- Copy stable/10 (r259064) to releng/10.0 as part of the

[FreeBSD/releng/10.0.git] / share / i18n / csmapper / APPLE / HEBREW%UCS.src

# $FreeBSD$

TYPE            ROWCOL
NAME            HEBREW/UCS
SRC_ZONE        0x00-0xFF
OOB_MODE        ILSEQ
DST_ILSEQ       0xFFFE
DST_UNIT_BITS   16

BEGIN_MAP
#=======================================================================
#   File name:  HEBREW.TXT
#
#   Contents:   Map (external version) from Mac OS Hebrew
#               character set 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 <c1.4> and Text Encoding Converter 2.0.
#      b3,c1 2002-Dec-19    Don't require left-right context for digits
#                           0x30-0x39. Change mapping of 0x81 to use
#                           decomposition. Reverse the mappings of 0xA8,
#                           0xA9. Update URLs, notes. Matches internal
#                           utom<b7>.
#       b02  1999-Sep-22    Update contact e-mail address. Matches
#                           internal utom<b1>, ufrm<b1>, and Text
#                           Encoding Converter version 1.5.
#       n03  1998-Feb-05    Show required Unicode character
#                           directionality in a different way. Update
#                           mappings for 0xC0 and 0xDE to use
#                           transcoding hints; matches internal utom<n6>,
#                           ufrm<n20>, and Text Encoding Converter
#                           version 1.3. Rewrite header comments.
#       n01  1995-Nov-15    First version. Matches internal ufrm<n8>.
#
# 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 Hebrew code (in hex as 0xNN).
#     Column #2 is the corresponding Unicode or Unicode sequence (in
#       hex as 0xNNNN, 0xNNNN+0xNNNN, etc.). Sequences of up to 3
#       Unicode characters are used here. A single Unicode character
#       may be preceded by a tag indicating required directionality
#       (i.e. 0xNNNN or 0xNNNN).
#     Column #3 is a comment containing the Unicode name.
#
#   The entries are in Mac OS Hebrew code order.
#
#   Some of these mappings require the use of corporate characters.
#   See the file "CORPCHAR.TXT" and notes below.
#
#   Control character mappings are not shown in this table, following
#   the conventions of the standard UTC mapping tables. However, the
#   Mac OS Hebrew character set uses the standard control characters at
#   0x00-0x1F and 0x7F.
#
# Notes on Mac OS Hebrew:
# -----------------------
#
#   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.
#
#   1. General
#
#   The Mac OS Hebrew character set supports the Hebrew and Yiddish
#   languages. It incorporates the Hebrew letter repertoire of
#   ISO 8859-8, and uses the same code points for them, 0xE0-0xFA.
#   It also incorporates the ASCII character set. In addition, the
#   Mac OS Hebrew character set includes the following:
#
#   - Hebrew points (nikud marks) at 0xC6, 0xCB-0xCF and 0xD8-0xDF.
#     These are non-spacing combining marks. Note that the RAFE point
#     at 0xD8 is not displayed correctly in some fonts, and cannot be
#     typed using the keyboard layouts in the current Hebrew localized
#     systems. Also note: The character given in Unicode as QAMATS
#     (U+05B8) actually refers to two different sounds, depending on
#     context. For example, when ALEF is followed by QAMATS, the QAMATS
#     can actually refer to two different sounds depending on the
#     following letters. The Mac OS Hebrew character set separately
#     encodes these two sounds for the same graphic shape, as "qamats"
#     (0xCB) and "qamats qatan" (0xDE). The "qamats" character is more
#     common, so it is mapped to the Unicode QAMATS; "qamats qatan" can
#     only be used with a limited number of characters, and it is
#     mapped using a corporate-zone variant tag (see below).
