added CopticLS parameter to converter

added CopticLS parametier to converter. use with David Brakke's ASCII files
CopticScriptorium · Apr 25, 2015 · 8480b20 · 8480b20
1 parent 242aa22
commit 8480b20
Show file tree

Hide file tree

Showing 4 changed files with 334 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -1,15 +1,18 @@
 This repository holds character encoding converters to covert ASCII characters in legacy fonts into Unicode Coptic characters and a processing perl script to convert a diplomatic, Coptic text transcription into SGML.
 ________________________________________
 Simple Perl Converter:
-recode_coptic.pl Version 0.9.1
+recode_coptic.pl Version 1.1.0
 
 This assumes a UTF-8 file in one word per line format and automatically converts Coptic encodings
 
 Usage:
 recode_coptic.pl file
+Read a file in Coptic font encoding and output standard Unicode as UTF-8
+  recode_coptic.pl in_Coptic.txt > out_utf8.txt
 See help (-h) for options
 
-Copyright 2013-14 Amir Zeldes, Caroline T. Schroeder. The perl program is free software. You may copy or redistribute the script under the same terms as Perl itself.
+
+Copyright 2013-15 Amir Zeldes, Caroline T. Schroeder. The perl program is free software. You may copy or redistribute the script under the same terms as Perl itself.
 _________________________________________
 About CopticVDWtoUTFConverter
 

