See in Reader
Revamping NT tool for use with OGNT
This commit is contained in:
parent
2f243dc5f5
commit
b8d70a29c2
|
|
@ -15,11 +15,12 @@ my @bookList;
|
|||
|
||||
open LOG, ">$Bin${d}Logs${d}log.log" or die "$Bin${d}Logs${d}log.log: $!";
|
||||
|
||||
open (my $file, "<:utf8", "$Bin${d}User${d}tW_work_NT.txt") or die "$Bin${d}User${d}tW.work.NT.dat:\n$!";
|
||||
open (my $file, "<:utf8", "$Bin${d}User${d}tW_work_NT.txt") or die "$Bin${d}User${d}tW.work.NT.txt:\n$!";
|
||||
|
||||
while (my $line = <$file>) {
|
||||
chomp $line;
|
||||
if ($line =~ /^([^#][^\t]*)\t([^\t]*)\t([^\t]*)\t([^\t]*)$/) {
|
||||
say LOG $line;
|
||||
if ($line =~ /^([^#][^\n\t]*)\t([^\n\t]*)\t([^\n\t]*)$/) {
|
||||
|
||||
$book = "$1";
|
||||
push @bookList, $book;
|
||||
|
|
@ -27,21 +28,22 @@ open LOG, ">$Bin${d}Logs${d}log.log" or die "$Bin${d}Logs${d}log.log: $!";
|
|||
}
|
||||
close $file;
|
||||
|
||||
say LOG "\@bookList: @bookList";
|
||||
say LOG "Removing old Extract.txt";
|
||||
|
||||
say LOG "Removing old Extract.txt";
|
||||
|
||||
unlink "Temp${d}Extract.txt";
|
||||
unlink "$Bin${d}Temp${d}Extract.txt";
|
||||
|
||||
say LOG "Building new Extract.txt";
|
||||
|
||||
open(OUT, ">:utf8", "Temp${d}Extract.txt") or die "$!: Temp${d}Extract.txt";
|
||||
open(OUT, ">:utf8", "$Bin${d}Temp${d}Extract.txt") or die "$!: $Bin${d}Temp${d}Extract.txt";
|
||||
|
||||
foreach $book (@bookList) {
|
||||
say LOG "\$book: $book";
|
||||
#say "\$book: $book";
|
||||
my $fileText = read_file("$Bin${d}Temp${d}ULB_text.txt", binmode => 'utf8');
|
||||
# While finds entries and Strong's numbers
|
||||
while ($fileText =~ /$book [0-9]*:[0-9]*[^\n]*\n/g) {
|
||||
say OUT $&;
|
||||
#say LOG $&;
|
||||
print OUT $&;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -6460,6 +6460,7 @@ Joel 2:17 4910 ||
|
|||
Joel 2:19 6030 ||
|
||||
Joel 2:19 7646 ||
|
||||
Joel 2:19 5414 ||
|
||||
Joel 2:19 1471 nations
|
||||
Joel 2:20 7368 ||
|
||||
Joel 2:20 6440 ||
|
||||
Joel 2:20 314 ||
|
||||
|
|
@ -7978,6 +7979,7 @@ Zechariah 7:9 6213 ||
|
|||
Zechariah 7:9 376 ||
|
||||
Zechariah 7:10 376 ||
|
||||
Zechariah 7:10 251 ||
|
||||
Zechariah 7:10 6041 ||
|
||||
Zechariah 7:11 241 ||
|
||||
Zechariah 7:11 3513 ||
|
||||
Zechariah 7:11 8085 ||
|
||||
|
|
@ -7992,6 +7994,7 @@ Zechariah 7:14 5674 ||
|
|||
Zechariah 7:14 7760 ||
|
||||
Zechariah 8:1 3068 ||
|
||||
Zechariah 8:2 6635 ||
|
||||
Zechariah 8:22 1471 nations
|
||||
Zechariah 8:3 7931 ||
|
||||
Zechariah 8:3 5892 ||
|
||||
Zechariah 8:4 6635 ||
|
||||
|
|
|
|||
|
|
@ -1,134 +0,0 @@
|
|||
use 5.12.0;
|
||||
use utf8;
|
||||
use Cwd;
|
||||
use File::Slurp;
|
||||
use File::Basename;
|
||||
use FindBin '$Bin';
|
||||
use open IO => ":utf8";
|
||||
$| = 1;
|
||||
$" = "\n";
|
||||
|
||||
my ($pwd, $d, $fileSpec) = ($Bin, "\\", "\.usfm");
|
||||
if ($^O eq "linux" || $^O eq "darwin") {
|
||||
($d) = ("/");
