diff options
Diffstat (limited to 'src/chrtrans')
32 files changed, 597 insertions, 489 deletions
diff --git a/src/chrtrans/README.tables b/src/chrtrans/README.tables index 5993ccee..14431dad 100644 --- a/src/chrtrans/README.tables +++ b/src/chrtrans/README.tables @@ -6,6 +6,22 @@ for some of the RFC 1345 Mnemonic codes are out of date, a cleanup and update would be needed for serious use. [See also http://czyborra.com/charsets/iso8859.html for codepages survey.] +These changes were made to all of the files used from ftp.unicode.org: + + a) add the MIME name of the charset. + b) add a name for the display charset (used on Options screen) + c) add the codepage number + d) remove lines for control characters 0x00 to 0x1f, 0x7f to 0x9f. + e) comment-out ASCII lines 0x20 to 0x7f + f) use idem to represent the commented-out lines + g) change C-style 0xNNNN constants to Unicode-style U+NNNN. + +Other changes include + + h) add code-points to several lines to provide Unicode equivalents + i) add extra mappings at the end of the files + j) comment-out other one-one mappings in the 0xa0-0xff range. + More translation files can be easily provided (and new character entities added to entities.h), this set is just to test whether the system works in principle (and also how it behaves with incomplete data...) diff --git a/src/chrtrans/cp1250_uni.tbl b/src/chrtrans/cp1250_uni.tbl index 64ad83c4..8a19d555 100644 --- a/src/chrtrans/cp1250_uni.tbl +++ b/src/chrtrans/cp1250_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1250 diff --git a/src/chrtrans/cp1251_uni.tbl b/src/chrtrans/cp1251_uni.tbl index 97a00449..0d928f9c 100644 --- a/src/chrtrans/cp1251_uni.tbl +++ b/src/chrtrans/cp1251_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1251 diff --git a/src/chrtrans/cp1252_uni.tbl b/src/chrtrans/cp1252_uni.tbl index 2365c9c5..50ce967c 100644 --- a/src/chrtrans/cp1252_uni.tbl +++ b/src/chrtrans/cp1252_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #Shall this become the "default" translation? #There has to be exactly one table marked as "default". D0 diff --git a/src/chrtrans/cp1253_uni.tbl b/src/chrtrans/cp1253_uni.tbl index 8d3116d8..49523d44 100644 --- a/src/chrtrans/cp1253_uni.tbl +++ b/src/chrtrans/cp1253_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1253 diff --git a/src/chrtrans/cp1255_uni.tbl b/src/chrtrans/cp1255_uni.tbl index 5b82fcfd..3f0af9e1 100644 --- a/src/chrtrans/cp1255_uni.tbl +++ b/src/chrtrans/cp1255_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1255 diff --git a/src/chrtrans/cp1256_uni.tbl b/src/chrtrans/cp1256_uni.tbl index 267aaefd..1ab99c06 100644 --- a/src/chrtrans/cp1256_uni.tbl +++ b/src/chrtrans/cp1256_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1256 diff --git a/src/chrtrans/cp1257_uni.tbl b/src/chrtrans/cp1257_uni.tbl index 49d3e307..6cd0081d 100644 --- a/src/chrtrans/cp1257_uni.tbl +++ b/src/chrtrans/cp1257_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mwindows-1257 diff --git a/src/chrtrans/cp437_uni.tbl b/src/chrtrans/cp437_uni.tbl index 95755693..4f45ce72 100644 --- a/src/chrtrans/cp437_uni.tbl +++ b/src/chrtrans/cp437_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #Shall this become the "default" translation? #There has to be exactly one table marked as "default". D0 diff --git a/src/chrtrans/cp737_uni.tbl b/src/chrtrans/cp737_uni.tbl index 710bd288..e57e2619 100644 --- a/src/chrtrans/cp737_uni.tbl +++ b/src/chrtrans/cp737_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp737 diff --git a/src/chrtrans/cp775_uni.tbl b/src/chrtrans/cp775_uni.tbl index 26a29912..26a3ff72 100644 --- a/src/chrtrans/cp775_uni.tbl +++ b/src/chrtrans/cp775_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp775 diff --git a/src/chrtrans/cp850_uni.tbl b/src/chrtrans/cp850_uni.tbl index 91fe44ee..9d05af26 100644 --- a/src/chrtrans/cp850_uni.tbl +++ b/src/chrtrans/cp850_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #Shall this become the "default" translation? #Meaning of that is currently unclear... It's different #from the default input or default output charset... diff --git a/src/chrtrans/cp852_uni.tbl b/src/chrtrans/cp852_uni.tbl index c4ac349b..978cca4e 100644 --- a/src/chrtrans/cp852_uni.tbl +++ b/src/chrtrans/cp852_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp852 diff --git a/src/chrtrans/cp857_uni.tbl b/src/chrtrans/cp857_uni.tbl index bf6a6be4..bd309968 100644 --- a/src/chrtrans/cp857_uni.tbl +++ b/src/chrtrans/cp857_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp857 diff --git a/src/chrtrans/cp862_uni.tbl b/src/chrtrans/cp862_uni.tbl index 3dfa09e5..ebf12224 100644 --- a/src/chrtrans/cp862_uni.tbl +++ b/src/chrtrans/cp862_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp862 diff --git a/src/chrtrans/cp864_uni.tbl b/src/chrtrans/cp864_uni.tbl index e5ec56d3..65685777 100644 --- a/src/chrtrans/cp864_uni.tbl +++ b/src/chrtrans/cp864_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp864 