diff --git a/recode_coptic_0.9.1.pl → old-versions/recode_coptic_0.9.1.pl b/recode_coptic_0.9.1.pl → old-versions/recode_coptic_0.9.1.pl
diff --git a/recode_coptic_1.0.0.pl → old-versions/recode_coptic_1.0.0.pl b/recode_coptic_1.0.0.pl → old-versions/recode_coptic_1.0.0.pl
diff --git a/recode_coptic.pl b/recode_coptic.pl
@@ -0,0 +1,329 @@
+#!/usr/bin/perl -w
+
+# recode_coptic.pl Version 1.0.0
+
+# this assumes a UTF-8 file in one word per line format and 
+# automatically converts Coptic encodings
+# usage:
+# recode_coptic.pl file
+# See help (-h) for options
+
+use Getopt::Std;
+use utf8;
+binmode(STDOUT, ":utf8");
+binmode STDIN;
+
+my $usage;
+{
+$usage = <<"_USAGE_";
+This script converts characters from one Coptic encoding to another.
+
+Notes and assumptions:
+- Supralinear strokes in Coptic font are supported
+- Other decorations not yet supported
+
+Usage:  recode_coptic.pl [options] <FILE>
+
+Options and argument:
+
+-h              print this message and quit
+-f <format>     Specify the input format. Default is Coptic font, other options are "CopticLS", "CMCL", "avva_shenouda", "low" (converts all upper case utf8 Coptic to all lower case)
+
+<FILE>    A text file with Coptic text in a supported encoding
+
+Examples:
+
+Read a file in Coptic font encoding and output standard Unicode as UTF-8:
+  recode_coptic.pl in_Coptic.txt > out_utf8.txt
+
+Read a file in CMCL encoding and output standard Unicode as UTF-8:
+  recode_coptic.pl -f CMCL in_Coptic.txt > out_utf8.txt
+
+  
+Copyright 2013-2015, Amir Zeldes, Caroline T. Schroeder
+
+This program is free software. You may copy or redistribute it under
+the same terms as Perl itself.
+_USAGE_
+}
+
+### OPTIONS BEGIN ###
+%opts = ();
+getopts('hf:',\%opts) or die $usage;
+
+#help
+if ($opts{h} || (@ARGV == 0)) {
+    print $usage;
+    exit;
+}
+
+#format
+if (!($format = $opts{f})) 
+    {$format = "Coptic";}
+elsif($format eq "CopticLS")
+	{$format="CopticLS"}
+elsif($format eq "CMCL") 
+	{$format="CMCL";}
+elsif($format eq "low") 
+	{$format="low";}
+elsif($format eq "avva_shenouda") 
+	{$format="avva_shenouda";}
+else {$format = "Coptic"}
+### OPTIONS END ###
+
+open FILE,"<:encoding(UTF-8)",shift or die "could not find input document";
+
+while (<FILE>) {
+
+    chomp;
+    $line = $_;
+
+	if ($format eq "Coptic")
+	{
+	#consonants (Replace various consonants and digraphs with IPA symbols)
+	$line =~ s/a/ⲁ/g;
+	$line =~ s/b/ⲃ/g;
+	$line =~ s/c/ⲑ/g;
+	$line =~ s/d/ⲇ/g;
+	$line =~ s/e/ⲉ/g;
+	$line =~ s/f/ϥ/g;
+	$line =~ s/g/ⲅ/g;
