See in Reader
298 lines
9.3 KiB
Perl
298 lines
9.3 KiB
Perl
# Routine to take missing.log entries and link to UGNT and ULB.KJV.Strongs
|
|
|
|
use 5.12.0;
|
|
use File::Slurp;
|
|
$| = "\n";
|
|
use utf8;
|
|
#use open IN => ":utf8", OUT => ":utf8";
|
|
use open IO => ":utf8";
|
|
binmode(STDOUT, ":utf8");
|
|
use File::Find ;
|
|
use FindBin '$Bin';
|
|
use Cwd ;
|
|
|
|
my ($pwd, $d, $textEditor, $repoPath, $browser) = ($Bin, "\\");
|
|
if ($^O eq "darwin" || $^O eq "linux") {$d = "/"}
|
|
|
|
open LOG, ">:utf8", "Logs${d}mine_log.log" or die ("$!");
|
|
|
|
my ($udf) = "User_defaults.windows.txt";
|
|
if ($^O eq "linux") {$udf = "User_defaults.linux.txt"}
|
|
elsif ($^O eq "darwin") {$udf = "User_defaults.mac.txt"}
|
|
|
|
chdir $Bin;
|
|
|
|
open (my $defaults, "<:utf8", "User${d}$udf") or die "User${d}$udf:\n$!";
|
|
|
|
GetUserDefaults();
|
|
|
|
my ($excFile, $topDir, $txtFile, $dataFile, $displayFile, $filePattern, $sn, $xfAbr, $thisULB) = (
|
|
"$Bin${d}Exceptions${d}Exceptions_tWs_from_OSHB.txt",
|
|
"$repoPath${d}en_tw/bible",
|
|
"$Bin${d}Temp${d}ULB_NASB_Strongs.txt",
|
|
"$Bin${d}User${d}tW_work_NT.txt",
|
|
"$Bin${d}Temp${d}mine_results.html",
|
|
"*\.md"
|
|
);
|
|
|
|
my ($missingLine, $bk, $ch, $vs, $ref, $strong, $word, $flag, $tNid, $abbr, $doFlag, $xmlFile, $outputFiles, $lbsBk, $url, $putative, $usfmFile);
|
|
my (%bkAbr, %wa);
|
|
my @tWfiles;
|
|
|
|
find( sub { push @tWfiles, $File::Find::name if ( m/^(.*)$filePattern$/ ) }, $topDir) ;
|
|
|
|
open OUT, ">:utf8", "$displayFile" or die;
|
|
|
|
say OUT "<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta charset=\"UTF-8\"/>
|
|
</head>
|
|
<body>
|
|
";
|
|
|
|
ParseLine();
|
|
FindURL();
|
|
FindVerse($ref);
|
|
ChecktWPages($word);
|
|
Finish();
|
|
|
|
say OUT "
|
|
</body>
|
|
</html>";
|
|
close OUT;
|
|
close LOG;
|
|
print "\n\tDone.\n\n";
|
|
|
|
sub GetUserDefaults {
|
|
open (my $defaults, "<:utf8", "$Bin${d}User${d}$udf") or die "$Bin${d}User${d}$udf:\n$!";
|
|
|
|
while (my $thisLine = <$defaults>) {
|
|
chomp $thisLine;
|
|
if ($thisLine =~ /^Text editor: (.*)$/) {
|
|
$textEditor = "\"$1\"";
|
|
} elsif ($thisLine =~ /^Repository directory: (.*)$/) {
|
|
$repoPath = $1
|
|
} elsif ($thisLine =~ /^HTML browser: (.*)$/) {
|
|
$browser = "\"$1\"";
|
|
}
|
|
}
|
|
|
|
say LOG "\$textEditor: $textEditor\n\$repoPath: $repoPath\n\$browser: $browser";
|
|
die "No text editor found" if $textEditor eq "";
|
|
die "No path to repo found" if $repoPath eq "";
|
|
|
|
if ($^O eq "darwin") {$textEditor = "open -a $textEditor"; $browser = "open -a $browser"}
|
|
|
|
close $defaults;
|
|
}
|
|
|
|
sub ParseLine {
|
|
my ($sch, $svs);
|
|
if ($^O eq "linux" || $^O eq "darwin") {
|
|
say "\nEnter line from Entries_not_handled.txt:\n";
|
|
$missingLine = <STDIN>; # I moved chomp to a new line to make it more readable
|
|
chomp $missingLine; # Get rid of newline character at the end
|
|
exit 0 if ($missingLine eq ""); # If empty string, exit.
