summaryrefslogtreecommitdiffstats
path: root/tools/encoding/macRoman.txt
diff options
context:
space:
mode:
Diffstat (limited to 'tools/encoding/macRoman.txt')
-rw-r--r--tools/encoding/macRoman.txt145
1 files changed, 104 insertions, 41 deletions
diff --git a/tools/encoding/macRoman.txt b/tools/encoding/macRoman.txt
index 3bf88da..8821f3b 100644
--- a/tools/encoding/macRoman.txt
+++ b/tools/encoding/macRoman.txt
@@ -1,11 +1,35 @@
+#=======================================================================
+# FTP file name: ROMAN.TXT
#
-# Name: MacOS_Roman [to Unicode]
-# Unicode versions: 1.1, 2.0
-# Table version: 0.2 (from internal ufrm version <9>)
-# Date: 15 April 1995
-# Author: Peter Edberg <edberg1@applelink.apple.com>
+# Contents: Map (external version) from Mac OS Roman
+# character set to Unicode 2.1
#
-# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved.
+# Copyright: (c) 1994-1999 by Apple Computer, Inc., all rights
+# reserved.
+#
+# Contact: charsets@apple.com
+#
+# Changes:
+#
+# b03 1999-Sep-22 Update contact e-mail address. Matches
+# internal utom<b4>, ufrm<b3>, and Text
+# Encoding Converter version 1.5.
+# b02 1998-Aug-18 Encoding changed for Mac OS 8.5; change
+# mapping of 0xDB from CURRENCY SIGN to
+# EURO SIGN. Matches internal utom<b3>,
+# ufrm<b3>.
+# n08 1998-Feb-05 Minor update to header comments
+# n06 1997-Dec-14 Add warning about future changes to 0xDB
+# from CURRENCY SIGN to EURO SIGN. Clarify
+# some header information
+# n04 1997-Dec-01 Update to match internal utom<n3>, ufrm<n22>:
+# Change standard mapping for 0xBD from U+2126
+# to its canonical decomposition, U+03A9.
+# n03 1995-Apr-15 First version (after fixing some typos).
+# Matches internal ufrm<n9>.
+#
+# Standard header:
+# ----------------
#
# Apple, the Apple logo, and Macintosh are trademarks of Apple
# Computer, Inc., registered in the United States and other countries.
@@ -17,55 +41,69 @@
# Apple makes no warranty or representation, either express or
# implied, with respect to these tables, their quality, accuracy, or
# fitness for a particular purpose. In no event will Apple be liable
-# for direct, indirect, special, incidental, or consequential damages
+# for direct, indirect, special, incidental, or consequential damages
# resulting from any defect or inaccuracy in this document or the
# accompanying tables.
#
-# These mapping tables and character lists are preliminary and
-# subject to change. Updated tables will be available from the
-# Unicode Inc. ftp site (unicode.org), the Apple Computer ftp site
-# (ftp.info.apple.com), the Apple Computer World-Wide Web pages
-# (http://www.info.apple.com), and possibly on diskette from APDA
-# (Apple's mail-order distribution service for developers).
+# These mapping tables and character lists are subject to change.
+# The latest tables should be available from the following:
+#
+# <ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
+# <ftp://dev.apple.com/devworld/Technical_Documentation/Misc._Standards/>
+#
+# For general information about Mac OS encodings and these mapping
+# tables, see the file "README.TXT".
#
-# Format:
-# -------
+# Format:
+# -------
#
# Three tab-separated columns;
# '#' begins a comment which continues to the end of the line.
-# Column #1 is the MacOS Roman code (in hex as 0xNN)
-# Column #2 is the Unicode (in hex as 0xNNNN)
-# Column #3 is the Unicode name (follows a comment sign, '#')
+# Column #1 is the Mac OS Roman code (in hex as 0xNN)
+# Column #2 is the corresponding Unicode (in hex as 0xNNNN)
+# Column #3 is a comment containing the Unicode name
#
-# The entries are in MacOS Roman code order.
+# The entries are in Mac OS Roman code order.
#
-# One of these mappings requires the use of a corporate character
-# (for the Apple logo character). See the file "MacOS-CorpCharList".
-# NOTE: The graphic image associated with the Apple logo character
-# is not authorized for use without permission of Apple, and
-# unauthorized use might constitute trademark infringement.
+# One of these mappings requires the use of a corporate character.
+# See the file "CORPCHAR.TXT" and notes below.
#
-# Notes on MacOS Roman:
-# ---------------------
+# Control character mappings are not shown in this table, following
+# the conventions of the standard UTC mapping tables. However, the
+# Mac OS Roman character set uses the standard control characters at
+# 0x00-0x1F and 0x7F.
