UBB.Developers Forums UBB.threads 7 Development Modification Ideas Auto-link generation for Scripture references

sub assemblebooks {
my @data = (); 					# To hold file source data
my @books = ();					# To hold book tokens for entire file
my @temp = ();					# To hold single book's tokens (one line in file)
my $line = "";					# For each line of the file
my $piece = "";					# For each record in line
open (DATA, '<:encoding(utf8)', $booksfile) or die "Cannot open the Bible book names file! $!\n";
@data = <DATA>;
close DATA;

my $bk = ''; #Full book name to be cached here
foreach $line (@data) {
chomp $line;
@temp = split/\s*\t|,\s*/, $line;
$bk=$temp[0];
	foreach $piece (@temp) {
		push @books, "$piece\n";
		$abbrev{$piece}=$bk;
	}
}

$book = Regexp::Assemble->new;
foreach $line (@books) {
  chomp $line;
  $book->add( "$line" );
}
} # END SUB

sub parsetext {
my $num = qr/\d+/;
my $roman_numeral = qr/\b(?=[IVXLCDM])(?>M{0,4}(?:CM|CD|D?C{0,3})(?:XC|XL|L?X{0,3})(?:IX|IV|V?I{0,3}))\b/i;
my $chapter = qr/$num|$roman_numeral/;

my $replace = sub {

my $REFERENCE		= $1;
my $BOOK		= $2||$7;
my $three		= $3;
my $VERSION		= "";
#NEED TO INCORPORATE SOME VERSION CHECKING ON $6
$VERSION = $VERSION || $DEFAULT_VER;
if ($abbrev{$BOOK}) { $BOOK = $abbrev{$BOOK} };
my $ThML = qq'$Lbracket\scripRef version="$VERSION" passage="$REFERENCE" parsed="$VERSION|$BOOK';
chomp $three;
$three=~s/^\.//;
$three=~s/;\s*$//;

my ($chapverse,$chap,$verses,$verse_start,$verse_end,$segment,$i) = '';
while ($three) {
($chapverse,$three) = split(/;/, $three, 2);
($chap, $verses) = split(/:|\./, $chapverse);
$chap =~ s/\s//g;
$chap = arabic($chap) if isroman($chap);
  while ($verses) {
	($segment,$verses) = split(/,|\s(?:and|\&)\s/i, $verses, 2);
	$segment=~s/\s//g;
	($verse_start,$verse_end) = split(/\-/, $segment);
	unless ($verse_end) { $verse_end=$verse_start };
	for ($i=$verse_start; $i<=$verse_end; $i++) {
		$ThML .= "|$chap|$i";
	}
  }
  if ($three) { $ThML .= ";$VERSION|$BOOK" } else { $ThML .= "|" };
}
$ThML .= qq|"$Rbracket$REFERENCE$Lbracket/scripRef$Rbracket|;
return $ThML;
};
###

$text =~ s%    
(						# BEGIN CAPTURE OF $1 ***
	(?:					# *LOOK FOR USUAL GRAMMAR FIRST (CAPTURED SEPARATELY)
    ($book)					# MATCH BIBLE BOOK NAMES FROM ASSEMBLED REGEX  $2
    (						# BEGIN CAPTURE OF $3
	\.?\s					# MATCH A SPACE FOLLOWING BOOK NAME
    ( (?:$chapter)+				# MATCH A CHAPTER
	(?:[:\-,. ]*				# MATCH A DELIMITER BETWEEN CHAPTERS AND VERSES
		(?: (?:and|\&) \s+)?		# MATCH AN OPTIONAL "AND" OR "&" BETWEEN VERSES
	\d+)*					# MATCH VERSE DIGITS
	)					# MATCH A NUMBER (USUALLY A CHAPT.)=$4 
						# OPTIONALLY FOLLOWED BY VERSE NUMBERS
						# WHICH MAY BE DELIMITED BY THE [:-, ] 
    (\;						# .MATCH A SEMI-COLON...ETC. (BELOW)=$5
        (?:\s*(?:$chapter)			# .MATCH AN OPTIONAL SPACE, THEN A NUMBER
        (?:[:\-,. ]*				# .MATCH A DELIMITER BETWEEN CHAPTERS AND VERSES
		(?:(?:and|\&)\s+)*		# .MATCH AN OPTIONAL "AND" OR "&" BETWEEN VERSES
		\d+)* )				# .MATCH ZERO+ VERSE DELIMITERS/NUMBERS
    )*						# .MAKE CLAUSE OPTIONAL & REPEATABLE
	
	)					# CLOSE CAPTURE OF $3
	) | (Book\sof\s($book))			# *OR CAPTURE WHOLE BOOK IN ABSENCE OF CHAP/VERSE
						# ABOVE LINE CAPTURES TO $7 & $8
)						# CLOSE CAPTURE OF $1 ***


#### 
    (						# >LOOK FOR OPTIONAL VERSION NOTATION=$6
        (?:\(\w+\)*)				# >MATCH WORD IN PARENTHESES
        |					# > -OR-
        (?:[, ]+(?!$book)\w+){0,6}		# >MATCH COMMA OR SPACE FOLLOWED BY WORD
    )*						# >CLOSE CAPTURE FOR $6
####
%$replace->()%egx;

=item Example
<scripRef version="NIV" passage="Rom. viii. 27,28; x. 8-13" 
parsed="NIV|Romans|8|27|8|28;NIV|Romans|10|8|10|13">
Romans viii. 27,28; x. 8-13
</scripRef>
=cut

} #END SUB parsetext