATCH,  or  "Partial  match:"  followed by the partially matching
-       substring when the return is PCRE2_ERROR_PARTIAL. (Note  that  this  is
-       the  entire  substring  that was inspected during the partial match; it
-       may include characters before the actual match start  if  a  lookbehind
+       ROR_NOMATCH, or "Partial match:" followed  by  the  partially  matching
+       substring  when  the  return is PCRE2_ERROR_PARTIAL. (Note that this is
+       the entire substring that was inspected during the  partial  match;  it
+       may  include  characters  before the actual match start if a lookbehind
        assertion, \K, \b, or \B was involved.)
 
        For any other return, pcre2test outputs the PCRE2 negative error number
-       and  a  short  descriptive  phrase. If the error is a failed UTF string
-       check, the code unit offset of the start of the  failing  character  is
+       and a short descriptive phrase. If the error is  a  failed  UTF  string
+       check,  the  code  unit offset of the start of the failing character is
        also output. Here is an example of an interactive pcre2test run.
 
          $ pcre2test
@@ -1684,8 +1687,8 @@ DEFAULT OUTPUT FROM pcre2test
        Unset capturing substrings that are not followed by one that is set are
        not shown by pcre2test unless the allcaptures modifier is specified. In
        the following example, there are two capturing substrings, but when the
-       first  data  line is matched, the second, unset substring is not shown.
-       An "internal" unset substring is shown as "", as for the  second
+       first data line is matched, the second, unset substring is  not  shown.
+       An  "internal" unset substring is shown as "", as for the second
        data line.
 
            re> /(a)|(b)/
@@ -1697,11 +1700,11 @@ DEFAULT OUTPUT FROM pcre2test
           1: 
           2: b
 
-       If  the strings contain any non-printing characters, they are output as
-       \xhh escapes if the value is less than 256 and UTF  mode  is  not  set.
+       If the strings contain any non-printing characters, they are output  as
+       \xhh  escapes  if  the  value is less than 256 and UTF mode is not set.
        Otherwise they are output as \x{hh...} escapes. See below for the defi-
-       nition  of  non-printing  characters. If the aftertext modifier is set,
-       the output for substring 0 is followed  by  the  rest  of  the  subject
+       nition of non-printing characters. If the aftertext  modifier  is  set,
+       the  output  for  substring  0  is  followed by the rest of the subject
        string, identified by "0+" like this:
 
            re> /cat/aftertext
@@ -1721,8 +1724,8 @@ DEFAULT OUTPUT FROM pcre2test
           0: ipp
           1: pp
 
-       "No  match" is output only if the first match attempt fails. Here is an
-       example of a failure message (the offset 4 that  is  specified  by  the
+       "No match" is output only if the first match attempt fails. Here is  an
+       example  of  a  failure  message (the offset 4 that is specified by the
        offset modifier is past the end of the subject string):
 
            re> /xyz/
@@ -1730,7 +1733,7 @@ DEFAULT OUTPUT FROM pcre2test
          Error -24 (bad offset value)
 
        Note that whereas patterns can be continued over several lines (a plain
-       ">"  prompt  is used for continuations), subject lines may not. However
+       ">" prompt is used for continuations), subject lines may  not.  However
        newlines can be included in a subject by means of the \n escape (or \r,
        \r\n, etc., depending on the newline sequence setting).
 
@@ -1738,7 +1741,7 @@ DEFAULT OUTPUT FROM pcre2test
 OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
 
        When the alternative matching function, pcre2_dfa_match(), is used, the
-       output consists of a list of all the matches that start  at  the  first
+       output  consists  of  a list of all the matches that start at the first
        point in the subject where there is at least one match. For example:
 
            re> /(tang|tangerine|tan)/
@@ -1747,11 +1750,11 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
           1: tang
           2: tan
 
-       Using  the normal matching function on this data finds only "tang". The
-       longest matching string is always given first (and numbered zero).  Af-
-       ter  a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol-
+       Using the normal matching function on this data finds only "tang".  The
+       longest  matching string is always given first (and numbered zero). Af-
+       ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:",  fol-
        lowed by the partially matching substring. Note that this is the entire
-       substring that was inspected during the partial match; it  may  include
+       substring  that  was inspected during the partial match; it may include
        characters before the actual match start if a lookbehind assertion, \b,
        or \B was involved. (\K is not supported for DFA matching.)
 
@@ -1767,16 +1770,16 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
           1: tan
           0: tan
 
-       The  alternative  matching function does not support substring capture,
-       so the modifiers that are concerned with captured  substrings  are  not
+       The alternative matching function does not support  substring  capture,
+       so  the  modifiers  that are concerned with captured substrings are not
        relevant.
 
 
 RESTARTING AFTER A PARTIAL MATCH
 
-       When  the  alternative matching function has given the PCRE2_ERROR_PAR-
+       When the alternative matching function has given  the  PCRE2_ERROR_PAR-
        TIAL return, indicating that the subject partially matched the pattern,
-       you can restart the match with additional subject data by means of  the
+       you  can restart the match with additional subject data by means of the
        dfa_restart modifier. For example:
 
            re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
@@ -1785,37 +1788,37 @@ RESTARTING AFTER A PARTIAL MATCH
          data> n05\=dfa,dfa_restart
           0: n05
 
-       For  further  information  about partial matching, see the pcre2partial
+       For further information about partial matching,  see  the  pcre2partial
        documentation.
 
 
 CALLOUTS
 
        If the pattern contains any callout requests, pcre2test's callout func-
-       tion is called during matching unless callout_none is  specified.  This
+       tion  is  called during matching unless callout_none is specified. This
        works with both matching functions, and with JIT, though there are some
-       differences  in behaviour. The output for callouts with numerical argu-
+       differences in behaviour. The output for callouts with numerical  argu-
        ments and those with string arguments is slightly different.
 
    Callouts with numerical arguments
 
        By default, the callout function displays the callout number, the start
-       and current positions in the subject text at the callout time, and  the
+       and  current positions in the subject text at the callout time, and the
        next pattern item to be tested. For example:
 
          --->pqrabcdef
            0    ^  ^     \d
 
-       This  output  indicates  that callout number 0 occurred for a match at-
-       tempt starting at the fourth character of the subject string, when  the
-       pointer  was  at  the seventh character, and when the next pattern item
-       was \d. Just one circumflex is output if the start  and  current  posi-
+       This output indicates that callout number 0 occurred for  a  match  at-
+       tempt  starting at the fourth character of the subject string, when the
+       pointer was at the seventh character, and when the  next  pattern  item
+       was  \d.  Just  one circumflex is output if the start and current posi-
        tions are the same, or if the current position precedes the start posi-
        tion, which can happen if the callout is in a lookbehind assertion.
 
        Callouts numbered 255 are assumed to be automatic callouts, inserted as
        a result of the auto_callout pattern modifier. In this case, instead of
-       showing  the  callout  number, the offset in the pattern, preceded by a
+       showing the callout number, the offset in the pattern,  preceded  by  a
        plus, is output. For example:
 
            re> /\d?[A-E]\*/auto_callout
@@ -1842,17 +1845,17 @@ CALLOUTS
          +12 ^  ^
           0: abc
 
-       The mark changes between matching "a" and "b", but stays the  same  for
-       the  rest  of  the match, so nothing more is output. If, as a result of
-       backtracking, the mark reverts to being unset, the  text  ""  is
+       The  mark  changes between matching "a" and "b", but stays the same for
+       the rest of the match, so nothing more is output. If, as  a  result  of
+       backtracking,  the  mark  reverts to being unset, the text "" is
        output.
 
    Callouts with string arguments
 
        The output for a callout with a string argument is similar, except that
-       instead  of outputting a callout number before the position indicators,
-       the callout string and its offset in the pattern string are output  be-
-       fore  the  reflection  of the subject string, and the subject string is
+       instead of outputting a callout number before the position  indicators,
+       the  callout string and its offset in the pattern string are output be-
+       fore the reflection of the subject string, and the  subject  string  is
        reflected for each callout. For example:
 
            re> /^ab(?C'first')cd(?C"second")ef/
@@ -1868,26 +1871,26 @@ CALLOUTS
 
    Callout modifiers
 
-       The callout function in pcre2test returns zero (carry on  matching)  by
-       default,  but  you can use a callout_fail modifier in a subject line to
+       The  callout  function in pcre2test returns zero (carry on matching) by
+       default, but you can use a callout_fail modifier in a subject  line  to
        change this and other parameters of the callout (see below).
 
        If the callout_capture modifier is set, the current captured groups are
        output when a callout occurs. This is useful only for non-DFA matching,
-       as pcre2_dfa_match() does not support capturing,  so  no  captures  are
+       as  pcre2_dfa_match()  does  not  support capturing, so no captures are
        ever shown.
 
        The normal callout output, showing the callout number or pattern offset
-       (as  described above) is suppressed if the callout_no_where modifier is
+       (as described above) is suppressed if the callout_no_where modifier  is
        set.
 
-       When using the interpretive  matching  function  pcre2_match()  without
-       JIT,  setting  the callout_extra modifier causes additional output from
-       pcre2test's callout function to be generated. For the first callout  in
-       a  match  attempt at a new starting position in the subject, "New match
-       attempt" is output. If there has been a backtrack since the last  call-
+       When  using  the  interpretive  matching function pcre2_match() without
+       JIT, setting the callout_extra modifier causes additional  output  from
+       pcre2test's  callout function to be generated. For the first callout in
+       a match attempt at a new starting position in the subject,  "New  match
+       attempt"  is output. If there has been a backtrack since the last call-
        out (or start of matching if this is the first callout), "Backtrack" is
-       output,  followed  by  "No other matching paths" if the backtrack ended
+       output, followed by "No other matching paths" if  the  backtrack  ended
        the previous match attempt. For example:
 
           re> /(a+)b/auto_callout,no_start_optimize,no_auto_possess
@@ -1924,86 +1927,86 @@ CALLOUTS
           +1    ^    a+
          No match
 
-       Notice that various optimizations must be turned off if  you  want  all
-       possible  matching  paths  to  be  scanned. If no_start_optimize is not
-       used, there is an immediate "no match", without any  callouts,  because
-       the  starting  optimization  fails to find "b" in the subject, which it
-       knows must be present for any match. If no_auto_possess  is  not  used,
-       the  "a+"  item is turned into "a++", which reduces the number of back-
+       Notice  that  various  optimizations must be turned off if you want all
+       possible matching paths to be  scanned.  If  no_start_optimize  is  not
+       used,  there  is an immediate "no match", without any callouts, because
+       the starting optimization fails to find "b" in the  subject,  which  it
+       knows  must  be  present for any match. If no_auto_possess is not used,
+       the "a+" item is turned into "a++", which reduces the number  of  back-
        tracks.
 
-       The callout_extra modifier has no effect if used with the DFA  matching
+       The  callout_extra modifier has no effect if used with the DFA matching
        function, or with JIT.
 
    Return values from callouts
 
-       The  default  return  from  the  callout function is zero, which allows
+       The default return from the callout  function  is  zero,  which  allows
        matching to continue. The callout_fail modifier can be given one or two
        numbers. If there is only one number, 1 is returned instead of 0 (caus-
        ing matching to backtrack) when a callout of that number is reached. If
-       two numbers (:) are given, 1 is  returned  when  callout    is
-       reached  and  there  have been at least  callouts. The callout_error
+       two  numbers  (:)  are  given,  1 is returned when callout  is
+       reached and there have been at least   callouts.  The  callout_error
        modifier is similar, except that PCRE2_ERROR_CALLOUT is returned, caus-
-       ing the entire matching process to be aborted. If both these  modifiers
-       are  set  for  the same callout number, callout_error takes precedence.
-       Note that callouts with string arguments are always  given  the  number
+       ing  the entire matching process to be aborted. If both these modifiers
+       are set for the same callout number,  callout_error  takes  precedence.
+       Note  that  callouts  with string arguments are always given the number
        zero.
 
-       The  callout_data  modifier can be given an unsigned or a negative num-
-       ber.  This is set as the "user data" that is  passed  to  the  matching
-       function,  and  passed  back  when the callout function is invoked. Any
-       value other than zero is used as  a  return  from  pcre2test's  callout
+       The callout_data modifier can be given an unsigned or a  negative  num-
+       ber.   This  is  set  as the "user data" that is passed to the matching
+       function, and passed back when the callout  function  is  invoked.  Any
+       value  other  than  zero  is  used as a return from pcre2test's callout
        function.
 
        Inserting callouts can be helpful when using pcre2test to check compli-
-       cated  regular expressions. For further information about callouts, see
+       cated regular expressions. For further information about callouts,  see
        the pcre2callout documentation.
 
 
 NON-PRINTING CHARACTERS
 
        When pcre2test is outputting text in the compiled version of a pattern,
-       bytes other than 32-126 are always treated as  non-printing  characters
+       bytes  other  than 32-126 are always treated as non-printing characters
        and are therefore shown as hex escapes.
 
-       When  pcre2test  is outputting text that is a matched part of a subject
-       string, it behaves in the same way, unless a different locale has  been
-       set  for the pattern (using the locale modifier). In this case, the is-
+       When pcre2test is outputting text that is a matched part of  a  subject
+       string,  it behaves in the same way, unless a different locale has been
+       set for the pattern (using the locale modifier). In this case, the  is-
        print() function is used to distinguish printing and non-printing char-
        acters.
 
 
 SAVING AND RESTORING COMPILED PATTERNS
 
-       It is possible to save compiled patterns on disc or elsewhere, and  re-
-       load  them  later, subject to a number of restrictions. JIT data cannot
-       be saved. The host on which the patterns are reloaded must  be  running
+       It  is possible to save compiled patterns on disc or elsewhere, and re-
+       load 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  ta-
-       bles.  A  single copy of the tables is included in the byte stream (its
+       have the same endianness, pointer width  and  PCRE2_SIZE  type.  Before
+       compiled  patterns  can be saved they must be serialized, that is, con-
+       verted to a stream of bytes. A single byte stream may contain any  num-
+       ber  of compiled patterns, but they must all use the same character ta-
+       bles. A single copy of the tables is included in the byte  stream  (its
        size is 1088 bytes).
 