diff --git a/src/chrtrans/cp866_uni.tbl b/src/chrtrans/cp866_uni.tbl index f88e17f8..029e0250 100644 --- a/src/chrtrans/cp866_uni.tbl +++ b/src/chrtrans/cp866_uni.tbl @@ -1,4 +1,5 @@ -# +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp866 diff --git a/src/chrtrans/cp866u_uni.tbl b/src/chrtrans/cp866u_uni.tbl index 99c30de6..8d2dee0c 100644 --- a/src/chrtrans/cp866u_uni.tbl +++ b/src/chrtrans/cp866u_uni.tbl @@ -1,4 +1,5 @@ -# +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp866u diff --git a/src/chrtrans/cp869_uni.tbl b/src/chrtrans/cp869_uni.tbl index e8941b41..d662b831 100644 --- a/src/chrtrans/cp869_uni.tbl +++ b/src/chrtrans/cp869_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mcp869 diff --git a/src/chrtrans/iso01_uni.tbl b/src/chrtrans/iso01_uni.tbl index 5a47e2f8..a042e636 100644 --- a/src/chrtrans/iso01_uni.tbl +++ b/src/chrtrans/iso01_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #Shall this become the "default" translation? #Meaning of that is currently not well defined. It is different #from the default input or default output charset... @@ -14,43 +16,51 @@ OWestern (ISO-8859-1) C819 # -# Name: ISO 8859-1 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-1:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-1 (1987) characters map into Unicode. +# ISO/IEC 8859-1:1998 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-1 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-1 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 8859-1 order +# The entries are in ISO/IEC 8859-1 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw diff --git a/src/chrtrans/iso02_uni.tbl b/src/chrtrans/iso02_uni.tbl index b245be55..fe3fc718 100644 --- a/src/chrtrans/iso02_uni.tbl +++ b/src/chrtrans/iso02_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-2 @@ -8,43 +10,51 @@ OEastern European (ISO-8859-2) C912 # -# Name: ISO 8859-2 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO 8859-2:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-2 (1987) characters map into Unicode. +# ISO/IEC 8859-2:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-2 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-2 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 8859-2 order +# The entries are in ISO/IEC 8859-2 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw diff --git a/src/chrtrans/iso03_uni.tbl b/src/chrtrans/iso03_uni.tbl index 565bbf46..aafce8dc 100644 --- a/src/chrtrans/iso03_uni.tbl +++ b/src/chrtrans/iso03_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-3 @@ -8,43 +10,51 @@ OLatin 3 (ISO-8859-3) C913 # -# Name: ISO 8859-3 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-3:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-3 (1988) characters map into Unicode. +# ISO/IEC 8859-3:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-3 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-3 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 8859-3 order +# The entries are in ISO/IEC 8859-3 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # 0x20-0x7e idem # diff --git a/src/chrtrans/iso04_uni.tbl b/src/chrtrans/iso04_uni.tbl index 99bcaec7..a1c3ed06 100644 --- a/src/chrtrans/iso04_uni.tbl +++ b/src/chrtrans/iso04_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-4 @@ -8,45 +10,51 @@ OLatin 4 (ISO-8859-4) C914 # -# Name: ISO 8859-4 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-4:1998 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-4 (1988) characters map into Unicode. +# ISO/IEC 8859-4:1998 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-4 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-4 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 8859-4 order +# The entries are in ISO/IEC 8859-4 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -0x20-0x7e idem +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # #0x20 U+0020 # SPACE #0x21 U+0021 # EXCLAMATION MARK diff --git a/src/chrtrans/iso05_uni.tbl b/src/chrtrans/iso05_uni.tbl index 7eeba113..afbb213c 100644 --- a/src/chrtrans/iso05_uni.tbl +++ b/src/chrtrans/iso05_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-5 @@ -8,43 +10,51 @@ OCyrillic (ISO-8859-5) C915 # -# Name: ISO 8859-5 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO 8859-5:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-5 (1988) characters map into Unicode. +# ISO/IEC 8859-5:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-5 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-5 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 8859-5 order +# The entries are in ISO/IEC 8859-5 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw diff --git a/src/chrtrans/iso06_uni.tbl b/src/chrtrans/iso06_uni.tbl index 0e390018..e4ef995d 100644 --- a/src/chrtrans/iso06_uni.tbl +++ b/src/chrtrans/iso06_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-6 @@ -8,43 +10,53 @@ OArabic (ISO-8859-6) C1089 # -# Name: ISO 8859-6 