glib2 3.0.7-x64-mingw32 → 3.0.8-x64-mingw32
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Rakefile +24 -12
- data/ext/glib2/extconf.rb +1 -0
- data/ext/glib2/glib2.def +4 -0
- data/ext/glib2/rbglib-variant.c +163 -12
- data/ext/glib2/rbglib.c +31 -8
- data/ext/glib2/rbglib.h +15 -1
- data/ext/glib2/rbglib2conversions.h +3 -0
- data/ext/glib2/rbglib_iochannel.c +0 -3
- data/ext/glib2/rbglib_iochannel_win32_socket.c +0 -1
- data/ext/glib2/rbglib_matchinfo.c +179 -0
- data/ext/glib2/rbglib_regex.c +484 -0
- data/ext/glib2/rbgobj_value.c +7 -1
- data/ext/glib2/rbgprivate.h +2 -0
- data/ext/glib2/rbgutil.c +7 -0
- data/ext/glib2/rbgutil.h +2 -0
- data/lib/2.2/glib2.so +0 -0
- data/lib/2.3/glib2.so +0 -0
- data/lib/glib2.rb +2 -1
- data/lib/glib2/regex.rb +29 -0
- data/lib/gnome2/rake/external-package.rb +6 -1
- data/lib/gnome2/rake/package-task.rb +1 -1
- data/lib/gnome2/rake/package.rb +9 -0
- data/lib/gnome2/rake/windows-binary-build-task.rb +35 -11
- data/lib/mkmf-gnome2.rb +3 -1
- data/test/test-match-info.rb +113 -0
- data/test/test-regex.rb +320 -0
- data/vendor/local/bin/asn1Coding.exe +0 -0
- data/vendor/local/bin/asn1Decoding.exe +0 -0
- data/vendor/local/bin/asn1Parser.exe +0 -0
- data/vendor/local/bin/envsubst.exe +0 -0
- data/vendor/local/bin/gdbus.exe +0 -0
- data/vendor/local/bin/gettext.exe +0 -0
- data/vendor/local/bin/gettext.sh +1 -1
- data/vendor/local/bin/gio-querymodules.exe +0 -0
- data/vendor/local/bin/glib-compile-resources.exe +0 -0
- data/vendor/local/bin/glib-compile-schemas.exe +0 -0
- data/vendor/local/bin/glib-genmarshal.exe +0 -0
- data/vendor/local/bin/glib-gettextize +1 -1
- data/vendor/local/bin/glib-mkenums +2 -2
- data/vendor/local/bin/gobject-query.exe +0 -0
- data/vendor/local/bin/gresource.exe +0 -0
- data/vendor/local/bin/gsettings.exe +0 -0
- data/vendor/local/bin/gspawn-win64-helper-console.exe +0 -0
- data/vendor/local/bin/gspawn-win64-helper.exe +0 -0
- data/vendor/local/bin/iconv.exe +0 -0
- data/vendor/local/bin/idn.exe +0 -0
- data/vendor/local/bin/libasprintf-0.dll +0 -0
- data/vendor/local/bin/libcharset-1.dll +0 -0
- data/vendor/local/bin/libffi-6.dll +0 -0
- data/vendor/local/bin/libgio-2.0-0.dll +0 -0
- data/vendor/local/bin/libglib-2.0-0.dll +0 -0
- data/vendor/local/bin/libgmodule-2.0-0.dll +0 -0
- data/vendor/local/bin/libgmp-10.dll +0 -0
- data/vendor/local/bin/libgnutls-30.def +993 -984
- data/vendor/local/bin/libgnutls-30.dll +0 -0
- data/vendor/local/bin/libgobject-2.0-0.dll +0 -0
- data/vendor/local/bin/libgthread-2.0-0.dll +0 -0
- data/vendor/local/bin/libhogweed-4-2.dll +0 -0
- data/vendor/local/bin/libiconv-2.dll +0 -0
- data/vendor/local/bin/libidn-11.dll +0 -0
- data/vendor/local/bin/libintl-8.dll +0 -0
- data/vendor/local/bin/{libnettle-6-1.dll → libnettle-6-2.dll} +0 -0
- data/vendor/local/bin/libp11-kit-0.dll +0 -0
- data/vendor/local/bin/libpcre-1.dll +0 -0
- data/vendor/local/bin/libpcrecpp-0.dll +0 -0
- data/vendor/local/bin/libpcreposix-0.dll +0 -0
- data/vendor/local/bin/libtasn1-6.dll +0 -0
- data/vendor/local/bin/nettle-hash.exe +0 -0
- data/vendor/local/bin/nettle-lfib-stream.exe +0 -0
- data/vendor/local/bin/nettle-pbkdf2.exe +0 -0
- data/vendor/local/bin/ngettext.exe +0 -0
- data/vendor/local/bin/p11-kit.exe +0 -0
- data/vendor/local/bin/pcre-config +133 -0
- data/vendor/local/bin/pcregrep.exe +0 -0
- data/vendor/local/bin/pcretest.exe +0 -0
- data/vendor/local/bin/pkcs1-conv.exe +0 -0
- data/vendor/local/bin/sexp-conv.exe +0 -0
- data/vendor/local/bin/trust.exe +0 -0
- data/vendor/local/include/glib-2.0/gio/gdatagrambased.h +144 -0
- data/vendor/local/include/glib-2.0/gio/gdbusconnection.h +9 -1
- data/vendor/local/include/glib-2.0/gio/gdtlsclientconnection.h +75 -0
- data/vendor/local/include/glib-2.0/gio/gdtlsconnection.h +191 -0
- data/vendor/local/include/glib-2.0/gio/gdtlsserverconnection.h +69 -0
- data/vendor/local/include/glib-2.0/gio/gfileinfo.h +14 -0
- data/vendor/local/include/glib-2.0/gio/gio-autocleanups.h +1 -0
- data/vendor/local/include/glib-2.0/gio/gio.h +4 -0
- data/vendor/local/include/glib-2.0/gio/gioenums.h +69 -13
- data/vendor/local/include/glib-2.0/gio/gioenumtypes.h +2 -0
- data/vendor/local/include/glib-2.0/gio/giotypes.h +77 -0
- data/vendor/local/include/glib-2.0/gio/gliststore.h +5 -0
- data/vendor/local/include/glib-2.0/gio/gnetworkmonitor.h +3 -0
- data/vendor/local/include/glib-2.0/gio/gsettings.h +1 -1
- data/vendor/local/include/glib-2.0/gio/gsettingsschema.h +3 -0
- data/vendor/local/include/glib-2.0/gio/gsimpleasyncresult.h +25 -25
- data/vendor/local/include/glib-2.0/gio/gsocket.h +7 -0
- data/vendor/local/include/glib-2.0/gio/gsocketconnectable.h +6 -0
- data/vendor/local/include/glib-2.0/gio/gsocketlistener.h +4 -1
- data/vendor/local/include/glib-2.0/gio/gtlsbackend.h +14 -0
- data/vendor/local/include/glib-2.0/gio/gtlsclientconnection.h +7 -0
- data/vendor/local/include/glib-2.0/glib/gasyncqueue.h +13 -0
- data/vendor/local/include/glib-2.0/glib/gbacktrace.h +2 -0
- data/vendor/local/include/glib-2.0/glib/glib-autocleanups.h +12 -4
- data/vendor/local/include/glib-2.0/glib/gmacros.h +46 -10
- data/vendor/local/include/glib-2.0/glib/gmain.h +3 -1
- data/vendor/local/include/glib-2.0/glib/gmem.h +7 -5
- data/vendor/local/include/glib-2.0/glib/gmessages.h +8 -8
- data/vendor/local/include/glib-2.0/glib/gnode.h +2 -2
- data/vendor/local/include/glib-2.0/glib/gpoll.h +2 -9
- data/vendor/local/include/glib-2.0/glib/gsequence.h +2 -0
- data/vendor/local/include/glib-2.0/glib/gstdio.h +1 -1
- data/vendor/local/include/glib-2.0/glib/gstrfuncs.h +1 -0
- data/vendor/local/include/glib-2.0/glib/gtestutils.h +15 -2
- data/vendor/local/include/glib-2.0/glib/gthreadpool.h +4 -0
- data/vendor/local/include/glib-2.0/glib/gtrashstack.h +10 -57
- data/vendor/local/include/glib-2.0/glib/gtypes.h +61 -6
- data/vendor/local/include/glib-2.0/glib/gunicode.h +15 -1
- data/vendor/local/include/glib-2.0/glib/gutils.h +36 -57
- data/vendor/local/include/glib-2.0/glib/gversionmacros.h +59 -10
- data/vendor/local/include/glib-2.0/gobject/gboxed.h +3 -3
- data/vendor/local/include/glib-2.0/gobject/gclosure.h +2 -1
- data/vendor/local/include/glib-2.0/gobject/glib-types.h +0 -7
- data/vendor/local/include/glib-2.0/gobject/gobject-autocleanups.h +0 -1
- data/vendor/local/include/glib-2.0/gobject/gobject.h +8 -4
- data/vendor/local/include/glib-2.0/gobject/gparam.h +5 -2
- data/vendor/local/include/glib-2.0/gobject/gsignal.h +3 -0
- data/vendor/local/include/glib-2.0/gobject/gtype.h +47 -26
- data/vendor/local/include/glib-2.0/gobject/gtypemodule.h +1 -0
- data/vendor/local/include/gmp.h +56 -24
- data/vendor/local/include/gnutls/gnutls.h +79 -39
- data/vendor/local/include/gnutls/pkcs11.h +6 -0
- data/vendor/local/include/gnutls/pkcs7.h +17 -4
- data/vendor/local/include/gnutls/x509.h +8 -0
- data/vendor/local/include/libintl.h +1 -1
- data/vendor/local/include/libtasn1.h +1 -1
- data/vendor/local/include/nettle/rsa.h +72 -0
- data/vendor/local/include/nettle/sha3.h +4 -0
- data/vendor/local/include/nettle/version.h +8 -1
- data/vendor/local/include/p11-kit-1/p11-kit/p11-kit.h +1 -0
- data/vendor/local/include/pcre.h +677 -0
- data/vendor/local/include/pcre_scanner.h +172 -0
- data/vendor/local/include/pcre_stringpiece.h +180 -0
- data/vendor/local/include/pcrecpp.h +710 -0
- data/vendor/local/include/pcrecpparg.h +174 -0
- data/vendor/local/include/pcreposix.h +146 -0
- data/vendor/local/lib/gio/modules/libgiognutls.a +0 -0
- data/vendor/local/lib/gio/modules/libgiognutls.dll +0 -0
- data/vendor/local/lib/gio/modules/libgiognutls.dll.a +0 -0
- data/vendor/local/lib/gio/modules/libgiognutls.la +3 -3
- data/vendor/local/lib/glib-2.0/include/glibconfig.h +4 -16
- data/vendor/local/lib/libasprintf.a +0 -0
- data/vendor/local/lib/libasprintf.dll.a +0 -0
- data/vendor/local/lib/libcharset.a +0 -0
- data/vendor/local/lib/libcharset.dll.a +0 -0
- data/vendor/local/lib/libffi.a +0 -0
- data/vendor/local/lib/libffi.dll.a +0 -0
- data/vendor/local/lib/libgio-2.0.dll.a +0 -0
- data/vendor/local/lib/libgio-2.0.la +5 -5
- data/vendor/local/lib/libglib-2.0.dll.a +0 -0
- data/vendor/local/lib/libglib-2.0.la +5 -5
- data/vendor/local/lib/libgmodule-2.0.dll.a +0 -0
- data/vendor/local/lib/libgmodule-2.0.la +5 -5
- data/vendor/local/lib/libgmp.dll.a +0 -0
- data/vendor/local/lib/libgmp.la +4 -4
- data/vendor/local/lib/libgnutls.dll.a +0 -0
- data/vendor/local/lib/libgnutls.la +4 -4
- data/vendor/local/lib/libgobject-2.0.dll.a +0 -0
- data/vendor/local/lib/libgobject-2.0.la +5 -5
- data/vendor/local/lib/libgthread-2.0.dll.a +0 -0
- data/vendor/local/lib/libgthread-2.0.la +5 -5
- data/vendor/local/lib/libhogweed.a +0 -0
- data/vendor/local/lib/libhogweed.dll.a +0 -0
- data/vendor/local/lib/libiconv.dll.a +0 -0
- data/vendor/local/lib/libidn.a +0 -0
- data/vendor/local/lib/libidn.dll.a +0 -0
- data/vendor/local/lib/libidn.la +1 -1
- data/vendor/local/lib/libintl.a +0 -0
- data/vendor/local/lib/libintl.dll.a +0 -0
- data/vendor/local/lib/libintl.la +2 -2
- data/vendor/local/lib/libnettle.a +0 -0
- data/vendor/local/lib/libnettle.dll.a +0 -0
- data/vendor/local/lib/libp11-kit.dll.a +0 -0
- data/vendor/local/lib/libp11-kit.la +1 -1
- data/vendor/local/lib/libpcre.a +0 -0
- data/vendor/local/lib/libpcre.dll.a +0 -0
- data/vendor/local/lib/libpcre.la +41 -0
- data/vendor/local/lib/libpcrecpp.a +0 -0
- data/vendor/local/lib/libpcrecpp.dll.a +0 -0
- data/vendor/local/lib/libpcrecpp.la +41 -0
- data/vendor/local/lib/libpcreposix.a +0 -0
- data/vendor/local/lib/libpcreposix.dll.a +0 -0
- data/vendor/local/lib/libpcreposix.la +41 -0
- data/vendor/local/lib/libtasn1.a +0 -0
- data/vendor/local/lib/libtasn1.dll.a +0 -0
- data/vendor/local/lib/libtasn1.la +1 -1
- data/vendor/local/lib/p11-kit/p11-kit-remote.exe +0 -0
- data/vendor/local/lib/pkcs11/p11-kit-trust.dll +0 -0
- data/vendor/local/lib/pkcs11/p11-kit-trust.dll.a +0 -0
- data/vendor/local/lib/pkcs11/p11-kit-trust.la +1 -1
- data/vendor/local/lib/pkgconfig/gio-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/gio-windows-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/glib-2.0.pc +3 -3
- data/vendor/local/lib/pkgconfig/gmodule-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/gmodule-export-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/gmodule-no-export-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/gnutls.pc +2 -2
- data/vendor/local/lib/pkgconfig/gobject-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/gthread-2.0.pc +1 -1
- data/vendor/local/lib/pkgconfig/hogweed.pc +1 -1
- data/vendor/local/lib/pkgconfig/libidn.pc +1 -1
- data/vendor/local/lib/pkgconfig/libpcre.pc +13 -0
- data/vendor/local/lib/pkgconfig/libpcrecpp.pc +12 -0
- data/vendor/local/lib/pkgconfig/libpcreposix.pc +13 -0
- data/vendor/local/lib/pkgconfig/libtasn1.pc +1 -1
- data/vendor/local/lib/pkgconfig/nettle.pc +1 -1
- data/vendor/local/lib/pkgconfig/p11-kit-1.pc +1 -1
- data/vendor/local/share/aclocal/glib-gettext.m4 +3 -2
- data/vendor/local/share/doc/pcre/AUTHORS +45 -0
- data/vendor/local/share/doc/pcre/COPYING +5 -0
- data/vendor/local/share/doc/pcre/ChangeLog +5918 -0
- data/vendor/local/share/doc/pcre/LICENCE +93 -0
- data/vendor/local/share/doc/pcre/NEWS +716 -0
- data/vendor/local/share/doc/pcre/README +1002 -0
- data/vendor/local/share/doc/pcre/html/NON-AUTOTOOLS-BUILD.txt +772 -0
- data/vendor/local/share/doc/pcre/html/README.txt +1002 -0
- data/vendor/local/share/doc/pcre/html/index.html +185 -0
- data/vendor/local/share/doc/pcre/html/pcre-config.html +109 -0
- data/vendor/local/share/doc/pcre/html/pcre.html +224 -0
- data/vendor/local/share/doc/pcre/html/pcre16.html +384 -0
- data/vendor/local/share/doc/pcre/html/pcre32.html +382 -0
- data/vendor/local/share/doc/pcre/html/pcre_assign_jit_stack.html +76 -0
- data/vendor/local/share/doc/pcre/html/pcre_compile.html +111 -0
- data/vendor/local/share/doc/pcre/html/pcre_compile2.html +115 -0
- data/vendor/local/share/doc/pcre/html/pcre_config.html +94 -0
- data/vendor/local/share/doc/pcre/html/pcre_copy_named_substring.html +65 -0
- data/vendor/local/share/doc/pcre/html/pcre_copy_substring.html +61 -0
- data/vendor/local/share/doc/pcre/html/pcre_dfa_exec.html +129 -0
- data/vendor/local/share/doc/pcre/html/pcre_exec.html +111 -0
- data/vendor/local/share/doc/pcre/html/pcre_free_study.html +46 -0
- data/vendor/local/share/doc/pcre/html/pcre_free_substring.html +46 -0
- data/vendor/local/share/doc/pcre/html/pcre_free_substring_list.html +46 -0
- data/vendor/local/share/doc/pcre/html/pcre_fullinfo.html +118 -0
- data/vendor/local/share/doc/pcre/html/pcre_get_named_substring.html +68 -0
- data/vendor/local/share/doc/pcre/html/pcre_get_stringnumber.html +57 -0
- data/vendor/local/share/doc/pcre/html/pcre_get_stringtable_entries.html +60 -0
- data/vendor/local/share/doc/pcre/html/pcre_get_substring.html +64 -0
- data/vendor/local/share/doc/pcre/html/pcre_get_substring_list.html +61 -0
- data/vendor/local/share/doc/pcre/html/pcre_jit_exec.html +108 -0
- data/vendor/local/share/doc/pcre/html/pcre_jit_stack_alloc.html +55 -0
- data/vendor/local/share/doc/pcre/html/pcre_jit_stack_free.html +48 -0
- data/vendor/local/share/doc/pcre/html/pcre_maketables.html +48 -0
- data/vendor/local/share/doc/pcre/html/pcre_pattern_to_host_byte_order.html +58 -0
- data/vendor/local/share/doc/pcre/html/pcre_refcount.html +51 -0
- data/vendor/local/share/doc/pcre/html/pcre_study.html +68 -0
- data/vendor/local/share/doc/pcre/html/pcre_utf16_to_host_byte_order.html +57 -0
- data/vendor/local/share/doc/pcre/html/pcre_utf32_to_host_byte_order.html +57 -0
- data/vendor/local/share/doc/pcre/html/pcre_version.html +46 -0
- data/vendor/local/share/doc/pcre/html/pcreapi.html +2922 -0
- data/vendor/local/share/doc/pcre/html/pcrebuild.html +534 -0
- data/vendor/local/share/doc/pcre/html/pcrecallout.html +286 -0
- data/vendor/local/share/doc/pcre/html/pcrecompat.html +235 -0
- data/vendor/local/share/doc/pcre/html/pcrecpp.html +368 -0
- data/vendor/local/share/doc/pcre/html/pcredemo.html +426 -0
- data/vendor/local/share/doc/pcre/html/pcregrep.html +759 -0
- data/vendor/local/share/doc/pcre/html/pcrejit.html +452 -0
- data/vendor/local/share/doc/pcre/html/pcrelimits.html +90 -0
- data/vendor/local/share/doc/pcre/html/pcrematching.html +242 -0
- data/vendor/local/share/doc/pcre/html/pcrepartial.html +509 -0
- data/vendor/local/share/doc/pcre/html/pcrepattern.html +3273 -0
- data/vendor/local/share/doc/pcre/html/pcreperform.html +195 -0
- data/vendor/local/share/doc/pcre/html/pcreposix.html +290 -0
- data/vendor/local/share/doc/pcre/html/pcreprecompile.html +163 -0
- data/vendor/local/share/doc/pcre/html/pcresample.html +110 -0
- data/vendor/local/share/doc/pcre/html/pcrestack.html +225 -0
- data/vendor/local/share/doc/pcre/html/pcresyntax.html +561 -0
- data/vendor/local/share/doc/pcre/html/pcretest.html +1158 -0
- data/vendor/local/share/doc/pcre/html/pcreunicode.html +262 -0
- data/vendor/local/share/doc/pcre/pcre-config.txt +86 -0
- data/vendor/local/share/doc/pcre/pcre.txt +10455 -0
- data/vendor/local/share/doc/pcre/pcregrep.txt +741 -0
- data/vendor/local/share/doc/pcre/pcretest.txt +1087 -0
- data/vendor/local/share/gdb/auto-load/{libglib-2.0.so.0.4400.1-gdb.py → home/vagrant/ruby-gnome2.win64/glib2/vendor/local/lib/libglib-2.0.so.0.4800.0-gdb.py} +0 -0
- data/vendor/local/share/gdb/auto-load/{libgobject-2.0.so.0.4400.1-gdb.py → home/vagrant/ruby-gnome2.win64/glib2/vendor/local/lib/libgobject-2.0.so.0.4800.0-gdb.py} +0 -0
- data/vendor/local/share/gettext/ABOUT-NLS +382 -413
- data/vendor/local/share/gettext/its/gschema.its +25 -0
- data/vendor/local/share/gettext/its/gschema.loc +10 -0
- data/vendor/local/share/glib-2.0/codegen/__init__.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/__init__.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen.py +22 -0
- data/vendor/local/share/glib-2.0/codegen/codegen.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen_docbook.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen_docbook.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen_main.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/codegen_main.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/config.py +1 -1
- data/vendor/local/share/glib-2.0/codegen/config.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/config.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/dbustypes.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/dbustypes.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/parser.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/parser.pyo +0 -0
- data/vendor/local/share/glib-2.0/codegen/utils.pyc +0 -0
- data/vendor/local/share/glib-2.0/codegen/utils.pyo +0 -0
- data/vendor/local/share/glib-2.0/gdb/glib.py +4 -0
- data/vendor/local/share/glib-2.0/schemas/gschemas.compiled +0 -0
- data/vendor/local/share/gtk-doc/html/gio/GAction.html +58 -64
- data/vendor/local/share/gtk-doc/html/gio/GActionGroup.html +75 -80
- data/vendor/local/share/gtk-doc/html/gio/GActionMap.html +50 -51
- data/vendor/local/share/gtk-doc/html/gio/GAppInfo.html +72 -97
- data/vendor/local/share/gtk-doc/html/gio/GAppInfoMonitor.html +7 -8
- data/vendor/local/share/gtk-doc/html/gio/GApplication.html +174 -160
- data/vendor/local/share/gtk-doc/html/gio/GApplicationCommandLine.html +127 -132
- data/vendor/local/share/gtk-doc/html/gio/GAsyncInitable.html +90 -92
- data/vendor/local/share/gtk-doc/html/gio/GAsyncResult.html +43 -46
- data/vendor/local/share/gtk-doc/html/gio/GBufferedInputStream.html +17 -26
- data/vendor/local/share/gtk-doc/html/gio/GBufferedOutputStream.html +12 -17
- data/vendor/local/share/gtk-doc/html/gio/GBytesIcon.html +10 -11
- data/vendor/local/share/gtk-doc/html/gio/GCancellable.html +45 -52
- data/vendor/local/share/gtk-doc/html/gio/GCharsetConverter.html +14 -18
- data/vendor/local/share/gtk-doc/html/gio/GConverter.html +20 -21
- data/vendor/local/share/gtk-doc/html/gio/GCredentials.html +41 -48
- data/vendor/local/share/gtk-doc/html/gio/GDBusActionGroup.html +9 -10
- data/vendor/local/share/gtk-doc/html/gio/GDBusAuthObserver.html +34 -40
- data/vendor/local/share/gtk-doc/html/gio/GDBusConnection.html +337 -258
- data/vendor/local/share/gtk-doc/html/gio/GDBusInterface.html +23 -22
- data/vendor/local/share/gtk-doc/html/gio/GDBusInterfaceSkeleton.html +44 -50
- data/vendor/local/share/gtk-doc/html/gio/GDBusMenuModel.html +9 -10
- data/vendor/local/share/gtk-doc/html/gio/GDBusMessage.html +143 -158
- data/vendor/local/share/gtk-doc/html/gio/GDBusMethodInvocation.html +59 -54
- data/vendor/local/share/gtk-doc/html/gio/GDBusObject.html +19 -22
- data/vendor/local/share/gtk-doc/html/gio/GDBusObjectManager.html +25 -27
- data/vendor/local/share/gtk-doc/html/gio/GDBusObjectManagerClient.html +48 -52
- data/vendor/local/share/gtk-doc/html/gio/GDBusObjectManagerServer.html +34 -31
- data/vendor/local/share/gtk-doc/html/gio/GDBusObjectProxy.html +15 -17
- data/vendor/local/share/gtk-doc/html/gio/GDBusObjectSkeleton.html +25 -28
- data/vendor/local/share/gtk-doc/html/gio/GDBusProxy.html +105 -122
- data/vendor/local/share/gtk-doc/html/gio/GDBusServer.html +32 -39
- data/vendor/local/share/gtk-doc/html/gio/GDataInputStream.html +40 -51
- data/vendor/local/share/gtk-doc/html/gio/GDataOutputStream.html +17 -28
- data/vendor/local/share/gtk-doc/html/gio/GDatagramBased.html +766 -0
- data/vendor/local/share/gtk-doc/html/gio/GDrive.html +56 -75
- data/vendor/local/share/gtk-doc/html/gio/GDtlsClientConnection.html +468 -0
- data/vendor/local/share/gtk-doc/html/gio/GDtlsConnection.html +1521 -0
- data/vendor/local/share/gtk-doc/html/gio/GDtlsServerConnection.html +208 -0
- data/vendor/local/share/gtk-doc/html/gio/GEmblem.html +16 -19
- data/vendor/local/share/gtk-doc/html/gio/GEmblemedIcon.html +16 -17
- data/vendor/local/share/gtk-doc/html/gio/GFile.html +204 -240
- data/vendor/local/share/gtk-doc/html/gio/GFileDescriptorBased.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/GFileEnumerator.html +36 -41
- data/vendor/local/share/gtk-doc/html/gio/GFileIOStream.html +13 -15
- data/vendor/local/share/gtk-doc/html/gio/GFileIcon.html +8 -9
- data/vendor/local/share/gtk-doc/html/gio/GFileInfo.html +128 -145
- data/vendor/local/share/gtk-doc/html/gio/GFileInputStream.html +8 -9
- data/vendor/local/share/gtk-doc/html/gio/GFileMonitor.html +75 -36
- data/vendor/local/share/gtk-doc/html/gio/GFileOutputStream.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/GFilenameCompleter.html +10 -13
- data/vendor/local/share/gtk-doc/html/gio/GFilterInputStream.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/GFilterOutputStream.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/GIOModule.html +41 -43
- data/vendor/local/share/gtk-doc/html/gio/GIOStream.html +56 -44
- data/vendor/local/share/gtk-doc/html/gio/GIcon.html +20 -23
- data/vendor/local/share/gtk-doc/html/gio/GInetAddress.html +103 -118
- data/vendor/local/share/gtk-doc/html/gio/GInetAddressMask.html +39 -47
- data/vendor/local/share/gtk-doc/html/gio/GInetSocketAddress.html +31 -37
- data/vendor/local/share/gtk-doc/html/gio/GInitable.html +17 -19
- data/vendor/local/share/gtk-doc/html/gio/GInputStream.html +32 -44
- data/vendor/local/share/gtk-doc/html/gio/GListModel.html +28 -29
- data/vendor/local/share/gtk-doc/html/gio/GListStore.html +80 -35
- data/vendor/local/share/gtk-doc/html/gio/GLoadableIcon.html +10 -11
- data/vendor/local/share/gtk-doc/html/gio/GMemoryInputStream.html +11 -15
- data/vendor/local/share/gtk-doc/html/gio/GMemoryOutputStream.html +38 -38
- data/vendor/local/share/gtk-doc/html/gio/GMenu.html +138 -145
- data/vendor/local/share/gtk-doc/html/gio/GMenuModel.html +84 -94
- data/vendor/local/share/gtk-doc/html/gio/GMount.html +54 -66
- data/vendor/local/share/gtk-doc/html/gio/GMountOperation.html +34 -42
- data/vendor/local/share/gtk-doc/html/gio/GNetworkAddress.html +26 -28
- data/vendor/local/share/gtk-doc/html/gio/GNetworkMonitor.html +97 -39
- data/vendor/local/share/gtk-doc/html/gio/GNetworkService.html +18 -23
- data/vendor/local/share/gtk-doc/html/gio/GNotification.html +49 -47
- data/vendor/local/share/gtk-doc/html/gio/GOutputStream.html +39 -56
- data/vendor/local/share/gtk-doc/html/gio/GPermission.html +26 -34
- data/vendor/local/share/gtk-doc/html/gio/GPollableInputStream.html +16 -20
- data/vendor/local/share/gtk-doc/html/gio/GPollableOutputStream.html +16 -20
- data/vendor/local/share/gtk-doc/html/gio/GPropertyAction.html +33 -20
- data/vendor/local/share/gtk-doc/html/gio/GProxy.html +30 -32
- data/vendor/local/share/gtk-doc/html/gio/GProxyAddress.html +42 -51
- data/vendor/local/share/gtk-doc/html/gio/GProxyResolver.html +17 -19
- data/vendor/local/share/gtk-doc/html/gio/GRemoteActionGroup.html +15 -16
- data/vendor/local/share/gtk-doc/html/gio/GResolver.html +46 -47
- data/vendor/local/share/gtk-doc/html/gio/GResource.html +79 -74
- data/vendor/local/share/gtk-doc/html/gio/GSeekable.html +12 -18
- data/vendor/local/share/gtk-doc/html/gio/GSettings.html +325 -200
- data/vendor/local/share/gtk-doc/html/gio/GSettingsBackend.html +28 -29
- data/vendor/local/share/gtk-doc/html/gio/GSimpleAction.html +46 -49
- data/vendor/local/share/gtk-doc/html/gio/GSimpleActionGroup.html +21 -23
- data/vendor/local/share/gtk-doc/html/gio/GSimpleAsyncResult.html +258 -162
- data/vendor/local/share/gtk-doc/html/gio/GSimpleIOStream.html +11 -13
- data/vendor/local/share/gtk-doc/html/gio/GSimplePermission.html +7 -9
- data/vendor/local/share/gtk-doc/html/gio/GSimpleProxyResolver.html +16 -18
- data/vendor/local/share/gtk-doc/html/gio/GSocket.html +470 -281
- data/vendor/local/share/gtk-doc/html/gio/GSocketAddress.html +27 -32
- data/vendor/local/share/gtk-doc/html/gio/GSocketClient.html +76 -85
- data/vendor/local/share/gtk-doc/html/gio/GSocketConnectable.html +118 -72
- data/vendor/local/share/gtk-doc/html/gio/GSocketConnection.html +28 -33
- data/vendor/local/share/gtk-doc/html/gio/GSocketControlMessage.html +26 -30
- data/vendor/local/share/gtk-doc/html/gio/GSocketListener.html +180 -62
- data/vendor/local/share/gtk-doc/html/gio/GSocketService.html +51 -28
- data/vendor/local/share/gtk-doc/html/gio/GSrvTarget.html +25 -31
- data/vendor/local/share/gtk-doc/html/gio/GSubprocess.html +63 -75
- data/vendor/local/share/gtk-doc/html/gio/GSubprocessLauncher.html +49 -54
- data/vendor/local/share/gtk-doc/html/gio/GTask.html +406 -404
- data/vendor/local/share/gtk-doc/html/gio/GTcpConnection.html +11 -13
- data/vendor/local/share/gtk-doc/html/gio/GTcpWrapperConnection.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/GTestDBus.html +36 -38
- data/vendor/local/share/gtk-doc/html/gio/GThemedIcon.html +30 -31
- data/vendor/local/share/gtk-doc/html/gio/GThreadedSocketService.html +11 -14
- data/vendor/local/share/gtk-doc/html/gio/GTlsBackend.html +172 -46
- data/vendor/local/share/gtk-doc/html/gio/GTlsCertificate.html +26 -32
- data/vendor/local/share/gtk-doc/html/gio/GTlsClientConnection.html +96 -37
- data/vendor/local/share/gtk-doc/html/gio/GTlsConnection.html +64 -66
- data/vendor/local/share/gtk-doc/html/gio/GTlsDatabase.html +256 -63
- data/vendor/local/share/gtk-doc/html/gio/GTlsFileDatabase.html +15 -16
- data/vendor/local/share/gtk-doc/html/gio/GTlsInteraction.html +150 -49
- data/vendor/local/share/gtk-doc/html/gio/GTlsPassword.html +46 -51
- data/vendor/local/share/gtk-doc/html/gio/GTlsServerConnection.html +21 -18
- data/vendor/local/share/gtk-doc/html/gio/GUnixConnection.html +21 -26
- data/vendor/local/share/gtk-doc/html/gio/GUnixCredentialsMessage.html +21 -25
- data/vendor/local/share/gtk-doc/html/gio/GUnixFDList.html +31 -37
- data/vendor/local/share/gtk-doc/html/gio/GUnixFDMessage.html +24 -28
- data/vendor/local/share/gtk-doc/html/gio/GUnixInputStream.html +15 -19
- data/vendor/local/share/gtk-doc/html/gio/GUnixOutputStream.html +15 -19
- data/vendor/local/share/gtk-doc/html/gio/GUnixSocketAddress.html +43 -47
- data/vendor/local/share/gtk-doc/html/gio/GVfs.html +22 -24
- data/vendor/local/share/gtk-doc/html/gio/GVolume.html +43 -54
- data/vendor/local/share/gtk-doc/html/gio/GVolumeMonitor.html +26 -27
- data/vendor/local/share/gtk-doc/html/gio/GZlibCompressor.html +15 -17
- data/vendor/local/share/gtk-doc/html/gio/GZlibDecompressor.html +11 -13
- data/vendor/local/share/gtk-doc/html/gio/annotation-glossary.html +21 -6
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-18.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-20.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-22.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-24.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-26.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-28.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-30.html +11 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-32.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-34.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-36.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-38.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-40.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-42.html +11 -5
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-44.html +5 -6
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-46.html +211 -0
- data/vendor/local/share/gtk-doc/html/gio/api-index-2-48.html +283 -0
- data/vendor/local/share/gtk-doc/html/gio/api-index-deprecated.html +107 -4
- data/vendor/local/share/gtk-doc/html/gio/api-index-full.html +459 -8
- data/vendor/local/share/gtk-doc/html/gio/application.html +5 -6
- data/vendor/local/share/gtk-doc/html/gio/async.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/ch01.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/ch02.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/ch03.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/ch32.html +29 -172
- data/vendor/local/share/gtk-doc/html/gio/ch33.html +187 -27
- data/vendor/local/share/gtk-doc/html/gio/ch33s02.html +15 -34
- data/vendor/local/share/gtk-doc/html/gio/ch33s03.html +16 -137
- data/vendor/local/share/gtk-doc/html/gio/ch34.html +26 -87
- data/vendor/local/share/gtk-doc/html/gio/ch34s02.html +37 -121
- data/vendor/local/share/gtk-doc/html/gio/ch34s03.html +132 -176
- data/vendor/local/share/gtk-doc/html/gio/ch34s04.html +19 -71
- data/vendor/local/share/gtk-doc/html/gio/ch34s05.html +24 -908
- data/vendor/local/share/gtk-doc/html/gio/{ch33s06.html → ch34s06.html} +9 -10
- data/vendor/local/share/gtk-doc/html/gio/{ch33s07.html → ch34s07.html} +9 -10
- data/vendor/local/share/gtk-doc/html/gio/ch35.html +94 -0
- data/vendor/local/share/gtk-doc/html/gio/ch35s02.html +141 -0
- data/vendor/local/share/gtk-doc/html/gio/ch35s03.html +201 -0
- data/vendor/local/share/gtk-doc/html/gio/ch35s04.html +96 -0
- data/vendor/local/share/gtk-doc/html/gio/conversion.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/data-models.html +4 -5
- data/vendor/local/share/gtk-doc/html/gio/extending-gio.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/extending.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/failable_initialization.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/file_mon.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/file_ops.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/gapplication-tool.html +11 -12
- data/vendor/local/share/gtk-doc/html/gio/gdbus-codegen.html +199 -200
- data/vendor/local/share/gtk-doc/html/gio/gdbus-convenience.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/gdbus-example-gdbus-codegen.html +89 -0
- data/vendor/local/share/gtk-doc/html/gio/gdbus-lowlevel.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/gdbus.html +9 -10
- data/vendor/local/share/gtk-doc/html/gio/gio-D-Bus-Addresses.html +24 -28
- data/vendor/local/share/gtk-doc/html/gio/gio-D-Bus-Introspection-Data.html +77 -87
- data/vendor/local/share/gtk-doc/html/gio/gio-D-Bus-Utilities.html +19 -27
- data/vendor/local/share/gtk-doc/html/gio/gio-Desktop-file-based-GAppInfo.html +43 -57
- data/vendor/local/share/gtk-doc/html/gio/gio-Extension-Points.html +47 -52
- data/vendor/local/share/gtk-doc/html/gio/gio-GActionGroup-exporter.html +11 -13
- data/vendor/local/share/gtk-doc/html/gio/gio-GContentType.html +20 -27
- data/vendor/local/share/gtk-doc/html/gio/gio-GConverterInputstream.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/gio-GConverterOutputstream.html +9 -11
- data/vendor/local/share/gtk-doc/html/gio/gio-GDBusError.html +59 -67
- data/vendor/local/share/gtk-doc/html/gio/gio-GFileAttribute.html +16 -21
- data/vendor/local/share/gtk-doc/html/gio/gio-GIOError.html +21 -17
- data/vendor/local/share/gtk-doc/html/gio/gio-GIOScheduler.html +9 -12
- data/vendor/local/share/gtk-doc/html/gio/gio-GMenuModel-exporter.html +11 -13
- data/vendor/local/share/gtk-doc/html/gio/gio-GSettingsSchema-GSettingsSchemaSource.html +147 -114
- data/vendor/local/share/gtk-doc/html/gio/gio-GWin32InputStream.html +12 -16
- data/vendor/local/share/gtk-doc/html/gio/gio-GWin32OutputStream.html +13 -17
- data/vendor/local/share/gtk-doc/html/gio/gio-GWin32RegistryKey.html +2066 -0
- data/vendor/local/share/gtk-doc/html/gio/gio-Owning-Bus-Names.html +29 -32
- data/vendor/local/share/gtk-doc/html/gio/gio-TLS-Overview.html +16 -13
- data/vendor/local/share/gtk-doc/html/gio/gio-Unix-Mounts.html +54 -75
- data/vendor/local/share/gtk-doc/html/gio/gio-Watching-Bus-Names.html +27 -30
- data/vendor/local/share/gtk-doc/html/gio/gio-gnetworking.h.html +5 -6
- data/vendor/local/share/gtk-doc/html/gio/gio-gpollableutils.html +16 -21
- data/vendor/local/share/gtk-doc/html/gio/gio-hierarchy.html +11 -8
- data/vendor/local/share/gtk-doc/html/gio/gio-querymodules.html +4 -5
- data/vendor/local/share/gtk-doc/html/gio/gio.devhelp2 +194 -140
- data/vendor/local/share/gtk-doc/html/gio/glib-compile-resources.html +6 -7
- data/vendor/local/share/gtk-doc/html/gio/glib-compile-schemas.html +12 -6
- data/vendor/local/share/gtk-doc/html/gio/gresource-tool.html +5 -6
- data/vendor/local/share/gtk-doc/html/gio/gsettings-tool.html +5 -6
- data/vendor/local/share/gtk-doc/html/gio/highlevel-socket.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/icons.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/index.html +41 -45
- data/vendor/local/share/gtk-doc/html/gio/index.sgml +204 -137
- data/vendor/local/share/gtk-doc/html/gio/migrating.html +22 -44
- data/vendor/local/share/gtk-doc/html/gio/networking.html +6 -4
- data/vendor/local/share/gtk-doc/html/gio/permissions.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/pt01.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/pt02.html +20 -5
- data/vendor/local/share/gtk-doc/html/gio/registry.html +32 -0
- data/vendor/local/share/gtk-doc/html/gio/resolver.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/resources.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/running-gio-apps.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/settings.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/streaming.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/style.css +9 -6
- data/vendor/local/share/gtk-doc/html/gio/subprocesses.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/testing.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/tls.html +12 -4
- data/vendor/local/share/gtk-doc/html/gio/tools.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/types.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/utils.html +3 -4
- data/vendor/local/share/gtk-doc/html/gio/volume_mon.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/annotation-glossary.html +16 -6