-       The functions whose names begin with pcre2_serialize_ are used for  se-
-       rializing  and de-serializing. They are described in the pcre2serialize
-       documentation. In this section we describe the  features  of  pcre2test
+       The  functions whose names begin with pcre2_serialize_ are used for se-
+       rializing and de-serializing. They are described in the  pcre2serialize
+       documentation.  In  this  section we describe the features of pcre2test
        that can be used to test these functions.
 
-       Note  that  "serialization" in PCRE2 does not convert compiled patterns
-       to an abstract format like Java or .NET. It  just  makes  a  reloadable
+       Note that "serialization" in PCRE2 does not convert  compiled  patterns
+       to  an  abstract  format  like Java or .NET. It just makes a reloadable
        byte code stream.  Hence the restrictions on reloading mentioned above.
 
-       In  pcre2test,  when  a pattern with push modifier is successfully com-
-       piled, it is pushed onto a stack of compiled  patterns,  and  pcre2test
-       expects  the next line to contain a new pattern (or command) instead of
+       In pcre2test, when a pattern with push modifier  is  successfully  com-
+       piled,  it  is  pushed onto a stack of compiled patterns, and pcre2test
+       expects the next line to contain a new pattern (or command) instead  of
        a subject line. By contrast, the pushcopy modifier causes a copy of the
-       compiled pattern to be stacked, leaving the original available for  im-
-       mediate  matching.  By using push and/or pushcopy, a number of patterns
-       can be compiled and retained. These  modifiers  are  incompatible  with
+       compiled  pattern to be stacked, leaving the original available for im-
+       mediate matching. By using push and/or pushcopy, a number  of  patterns
+       can  be  compiled  and  retained. These modifiers are incompatible with
        posix, and control modifiers that act at match time are ignored (with a
-       message)  for the stacked patterns. The jitverify modifier applies only
+       message) for the stacked patterns. The jitverify modifier applies  only
        at compile time.
 
        The command
@@ -2011,21 +2014,21 @@ SAVING AND RESTORING COMPILED PATTERNS
          #save 
 
        causes all the stacked patterns to be serialized and the result written
-       to the named file. Afterwards, all the stacked patterns are freed.  The
+       to  the named file. Afterwards, all the stacked patterns are freed. The
        command
 
          #load 
 
-       reads  the  data in the file, and then arranges for it to be de-serial-
-       ized, with the resulting compiled patterns added to the pattern  stack.
-       The  pattern  on the top of the stack can be retrieved by the #pop com-
-       mand, which must be followed by  lines  of  subjects  that  are  to  be
-       matched  with  the pattern, terminated as usual by an empty line or end
-       of file. This command may be followed by  a  modifier  list  containing
-       only  control  modifiers that act after a pattern has been compiled. In
-       particular, hex, posix, posix_nosub, push, and  pushcopy  are  not  al-
-       lowed,  nor  are  any option-setting modifiers.  The JIT modifiers are,
-       however permitted. Here is an example that saves and reloads  two  pat-
+       reads the data in the file, and then arranges for it to  be  de-serial-
+       ized,  with the resulting compiled patterns added to the pattern stack.
+       The pattern on the top of the stack can be retrieved by the  #pop  com-
+       mand,  which  must  be  followed  by  lines  of subjects that are to be
+       matched with the pattern, terminated as usual by an empty line  or  end
+       of  file.  This  command  may be followed by a modifier list containing
+       only control modifiers that act after a pattern has been  compiled.  In
+       particular,  hex,  posix,  posix_nosub,  push, and pushcopy are not al-
+       lowed, nor are any option-setting modifiers.  The  JIT  modifiers  are,
+       however  permitted.  Here is an example that saves and reloads two pat-
        terns.
 
          /abc/push
@@ -2038,10 +2041,10 @@ SAVING AND RESTORING COMPILED PATTERNS
          #pop jit,bincode
          abc
 
-       If  jitverify  is  used with #pop, it does not automatically imply jit,
+       If jitverify is used with #pop, it does not  automatically  imply  jit,
        which is different behaviour from when it is used on a pattern.
 
-       The #popcopy command is analogous to the pushcopy modifier in  that  it
+       The  #popcopy  command is analogous to the pushcopy modifier in that it
        makes current a copy of the topmost stack pattern, leaving the original
        still on the stack.
 
diff --git a/maint/PrepareRelease b/maint/PrepareRelease
index 98a9b0799..1f205e6f8 100755
--- a/maint/PrepareRelease
+++ b/maint/PrepareRelease
@@ -250,6 +250,8 @@ c_files=(
   src/pcre2.h.in
   src/pcre2_auto_possess.c
   src/pcre2_chartables.c.dist
+  src/pcre2_chartables.c.ebcdic-1047-nl15
+  src/pcre2_chartables.c.ebcdic-1047-nl25
   src/pcre2_chkdint.c
   src/pcre2_compile.c
   src/pcre2_compile.h
diff --git a/maint/manifest-tarball b/maint/manifest-tarball
index 7cdc99554..7f4a15133 100644
--- a/maint/manifest-tarball
+++ b/maint/manifest-tarball
@@ -304,6 +304,8 @@ drwxr-xr-x tarball-dir/pcre2-SNAPSHOT/src
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2.h.in
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_auto_possess.c
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_chartables.c.dist
+-rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_chartables.c.ebcdic-1047-nl15
+-rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_chartables.c.ebcdic-1047-nl25
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_chkdint.c
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_compile.c
 -rw-r--r-- tarball-dir/pcre2-SNAPSHOT/src/pcre2_compile.h
diff --git a/src/config.h.generic b/src/config.h.generic
index b620fd4f7..7fd04814e 100644
--- a/src/config.h.generic
+++ b/src/config.h.generic
@@ -44,9 +44,14 @@ sure both macros are undefined; an emulation function will then be used. */
    assumes that all input strings are in EBCDIC. If you do not define this
    macro, PCRE2 will assume input strings are ASCII or UTF-8/16/32 Unicode. It
    is not possible to build a version of PCRE2 that supports both EBCDIC and
-   UTF-8/16/32. */
+   ASCII or UTF-8/16/32. */
 /* #undef EBCDIC */
 
+/* To force an EBCDIC environment, define this macro to make the core PCRE2
+   library functions use EBCDIC codepage 1047, regardless of whether the
+   compiler supports it using C character literals. */
+/* #undef EBCDIC_IGNORING_COMPILER */
+
 /* In an EBCDIC environment, define this macro to any value to arrange for the
    NL character to be 0x25 instead of the default 0x15. NL plays the role that
    LF does in an ASCII/Unicode environment. */
diff --git a/src/pcre2_chartables.c.ebcdic-1047-nl15 b/src/pcre2_chartables.c.ebcdic-1047-nl15
new file mode 100644
index 000000000..071a8f425
--- /dev/null
+++ b/src/pcre2_chartables.c.ebcdic-1047-nl15
@@ -0,0 +1,196 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* This file was automatically written by the pcre2_dftables auxiliary
+program. It contains character tables that are used when no external
+tables are passed to PCRE2 by the application that calls it. The tables
+are used only for characters whose code values are less than 256, and
+only relevant if not in UCP mode. */
+
+/* This set of tables was written in the EBCDIC 1047 (NL 0x15) locale. */
+
+/* The pcre2_ftables program (which is distributed with PCRE2) can be used
+to build alternative versions of this file. This is necessary if you are
+running in an EBCDIC environment, or if you want to default to a different
+encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
+these tables in the "C" locale by default. This happens automatically if
+PCRE2 is configured with --enable-rebuild-chartables. However, you can run
+pcre2_dftables manually with the -L option to build tables using the LC_ALL
+locale. */
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "pcre2_internal.h"
+
+const uint8_t PRIV(default_tables)[] = {
+
+/* This table is a lower casing table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 65, 66, 67, 68, 69, 70, 71,
+   72, 73, 74, 75, 76, 77, 78, 79,
+   80, 81, 82, 83, 84, 85, 86, 87,
+   88, 89, 90, 91, 92, 93, 94, 95,
+   96, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122,123,124,125,126,127,
+  128,129,130,131,132,133,134,135,
+  136,137,138,139,140,141,142,143,
+  144,145,146,147,148,149,150,151,
+  152,153,154,155,156,157,158,159,
+  160,161,162,163,164,165,166,167,
+  168,169,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,129,130,131,132,133,134,135,
+  136,137,202,203,204,205,206,207,
+  208,145,146,147,148,149,150,151,
+  152,153,218,219,220,221,222,223,
+  224,225,162,163,164,165,166,167,
+  168,169,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table is a case flipping table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 65, 66, 67, 68, 69, 70, 71,
+   72, 73, 74, 75, 76, 77, 78, 79,
+   80, 81, 82, 83, 84, 85, 86, 87,
+   88, 89, 90, 91, 92, 93, 94, 95,
+   96, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122,123,124,125,126,127,
+  128,193,194,195,196,197,198,199,
+  200,201,138,139,140,141,142,143,
+  144,209,210,211,212,213,214,215,
+  216,217,154,155,156,157,158,159,
+  160,161,226,227,228,229,230,231,
+  232,233,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,129,130,131,132,133,134,135,
+  136,137,202,203,204,205,206,207,
+  208,145,146,147,148,149,150,151,
+  152,153,218,219,220,221,222,223,
+  224,225,162,163,164,165,166,167,
+  168,169,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table contains bit maps for various character classes. Each map is 32
+bytes long and the bits run from the least significant end of each byte. The
+classes that have their own maps are: space, xdigit, digit, upper, lower, word,
+graph, print, punct, and cntrl. Other classes are built from combinations. */
+
+  0x20,0x38,0x20,0x00,0x00,0x00,0x00,0x00,  /* space */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* xdigit */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x7e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x7e,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* digit */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* upper */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* lower */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* word */
+  0x00,0x00,0x00,0x00,0x00,0x20,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* graph */
+  0x00,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0xfe,0x03,0xfe,0x03,0xfe,0x23,0x00,0x20,
+  0xff,0x03,0xff,0x03,0xfd,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* print */
+  0x01,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0xfe,0x03,0xfe,0x03,0xfe,0x23,0x00,0x20,
+  0xff,0x03,0xff,0x03,0xfd,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* punct */
+  0x00,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0x00,0x00,0x00,0x00,0x02,0x20,0x00,0x20,
+  0x01,0x00,0x01,0x00,0x01,0x00,0x00,0x00,
+
+  0xaf,0xf8,0x6f,0xf3,0xc0,0xe0,0x84,0xb0,  /* cntrl */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+/* This table identifies various classes of character by individual bits:
+  0x01   white space character
+  0x02   letter
+  0x04   lower case letter
+  0x08   decimal digit
+  0x10   word (alphanumeric or '_')
+*/
+
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*   0-  7 */
+  0x00,0x00,0x00,0x01,0x01,0x01,0x00,0x00, /*   8- 15 */
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*  16- 23 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*    - '  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ( - /  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  0 - 7  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  8 - ?  */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  @ - G  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  H - O  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  P - W  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  X - _  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ` - g  */
+  0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x00, /*  h - o  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  p - w  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  x -127 */
+  0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* 128-135 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
+  0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* 144-151 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
+  0x00,0x00,0x16,0x16,0x16,0x16,0x16,0x16, /* 160-167 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 192-199 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 208-215 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
+  0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 224-231 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
+  0x18,0x18,0x18,0x18,0x18,0x18,0x18,0x18, /* 240-247 */
+  0x18,0x18,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
+
+/* End of pcre2_chartables.c */
diff --git a/src/pcre2_chartables.c.ebcdic-1047-nl25 b/src/pcre2_chartables.c.ebcdic-1047-nl25
new file mode 100644
index 000000000..99ba81b20
--- /dev/null
+++ b/src/pcre2_chartables.c.ebcdic-1047-nl25
@@ -0,0 +1,196 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* This file was automatically written by the pcre2_dftables auxiliary
+program. It contains character tables that are used when no external
+tables are passed to PCRE2 by the application that calls it. The tables
+are used only for characters whose code values are less than 256, and
+only relevant if not in UCP mode. */
+
+/* This set of tables was written in the EBCDIC 1047 (NL 0x25) locale. */
+
+/* The pcre2_ftables program (which is distributed with PCRE2) can be used
+to build alternative versions of this file. This is necessary if you are
+running in an EBCDIC environment, or if you want to default to a different
+encoding, for example ISO-8859-1. When pcre2_dftables is run, it creates
+these tables in the "C" locale by default. This happens automatically if
+PCRE2 is configured with --enable-rebuild-chartables. However, you can run
+pcre2_dftables manually with the -L option to build tables using the LC_ALL
+locale. */
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "pcre2_internal.h"
+
+const uint8_t PRIV(default_tables)[] = {
+
+/* This table is a lower casing table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 65, 66, 67, 68, 69, 70, 71,
+   72, 73, 74, 75, 76, 77, 78, 79,
+   80, 81, 82, 83, 84, 85, 86, 87,
+   88, 89, 90, 91, 92, 93, 94, 95,
+   96, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122,123,124,125,126,127,
+  128,129,130,131,132,133,134,135,
+  136,137,138,139,140,141,142,143,
+  144,145,146,147,148,149,150,151,
+  152,153,154,155,156,157,158,159,
+  160,161,162,163,164,165,166,167,
+  168,169,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,129,130,131,132,133,134,135,
+  136,137,202,203,204,205,206,207,
+  208,145,146,147,148,149,150,151,
+  152,153,218,219,220,221,222,223,
+  224,225,162,163,164,165,166,167,
+  168,169,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table is a case flipping table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 65, 66, 67, 68, 69, 70, 71,
+   72, 73, 74, 75, 76, 77, 78, 79,
+   80, 81, 82, 83, 84, 85, 86, 87,
+   88, 89, 90, 91, 92, 93, 94, 95,
+   96, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122,123,124,125,126,127,
+  128,193,194,195,196,197,198,199,
+  200,201,138,139,140,141,142,143,
+  144,209,210,211,212,213,214,215,
+  216,217,154,155,156,157,158,159,
+  160,161,226,227,228,229,230,231,
+  232,233,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,129,130,131,132,133,134,135,
+  136,137,202,203,204,205,206,207,
+  208,145,146,147,148,149,150,151,
+  152,153,218,219,220,221,222,223,
+  224,225,162,163,164,165,166,167,
+  168,169,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table contains bit maps for various character classes. Each map is 32
+bytes long and the bits run from the least significant end of each byte. The
+classes that have their own maps are: space, xdigit, digit, upper, lower, word,
+graph, print, punct, and cntrl. Other classes are built from combinations. */
+
+  0x20,0x38,0x00,0x00,0x20,0x00,0x00,0x00,  /* space */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* xdigit */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x7e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x7e,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* digit */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* upper */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* lower */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* word */
+  0x00,0x00,0x00,0x00,0x00,0x20,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0x00,0x00,
+  0xfe,0x03,0xfe,0x03,0xfc,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* graph */
+  0x00,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0xfe,0x03,0xfe,0x03,0xfe,0x23,0x00,0x20,
+  0xff,0x03,0xff,0x03,0xfd,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* print */
+  0x01,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0xfe,0x03,0xfe,0x03,0xfe,0x23,0x00,0x20,
+  0xff,0x03,0xff,0x03,0xfd,0x03,0xff,0x03,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,  /* punct */
+  0x00,0xf8,0x01,0xfc,0x03,0xf8,0x00,0xfe,
+  0x00,0x00,0x00,0x00,0x02,0x20,0x00,0x20,
+  0x01,0x00,0x01,0x00,0x01,0x00,0x00,0x00,
+
+  0xaf,0xf8,0x4f,0xf3,0xe0,0xe0,0x84,0xb0,  /* cntrl */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+/* This table identifies various classes of character by individual bits:
+  0x01   white space character
+  0x02   letter
+  0x04   lower case letter
+  0x08   decimal digit
+  0x10   word (alphanumeric or '_')
+*/
+
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*   0-  7 */
+  0x00,0x00,0x00,0x01,0x01,0x01,0x00,0x00, /*   8- 15 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  16- 23 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*    - '  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ( - /  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  0 - 7  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  8 - ?  */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  @ - G  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  H - O  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  P - W  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  X - _  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ` - g  */
+  0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x00, /*  h - o  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  p - w  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  x -127 */
+  0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* 128-135 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
+  0x00,0x16,0x16,0x16,0x16,0x16,0x16,0x16, /* 144-151 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
+  0x00,0x00,0x16,0x16,0x16,0x16,0x16,0x16, /* 160-167 */
+  0x16,0x16,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 192-199 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 208-215 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
+  0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 224-231 */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
+  0x18,0x18,0x18,0x18,0x18,0x18,0x18,0x18, /* 240-247 */
+  0x18,0x18,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
+
+/* End of pcre2_chartables.c */
diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c
index 0ffac8939..9ab5292bf 100644
--- a/src/pcre2_compile.c
+++ b/src/pcre2_compile.c
@@ -400,10 +400,10 @@ static const short int escapes[] = {
     /* 4 */ 0,                       /* 5 */ 0,
     /* 6 */ 0,                       /* 7 */ 0,
     /* 8 */ 0,                       /* 9 */ 0,
-    /* : */ CHAR_COLON,              /* ; */ CHAR_SEMICOLON,
-    /* < */ CHAR_LESS_THAN_SIGN,     /* = */ CHAR_EQUALS_SIGN,
-    /* > */ CHAR_GREATER_THAN_SIGN,  /* ? */ CHAR_QUESTION_MARK,
-    /* @ */ CHAR_COMMERCIAL_AT,      /* A */ -ESC_A,
+    /* : */ ESCAPES_FIRST+0x0a,      /* ; */ ESCAPES_FIRST+0x0b,
+    /* < */ ESCAPES_FIRST+0x0c,      /* = */ ESCAPES_FIRST+0x0d,
+    /* > */ ESCAPES_FIRST+0x0e,      /* ? */ ESCAPES_FIRST+0x0f,
+    /* @ */ ESCAPES_FIRST+0x10,      /* A */ -ESC_A,
     /* B */ -ESC_B,                  /* C */ -ESC_C,
     /* D */ -ESC_D,                  /* E */ -ESC_E,
     /* F */ 0,                       /* G */ -ESC_G,
@@ -416,10 +416,10 @@ static const short int escapes[] = {
     /* T */ 0,                       /* U */ 0,
     /* V */ -ESC_V,                  /* W */ -ESC_W,
     /* X */ -ESC_X,                  /* Y */ 0,
-    /* Z */ -ESC_Z,                  /* [ */ CHAR_LEFT_SQUARE_BRACKET,
-    /* \ */ CHAR_BACKSLASH,          /* ] */ CHAR_RIGHT_SQUARE_BRACKET,
-    /* ^ */ CHAR_CIRCUMFLEX_ACCENT,  /* _ */ CHAR_UNDERSCORE,
-    /* ` */ CHAR_GRAVE_ACCENT,       /* a */ CHAR_BEL,
+    /* Z */ -ESC_Z,                  /* [ */ ESCAPES_FIRST+0x2b,
+    /* \ */ ESCAPES_FIRST+0x2c,      /* ] */ ESCAPES_FIRST+0x2d,
+    /* ^ */ ESCAPES_FIRST+0x2e,      /* _ */ ESCAPES_FIRST+0x2f,
+    /* ` */ ESCAPES_FIRST+0x30,      /* a */ CHAR_BEL,
     /* b */ -ESC_b,                  /* c */ 0,
     /* d */ -ESC_d,                  /* e */ CHAR_ESC,
     /* f */ CHAR_FF,                 /* g */ 0,
@@ -438,43 +438,94 @@ static const short int escapes[] = {
 #else
 