|
|
#$missingLine = "Zephaniah 1:2 5486";
|
|
} else {
|
|
$missingLine = read_file ("Temp${d}temp.tmp");
|
|
}
|
|
|
|
if ($missingLine =~ /^(([^:]*) (\d+):(\d+))\t([^\/]*\/([^\t]*))/) {
|
|
($ref, $bk, $ch, $vs, $url, $putative) = ($1, $2, $3, $4, $5, $6);
|
|
$outputFiles .= "${url}.md ";
|
|
say LOG "\$bk: $bk";
|
|
open (my $file, "<:utf8", "$dataFile") or die "$dataFile:\n$!";
|
|
|
|
while (my $line = <$file>) {
|
|
chomp $line;
|
|
if ($line =~ /^(# )?([^\t]*)\t([^\t]*)\t([^\t]*)$/) {
|
|
my ($fullBk, $numBk, $abr) = ($2, $3, $4);
|
|
say LOG "\$fullBk: |$fullBk|, \$numBk: $numBk, \$abr: $abr, \$bk: |$bk|";
|
|
if ($fullBk eq $bk) {
|
|
say LOG "\$fullBk: |$fullBk|, \$bk: |$bk|";
|
|
$lbsBk = $abr;
|
|
if ($numBk =~ /(\d\d)-(...)/) {
|
|
$abbr = lc $2;
|
|
say LOG "\$abbr: $abbr";
|
|
if ($^O eq "darwin") {system `open -a /Applications/Logos.app "logos4:TextComparison;ref=BibleESV.$lbsBk${ch}.$vs;res=esv,niv2011,niv,nasb95,nrsv,gs-netbible,nlt,leb,kjv1900"`}
|
|
my $mxl;
|
|
if ($bk eq "Psalms?") {$mxl = 3}
|
|
else {$mxl = 2}
|
|
while (length $ch < $mxl) {$ch =~ s/^/0/}
|
|
while (length $vs < $mxl) {$vs =~ s/^/0/}
|
|
}
|
|
$usfmFile = "$repoPath${d}UGNT${d}${numBk}.usfm";
|
|
say LOG "\$abbr${d}\$ch${d}\$vs: $abbr${d}$ch${d}$vs";
|
|
if ($^O eq "darwin") {system `$textEditor $repoPath${d}en_tn${d}$abbr${d}$ch${d}$vs.md`}
|
|
}
|
|
}
|
|
}
|
|
|
|
close $file;
|
|
|
|
} else {
|
|
die "\n\tInput unreadable.\n"
|
|
}
|
|
say LOG "Looking for $putative in $usfmFile";
|
|
say LOG "\$missingLine: $missingLine, \$ref: $ref, \$bk: $bk, \$ch: $ch, \$vs: $vs, \$url: $url\n\n";
|
|
}
|
|
sub FindURL {
|
|
|
|
my ($thisChap, $thisVers);
|
|
|
|
open (my $file, "<:utf8", "$usfmFile") or die "$usfmFile:\n$!";
|
|
|
|
while (my $line = <$file>) {
|
|
chomp $line;
|
|
if ($line =~ /\\mt (.*)$/) {
|
|
my $thisBook = $1;
|
|
if ($thisBook eq $bk) {
|
|
say LOG "\$thisBook: $thisBook\t\$bk: $bk";
|
|
$doFlag = 1;
|
|
} else {
|
|
say LOG "\nThe wrong book is being searched.\n"
|
|
}
|
|
} elsif ($doFlag && $line =~ /^\\c (\d+)$/) {
|
|
$thisChap = $1
|
|
} elsif ($doFlag && $line =~ /^\\v (\d+)$/) {
|
|
$thisVers = $1
|
|
} elsif ($doFlag && $thisChap == $ch && $thisVers == $vs) {
|
|
say LOG "\$thisChap:\$thisVers: $thisChap:$thisVers \$line: $line";
|
|
if ($line =~ /strong="([GH]....)(.).*$url/) {
|
|
say OUT "<p>$line</p>";
|
|