|
||||
}
|
||||
|
||||
chdir $pwd;
|
||||
|
||||
my ($inDir, $outDir) = ("", "out");
|
||||
my (@array, @usfmLines);
|
||||
my (%hash);
|
||||
my ($whatami, $inFile);
|
||||
my ($book, $chap, $vers, $text, $outText, $newV, $newC, $newB, $outFile, $usfmText, $metathesis, $repoPath);
|
||||
|
||||
open(LOG, ">:utf8", "Logs${d}log.log") or die "${d}Logs${d}log.log:\n$!";
|
||||
|
||||
my ($udf) = "User_defaults.windows.txt";
|
||||
if ($^O eq "linux") {$udf = "User_defaults.linux.txt"}
|
||||
elsif ($^O eq "darwin") {$udf = "User_defaults.mac.txt"}
|
||||
|
||||
open (my $defaults, "<:utf8", "User${d}$udf") or die "User${d}$udf:\n$!";
|
||||
|
||||
GetUserDefaults();
|
||||
|
||||
say LOG "\$inDir: $inDir";
|
||||
chdir("$repoPath");
|
||||
opendir THISDIR, "." or die "serious dainbramage: $!";
|
||||
my @infiles = grep /$fileSpec$/i, readdir *THISDIR;
|
||||
say LOG "\$repoPath: $repoPath, \$fileSpec: $fileSpec\n\@infiles:\n@infiles";
|
||||
closedir THISDIR;
|
||||
chdir("$pwd");
|
||||
ProcessFiles();
|
||||
say "Done.";
|
||||
close LOG;
|
||||
|
||||
sub GetUserDefaults {
|
||||
open (my $defaults, "<:utf8", "User${d}$udf") or die "User{d}$udf:\n$!";
|
||||
|
||||
my ($ptte, $ptr);
|
||||
while (my $thisLine = <$defaults>) {
|
||||
chomp $thisLine;
|
||||
if ($thisLine =~ /^Repository directory: (.*)$/) {
|
||||
$repoPath = $1
|
||||
}
|
||||
}
|
||||
die "No path to repo found" if $repoPath eq "";
|
||||
|
||||
($repoPath) = ("$repoPath${d}en_ulb");
|
||||
say LOG "\$repoPath: $repoPath";
|
||||
|
||||
close $defaults;
|
||||
}
|
||||
|
||||
|
||||
sub ProcessFiles {
|
||||
say "Processing files";
|
||||
my $thisLine;
|
||||
open(OUT, ">:utf8", "Temp${d}ULB_text.txt") or die "Temp${d}ULB_text.txt:\n$!";
|
||||
my $finalTextForm;
|
||||
@infiles = sort @infiles;
|
||||
foreach $inFile (@infiles) {
|
||||
#say LOG $inFile;
|
||||
my $thisFile;
|
||||
$usfmText = read_file("$repoPath${d}$inFile", binmode => 'utf8') or die;
|
||||
$usfmText =~ s/\r?\n([^\\ \r\n])/ $1/g;
|
||||
$usfmText =~ s/\\f \+.*?\\f\*//g;
|
||||
$usfmText =~ s/\\pi/\\p/g;
|
||||
$usfmText =~ s/\\((ide?)|(toc.)|(mt|sp)|(c \\d+))[^\r\n]*\r?\n//g;
|
||||
$usfmText =~ s/\r?\n\\(m|pi?|(q\d?)) ([^\r\n]*)\r?\n/ $3/g;
|
||||
$usfmText =~ s/([^\r\n])\\q/$1/g;
|
||||
$usfmText =~ s/ +\r?\n/\n/g;
|
||||
$usfmText =~ s/(\r?\n\\v \d+)\r?\n/$1 \[blank\]\n/g;
|
||||
$usfmText =~ s/ —/—/g;
|
||||
#say LOG $usfmText;
|
||||
#say LOG "\$usfmText:\n$usfmText\n=====\n";
|
||||
@usfmLines = "";
|
||||
@usfmLines = split /\r?\n/, $usfmText;
|
||||
#say LOG "\@usfmLines:\n@usfmLines";
|
||||
foreach $thisLine (@usfmLines) {
|
||||
chomp $thisLine;
|
||||
say LOG "<3>\t$thisLine";
|
||||
$thisLine =~ s/^(\\q)$//;
|
||||
say LOG "<4>\t$thisLine";
|
||||
$thisLine = SearchAndReplace($thisLine);
|
||||
say LOG "<5>\t$thisLine";
|
||||
$thisFile .= $thisLine;
|
||||
}
|
||||
