Changeset 5536f74

Timestamp:

12/26/2005 07:00:06 PM (18 years ago)

Author:

Archaic <archaic@…>

Branches:

10.0, 10.0-rc1, 10.1, 10.1-rc1, 11.0, 11.0-rc1, 11.0-rc2, 11.0-rc3, 11.1, 11.1-rc1, 11.2, 11.2-rc1, 11.3, 11.3-rc1, 12.0, 12.0-rc1, 12.1, 12.1-rc1, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8, 7.0, 7.1, 7.2, 7.3, 7.4, 7.5, 7.5-systemd, 7.6, 7.6-systemd, 7.7, 7.7-systemd, 7.8, 7.8-systemd, 7.9, 7.9-systemd, 8.0, 8.1, 8.2, 8.3, 8.4, 9.0, 9.1, arm, bdubbs/gcc13, ml-11.0, multilib, renodr/libudev-from-systemd, s6-init, trunk, xry111/arm64, xry111/arm64-12.0, xry111/clfs-ng, xry111/lfs-next, xry111/loongarch, xry111/loongarch-12.0, xry111/loongarch-12.1, xry111/mips64el, xry111/pip3, xry111/rust-wip-20221008, xry111/update-glibc

Children:

94aa6621

Parents:

2550494

Message:

Applied Alexander Patrakov's patch which adds UTF-8 capability to the
development branch of the LFS Book.

git-svn-id: ​http://svn.linuxfromscratch.org/LFS/trunk/BOOK@7235 4aa44e1e-78dd-0310-a6d2-fbcd4c07a689

Files:

• chapter01/changelog.xml (modified) (5 diffs)
• chapter03/packages.xml (modified) (5 diffs)
• chapter03/patches.xml (modified) (8 diffs)
• chapter05/gawk.xml (modified) (1 diff)
• chapter05/glibc.xml (modified) (3 diffs)
• chapter06/chapter06.xml (modified) (2 diffs)
• chapter06/coreutils.xml (modified) (1 diff)
• chapter06/diffutils.xml (modified) (1 diff)
• chapter06/gawk.xml (modified) (2 diffs)
• chapter06/gdbm.xml (added)
• chapter06/glibc.xml (modified) (5 diffs)
• chapter06/grep.xml (modified) (1 diff)
• chapter06/groff.xml (modified) (1 diff)
• chapter06/kbd.xml (modified) (3 diffs)
• chapter06/man-db.xml (added)
• chapter06/man.xml (modified) (1 diff)
• chapter06/ncurses.xml (modified) (4 diffs)
• chapter06/readline.xml (modified) (1 diff)
• chapter06/sysklogd.xml (modified) (1 diff)
• chapter06/sysvinit.xml (modified) (1 diff)
• chapter06/texinfo.xml (modified) (1 diff)
• chapter06/udev.xml (modified) (1 diff)
• chapter06/vim.xml (modified) (2 diffs)
• chapter07/bootscripts.xml (modified) (1 diff)
• chapter07/console.xml (modified) (1 diff)
• chapter07/profile.xml (modified) (5 diffs)
• chapter08/fstab.xml (modified) (1 diff)
• chapter08/kernel.xml (modified) (2 diffs)
• general.ent (modified) (3 diffs)
• patches.ent (modified) (4 diffs)

chapter01/changelog.xml

@@ -45 +45 @@
 <listitem><para>Glibc &glibc-version;</para></listitem>
 <!-- <listitem><para>Grep &grep-version;</para></listitem> -->
-<listitem><para>Groff &groff-version;</para></listitem>
+<!-- <listitem><para>Groff &groff-version;</para></listitem> -->
 <listitem><para>GRUB &grub-version;</para></listitem>
 <!-- <listitem><para>Gzip &gzip-version;</para></listitem> -->
@@ -60 +60 @@
 <listitem><para>M4 &m4-version;</para></listitem>
 <!-- <listitem><para>Make &make-version;</para></listitem> -->
-<listitem><para>Man &man-version;</para></listitem>
+<listitem><para>Man-DB &man-db-version;</para></listitem>
 <listitem><para>Man-pages &man-pages-version;</para></listitem>
 <!-- <listitem><para>Mktemp &mktemp-version;</para></listitem> -->
@@ -84 +84 @@
 </listitem>
 
+<listitem><para>Downgraded to:</para>
+<itemizedlist>
+<listitem><para>Groff &groff-version;-&groff-patchlevel;</para></listitem>
+</itemizedlist>
+</listitem>
+
 <listitem><para>Added:</para>
 <itemizedlist>
@@ -90 +96 @@
 <listitem><para>&gawk-segfault-patch;</para></listitem>
 <listitem><para>&gcc-specs-patch;</para></listitem>
+<listitem><para>GDBM-&gdbm-version;</para></listitem>
 <listitem><para>&inetutils-gcc4_fixes-patch;</para></listitem>
 <listitem><para>&kbd-gcc4_fixes-patch;</para></listitem>
+<listitem><para>MAN-DB-&man-db-version;</para></listitem>
 <listitem><para>&mktemp-tempfile-patch;</para></listitem>
 <listitem><para>&perl-libc-patch;</para></listitem>
@@ -108 +116 @@
 <listitem><para>inetutils-1.4.2-kernel_headers-1.patch</para></listitem>
 <listitem><para>iproute2-2.6.11-050330-remove_db-1.patch</para></listitem>
+<listitem><para>Man-1.6b</para></listitem>
 <listitem><para>mktemp-1.5-add_tempfile-2.patch</para></listitem>
 <listitem><para>perl-5.8.6-libc-1.patch</para></listitem>

chapter03/packages.xml

@@ -138 +138 @@
 
 <varlistentry>
+<term>GDBM (&gdbm-version;) - 228 KB:</term>
+<listitem>
+<para><ulink url="&gnu;gdbm/"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Gettext (&gettext-version;) - 4,668 KB:</term>
 <listitem>
@@ -159 +166 @@
 
 <varlistentry>
-<term>Groff (&groff-version;) - 2,096 KB:</term>
+<term>Groff (&groff-version;) - 2,260 KB:</term>
 <listitem>
 <para><ulink url="&gnu;groff/"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
+<term>Groff Debian Patch - 129 KB:</term>
+<listitem>
+<para><ulink url="http://ftp.debian.org/debian/pool/main/g/groff/&groff-debian-patch;"/></para>
+<note><para>Groff Debian Patch (&groff-version;-&groff-patchlevel;)
+may no longer be available at the
+listed location. The site administrators of the master download
+location occasionally remove older versions when new ones are
+released. There is no alternative download location yet.</para></note>
+<!-- Actually there's snapshot.debian.net, but they have hardware problems -->
 </listitem>
 </varlistentry>
@@ -230 +250 @@
 
 <varlistentry>
+<term>Replacement <command>console</command> script for LFS-Bootscripts (&lfs-bootscripts-version;) - 3 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;console"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Libtool (&libtool-version;) - 1,642 KB:</term>
 <listitem>
@@ -265 +292 @@
 
 <varlistentry>
-<term>Man (&man-version;) - 205 KB:</term>
-<listitem>
-<para><ulink url="http://primates.ximian.com/~flucifredi/man/"/></para>
+<term>Man-DB (&man-db-version;) - 816 KB:</term>
+<listitem>
+<para><ulink url="http://savannah.nongnu.org/download/man-db/"/></para>
 </listitem>
 </varlistentry>
@@ -298 +325 @@
 </listitem>
 </varlistentry>
+
+<!--
+<varlistentry>
+<term>Ncurses Rollup Patch (&ncurses-date;) - 328 KB:</term>
+<listitem>
+<para><ulink url="ftp://invisible-island.net/ncurses/&ncurses-version;/"/></para>
+<note><para>Ncurses Rollup Patch (&ncurses-date;) may no longer be available at the
+listed location. The site administrators of the master download
+location occasionally remove older versions when new ones are
+released. There is no alternative download location yet.</para></note>
+</listitem>
+</varlistentry>
+-->
 
 <varlistentry>

chapter03/patches.xml

@@ -31 +31 @@
 
 <varlistentry>
+<term>Coreutils Internationalization Fixes Patch - 110 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&coreutils-i18n-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Coreutils Suppress Uptime, Kill, Su Patch - 15 KB:</term>
 <listitem>
@@ -45 +52 @@
 
