summaryrefslogtreecommitdiff
path: root/scripts
diff options
context:
space:
mode:
authorTor Andersson <tor.andersson@artifex.com>2018-03-20 13:03:21 +0100
committerTor Andersson <tor.andersson@artifex.com>2018-03-22 14:58:01 +0100
commitdd0badd75b48f50e7bd9f15c0ebafcdb48e16e66 (patch)
treecf749bb9c776323a9bd7c0b71264605661063187 /scripts
parent81c77a6b6464f5af66f851837f85ed6f9724f19e (diff)
downloadmupdf-dd0badd75b48f50e7bd9f15c0ebafcdb48e16e66.tar.xz
Check in script used to create encoding tables.
Diffstat (limited to 'scripts')
-rw-r--r--scripts/8859-7.TXT299
-rw-r--r--scripts/KOI8-U.TXT301
-rw-r--r--scripts/makeencoding.py49
3 files changed, 649 insertions, 0 deletions
diff --git a/scripts/8859-7.TXT b/scripts/8859-7.TXT
new file mode 100644
index 00000000..49131a4d
--- /dev/null
+++ b/scripts/8859-7.TXT
@@ -0,0 +1,299 @@
+# 8859-7.TXT
+# Date: 2015-12-02 21:47:00 GMT [KW]
+# © 2015 Unicode®, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+#
+# Name: ISO 8859-7:2003 to Unicode
+# Unicode version: 4.0
+# Table version: 3.0
+# Table format: Format A
+# Date: 2003-Nov-12 (header updated: 2015 December 02)
+# Authors: Ken Whistler <ken@unicode.org>
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO 8859-7:2003 characters map into Unicode.
+#
+# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928,
+# and ECMA 118. ISO 8859-7:2003 adds two currency signs
+# and one other character not in the earlier standard.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO 8859-7 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO 8859-7 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+# Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7
+# Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7
+#
+# 2.0 version updates 1.0 version by adding mappings for the
+# three newly added characters 0xA4, 0xA5, 0xAA.
+#
+# 3.0 version: updates to copyright notice and terms of use; no
+# changes to character mappings
+#
+# Updated versions of this file may be found in:
+# http://www.unicode.org/Public/MAPPINGS/
+#
+# Any comments or problems, contact us at:
+# http://www.unicode.org/reporting.html
+#
+0x00 0x0000 # NULL
+0x01 0x0001 # START OF HEADING
+0x02 0x0002 # START OF TEXT
+0x03 0x0003 # END OF TEXT
+0x04 0x0004 # END OF TRANSMISSION
+0x05 0x0005 # ENQUIRY
+0x06 0x0006 # ACKNOWLEDGE
+0x07 0x0007 # BELL
+0x08 0x0008 # BACKSPACE
+0x09 0x0009 # HORIZONTAL TABULATION
+0x0A 0x000A # LINE FEED
+0x0B 0x000B # VERTICAL TABULATION
+0x0C 0x000C # FORM FEED
+0x0D 0x000D # CARRIAGE RETURN
+0x0E 0x000E # SHIFT OUT
+0x0F 0x000F # SHIFT IN
+0x10 0x0010 # DATA LINK ESCAPE
+0x11 0x0011 # DEVICE CONTROL ONE
+0x12 0x0012 # DEVICE CONTROL TWO
+0x13 0x0013 # DEVICE CONTROL THREE
+0x14 0x0014 # DEVICE CONTROL FOUR
+0x15 0x0015 # NEGATIVE ACKNOWLEDGE
+0x16 0x0016 # SYNCHRONOUS IDLE
+0x17 0x0017 # END OF TRANSMISSION BLOCK