say LOG "Before changes:\n$thisFile";
|
||||
$thisFile =~ s/\r?\n>>\t/ /g;
|
||||
$thisFile =~ s/>\t//g;
|
||||
$thisFile =~ s/[\r\n]/÷/g;;
|
||||
$thisFile =~ s/— /—/g;
|
||||
$thisFile =~ s/\\q\d//g;
|
||||
$thisFile =~ s/\\p//g;
|
||||
$thisFile =~ s/\\q //g;
|
||||
$thisFile =~ s/\\qs( .*)\\qs\* ?/$1/g;
|
||||
$thisFile =~ s/\÷+/\n/g;
|
||||
$thisFile =~ s/ {2,}/ /g;
|
||||
#say LOG "After changes:\n$thisFile";
|
||||
say OUT $thisFile;
|
||||
}
|
||||
close OUT;
|
||||
}
|
||||
|
||||
sub SearchAndReplace {
|
||||
my $thisxLine = shift;
|
||||
$thisxLine =~ s/\\s5.*$/\n-------\n/;
|
||||
say LOG "<0>\t$thisxLine";
|
||||
if ($thisxLine =~ s/\\h (.+) *$//) {$book = $1;$newB = 1}
|
||||
elsif ($thisxLine =~ s/\\c (\d+)//) {$chap = $1; $newC = 1}
|
||||
elsif ($thisxLine =~ s/\\v (\d+(-\d+)?) (.*)$/$3/) {
|
||||
#print OUT "\n$outText\n";
|
||||
$vers = $1;
|
||||
$newV = 1;
|
||||
$thisxLine = "\n$book $chap:$vers\t$metathesis$thisxLine";
|
||||
$metathesis = "";
|
||||
say LOG "<1>\t<$book> $chap:$vers\t$thisxLine";
|
||||
}
|
||||
elsif ($thisxLine =~ s/^\\q\d? (.*)$/ $1/) {}
|
||||
elsif ($thisxLine =~ s/^\\m (.*)$/ $1/) {}
|
||||
elsif ($thisxLine =~ s/^\\d (.*)//) {$metathesis = "$1 "}
|
||||
elsif ($thisxLine =~ s/^\\[qpm]$//) {}
|
||||
say LOG "<2>\t|$thisxLine|";
|
||||
return $thisxLine;
|
||||
}
|
||||
|
|
@ -20,7 +20,7 @@ my $all_file = "/Users/Henry/Documents/git.Door43/OpenGNT_version3_3.csv";# late
|
|||
# my $all_file = "/Users/Henry/Documents/git.Door43/Test.csv";# latest version of OGNT
|
||||
my $OGNT_directory = "/Users/Henry/Documents/git.Door43/OGNT";
|
||||
my (%book_no, %wa_book_no, %abbr, %full, %bk_abr, %book_name, %wa_book_name);
|
||||
my ($old_bk_abr, $old_ch, $old_vs);
|
||||
my ($old_bk_abr, $old_ch, $old_vs, $file_ID);
|
||||
my ($udf) = "User_defaults.windows.txt";
|
||||
if ($^O eq "linux") {$udf = "User_defaults.linux.txt"}
|
||||
elsif ($^O eq "darwin") {$udf = "User_defaults.mac.txt"}
|
||||
|
|
@ -39,7 +39,7 @@ while (<DATA>) {
|
|||
chomp;
|
||||
if (/^([^\t]*)\t([^\t]*)\t([^\t]*)\t([^\t]*)/) {
|
||||
($book_no{$4}, $wa_book_no{$4}, $abbr{$4}, $full{$3}) = ($1, $2, $3, $4);
|
||||
($book_name{$1}, $bk_abr{$1})= ($4, $3);
|
||||
($book_name{$1}, $bk_abr{$1}, $file_ID) = ($4, $3, "$2-" . uc $3);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -80,14 +80,15 @@ sub PlaceParsed {
|
|||
if ($bkabr ne $old_bk_abr) {
|
||||
#say LOG "\$bkabr $bkabr ne \$old_bk_abr $old_bk_abr. Should be opening $Bin${d}OGNT${d}$bkabr.xml";
|
||||
EndFile();
|
||||
open OUT, ">$repoPath${d}OGNT${d}$bkabr.xml" or die "$!: $Bin${d}OGNT${d}$bkabr.xml";
|
||||
# Find out where file_ID is established and get it into the next line
|
||||
open OUT, ">$repoPath${d}OGNT${d}$file_ID.xml" or die "$!: $Bin${d}OGNT${d}$file_ID.xml";
|
||||