 <varlistentry>
+<term>Diffutils Internationalization Fixes Patch - 18 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&diffutils-i18n-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Expect Spawn Patch - 7 KB:</term>
 <listitem>
@@ -69 +83 @@
 <listitem>
 <para><ulink url="&patches-root;&gcc-specs-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
+<term>Grep RedHat Fixes Patch - 56 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&grep-fixes-patch;"/></para>
 </listitem>
 </varlistentry>
@@ -79 +100 @@
 
 <varlistentry>
+<term>Kbd Backspace/Delete Fix Patch - 1 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&kbd-backspace-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Kbd GCC-4.x Fix Patch - 1 KB:</term>
 <listitem>
@@ -100 +128 @@
 
 <varlistentry>
+<term>Linux kernel UTF-8 Composing Patch - 3 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&linux-utf8-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Mktemp Tempfile Patch - 4 KB:</term>
 <listitem>
@@ -107 +142 @@
 
 <varlistentry>
+<term>Ncurses Fixes Patch - 9 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&ncurses-fixes-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Perl Libc Patch - 1 KB:</term>
 <listitem>
@@ -114 +156 @@
 
 <varlistentry>
+<term>Sysklogd 8-Bit Cleanness Patch - 1 KB:</term>
+<listitem>
+<para><ulink url="&lfs-root;patches/downloads/sysklogd/&sysklogd-8bit-patch;"/></para>
+</listitem>
+</varlistentry>
+
+<varlistentry>
 <term>Shadow Configure Script Patch - 1KB:</term>
 <listitem>
@@ -140 +189 @@
 </listitem>
 </varlistentry>
+
+<varlistentry>
+<term>Texinfo Multibyte Fixes Patch - 1 KB:</term>
+<listitem>
+<para><ulink url="&alexpatches;&texinfo-multibyte-patch;"/></para>
+</listitem>
+</varlistentry>
+
 
 <varlistentry>

chapter05/gawk.xml

@@ -32 +32 @@
 <screen><userinput>./configure --prefix=/tools</userinput></screen>
 
-<para>The configure script doesn't detect some functionality correctly.  The
-following commands correct this problem:</para>
-
-<screen><userinput>echo "#define HAVE_LANGINFO_CODESET 1" >> config.h
-echo "#define HAVE_LC_MESSAGES 1" >> config.h</userinput></screen>
+<para>Due to a bug in the <command>./configure</command> script, Gawk fails
+to detect certain aspects of locale support in glibc. This
+bug leads to, e.g., Gettext testsuite failures. Work around this issue
+by appending the missing macro definitions to <filename>config.h</filename>:</para>
+<screen><userinput>cat &gt;&gt;config.h &lt;&lt;"EOF"
+<literal>#define HAVE_LANGINFO_CODESET 1
+#define HAVE_LC_MESSAGES 1</literal>
+EOF</userinput></screen>
 
 <para>Compile the package:</para>

chapter05/glibc.xml

@@ -28 +28 @@
 <title>Installation of Glibc</title>
 
+<para>The glibc-libidn tarball adds support for internationalized
+(non-ASCII) domain names to Glibc. While this facility is not
+useful in this chapter, the installation commands of
+<xref linkend="chapter-building-system"/>
+glibc (wrongly) check <xref linkend="chapter-temporary-tools"/> glibc for
+this feature. Unpack the tarball from within the Glibc source
+directory in order to avoid this bogus failure:</para>
+
+<screen><userinput>tar jxf ../glibc-libidn-&glibc-version;.tar.bz2</userinput></screen>
+<!-- TODO: DIY Linux modifies the installation check script in Chapte 6 instead -->
+
 <para>The Glibc documentation recommends building Glibc outside of the source
 directory in a dedicated build directory:</para>
@@ -37 +48 @@
 
 <screen><userinput>../glibc-&glibc-version;/configure --prefix=/tools \
-    --disable-profile --enable-add-ons \
+    --disable-profile --enable-add-ons=nptl,libidn \
     --enable-kernel=2.6.0 --with-binutils=/tools/bin \
     --without-gd --with-headers=/tools/include \
@@ -53 +64 @@
 
 <varlistentry>
-<term><parameter>--enable-add-ons</parameter></term>
+<term><parameter>--enable-add-ons=nptl,libidn</parameter></term>
 <listitem><para>This tells Glibc to use the NPTL add-on as its threading 
-library.</para></listitem>
+library, and adds support for non-ASCII domain names.</para></listitem>
 </varlistentry>
 

chapter06/chapter06.xml

@@ -35 +35 @@
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="bison.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="less.xml"/>
+<xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="gdbm.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="groff.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="sed.xml"/>
@@ -56 +57 @@
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="gzip.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="hotplug.xml"/>
-<xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="man.xml"/>
+<xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="man-db.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="make.xml"/>
 <xi:include xmlns:xi="http://www.w3.org/2003/XInclude" href="module-init-tools.xml"/>

chapter06/coreutils.xml

@@ -41 +41 @@
 
 <screen><userinput>patch -Np1 -i ../&coreutils-suppress-patch;</userinput></screen>
+
+<para>POSIX requires that programs from Coreutils recognize character
+boundaries correctly even in multibyte locales. The following patch
+fixes this non-compliance and other internationalization-related bugs:</para>
+
+<screen><userinput>patch -Np1 -i ../&coreutils-i18n-patch;</userinput></screen>
+
+<para>In order for the tests added by this patch to pass, the permissions for
+the test file have to be changed:</para>
+
+<screen><userinput>chmod +x tests/sort/sort-mb-tests</userinput></screen>
+
+<note><para>In the past, many bugs were found in this patch. When reporting
+new bugs to Coreutils maintainers, please check first if they are reproducible
+without this patch.</para></note>
+
+<para>It has been found that translated messages sometimes overflow a buffer
+in the <command>who -Hu</command> command. Increase the buffer size:</para>
+
+<screen><userinput>sed -i 's,_LEN 6,_LEN 20,' src/who.c</userinput></screen>
 
 <para>Now prepare Coreutils for compilation:</para>

chapter06/diffutils.xml

@@ -29 +29 @@
 <sect2 role="installation">
 <title>Installation of Diffutils</title>
+
+<para>POSIX requires that the <command>diff</command> command treats whitespace
+characters according to the current locale. The following patch fixes the
+non-complinace issue:</para>
+
+<screen><userinput>patch -Np1 -i ../&diffutils-i18n-patch;</userinput></screen>
 
 <para>Prepare Diffutils for compilation:</para>

chapter06/gawk.xml

@@ -29 +29 @@
 <title>Installation of Gawk</title>
 
-<para>Patch Gawk to fix a bug which causes it to segfault when invoked on a
-non-existent file:</para>
+<para>Under some circumstances, Gawk-&gawk-version;  attempts to free a chunk
+of memory that was not allocated. This bug is fixed by the following patch:</para>
 
 <screen><userinput>patch -Np1 -i ../&gawk-segfault-patch;</userinput></screen>
@@ -38 +38 @@
 <screen><userinput>./configure --prefix=/usr --libexecdir=/usr/lib</userinput></screen>
 
-<para>The configure script doesn't detect some functionality correctly.  The
-following commands correct this problem:</para>
+<para>Due to a bug in the <command>./configure</command> script, Gawk fails
+to detect certain aspects of locale support in glibc. This
+bug leads to, e.g., Gettext testsuite failures. Work around this issue
+by appending the missing macro definitions to <filename>config.h</filename>:</para>
 
-<screen><userinput>echo "#define HAVE_LANGINFO_CODESET 1" >> config.h
-echo "#define HAVE_LC_MESSAGES 1" >> config.h</userinput></screen>
+<screen><userinput>cat &gt;&gt;config.h &lt;&lt;"EOF"
+<literal>#define HAVE_LANGINFO_CODESET 1
+#define HAVE_LC_MESSAGES 1</literal>
+EOF</userinput></screen>
 
 <para>Compile the package:</para>

chapter06/glibc.xml

@@ -48 +48 @@
 of achieving a clean build.</para>
 
+<para>The glibc-libidn tarball adds support for internationalized
+domain names (IDN) to Glibc. Note that many programs that
+support IDN require the full libidn library from
+<ulink url="http://josefsson.org/libidn/releases/"/>, not this add-on.
+Unpack the tarball from within the Glibc source
+directory:</para>
+
+<screen><userinput>tar jxf ../glibc-libidn-&glibc-version;.tar.bz2</userinput></screen>
+
+<para>In the vi_VN.TCVN locale, bash enters infinite loop at startup. It is
+unknown whether this is a bash bug or a glibc problem. Disable installation
+of this locale in order to avoid the problem:</para>
+
+<screen><userinput>sed -i '/vi_VN.TCVN/d' localedata/SUPPORTED</userinput></screen>
+
 <para>The Glibc documentation recommends building Glibc outside of the source
 directory in a dedicated build directory:</para>
@@ -57 +72 @@
 