#
#   - Various Hebrew ligatures at 0x81, 0xC0, 0xC7, 0xC8, 0xD6, and
#     0xD7. Also note that the Yiddish YOD YOD PATAH ligature at 0x81
#     is missing in some fonts.
#
#   - The NEW SHEQEL SIGN at 0xA6.
#
#   - Latin characters with diacritics at 0x80 and 0x82-0x9F. However,
#     most of these cannot be typed using the keyboard layouts in the
#     Hebrew localized systems.
#
#   - Right-left versions of certain ASCII punctuation, symbols and
#     digits: 0xA0-0xA5, 0xA7-0xBF, 0xFB-0xFF. See below.
#
#   - Miscellaneous additional punctuation at 0xC1, 0xC9, 0xCA, and
#     0xD0-0xD5. There is a variant of the Hebrew encoding in which
#     the LEFT SINGLE QUOTATION MARK at 0xD4 is replaced by FIGURE
#     SPACE. The glyphs for some of the other punctuation characters
#     are missing in some fonts.
#
#   - Four obsolete characters at 0xC2-0xC5 known as canorals (not to
#     be confused with cantillation marks!). These were used for
#     manual positioning of nikud marks before System 7.1 (at which
#     point nikud positioning became automatic with WorldScript.).
#
#   2. Directional characters and roundtrip fidelity
#
#   The Mac OS Hebrew character set was developed around 1987. At that
#   time the bidirectional line line layout algorithm used in the Mac OS
#   Hebrew system was fairly simple; it used only a few direction
#   classes (instead of the 19 now used in the Unicode bidirectional
#   algorithm). In order to permit users to handle some tricky layou
#   problems, certain punctuation, symbol, and digit characters have
#   duplicate code points, one with a left-right direction attribute and
#   the other with a right-left direction attribute.
#
#   For example, plus sign is encoded at 0x2B with a left-right
#   attribute, and at 0xAB with a right-left attribute. However, there
#   is only one PLUS SIGN character in Unicode. This leads to some
#   interesting problems when mapping between Mac OS Hebrew and Unicode;
#   see below.
#
#   A related problem is that even when a particular character is
#   encoded only once in Mac OS Hebrew, it may have a different
#   direction attribute than the corresponding Unicode character.
#
#   For example, the Mac OS Hebrew character at 0xC9 is HORIZONTAL
#   ELLIPSIS with strong right-left direction. However, the Unicode
#   character HORIZONTAL ELLIPSIS has direction class neutral.
#
#   3. Font variants
#
#   The table in this file gives the Unicode mappings for the standard
#   Mac OS Hebrew encoding. This encoding is supported by many of the
#   Apple fonts (including all of the fonts in the Hebrew Language Kit),
#   and is the encoding supported by the text processing utilities.
#   However, some TrueType fonts provided with the localized Hebrew
#   system implement a slightly different encoding; the difference is
#   only in one code point, 0xD4. For the standard variant, this is:
#     0xD4 -> 0x2018  LEFT SINGLE QUOTATION MARK, right-left
#
#   The TrueType variant is used by the following TrueType fonts from
#   the localized system: Caesarea, Carmel Book, Gilboa, Ramat Sharon,
#   and Sinai Book. For these, 0xD4 is as follows:
#     0xD4 -> 0x2007  FIGURE SPACE, right-left
#
# Unicode mapping issues and notes:
# ---------------------------------
#
#   1. Matching the direction of Mac OS Hebrew characters
#
#   When Mac OS Hebrew encodes a character twice but with different
#   direction attributes for the two code points - as in the case of
#   plus sign mentioned above - we need a way to map both Mac OS Hebrew
#   code points to Unicode and back again without loss of information.
