Refbase update_2021-01-28_15_58
This commit is contained in:
415
includes/transtab_latin1_ascii.inc.php
Normal file
415
includes/transtab_latin1_ascii.inc.php
Normal file
@@ -0,0 +1,415 @@
|
||||
<?php
|
||||
// Project: Web Reference Database (refbase) <http://www.refbase.net>
|
||||
// Copyright: Matthias Steffens <mailto:refbase@extracts.de> and the file's
|
||||
// original author(s).
|
||||
//
|
||||
// This code is distributed in the hope that it will be useful,
|
||||
// but WITHOUT ANY WARRANTY. Please see the GNU General Public
|
||||
// License for more details.
|
||||
//
|
||||
// File: ./includes/transtab_latin1_ascii.inc.php
|
||||
// Repository: $HeadURL: file:///svn/p/refbase/code/branches/bleeding-edge/includes/transtab_latin1_ascii.inc.php $
|
||||
// Author(s): Matthias Steffens <mailto:refbase@extracts.de>
|
||||
//
|
||||
// Created: 24-Aug-05, 20:11
|
||||
// Modified: $Date: 2007-02-17 01:10:14 +0000 (Sat, 17 Feb 2007) $
|
||||
// $Author: msteffens $
|
||||
// $Revision: 894 $
|
||||
|
||||
// This is a transliteration table for a best-effort conversion from ISO-8859-1 to ASCII. It contains a list of substitution strings for 'ISO-8859-1 West European' characters,
|
||||
// comparable to the fallback notations that people use commonly in email and on typewriters to represent unavailable characters. Adopted from 'transtab' by Markus Kuhn
|
||||
// (transtab.utf v1.8 2000-10-12 11:01:28+01 mgk25 Exp); see <http://www.cl.cam.ac.uk/~mgk25/unicode.html> for more info about Unicode and transtab.
|
||||
|
||||
$transtab_latin1_ascii = array(
|
||||
|
||||
// APOSTROPHE
|
||||
"'" => "'",
|
||||
// <U0027> <U2019>
|
||||
|
||||
// GRAVE ACCENT
|
||||
"`" => "'",
|
||||
// <U0060> <U201B>;<U2018>
|
||||
|
||||
// NO-BREAK SPACE
|
||||
"<EFBFBD>" => " ",
|
||||
// <U00A0> <U0020>
|
||||
|
||||
// INVERTED EXCLAMATION MARK
|
||||
"<EFBFBD>" => "!",
|
||||
// <U00A1> <U0021>
|
||||
|
||||
// CENT SIGN
|
||||
"<EFBFBD>" => "c",
|
||||
// <U00A2> <U0063>
|
||||
|
||||
// POUND SIGN
|
||||
"<EFBFBD>" => "GBP",
|
||||
// <U00A3> "<U0047><U0042><U0050>"
|
||||
|
||||
// YEN SIGN
|
||||
"<EFBFBD>" => "Y",
|
||||
// <U00A5> <U0059>
|
||||
|
||||
// BROKEN BAR
|
||||
"<EFBFBD>" => "|",
|
||||
// <U00A6> <U007C>
|
||||
|
||||
// SECTION SIGN
|
||||
"<EFBFBD>" => "S",
|
||||
// <U00A7> <U0053>
|
||||
|
||||
// DIAERESIS
|
||||
"<EFBFBD>" => "\"",
|
||||
// <U00A8> <U0022>
|
||||
|
||||
// COPYRIGHT SIGN
|
||||
"<EFBFBD>" => "(c)", // "c"
|
||||
// <U00A9> "<U0028><U0063><U0029>";<U0063>
|
||||
|
||||
// FEMININE ORDINAL INDICATOR
|
||||
"<EFBFBD>" => "a",
|
||||
// <U00AA> <U0061>
|
||||
|
||||
// LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
"<EFBFBD>" => "<<",
|
||||
// <U00AB> "<U003C><U003C>"
|
||||
|
||||
// NOT SIGN
|
||||
"<EFBFBD>" => "-",
|
||||
// <U00AC> <U002D>
|
||||
|
||||
// SOFT HYPHEN
|
||||
"<EFBFBD>" => "-",
|
||||
// <U00AD> <U002D>