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-10.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-12.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-14.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-16.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-18.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-2.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-20.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-22.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-24.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-26.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-28.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-30.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-32.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-34.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-36.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-38.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-4.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-40.html +7 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-42.html +12 -6
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-44.html +5 -6
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-46.html +68 -0
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-48.html +68 -0
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-6.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-2-8.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/api-index-deprecated.html +46 -8
- data/vendor/local/share/gtk-doc/html/glib/api-index-full.html +80 -9
- data/vendor/local/share/gtk-doc/html/glib/deprecated.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-Arrays.html +68 -85
- data/vendor/local/share/gtk-doc/html/glib/glib-Asynchronous-Queues.html +254 -84
- data/vendor/local/share/gtk-doc/html/glib/glib-Atomic-Operations.html +130 -144
- data/vendor/local/share/gtk-doc/html/glib/glib-Automatic-String-Completion.html +19 -23
- data/vendor/local/share/gtk-doc/html/glib/glib-Balanced-Binary-Trees.html +33 -46
- data/vendor/local/share/gtk-doc/html/glib/glib-Base64-Encoding.html +22 -26
- data/vendor/local/share/gtk-doc/html/glib/glib-Basic-Types.html +89 -82
- data/vendor/local/share/gtk-doc/html/glib/glib-Bookmark-file-parser.html +87 -112
- data/vendor/local/share/gtk-doc/html/glib/glib-Bounds-checked-integer-arithmetic.html +384 -0
- data/vendor/local/share/gtk-doc/html/glib/glib-Byte-Arrays.html +100 -114
- data/vendor/local/share/gtk-doc/html/glib/glib-Byte-Order-Macros.html +83 -143
- data/vendor/local/share/gtk-doc/html/glib/glib-Caches.html +14 -19
- data/vendor/local/share/gtk-doc/html/glib/glib-Character-Set-Conversion.html +49 -64
- data/vendor/local/share/gtk-doc/html/glib/glib-Commandline-option-parser.html +141 -156
- data/vendor/local/share/gtk-doc/html/glib/glib-Data-Checksums.html +32 -38
- data/vendor/local/share/gtk-doc/html/glib/glib-Data-HMACs.html +24 -31
- data/vendor/local/share/gtk-doc/html/glib/glib-Datasets.html +28 -32
- data/vendor/local/share/gtk-doc/html/glib/glib-Date-and-Time-Functions.html +108 -141
- data/vendor/local/share/gtk-doc/html/glib/glib-Deprecated-Thread-APIs.html +98 -113
- data/vendor/local/share/gtk-doc/html/glib/glib-Double-ended-Queues.html +89 -112
- data/vendor/local/share/gtk-doc/html/glib/glib-Doubly-Linked-Lists.html +93 -125
- data/vendor/local/share/gtk-doc/html/glib/glib-Dynamic-Loading-of-Modules.html +50 -58
- data/vendor/local/share/gtk-doc/html/glib/glib-Error-Reporting.html +189 -171
- data/vendor/local/share/gtk-doc/html/glib/glib-File-Utilities.html +99 -134
- data/vendor/local/share/gtk-doc/html/glib/glib-GDateTime.html +172 -217
- data/vendor/local/share/gtk-doc/html/glib/glib-GTimeZone.html +32 -42
- data/vendor/local/share/gtk-doc/html/glib/glib-GVariant.html +430 -451
- data/vendor/local/share/gtk-doc/html/glib/glib-GVariantType.html +53 -66
- data/vendor/local/share/gtk-doc/html/glib/glib-Glob-style-pattern-matching.html +12 -18
- data/vendor/local/share/gtk-doc/html/glib/glib-Hash-Tables.html +167 -192
- data/vendor/local/share/gtk-doc/html/glib/glib-Hook-Functions.html +58 -78
- data/vendor/local/share/gtk-doc/html/glib/glib-Hostname-Utilities.html +14 -20
- data/vendor/local/share/gtk-doc/html/glib/glib-I18N.html +70 -79
- data/vendor/local/share/gtk-doc/html/glib/glib-IO-Channels.html +68 -102
- data/vendor/local/share/gtk-doc/html/glib/glib-Key-value-file-parser.html +166 -183
- data/vendor/local/share/gtk-doc/html/glib/glib-Keyed-Data-Lists.html +33 -41
- data/vendor/local/share/gtk-doc/html/glib/glib-Lexical-Scanner.html +80 -92
- data/vendor/local/share/gtk-doc/html/glib/glib-Memory-Allocation.html +101 -119
- data/vendor/local/share/gtk-doc/html/glib/glib-Memory-Slices.html +102 -75
- data/vendor/local/share/gtk-doc/html/glib/glib-Message-Logging.html +133 -60
- data/vendor/local/share/gtk-doc/html/glib/glib-Miscellaneous-Macros.html +192 -162
- data/vendor/local/share/gtk-doc/html/glib/glib-Miscellaneous-Utility-Functions.html +107 -155
- data/vendor/local/share/gtk-doc/html/glib/glib-N-ary-Trees.html +69 -103
- data/vendor/local/share/gtk-doc/html/glib/glib-Numerical-Definitions.html +12 -16
- data/vendor/local/share/gtk-doc/html/glib/glib-Perl-compatible-regular-expressions.html +199 -230
- data/vendor/local/share/gtk-doc/html/glib/glib-Pointer-Arrays.html +54 -67
- data/vendor/local/share/gtk-doc/html/glib/glib-Quarks.html +15 -22
- data/vendor/local/share/gtk-doc/html/glib/glib-Random-Numbers.html +24 -39
- data/vendor/local/share/gtk-doc/html/glib/glib-Relations-and-Tuples.html +29 -36
- data/vendor/local/share/gtk-doc/html/glib/glib-Sequences.html +187 -173
- data/vendor/local/share/gtk-doc/html/glib/glib-Shell-related-Utilities.html +13 -17
- data/vendor/local/share/gtk-doc/html/glib/glib-Simple-XML-Subset-Parser.html +104 -117
- data/vendor/local/share/gtk-doc/html/glib/glib-Singly-Linked-Lists.html +62 -89
- data/vendor/local/share/gtk-doc/html/glib/glib-Spawning-Processes.html +26 -38
- data/vendor/local/share/gtk-doc/html/glib/glib-Standard-Macros.html +15 -23
- data/vendor/local/share/gtk-doc/html/glib/glib-String-Chunks.html +13 -18
- data/vendor/local/share/gtk-doc/html/glib/glib-String-Utility-Functions.html +210 -261
- data/vendor/local/share/gtk-doc/html/glib/glib-Strings.html +95 -101
- data/vendor/local/share/gtk-doc/html/glib/glib-Testing.html +306 -268
- data/vendor/local/share/gtk-doc/html/glib/glib-The-Main-Event-Loop.html +373 -369
- data/vendor/local/share/gtk-doc/html/glib/glib-Thread-Pools.html +79 -45
- data/vendor/local/share/gtk-doc/html/glib/glib-Threads.html +316 -319
- data/vendor/local/share/gtk-doc/html/glib/glib-Timers.html +12 -15
- data/vendor/local/share/gtk-doc/html/glib/glib-Trash-Stacks.html +44 -26
- data/vendor/local/share/gtk-doc/html/glib/glib-Type-Conversion-Macros.html +20 -21
- data/vendor/local/share/gtk-doc/html/glib/glib-UNIX-specific-utilities-and-integration.html +44 -53
- data/vendor/local/share/gtk-doc/html/glib/glib-URI-Functions.html +21 -26
- data/vendor/local/share/gtk-doc/html/glib/glib-Unicode-Manipulation.html +200 -220
- data/vendor/local/share/gtk-doc/html/glib/glib-Version-Information.html +51 -28
- data/vendor/local/share/gtk-doc/html/glib/glib-Warnings-and-Assertions.html +38 -41
- data/vendor/local/share/gtk-doc/html/glib/glib-Windows-Compatibility-Functions.html +25 -34
- data/vendor/local/share/gtk-doc/html/glib/glib-building.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-changes.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-compiling.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-core.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-cross-compiling.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-data-types.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-fundamentals.html +6 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-gettextize.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-programming.html +4 -5
- data/vendor/local/share/gtk-doc/html/glib/glib-regex-syntax.html +14 -15
- data/vendor/local/share/gtk-doc/html/glib/glib-resources.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-running.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib-utilities.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/glib.devhelp2 +44 -59
- data/vendor/local/share/gtk-doc/html/glib/glib.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/gtester-report.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/gtester.html +3 -4
- data/vendor/local/share/gtk-doc/html/glib/gvariant-format-strings.html +149 -149
- data/vendor/local/share/gtk-doc/html/glib/gvariant-text.html +11 -12
- data/vendor/local/share/gtk-doc/html/glib/index.html +9 -5
- data/vendor/local/share/gtk-doc/html/glib/index.sgml +36 -2
- data/vendor/local/share/gtk-doc/html/glib/style.css +9 -6
- data/vendor/local/share/gtk-doc/html/glib/tools.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/GBinding.html +53 -57
- data/vendor/local/share/gtk-doc/html/gobject/GTypeModule.html +72 -77
- data/vendor/local/share/gtk-doc/html/gobject/GTypePlugin.html +19 -20
- data/vendor/local/share/gtk-doc/html/gobject/annotation-glossary.html +14 -6
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-10.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-12.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-14.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-18.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-2.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-22.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-24.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-26.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-28.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-30.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-32.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-34.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-36.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-38.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-4.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-40.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-42.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-44.html +5 -6
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-46.html +34 -0
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-6.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-2-8.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-deprecated.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/api-index-full.html +7 -8
- data/vendor/local/share/gtk-doc/html/gobject/ch01s02.html +22 -17
- data/vendor/local/share/gtk-doc/html/gobject/chapter-gobject.html +85 -135
- data/vendor/local/share/gtk-doc/html/gobject/chapter-gtype.html +80 -144
- data/vendor/local/share/gtk-doc/html/gobject/chapter-intro.html +7 -8
- data/vendor/local/share/gtk-doc/html/gobject/chapter-signal.html +59 -75
- data/vendor/local/share/gtk-doc/html/gobject/glib-genmarshal.html +20 -21
- data/vendor/local/share/gtk-doc/html/gobject/glib-mkenums.html +19 -20
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Boxed-Types.html +68 -89
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Closures.html +227 -218
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Enumeration-and-Flag-Types.html +48 -57
- data/vendor/local/share/gtk-doc/html/gobject/gobject-GParamSpec.html +125 -96
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Generic-values.html +78 -90
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Signals.html +143 -138
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Standard-Parameter-and-Value-Types.html +226 -285
- data/vendor/local/share/gtk-doc/html/gobject/gobject-The-Base-Object-Type.html +306 -289
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Type-Information.html +450 -448
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Value-arrays.html +22 -23
- data/vendor/local/share/gtk-doc/html/gobject/gobject-Varargs-Value-Collection.html +11 -12
- data/vendor/local/share/gtk-doc/html/gobject/gobject-memory.html +32 -91
- data/vendor/local/share/gtk-doc/html/gobject/gobject-properties.html +134 -133
- data/vendor/local/share/gtk-doc/html/gobject/gobject-query.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/gobject.devhelp2 +4 -8
- data/vendor/local/share/gtk-doc/html/gobject/gtype-conventions.html +89 -98
- data/vendor/local/share/gtk-doc/html/gobject/gtype-instantiable-classed.html +119 -112
- data/vendor/local/share/gtk-doc/html/gobject/gtype-non-instantiable-classed.html +199 -183
- data/vendor/local/share/gtk-doc/html/gobject/gtype-non-instantiable.html +30 -30
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject-chainup.html +32 -33
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject-code.html +80 -32
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject-construction.html +73 -53
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject-destruction.html +52 -50
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject-methods.html +255 -133
- data/vendor/local/share/gtk-doc/html/gobject/howto-gobject.html +147 -111
- data/vendor/local/share/gtk-doc/html/gobject/howto-interface-implement.html +65 -122
- data/vendor/local/share/gtk-doc/html/gobject/howto-interface-override.html +93 -79
- data/vendor/local/share/gtk-doc/html/gobject/howto-interface-prerequisite.html +80 -54
- data/vendor/local/share/gtk-doc/html/gobject/howto-interface-properties.html +82 -87
- data/vendor/local/share/gtk-doc/html/gobject/howto-interface.html +126 -62
- data/vendor/local/share/gtk-doc/html/gobject/howto-signals.html +61 -54
- data/vendor/local/share/gtk-doc/html/gobject/index.html +10 -10
- data/vendor/local/share/gtk-doc/html/gobject/index.sgml +4 -2
- data/vendor/local/share/gtk-doc/html/gobject/pr01.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/pt01.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/pt02.html +10 -11
- data/vendor/local/share/gtk-doc/html/gobject/pt03.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/rn01.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/rn02.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/signal.html +98 -198
- data/vendor/local/share/gtk-doc/html/gobject/style.css +9 -6
- data/vendor/local/share/gtk-doc/html/gobject/tools-ginspector.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/tools-gob.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/tools-gtkdoc.html +10 -11
- data/vendor/local/share/gtk-doc/html/gobject/tools-refdb.html +3 -4
- data/vendor/local/share/gtk-doc/html/gobject/tools-vala.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/config-example.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/config-files.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/config.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-building-style.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-building.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-commands.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-debugging.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-paths.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel-testing.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/devel.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/gtk-doc.css +9 -6
- data/vendor/local/share/gtk-doc/html/p11-kit/index.html +2 -3
- data/vendor/local/share/gtk-doc/html/p11-kit/index.sgml +22 -0
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-Deprecated.html +3 -13
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-Future.html +3 -14
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-Modules.html +3 -15
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-PIN-Callbacks.html +3 -14
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-URIs.html +3 -18
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit-Utilities.html +3 -8
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit.devhelp2 +22 -1
- data/vendor/local/share/gtk-doc/html/p11-kit/p11-kit.html +2 -3
- data/vendor/local/share/gtk-doc/html/p11-kit/pkcs11-conf.html +7 -8
- data/vendor/local/share/gtk-doc/html/p11-kit/reference.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/sharing-managed.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/sharing.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/tools.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/trust-disable.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/trust-glib-networking.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/trust-module.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/trust-nss.html +3 -4
- data/vendor/local/share/gtk-doc/html/p11-kit/trust.html +3 -4
- data/vendor/local/share/info/gmp.info +153 -158
- data/vendor/local/share/info/gmp.info-1 +131 -178
- data/vendor/local/share/info/gmp.info-2 +250 -193
- data/vendor/local/share/info/libtasn1.info +2 -2
- data/vendor/local/share/license/gmp/AUTHORS +1 -1
- data/vendor/local/share/license/pcre/AUTHORS +45 -0
- data/vendor/local/share/license/pcre/COPYING +5 -0
- data/vendor/local/share/locale/be/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/bg/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/bg/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/ca/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/ca/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/cs/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/cs/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/cs/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/da/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/da/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/de/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/de/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/de/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/el/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/el/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/en@boldquot/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/en@boldquot/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/en@quot/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/en@quot/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/eo/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/eo/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/es/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/es/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/et/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/eu/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/fi/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/fi/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/fi/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/fr/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/fr/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/fr/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/ga/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/gd/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/gl/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/gl/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/he/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/hr/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/hu/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/hu/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/id/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/id/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/is/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/it/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/it/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/it/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/ja/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/ja/LC_MESSAGES/glib-networking.mo +0 -0
- data/vendor/local/share/locale/kk/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/ko/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/ko/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/lt/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/lv/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/ms/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/nb/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/nb/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/nl/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/nl/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/nn/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/oc/LC_MESSAGES/glib-networking.mo +0 -0
- data/vendor/local/share/locale/oc/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/pl/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/pl/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/pl/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/pt/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/pt/LC_MESSAGES/glib-networking.mo +0 -0
- data/vendor/local/share/locale/pt/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/pt_BR/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/pt_BR/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/ro/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/ru/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/ru/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sk/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/sk/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sl/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/sl/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sr/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/sr/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sr@latin/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sv/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/sv/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/sv/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/th/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/tr/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/tr/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/uk/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/uk/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/vi/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/vi/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/vi/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/zh_CN/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/zh_CN/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/locale/zh_CN/LC_MESSAGES/gnutls.mo +0 -0
- data/vendor/local/share/locale/zh_HK/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/zh_TW/LC_MESSAGES/gettext-runtime.mo +0 -0
- data/vendor/local/share/locale/zh_TW/LC_MESSAGES/glib20.mo +0 -0
- data/vendor/local/share/man/man1/asn1Coding.1 +1 -1
- data/vendor/local/share/man/man1/asn1Decoding.1 +1 -1
- data/vendor/local/share/man/man1/asn1Parser.1 +1 -1
- data/vendor/local/share/man/man1/envsubst.1 +1 -1
- data/vendor/local/share/man/man1/gapplication.1 +2 -2
- data/vendor/local/share/man/man1/gdbus-codegen.1 +23 -22
- data/vendor/local/share/man/man1/gdbus.1 +2 -2
- data/vendor/local/share/man/man1/gettext.1 +1 -1
- data/vendor/local/share/man/man1/gio-querymodules.1 +2 -2
- data/vendor/local/share/man/man1/glib-compile-resources.1 +2 -2
- data/vendor/local/share/man/man1/glib-compile-schemas.1 +7 -2
- data/vendor/local/share/man/man1/glib-genmarshal.1 +2 -2
- data/vendor/local/share/man/man1/glib-gettextize.1 +2 -2
- data/vendor/local/share/man/man1/glib-mkenums.1 +2 -2
- data/vendor/local/share/man/man1/gobject-query.1 +2 -2
- data/vendor/local/share/man/man1/gresource.1 +2 -2
- data/vendor/local/share/man/man1/gsettings.1 +2 -2
- data/vendor/local/share/man/man1/gtester-report.1 +2 -2
- data/vendor/local/share/man/man1/gtester.1 +2 -2
- data/vendor/local/share/man/man1/ngettext.1 +1 -1
- data/vendor/local/share/man/man1/pcre-config.1 +92 -0
- data/vendor/local/share/man/man1/pcregrep.1 +683 -0
- data/vendor/local/share/man/man1/pcretest.1 +1156 -0
- data/vendor/local/share/man/man3/asn1_array2tree.3 +1 -1
- data/vendor/local/share/man/man3/asn1_bit_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_check_version.3 +1 -1
- data/vendor/local/share/man/man3/asn1_copy_node.3 +1 -1
- data/vendor/local/share/man/man3/asn1_create_element.3 +1 -1
- data/vendor/local/share/man/man3/asn1_decode_simple_ber.3 +1 -1
- data/vendor/local/share/man/man3/asn1_decode_simple_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_delete_element.3 +1 -1
- data/vendor/local/share/man/man3/asn1_delete_structure.3 +1 -1
- data/vendor/local/share/man/man3/asn1_delete_structure2.3 +1 -1
- data/vendor/local/share/man/man3/asn1_der_coding.3 +1 -1
- data/vendor/local/share/man/man3/asn1_der_decoding.3 +1 -1
- data/vendor/local/share/man/man3/asn1_der_decoding2.3 +1 -1
- data/vendor/local/share/man/man3/asn1_der_decoding_element.3 +1 -1
- data/vendor/local/share/man/man3/asn1_der_decoding_startEnd.3 +1 -1
- data/vendor/local/share/man/man3/asn1_dup_node.3 +1 -1
- data/vendor/local/share/man/man3/asn1_encode_simple_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_expand_any_defined_by.3 +1 -1
- data/vendor/local/share/man/man3/asn1_expand_octet_string.3 +1 -1
- data/vendor/local/share/man/man3/asn1_find_node.3 +1 -1
- data/vendor/local/share/man/man3/asn1_find_structure_from_oid.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_bit_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_length_ber.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_length_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_object_id_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_octet_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_get_tag_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_length_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_number_of_elements.3 +1 -1
- data/vendor/local/share/man/man3/asn1_octet_der.3 +1 -1
- data/vendor/local/share/man/man3/asn1_parser2array.3 +1 -1
- data/vendor/local/share/man/man3/asn1_parser2tree.3 +1 -1
- data/vendor/local/share/man/man3/asn1_perror.3 +1 -1
- data/vendor/local/share/man/man3/asn1_print_structure.3 +1 -1
- data/vendor/local/share/man/man3/asn1_read_node_value.3 +1 -1
- data/vendor/local/share/man/man3/asn1_read_tag.3 +1 -1
- data/vendor/local/share/man/man3/asn1_read_value.3 +1 -1
- data/vendor/local/share/man/man3/asn1_read_value_type.3 +1 -1
- data/vendor/local/share/man/man3/asn1_strerror.3 +1 -1
- data/vendor/local/share/man/man3/asn1_write_value.3 +1 -1
- data/vendor/local/share/man/man3/bind_textdomain_codeset.3 +1 -1
- data/vendor/local/share/man/man3/bindtextdomain.3 +1 -1
- data/vendor/local/share/man/man3/gettext.3 +1 -1
- data/vendor/local/share/man/man3/ngettext.3 +1 -1
- data/vendor/local/share/man/man3/pcre.3 +230 -0
- data/vendor/local/share/man/man3/pcre16.3 +371 -0
- data/vendor/local/share/man/man3/pcre16_assign_jit_stack.3 +59 -0
- data/vendor/local/share/man/man3/pcre16_compile.3 +96 -0
- data/vendor/local/share/man/man3/pcre16_compile2.3 +101 -0
- data/vendor/local/share/man/man3/pcre16_config.3 +79 -0
- data/vendor/local/share/man/man3/pcre16_copy_named_substring.3 +51 -0
- data/vendor/local/share/man/man3/pcre16_copy_substring.3 +47 -0
- data/vendor/local/share/man/man3/pcre16_dfa_exec.3 +118 -0
- data/vendor/local/share/man/man3/pcre16_exec.3 +99 -0
- data/vendor/local/share/man/man3/pcre16_free_study.3 +31 -0
- data/vendor/local/share/man/man3/pcre16_free_substring.3 +31 -0
- data/vendor/local/share/man/man3/pcre16_free_substring_list.3 +31 -0
- data/vendor/local/share/man/man3/pcre16_fullinfo.3 +103 -0
- data/vendor/local/share/man/man3/pcre16_get_named_substring.3 +54 -0
- data/vendor/local/share/man/man3/pcre16_get_stringnumber.3 +43 -0
- data/vendor/local/share/man/man3/pcre16_get_stringtable_entries.3 +46 -0
- data/vendor/local/share/man/man3/pcre16_get_substring.3 +50 -0
- data/vendor/local/share/man/man3/pcre16_get_substring_list.3 +47 -0
- data/vendor/local/share/man/man3/pcre16_jit_exec.3 +96 -0
- data/vendor/local/share/man/man3/pcre16_jit_stack_alloc.3 +43 -0
- data/vendor/local/share/man/man3/pcre16_jit_stack_free.3 +35 -0
- data/vendor/local/share/man/man3/pcre16_maketables.3 +33 -0
- data/vendor/local/share/man/man3/pcre16_pattern_to_host_byte_order.3 +44 -0
- data/vendor/local/share/man/man3/pcre16_refcount.3 +36 -0
- data/vendor/local/share/man/man3/pcre16_study.3 +54 -0
- data/vendor/local/share/man/man3/pcre16_utf16_to_host_byte_order.3 +45 -0
- data/vendor/local/share/man/man3/pcre16_version.3 +31 -0
- data/vendor/local/share/man/man3/pcre32.3 +369 -0
- data/vendor/local/share/man/man3/pcre32_assign_jit_stack.3 +59 -0
- data/vendor/local/share/man/man3/pcre32_compile.3 +96 -0
- data/vendor/local/share/man/man3/pcre32_compile2.3 +101 -0
- data/vendor/local/share/man/man3/pcre32_config.3 +79 -0
- data/vendor/local/share/man/man3/pcre32_copy_named_substring.3 +51 -0
- data/vendor/local/share/man/man3/pcre32_copy_substring.3 +47 -0
- data/vendor/local/share/man/man3/pcre32_dfa_exec.3 +118 -0
- data/vendor/local/share/man/man3/pcre32_exec.3 +99 -0
- data/vendor/local/share/man/man3/pcre32_free_study.3 +31 -0
- data/vendor/local/share/man/man3/pcre32_free_substring.3 +31 -0
- data/vendor/local/share/man/man3/pcre32_free_substring_list.3 +31 -0
- data/vendor/local/share/man/man3/pcre32_fullinfo.3 +103 -0
- data/vendor/local/share/man/man3/pcre32_get_named_substring.3 +54 -0
- data/vendor/local/share/man/man3/pcre32_get_stringnumber.3 +43 -0
- data/vendor/local/share/man/man3/pcre32_get_stringtable_entries.3 +46 -0
- data/vendor/local/share/man/man3/pcre32_get_substring.3 +50 -0
- data/vendor/local/share/man/man3/pcre32_get_substring_list.3 +47 -0
- data/vendor/local/share/man/man3/pcre32_jit_exec.3 +96 -0
- data/vendor/local/share/man/man3/pcre32_jit_stack_alloc.3 +43 -0
- data/vendor/local/share/man/man3/pcre32_jit_stack_free.3 +35 -0
- data/vendor/local/share/man/man3/pcre32_maketables.3 +33 -0
- data/vendor/local/share/man/man3/pcre32_pattern_to_host_byte_order.3 +44 -0
- data/vendor/local/share/man/man3/pcre32_refcount.3 +36 -0
- data/vendor/local/share/man/man3/pcre32_study.3 +54 -0
- data/vendor/local/share/man/man3/pcre32_utf32_to_host_byte_order.3 +45 -0
- data/vendor/local/share/man/man3/pcre32_version.3 +31 -0
- data/vendor/local/share/man/man3/pcre_assign_jit_stack.3 +59 -0
- data/vendor/local/share/man/man3/pcre_compile.3 +96 -0
- data/vendor/local/share/man/man3/pcre_compile2.3 +101 -0
- data/vendor/local/share/man/man3/pcre_config.3 +79 -0
- data/vendor/local/share/man/man3/pcre_copy_named_substring.3 +51 -0
- data/vendor/local/share/man/man3/pcre_copy_substring.3 +47 -0
- data/vendor/local/share/man/man3/pcre_dfa_exec.3 +118 -0
- data/vendor/local/share/man/man3/pcre_exec.3 +99 -0
- data/vendor/local/share/man/man3/pcre_free_study.3 +31 -0
- data/vendor/local/share/man/man3/pcre_free_substring.3 +31 -0
- data/vendor/local/share/man/man3/pcre_free_substring_list.3 +31 -0
- data/vendor/local/share/man/man3/pcre_fullinfo.3 +103 -0
- data/vendor/local/share/man/man3/pcre_get_named_substring.3 +54 -0
- data/vendor/local/share/man/man3/pcre_get_stringnumber.3 +43 -0
- data/vendor/local/share/man/man3/pcre_get_stringtable_entries.3 +46 -0
- data/vendor/local/share/man/man3/pcre_get_substring.3 +50 -0
- data/vendor/local/share/man/man3/pcre_get_substring_list.3 +47 -0
- data/vendor/local/share/man/man3/pcre_jit_exec.3 +96 -0
- data/vendor/local/share/man/man3/pcre_jit_stack_alloc.3 +43 -0
- data/vendor/local/share/man/man3/pcre_jit_stack_free.3 +35 -0
- data/vendor/local/share/man/man3/pcre_maketables.3 +33 -0
- data/vendor/local/share/man/man3/pcre_pattern_to_host_byte_order.3 +44 -0
- data/vendor/local/share/man/man3/pcre_refcount.3 +36 -0
- data/vendor/local/share/man/man3/pcre_study.3 +54 -0
- data/vendor/local/share/man/man3/pcre_utf16_to_host_byte_order.3 +45 -0
- data/vendor/local/share/man/man3/pcre_utf32_to_host_byte_order.3 +45 -0
- data/vendor/local/share/man/man3/pcre_version.3 +31 -0
- data/vendor/local/share/man/man3/pcreapi.3 +2919 -0
- data/vendor/local/share/man/man3/pcrebuild.3 +550 -0
- data/vendor/local/share/man/man3/pcrecallout.3 +255 -0
- data/vendor/local/share/man/man3/pcrecompat.3 +200 -0
- data/vendor/local/share/man/man3/pcrecpp.3 +348 -0
- data/vendor/local/share/man/man3/pcredemo.3 +424 -0
- data/vendor/local/share/man/man3/pcrejit.3 +431 -0
- data/vendor/local/share/man/man3/pcrelimits.3 +71 -0
- data/vendor/local/share/man/man3/pcrematching.3 +214 -0
- data/vendor/local/share/man/man3/pcrepartial.3 +476 -0
- data/vendor/local/share/man/man3/pcrepattern.3 +3301 -0
- data/vendor/local/share/man/man3/pcreperform.3 +177 -0
- data/vendor/local/share/man/man3/pcreposix.3 +267 -0
- data/vendor/local/share/man/man3/pcreprecompile.3 +155 -0
- data/vendor/local/share/man/man3/pcresample.3 +99 -0
- data/vendor/local/share/man/man3/pcrestack.3 +215 -0
- data/vendor/local/share/man/man3/pcresyntax.3 +540 -0
- data/vendor/local/share/man/man3/pcreunicode.3 +249 -0
- data/vendor/local/share/man/man3/textdomain.3 +1 -1
- metadata +233 -22
- data/lib/2.0/glib2.so +0 -0
- data/lib/2.1/glib2.so +0 -0
- data/vendor/local/bin/libhogweed-4-1.dll +0 -0
- data/vendor/local/share/gtk-doc/html/gio/ExampleAnimal.html +0 -1537
- data/vendor/local/share/gtk-doc/html/gio/ExampleCat.html +0 -679
- data/vendor/local/share/gtk-doc/html/gio/ExampleObject.html +0 -572
- data/vendor/local/share/gtk-doc/html/gio/ExampleObjectManagerClient.html +0 -561
- data/vendor/local/share/gtk-doc/html/gio/ch31.html +0 -75
- data/vendor/local/share/gtk-doc/html/gio/ch32s02.html +0 -41
- data/vendor/local/share/gtk-doc/html/gio/ch32s03.html +0 -39
- data/vendor/local/share/gtk-doc/html/gio/ch33s04.html +0 -46
- data/vendor/local/share/gtk-doc/html/gio/ch33s05.html +0 -48
- data/vendor/local/share/gtk-doc/html/gio/gdbus-org.gtk.GDBus.Example.ObjectManager.Animal.html +0 -161
- data/vendor/local/share/gtk-doc/html/gio/gdbus-org.gtk.GDBus.Example.ObjectManager.Cat.html +0 -51
@@ -0,0 +1,3273 @@
|
|
1
|
+
<html>
|
2
|
+
<head>
|
3
|
+
<title>pcrepattern specification</title>
|
4
|
+
</head>
|
5
|
+
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
|
6
|
+
<h1>pcrepattern man page</h1>
|
7
|
+
<p>
|
8
|
+
Return to the <a href="index.html">PCRE index page</a>.
