summaryrefslogtreecommitdiffstats
path: root/versification/makeabbrevs.pl
blob: 7789ce71f1a00c5a0a483690ce7368c467a7d095 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
#!/usr/bin/perl


# @canons will contain this list of files, these are in a basic XML format.

# Each file lists osisIDs along with the English names associated with the

# osisID. These aren't exhaustive, and may or may not overlap (but hopefully

# don't). We are only using these to load mappings from osisIDs.

@canons = (
    "canon.bible.xml",      # the Bible, broadly defined

#    "canon.af.xml",         # Apostolic Fathers

#    "canon.otp.xml",        # OT pseudepigrapha

#    "canon.nta.xml",        # NT apocrypha

#    "canon.lds.xml",        # Mormon books

#    "canon.naghammadi.xml", # Nag Hammadi Library

#    "canon.qumran.xml",     # Qumran mss

#    "canon.classical.xml",  # intended for classical works, currently just Josephus

);

@abbrevsQueue = (); 
 
foreach $mapfile (@canons) {
    open MAP, "$mapfile";
    while (<MAP>) {
	$line = $_;
	
	$line =~ s/<!\-\-.+?\-\->//g;
	$line =~ s/\&amp;/\&/g;

	if ($line =~ /<id>(.+?)<\/id>/) {
	    $id = $1;
	    $osis{lc($id)} = $id;
	    push @abbrevsQueue, "$id"
	}
	elsif ($line =~ /<name>(.+?)<\/name>/) {
	    $name = $1;
	    if ($osis{lc($name)} eq "") {
		$osis{lc($name)} = $id;
		push @abbrevsQueue, "$name"
	    }
	    else {
		if ($warn) {
		    print "ERROR: Duplicate mapping from $id found in $mapfile.\n";
		}
	    }

	    if ($idmap{$id} eq "") {
		$idmap{$id} = $name;
	    }
	    else {
		# Duplicates most likely indicate alternate names, so ignore them.

		if ($warn) {
		    print "ERROR: Duplicate mapping from $id found in $mapfile.\n";
		}
	    }
	}
    }
    close (MAP);
}

$abbrevs = "/******************************************************************************\n *	Abbreviations - MUST be in alphabetical order & by PRIORITY\n *		RULE: first match of entire key\n *			(e.g. key: \"1CH\"; match: \"1CHRONICLES\")\n */\n\nconst struct abbrev builtin_abbrevs\[\] = {\n";

@abbrevsQueue = sort @abbrevsQueue;
foreach $a (@abbrevsQueue) {
    if ($a =~ /^.+\d/) {
	$abbrevs .= "//";
    }
    $abbrevs .= "  {\"" . uc($a) . "\", \"" . $osis{lc($a)} . "\"},\t\t//" . $idmap{$osis{lc($a)}} . "\n";
}
$abbrevs .= "  {\"\", \"\"}\n};\n\n\n";

open OUTF, ">builtin_abbrevs.h";
print OUTF $abbrevs;
close OUTF;