From 636050f9be374fc15acad8b047c1ae227d38b225 Mon Sep 17 00:00:00 2001 From: Fridolin Somers Date: Wed, 29 Apr 2015 12:35:00 +0200 Subject: [PATCH] Bug 14078: (followup) converting from ISO5426 is not complete Conversion of MARC from ISO5426 is defined in C4::Charset::char_decode5426(). Each character or combined characters conversion is defined in a map. This patch adds missing conversions. See http://www.gymel.com/charsets/MAB2.html Signed-off-by: Frederic Demians Signed-off-by: Jonathan Druart Signed-off-by: Tomas Cohen Arazi --- C4/Charset.pm | 43 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 39 insertions(+), 4 deletions(-) diff --git a/C4/Charset.pm b/C4/Charset.pm index c0f829a436..cd7a61fa25 100644 --- a/C4/Charset.pm +++ b/C4/Charset.pm @@ -804,6 +804,9 @@ Converts a string from ISO-5426 to UTF-8. my %chars; + +#### +## 0xb $chars{0xb0}=0x0101;#3/0ayn[ain] $chars{0xb1}=0x0623;#3/1alif/hamzah[alefwithhamzaabove] #$chars{0xb2}=0x00e0;#'à'; @@ -812,14 +815,46 @@ $chars{0xb2}=0x00e0;#3/2leftlowsinglequotationmark $chars{0xb3}=0x00e7;#3/2leftlowsinglequotationmark # $chars{0xb4}='è'; $chars{0xb4}=0x00e8; -$chars{0xbd}=0x02b9; -$chars{0xbe}=0x02ba; # $chars{0xb5}='é'; $chars{0xb5}=0x00e9; +$chars{0xb6}=0x2021; # double dagger +$chars{0xb7}=0x00b7; # middle dot +$chars{0xb8}=0x2033; # double prime +$chars{0xb9}=0x2019; # right single quotation mark +$chars{0xba}=0x201d; # right double quotation mark +$chars{0xbb}=0x00bb; # right-pointing double angle quotation mark +$chars{0xbc}=0x266f; # music sharp sign +$chars{0xbd}=0x02b9; # modifier letter prime +$chars{0xbe}=0x02ba; # modifier letter double prime +$chars{0xbf}=0x00bf; # inverted question mark + +#### +## 0xe +$chars{0xe1}=0x00c6; # latin capital letter ae +$chars{0xe2}=0x0110; # latin capital letter d with stroke +$chars{0xe6}=0x0132; # latin capital ligature ij +$chars{0xe8}=0x0141; # latin capital letter l with stroke +$chars{0xe9}=0x00d8; # latin capital letter o with stroke +$chars{0xea}=0x0152; # latin capital ligature oe +$chars{0xec}=0x00de; # latin capital letter thorn + +#### +## 0xf +$chars{0xf1}=0x00e6; # latin small letter ae +$chars{0xf2}=0x0111; # latin small letter d with stroke +$chars{0xf3}=0x00f0; # latin small letter eth +$chars{0xf5}=0x0131; # latin small letter dotless i +$chars{0xf6}=0x0133; # latin small ligature ij +$chars{0xf8}=0x0142; # latin small letter l with stroke +$chars{0xf9}=0x00f8; # latin small letter o with stroke +$chars{0xfa}=0x0153; # latin small ligature oe +$chars{0xfb}=0x00df; # latin small letter sharp s +$chars{0xfc}=0x00fe; # latin small letter thorn + +#### +## Others $chars{0x97}=0x003c;#3/2leftlowsinglequotationmark $chars{0x98}=0x003e;#3/2leftlowsinglequotationmark -$chars{0xfa}=0x0153; #oe -$chars{0xea}=0x0152; #oe #$chars{0x81d1}=0x00b0; # FIXME useless #### -- 2.39.5