say OUT "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n\t<book osisID=\"$bkabr\">\n\t\t<chapter osisID=\"$bkabr.$ch\">\n\t\t\t<verse osisID=\"$bkabr.$ch.$vs\">"
|
||||
} elsif ($ch ne $old_ch) {
|
||||
say OUT "\t\t\t</verse>\n\t\t</chapter>\n\t\t<chapter osisID=\"$bkabr.$ch\">\n\t\t\t<verse osisID=\"$bkabr.$ch.$vs\">"
|
||||
} elsif ($vs ne $old_vs) {
|
||||
say OUT "\t\t\t</verse>\n\t\t\t<verse osisID=\"$bkabr.$ch.$vs\">"
|
||||
}
|
||||
say OUT "\t\t\t\t<w lemma\"$strong\" morph=\"$parse\">$word</w>";
|
||||
say OUT "\t\t\t\t<w lemma=\"$strong\" morph=\"$parse\">$word</w>";
|
||||
($old_bk_abr, $old_ch, $old_vs) = ($bkabr, $ch, $vs);
|
||||
#say LOG "(\$old_bk_abr: $old_bk_abr, \$old_ch: $old_ch, \$old_vs: $old_vs) = (\$bkabr: $bkabr, \$ch: $ch, \$vs: $vs)";
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,9 +1,9 @@
|
|||
# Produces list of tWs for each verse by linking OGNT to ULB through tWs.
|
||||
|
||||
# Taken from tWs.from.OSHB.2.pl.
|
||||
# Taken from tWs.from.OGNT.2.pl.
|
||||
|
||||
# The output from this script is useful for the interleaved PDFs used in MAST.
|
||||
# This version uses an exception file to handle places where the OSHB points to
|
||||
# This version uses an exception file to handle places where the OGNT points to
|
||||
# a tW page different from that on which the ULB term appears.
|
||||
|
||||
# Make sure the correct input file is $ULBfile. Run script.
|
||||
|
|
@ -37,25 +37,25 @@ elsif ($^O eq "darwin") {$udf = "User_defaults.mac.txt"}
|
|||
|
||||
open (my $defaults, "<:utf8", "$pwd${d}User${d}$udf") or die "$pwd${d}User${d}$udf:\n$!";
|
||||
|
||||
my ($cv, $ULBfile, $exceptions, $missing, $log, $output, $workFile, $verseMap) =
|
||||
my ($cv, $ULBfile, $exceptions, $missing, $log, $output, $workFile) =
|
||||
("00000",
|
||||
"Temp${d}Extract.txt",
|
||||
"Exceptions${d}Exceptions_tWs_from_OGNT.txt",
|
||||
"Output${d}Entries_not_handled.txt",
|
||||
"Logs${d}log.log",
|
||||
"Output${d}tWs_for_PDF.txt",
|
||||
"User${d}tW_work_NT.txt",
|
||||
"OSHB${d}VerseMap.xml",
|
||||
"$Bin${d}Temp${d}Extract.txt",
|
||||
"$Bin${d}Exceptions${d}Exceptions_tWs_from_OGNT.txt",
|
||||
"$Bin${d}Output${d}Entries_not_handled.txt",
|
||||
"$Bin${d}Logs${d}log.log",
|
||||
"$Bin${d}Output${d}tWs_for_PDF.txt",
|
||||
"$Bin${d}User${d}tW_work_NT.txt",
|
||||
);
|
||||
|
||||
my ($OSHBfile, $topTwDir, $textEditor, $repoPath, $topSourceLangDir);
|
||||
|
||||
my ($OGNTfile, $topTwDir, $textEditor, $repoPath, $topSourceLangDir);
|
||||
|
||||
my (%entries, %text, %ref, %order, %pages, %listOfPages, %sourcePage, %checkPages, %foundPages, %substitutedPages,
|
||||
%specifiedText, %realPage, %checkPage, %workEntries, %vsn, %StrongNum, %fullText, %ulbOrder, %bkAbr, %bkFull, %relevantSNs,
|
||||
%SNsInCV, %entriesThisSN, %entriesThisPage, %pagesThisSN, %pageThisEntry, %adjust, %newRef);
|
||||
|
||||
my $book;
|
||||
my (@OSHBfileList);
|
||||
my (@OGNTfileList);