+0x18 0x0018 # CANCEL
+0x19 0x0019 # END OF MEDIUM
+0x1A 0x001A # SUBSTITUTE
+0x1B 0x001B # ESCAPE
+0x1C 0x001C # FILE SEPARATOR
+0x1D 0x001D # GROUP SEPARATOR
+0x1E 0x001E # RECORD SEPARATOR
+0x1F 0x001F # UNIT SEPARATOR
+0x20 0x0020 # SPACE
+0x21 0x0021 # EXCLAMATION MARK
+0x22 0x0022 # QUOTATION MARK
+0x23 0x0023 # NUMBER SIGN
+0x24 0x0024 # DOLLAR SIGN
+0x25 0x0025 # PERCENT SIGN
+0x26 0x0026 # AMPERSAND
+0x27 0x0027 # APOSTROPHE
+0x28 0x0028 # LEFT PARENTHESIS
+0x29 0x0029 # RIGHT PARENTHESIS
+0x2A 0x002A # ASTERISK
+0x2B 0x002B # PLUS SIGN
+0x2C 0x002C # COMMA
+0x2D 0x002D # HYPHEN-MINUS
+0x2E 0x002E # FULL STOP
+0x2F 0x002F # SOLIDUS
+0x30 0x0030 # DIGIT ZERO
+0x31 0x0031 # DIGIT ONE
+0x32 0x0032 # DIGIT TWO
+0x33 0x0033 # DIGIT THREE
+0x34 0x0034 # DIGIT FOUR
+0x35 0x0035 # DIGIT FIVE
+0x36 0x0036 # DIGIT SIX
+0x37 0x0037 # DIGIT SEVEN
+0x38 0x0038 # DIGIT EIGHT
+0x39 0x0039 # DIGIT NINE
+0x3A 0x003A # COLON
+0x3B 0x003B # SEMICOLON
+0x3C 0x003C # LESS-THAN SIGN
+0x3D 0x003D # EQUALS SIGN
+0x3E 0x003E # GREATER-THAN SIGN
+0x3F 0x003F # QUESTION MARK
+0x40 0x0040 # COMMERCIAL AT
+0x41 0x0041 # LATIN CAPITAL LETTER A
+0x42 0x0042 # LATIN CAPITAL LETTER B
+0x43 0x0043 # LATIN CAPITAL LETTER C
+0x44 0x0044 # LATIN CAPITAL LETTER D
+0x45 0x0045 # LATIN CAPITAL LETTER E
+0x46 0x0046 # LATIN CAPITAL LETTER F
+0x47 0x0047 # LATIN CAPITAL LETTER G
+0x48 0x0048 # LATIN CAPITAL LETTER H
+0x49 0x0049 # LATIN CAPITAL LETTER I
+0x4A 0x004A # LATIN CAPITAL LETTER J
+0x4B 0x004B # LATIN CAPITAL LETTER K
+0x4C 0x004C # LATIN CAPITAL LETTER L
+0x4D 0x004D # LATIN CAPITAL LETTER M
+0x4E 0x004E # LATIN CAPITAL LETTER N
+0x4F 0x004F # LATIN CAPITAL LETTER O
+0x50 0x0050 # LATIN CAPITAL LETTER P
+0x51 0x0051 # LATIN CAPITAL LETTER Q
+0x52 0x0052 # LATIN CAPITAL LETTER R
+0x53 0x0053 # LATIN CAPITAL LETTER S
+0x54 0x0054 # LATIN CAPITAL LETTER T
+0x55 0x0055 # LATIN CAPITAL LETTER U
+0x56 0x0056 # LATIN CAPITAL LETTER V
+0x57 0x0057 # LATIN CAPITAL LETTER W
+0x58 0x0058 # LATIN CAPITAL LETTER X
+0x59 0x0059 # LATIN CAPITAL LETTER Y
+0x5A 0x005A # LATIN CAPITAL LETTER Z
+0x5B 0x005B # LEFT SQUARE BRACKET
+0x5C 0x005C # REVERSE SOLIDUS
+0x5D 0x005D # RIGHT SQUARE BRACKET
+0x5E 0x005E # CIRCUMFLEX ACCENT
+0x5F 0x005F # LOW LINE
+0x60 0x0060 # GRAVE ACCENT
+0x61 0x0061 # LATIN SMALL LETTER A
+0x62 0x0062 # LATIN SMALL LETTER B
+0x63 0x0063 # LATIN SMALL LETTER C
+0x64 0x0064 # LATIN SMALL LETTER D
+0x65 0x0065 # LATIN SMALL LETTER E
+0x66 0x0066 # LATIN SMALL LETTER F
+0x67 0x0067 # LATIN SMALL LETTER G
+0x68 0x0068 # LATIN SMALL LETTER H
+0x69 0x0069 # LATIN SMALL LETTER I
+0x6A 0x006A # LATIN SMALL LETTER J
+0x6B 0x006B # LATIN SMALL LETTER K
+0x6C 0x006C # LATIN SMALL LETTER L
+0x6D 0x006D # LATIN SMALL LETTER M
+0x6E 0x006E # LATIN SMALL LETTER N
+0x6F 0x006F # LATIN SMALL LETTER O
+0x70 0x0070 # LATIN SMALL LETTER P
