added \cl handling

improved \qr, \qs handling
trimmed lots of extraneous whitespace


git-svn-id: https://www.crosswire.org/svn/sword-tools/trunk@220 07627401-56e2-0310-80f4-f8cd0041bdcd

1 files changed, 20 insertions, 12 deletions

diff --git a/modules/perlconverters/usfm2osis.pl b/modules/perlconverters/usfm2osis.pl
index 97e7d77..af8fc04 100644
--- a/modules/perlconverters/usfm2osis.pl
+++ b/modules/perlconverters/usfm2osis.pl
@@ -4,7 +4,7 @@
 
 ## Licensed under the standard BSD license:
 
-# Copyright (c) 2002-2008 CrossWire Bible Society <http://www.crosswire.org/>
+# Copyright (c) 2002-2009 CrossWire Bible Society <http://www.crosswire.org/>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -40,12 +40,12 @@
 #########################################################################
 
 # Stores the script version and date
-$version = "1.6";
-$date = "2009-08-29";
+$version = "1.7";
+$date = "2009-10-26";
 # Sets the version of OSIS used in the OSIS header
 $osisVersion = "2.1.1";
 # Stores the USFM Version
-$usfmVersion = "2.1"; # The USFM reference document can be found at http://confluence.ubs-icap.org/display/USFM/Home;jsessionid=97071C5C1E562036A1CAF4FF77147565 (as of 2008-07-07)
+$usfmVersion = "2.2"; # The USFM reference document can be found at http://www.ubs-icap.org/chm/usfm/2.2/ (as of 2009-10-26)
 
 # This is the hash which maps the conversion of USFM book abbreviations to OSIS book abbreviations. ***I would like to add the ability to access an external file to provide options for other languages. In other words, in preparing a USFM file for conversion, a separate file could be created which could be used to map the conversion of abbreviated book names in other languages to OSIS. This would be especially useful for cross-references, but I haven't figured out how to do it yet.
 %OSISbook = (
@@ -189,6 +189,10 @@ foreach $file (@files) {
     for ($i = 0; $i < scalar(@filedata); $i++) {
 	$line = @filedata[$i];
 	$line =~ s/[\r\n]//g;
+	
+	### Trim leading/trailing whitespace
+	$line =~ s/\s*$//;
+	$line =~ s/^\s*//;
 
 	### Basic XML entity encoding
 	$line =~ s/&(?![a-zA-Z0-9])/&amp;/g;
@@ -425,8 +429,8 @@ foreach $file (@files) {
 	}
 
 
-	### Chapters and Verses--Markers Supported: \c, \v, \vp...\vp*
-	#### Markers Not Yet Supported: \ca...\ca*, \cl, \cp, \cd, \va...\va*
+	### Chapters and Verses--Markers Supported: \c, \v, \vp...\vp*, \cl
+	#### Markers Not Yet Supported: \ca...\ca*, \cp, \cd, \va...\va*
 
 	# \c chapter
 	if ($line =~ /^\\c\b\s*([^ ]*)/) {
@@ -452,6 +456,11 @@ foreach $file (@files) {
 	    $line =~ s/\\c\b\s*([^ ]*)//;
 	}
 
+	# \cl chapter label
+	if ($line =~ /^\\cl\b\s*(.*)/) {
+	    $line = "<title>$1<\/title>";
+	}
+
 	# \v verse
 	if ($line =~ /^\\v\b\s*(\d[^\\ ]*)?/) {
 	    if ($1 ne "") {
@@ -540,7 +549,7 @@ foreach $file (@files) {
 	# \qac...\qac*, acrostic character style (used within a line)
 	$line =~ s/\\qac\b\s*(.*?)\\qac\*/<hi type="acrostic">$1<\/hi>/g;	
 	
-	# \q line
+	# \q line (including \q#, \qr, \qc, and \qs...\qs*)
 	if ($line =~ /^\\q/) {
 	    if ($l != 1) {
 		push (@outdata, "<lg>\n");
@@ -569,16 +578,15 @@ foreach $file (@files) {
 		$line =~ s/\\q\b\s*(.+)/<l>$1<\/l>/;
 		$line =~ s/\\qm?(\d+)\b\s*(.+)/<l level=\"$1\">$2<\/l>/;
 		$line =~ s/\\qc\b\s*(.+)/<l type=\"x-centered\">$1<\/l>/;
-		if (@filedata[$i+1] !~ /\\q(?!t)/) {
+		$line =~ s/\\qr\b\s*(.+)/<l type=\"x-right\">$1<\/l>/;
+		$line =~ s/\\qs\b\s*(.+?)\s*\\qs\*/<l type="selah">$1<\/l>/;
+		if (@filedata[$i+1] !~ /\\q(?![ta])/) {
 		    $line .= "\n<\/lg>";
 		    $l = 0;
 		}
 	    }
 	}
 
-	# \qs...\qs*, Selah
-	$line =~ s/\\qs\b\s*([^\\]+)\\qs\*/<l type="selah"> $1<\/l>/;
-
 	### Tables--Markers Supported: \tr, \th#, \tc#, \tcr#
 	####Markers Not Yet Supported: \thr#
 
@@ -696,7 +704,7 @@ foreach $file (@files) {
 	    $note =~ s/\\ft\*//g;
 
 	    # \f* Footnote closer
-	    $note =~ s/\\f\*//;
+	    $note =~ s/\s*\\f\*//;
 
 	    # \f Footnote opener
 	    $note =~ s/\\f\b\s*([^\s]\s*)?//;