|
||||
|
||||
# ==============================
|
||||
|
||||
|
|
@ -75,7 +75,7 @@ while (<DATA>) {
|
|||
|
||||
GetUserDefaults();
|
||||
GetULBBooksToProcess();
|
||||
CheckForRemaps();
|
||||
#CheckForRemaps();
|
||||
ReadExceptions();
|
||||
PairtWEntriesTotWPageAndUniqSNs();
|
||||
ReadLinkedSNs();
|
||||
|
|
@ -113,48 +113,48 @@ sub GetUserDefaults {
|
|||
die "No text editor found" if $textEditor eq "";
|
||||
die "No path to repo found" if $repoPath eq "";
|
||||
|
||||
($topTwDir, $topSourceLangDir) = ("$repoPath${d}en_tw${d}bible", "$repoPath${d}OSHB");
|
||||
($topTwDir, $topSourceLangDir) = ("$repoPath${d}en_tw${d}bible", "$repoPath${d}OGNT");
|
||||
|
||||
close $defaults;
|
||||
}
|
||||
|
||||
sub GetULBBooksToProcess {
|
||||
say LOG "GetULBBooksToProcess";
|
||||
say LOG "GetULBBooksToProcess on \$workFile: $workFile";
|
||||
open (my $file, "<:utf8", "$workFile") or die "$workFile:\n$!";
|
||||
|
||||
while (my $line = <$file>) {
|
||||
chomp $line;
|
||||
say LOG $line;
|
||||
if ($line =~ /^[^#][^\t]*\t[^\t]*\t([^\t]*)\t[^\t]*$/) {
|
||||
$OSHBfile = "$topSourceLangDir${d}$1.xml";
|
||||
push @OSHBfileList, $OSHBfile;
|
||||
say LOG "\t$line";
|
||||
if ($line =~ /^[^#][^\t]*\t[^\t]*\t([^\t]*)$/) {
|
||||
$OGNTfile = "$topSourceLangDir${d}$1.xml";
|
||||
push @OGNTfileList, $OGNTfile;
|
||||
}
|
||||
}
|
||||
|
||||
close $file;
|
||||
say LOG "\@OSHBfileList: @OSHBfileList"
|
||||
say LOG "\@OGNTfileList: @OGNTfileList";die;
|
||||
}
|
||||
|
||||
sub CheckForRemaps {
|
||||
say "Checking for remaps in $repoPath${d}$verseMap";
|
||||
#/media/henry/92C6F7E3C6F7C58F/Users/henry/Documents/WA_Repo/OSHB/VerseMap.xml:
|
||||
#/media/henry/92C6F7E3C6F7C58F/Users/henry/WA_Repo/OSHB/VerseMap.xml
|
||||
open (my $file, "<:utf8", "$repoPath${d}$verseMap") or die "$repoPath${d}$verseMap:\n$!";
|
||||
|
||||
while (my $thisLine = <$file>) {
|
||||
chomp $thisLine;
|
||||
#say LOG $thisLine;
|
||||
if ($thisLine =~ /<verse wlc="([^\.]*)\.(\d+)\.(\d+)" kjv="([^\.]*)\.(\d+)\.(\d+)" type="full"\/>/) {
|
||||
#say LOG "*\t$thisLine";
|
||||
my ($oldB, $oldC, $oldV, $newB, $newC, $newV) =($bkFull{$1}, $2, $3, $bkFull{$4}, $5, $6);
|
||||
my $oldie = "$oldB $oldC:$oldV";
|
||||
$newRef{$oldie} = "$newB $newC:$newV";
|
||||
say LOG "**\t" . "\$newRef{$oldie}: " . $newRef{"$oldB $oldC:$oldV"}
|
||||
}
|
||||
}
|
||||
|
||||
close $file;
|
||||
}
|
||||
#sub CheckForRemaps {
|
||||
# say "Checking for remaps in $repoPath${d}$verseMap";
|
||||
# #/media/henry/92C6F7E3C6F7C58F/Users/henry/Documents/WA_Repo/OGNT/VerseMap.xml:
|
||||
# #/media/henry/92C6F7E3C6F7C58F/Users/henry/WA_Repo/OGNT/VerseMap.xml
|
||||
# open (my $file, "<:utf8", "$repoPath${d}$verseMap") or die "$repoPath${d}$verseMap:\n$!";
|
||||
#
|
||||
# while (my $thisLine = <$file>) {
|
||||
# chomp $thisLine;
|
||||
# #say LOG $thisLine;
|
||||