 /* This is the "abnormal" table for EBCDIC systems without UTF-8 support.
-It runs from 'a' to '9'. For some minimal testing of EBCDIC features, the code
-is sometimes compiled on an ASCII system. In this case, we must not use CHAR_a
-because it is defined as 'a', which of course picks up the ASCII value. */
+It runs from 'a' to '9'. Our EBCDIC support can be provided via the compiler,
+which can interpret character literals like 'a' or '[' in an EBCDIC codepage;
+in this case, there is wide variance between codepages on the interpretation of
+characters between the letters ('[' and '{' and so on are placed in all sorts of
+different positions in the table). Thankfully however, all EBCDIC codepages
+place the letters and digits in the same location, so we hardcode that here.
+Our EBCDIC support can also be provided via numeric literals instead of
+character literals, so either way, 'CHAR_a' will be 0x81 when PCRE2 is compiled
+in EBCDIC mode. */
 
-#if 'a' == 0x81                    /* Check for a real EBCDIC environment */
 #define ESCAPES_FIRST       CHAR_a
 #define ESCAPES_LAST        CHAR_9
 #define UPPER_CASE(c)       (c+64)
-#else                              /* Testing in an ASCII environment */
-#define ESCAPES_FIRST  ((unsigned char)'\x81')   /* EBCDIC 'a' */
-#define ESCAPES_LAST   ((unsigned char)'\xf9')   /* EBCDIC '9' */
-#define UPPER_CASE(c)  (c-32)
-#endif
 
 static const short int escapes[] = {
-/*  80 */         CHAR_BEL, -ESC_b,       0, -ESC_d, CHAR_ESC, CHAR_FF,      0,
-/*  88 */ -ESC_h,        0,      0,     '{',      0,        0,       0,      0,
-/*  90 */      0,        0, -ESC_k,       0,      0,  CHAR_LF,       0, -ESC_p,
-/*  98 */      0,  CHAR_CR,      0,     '}',      0,        0,       0,      0,
-/*  A0 */      0,      '~', -ESC_s, CHAR_HT,      0,   -ESC_v,  -ESC_w,      0,
-/*  A8 */      0,   -ESC_z,      0,       0,      0,      '[',       0,      0,
-/*  B0 */      0,        0,      0,       0,      0,        0,       0,      0,
-/*  B8 */      0,        0,      0,       0,      0,      ']',     '=',    '-',
-/*  C0 */    '{',   -ESC_A, -ESC_B,  -ESC_C, -ESC_D,   -ESC_E,       0, -ESC_G,
-/*  C8 */ -ESC_H,        0,      0,       0,      0,        0,       0,      0,
-/*  D0 */    '}',        0, -ESC_K,       0,      0,   -ESC_N,       0, -ESC_P,
-/*  D8 */ -ESC_Q,   -ESC_R,      0,       0,      0,        0,       0,      0,
-/*  E0 */   '\\',        0, -ESC_S,       0,      0,   -ESC_V,  -ESC_W, -ESC_X,
-/*  E8 */      0,   -ESC_Z,      0,       0,      0,        0,       0,      0,
-/*  F0 */      0,        0,      0,       0,      0,        0,       0,      0,
-/*  F8 */      0,        0
+    /* 0x81 a */ CHAR_BEL,             /* 0x82 b */ -ESC_b,
+    /* 0x83 c */ 0,                    /* 0x84 d */ -ESC_d,
+    /* 0x85 e */ CHAR_ESC,             /* 0x86 f */ CHAR_FF,
+    /* 0x87 g */ 0,                    /* 0x88 h */ -ESC_h,
+    /* 0x89 i */ 0,                    /* 0x8a   */ ESCAPES_FIRST+0x09,
+    /* 0x8b   */ ESCAPES_FIRST+0x0a,   /* 0x8c   */ ESCAPES_FIRST+0x0b,
+    /* 0x8d   */ ESCAPES_FIRST+0x0c,   /* 0x8e   */ ESCAPES_FIRST+0x0d,
+    /* 0x8f   */ ESCAPES_FIRST+0x0e,   /* 0x90   */ ESCAPES_FIRST+0x0f,
+    /* 0x91 j */ 0,                    /* 0x92 k */ -ESC_k,
+    /* 0x93 l */ 0,                    /* 0x94 m */ 0,
+    /* 0x95 n */ CHAR_LF,              /* 0x96 o */ 0,
+    /* 0x97 p */ -ESC_p,               /* 0x98 q */ 0,
+    /* 0x99 r */ CHAR_CR,              /* 0x9a   */ ESCAPES_FIRST+0x19,
+    /* 0x9b   */ ESCAPES_FIRST+0x1a,   /* 0x9c   */ ESCAPES_FIRST+0x1b,
+    /* 0x9d   */ ESCAPES_FIRST+0x1c,   /* 0x9e   */ ESCAPES_FIRST+0x1d,
+    /* 0x9f   */ ESCAPES_FIRST+0x1e,   /* 0xa0   */ ESCAPES_FIRST+0x1f,
+    /* 0xa1   */ ESCAPES_FIRST+0x20,   /* 0xa2 s */ -ESC_s,
+    /* 0xa3 t */ CHAR_HT,              /* 0xa4 u */ 0,
+    /* 0xa5 v */ -ESC_v,               /* 0xa6 w */ -ESC_w,
+    /* 0xa7 x */ 0,                    /* 0xa8 y */ 0,
+    /* 0xa9 z */ -ESC_z,               /* 0xaa   */ ESCAPES_FIRST+0x29,
+    /* 0xab   */ ESCAPES_FIRST+0x2a,   /* 0xac   */ ESCAPES_FIRST+0x2b,
+    /* 0xad   */ ESCAPES_FIRST+0x2c,   /* 0xae   */ ESCAPES_FIRST+0x2d,
+    /* 0xaf   */ ESCAPES_FIRST+0x2e,   /* 0xb0   */ ESCAPES_FIRST+0x2f,
+    /* 0xb1   */ ESCAPES_FIRST+0x30,   /* 0xb2   */ ESCAPES_FIRST+0x31,
+    /* 0xb3   */ ESCAPES_FIRST+0x32,   /* 0xb4   */ ESCAPES_FIRST+0x33,
+    /* 0xb5   */ ESCAPES_FIRST+0x34,   /* 0xb6   */ ESCAPES_FIRST+0x35,
+    /* 0xb7   */ ESCAPES_FIRST+0x36,   /* 0xb8   */ ESCAPES_FIRST+0x37,
+    /* 0xb9   */ ESCAPES_FIRST+0x38,   /* 0xba   */ ESCAPES_FIRST+0x39,
+    /* 0xbb   */ ESCAPES_FIRST+0x3a,   /* 0xbc   */ ESCAPES_FIRST+0x3b,
+    /* 0xbd   */ ESCAPES_FIRST+0x3c,   /* 0xbe   */ ESCAPES_FIRST+0x3d,
+    /* 0xbf   */ ESCAPES_FIRST+0x3e,   /* 0xc0   */ ESCAPES_FIRST+0x3f,
+    /* 0xc1 A */ -ESC_A,               /* 0xc2 B */ -ESC_B,
+    /* 0xc3 C */ -ESC_C,               /* 0xc4 D */ -ESC_D,
+    /* 0xc5 E */ -ESC_E,               /* 0xc6 F */ 0,
+    /* 0xc7 G */ -ESC_G,               /* 0xc8 H */ -ESC_H,
+    /* 0xc9 I */ 0,                    /* 0xca   */ ESCAPES_FIRST+0x49,
+    /* 0xcb   */ ESCAPES_FIRST+0x4a,   /* 0xcc   */ ESCAPES_FIRST+0x4b,
+    /* 0xcd   */ ESCAPES_FIRST+0x4c,   /* 0xce   */ ESCAPES_FIRST+0x4d,
+    /* 0xcf   */ ESCAPES_FIRST+0x4e,   /* 0xd0   */ ESCAPES_FIRST+0x4f,
+    /* 0xd1 J */ 0,                    /* 0xd2 K */ -ESC_K,
+    /* 0xd3 L */ 0,                    /* 0xd4 M */ 0,
+    /* 0xd5 N */ -ESC_N,               /* 0xd6 O */ 0,
+    /* 0xd7 P */ -ESC_P,               /* 0xd8 Q */ -ESC_Q,
+    /* 0xd9 R */ -ESC_R,               /* 0xda   */ ESCAPES_FIRST+0x59,
+    /* 0xdb   */ ESCAPES_FIRST+0x5a,   /* 0xdc   */ ESCAPES_FIRST+0x5b,
+    /* 0xdd   */ ESCAPES_FIRST+0x5c,   /* 0xde   */ ESCAPES_FIRST+0x5d,
+    /* 0xdf   */ ESCAPES_FIRST+0x5e,   /* 0xe0   */ ESCAPES_FIRST+0x5f,
+    /* 0xe1   */ ESCAPES_FIRST+0x60,   /* 0xe2 S */ -ESC_S,
+    /* 0xe3 T */ 0,                    /* 0xe4 U */ 0,
+    /* 0xe5 V */ -ESC_V,               /* 0xe6 W */ -ESC_W,
+    /* 0xe7 X */ -ESC_X,               /* 0xe8 Y */ 0,
+    /* 0xe9 Z */ -ESC_Z,               /* 0xea   */ ESCAPES_FIRST+0x69,
+    /* 0xeb   */ ESCAPES_FIRST+0x6a,   /* 0xec   */ ESCAPES_FIRST+0x6b,
+    /* 0xed   */ ESCAPES_FIRST+0x6c,   /* 0xee   */ ESCAPES_FIRST+0x6d,
+    /* 0xef   */ ESCAPES_FIRST+0x6e,   /* 0xf0 0 */ 0,
+    /* 0xf1 1 */ 0,                    /* 0xf2 2 */ 0,
+    /* 0xf3 3 */ 0,                    /* 0xf4 4 */ 0,
+    /* 0xf5 5 */ 0,                    /* 0xf6 6 */ 0,
+    /* 0xf7 7 */ 0,                    /* 0xf8 8 */ 0,
+    /* 0xf9 9 */ 0,
 };
 
