After adding the AddCharset's back in; here is some

minor stuff to make that work and some examples.

PR:
Obtained from:
Submitted by:
Reviewed by:


git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@84786 13f79535-47bb-0310-9956-ffa450edef68

2 files changed, 72 insertions, 16 deletions

diff --git a/docs/conf/httpd-std.conf b/docs/conf/httpd-std.conf
index 7b0f6632ad..6f45132efd 100644
--- a/docs/conf/httpd-std.conf
+++ b/docs/conf/httpd-std.conf
@@ -630,9 +630,20 @@ AddEncoding x-compress Z
 AddEncoding x-gzip gz tgz
 
 #
-# AddLanguage allows you to specify the language of a document. You can
-# then use content negotiation to give a browser a file in a language
-# it can understand.
+# DefaultLanguage and AddLanguage allows you to specify the language of 
+# a document. You can then use content negotiation to give a browser a 
+# file in a language the user can understand.
+#
+# Specify a default langyage. This means that all data
+# going out without a specific language tag (See below) will 
+# be marked with this one. You propably do NOT want to set
+# this unless you are sure it is correct for all cases.
+#
+# * It is generally better to not mark a pages as in
+# * being a certain language than marking it with the wrong
+# * language!
+#
+# DefaultLanguage nl
 #
 # Note 1: The suffix does not have to be the same as the language
 # keyword --- those with documents in Polish (whose net-standard
@@ -648,7 +659,7 @@ AddEncoding x-gzip gz tgz
 # specifier. But there is 'work in progress' to fix this and get
 # the reference data for rfc1766 cleaned up.
 #
-# Danish (da) - Dutch (nl) - English (en) - Estonian (ee)
+# Danish (da) - Dutch (nl) - English (en) - Estonian (et)
 # French (fr) - German (de) - Greek-Modern (el)
 # Italian (it) - Norwegian (no) - Korean (kr) 
 # Portugese (pt) - Luxembourgeois* (ltz)
@@ -658,21 +669,18 @@ AddEncoding x-gzip gz tgz
 AddLanguage da .dk
 AddLanguage nl .nl
 AddLanguage en .en
-AddLanguage et .ee
+AddLanguage et .et
 AddLanguage fr .fr
 AddLanguage de .de
 AddLanguage el .el
 AddLanguage it .it
 AddLanguage ja .ja
-AddCharset ISO-2022-JP .jis
 AddLanguage pl .po
 AddLanguage kr .kr
-AddCharset ISO-2022-KR .iso-kr
-AddCharset ISO-8859-2 .iso-pl
 AddLanguage pt .pt
 AddLanguage no .no
 AddLanguage pt-br .pt-br
-AddLanguage ltz .lu
+AddLanguage ltz .ltz
 AddLanguage ca .ca
 AddLanguage es .es
 AddLanguage sv .se
@@ -686,7 +694,55 @@ AddLanguage cz .cz
 #
 LanguagePriority en da nl et fr de el it ja kr no pl pt pt-br ltz ca es sv
 
-#
+
+# Specify a default charset for all pages sent out. This is
+# always a good idea and opens the door for future internationalisation
+# of your web site, should you ever want it. Specifying it as
+# a default does little harm; as the standart dictates that a page
+# is in iso-8859-1 (latin1) unless specified otherwise. I.e. you
+# are merely stating the obvious. There are also some security
+# reasons in browsers, related to javascript and URL parsing
+# which encourage to always set a default char set.
+#
+AddDefaultCharset	ISO-8859-1
+
+#
+# Commonly used filename extensions to character sets. You propably
+# want to avoid clashes with the language extensions, unless you
+# are good at carefully testing your setup after each change.
+#
+AddCharset ISO-8859-1  .iso8859-1 .latin1
+AddCharset ISO-8859-2  .iso8859-2 .latin2 .cen
+AddCharset ISO-8859-3  .iso8859-3 .latin3
+AddCharset ISO-8859-4  .iso8859-4 .latin4
+AddCharset ISO-8859-5  .iso8859-5 .latin5 .cyr
+AddCharset ISO-8859-6  .iso8859-6 .latin6 .arb
+AddCharset ISO-8859-7  .iso8859-7 .latin7 .grk
+AddCharset ISO-8859-8  .iso8859-8 .latin8 .heb	
+AddCharset ISO-8859-9  .iso8859-9 .latin9 .trk
+AddCharset ISO-2022-JP .iso2022-jp .jis
+AddCharset ISO-2022-KR .iso2022-kr .kis
+AddCharset ISO-2022-CN .iso2022-cn .cis
+
+# The set below does not map to a specific (iso) standard
+# but works on a fairly wide range of browser. Note that
+# capitalization actually matters (it should not, but it
+# does for some browsers).
+#
+# See ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets
+# for a list of sorts. But browsers support few.
+#
+AddCharset KOI8-r      .koi8-ru .ru
+AddCharset KOI8-ru     .koi8-uk .ua
+AddCharset GB2312      .gb2312 .gb 
+AddCharset utf-7       .utf7
+AddCharset utf-8       .utf8
+AddCharset big5	       .big5 .b5
+AddCharset EUC-TW      .euc-tw	
+AddCharset EUC-JP      .euc-jp
+AddCharset EUC-KR      .euc-kr
+AddCharset shift_jis   .sjis
+
 # AddType allows you to tweak mime.types without actually editing it, or to
 # make certain files to be certain types.
 #
diff --git a/docs/conf/httpd-win.conf b/docs/conf/httpd-win.conf
index 6890183b75..03f6a9d9e4 100644
--- a/docs/conf/httpd-win.conf
+++ b/docs/conf/httpd-win.conf
@@ -580,7 +580,7 @@ AddEncoding x-gzip gz tgz
 # specifier. But there is 'work in progress' to fix this and get
 # the reference data for rfc1766 cleaned up.
 #
-# Danish (da) - Dutch (nl) - English (en) - Estonian (ee)
+# Danish (da) - Dutch (nl) - English (en) - Estonian (et)
 # French (fr) - German (de) - Greek-Modern (el)
 # Italian (it) - Norwegian (no) - Korean (kr)
 # Portugese (pt) - Luxembourgeois* (ltz)
@@ -590,21 +590,21 @@ AddEncoding x-gzip gz tgz
 AddLanguage da .dk
 AddLanguage nl .nl
 AddLanguage en .en
-AddLanguage et .ee
+AddLanguage et .et
 AddLanguage fr .fr
 AddLanguage de .de
 AddLanguage el .el
 AddLanguage it .it
 AddLanguage ja .ja
-AddCharset ISO-2022-JP .jis
+AddCharset ISO-2022-JP .iso2022-jp
 AddLanguage pl .po
 AddLanguage kr .kr
-AddCharset ISO-2022-KR .iso-kr
-AddCharset ISO-8859-2 .iso-pl
+AddCharset ISO-2022-KR .iso2022-kr
+AddCharset ISO-8859-2 .iso8859-pl
 AddLanguage pt .pt
 AddLanguage no .no
 AddLanguage pt-br .pt-br
-AddLanguage ltz .lu
+AddLanguage ltz .ltz
 AddLanguage ca .ca
 AddLanguage es .es
 AddLanguage sv .se