+	$line =~ s/h/ⲏ/g;
+	$line =~ s/i/ⲓ/g;
+	$line =~ s/j/ϫ/g;
+	$line =~ s/k/ⲕ/g;
+	$line =~ s/l/ⲗ/g;
+	$line =~ s/m/ⲙ/g;
+	$line =~ s/n/ⲛ/g;
+	$line =~ s/o/ⲟ/g;
+	$line =~ s/p/ⲡ/g;
+	$line =~ s/q/ϭ/g;
+	$line =~ s/r/ⲣ/g;
+	$line =~ s/s/ⲥ/g;
+	$line =~ s/t/ⲧ/g;
+	$line =~ s/u/ⲩ/g;
+	$line =~ s/v/ⲫ/g;
+	$line =~ s/w/ⲱ/g;
+	$line =~ s/x/ϩ/g;
+	$line =~ s/y/ⲭ/g;
+	$line =~ s/z/ⲍ/g;
+	$line =~ s/¥/ϣ/g;
+	$line =~ s/\+/ϯ/g;
+
+	#NB psi and xi in Coptic font are 2, 3
+	#these numbers will be replaced
+	$line =~ s/2/ⲯ/g;
+	$line =~ s/3/ⲝ/g;
+
+	#capitals express supralinear stroke in Coptic font
+	$line =~ s/A/ⲁ̄/g;
+	$line =~ s/B/ⲃ̄/g;
+	$line =~ s/C/ⲑ̄/g;
+	$line =~ s/D/ⲇ̄/g;
+	$line =~ s/E/ⲉ̄/g;
+	$line =~ s/F/ϥ̄/g;
+	$line =~ s/G/ⲅ̄/g;
+	$line =~ s/H/ⲏ̄/g;
+	$line =~ s/I/ⲓ̄/g;
+	$line =~ s/J/ϫ̄/g;
+	$line =~ s/K/ⲕ̄/g;
+	$line =~ s/L/ⲗ̄/g;
+	$line =~ s/M/ⲙ̄/g;
+	$line =~ s/N/ⲛ̄/g;
+	$line =~ s/O/ⲟ̄/g;
+	$line =~ s/P/ⲡ̄/g;
+	$line =~ s/Q/ϭ̄/g;
+	$line =~ s/R/ⲣ̄/g;
+	$line =~ s/S/ⲥ̄/g;
+	$line =~ s/T/ⲧ̄/g;
+	$line =~ s/U/ⲩ̄/g;
+	$line =~ s/V/ⲫ̄/g;
+	$line =~ s/W/ⲱ̄/g;
+	$line =~ s/X/ϩ̄/g;
+	$line =~ s/Y/ⲭ̄/g;
+	$line =~ s/Z/ⲍ̄/g;
+	#$line =~ s/¥/ϣ̄/g;
+	#$line =~ s/\+/ϯ̄/g;
+	}
+	elsif ($format eq "CopticLS")
+	#need to add c±s
+	{
+	$line =~ s/a/ⲁ/g;
+	$line =~ s/b/ⲃ/g;
+	$line =~ s/c/ⲭ/g;
+	$line =~ s/d/ⲇ/g;
+	$line =~ s/e/ⲉ/g;
+	$line =~ s/f/ⲫ/g;
+	$line =~ s/g/ⲅ/g;
+	$line =~ s/h/ⲏ/g;
+	$line =~ s/i/ⲓ/g;
+	$line =~ s/j/ϫ/g;
+	$line =~ s/k/ⲕ/g;
+	$line =~ s/l/ⲗ/g;
+	$line =~ s/m/ⲙ/g;
+	$line =~ s/n/ⲛ/g;
+	$line =~ s/o/ⲟ/g;
+	$line =~ s/p/ⲡ/g;
+	$line =~ s/q/ϭ/g;
+	$line =~ s/r/ⲣ/g;
+	$line =~ s/s/ⲥ/g;
+	$line =~ s/t/ⲧ/g;
+	$line =~ s/u/ⲩ/g;
+	$line =~ s/v/ϣ/g;
+	$line =~ s/w/ⲱ/g;
+	$line =~ s/x/ⲝ/g;
+	$line =~ s/y/ⲯ/g;
+	$line =~ s/z/ⲍ/g;
+	$line =~ s/v/ϣ/g;
+	$line =~ s/C/ϭ/g;
+	$line =~ s/D/Ⲇ/g;
+	$line =~ s/F/ϥ/g;
+	$line =~ s/G/ⳉ/g;
+	$line =~ s/H/ϩ/g;
+	$line =~ s/J/ϧ/g;
+	$line =~ s/Q/ⳋ/g;
+	$line =~ s/R/ⳁ/g;
+	$line =~ s/T/ϯ/g;
+	$line =~ s/Z/ⲹ/g;
+
+	#diacritics and strokes
+	$line =~ s/(.)±(.)=±(.)/$1︤$2︦$3︥/g;
+	$line =~ s/(.)±(.)/$1︤$2︥/g; #place binding supralinear strokes after each character
+	$line =~ s/=/̄/g; #equals sign after letter is a supralinear stroke
+	$line =~ s/O/᷍/g;
+	$line =~ s/P/̂/g;
+	$line =~ s/\//̣/g;
+	$line =~ s/Ú/̈/g;
+	$line =~ s/A/ⲏ̂/g;
+	$line =~ s/E/ⲉ̄/g;
+	$line =~ s/I/ⲓ̄/g;
+	$line =~ s/M/ⲛ̀/g;
+	$line =~ s/N/ⲛ̄/g;
+	$line =~ s/S/ⲏ⳰/g;
+	$line =~ s/U/ⲩ̄/g;
+
+	$line =~ s/K/K/g; #couldn't find keyboard character
+	$line =~ s/L/L/g; #couldn't find keyboard character
