#  Copyright (c) 1994, 1997, 1998 by Oracle Corporation 
#    NAME
#      lx22711.nlt - Example User-Defined Character set definition file
#    DESCRIPTION
#      This is an example of a text-format User-Defined Character set 
#      definition file.  This demo file format is specific to Release  
#      8.0.4 and beyond. 
#    MODIFIED   (MM/DD/YY)
#     chaowang   05/11/98 - Editorial polish for demo file
#     chaowang   11/02/97 - Add more comments
#     chaowang   10/31/97 - Creation

# The following is a demo of an Oracle's User-Defined Character set  
# definition file. You may edit this demo file to create a user  
# defined character set or copy and modify an existing character set  
# definition file. The convention used for naming character set  
# definition (.nlt) files is in the format:  
# lx2dddd.nlt, where dddd = 4 digit character set ID in hex. 
# All letters in the definition file are case-insensitive.  
 
# Version number: specify the current loadable data version. 
# 
VERSION = 2.1.0.0.0

# The following is the body of the definition file 
# 
DEFINE character_set

# Starting in release 8.0.4 the 'base_char_set' feature allows you to 
# extend an existing Oracle character set. 
# Generally, you may only need to edit the following fields: 
 
# Name and Id of the character set are required for any character sets. 
 
# Character set name must be specified in a double quoted string. 
# Rules for choosing a character set name:  
#          - Cannot use a character set name that is already in use.  
#            (Each character set must be assigned a unique character set 
#             name). 
#          - Must consist of single-byte ASCII or EBCDIC characters only  
#            (single-byte compiler character set).  
#          - Cannot contain multibyte characters. 
#          - Maximum length of 30 characters. 
#          - Must start with an alphabetic character. 
#          - Composed of alphanumeric characters only  
#            (e.g. no periods, dashes, underscore characters allowed) 
#          - The name is case-insensitive. 
# To register a unique character set name, send mail to nlsreg@us.oracle.com. 
# E.g.
  name = "JA16EUCSUNWEXT1"

# Character set ID is specified as an integer value. 
# Rules for choosing a character set ID: 
#         - Cannot use a character set ID that is already in use.  
#           (Each character set must be assigned a unique character set ID.) 
#         - Must be in the decimal range of 10000-20000 
#         - Character set IDs must be registered with Oracle to receive a  
#            uniquely assigned character set id number. 
# To register a unique character set id, send mail to nlsreg@us.oracle.com. 
# E.g. 
  id = 10001

# The base character set feature was introduced in version 8.0.4.  
# It allows you to define the new character set based on an existing  
# Oracle character set. The new character set will inherit all  
# definitions from the base character set. Therefore, you typically 
# will need to add only the user defined character data into the  
# new character set definition file. 
# The syntax of the base character set is: 
#       base_char_set = <id> | <name> 
#  - <id> or <name> should be a valid Oracle NLS character set id or name. 
#  - All letters are case-insensitive. 
# Example is: base_char_set = "JA16EUC" or base_char_set = 830 
# E.g. 
  base_char_set = 830

# If you use the base_char_set feature, you need to copy your base  
# character set definition file (text-format or binary) from the $ORA_NLS33  
# directory into the working directory specified by $ORANLS.  This will 
# allow the new character set to inherit the definition from the  
# base character set. 
# Example to the above is: 
#  %cp $ORA_NLS33/lx2033e.nlt $ORANLS   (JA16EUC text-format defintion) 
#  or  
#  %cp $ORA_NLS33/lx*33e.nlb $ORANLS    (JA16EUC binary defintion) 
 
 
# Character data is defined as a list of  <char_value>:<unicode_value>  
# pairs. <char_value> is a hex number specifying the complete character  
# value in this character set (e.g. 0xa1b1), while <unicode_value> is a  
# 16-bit hex number specifying its corresponding Unicode 2.0 character value.  
# Alternatively, a range of characters can be specified with a corresponding  
# range of Unicode values. Each successive character in the  
# <start_char>-<end_char> range will be assigned to each successive  
# character in the <start_unicode>-<end_unicode> range. There must be  
# an equal number of characters in each range. 
# User-defined characters must be assigned to characters in the Unicode 
# 2.0 private use area, and in particular the range 0xe000 to 0xf4ff.  
# The remaining 1024 characters in the private use area are reserved  
# for Oracle private use. 
# E.g. 
  character_data = {
     0x9a41 : 0xe001,
     0x9a42 : 0xe002,
  }


# A character classification list is used to specify the type of characters.  
# Valid values: 
# 	UPPER LOWER DIGIT SPACE PUNCTUATION CONTROL  
#            HEX_DIGIT LETTER PRINTABLE 
# E.g. 
  classification = {
     0x9a41 = { LETTER, LOWER },
     0x9a42 = { LETTER, UPPER },
  }

# Lower-to-Upper case character relationships are defined as pairs, where  
# the first specifies the value of a character in this character set and the 
# second specifies its uppercase value in this character set.  Character  
# ranges are also allowed in the manner described for character data above. 
# Define this field only if needed. 
# E.g. 
  uppercase = {
     0x9a41 : 0x9a42,
  }


# Upper-to-Lower case character relationships are defined as pairs, where  
# the first specifies the value of a character in this character set and the 
# second specifies its lowercase value in this character set.  Character  
# ranges are also allowed in the manner described for character data above. 
# Define this field only if needed. 
# E.g. 
  lowercase = { 
     0x9a42 : 0x9a41,
  }

# There are many more fields in Oracle's character set definition file, 
# Presumably, you will only need the above mentioned fields at most.  
# For full details on all fields and keywords, refer to the Oracle 
# User Defined Character Set white paper. 

ENDDEFINE character_set