$strong = $1;
|
|
my $test = $2;
|
|
if ($test ne "0") {die "\n\t\tStrong's number won't work.\n\n"}
|
|
unless ($strong =~ /^.+$/) {die "\nThe Strong's number <$strong> is not found.\n"}
|
|
while ($strong =~ s/([GH])0/$1/) {}
|
|
if ($strong =~ /^.+$/) {
|
|
say OUT "<p><span style=\"color:red\">$strong</span></p>\n";
|
|
last
|
|
}
|
|
} elsif ($line =~ /\\k-s[^\n]*$url/) {
|
|
say OUT "<p><span style=\"color:red\">$url</span> is part of a phrase</p>\n";
|
|
$flag = 1;
|
|
}
|
|
} elsif ($line =~ /\\mt (.*)$/) {
|
|
$doFlag = 0
|
|
}
|
|
}
|
|
|
|
close $file;
|
|
|
|
}
|
|
|
|
|
|
sub FindVerse {
|
|
|
|
my $fileText = read_file("$txtFile", binmode => 'utf8');
|
|
|
|
say LOG "FindVerse |$strong|.";
|
|
|
|
if ($flag && $fileText =~ /$ref\t[^\n]*\n[^\n]*\n/) {
|
|
say LOG "$ref\n$&";
|
|
say $&;
|
|
exit 0;
|
|
} else {
|
|
if ($fileText =~ /$ref([^\n]*\n )([^\n]*<)$strong(.?>[^\n]*)/) {
|
|
my ($fore, $precon, $aft) = ($1, $2, $3);
|
|
say LOG "\$ref: $ref\n\$fore: $fore\n\$precon:\n$precon\n\$aft: $aft";
|
|
my $preprecon;
|
|
if ($precon =~ /^(.*([,>\w\'\"\- —;] |['";\.\?\!]))([\w\-]+) (<[^<>]*> )?<$/) {
|
|
($preprecon, $word) = ($1, $3);
|
|
say LOG "\$&: $&\n\$preprecon: $preprecon\n\$word: $word";
|
|
}
|
|
$preprecon =~ s/</</g;
|
|
$preprecon =~ s/>/>/g;
|
|
$aft =~ s/</</g;
|
|
$aft =~ s/>/>/g;
|
|
say OUT "<p>$ref$fore</p>\n<p>$preprecon<span style=\"color:red\">$word</span> <<span style=\"color:red\">$strong</span>$aft</p>\n";
|
|
}
|
|
else {
|
|
say OUT "<p>The Strong's code <<<span style=\"color:red\">$strong</span>>> is not found in $ref.</p>";
|
|
say OUT "<p>${ref}\\t[^\\n]*\\n[^\\n]*</p>";
|
|
#system ("bbfind -g \"${ref}\\t[^\\n]*\\n[^\\n]*\" 'data${d}ULB_NASB_Strongs.txt'") or die "$!";
|
|
|
|
if ($^O eq "darwin") {system ("find $topDir -name \"*.md\" -exec grep -H --color \"$strong\[, \\n\\r\]\" {} \\;")}
|
|
#system ("find $topDir -name \"*.md\" -exec grep -H --color \"$strong\$\" {} \\;");
|
|
}
|
|
}
|
|
return $word;
|
|
}
|
|
|
|
sub ChecktWPages{
|
|
|
|
say LOG "<<$word>>";
|
|
die "\n\$word is empty.\n" if $word eq "";
|
|
my $topDir = "$repoPath${d}en_tw${d}bible";
|
|
|
|
foreach my $file ( @tWfiles ) {
|
|
my $fileText = read_file("$file", binmode => 'utf8');
|
|
# While finds entries and Strong's numbers
|
|
while ($fileText =~ /($strong)[^\d]|^(# [^\n]*\b$word\b)/g) {
|
|
#system `clear`;
|
|