+0x71 0x0071 # LATIN SMALL LETTER Q
+0x72 0x0072 # LATIN SMALL LETTER R
+0x73 0x0073 # LATIN SMALL LETTER S
+0x74 0x0074 # LATIN SMALL LETTER T
+0x75 0x0075 # LATIN SMALL LETTER U
+0x76 0x0076 # LATIN SMALL LETTER V
+0x77 0x0077 # LATIN SMALL LETTER W
+0x78 0x0078 # LATIN SMALL LETTER X
+0x79 0x0079 # LATIN SMALL LETTER Y
+0x7A 0x007A # LATIN SMALL LETTER Z
+0x7B 0x007B # LEFT CURLY BRACKET
+0x7C 0x007C # VERTICAL LINE
+0x7D 0x007D # RIGHT CURLY BRACKET
+0x7E 0x007E # TILDE
+0x7F 0x007F # DELETE
+0x80 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x2018 # LEFT SINGLE QUOTATION MARK
+0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x20AC # EURO SIGN
+0xA5 0x20AF # DRACHMA SIGN
+0xA6 0x00A6 # BROKEN BAR
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x00A8 # DIAERESIS
+0xA9 0x00A9 # COPYRIGHT SIGN
+0xAA 0x037A # GREEK YPOGEGRAMMENI
+0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xAC 0x00AC # NOT SIGN
+0xAD 0x00AD # SOFT HYPHEN
+0xAF 0x2015 # HORIZONTAL BAR
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x00B1 # PLUS-MINUS SIGN
+0xB2 0x00B2 # SUPERSCRIPT TWO
+0xB3 0x00B3 # SUPERSCRIPT THREE
+0xB4 0x0384 # GREEK TONOS
+0xB5 0x0385 # GREEK DIALYTIKA TONOS
+0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS
+0xB7 0x00B7 # MIDDLE DOT
+0xB8 0x0388 # GREEK CAPITAL LETTER EPSILON WITH TONOS
+0xB9 0x0389 # GREEK CAPITAL LETTER ETA WITH TONOS
+0xBA 0x038A # GREEK CAPITAL LETTER IOTA WITH TONOS
+0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xBC 0x038C # GREEK CAPITAL LETTER OMICRON WITH TONOS
+0xBD 0x00BD # VULGAR FRACTION ONE HALF
+0xBE 0x038E # GREEK CAPITAL LETTER UPSILON WITH TONOS
+0xBF 0x038F # GREEK CAPITAL LETTER OMEGA WITH TONOS
+0xC0 0x0390 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+0xC1 0x0391 # GREEK CAPITAL LETTER ALPHA
+0xC2 0x0392 # GREEK CAPITAL LETTER BETA
+0xC3 0x0393 # GREEK CAPITAL LETTER GAMMA
+0xC4 0x0394 # GREEK CAPITAL LETTER DELTA
+0xC5 0x0395 # GREEK CAPITAL LETTER EPSILON
+0xC6 0x0396 # GREEK CAPITAL LETTER ZETA
+0xC7 0x0397 # GREEK CAPITAL LETTER ETA
+0xC8 0x0398 # GREEK CAPITAL LETTER THETA
+0xC9 0x0399 # GREEK CAPITAL LETTER IOTA
+0xCA 0x039A # GREEK CAPITAL LETTER KAPPA
+0xCB 0x039B # GREEK CAPITAL LETTER LAMDA
+0xCC 0x039C # GREEK CAPITAL LETTER MU
+0xCD 0x039D # GREEK CAPITAL LETTER NU
+0xCE 0x039E # GREEK CAPITAL LETTER XI
+0xCF 0x039F # GREEK CAPITAL LETTER OMICRON
+0xD0 0x03A0 # GREEK CAPITAL LETTER PI
+0xD1 0x03A1 # GREEK CAPITAL LETTER RHO
+0xD3 0x03A3 # GREEK CAPITAL LETTER SIGMA
+0xD4 0x03A4 # GREEK CAPITAL LETTER TAU
+0xD5 0x03A5 # GREEK CAPITAL LETTER UPSILON
+0xD6 0x03A6 # GREEK CAPITAL LETTER PHI
+0xD7 0x03A7 # GREEK CAPITAL LETTER CHI
+0xD8 0x03A8 # GREEK CAPITAL LETTER PSI
+0xD9 0x03A9 # GREEK CAPITAL LETTER OMEGA
+0xDA 0x03AA # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+0xDB 0x03AB # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+0xDC 0x03AC # GREEK SMALL LETTER ALPHA WITH TONOS
