Add GRegex for regular expression matching. (#50075)

2007-03-15 Marco Barisione <[email protected]> Add GRegex for regular expression matching. (#50075) * configure.in: Handle GRegex compilation. * glib/gregex.c: * glib/gregex.h: Code for GRegex. * glib/Makefile.am: * glib/makefile.msc.in: Updated makefiles. * glib/pcre/*: Internal copy of PCRE. * glib/update-pcre/*: Stuff to automatically update the internal PCRE to a newer version. * tests/regex-test.c: * tests/Makefile.am: * tests/makefile.msc.in: Add tests for GRegex. svn path=/trunk/; revision=5408
lsem · Mar 15, 2007 · 0196d63 · 0196d63
1 parent af86717
commit 0196d63
Show file tree

Hide file tree

Showing 54 changed files with 26,185 additions and 11 deletions.
diff --git a/ChangeLog b/ChangeLog
@@ -1,3 +1,24 @@
+2007-03-15  Marco Barisione <[email protected]>
+
+	Add GRegex for regular expression matching.  (#50075)
+
+	* configure.in: Handle GRegex compilation.
+
+	* glib/gregex.c:
+	* glib/gregex.h: Code for GRegex.
+
+	* glib/Makefile.am:
+	* glib/makefile.msc.in: Updated makefiles.
+
+	* glib/pcre/*: Internal copy of PCRE.
+
+	* glib/update-pcre/*: Stuff to automatically update the internal PCRE
+	to a newer version.
+
+	* tests/regex-test.c:
+	* tests/Makefile.am:
+	* tests/makefile.msc.in: Add tests for GRegex.
+
 2007-03-15  Chris Wilson  <[email protected]>
 
 	* glib/gmain.c (g_main_dispatch): Replace a

diff --git a/configure.in b/configure.in
@@ -173,7 +173,7 @@ AM_CONDITIONAL(MS_LIB_AVAILABLE, [test x$ms_librarian = xyes])
 if test "$glib_native_win32" != yes; then
     # libtool option to control which symbols are exported
     # right now, symbols starting with _ are not exported
-    LIBTOOL_EXPORT_OPTIONS='-export-symbols-regex "^[[^_]].*"'
+    LIBTOOL_EXPORT_OPTIONS='-export-symbols-regex "^g.*"'
 else
     # We currently use .def files on Windows
     LIBTOOL_EXPORT_OPTIONS=
@@ -2146,6 +2146,74 @@ AC_RUN_IFELSE([AC_LANG_SOURCE([[
   [broken_poll="no (cross compiling)"])
 AC_MSG_RESULT($broken_poll)
 
+dnl *********************
+dnl *** GRegex checks ***
+dnl *********************
+PCRE_REQUIRED_VERSION=7.0
+
+# Check if we should compile GRegex
+AC_ARG_ENABLE(regex, AC_HELP_STRING([--disable-regex],
+              [disable the compilation of GRegex]),
+[case "${enableval}" in
+  yes) enable_regex=true ;;
+  no)  enable_regex=false ;;
+  *) AC_MSG_ERROR(bad value ${enableval} for --enable-regex) ;;
+esac],
+[enable_regex=true])
+
+AM_CONDITIONAL(ENABLE_REGEX, $enable_regex)
+
+if test x$enable_regex = xtrue; then
+  # Check if we should use the internal or the system-supplied pcre
+  AC_ARG_WITH(pcre,
+             [AC_HELP_STRING([--with-pcre=@<:@internal/system@:>@],
+                             [specify whether to use the internal or the
+                              system-supplied PCRE library])])
+
+  AM_CONDITIONAL(USE_SYSTEM_PCRE, [test "x$with_pcre" = xsystem])
+
+  if test "x$with_pcre" = xsystem; then
+    PKG_CHECK_MODULES(PCRE,
+                      libpcre >= $PCRE_REQUIRED_VERSION)
+    AC_CACHE_CHECK([for Unicode support in PCRE],glib_cv_pcre_has_unicode,[
+                   CFLAGS="$PCRE_CFLAGS" LDFLAGS="$PCRE_LIBS"
+                   AC_TRY_RUN([#include <pcre.h>
+                               int main () {
+                                 int support;
+                                 pcre_config (PCRE_CONFIG_UTF8, &support);
+                                 if (!support)
+                                   return 1;
+                                 pcre_config (PCRE_CONFIG_UNICODE_PROPERTIES, &support);
+                                 if (!support)
+                                   return 1;
+                                 return 0;
+                               }],
+                   glib_cv_pcre_has_unicode=yes,
+                   glib_cv_pcre_has_unicode=no,
+                   glib_cv_pcre_has_unicode=yes)])
+    if test "$glib_cv_pcre_has_unicode" = "no"; then
+      AC_MSG_ERROR([*** The system-supplied PCRE does not support Unicode properties or UTF-8.])
+    fi
+    AC_SUBST(PCRE_CFLAGS)
+    AC_SUBST(PCRE_LIBS)
+    AC_DEFINE(USE_SYSTEM_PCRE, [], [using the system-supplied PCRE library])
+  else
+    # If using gcc 4 pass -Wno-pointer-sign when compiling the internal PCRE
+    if test x"$GCC" = xyes; then
+      AC_MSG_CHECKING([whether gcc understands -Wno-pointer-sign])
+      if test [`$CC --version | sed -e 's/[^0-9]*\([0-9]\).*/\1/' -e q`] -ge 4; then
+        PCRE_WARN_CFLAGS="$PCRE_WARN_CFLAGS -Wno-pointer-sign"
+        AC_MSG_RESULT([yes]) 
+      else
+        AC_MSG_RESULT([no]) 
+      fi
+    fi
+  fi
+  AC_SUBST(PCRE_WARN_CFLAGS)
+else
+  AM_CONDITIONAL(USE_SYSTEM_PCRE, false])
+fi
+
 dnl **********************
 dnl *** Win32 API libs ***
 dnl **********************
@@ -2864,6 +2932,8 @@ Makefile
 glib/Makefile
 glib/libcharset/Makefile
 glib/gnulib/Makefile
+glib/pcre/Makefile
+glib/update-pcre/Makefile
 gmodule/Makefile
 gmodule/gmoduleconf.h
 gobject/Makefile