#   With the plus sign, for example, mapping one of the Mac OS Hebrew
#   characters to a code in the Unicode corporate use zone is
#   undesirable, since both of the plus sign characters are likely to
#   be used in text that is interchanged.
#
#   The problem is solved with the use of direction override characters
#   and direction-dependent mappings. When mapping from Mac OS Hebrew
#   to Unicode, we use direction overrides as necessary to force the
#   direction of the resulting Unicode characters.
#
#   The required direction is indicated by a direction tag in the
#   mappings. A tag of <LR> means the corresponding Unicode character
#   must have a strong left-right context, and a tag of <RL> indicates
#   a right-left context.
#
#   For example, the mapping of 0x2B is given as 0x002B; the
#   mapping of 0xAB is given as 0x002B. If we map an isolated
#   instance of 0x2B to Unicode, it should be mapped as follows (LRO
#   indicates LEFT-RIGHT OVERRIDE, PDF indicates POP DIRECTION
#   FORMATTING):
#
#     0x2B ->  0x202D (LRO) + 0x002B (PLUS SIGN) + 0x202C (PDF)
#
#   When mapping several characters in a row that require direction
#   forcing, the overrides need only be used at the beginning and end.
#   For example:
#
#     0x24 0x20 0x28 0x29 -> 0x202D 0x0024 0x0020 0x0028 0x0029 0x202C
#
#   If neutral characters that require direction forcing are already
#   between strong-direction characters with matching directionality,
#   then direction overrides need not be used. Direction overrides are
#   always needed to map the right-left digits at 0xB0-0xB9.
#
#   When mapping from Unicode to Mac OS Hebrew, the Unicode
#   bidirectional algorithm should be used to determine resolved
#   direction of the Unicode characters. The mapping from Unicode to
#   Mac OS Hebrew can then be disambiguated by the use of the resolved
#   direction:
#
#     Unicode 0x002B -> Mac OS Hebrew 0x2B (if L) or 0xAB (if R)
#
#   However, this also means the direction override characters should
#   be discarded when mapping from Unicode to Mac OS Hebrew (after
#   they have been used to determine resolved direction), since the
#   direction override information is carried by the code point itself.
#
#   Even when direction overrides are not needed for roundtrip
#   fidelity, they are sometimes used when mapping Mac OS Hebrew
#   characters to Unicode in order to achieve similar text layout with
#   the resulting Unicode text. For example, the single Mac OS Hebrew
#   ellipsis character has direction class right-left,and there is no
#   left-right version. However, the Unicode HORIZONTAL ELLIPSIS
#   character has direction class neutral (which means it may end up
#   with a resolved direction of left-right if surrounded by left-right
#   characters). When mapping the Mac OS Hebrew ellipsis to Unicode, it
#   is surrounded with a direction override to help preserve proper
#   text layout. The resolved direction is not needed or used when
#   mapping the Unicode HORIZONTAL ELLIPSIS back to Mac OS Hebrew.
#
#   2. Use of corporate-zone Unicodes
#
#   The goals in the mappings provided here are:
#   - Ensure roundtrip mapping from every character in the Mac OS
#     Hebrew character set to Unicode and back
#   - Use standard Unicode characters as much as possible, to
#     maximize interchangeability of the resulting Unicode text.
#     Whenever possible, avoid having content carried by private-use
#     characters.
#
#   Some of the characters in the Mac OS Hebrew character set do not
#   correspond to distinct, single Unicode characters. To map these
#   and satisfy both goals above, we employ various strategies.
#
#   a) If possible, use private use characters in combination with
#   standard Unicode characters to mark variants of the standard
#   Unicode character.