+0xDD 0x03AD # GREEK SMALL LETTER EPSILON WITH TONOS
+0xDE 0x03AE # GREEK SMALL LETTER ETA WITH TONOS
+0xDF 0x03AF # GREEK SMALL LETTER IOTA WITH TONOS
+0xE0 0x03B0 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+0xE1 0x03B1 # GREEK SMALL LETTER ALPHA
+0xE2 0x03B2 # GREEK SMALL LETTER BETA
+0xE3 0x03B3 # GREEK SMALL LETTER GAMMA
+0xE4 0x03B4 # GREEK SMALL LETTER DELTA
+0xE5 0x03B5 # GREEK SMALL LETTER EPSILON
+0xE6 0x03B6 # GREEK SMALL LETTER ZETA
+0xE7 0x03B7 # GREEK SMALL LETTER ETA
+0xE8 0x03B8 # GREEK SMALL LETTER THETA
+0xE9 0x03B9 # GREEK SMALL LETTER IOTA
+0xEA 0x03BA # GREEK SMALL LETTER KAPPA
+0xEB 0x03BB # GREEK SMALL LETTER LAMDA
+0xEC 0x03BC # GREEK SMALL LETTER MU
+0xED 0x03BD # GREEK SMALL LETTER NU
+0xEE 0x03BE # GREEK SMALL LETTER XI
+0xEF 0x03BF # GREEK SMALL LETTER OMICRON
+0xF0 0x03C0 # GREEK SMALL LETTER PI
+0xF1 0x03C1 # GREEK SMALL LETTER RHO
+0xF2 0x03C2 # GREEK SMALL LETTER FINAL SIGMA
+0xF3 0x03C3 # GREEK SMALL LETTER SIGMA
+0xF4 0x03C4 # GREEK SMALL LETTER TAU
+0xF5 0x03C5 # GREEK SMALL LETTER UPSILON
+0xF6 0x03C6 # GREEK SMALL LETTER PHI
+0xF7 0x03C7 # GREEK SMALL LETTER CHI
+0xF8 0x03C8 # GREEK SMALL LETTER PSI
+0xF9 0x03C9 # GREEK SMALL LETTER OMEGA
+0xFA 0x03CA # GREEK SMALL LETTER IOTA WITH DIALYTIKA
+0xFB 0x03CB # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+0xFC 0x03CC # GREEK SMALL LETTER OMICRON WITH TONOS
+0xFD 0x03CD # GREEK SMALL LETTER UPSILON WITH TONOS
+0xFE 0x03CE # GREEK SMALL LETTER OMEGA WITH TONOS
diff --git a/scripts/KOI8-U.TXT b/scripts/KOI8-U.TXT
new file mode 100644
index 00000000..c533b394
--- /dev/null
+++ b/scripts/KOI8-U.TXT
@@ -0,0 +1,301 @@
+# KOI8-U.TXT
+# Date: 2016-01-04 23:09:00 GMT [KW]
+# © 2016 Unicode®, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+#
+#
+# Name: KOI8-U (RFC2319) to Unicode
+# Unicode version: 5.1
+# Table version: 2.0
+# Table format: Format A
+# Date: 13 October 2008 (header updated: 2016-January-04)
+# Authors: Philippe Verdy <verdy_p AT wanadoo.fr>,
+# Helmut Richter <richter@lrz.de>
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# KOI8-U characters map into Unicode. The underlying document is the
+# mapping described in RFC 2319. No statements are made as to whether
+# this mapping is the same as the mapping defined as "Code Page 878"
+# with some vendors.
+#
+# The KOI8-U (RFC2319) encoding is a variant based on KOI8-R (RFC1489),
+# where the support for four additional Cyrillic letters was added (both small
+# and capital letters), replacing 8 box-drawing characters. It is still widely
+# used to encode texts in Ukrainian, Byelorussian and Bulgarian.
+#
+# Format: Three tab-separated columns
+# Column #1 is the KOI8-U code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in KOI8-U order.
+#
+# Version history
+# 1.0 version: created.
