From 92c7b7ca6e31d31a54a9d1884b87e6c04728ae49 Mon Sep 17 00:00:00 2001
From: Henry Whitney <henry_whitney@wycliffeassociates.org>
Date: Mon, 27 Apr 2020 13:35:01 -0400
Subject: [PATCH] Trying to make more useful

---
 .../Build_MAST_NT_from_csv.generic.pl         | 103 ++++++++++++++++++
 .../Find_duplicate_tW_entries.pl              |  48 ++++++++
 2 files changed, 151 insertions(+)
 create mode 100755 MAST_tW_PDF_Updater/FilesForUpdates/Build_MAST_NT_from_csv.generic.pl
 create mode 100644 MAST_tW_PDF_Updater/FilesForUpdates/Find_duplicate_tW_entries.pl

diff --git a/MAST_tW_PDF_Updater/FilesForUpdates/Build_MAST_NT_from_csv.generic.pl b/MAST_tW_PDF_Updater/FilesForUpdates/Build_MAST_NT_from_csv.generic.pl
new file mode 100755
index 0000000..4a5439f
--- /dev/null
+++ b/MAST_tW_PDF_Updater/FilesForUpdates/Build_MAST_NT_from_csv.generic.pl
@@ -0,0 +1,103 @@
+use 5.12.0;
+use File::Slurp;
+use File::Find ; 
+use Cwd ; 
+use utf8;
+#use open IN => ":utf8", OUT => ":utf8";
+use open IO => ":utf8";
+binmode STDOUT, ":encoding(UTF-8)";
+mkdir "OGNT";
+mkdir "Logs";
+
+open LOG, ">Logs/log.log";
+
+my (%bk);
+my ($last_bn, $last_ch, $last_vs, $bklc) = ("00", "00", "00");
+
+say "Reading data ...";
+while (<DATA>) {
+	chomp;
+	if (/^(\d\d)-(...)/) {
+		$bk{$1} = $2;
+	}
+}
+
+
+#open IN, "/Users/Henry/Documents/WACS/Tips_and_Hacks/MAST_tW_PDF_Updater/FilesForUpdates/OGNT/OpenGNT_version3_3.csv" or die "$!";
+open IN, "OpenGNT_version3_3.csv" or die "$!";
+
+say "Reading input ...";
+
+while (<IN>) {
+	chomp;
+	Separate();
+}
+
+say OUT "			</verse>\n		</chapter>\n	</book>\n</xml>";
+
+say "Closing input and output files ...";
+
+close OUT;
+close IN;
+close LOG;
+
+say "Done.";
+
+sub Separate {
+	if (/[^\t]*\t[^\t]*\t[^\t]*\t[^\t]*\t.\t[^\t]*\t〔(\d+)｜(\d+)｜(\d+)〕\t〔[^\｜]*｜[^\｜]*｜([^\｜]*)｜([^\｜]*)｜([^\｜]*)｜([^\｜]*)〕/) {
+		my ($bn, $ch, $vs, $word, $lexeme, $gram, $sn) = ($1, $2, $3, $4, $5, $6, $7);
+		say LOG "$1, $2, $3, $4, $5, $6, $7";
+		$sn =~ s/[GH]//;
+		$bn = $bn + 1;
+		if ($bn ne $last_bn) {
+			my ($this_bk) = ($bk{$bn});
+			$bklc = lc $bk{$bn};
+			if (OUT-> opened()) {
+				say OUT "			</verse>\n		</chapter>\n	</book>\n</xml>";
+				close OUT;
+			}
+			open OUT, ">:utf8", "OGNT/$bn-$bk{$bn}.xml" or die "$! $bn-$bk{$bn}.xml";
+			say OUT "\n<xml>\n	<div type=\"book\" osisID=\"$bklc\">\n		<chapter osisID=\"$bklc.$ch\">\n			<verse osisID=\"$bklc.$ch.$vs\">";
+			($last_bn, $last_ch, $last_vs) = ($bn, $ch, $vs)
+		}
+		elsif ($ch ne $last_ch) {
+			say OUT "			</verse>\n		</chapter>\n		<chapter osisID=\"$bklc.$ch\">\n			<verse osisID=\"$bklc.$ch.$vs\">";
+			($last_ch, $last_vs) = ($ch, $vs)
+		}
+		elsif ($vs ne $last_vs) {
+			my ($this_bk, $bklc) = ($bk{$bn}, lc $bk{$bn});
+			say OUT "			</verse>\n		<verse osisID=\"$bklc.$ch.$vs\">";
+			$last_vs = $vs;
+		}
+	say OUT "\t\t\t\t<w lemma=\"$sn\" morph=\"$gram\" lexeme=\"$lexeme\">$word</w>"
+	}
+}
+
+__DATA__
+41-MAT.xml
+42-MRK.xml
+43-LUK.xml
+44-JHN.xml
+45-ACT.xml
+46-ROM.xml
+47-1CO.xml
+48-2CO.xml
+49-GAL.xml
+50-EPH.xml
+51-PHP.xml
+52-COL.xml
+53-1TH.xml
+54-2TH.xml
+55-1TI.xml
+56-2TI.xml
+57-TIT.xml
+58-PHM.xml
+59-HEB.xml
+60-JAS.xml
+61-1PE.xml
+62-2PE.xml
+63-1JN.xml
+64-2JN.xml
+65-3JN.xml
+66-JUD.xml
+67-REV.xml
diff --git a/MAST_tW_PDF_Updater/FilesForUpdates/Find_duplicate_tW_entries.pl b/MAST_tW_PDF_Updater/FilesForUpdates/Find_duplicate_tW_entries.pl
new file mode 100644
index 0000000..bd8bf39
--- /dev/null
+++ b/MAST_tW_PDF_Updater/FilesForUpdates/Find_duplicate_tW_entries.pl
@@ -0,0 +1,48 @@
+use 5.12.0;
+use File::Slurp;
+use File::Find ; 
+use Cwd ; 
+use utf8;
+#use open IN => ":utf8", OUT => ":utf8";
+use open IO => ":utf8";
+
+open LOG, ">:utf8", "Logs/log.log" or die;
+open OUT, ">:utf8", "Output/output.txt" or die;
+
+my $topDir = "/Users/Henry/Documents/WACS/en_tw/bible";
+my $filePattern = '\.md' ;
+my %foundEntries;
+my @theseEntries;
+
+my @filesToRun = ();
+find( sub { push @filesToRun, $File::Find::name  if ( m/^(.*)$filePattern$/ ) }, $topDir) ;
+
+foreach  my $file ( @filesToRun  ) {
+	say LOG $file;
+	my $fileText = read_file("$file", binmode => 'utf8');
+	my $theseEntries;
+	if ($fileText =~ /^# ([^\n]*?)\n/) {
+		$theseEntries = $1;
+		@theseEntries = split /, /, $theseEntries;
+		ParseEntries();
+	}
+} 
+
+close OUT;
+close LOG;
+
+print "\n\tDone.";
+
+# ============
+
+sub ParseEntries {
+	foreach my $entry (@theseEntries) {
+		$entry =~ s/ \([^\)]*\)//g;
+		if (exists $foundEntries{$entry}) {
+			say OUT $entry;
+		} else {
+			$foundEntries{$entry} = $entry
+		}
+	}
+	@theseEntries = "";
+}
\ No newline at end of file