# if ($thisLine =~ /<verse wlc="([^\.]*)\.(\d+)\.(\d+)" kjv="([^\.]*)\.(\d+)\.(\d+)" type="full"\/>/) {
|
||||
# #say LOG "*\t$thisLine";
|
||||
# my ($oldB, $oldC, $oldV, $newB, $newC, $newV) =($bkFull{$1}, $2, $3, $bkFull{$4}, $5, $6);
|
||||
# my $oldie = "$oldB $oldC:$oldV";
|
||||
# $newRef{$oldie} = "$newB $newC:$newV";
|
||||
# say LOG "**\t" . "\$newRef{$oldie}: " . $newRef{"$oldB $oldC:$oldV"}
|
||||
# }
|
||||
# }
|
||||
#
|
||||
# close $file;
|
||||
#}
|
||||
|
||||
sub ReadExceptions {
|
||||
say "Reading exceptions";
|
||||
|
|
@ -181,12 +181,12 @@ sub PairtWEntriesTotWPageAndUniqSNs {
|
|||
my $filePattern = '*.md' ;
|
||||
find (sub {push @filesToRun, $File::Find::name if (m/^(.*)$filePattern$/)}, $topTwDir) ;
|
||||
@filesToRun = sort @filesToRun;
|
||||
say LOG "\@filesToRun: @filesToRun";
|
||||
#say LOG "\@filesToRun: @filesToRun";
|
||||
foreach my $file (@filesToRun) {
|
||||
print ".";
|
||||
$file =~ s/\//\\/g unless $^O eq "linux" || $^O eq "darwin";
|
||||
my ($thisList, $shortFile) = ("", $file);
|
||||
#say "|$shortFile|\t|$topTwDir|";
|
||||
say LOG "\$file: $file, \$shortFile: $shortFile, \$topTwDir: $topTwDir";
|
||||
$shortFile =~ s/^\Q$topTwDir${d}\E//;
|
||||
$shortFile =~ s/\.md$//;
|
||||
$shortFile =~ s/\Q$d\E/,/;
|
||||
|
|
@ -198,7 +198,7 @@ sub PairtWEntriesTotWPageAndUniqSNs {
|
|||
if (/^# ([^\n]*)$/) {
|
||||
$thisList = $1;
|
||||
$thisList =~ s/[\r\n]*$//;
|
||||
say LOG "\$thisList = |$thisList|";
|
||||
#say LOG "\$thisList = |$thisList|";
|
||||
$thisList =~ s/ \([^\)]*\)//g;
|
||||
$entriesThisPage{$shortFile} = $thisList;
|
||||
my @ULBEntries = split /, /, $thisList;
|
||||
|
|
@ -213,7 +213,7 @@ sub PairtWEntriesTotWPageAndUniqSNs {
|
|||
}
|
||||
if (/Strong's(.*)$/) {
|
||||
my $SNs = $1;
|
||||
while ($SNs =~ s/[H](\d*)//) {
|
||||
while ($SNs =~ s/[G](\d*)//) {
|
||||
push @relevantSNs, $1;
|
||||
$entriesThisSN{$1} .= "$thisList, ";
|
||||
$pagesThisSN{$1} .= "$shortFile, ";
|
||||
|
|
@ -226,41 +226,18 @@ sub PairtWEntriesTotWPageAndUniqSNs {
|
|||
}
|
||||
}
|
||||
close IN;
|
||||
|
||||
#}
|
||||
#say LOG "|$shortFile|: \t |$entriesThisPage{$shortFile}|"
|
||||
}
|
||||
say "";
|
||||
#say LOG "====";
|
||||
#say LOG "====";
|
||||
}
|
||||
|
||||
sub LinkULBtoCV {
|
||||
say "Linking ULB to chapter and verse";
|
||||
say LOG "LinkULBtoCV, \$ULBfile: $ULBfile";
|
||||
open IN, "$ULBfile" or die "$ULBfile: $!";
|
||||
while (<IN>) {
|
||||
#say LOG $_;
|
||||
if (/^([^\t]*)\t(.*)$/) {
|
||||
$cv ++;
|
||||
($text{$1}, $fullText{$1}) = ($2, $2);
|
||||
$ref{$cv} = $1;
|
||||
$order{$1} = $cv;
|
||||
}
|
||||
#say LOG "First \$ref{$cv}: $ref{$cv}\n\$text{$ref{$cv}}: $text{$ref{$cv}}";
|
||||
}
|
||||
close IN;
|
||||
foreach my $key (sort keys %ref) {
|
||||
#say LOG "\$key: $key:, \$ref{$key}: $ref{$key}, \$text{$ref{$key}}: $text{$ref{$key}}"
|
||||
}
|
||||
}
|
||||