 /* We also need a table of characters that may follow \c in an EBCDIC
 environment for characters 0-31. */
 
-static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
+static unsigned char ebcdic_escape_c[] = {
+  CHAR_COMMERCIAL_AT, CHAR_A, CHAR_B, CHAR_C, CHAR_D, CHAR_E, CHAR_F, CHAR_G,
+  CHAR_H, CHAR_I, CHAR_J, CHAR_K, CHAR_L, CHAR_M, CHAR_N, CHAR_O, CHAR_P,
+  CHAR_Q, CHAR_R, CHAR_S, CHAR_T, CHAR_U, CHAR_V, CHAR_W, CHAR_X, CHAR_Y,
+  CHAR_Z, CHAR_LEFT_SQUARE_BRACKET, CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET,
+  CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE
+};
 
 #endif   /* EBCDIC */
 
@@ -2113,11 +2164,7 @@ else
     For testing the EBCDIC handling of \c in an ASCII environment, recognize
     the EBCDIC value of 'c' explicitly. */
 
-#if defined EBCDIC && 'a' != 0x81
-    case 0x83:
-#else
     case CHAR_c:
-#endif
     if (ptr >= ptrend)
       {
       *errorcodeptr = ERR2;
@@ -2143,7 +2190,7 @@ else
 
 #else
     if (c == CHAR_QUESTION_MARK)
-      c = ('\\' == 188 && '`' == 74)? 0x5f : 0xff;
+      c = (CHAR_BACKSLASH == 188 && CHAR_GRAVE_ACCENT == 74)? 0x5f : 0xff;
     else
       {
       for (i = 0; i < 32; i++)
diff --git a/src/pcre2_convert.c b/src/pcre2_convert.c
index d2b238ca4..a7ecd7b20 100644
--- a/src/pcre2_convert.c
+++ b/src/pcre2_convert.c
@@ -190,6 +190,7 @@ while (plength > 0)
       switch (posix_state)
         {
         case POSIX_CLASS_STARTED:
+        // XXX EBCDIC
         if (c <= 127 && islower(c)) break;  /* Remain in started state */
         posix_state = POSIX_CLASS_NOT_STARTED;
         if (c == CHAR_COLON  && plength > 0 &&
@@ -277,6 +278,7 @@ while (plength > 0)
     if (plength == 0) return PCRE2_ERROR_END_BACKSLASH;
     if (extended) nextisliteral = TRUE; else
       {
+      // XXX EBCDIC
       if (*posix < 127 && strchr(posix_meta_escapes, *posix) != NULL)
         {
         if (isdigit(*posix)) PUTCHARS(STR_BACKSLASH);
@@ -335,6 +337,7 @@ while (plength > 0)
     /* Fall through */
 
     default:
+    // XXX EBCDIC
     if (c < 128 && strchr(pcre2_escaped_literals, c) != NULL)
       {
       ESCAPE_LITERAL:
@@ -474,6 +477,7 @@ static int
 convert_glob_parse_class(PCRE2_SPTR *from, PCRE2_SPTR pattern_end,
   pcre2_output_context *out)
 {
+// XXX EBCDIC
 static const char *posix_classes = "alnum:alpha:ascii:blank:cntrl:digit:"
   "graph:lower:print:punct:space:upper:word:xdigit:";
 PCRE2_SPTR start = *from + 1;
@@ -547,6 +551,7 @@ if (c > 0xff)
   }
 #endif
 
+// XXX EBCDIC
 switch (class_index)
   {
   case 1: return isalnum(c);
@@ -1005,6 +1010,7 @@ while (pattern < pattern_end)
     c = *pattern++;
     }
 
+  // XXX EBCDIC
   if (c < 128 && strchr(pcre2_escaped_literals, c) != NULL)
     convert_glob_write(&out, CHAR_BACKSLASH);
 
diff --git a/src/pcre2_dftables.c b/src/pcre2_dftables.c
index 0f9aedf85..374152ccc 100644
--- a/src/pcre2_dftables.c
+++ b/src/pcre2_dftables.c
@@ -56,12 +56,16 @@ given, they are written in binary. */
 #include 
 #include 
 
-#define PCRE2_DFTABLES            /* for pcre2_internal.h, pcre2_maketables.c */
+/* For pcre2_internal.h, pcre2_maketables.c, pcre2_tables.c */
+#define PCRE2_DFTABLES
+/* For pcre2_tables.c */
+#define PRIV(name) name
 
 #define PCRE2_CODE_UNIT_WIDTH 0   /* Must be set, but not relevant here */
 #include "pcre2_internal.h"
 
 #include "pcre2_maketables.c"
+#include "pcre2_tables.c"
 
 
 static const char *classlist[] =
@@ -70,6 +74,23 @@ static const char *classlist[] =
   "word", "graph", "print", "punct", "cntrl"
   };
 
+static int identity(int c) { return c; }
+
+#ifdef EBCDIC
+static int ebcdic_to_unicode(int c)
+{
+if (c < 0 || c > 255) abort();
+
+return ebcdic_1047_to_ascii[c];
+}
+
+static int unicode_to_ebcdic(int c)
+{
+if (c < 0 || c > 255) abort();
+
+return ascii_to_ebcdic_1047[c];
+}
+#endif
 
 
 /*************************************************
@@ -83,6 +104,9 @@ usage(void)
   "Usage: pcre2_dftables [options] \n"
   "  -b    Write output in binary (default is source code)\n"
   "  -L    Use locale from LC_ALL (default is \"C\" locale)\n"
+#ifdef EBCDIC
+  "  -E    Use EBCDIC 1047 via locale C.UTF-8\n"
+#endif
   );
 }
 
@@ -101,6 +125,8 @@ BOOL binary = FALSE;
 char *env = (char *)"C";
 const uint8_t *tables;
 const uint8_t *base_of_tables;
+int (*charfn_to)(int) = identity;
+int (*charfn_from)(int) = identity;
 
 /* Process options */
 
@@ -125,6 +151,24 @@ for (i = 1; i < argc; i++)
     env = getenv("LC_ALL");
     }
 
+#ifdef EBCDIC
+  else if (strcmp(arg, "-E") == 0)
+    {
+    if (setlocale(LC_ALL, "C.UTF-8") == NULL)
+      {
+      (void)fprintf(stderr, "pcre2_dftables: setlocale() failed\n");
+      return 1;
+      }
+#ifdef EBCDIC_NL25
+    env = "EBCDIC 1047 (NL 0x25)";
+#else
+    env = "EBCDIC 1047 (NL 0x15)";
+#endif
+    charfn_to = ebcdic_to_unicode;
+    charfn_from = unicode_to_ebcdic;
+    }
+#endif
+
   else if (strcmp(arg, "-b") == 0)
     binary = TRUE;
 
@@ -143,7 +187,7 @@ if (i != argc - 1)
 
 /* Make the tables */
 
-tables = maketables();
+tables = maketables(charfn_to, charfn_from);
 base_of_tables = tables;
 
 f = fopen(argv[i], "wb");
diff --git a/src/pcre2_error.c b/src/pcre2_error.c
index 8b7423c6c..9ae3a54ee 100644
--- a/src/pcre2_error.c
+++ b/src/pcre2_error.c
@@ -60,7 +60,12 @@ performance issue because these strings are used only when there is an error.
 
 Each substring ends with \0 to insert a null character. This includes the final
 substring, so that the whole string ends with \0\0, which can be detected when
-counting through. */
+counting through.
+
+In the rare configuration of EBCDIC-with-ASCII-compiler, we currently output
+ASCII strings for the error messages, which is unlikely to cause complaints if
+some client does want to use PCRE2 on Linux or Windows to process their EBCDIC
+files. */
 
 static const unsigned char compile_error_texts[] =
   "no error\0"
diff --git a/src/pcre2_internal.h b/src/pcre2_internal.h
index 6e0a5e05d..eaa930363 100644
--- a/src/pcre2_internal.h
+++ b/src/pcre2_internal.h
@@ -59,7 +59,7 @@ be including this file. There is no explicit way of forcing a compile to be
 abandoned, but trying to include a non-existent file seems cleanest. Otherwise
 there will be many irrelevant consequential errors. */
 
-#if (!defined PCRE2_BUILDING_PCRE2TEST && !defined PCRE2_DFTABLES) && \
+#if (!defined PCRE2_PCRE2TEST && !defined PCRE2_DFTABLES) && \
   (!defined PCRE2_CODE_UNIT_WIDTH ||     \
     (PCRE2_CODE_UNIT_WIDTH != 8 &&       \
      PCRE2_CODE_UNIT_WIDTH != 16 &&      \
@@ -698,6 +698,10 @@ same code point. */
 compatibility. NEL is the Unicode newline character; make sure it is
 a positive value. */
 
+#if '\n' != 0x0a
+#error "ASCII character '\n' is not 0x0a"
+#endif
+
 #define CHAR_LF                     '\n'
 #define CHAR_NL                     CHAR_LF
 #define CHAR_NEL                    ((unsigned char)'\x85')
@@ -713,7 +717,232 @@ a positive value. */
 