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO 8859-6:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-6 (1987) characters map into Unicode. +# ISO/IEC 8859-6:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-6 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-6 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 8859-6 order +# The entries are in ISO/IEC 8859-6 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead +# of the Arabic digits (U+0660..U+0669). +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # 0x20-0x7e idem # @@ -64,16 +76,16 @@ C1089 #0x2D U+002D # HYPHEN-MINUS #0x2E U+002E # FULL STOP #0x2F U+002F # SOLIDUS -#0x30 U+0660 # ARABIC-INDIC DIGIT ZERO -#0x31 U+0661 # ARABIC-INDIC DIGIT ONE -#0x32 U+0662 # ARABIC-INDIC DIGIT TWO -#0x33 U+0663 # ARABIC-INDIC DIGIT THREE -#0x34 U+0664 # ARABIC-INDIC DIGIT FOUR -#0x35 U+0665 # ARABIC-INDIC DIGIT FIVE -#0x36 U+0666 # ARABIC-INDIC DIGIT SIX -#0x37 U+0667 # ARABIC-INDIC DIGIT SEVEN -#0x38 U+0668 # ARABIC-INDIC DIGIT EIGHT -#0x39 U+0669 # ARABIC-INDIC DIGIT NINE +#0x30 U+0030 # DIGIT ZERO +#0x31 U+0031 # DIGIT ONE +#0x32 U+0032 # DIGIT TWO +#0x33 U+0033 # DIGIT THREE +#0x34 U+0034 # DIGIT FOUR +#0x35 U+0035 # DIGIT FIVE +#0x36 U+0036 # DIGIT SIX +#0x37 U+0037 # DIGIT SEVEN +#0x38 U+0038 # DIGIT EIGHT +#0x39 U+0039 # DIGIT NINE #0x3A U+003A # COLON #0x3B U+003B # SEMICOLON #0x3C U+003C # LESS-THAN SIGN @@ -194,5 +206,3 @@ C1089 0xF0 U+0650 # ARABIC KASRA 0xF1 U+0651 # ARABIC SHADDA 0xF2 U+0652 # ARABIC SUKUN - - diff --git a/src/chrtrans/iso07_uni.tbl b/src/chrtrans/iso07_uni.tbl index 3eb3aeb7..87372a9e 100644 --- a/src/chrtrans/iso07_uni.tbl +++ b/src/chrtrans/iso07_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-7 @@ -8,43 +10,59 @@ OGreek (ISO-8859-7) C813 # -# Name: ISO 8859-7 (1987) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO 8859-7:2003 to Unicode +# Unicode version: 4.0 +# Table version: 2.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 2003-Nov-12 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-2003 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-7 (1987) characters map into Unicode. +# 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 +# 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. +# +# Updated versions of this file may be found in: +# <http://www.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact the Unicode Consortium at: +# <http://www.unicode.org/reporting.html> # # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw @@ -159,10 +177,13 @@ C813 0xA1 U+02BD U+2018 U+0371 # MODIFIER LETTER REVERSED COMMA 0xA2 U+02BC U+2019 U+0372 # MODIFIER LETTER APOSTROPHE 0xA3 U+00A3 # POUND SIGN +0xA4 U+20AC # EURO SIGN +0xA5 U+20AF # DRACHMA SIGN 0xA6 U+00A6 # BROKEN BAR 0xA7 U+00A7 # SECTION SIGN 0xA8 U+00A8 # DIAERESIS 0xA9 U+00A9 # COPYRIGHT SIGN +0xAA U+037A # GREEK YPOGEGRAMMENI 0xAB U+00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0xAC U+00AC # NOT SIGN 0xAD U+00AD # SOFT HYPHEN diff --git a/src/chrtrans/iso08_uni.tbl b/src/chrtrans/iso08_uni.tbl index d8c9d848..d162396a 100644 --- a/src/chrtrans/iso08_uni.tbl +++ b/src/chrtrans/iso08_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-8 @@ -8,43 +10,53 @@ OHebrew (ISO-8859-8) C916 # -# Name: ISO 8859-8 (1988) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-8:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.1 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 2000-Jan-03 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No # warranties of any kind are expressed or implied. The recipient # agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole +# file has been provided on optical media by Unicode, Inc., the sole # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-8 (1988) characters map into Unicode. +# ISO/IEC 8859-8:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-8 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-8 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 8859-8 order +# The entries are in ISO/IEC 8859-8 order. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# 1.1 version updates to the published 8859-8:1999, correcting +# the mapping of 0xAF and adding mappings for LRM and RLM. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # 0x20-0x7e idem # @@ -157,7 +169,7 @@ C916 0xAC U+00AC # NOT SIGN 0xAD U+00AD # SOFT HYPHEN 0xAE U+00AE # REGISTERED SIGN -0xAF U+203E # OVERLINE +0xAF U+00AF # MACRON 0xB0 U+00B0 # DEGREE SIGN 0xB1 U+00B1 # PLUS-MINUS SIGN 0xB2 U+00B2 # SUPERSCRIPT TWO @@ -201,6 +213,8 @@ C916 0xF8 U+05E8 # HEBREW LETTER RESH 0xF9 U+05E9 # HEBREW LETTER SHIN 0xFA U+05EA # HEBREW LETTER TAV +0xFD U+200E # LEFT-TO-RIGHT MARK +0xFE U+200F # RIGHT-TO-LEFT MARK #Hebrew points - map to empty string diff --git a/src/chrtrans/iso09_uni.tbl b/src/chrtrans/iso09_uni.tbl index 5dc9660c..87afe48b 100644 --- a/src/chrtrans/iso09_uni.tbl +++ b/src/chrtrans/iso09_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Miso-8859-9 @@ -8,15 +10,14 @@ OTurkish (ISO-8859-9) C920 # -# Name: ISO 8859-9 (1989) to Unicode -# Unicode version: 1.1 -# Table version: 0.1 +# Name: ISO/IEC 8859-9:1999 to Unicode +# Unicode version: 3.0 +# Table version: 1.0 # Table format: Format A -# Date: 16 January 1995 -# Authors: Tim Greenwood <greenwood@r2me2.enet.dec.com> -# John H. Jenkins <John_Jenkins@taligent.com> +# Date: 1999 July 27 +# Authors: Ken Whistler <kenw@sybase.com> # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # # This file is provided as-is by Unicode, Inc. (The Unicode Consortium). # No claims are made as to fitness for any particular purpose. No @@ -26,25 +27,36 @@ C920 # remedy for any claim will be exchange of defective media within 90 # days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-9 (1989) characters map into Unicode. +# ISO/IEC 8859-9:1999 characters map into Unicode. # # Format: Three tab-separated columns -# Column #1 is the ISO 8859-9 code (in hex as 0xXX) +# Column #1 is the ISO/IEC 8859-9 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 8859-9 order +# The entries are in ISO/IEC 8859-9 order. +# +# ISO/IEC 8859-9 is also equivalent to ISO-IR-148. +# +# Version history +# 1.0 version updates 0.1 version by adding mappings for all +# control characters. +# +# Updated versions of this file may be found in: +# <ftp://ftp.unicode.org/Public/MAPPINGS/> # -# Any comments or problems, contact <John_Jenkins@taligent.com> +# Any comments or problems, contact <errata@unicode.org> +# Please note that <errata@unicode.org> is an archival address; +# notices will be checked, but do not expect an immediate response. # # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw diff --git a/src/chrtrans/mac_uni.tbl b/src/chrtrans/mac_uni.tbl index c2457e7b..25647017 100644 --- a/src/chrtrans/mac_uni.tbl +++ b/src/chrtrans/mac_uni.tbl @@ -1,3 +1,5 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mmacintosh @@ -5,310 +7,250 @@ Mmacintosh OMacintosh (8 bit) # -# 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> -# -# Copyright (c) 1995 Apple Computer, Inc. All Rights reserved. -# -# 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 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 -# 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). -# -# 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, '#') +# Name: cp10000_MacRoman to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Authors: Lori Brownell <loribr@microsoft.com> +# K.D. Chang <a-kchang@microsoft.com> +# General notes: none # -# The entries are in MacOS Roman code order. +# Format: Three tab-separated columns +# Column #1 is the cp10000_MacRoman code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') # -# 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. +# The entries are in cp10000_MacRoman order # -# Notes on MacOS Roman: -# --------------------- -# -# This character set is used for at least the following MacOS -# 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. -# -# 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. -# -# In all MacOS 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 -# text, and the associated code points are not generally -# interpreted as associated with these glyphs; they are usually -# interpreted (if at all) as the control codes DC1-DC4. -# -################## # Lines with more than one Unicode (U+XXXX) value contain additional # replacement mappings added for lynx. - kw - -#0x20 U+0020 # SPACE -#0x21 U+0021 # EXCLAMATION MARK -#0x22 U+0022 # QUOTATION MARK -#0x23 U+0023 # NUMBER SIGN -#0x24 U+0024 # DOLLAR SIGN -#0x25 U+0025 # PERCENT SIGN -#0x26 U+0026 # AMPERSAND -#0x27 U+0027 # APOSTROPHE -#0x28 U+0028 # LEFT PARENTHESIS -#0x29 U+0029 # RIGHT PARENTHESIS -#0x2A U+002A # ASTERISK -#0x2B U+002B # PLUS SIGN -#0x2C U+002C # COMMA -#0x2D U+002D # HYPHEN-MINUS -#0x2E U+002E # FULL STOP -#0x2F U+002F # SOLIDUS -#0x30 U+0030 # DIGIT ZERO -#0x31 U+0031 # DIGIT ONE -#0x32 U+0032 # DIGIT TWO -#0x33 U+0033 # DIGIT THREE -#0x34 U+0034 # DIGIT FOUR -#0x35 U+0035 # DIGIT FIVE -#0x36 U+0036 # DIGIT SIX -#0x37 U+0037 # DIGIT SEVEN -#0x38 U+0038 # DIGIT EIGHT -#0x39 U+0039 # DIGIT NINE -#0x3A U+003A # COLON -#0x3B U+003B # SEMICOLON -#0x3C U+003C # LESS-THAN SIGN -#0x3D U+003D # EQUALS SIGN -#0x3E U+003E # GREATER-THAN SIGN -#0x3F U+003F # QUESTION MARK -#0x40 U+0040 # COMMERCIAL AT -#0x41 U+0041 # LATIN CAPITAL LETTER A -#0x42 U+0042 # LATIN CAPITAL LETTER B -#0x43 U+0043 # LATIN CAPITAL LETTER C -#0x44 U+0044 # LATIN CAPITAL LETTER D -#0x45 U+0045 # LATIN CAPITAL LETTER E -#0x46 U+0046 # LATIN CAPITAL LETTER F -#0x47 U+0047 # LATIN CAPITAL LETTER G -#0x48 U+0048 # LATIN CAPITAL LETTER H -#0x49 U+0049 # LATIN CAPITAL LETTER I -#0x4A U+004A # LATIN CAPITAL LETTER J -#0x4B U+004B # LATIN CAPITAL LETTER K -#0x4C U+004C # LATIN CAPITAL LETTER L -#0x4D U+004D # LATIN CAPITAL LETTER M -#0x4E U+004E # LATIN CAPITAL LETTER N -#0x4F U+004F # LATIN CAPITAL LETTER O -#0x50 U+0050 # LATIN