Changeset 1870 for trunk/gsdl/etc/main.cfg

Timestamp:

2001-01-29T14:54:58+13:00 (23 years ago)

Author:

sjboddie

Message:

Tidied up language support stuff.

File:

• trunk/gsdl/etc/main.cfg (modified) (2 diffs)

trunk/gsdl/etc/main.cfg

@@ -78 +78 @@
 # Define the interface languages and encodings supported by this receptionist
 
-# An "Encoding" line defines an encoding to be used by the receptionist
-# options are:
-# shortname -- Identifier for the given encoding. The shortname option is
-#              mandatory and must be unique for each "Encoding" line.
+# An "Encoding" line defines an encoding to be used by the receptionist.
+# Uncomment "Encoding" lines to include an encoding on your "preferences" page.
+# Encoding line options are:
+# shortname -- The standard charset label for the given encoding. The
+#              shortname option is mandatory.
 # longname  -- The display name of the given encoding. If longname isn't set
 #              it will default to using shortname instead.
-# type      -- The type of encoding. Note that for most encodings this
-#              value is the directory name under which the map file for
-#              this encoding resides in the Greenstone unicode/MAPPINGS
-#              directory (e.g. 'WINDOWS', 'ISO_8859' etc.). It may also
-#              take the values 'CJK' and 'UTF8'.
-# mapfile   -- The name of the map file for use when converting between
-#              utf8 and the given encoding. The mapfile option is mandatory
-#              for all encoding types with the exception of UTF8. If type
-#              is CJK, mapfile is the abbreviated name of the encoding as
-#              used by the binary mapping files (.ump files). i.e. if the
-#              encoding uses the map files gbku.ump and ugbk.ump, mapfile
-#              will be set to "gbk".
-# label     -- The standard label to which you must set the value of
-#              "charset" within http headers or html meta tags to get a web
-#              browser to use the given encoding. The label option is
-#              mandatory.
-Encoding shortname=utf8 "longname=Unicode (UTF-8)" type=UTF8 label=UTF-8
-Encoding shortname=iso1 "longname=Western (ISO-8859-1)" type=ISO_8859 mapfile=1.TXT label=ISO-8859-1
-Encoding shortname=w1251 "longname=Cyrillic (Windows-1251)" type=WINDOWS mapfile=1251.TXT label=windows-1251
-Encoding shortname=w1256 "longname=Arabic (Windows-1256)" type=WINDOWS mapfile=1256.TXT label=windows-1256
-Encoding shortname=w1256 "longname=Central European (Windows-1250)" type=WINDOWS mapfile=1250.TXT label=windows-1250
-Encoding shortname=gb "longname=Chinese Simplified (GBK)" type=CJK label=GBK mapfile=gbk
-Encoding shortname=sjis "longname=Japanese (Shift-JIS)" type=CJK label=shift_jis mapfile=sjis
-Encoding shortname=koi8r "longname=Cyrillic (KOI8-R)" type=CYRILLIC mapfile=koi8_r.txt label=koi8-r
+# map       -- The name of the map file (i.e. the .ump file) for use when
+#              converting between unicode and the given encoding. The map
+#              option is mandatory for all encoding lines except the
+#              special case for utf8.
 