|
9
|
+
</p>
|
10
|
+
<p>
|
11
|
+
This page is part of the PCRE HTML documentation. It was generated automatically
|
12
|
+
from the original man page. If there is any nonsense in it, please consult the
|
13
|
+
man page, in case the conversion went wrong.
|
14
|
+
<br>
|
15
|
+
<ul>
|
16
|
+
<li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION DETAILS</a>
|
17
|
+
<li><a name="TOC2" href="#SEC2">SPECIAL START-OF-PATTERN ITEMS</a>
|
18
|
+
<li><a name="TOC3" href="#SEC3">EBCDIC CHARACTER CODES</a>
|
19
|
+
<li><a name="TOC4" href="#SEC4">CHARACTERS AND METACHARACTERS</a>
|
20
|
+
<li><a name="TOC5" href="#SEC5">BACKSLASH</a>
|
21
|
+
<li><a name="TOC6" href="#SEC6">CIRCUMFLEX AND DOLLAR</a>
|
22
|
+
<li><a name="TOC7" href="#SEC7">FULL STOP (PERIOD, DOT) AND \N</a>
|
23
|
+
<li><a name="TOC8" href="#SEC8">MATCHING A SINGLE DATA UNIT</a>
|
24
|
+
<li><a name="TOC9" href="#SEC9">SQUARE BRACKETS AND CHARACTER CLASSES</a>
|
25
|
+
<li><a name="TOC10" href="#SEC10">POSIX CHARACTER CLASSES</a>
|
26
|
+
<li><a name="TOC11" href="#SEC11">COMPATIBILITY FEATURE FOR WORD BOUNDARIES</a>
|
27
|
+
<li><a name="TOC12" href="#SEC12">VERTICAL BAR</a>
|
28
|
+
<li><a name="TOC13" href="#SEC13">INTERNAL OPTION SETTING</a>
|
29
|
+
<li><a name="TOC14" href="#SEC14">SUBPATTERNS</a>
|
30
|
+
<li><a name="TOC15" href="#SEC15">DUPLICATE SUBPATTERN NUMBERS</a>
|
31
|
+
<li><a name="TOC16" href="#SEC16">NAMED SUBPATTERNS</a>
|
32
|
+
<li><a name="TOC17" href="#SEC17">REPETITION</a>
|
33
|
+
<li><a name="TOC18" href="#SEC18">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a>
|
34
|
+
<li><a name="TOC19" href="#SEC19">BACK REFERENCES</a>
|
35
|
+
<li><a name="TOC20" href="#SEC20">ASSERTIONS</a>
|
36
|
+
<li><a name="TOC21" href="#SEC21">CONDITIONAL SUBPATTERNS</a>
|
37
|
+
<li><a name="TOC22" href="#SEC22">COMMENTS</a>
|
38
|
+
<li><a name="TOC23" href="#SEC23">RECURSIVE PATTERNS</a>
|
39
|
+
<li><a name="TOC24" href="#SEC24">SUBPATTERNS AS SUBROUTINES</a>
|
40
|
+
<li><a name="TOC25" href="#SEC25">ONIGURUMA SUBROUTINE SYNTAX</a>
|
41
|
+
<li><a name="TOC26" href="#SEC26">CALLOUTS</a>
|
42
|
+
<li><a name="TOC27" href="#SEC27">BACKTRACKING CONTROL</a>
|
43
|
+
<li><a name="TOC28" href="#SEC28">SEE ALSO</a>
|
44
|
+
<li><a name="TOC29" href="#SEC29">AUTHOR</a>
|
45
|
+
<li><a name="TOC30" href="#SEC30">REVISION</a>
|
46
|
+
</ul>
|
47
|
+
<br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION DETAILS</a><br>
|
48
|
+
<P>
|
49
|
+
The syntax and semantics of the regular expressions that are supported by PCRE
|
50
|
+
are described in detail below. There is a quick-reference syntax summary in the
|
51
|
+
<a href="pcresyntax.html"><b>pcresyntax</b></a>
|
52
|
+
page. PCRE tries to match Perl syntax and semantics as closely as it can. PCRE
|
53
|
+
also supports some alternative regular expression syntax (which does not
|
54
|
+
conflict with the Perl syntax) in order to provide some compatibility with
|
55
|
+
regular expressions in Python, .NET, and Oniguruma.
|
56
|
+
</P>
|
57
|
+
<P>
|
58
|
+
Perl's regular expressions are described in its own documentation, and
|
59
|
+
regular expressions in general are covered in a number of books, some of which
|
60
|
+
have copious examples. Jeffrey Friedl's "Mastering Regular Expressions",
|
61
|
+
published by O'Reilly, covers regular expressions in great detail. This
|
62
|
+
description of PCRE's regular expressions is intended as reference material.
|
63
|
+
</P>
|
64
|
+
<P>
|
65
|
+
This document discusses the patterns that are supported by PCRE when one its
|
66
|
+
main matching functions, <b>pcre_exec()</b> (8-bit) or <b>pcre[16|32]_exec()</b>
|
67
|
+
(16- or 32-bit), is used. PCRE also has alternative matching functions,
|
68
|
+
<b>pcre_dfa_exec()</b> and <b>pcre[16|32_dfa_exec()</b>, which match using a
|
69
|
+
different algorithm that is not Perl-compatible. Some of the features discussed
|
70
|
+
below are not available when DFA matching is used. The advantages and
|
71
|
+
disadvantages of the alternative functions, and how they differ from the normal
|
72
|
+
functions, are discussed in the
|
73
|
+
<a href="pcrematching.html"><b>pcrematching</b></a>
|
74
|
+
page.
|
75
|
+
</P>
|
76
|
+
<br><a name="SEC2" href="#TOC1">SPECIAL START-OF-PATTERN ITEMS</a><br>
|
77
|
+
<P>
|
78
|
+
A number of options that can be passed to <b>pcre_compile()</b> can also be set
|
79
|
+
by special items at the start of a pattern. These are not Perl-compatible, but
|
80
|
+
are provided to make these options accessible to pattern writers who are not
|
81
|
+
able to change the program that processes the pattern. Any number of these
|
82
|
+
items may appear, but they must all be together right at the start of the
|
83
|
+
pattern string, and the letters must be in upper case.
|
84
|
+
</P>
|
85
|
+
<br><b>
|
86
|
+
UTF support
|
87
|
+
</b><br>
|
88
|
+
<P>
|
89
|
+
The original operation of PCRE was on strings of one-byte characters. However,
|
90
|
+
there is now also support for UTF-8 strings in the original library, an
|
91
|
+
extra library that supports 16-bit and UTF-16 character strings, and a
|
92
|
+
third library that supports 32-bit and UTF-32 character strings. To use these
|
93
|
+
features, PCRE must be built to include appropriate support. When using UTF
|
94
|
+
strings you must either call the compiling function with the PCRE_UTF8,
|
95
|
+
PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of
|
96
|
+
these special sequences:
|
97
|
+
<pre>
|
98
|
+
(*UTF8)
|
99
|
+
(*UTF16)
|
100
|
+
(*UTF32)
|
101
|
+
(*UTF)
|
102
|
+
</pre>
|
103
|
+
(*UTF) is a generic sequence that can be used with any of the libraries.
|
104
|
+
Starting a pattern with such a sequence is equivalent to setting the relevant
|
105
|
+
option. How setting a UTF mode affects pattern matching is mentioned in several
|
106
|
+
places below. There is also a summary of features in the
|
107
|
+
<a href="pcreunicode.html"><b>pcreunicode</b></a>
|
108
|
+
page.
|
109
|
+
</P>
|
110
|
+
<P>
|
111
|
+
Some applications that allow their users to supply patterns may wish to
|
112
|
+
restrict them to non-UTF data for security reasons. If the PCRE_NEVER_UTF
|
113
|
+
option is set at compile time, (*UTF) etc. are not allowed, and their
|
114
|
+
appearance causes an error.
|
115
|
+
</P>
|
116
|
+
<br><b>
|
117
|
+
Unicode property support
|
118
|
+
</b><br>
|
119
|
+
<P>
|
120
|
+
Another special sequence that may appear at the start of a pattern is (*UCP).
|
121
|
+
This has the same effect as setting the PCRE_UCP option: it causes sequences
|
122
|
+
such as \d and \w to use Unicode properties to determine character types,
|
123
|
+
instead of recognizing only characters with codes less than 128 via a lookup
|
124
|
+
table.
|
125
|
+
</P>
|
126
|
+
<br><b>
|
127
|
+
Disabling auto-possessification
|
128
|
+
</b><br>
|
129
|
+
<P>
|
130
|
+
If a pattern starts with (*NO_AUTO_POSSESS), it has the same effect as setting
|
131
|
+
the PCRE_NO_AUTO_POSSESS option at compile time. This stops PCRE from making
|
132
|
+
quantifiers possessive when what follows cannot match the repeated item. For
|
133
|
+
example, by default a+b is treated as a++b. For more details, see the
|
134
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
135
|
+
documentation.
|
136
|
+
</P>
|
137
|
+
<br><b>
|
138
|
+
Disabling start-up optimizations
|
139
|
+
</b><br>
|
140
|
+
<P>
|
141
|
+
If a pattern starts with (*NO_START_OPT), it has the same effect as setting the
|
142
|
+
PCRE_NO_START_OPTIMIZE option either at compile or matching time. This disables
|
143
|
+
several optimizations for quickly reaching "no match" results. For more
|
144
|
+
details, see the
|
145
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
146
|
+
documentation.
|
147
|
+
<a name="newlines"></a></P>
|
148
|
+
<br><b>
|
149
|
+
Newline conventions
|
150
|
+
</b><br>
|
151
|
+
<P>
|
152
|
+
PCRE supports five different conventions for indicating line breaks in
|
153
|
+
strings: a single CR (carriage return) character, a single LF (linefeed)
|
154
|
+
character, the two-character sequence CRLF, any of the three preceding, or any
|
155
|
+
Unicode newline sequence. The
|
156
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
157
|
+
page has
|
158
|
+
<a href="pcreapi.html#newlines">further discussion</a>
|
159
|
+
about newlines, and shows how to set the newline convention in the
|
160
|
+
<i>options</i> arguments for the compiling and matching functions.
|
161
|
+
</P>
|
162
|
+
<P>
|
163
|
+
It is also possible to specify a newline convention by starting a pattern
|
164
|
+
string with one of the following five sequences:
|
165
|
+
<pre>
|
166
|
+
(*CR) carriage return
|
167
|
+
(*LF) linefeed
|
168
|
+
(*CRLF) carriage return, followed by linefeed
|
169
|
+
(*ANYCRLF) any of the three above
|
170
|
+
(*ANY) all Unicode newline sequences
|
171
|
+
</pre>
|
172
|
+
These override the default and the options given to the compiling function. For
|
173
|
+
example, on a Unix system where LF is the default newline sequence, the pattern
|
174
|
+
<pre>
|
175
|
+
(*CR)a.b
|
176
|
+
</pre>
|
177
|
+
changes the convention to CR. That pattern matches "a\nb" because LF is no
|
178
|
+
longer a newline. If more than one of these settings is present, the last one
|
179
|
+
is used.
|
180
|
+
</P>
|
181
|
+
<P>
|
182
|
+
The newline convention affects where the circumflex and dollar assertions are
|
183
|
+
true. It also affects the interpretation of the dot metacharacter when
|
184
|
+
PCRE_DOTALL is not set, and the behaviour of \N. However, it does not affect
|
185
|
+
what the \R escape sequence matches. By default, this is any Unicode newline
|
186
|
+
sequence, for Perl compatibility. However, this can be changed; see the
|
187
|
+
description of \R in the section entitled
|
188
|
+
<a href="#newlineseq">"Newline sequences"</a>
|
189
|
+
below. A change of \R setting can be combined with a change of newline
|
190
|
+
convention.
|
191
|
+
</P>
|
192
|
+
<br><b>
|
193
|
+
Setting match and recursion limits
|
194
|
+
</b><br>
|
195
|
+
<P>
|
196
|
+
The caller of <b>pcre_exec()</b> can set a limit on the number of times the
|
197
|
+
internal <b>match()</b> function is called and on the maximum depth of
|
198
|
+
recursive calls. These facilities are provided to catch runaway matches that
|
199
|
+
are provoked by patterns with huge matching trees (a typical example is a
|
200
|
+
pattern with nested unlimited repeats) and to avoid running out of system stack
|
201
|
+
by too much recursion. When one of these limits is reached, <b>pcre_exec()</b>
|
202
|
+
gives an error return. The limits can also be set by items at the start of the
|
203
|
+
pattern of the form
|
204
|
+
<pre>
|
205
|
+
(*LIMIT_MATCH=d)
|
206
|
+
(*LIMIT_RECURSION=d)
|
207
|
+
</pre>
|
208
|
+
where d is any number of decimal digits. However, the value of the setting must
|
209
|
+
be less than the value set (or defaulted) by the caller of <b>pcre_exec()</b>
|
210
|
+
for it to have any effect. In other words, the pattern writer can lower the
|
211
|
+
limits set by the programmer, but not raise them. If there is more than one
|
212
|
+
setting of one of these limits, the lower value is used.
|
213
|
+
</P>
|
214
|
+
<br><a name="SEC3" href="#TOC1">EBCDIC CHARACTER CODES</a><br>
|
215
|
+
<P>
|
216
|
+
PCRE can be compiled to run in an environment that uses EBCDIC as its character
|
217
|
+
code rather than ASCII or Unicode (typically a mainframe system). In the
|
218
|
+
sections below, character code values are ASCII or Unicode; in an EBCDIC
|
219
|
+
environment these characters may have different code values, and there are no
|
220
|
+
code points greater than 255.
|
221
|
+
</P>
|
222
|
+
<br><a name="SEC4" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br>
|
223
|
+
<P>
|
224
|
+
A regular expression is a pattern that is matched against a subject string from
|
225
|
+
left to right. Most characters stand for themselves in a pattern, and match the
|
226
|
+
corresponding characters in the subject. As a trivial example, the pattern
|
227
|
+
<pre>
|
228
|
+
The quick brown fox
|
229
|
+
</pre>
|
230
|
+
matches a portion of a subject string that is identical to itself. When
|
231
|
+
caseless matching is specified (the PCRE_CASELESS option), letters are matched
|
232
|
+
independently of case. In a UTF mode, PCRE always understands the concept of
|
233
|
+
case for characters whose values are less than 128, so caseless matching is
|
234
|
+
always possible. For characters with higher values, the concept of case is
|
235
|
+
supported if PCRE is compiled with Unicode property support, but not otherwise.
|
236
|
+
If you want to use caseless matching for characters 128 and above, you must
|
237
|
+
ensure that PCRE is compiled with Unicode property support as well as with
|
238
|
+
UTF support.
|
239
|
+
</P>
|
240
|
+
<P>
|
241
|
+
The power of regular expressions comes from the ability to include alternatives
|
242
|
+
and repetitions in the pattern. These are encoded in the pattern by the use of
|
243
|
+
<i>metacharacters</i>, which do not stand for themselves but instead are
|
244
|
+
interpreted in some special way.
|
245
|
+
</P>
|
246
|
+
<P>
|
247
|
+
There are two different sets of metacharacters: those that are recognized
|
248
|
+
anywhere in the pattern except within square brackets, and those that are
|
249
|
+
recognized within square brackets. Outside square brackets, the metacharacters
|
250
|
+
are as follows:
|
251
|
+
<pre>
|
252
|
+
\ general escape character with several uses
|
253
|
+
^ assert start of string (or line, in multiline mode)
|
254
|
+
$ assert end of string (or line, in multiline mode)
|
255
|
+
. match any character except newline (by default)
|
256
|
+
[ start character class definition
|
257
|
+
| start of alternative branch
|
258
|
+
( start subpattern
|
259
|
+
) end subpattern
|
260
|
+
? extends the meaning of (
|
261
|
+
also 0 or 1 quantifier
|
262
|
+
also quantifier minimizer
|
263
|
+
* 0 or more quantifier
|
264
|
+
+ 1 or more quantifier
|
265
|
+
also "possessive quantifier"
|
266
|
+
{ start min/max quantifier
|
267
|
+
</pre>
|
268
|
+
Part of a pattern that is in square brackets is called a "character class". In
|
269
|
+
a character class the only metacharacters are:
|
270
|
+
<pre>
|
271
|
+
\ general escape character
|
272
|
+
^ negate the class, but only if the first character
|
273
|
+
- indicates character range
|
274
|
+
[ POSIX character class (only if followed by POSIX syntax)
|
275
|
+
] terminates the character class
|
276
|
+
</pre>
|
277
|
+
The following sections describe the use of each of the metacharacters.
|
278
|
+
</P>
|
279
|
+
<br><a name="SEC5" href="#TOC1">BACKSLASH</a><br>
|
280
|
+
<P>
|
281
|
+
The backslash character has several uses. Firstly, if it is followed by a
|
282
|
+
character that is not a number or a letter, it takes away any special meaning
|
283
|
+
that character may have. This use of backslash as an escape character applies
|
284
|
+
both inside and outside character classes.
|
285
|
+
</P>
|
286
|
+
<P>
|
287
|
+
For example, if you want to match a * character, you write \* in the pattern.
|
288
|
+
This escaping action applies whether or not the following character would
|
289
|
+
otherwise be interpreted as a metacharacter, so it is always safe to precede a
|
290
|
+
non-alphanumeric with backslash to specify that it stands for itself. In
|
291
|
+
particular, if you want to match a backslash, you write \\.
|
292
|
+
</P>
|
293
|
+
<P>
|
294
|
+
In a UTF mode, only ASCII numbers and letters have any special meaning after a
|
295
|
+
backslash. All other characters (in particular, those whose codepoints are
|
296
|
+
greater than 127) are treated as literals.
|
297
|
+
</P>
|
298
|
+
<P>
|
299
|
+
If a pattern is compiled with the PCRE_EXTENDED option, most white space in the
|
300
|
+
pattern (other than in a character class), and characters between a # outside a
|
301
|
+
character class and the next newline, inclusive, are ignored. An escaping
|
302
|
+
backslash can be used to include a white space or # character as part of the
|
303
|
+
pattern.
|
304
|
+
</P>
|
305
|
+
<P>
|
306
|
+
If you want to remove the special meaning from a sequence of characters, you
|
307
|
+
can do so by putting them between \Q and \E. This is different from Perl in
|
308
|
+
that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in
|
309
|
+
Perl, $ and @ cause variable interpolation. Note the following examples:
|
310
|
+
<pre>
|
311
|
+
Pattern PCRE matches Perl matches
|
312
|
+
|
313
|
+
\Qabc$xyz\E abc$xyz abc followed by the contents of $xyz
|
314
|
+
\Qabc\$xyz\E abc\$xyz abc\$xyz
|
315
|
+
\Qabc\E\$\Qxyz\E abc$xyz abc$xyz
|
316
|
+
</pre>
|
317
|
+
The \Q...\E sequence is recognized both inside and outside character classes.
|
318
|
+
An isolated \E that is not preceded by \Q is ignored. If \Q is not followed
|
319
|
+
by \E later in the pattern, the literal interpretation continues to the end of
|
320
|
+
the pattern (that is, \E is assumed at the end). If the isolated \Q is inside
|
321
|
+
a character class, this causes an error, because the character class is not
|
322
|
+
terminated.
|
323
|
+
<a name="digitsafterbackslash"></a></P>
|
324
|
+
<br><b>
|
325
|
+
Non-printing characters
|
326
|
+
</b><br>
|
327
|
+
<P>
|
328
|
+
A second use of backslash provides a way of encoding non-printing characters
|
329
|
+
in patterns in a visible manner. There is no restriction on the appearance of
|
330
|
+
non-printing characters, apart from the binary zero that terminates a pattern,
|
331
|
+
but when a pattern is being prepared by text editing, it is often easier to use
|
332
|
+
one of the following escape sequences than the binary character it represents.
|
333
|
+
In an ASCII or Unicode environment, these escapes are as follows:
|
334
|
+
<pre>
|
335
|
+
\a alarm, that is, the BEL character (hex 07)
|
336
|
+
\cx "control-x", where x is any ASCII character
|
337
|
+
\e escape (hex 1B)
|
338
|
+
\f form feed (hex 0C)
|
339
|
+
\n linefeed (hex 0A)
|
340
|
+
\r carriage return (hex 0D)
|
341
|
+
\t tab (hex 09)
|
342
|
+
\0dd character with octal code 0dd
|
343
|
+
\ddd character with octal code ddd, or back reference
|
344
|
+
\o{ddd..} character with octal code ddd..
|
345
|
+
\xhh character with hex code hh
|
346
|
+
\x{hhh..} character with hex code hhh.. (non-JavaScript mode)
|
347
|
+
\uhhhh character with hex code hhhh (JavaScript mode only)
|
348
|
+
</pre>
|
349
|
+
The precise effect of \cx on ASCII characters is as follows: if x is a lower
|
350
|
+
case letter, it is converted to upper case. Then bit 6 of the character (hex
|
351
|
+
40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A),
|
352
|
+
but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the
|
353
|
+
data item (byte or 16-bit value) following \c has a value greater than 127, a
|
354
|
+
compile-time error occurs. This locks out non-ASCII characters in all modes.
|
355
|
+
</P>
|
356
|
+
<P>
|
357
|
+
When PCRE is compiled in EBCDIC mode, \a, \e, \f, \n, \r, and \t
|
358
|
+
generate the appropriate EBCDIC code values. The \c escape is processed
|
359
|
+
as specified for Perl in the <b>perlebcdic</b> document. The only characters
|
360
|
+
that are allowed after \c are A-Z, a-z, or one of @, [, \, ], ^, _, or ?. Any
|
361
|
+
other character provokes a compile-time error. The sequence \@ encodes
|
362
|
+
character code 0; the letters (in either case) encode characters 1-26 (hex 01
|
363
|
+
to hex 1A); [, \, ], ^, and _ encode characters 27-31 (hex 1B to hex 1F), and
|
364
|
+
\? becomes either 255 (hex FF) or 95 (hex 5F).
|
365
|
+
</P>
|
366
|
+
<P>
|
367
|
+
Thus, apart from \?, these escapes generate the same character code values as
|
368
|
+
they do in an ASCII environment, though the meanings of the values mostly
|
369
|
+
differ. For example, \G always generates code value 7, which is BEL in ASCII
|
370
|
+
but DEL in EBCDIC.
|
371
|
+
</P>
|
372
|
+
<P>
|
373
|
+
The sequence \? generates DEL (127, hex 7F) in an ASCII environment, but
|
374
|
+
because 127 is not a control character in EBCDIC, Perl makes it generate the
|
375
|
+
APC character. Unfortunately, there are several variants of EBCDIC. In most of
|
376
|
+
them the APC character has the value 255 (hex FF), but in the one Perl calls
|
377
|
+
POSIX-BC its value is 95 (hex 5F). If certain other characters have POSIX-BC
|
378
|
+
values, PCRE makes \? generate 95; otherwise it generates 255.
|
379
|
+
</P>
|
380
|
+
<P>
|
381
|
+
After \0 up to two further octal digits are read. If there are fewer than two
|
382
|
+
digits, just those that are present are used. Thus the sequence \0\x\015
|
383
|
+
specifies two binary zeros followed by a CR character (code value 13). Make
|
384
|
+
sure you supply two digits after the initial zero if the pattern character that
|
385
|
+
follows is itself an octal digit.
|
386
|
+
</P>
|
387
|
+
<P>
|
388
|
+
The escape \o must be followed by a sequence of octal digits, enclosed in
|
389
|
+
braces. An error occurs if this is not the case. This escape is a recent
|
390
|
+
addition to Perl; it provides way of specifying character code points as octal
|
391
|
+
numbers greater than 0777, and it also allows octal numbers and back references
|
392
|
+
to be unambiguously specified.
|
393
|
+
</P>
|
394
|
+
<P>
|
395
|
+
For greater clarity and unambiguity, it is best to avoid following \ by a
|
396
|
+
digit greater than zero. Instead, use \o{} or \x{} to specify character
|
397
|
+
numbers, and \g{} to specify back references. The following paragraphs
|
398
|
+
describe the old, ambiguous syntax.
|
399
|
+
</P>
|
400
|
+
<P>
|
401
|
+
The handling of a backslash followed by a digit other than 0 is complicated,
|
402
|
+
and Perl has changed in recent releases, causing PCRE also to change. Outside a
|
403
|
+
character class, PCRE reads the digit and any following digits as a decimal
|
404
|
+
number. If the number is less than 8, or if there have been at least that many
|
405
|
+
previous capturing left parentheses in the expression, the entire sequence is
|
406
|
+
taken as a <i>back reference</i>. A description of how this works is given
|
407
|
+
<a href="#backreferences">later,</a>
|
408
|
+
following the discussion of
|
409
|
+
<a href="#subpattern">parenthesized subpatterns.</a>
|
410
|
+
</P>
|
411
|
+
<P>
|
412
|
+
Inside a character class, or if the decimal number following \ is greater than
|
413
|
+
7 and there have not been that many capturing subpatterns, PCRE handles \8 and
|
414
|
+
\9 as the literal characters "8" and "9", and otherwise re-reads up to three
|
415
|
+
octal digits following the backslash, using them to generate a data character.
|
416
|
+
Any subsequent digits stand for themselves. For example:
|
417
|
+
<pre>
|
418
|
+
\040 is another way of writing an ASCII space
|
419
|
+
\40 is the same, provided there are fewer than 40 previous capturing subpatterns
|
420
|
+
\7 is always a back reference
|
421
|
+
\11 might be a back reference, or another way of writing a tab
|
422
|
+
\011 is always a tab
|
423
|
+
\0113 is a tab followed by the character "3"
|
424
|
+
\113 might be a back reference, otherwise the character with octal code 113
|
425
|
+
\377 might be a back reference, otherwise the value 255 (decimal)
|
426
|
+
\81 is either a back reference, or the two characters "8" and "1"
|
427
|
+
</pre>
|
428
|
+
Note that octal values of 100 or greater that are specified using this syntax
|
429
|
+
must not be introduced by a leading zero, because no more than three octal
|
430
|
+
digits are ever read.