 <screen><userinput>../glibc-&glibc-version;/configure --prefix=/usr \
-    --disable-profile --enable-add-ons \
+    --disable-profile --enable-add-ons=nptl,libidn \
     --enable-kernel=2.6.0 --libexecdir=/usr/lib/glibc</userinput></screen>
 
@@ -129 +144 @@
 
 <screen><userinput>make localedata/install-locales</userinput></screen>
+
+<note><para>It is possible to create and install additional locales such as
+ru_RU.CP1251 by means of the <command>localedef</command> command, as
+explained in the <filename>INSTALL</filename> file in the Glibc source.</para></note>
+<!-- The Live CD patches the localedata/SUPPORTED file instead of running localedef -->
 
 <para>To save time, an alternative to running the
@@ -143 +163 @@
 for the tests to run successfully:</para>
 
+<!-- FIXME: recheck that "make localedata/install_locales" actually does the same -->
 <screen role="nodump"><userinput>mkdir -pv /usr/lib/locale
 localedef -i de_DE -f ISO-8859-1 de_DE
@@ -153 +174 @@
 localedef -i fr_FR -f ISO-8859-1 fr_FR
 localedef -i fr_FR@euro -f ISO-8859-15 fr_FR@euro
+localedef -i fr_FR.UTF-8 -f UTF-8 fr_FR
 localedef -i it_IT -f ISO-8859-1 it_IT
 localedef -i ja_JP -f EUC-JP ja_JP</userinput></screen>
 
-<para>Some locales installed by the <command>make
-localedata/install-locales</command> command above are not properly
-supported by some applications that are in the LFS and BLFS books.
-Because of the various problems that arise due to application
-programmers making assumptions that break in such locales, LFS should
-not be used in locales that utilize multibyte character sets
-(including UTF-8) or right-to-left writing order.  Numerous unofficial
-and unstable patches are required to fix these problems, and it has
-been decided by the LFS developers not to support such complex locales at this
-time.  This applies to the ja_JP and fa_IR locales as well&mdash;they have been
-installed only for GCC and Gettext tests to pass, and the
-<command>watch</command> program (part of the Procps package) does not work
-properly in them. Various attempts to circumvent these restrictions are
-documented in internationalization-related hints.</para>
-
+<para>The first <command>localedef</command> above combines the
+<filename>/usr/share/i18n/locales/de_DE</filename> charset-independent
+locale definition with the
+<filename>/usr/share/i18n/charmaps/ISO-8859-1.gz</filename> charmap definition
+and appends the result to the
+<filename>/usr/lib/locale/locale-archive</filename> file.</para>
 </sect2>
 

chapter06/grep.xml

@@ -28 +28 @@
 <sect2 role="installation">
 <title>Installation of Grep</title>
+
+<para>The original Grep package has many bugs, especially in the support of
+multibyte locales. RedHat fixed some of them by the following patch:</para>
+
+<screen><userinput>patch -Np1 -i ../&grep-fixes-patch;</userinput></screen>
+
+<para>In order for the tests added by this patch to pass, the permissions for
+the test file have to be changed:</para>
+
+<screen><userinput>chmod +x tests/fmbtest.sh</userinput></screen>
 
 <para>Prepare Grep for compilation:</para>

chapter06/groff.xml

@@ -29 +29 @@
 <title>Installation of Groff</title>
 
+<para>Apply the patch that adds the "ascii8" and "nippon" devices to Groff:</para>
+
+<screen><userinput>zcat ../&groff-debian-patch; | patch -Np1</userinput></screen>
+
+<note><para>These devices are used by Man-DB when formatting non-English manual
+pages that are not in the ISO-8859-1 encoding. There is no working patch for
+Groff-1.19.x that adds this functionality at the time of this writing.
+<!-- Details: http://bugs.debian.org/196762 -->
+</para></note>
+
+<para>Many screen fonts don't have Unicode dashes in them. Tell groff to use
+the ASCII hyphen instead:</para>
+
+<screen><userinput>sed -i 's,2010,002D,' font/devutf8/R.proto
+sed -i 's,2212,002D,' font/devutf8/R.proto</userinput></screen>
+
 <para>Groff expects the environment variable <envar>PAGE</envar>
 to contain the default paper size. For users in the United States,
 <parameter>PAGE=letter</parameter> is appropriate. Elsewhere,
-<parameter>PAGE=A4</parameter> may be more suitable.</para>
+<parameter>PAGE=A4</parameter> may be more suitable.
+The default paper size can be changed after installation by writing
+the word "A4" or "letter" to the <filename>/etc/papersize</filename>
+file.</para>
 
 <para>Prepare Groff for compilation:</para>

chapter06/kbd.xml

@@ -29 +29 @@
 <title>Installation of Kbd</title>
 
+<para>The behaviour of Backspace and Delete keys is not consistent across the
+keymaps in the Kbd package. The following patch fixes this issue for
+i386 keymaps:</para>
+
+<screen><userinput>patch -Np1 -i ../&kbd-backspace-patch;</userinput></screen>
+
+<para>After patching, the Backspace key generates the character with code 127,
+and the Delete key generates a well-known escape sequence.</para>
+
 <para>Patch Kbd to fix a bug in <command>setfont</command> that is triggered
 when compiling with GCC-&gcc-version;:</para>
@@ -47 +56 @@
 
 <screen><userinput>make install</userinput></screen>
+
+<note>For some languages, e.g. Belarusian, the Kbd package doesn't provide
+a useful keymap (the stock "by" keymap assumes the ISO-8859-5 encoding,
+while everybody uses CP1251 instead). Users of such languages
+have to download working keymaps separately.</note>
 
 </sect2>
@@ -275 +289 @@
 <term><command>unicode_start</command></term>
 <listitem>
-<para>Puts the keyboard and console in UNICODE mode. Never use it on LFS, 
-because applications are not configured to support UNICODE.</para>
+<para>Puts the keyboard and console in UNICODE mode. Don't use this program
+unless your keymap file is in the ISO-8859-1 encoding. For other encodings,
+this utility produces incorrect results.</para>
 <indexterm zone="ch-system-kbd unicode_start"><primary sortas="b-unicode_start">unicode_start</primary></indexterm>
 </listitem>