|
||||
sub ReadLinkedSNs {
|
||||
say "Reading linked Strong's numbers";
|
||||
my ($flag, $OSHBfile) = ("","");
|
||||
foreach $OSHBfile (@OSHBfileList) {
|
||||
#say LOG "opening \$^OHB $OSHBfile";
|
||||
open IN, "$OSHBfile" or die "$OSHBfile can't be opened\n\n";
|
||||
my ($flag, $OGNTfile) = ("","");
|
||||
foreach $OGNTfile (@OGNTfileList) {
|
||||
say LOG "opening \$OGNTfile: $OGNTfile";
|
||||
open IN, "$OGNTfile" or die "$OGNTfile can't be opened\n\n";
|
||||
my ($thisBook, $thisChap, $thisVers, $thisRef);
|
||||
my (@pages);
|
||||
while (<IN>) {
|
||||
|
|
@ -276,7 +253,7 @@ sub ReadLinkedSNs {
|
|||
say LOG "##\t$bk $ch:$vs, $thisRef";
|
||||
}
|
||||
else {
|
||||
while (/<w lemma="(\w\/)?(\d+)( \w)?"/g) {
|
||||
while (/<w lemma="(\d+)"/g) {
|
||||
#say LOG $_;
|
||||
my ($thisNum) = ($2);
|
||||
say LOG "\t\$thisNum: $thisNum, \$SNsInCV{$thisRef}: $SNsInCV{$thisRef}";
|
||||
|
|
@ -301,6 +278,25 @@ sub ReadLinkedSNs {
|
|||
}
|
||||
}
|
||||
|
||||
sub LinkULBtoCV {
|
||||
say "Linking ULB to chapter and verse";
|
||||
say LOG "LinkULBtoCV, \$ULBfile: $ULBfile";
|
||||
open IN, "$ULBfile" or die "$ULBfile: $!";
|
||||
while (<IN>) {
|
||||
if (/^([^\t]*)\t(.*)$/) {
|
||||
$cv ++;
|
||||
($text{$1}, $fullText{$1}) = ($2, $2);
|
||||
$ref{$cv} = $1;
|
||||
$order{$1} = $cv;
|
||||
}
|
||||
#say "First \$ref{$cv}: $ref{$cv}\nGetULBBooksToProcess\$text{$ref{$cv}}: $text{$ref{$cv}}";
|
||||
}
|
||||
close IN;
|
||||
foreach my $key (sort keys %ref) {
|
||||
#say LOG "\$key: $key:, \$ref{$key}: $ref{$key}, \$text{$ref{$key}}: $text{$ref{$key}}"
|
||||
}
|
||||
}
|
||||
|
||||
sub LinkSNsToULBtextViaEntries {
|
||||
say "Linking Strong's numbers to ULB text via tW page entries";
|
||||
say LOG "sub LinkSNsToULBtextViaEntries called";
|
||||
|
|
@ -387,47 +383,6 @@ sub LinkSNsToULBtextViaEntries {
|
|||
}
|
||||
}
|
||||
|
||||
sub Adjust {
|
||||
my ($snsOld, $ref, $snsNew, $addToSnsNew) = ($_[0], $_[1], "", "");
|
||||
say LOG "\$specifiedText{$ref}: $specifiedText{$ref}\n\$snsOld: $snsOld";
|
||||
my (%tempEntries);
|
||||
#say LOG ">\t\$sns: |$sns|";
|
||||
#say LOG ">\t\$specifiedText{$ref}: |$specifiedText{$ref}|";
|
||||
$snsOld =~ s/^ +LinkSNsToULBtextViaEntries//;
|
||||
my @oldArray = split / /, $snsOld;
|
||||
#say LOG "\$adjust{$ref}: $adjust{$ref}";
|
||||
my @preadjustments = split /, /, $adjust{$ref};
|
||||
foreach my $adjustment (@preadjustments) {
|
||||
#say LOG "<><>\t\$adjustment: >$adjustment<";
|
||||
if ($adjustment =~ /([^\t]*)\t\|\|$/) { # delete this from list to look for
|
||||
my $found = $1;
|
||||
$snsOld =~ s/\b$found\b ?//;
|
||||
say LOG "\$found: $found should be deleted from \$snsOld: $snsOld";
|
||||
} elsif ($adjustment =~ /^\|\|\t(.*)/) { # add this to list to look for
|
||||
my $adj = $1;
|
||||
say LOG "\$adjustment: $adjustment, \$adj: $adj";
|
||||