|
431
|
+
</P>
|
432
|
+
<P>
|
433
|
+
By default, after \x that is not followed by {, from zero to two hexadecimal
|
434
|
+
digits are read (letters can be in upper or lower case). Any number of
|
435
|
+
hexadecimal digits may appear between \x{ and }. If a character other than
|
436
|
+
a hexadecimal digit appears between \x{ and }, or if there is no terminating
|
437
|
+
}, an error occurs.
|
438
|
+
</P>
|
439
|
+
<P>
|
440
|
+
If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x is
|
441
|
+
as just described only when it is followed by two hexadecimal digits.
|
442
|
+
Otherwise, it matches a literal "x" character. In JavaScript mode, support for
|
443
|
+
code points greater than 256 is provided by \u, which must be followed by
|
444
|
+
four hexadecimal digits; otherwise it matches a literal "u" character.
|
445
|
+
</P>
|
446
|
+
<P>
|
447
|
+
Characters whose value is less than 256 can be defined by either of the two
|
448
|
+
syntaxes for \x (or by \u in JavaScript mode). There is no difference in the
|
449
|
+
way they are handled. For example, \xdc is exactly the same as \x{dc} (or
|
450
|
+
\u00dc in JavaScript mode).
|
451
|
+
</P>
|
452
|
+
<br><b>
|
453
|
+
Constraints on character values
|
454
|
+
</b><br>
|
455
|
+
<P>
|
456
|
+
Characters that are specified using octal or hexadecimal numbers are
|
457
|
+
limited to certain values, as follows:
|
458
|
+
<pre>
|
459
|
+
8-bit non-UTF mode less than 0x100
|
460
|
+
8-bit UTF-8 mode less than 0x10ffff and a valid codepoint
|
461
|
+
16-bit non-UTF mode less than 0x10000
|
462
|
+
16-bit UTF-16 mode less than 0x10ffff and a valid codepoint
|
463
|
+
32-bit non-UTF mode less than 0x100000000
|
464
|
+
32-bit UTF-32 mode less than 0x10ffff and a valid codepoint
|
465
|
+
</pre>
|
466
|
+
Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so-called
|
467
|
+
"surrogate" codepoints), and 0xffef.
|
468
|
+
</P>
|
469
|
+
<br><b>
|
470
|
+
Escape sequences in character classes
|
471
|
+
</b><br>
|
472
|
+
<P>
|
473
|
+
All the sequences that define a single character value can be used both inside
|
474
|
+
and outside character classes. In addition, inside a character class, \b is
|
475
|
+
interpreted as the backspace character (hex 08).
|
476
|
+
</P>
|
477
|
+
<P>
|
478
|
+
\N is not allowed in a character class. \B, \R, and \X are not special
|
479
|
+
inside a character class. Like other unrecognized escape sequences, they are
|
480
|
+
treated as the literal characters "B", "R", and "X" by default, but cause an
|
481
|
+
error if the PCRE_EXTRA option is set. Outside a character class, these
|
482
|
+
sequences have different meanings.
|
483
|
+
</P>
|
484
|
+
<br><b>
|
485
|
+
Unsupported escape sequences
|
486
|
+
</b><br>
|
487
|
+
<P>
|
488
|
+
In Perl, the sequences \l, \L, \u, and \U are recognized by its string
|
489
|
+
handler and used to modify the case of following characters. By default, PCRE
|
490
|
+
does not support these escape sequences. However, if the PCRE_JAVASCRIPT_COMPAT
|
491
|
+
option is set, \U matches a "U" character, and \u can be used to define a
|
492
|
+
character by code point, as described in the previous section.
|
493
|
+
</P>
|
494
|
+
<br><b>
|
495
|
+
Absolute and relative back references
|
496
|
+
</b><br>
|
497
|
+
<P>
|
498
|
+
The sequence \g followed by an unsigned or a negative number, optionally
|
499
|
+
enclosed in braces, is an absolute or relative back reference. A named back
|
500
|
+
reference can be coded as \g{name}. Back references are discussed
|
501
|
+
<a href="#backreferences">later,</a>
|
502
|
+
following the discussion of
|
503
|
+
<a href="#subpattern">parenthesized subpatterns.</a>
|
504
|
+
</P>
|
505
|
+
<br><b>
|
506
|
+
Absolute and relative subroutine calls
|
507
|
+
</b><br>
|
508
|
+
<P>
|
509
|
+
For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
|
510
|
+
a number enclosed either in angle brackets or single quotes, is an alternative
|
511
|
+
syntax for referencing a subpattern as a "subroutine". Details are discussed
|
512
|
+
<a href="#onigurumasubroutines">later.</a>
|
513
|
+
Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i>
|
514
|
+
synonymous. The former is a back reference; the latter is a
|
515
|
+
<a href="#subpatternsassubroutines">subroutine</a>
|
516
|
+
call.
|
517
|
+
<a name="genericchartypes"></a></P>
|
518
|
+
<br><b>
|
519
|
+
Generic character types
|
520
|
+
</b><br>
|
521
|
+
<P>
|
522
|
+
Another use of backslash is for specifying generic character types:
|
523
|
+
<pre>
|
524
|
+
\d any decimal digit
|
525
|
+
\D any character that is not a decimal digit
|
526
|
+
\h any horizontal white space character
|
527
|
+
\H any character that is not a horizontal white space character
|
528
|
+
\s any white space character
|
529
|
+
\S any character that is not a white space character
|
530
|
+
\v any vertical white space character
|
531
|
+
\V any character that is not a vertical white space character
|
532
|
+
\w any "word" character
|
533
|
+
\W any "non-word" character
|
534
|
+
</pre>
|
535
|
+
There is also the single sequence \N, which matches a non-newline character.
|
536
|
+
This is the same as
|
537
|
+
<a href="#fullstopdot">the "." metacharacter</a>
|
538
|
+
when PCRE_DOTALL is not set. Perl also uses \N to match characters by name;
|
539
|
+
PCRE does not support this.
|
540
|
+
</P>
|
541
|
+
<P>
|
542
|
+
Each pair of lower and upper case escape sequences partitions the complete set
|
543
|
+
of characters into two disjoint sets. Any given character matches one, and only
|
544
|
+
one, of each pair. The sequences can appear both inside and outside character
|
545
|
+
classes. They each match one character of the appropriate type. If the current
|
546
|
+
matching point is at the end of the subject string, all of them fail, because
|
547
|
+
there is no character to match.
|
548
|
+
</P>
|
549
|
+
<P>
|
550
|
+
For compatibility with Perl, \s did not used to match the VT character (code
|
551
|
+
11), which made it different from the the POSIX "space" class. However, Perl
|
552
|
+
added VT at release 5.18, and PCRE followed suit at release 8.34. The default
|
553
|
+
\s characters are now HT (9), LF (10), VT (11), FF (12), CR (13), and space
|
554
|
+
(32), which are defined as white space in the "C" locale. This list may vary if
|
555
|
+
locale-specific matching is taking place. For example, in some locales the
|
556
|
+
"non-breaking space" character (\xA0) is recognized as white space, and in
|
557
|
+
others the VT character is not.
|
558
|
+
</P>
|
559
|
+
<P>
|
560
|
+
A "word" character is an underscore or any character that is a letter or digit.
|
561
|
+
By default, the definition of letters and digits is controlled by PCRE's
|
562
|
+
low-valued character tables, and may vary if locale-specific matching is taking
|
563
|
+
place (see
|
564
|
+
<a href="pcreapi.html#localesupport">"Locale support"</a>
|
565
|
+
in the
|
566
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
567
|
+
page). For example, in a French locale such as "fr_FR" in Unix-like systems,
|
568
|
+
or "french" in Windows, some character codes greater than 127 are used for
|
569
|
+
accented letters, and these are then matched by \w. The use of locales with
|
570
|
+
Unicode is discouraged.
|
571
|
+
</P>
|
572
|
+
<P>
|
573
|
+
By default, characters whose code points are greater than 127 never match \d,
|
574
|
+
\s, or \w, and always match \D, \S, and \W, although this may vary for
|
575
|
+
characters in the range 128-255 when locale-specific matching is happening.
|
576
|
+
These escape sequences retain their original meanings from before Unicode
|
577
|
+
support was available, mainly for efficiency reasons. If PCRE is compiled with
|
578
|
+
Unicode property support, and the PCRE_UCP option is set, the behaviour is
|
579
|
+
changed so that Unicode properties are used to determine character types, as
|
580
|
+
follows:
|
581
|
+
<pre>
|
582
|
+
\d any character that matches \p{Nd} (decimal digit)
|
583
|
+
\s any character that matches \p{Z} or \h or \v
|
584
|
+
\w any character that matches \p{L} or \p{N}, plus underscore
|
585
|
+
</pre>
|
586
|
+
The upper case escapes match the inverse sets of characters. Note that \d
|
587
|
+
matches only decimal digits, whereas \w matches any Unicode digit, as well as
|
588
|
+
any Unicode letter, and underscore. Note also that PCRE_UCP affects \b, and
|
589
|
+
\B because they are defined in terms of \w and \W. Matching these sequences
|
590
|
+
is noticeably slower when PCRE_UCP is set.
|
591
|
+
</P>
|
592
|
+
<P>
|
593
|
+
The sequences \h, \H, \v, and \V are features that were added to Perl at
|
594
|
+
release 5.10. In contrast to the other sequences, which match only ASCII
|
595
|
+
characters by default, these always match certain high-valued code points,
|
596
|
+
whether or not PCRE_UCP is set. The horizontal space characters are:
|
597
|
+
<pre>
|
598
|
+
U+0009 Horizontal tab (HT)
|
599
|
+
U+0020 Space
|
600
|
+
U+00A0 Non-break space
|
601
|
+
U+1680 Ogham space mark
|
602
|
+
U+180E Mongolian vowel separator
|
603
|
+
U+2000 En quad
|
604
|
+
U+2001 Em quad
|
605
|
+
U+2002 En space
|
606
|
+
U+2003 Em space
|
607
|
+
U+2004 Three-per-em space
|
608
|
+
U+2005 Four-per-em space
|
609
|
+
U+2006 Six-per-em space
|
610
|
+
U+2007 Figure space
|
611
|
+
U+2008 Punctuation space
|
612
|
+
U+2009 Thin space
|
613
|
+
U+200A Hair space
|
614
|
+
U+202F Narrow no-break space
|
615
|
+
U+205F Medium mathematical space
|
616
|
+
U+3000 Ideographic space
|
617
|
+
</pre>
|
618
|
+
The vertical space characters are:
|
619
|
+
<pre>
|
620
|
+
U+000A Linefeed (LF)
|
621
|
+
U+000B Vertical tab (VT)
|
622
|
+
U+000C Form feed (FF)
|
623
|
+
U+000D Carriage return (CR)
|
624
|
+
U+0085 Next line (NEL)
|
625
|
+
U+2028 Line separator
|
626
|
+
U+2029 Paragraph separator
|
627
|
+
</pre>
|
628
|
+
In 8-bit, non-UTF-8 mode, only the characters with codepoints less than 256 are
|
629
|
+
relevant.
|
630
|
+
<a name="newlineseq"></a></P>
|
631
|
+
<br><b>
|
632
|
+
Newline sequences
|
633
|
+
</b><br>
|
634
|
+
<P>
|
635
|
+
Outside a character class, by default, the escape sequence \R matches any
|
636
|
+
Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the
|
637
|
+
following:
|
638
|
+
<pre>
|
639
|
+
(?>\r\n|\n|\x0b|\f|\r|\x85)
|
640
|
+
</pre>
|
641
|
+
This is an example of an "atomic group", details of which are given
|
642
|
+
<a href="#atomicgroup">below.</a>
|
643
|
+
This particular group matches either the two-character sequence CR followed by
|
644
|
+
LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab,
|
645
|
+
U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next
|
646
|
+
line, U+0085). The two-character sequence is treated as a single unit that
|
647
|
+
cannot be split.
|
648
|
+
</P>
|
649
|
+
<P>
|
650
|
+
In other modes, two additional characters whose codepoints are greater than 255
|
651
|
+
are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029).
|
652
|
+
Unicode character property support is not needed for these characters to be
|
653
|
+
recognized.
|
654
|
+
</P>
|
655
|
+
<P>
|
656
|
+
It is possible to restrict \R to match only CR, LF, or CRLF (instead of the
|
657
|
+
complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF
|
658
|
+
either at compile time or when the pattern is matched. (BSR is an abbrevation
|
659
|
+
for "backslash R".) This can be made the default when PCRE is built; if this is
|
660
|
+
the case, the other behaviour can be requested via the PCRE_BSR_UNICODE option.
|
661
|
+
It is also possible to specify these settings by starting a pattern string with
|
662
|
+
one of the following sequences:
|
663
|
+
<pre>
|
664
|
+
(*BSR_ANYCRLF) CR, LF, or CRLF only
|
665
|
+
(*BSR_UNICODE) any Unicode newline sequence
|
666
|
+
</pre>
|
667
|
+
These override the default and the options given to the compiling function, but
|
668
|
+
they can themselves be overridden by options given to a matching function. Note
|
669
|
+
that these special settings, which are not Perl-compatible, are recognized only
|
670
|
+
at the very start of a pattern, and that they must be in upper case. If more
|
671
|
+
than one of them is present, the last one is used. They can be combined with a
|
672
|
+
change of newline convention; for example, a pattern can start with:
|
673
|
+
<pre>
|
674
|
+
(*ANY)(*BSR_ANYCRLF)
|
675
|
+
</pre>
|
676
|
+
They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or
|
677
|
+
(*UCP) special sequences. Inside a character class, \R is treated as an
|
678
|
+
unrecognized escape sequence, and so matches the letter "R" by default, but
|
679
|
+
causes an error if PCRE_EXTRA is set.
|
680
|
+
<a name="uniextseq"></a></P>
|
681
|
+
<br><b>
|
682
|
+
Unicode character properties
|
683
|
+
</b><br>
|
684
|
+
<P>
|
685
|
+
When PCRE is built with Unicode character property support, three additional
|
686
|
+
escape sequences that match characters with specific properties are available.
|
687
|
+
When in 8-bit non-UTF-8 mode, these sequences are of course limited to testing
|
688
|
+
characters whose codepoints are less than 256, but they do work in this mode.
|
689
|
+
The extra escape sequences are:
|
690
|
+
<pre>
|
691
|
+
\p{<i>xx</i>} a character with the <i>xx</i> property
|
692
|
+
\P{<i>xx</i>} a character without the <i>xx</i> property
|
693
|
+
\X a Unicode extended grapheme cluster
|
694
|
+
</pre>
|
695
|
+
The property names represented by <i>xx</i> above are limited to the Unicode
|
696
|
+
script names, the general category properties, "Any", which matches any
|
697
|
+
character (including newline), and some special PCRE properties (described
|
698
|
+
in the
|
699
|
+
<a href="#extraprops">next section).</a>
|
700
|
+
Other Perl properties such as "InMusicalSymbols" are not currently supported by
|
701
|
+
PCRE. Note that \P{Any} does not match any characters, so always causes a
|
702
|
+
match failure.
|
703
|
+
</P>
|
704
|
+
<P>
|
705
|
+
Sets of Unicode characters are defined as belonging to certain scripts. A
|
706
|
+
character from one of these sets can be matched using a script name. For
|
707
|
+
example:
|
708
|
+
<pre>
|
709
|
+
\p{Greek}
|
710
|
+
\P{Han}
|
711
|
+
</pre>
|
712
|
+
Those that are not part of an identified script are lumped together as
|
713
|
+
"Common". The current list of scripts is:
|
714
|
+
</P>
|
715
|
+
<P>
|
716
|
+
Arabic,
|
717
|
+
Armenian,
|
718
|
+
Avestan,
|
719
|
+
Balinese,
|
720
|
+
Bamum,
|
721
|
+
Bassa_Vah,
|
722
|
+
Batak,
|
723
|
+
Bengali,
|
724
|
+
Bopomofo,
|
725
|
+
Brahmi,
|
726
|
+
Braille,
|
727
|
+
Buginese,
|
728
|
+
Buhid,
|
729
|
+
Canadian_Aboriginal,
|
730
|
+
Carian,
|
731
|
+
Caucasian_Albanian,
|
732
|
+
Chakma,
|
733
|
+
Cham,
|
734
|
+
Cherokee,
|
735
|
+
Common,
|
736
|
+
Coptic,
|
737
|
+
Cuneiform,
|
738
|
+
Cypriot,
|
739
|
+
Cyrillic,
|
740
|
+
Deseret,
|
741
|
+
Devanagari,
|
742
|
+
Duployan,
|
743
|
+
Egyptian_Hieroglyphs,
|
744
|
+
Elbasan,
|
745
|
+
Ethiopic,
|
746
|
+
Georgian,
|
747
|
+
Glagolitic,
|
748
|
+
Gothic,
|
749
|
+
Grantha,
|
750
|
+
Greek,
|
751
|
+
Gujarati,
|
752
|
+
Gurmukhi,
|
753
|
+
Han,
|
754
|
+
Hangul,
|
755
|
+
Hanunoo,
|
756
|
+
Hebrew,
|
757
|
+
Hiragana,
|
758
|
+
Imperial_Aramaic,
|
759
|
+
Inherited,
|
760
|
+
Inscriptional_Pahlavi,
|
761
|
+
Inscriptional_Parthian,
|
762
|
+
Javanese,
|
763
|
+
Kaithi,
|
764
|
+
Kannada,
|
765
|
+
Katakana,
|
766
|
+
Kayah_Li,
|
767
|
+
Kharoshthi,
|
768
|
+
Khmer,
|
769
|
+
Khojki,
|
770
|
+
Khudawadi,
|
771
|
+
Lao,
|
772
|
+
Latin,
|
773
|
+
Lepcha,
|
774
|
+
Limbu,
|
775
|
+
Linear_A,
|
776
|
+
Linear_B,
|
777
|
+
Lisu,
|
778
|
+
Lycian,
|
779
|
+
Lydian,
|
780
|
+
Mahajani,
|
781
|
+
Malayalam,
|
782
|
+
Mandaic,
|
783
|
+
Manichaean,
|
784
|
+
Meetei_Mayek,
|
785
|
+
Mende_Kikakui,
|
786
|
+
Meroitic_Cursive,
|
787
|
+
Meroitic_Hieroglyphs,
|
788
|
+
Miao,
|
789
|
+
Modi,
|
790
|
+
Mongolian,
|
791
|
+
Mro,
|
792
|
+
Myanmar,
|
793
|
+
Nabataean,
|
794
|
+
New_Tai_Lue,
|
795
|
+
Nko,
|
796
|
+
Ogham,
|
797
|
+
Ol_Chiki,
|
798
|
+
Old_Italic,
|
799
|
+
Old_North_Arabian,
|
800
|
+
Old_Permic,
|
801
|
+
Old_Persian,
|
802
|
+
Old_South_Arabian,
|
803
|
+
Old_Turkic,
|
804
|
+
Oriya,
|
805
|
+
Osmanya,
|
806
|
+
Pahawh_Hmong,
|
807
|
+
Palmyrene,
|
808
|
+
Pau_Cin_Hau,
|
809
|
+
Phags_Pa,
|
810
|
+
Phoenician,
|
811
|
+
Psalter_Pahlavi,
|
812
|
+
Rejang,
|
813
|
+
Runic,
|
814
|
+
Samaritan,
|
815
|
+
Saurashtra,
|
816
|
+
Sharada,
|
817
|
+
Shavian,
|
818
|
+
Siddham,
|
819
|
+
Sinhala,
|
820
|
+
Sora_Sompeng,
|
821
|
+
Sundanese,
|
822
|
+
Syloti_Nagri,
|
823
|
+
Syriac,
|
824
|
+
Tagalog,
|
825
|
+
Tagbanwa,
|
826
|
+
Tai_Le,
|
827
|
+
Tai_Tham,
|
828
|
+
Tai_Viet,
|
829
|
+
Takri,
|
830
|
+
Tamil,
|
831
|
+
Telugu,
|
832
|
+
Thaana,
|
833
|
+
Thai,
|
834
|
+
Tibetan,
|
835
|
+
Tifinagh,
|
836
|
+
Tirhuta,
|
837
|
+
Ugaritic,
|
838
|
+
Vai,
|
839
|
+
Warang_Citi,
|
840
|
+
Yi.
|
841
|
+
</P>
|
842
|
+
<P>
|
843
|
+
Each character has exactly one Unicode general category property, specified by
|
844
|
+
a two-letter abbreviation. For compatibility with Perl, negation can be
|
845
|
+
specified by including a circumflex between the opening brace and the property
|
846
|
+
name. For example, \p{^Lu} is the same as \P{Lu}.
|
847
|
+
</P>
|
848
|
+
<P>
|
849
|
+
If only one letter is specified with \p or \P, it includes all the general
|
850
|
+
category properties that start with that letter. In this case, in the absence
|
851
|
+
of negation, the curly brackets in the escape sequence are optional; these two
|
852
|
+
examples have the same effect:
|
853
|
+
<pre>
|
854
|
+
\p{L}
|
855
|
+
\pL
|
856
|
+
</pre>
|
857
|
+
The following general category property codes are supported:
|
858
|
+
<pre>
|
859
|
+
C Other
|
860
|
+
Cc Control
|
861
|
+
Cf Format
|
862
|
+
Cn Unassigned
|
863
|
+
Co Private use
|
864
|
+
Cs Surrogate
|
865
|
+
|
866
|
+
L Letter
|
867
|
+
Ll Lower case letter
|
868
|
+
Lm Modifier letter
|
869
|
+
Lo Other letter
|
870
|
+
Lt Title case letter
|
871
|
+
Lu Upper case letter
|
872
|
+
|
873
|
+
M Mark
|
874
|
+
Mc Spacing mark
|
875
|
+
Me Enclosing mark
|
876
|
+
Mn Non-spacing mark
|
877
|
+
|
878
|
+
N Number
|
879
|
+
Nd Decimal number
|
880
|
+
Nl Letter number
|
881
|
+
No Other number
|
882
|
+
|
883
|
+
P Punctuation
|
884
|
+
Pc Connector punctuation
|
885
|
+
Pd Dash punctuation
|
886
|
+
Pe Close punctuation
|
887
|
+
Pf Final punctuation
|
888
|
+
Pi Initial punctuation
|
889
|
+
Po Other punctuation
|
890
|
+
Ps Open punctuation
|
891
|
+
|
892
|
+
S Symbol
|
893
|
+
Sc Currency symbol
|
894
|
+
Sk Modifier symbol
|
895
|
+
Sm Mathematical symbol
|
896
|
+
So Other symbol
|
897
|
+
|
898
|
+
Z Separator
|
899
|
+
Zl Line separator
|
900
|
+
Zp Paragraph separator
|
901
|
+
Zs Space separator
|
902
|
+
</pre>
|
903
|
+
The special property L& is also supported: it matches a character that has
|
904
|
+
the Lu, Ll, or Lt property, in other words, a letter that is not classified as
|
905
|
+
a modifier or "other".
|
906
|
+
</P>
|
907
|
+
<P>
|
908
|
+
The Cs (Surrogate) property applies only to characters in the range U+D800 to
|
909
|
+
U+DFFF. Such characters are not valid in Unicode strings and so
|
910
|
+
cannot be tested by PCRE, unless UTF validity checking has been turned off
|
911
|
+
(see the discussion of PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK and
|
912
|
+
PCRE_NO_UTF32_CHECK in the
|
913
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
914
|
+
page). Perl does not support the Cs property.
|
915
|
+
</P>
|
916
|
+
<P>
|
917
|
+
The long synonyms for property names that Perl supports (such as \p{Letter})
|
918
|
+
are not supported by PCRE, nor is it permitted to prefix any of these
|
919
|
+
properties with "Is".
|
920
|
+
</P>
|
921
|
+
<P>
|
922
|
+
No character that is in the Unicode table has the Cn (unassigned) property.
|
923
|
+
Instead, this property is assumed for any code point that is not in the
|
924
|
+
Unicode table.
|
925
|
+
</P>
|
926
|
+
<P>
|
927
|
+
Specifying caseless matching does not affect these escape sequences. For
|
928
|
+
example, \p{Lu} always matches only upper case letters. This is different from
|
929
|
+
the behaviour of current versions of Perl.
|
930
|
+
</P>
|
931
|
+
<P>
|
932
|
+
Matching characters by Unicode property is not fast, because PCRE has to do a
|
933
|
+
multistage table lookup in order to find a character's property. That is why
|
934
|
+
the traditional escape sequences such as \d and \w do not use Unicode
|
935
|
+
properties in PCRE by default, though you can make them do so by setting the
|
936
|
+
PCRE_UCP option or by starting the pattern with (*UCP).
|
937
|
+
</P>
|
938
|
+
<br><b>
|
939
|
+
Extended grapheme clusters
|
940
|
+
</b><br>
|
941
|
+
<P>
|
942
|
+
The \X escape matches any number of Unicode characters that form an "extended
|
943
|
+
grapheme cluster", and treats the sequence as an atomic group
|
944
|
+
<a href="#atomicgroup">(see below).</a>
|
945
|
+
Up to and including release 8.31, PCRE matched an earlier, simpler definition
|
946
|
+
that was equivalent to
|
947
|
+
<pre>
|
948
|
+
(?>\PM\pM*)
|
949
|
+
</pre>
|
950
|
+
That is, it matched a character without the "mark" property, followed by zero
|
951
|
+
or more characters with the "mark" property. Characters with the "mark"
|
952
|
+
property are typically non-spacing accents that affect the preceding character.
|
953
|
+
</P>
|
954
|
+
<P>
|
955
|
+
This simple definition was extended in Unicode to include more complicated
|
956
|
+
kinds of composite character by giving each character a grapheme breaking
|
957
|
+
property, and creating rules that use these properties to define the boundaries
|
958
|
+
of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches
|
959
|
+
one of these clusters.
|
960
|
+
</P>
|
961
|
+
<P>
|
962
|
+
\X always matches at least one character. Then it decides whether to add
|
963
|
+
additional characters according to the following rules for ending a cluster:
|
964
|
+
</P>
|
965
|
+
<P>
|
966
|
+
1. End at the end of the subject string.
|
967
|
+
</P>
|
968
|
+
<P>
|
969
|
+
2. Do not end between CR and LF; otherwise end after any control character.
|
970
|
+
</P>
|
971
|
+
<P>
|
972
|
+
3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters
|
973
|
+
are of five types: L, V, T, LV, and LVT. An L character may be followed by an
|
974
|
+
L, V, LV, or LVT character; an LV or V character may be followed by a V or T
|
975
|
+
character; an LVT or T character may be follwed only by a T character.
|
976
|
+
</P>
|
977
|
+
<P>
|
978
|
+
4. Do not end before extending characters or spacing marks. Characters with
|
979
|
+
the "mark" property always have the "extend" grapheme breaking property.
|
980
|
+
</P>
|
981
|
+
<P>
|
982
|
+
5. Do not end after prepend characters.
|
983
|
+
</P>
|
984
|
+
<P>
|
985
|
+
6. Otherwise, end the cluster.
|
986
|
+
<a name="extraprops"></a></P>
|
987
|
+
<br><b>
|
988
|
+
PCRE's additional properties
|
989
|
+
</b><br>
|
990
|
+
<P>
|
991
|
+
As well as the standard Unicode properties described above, PCRE supports four
|
992
|
+
more that make it possible to convert traditional escape sequences such as \w
|
993
|
+
and \s to use Unicode properties. PCRE uses these non-standard, non-Perl
|
994
|
+
properties internally when PCRE_UCP is set. However, they may also be used
|
995
|
+
explicitly. These properties are:
|
996
|
+
<pre>
|
997
|
+
Xan Any alphanumeric character
|
998
|
+
Xps Any POSIX space character
|
999
|
+
Xsp Any Perl space character
|
1000
|
+
Xwd Any Perl "word" character
|
1001
|
+
</pre>
|
1002
|
+
Xan matches characters that have either the L (letter) or the N (number)
|
1003
|
+
property. Xps matches the characters tab, linefeed, vertical tab, form feed, or
|
1004
|
+
carriage return, and any other character that has the Z (separator) property.
|
1005
|
+
Xsp is the same as Xps; it used to exclude vertical tab, for Perl
|
1006
|
+
compatibility, but Perl changed, and so PCRE followed at release 8.34. Xwd
|
1007
|
+
matches the same characters as Xan, plus underscore.
|
1008
|
+
</P>
|
1009
|
+
<P>
|
1010
|
+
There is another non-standard property, Xuc, which matches any character that
|
1011
|
+
can be represented by a Universal Character Name in C++ and other programming
|
1012
|
+
languages. These are the characters $, @, ` (grave accent), and all characters
|
1013
|
+
with Unicode code points greater than or equal to U+00A0, except for the
|
1014
|
+
surrogates U+D800 to U+DFFF. Note that most base (ASCII) characters are
|
1015
|
+
excluded. (Universal Character Names are of the form \uHHHH or \UHHHHHHHH
|
1016
|
+
where H is a hexadecimal digit. Note that the Xuc property does not match these
|
1017
|
+
sequences but the characters that they represent.)
|
1018
|
+
<a name="resetmatchstart"></a></P>
|
1019
|
+
<br><b>
|
1020
|
+
Resetting the match start
|
1021
|
+
</b><br>
|
1022
|
+
<P>
|
1023
|
+
The escape sequence \K causes any previously matched characters not to be
|
1024
|
+
included in the final matched sequence. For example, the pattern:
|
1025
|
+
<pre>
|
1026
|
+
foo\Kbar
|
1027
|
+
</pre>
|
1028
|
+
matches "foobar", but reports that it has matched "bar". This feature is
|
1029
|
+
similar to a lookbehind assertion
|
1030
|
+
<a href="#lookbehind">(described below).</a>
|
1031
|
+
However, in this case, the part of the subject before the real match does not
|
1032
|
+
have to be of fixed length, as lookbehind assertions do. The use of \K does
|
1033
|
+
not interfere with the setting of
|
1034
|
+
<a href="#subpattern">captured substrings.</a>
|
1035
|
+
For example, when the pattern
|
1036
|
+
<pre>
|
1037
|
+
(foo)\Kbar
|
1038
|
+
</pre>
|
1039
|
+
matches "foobar", the first substring is still set to "foo".
|
1040
|
+
</P>
|
1041
|
+
<P>
|
1042
|
+
Perl documents that the use of \K within assertions is "not well defined". In
|
1043
|
+
PCRE, \K is acted upon when it occurs inside positive assertions, but is
|
1044
|
+
ignored in negative assertions. Note that when a pattern such as (?=ab\K)
|
1045
|
+
matches, the reported start of the match can be greater than the end of the
|
1046
|
+
match.
|
1047
|
+
<a name="smallassertions"></a></P>
|
1048
|
+
<br><b>
|
1049
|
+
Simple assertions
|
1050
|
+
</b><br>
|
1051
|
+
<P>
|
1052
|
+
The final use of backslash is for certain simple assertions. An assertion
|
1053
|
+
specifies a condition that has to be met at a particular point in a match,
|
1054
|
+
without consuming any characters from the subject string. The use of
|
1055
|
+
subpatterns for more complicated assertions is described
|
1056
|
+
<a href="#bigassertions">below.</a>
|
1057
|
+
The backslashed assertions are:
|
1058
|
+
<pre>
|
1059
|
+
\b matches at a word boundary
|
1060
|
+
\B matches when not at a word boundary
|
1061
|
+
\A matches at the start of the subject
|
1062
|
+
\Z matches at the end of the subject
|
1063
|
+
also matches before a newline at the end of the subject
|
1064
|
+
\z matches only at the end of the subject
|
1065
|
+
\G matches at the first matching position in the subject
|
1066
|
+
</pre>
|
1067
|
+
Inside a character class, \b has a different meaning; it matches the backspace
|
1068
|
+
character. If any other of these assertions appears in a character class, by
|
1069
|
+
default it matches the corresponding literal character (for example, \B
|
1070
|
+
matches the letter B). However, if the PCRE_EXTRA option is set, an "invalid
|
1071
|
+
escape sequence" error is generated instead.