|
||||
|
||||
// REGISTERED SIGN
|
||||
"<EFBFBD>" => "(R)",
|
||||
// <U00AE> "<U0028><U0052><U0029>"
|
||||
|
||||
// MACRON
|
||||
"<EFBFBD>" => "-",
|
||||
// <U00AF> <U002D>
|
||||
|
||||
// DEGREE SIGN
|
||||
"<EFBFBD>" => " ",
|
||||
// <U00B0> <U0020>
|
||||
|
||||
// PLUS-MINUS SIGN
|
||||
"<EFBFBD>" => "+/-",
|
||||
// <U00B1> "<U002B><U002F><U002D>"
|
||||
|
||||
// SUPERSCRIPT TWO
|
||||
"<EFBFBD>" => "^2", // "2"
|
||||
// <U00B2> "<U005E><U0032>";<U0032>
|
||||
|
||||
// SUPERSCRIPT THREE
|
||||
"<EFBFBD>" => "^3", // "3"
|
||||
// <U00B3> "<U005E><U0033>";<U0033>
|
||||
|
||||
// ACUTE ACCENT
|
||||
"<EFBFBD>" => "'",
|
||||
// <U00B4> <U0027>
|
||||
|
||||
// MICRO SIGN
|
||||
"<EFBFBD>" => "u",
|
||||
// <U00B5> <U03BC>;<U0075>
|
||||
|
||||
// PILCROW SIGN
|
||||
"<EFBFBD>" => "P",
|
||||
// <U00B6> <U0050>
|
||||
|
||||
// MIDDLE DOT
|
||||
"<EFBFBD>" => ".",
|
||||
// <U00B7> <U002E>
|
||||
|
||||
// CEDILLA
|
||||
"<EFBFBD>" => ",",
|
||||
// <U00B8> <U002C>
|
||||
|
||||
// SUPERSCRIPT ONE
|
||||
"<EFBFBD>" => "^1", // "1"
|
||||
// <U00B9> "<U005E><U0031>";<U0031>
|
||||
|
||||
// MASCULINE ORDINAL INDICATOR
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00BA> <U006F>
|
||||
|
||||
// RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
"<EFBFBD>" => ">>",
|
||||
// <U00BB> "<U003E><U003E>"
|
||||
|
||||
// VULGAR FRACTION ONE QUARTER
|
||||
"<EFBFBD>" => " 1/4",
|
||||
// <U00BC> "<U0020><U0031><U002F><U0034>"
|
||||
|
||||
// VULGAR FRACTION ONE HALF
|
||||
"<EFBFBD>" => " 1/2",
|
||||
// <U00BD> "<U0020><U0031><U002F><U0032>"
|
||||
|
||||
// VULGAR FRACTION THREE QUARTERS
|
||||
"<EFBFBD>" => " 3/4",
|
||||
// <U00BE> "<U0020><U0033><U002F><U0034>"
|
||||
|
||||
// INVERTED QUESTION MARK
|
||||
"<EFBFBD>" => "?",
|
||||
// <U00BF> <U003F>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH GRAVE
|
||||
"<EFBFBD>" => "A",
|
||||
// <U00C0> <U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH ACUTE
|
||||
"<EFBFBD>" => "A",
|
||||
// <U00C1> <U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "A",
|
||||
// <U00C2> <U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH TILDE
|
||||
"<EFBFBD>" => "A",
|
||||
// <U00C3> <U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
"<EFBFBD>" => "Ae", // "A"
|
||||
// <U00C4> "<U0041><U0065>";<U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
"<EFBFBD>" => "Aa", // "A"
|
||||
// <U00C5> "<U0041><U0061>";<U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER AE
|
||||
"<EFBFBD>" => "AE", // "A"
|
||||
// <U00C6> "<U0041><U0045>";<U0041>
|
||||
|
||||
// LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
"<EFBFBD>" => "C",
|
||||
// <U00C7> <U0043>
|
||||
|
||||
// LATIN CAPITAL LETTER E WITH GRAVE
|
||||
"<EFBFBD>" => "E",
|
||||
// <U00C8> <U0045>
|
||||
|
||||
// LATIN CAPITAL LETTER E WITH ACUTE
|
||||
"<EFBFBD>" => "E",
|
||||
// <U00C9> <U0045>
|
||||
|
||||
// LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "E",
|
||||
// <U00CA> <U0045>
|
||||
|
||||
// LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
"<EFBFBD>" => "E",
|
||||
// <U00CB> <U0045>
|
||||
|
||||
// LATIN CAPITAL LETTER I WITH GRAVE
|
||||
"<EFBFBD>" => "I",
|
||||
// <U00CC> <U0049>
|
||||
|
||||
// LATIN CAPITAL LETTER I WITH ACUTE
|
||||
"<EFBFBD>" => "I",
|
||||
// <U00CD> <U0049>
|
||||
|
||||
// LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "I",
|
||||
// <U00CE> <U0049>
|
||||
|
||||
// LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
"<EFBFBD>" => "I",
|
||||
// <U00CF> <U0049>
|
||||
|
||||
// LATIN CAPITAL LETTER ETH
|
||||
"<EFBFBD>" => "D",
|
||||
// <U00D0> <U0044>
|
||||
|
||||
// LATIN CAPITAL LETTER N WITH TILDE
|
||||
"<EFBFBD>" => "N",
|
||||
// <U00D1> <U004E>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH GRAVE
|
||||
"<EFBFBD>" => "O",
|
||||
// <U00D2> <U004F>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH ACUTE
|
||||
"<EFBFBD>" => "O",
|
||||
// <U00D3> <U004F>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "O",
|
||||
// <U00D4> <U004F>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH TILDE
|
||||
"<EFBFBD>" => "O",
|
||||
// <U00D5> <U004F>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
"<EFBFBD>" => "Oe", // "O"
|
||||
// <U00D6> "<U004F><U0065>";<U004F>
|
||||
|
||||
// MULTIPLICATION SIGN
|
||||
"<EFBFBD>" => "x",
|
||||
// <U00D7> <U0078>
|
||||
|
||||
// LATIN CAPITAL LETTER O WITH STROKE
|
||||
"<EFBFBD>" => "O",
|
||||
// <U00D8> <U004F>
|
||||
|
||||
// LATIN CAPITAL LETTER U WITH GRAVE
|
||||
"<EFBFBD>" => "U",
|
||||
// <U00D9> <U0055>
|
||||
|
||||
// LATIN CAPITAL LETTER U WITH ACUTE
|
||||
"<EFBFBD>" => "U",
|
||||
// <U00DA> <U0055>
|
||||
|
||||
// LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "U",
|
||||
// <U00DB> <U0055>
|
||||
|
||||
// LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
"<EFBFBD>" => "Ue", // "U"
|
||||
// <U00DC> "<U0055><U0065>";<U0055>
|
||||
|
||||
// LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
"<EFBFBD>" => "Y",
|
||||
// <U00DD> <U0059>
|
||||
|
||||
// LATIN CAPITAL LETTER THORN
|
||||
"<EFBFBD>" => "Th",
|
||||
// <U00DE> "<U0054><U0068>"
|
||||
|
||||
// LATIN SMALL LETTER SHARP S
|
||||
"<EFBFBD>" => "ss",
|
||||
// <U00DF> "<U0073><U0073>";<U03B2>
|
||||
|
||||
// LATIN SMALL LETTER A WITH GRAVE
|
||||
"<EFBFBD>" => "a",
|
||||
// <U00E0> <U0061>
|
||||
|
||||
// LATIN SMALL LETTER A WITH ACUTE
|
||||
"<EFBFBD>" => "a",
|
||||
// <U00E1> <U0061>
|
||||
|
||||
// LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "a",
|
||||
// <U00E2> <U0061>
|
||||
|
||||
// LATIN SMALL LETTER A WITH TILDE
|
||||
"<EFBFBD>" => "a",
|
||||
// <U00E3> <U0061>
|
||||
|
||||
// LATIN SMALL LETTER A WITH DIAERESIS
|
||||
"<EFBFBD>" => "ae", // "a"
|
||||
// <U00E4> "<U0061><U0065>";<U0061>
|
||||
|
||||
// LATIN SMALL LETTER A WITH RING ABOVE