chapter06/man.xml

@@ -1 @@
-<?xml version="1.0" encoding="ISO-8859-1"?>
-<!DOCTYPE sect1 PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN" "http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd" [
-  <!ENTITY % general-entities SYSTEM "../general.ent">
-  %general-entities;
-]>
-<sect1 id="ch-system-man" role="wrap">
-<title>Man-&man-version;</title>
-<?dbhtml filename="man.html"?>
-
-<indexterm zone="ch-system-man"><primary sortas="a-Man">Man</primary></indexterm>
-
-<sect2 role="package"><title/>
-<para>The Man package contains programs for finding and viewing man pages.</para>
-
-<segmentedlist>
-<segtitle>&buildtime;</segtitle>
-<segtitle>&diskspace;</segtitle>
-<seglistitem><seg>0.1 SBU</seg><seg>1.3 MB</seg></seglistitem>
-</segmentedlist>
-
-<segmentedlist>
-<segtitle>&dependencies;</segtitle>
-<seglistitem><seg>Bash, Binutils, Coreutils, Gawk, GCC,
-Glibc, Grep, Make, and Sed</seg></seglistitem>
-</segmentedlist>
-</sect2>
-
-<sect2 role="installation">
-<title>Installation of Man</title>
-
-<para>Two adjustments need to be made to the sources of Man.</para>
-
-<para>The first is a <command>sed</command> substitution to add the
-<parameter>-R</parameter> switch to the <envar>PAGER</envar>
-variable so that escape sequences are properly handled by Less:</para>
-
-<screen><userinput>sed -i 's@-is@&amp;R@g' configure</userinput></screen>
-
-<para>The second is also a <command>sed</command> substitution to comment out the
-<quote>MANPATH /usr/man</quote> line in the
-<filename>man.conf</filename> file to prevent redundant results when
-using programs such as <command>whatis</command>:</para>
-
-<screen><userinput>sed -i 's@MANPATH./usr/man@#&amp;@g' src/man.conf.in</userinput></screen>
-
-<para>Prepare Man for compilation:</para>
-
-<screen><userinput>./configure -confdir=/etc</userinput></screen>
-
-<para>The meaning of the configure options:</para>
-
-<variablelist>
-<varlistentry>
-<term><parameter>-confdir=/etc</parameter></term>
-<listitem><para>This tells the <command>man</command> program to look for the
-<filename>man.conf</filename> configuration file in the <filename
-class="directory">/etc</filename> directory.</para></listitem>
-</varlistentry>
-</variablelist>
-
-<para>Compile the package:</para>
-
-<screen><userinput>make</userinput></screen>
-
-<para>This package does not come with a test suite.</para>
-
-<para>Install the package:</para>
-
-<screen><userinput>make install</userinput></screen>
-
-<note><para>If you will be working on a terminal that does not support text
-attributes such as color and bold, you can disable Select Graphic Rendition
-(SGR) escape sequences by editing the <filename>man.conf</filename> file and
-adding the <parameter>-c</parameter> option to the <envar>NROFF</envar>
-variable. If you use multiple terminal types for one computer it may be better
-to selectively add the <envar>GROFF_NO_SGR</envar> environment variable for the
-terminals that do not support SGR.</para></note>
-
-<para>If the character set of the locale uses 8-bit characters, search for the
-line beginning with <quote>NROFF</quote> in <filename>/etc/man.conf</filename>,
-and verify that it matches the following:</para>
-
-<screen>NROFF  /usr/bin/nroff -Tlatin1 -mandoc</screen>
-
-<para>Note that <quote>latin1</quote> should be used even if it is not
-the character set of the locale. The reason is that, according to the
-specification, <command>groff</command> has no means of typesetting
-characters outside International Organization for Standards
-(ISO) 8859-1 without some strange escape codes. When formatting man
-pages, <command>groff</command> thinks that they are in the ISO 8859-1
-encoding and this <parameter>-Tlatin1</parameter> switch tells
-<command>groff</command> to use the same encoding for output. Since
-<command>groff</command> does no recoding of input characters, the
-formatted result is really in the same encoding as input, and therefore
-it is usable as the input for a pager.</para>
-
-<para>This does not solve the problem of a non-working
-<command>man2dvi</command> program for localized man pages in
-non-ISO 8859-1 locales. Also, it does not work with multibyte
-character sets. The first problem does not currently have a solution.
-The second issue is not of concern because the LFS installation does
-not support multibyte character sets.</para>
-
-<para>Additional information with regards to the compression of
-man and info pages can be found in the BLFS book at
-<ulink url="&blfs-root;view/cvs/postlfs/compressdoc.html"/>.</para>
-
-</sect2>
-
-
-<sect2 id="contents-man" role="content"><title>Contents of Man</title>
-
-<segmentedlist>
-<segtitle>Installed programs</segtitle>
-<seglistitem><seg>apropos, makewhatis, man,
-man2dvi, man2html, and whatis</seg></seglistitem>
-</segmentedlist>
-
-<variablelist><bridgehead renderas="sect3">Short Descriptions</bridgehead>
-<?dbfo list-presentation="list"?>
-<?dbhtml list-presentation="table"?>
-
-<varlistentry id="apropos">
-<term><command>apropos</command></term>
-<listitem>
-<para>Searches the <command>whatis</command> database and displays the short descriptions
-of system commands that contain a given string</para>
-<indexterm zone="ch-system-man apropos"><primary sortas="b-apropos">apropos</primary></indexterm>
-</listitem>
-</varlistentry>
-
-<varlistentry id="makewhatis">
-<term><command>makewhatis</command></term>
-<listitem>
-<para>Builds the <command>whatis</command> database; it reads all the man pages
-in the <envar>MANPATH</envar> and writes the name and a short description in the
-<command>whatis</command> database for each page</para>
-<indexterm zone="ch-system-man makewhatis"><primary sortas="b-makewhatis">makewhatis</primary></indexterm>
-</listitem>
-</varlistentry>
-
-<varlistentry id="man">
-<term><command>man</command></term>
-<listitem>
-<para>Formats and displays the requested on-line man page</para>
-<indexterm zone="ch-system-man man"><primary sortas="b-man">man</primary></indexterm>
-</listitem>
-</varlistentry>
-
-<varlistentry id="man2dvi">
-<term><command>man2dvi</command></term>
-<listitem>
-<para>Converts a man page into dvi format</para>
-<indexterm zone="ch-system-man man2dvi"><primary sortas="b-man2dvi">man2dvi</primary></indexterm>
-</listitem>
-</varlistentry>
-
-<varlistentry id="man2html">
-<term><command>man2html</command></term>
-<listitem>
-<para>Converts a man page into HTML</para>
-<indexterm zone="ch-system-man man2html"><primary sortas="b-man2html">man2html</primary></indexterm>
-</listitem>
-</varlistentry>
-
-<varlistentry id="whatis">
-<term><command>whatis</command></term>
-<listitem>
-<para>Searches the <command>whatis</command> database and displays the short descriptions
-of system commands that contain the given keyword as a separate
-word</para>
-<indexterm zone="ch-system-man whatis"><primary sortas="b-whatis">whatis</primary></indexterm>
-</listitem>
-</varlistentry>
-</variablelist>
-
-</sect2>
-
-</sect1>
-

chapter06/ncurses.xml

@@ -29 +29 @@
 <sect2 role="installation">
 <title>Installation of Ncurses</title>
+<!-- Uncomment if using a dated ncurses release instead of a numbered one.
+
+<para>Since the release of Ncurses-&ncurses-version;, some bugs have been fixed
+and features added. The most important news are .......
+To get these fixes and features, apply the rollup patch:</para>
+
+<screen><userinput>bzcat ../&ncurses-rollup-patch; | patch -Np1</userinput></screen>
+-->
+
+<para>Since the release of Ncurses-&ncurses-version;, a memory leak and some
+display bugs were found and fixed upstream. Apply those fixes:</para>
+
+<screen><userinput>patch -Np1 -i ../&ncurses-fixes-patch;</userinput></screen>
 
 <para>Prepare Ncurses for compilation:</para>
 
-<screen><userinput>./configure --prefix=/usr --with-shared --without-debug</userinput></screen>
+<screen><userinput>./configure --prefix=/usr --with-shared --without-debug --enable-widec</userinput></screen>
+
+<para>The meaning of the configure options:</para>
+
+<variablelist>
+<varlistentry>
+<term><parameter>--enable-widec</parameter></term>
+<listitem><para>This switch causes wide-character libraries
+(e.g. <filename class="libraryfile">libncursesw.so.&ncurses-version;</filename>)
+to be built instead of normal ones
+(e.g. <filename class="libraryfile">libncurses.so.&ncurses-version;</filename>).
+Those wide-character libraries are usable in both multibyte and traditional 8-bit
+locales, while normal libraries work properly only in 8-bit locales.
+Wide-character and normal libraries are source-compatible, but not
+binary-compatible.</para>
+</listitem>
+</varlistentry>
+<!--
+<varlistentry>
+<term><parameter>- -without-cxx-binding</parameter></term>
+<listitem><para>This optional switch causes the
+<filename class="libraryfile">libncurses++w.a</filename> library
+not to be built. Nothing in LFS and BLFS uses this library.</para>
+</listitem>
+</varlistentry>
+-->
+</variablelist>
 
 <para>Compile the package:</para>
@@ -50 +89 @@
 <para>Fix a library that should not be executable:</para>
 
-<screen><userinput>chmod -v 644 /usr/lib/libncurses++.a</userinput></screen>
+<screen><userinput>chmod -v 644 /usr/lib/libncurses++w.a</userinput></screen>
 
 <para>Move the libraries to the <filename class="directory">/lib</filename> directory,
 where they are expected to reside:</para>
 