+# 2.0 version: updates to copyright notice and terms of use; no
+# changes to character mappings
+#
+# Updated versions of this file may be found in:
+# <http://www.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact the Unicode Consortium at:
+# <http://www.unicode.org/reporting.html>
+#
+0x00 0x0000 # NULL
+0x01 0x0001 # START OF HEADING
+0x02 0x0002 # START OF TEXT
+0x03 0x0003 # END OF TEXT
+0x04 0x0004 # END OF TRANSMISSION
+0x05 0x0005 # ENQUIRY
+0x06 0x0006 # ACKNOWLEDGE
+0x07 0x0007 # BELL
+0x08 0x0008 # BACKSPACE
+0x09 0x0009 # HORIZONTAL TABULATION
+0x0A 0x000A # LINE FEED
+0x0B 0x000B # VERTICAL TABULATION
+0x0C 0x000C # FORM FEED
+0x0D 0x000D # CARRIAGE RETURN
+0x0E 0x000E # SHIFT OUT
+0x0F 0x000F # SHIFT IN
+0x10 0x0010 # DATA LINK ESCAPE
+0x11 0x0011 # DEVICE CONTROL ONE
+0x12 0x0012 # DEVICE CONTROL TWO
+0x13 0x0013 # DEVICE CONTROL THREE
+0x14 0x0014 # DEVICE CONTROL FOUR
+0x15 0x0015 # NEGATIVE ACKNOWLEDGE
+0x16 0x0016 # SYNCHRONOUS IDLE
+0x17 0x0017 # END OF TRANSMISSION BLOCK
+0x18 0x0018 # CANCEL
+0x19 0x0019 # END OF MEDIUM
+0x1A 0x001A # SUBSTITUTE
+0x1B 0x001B # ESCAPE
+0x1C 0x001C # FILE SEPARATOR
+0x1D 0x001D # GROUP SEPARATOR
+0x1E 0x001E # RECORD SEPARATOR
+0x1F 0x001F # UNIT SEPARATOR
+0x20 0x0020 # SPACE
+0x21 0x0021 # EXCLAMATION MARK
+0x22 0x0022 # QUOTATION MARK
+0x23 0x0023 # NUMBER SIGN
+0x24 0x0024 # DOLLAR SIGN
+0x25 0x0025 # PERCENT SIGN
+0x26 0x0026 # AMPERSAND
+0x27 0x0027 # APOSTROPHE
+0x28 0x0028 # LEFT PARENTHESIS
+0x29 0x0029 # RIGHT PARENTHESIS
+0x2A 0x002A # ASTERISK
+0x2B 0x002B # PLUS SIGN
+0x2C 0x002C # COMMA
+0x2D 0x002D # HYPHEN-MINUS
+0x2E 0x002E # FULL STOP
+0x2F 0x002F # SOLIDUS
+0x30 0x0030 # DIGIT ZERO
+0x31 0x0031 # DIGIT ONE
+0x32 0x0032 # DIGIT TWO
+0x33 0x0033 # DIGIT THREE
+0x34 0x0034 # DIGIT FOUR
+0x35 0x0035 # DIGIT FIVE
+0x36 0x0036 # DIGIT SIX
+0x37 0x0037 # DIGIT SEVEN
+0x38 0x0038 # DIGIT EIGHT
+0x39 0x0039 # DIGIT NINE
+0x3A 0x003A # COLON
+0x3B 0x003B # SEMICOLON
+0x3C 0x003C # LESS-THAN SIGN
+0x3D 0x003D # EQUALS SIGN
+0x3E 0x003E # GREATER-THAN SIGN
+0x3F 0x003F # QUESTION MARK
+0x40 0x0040 # COMMERCIAL AT
+0x41 0x0041 # LATIN CAPITAL LETTER A
+0x42 0x0042 # LATIN CAPITAL LETTER B
+0x43 0x0043 # LATIN CAPITAL LETTER C
+0x44 0x0044 # LATIN CAPITAL LETTER D
+0x45 0x0045 # LATIN CAPITAL LETTER E
+0x46 0x0046 # LATIN CAPITAL LETTER F
+0x47 0x0047 # LATIN CAPITAL LETTER G
+0x48 0x0048 # LATIN CAPITAL LETTER H
+0x49 0x0049 # LATIN CAPITAL LETTER I
+0x4A 0x004A # LATIN CAPITAL LETTER J
+0x4B 0x004B # LATIN CAPITAL LETTER K
+0x4C 0x004C # LATIN CAPITAL LETTER L
+0x4D 0x004D # LATIN CAPITAL LETTER M
+0x4E 0x004E # LATIN CAPITAL LETTER N
+0x4F 0x004F # LATIN CAPITAL LETTER O
+0x50 0x0050 # LATIN CAPITAL LETTER P
+0x51 0x0051 # LATIN CAPITAL LETTER Q
+0x52 0x0052 # LATIN CAPITAL LETTER R
+0x53 0x0053 # LATIN CAPITAL LETTER S
+0x54 0x0054 # LATIN CAPITAL LETTER T
+0x55 0x0055 # LATIN CAPITAL LETTER U
+0x56 0x0056 # LATIN CAPITAL LETTER V
+0x57 0x0057 # LATIN CAPITAL LETTER W
+0x58 0x0058 # LATIN CAPITAL LETTER X
+0x59 0x0059 # LATIN CAPITAL LETTER Y
+0x5A 0x005A # LATIN CAPITAL LETTER Z
+0x5B 0x005B # LEFT SQUARE BRACKET
+0x5C 0x005C # REVERSE SOLIDUS
+0x5D 0x005D # RIGHT SQUARE BRACKET
+0x5E 0x005E # CIRCUMFLEX ACCENT
+0x5F 0x005F # LOW LINE
+0x60 0x0060 # GRAVE ACCENT
+0x61 0x0061 # LATIN SMALL LETTER A
+0x62 0x0062 # LATIN SMALL LETTER B
+0x63 0x0063 # LATIN SMALL LETTER C
+0x64 0x0064 # LATIN SMALL LETTER D
+0x65 0x0065 # LATIN SMALL LETTER E
+0x66 0x0066 # LATIN SMALL LETTER F
+0x67 0x0067 # LATIN SMALL LETTER G
