diff options
Diffstat (limited to 'share/i18n/csmapper/APPLE/DEVANAGA%UCS.src')
| -rw-r--r-- | share/i18n/csmapper/APPLE/DEVANAGA%UCS.src | 359 |
1 files changed, 359 insertions, 0 deletions
diff --git a/share/i18n/csmapper/APPLE/DEVANAGA%UCS.src b/share/i18n/csmapper/APPLE/DEVANAGA%UCS.src new file mode 100644 index 0000000..9d4c0fd --- /dev/null +++ b/share/i18n/csmapper/APPLE/DEVANAGA%UCS.src @@ -0,0 +1,359 @@ +# $FreeBSD$ + +TYPE ROWCOL +NAME DEVANAGA/UCS +SRC_ZONE 0x00-0xFA +OOB_MODE ILSEQ +DST_ILSEQ 0xFFFE +DST_UNIT_BITS 16 +#======================================================================= +# File name: DEVANAGA.TXT +# +# Contents: Map (external version) from Mac OS Devanagari +# encoding to Unicode 2.1 and later. +# +# Copyright: (c) 1995-2002, 2005 by Apple Computer, Inc., all rights +# reserved. +# +# Contact: charsets@apple.com +# +# Changes: +# +# c02 2005-Apr-05 Update header comments; add section on +# roundtrip considerations. Matches internal +# xml <c1.1> and Text Encoding Converter 2.0. +# b3,c1 2002-Dec-19 Update URLs. Matches internal utom<b1>. +# b02 1999-Sep-22 Update contact e-mail address. Matches +# internal utom<b1>, ufrm<b1>, and Text +# Encoding Converter version 1.5. +# n04 1998-Feb-05 First version; matches internal utom<n9>, +# ufrm<n15>. +# +# Standard header: +# ---------------- +# +# Apple, the Apple logo, and Macintosh are trademarks of Apple +# Computer, Inc., registered in the United States and other countries. +# Unicode is a trademark of Unicode Inc. For the sake of brevity, +# throughout this document, "Macintosh" can be used to refer to +# Macintosh computers and "Unicode" can be used to refer to the +# Unicode standard. +# +# Apple Computer, Inc. ("Apple") makes no warranty or representation, +# either express or implied, with respect to this document and the +# included data, its quality, accuracy, or fitness for a particular +# purpose. In no event will Apple be liable for direct, indirect, +# special, incidental, or consequential damages resulting from any +# defect or inaccuracy in this document or the included data. +# +# These mapping tables and character lists are subject to change. +# The latest tables should be available from the following: +# +# <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/> +# +# For general information about Mac OS encodings and these mapping +# tables, see the file "README.TXT". +# +# Format: +# ------- +# +# Three tab-separated columns; +# '#' begins a comment which continues to the end of the line. +# Column #1 is the Mac OS Devanagari code or code sequence +# (in hex as 0xNN or 0xNN+0xNN) +# Column #2 is the corresponding Unicode or Unicode sequence +# (in hex as 0xNNNN or 0xNNNN+0xNNNN). +# Column #3 is a comment containing the Unicode name or sequence +# of names. In some cases an additional comment follows the +# Unicode name(s). +# +# The entries are in two sections. The first section is for pairs of +# Mac OS Devanagari code points that must be mapped in a special way. +# The second section maps individual code points. +# +# Within each section, the entries are in Mac OS Devanagari code order. +# +# Control character mappings are not shown in this table, following +# the conventions of the standard UTC mapping tables. However, the +# Mac OS Devanagari character set uses the standard control characters +# at 0x00-0x1F and 0x7F. +# +# Notes on Mac OS Devanagari: +# --------------------------- +# +# This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa +# environments, it is only supported via transcoding to and from +# Unicode. +# +# Mac OS Devanagari is based on IS 13194:1991 (ISCII-91), with the +# addition of several punctuation and symbol characters. However, +# Mac OS Devanagari does not support the ATR (attribute) mechanism of +# ISCII-91. +# +# 1. ISCII-91 features in Mac OS Devanagari include: +# +# a) Overloading of nukta +# +# In addition to using the nukta (0xE9) like a combining dot below, +# nukta is overloaded to function as a general