 #endif  /* EBCDIC */
 
-/* The remaining definitions work in both environments. */
+/* When we want to use EBCDIC with an ASCII compiler, for testing EBCDIC on
+ASCII platforms, then we can hardcode an EBCDIC codepage (IBM-1047). */
+
+#ifdef EBCDIC_IGNORING_COMPILER
+
+#define CHAR_NUL                    '\000'
+#define CHAR_HT                     '\005'
+#define CHAR_VT                     '\013'
+#define CHAR_FF                     '\014'
+#define CHAR_CR                     '\015'
+#define CHAR_BS                     '\026'
+#define CHAR_BEL                    '\057'
+
+#define CHAR_SPACE                  '\100'
+#define CHAR_EXCLAMATION_MARK       '\132'
+#define CHAR_QUOTATION_MARK         '\177'
+#define CHAR_NUMBER_SIGN            '\173'
+#define CHAR_DOLLAR_SIGN            '\133'
+#define CHAR_PERCENT_SIGN           '\154'
+#define CHAR_AMPERSAND              '\120'
+#define CHAR_APOSTROPHE             '\175'
+#define CHAR_LEFT_PARENTHESIS       '\115'
+#define CHAR_RIGHT_PARENTHESIS      '\135'
+#define CHAR_ASTERISK               '\134'
+#define CHAR_PLUS                   '\116'
+#define CHAR_COMMA                  '\153'
+#define CHAR_MINUS                  '\140'
+#define CHAR_DOT                    '\113'
+#define CHAR_SLASH                  '\141'
+#define CHAR_0                      ((unsigned char)'\xf0')
+#define CHAR_1                      ((unsigned char)'\xf1')
+#define CHAR_2                      ((unsigned char)'\xf2')
+#define CHAR_3                      ((unsigned char)'\xf3')
+#define CHAR_4                      ((unsigned char)'\xf4')
+#define CHAR_5                      ((unsigned char)'\xf5')
+#define CHAR_6                      ((unsigned char)'\xf6')
+#define CHAR_7                      ((unsigned char)'\xf7')
+#define CHAR_8                      ((unsigned char)'\xf8')
+#define CHAR_9                      ((unsigned char)'\xf9')
+#define CHAR_COLON                  '\172'
+#define CHAR_SEMICOLON              '\136'
+#define CHAR_LESS_THAN_SIGN         '\114'
+#define CHAR_EQUALS_SIGN            '\176'
+#define CHAR_GREATER_THAN_SIGN      '\156'
+#define CHAR_QUESTION_MARK          '\157'
+#define CHAR_COMMERCIAL_AT          '\174'
+#define CHAR_A                      ((unsigned char)'\xc1')
+#define CHAR_B                      ((unsigned char)'\xc2')
+#define CHAR_C                      ((unsigned char)'\xc3')
+#define CHAR_D                      ((unsigned char)'\xc4')
+#define CHAR_E                      ((unsigned char)'\xc5')
+#define CHAR_F                      ((unsigned char)'\xc6')
+#define CHAR_G                      ((unsigned char)'\xc7')
+#define CHAR_H                      ((unsigned char)'\xc8')
+#define CHAR_I                      ((unsigned char)'\xc9')
+#define CHAR_J                      ((unsigned char)'\xd1')
+#define CHAR_K                      ((unsigned char)'\xd2')
+#define CHAR_L                      ((unsigned char)'\xd3')
+#define CHAR_M                      ((unsigned char)'\xd4')
+#define CHAR_N                      ((unsigned char)'\xd5')
+#define CHAR_O                      ((unsigned char)'\xd6')
+#define CHAR_P                      ((unsigned char)'\xd7')
+#define CHAR_Q                      ((unsigned char)'\xd8')
+#define CHAR_R                      ((unsigned char)'\xd9')
+#define CHAR_S                      ((unsigned char)'\xe2')
+#define CHAR_T                      ((unsigned char)'\xe3')
+#define CHAR_U                      ((unsigned char)'\xe4')
+#define CHAR_V                      ((unsigned char)'\xe5')
+#define CHAR_W                      ((unsigned char)'\xe6')
+#define CHAR_X                      ((unsigned char)'\xe7')
+#define CHAR_Y                      ((unsigned char)'\xe8')
+#define CHAR_Z                      ((unsigned char)'\xe9')
+#define CHAR_LEFT_SQUARE_BRACKET    ((unsigned char)'\xad')
+#define CHAR_BACKSLASH              ((unsigned char)'\xe0')
+#define CHAR_RIGHT_SQUARE_BRACKET   ((unsigned char)'\xbd')
+#define CHAR_CIRCUMFLEX_ACCENT      '\137'
+#define CHAR_UNDERSCORE             '\155'
+#define CHAR_GRAVE_ACCENT           '\171'
+#define CHAR_a                      ((unsigned char)'\x81')
+#define CHAR_b                      ((unsigned char)'\x82')
+#define CHAR_c                      ((unsigned char)'\x83')
+#define CHAR_d                      ((unsigned char)'\x84')
+#define CHAR_e                      ((unsigned char)'\x85')
+#define CHAR_f                      ((unsigned char)'\x86')
+#define CHAR_g                      ((unsigned char)'\x87')
+#define CHAR_h                      ((unsigned char)'\x88')
+#define CHAR_i                      ((unsigned char)'\x89')
+#define CHAR_j                      ((unsigned char)'\x91')
+#define CHAR_k                      ((unsigned char)'\x92')
+#define CHAR_l                      ((unsigned char)'\x93')
+#define CHAR_m                      ((unsigned char)'\x94')
+#define CHAR_n                      ((unsigned char)'\x95')
+#define CHAR_o                      ((unsigned char)'\x96')
+#define CHAR_p                      ((unsigned char)'\x97')
+#define CHAR_q                      ((unsigned char)'\x98')
+#define CHAR_r                      ((unsigned char)'\x99')
+#define CHAR_s                      ((unsigned char)'\xa2')
+#define CHAR_t                      ((unsigned char)'\xa3')
+#define CHAR_u                      ((unsigned char)'\xa4')
+#define CHAR_v                      ((unsigned char)'\xa5')
+#define CHAR_w                      ((unsigned char)'\xa6')
+#define CHAR_x                      ((unsigned char)'\xa7')
+#define CHAR_y                      ((unsigned char)'\xa8')
+#define CHAR_z                      ((unsigned char)'\xa9')
+#define CHAR_LEFT_CURLY_BRACKET     ((unsigned char)'\xc0')
+#define CHAR_VERTICAL_LINE          '\117'
+#define CHAR_RIGHT_CURLY_BRACKET    ((unsigned char)'\xd0')
+#define CHAR_TILDE                  ((unsigned char)'\xa1')
+
+#define STR_HT                      "\005"
+#define STR_VT                      "\013"
+#define STR_FF                      "\014"
+#define STR_CR                      "\015"
+#define STR_BS                      "\026"
+#define STR_BEL                     "\057"
+
+#define STR_SPACE                   "\100"
+#define STR_EXCLAMATION_MARK        "\132"
+#define STR_QUOTATION_MARK          "\177"
+#define STR_NUMBER_SIGN             "\173"
+#define STR_DOLLAR_SIGN             "\133"
+#define STR_PERCENT_SIGN            "\154"
+#define STR_AMPERSAND               "\120"
+#define STR_APOSTROPHE              "\175"
+#define STR_LEFT_PARENTHESIS        "\115"
+#define STR_RIGHT_PARENTHESIS       "\135"
+#define STR_ASTERISK                "\134"
+#define STR_PLUS                    "\116"
+#define STR_COMMA                   "\153"
+#define STR_MINUS                   "\140"
+#define STR_DOT                     "\113"
+#define STR_SLASH                   "\141"
+#define STR_0                       "\360"
+#define STR_1                       "\361"
+#define STR_2                       "\362"
+#define STR_3                       "\363"
+#define STR_4                       "\364"
+#define STR_5                       "\365"
+#define STR_6                       "\366"
+#define STR_7                       "\367"
+#define STR_8                       "\370"
+#define STR_9                       "\371"
+#define STR_COLON                   "\172"
+#define STR_SEMICOLON               "\136"
+#define STR_LESS_THAN_SIGN          "\114"
+#define STR_EQUALS_SIGN             "\176"
+#define STR_GREATER_THAN_SIGN       "\156"
+#define STR_QUESTION_MARK           "\157"
+#define STR_COMMERCIAL_AT           "\174"
+#define STR_A                       "\301"
+#define STR_B                       "\302"
+#define STR_C                       "\303"
+#define STR_D                       "\304"
+#define STR_E                       "\305"
+#define STR_F                       "\306"
+#define STR_G                       "\307"
+#define STR_H                       "\310"
+#define STR_I                       "\311"
+#define STR_J                       "\321"
+#define STR_K                       "\322"
+#define STR_L                       "\323"
+#define STR_M                       "\324"
+#define STR_N                       "\325"
+#define STR_O                       "\326"
+#define STR_P                       "\327"
+#define STR_Q                       "\330"
+#define STR_R                       "\331"
+#define STR_S                       "\342"
+#define STR_T                       "\343"
+#define STR_U                       "\344"
+#define STR_V                       "\345"
+#define STR_W                       "\346"
+#define STR_X                       "\347"
+#define STR_Y                       "\350"
+#define STR_Z                       "\351"
+#define STR_LEFT_SQUARE_BRACKET     "\255"
+#define STR_BACKSLASH               "\340"
+#define STR_RIGHT_SQUARE_BRACKET    "\275"
+#define STR_CIRCUMFLEX_ACCENT       "\137"
+#define STR_UNDERSCORE              "\155"
+#define STR_GRAVE_ACCENT            "\171"
+#define STR_a                       "\201"
+#define STR_b                       "\202"
+#define STR_c                       "\203"
+#define STR_d                       "\204"
+#define STR_e                       "\205"
+#define STR_f                       "\206"
+#define STR_g                       "\207"
+#define STR_h                       "\210"
+#define STR_i                       "\211"
+#define STR_j                       "\221"
+#define STR_k                       "\222"
+#define STR_l                       "\223"
+#define STR_m                       "\224"
+#define STR_n                       "\225"
+#define STR_o                       "\226"
+#define STR_p                       "\227"
+#define STR_q                       "\230"
+#define STR_r                       "\231"
+#define STR_s                       "\242"
+#define STR_t                       "\243"
+#define STR_u                       "\244"
+#define STR_v                       "\245"
+#define STR_w                       "\246"
+#define STR_x                       "\247"
+#define STR_y                       "\250"
+#define STR_z                       "\251"
+#define STR_LEFT_CURLY_BRACKET      "\300"
+#define STR_VERTICAL_LINE           "\117"
+#define STR_RIGHT_CURLY_BRACKET     "\320"
+#define STR_TILDE                   "\241"
+
+#else  /* EBCDIC_IGNORING_COMPILER */
+
+/* Otherwise, on a real EBCDIC compiler or an ASCII compiler, we can use simple
+string and character literals. */
+
+#ifdef EBCDIC
+#if 'a' != 0x81
+#error "EBCDIC character 'a' is not 0x81"
+#endif
+#else
+#if 'a' != 0x61
+#error "ASCII character 'a' is not 0x61"
+#endif
+#endif
 
 #define CHAR_NUL                    '\0'
 #define CHAR_HT                     '\t'
@@ -922,88 +1151,7 @@ a positive value. */
 #define STR_RIGHT_CURLY_BRACKET     "}"
 #define STR_TILDE                   "~"
 
-#define STRING_ACCEPT0               "ACCEPT\0"
-#define STRING_COMMIT0               "COMMIT\0"
-#define STRING_F0                    "F\0"
-#define STRING_FAIL0                 "FAIL\0"
-#define STRING_MARK0                 "MARK\0"
-#define STRING_PRUNE0                "PRUNE\0"
-#define STRING_SKIP0                 "SKIP\0"
-#define STRING_THEN                  "THEN"
-
-#define STRING_atomic0               "atomic\0"
-#define STRING_pla0                  "pla\0"
-#define STRING_plb0                  "plb\0"
-#define STRING_napla0                "napla\0"
-#define STRING_naplb0                "naplb\0"
-#define STRING_nla0                  "nla\0"
-#define STRING_nlb0                  "nlb\0"
-#define STRING_scs0                  "scs\0"
-#define STRING_sr0                   "sr\0"
-#define STRING_asr0                  "asr\0"
-#define STRING_positive_lookahead0   "positive_lookahead\0"
-#define STRING_positive_lookbehind0  "positive_lookbehind\0"
-#define STRING_non_atomic_positive_lookahead0   "non_atomic_positive_lookahead\0"
-#define STRING_non_atomic_positive_lookbehind0  "non_atomic_positive_lookbehind\0"
-#define STRING_negative_lookahead0   "negative_lookahead\0"
-#define STRING_negative_lookbehind0  "negative_lookbehind\0"
-#define STRING_script_run0           "script_run\0"
-#define STRING_atomic_script_run     "atomic_script_run"
-#define STRING_scan_substring0       "scan_substring\0"
-
-#define STRING_alpha0                "alpha\0"
-#define STRING_lower0                "lower\0"
-#define STRING_upper0                "upper\0"
-#define STRING_alnum0                "alnum\0"
-#define STRING_ascii0                "ascii\0"
-#define STRING_blank0                "blank\0"
-#define STRING_cntrl0                "cntrl\0"
-#define STRING_digit0                "digit\0"
-#define STRING_graph0                "graph\0"
-#define STRING_print0                "print\0"
-#define STRING_punct0                "punct\0"
-#define STRING_space0                "space\0"
-#define STRING_word0                 "word\0"
-#define STRING_xdigit                "xdigit"
-
-#define STRING_DEFINE                "DEFINE"
-#define STRING_VERSION               "VERSION"
-#define STRING_WEIRD_STARTWORD       "[:<:]]"
-#define STRING_WEIRD_ENDWORD         "[:>:]]"
-
-#define STRING_CR_RIGHTPAR                "CR)"
-#define STRING_LF_RIGHTPAR                "LF)"
-#define STRING_CRLF_RIGHTPAR              "CRLF)"
-#define STRING_ANY_RIGHTPAR               "ANY)"
-#define STRING_ANYCRLF_RIGHTPAR           "ANYCRLF)"
-#define STRING_NUL_RIGHTPAR               "NUL)"
-#define STRING_BSR_ANYCRLF_RIGHTPAR       "BSR_ANYCRLF)"
-#define STRING_BSR_UNICODE_RIGHTPAR       "BSR_UNICODE)"
-#define STRING_UTF8_RIGHTPAR              "UTF8)"
-#define STRING_UTF16_RIGHTPAR             "UTF16)"
-#define STRING_UTF32_RIGHTPAR             "UTF32)"
-#define STRING_UTF_RIGHTPAR               "UTF)"
-#define STRING_UCP_RIGHTPAR               "UCP)"
-#define STRING_NO_AUTO_POSSESS_RIGHTPAR   "NO_AUTO_POSSESS)"
-#define STRING_NO_DOTSTAR_ANCHOR_RIGHTPAR "NO_DOTSTAR_ANCHOR)"
-#define STRING_NO_JIT_RIGHTPAR            "NO_JIT)"
-#define STRING_NO_START_OPT_RIGHTPAR      "NO_START_OPT)"
-#define STRING_NOTEMPTY_RIGHTPAR          "NOTEMPTY)"
-#define STRING_NOTEMPTY_ATSTART_RIGHTPAR  "NOTEMPTY_ATSTART)"
-#define STRING_CASELESS_RESTRICT_RIGHTPAR "CASELESS_RESTRICT)"
-#define STRING_TURKISH_CASING_RIGHTPAR    "TURKISH_CASING)"
-#define STRING_LIMIT_HEAP_EQ              "LIMIT_HEAP="
-#define STRING_LIMIT_MATCH_EQ             "LIMIT_MATCH="
-#define STRING_LIMIT_DEPTH_EQ             "LIMIT_DEPTH="
-#define STRING_LIMIT_RECURSION_EQ         "LIMIT_RECURSION="
-#define STRING_MARK                       "MARK"
-
-#define STRING_bc                         "bc"
-#define STRING_bidiclass                  "bidiclass"
-#define STRING_sc                         "sc"
-#define STRING_script                     "script"
-#define STRING_scriptextensions           "scriptextensions"
-#define STRING_scx                        "scx"
+#endif  /* EBCDIC_WITH_ASCII_COMPILER */
 
 #else  /* SUPPORT_UNICODE */
 
@@ -1227,6 +1375,9 @@ only. */
 #define STR_RIGHT_CURLY_BRACKET     "\175"
 #define STR_TILDE                   "\176"
 
+#endif  /* SUPPORT_UNICODE */
+
+
 #define STRING_ACCEPT0               STR_A STR_C STR_C STR_E STR_P STR_T "\0"
 #define STRING_COMMIT0               STR_C STR_O STR_M STR_M STR_I STR_T "\0"
 #define STRING_F0                    STR_F "\0"
@@ -1311,8 +1462,6 @@ only. */
 #define STRING_scx                        STR_s STR_c STR_x
 
 
-#endif  /* SUPPORT_UNICODE */
-
 /* -------------------- End of character and string names -------------------*/
 
 /* -------------------- Definitions for compiled patterns -------------------*/
diff --git a/src/pcre2_maketables.c b/src/pcre2_maketables.c
index 0474cc7db..fe336f565 100644
--- a/src/pcre2_maketables.c
+++ b/src/pcre2_maketables.c
@@ -64,14 +64,15 @@ supplied, but when PCRE2_DFTABLES is defined (when compiling the pcre2_dftables
 freestanding auxiliary program) malloc() is used, and the function has a
 different name so as not to clash with the prototype in pcre2.h.
 