-<screen><userinput>mv -v /usr/lib/libncurses.so.5* /lib</userinput></screen>
-
-<para>Because the libraries have been moved, a few symlinks point to
-non-existent files. Recreate those symlinks:</para>
-
-<screen><userinput>ln -sfv ../../lib/libncurses.so.5 /usr/lib/libncurses.so
-ln -sfv libncurses.so /usr/lib/libcurses.so</userinput></screen>
+<screen><userinput>mv -v /usr/lib/libncursesw.so.5* /lib</userinput></screen>
+
+<para>Because the libraries have been moved, one symlink points to
+a non-existent file. Recreate it:</para>
+
+<screen><userinput>ln -sfv ../../lib/libncursesw.so.5 /usr/lib/libncursesw.so</userinput></screen>
+
+<para>Many applications still expect the linker to be able to find
+non-wide-character Ncurses libraries. Trick such applications into linking with
+wide-character libraries by means of symlinks and linker scripts:</para>
+
+<screen><userinput>for lib in curses ncurses form panel menu ; do \
+        rm -vf /usr/lib/lib${lib}.so ; \
+        echo "INPUT(-l${lib}w)" &gt;/usr/lib/lib${lib}.so ; \
+        ln -sfv lib${lib}w.a /usr/lib/lib${lib}.a ; \
+done &amp;&amp;
+ln -sfv libncurses++w.a /usr/lib/libncurses++.a</userinput></screen>
+
+<para>Finally, make sure that really old applications that look for
+<filename class="libaryfile">-lcurses</filename> at build time are still
+buildable:</para>
+
+<screen><userinput>echo "INPUT(-lncursesw)" &gt;/usr/lib/libcursesw.so &amp;&amp;
+ln -sfv libncurses.so /usr/lib/libcurses.so &amp;&amp;
+ln -sfv libncursesw.a /usr/lib/libcursesw.a &amp;&amp;
+ln -sfv libncurses.a /usr/lib/libcurses.a</userinput></screen>
+
+<note><para>The instructions above don't create non-wide-character Ncurses
+libraries since nothing in LFS and BLFS would link against them at runtime.
+If you must have such libraries because of some binary-only application,
+build them with the following commands:</para>
+<screen role="nodump"><userinput>make distclean &amp;&amp;
+./configure --prefix=/usr --with-shared --without-normal \
+        --without-debug --without-cxx-binding &amp;&amp;
+make sources libs &amp;&amp;
+cp -av lib/lib*.so.5* /usr/lib</userinput></screen>
+</note>
 </sect2>
 
@@ -72 +141 @@
 <seglistitem><seg>captoinfo (link to tic), clear, infocmp, infotocap (link to tic), 
 reset (link to tset), tack, tic, toe, tput, and tset</seg>
-<seg>libcurses.[a,so] (link to libncurses.[a,so]), libform.[a,so], libmenu.[a,so], 
-libncurses++.a, libncurses.[a,so], and libpanel.[a,so]</seg></seglistitem>
+<seg>libcursesw.[a,so] (symlink and linker script to libncursesw.[a,so]),
+libformw.[a,so], libmenuw.[a,so], 
+libncurses++w.a, libncursesw.[a,so], libpanelw.[a,so] and their
+non-wide-character counterparts without "w" in the library names.</seg></seglistitem>
 </segmentedlist>
 
@@ -213 +284 @@
 
 </sect1>
-

chapter06/readline.xml

@@ -44 +44 @@
 <term><parameter>SHLIB_LIBS=-lncurses</parameter></term>
 <listitem><para>This option forces Readline to link against the
-<filename class="libraryfile">libncurses</filename> library.</para></listitem>
+<filename class="libraryfile">libncurses</filename>
+(really, <filename class="libraryfile">libncursesw</filename>)
+library.</para></listitem>
 </varlistentry>
 </variablelist>

chapter06/sysklogd.xml

@@ -33 +33 @@
 
 <screen><userinput>patch -Np1 -i ../&sysklogd-fixes-patch;</userinput></screen>
+
+<para>The following patch makes sysklogd treat bytes in the 0x80--0x9f range
+literally in the messages being logged, instead of replacing them with octal
+codes. Such replacement caused damage to messages in UTF-8 encoding.</para>
+
+<screen><userinput>patch -Np1 -i ../&sysklogd-8bit-patch;</userinput></screen>
 
 <para>Compile the package:</para>

chapter06/sysvinit.xml

@@ -85 +85 @@
 su:S016:once:/sbin/sulogin
 
-1:2345:respawn:/sbin/agetty -I '\033(K' tty1 9600
-2:2345:respawn:/sbin/agetty -I '\033(K' tty2 9600
-3:2345:respawn:/sbin/agetty -I '\033(K' tty3 9600
-4:2345:respawn:/sbin/agetty -I '\033(K' tty4 9600
-5:2345:respawn:/sbin/agetty -I '\033(K' tty5 9600
-6:2345:respawn:/sbin/agetty -I '\033(K' tty6 9600
+1:2345:respawn:/sbin/agetty tty1 9600
+2:2345:respawn:/sbin/agetty tty2 9600
+3:2345:respawn:/sbin/agetty tty3 9600
+4:2345:respawn:/sbin/agetty tty4 9600
+5:2345:respawn:/sbin/agetty tty5 9600
+6:2345:respawn:/sbin/agetty tty6 9600
 
 # End /etc/inittab</literal>
 EOF</userinput></screen>
-
-<para>The <parameter>-I '\033(K'</parameter> option tells
-<command>agetty</command> to send this escape sequence to the terminal
-before doing anything else. This escape sequence switches the console
-character set to a user-defined one, which can be modified by running
-the <command>setfont</command> program. The <command>console</command>
-initscript from the LFS-Bootscripts package calls the <command>setfont</command>
-program during system startup. Sending this escape sequence is
-necessary for people who use non-ISO 8859-1 screen fonts, but it does
-not affect native English speakers.</para>
-
 </sect2>
 

chapter06/texinfo.xml

@@ -29 +29 @@
 <sect2 role="installation">
 <title>Installation of Texinfo</title>
+
+<para>The <command>info</command> program makes assumptions such as "a string
+occupies the same number of character cells on the screen and bytes in memory"
+and "one can break the string anywhere" that are incorrect in UTF-8 locales.
+While the patch below is not the proper solution, it at least hides the problem
+by falling back to English messages when a multibyte locale is in use:</para>
+
+<screen><userinput>patch -Np1 -i ../&texinfo-multibyte-patch;</userinput></screen>
 
 <para>Texinfo allows local users to overwrite arbitrary files via a symlink

chapter06/udev.xml

@@ -79 +79 @@
 <screen><userinput>install -m644 -D -v docs/writing_udev_rules/index.html /usr/share/doc/udev-&udev-version;/index.html</userinput></screen>
 
+<!-- Not for the LiveCD -->
 <!-- Edit Me -->
 <para>Run the <command>udevstart</command> program to create our full

chapter06/vim.xml

@@ -54 +54 @@
 <varlistentry>
 <term><parameter>--enable-multibyte</parameter></term>
-<listitem><para>This optional but highly recommended switch enables support for
+<listitem><para>This switch enables support for
 editing files in multibyte character encodings.  This is needed if using a
 locale with a multibyte character set. This switch is also helpful to be able to
@@ -75 +75 @@
 
 <screen><userinput>make install</userinput></screen>
+
+<para>In UTF-8 locales, the <command>vimtutor</command> program
+tries to convert the tutorials from ISO-8859-1 to UTF-8. Since
+some tutorials are not in ISO-8859-1, the text in them is thus made unreadable.
+If you unpacked the <filename>vim-&vim-version;-lang.tar.gz</filename>
+archive and are going to use a UTF-8 based locale, remove non-ISO-8859-1
+tutorials. An English tutorial will be used instead.</para>
+<!-- Removal is used instead of conversion in order for the user to be able to
+painlessly revert his UTF-8 locale choice. -->
+
+<screen><userinput>rm -f /usr/share/vim/vim64/tutor/tutor.{gr,pl,ru,sk}
+rm -f /usr/share/vim/vim64/tutor/tutor.??.*</userinput></screen>
 
 <para>Many users are used to using <command>vi</command> instead of

chapter07/bootscripts.xml

@@ -47 +47 @@
 
 <screen><userinput>make install</userinput></screen>
+
+    <para>The <command>console</command> script that comes with
+    LFS-Bootscripts-&lfs-bootscripts-version; doesn't support Unicode. Install
+    a replacement version:</para>
+
+<screen><userinput>install -m755 ../console /etc/rc.d/init.d</userinput></screen>
 
   </sect2>

chapter07/console.xml

@@ -18 +18 @@
   <para>This section discusses how to configure the <command>console</command>
   bootscript that sets up the keyboard map and the console font. If non-ASCII
-  characters (e.g., the British pound sign and Euro character) will not be used
-  and the keyboard is a U.S. one, skip this section. Without the configuration
-  file, the <command>console</command> bootscript will do nothing.</para>
+  characters (e.g., the copyright sign, the British pound sign and Euro symbol)
+  will not be used and the keyboard is a U.S. one, skip this section. Without
+  the configuration file, the <command>console</command> bootscript will do
+  nothing.</para>
 