CAPITAL LETTER P -#0x51 U+0051 # LATIN CAPITAL LETTER Q -#0x52 U+0052 # LATIN CAPITAL LETTER R -#0x53 U+0053 # LATIN CAPITAL LETTER S -#0x54 U+0054 # LATIN CAPITAL LETTER T -#0x55 U+0055 # LATIN CAPITAL LETTER U -#0x56 U+0056 # LATIN CAPITAL LETTER V -#0x57 U+0057 # LATIN CAPITAL LETTER W -#0x58 U+0058 # LATIN CAPITAL LETTER X -#0x59 U+0059 # LATIN CAPITAL LETTER Y -#0x5A U+005A # LATIN CAPITAL LETTER Z -#0x5B U+005B # LEFT SQUARE BRACKET -#0x5C U+005C # REVERSE SOLIDUS -#0x5D U+005D # RIGHT SQUARE BRACKET -#0x5E U+005E # CIRCUMFLEX ACCENT -#0x5F U+005F # LOW LINE -#0x60 U+0060 # GRAVE ACCENT -#0x61 U+0061 # LATIN SMALL LETTER A -#0x62 U+0062 # LATIN SMALL LETTER B -#0x63 U+0063 # LATIN SMALL LETTER C -#0x64 U+0064 # LATIN SMALL LETTER D -#0x65 U+0065 # LATIN SMALL LETTER E -#0x66 U+0066 # LATIN SMALL LETTER F -#0x67 U+0067 # LATIN SMALL LETTER G -#0x68 U+0068 # LATIN SMALL LETTER H -#0x69 U+0069 # LATIN SMALL LETTER I -#0x6A U+006A # LATIN SMALL LETTER J -#0x6B U+006B # LATIN SMALL LETTER K -#0x6C U+006C # LATIN SMALL LETTER L -#0x6D U+006D # LATIN SMALL LETTER M -#0x6E U+006E # LATIN SMALL LETTER N -#0x6F U+006F # LATIN SMALL LETTER O -#0x70 U+0070 # LATIN SMALL LETTER P -#0x71 U+0071 # LATIN SMALL LETTER Q -#0x72 U+0072 # LATIN SMALL LETTER R -#0x73 U+0073 # LATIN SMALL LETTER S -#0x74 U+0074 # LATIN SMALL LETTER T -#0x75 U+0075 # LATIN SMALL LETTER U -#0x76 U+0076 # LATIN SMALL LETTER V -#0x77 U+0077 # LATIN SMALL LETTER W -#0x78 U+0078 # LATIN SMALL LETTER X -#0x79 U+0079 # LATIN SMALL LETTER Y -#0x7A U+007A # LATIN SMALL LETTER Z -#0x7B U+007B # LEFT CURLY BRACKET -#0x7C U+007C # VERTICAL LINE -#0x7D U+007D # RIGHT CURLY BRACKET -#0x7E U+007E # TILDE # 0x20-0x7f idem # -0x80 U+00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS -0x81 U+00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE -0x82 U+00C7 # LATIN CAPITAL LETTER C WITH CEDILLA -0x83 U+00C9 # LATIN CAPITAL LETTER E WITH ACUTE -0x84 U+00D1 # LATIN CAPITAL LETTER N WITH TILDE -0x85 U+00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS -0x86 U+00DC # LATIN CAPITAL LETTER U WITH DIAERESIS -0x87 U+00E1 # LATIN SMALL LETTER A WITH ACUTE -0x88 U+00E0 # LATIN SMALL LETTER A WITH GRAVE -0x89 U+00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX -0x8A U+00E4 # LATIN SMALL LETTER A WITH DIAERESIS -0x8B U+00E3 # LATIN SMALL LETTER A WITH TILDE -0x8C U+00E5 # LATIN SMALL LETTER A WITH RING ABOVE -0x8D U+00E7 # LATIN SMALL LETTER C WITH CEDILLA -0x8E U+00E9 # LATIN SMALL LETTER E WITH ACUTE -0x8F U+00E8 # LATIN SMALL LETTER E WITH GRAVE -0x90 U+00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX -0x91 U+00EB # LATIN SMALL LETTER E WITH DIAERESIS -0x92 U+00ED # LATIN SMALL LETTER I WITH ACUTE -0x93 U+00EC # LATIN SMALL LETTER I WITH GRAVE -0x94 U+00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX -0x95 U+00EF # LATIN SMALL LETTER I WITH DIAERESIS -0x96 U+00F1 # LATIN SMALL LETTER N WITH TILDE -0x97 U+00F3 # LATIN SMALL LETTER O WITH ACUTE -0x98 U+00F2 # LATIN SMALL LETTER O WITH GRAVE -0x99 U+00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX -0x9A U+00F6 # LATIN SMALL LETTER O WITH DIAERESIS -0x9B U+00F5 # LATIN SMALL LETTER O WITH TILDE -0x9C U+00FA # LATIN SMALL LETTER U WITH ACUTE -0x9D U+00F9 # LATIN SMALL LETTER U WITH GRAVE -0x9E U+00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX -0x9F U+00FC # LATIN SMALL LETTER U WITH DIAERESIS -0xA0 U+2020 # DAGGER -0xA1 U+00B0 # DEGREE SIGN -0xA2 U+00A2 # CENT SIGN -0xA3 U+00A3 # POUND SIGN -0xA4 U+00A7 # SECTION SIGN -0xA5 U+2022 # BULLET -0xA6 U+00B6 # PILCROW SIGN -0xA7 U+00DF # LATIN SMALL LETTER SHARP S -0xA8 U+00AE # REGISTERED SIGN -0xA9 U+00A9 # COPYRIGHT SIGN -0xAA U+2122 # TRADE MARK SIGN -0xAB U+00B4 # ACUTE ACCENT -0xAC U+00A8 # DIAERESIS -0xAD U+2260 # NOT EQUAL TO -0xAE U+00C6 # LATIN CAPITAL LIGATURE AE -0xAF U+00D8 # LATIN CAPITAL LETTER O WITH STROKE -0xB0 U+221E # INFINITY -0xB1 U+00B1 # PLUS-MINUS SIGN -0xB2 U+2264 # LESS-THAN OR EQUAL TO -0xB3 U+2265 # GREATER-THAN OR EQUAL TO -0xB4 U+00A5 # YEN SIGN -0xB5 U+00B5 # MICRO SIGN -0xB6 U+2202 # PARTIAL DIFFERENTIAL -0xB7 U+2211 # N-ARY SUMMATION -0xB8 U+220F # N-ARY PRODUCT -0xB9 U+03C0 # GREEK SMALL LETTER PI -0xBA U+222B # INTEGRAL -0xBB U+00AA # FEMININE ORDINAL INDICATOR -0xBC U+00BA # MASCULINE ORDINAL INDICATOR -0xBD U+2126 # OHM SIGN -0xBE U+00E6 # LATIN SMALL LIGATURE AE -0xBF U+00F8 # LATIN SMALL LETTER O WITH STROKE -0xC0 U+00BF # INVERTED QUESTION MARK -0xC1 U+00A1 # INVERTED EXCLAMATION MARK -0xC2 U+00AC # NOT SIGN -0xC3 U+221A # SQUARE ROOT -0xC4 U+0192 # LATIN SMALL LETTER F WITH HOOK -0xC5 U+2248 # ALMOST EQUAL TO -0xC6 U+2206 # INCREMENT -0xC7 U+00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xC8 U+00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -0xC9 U+2026 # HORIZONTAL ELLIPSIS -0xCA U+00A0 # NO-BREAK SPACE -0xCB U+00C0 # LATIN CAPITAL LETTER A WITH GRAVE -0xCC U+00C3 # LATIN CAPITAL LETTER A WITH TILDE -0xCD U+00D5 # LATIN CAPITAL