diff --git a/docs/reference/ChangeLog b/docs/reference/ChangeLog
@@ -1,3 +1,17 @@
+2007-03-15  Marco Barisione <[email protected]>
+
+	Add GRegex for regular expression matching.  (#50075)
+
+	* glib/Makefile.am:
+	* glib/glib-docs.sgml:
+	* glib/glib-sections.txt:
+	* glib/tmpl/glib-unused.sgml:
+	* glib/regex-syntax.sgml:
+	* glib/tmpl/gregex-unused.sgml:
+	* glib/tmpl/gregex.sgml: Add GRegex.
+
+	* glib/building.sgml: Document build options for GRegex.
+
 2007-03-14  Stefan Kost  <[email protected]>
 
 	* gobject/tmpl/gparamspec.sgml:

diff --git a/docs/reference/glib/Makefile.am b/docs/reference/glib/Makefile.am
@@ -37,7 +37,9 @@ IGNORE_HFILES=			\
 	gmirroringtable.h	\
 	gscripttable.h		\
 	glib-mirroring-tab	\
-	gnulib
+	gnulib			\
+	pcre			\
+	update-pcre
 
 # Extra options to supply to gtkdoc-mkdb
 MKDB_OPTIONS=--sgml-mode --output-format=xml --ignore-files=trio
@@ -55,6 +57,7 @@ content_files =				\
 	changes.sgml			\
 	compiling.sgml			\
 	resources.sgml			\
+	regex-syntax.sgml		\
 	version.xml			\
 	glib-gettextize.xml
 

diff --git a/docs/reference/glib/building.sgml b/docs/reference/glib/building.sgml
@@ -146,6 +146,16 @@ How to compile GLib itself
 	  e.g. POSIX threads, DCE threads or Solaris threads. 
 	</para>
       </listitem>
+      <listitem>
+	<para>
+	  GRegex uses the the <ulink url="http://www.pcre.org/">PCRE library</ulink>
+	  for regular expression matching. The default is to use the internal
+	  version of PCRE that is patched to use GLib for memory management
+	  and Unicode handling. If you prefer to use the system-supplied PCRE
+	  library  you can pass the --with-pcre=system option to configure,
+	  but it is not recommended.
+	</para>
+      </listitem>
     </itemizedlist>
 
     </refsect1>
@@ -177,6 +187,13 @@ How to compile GLib itself
           <group>
             <arg>--with-threads=[none|posix|dce|win32]</arg>
           </group>
+          <group>
+            <arg>--disable-regex</arg>
+            <arg>--enable-regex</arg>
+          </group>
+          <group>
+            <arg>--with-pcre=[internal|system]</arg>
+          </group>
 	  <group>
              <arg>--disable-included-printf</arg>
              <arg>--enable-included-printf</arg>
@@ -361,6 +378,61 @@ How to compile GLib itself
         </para>
       </formalpara>
 