   <para>The <command>console</command> script reads the
   <filename>/etc/sysconfig/console</filename> file for configuration information.
   Decide which keymap and screen font will be used. Various language-specific
-  HOWTO's can also help with this (see <ulink
-  url="http://www.tldp.org/HOWTO/HOWTO-INDEX/other-lang.html"/>. A pre-made
-  <filename>/etc/sysconfig/console</filename> file with known settings for several
-  countries was installed with the LFS-Bootscripts package, so the relevant
-  section can be uncommented if the country is supported. If still in doubt, look
-  in the <filename class="directory">/usr/share/kbd</filename> directory for valid
-  keymaps and screen fonts. Read <filename>loadkeys(1)</filename> and
-  <filename>setfont(8)</filename> to determine the correct arguments for
-  these programs. Once decided, create the configuration file with the following
-  command:</para>
-
-<screen><userinput>cat &gt;/etc/sysconfig/console &lt;&lt;"EOF"
-<literal>KEYMAP="<replaceable>[arguments for loadkeys]</replaceable>"
-FONT="<replaceable>[arguments for setfont]</replaceable>"</literal>
-EOF</userinput></screen>
-
-  <para>For example, for Spanish users who also want to use the Euro
-  character (accessible by pressing AltGr+E), the following settings are
-  correct:</para>
-
-<screen role="nodump"><userinput>cat &gt;/etc/sysconfig/console &lt;&lt;"EOF"
-<literal>KEYMAP="es euro2"
-FONT="lat9-16 -u iso01"</literal>
-EOF</userinput></screen>
-
+  HOWTO's can also help with this, see <ulink
+  url="http://www.tldp.org/HOWTO/HOWTO-INDEX/other-lang.html"/>. If still in
+  doubt, look in the <filename class="directory">/usr/share/kbd</filename>
+  directory for valid keymaps and screen fonts. Read
+  <filename>loadkeys(1)</filename> and <filename>setfont(8)</filename> manual
+  pages to determine the correct arguments for these programs.</para>
+
+  <para>The <filename>/etc/sysconfig/console</filename> file should contain lines
+  of the form: VARIABLE="value". The following variables are recognized:</para>
+
+  <variablelist>
+
+    <varlistentry>
+      <term>KEYMAP</term>
+      <listitem>
+        <para>This variable specifies the arguments for the
+        <command>loadkeys</command> program, typically, the name of keymap
+        to load, e.g. "es". If this variable is not set, the bootscript will
+        not run the <command>loadkeys</command> program, and the default kernel
+        keymap will be used.</para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>KEYMAP_CORRECTIONS</term>
+      <listitem>
+        <para>This (rarely used) variable
+        specifies the arguments for the second call to the
+        <command>loadkeys</command> program. This is useful if the stock keymap
+        is not completely satisfactory and a small adjustment has to be made. E.g.,
+        to include the Euro sign into a keymap that normally doesn't have it,
+        set this variable to "euro2".</para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>FONT</term>
+      <listitem>
+        <para>This variable specifies the arguments for the
+        <command>setfont</command> program. Typically, this includes the font
+        name, "-m", and the name of the application character map to load.
+        E.g., in order to load the "lat1-16" font together with the "8859-1"
+        application character map, set this variable to "lat1-16 -m 8859-1".
+        If this variable is not set, the bootscript will not run the
+        <command>setfont</command> program, and the default VGA font will be
+        used together with the default application character map.</para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>UNICODE</term>
+      <listitem>
+        <para>Set this variable to "1", "yes" or "true" in order to put the
+        console into UTF-8 mode. This is useful in UTF-8 based locales and
+        harmful otherwise.</para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>LEGACY_CHARSET</term>
+      <listitem>
+        <para>For many keyboard layouts, there is no stock Unicode keymap in
+        the Kbd package. The <command>console</command> bootscript will
+        convert an available keymap to UTF-8 on the fly if this variable is
+        set to the encoding of the available non-UTF-8 keymap. Note, however,
+        that dead keys and composing will not work in UTF-8 mode without the
+        special kernel patch.</para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry>
+      <term>BROKEN_COMPOSE</term>
+      <listitem>
+        <para>Set this to "0" if you are going to apply that kernel patch in
+        Chapter 8. Note that you also have to add the character set expected
+        by composition rules in your keymap to the FONT variable after the
+        "-m" switch.</para>
+      </listitem>
+    </varlistentry>
+
+  </variablelist>
+
+  <para>Support for compiling the keymap directly into the kernel has been
+  removed because there were reports that it leads to incorrect results.</para>
+
+  <para>Some examples:</para>
+
+  <itemizedlist>
+
+    <listitem>
+      <para>For a non-Unicode setup, only the KEYMAP and FONT variables are
+      generally needed. E.g., for a Polish setup, one would use:</para>
+
+<screen role="nodump"><userinput>cat &gt; /etc/sysconfig/console &lt;&lt; "EOF"
+<literal># Begin /etc/sysconfig/console
+
+KEYMAP="pl2"
+FONT="lat2a-16 -m 8859-2"
+
+# End /etc/sysconfig/console</literal>
+EOF</userinput></screen>
+    </listitem>
+
+    <listitem>
+      <para>As mentioned above, it is sometimes necessary to adjust a
+      stock keymap slightly. The following example adds the Euro symbol to the
+      German keymap:</para>
+
+<screen role="nodump"><userinput>cat &gt; /etc/sysconfig/console &lt;&lt; "EOF"
+<literal># Begin /etc/sysconfig/console
+
+KEYMAP="de-latin1"
+KEYMAP_CORRECTIONS="euro2"
+FONT="lat0-16 -m 8859-15"
+
+# End /etc/sysconfig/console</literal>
+EOF</userinput></screen>
+    </listitem>
+
+    <listitem>
+      <para>Here is a Unicode-enabled example for Bulgarian, where a stock
+      UTF-8 keymap exists and defines no dead keys or composition rules:</para>
+
+<screen role="nodump"><userinput>cat &gt; /etc/sysconfig/console &lt;&lt; "EOF"
+<literal># Begin /etc/sysconfig/console
+
+UNICODE="1"
+KEYMAP="bg_bds-utf8"
+FONT="LatArCyrHeb-16"
+
+# End /etc/sysconfig/console</literal>
+EOF</userinput></screen>
+    </listitem>
+
+    <listitem>
+      <para>Due to the use of a 512-glyph LatArCyrHeb-16 font in the previous
+      example, bright colors are no longer available on the Linux console unless
+      a framebuffer is used. If one wants to have bright colors without
+      framebuffer and can live without characters not belonging to his language,
+      it is still possible to use a language-specific 256-glyph font, as
+      illustrated below. This would, however, also break single quotes in manual
+      pages.</para>
+
+      <!-- And even with the LatArCyrHeb-16 font, copying-and-pasting produces
+      non-ASCII variants of opening and closing single quote instead of ` and '.
+      Maybe another sed has to be added to groff instructions that will remove
+      both issues. -->
+
+<screen role="nodump"><userinput>cat &gt; /etc/sysconfig/console &lt;&lt; "EOF"
+<literal># Begin /etc/sysconfig/console
+
+UNICODE="1"
+KEYMAP="bg_bds-utf8"
+FONT="cyr-sun16"
+
+# End /etc/sysconfig/console</literal>
+EOF</userinput></screen>
+    </listitem>
+
+    <listitem>
+      <para>The following example illustrates keymap autoconversion from
+      ISO-8859-15 to UTF-8 and enabling dead keys in Unicode mode:</para>
+
+<screen role="nodump"><userinput>cat &gt; /etc/sysconfig/console &lt;&lt; "EOF"
+<literal># Begin /etc/sysconfig/console
+
+UNICODE="1"
+KEYMAP="de-latin1"
+KEYMAP_CORRECTIONS="euro2"
+LEGACY_CHARSET="iso-8859-15"
+BROKEN_COMPOSE="0"
+FONT="LatArCyrHeb-16 -m 8859-15"
+
+# End /etc/sysconfig/console</literal>
+EOF</userinput></screen>
+    </listitem>
+
+    <listitem>
+      <para>For Chinese, Japanese, Korean and some other languages, the Linux
+      console cannot be configured to display the needed characters. Users
+      who need such languages should install the X Window System, fonts that
+      cover the necessary character ranges, and the proper input Method (e.g.
+      SCIM, it supports a wide variety of languages).</para>
+    </listitem>
+
+  </itemizedlist>
+
+  <!-- Added because folks keep posting their console file with X questions
+  to blfs-support list -->
   <note>
-    <para>The <envar>FONT</envar> line above is correct only for the ISO 8859-15
-    character set. If using ISO 8859-1 and, therefore, a pound sign
-    instead of Euro, the correct <envar>FONT</envar> line would be:</para>
-
-<screen role="nodump"><userinput>FONT="lat1-16"</userinput></screen>
+    <para>The <filename>/etc/sysconfig/console</filename> file only controls
+    Linux text console localization. It has nothing to do with setting the proper
+    keyboard layout and terminal fonts in X Window System.</para>
   </note>
 