|
1072
|
+
</P>
|
1073
|
+
<P>
|
1074
|
+
A word boundary is a position in the subject string where the current character
|
1075
|
+
and the previous character do not both match \w or \W (i.e. one matches
|
1076
|
+
\w and the other matches \W), or the start or end of the string if the
|
1077
|
+
first or last character matches \w, respectively. In a UTF mode, the meanings
|
1078
|
+
of \w and \W can be changed by setting the PCRE_UCP option. When this is
|
1079
|
+
done, it also affects \b and \B. Neither PCRE nor Perl has a separate "start
|
1080
|
+
of word" or "end of word" metasequence. However, whatever follows \b normally
|
1081
|
+
determines which it is. For example, the fragment \ba matches "a" at the start
|
1082
|
+
of a word.
|
1083
|
+
</P>
|
1084
|
+
<P>
|
1085
|
+
The \A, \Z, and \z assertions differ from the traditional circumflex and
|
1086
|
+
dollar (described in the next section) in that they only ever match at the very
|
1087
|
+
start and end of the subject string, whatever options are set. Thus, they are
|
1088
|
+
independent of multiline mode. These three assertions are not affected by the
|
1089
|
+
PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the
|
1090
|
+
circumflex and dollar metacharacters. However, if the <i>startoffset</i>
|
1091
|
+
argument of <b>pcre_exec()</b> is non-zero, indicating that matching is to start
|
1092
|
+
at a point other than the beginning of the subject, \A can never match. The
|
1093
|
+
difference between \Z and \z is that \Z matches before a newline at the end
|
1094
|
+
of the string as well as at the very end, whereas \z matches only at the end.
|
1095
|
+
</P>
|
1096
|
+
<P>
|
1097
|
+
The \G assertion is true only when the current matching position is at the
|
1098
|
+
start point of the match, as specified by the <i>startoffset</i> argument of
|
1099
|
+
<b>pcre_exec()</b>. It differs from \A when the value of <i>startoffset</i> is
|
1100
|
+
non-zero. By calling <b>pcre_exec()</b> multiple times with appropriate
|
1101
|
+
arguments, you can mimic Perl's /g option, and it is in this kind of
|
1102
|
+
implementation where \G can be useful.
|
1103
|
+
</P>
|
1104
|
+
<P>
|
1105
|
+
Note, however, that PCRE's interpretation of \G, as the start of the current
|
1106
|
+
match, is subtly different from Perl's, which defines it as the end of the
|
1107
|
+
previous match. In Perl, these can be different when the previously matched
|
1108
|
+
string was empty. Because PCRE does just one match at a time, it cannot
|
1109
|
+
reproduce this behaviour.
|
1110
|
+
</P>
|
1111
|
+
<P>
|
1112
|
+
If all the alternatives of a pattern begin with \G, the expression is anchored
|
1113
|
+
to the starting match position, and the "anchored" flag is set in the compiled
|
1114
|
+
regular expression.
|
1115
|
+
</P>
|
1116
|
+
<br><a name="SEC6" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br>
|
1117
|
+
<P>
|
1118
|
+
The circumflex and dollar metacharacters are zero-width assertions. That is,
|
1119
|
+
they test for a particular condition being true without consuming any
|
1120
|
+
characters from the subject string.
|
1121
|
+
</P>
|
1122
|
+
<P>
|
1123
|
+
Outside a character class, in the default matching mode, the circumflex
|
1124
|
+
character is an assertion that is true only if the current matching point is at
|
1125
|
+
the start of the subject string. If the <i>startoffset</i> argument of
|
1126
|
+
<b>pcre_exec()</b> is non-zero, circumflex can never match if the PCRE_MULTILINE
|
1127
|
+
option is unset. Inside a character class, circumflex has an entirely different
|
1128
|
+
meaning
|
1129
|
+
<a href="#characterclass">(see below).</a>
|
1130
|
+
</P>
|
1131
|
+
<P>
|
1132
|
+
Circumflex need not be the first character of the pattern if a number of
|
1133
|
+
alternatives are involved, but it should be the first thing in each alternative
|
1134
|
+
in which it appears if the pattern is ever to match that branch. If all
|
1135
|
+
possible alternatives start with a circumflex, that is, if the pattern is
|
1136
|
+
constrained to match only at the start of the subject, it is said to be an
|
1137
|
+
"anchored" pattern. (There are also other constructs that can cause a pattern
|
1138
|
+
to be anchored.)
|
1139
|
+
</P>
|
1140
|
+
<P>
|
1141
|
+
The dollar character is an assertion that is true only if the current matching
|
1142
|
+
point is at the end of the subject string, or immediately before a newline at
|
1143
|
+
the end of the string (by default). Note, however, that it does not actually
|
1144
|
+
match the newline. Dollar need not be the last character of the pattern if a
|
1145
|
+
number of alternatives are involved, but it should be the last item in any
|
1146
|
+
branch in which it appears. Dollar has no special meaning in a character class.
|
1147
|
+
</P>
|
1148
|
+
<P>
|
1149
|
+
The meaning of dollar can be changed so that it matches only at the very end of
|
1150
|
+
the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This
|
1151
|
+
does not affect the \Z assertion.
|
1152
|
+
</P>
|
1153
|
+
<P>
|
1154
|
+
The meanings of the circumflex and dollar characters are changed if the
|
1155
|
+
PCRE_MULTILINE option is set. When this is the case, a circumflex matches
|
1156
|
+
immediately after internal newlines as well as at the start of the subject
|
1157
|
+
string. It does not match after a newline that ends the string. A dollar
|
1158
|
+
matches before any newlines in the string, as well as at the very end, when
|
1159
|
+
PCRE_MULTILINE is set. When newline is specified as the two-character
|
1160
|
+
sequence CRLF, isolated CR and LF characters do not indicate newlines.
|
1161
|
+
</P>
|
1162
|
+
<P>
|
1163
|
+
For example, the pattern /^abc$/ matches the subject string "def\nabc" (where
|
1164
|
+
\n represents a newline) in multiline mode, but not otherwise. Consequently,
|
1165
|
+
patterns that are anchored in single line mode because all branches start with
|
1166
|
+
^ are not anchored in multiline mode, and a match for circumflex is possible
|
1167
|
+
when the <i>startoffset</i> argument of <b>pcre_exec()</b> is non-zero. The
|
1168
|
+
PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
|
1169
|
+
</P>
|
1170
|
+
<P>
|
1171
|
+
Note that the sequences \A, \Z, and \z can be used to match the start and
|
1172
|
+
end of the subject in both modes, and if all branches of a pattern start with
|
1173
|
+
\A it is always anchored, whether or not PCRE_MULTILINE is set.
|
1174
|
+
<a name="fullstopdot"></a></P>
|
1175
|
+
<br><a name="SEC7" href="#TOC1">FULL STOP (PERIOD, DOT) AND \N</a><br>
|
1176
|
+
<P>
|
1177
|
+
Outside a character class, a dot in the pattern matches any one character in
|
1178
|
+
the subject string except (by default) a character that signifies the end of a
|
1179
|
+
line.
|
1180
|
+
</P>
|
1181
|
+
<P>
|
1182
|
+
When a line ending is defined as a single character, dot never matches that
|
1183
|
+
character; when the two-character sequence CRLF is used, dot does not match CR
|
1184
|
+
if it is immediately followed by LF, but otherwise it matches all characters
|
1185
|
+
(including isolated CRs and LFs). When any Unicode line endings are being
|
1186
|
+
recognized, dot does not match CR or LF or any of the other line ending
|
1187
|
+
characters.
|
1188
|
+
</P>
|
1189
|
+
<P>
|
1190
|
+
The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL
|
1191
|
+
option is set, a dot matches any one character, without exception. If the
|
1192
|
+
two-character sequence CRLF is present in the subject string, it takes two dots
|
1193
|
+
to match it.
|
1194
|
+
</P>
|
1195
|
+
<P>
|
1196
|
+
The handling of dot is entirely independent of the handling of circumflex and
|
1197
|
+
dollar, the only relationship being that they both involve newlines. Dot has no
|
1198
|
+
special meaning in a character class.
|
1199
|
+
</P>
|
1200
|
+
<P>
|
1201
|
+
The escape sequence \N behaves like a dot, except that it is not affected by
|
1202
|
+
the PCRE_DOTALL option. In other words, it matches any character except one
|
1203
|
+
that signifies the end of a line. Perl also uses \N to match characters by
|
1204
|
+
name; PCRE does not support this.
|
1205
|
+
</P>
|
1206
|
+
<br><a name="SEC8" href="#TOC1">MATCHING A SINGLE DATA UNIT</a><br>
|
1207
|
+
<P>
|
1208
|
+
Outside a character class, the escape sequence \C matches any one data unit,
|
1209
|
+
whether or not a UTF mode is set. In the 8-bit library, one data unit is one
|
1210
|
+
byte; in the 16-bit library it is a 16-bit unit; in the 32-bit library it is
|
1211
|
+
a 32-bit unit. Unlike a dot, \C always
|
1212
|
+
matches line-ending characters. The feature is provided in Perl in order to
|
1213
|
+
match individual bytes in UTF-8 mode, but it is unclear how it can usefully be
|
1214
|
+
used. Because \C breaks up characters into individual data units, matching one
|
1215
|
+
unit with \C in a UTF mode means that the rest of the string may start with a
|
1216
|
+
malformed UTF character. This has undefined results, because PCRE assumes that
|
1217
|
+
it is dealing with valid UTF strings (and by default it checks this at the
|
1218
|
+
start of processing unless the PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or
|
1219
|
+
PCRE_NO_UTF32_CHECK option is used).
|
1220
|
+
</P>
|
1221
|
+
<P>
|
1222
|
+
PCRE does not allow \C to appear in lookbehind assertions
|
1223
|
+
<a href="#lookbehind">(described below)</a>
|
1224
|
+
in a UTF mode, because this would make it impossible to calculate the length of
|
1225
|
+
the lookbehind.
|
1226
|
+
</P>
|
1227
|
+
<P>
|
1228
|
+
In general, the \C escape sequence is best avoided. However, one
|
1229
|
+
way of using it that avoids the problem of malformed UTF characters is to use a
|
1230
|
+
lookahead to check the length of the next character, as in this pattern, which
|
1231
|
+
could be used with a UTF-8 string (ignore white space and line breaks):
|
1232
|
+
<pre>
|
1233
|
+
(?| (?=[\x00-\x7f])(\C) |
|
1234
|
+
(?=[\x80-\x{7ff}])(\C)(\C) |
|
1235
|
+
(?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
|
1236
|
+
(?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))
|
1237
|
+
</pre>
|
1238
|
+
A group that starts with (?| resets the capturing parentheses numbers in each
|
1239
|
+
alternative (see
|
1240
|
+
<a href="#dupsubpatternnumber">"Duplicate Subpattern Numbers"</a>
|
1241
|
+
below). The assertions at the start of each branch check the next UTF-8
|
1242
|
+
character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
|
1243
|
+
character's individual bytes are then captured by the appropriate number of
|
1244
|
+
groups.
|
1245
|
+
<a name="characterclass"></a></P>
|
1246
|
+
<br><a name="SEC9" href="#TOC1">SQUARE BRACKETS AND CHARACTER CLASSES</a><br>
|
1247
|
+
<P>
|
1248
|
+
An opening square bracket introduces a character class, terminated by a closing
|
1249
|
+
square bracket. A closing square bracket on its own is not special by default.
|
1250
|
+
However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square
|
1251
|
+
bracket causes a compile-time error. If a closing square bracket is required as
|
1252
|
+
a member of the class, it should be the first data character in the class
|
1253
|
+
(after an initial circumflex, if present) or escaped with a backslash.
|
1254
|
+
</P>
|
1255
|
+
<P>
|
1256
|
+
A character class matches a single character in the subject. In a UTF mode, the
|
1257
|
+
character may be more than one data unit long. A matched character must be in
|
1258
|
+
the set of characters defined by the class, unless the first character in the
|
1259
|
+
class definition is a circumflex, in which case the subject character must not
|
1260
|
+
be in the set defined by the class. If a circumflex is actually required as a
|
1261
|
+
member of the class, ensure it is not the first character, or escape it with a
|
1262
|
+
backslash.
|
1263
|
+
</P>
|
1264
|
+
<P>
|
1265
|
+
For example, the character class [aeiou] matches any lower case vowel, while
|
1266
|
+
[^aeiou] matches any character that is not a lower case vowel. Note that a
|
1267
|
+
circumflex is just a convenient notation for specifying the characters that
|
1268
|
+
are in the class by enumerating those that are not. A class that starts with a
|
1269
|
+
circumflex is not an assertion; it still consumes a character from the subject
|
1270
|
+
string, and therefore it fails if the current pointer is at the end of the
|
1271
|
+
string.
|
1272
|
+
</P>
|
1273
|
+
<P>
|
1274
|
+
In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 (0xffff)
|
1275
|
+
can be included in a class as a literal string of data units, or by using the
|
1276
|
+
\x{ escaping mechanism.
|
1277
|
+
</P>
|
1278
|
+
<P>
|
1279
|
+
When caseless matching is set, any letters in a class represent both their
|
1280
|
+
upper case and lower case versions, so for example, a caseless [aeiou] matches
|
1281
|
+
"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a
|
1282
|
+
caseful version would. In a UTF mode, PCRE always understands the concept of
|
1283
|
+
case for characters whose values are less than 128, so caseless matching is
|
1284
|
+
always possible. For characters with higher values, the concept of case is
|
1285
|
+
supported if PCRE is compiled with Unicode property support, but not otherwise.
|
1286
|
+
If you want to use caseless matching in a UTF mode for characters 128 and
|
1287
|
+
above, you must ensure that PCRE is compiled with Unicode property support as
|
1288
|
+
well as with UTF support.
|
1289
|
+
</P>
|
1290
|
+
<P>
|
1291
|
+
Characters that might indicate line breaks are never treated in any special way
|
1292
|
+
when matching character classes, whatever line-ending sequence is in use, and
|
1293
|
+
whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class
|
1294
|
+
such as [^a] always matches one of these characters.
|
1295
|
+
</P>
|
1296
|
+
<P>
|
1297
|
+
The minus (hyphen) character can be used to specify a range of characters in a
|
1298
|
+
character class. For example, [d-m] matches any letter between d and m,
|
1299
|
+
inclusive. If a minus character is required in a class, it must be escaped with
|
1300
|
+
a backslash or appear in a position where it cannot be interpreted as
|
1301
|
+
indicating a range, typically as the first or last character in the class, or
|
1302
|
+
immediately after a range. For example, [b-d-z] matches letters in the range b
|
1303
|
+
to d, a hyphen character, or z.
|
1304
|
+
</P>
|
1305
|
+
<P>
|
1306
|
+
It is not possible to have the literal character "]" as the end character of a
|
1307
|
+
range. A pattern such as [W-]46] is interpreted as a class of two characters
|
1308
|
+
("W" and "-") followed by a literal string "46]", so it would match "W46]" or
|
1309
|
+
"-46]". However, if the "]" is escaped with a backslash it is interpreted as
|
1310
|
+
the end of range, so [W-\]46] is interpreted as a class containing a range
|
1311
|
+
followed by two other characters. The octal or hexadecimal representation of
|
1312
|
+
"]" can also be used to end a range.
|
1313
|
+
</P>
|
1314
|
+
<P>
|
1315
|
+
An error is generated if a POSIX character class (see below) or an escape
|
1316
|
+
sequence other than one that defines a single character appears at a point
|
1317
|
+
where a range ending character is expected. For example, [z-\xff] is valid,
|
1318
|
+
but [A-\d] and [A-[:digit:]] are not.
|
1319
|
+
</P>
|
1320
|
+
<P>
|
1321
|
+
Ranges operate in the collating sequence of character values. They can also be
|
1322
|
+
used for characters specified numerically, for example [\000-\037]. Ranges
|
1323
|
+
can include any characters that are valid for the current mode.
|
1324
|
+
</P>
|
1325
|
+
<P>
|
1326
|
+
If a range that includes letters is used when caseless matching is set, it
|
1327
|
+
matches the letters in either case. For example, [W-c] is equivalent to
|
1328
|
+
[][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if character
|
1329
|
+
tables for a French locale are in use, [\xc8-\xcb] matches accented E
|
1330
|
+
characters in both cases. In UTF modes, PCRE supports the concept of case for
|
1331
|
+
characters with values greater than 128 only when it is compiled with Unicode
|
1332
|
+
property support.
|
1333
|
+
</P>
|
1334
|
+
<P>
|
1335
|
+
The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v,
|
1336
|
+
\V, \w, and \W may appear in a character class, and add the characters that
|
1337
|
+
they match to the class. For example, [\dABCDEF] matches any hexadecimal
|
1338
|
+
digit. In UTF modes, the PCRE_UCP option affects the meanings of \d, \s, \w
|
1339
|
+
and their upper case partners, just as it does when they appear outside a
|
1340
|
+
character class, as described in the section entitled
|
1341
|
+
<a href="#genericchartypes">"Generic character types"</a>
|
1342
|
+
above. The escape sequence \b has a different meaning inside a character
|
1343
|
+
class; it matches the backspace character. The sequences \B, \N, \R, and \X
|
1344
|
+
are not special inside a character class. Like any other unrecognized escape
|
1345
|
+
sequences, they are treated as the literal characters "B", "N", "R", and "X" by
|
1346
|
+
default, but cause an error if the PCRE_EXTRA option is set.
|
1347
|
+
</P>
|
1348
|
+
<P>
|
1349
|
+
A circumflex can conveniently be used with the upper case character types to
|
1350
|
+
specify a more restricted set of characters than the matching lower case type.
|
1351
|
+
For example, the class [^\W_] matches any letter or digit, but not underscore,
|
1352
|
+
whereas [\w] includes underscore. A positive character class should be read as
|
1353
|
+
"something OR something OR ..." and a negative class as "NOT something AND NOT
|
1354
|
+
something AND NOT ...".
|
1355
|
+
</P>
|
1356
|
+
<P>
|
1357
|
+
The only metacharacters that are recognized in character classes are backslash,
|
1358
|
+
hyphen (only where it can be interpreted as specifying a range), circumflex
|
1359
|
+
(only at the start), opening square bracket (only when it can be interpreted as
|
1360
|
+
introducing a POSIX class name, or for a special compatibility feature - see
|
1361
|
+
the next two sections), and the terminating closing square bracket. However,
|
1362
|
+
escaping other non-alphanumeric characters does no harm.
|
1363
|
+
</P>
|
1364
|
+
<br><a name="SEC10" href="#TOC1">POSIX CHARACTER CLASSES</a><br>
|
1365
|
+
<P>
|
1366
|
+
Perl supports the POSIX notation for character classes. This uses names
|
1367
|
+
enclosed by [: and :] within the enclosing square brackets. PCRE also supports
|
1368
|
+
this notation. For example,
|
1369
|
+
<pre>
|
1370
|
+
[01[:alpha:]%]
|
1371
|
+
</pre>
|
1372
|
+
matches "0", "1", any alphabetic character, or "%". The supported class names
|
1373
|
+
are:
|
1374
|
+
<pre>
|
1375
|
+
alnum letters and digits
|
1376
|
+
alpha letters
|
1377
|
+
ascii character codes 0 - 127
|
1378
|
+
blank space or tab only
|
1379
|
+
cntrl control characters
|
1380
|
+
digit decimal digits (same as \d)
|
1381
|
+
graph printing characters, excluding space
|
1382
|
+
lower lower case letters
|
1383
|
+
print printing characters, including space
|
1384
|
+
punct printing characters, excluding letters and digits and space
|
1385
|
+
space white space (the same as \s from PCRE 8.34)
|
1386
|
+
upper upper case letters
|
1387
|
+
word "word" characters (same as \w)
|
1388
|
+
xdigit hexadecimal digits
|
1389
|
+
</pre>
|
1390
|
+
The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13),
|
1391
|
+
and space (32). If locale-specific matching is taking place, the list of space
|
1392
|
+
characters may be different; there may be fewer or more of them. "Space" used
|
1393
|
+
to be different to \s, which did not include VT, for Perl compatibility.
|
1394
|
+
However, Perl changed at release 5.18, and PCRE followed at release 8.34.
|
1395
|
+
"Space" and \s now match the same set of characters.
|
1396
|
+
</P>
|
1397
|
+
<P>
|
1398
|
+
The name "word" is a Perl extension, and "blank" is a GNU extension from Perl
|
1399
|
+
5.8. Another Perl extension is negation, which is indicated by a ^ character
|
1400
|
+
after the colon. For example,
|
1401
|
+
<pre>
|
1402
|
+
[12[:^digit:]]
|
1403
|
+
</pre>
|
1404
|
+
matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX
|
1405
|
+
syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not
|
1406
|
+
supported, and an error is given if they are encountered.
|
1407
|
+
</P>
|
1408
|
+
<P>
|
1409
|
+
By default, characters with values greater than 128 do not match any of the
|
1410
|
+
POSIX character classes. However, if the PCRE_UCP option is passed to
|
1411
|
+
<b>pcre_compile()</b>, some of the classes are changed so that Unicode character
|
1412
|
+
properties are used. This is achieved by replacing certain POSIX classes by
|
1413
|
+
other sequences, as follows:
|
1414
|
+
<pre>
|
1415
|
+
[:alnum:] becomes \p{Xan}
|
1416
|
+
[:alpha:] becomes \p{L}
|
1417
|
+
[:blank:] becomes \h
|
1418
|
+
[:digit:] becomes \p{Nd}
|
1419
|
+
[:lower:] becomes \p{Ll}
|
1420
|
+
[:space:] becomes \p{Xps}
|
1421
|
+
[:upper:] becomes \p{Lu}
|
1422
|
+
[:word:] becomes \p{Xwd}
|
1423
|
+
</pre>
|
1424
|
+
Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX
|
1425
|
+
classes are handled specially in UCP mode:
|
1426
|
+
</P>
|
1427
|
+
<P>
|
1428
|
+
[:graph:]
|
1429
|
+
This matches characters that have glyphs that mark the page when printed. In
|
1430
|
+
Unicode property terms, it matches all characters with the L, M, N, P, S, or Cf
|
1431
|
+
properties, except for:
|
1432
|
+
<pre>
|
1433
|
+
U+061C Arabic Letter Mark
|
1434
|
+
U+180E Mongolian Vowel Separator
|
1435
|
+
U+2066 - U+2069 Various "isolate"s
|
1436
|
+
|
1437
|
+
</PRE>
|
1438
|
+
</P>
|
1439
|
+
<P>
|
1440
|
+
[:print:]
|
1441
|
+
This matches the same characters as [:graph:] plus space characters that are
|
1442
|
+
not controls, that is, characters with the Zs property.
|
1443
|
+
</P>
|
1444
|
+
<P>
|
1445
|
+
[:punct:]
|
1446
|
+
This matches all characters that have the Unicode P (punctuation) property,
|
1447
|
+
plus those characters whose code points are less than 128 that have the S
|
1448
|
+
(Symbol) property.
|
1449
|
+
</P>
|
1450
|
+
<P>
|
1451
|
+
The other POSIX classes are unchanged, and match only characters with code
|
1452
|
+
points less than 128.
|
1453
|
+
</P>
|
1454
|
+
<br><a name="SEC11" href="#TOC1">COMPATIBILITY FEATURE FOR WORD BOUNDARIES</a><br>
|
1455
|
+
<P>
|
1456
|
+
In the POSIX.2 compliant library that was included in 4.4BSD Unix, the ugly
|
1457
|
+
syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of
|
1458
|
+
word". PCRE treats these items as follows:
|
1459
|
+
<pre>
|
1460
|
+
[[:<:]] is converted to \b(?=\w)
|
1461
|
+
[[:>:]] is converted to \b(?<=\w)
|
1462
|
+
</pre>
|
1463
|
+
Only these exact character sequences are recognized. A sequence such as
|
1464
|
+
[a[:<:]b] provokes error for an unrecognized POSIX class name. This support is
|
1465
|
+
not compatible with Perl. It is provided to help migrations from other
|
1466
|
+
environments, and is best not used in any new patterns. Note that \b matches
|
1467
|
+
at the start and the end of a word (see
|
1468
|
+
<a href="#smallassertions">"Simple assertions"</a>
|
1469
|
+
above), and in a Perl-style pattern the preceding or following character
|
1470
|
+
normally shows which is wanted, without the need for the assertions that are
|
1471
|
+
used above in order to give exactly the POSIX behaviour.
|
1472
|
+
</P>
|
1473
|
+
<br><a name="SEC12" href="#TOC1">VERTICAL BAR</a><br>
|
1474
|
+
<P>
|
1475
|
+
Vertical bar characters are used to separate alternative patterns. For example,
|
1476
|
+
the pattern
|
1477
|
+
<pre>
|
1478
|
+
gilbert|sullivan
|
1479
|
+
</pre>
|
1480
|
+
matches either "gilbert" or "sullivan". Any number of alternatives may appear,
|
1481
|
+
and an empty alternative is permitted (matching the empty string). The matching
|
1482
|
+
process tries each alternative in turn, from left to right, and the first one
|
1483
|
+
that succeeds is used. If the alternatives are within a subpattern
|
1484
|
+
<a href="#subpattern">(defined below),</a>
|
1485
|
+
"succeeds" means matching the rest of the main pattern as well as the
|
1486
|
+
alternative in the subpattern.
|
1487
|
+
</P>
|
1488
|
+
<br><a name="SEC13" href="#TOC1">INTERNAL OPTION SETTING</a><br>
|
1489
|
+
<P>
|
1490
|
+
The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and
|
1491
|
+
PCRE_EXTENDED options (which are Perl-compatible) can be changed from within
|
1492
|
+
the pattern by a sequence of Perl option letters enclosed between "(?" and ")".
|
1493
|
+
The option letters are
|
1494
|
+
<pre>
|
1495
|
+
i for PCRE_CASELESS
|
1496
|
+
m for PCRE_MULTILINE
|
1497
|
+
s for PCRE_DOTALL
|
1498
|
+
x for PCRE_EXTENDED
|
1499
|
+
</pre>
|
1500
|
+
For example, (?im) sets caseless, multiline matching. It is also possible to
|
1501
|
+
unset these options by preceding the letter with a hyphen, and a combined
|
1502
|
+
setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and
|
1503
|
+
PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also
|
1504
|
+
permitted. If a letter appears both before and after the hyphen, the option is
|
1505
|
+
unset.
|
1506
|
+
</P>
|
1507
|
+
<P>
|
1508
|
+
The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be
|
1509
|
+
changed in the same way as the Perl-compatible options by using the characters
|
1510
|
+
J, U and X respectively.
|
1511
|
+
</P>
|
1512
|
+
<P>
|
1513
|
+
When one of these option changes occurs at top level (that is, not inside
|
1514
|
+
subpattern parentheses), the change applies to the remainder of the pattern
|
1515
|
+
that follows. If the change is placed right at the start of a pattern, PCRE
|
1516
|
+
extracts it into the global options (and it will therefore show up in data
|
1517
|
+
extracted by the <b>pcre_fullinfo()</b> function).
|
1518
|
+
</P>
|
1519
|
+
<P>
|
1520
|
+
An option change within a subpattern (see below for a description of
|
1521
|
+
subpatterns) affects only that part of the subpattern that follows it, so
|
1522
|
+
<pre>
|
1523
|
+
(a(?i)b)c
|
1524
|
+
</pre>
|
1525
|
+
matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used).
|
1526
|
+
By this means, options can be made to have different settings in different
|
1527
|
+
parts of the pattern. Any changes made in one alternative do carry on
|
1528
|
+
into subsequent branches within the same subpattern. For example,
|
1529
|
+
<pre>
|
1530
|
+
(a(?i)b|c)
|
1531
|
+
</pre>
|
1532
|
+
matches "ab", "aB", "c", and "C", even though when matching "C" the first
|
1533
|
+
branch is abandoned before the option setting. This is because the effects of
|
1534
|
+
option settings happen at compile time. There would be some very weird
|
1535
|
+
behaviour otherwise.
|
1536
|
+
</P>
|
1537
|
+
<P>
|
1538
|
+
<b>Note:</b> There are other PCRE-specific options that can be set by the
|
1539
|
+
application when the compiling or matching functions are called. In some cases
|
1540
|
+
the pattern can contain special leading sequences such as (*CRLF) to override
|
1541
|
+
what the application has set or what has been defaulted. Details are given in
|
1542
|
+
the section entitled
|
1543
|
+
<a href="#newlineseq">"Newline sequences"</a>
|
1544
|
+
above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading
|
1545
|
+
sequences that can be used to set UTF and Unicode property modes; they are
|
1546
|
+
equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP
|
1547
|
+
options, respectively. The (*UTF) sequence is a generic version that can be
|
1548
|
+
used with any of the libraries. However, the application can set the
|
1549
|
+
PCRE_NEVER_UTF option, which locks out the use of the (*UTF) sequences.
|
1550
|
+
<a name="subpattern"></a></P>
|
1551
|
+
<br><a name="SEC14" href="#TOC1">SUBPATTERNS</a><br>
|
1552
|
+
<P>
|
1553
|
+
Subpatterns are delimited by parentheses (round brackets), which can be nested.
|
1554
|
+
Turning part of a pattern into a subpattern does two things:
|
1555
|
+
<br>
|
1556
|
+
<br>
|
1557
|
+
1. It localizes a set of alternatives. For example, the pattern
|
1558
|
+
<pre>
|
1559
|
+
cat(aract|erpillar|)
|
1560
|
+
</pre>
|
1561
|
+
matches "cataract", "caterpillar", or "cat". Without the parentheses, it would
|
1562
|
+
match "cataract", "erpillar" or an empty string.
|
1563
|
+
<br>
|
1564
|
+
<br>
|
1565
|
+
2. It sets up the subpattern as a capturing subpattern. This means that, when
|
1566
|
+
the whole pattern matches, that portion of the subject string that matched the
|
1567
|
+
subpattern is passed back to the caller via the <i>ovector</i> argument of the
|
1568
|
+
matching function. (This applies only to the traditional matching functions;
|
1569
|
+
the DFA matching functions do not support capturing.)
|
1570
|
+
</P>
|
1571
|
+
<P>
|
1572
|
+
Opening parentheses are counted from left to right (starting from 1) to obtain
|
1573
|
+
numbers for the capturing subpatterns. For example, if the string "the red
|
1574
|
+
king" is matched against the pattern
|
1575
|
+
<pre>
|
1576
|
+
the ((red|white) (king|queen))
|
1577
|
+
</pre>
|
1578
|
+
the captured substrings are "red king", "red", and "king", and are numbered 1,
|
1579
|
+
2, and 3, respectively.
|
1580
|
+
</P>
|
1581
|
+
<P>
|
1582
|
+
The fact that plain parentheses fulfil two functions is not always helpful.
|
1583
|
+
There are often times when a grouping subpattern is required without a
|
1584
|
+
capturing requirement. If an opening parenthesis is followed by a question mark
|
1585
|
+
and a colon, the subpattern does not do any capturing, and is not counted when
|
1586
|
+
computing the number of any subsequent capturing subpatterns. For example, if
|
1587
|
+
the string "the white queen" is matched against the pattern
|
1588
|
+
<pre>
|
1589
|
+
the ((?:red|white) (king|queen))
|
1590
|
+
</pre>
|
1591
|
+
the captured substrings are "white queen" and "queen", and are numbered 1 and
|
1592
|
+
2. The maximum number of capturing subpatterns is 65535.
|
1593
|
+
</P>
|
1594
|
+
<P>
|
1595
|
+
As a convenient shorthand, if any option settings are required at the start of
|
1596
|
+
a non-capturing subpattern, the option letters may appear between the "?" and
|
1597
|
+
the ":". Thus the two patterns
|
1598
|
+
<pre>
|
1599
|
+
(?i:saturday|sunday)
|
1600
|
+
(?:(?i)saturday|sunday)
|
1601
|
+
</pre>
|
1602
|
+
match exactly the same set of strings. Because alternative branches are tried
|
1603
|
+
from left to right, and options are not reset until the end of the subpattern
|
1604
|
+
is reached, an option setting in one branch does affect subsequent branches, so
|
1605
|
+
the above patterns match "SUNDAY" as well as "Saturday".