#
#   Apple has defined a block of 32 corporate characters as "transcoding
#   hints." These are used in combination with standard Unicode characters
#   to force them to be treated in a special way for mapping to other
#   encodings; they have no other effect. Sixteen of these transcoding
#   hints are "grouping hints" - they indicate that the next 2-4 Unicode
#   characters should be treated as a single entity for transcoding. The
#   other sixteen transcoding hints are "variant tags" - they are like
#   combining characters, and can follow a standard Unicode (or a sequence
#   consisting of a base character and other combining characters) to
#   cause it to be treated in a special way for transcoding. These always
#   terminate a combining-character sequence.
#
#   Two transcoding hints are used in this mapping table: a grouping hint
#   and a variant tag:
#   hint:
#     0xF86A  group next 2 characters, right-left directionality
#     0xF87F  variant tag
#
#   In Mac OS Hebrew, 0xC0 is a ligature for lamed holam. This can also
#   be represented in Mac OS Hebrew as 0xEC+0xDD, using separate
#   characters for lamed and holam. The latter sequence is mapped to
#   Unicode as 0x05DC+0x05B9, i.e. as the sequence HEBREW LETTER LAMED +
#   HEBREW POINT HOLAM. We want to map the ligature 0xC0 using the same
#   standard Unicode characters, but for round-trip fidelity we need to
#   distinguish it from the mapping of the sequence 0xEC+0xDD. Thus for
#   0xC0 we use a grouping hint, and map as follows:
#
#     0xC0 -> 0xF86A+0x05DC+0x05B9
#
#   The variant tag is used for "qamats qatan" to mark it as an alternate
#   for HEBREW POINT QAMATS, as follows:
#
#     0xDE -> 0x05B8+0xF87F
#
#   b) Otherwise, use private use characters by themselves to map Mac OS
#   Hebrew characters which  have no relationship to any standard Unicode
#   character.
#
#   The following additional corporate zone Unicode characters are used
#   for this purpose here (to map the obsolete "canorals", see above):
#
#     0xF89B  Hebrew canoral 1
#     0xF89C  Hebrew canoral 2
#     0xF89D  Hebrew canoral 3
#     0xF89E  Hebrew canoral 4
#
#   3. Roundtrip considerations when mapping to decomposed Unicode
#
#   Both Mac OS Hebrew and Unicode provide multiple ways of representing
#   certain letter-and-point combinations. For example, HEBREW LETTER
#   VAV WITH HOLAM can be represented in Unicode as the single character
#   0xFB4B or as the sequence 0x05D5 0x05B9; similarly, it can be
#   represented in Mac OS Hebrew as 0xC7 or as the sequence 0xE5 0xDD.
#   This leads to some roundtrip problems. First note that we have the
#   following mappings without such problems:
#
#   Mac   standard                            decomp. of     reverse map
#   OS    Unicode mapping                     std. mapping   of decomp.
#   ----  ----------------------------------  -------------  -----------
#   0xC6  0x05BC  ... POINT DAGESH OR MAPIQ   0x05BC (same)  0xC6
#   0xE5  0x05D5  ... LETTER VAV              0x05D5 (same)  0xE5
#   0xDD  0x05B9  ... POINT HOLAM             0x05B9 (same)  0xDD
#
#   However, those mappings above cause roundtrip problems for the
#   the following mappings if they are decomposed:
#
#   Mac   standard                            decomp. of     reverse map
#   OS    Unicode mapping                     std. mapping   of decomp.