+0x68 0x0068 # LATIN SMALL LETTER H
+0x69 0x0069 # LATIN SMALL LETTER I
+0x6A 0x006A # LATIN SMALL LETTER J
+0x6B 0x006B # LATIN SMALL LETTER K
+0x6C 0x006C # LATIN SMALL LETTER L
+0x6D 0x006D # LATIN SMALL LETTER M
+0x6E 0x006E # LATIN SMALL LETTER N
+0x6F 0x006F # LATIN SMALL LETTER O
+0x70 0x0070 # LATIN SMALL LETTER P
+0x71 0x0071 # LATIN SMALL LETTER Q
+0x72 0x0072 # LATIN SMALL LETTER R
+0x73 0x0073 # LATIN SMALL LETTER S
+0x74 0x0074 # LATIN SMALL LETTER T
+0x75 0x0075 # LATIN SMALL LETTER U
+0x76 0x0076 # LATIN SMALL LETTER V
+0x77 0x0077 # LATIN SMALL LETTER W
+0x78 0x0078 # LATIN SMALL LETTER X
+0x79 0x0079 # LATIN SMALL LETTER Y
+0x7A 0x007A # LATIN SMALL LETTER Z
+0x7B 0x007B # LEFT CURLY BRACKET
+0x7C 0x007C # VERTICAL LINE
+0x7D 0x007D # RIGHT CURLY BRACKET
+0x7E 0x007E # TILDE
+0x7F 0x007F # DELETE
+0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
+0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
+0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
+0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
+0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
+0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
+0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0x8B 0x2580 # UPPER HALF BLOCK
+0x8C 0x2584 # LOWER HALF BLOCK
+0x8D 0x2588 # FULL BLOCK
+0x8E 0x258C # LEFT HALF BLOCK
+0x8F 0x2590 # RIGHT HALF BLOCK
+0x90 0x2591 # LIGHT SHADE
+0x91 0x2592 # MEDIUM SHADE
+0x92 0x2593 # DARK SHADE
+0x93 0x2320 # TOP HALF INTEGRAL
+0x94 0x25A0 # BLACK SQUARE
+0x95 0x2219 # BULLET OPERATOR
+0x96 0x221A # SQUARE ROOT
+0x97 0x2248 # ALMOST EQUAL TO
+0x98 0x2264 # LESS-THAN OR EQUAL TO
+0x99 0x2265 # GREATER-THAN OR EQUAL TO
+0x9A 0x00A0 # NO-BREAK SPACE
+0x9B 0x2321 # BOTTOM HALF INTEGRAL
+0x9C 0x00B0 # DEGREE SIGN
+0x9D 0x00B2 # SUPERSCRIPT TWO
+0x9E 0x00B7 # MIDDLE DOT
+0x9F 0x00F7 # DIVISION SIGN
+0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
+0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
+0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xA3 0x0451 # CYRILLIC SMALL LETTER IO
+0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
+0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN)
+0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
+0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN
+0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
+0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
+0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN)
+0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xBF 0x00A9 # COPYRIGHT SIGN
+0xC0 0x044E # CYRILLIC SMALL LETTER YU
+0xC1 0x0430 # CYRILLIC SMALL LETTER A
+0xC2 0x0431 # CYRILLIC SMALL LETTER BE
+0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
+0xC4 0x0434 # CYRILLIC SMALL LETTER DE
+0xC5 0x0435 # CYRILLIC SMALL LETTER IE
+0xC6 0x0444 # CYRILLIC SMALL LETTER EF
+0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
+0xC8 0x0445 # CYRILLIC SMALL LETTER HA
+0xC9 0x0438 # CYRILLIC SMALL LETTER I
+0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
+0xCB 0x043A # CYRILLIC SMALL LETTER KA
+0xCC 0x043B # CYRILLIC SMALL LETTER EL
+0xCD 0x043C # CYRILLIC SMALL LETTER EM
+0xCE 0x043D # CYRILLIC SMALL LETTER EN
+0xCF 0x043E # CYRILLIC SMALL LETTER O
+0xD0 0x043F # CYRILLIC SMALL LETTER PE
+0xD1 0x044F # CYRILLIC SMALL LETTER YA
+0xD2 0x0440 # CYRILLIC SMALL LETTER ER
+0xD3 0x0441 # CYRILLIC SMALL LETTER ES
+0xD4 0x0442 # CYRILLIC SMALL LETTER TE
+0xD5 0x0443 # CYRILLIC SMALL LETTER U
+0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
+0xD7 0x0432 # CYRILLIC SMALL LETTER VE