my $abb = $file;
|
|
$abb =~ s/.md$//;
|
|
say OUT "<p>$abb</p>\n";
|
|
$outputFiles .= "$file "
|
|
}
|
|
}
|
|
}
|
|
sub Finish {
|
|
say "\nLooking for $strong.";
|
|
# find $topDir -name "*.md" -exec grep -H '($strong[^\d]|$strong$)' {} +
|
|
#system ("find $topDir -name \"*.md\" -exec grep -H --color \"$strong\[, \\n\\r\]\" {} \\;");
|
|
|
|
foreach my $file ( @tWfiles ) {
|
|
my $fileText = read_file("$file", binmode => 'utf8');
|
|
# While finds entries and Strong's numbers
|
|
if ($fileText =~ /([^\n]*)($strong)([^\n]*)/g) {
|
|
my ($pre, $found, $post) = ($1, $2, $3);
|
|
my $abb = $file;
|
|
$abb =~ s/.md$//;
|
|
say OUT "<p>$abb: $pre<span style=\"color:red\">$found</span>$post</p>\n";
|
|
$outputFiles .= "$file "
|
|
}
|
|
}
|
|
say "\nLooking for $putative.";
|
|
foreach my $file ( @tWfiles ) {
|
|
my $fileText = read_file("$file", binmode => 'utf8');
|
|
# While finds entries and Strong's numbers
|
|
if ($fileText =~ /#{1,1} ([^\n]*)(\b$putative\b)([^\n]*)/g) {
|
|
my ($pre, $found, $post) = ($1, $2, $3);
|
|
my $abb = $file;
|
|
$abb =~ s/.md$//;
|
|
say OUT "<p>$abb: $pre<span style=\"color:red\">$found</span>$post</p>\n";
|
|
$outputFiles .= "$file "
|
|
}
|
|
}
|
|
say "\nLooking for $word.";
|
|
foreach my $file ( @tWfiles ) {
|
|
my $fileText = read_file("$file", binmode => 'utf8');
|
|
# While finds entries and Strong's numbers
|
|
if ($fileText =~ /#{1,1} ([^\n]*)(\b$word\b)([^\n]*)/g) {
|
|
my ($pre, $found, $post) = ($1, $2, $3);
|
|
my $abb = $file;
|
|
$abb =~ s/.md$//;
|
|
say OUT "<p>$abb: $pre<span style=\"color:red\">$found</span>$post</p>\n";
|
|
$outputFiles .= "$file "
|
|
}
|
|
}
|
|
say "Opening .md files.";
|
|
if ($^O eq "darwin") {
|
|
system `$browser https://www.blueletterbible.org/lang/lexicon/lexicon.cfm?strongs=$strong`;
|
|
system `$textEditor $outputFiles`;
|
|
system `$textEditor $excFile`;}
|
|
if ($^O eq "linux") {
|
|
system `$browser https://www.blueletterbible.org/lang/lexicon/lexicon.cfm?strongs=$strong &`;
|
|
system `$textEditor $outputFiles &`;
|
|
system `$textEditor $excFile &`;}
|
|
if ($^O eq "MSWin32" || $^O eq "MSWin64" ) {
|
|
system `START "" $browser https://www.blueletterbible.org/lang/lexicon/lexicon.cfm?strongs=$strong`;
|
|
system `START "" $textEditor $outputFiles`;
|
|
system `START "" $textEditor $excFile`;
|
|
system `START "" $browser $displayFile`;}
|
|
}
|