-  <para>If the <envar>KEYMAP</envar> or <envar>FONT</envar> variable is not set,
-  the <command>console</command> initscript will not run the corresponding
-  program.</para>
-
-  <para>In some keymaps, the Backspace and Delete keys send characters different
-  from ones in the default keymap built into the kernel. This confuses some
-  applications. For example, Emacs displays its help (instead of erasing the
-  character before the cursor) when Backspace is pressed. To check if the keymap
-  in use is affected (this works only for i386 keymaps):</para>
-
-<screen role="nodump"><userinput>zgrep '\W14\W' <replaceable>[/path/to/your/keymap]</replaceable></userinput></screen>
-
-  <para>If the keycode 14 is Backspace instead of Delete, create the
-  following keymap snippet to fix this issue:</para>
-
-<screen role="nodump"><userinput>mkdir -pv /etc/kbd &amp;&amp; cat &gt; /etc/kbd/bs-sends-del &lt;&lt;"EOF"
-<literal>                  keycode  14 = Delete Delete Delete Delete
-              alt keycode  14 = Meta_Delete
-        altgr alt keycode  14 = Meta_Delete
-                  keycode 111 = Remove
-    altgr control keycode 111 = Boot
-      control alt keycode 111 = Boot
-altgr control alt keycode 111 = Boot</literal>
-EOF</userinput></screen>
-
-  <para>Tell the <command>console</command> script to load this
-  snippet after the main keymap:</para>
-
-<screen role="nodump"><userinput>cat &gt;&gt;/etc/sysconfig/console &lt;&lt;"EOF"
-<literal>KEYMAP_CORRECTIONS="/etc/kbd/bs-sends-del"</literal>
-EOF</userinput></screen>
-
-  <para>To compile the keymap directly into the kernel instead of
-  setting it every time from the <command>console</command> bootscript,
-  follow the instructions given in <xref linkend="ch-bootable-kernel" role="."/>
-  Doing this ensures that the keyboard will always work as expected,
-  even when booting into maintenance mode (by passing
-  <parameter>init=/bin/sh</parameter> to the kernel), because the
-  <command>console</command> bootscript will not be run in that
-  situation. Additionally, the kernel will not set the screen font
-  automatically. This should not pose many problems because ASCII characters
-  will be handled correctly, and it is unlikely that a user would need
-  to rely on non-ASCII characters while in maintenance mode.</para>
-
-  <para>Since the kernel will set up the keymap, it is possible to omit
-  the <envar>KEYMAP</envar> variable from the
-  <filename>/etc/sysconfig/console</filename> configuration file. It can
-  also be left in place, if desired, without consequence.  Keeping it
-  could be beneficial if running several different kernels where it is
-  difficult to ensure that the keymap is compiled into every one of
-  them.</para>
-
 </sect1>

chapter07/profile.xml

@@ -70 +70 @@
   <replaceable>[CC]</replaceable> with the two-letter code for the appropriate
   country (e.g., <quote>GB</quote>). <replaceable>[charmap]</replaceable> should
-  be replaced with the canonical charmap for your chosen locale.</para>
+  be replaced with the canonical charmap for your chosen locale. Optional
+  modifiers such as <quote>@euro</quote> may also be present.</para>
 
   <para>The list of all locales supported by Glibc can be obtained by running
@@ -77 +78 @@
 <screen role="nodump"><userinput>locale -a</userinput></screen>
 
-  <para>Locales can have a number of synonyms, e.g. <quote>ISO-8859-1</quote>
+  <para>Charmaps can have a number of aliases, e.g. <quote>ISO-8859-1</quote>
   is also referred to as <quote>iso8859-1</quote> and <quote>iso88591</quote>.
-  Some applications cannot handle the various synonyms correctly, so it is
-  safest to choose the canonical name for a particular locale. To determine
+  Some applications cannot handle the various synonyms correctly (e.g. require
+  that "UTF-8" is written as "UTF-8", not "utf8"), so it is safest in most
+  cases to choose the canonical name for a particular locale. To determine
   the canonical name, run the following command, where <replaceable>[locale
   name]</replaceable> is the output given by <command>locale -a</command> for
@@ -116 +118 @@
   Glibc.</para>
 
+  <!-- FIXME: the xlib example will became obsolete real soon -->
   <para>Some packages beyond LFS may also lack support for your chosen locale. One
   example is the X library (part of the X Window System), which outputs the
@@ -140 +143 @@
 <literal># Begin /etc/profile
 
-export LANG=<replaceable>[ll]</replaceable>_<replaceable>[CC]</replaceable>.<replaceable>[charmap]</replaceable>
+export LANG=<replaceable>[ll]</replaceable>_<replaceable>[CC]</replaceable>.<replaceable>[charmap]</replaceable><replaceable>[@modifiers]</replaceable>
 export INPUTRC=/etc/inputrc
 
@@ -146 +149 @@
 EOF</userinput></screen>
 
+  <para>The <quote>C</quote> (default) and <quote>en_US</quote> (the recommended
+  one for United States English users) locales are different. <quote>C</quote>
+  uses the US-ASCII 7-bit character set, and treats bytes with the high bit set
+  as invalid characters. That's why, e.g., the <command>ls</command> command
+  substitutes them with question marks in that locale. Also, an attempt to send
+  mail with such characters from Mutt or Pine results in non-RFC-conforming
+  messages being set (the charset in the outgoing mail is indicatsed as "unknown
+  8-bit"). So you can use the <quote>C</quote> locale only if you are sure that
+  you will never need 8-bit characters.</para>
+
+  <para>UTF-8 based locales are not supported well by many programs. E.g., the
+  <command>watch</command> program displays only ASCII characters in UTF-8
+  locales and has no such restriction in traditional 8-bit locales like en_US.
+  Without patches and/or installing software beyond BLFS, in UTF-8 based locales
+  you will not be able to do such basic tasks as printing plain-text files from
+  the command line, recording Windows-readable CDs with filenames containing
+  non-ASCII characters, viewing ID3v1 tags in MP3 files and so on. It is also
+  impossible (without damaging non-ASCII characters) to connect using ssh from
+  the system using a UTF-8 based locale to a host that still uses a traditional
+  8-bit locale, and vice versa. In short, use UTF-8 only if you are going to
+  use KDE or GNOME and never open the terminal, or if you are going to tolerate
+  bugs.</para>
+  <!-- All abovementioned problems except "watch" have a known fix beyond BLFS -->
+
   <note>
-    <para>The <quote>C</quote> (default) and <quote>en_US</quote> (the
-    recommended one for United States English users) locales are different.</para>
+    <para>Bug reports reproducible only in UTF-8 locales and for which there
+    is no patch or other fix mentioned in the report, will be closed immediately,
+    without investigation, with the "WONTFIX" resolution and a "don't use this
+    program or revert to non-UTF-8 locale" comment. Patches that have ill
+    effects in non-UTF-8 locales (other than replacement of translated program
+    messages with English ones) will be rejected.</para>
   </note>
 