|
1606
|
+
<a name="dupsubpatternnumber"></a></P>
|
1607
|
+
<br><a name="SEC15" href="#TOC1">DUPLICATE SUBPATTERN NUMBERS</a><br>
|
1608
|
+
<P>
|
1609
|
+
Perl 5.10 introduced a feature whereby each alternative in a subpattern uses
|
1610
|
+
the same numbers for its capturing parentheses. Such a subpattern starts with
|
1611
|
+
(?| and is itself a non-capturing subpattern. For example, consider this
|
1612
|
+
pattern:
|
1613
|
+
<pre>
|
1614
|
+
(?|(Sat)ur|(Sun))day
|
1615
|
+
</pre>
|
1616
|
+
Because the two alternatives are inside a (?| group, both sets of capturing
|
1617
|
+
parentheses are numbered one. Thus, when the pattern matches, you can look
|
1618
|
+
at captured substring number one, whichever alternative matched. This construct
|
1619
|
+
is useful when you want to capture part, but not all, of one of a number of
|
1620
|
+
alternatives. Inside a (?| group, parentheses are numbered as usual, but the
|
1621
|
+
number is reset at the start of each branch. The numbers of any capturing
|
1622
|
+
parentheses that follow the subpattern start after the highest number used in
|
1623
|
+
any branch. The following example is taken from the Perl documentation. The
|
1624
|
+
numbers underneath show in which buffer the captured content will be stored.
|
1625
|
+
<pre>
|
1626
|
+
# before ---------------branch-reset----------- after
|
1627
|
+
/ ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
|
1628
|
+
# 1 2 2 3 2 3 4
|
1629
|
+
</pre>
|
1630
|
+
A back reference to a numbered subpattern uses the most recent value that is
|
1631
|
+
set for that number by any subpattern. The following pattern matches "abcabc"
|
1632
|
+
or "defdef":
|
1633
|
+
<pre>
|
1634
|
+
/(?|(abc)|(def))\1/
|
1635
|
+
</pre>
|
1636
|
+
In contrast, a subroutine call to a numbered subpattern always refers to the
|
1637
|
+
first one in the pattern with the given number. The following pattern matches
|
1638
|
+
"abcabc" or "defabc":
|
1639
|
+
<pre>
|
1640
|
+
/(?|(abc)|(def))(?1)/
|
1641
|
+
</pre>
|
1642
|
+
If a
|
1643
|
+
<a href="#conditions">condition test</a>
|
1644
|
+
for a subpattern's having matched refers to a non-unique number, the test is
|
1645
|
+
true if any of the subpatterns of that number have matched.
|
1646
|
+
</P>
|
1647
|
+
<P>
|
1648
|
+
An alternative approach to using this "branch reset" feature is to use
|
1649
|
+
duplicate named subpatterns, as described in the next section.
|
1650
|
+
</P>
|
1651
|
+
<br><a name="SEC16" href="#TOC1">NAMED SUBPATTERNS</a><br>
|
1652
|
+
<P>
|
1653
|
+
Identifying capturing parentheses by number is simple, but it can be very hard
|
1654
|
+
to keep track of the numbers in complicated regular expressions. Furthermore,
|
1655
|
+
if an expression is modified, the numbers may change. To help with this
|
1656
|
+
difficulty, PCRE supports the naming of subpatterns. This feature was not
|
1657
|
+
added to Perl until release 5.10. Python had the feature earlier, and PCRE
|
1658
|
+
introduced it at release 4.0, using the Python syntax. PCRE now supports both
|
1659
|
+
the Perl and the Python syntax. Perl allows identically numbered subpatterns to
|
1660
|
+
have different names, but PCRE does not.
|
1661
|
+
</P>
|
1662
|
+
<P>
|
1663
|
+
In PCRE, a subpattern can be named in one of three ways: (?<name>...) or
|
1664
|
+
(?'name'...) as in Perl, or (?P<name>...) as in Python. References to capturing
|
1665
|
+
parentheses from other parts of the pattern, such as
|
1666
|
+
<a href="#backreferences">back references,</a>
|
1667
|
+
<a href="#recursion">recursion,</a>
|
1668
|
+
and
|
1669
|
+
<a href="#conditions">conditions,</a>
|
1670
|
+
can be made by name as well as by number.
|
1671
|
+
</P>
|
1672
|
+
<P>
|
1673
|
+
Names consist of up to 32 alphanumeric characters and underscores, but must
|
1674
|
+
start with a non-digit. Named capturing parentheses are still allocated numbers
|
1675
|
+
as well as names, exactly as if the names were not present. The PCRE API
|
1676
|
+
provides function calls for extracting the name-to-number translation table
|
1677
|
+
from a compiled pattern. There is also a convenience function for extracting a
|
1678
|
+
captured substring by name.
|
1679
|
+
</P>
|
1680
|
+
<P>
|
1681
|
+
By default, a name must be unique within a pattern, but it is possible to relax
|
1682
|
+
this constraint by setting the PCRE_DUPNAMES option at compile time. (Duplicate
|
1683
|
+
names are also always permitted for subpatterns with the same number, set up as
|
1684
|
+
described in the previous section.) Duplicate names can be useful for patterns
|
1685
|
+
where only one instance of the named parentheses can match. Suppose you want to
|
1686
|
+
match the name of a weekday, either as a 3-letter abbreviation or as the full
|
1687
|
+
name, and in both cases you want to extract the abbreviation. This pattern
|
1688
|
+
(ignoring the line breaks) does the job:
|
1689
|
+
<pre>
|
1690
|
+
(?<DN>Mon|Fri|Sun)(?:day)?|
|
1691
|
+
(?<DN>Tue)(?:sday)?|
|
1692
|
+
(?<DN>Wed)(?:nesday)?|
|
1693
|
+
(?<DN>Thu)(?:rsday)?|
|
1694
|
+
(?<DN>Sat)(?:urday)?
|
1695
|
+
</pre>
|
1696
|
+
There are five capturing substrings, but only one is ever set after a match.
|
1697
|
+
(An alternative way of solving this problem is to use a "branch reset"
|
1698
|
+
subpattern, as described in the previous section.)
|
1699
|
+
</P>
|
1700
|
+
<P>
|
1701
|
+
The convenience function for extracting the data by name returns the substring
|
1702
|
+
for the first (and in this example, the only) subpattern of that name that
|
1703
|
+
matched. This saves searching to find which numbered subpattern it was.
|
1704
|
+
</P>
|
1705
|
+
<P>
|
1706
|
+
If you make a back reference to a non-unique named subpattern from elsewhere in
|
1707
|
+
the pattern, the subpatterns to which the name refers are checked in the order
|
1708
|
+
in which they appear in the overall pattern. The first one that is set is used
|
1709
|
+
for the reference. For example, this pattern matches both "foofoo" and
|
1710
|
+
"barbar" but not "foobar" or "barfoo":
|
1711
|
+
<pre>
|
1712
|
+
(?:(?<n>foo)|(?<n>bar))\k<n>
|
1713
|
+
|
1714
|
+
</PRE>
|
1715
|
+
</P>
|
1716
|
+
<P>
|
1717
|
+
If you make a subroutine call to a non-unique named subpattern, the one that
|
1718
|
+
corresponds to the first occurrence of the name is used. In the absence of
|
1719
|
+
duplicate numbers (see the previous section) this is the one with the lowest
|
1720
|
+
number.
|
1721
|
+
</P>
|
1722
|
+
<P>
|
1723
|
+
If you use a named reference in a condition
|
1724
|
+
test (see the
|
1725
|
+
<a href="#conditions">section about conditions</a>
|
1726
|
+
below), either to check whether a subpattern has matched, or to check for
|
1727
|
+
recursion, all subpatterns with the same name are tested. If the condition is
|
1728
|
+
true for any one of them, the overall condition is true. This is the same
|
1729
|
+
behaviour as testing by number. For further details of the interfaces for
|
1730
|
+
handling named subpatterns, see the
|
1731
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
1732
|
+
documentation.
|
1733
|
+
</P>
|
1734
|
+
<P>
|
1735
|
+
<b>Warning:</b> You cannot use different names to distinguish between two
|
1736
|
+
subpatterns with the same number because PCRE uses only the numbers when
|
1737
|
+
matching. For this reason, an error is given at compile time if different names
|
1738
|
+
are given to subpatterns with the same number. However, you can always give the
|
1739
|
+
same name to subpatterns with the same number, even when PCRE_DUPNAMES is not
|
1740
|
+
set.
|
1741
|
+
</P>
|
1742
|
+
<br><a name="SEC17" href="#TOC1">REPETITION</a><br>
|
1743
|
+
<P>
|
1744
|
+
Repetition is specified by quantifiers, which can follow any of the following
|
1745
|
+
items:
|
1746
|
+
<pre>
|
1747
|
+
a literal data character
|
1748
|
+
the dot metacharacter
|
1749
|
+
the \C escape sequence
|
1750
|
+
the \X escape sequence
|
1751
|
+
the \R escape sequence
|
1752
|
+
an escape such as \d or \pL that matches a single character
|
1753
|
+
a character class
|
1754
|
+
a back reference (see next section)
|
1755
|
+
a parenthesized subpattern (including assertions)
|
1756
|
+
a subroutine call to a subpattern (recursive or otherwise)
|
1757
|
+
</pre>
|
1758
|
+
The general repetition quantifier specifies a minimum and maximum number of
|
1759
|
+
permitted matches, by giving the two numbers in curly brackets (braces),
|
1760
|
+
separated by a comma. The numbers must be less than 65536, and the first must
|
1761
|
+
be less than or equal to the second. For example:
|
1762
|
+
<pre>
|
1763
|
+
z{2,4}
|
1764
|
+
</pre>
|
1765
|
+
matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special
|
1766
|
+
character. If the second number is omitted, but the comma is present, there is
|
1767
|
+
no upper limit; if the second number and the comma are both omitted, the
|
1768
|
+
quantifier specifies an exact number of required matches. Thus
|
1769
|
+
<pre>
|
1770
|
+
[aeiou]{3,}
|
1771
|
+
</pre>
|
1772
|
+
matches at least 3 successive vowels, but may match many more, while
|
1773
|
+
<pre>
|
1774
|
+
\d{8}
|
1775
|
+
</pre>
|
1776
|
+
matches exactly 8 digits. An opening curly bracket that appears in a position
|
1777
|
+
where a quantifier is not allowed, or one that does not match the syntax of a
|
1778
|
+
quantifier, is taken as a literal character. For example, {,6} is not a
|
1779
|
+
quantifier, but a literal string of four characters.
|
1780
|
+
</P>
|
1781
|
+
<P>
|
1782
|
+
In UTF modes, quantifiers apply to characters rather than to individual data
|
1783
|
+
units. Thus, for example, \x{100}{2} matches two characters, each of
|
1784
|
+
which is represented by a two-byte sequence in a UTF-8 string. Similarly,
|
1785
|
+
\X{3} matches three Unicode extended grapheme clusters, each of which may be
|
1786
|
+
several data units long (and they may be of different lengths).
|
1787
|
+
</P>
|
1788
|
+
<P>
|
1789
|
+
The quantifier {0} is permitted, causing the expression to behave as if the
|
1790
|
+
previous item and the quantifier were not present. This may be useful for
|
1791
|
+
subpatterns that are referenced as
|
1792
|
+
<a href="#subpatternsassubroutines">subroutines</a>
|
1793
|
+
from elsewhere in the pattern (but see also the section entitled
|
1794
|
+
<a href="#subdefine">"Defining subpatterns for use by reference only"</a>
|
1795
|
+
below). Items other than subpatterns that have a {0} quantifier are omitted
|
1796
|
+
from the compiled pattern.
|
1797
|
+
</P>
|
1798
|
+
<P>
|
1799
|
+
For convenience, the three most common quantifiers have single-character
|
1800
|
+
abbreviations:
|
1801
|
+
<pre>
|
1802
|
+
* is equivalent to {0,}
|
1803
|
+
+ is equivalent to {1,}
|
1804
|
+
? is equivalent to {0,1}
|
1805
|
+
</pre>
|
1806
|
+
It is possible to construct infinite loops by following a subpattern that can
|
1807
|
+
match no characters with a quantifier that has no upper limit, for example:
|
1808
|
+
<pre>
|
1809
|
+
(a?)*
|
1810
|
+
</pre>
|
1811
|
+
Earlier versions of Perl and PCRE used to give an error at compile time for
|
1812
|
+
such patterns. However, because there are cases where this can be useful, such
|
1813
|
+
patterns are now accepted, but if any repetition of the subpattern does in fact
|
1814
|
+
match no characters, the loop is forcibly broken.
|
1815
|
+
</P>
|
1816
|
+
<P>
|
1817
|
+
By default, the quantifiers are "greedy", that is, they match as much as
|
1818
|
+
possible (up to the maximum number of permitted times), without causing the
|
1819
|
+
rest of the pattern to fail. The classic example of where this gives problems
|
1820
|
+
is in trying to match comments in C programs. These appear between /* and */
|
1821
|
+
and within the comment, individual * and / characters may appear. An attempt to
|
1822
|
+
match C comments by applying the pattern
|
1823
|
+
<pre>
|
1824
|
+
/\*.*\*/
|
1825
|
+
</pre>
|
1826
|
+
to the string
|
1827
|
+
<pre>
|
1828
|
+
/* first comment */ not comment /* second comment */
|
1829
|
+
</pre>
|
1830
|
+
fails, because it matches the entire string owing to the greediness of the .*
|
1831
|
+
item.
|
1832
|
+
</P>
|
1833
|
+
<P>
|
1834
|
+
However, if a quantifier is followed by a question mark, it ceases to be
|
1835
|
+
greedy, and instead matches the minimum number of times possible, so the
|
1836
|
+
pattern
|
1837
|
+
<pre>
|
1838
|
+
/\*.*?\*/
|
1839
|
+
</pre>
|
1840
|
+
does the right thing with the C comments. The meaning of the various
|
1841
|
+
quantifiers is not otherwise changed, just the preferred number of matches.
|
1842
|
+
Do not confuse this use of question mark with its use as a quantifier in its
|
1843
|
+
own right. Because it has two uses, it can sometimes appear doubled, as in
|
1844
|
+
<pre>
|
1845
|
+
\d??\d
|
1846
|
+
</pre>
|
1847
|
+
which matches one digit by preference, but can match two if that is the only
|
1848
|
+
way the rest of the pattern matches.
|
1849
|
+
</P>
|
1850
|
+
<P>
|
1851
|
+
If the PCRE_UNGREEDY option is set (an option that is not available in Perl),
|
1852
|
+
the quantifiers are not greedy by default, but individual ones can be made
|
1853
|
+
greedy by following them with a question mark. In other words, it inverts the
|
1854
|
+
default behaviour.
|
1855
|
+
</P>
|
1856
|
+
<P>
|
1857
|
+
When a parenthesized subpattern is quantified with a minimum repeat count that
|
1858
|
+
is greater than 1 or with a limited maximum, more memory is required for the
|
1859
|
+
compiled pattern, in proportion to the size of the minimum or maximum.
|
1860
|
+
</P>
|
1861
|
+
<P>
|
1862
|
+
If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent
|
1863
|
+
to Perl's /s) is set, thus allowing the dot to match newlines, the pattern is
|
1864
|
+
implicitly anchored, because whatever follows will be tried against every
|
1865
|
+
character position in the subject string, so there is no point in retrying the
|
1866
|
+
overall match at any position after the first. PCRE normally treats such a
|
1867
|
+
pattern as though it were preceded by \A.
|
1868
|
+
</P>
|
1869
|
+
<P>
|
1870
|
+
In cases where it is known that the subject string contains no newlines, it is
|
1871
|
+
worth setting PCRE_DOTALL in order to obtain this optimization, or
|
1872
|
+
alternatively using ^ to indicate anchoring explicitly.
|
1873
|
+
</P>
|
1874
|
+
<P>
|
1875
|
+
However, there are some cases where the optimization cannot be used. When .*
|
1876
|
+
is inside capturing parentheses that are the subject of a back reference
|
1877
|
+
elsewhere in the pattern, a match at the start may fail where a later one
|
1878
|
+
succeeds. Consider, for example:
|
1879
|
+
<pre>
|
1880
|
+
(.*)abc\1
|
1881
|
+
</pre>
|
1882
|
+
If the subject is "xyz123abc123" the match point is the fourth character. For
|
1883
|
+
this reason, such a pattern is not implicitly anchored.
|
1884
|
+
</P>
|
1885
|
+
<P>
|
1886
|
+
Another case where implicit anchoring is not applied is when the leading .* is
|
1887
|
+
inside an atomic group. Once again, a match at the start may fail where a later
|
1888
|
+
one succeeds. Consider this pattern:
|
1889
|
+
<pre>
|
1890
|
+
(?>.*?a)b
|
1891
|
+
</pre>
|
1892
|
+
It matches "ab" in the subject "aab". The use of the backtracking control verbs
|
1893
|
+
(*PRUNE) and (*SKIP) also disable this optimization.
|
1894
|
+
</P>
|
1895
|
+
<P>
|
1896
|
+
When a capturing subpattern is repeated, the value captured is the substring
|
1897
|
+
that matched the final iteration. For example, after
|
1898
|
+
<pre>
|
1899
|
+
(tweedle[dume]{3}\s*)+
|
1900
|
+
</pre>
|
1901
|
+
has matched "tweedledum tweedledee" the value of the captured substring is
|
1902
|
+
"tweedledee". However, if there are nested capturing subpatterns, the
|
1903
|
+
corresponding captured values may have been set in previous iterations. For
|
1904
|
+
example, after
|
1905
|
+
<pre>
|
1906
|
+
/(a|(b))+/
|
1907
|
+
</pre>
|
1908
|
+
matches "aba" the value of the second captured substring is "b".
|
1909
|
+
<a name="atomicgroup"></a></P>
|
1910
|
+
<br><a name="SEC18" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br>
|
1911
|
+
<P>
|
1912
|
+
With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy")
|
1913
|
+
repetition, failure of what follows normally causes the repeated item to be
|
1914
|
+
re-evaluated to see if a different number of repeats allows the rest of the
|
1915
|
+
pattern to match. Sometimes it is useful to prevent this, either to change the
|
1916
|
+
nature of the match, or to cause it fail earlier than it otherwise might, when
|
1917
|
+
the author of the pattern knows there is no point in carrying on.
|
1918
|
+
</P>
|
1919
|
+
<P>
|
1920
|
+
Consider, for example, the pattern \d+foo when applied to the subject line
|
1921
|
+
<pre>
|
1922
|
+
123456bar
|
1923
|
+
</pre>
|
1924
|
+
After matching all 6 digits and then failing to match "foo", the normal
|
1925
|
+
action of the matcher is to try again with only 5 digits matching the \d+
|
1926
|
+
item, and then with 4, and so on, before ultimately failing. "Atomic grouping"
|
1927
|
+
(a term taken from Jeffrey Friedl's book) provides the means for specifying
|
1928
|
+
that once a subpattern has matched, it is not to be re-evaluated in this way.
|
1929
|
+
</P>
|
1930
|
+
<P>
|
1931
|
+
If we use atomic grouping for the previous example, the matcher gives up
|
1932
|
+
immediately on failing to match "foo" the first time. The notation is a kind of
|
1933
|
+
special parenthesis, starting with (?> as in this example:
|
1934
|
+
<pre>
|
1935
|
+
(?>\d+)foo
|
1936
|
+
</pre>
|
1937
|
+
This kind of parenthesis "locks up" the part of the pattern it contains once
|
1938
|
+
it has matched, and a failure further into the pattern is prevented from
|
1939
|
+
backtracking into it. Backtracking past it to previous items, however, works as
|
1940
|
+
normal.
|
1941
|
+
</P>
|
1942
|
+
<P>
|
1943
|
+
An alternative description is that a subpattern of this type matches the string
|
1944
|
+
of characters that an identical standalone pattern would match, if anchored at
|
1945
|
+
the current point in the subject string.
|
1946
|
+
</P>
|
1947
|
+
<P>
|
1948
|
+
Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as
|
1949
|
+
the above example can be thought of as a maximizing repeat that must swallow
|
1950
|
+
everything it can. So, while both \d+ and \d+? are prepared to adjust the
|
1951
|
+
number of digits they match in order to make the rest of the pattern match,
|
1952
|
+
(?>\d+) can only match an entire sequence of digits.
|
1953
|
+
</P>
|
1954
|
+
<P>
|
1955
|
+
Atomic groups in general can of course contain arbitrarily complicated
|
1956
|
+
subpatterns, and can be nested. However, when the subpattern for an atomic
|
1957
|
+
group is just a single repeated item, as in the example above, a simpler
|
1958
|
+
notation, called a "possessive quantifier" can be used. This consists of an
|
1959
|
+
additional + character following a quantifier. Using this notation, the
|
1960
|
+
previous example can be rewritten as
|
1961
|
+
<pre>
|
1962
|
+
\d++foo
|
1963
|
+
</pre>
|
1964
|
+
Note that a possessive quantifier can be used with an entire group, for
|
1965
|
+
example:
|
1966
|
+
<pre>
|
1967
|
+
(abc|xyz){2,3}+
|
1968
|
+
</pre>
|
1969
|
+
Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY
|
1970
|
+
option is ignored. They are a convenient notation for the simpler forms of
|
1971
|
+
atomic group. However, there is no difference in the meaning of a possessive
|
1972
|
+
quantifier and the equivalent atomic group, though there may be a performance
|
1973
|
+
difference; possessive quantifiers should be slightly faster.
|
1974
|
+
</P>
|
1975
|
+
<P>
|
1976
|
+
The possessive quantifier syntax is an extension to the Perl 5.8 syntax.
|
1977
|
+
Jeffrey Friedl originated the idea (and the name) in the first edition of his
|
1978
|
+
book. Mike McCloskey liked it, so implemented it when he built Sun's Java
|
1979
|
+
package, and PCRE copied it from there. It ultimately found its way into Perl
|
1980
|
+
at release 5.10.
|
1981
|
+
</P>
|
1982
|
+
<P>
|
1983
|
+
PCRE has an optimization that automatically "possessifies" certain simple
|
1984
|
+
pattern constructs. For example, the sequence A+B is treated as A++B because
|
1985
|
+
there is no point in backtracking into a sequence of A's when B must follow.
|
1986
|
+
</P>
|
1987
|
+
<P>
|
1988
|
+
When a pattern contains an unlimited repeat inside a subpattern that can itself
|
1989
|
+
be repeated an unlimited number of times, the use of an atomic group is the
|
1990
|
+
only way to avoid some failing matches taking a very long time indeed. The
|
1991
|
+
pattern
|
1992
|
+
<pre>
|
1993
|
+
(\D+|<\d+>)*[!?]
|
1994
|
+
</pre>
|
1995
|
+
matches an unlimited number of substrings that either consist of non-digits, or
|
1996
|
+
digits enclosed in <>, followed by either ! or ?. When it matches, it runs
|
1997
|
+
quickly. However, if it is applied to
|
1998
|
+
<pre>
|
1999
|
+
aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
|
2000
|
+
</pre>
|
2001
|
+
it takes a long time before reporting failure. This is because the string can
|
2002
|
+
be divided between the internal \D+ repeat and the external * repeat in a
|
2003
|
+
large number of ways, and all have to be tried. (The example uses [!?] rather
|
2004
|
+
than a single character at the end, because both PCRE and Perl have an
|
2005
|
+
optimization that allows for fast failure when a single character is used. They
|
2006
|
+
remember the last single character that is required for a match, and fail early
|
2007
|
+
if it is not present in the string.) If the pattern is changed so that it uses
|
2008
|
+
an atomic group, like this:
|
2009
|
+
<pre>
|
2010
|
+
((?>\D+)|<\d+>)*[!?]
|
2011
|
+
</pre>
|
2012
|
+
sequences of non-digits cannot be broken, and failure happens quickly.
|
2013
|
+
<a name="backreferences"></a></P>
|
2014
|
+
<br><a name="SEC19" href="#TOC1">BACK REFERENCES</a><br>
|
2015
|
+
<P>
|
2016
|
+
Outside a character class, a backslash followed by a digit greater than 0 (and
|
2017
|
+
possibly further digits) is a back reference to a capturing subpattern earlier
|
2018
|
+
(that is, to its left) in the pattern, provided there have been that many
|
2019
|
+
previous capturing left parentheses.
|
2020
|
+
</P>
|
2021
|
+
<P>
|
2022
|
+
However, if the decimal number following the backslash is less than 10, it is
|
2023
|
+
always taken as a back reference, and causes an error only if there are not
|
2024
|
+
that many capturing left parentheses in the entire pattern. In other words, the
|
2025
|
+
parentheses that are referenced need not be to the left of the reference for
|
2026
|
+
numbers less than 10. A "forward back reference" of this type can make sense
|
2027
|
+
when a repetition is involved and the subpattern to the right has participated
|
2028
|
+
in an earlier iteration.
|
2029
|
+
</P>
|
2030
|
+
<P>
|
2031
|
+
It is not possible to have a numerical "forward back reference" to a subpattern
|
2032
|
+
whose number is 10 or more using this syntax because a sequence such as \50 is
|
2033
|
+
interpreted as a character defined in octal. See the subsection entitled
|
2034
|
+
"Non-printing characters"
|
2035
|
+
<a href="#digitsafterbackslash">above</a>
|
2036
|
+
for further details of the handling of digits following a backslash. There is
|
2037
|
+
no such problem when named parentheses are used. A back reference to any
|
2038
|
+
subpattern is possible using named parentheses (see below).
|
2039
|
+
</P>
|
2040
|
+
<P>
|
2041
|
+
Another way of avoiding the ambiguity inherent in the use of digits following a
|
2042
|
+
backslash is to use the \g escape sequence. This escape must be followed by an
|
2043
|
+
unsigned number or a negative number, optionally enclosed in braces. These
|
2044
|
+
examples are all identical:
|
2045
|
+
<pre>
|
2046
|
+
(ring), \1
|
2047
|
+
(ring), \g1
|
2048
|
+
(ring), \g{1}
|
2049
|
+
</pre>
|
2050
|
+
An unsigned number specifies an absolute reference without the ambiguity that
|
2051
|
+
is present in the older syntax. It is also useful when literal digits follow
|
2052
|
+
the reference. A negative number is a relative reference. Consider this
|
2053
|
+
example:
|
2054
|
+
<pre>
|
2055
|
+
(abc(def)ghi)\g{-1}
|
2056
|
+
</pre>
|
2057
|
+
The sequence \g{-1} is a reference to the most recently started capturing
|
2058
|
+
subpattern before \g, that is, is it equivalent to \2 in this example.
|
2059
|
+
Similarly, \g{-2} would be equivalent to \1. The use of relative references
|
2060
|
+
can be helpful in long patterns, and also in patterns that are created by
|
2061
|
+
joining together fragments that contain references within themselves.
|
2062
|
+
</P>
|
2063
|
+
<P>
|
2064
|
+
A back reference matches whatever actually matched the capturing subpattern in
|
2065
|
+
the current subject string, rather than anything matching the subpattern
|
2066
|
+
itself (see
|
2067
|
+
<a href="#subpatternsassubroutines">"Subpatterns as subroutines"</a>
|
2068
|
+
below for a way of doing that). So the pattern
|
2069
|
+
<pre>
|
2070
|
+
(sens|respons)e and \1ibility
|
2071
|
+
</pre>
|
2072
|
+
matches "sense and sensibility" and "response and responsibility", but not
|
2073
|
+
"sense and responsibility". If caseful matching is in force at the time of the
|
2074
|
+
back reference, the case of letters is relevant. For example,
|
2075
|
+
<pre>
|
2076
|
+
((?i)rah)\s+\1
|
2077
|
+
</pre>
|
2078
|
+
matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
|
2079
|
+
capturing subpattern is matched caselessly.
|
2080
|
+
</P>
|
2081
|
+
<P>
|
2082
|
+
There are several different ways of writing back references to named
|
2083
|
+
subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or
|
2084
|
+
\k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified
|
2085
|
+
back reference syntax, in which \g can be used for both numeric and named
|
2086
|
+
references, is also supported. We could rewrite the above example in any of
|
2087
|
+
the following ways:
|
2088
|
+
<pre>
|
2089
|
+
(?<p1>(?i)rah)\s+\k<p1>
|
2090
|
+
(?'p1'(?i)rah)\s+\k{p1}
|
2091
|
+
(?P<p1>(?i)rah)\s+(?P=p1)
|
2092
|
+
(?<p1>(?i)rah)\s+\g{p1}
|
2093
|
+
</pre>
|
2094
|
+
A subpattern that is referenced by name may appear in the pattern before or
|
2095
|
+
after the reference.
|
2096
|
+
</P>
|
2097
|
+
<P>
|
2098
|
+
There may be more than one back reference to the same subpattern. If a
|
2099
|
+
subpattern has not actually been used in a particular match, any back
|
2100
|
+
references to it always fail by default. For example, the pattern
|
2101
|
+
<pre>
|
2102
|
+
(a|(bc))\2
|
2103
|
+
</pre>
|
2104
|
+
always fails if it starts to match "a" rather than "bc". However, if the
|
2105
|
+
PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back reference to an
|
2106
|
+
unset value matches an empty string.
|
2107
|
+
</P>
|
2108
|
+
<P>
|
2109
|
+
Because there may be many capturing parentheses in a pattern, all digits
|
2110
|
+
following a backslash are taken as part of a potential back reference number.
|
2111
|
+
If the pattern continues with a digit character, some delimiter must be used to
|
2112
|
+
terminate the back reference. If the PCRE_EXTENDED option is set, this can be
|
2113
|
+
white space. Otherwise, the \g{ syntax or an empty comment (see
|
2114
|
+
<a href="#comments">"Comments"</a>
|
2115
|
+
below) can be used.
|
2116
|
+
</P>
|
2117
|
+
<br><b>
|
2118
|
+
Recursive back references
|
2119
|
+
</b><br>
|
2120
|
+
<P>
|
2121
|
+
A back reference that occurs inside the parentheses to which it refers fails
|
2122
|
+
when the subpattern is first used, so, for example, (a\1) never matches.
|
2123
|
+
However, such references can be useful inside repeated subpatterns. For
|
2124
|
+
example, the pattern
|
2125
|
+
<pre>
|
2126
|
+
(a|b\1)+
|
2127
|
+
</pre>
|
2128
|
+
matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of
|
2129
|
+
the subpattern, the back reference matches the character string corresponding
|
2130
|
+
to the previous iteration. In order for this to work, the pattern must be such
|
2131
|
+
that the first iteration does not need to match the back reference. This can be
|
2132
|
+
done using alternation, as in the example above, or by a quantifier with a
|
2133
|
+
minimum of zero.
|
2134
|
+
</P>
|
2135
|
+
<P>
|
2136
|
+
Back references of this type cause the group that they reference to be treated
|
2137
|
+
as an
|
2138
|
+
<a href="#atomicgroup">atomic group.</a>
|
2139
|
+
Once the whole group has been matched, a subsequent matching failure cannot
|
2140
|
+
cause backtracking into the middle of the group.
|
2141
|
+
<a name="bigassertions"></a></P>
|
2142
|
+
<br><a name="SEC20" href="#TOC1">ASSERTIONS</a><br>
|
2143
|
+
<P>
|
2144
|
+
An assertion is a test on the characters following or preceding the current
|
2145
|
+
matching point that does not actually consume any characters. The simple
|
2146
|
+
assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described
|
2147
|
+
<a href="#smallassertions">above.</a>
|
2148
|
+
</P>
|
2149
|
+
<P>
|
2150
|
+
More complicated assertions are coded as subpatterns. There are two kinds:
|
2151
|
+
those that look ahead of the current position in the subject string, and those
|
2152
|
+
that look behind it. An assertion subpattern is matched in the normal way,
|
2153
|
+
except that it does not cause the current matching position to be changed.
|
2154
|
+
</P>
|
2155
|
+
<P>
|
2156
|
+
Assertion subpatterns are not capturing subpatterns. If such an assertion
|
2157
|
+
contains capturing subpatterns within it, these are counted for the purposes of
|
2158
|
+
numbering the capturing subpatterns in the whole pattern. However, substring
|
2159
|
+
capturing is carried out only for positive assertions. (Perl sometimes, but not
|
2160
|
+
always, does do capturing in negative assertions.)
|
2161
|
+
</P>
|
2162
|
+
<P>
|
2163
|
+
For compatibility with Perl, assertion subpatterns may be repeated; though
|
2164
|
+
it makes no sense to assert the same thing several times, the side effect of
|
2165
|
+
capturing parentheses may occasionally be useful. In practice, there only three
|
2166
|
+
cases:
|
2167
|
+
<br>
|
2168
|
+
<br>
|
2169
|
+
(1) If the quantifier is {0}, the assertion is never obeyed during matching.