#
-# This character set is used for at least the following MacOS
+# Notes on Mac OS Roman:
+# ----------------------
+#
+# This character set is used for at least the following Mac OS
# localizations: U.S., British, Canadian French, French, Swiss
# French, German, Swiss German, Italian, Swiss Italian, Dutch,
# Swedish, Norwegian, Danish, Finnish, Spanish, Catalan,
# Portuguese, Brazilian, and the default International system.
#
-# Variants of MacRoman are used for Croatian, Icelandic,
-# Turkish, and Romanian. Separate mapping tables are available
-# for these encodings.
+# Variants of Mac OS Roman are used for Croatian, Icelandic,
+# Turkish, Romanian, and other encodings. Separate mapping tables
+# are available for these encodings.
+#
+# Before Mac OS 8.5, code point 0xDB was CURRENCY SIGN, and was
+# mapped to U+00A4. In Mac OS 8.5 and later versions, code point
+# 0xDB is changed to EURO SIGN and maps to U+20AC; the standard
+# Apple fonts are updated for Mac OS 8.5 to reflect this. There is
+# a "currency sign" variant of the Mac OS Roman encoding that still
+# maps 0xDB to U+00A4; this can be used for older fonts.
+# Note: U+20AC is new with Unicode 2.1; for earlier Unicode
+# versions, Mac OS Roman 0xDB may be mapped to private-use character
+# U+F8A0.
#
-# At least through System 7.5, the bitmap versions of the fonts
-# Chicago, New York, Geneva, and Monaco do not implement the
-# full Roman character set; they only support MacOS Roman character
-# codes up to 0xD8. The TrueType versions of these fonts do
-# implement the full character set, as do both the bitmap and
-# TrueType versions of the other standard Roman fonts.
+# Before Mac OS 8.5, the ROM bitmap versions of the fonts Chicago,
+# New York, Geneva, and Monaco did not implement the full Mac OS
+# Roman character set; they only supported character codes up to
+# 0xD8. The TrueType versions of these fonts have always implemented
+# the full character set, as with the bitmap and TrueType versions
+# of the other standard Roman fonts.
#
-# In all MacOS encodings, fonts such as Chicago which are used
+# In all Mac OS encodings, fonts such as Chicago which are used
# as "system" fonts (for menus, dialogs, etc.) have four glyphs
# at code points 0x11-0x14 for transient use by the Menu Manager.
# These glyphs are not intended as characters for use in normal
@@ -73,6 +111,31 @@
# interpreted as associated with these glyphs; they are usually
# interpreted (if at all) as the control codes DC1-DC4.
#
+# Unicode mapping issues and notes:
+# ---------------------------------
+#
+# The following corporate zone Unicode character is used in this
+# mapping:
+#
+# 0xF8FF Apple logo
+#
+# NOTE: The graphic image associated with the Apple logo character
+# is not authorized for use without permission of Apple, and
+# unauthorized use might constitute trademark infringement.
+#
+# Details of mapping changes in each version:
+# -------------------------------------------
+#
+# Changes from version n08 to version b02:
+#
+# - Encoding changed for Mac OS 8.5; change mapping of 0xDB from
+# CURRENCY SIGN (U+00A4) to EURO SIGN (U+20AC).
+#
+# Changes from version n03 to version n04:
+#
+# - Change mapping of 0xBD from U+2126 to its canonical
+# decomposition, U+03A9.
+#
##################
0x20 0x0020 # SPACE
@@ -217,7 +280,7 @@
0xAB 0x00B4 # ACUTE ACCENT
0xAC 0x00A8 # DIAERESIS
0xAD 0x2260 # NOT EQUAL TO
-0xAE 0x00C6 # LATIN CAPITAL LIGATURE AE
+0xAE 0x00C6 # LATIN CAPITAL LETTER AE
0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
0xB0 0x221E # INFINITY
0xB1 0x00B1 # PLUS-MINUS SIGN
@@ -232,8 +295,8 @@
0xBA 0x222B # INTEGRAL
0xBB 0x00AA # FEMININE ORDINAL INDICATOR
0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
-0xBD 0x2126 # OHM SIGN
-0xBE 0x00E6 # LATIN SMALL LIGATURE AE
+0xBD 0x03A9 # GREEK CAPITAL LETTER OMEGA
+0xBE 0x00E6 # LATIN SMALL LETTER AE
0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
0xC0 0x00BF # INVERTED QUESTION MARK
0xC1 0x00A1 # INVERTED EXCLAMATION MARK
@@ -262,7 +325,7 @@
0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
0xDA 0x2044 # FRACTION SLASH
-0xDB 0x00A4 # CURRENCY SIGN
+0xDB 0x20AC # EURO SIGN
0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0xDE 0xFB01 # LATIN SMALL LIGATURE FI