+      <formalpara>
+        <title><systemitem>--disable-regex</systemitem> and
+          <systemitem>--enable-regex</systemitem></title>
+
+        <para>
+           Do not compile GLib with regular expression support.
+           GLib will be smaller because it will not need the
+           PCRE library. This is however not recommended, as
+           programs may need GRegex.
+        </para>
+      </formalpara>
+
+      <formalpara>
+        <title><systemitem>--with-pcre</systemitem></title>
+
+        <para>
+          Specify whether to use the internal or the system-supplied
+          PCRE library.
+          <itemizedlist>
+            <listitem><para>
+              'internal' means that GRegex will be compiled to use
+              the internal PCRE library.
+            </para></listitem>
+
+            <listitem><para>
+              'system' means that GRegex will be compiled to use
+              the system-supplied PCRE library.
+            </para></listitem>
+          </itemizedlist>
+          Using the internal PCRE is the preferred solution:
+          <itemizedlist>
+            <listitem>
+              <para>
+                System-supplied PCRE has a separated copy of the big tables
+                used for Unicode handling.
+              </para>
+            </listitem>
+            <listitem>
+              <para>
+                Some systems have PCRE libraries compiled without some needed
+                features, such as UTF-8 and Unicode support.
+              </para>
+            </listitem>
+            <listitem>
+              <para>
+                PCRE uses some global variables for memory management and
+                other features. In the rare case of a program using both
+                GRegex and PCRE (maybe indirectly through a library),
+                this variables could lead to problems when they are modified.
+              </para>
+            </listitem>
+          </itemizedlist>
+        </para>
+      </formalpara>
+
       <formalpara>
          <title><systemitem>--disable-included-printf</systemitem> and
            <systemitem>--enable-included-printf</systemitem></title>

diff --git a/docs/reference/glib/glib-docs.sgml b/docs/reference/glib/glib-docs.sgml
@@ -61,6 +61,7 @@
 <!ENTITY glib-Bookmarkfile SYSTEM "xml/bookmarkfile.xml">
 <!ENTITY glib-Base64 SYSTEM "xml/base64.xml">
 <!ENTITY glib-i18n SYSTEM "xml/i18n.xml">
+<!ENTITY glib-Regex SYSTEM "xml/gregex.xml">
 <!ENTITY glib-Version SYSTEM "xml/version.xml">
 
 <!ENTITY glib-Compiling SYSTEM "compiling.sgml">
@@ -69,6 +70,7 @@
 <!ENTITY glib-Running SYSTEM "running.sgml">
 <!ENTITY glib-Resources SYSTEM "resources.sgml">
 <!ENTITY glib-Changes SYSTEM "changes.sgml">
+<!ENTITY glib-RegexSyntax SYSTEM "regex-syntax.sgml">
 
 <!ENTITY glib-gettextize SYSTEM "glib-gettextize.xml">
 
@@ -101,6 +103,7 @@ synchronize their operation.
     &glib-Compiling;
     &glib-Running;
     &glib-Changes;
+    &glib-RegexSyntax;
     &glib-Resources;
 
   </chapter> 
@@ -151,6 +154,7 @@ synchronize their operation.
     &glib-Shell;
     &glib-Option;
     &glib-Pattern-Matching;
+    &glib-Regex;
     &glib-Markup;
     &glib-Keyfile;
     &glib-Bookmarkfile;

diff --git a/docs/reference/glib/glib-sections.txt b/docs/reference/glib/glib-sections.txt
@@ -863,6 +863,50 @@ g_pattern_match_string
 g_pattern_match_simple
 </SECTION>
 
+<SECTION>
+<TITLE>Perl-compatible regular expressions</TITLE>
+<FILE>gregex</FILE>
+GRegexError
+G_REGEX_ERROR
+GRegexCompileFlags
+GRegexMatchFlags
+GRegex
+GRegexEvalCallback
+g_regex_new
+g_regex_free
+g_regex_optimize
+g_regex_copy
+g_regex_get_pattern
+g_regex_clear
+g_regex_match_simple
+g_regex_match
+g_regex_match_full
+g_regex_match_next
+g_regex_match_next_full
+g_regex_match_all
+g_regex_match_all_full
+g_regex_get_match_count
+g_regex_is_partial_match
+g_regex_fetch
+g_regex_fetch_pos
+g_regex_fetch_named
+g_regex_fetch_named_pos
+g_regex_fetch_all
+g_regex_get_string_number
+g_regex_split_simple
+g_regex_split
+g_regex_split_full
+g_regex_split_next
+g_regex_split_next_full
+g_regex_expand_references
+g_regex_replace
+g_regex_replace_literal
+g_regex_replace_eval
+g_regex_escape_string
+<SUBSECTION Private>
+g_regex_error_quark
+</SECTION>
+
 <SECTION>
 <TITLE>Message Logging</TITLE>
 <FILE>messages</FILE>