-Arguments:   none when PCRE2_DFTABLES is defined
+Arguments:   pointers to character-transforming functions when PCRE2_DFTABLES is
+             defined;
                else a PCRE2 general context or NULL
-Returns:     pointer to the contiguous block of data
+Returns:     pointer to the contiguous block of data;
                else NULL if memory allocation failed
 */
 
 #ifdef PCRE2_DFTABLES  /* Included in freestanding pcre2_dftables program */
-static const uint8_t *maketables(void)
+static const uint8_t *maketables(int (*charfn_to)(int), int (*charfn_from)(int))
 {
 uint8_t *yield = (uint8_t *)malloc(TABLES_LENGTH);
 
@@ -82,6 +83,9 @@ pcre2_maketables(pcre2_general_context *gcontext)
 uint8_t *yield = (uint8_t *)((gcontext != NULL)?
   gcontext->memctl.malloc(TABLES_LENGTH, gcontext->memctl.memory_data) :
   malloc(TABLES_LENGTH));
+
+#define charfn_to(c)    (c)
+#define charfn_from(c)  (c)
 #endif  /* PCRE2_DFTABLES */
 
 int i;
@@ -92,13 +96,18 @@ p = yield;
 
 /* First comes the lower casing table */
 
-for (i = 0; i < 256; i++) *p++ = tolower(i);
+for (i = 0; i < 256; i++)
+  {
+  int c = charfn_from(tolower(charfn_to(i)));
+  *p++ = (c < 256)? c : i;
+  }
 
 /* Next the case-flipping table */
 
 for (i = 0; i < 256; i++)
   {
-  int c = islower(i)? toupper(i) : tolower(i);
+  int c = charfn_from(islower(charfn_to(i))? toupper(charfn_to(i))
+                                           : tolower(charfn_to(i)));
   *p++ = (c < 256)? c : i;
   }
 
@@ -118,17 +127,17 @@ test for alnum specially. */
 memset(p, 0, cbit_length);
 for (i = 0; i < 256; i++)
   {
-  if (isdigit(i))  p[cbit_digit  + i/8] |= 1u << (i&7);
-  if (isupper(i))  p[cbit_upper  + i/8] |= 1u << (i&7);
-  if (islower(i))  p[cbit_lower  + i/8] |= 1u << (i&7);
-  if (isalnum(i))  p[cbit_word   + i/8] |= 1u << (i&7);
-  if (i == '_')    p[cbit_word   + i/8] |= 1u << (i&7);
-  if (isspace(i))  p[cbit_space  + i/8] |= 1u << (i&7);
-  if (isxdigit(i)) p[cbit_xdigit + i/8] |= 1u << (i&7);
-  if (isgraph(i))  p[cbit_graph  + i/8] |= 1u << (i&7);
-  if (isprint(i))  p[cbit_print  + i/8] |= 1u << (i&7);
-  if (ispunct(i))  p[cbit_punct  + i/8] |= 1u << (i&7);
-  if (iscntrl(i))  p[cbit_cntrl  + i/8] |= 1u << (i&7);
+  if (isdigit(charfn_to(i)))  p[cbit_digit  + i/8] |= 1u << (i&7);
+  if (isupper(charfn_to(i)))  p[cbit_upper  + i/8] |= 1u << (i&7);
+  if (islower(charfn_to(i)))  p[cbit_lower  + i/8] |= 1u << (i&7);
+  if (isalnum(charfn_to(i)))  p[cbit_word   + i/8] |= 1u << (i&7);
+  if (i == CHAR_UNDERSCORE)   p[cbit_word   + i/8] |= 1u << (i&7);
+  if (isspace(charfn_to(i)))  p[cbit_space  + i/8] |= 1u << (i&7);
+  if (isxdigit(charfn_to(i))) p[cbit_xdigit + i/8] |= 1u << (i&7);
+  if (isgraph(charfn_to(i)))  p[cbit_graph  + i/8] |= 1u << (i&7);
+  if (isprint(charfn_to(i)))  p[cbit_print  + i/8] |= 1u << (i&7);
+  if (ispunct(charfn_to(i)))  p[cbit_punct  + i/8] |= 1u << (i&7);
+  if (iscntrl(charfn_to(i)))  p[cbit_cntrl  + i/8] |= 1u << (i&7);
   }
 p += cbit_length;
 
@@ -140,11 +149,11 @@ changed at release 8.34 and it's always been this way for PCRE2. */
 for (i = 0; i < 256; i++)
   {
   int x = 0;
-  if (isspace(i)) x += ctype_space;
-  if (isalpha(i)) x += ctype_letter;
-  if (islower(i)) x += ctype_lcletter;
-  if (isdigit(i)) x += ctype_digit;
-  if (isalnum(i) || i == '_') x += ctype_word;
+  if (isspace(charfn_to(i))) x += ctype_space;
+  if (isalpha(charfn_to(i))) x += ctype_letter;
+  if (islower(charfn_to(i))) x += ctype_lcletter;
+  if (isdigit(charfn_to(i))) x += ctype_digit;
+  if (isalnum(charfn_to(i)) || i == CHAR_UNDERSCORE) x += ctype_word;
   *p++ = x;
   }
 
@@ -152,6 +161,9 @@ return yield;
 }
 
 #ifndef PCRE2_DFTABLES   /* Compiling the library */
+#undef charfn_to
+#undef charfn_from
+
 PCRE2_EXP_DEFN void PCRE2_CALL_CONVENTION
 pcre2_maketables_free(pcre2_general_context *gcontext, const uint8_t *tables)
 {
diff --git a/src/pcre2_tables.c b/src/pcre2_tables.c
index 097a1acca..551ac0f82 100644
--- a/src/pcre2_tables.c
+++ b/src/pcre2_tables.c
@@ -44,19 +44,19 @@ which uses macros to change their names from _pcre2_xxx to xxxx, thereby
 avoiding name clashes with the library. In this case, PCRE2_PCRE2TEST is
 defined. */
 
-#ifndef PCRE2_PCRE2TEST           /* We're compiling the library */
+#if !defined(PCRE2_PCRE2TEST) && !defined(PCRE2_DFTABLES) /* We're compiling the library */
 #ifdef HAVE_CONFIG_H
 #include "config.h"
 #endif
 #include "pcre2_internal.h"
-#endif /* PCRE2_PCRE2TEST */
+#endif
 
 /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
 the definition is next to the definition of the opcodes in pcre2_internal.h.
 This is mode-dependent, so it is skipped when this file is included by
 pcre2test. */
 
-#ifndef PCRE2_PCRE2TEST
+#if !defined(PCRE2_PCRE2TEST) && !defined(PCRE2_DFTABLES)
 const uint8_t PRIV(OP_lengths)[] = { OP_LENGTHS };
 #endif
 
@@ -91,6 +91,7 @@ handling wide characters. */
 
 #if defined PCRE2_PCRE2TEST || \
    (defined SUPPORT_UNICODE && \
+    !defined(PCRE2_DFTABLES) && \
     defined PCRE2_CODE_UNIT_WIDTH && \
     PCRE2_CODE_UNIT_WIDTH == 8)
 
@@ -123,7 +124,7 @@ const uint8_t PRIV(utf8_table4)[] = {
 support is enabled. See also the pcre2_ucptables.c file, which is generated by
 a Python script from Unicode data files. */
 
-#ifdef SUPPORT_UNICODE
+#if defined(SUPPORT_UNICODE) && !defined(PCRE2_DFTABLES)
 
 /* Table to translate from particular type value to the general value. */
 
@@ -229,6 +230,66 @@ files. */
 
 #include "pcre2_ucptables.c"
 
-#endif /* SUPPORT_UNICODE */
+#endif /* Unicode support needed */
+
+
+/*************************************************
+*          Tables for EBCDIC support             *
+*************************************************/
+
+#if defined(EBCDIC) && (defined(PCRE2_PCRE2TEST) || defined(PCRE2_DFTABLES))
+
+const uint8_t ebcdic_1047_to_ascii[256] = {
+  0x00,0x01,0x02,0x03,0x9c,0x09,0x86,0x7f,0x97,0x8d,0x8e,0x0b,0x0c,0x0d,0x0e,0x0f,
+#ifdef EBCDIC_NL25
+  0x10,0x11,0x12,0x13,0x9d,0x85,0x08,0x87,0x18,0x19,0x92,0x8f,0x1c,0x1d,0x1e,0x1f,
+  0x80,0x81,0x82,0x83,0x84,0x0a,0x17,0x1b,0x88,0x89,0x8a,0x8b,0x8c,0x05,0x06,0x07,
+#else
+  0x10,0x11,0x12,0x13,0x9d,0x0a,0x08,0x87,0x18,0x19,0x92,0x8f,0x1c,0x1d,0x1e,0x1f,
+  0x80,0x81,0x82,0x83,0x84,0x85,0x17,0x1b,0x88,0x89,0x8a,0x8b,0x8c,0x05,0x06,0x07,
+#endif
+  0x90,0x91,0x16,0x93,0x94,0x95,0x96,0x04,0x98,0x99,0x9a,0x9b,0x14,0x15,0x9e,0x1a,
+  0x20,0xa0,0xe2,0xe4,0xe0,0xe1,0xe3,0xe5,0xe7,0xf1,0xa2,0x2e,0x3c,0x28,0x2b,0x7c,
+  0x26,0xe9,0xea,0xeb,0xe8,0xed,0xee,0xef,0xec,0xdf,0x21,0x24,0x2a,0x29,0x3b,0x5e,
+  0x2d,0x2f,0xc2,0xc4,0xc0,0xc1,0xc3,0xc5,0xc7,0xd1,0xa6,0x2c,0x25,0x5f,0x3e,0x3f,
+  0xf8,0xc9,0xca,0xcb,0xc8,0xcd,0xce,0xcf,0xcc,0x60,0x3a,0x23,0x40,0x27,0x3d,0x22,
+  0xd8,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0xab,0xbb,0xf0,0xfd,0xfe,0xb1,
+  0xb0,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f,0x70,0x71,0x72,0xaa,0xba,0xe6,0xb8,0xc6,0xa4,
+  0xb5,0x7e,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0xa1,0xbf,0xd0,0x5b,0xde,0xae,
+  0xac,0xa3,0xa5,0xb7,0xa9,0xa7,0xb6,0xbc,0xbd,0xbe,0xdd,0xa8,0xaf,0x5d,0xb4,0xd7,
+  0x7b,0x41,0x42,0x43,0x44,0x45,0x46,0x47,0x48,0x49,0xad,0xf4,0xf6,0xf2,0xf3,0xf5,
+  0x7d,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f,0x50,0x51,0x52,0xb9,0xfb,0xfc,0xf9,0xfa,0xff,
+  0x5c,0xf7,0x53,0x54,0x55,0x56,0x57,0x58,0x59,0x5a,0xb2,0xd4,0xd6,0xd2,0xd3,0xd5,
+  0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0xb3,0xdb,0xdc,0xd9,0xda,0x9f,
+};
+
+const uint8_t ascii_to_ebcdic_1047[256] = {
+#ifdef EBCDIC_NL25
+  0x00,0x01,0x02,0x03,0x37,0x2d,0x2e,0x2f,0x16,0x05,0x25,0x0b,0x0c,0x0d,0x0e,0x0f,
+#else
+  0x00,0x01,0x02,0x03,0x37,0x2d,0x2e,0x2f,0x16,0x05,0x15,0x0b,0x0c,0x0d,0x0e,0x0f,
+#endif
+  0x10,0x11,0x12,0x13,0x3c,0x3d,0x32,0x26,0x18,0x19,0x3f,0x27,0x1c,0x1d,0x1e,0x1f,
+  0x40,0x5a,0x7f,0x7b,0x5b,0x6c,0x50,0x7d,0x4d,0x5d,0x5c,0x4e,0x6b,0x60,0x4b,0x61,
+  0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7,0xf8,0xf9,0x7a,0x5e,0x4c,0x7e,0x6e,0x6f,
+  0x7c,0xc1,0xc2,0xc3,0xc4,0xc5,0xc6,0xc7,0xc8,0xc9,0xd1,0xd2,0xd3,0xd4,0xd5,0xd6,
+  0xd7,0xd8,0xd9,0xe2,0xe3,0xe4,0xe5,0xe6,0xe7,0xe8,0xe9,0xad,0xe0,0xbd,0x5f,0x6d,
+  0x79,0x81,0x82,0x83,0x84,0x85,0x86,0x87,0x88,0x89,0x91,0x92,0x93,0x94,0x95,0x96,
+  0x97,0x98,0x99,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7,0xa8,0xa9,0xc0,0x4f,0xd0,0xa1,0x07,
+#ifdef EBCDIC_NL25
+  0x20,0x21,0x22,0x23,0x24,0x15,0x06,0x17,0x28,0x29,0x2a,0x2b,0x2c,0x09,0x0a,0x1b,
+#else
+  0x20,0x21,0x22,0x23,0x24,0x25,0x06,0x17,0x28,0x29,0x2a,0x2b,0x2c,0x09,0x0a,0x1b,
+#endif
+  0x30,0x31,0x1a,0x33,0x34,0x35,0x36,0x08,0x38,0x39,0x3a,0x3b,0x04,0x14,0x3e,0xff,
+  0x41,0xaa,0x4a,0xb1,0x9f,0xb2,0x6a,0xb5,0xbb,0xb4,0x9a,0x8a,0xb0,0xca,0xaf,0xbc,
+  0x90,0x8f,0xea,0xfa,0xbe,0xa0,0xb6,0xb3,0x9d,0xda,0x9b,0x8b,0xb7,0xb8,0xb9,0xab,
+  0x64,0x65,0x62,0x66,0x63,0x67,0x9e,0x68,0x74,0x71,0x72,0x73,0x78,0x75,0x76,0x77,
+  0xac,0x69,0xed,0xee,0xeb,0xef,0xec,0xbf,0x80,0xfd,0xfe,0xfb,0xfc,0xba,0xae,0x59,
+  0x44,0x45,0x42,0x46,0x43,0x47,0x9c,0x48,0x54,0x51,0x52,0x53,0x58,0x55,0x56,0x57,
+  0x8c,0x49,0xcd,0xce,0xcb,0xcf,0xcc,0xe1,0x70,0xdd,0xde,0xdb,0xdc,0x8d,0x8e,0xdf,
+};
+
+#endif /* EBCDIC support needed */
 