LETTER O WITH TILDE -0xCE U+0152 # LATIN CAPITAL LIGATURE OE -0xCF U+0153 # LATIN SMALL LIGATURE OE -0xD0 U+2013 # EN DASH -0xD1 U+2014 # EM DASH -0xD2 U+201C # LEFT DOUBLE QUOTATION MARK -0xD3 U+201D # RIGHT DOUBLE QUOTATION MARK -0xD4 U+2018 # LEFT SINGLE QUOTATION MARK -0xD5 U+2019 # RIGHT SINGLE QUOTATION MARK -0xD6 U+00F7 # DIVISION SIGN -0xD7 U+25CA # LOZENGE -0xD8 U+00FF # LATIN SMALL LETTER Y WITH DIAERESIS -0xD9 U+0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS -0xDA U+2044 # FRACTION SLASH -0xDB U+00A4 # CURRENCY SIGN -0xDC U+2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK -0xDD U+203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -0xDE U+FB01 # LATIN SMALL LIGATURE FI -0xDF U+FB02 # LATIN SMALL LIGATURE FL -0xE0 U+2021 # DOUBLE DAGGER +#0x20 U+0020 # SPACE +#0x21 U+0021 # EXCLAMATION MARK +#0x22 U+0022 # QUOTATION MARK +#0x23 U+0023 # NUMBER SIGN +#0x24 U+0024 # DOLLAR SIGN +#0x25 U+0025 # PERCENT SIGN +#0x26 U+0026 # AMPERSAND +#0x27 U+0027 # APOSTROPHE +#0x28 U+0028 # LEFT PARENTHESIS +#0x29 U+0029 # RIGHT PARENTHESIS +#0x2A U+002A # ASTERISK +#0x2B U+002B # PLUS SIGN +#0x2C U+002C # COMMA +#0x2D U+002D # HYPHEN-MINUS +#0x2E U+002E # FULL STOP +#0x2F U+002F # SOLIDUS +#0x30 U+0030 # DIGIT ZERO +#0x31 U+0031 # DIGIT ONE +#0x32 U+0032 # DIGIT TWO +#0x33 U+0033 # DIGIT THREE +#0x34 U+0034 # DIGIT FOUR +#0x35 U+0035 # DIGIT FIVE +#0x36 U+0036 # DIGIT SIX +#0x37 U+0037 # DIGIT SEVEN +#0x38 U+0038 # DIGIT EIGHT +#0x39 U+0039 # DIGIT NINE +#0x3A U+003A # COLON +#0x3B U+003B # SEMICOLON +#0x3C U+003C # LESS-THAN SIGN +#0x3D U+003D # EQUALS SIGN +#0x3E U+003E # GREATER-THAN SIGN +#0x3F U+003F # QUESTION MARK +#0x40 U+0040 # COMMERCIAL AT +#0x41 U+0041 # LATIN CAPITAL LETTER A +#0x42 U+0042 # LATIN CAPITAL LETTER B +#0x43 U+0043 # LATIN CAPITAL LETTER C +#0x44 U+0044 # LATIN CAPITAL LETTER D +#0x45 U+0045 # LATIN CAPITAL LETTER E +#0x46 U+0046 # LATIN CAPITAL LETTER F +#0x47 U+0047 # LATIN CAPITAL LETTER G +#0x48 U+0048 # LATIN CAPITAL LETTER H +#0x49 U+0049 # LATIN CAPITAL LETTER I +#0x4A U+004A # LATIN CAPITAL LETTER J +#0x4B U+004B # LATIN CAPITAL LETTER K +#0x4C U+004C # LATIN CAPITAL LETTER L +#0x4D U+004D # LATIN CAPITAL LETTER M +#0x4E U+004E # LATIN CAPITAL LETTER N +#0x4F U+004F # LATIN CAPITAL LETTER O +#0x50 U+0050 # LATIN CAPITAL LETTER P +#0x51 U+0051 # LATIN CAPITAL LETTER Q +#0x52 U+0052 # LATIN CAPITAL LETTER R +#0x53 U+0053 # LATIN CAPITAL LETTER S +#0x54 U+0054 # LATIN CAPITAL LETTER T +#0x55 U+0055 # LATIN CAPITAL LETTER U +#0x56 U+0056 # LATIN CAPITAL LETTER V +#0x57 U+0057 # LATIN CAPITAL LETTER W +#0x58 U+0058 # LATIN CAPITAL LETTER X +#0x59 U+0059 # LATIN CAPITAL LETTER Y +#0x5A U+005A # LATIN CAPITAL LETTER Z +#0x5B U+005B # LEFT SQUARE BRACKET +#0x5C U+005C # REVERSE SOLIDUS +#0x5D U+005D # RIGHT SQUARE BRACKET +#0x5E U+005E # CIRCUMFLEX ACCENT +#0x5F U+005F # LOW LINE +#0x60 U+0060 # GRAVE ACCENT +#0x61 U+0061 # LATIN SMALL LETTER A +#0x62 U+0062 # LATIN SMALL LETTER B +#0x63 U+0063 # LATIN SMALL LETTER C +#0x64 U+0064 # LATIN SMALL LETTER D +#0x65 U+0065 # LATIN SMALL LETTER E +#0x66 U+0066 # LATIN SMALL LETTER F +#0x67 U+0067 # LATIN SMALL LETTER G +#0x68 U+0068 # LATIN SMALL LETTER H +#0x69 U+0069 # LATIN SMALL LETTER I +#0x6A U+006A # LATIN SMALL LETTER J +#0x6B U+006B # LATIN SMALL LETTER K +#0x6C U+006C # LATIN SMALL LETTER L +#0x6D U+006D # LATIN SMALL LETTER M +#0x6E U+006E # LATIN SMALL LETTER N +#0x6F U+006F # LATIN SMALL LETTER O +#0x70 U+0070 # LATIN SMALL LETTER P +#0x71 U+0071 # LATIN SMALL LETTER Q +#0x72 U+0072 # LATIN SMALL LETTER R +#0x73 U+0073 # LATIN SMALL LETTER S +#0x74 U+0074 # LATIN SMALL LETTER T +#0x75 U+0075 # LATIN SMALL LETTER U +#0x76 U+0076 # LATIN SMALL LETTER V +#0x77 U+0077 # LATIN SMALL LETTER W +#0x78 U+0078 # LATIN SMALL LETTER X +#0x79 U+0079 # LATIN SMALL LETTER Y +#0x7A U+007A # LATIN SMALL LETTER Z +#0x7B U+007B # LEFT CURLY BRACKET +#0x7C U+007C # VERTICAL LINE +#0x7D U+007D # RIGHT CURLY BRACKET +#0x7E U+007E # TILDE +0x80 U+00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS +0x81 U+00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE +0x82 U+00C7 # LATIN CAPITAL LETTER C WITH CEDILLA +0x83 U+00C9 # LATIN CAPITAL LETTER E WITH ACUTE +0x84 U+00D1 # LATIN CAPITAL LETTER N WITH TILDE +0x85 U+00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS +0x86 U+00DC # LATIN CAPITAL LETTER U WITH DIAERESIS +0x87 U+00E1 # LATIN SMALL LETTER A WITH ACUTE +0x88 U+00E0 # LATIN SMALL LETTER A WITH GRAVE +0x89 U+00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX +0x8A U+00E4 # LATIN SMALL LETTER A WITH DIAERESIS +0x8B U+00E3 # LATIN SMALL LETTER A WITH TILDE +0x8C U+00E5 # LATIN SMALL LETTER A WITH RING ABOVE +0x8D U+00E7 # LATIN SMALL LETTER C WITH CEDILLA +0x8E U+00E9 # LATIN SMALL LETTER E WITH ACUTE +0x8F U+00E8 # LATIN SMALL LETTER E WITH GRAVE +0x90 U+00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX +0x91 U+00EB # LATIN SMALL LETTER E WITH DIAERESIS +0x92 U+00ED # LATIN SMALL LETTER I WITH ACUTE +0x93 U+00EC # LATIN SMALL LETTER I WITH GRAVE +0x94 U+00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX +0x95 U+00EF # LATIN SMALL LETTER I WITH DIAERESIS +0x96 U+00F1 # LATIN SMALL LETTER N WITH TILDE +0x97 U+00F3 # LATIN SMALL LETTER O WITH ACUTE +0x98 U+00F2 # LATIN SMALL LETTER O WITH GRAVE +0x99 U+00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX +0x9A U+00F6 # LATIN SMALL LETTER O WITH DIAERESIS +0x9B U+00F5 # LATIN SMALL LETTER O WITH TILDE +0x9C U+00FA # LATIN SMALL LETTER U WITH ACUTE +0x9D U+00F9 # LATIN SMALL LETTER U WITH GRAVE +0x9E U+00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX +0x9F U+00FC # LATIN SMALL LETTER U WITH DIAERESIS +0xA0 U+2020 # DAGGER +0xA1 U+00B0 # DEGREE SIGN +0xA2 U+00A2 # CENT SIGN +0xA3 U+00A3 # POUND SIGN +0xA4 U+00A7 # SECTION SIGN +0xA5 U+2022 # BULLET +0xA6 U+00B6 # PILCROW SIGN +0xA7 U+00DF # LATIN SMALL LETTER SHARP S +0xA8 U+00AE # REGISTERED SIGN +0xA9 U+00A9 # COPYRIGHT SIGN +0xAA U+2122 # TRADE MARK SIGN +0xAB U+00B4 # ACUTE ACCENT +0xAC U+00A8 # DIAERESIS +0xAD U+2260 # NOT EQUAL TO +0xAE U+00C6 # LATIN CAPITAL LIGATURE AE +0xAF U+00D8 # LATIN CAPITAL LETTER O WITH STROKE +0xB0 U+221E # INFINITY +0xB1 U+00B1 # PLUS-MINUS SIGN +0xB2 U+2264 # LESS-THAN OR EQUAL TO +0xB3 U+2265 # GREATER-THAN OR EQUAL TO +0xB4 U+00A5 # YEN SIGN +0xB5 U+00B5 # MICRO SIGN +0xB6 U+2202 # PARTIAL DIFFERENTIAL +0xB7 U+2211 # N-ARY SUMMATION +0xB8 U+220F # N-ARY PRODUCT +0xB9 U+03C0 # GREEK SMALL LETTER PI +0xBA U+222B # INTEGRAL +0xBB U+00AA # FEMININE ORDINAL INDICATOR +0xBC U+00BA # MASCULINE ORDINAL INDICATOR +0xBD U+2126 # OHM SIGN +0xBE U+00E6 # LATIN SMALL LIGATURE AE +0xBF U+00F8 # LATIN SMALL LETTER O WITH STROKE +0xC0 U+00BF # INVERTED QUESTION MARK +0xC1 U+00A1 # INVERTED EXCLAMATION MARK +0xC2 U+00AC # NOT SIGN +0xC3 U+221A # SQUARE ROOT +0xC4 U+0192 # LATIN SMALL LETTER F WITH HOOK +0xC5 U+2248 # ALMOST EQUAL TO +0xC6 U+2206 # INCREMENT +0xC7 U+00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC8 U+00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xC9 U+2026 # HORIZONTAL ELLIPSIS +0xCA U+00A0 # NO-BREAK SPACE +0xCB U+00C0 # LATIN CAPITAL LETTER A WITH GRAVE +0xCC U+00C3 # LATIN CAPITAL LETTER A WITH TILDE +0xCD U+00D5 # LATIN CAPITAL LETTER O WITH TILDE +0xCE U+0152 # LATIN CAPITAL LIGATURE OE +0xCF U+0153 # LATIN SMALL LIGATURE OE +0xD0 U+2013 # EN DASH +0xD1 U+2014 # EM DASH +0xD2 U+201C # LEFT DOUBLE QUOTATION MARK +0xD3 U+201D # RIGHT DOUBLE QUOTATION MARK +0xD4 U+2018 # LEFT SINGLE QUOTATION MARK +0xD5 U+2019 # RIGHT SINGLE QUOTATION MARK +0xD6 U+00F7 # DIVISION SIGN +0xD7 U+25CA # LOZENGE +0xD8 U+00FF # LATIN SMALL LETTER Y WITH DIAERESIS +0xD9 U+0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS +0xDA U+2044 # FRACTION SLASH +0xDB U+00A4 # CURRENCY SIGN +0xDC U+2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0xDD U+203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +0xDE U+FB01 # LATIN SMALL LIGATURE FI +0xDF U+FB02 # LATIN SMALL LIGATURE FL +0xE0 U+2021 # DOUBLE DAGGER 0xE1 U+00B7 U+0307 U+0387 U+2027 # MIDDLE DOT -0xE2 U+201A # SINGLE LOW-9 QUOTATION MARK -0xE3 U+201E # DOUBLE LOW-9 QUOTATION MARK -0xE4 U+2030 # PER MILLE SIGN -0xE5 U+00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX -0xE6 U+00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX -0xE7 U+00C1 # LATIN CAPITAL LETTER A WITH ACUTE -0xE8 U+00CB # LATIN CAPITAL LETTER E WITH DIAERESIS -0xE9 U+00C8 # LATIN CAPITAL LETTER E WITH GRAVE -0xEA U+00CD # LATIN CAPITAL LETTER I WITH ACUTE -0xEB U+00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX -0xEC U+00CF # LATIN CAPITAL LETTER I WITH DIAERESIS -0xED U+00CC # LATIN CAPITAL LETTER I WITH GRAVE -0xEE U+00D3 # LATIN CAPITAL LETTER O WITH ACUTE -0xEF U+00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX -0xF0 U+F8FF # Apple logo -0xF1 U+00D2 # LATIN CAPITAL LETTER O WITH GRAVE -0xF2 U+00DA # LATIN CAPITAL LETTER U WITH ACUTE -0xF3 U+00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX -0xF4 U+00D9 # LATIN CAPITAL LETTER U WITH GRAVE -0xF5 U+0131 # LATIN SMALL LETTER DOTLESS I -0xF6 U+02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT -0xF7 U+02DC # SMALL TILDE -0xF8 U+00AF # MACRON -0xF9 U+02D8 # BREVE -0xFA U+02D9 # DOT ABOVE -0xFB U+02DA # RING ABOVE -0xFC U+00B8 # CEDILLA -0xFD U+02DD # DOUBLE ACUTE ACCENT -0xFE U+02DB # OGONEK -0xFF U+02C7 # CARON +0xE2 U+201A # SINGLE LOW-9 QUOTATION MARK +0xE3 U+201E # DOUBLE LOW-9 QUOTATION MARK +0xE4 U+2030 # PER MILLE SIGN +0xE5 U+00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xE6 U+00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xE7 U+00C1 # LATIN CAPITAL LETTER A WITH ACUTE +0xE8 U+00CB # LATIN CAPITAL LETTER E WITH DIAERESIS +0xE9 U+00C8 # LATIN CAPITAL LETTER E WITH GRAVE +0xEA U+00CD # LATIN CAPITAL LETTER I WITH ACUTE +0xEB U+00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xEC U+00CF # LATIN CAPITAL LETTER I WITH DIAERESIS +0xED U+00CC # LATIN CAPITAL LETTER I WITH GRAVE +0xEE U+00D3 # LATIN CAPITAL LETTER O WITH ACUTE +0xEF U+00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xF0 # UNDEFINED +0xF1 U+00D2 # LATIN CAPITAL LETTER O WITH GRAVE +0xF2 U+00DA # LATIN CAPITAL LETTER U WITH ACUTE +0xF3 U+00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xF4 U+00D9 # LATIN CAPITAL LETTER U WITH GRAVE +0xF5 U+0131 # LATIN SMALL LETTER DOTLESS I +0xF6 U+02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT +0xF7 U+02DC # SMALL TILDE +0xF8 U+00AF # MACRON +0xF9 U+02D8 # BREVE +0xFA U+02D9 # DOT ABOVE +0xFB U+02DA # RING ABOVE +0xFC U+00B8 # CEDILLA +0xFD U+02DD # DOUBLE ACUTE ACCENT +0xFE U+02DB # OGONEK +0xFF U+02C7 # CARON # # broken vertical bar (¦) - brvbar, brkbar U+00A6:| diff --git a/src/chrtrans/makefile.bcb b/src/chrtrans/makefile.bcb index bc70b798..134a3958 100644 --- a/src/chrtrans/makefile.bcb +++ b/src/chrtrans/makefile.bcb @@ -114,6 +114,7 @@ BccW32.cfg : clean : -del *_uni.h + -del *_suni.h -del *.exe -del *.map -del *.obj diff --git a/src/chrtrans/makeuctb.c b/src/chrtrans/makeuctb.c index 9d3d9280..e4752b0c 100644 --- a/src/chrtrans/makeuctb.c +++ b/src/chrtrans/makeuctb.c @@ -18,8 +18,10 @@ #ifndef HAVE_CONFIG_H /* override HTUtils.h fallbacks for cross-compiling */ -#define HAVE_LSTAT -#define NO_FILIO_H +#undef HAVE_LSTAT +#undef NO_FILIO_H +#define HAVE_LSTAT 1 +#define NO_FILIO_H 1 #endif #define DONT_USE_GETTEXT diff --git a/src/chrtrans/next_uni.tbl b/src/chrtrans/next_uni.tbl index 2aa665f8..a166ba5c 100644 --- a/src/chrtrans/next_uni.tbl +++ b/src/chrtrans/next_uni.tbl @@ -1,47 +1,55 @@ +# This file has been modified for lynx (see README.tables) + #The MIME name of this charset. Mnext #Name as a Display Charset (used on Options screen) ONeXT character set +# # Name: NextStep Encoding to Unicode # Unicode version: 1.1 # Table version: 0.1 # Table format: Format A -# Date: 14 February 1995 -# Authors: Rick McGowan (rick@unicode.org) +# Date: 1999 September 23 +# Authors: Rick McGowan # -# Copyright (c) 1991-1995 Unicode, Inc. All Rights reserved. +# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. # -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# No claims are made as to fitness for any particular purpose. No -# warranties of any kind are expressed or implied. The recipient -# agrees to determine applicability of information provided. If this -# file has been provided on magnetic media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). +# No claims are made as to fitness for any particular purpose. No +# warranties of any kind are expressed or implied. The recipient +# agrees to determine applicability of information provided. If this +# file has been provided on optical media by Unicode, Inc., the sole +# remedy for any claim will be exchange of defective media within 90 +# days of receipt. # -# Recipient is granted the right to make copies in any form for -# internal distribution and to freely use the information supplied -# in the creation of products supporting Unicode. Unicode, Inc. -# specifically excludes the right to re-distribute this file directly -# to third parties or other organizations whether for profit or not. +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. # -# General notes: +# General notes: # -# This table contains the data the Unicode Consortium has on how -# NextStep Encoding characters map into Unicode. Since the first +# This table contains the data the Unicode Consortium has on how +# NextStep Encoding characters map into Unicode. Since the first # 128 characters (0x0 - 0x7f) are identical to ASCII and Unicode, # this table only maps the NextStep range from 0x80 - 0xFF. # -# Format: Three tab-separated columns -# Column #1 is the NextStep code (in hex as 0xXX) -# Column #2 is the Unicode (in hex as 0xXXXX) -# Column #3 NextStep name, Unicode name (follows a comment sign) +# This file is provided for historical reference only and pertains +# to NextStep and OpenStep products shipped prior to the aquisition +# of NeXT by Apple Computer, Inc. See http://www.apple.com for +# further information. +# +# Format: Three tab-separated columns +# Column #1 is the NextStep code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 NextStep name, Unicode name (follows a comment sign, '#') # # The entries are in NextStep order # -# Any comments or problems, contact rick@unicode.org +# Any comments or problems, contact info@unicode.org # # 0x20-0x7f idem @@ -90,8 +98,8 @@ ONeXT character set 0xa9 U+2019 # RIGHT SINGLE QUOTATION MARK 0xaa U+201c # LEFT DOUBLE QUOTATION MARK 0xab U+00ab # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -0xac U+2039 # LATIN SMALL LETTER -0xad U+203a # LATIN SMALL LETTER +0xac U+2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK +0xad U+203a # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK 0xae U+fb01 # LATIN SMALL LIGATURE FI 0xaf U+fb02 # LATIN SMALL LIGATURE FL 0xb0 U+00ae # REGISTERED SIGN |