if ($adj =~ /([^\t]*)\t([^\t]*)/) {
|
||||
$snsNew = "[$1]($pageThisEntry{$2})"
|
||||
} else {
|
||||
$snsNew .= "$adj "
|
||||
}
|
||||
} elsif ($adjustment =~ /^(\d+)\t(\w+)$/) { # add specified word
|
||||
my ($found1, $found2) = ($1, $2);
|
||||
#$addToSnsNew .= "$1\[$2\] ";
|
||||
$snsOld =~ s/$found1/$found1\[$found2\]/;
|
||||
say LOG "\$snsOld: $snsOld";
|
||||
} elsif (($adjustment =~ /^(\d+)\t([\/\d\w]+)$/)) { # add specified page
|
||||
#$addToSnsNew .= "$1\{$2\} "
|
||||
my ($found1, $found2) = ($1, $2);
|
||||
$snsOld =~ s/$found1/$found1\($found2\)/;
|
||||
say LOG "\$snsOld: $snsOld";
|
||||
}
|
||||
}
|
||||
say LOG "\$snsNew: >$snsNew<\n\$snsOld+\$snsNew: >$snsOld< >$snsNew<";
|
||||
$snsNew = "$snsOld $snsNew";
|
||||
return $snsNew;
|
||||
}
|
||||
|
||||
sub Output {
|
||||
say "Outputting";
|
||||
#say LOG "Output subRoutine called";
|
||||
|
|
@ -485,6 +440,47 @@ sub Output {
|
|||
}
|
||||
}
|
||||
|
||||
sub Adjust {
|
||||
my ($snsOld, $ref, $snsNew, $addToSnsNew) = ($_[0], $_[1], "", "");
|
||||
say LOG "\$specifiedText{$ref}: $specifiedText{$ref}\n\$snsOld: $snsOld";
|
||||
my (%tempEntries);
|
||||
#say LOG ">\t\$sns: |$sns|";
|
||||
#say LOG ">\t\$specifiedText{$ref}: |$specifiedText{$ref}|";
|
||||
$snsOld =~ s/^ +LinkSNsToULBtextViaEntries//;
|
||||
my @oldArray = split / /, $snsOld;
|
||||
#say LOG "\$adjust{$ref}: $adjust{$ref}";
|
||||
my @preadjustments = split /, /, $adjust{$ref};
|
||||
foreach my $adjustment (@preadjustments) {
|
||||
#say LOG "<><>\t\$adjustment: >$adjustment<";
|
||||
if ($adjustment =~ /([^\t]*)\t\|\|$/) { # delete this from list to look for
|
||||
my $found = $1;
|
||||
$snsOld =~ s/\b$found\b ?//;
|
||||
say LOG "\$found: $found should be deleted from \$snsOld: $snsOld";
|
||||
} elsif ($adjustment =~ /^\|\|\t(.*)/) { # add this to list to look for
|
||||
my $adj = $1;
|
||||
say LOG "\$adjustment: $adjustment, \$adj: $adj";
|
||||
if ($adj =~ /([^\t]*)\t([^\t]*)/) {
|
||||
$snsNew = "[$1]($pageThisEntry{$2})"
|
||||
} else {
|
||||
$snsNew .= "$adj "
|
||||
}
|
||||
} elsif ($adjustment =~ /^(\d+)\t(\w+)$/) { # add specified word
|
||||
my ($found1, $found2) = ($1, $2);
|
||||
#$addToSnsNew .= "$1\[$2\] ";
|
||||
$snsOld =~ s/$found1/$found1\[$found2\]/;
|
||||
say LOG "\$snsOld: $snsOld";
|
||||
} elsif (($adjustment =~ /^(\d+)\t([\/\d\w]+)$/)) { # add specified page
|
||||
#$addToSnsNew .= "$1\{$2\} "
|
||||
my ($found1, $found2) = ($1, $2);
|
||||
$snsOld =~ s/$found1/$found1\($found2\)/;
|
||||
say LOG "\$snsOld: $snsOld";
|
||||
}
|
||||
}
|
||||
say LOG "\$snsNew: >$snsNew<\n\$snsOld+\$snsNew: >$snsOld< >$snsNew<";
|
||||
$snsNew = "$snsOld $snsNew";
|
||||
return $snsNew;
|
||||
}
|
||||
|
||||
sub Substitute {
|
||||
foreach my $key (sort keys %pages) {
|
||||
say LOG "\$key: $key\t\$SNsInCV{$key}: $SNsInCV{$key}";
|
||||
|
|
|
|||
Loading…
Reference in New Issue