character modifier. +# In this role, certain code points followed by 0xE9 are treated as +# a two-byte code point representing a character which may be +# rather different than the characters represented by either of +# the code points alone. For example, the character DEVANAGARI OM +# (U+0950) is represented in ISCII-91 as candrabindu + nukta. +# +# b) Explicit halant and soft halant +# +# A double halant (0xE8 + 0xE8) constitutes an "explicit halant", +# which will always appear as a halant instead of causing formation +# of a ligature or half-form consonant. +# +# Halant followed by nukta (0xE8 + 0xE9) constitutes a "soft +# halant", which prevents formation of a ligature and instead +# retains the half-form of the first consonant. +# +# c) Invisible consonant +# +# The byte 0xD9 (called INV in ISCII-91) is an invisible consonant: +# It behaves like a consonant but has no visible appearance. It is +# intended to be used (often in combination with halant) to display +# dependent forms in isolation, such as the RA forms or consonant +# half-forms. +# +# d) Extensions for Vedic, etc. +# +# The byte 0xF0 (called EXT in ISCII-91) followed by any byte in +# the range 0xA1-0xEE constitutes a two-byte code point which can +# be used to represent additional characters for Vedic (or other +# extensions); 0xF0 followed by any other byte value constitutes +# malformed text. Mac OS Devanagari supports this mechanism, but +# does not currently map any of these two-byte code points to +# anything. +# +# 2. Mac OS Devanagari additions +# +# Mac OS Devanagari adds characters using the code points +# 0x80-0x8A and 0x90-0x91 (the latter are some Devanagari additions +# from Unicode). +# +# 3. Unused code points +# +# The following code points are currently unused, and are not shown +# here: 0x8B-0x8F, 0x92-0xA0, 0xEB-0xEF, 0xFB-0xFF. In addition, +# 0xF0 is not shown here, but it has a special function as described +# above. +# +# Unicode mapping issues and notes: +# --------------------------------- +# +# 1. Mapping the byte pairs +# +# If one of the following byte values is encountered when mapping +# Mac OS Devanagari text - 0xA1, 0xA6, 0xA7, 0xAA, 0xDB, 0xDC, 0xDF, +# 0xE8, or 0xEA - then the next byte (if there is one) should be +# examined. If the next byte is 0xE9 - or also 0xE8, if the first +# byte was 0xE8 - then the byte pair should be mapped using the +# first section of the mapping table below. Otherwise, each byte +# should be mapped using the second section of the mapping table +# below. +# +# - The Unicode Standard, Version 2.0, specifies how explicit +# halant and soft halant should be represented in Unicode; +# these mappings are used below. +# +# If the byte value 0xF0 is encountered when mapping Mac OS +# Devanagari text, then the next byte should be examined. If there +# is no next byte (e.g. 0xF0 at end of buffer), the mapping +# process should indicate incomplete character. If there is a next +# byte but it is not in the range 0xA1-0xEE, the mapping process +# should indicate malformed text. Otherwise, the mapping process +# should treat the byte pair as a valid two-byte code point with no +# mapping (e.g. map it to QUESTION MARK, REPLACEMENT CHARACTER, +# etc.). +# +# 2. Mapping the invisible consonant +# +# It has been suggested that INV in ISCII-91 should map to ZERO +# WIDTH NON-JOINER in Unicode. However, this causes problems with +# roundtrip fidelity: The ISCII-91 sequences 0xE8+0xE8 and 0xE8+0xD9 +# would map to the same sequence of Unicode characters. We have +# instead mapped INV to LEFT-TO-RIGHT MARK, which avoids these +# problems. +# +# 3. Additional loose mappings from Unicode +# +# These are not preserved in roundtrip mappings. +# +# U+0958 0xB3+0xE9 # DEVANAGARI LETTER QA +# U+0959 0xB4+0xE9 # DEVANAGARI LETTER KHHA +# U+095A 0xB5+0xE9 # DEVANAGARI LETTER GHHA +# U+095B 0xBA+0xE9 # DEVANAGARI LETTER ZA +# U+095C 0xBF+0xE9 # DEVANAGARI LETTER DDDHA +# U+095D 0xC0+0xE9 # DEVANAGARI LETTER RHA +# U+095E 0xC9+0xE9 # DEVANAGARI