|
2170
|
+
However, it may contain internal capturing parenthesized groups that are called
|
2171
|
+
from elsewhere via the
|
2172
|
+
<a href="#subpatternsassubroutines">subroutine mechanism.</a>
|
2173
|
+
<br>
|
2174
|
+
<br>
|
2175
|
+
(2) If quantifier is {0,n} where n is greater than zero, it is treated as if it
|
2176
|
+
were {0,1}. At run time, the rest of the pattern match is tried with and
|
2177
|
+
without the assertion, the order depending on the greediness of the quantifier.
|
2178
|
+
<br>
|
2179
|
+
<br>
|
2180
|
+
(3) If the minimum repetition is greater than zero, the quantifier is ignored.
|
2181
|
+
The assertion is obeyed just once when encountered during matching.
|
2182
|
+
</P>
|
2183
|
+
<br><b>
|
2184
|
+
Lookahead assertions
|
2185
|
+
</b><br>
|
2186
|
+
<P>
|
2187
|
+
Lookahead assertions start with (?= for positive assertions and (?! for
|
2188
|
+
negative assertions. For example,
|
2189
|
+
<pre>
|
2190
|
+
\w+(?=;)
|
2191
|
+
</pre>
|
2192
|
+
matches a word followed by a semicolon, but does not include the semicolon in
|
2193
|
+
the match, and
|
2194
|
+
<pre>
|
2195
|
+
foo(?!bar)
|
2196
|
+
</pre>
|
2197
|
+
matches any occurrence of "foo" that is not followed by "bar". Note that the
|
2198
|
+
apparently similar pattern
|
2199
|
+
<pre>
|
2200
|
+
(?!foo)bar
|
2201
|
+
</pre>
|
2202
|
+
does not find an occurrence of "bar" that is preceded by something other than
|
2203
|
+
"foo"; it finds any occurrence of "bar" whatsoever, because the assertion
|
2204
|
+
(?!foo) is always true when the next three characters are "bar". A
|
2205
|
+
lookbehind assertion is needed to achieve the other effect.
|
2206
|
+
</P>
|
2207
|
+
<P>
|
2208
|
+
If you want to force a matching failure at some point in a pattern, the most
|
2209
|
+
convenient way to do it is with (?!) because an empty string always matches, so
|
2210
|
+
an assertion that requires there not to be an empty string must always fail.
|
2211
|
+
The backtracking control verb (*FAIL) or (*F) is a synonym for (?!).
|
2212
|
+
<a name="lookbehind"></a></P>
|
2213
|
+
<br><b>
|
2214
|
+
Lookbehind assertions
|
2215
|
+
</b><br>
|
2216
|
+
<P>
|
2217
|
+
Lookbehind assertions start with (?<= for positive assertions and (?<! for
|
2218
|
+
negative assertions. For example,
|
2219
|
+
<pre>
|
2220
|
+
(?<!foo)bar
|
2221
|
+
</pre>
|
2222
|
+
does find an occurrence of "bar" that is not preceded by "foo". The contents of
|
2223
|
+
a lookbehind assertion are restricted such that all the strings it matches must
|
2224
|
+
have a fixed length. However, if there are several top-level alternatives, they
|
2225
|
+
do not all have to have the same fixed length. Thus
|
2226
|
+
<pre>
|
2227
|
+
(?<=bullock|donkey)
|
2228
|
+
</pre>
|
2229
|
+
is permitted, but
|
2230
|
+
<pre>
|
2231
|
+
(?<!dogs?|cats?)
|
2232
|
+
</pre>
|
2233
|
+
causes an error at compile time. Branches that match different length strings
|
2234
|
+
are permitted only at the top level of a lookbehind assertion. This is an
|
2235
|
+
extension compared with Perl, which requires all branches to match the same
|
2236
|
+
length of string. An assertion such as
|
2237
|
+
<pre>
|
2238
|
+
(?<=ab(c|de))
|
2239
|
+
</pre>
|
2240
|
+
is not permitted, because its single top-level branch can match two different
|
2241
|
+
lengths, but it is acceptable to PCRE if rewritten to use two top-level
|
2242
|
+
branches:
|
2243
|
+
<pre>
|
2244
|
+
(?<=abc|abde)
|
2245
|
+
</pre>
|
2246
|
+
In some cases, the escape sequence \K
|
2247
|
+
<a href="#resetmatchstart">(see above)</a>
|
2248
|
+
can be used instead of a lookbehind assertion to get round the fixed-length
|
2249
|
+
restriction.
|
2250
|
+
</P>
|
2251
|
+
<P>
|
2252
|
+
The implementation of lookbehind assertions is, for each alternative, to
|
2253
|
+
temporarily move the current position back by the fixed length and then try to
|
2254
|
+
match. If there are insufficient characters before the current position, the
|
2255
|
+
assertion fails.
|
2256
|
+
</P>
|
2257
|
+
<P>
|
2258
|
+
In a UTF mode, PCRE does not allow the \C escape (which matches a single data
|
2259
|
+
unit even in a UTF mode) to appear in lookbehind assertions, because it makes
|
2260
|
+
it impossible to calculate the length of the lookbehind. The \X and \R
|
2261
|
+
escapes, which can match different numbers of data units, are also not
|
2262
|
+
permitted.
|
2263
|
+
</P>
|
2264
|
+
<P>
|
2265
|
+
<a href="#subpatternsassubroutines">"Subroutine"</a>
|
2266
|
+
calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
|
2267
|
+
as the subpattern matches a fixed-length string.
|
2268
|
+
<a href="#recursion">Recursion,</a>
|
2269
|
+
however, is not supported.
|
2270
|
+
</P>
|
2271
|
+
<P>
|
2272
|
+
Possessive quantifiers can be used in conjunction with lookbehind assertions to
|
2273
|
+
specify efficient matching of fixed-length strings at the end of subject
|
2274
|
+
strings. Consider a simple pattern such as
|
2275
|
+
<pre>
|
2276
|
+
abcd$
|
2277
|
+
</pre>
|
2278
|
+
when applied to a long string that does not match. Because matching proceeds
|
2279
|
+
from left to right, PCRE will look for each "a" in the subject and then see if
|
2280
|
+
what follows matches the rest of the pattern. If the pattern is specified as
|
2281
|
+
<pre>
|
2282
|
+
^.*abcd$
|
2283
|
+
</pre>
|
2284
|
+
the initial .* matches the entire string at first, but when this fails (because
|
2285
|
+
there is no following "a"), it backtracks to match all but the last character,
|
2286
|
+
then all but the last two characters, and so on. Once again the search for "a"
|
2287
|
+
covers the entire string, from right to left, so we are no better off. However,
|
2288
|
+
if the pattern is written as
|
2289
|
+
<pre>
|
2290
|
+
^.*+(?<=abcd)
|
2291
|
+
</pre>
|
2292
|
+
there can be no backtracking for the .*+ item; it can match only the entire
|
2293
|
+
string. The subsequent lookbehind assertion does a single test on the last four
|
2294
|
+
characters. If it fails, the match fails immediately. For long strings, this
|
2295
|
+
approach makes a significant difference to the processing time.
|
2296
|
+
</P>
|
2297
|
+
<br><b>
|
2298
|
+
Using multiple assertions
|
2299
|
+
</b><br>
|
2300
|
+
<P>
|
2301
|
+
Several assertions (of any sort) may occur in succession. For example,
|
2302
|
+
<pre>
|
2303
|
+
(?<=\d{3})(?<!999)foo
|
2304
|
+
</pre>
|
2305
|
+
matches "foo" preceded by three digits that are not "999". Notice that each of
|
2306
|
+
the assertions is applied independently at the same point in the subject
|
2307
|
+
string. First there is a check that the previous three characters are all
|
2308
|
+
digits, and then there is a check that the same three characters are not "999".
|
2309
|
+
This pattern does <i>not</i> match "foo" preceded by six characters, the first
|
2310
|
+
of which are digits and the last three of which are not "999". For example, it
|
2311
|
+
doesn't match "123abcfoo". A pattern to do that is
|
2312
|
+
<pre>
|
2313
|
+
(?<=\d{3}...)(?<!999)foo
|
2314
|
+
</pre>
|
2315
|
+
This time the first assertion looks at the preceding six characters, checking
|
2316
|
+
that the first three are digits, and then the second assertion checks that the
|
2317
|
+
preceding three characters are not "999".
|
2318
|
+
</P>
|
2319
|
+
<P>
|
2320
|
+
Assertions can be nested in any combination. For example,
|
2321
|
+
<pre>
|
2322
|
+
(?<=(?<!foo)bar)baz
|
2323
|
+
</pre>
|
2324
|
+
matches an occurrence of "baz" that is preceded by "bar" which in turn is not
|
2325
|
+
preceded by "foo", while
|
2326
|
+
<pre>
|
2327
|
+
(?<=\d{3}(?!999)...)foo
|
2328
|
+
</pre>
|
2329
|
+
is another pattern that matches "foo" preceded by three digits and any three
|
2330
|
+
characters that are not "999".
|
2331
|
+
<a name="conditions"></a></P>
|
2332
|
+
<br><a name="SEC21" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br>
|
2333
|
+
<P>
|
2334
|
+
It is possible to cause the matching process to obey a subpattern
|
2335
|
+
conditionally or to choose between two alternative subpatterns, depending on
|
2336
|
+
the result of an assertion, or whether a specific capturing subpattern has
|
2337
|
+
already been matched. The two possible forms of conditional subpattern are:
|
2338
|
+
<pre>
|
2339
|
+
(?(condition)yes-pattern)
|
2340
|
+
(?(condition)yes-pattern|no-pattern)
|
2341
|
+
</pre>
|
2342
|
+
If the condition is satisfied, the yes-pattern is used; otherwise the
|
2343
|
+
no-pattern (if present) is used. If there are more than two alternatives in the
|
2344
|
+
subpattern, a compile-time error occurs. Each of the two alternatives may
|
2345
|
+
itself contain nested subpatterns of any form, including conditional
|
2346
|
+
subpatterns; the restriction to two alternatives applies only at the level of
|
2347
|
+
the condition. This pattern fragment is an example where the alternatives are
|
2348
|
+
complex:
|
2349
|
+
<pre>
|
2350
|
+
(?(1) (A|B|C) | (D | (?(2)E|F) | E) )
|
2351
|
+
|
2352
|
+
</PRE>
|
2353
|
+
</P>
|
2354
|
+
<P>
|
2355
|
+
There are four kinds of condition: references to subpatterns, references to
|
2356
|
+
recursion, a pseudo-condition called DEFINE, and assertions.
|
2357
|
+
</P>
|
2358
|
+
<br><b>
|
2359
|
+
Checking for a used subpattern by number
|
2360
|
+
</b><br>
|
2361
|
+
<P>
|
2362
|
+
If the text between the parentheses consists of a sequence of digits, the
|
2363
|
+
condition is true if a capturing subpattern of that number has previously
|
2364
|
+
matched. If there is more than one capturing subpattern with the same number
|
2365
|
+
(see the earlier
|
2366
|
+
<a href="#recursion">section about duplicate subpattern numbers),</a>
|
2367
|
+
the condition is true if any of them have matched. An alternative notation is
|
2368
|
+
to precede the digits with a plus or minus sign. In this case, the subpattern
|
2369
|
+
number is relative rather than absolute. The most recently opened parentheses
|
2370
|
+
can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside
|
2371
|
+
loops it can also make sense to refer to subsequent groups. The next
|
2372
|
+
parentheses to be opened can be referenced as (?(+1), and so on. (The value
|
2373
|
+
zero in any of these forms is not used; it provokes a compile-time error.)
|
2374
|
+
</P>
|
2375
|
+
<P>
|
2376
|
+
Consider the following pattern, which contains non-significant white space to
|
2377
|
+
make it more readable (assume the PCRE_EXTENDED option) and to divide it into
|
2378
|
+
three parts for ease of discussion:
|
2379
|
+
<pre>
|
2380
|
+
( \( )? [^()]+ (?(1) \) )
|
2381
|
+
</pre>
|
2382
|
+
The first part matches an optional opening parenthesis, and if that
|
2383
|
+
character is present, sets it as the first captured substring. The second part
|
2384
|
+
matches one or more characters that are not parentheses. The third part is a
|
2385
|
+
conditional subpattern that tests whether or not the first set of parentheses
|
2386
|
+
matched. If they did, that is, if subject started with an opening parenthesis,
|
2387
|
+
the condition is true, and so the yes-pattern is executed and a closing
|
2388
|
+
parenthesis is required. Otherwise, since no-pattern is not present, the
|
2389
|
+
subpattern matches nothing. In other words, this pattern matches a sequence of
|
2390
|
+
non-parentheses, optionally enclosed in parentheses.
|
2391
|
+
</P>
|
2392
|
+
<P>
|
2393
|
+
If you were embedding this pattern in a larger one, you could use a relative
|
2394
|
+
reference:
|
2395
|
+
<pre>
|
2396
|
+
...other stuff... ( \( )? [^()]+ (?(-1) \) ) ...
|
2397
|
+
</pre>
|
2398
|
+
This makes the fragment independent of the parentheses in the larger pattern.
|
2399
|
+
</P>
|
2400
|
+
<br><b>
|
2401
|
+
Checking for a used subpattern by name
|
2402
|
+
</b><br>
|
2403
|
+
<P>
|
2404
|
+
Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a used
|
2405
|
+
subpattern by name. For compatibility with earlier versions of PCRE, which had
|
2406
|
+
this facility before Perl, the syntax (?(name)...) is also recognized.
|
2407
|
+
</P>
|
2408
|
+
<P>
|
2409
|
+
Rewriting the above example to use a named subpattern gives this:
|
2410
|
+
<pre>
|
2411
|
+
(?<OPEN> \( )? [^()]+ (?(<OPEN>) \) )
|
2412
|
+
</pre>
|
2413
|
+
If the name used in a condition of this kind is a duplicate, the test is
|
2414
|
+
applied to all subpatterns of the same name, and is true if any one of them has
|
2415
|
+
matched.
|
2416
|
+
</P>
|
2417
|
+
<br><b>
|
2418
|
+
Checking for pattern recursion
|
2419
|
+
</b><br>
|
2420
|
+
<P>
|
2421
|
+
If the condition is the string (R), and there is no subpattern with the name R,
|
2422
|
+
the condition is true if a recursive call to the whole pattern or any
|
2423
|
+
subpattern has been made. If digits or a name preceded by ampersand follow the
|
2424
|
+
letter R, for example:
|
2425
|
+
<pre>
|
2426
|
+
(?(R3)...) or (?(R&name)...)
|
2427
|
+
</pre>
|
2428
|
+
the condition is true if the most recent recursion is into a subpattern whose
|
2429
|
+
number or name is given. This condition does not check the entire recursion
|
2430
|
+
stack. If the name used in a condition of this kind is a duplicate, the test is
|
2431
|
+
applied to all subpatterns of the same name, and is true if any one of them is
|
2432
|
+
the most recent recursion.
|
2433
|
+
</P>
|
2434
|
+
<P>
|
2435
|
+
At "top level", all these recursion test conditions are false.
|
2436
|
+
<a href="#recursion">The syntax for recursive patterns</a>
|
2437
|
+
is described below.
|
2438
|
+
<a name="subdefine"></a></P>
|
2439
|
+
<br><b>
|
2440
|
+
Defining subpatterns for use by reference only
|
2441
|
+
</b><br>
|
2442
|
+
<P>
|
2443
|
+
If the condition is the string (DEFINE), and there is no subpattern with the
|
2444
|
+
name DEFINE, the condition is always false. In this case, there may be only one
|
2445
|
+
alternative in the subpattern. It is always skipped if control reaches this
|
2446
|
+
point in the pattern; the idea of DEFINE is that it can be used to define
|
2447
|
+
subroutines that can be referenced from elsewhere. (The use of
|
2448
|
+
<a href="#subpatternsassubroutines">subroutines</a>
|
2449
|
+
is described below.) For example, a pattern to match an IPv4 address such as
|
2450
|
+
"192.168.23.245" could be written like this (ignore white space and line
|
2451
|
+
breaks):
|
2452
|
+
<pre>
|
2453
|
+
(?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
|
2454
|
+
\b (?&byte) (\.(?&byte)){3} \b
|
2455
|
+
</pre>
|
2456
|
+
The first part of the pattern is a DEFINE group inside which a another group
|
2457
|
+
named "byte" is defined. This matches an individual component of an IPv4
|
2458
|
+
address (a number less than 256). When matching takes place, this part of the
|
2459
|
+
pattern is skipped because DEFINE acts like a false condition. The rest of the
|
2460
|
+
pattern uses references to the named group to match the four dot-separated
|
2461
|
+
components of an IPv4 address, insisting on a word boundary at each end.
|
2462
|
+
</P>
|
2463
|
+
<br><b>
|
2464
|
+
Assertion conditions
|
2465
|
+
</b><br>
|
2466
|
+
<P>
|
2467
|
+
If the condition is not in any of the above formats, it must be an assertion.
|
2468
|
+
This may be a positive or negative lookahead or lookbehind assertion. Consider
|
2469
|
+
this pattern, again containing non-significant white space, and with the two
|
2470
|
+
alternatives on the second line:
|
2471
|
+
<pre>
|
2472
|
+
(?(?=[^a-z]*[a-z])
|
2473
|
+
\d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} )
|
2474
|
+
</pre>
|
2475
|
+
The condition is a positive lookahead assertion that matches an optional
|
2476
|
+
sequence of non-letters followed by a letter. In other words, it tests for the
|
2477
|
+
presence of at least one letter in the subject. If a letter is found, the
|
2478
|
+
subject is matched against the first alternative; otherwise it is matched
|
2479
|
+
against the second. This pattern matches strings in one of the two forms
|
2480
|
+
dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits.
|
2481
|
+
<a name="comments"></a></P>
|
2482
|
+
<br><a name="SEC22" href="#TOC1">COMMENTS</a><br>
|
2483
|
+
<P>
|
2484
|
+
There are two ways of including comments in patterns that are processed by
|
2485
|
+
PCRE. In both cases, the start of the comment must not be in a character class,
|
2486
|
+
nor in the middle of any other sequence of related characters such as (?: or a
|
2487
|
+
subpattern name or number. The characters that make up a comment play no part
|
2488
|
+
in the pattern matching.
|
2489
|
+
</P>
|
2490
|
+
<P>
|
2491
|
+
The sequence (?# marks the start of a comment that continues up to the next
|
2492
|
+
closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED
|
2493
|
+
option is set, an unescaped # character also introduces a comment, which in
|
2494
|
+
this case continues to immediately after the next newline character or
|
2495
|
+
character sequence in the pattern. Which characters are interpreted as newlines
|
2496
|
+
is controlled by the options passed to a compiling function or by a special
|
2497
|
+
sequence at the start of the pattern, as described in the section entitled
|
2498
|
+
<a href="#newlines">"Newline conventions"</a>
|
2499
|
+
above. Note that the end of this type of comment is a literal newline sequence
|
2500
|
+
in the pattern; escape sequences that happen to represent a newline do not
|
2501
|
+
count. For example, consider this pattern when PCRE_EXTENDED is set, and the
|
2502
|
+
default newline convention is in force:
|
2503
|
+
<pre>
|
2504
|
+
abc #comment \n still comment
|
2505
|
+
</pre>
|
2506
|
+
On encountering the # character, <b>pcre_compile()</b> skips along, looking for
|
2507
|
+
a newline in the pattern. The sequence \n is still literal at this stage, so
|
2508
|
+
it does not terminate the comment. Only an actual character with the code value
|
2509
|
+
0x0a (the default newline) does so.
|
2510
|
+
<a name="recursion"></a></P>
|
2511
|
+
<br><a name="SEC23" href="#TOC1">RECURSIVE PATTERNS</a><br>
|
2512
|
+
<P>
|
2513
|
+
Consider the problem of matching a string in parentheses, allowing for
|
2514
|
+
unlimited nested parentheses. Without the use of recursion, the best that can
|
2515
|
+
be done is to use a pattern that matches up to some fixed depth of nesting. It
|
2516
|
+
is not possible to handle an arbitrary nesting depth.
|
2517
|
+
</P>
|
2518
|
+
<P>
|
2519
|
+
For some time, Perl has provided a facility that allows regular expressions to
|
2520
|
+
recurse (amongst other things). It does this by interpolating Perl code in the
|
2521
|
+
expression at run time, and the code can refer to the expression itself. A Perl
|
2522
|
+
pattern using code interpolation to solve the parentheses problem can be
|
2523
|
+
created like this:
|
2524
|
+
<pre>
|
2525
|
+
$re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
|
2526
|
+
</pre>
|
2527
|
+
The (?p{...}) item interpolates Perl code at run time, and in this case refers
|
2528
|
+
recursively to the pattern in which it appears.
|
2529
|
+
</P>
|
2530
|
+
<P>
|
2531
|
+
Obviously, PCRE cannot support the interpolation of Perl code. Instead, it
|
2532
|
+
supports special syntax for recursion of the entire pattern, and also for
|
2533
|
+
individual subpattern recursion. After its introduction in PCRE and Python,
|
2534
|
+
this kind of recursion was subsequently introduced into Perl at release 5.10.
|
2535
|
+
</P>
|
2536
|
+
<P>
|
2537
|
+
A special item that consists of (? followed by a number greater than zero and a
|
2538
|
+
closing parenthesis is a recursive subroutine call of the subpattern of the
|
2539
|
+
given number, provided that it occurs inside that subpattern. (If not, it is a
|
2540
|
+
<a href="#subpatternsassubroutines">non-recursive subroutine</a>
|
2541
|
+
call, which is described in the next section.) The special item (?R) or (?0) is
|
2542
|
+
a recursive call of the entire regular expression.
|
2543
|
+
</P>
|
2544
|
+
<P>
|
2545
|
+
This PCRE pattern solves the nested parentheses problem (assume the
|
2546
|
+
PCRE_EXTENDED option is set so that white space is ignored):
|
2547
|
+
<pre>
|
2548
|
+
\( ( [^()]++ | (?R) )* \)
|
2549
|
+
</pre>
|
2550
|
+
First it matches an opening parenthesis. Then it matches any number of
|
2551
|
+
substrings which can either be a sequence of non-parentheses, or a recursive
|
2552
|
+
match of the pattern itself (that is, a correctly parenthesized substring).
|
2553
|
+
Finally there is a closing parenthesis. Note the use of a possessive quantifier
|
2554
|
+
to avoid backtracking into sequences of non-parentheses.
|
2555
|
+
</P>
|
2556
|
+
<P>
|
2557
|
+
If this were part of a larger pattern, you would not want to recurse the entire
|
2558
|
+
pattern, so instead you could use this:
|
2559
|
+
<pre>
|
2560
|
+
( \( ( [^()]++ | (?1) )* \) )
|
2561
|
+
</pre>
|
2562
|
+
We have put the pattern into parentheses, and caused the recursion to refer to
|
2563
|
+
them instead of the whole pattern.
|
2564
|
+
</P>
|
2565
|
+
<P>
|
2566
|
+
In a larger pattern, keeping track of parenthesis numbers can be tricky. This
|
2567
|
+
is made easier by the use of relative references. Instead of (?1) in the
|
2568
|
+
pattern above you can write (?-2) to refer to the second most recently opened
|
2569
|
+
parentheses preceding the recursion. In other words, a negative number counts
|
2570
|
+
capturing parentheses leftwards from the point at which it is encountered.
|
2571
|
+
</P>
|
2572
|
+
<P>
|
2573
|
+
It is also possible to refer to subsequently opened parentheses, by writing
|
2574
|
+
references such as (?+2). However, these cannot be recursive because the
|
2575
|
+
reference is not inside the parentheses that are referenced. They are always
|
2576
|
+
<a href="#subpatternsassubroutines">non-recursive subroutine</a>
|
2577
|
+
calls, as described in the next section.
|
2578
|
+
</P>
|
2579
|
+
<P>
|
2580
|
+
An alternative approach is to use named parentheses instead. The Perl syntax
|
2581
|
+
for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We
|
2582
|
+
could rewrite the above example as follows:
|
2583
|
+
<pre>
|
2584
|
+
(?<pn> \( ( [^()]++ | (?&pn) )* \) )
|
2585
|
+
</pre>
|
2586
|
+
If there is more than one subpattern with the same name, the earliest one is
|
2587
|
+
used.
|
2588
|
+
</P>
|
2589
|
+
<P>
|
2590
|
+
This particular example pattern that we have been looking at contains nested
|
2591
|
+
unlimited repeats, and so the use of a possessive quantifier for matching
|
2592
|
+
strings of non-parentheses is important when applying the pattern to strings
|
2593
|
+
that do not match. For example, when this pattern is applied to
|
2594
|
+
<pre>
|
2595
|
+
(aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
|
2596
|
+
</pre>
|
2597
|
+
it yields "no match" quickly. However, if a possessive quantifier is not used,
|
2598
|
+
the match runs for a very long time indeed because there are so many different
|
2599
|
+
ways the + and * repeats can carve up the subject, and all have to be tested
|
2600
|
+
before failure can be reported.
|
2601
|
+
</P>
|
2602
|
+
<P>
|
2603
|
+
At the end of a match, the values of capturing parentheses are those from
|
2604
|
+
the outermost level. If you want to obtain intermediate values, a callout
|
2605
|
+
function can be used (see below and the
|
2606
|
+
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
2607
|
+
documentation). If the pattern above is matched against
|
2608
|
+
<pre>
|
2609
|
+
(ab(cd)ef)
|
2610
|
+
</pre>
|
2611
|
+
the value for the inner capturing parentheses (numbered 2) is "ef", which is
|
2612
|
+
the last value taken on at the top level. If a capturing subpattern is not
|
2613
|
+
matched at the top level, its final captured value is unset, even if it was
|
2614
|
+
(temporarily) set at a deeper level during the matching process.
|
2615
|
+
</P>
|
2616
|
+
<P>
|
2617
|
+
If there are more than 15 capturing parentheses in a pattern, PCRE has to
|
2618
|
+
obtain extra memory to store data during a recursion, which it does by using
|
2619
|
+
<b>pcre_malloc</b>, freeing it via <b>pcre_free</b> afterwards. If no memory can
|
2620
|
+
be obtained, the match fails with the PCRE_ERROR_NOMEMORY error.
|
2621
|
+
</P>
|
2622
|
+
<P>
|
2623
|
+
Do not confuse the (?R) item with the condition (R), which tests for recursion.
|
2624
|
+
Consider this pattern, which matches text in angle brackets, allowing for
|
2625
|
+
arbitrary nesting. Only digits are allowed in nested brackets (that is, when
|
2626
|
+
recursing), whereas any characters are permitted at the outer level.
|
2627
|
+
<pre>
|
2628
|
+
< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >
|
2629
|
+
</pre>
|
2630
|
+
In this pattern, (?(R) is the start of a conditional subpattern, with two
|
2631
|
+
different alternatives for the recursive and non-recursive cases. The (?R) item
|
2632
|
+
is the actual recursive call.
|
2633
|
+
<a name="recursiondifference"></a></P>
|
2634
|
+
<br><b>
|
2635
|
+
Differences in recursion processing between PCRE and Perl
|
2636
|
+
</b><br>
|
2637
|
+
<P>
|
2638
|
+
Recursion processing in PCRE differs from Perl in two important ways. In PCRE
|
2639
|
+
(like Python, but unlike Perl), a recursive subpattern call is always treated
|
2640
|
+
as an atomic group. That is, once it has matched some of the subject string, it
|
2641
|
+
is never re-entered, even if it contains untried alternatives and there is a
|
2642
|
+
subsequent matching failure. This can be illustrated by the following pattern,
|
2643
|
+
which purports to match a palindromic string that contains an odd number of
|
2644
|
+
characters (for example, "a", "aba", "abcba", "abcdcba"):
|
2645
|
+
<pre>
|
2646
|
+
^(.|(.)(?1)\2)$
|
2647
|
+
</pre>
|
2648
|
+
The idea is that it either matches a single character, or two identical
|
2649
|
+
characters surrounding a sub-palindrome. In Perl, this pattern works; in PCRE
|
2650
|
+
it does not if the pattern is longer than three characters. Consider the
|
2651
|
+
subject string "abcba":
|
2652
|
+
</P>
|
2653
|
+
<P>
|
2654
|
+
At the top level, the first character is matched, but as it is not at the end
|
2655
|
+
of the string, the first alternative fails; the second alternative is taken
|
2656
|
+
and the recursion kicks in. The recursive call to subpattern 1 successfully
|
2657
|
+
matches the next character ("b"). (Note that the beginning and end of line
|
2658
|
+
tests are not part of the recursion).
|
2659
|
+
</P>
|
2660
|
+
<P>
|
2661
|
+
Back at the top level, the next character ("c") is compared with what
|
2662
|
+
subpattern 2 matched, which was "a". This fails. Because the recursion is
|
2663
|
+
treated as an atomic group, there are now no backtracking points, and so the
|
2664
|
+
entire match fails. (Perl is able, at this point, to re-enter the recursion and
|
2665
|
+
try the second alternative.) However, if the pattern is written with the
|
2666
|
+
alternatives in the other order, things are different:
|
2667
|
+
<pre>
|
2668
|
+
^((.)(?1)\2|.)$
|
2669
|
+
</pre>
|
2670
|
+
This time, the recursing alternative is tried first, and continues to recurse
|
2671
|
+
until it runs out of characters, at which point the recursion fails. But this
|
2672
|
+
time we do have another alternative to try at the higher level. That is the big
|
2673
|
+
difference: in the previous case the remaining alternative is at a deeper
|
2674
|
+
recursion level, which PCRE cannot use.
|
2675
|
+
</P>
|
2676
|
+
<P>
|
2677
|
+
To change the pattern so that it matches all palindromic strings, not just
|
2678
|
+
those with an odd number of characters, it is tempting to change the pattern to
|
2679
|
+
this:
|
2680
|
+
<pre>
|
2681
|
+
^((.)(?1)\2|.?)$
|
2682
|
+
</pre>
|
2683
|
+
Again, this works in Perl, but not in PCRE, and for the same reason. When a
|
2684
|
+
deeper recursion has matched a single character, it cannot be entered again in
|
2685
|
+
order to match an empty string. The solution is to separate the two cases, and
|
2686
|
+
write out the odd and even cases as alternatives at the higher level:
|
2687
|
+
<pre>
|
2688
|
+
^(?:((.)(?1)\2|)|((.)(?3)\4|.))
|
2689
|
+
</pre>
|
2690
|
+
If you want to match typical palindromic phrases, the pattern has to ignore all
|
2691
|
+
non-word characters, which can be done like this:
|
2692
|
+
<pre>
|
2693
|
+
^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$
|
2694
|
+
</pre>
|
2695
|
+
If run with the PCRE_CASELESS option, this pattern matches phrases such as "A
|
2696
|
+
man, a plan, a canal: Panama!" and it works well in both PCRE and Perl. Note
|
2697
|
+
the use of the possessive quantifier *+ to avoid backtracking into sequences of
|
2698
|
+
non-word characters. Without this, PCRE takes a great deal longer (ten times or
|
2699
|
+
more) to match typical phrases, and Perl takes so long that you think it has
|
2700
|
+
gone into a loop.
|
2701
|
+
</P>
|
2702
|
+
<P>
|
2703
|
+
<b>WARNING</b>: The palindrome-matching patterns above work only if the subject
|
2704
|
+
string does not start with a palindrome that is shorter than the entire string.
|
2705
|
+
For example, although "abcba" is correctly matched, if the subject is "ababa",
|
2706
|
+
PCRE finds the palindrome "aba" at the start, then fails at top level because
|
2707
|
+
the end of the string does not follow. Once again, it cannot jump back into the
|
2708
|
+
recursion to try other alternatives, so the entire match fails.
|
2709
|
+
</P>
|
2710
|
+
<P>
|
2711
|
+
The second way in which PCRE and Perl differ in their recursion processing is
|
2712
|
+
in the handling of captured values. In Perl, when a subpattern is called
|
2713
|
+
recursively or as a subpattern (see the next section), it has no access to any
|
2714
|
+
values that were captured outside the recursion, whereas in PCRE these values
|
2715
|
+
can be referenced. Consider this pattern:
|
2716
|
+
<pre>
|
2717
|
+
^(.)(\1|a(?2))
|
2718
|
+
</pre>
|
2719
|
+
In PCRE, this pattern matches "bab". The first capturing parentheses match "b",
|
2720
|
+
then in the second group, when the back reference \1 fails to match "b", the
|
2721
|
+
second alternative matches "a" and then recurses. In the recursion, \1 does
|
2722
|
+
now match "b" and so the whole match succeeds. In Perl, the pattern fails to
|
2723
|
+
match because inside the recursive call \1 cannot access the externally set
|
2724
|
+
value.