|
||||
"<EFBFBD>" => "aa", // "a"
|
||||
// <U00E5> "<U0061><U0061>";<U0061>
|
||||
|
||||
// LATIN SMALL LETTER AE
|
||||
"<EFBFBD>" => "ae", // "a"
|
||||
// <U00E6> "<U0061><U0065>";<U0061>
|
||||
|
||||
// LATIN SMALL LETTER C WITH CEDILLA
|
||||
"<EFBFBD>" => "c",
|
||||
// <U00E7> <U0063>
|
||||
|
||||
// LATIN SMALL LETTER E WITH GRAVE
|
||||
"<EFBFBD>" => "e",
|
||||
// <U00E8> <U0065>
|
||||
|
||||
// LATIN SMALL LETTER E WITH ACUTE
|
||||
"<EFBFBD>" => "e",
|
||||
// <U00E9> <U0065>
|
||||
|
||||
// LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "e",
|
||||
// <U00EA> <U0065>
|
||||
|
||||
// LATIN SMALL LETTER E WITH DIAERESIS
|
||||
"<EFBFBD>" => "e",
|
||||
// <U00EB> <U0065>
|
||||
|
||||
// LATIN SMALL LETTER I WITH GRAVE
|
||||
"<EFBFBD>" => "i",
|
||||
// <U00EC> <U0069>
|
||||
|
||||
// LATIN SMALL LETTER I WITH ACUTE
|
||||
"<EFBFBD>" => "i",
|
||||
// <U00ED> <U0069>
|
||||
|
||||
// LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "i",
|
||||
// <U00EE> <U0069>
|
||||
|
||||
// LATIN SMALL LETTER I WITH DIAERESIS
|
||||
"<EFBFBD>" => "i",
|
||||
// <U00EF> <U0069>
|
||||
|
||||
// LATIN SMALL LETTER ETH
|
||||
"<EFBFBD>" => "d",
|
||||
// <U00F0> <U0064>
|
||||
|
||||
// LATIN SMALL LETTER N WITH TILDE
|
||||
"<EFBFBD>" => "n",
|
||||
// <U00F1> <U006E>
|
||||
|
||||
// LATIN SMALL LETTER O WITH GRAVE
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00F2> <U006F>
|
||||
|
||||
// LATIN SMALL LETTER O WITH ACUTE
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00F3> <U006F>
|
||||
|
||||
// LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00F4> <U006F>
|
||||
|
||||
// LATIN SMALL LETTER O WITH TILDE
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00F5> <U006F>
|
||||
|
||||
// LATIN SMALL LETTER O WITH DIAERESIS
|
||||
"<EFBFBD>" => "oe", // "o"
|
||||
// <U00F6> "<U006F><U0065>";<U006F>
|
||||
|
||||
// DIVISION SIGN
|
||||
"<EFBFBD>" => ":",
|
||||
// <U00F7> <U003A>
|
||||
|
||||
// LATIN SMALL LETTER O WITH STROKE
|
||||
"<EFBFBD>" => "o",
|
||||
// <U00F8> <U006F>
|
||||
|
||||
// LATIN SMALL LETTER U WITH GRAVE
|
||||
"<EFBFBD>" => "u",
|
||||
// <U00F9> <U0075>
|
||||
|
||||
// LATIN SMALL LETTER U WITH ACUTE
|
||||
"<EFBFBD>" => "u",
|
||||
// <U00FA> <U0075>
|
||||
|
||||
// LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
"<EFBFBD>" => "u",
|
||||
// <U00FB> <U0075>
|
||||
|
||||
// LATIN SMALL LETTER U WITH DIAERESIS
|
||||
"<EFBFBD>" => "ue", // "u"
|
||||
// <U00FC> "<U0075><U0065>";<U0075>
|
||||
|
||||
// LATIN SMALL LETTER Y WITH ACUTE
|
||||
"<EFBFBD>" => "y",
|
||||
// <U00FD> <U0079>
|
||||
|
||||
// LATIN SMALL LETTER THORN
|
||||
"<EFBFBD>" => "th",
|
||||
// <U00FE> "<U0074><U0068>"
|
||||
|
||||
// LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
"<EFBFBD>" => "y"
|
||||
// <U00FF> <U0079>
|
||||
|
||||
);
|
||||
|
||||
?>
|
Reference in New Issue
Block a user