#   ----  ----------------------------------  -------------  -----------
#   0xC7  0xFB4B  ... LETTER VAV WITH HOLAM   0x05D5 0x05B9  0xE5 0xDD
#   0xC8  0xFB35  ... LETTER VAV WITH DAGESH  0x05D5 0x05BC  0xE5 0xC6
#
#   One solution is to use a grouping transcoding hint with the two
#   decompositions above to mark the decomposed sequence for special
#   treatment in transcoding. This yields the following mappings to
#   decomposed Unicode:
#
#   Mac                                decomposed
#   OS                                 Unicode mapping
#   ----                               --------------------
#   0xC7                               0xF86A 0x05D5 0x05B9
#   0xC8                               0xF86A 0x05D5 0x05BC
#
# Details of mapping changes in each version:
# -------------------------------------------
#
#   Changes from version b02 to version b03/c01:
#
#   - Stop specifying left-right context for digits 0x30-0x39, since the
#     corresponding Unicodes 0x0030-0x0039 already have left-right
#     directionality.
#
#   - Change mapping of 0x81 from 0xFB1F HEBREW LIGATURE YIDDISH YOD YOD
#     PATAH to its canonical decomposition 0x05F2+0x05B7 to improve
#     cross-platform compatibility (Windows doesn't handle 0xFB1F)
#
#   - Interchange the mappings of 0xA8 and 0xA9 to obtain the correct
#     open/close behavior; they work differently than in Mac Arabic.
#     The old mapping was
#         0xA8 0x0028 # LEFT PARENTHESIS, right-left
#         0xA9 0x0029 # RIGHT PARENTHESIS, right-left
#     and the new mapping is
#         0xA8 0x0029 # RIGHT PARENTHESIS, right-left
#         0xA9 0x0028 # LEFT PARENTHESIS, right-left
#
#   Changes from version n01 to version n03:
#
#   - Change mapping for 0xC0 from single corporate character to
#     grouping hint plus standard Unicodes
#
#   - Change mapping for 0xDE from single corporate character to
#     standard Unicode plus variant tag
#
##################

0x00 - 0x7F = 0x0000 -
0x80 = 0x00C4   # LATIN CAPITAL LETTER A WITH DIAERESIS
0x81 = 0xFB1F   # 0x05F2+0x05B7 # HEBREW LIGATURE YIDDISH YOD YOD PATAH
0x82 = 0x00C7   # LATIN CAPITAL LETTER C WITH CEDILLA
0x83 = 0x00C9   # LATIN CAPITAL LETTER E WITH ACUTE
0x84 = 0x00D1   # LATIN CAPITAL LETTER N WITH TILDE
0x85 = 0x00D6   # LATIN CAPITAL LETTER O WITH DIAERESIS
0x86 = 0x00DC   # LATIN CAPITAL LETTER U WITH DIAERESIS
0x87 = 0x00E1   # LATIN SMALL LETTER A WITH ACUTE
0x88 = 0x00E0   # LATIN SMALL LETTER A WITH GRAVE
0x89 = 0x00E2   # LATIN SMALL LETTER A WITH CIRCUMFLEX
0x8A = 0x00E4   # LATIN SMALL LETTER A WITH DIAERESIS
0x8B = 0x00E3   # LATIN SMALL LETTER A WITH TILDE
0x8C = 0x00E5   # LATIN SMALL LETTER A WITH RING ABOVE
0x8D = 0x00E7   # LATIN SMALL LETTER C WITH CEDILLA
0x8E = 0x00E9   # LATIN SMALL LETTER E WITH ACUTE
0x8F = 0x00E8   # LATIN SMALL LETTER E WITH GRAVE
0x90 = 0x00EA   # LATIN SMALL LETTER E WITH CIRCUMFLEX
0x91 = 0x00EB   # LATIN SMALL LETTER E WITH DIAERESIS
0x92 = 0x00ED   # LATIN SMALL LETTER I WITH ACUTE
0x93 = 0x00EC   # LATIN SMALL LETTER I WITH GRAVE
0x94 = 0x00EE   # LATIN SMALL LETTER I WITH CIRCUMFLEX
0x95 = 0x00EF   # LATIN SMALL LETTER I WITH DIAERESIS
0x96 = 0x00F1   # LATIN SMALL LETTER N WITH TILDE
0x97 = 0x00F3   # LATIN SMALL LETTER O WITH ACUTE
0x98 = 0x00F2   # LATIN SMALL LETTER O WITH GRAVE
0x99 = 0x00F4   # LATIN SMALL LETTER O WITH CIRCUMFLEX
0x9A = 0x00F6   # LATIN SMALL LETTER O WITH DIAERESIS
0x9B = 0x00F5   # LATIN SMALL LETTER O WITH TILDE
0x9C = 0x00FA   # LATIN SMALL LETTER U WITH ACUTE
0x9D = 0x00F9   # LATIN SMALL LETTER U WITH GRAVE
0x9E = 0x00FB   # LATIN SMALL LETTER U WITH CIRCUMFLEX
0x9F = 0x00FC   # LATIN SMALL LETTER U WITH DIAERESIS
0xA0 = 0x0020   # SPACE, right-left
0xA1 = 0x0021   # EXCLAMATION MARK, right-left
0xA2 = 0x0022   # QUOTATION MARK, right-left
0xA3 = 0x0023   # NUMBER SIGN, right-left
0xA4 = 0x0024   # DOLLAR SIGN, right-left
0xA5 = 0x0025   # PERCENT SIGN, right-left
0xA6 = 0x20AA   # NEW SHEQEL SIGN
0xA7 = 0x0027   # APOSTROPHE, right-left
0xA8 = 0x0029   # RIGHT PARENTHESIS, right-left # close parenthesis
0xA9 = 0x0028   # LEFT PARENTHESIS, right-left # open parenthesis
0xAA = 0x002A   # ASTERISK, right-left