-  <para>Setting the keyboard layout, screen font, and locale-related environment
-  variables are the only internationalization steps needed to support locales
-  that use ordinary single-byte encodings and left-to-right writing direction.
-  More complex cases (including UTF-8 based locales) require additional steps
-  and additional patches because many applications tend to not work properly
-  under such conditions. These steps and patches are not included in the LFS
-  book and such locales are not yet supported by LFS.</para>
-
 </sect1>

chapter08/fstab.xml

@@ -66 +66 @@
   <filename>/etc/sysconfig/modules</filename>.</para>
 
+  <para>Filesystems with MS-DOS or Windows origin (i.e.: vfat, ntfs, smbfs, cifs,
+  iso9660, udf) need the <quote>iocharset</quote> mount option in order for
+  non-ASCII characters in file names to be interpreted properly. The value
+  of this option should be the same as the character set of your locale,
+  adjusted in such a way that the kernel understands it. This works if the
+  relevant character set definition (found under File systems -&gt;
+  Native Language Support) has been compiled into the kernel
+  or built as a module. The <quote>codepage</quote> option is also needed for
+  vfat and smbfs filesystems. It
+  should be set to the codepage number used under MS-DOS in your country. E.g.,
+  in order to mount USB flash drives, a ru_RU.KOI8-R user would need the
+  following line in <filename>/etc/fstab</filename>:</para>
+
+<screen>/dev/sda1    /media/flash vfat noauto,user,quiet,showexec,iocharset=koi8r,codepage=866 0 0</screen>
+
+  <para>The corresponding line for ru_RU.UTF-8 users is:</para>
+
+<screen>/dev/sda1    /media/flash vfat noauto,user,quiet,showexec,iocharset=utf8,codepage=866 0 0</screen>
+
+  <note><para>In the latter case, the kernel emits the following message:</para>
+
+<screen><computeroutput>FAT: utf8 is not a recommended IO charset for FAT filesystems, filesystem will be case sensitive!</computeroutput></screen>
+
+  <para>This negative recommendation should be ignored, since all other values
+  of the <quote>iocharset</quote> option result in wrong display of filenames in
+  UTF-8 locales.</para></note>
+
+  <para>It is also possible to specify default codepage and iocharset values for
+  some filesystems during kernel configuration, the relevant parameters
+  are named
+  <quote>Default NLS Option</quote> (CONFIG_NLS_DEFAULT),
+  <quote>Default Remote NLS Option</quote> (CONFIG_SMB_NLS_DEFAULT),
+  <quote>Default codepage for FAT</quote> (CONFIG_FAT_DEFAULT_CODEPAGE), and
+  <quote>Default iocharset for FAT</quote> (CONFIG_FAT_DEFAULT_IOCHARSET).
+  There is no way to specify these settings for the
+  ntfs filesystem at kernel compilation time.</para>
+  <!-- Personally, I find it more foolproof to always specify the iocharset and
+  codepage in /etc/fstab for MS-based filesystems - Alexander E. Patrakov -->
+
 </sect1>

chapter08/kernel.xml

@@ -49 +49 @@
     configures the kernel.</para>
 
+    <para>By default, Linux kernel generates wrong sequences of bytes when
+    dead keys are used in UTF-8 keyboard mode. Also, one cannot copy and paste
+    non-ASCII characters when UTF-8 mode is aciive. Fix these issues with the
+    patch:</para>
+
+<screen><userinput>patch -Np1 -i ../&linux-utf8-patch;</userinput></screen>
+
     <para>Prepare for compilation by running the following command:</para>
 
@@ -58 +65 @@
     un-tarring.</para>
 
-    <para>If, in <xref linkend="ch-scripts-console" role=","/> it was decided to
-    compile the keymap into the kernel, issue the command below:</para>
-
-<screen role="nodump"><userinput>loadkeys -m /usr/share/kbd/keymaps/<replaceable>[path to  keymap]</replaceable> &gt; \
-    drivers/char/defkeymap.c</userinput></screen>
-
-    <para>For example, if using a Dutch keyboard, use
-    <filename>/usr/share/kbd/keymaps/i386/qwerty/nl.map.gz</filename>.</para>
+    <!-- Support for compiling a keymap into the kernel is deliberately removed -->
 
     <para>Configure the kernel via a menu-driven interface. BLFS has some

general.ent

@@ -23 +23 @@
 <!ENTITY kernel "http://www.kernel.org/pub/">
 <!ENTITY sourceforge "http://prdownloads.sourceforge.net/">
+<!ENTITY alexpatches "&lfs-root;~alexander/patches/">
 
 <!ENTITY % patches-entities SYSTEM "patches.ent">
@@ -45 +46 @@
 <!ENTITY gawk-version "3.1.5">
 <!ENTITY gcc-version "4.0.2">
+<!ENTITY gdbm-version "1.8.3">
 <!ENTITY gettext-version "0.14.5">
 <!ENTITY glibc-version "2.3.6">
 <!ENTITY grep-version "2.5.1a">
-<!ENTITY groff-version "1.19.2">
+<!ENTITY groff-version "1.18.1.1">
+<!ENTITY groff-patchlevel "10">
 <!ENTITY grub-version "0.97">
 <!ENTITY gzip-version "1.3.5">
@@ -64 +67 @@
 <!ENTITY m4-version "1.4.4">
 <!ENTITY make-version "3.80">
-<!ENTITY man-version "1.6b">
+<!ENTITY man-db-version "2.4.3">
 <!ENTITY man-pages-version "2.17">
 <!ENTITY mktemp-version "1.5">
 <!ENTITY module-init-tools-version "3.2.2">
 <!ENTITY ncurses-version "5.5">
+<!-- <!ENTITY ncurses-date "20050319"> -->
 <!ENTITY patch-version "2.5.4">
 <!ENTITY perl-version "5.8.7">

patches.ent

@@ -2 +2 @@
 
 <!-- Start of Common Patches -->
+<!ENTITY bzip2-bzgrep-patch "bzip2-&bzip2-version;-bzgrep_security-1.patch">
 <!ENTITY bzip2-docs-patch "bzip2-&bzip2-version;-install_docs-1.patch">
-<!ENTITY bzip2-bzgrep-patch "bzip2-&bzip2-version;-bzgrep_security-1.patch">
 
+<!ENTITY coreutils-i18n-patch "coreutils-&coreutils-version;-i18n-1.patch">
 <!ENTITY coreutils-suppress-patch "coreutils-&coreutils-version;-suppress_uptime_kill_su-1.patch">
 <!ENTITY coreutils-uname-patch "coreutils-&coreutils-version;-uname-1.patch">
+
+<!ENTITY diffutils-i18n-patch "diffutils-&diffutils-version;-i18n-1.patch">
 
 <!ENTITY expect-spawn-patch "expect-&expect-version;-spawn-1.patch">
@@ -16 +19 @@
 <!ENTITY gcc-specs-patch "gcc-&gcc-version;-specs-1.patch">
 
+<!ENTITY grep-fixes-patch "grep-&grep-version;-redhat_fixes-2.patch">
+
+<!ENTITY groff-debian-patch "groff_&groff-version;-&groff-patchlevel;.diff.gz">
+
 <!ENTITY gzip-security_fix-patch "gzip-&gzip-version;-security_fixes-1.patch">
 
+<!ENTITY kbd-backspace-patch "kbd-&kbd-version;-backspace-1.patch">
 <!ENTITY kbd-gcc4_fixes-patch "kbd-&kbd-version;-gcc4_fixes-1.patch">
 
@@ -23 +31 @@
 <!ENTITY inetutils-man_pages-patch "inetutils-&inetutils-version;-no_server_man_pages-1.patch">
 
+<!ENTITY linux-utf8-patch "linux-&linux-version;-utf8_input-2.patch">
+
 <!ENTITY mktemp-tempfile-patch "mktemp-&mktemp-version;-add_tempfile-3.patch">
 
+<!ENTITY ncurses-fixes-patch "ncurses-&ncurses-version;-fixes-1.patch">
+<!-- <!ENTITY ncurses-rollup-patch "ncurses-&ncurses-version;-&ncurses-date;-patch.sh.bz2"> -->
+
 <!ENTITY perl-libc-patch "perl-&perl-version;-libc-1.patch">
+
+<!ENTITY sysklogd-8bit-patch "sysklogd-&sysklogd-version;-8bit-1.patch">
 
 <!ENTITY shadow-configure-patch "shadow-&shadow-version;-configure_fix-1.patch">
@@ -31 +46 @@
 <!ENTITY sysklogd-fixes-patch "sysklogd-&sysklogd-version;-fixes-1.patch">
 
+<!ENTITY tar-gcc4_fix-patch "tar-&tar-version;-gcc4_fix_tests-1.patch">
 <!ENTITY tar-sparse_fix-patch "tar-&tar-version;-sparse_fix-1.patch">
-<!ENTITY tar-gcc4_fix-patch "tar-&tar-version;-gcc4_fix_tests-1.patch">
 
-<!ENTITY texinfo-tempfile_fix-patch "texinfo-&texinfo-version;-tempfile_fix-2.patch">
+<!ENTITY texinfo-multibyte-patch "texinfo-&texinfo-version;-multibyte-2.patch">
+<!ENTITY texinfo-tempfile_fix-patch "texinfo-&texinfo-version;-tempfile_fix-1.patch">
 
 <!ENTITY util-linux-cramfs-patch "util-linux-&util-linux-version;-cramfs-1.patch">