 /* End of pcre2_tables.c */
diff --git a/src/pcre2test.c b/src/pcre2test.c
index 80ab4f809..1f3784735 100644
--- a/src/pcre2test.c
+++ b/src/pcre2test.c
@@ -240,6 +240,19 @@ to hold them as 32-bit code units. */
 
 enum { PR_OK, PR_SKIP, PR_ABEND };
 
+/* The macro EBCDIC_IO describes whether pcre2tests takes ASCII or EBCDIC as
+its input files (or terminal input). If the compiler uses ASCII for character
+literals, then we make pcre2test take ASCII as its input and output. This is
+different to the core PCRE2 library, where we use macros like "CHAR_A" for every
+single character and string literal used in pattern parsing and matching. It
+would simply be too arduous to do the same for pcre2test, so we make its
+input/output format match the compiler's codepage. */
+#if defined(EBCDIC) && 'a' == 0x81
+#define EBCDIC_IO 1
+#else
+#define EBCDIC_IO 0
+#endif
+
 /* The macro PRINTABLE determines whether to print an output character as-is or
 as a hex value when showing compiled patterns. We use it in cases when the
 locale has not been explicitly changed, so as to get consistent output from
@@ -251,7 +264,21 @@ systems that differ in their output from isprint() even in the "C" locale. */
 #define PRINTABLE(c) ((c) >= 32 && (c) < 127)
 #endif
 
-#define PRINTOK(c) ((use_tables != NULL && c < 256)? isprint(c) : PRINTABLE(c))
+#define PRINTOK(c) \
+  (PRINTABLE(c) && \
+   (use_tables == NULL || \
+    (((c) > 255)? FALSE : \
+     ((use_tables + cbits_offset + cbit_print)[(c)/8] & (1u << ((c)&7))) != 0)))
+
+/* The macro CHAR_OUTPUT is used to output characters in pcre2test's output
+format. The input character is encoded in PCRE2's native codepage (EBCDIC, if
+enabled), but the output may differ in the case where pcre2test uses ASCII input
+and output. */
+#if defined(EBCDIC) && !EBCDIC_IO
+#define CHAR_OUTPUT(c)  ebcdic_to_ascii(c)
+#else
+#define CHAR_OUTPUT(c)  (c)
+#endif
 
 /* We have to include some of the library source files because we need
 to use some of the macros, internal structure definitions, and other internal
@@ -266,22 +293,21 @@ so that the PCRE2_EXP_xxx macros get set appropriately for an application, not
 for building the library.
 
 Setting PCRE2_CODE_UNIT_WIDTH to zero cuts out all the width-specific settings
-in pcre2.h and pcre2_internal.h. Defining PCRE2_BUILDING_PCRE2TEST cuts out the
-check in pcre2_internal.h that ensures PCRE2_CODE_UNIT_WIDTH is 8, 16, or 32
-(which it needs to be when compiling one of the libraries). */
+in pcre2.h and pcre2_internal.h. Defining PCRE2_PCRE2TEST cuts out the check in
+pcre2_internal.h that ensures PCRE2_CODE_UNIT_WIDTH is 8, 16, or 32 (which it
+needs to be when compiling one of the libraries). */
 
 #define PRIV(name) name
 #define PCRE2_CODE_UNIT_WIDTH 0
-#define PCRE2_BUILDING_PCRE2TEST
+#define PCRE2_PCRE2TEST
 #include "pcre2.h"
 #include "pcre2posix.h"
 #include "pcre2_internal.h"
 
-/* We need access to some of the data tables that PCRE2 uses. Defining
-PCRE2_PCRE2TEST makes some minor changes in the files. The previous definition
-of PRIV avoids name clashes. */
+/* We need access to some of the data tables that PCRE2 uses. The previous
+definition of PCRE2_PCRE2TEST makes some minor changes in the files. The
+previous definition of PRIV avoids name clashes. */
 
-#define PCRE2_PCRE2TEST
 #include "pcre2_tables.c"
 #include "pcre2_ucd.c"
 
@@ -946,6 +972,7 @@ static coptstruct coptlist[] = {
   { "bsr",         CONF_BSR, PCRE2_CONFIG_BSR },
   { "ebcdic",      CONF_FIX, SUPPORT_EBCDIC },
   { "ebcdic-nl",   CONF_FIZ, EBCDIC_NL },
+  { "ebcdic-io",   CONF_FIX, EBCDIC_IO },
   { "jit",         CONF_INT, PCRE2_CONFIG_JIT },
   { "jitusable",   CONF_JU,  0 },
   { "linksize",    CONF_INT, PCRE2_CONFIG_LINKSIZE },
@@ -962,6 +989,8 @@ static coptstruct coptlist[] = {
 #undef SUPPORT_16
 #undef SUPPORT_32
 #undef SUPPORT_EBCDIC
+#undef EBDCIC_NL
+#undef BACKSLASH_C
 
 /* Types for the parser, to be used in process_data() */
 
@@ -3003,6 +3032,26 @@ return (PCRE2_JIT_STACK *)arg;
 }
 
 
+/*************************************************
+*         EBCDIC support functions               *
+*************************************************/
+
+#if defined(EBCDIC) && !EBCDIF_IO
+static void
+ascii_to_ebcdic(uint8_t *buf, size_t len)
+{
+for (size_t i = 0; i < len; ++i)
+  buf[i] = ascii_to_ebcdic_1047[buf[i]];
+}
+
+static uint32_t
+ebcdic_to_ascii(uint32_t c)
+{
+return (c < 256)? ebcdic_1047_to_ascii[c] : c;
+}
+#endif
+
+
 /*************************************************
 *      Convert UTF-8 character to code point     *
 *************************************************/
@@ -3092,10 +3141,13 @@ char tempbuffer[16];
 
 if (PRINTOK(c))
   {
+  c = CHAR_OUTPUT(c);
   if (f != NULL) fprintf(f, "%c", c);
   return 1;
   }
 
+c = CHAR_OUTPUT(c);
+
 if (c < 0x100)
   {
   if (utf)
@@ -3462,59 +3514,6 @@ return 0;
 
 
 
-/* This function is no longer used. Keep it around for a while, just in case it
-needs to be re-instated. */
-
-#ifdef NEVERNEVERNEVER
-
-/*************************************************
-*         Move back by so many characters        *
-*************************************************/
-
-/* Given a code unit offset in a subject string, move backwards by a number of
-characters, and return the resulting offset.
-
-Arguments:
-  subject   pointer to the string
-  offset    start offset
-  count     count to move back by
-  utf       TRUE if in UTF mode
-
-Returns:   a possibly changed offset
-*/
-
-static PCRE2_SIZE
-backchars(uint8_t *subject, PCRE2_SIZE offset, uint32_t count, BOOL utf)
-{
-if (!utf || test_mode == PCRE32_MODE)
-  return (count >= offset)? 0 : (offset - count);
-
-else if (test_mode == PCRE8_MODE)
-  {
-  PCRE2_SPTR8 pp = (PCRE2_SPTR8)subject + offset;
-  for (; count > 0 && pp > (PCRE2_SPTR8)subject; count--)
-    {
-    pp--;
-    while ((*pp & 0xc0) == 0x80) pp--;
-    }
-  return pp - (PCRE2_SPTR8)subject;
-  }
-
-else  /* 16-bit mode */
-  {
-  PCRE2_SPTR16 pp = (PCRE2_SPTR16)subject + offset;
-  for (; count > 0 && pp > (PCRE2_SPTR16)subject; count--)
-    {
-    pp--;
-    if ((*pp & 0xfc00) == 0xdc00) pp--;
-    }
-  return pp - (PCRE2_SPTR16)subject;
-  }
-}
-#endif  /* NEVERNEVERNEVER */
-
-
-
 /*************************************************
 *           Expand input buffers                 *
 *************************************************/
@@ -4597,7 +4596,21 @@ if (len < 0)
 else
   {
   fprintf(outfile, "%s", before);
-  PCHARSV(CASTVAR(void *, pbuffer), 0, len, FALSE, outfile);
+
+  /* In the rare configuration of EBCDIC-with-ASCII-compiler, we currently
+  output ASCII strings for the error messages, so we do special filtering for
+  that here. */
+
+#ifdef SUPPORT_PCRE2_16
+  if (test_mode == PCRE16_MODE)
+    for (int i = 0; i <= len; i++) pbuffer8[i] = (uint8_t)pbuffer16[i];
+#endif
+#ifdef SUPPORT_PCRE2_32
+  if (test_mode == PCRE32_MODE)
+    for (int i = 0; i <= len; i++) pbuffer8[i] = (uint8_t)pbuffer32[i];
+#endif
+  fprintf(outfile, "%s", pbuffer8);
+
   fprintf(outfile, "%s", after);
   }
 return len >= 0;
@@ -4676,6 +4689,7 @@ BOOL utf = (FLD(compiled_code, overall_options) & PCRE2_UTF) != 0;
 
 if ((pat_patctl.control & (CTL_BINCODE|CTL_FULLBINCODE)) != 0)
   {
+    // XXX XXX NEEDS EBCDIC SUPPORT
   fprintf(outfile, "------------------------------------------------------------------\n");
   PCRE2_PRINTINT((pat_patctl.control & CTL_FULLBINCODE) != 0);
   }
@@ -4943,7 +4957,8 @@ if ((pat_patctl.control & CTL_INFO) != 0)
       ((FLD(compiled_code, flags) & PCRE2_FIRSTCASELESS) == 0)?
       "" : " (caseless)";
     if (PRINTOK(first_cunit))
-      fprintf(outfile, "First code unit = \'%c\'%s\n", first_cunit, caseless);
+      fprintf(outfile, "First code unit = \'%c\'%s\n", CHAR_OUTPUT(first_cunit),
+              caseless);
     else
       {
       fprintf(outfile, "First code unit = ");
@@ -4965,14 +4980,14 @@ if ((pat_patctl.control & CTL_INFO) != 0)
           fprintf(outfile, "\n ");
           c = 2;
           }
-        if (PRINTOK(i) && i != ' ')
+        if (PRINTOK(i) && i != CHAR_SPACE)
           {
-          fprintf(outfile, " %c", i);
+          fprintf(outfile, " %c", CHAR_OUTPUT(i));
           c += 2;
           }
         else
           {
-          fprintf(outfile, " \\x%02x", i);
+          fprintf(outfile, " \\x%02x", CHAR_OUTPUT(i));
           c += 5;
           }
         }
@@ -4986,7 +5001,8 @@ if ((pat_patctl.control & CTL_INFO) != 0)
       ((FLD(compiled_code, flags) & PCRE2_LASTCASELESS) == 0)?
       "" : " (caseless)";
     if (PRINTOK(last_cunit))
-      fprintf(outfile, "Last code unit = \'%c\'%s\n", last_cunit, caseless);
+      fprintf(outfile, "Last code unit = \'%c\'%s\n", CHAR_OUTPUT(last_cunit),
+              caseless);
     else
       {
       fprintf(outfile, "Last code unit = ");
@@ -5896,6 +5912,10 @@ if ((pat_patctl.control & (CTL_PUSH|CTL_PUSHCOPY|CTL_PUSHTABLESCOPY)) != 0)
 
 errorcode = 0;
 