0xAB = 0x002B   # PLUS SIGN, right-left
0xAC = 0x002C   # COMMA, right-left
0xAD = 0x002D   # HYPHEN-MINUS, right-left
0xAE = 0x002E   # FULL STOP, right-left
0xAF = 0x002F   # SOLIDUS, right-left
0xB0 = 0x0030   # DIGIT ZERO, right-left (need override)
0xB1 = 0x0031   # DIGIT ONE, right-left (need override)
0xB2 = 0x0032   # DIGIT TWO, right-left (need override)
0xB3 = 0x0033   # DIGIT THREE, right-left (need override)
0xB4 = 0x0034   # DIGIT FOUR, right-left (need override)
0xB5 = 0x0035   # DIGIT FIVE, right-left (need override)
0xB6 = 0x0036   # DIGIT SIX, right-left (need override)
0xB7 = 0x0037   # DIGIT SEVEN, right-left (need override)
0xB8 = 0x0038   # DIGIT EIGHT, right-left (need override)
0xB9 = 0x0039   # DIGIT NINE, right-left (need override)
0xBA = 0x003A   # COLON, right-left
0xBB = 0x003B   # SEMICOLON, right-left
0xBC = 0x003C   # LESS-THAN SIGN, right-left
0xBD = 0x003D   # EQUALS SIGN, right-left
0xBE = 0x003E   # GREATER-THAN SIGN, right-left
0xBF = 0x003F   # QUESTION MARK, right-left
0xC0 = 0x05B9   # 0xF86A+0x05DC+0x05B9  # Hebrew ligature lamed holam
0xC1 = 0x201E   # DOUBLE LOW-9 QUOTATION MARK, right-left
0xC2 = 0xF89B   # Hebrew canoral 1
0xC3 = 0xF89C   # Hebrew canoral 2
0xC4 = 0xF89D   # Hebrew canoral 3
0xC5 = 0xF89E   # Hebrew canoral 4
0xC6 = 0x05BC   # HEBREW POINT DAGESH OR MAPIQ
0xC7 = 0xFB4B   # HEBREW LETTER VAV WITH HOLAM
0xC8 = 0xFB35   # HEBREW LETTER VAV WITH DAGESH
0xC9 = 0x2026   # HORIZONTAL ELLIPSIS, right-left
0xCA = 0x00A0   # NO-BREAK SPACE, right-left
0xCB = 0x05B8   # HEBREW POINT QAMATS
0xCC = 0x05B7   # HEBREW POINT PATAH
0xCD = 0x05B5   # HEBREW POINT TSERE
0xCE = 0x05B6   # HEBREW POINT SEGOL
0xCF = 0x05B4   # HEBREW POINT HIRIQ
0xD0 = 0x2013   # EN DASH, right-left
0xD1 = 0x2014   # EM DASH, right-left
0xD2 = 0x201C   # LEFT DOUBLE QUOTATION MARK, right-left
0xD3 = 0x201D   # RIGHT DOUBLE QUOTATION MARK, right-left
0xD4 = 0x2018   # LEFT SINGLE QUOTATION MARK, right-left
0xD5 = 0x2019   # RIGHT SINGLE QUOTATION MARK, right-left
0xD6 = 0xFB2A   # HEBREW LETTER SHIN WITH SHIN DOT
0xD7 = 0xFB2B   # HEBREW LETTER SHIN WITH SIN DOT
0xD8 = 0x05BF   # HEBREW POINT RAFE
0xD9 = 0x05B0   # HEBREW POINT SHEVA
0xDA = 0x05B2   # HEBREW POINT HATAF PATAH
0xDB = 0x05B1   # HEBREW POINT HATAF SEGOL
0xDC = 0x05BB   # HEBREW POINT QUBUTS
0xDD = 0x05B9   # HEBREW POINT HOLAM
0xDE = 0xF87F   # 0x05B8+0xF87F # HEBREW POINT QAMATS, alternate form "qamats qatan"
0xDF = 0x05B3   # HEBREW POINT HATAF QAMATS
0xE0 = 0x05D0   # HEBREW LETTER ALEF
0xE1 = 0x05D1   # HEBREW LETTER BET
0xE2 = 0x05D2   # HEBREW LETTER GIMEL
0xE3 = 0x05D3   # HEBREW LETTER DALET
0xE4 = 0x05D4   # HEBREW LETTER HE
0xE5 = 0x05D5   # HEBREW LETTER VAV
0xE6 = 0x05D6   # HEBREW LETTER ZAYIN
0xE7 = 0x05D7   # HEBREW LETTER HET
0xE8 = 0x05D8   # HEBREW LETTER TET
0xE9 = 0x05D9   # HEBREW LETTER YOD
0xEA = 0x05DA   # HEBREW LETTER FINAL KAF
0xEB = 0x05DB   # HEBREW LETTER KAF
0xEC = 0x05DC   # HEBREW LETTER LAMED
0xED = 0x05DD   # HEBREW LETTER FINAL MEM
0xEE = 0x05DE   # HEBREW LETTER MEM
0xEF = 0x05DF   # HEBREW LETTER FINAL NUN
0xF0 = 0x05E0   # HEBREW LETTER NUN
0xF1 = 0x05E1   # HEBREW LETTER SAMEKH
0xF2 = 0x05E2   # HEBREW LETTER AYIN
0xF3 = 0x05E3   # HEBREW LETTER FINAL PE
0xF4 = 0x05E4   # HEBREW LETTER PE
0xF5 = 0x05E5   # HEBREW LETTER FINAL TSADI
0xF6 = 0x05E6   # HEBREW LETTER TSADI
0xF7 = 0x05E7   # HEBREW LETTER QOF
0xF8 = 0x05E8   # HEBREW LETTER RESH
0xF9 = 0x05E9   # HEBREW LETTER SHIN
0xFA = 0x05EA   # HEBREW LETTER TAV
0xFB = 0x007D   # RIGHT CURLY BRACKET, right-left
0xFC = 0x005D   # RIGHT SQUARE BRACKET, right-left
0xFD = 0x007B   # LEFT CURLY BRACKET, right-left
0xFE = 0x005B   # LEFT SQUARE BRACKET, right-left
0xFF = 0x007C   # VERTICAL LINE, right-left
END_MAP