|
2725
|
+
<a name="subpatternsassubroutines"></a></P>
|
2726
|
+
<br><a name="SEC24" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br>
|
2727
|
+
<P>
|
2728
|
+
If the syntax for a recursive subpattern call (either by number or by
|
2729
|
+
name) is used outside the parentheses to which it refers, it operates like a
|
2730
|
+
subroutine in a programming language. The called subpattern may be defined
|
2731
|
+
before or after the reference. A numbered reference can be absolute or
|
2732
|
+
relative, as in these examples:
|
2733
|
+
<pre>
|
2734
|
+
(...(absolute)...)...(?2)...
|
2735
|
+
(...(relative)...)...(?-1)...
|
2736
|
+
(...(?+1)...(relative)...
|
2737
|
+
</pre>
|
2738
|
+
An earlier example pointed out that the pattern
|
2739
|
+
<pre>
|
2740
|
+
(sens|respons)e and \1ibility
|
2741
|
+
</pre>
|
2742
|
+
matches "sense and sensibility" and "response and responsibility", but not
|
2743
|
+
"sense and responsibility". If instead the pattern
|
2744
|
+
<pre>
|
2745
|
+
(sens|respons)e and (?1)ibility
|
2746
|
+
</pre>
|
2747
|
+
is used, it does match "sense and responsibility" as well as the other two
|
2748
|
+
strings. Another example is given in the discussion of DEFINE above.
|
2749
|
+
</P>
|
2750
|
+
<P>
|
2751
|
+
All subroutine calls, whether recursive or not, are always treated as atomic
|
2752
|
+
groups. That is, once a subroutine has matched some of the subject string, it
|
2753
|
+
is never re-entered, even if it contains untried alternatives and there is a
|
2754
|
+
subsequent matching failure. Any capturing parentheses that are set during the
|
2755
|
+
subroutine call revert to their previous values afterwards.
|
2756
|
+
</P>
|
2757
|
+
<P>
|
2758
|
+
Processing options such as case-independence are fixed when a subpattern is
|
2759
|
+
defined, so if it is used as a subroutine, such options cannot be changed for
|
2760
|
+
different calls. For example, consider this pattern:
|
2761
|
+
<pre>
|
2762
|
+
(abc)(?i:(?-1))
|
2763
|
+
</pre>
|
2764
|
+
It matches "abcabc". It does not match "abcABC" because the change of
|
2765
|
+
processing option does not affect the called subpattern.
|
2766
|
+
<a name="onigurumasubroutines"></a></P>
|
2767
|
+
<br><a name="SEC25" href="#TOC1">ONIGURUMA SUBROUTINE SYNTAX</a><br>
|
2768
|
+
<P>
|
2769
|
+
For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or
|
2770
|
+
a number enclosed either in angle brackets or single quotes, is an alternative
|
2771
|
+
syntax for referencing a subpattern as a subroutine, possibly recursively. Here
|
2772
|
+
are two of the examples used above, rewritten using this syntax:
|
2773
|
+
<pre>
|
2774
|
+
(?<pn> \( ( (?>[^()]+) | \g<pn> )* \) )
|
2775
|
+
(sens|respons)e and \g'1'ibility
|
2776
|
+
</pre>
|
2777
|
+
PCRE supports an extension to Oniguruma: if a number is preceded by a
|
2778
|
+
plus or a minus sign it is taken as a relative reference. For example:
|
2779
|
+
<pre>
|
2780
|
+
(abc)(?i:\g<-1>)
|
2781
|
+
</pre>
|
2782
|
+
Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are <i>not</i>
|
2783
|
+
synonymous. The former is a back reference; the latter is a subroutine call.
|
2784
|
+
</P>
|
2785
|
+
<br><a name="SEC26" href="#TOC1">CALLOUTS</a><br>
|
2786
|
+
<P>
|
2787
|
+
Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl
|
2788
|
+
code to be obeyed in the middle of matching a regular expression. This makes it
|
2789
|
+
possible, amongst other things, to extract different substrings that match the
|
2790
|
+
same pair of parentheses when there is a repetition.
|
2791
|
+
</P>
|
2792
|
+
<P>
|
2793
|
+
PCRE provides a similar feature, but of course it cannot obey arbitrary Perl
|
2794
|
+
code. The feature is called "callout". The caller of PCRE provides an external
|
2795
|
+
function by putting its entry point in the global variable <i>pcre_callout</i>
|
2796
|
+
(8-bit library) or <i>pcre[16|32]_callout</i> (16-bit or 32-bit library).
|
2797
|
+
By default, this variable contains NULL, which disables all calling out.
|
2798
|
+
</P>
|
2799
|
+
<P>
|
2800
|
+
Within a regular expression, (?C) indicates the points at which the external
|
2801
|
+
function is to be called. If you want to identify different callout points, you
|
2802
|
+
can put a number less than 256 after the letter C. The default value is zero.
|
2803
|
+
For example, this pattern has two callout points:
|
2804
|
+
<pre>
|
2805
|
+
(?C1)abc(?C2)def
|
2806
|
+
</pre>
|
2807
|
+
If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, callouts are
|
2808
|
+
automatically installed before each item in the pattern. They are all numbered
|
2809
|
+
255. If there is a conditional group in the pattern whose condition is an
|
2810
|
+
assertion, an additional callout is inserted just before the condition. An
|
2811
|
+
explicit callout may also be set at this position, as in this example:
|
2812
|
+
<pre>
|
2813
|
+
(?(?C9)(?=a)abc|def)
|
2814
|
+
</pre>
|
2815
|
+
Note that this applies only to assertion conditions, not to other types of
|
2816
|
+
condition.
|
2817
|
+
</P>
|
2818
|
+
<P>
|
2819
|
+
During matching, when PCRE reaches a callout point, the external function is
|
2820
|
+
called. It is provided with the number of the callout, the position in the
|
2821
|
+
pattern, and, optionally, one item of data originally supplied by the caller of
|
2822
|
+
the matching function. The callout function may cause matching to proceed, to
|
2823
|
+
backtrack, or to fail altogether.
|
2824
|
+
</P>
|
2825
|
+
<P>
|
2826
|
+
By default, PCRE implements a number of optimizations at compile time and
|
2827
|
+
matching time, and one side-effect is that sometimes callouts are skipped. If
|
2828
|
+
you need all possible callouts to happen, you need to set options that disable
|
2829
|
+
the relevant optimizations. More details, and a complete description of the
|
2830
|
+
interface to the callout function, are given in the
|
2831
|
+
<a href="pcrecallout.html"><b>pcrecallout</b></a>
|
2832
|
+
documentation.
|
2833
|
+
<a name="backtrackcontrol"></a></P>
|
2834
|
+
<br><a name="SEC27" href="#TOC1">BACKTRACKING CONTROL</a><br>
|
2835
|
+
<P>
|
2836
|
+
Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which
|
2837
|
+
are still described in the Perl documentation as "experimental and subject to
|
2838
|
+
change or removal in a future version of Perl". It goes on to say: "Their usage
|
2839
|
+
in production code should be noted to avoid problems during upgrades." The same
|
2840
|
+
remarks apply to the PCRE features described in this section.
|
2841
|
+
</P>
|
2842
|
+
<P>
|
2843
|
+
The new verbs make use of what was previously invalid syntax: an opening
|
2844
|
+
parenthesis followed by an asterisk. They are generally of the form
|
2845
|
+
(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving
|
2846
|
+
differently depending on whether or not a name is present. A name is any
|
2847
|
+
sequence of characters that does not include a closing parenthesis. The maximum
|
2848
|
+
length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit
|
2849
|
+
libraries. If the name is empty, that is, if the closing parenthesis
|
2850
|
+
immediately follows the colon, the effect is as if the colon were not there.
|
2851
|
+
Any number of these verbs may occur in a pattern.
|
2852
|
+
</P>
|
2853
|
+
<P>
|
2854
|
+
Since these verbs are specifically related to backtracking, most of them can be
|
2855
|
+
used only when the pattern is to be matched using one of the traditional
|
2856
|
+
matching functions, because these use a backtracking algorithm. With the
|
2857
|
+
exception of (*FAIL), which behaves like a failing negative assertion, the
|
2858
|
+
backtracking control verbs cause an error if encountered by a DFA matching
|
2859
|
+
function.
|
2860
|
+
</P>
|
2861
|
+
<P>
|
2862
|
+
The behaviour of these verbs in
|
2863
|
+
<a href="#btrepeat">repeated groups,</a>
|
2864
|
+
<a href="#btassert">assertions,</a>
|
2865
|
+
and in
|
2866
|
+
<a href="#btsub">subpatterns called as subroutines</a>
|
2867
|
+
(whether or not recursively) is documented below.
|
2868
|
+
<a name="nooptimize"></a></P>
|
2869
|
+
<br><b>
|
2870
|
+
Optimizations that affect backtracking verbs
|
2871
|
+
</b><br>
|
2872
|
+
<P>
|
2873
|
+
PCRE contains some optimizations that are used to speed up matching by running
|
2874
|
+
some checks at the start of each match attempt. For example, it may know the
|
2875
|
+
minimum length of matching subject, or that a particular character must be
|
2876
|
+
present. When one of these optimizations bypasses the running of a match, any
|
2877
|
+
included backtracking verbs will not, of course, be processed. You can suppress
|
2878
|
+
the start-of-match optimizations by setting the PCRE_NO_START_OPTIMIZE option
|
2879
|
+
when calling <b>pcre_compile()</b> or <b>pcre_exec()</b>, or by starting the
|
2880
|
+
pattern with (*NO_START_OPT). There is more discussion of this option in the
|
2881
|
+
section entitled
|
2882
|
+
<a href="pcreapi.html#execoptions">"Option bits for <b>pcre_exec()</b>"</a>
|
2883
|
+
in the
|
2884
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
2885
|
+
documentation.
|
2886
|
+
</P>
|
2887
|
+
<P>
|
2888
|
+
Experiments with Perl suggest that it too has similar optimizations, sometimes
|
2889
|
+
leading to anomalous results.
|
2890
|
+
</P>
|
2891
|
+
<br><b>
|
2892
|
+
Verbs that act immediately
|
2893
|
+
</b><br>
|
2894
|
+
<P>
|
2895
|
+
The following verbs act as soon as they are encountered. They may not be
|
2896
|
+
followed by a name.
|
2897
|
+
<pre>
|
2898
|
+
(*ACCEPT)
|
2899
|
+
</pre>
|
2900
|
+
This verb causes the match to end successfully, skipping the remainder of the
|
2901
|
+
pattern. However, when it is inside a subpattern that is called as a
|
2902
|
+
subroutine, only that subpattern is ended successfully. Matching then continues
|
2903
|
+
at the outer level. If (*ACCEPT) in triggered in a positive assertion, the
|
2904
|
+
assertion succeeds; in a negative assertion, the assertion fails.
|
2905
|
+
</P>
|
2906
|
+
<P>
|
2907
|
+
If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For
|
2908
|
+
example:
|
2909
|
+
<pre>
|
2910
|
+
A((?:A|B(*ACCEPT)|C)D)
|
2911
|
+
</pre>
|
2912
|
+
This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is captured by
|
2913
|
+
the outer parentheses.
|
2914
|
+
<pre>
|
2915
|
+
(*FAIL) or (*F)
|
2916
|
+
</pre>
|
2917
|
+
This verb causes a matching failure, forcing backtracking to occur. It is
|
2918
|
+
equivalent to (?!) but easier to read. The Perl documentation notes that it is
|
2919
|
+
probably useful only when combined with (?{}) or (??{}). Those are, of course,
|
2920
|
+
Perl features that are not present in PCRE. The nearest equivalent is the
|
2921
|
+
callout feature, as for example in this pattern:
|
2922
|
+
<pre>
|
2923
|
+
a+(?C)(*FAIL)
|
2924
|
+
</pre>
|
2925
|
+
A match with the string "aaaa" always fails, but the callout is taken before
|
2926
|
+
each backtrack happens (in this example, 10 times).
|
2927
|
+
</P>
|
2928
|
+
<br><b>
|
2929
|
+
Recording which path was taken
|
2930
|
+
</b><br>
|
2931
|
+
<P>
|
2932
|
+
There is one verb whose main purpose is to track how a match was arrived at,
|
2933
|
+
though it also has a secondary use in conjunction with advancing the match
|
2934
|
+
starting point (see (*SKIP) below).
|
2935
|
+
<pre>
|
2936
|
+
(*MARK:NAME) or (*:NAME)
|
2937
|
+
</pre>
|
2938
|
+
A name is always required with this verb. There may be as many instances of
|
2939
|
+
(*MARK) as you like in a pattern, and their names do not have to be unique.
|
2940
|
+
</P>
|
2941
|
+
<P>
|
2942
|
+
When a match succeeds, the name of the last-encountered (*MARK:NAME),
|
2943
|
+
(*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to the
|
2944
|
+
caller as described in the section entitled
|
2945
|
+
<a href="pcreapi.html#extradata">"Extra data for <b>pcre_exec()</b>"</a>
|
2946
|
+
in the
|
2947
|
+
<a href="pcreapi.html"><b>pcreapi</b></a>
|
2948
|
+
documentation. Here is an example of <b>pcretest</b> output, where the /K
|
2949
|
+
modifier requests the retrieval and outputting of (*MARK) data:
|
2950
|
+
<pre>
|
2951
|
+
re> /X(*MARK:A)Y|X(*MARK:B)Z/K
|
2952
|
+
data> XY
|
2953
|
+
0: XY
|
2954
|
+
MK: A
|
2955
|
+
XZ
|
2956
|
+
0: XZ
|
2957
|
+
MK: B
|
2958
|
+
</pre>
|
2959
|
+
The (*MARK) name is tagged with "MK:" in this output, and in this example it
|
2960
|
+
indicates which of the two alternatives matched. This is a more efficient way
|
2961
|
+
of obtaining this information than putting each alternative in its own
|
2962
|
+
capturing parentheses.
|
2963
|
+
</P>
|
2964
|
+
<P>
|
2965
|
+
If a verb with a name is encountered in a positive assertion that is true, the
|
2966
|
+
name is recorded and passed back if it is the last-encountered. This does not
|
2967
|
+
happen for negative assertions or failing positive assertions.
|
2968
|
+
</P>
|
2969
|
+
<P>
|
2970
|
+
After a partial match or a failed match, the last encountered name in the
|
2971
|
+
entire match process is returned. For example:
|
2972
|
+
<pre>
|
2973
|
+
re> /X(*MARK:A)Y|X(*MARK:B)Z/K
|
2974
|
+
data> XP
|
2975
|
+
No match, mark = B
|
2976
|
+
</pre>
|
2977
|
+
Note that in this unanchored example the mark is retained from the match
|
2978
|
+
attempt that started at the letter "X" in the subject. Subsequent match
|
2979
|
+
attempts starting at "P" and then with an empty string do not get as far as the
|
2980
|
+
(*MARK) item, but nevertheless do not reset it.
|
2981
|
+
</P>
|
2982
|
+
<P>
|
2983
|
+
If you are interested in (*MARK) values after failed matches, you should
|
2984
|
+
probably set the PCRE_NO_START_OPTIMIZE option
|
2985
|
+
<a href="#nooptimize">(see above)</a>
|
2986
|
+
to ensure that the match is always attempted.
|
2987
|
+
</P>
|
2988
|
+
<br><b>
|
2989
|
+
Verbs that act after backtracking
|
2990
|
+
</b><br>
|
2991
|
+
<P>
|
2992
|
+
The following verbs do nothing when they are encountered. Matching continues
|
2993
|
+
with what follows, but if there is no subsequent match, causing a backtrack to
|
2994
|
+
the verb, a failure is forced. That is, backtracking cannot pass to the left of
|
2995
|
+
the verb. However, when one of these verbs appears inside an atomic group or an
|
2996
|
+
assertion that is true, its effect is confined to that group, because once the
|
2997
|
+
group has been matched, there is never any backtracking into it. In this
|
2998
|
+
situation, backtracking can "jump back" to the left of the entire atomic group
|
2999
|
+
or assertion. (Remember also, as stated above, that this localization also
|
3000
|
+
applies in subroutine calls.)
|
3001
|
+
</P>
|
3002
|
+
<P>
|
3003
|
+
These verbs differ in exactly what kind of failure occurs when backtracking
|
3004
|
+
reaches them. The behaviour described below is what happens when the verb is
|
3005
|
+
not in a subroutine or an assertion. Subsequent sections cover these special
|
3006
|
+
cases.
|
3007
|
+
<pre>
|
3008
|
+
(*COMMIT)
|
3009
|
+
</pre>
|
3010
|
+
This verb, which may not be followed by a name, causes the whole match to fail
|
3011
|
+
outright if there is a later matching failure that causes backtracking to reach
|
3012
|
+
it. Even if the pattern is unanchored, no further attempts to find a match by
|
3013
|
+
advancing the starting point take place. If (*COMMIT) is the only backtracking
|
3014
|
+
verb that is encountered, once it has been passed <b>pcre_exec()</b> is
|
3015
|
+
committed to finding a match at the current starting point, or not at all. For
|
3016
|
+
example:
|
3017
|
+
<pre>
|
3018
|
+
a+(*COMMIT)b
|
3019
|
+
</pre>
|
3020
|
+
This matches "xxaab" but not "aacaab". It can be thought of as a kind of
|
3021
|
+
dynamic anchor, or "I've started, so I must finish." The name of the most
|
3022
|
+
recently passed (*MARK) in the path is passed back when (*COMMIT) forces a
|
3023
|
+
match failure.
|
3024
|
+
</P>
|
3025
|
+
<P>
|
3026
|
+
If there is more than one backtracking verb in a pattern, a different one that
|
3027
|
+
follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a
|
3028
|
+
match does not always guarantee that a match must be at this starting point.
|
3029
|
+
</P>
|
3030
|
+
<P>
|
3031
|
+
Note that (*COMMIT) at the start of a pattern is not the same as an anchor,
|
3032
|
+
unless PCRE's start-of-match optimizations are turned off, as shown in this
|
3033
|
+
output from <b>pcretest</b>:
|
3034
|
+
<pre>
|
3035
|
+
re> /(*COMMIT)abc/
|
3036
|
+
data> xyzabc
|
3037
|
+
0: abc
|
3038
|
+
data> xyzabc\Y
|
3039
|
+
No match
|
3040
|
+
</pre>
|
3041
|
+
For this pattern, PCRE knows that any match must start with "a", so the
|
3042
|
+
optimization skips along the subject to "a" before applying the pattern to the
|
3043
|
+
first set of data. The match attempt then succeeds. In the second set of data,
|
3044
|
+
the escape sequence \Y is interpreted by the <b>pcretest</b> program. It causes
|
3045
|
+
the PCRE_NO_START_OPTIMIZE option to be set when <b>pcre_exec()</b> is called.
|
3046
|
+
This disables the optimization that skips along to the first character. The
|
3047
|
+
pattern is now applied starting at "x", and so the (*COMMIT) causes the match
|
3048
|
+
to fail without trying any other starting points.
|
3049
|
+
<pre>
|
3050
|
+
(*PRUNE) or (*PRUNE:NAME)
|
3051
|
+
</pre>
|
3052
|
+
This verb causes the match to fail at the current starting position in the
|
3053
|
+
subject if there is a later matching failure that causes backtracking to reach
|
3054
|
+
it. If the pattern is unanchored, the normal "bumpalong" advance to the next
|
3055
|
+
starting character then happens. Backtracking can occur as usual to the left of
|
3056
|
+
(*PRUNE), before it is reached, or when matching to the right of (*PRUNE), but
|
3057
|
+
if there is no match to the right, backtracking cannot cross (*PRUNE). In
|
3058
|
+
simple cases, the use of (*PRUNE) is just an alternative to an atomic group or
|
3059
|
+
possessive quantifier, but there are some uses of (*PRUNE) that cannot be
|
3060
|
+
expressed in any other way. In an anchored pattern (*PRUNE) has the same effect
|
3061
|
+
as (*COMMIT).
|
3062
|
+
</P>
|
3063
|
+
<P>
|
3064
|
+
The behaviour of (*PRUNE:NAME) is the not the same as (*MARK:NAME)(*PRUNE).
|
3065
|
+
It is like (*MARK:NAME) in that the name is remembered for passing back to the
|
3066
|
+
caller. However, (*SKIP:NAME) searches only for names set with (*MARK).
|
3067
|
+
<pre>
|
3068
|
+
(*SKIP)
|
3069
|
+
</pre>
|
3070
|
+
This verb, when given without a name, is like (*PRUNE), except that if the
|
3071
|
+
pattern is unanchored, the "bumpalong" advance is not to the next character,
|
3072
|
+
but to the position in the subject where (*SKIP) was encountered. (*SKIP)
|
3073
|
+
signifies that whatever text was matched leading up to it cannot be part of a
|
3074
|
+
successful match. Consider:
|
3075
|
+
<pre>
|
3076
|
+
a+(*SKIP)b
|
3077
|
+
</pre>
|
3078
|
+
If the subject is "aaaac...", after the first match attempt fails (starting at
|
3079
|
+
the first character in the string), the starting point skips on to start the
|
3080
|
+
next attempt at "c". Note that a possessive quantifer does not have the same
|
3081
|
+
effect as this example; although it would suppress backtracking during the
|
3082
|
+
first match attempt, the second attempt would start at the second character
|
3083
|
+
instead of skipping on to "c".
|
3084
|
+
<pre>
|
3085
|
+
(*SKIP:NAME)
|
3086
|
+
</pre>
|
3087
|
+
When (*SKIP) has an associated name, its behaviour is modified. When it is
|
3088
|
+
triggered, the previous path through the pattern is searched for the most
|
3089
|
+
recent (*MARK) that has the same name. If one is found, the "bumpalong" advance
|
3090
|
+
is to the subject position that corresponds to that (*MARK) instead of to where
|
3091
|
+
(*SKIP) was encountered. If no (*MARK) with a matching name is found, the
|
3092
|
+
(*SKIP) is ignored.
|
3093
|
+
</P>
|
3094
|
+
<P>
|
3095
|
+
Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores
|
3096
|
+
names that are set by (*PRUNE:NAME) or (*THEN:NAME).
|
3097
|
+
<pre>
|
3098
|
+
(*THEN) or (*THEN:NAME)
|
3099
|
+
</pre>
|
3100
|
+
This verb causes a skip to the next innermost alternative when backtracking
|
3101
|
+
reaches it. That is, it cancels any further backtracking within the current
|
3102
|
+
alternative. Its name comes from the observation that it can be used for a
|
3103
|
+
pattern-based if-then-else block:
|
3104
|
+
<pre>
|
3105
|
+
( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ...
|
3106
|
+
</pre>
|
3107
|
+
If the COND1 pattern matches, FOO is tried (and possibly further items after
|
3108
|
+
the end of the group if FOO succeeds); on failure, the matcher skips to the
|
3109
|
+
second alternative and tries COND2, without backtracking into COND1. If that
|
3110
|
+
succeeds and BAR fails, COND3 is tried. If subsequently BAZ fails, there are no
|
3111
|
+
more alternatives, so there is a backtrack to whatever came before the entire
|
3112
|
+
group. If (*THEN) is not inside an alternation, it acts like (*PRUNE).
|
3113
|
+
</P>
|
3114
|
+
<P>
|
3115
|
+
The behaviour of (*THEN:NAME) is the not the same as (*MARK:NAME)(*THEN).
|
3116
|
+
It is like (*MARK:NAME) in that the name is remembered for passing back to the
|
3117
|
+
caller. However, (*SKIP:NAME) searches only for names set with (*MARK).
|
3118
|
+
</P>
|
3119
|
+
<P>
|
3120
|
+
A subpattern that does not contain a | character is just a part of the
|
3121
|
+
enclosing alternative; it is not a nested alternation with only one
|
3122
|
+
alternative. The effect of (*THEN) extends beyond such a subpattern to the
|
3123
|
+
enclosing alternative. Consider this pattern, where A, B, etc. are complex
|
3124
|
+
pattern fragments that do not contain any | characters at this level:
|
3125
|
+
<pre>
|
3126
|
+
A (B(*THEN)C) | D
|
3127
|
+
</pre>
|
3128
|
+
If A and B are matched, but there is a failure in C, matching does not
|
3129
|
+
backtrack into A; instead it moves to the next alternative, that is, D.
|
3130
|
+
However, if the subpattern containing (*THEN) is given an alternative, it
|
3131
|
+
behaves differently:
|
3132
|
+
<pre>
|
3133
|
+
A (B(*THEN)C | (*FAIL)) | D
|
3134
|
+
</pre>
|
3135
|
+
The effect of (*THEN) is now confined to the inner subpattern. After a failure
|
3136
|
+
in C, matching moves to (*FAIL), which causes the whole subpattern to fail
|
3137
|
+
because there are no more alternatives to try. In this case, matching does now
|
3138
|
+
backtrack into A.
|
3139
|
+
</P>
|
3140
|
+
<P>
|
3141
|
+
Note that a conditional subpattern is not considered as having two
|
3142
|
+
alternatives, because only one is ever used. In other words, the | character in
|
3143
|
+
a conditional subpattern has a different meaning. Ignoring white space,
|
3144
|
+
consider:
|
3145
|
+
<pre>
|
3146
|
+
^.*? (?(?=a) a | b(*THEN)c )
|
3147
|
+
</pre>
|
3148
|
+
If the subject is "ba", this pattern does not match. Because .*? is ungreedy,
|
3149
|
+
it initially matches zero characters. The condition (?=a) then fails, the
|
3150
|
+
character "b" is matched, but "c" is not. At this point, matching does not
|
3151
|
+
backtrack to .*? as might perhaps be expected from the presence of the |
|
3152
|
+
character. The conditional subpattern is part of the single alternative that
|
3153
|
+
comprises the whole pattern, and so the match fails. (If there was a backtrack
|
3154
|
+
into .*?, allowing it to match "b", the match would succeed.)
|
3155
|
+
</P>
|
3156
|
+
<P>
|
3157
|
+
The verbs just described provide four different "strengths" of control when
|
3158
|
+
subsequent matching fails. (*THEN) is the weakest, carrying on the match at the
|
3159
|
+
next alternative. (*PRUNE) comes next, failing the match at the current
|
3160
|
+
starting position, but allowing an advance to the next character (for an
|
3161
|
+
unanchored pattern). (*SKIP) is similar, except that the advance may be more
|
3162
|
+
than one character. (*COMMIT) is the strongest, causing the entire match to
|
3163
|
+
fail.
|
3164
|
+
</P>
|
3165
|
+
<br><b>
|
3166
|
+
More than one backtracking verb
|
3167
|
+
</b><br>
|
3168
|
+
<P>
|
3169
|
+
If more than one backtracking verb is present in a pattern, the one that is
|
3170
|
+
backtracked onto first acts. For example, consider this pattern, where A, B,
|
3171
|
+
etc. are complex pattern fragments:
|
3172
|
+
<pre>
|
3173
|
+
(A(*COMMIT)B(*THEN)C|ABD)
|
3174
|
+
</pre>
|
3175
|
+
If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to
|
3176
|
+
fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes
|
3177
|
+
the next alternative (ABD) to be tried. This behaviour is consistent, but is
|
3178
|
+
not always the same as Perl's. It means that if two or more backtracking verbs
|
3179
|
+
appear in succession, all the the last of them has no effect. Consider this
|
3180
|
+
example:
|
3181
|
+
<pre>
|
3182
|
+
...(*COMMIT)(*PRUNE)...
|
3183
|
+
</pre>
|
3184
|
+
If there is a matching failure to the right, backtracking onto (*PRUNE) causes
|
3185
|
+
it to be triggered, and its action is taken. There can never be a backtrack
|
3186
|
+
onto (*COMMIT).
|
3187
|
+
<a name="btrepeat"></a></P>
|
3188
|
+
<br><b>
|
3189
|
+
Backtracking verbs in repeated groups
|
3190
|
+
</b><br>
|
3191
|
+
<P>
|
3192
|
+
PCRE differs from Perl in its handling of backtracking verbs in repeated
|
3193
|
+
groups. For example, consider:
|
3194
|
+
<pre>
|
3195
|
+
/(a(*COMMIT)b)+ac/
|
3196
|
+
</pre>
|
3197
|
+
If the subject is "abac", Perl matches, but PCRE fails because the (*COMMIT) in
|
3198
|
+
the second repeat of the group acts.
|
3199
|
+
<a name="btassert"></a></P>
|
3200
|
+
<br><b>
|
3201
|
+
Backtracking verbs in assertions
|
3202
|
+
</b><br>
|
3203
|
+
<P>
|
3204
|
+
(*FAIL) in an assertion has its normal effect: it forces an immediate backtrack.
|
3205
|
+
</P>
|
3206
|
+
<P>
|
3207
|
+
(*ACCEPT) in a positive assertion causes the assertion to succeed without any
|
3208
|
+
further processing. In a negative assertion, (*ACCEPT) causes the assertion to
|
3209
|
+
fail without any further processing.
|
3210
|
+
</P>
|
3211
|
+
<P>
|
3212
|
+
The other backtracking verbs are not treated specially if they appear in a
|
3213
|
+
positive assertion. In particular, (*THEN) skips to the next alternative in the
|
3214
|
+
innermost enclosing group that has alternations, whether or not this is within
|
3215
|
+
the assertion.
|
3216
|
+
</P>
|
3217
|
+
<P>
|
3218
|
+
Negative assertions are, however, different, in order to ensure that changing a
|
3219
|
+
positive assertion into a negative assertion changes its result. Backtracking
|
3220
|
+
into (*COMMIT), (*SKIP), or (*PRUNE) causes a negative assertion to be true,
|
3221
|
+
without considering any further alternative branches in the assertion.
|
3222
|
+
Backtracking into (*THEN) causes it to skip to the next enclosing alternative
|
3223
|
+
within the assertion (the normal behaviour), but if the assertion does not have
|
3224
|
+
such an alternative, (*THEN) behaves like (*PRUNE).
|
3225
|
+
<a name="btsub"></a></P>
|
3226
|
+
<br><b>
|
3227
|
+
Backtracking verbs in subroutines
|
3228
|
+
</b><br>
|
3229
|
+
<P>
|
3230
|
+
These behaviours occur whether or not the subpattern is called recursively.
|
3231
|
+
Perl's treatment of subroutines is different in some cases.
|
3232
|
+
</P>
|
3233
|
+
<P>
|
3234
|
+
(*FAIL) in a subpattern called as a subroutine has its normal effect: it forces
|
3235
|
+
an immediate backtrack.
|
3236
|
+
</P>
|
3237
|
+
<P>
|
3238
|
+
(*ACCEPT) in a subpattern called as a subroutine causes the subroutine match to
|
3239
|
+
succeed without any further processing. Matching then continues after the
|
3240
|
+
subroutine call.
|
3241
|
+
</P>
|
3242
|
+
<P>
|
3243
|
+
(*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause
|
3244
|
+
the subroutine match to fail.
|
3245
|
+
</P>
|
3246
|
+
<P>
|
3247
|
+
(*THEN) skips to the next alternative in the innermost enclosing group within
|
3248
|
+
the subpattern that has alternatives. If there is no such group within the
|
3249
|
+
subpattern, (*THEN) causes the subroutine match to fail.
|
3250
|
+
</P>
|
3251
|
+
<br><a name="SEC28" href="#TOC1">SEE ALSO</a><br>
|
3252
|
+
<P>
|
3253
|
+
<b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3),
|
3254
|
+
<b>pcresyntax</b>(3), <b>pcre</b>(3), <b>pcre16(3)</b>, <b>pcre32(3)</b>.
|
3255
|
+
</P>
|
3256
|
+
<br><a name="SEC29" href="#TOC1">AUTHOR</a><br>
|
3257
|
+
<P>
|
3258
|
+
Philip Hazel
|
3259
|
+
<br>
|
3260
|
+
University Computing Service
|
3261
|
+
<br>
|
3262
|
+
Cambridge CB2 3QH, England.
|
3263
|
+
<br>
|
3264
|
+
</P>
|
3265
|
+
<br><a name="SEC30" href="#TOC1">REVISION</a><br>
|
3266
|
+
<P>
|
3267
|
+
Last updated: 14 June 2015
|
3268
|
+
<br>
|
3269
|
+
Copyright © 1997-2015 University of Cambridge.
|
3270
|
+
<br>
|
3271
|
+
<p>
|
3272
|
+
Return to the <a href="index.html">PCRE index page</a>.
|
3273
|
+
</p>
|