+	$line =~ s/V/V/g; #couldn't find keyboard character
+	$line =~ s/W/W/g; #couldn't find keyboard character
+	$line =~ s/X/X/g; #couldn't find keyboard character
+	$line =~ s/Y/Y/g; #couldn't find keyboard character
+
+	#punctuation
+	$line =~ s/>/·/g;
+	$line =~ s/B/⟦/g;
+	$line =~ s/ı/⟧/g;
+	$line =~ s/:/:/g;
+	$line =~ s/…/;/g;
+	$line =~ s/</⳿/g;
+
+
+
+	}
+	elsif ($format eq "CMCL")
+	{
+	$line =~ s/a/ⲁ/g;
+	$line =~ s/b/ⲃ/g;
+	$line =~ s/q/ⲑ/g;
+	$line =~ s/d/ⲇ/g;
+	$line =~ s/e/ⲉ/g;
+	$line =~ s/f/ϥ/g;
+	$line =~ s/g/ⲅ/g;
+	$line =~ s/H/ⲏ/g;
+	$line =~ s/i/ⲓ/g;
+	$line =~ s/j/ϫ/g;
+	$line =~ s/k/ⲕ/g;
+	$line =~ s/l/ⲗ/g;
+	$line =~ s/m/ⲙ/g;
+	$line =~ s/n/ⲛ/g;
+	$line =~ s/o/ⲟ/g;
+	$line =~ s/p/ⲡ/g;
+	$line =~ s/c/ϭ/g;
+	$line =~ s/r/ⲣ/g;
+	$line =~ s/s/ⲥ/g;
+	$line =~ s/t/ⲧ/g;
+	$line =~ s/u/ⲩ/g;
+	$line =~ s/P/ⲫ/g;
+	$line =~ s/w/ⲱ/g;
+	$line =~ s/h/ϩ/g;
+	$line =~ s/C/ⲭ/g;
+	$line =~ s/z/ⲍ/g;
+	$line =~ s/y/ϣ/g;
+	$line =~ s/Y/ϯ/g;
+	$line =~ s/T/ⲯ/g;
+	$line =~ s/x/ⲝ/g;
+
+	}
+	elsif ($format eq "low")
+	{
+	$line =~ s/Ⲁ/ⲁ/g;
+	$line =~ s/Ⲃ/ⲃ/g;
+	$line =~ s/Ⲑ/ⲑ/g;
+	$line =~ s/Ⲇ/ⲇ/g;
+	$line =~ s/Ⲉ/ⲉ/g;
+	$line =~ s/Ϥ/ϥ/g;
+	$line =~ s/Ⲅ/ⲅ/g;
+	$line =~ s/Ⲏ/ⲏ/g;
+	$line =~ s/Ⲓ/ⲓ/g;
+	$line =~ s/Ϫ/ϫ/g;
+	$line =~ s/Ⲕ/ⲕ/g;
+	$line =~ s/Ⲗ/ⲗ/g;
+	$line =~ s/Ⲙ/ⲙ/g;
+	$line =~ s/Ⲛ/ⲛ/g;
+	$line =~ s/Ⲟ/ⲟ/g;
+	$line =~ s/Ⲡ/ⲡ/g;
+	$line =~ s/Ϭ/ϭ/g;
+	$line =~ s/Ⲣ/ⲣ/g;
+	$line =~ s/Ⲥ/ⲥ/g;
+	$line =~ s/Ⲧ/ⲧ/g;
+	$line =~ s/Ⲩ/ⲩ/g;
+	$line =~ s/Ⲫ/ⲫ/g;
+	$line =~ s/Ⲱ/ⲱ/g;
+	$line =~ s/Ϩ/ϩ/g;
+	$line =~ s/Ⲭ/ⲭ/g;
+	$line =~ s/Ⲍ/ⲍ/g;
+	$line =~ s/Ϣ/ϣ/g;
+	$line =~ s/Ϯ/ϯ/g;
+	$line =~ s/Ⲯ/ⲯ/g;
+	$line =~ s/Ⲝ/ⲝ/g;
+
+	}
+	elsif ($format eq "avva_shenouda")
+	{
+	$line =~ s/=(.)/$1̄/g; #place supralinear stroke after character, not before as in avva shenouda
+	$line =~ s/a/ⲁ/g;
+	$line =~ s/b/ⲃ/g;
+	$line =~ s/c/ⲥ/g; #c is sigma
+	$line =~ s/d/ⲇ/g;
+	$line =~ s/e/ⲉ/g;
+	$line =~ s/f/ϥ/g;
+	$line =~ s/g/ⲅ/g;
+	$line =~ s/y/ⲏ/g; #y is eta
+	$line =~ s/i/ⲓ/g;
+	$line =~ s/j/ϫ/g;
+	$line =~ s/k/ⲕ/g;
+	$line =~ s/l/ⲗ/g;
+	$line =~ s/m/ⲙ/g;
+	$line =~ s/n/ⲛ/g;
+	$line =~ s/o/ⲟ/g;
+	$line =~ s/p/ⲡ/g;
+	$line =~ s/\[/ϭ/g; #chima is an opening square bracket
+	$line =~ s/r/ⲣ/g;
+	$line =~ s/\;/ⲑ/g; #semi colon is theta
+	$line =~ s/t/ⲧ/g;
+	$line =~ s/u/ⲩ/g;
+	$line =~ s/v/ⲫ/g;
+	$line =~ s/w/ⲱ/g;
+	$line =~ s/h/ϩ/g; #h is hori
+	$line =~ s/y/ⲭ/g;
+	$line =~ s/z/ⲍ/g;
+	$line =~ s/s/ϣ/g; #s is shai
+	$line =~ s/\]/ϯ/g; #right square bracket is ti
+	$line =~ s/v/ⲯ/g;
+	$line =~ s/x/ⲝ/g;
+
+	}
+
+	print $line ."\n";
+}
+