-# The following encoding is not currently supported
-# Encoding shortname=eucjp "longname=Japanese (EUC)" type=CJK label=euc-jp mapfile=jis
+# The utf8 encoding is handled internally and doesn't require a map file.
+# As a rule the utf8 encoding should always be enabled, especially if you
+# have collections of documents that may not all be in the same
+# language/encoding.
+Encoding shortname=utf-8 "longname=Unicode (UTF-8)"
+
+# The ISO-8859 series
+Encoding shortname=iso-8859-1 "longname=Western (ISO-8859-1)" map=8859_1.ump
+#Encoding shortname=iso-8859-2 "longname=Central European (ISO-8859-2)" map=8859_2.ump
+#Encoding shortname=iso-8859-3 "longname=Latin 3 (ISO-8859-3)" map=8859_3.ump
+#Encoding shortname=iso-8859-4 "longname=Latin 4 (ISO-8859-4)" map=8859_4.ump
+#Encoding shortname=iso-8859-5 "longname=Cyrillic (ISO-8859-5)" map=8859_5.ump
+#Encoding shortname=iso-8859-6 "longname=Arabic (ISO-8859-6)" map=8859_6.ump
+#Encoding shortname=iso-8859-7 "longname=Greek (ISO-8859-7)" map=8859_7.ump
+#Encoding shortname=iso-8859-8 "longname=Hebrew (ISO-8859-8)" map=8859_8.ump
+#Encoding shortname=iso-8859-9 "longname=Turkish (ISO-8859-9)" map=8859_9.ump
+
+# Windows codepages
+#Encoding shortname=windows-1250 "longname=Central European (Windows-1250)" map=win1250.ump
+#Encoding shortname=windows-1251 "longname=Cyrillic (Windows-1251)" map=win1251.ump
+#Encoding shortname=windows-1252 "longname=Western (Windows-1252)" map=win1252.ump
+#Encoding shortname=windows-1253 "longname=Greek (Windows-1253)" map=win1253.ump
+#Encoding shortname=windows-1254 "longname=Turkish (Windows-1254)" map=win1254.ump
+#Encoding shortname=windows-1255 "longname=Hebrew (Windows-1255)" map=win1255.ump
+Encoding shortname=windows-1256 "longname=Arabic (Windows-1256)" map=win1256.ump
+#Encoding shortname=windows-1257 "longname=Baltic (Windows-1257)" map=win1257.ump
+#Encoding shortname=windows-1258 "longname=Vietnamese (Windows-1258)" map=win1258.ump
+#Encoding shortname=windows-874 "longname=Thai (Windows-874)" map=win874.ump
+
+# KOI8 Cyrillic encodings
+#Encoding shortname=koi8-r "longname=Cyrillic (KOI8-R)" map=koi8_r.ump
+#Encoding shortname=koi8-u "longname=Cyrillic (KOI8-U)" map=koi8_u.ump
+
+# CJK encodings (note that Shift-JIS Japanese isn't currently supported)
+Encoding shortname=gbk "longname=Chinese Simplified (GBK)" map=gbk.ump
+Encoding shortname=big5 "longname=Chinese Traditional (Big5)" map=big5.ump
+Encoding shortname=euc-jp "longname=Japanese (EUC)" map=euc_jp.ump
+Encoding shortname=euc-kr "longname=Korean (UHC)" map=uhc.ump
 
 
@@ -126 +143 @@
 #                     interface language. This should be set to the
 #                     "shortname" of a valid "Encoding" line
-Language shortname=en longname=English default_encoding=iso1
-Language shortname=fr longname=French default_encoding=iso1
-Language shortname=zh longname=Chinese default_encoding=gb
-Language shortname=de longname=German default_encoding=iso1
-Language shortname=es longname=Spanish default_encoding=iso1
-Language shortname=mi longname=Maori default_encoding=iso1
-Language shortname=ar longname=Arabic default_encoding=w1256
-Language shortname=pt longname=Portuguese default_encoding=iso1
-Language shortname=nl longname=Dutch default_encoding=iso1
+Language shortname=en longname=English default_encoding=iso-8859-1
+Language shortname=fr longname=French default_encoding=iso-8859-1
+Language shortname=zh longname=Chinese default_encoding=gbk
+Language shortname=de longname=German default_encoding=iso-8859-1
+Language shortname=es longname=Spanish default_encoding=iso-8859-1
+Language shortname=mi longname=Maori default_encoding=iso-8859-1
+Language shortname=ar longname=Arabic default_encoding=windows-1256
+Language shortname=pt longname=Portuguese default_encoding=iso-8859-1
+Language shortname=nl longname=Dutch default_encoding=iso-8859-1