+#if defined(EBCDIC) && !EBCDIC_IO
+ascii_to_ebcdic(pbuffer8, patlen);
+#endif
+
 #ifdef SUPPORT_PCRE2_16
 if (test_mode == PCRE16_MODE) errorcode = to16(pbuffer8, utf, &patlen);
 #endif
@@ -7007,6 +7027,9 @@ for (;;)
 #ifdef SUPPORT_PCRE2_8
   if (test_mode == PCRE8_MODE) strcpy((char *)pbuffer8, (char *)nptr);
 #endif
+#if defined(EBCDIC) && !EBCDIC_IO
+  ascii_to_ebcdic(pbuffer8, namelen);
+#endif
 #ifdef SUPPORT_PCRE2_16
   if (test_mode == PCRE16_MODE)(void)to16(nptr, utf, &cnl);
 #endif
@@ -7088,6 +7111,9 @@ for (;;)
 #ifdef SUPPORT_PCRE2_8
   if (test_mode == PCRE8_MODE) strcpy((char *)pbuffer8, (char *)nptr);
 #endif
+#if defined(EBCDIC) && !EBCDIC_IO
+  ascii_to_ebcdic(pbuffer8, namelen);
+#endif
 #ifdef SUPPORT_PCRE2_16
   if (test_mode == PCRE16_MODE)(void)to16(nptr, utf, &cnl);
 #endif
@@ -7717,6 +7743,10 @@ pp = memmove(dbuffer + dbuffer_size - len - c, dbuffer, len + c);
   VALGRIND_MAKE_MEM_NOACCESS(dbuffer, dbuffer_size - (len + c));
 #endif
 
+#if defined(EBCDIC) && !EBCDIC_IO
+ascii_to_ebcdic(pp, len);
+#endif
+
 /* Now pp points to the subject string, but if null_subject was specified, set
 it to NULL to test PCRE2's behaviour. */
 
@@ -8916,8 +8946,10 @@ printf("  -C arg        show a specific compile-time option and exit with its\n"
 printf("                  value if numeric (else 0). The arg can be:\n");
 printf("     backslash-C    use of \\C is enabled [0, 1]\n");
 printf("     bsr            \\R type [ANYCRLF, ANY]\n");
-printf("     ebcdic         compiled for EBCDIC character code [0,1]\n");
+printf("     ebcdic         compiled for EBCDIC character code [0, 1]\n");
 printf("     ebcdic-nl      NL code if compiled for EBCDIC\n");
+printf("     ebcdic-io      if PCRE2 is compiled for EBCDIC, whether pcre2test's\n");
+printf("                      input and output is EBCDIC or ASCII [0, 1]\n");
 printf("     jit            just-in-time compiler supported [0, 1]\n");
 printf("     jitusable      test JIT usability [0, 1, 2, 3]\n");
 printf("     linksize       internal link size [2, 3, 4]\n");
@@ -9067,6 +9099,11 @@ printf("  EBCDIC code support: LF is 0x%02x\n", CHAR_LF);
 #if defined NATIVE_ZOS
 printf("  EBCDIC code page %s or similar\n", pcrz_cpversion());
 #endif
+#if EBCDIC_IO
+printf("  Input/output for pcre2test is EBCDIC\n");
+#else
+printf("  Input/output for pcre2test is ASCII, not EBCDIC\n");
+#endif
 #endif
 
 (void)PCRE2_CONFIG(PCRE2_CONFIG_COMPILED_WIDTHS, &optval);
@@ -9817,7 +9854,7 @@ least 128 code units, because it is used for retrieving error messages. */
   for (;;)
     {
     errcode = strtol(arg_error, &endptr, 10);
-    if (*endptr != 0 && *endptr != CHAR_COMMA)
+    if (*endptr != 0 && *endptr != ',')
       {
       fprintf(stderr, "** \"%s\" is not a valid error number list\n", arg_error);
       yield = 1;
@@ -9844,7 +9881,15 @@ least 128 code units, because it is used for retrieving error messages. */
       }
     else
       {
-      PCHARSV(CASTVAR(void *, pbuffer), 0, len, FALSE, stdout);
+#ifdef SUPPORT_PCRE2_16
+      if (test_mode == PCRE16_MODE)
+        for (int i = 0; i <= len; i++) pbuffer8[i] = (uint8_t)pbuffer16[i];
+#endif
+#ifdef SUPPORT_PCRE2_32
+      if (test_mode == PCRE32_MODE)
+        for (int i = 0; i <= len; i++) pbuffer8[i] = (uint8_t)pbuffer32[i];
+#endif
+      printf("%s", pbuffer8);
       }
     printf("\n");
     if (*endptr == 0) goto EXIT;
diff --git a/testdata/testinputEBC b/testdata/testinputEBC
index 36df20b81..7d5c09f3f 100644
--- a/testdata/testinputEBC
+++ b/testdata/testinputEBC
@@ -10,128 +10,128 @@
 
 /^A/m
     ABC
-    12\x15ABC
+    12\nABC
 
 /^A/m,newline=any
-    12\x15ABC
-    12\x0dABC
-    12\x0d\x15ABC
-    12\x25ABC
+    12\nABC
+    12\rABC
+    12\r\nABC
+    12\x85ABC
 
 /^A/m,newline=anycrlf
-    12\x15ABC
-    12\x0dABC
-    12\x0d\x15ABC
-    ** Fail
-    12\x25ABC
+    12\nABC
+    12\rABC
+    12\r\nABC
+\= Expect no match
+    12\x85ABC
 
 # Test \h
 
-/^A\ˆ/
+/^A\h/
     A B
-    A\x41B 
+    A\x41B
 
 # Test \H
 
-/^A\È/
+/^A\H/
     AB
-    A\x42B 
-    ** Fail
+    A\x42B
+\= Expect no match
     A B
-    A\x41B 
+    A\x41B
 
 # Test \R
 
-/^A\Ù/
-    A\x15B
-    A\x0dB
-    A\x25B
+/^A\R/
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    ** Fail
+\= Expect no match
     A B
 
 # Test \v
 
-/^A\¥/
-    A\x15B
-    A\x0dB
-    A\x25B
+/^A\v/
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    ** Fail
+\= Expect no match
     A B
 
 # Test \V
 
-/^A\å/
+/^A\V/
     A B
-    ** Fail
-    A\x15B
-    A\x0dB
-    A\x25B
+\= Expect no match
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    
+
 # For repeated items, use an atomic group so that the output is the same
 # for DFA matching (otherwise it may show multiple matches).
 
 # Test \h+
 
-/^A(?>\ˆ+)/
+/^A(?>\h+)/
     A B
 
 # Test \H+
 
-/^A(?>\È+)/
+/^A(?>\H+)/
     AB
-    ** Fail
+\= Expect no match
     A B
 
 # Test \R+
 
-/^A(?>\Ù+)/
-    A\x15B
-    A\x0dB
-    A\x25B
+/^A(?>\R+)/
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    ** Fail
+\= Expect no match
     A B
 
 # Test \v+
 
-/^A(?>\¥+)/
-    A\x15B
-    A\x0dB
-    A\x25B
+/^A(?>\v+)/
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    ** Fail
+\= Expect no match
     A B
 
 # Test \V+
 
-/^A(?>\å+)/
+/^A(?>\V+)/
     A B
-    ** Fail
-    A\x15B
-    A\x0dB
-    A\x25B
+\= Expect no match
+    A\nB
+    A\rB
+    A\x85B
     A\x0bB
     A\x0cB
-    
-# Test \c functionality 
-    
-/\ƒ@\ƒA\ƒb\ƒC\ƒd\ƒE\ƒf\ƒG\ƒh\ƒI\ƒJ\ƒK\ƒl\ƒm\ƒN\ƒO\ƒp\ƒq\ƒr\ƒS\ƒT\ƒu\ƒV\ƒW\ƒX\ƒy\ƒZ/
-    \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
 
-/\ƒ[\ƒ\\ƒ]\ƒ^\ƒ_/
+# Test \c functionality
+
+/\�@\�A\�b\�C\�d\�E\�f\�G\�h\�I\�J\�K\�l\�m\�N\�O\�p\�q\�r\�S\�T\�u\�V\�W\�X\�y\�Z/
+    \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\n\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
+
+/\�[\�\\�]\�^\�_/
     \x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
-    
-/\ƒ?/
+
+/\�?/
     A\xffB
 
-/\ƒ&/
+/\�&/
 
 # End
diff --git a/testdata/testoutputEBC b/testdata/testoutputEBC
index 4edc8f998..a408b9f08 100644
--- a/testdata/testoutputEBC
+++ b/testdata/testoutputEBC
@@ -1,4 +1,3 @@
-PCRE2 version 10.32-RC1 2018-02-19
 # This is a specialized test for checking, when PCRE2 is compiled with the
 # EBCDIC option but in an ASCII environment, that newline, white space, and \c
 # functionality is working. It catches cases where explicit values such as 0x0a
@@ -12,195 +11,186 @@ PCRE2 version 10.32-RC1 2018-02-19
 /^A/m
     ABC
  0: A
-    12\x15ABC
+    12\nABC
  0: A
 
 /^A/m,newline=any
-    12\x15ABC
+    12\nABC
  0: A
-    12\x0dABC
+    12\rABC
  0: A
-    12\x0d\x15ABC
+    12\r\nABC
  0: A
-    12\x25ABC
+    12\x85ABC
  0: A
 
 /^A/m,newline=anycrlf
-    12\x15ABC
+    12\nABC
  0: A
-    12\x0dABC
+    12\rABC
  0: A
-    12\x0d\x15ABC
+    12\r\nABC
  0: A
-    ** Fail
-No match
-    12\x25ABC
+\= Expect no match
+    12\x85ABC
 No match
 
 # Test \h
 
-/^A\ˆ/
+/^A\h/
     A B
  0: A\x20
-    A\x41B 
+    A\x41B
  0: AA
 
 # Test \H
 
-/^A\È/
+/^A\H/
     AB
  0: AB
-    A\x42B 
+    A\x42B
  0: AB
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
-    A\x41B 
+    A\x41B
 No match
 
 # Test \R
 
-/^A\Ù/
-    A\x15B
- 0: A\x15
-    A\x0dB
- 0: A\x0d
-    A\x25B
- 0: A\x25
+/^A\R/
+    A\nB
+ 0: A\n
+    A\rB
+ 0: A\r
+    A\x85B
+ 0: A\x85
     A\x0bB
  0: A\x0b
     A\x0cB
  0: A\x0c
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
 
 # Test \v
 
-/^A\¥/
-    A\x15B
- 0: A\x15
-    A\x0dB
- 0: A\x0d
-    A\x25B
- 0: A\x25
+/^A\v/
+    A\nB
+ 0: A\n
+    A\rB
+ 0: A\r
+    A\x85B
+ 0: A\x85
     A\x0bB
  0: A\x0b
     A\x0cB
  0: A\x0c
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
 
 # Test \V
 
-/^A\å/
+/^A\V/
     A B
  0: A\x20
-    ** Fail
+\= Expect no match
+    A\nB
 No match
-    A\x15B
+    A\rB
 No match
-    A\x0dB
-No match
-    A\x25B
+    A\x85B
 No match
     A\x0bB
 No match
     A\x0cB
 No match
-    
+
 # For repeated items, use an atomic group so that the output is the same
 # for DFA matching (otherwise it may show multiple matches).
 
 # Test \h+
 
-/^A(?>\ˆ+)/
+/^A(?>\h+)/
     A B
  0: A\x20
 
 # Test \H+
 
-/^A(?>\È+)/
+/^A(?>\H+)/
     AB
  0: AB
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
 
 # Test \R+
 
-/^A(?>\Ù+)/
-    A\x15B
- 0: A\x15
-    A\x0dB
- 0: A\x0d
-    A\x25B
- 0: A\x25
+/^A(?>\R+)/
+    A\nB
+ 0: A\n
+    A\rB
+ 0: A\r
+    A\x85B
+ 0: A\x85
     A\x0bB
  0: A\x0b
     A\x0cB
  0: A\x0c
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
 
 # Test \v+
 
-/^A(?>\¥+)/
-    A\x15B
- 0: A\x15
-    A\x0dB
- 0: A\x0d
-    A\x25B
- 0: A\x25
+/^A(?>\v+)/
+    A\nB
+ 0: A\n
+    A\rB
+ 0: A\r
+    A\x85B
+ 0: A\x85
     A\x0bB
  0: A\x0b
     A\x0cB
  0: A\x0c
-    ** Fail
-No match
+\= Expect no match
     A B
 No match
 
 # Test \V+
 
-/^A(?>\å+)/
+/^A(?>\V+)/
     A B
  0: A\x20B
-    ** Fail
-No match
-    A\x15B
+\= Expect no match
+    A\nB
 No match
-    A\x0dB
+    A\rB
 No match
-    A\x25B
+    A\x85B
 No match
     A\x0bB
 No match
     A\x0cB
 No match
-    
-# Test \c functionality 
-    
-/\ƒ@\ƒA\ƒb\ƒC\ƒd\ƒE\ƒf\ƒG\ƒh\ƒI\ƒJ\ƒK\ƒl\ƒm\ƒN\ƒO\ƒp\ƒq\ƒr\ƒS\ƒT\ƒu\ƒV\ƒW\ƒX\ƒy\ƒZ/
-    \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
- 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a
 
-/\ƒ[\ƒ\\ƒ]\ƒ^\ƒ_/
+# Test \c functionality
+
+/\�@\�A\�b\�C\�d\�E\�f\�G\�h\�I\�J\�K\�l\�m\�N\�O\�p\�q\�r\�S\�T\�u\�V\�W\�X\�y\�Z/
+    \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\n\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
+ 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\n\x16\x17\x18\x19\x1a
+
+/\�[\�\\�]\�^\�_/
     \x18\x19\x1a\x1b\x1c\x1d\x1e\x1f
  0: \x1b\x1c\x1d\x1e\x1f
-    
-/\ƒ?/
+
+/\�?/
     A\xffB
  0: \xff
 
-/\ƒ&/
+/\�&/
 Failed: error 168 at offset 3: \c\x20must\x20be\x20followed\x20by\x20a\x20letter\x20or\x20one\x20of\x20[\]^_\x3f
 
 # End