+0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
+0xD9 0x044B # CYRILLIC SMALL LETTER YERU
+0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
+0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
+0xDC 0x044D # CYRILLIC SMALL LETTER E
+0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
+0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
+0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
+0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
+0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
+0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
+0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
+0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
+0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
+0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
+0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
+0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
+0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
+0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
+0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
+0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
+0xED 0x041C # CYRILLIC CAPITAL LETTER EM
+0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
+0xEF 0x041E # CYRILLIC CAPITAL LETTER O
+0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
+0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
+0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
+0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
+0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
+0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
+0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
+0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
+0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
+0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
+0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
+0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
+0xFC 0x042D # CYRILLIC CAPITAL LETTER E
+0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
+0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
+0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
diff --git a/scripts/makeencoding.py b/scripts/makeencoding.py
new file mode 100644
index 00000000..054be9c0
--- /dev/null
+++ b/scripts/makeencoding.py
@@ -0,0 +1,49 @@
+# Convert unicode mapping table to C arrays mapping glyph names and unicode values.
+#
+# ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-U.TXT
+# ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT
+#
+
+glyphs = {}
+for line in open("scripts/glyphlist.txt").readlines():
+ if line[0] != '#':
+ n, u = line.rstrip().split(';')
+ if len(u) == 4:
+ u = int(u, base=16)
+ glyphs[u] = n
+
+def load_table(fn):
+ table = [0] * 256
+ for line in open(fn).readlines():
+ if line[0] != '#':
+ line = line.split()
+ c = int(line[0][2:], base=16)
+ u = int(line[1][2:], base=16)
+ table[c] = u
+ return table
+
+def dump_table(name, table):
+ print "const char *pdf_glyph_name_from_%s[%d] = {" % (name, len(table))
+ for u in table:
+ if u in glyphs:
+ print '"%s",' % glyphs[u]
+ else:
+ print '_notdef,'
+ print "};"
+ print
+ print "static const struct { unsigned short u, c; } %s_from_unicode[] = {" % name
+ rev = []
+ i = 0
+ for u in table:
+ if u in glyphs:
+ if u >= 128:
+ rev += ['{0x%04x,%d},' % (u, i)]
+ i = i + 1
+ rev.sort()
+ for s in rev:
+ print s
+ print "};"
+ print
+
+dump_table("koi8u", load_table("scripts/KOI8-U.TXT"))
+dump_table("iso8859_7", load_table("scripts/8859-7.TXT"))