LETTER FA +# +# 4. Roundtrip considerations when mapping to decomposed Unicode +# +# Both ISCII-91 (hence Mac OS Devanagari) and Unicode provide multiple +# ways of representing certain Devanagari consonants. For example, +# DEVANAGARI LETTER NNNA can be represented in Unicode as the single +# character 0x0929 or as the sequence 0x0928 0x093C; similarly, this +# consonant can be represented in Mac OS Devanagari as 0xC7 or as the +# sequence 0xC6 0xE9. This leads to some roundtrip problems. First +# note that we have the following mappings without such problems: +# +# ISCII/ standard decomposition of reverse mapping +# Mac OS Unicode mapping standard mapping of decomposition +# ------ ----------------------- ---------------- ---------------- +# 0xC6 0x0928 ... LETTER NA 0x0928 (same) 0xC6 +# 0xCD 0x092F ... LETTER YA 0x092F (same) 0xCD +# 0xCF 0x0930 ... LETTER RA 0x0930 (same) 0xCF +# 0xD2 0x0933 ... LETTER LLA 0x0933 (same) 0xD2 +# 0xE9 0x093C ... SIGN NUKTA 0x093C (same) 0xE9 +# +# However, those mappings above cause roundtrip problems for the +# the following mappings if they are decomposed: +# +# ISCII/ standard decomposition of reverse mapping +# Mac OS Unicode mapping standard mapping of decomposition +# ------ ----------------------- ---------------- ---------------- +# 0xC7 0x0929 ... LETTER NNNA 0x0928 0x093C 0xC6 0xE9 +# 0xCE 0x095F ... LETTER YYA 0x092F 0x093C 0xCD 0xE9 +# 0xD0 0x0931 ... LETTER RRA 0x0930 0x093C 0xCF 0xE9 +# 0xD3 0x0934 ... LETTER LLLA 0x0933 0x093C 0xD2 0xE9 +# +# One solution is to use a grouping transcoding hint with the four +# decompositions above to mark the decomposed sequence for special +# treatment in transcoding. This yields the following mappings to +# decomposed Unicode: +# +# ISCII/ decomposed +# Mac OS Unicode mapping +# ------ ---------------- +# 0xC7 0xF860 0x0928 0x093C +# 0xCE 0xF860 0x092F 0x093C +# 0xD0 0xF860 0x0930 0x093C +# 0xD3 0xF860 0x0933 0x093C +# +# Details of mapping changes in each version: +# ------------------------------------------- +# +################## +# Section 1: Map the following byte pairs as indicated: +# (ZWNJ means ZERO WIDTH NON-JOINER, ZWJ means ZERO WIDTH JOINER) +# (Also see note about 0xF0 in comments above) +# Section 2: Map the remaining bytes as follows: +# +# +# +# +BEGIN_MAP +0x00 - 0x7F = 0x0000 - +0x80 = 0x00D7 +0x81 = 0x2212 +0x82 = 0x2013 +0x83 = 0x2014 +0x84 = 0x2018 +0x85 = 0x2019 +0x86 = 0x2026 +0x87 = 0x2022 +0x88 = 0x00A9 +0x89 = 0x00AE +0x8A = 0x2122 +0x90 = 0x0965 +0x91 = 0x0970 +0xA1 = 0x0901 +#0xA1+0xE9 = 0x0950 +0xA2 = 0x0902 +0xA3 = 0x0903 +0xA4 = 0x0905 +0xA5 = 0x0906 +0xA6 = 0x0907 +#0xA6+0xE9 = 0x090C +0xA7 = 0x0908 +#0xA7+0xE9 = 0x0961 +0xA8 = 0x0909 +0xA9 = 0x090A +0xAA = 0x090B +#0xAA+0xE9 = 0x0960 +0xAB = 0x090E +0xAC = 0x090F +0xAD = 0x0910 +0xAE = 0x090D +0xAF = 0x0912 +0xB0 = 0x0913 +0xB1 = 0x0914 +0xB2 = 0x0911 +0xB3 = 0x0915 +0xB4 = 0x0916 +0xB5 = 0x0917 +0xB6 = 0x0918 +0xB7 = 0x0919 +0xB8 = 0x091A +0xB9 = 0x091B +0xBA = 0x091C +0xBB = 0x091D +0xBC = 0x091E +0xBD = 0x091F +0xBE = 0x0920 +0xBF = 0x0921 +0xC0 = 0x0922 +0xC1 = 0x0923 +0xC2 = 0x0924 +0xC3 = 0x0925 +0xC4 = 0x0926 +0xC5 = 0x0927 +0xC6 = 0x0928 +0xC7 = 0x0929 +0xC8 = 0x092A +0xC9 = 0x092B +0xCA = 0x092C +0xCB = 0x092D +0xCC = 0x092E +0xCD = 0x092F +0xCE = 0x095F +0xCF = 0x0930 +0xD0 = 0x0931 +0xD1 = 0x0932 +0xD2 = 0x0933 +0xD3 = 0x0934 +0xD4 = 0x0935 +0xD5 = 0x0936 +0xD6 = 0x0937 +0xD7 = 0x0938 +0xD8 = 0x0939 +0xD9 = 0x200E +0xDA = 0x093E +0xDB = 0x093F +#0xDB+0xE9 = 0x0962 +0xDC = 0x0940 +#0xDC+0xE9 = 0x0963 +0xDD = 0x0941 +0xDE = 0x0942 +0xDF = 0x0943 +#0xDF+0xE9 = 0x0944 +0xE0 = 0x0946 +0xE1 = 0x0947 +0xE2 = 0x0948 +0xE3 = 0x0945 +0xE4 = 0x094A +0xE5 = 0x094B +0xE6 = 0x094C +0xE7 = 0x0949 +0xE8 = 0x094D +#0xE8+0xE8 = 0x094D+0x200C +#0xE8+0xE9 = 0x094D+0x200D +0xE9 = 0x093C +0xEA = 0x0964 +#0xEA+0xE9 = 0x093D +0xF1 = 0x0966 +0xF2 = 0x0967 +0xF3 = 0x0968 +0xF4 = 0x0969 +0xF5 = 0x096A +0xF6 = 0x096B +0xF7 = 0x096C +0xF8 = 0x096D +0xF9 = 0x096E +0xFA = 0x096F +END_MAP |
