updated branches to HEAD

git-svn-id: file:///home/dpavlin/private/svn/webpac/branches/hidra@303 13eb9ef6-21d5-0310-b721-a9d68796d827

diff --git a/all2xml.pl b/all2xml.pl
index 0ffee07..860560b 100755 (executable)
--- a/all2xml.pl
+++ b/all2xml.pl
@@ -17,6 +17,7 @@ $|=1;
 
 my $config_file = $0;
 $config_file =~ s/\.pl$/.conf/;
+$config_file = $ARGV[0] if (-f $ARGV[0]);
 die "FATAL: can't find configuration file '$config_file'" if (! -e $config_file);
 
 my $config;
@@ -918,6 +919,10 @@ __END__
 
 all2xml.pl - read various file formats and dump XML for SWISH-E
 
+=head1 SYNOPSYS
+
+ $ all2xml.pl [test.conf]
+
 =head1 DESCRIPTION
 
 This command will read ISIS data file using OpenIsis perl module, MARC
@@ -926,6 +931,9 @@ create one XML file for usage with I<SWISH-E> indexer. Dispite it's name,
 this script B<isn't general xml generator> from isis files (isis allready
 has something like that). Output of this script is tailor-made for SWISH-E.
 
+If no configuration file is specified, it will use default one called
+C<all2xml.conf>.
+
 =head1 BUGS
 
 Documentation is really lacking. However, in true Open Source spirit, source

diff --git a/doc/exact_match.txt b/doc/exact_match.txt
index d749552..2dbb277 100644 (file)
--- a/doc/exact_match.txt
+++ b/doc/exact_match.txt
@@ -27,3 +27,30 @@ on TitleAndResponsibility, you would use:
 <input type="text" name="v1">
 <input type="hidden" name="e1" value="5">
 
+
+What are bit-masks?
+
+Bit-mask is usage of one byte (8 bits) as 8 separate bits with it's own
+meaning (this is simplification, but bear with me for now).
+
+So, 1 = 2^0, thus it's bit 1. With analogy, 2=2^1 and 3=2^0+2^1. 
+So, for 1-3 we use two bits and have:
+
+number bits
+1      01      (just begin bit set)
+2      10      (just end bit set)
+3      11      (begin and end bit set)
+
+Thus, with two bits (and values 1-3) we can express should we exact match from
+beginning, end or both. For wild-card match, we use additional bit 3 (2^3 = 4)
+so we have:
+
+number bits    exact match
+1      001     begin
+2      010     end
+3      011     begin+end
+4      100     (not used)
+5      101     (4+1) begin+wild-card
+6      110     (4+2) end+wild-card
+7      111     (4+3) begin+end+wild-card
+

diff --git a/parse_format.pm b/parse_format.pm
index d12a94c..e5b23a6 100644 (file)
--- a/parse_format.pm
+++ b/parse_format.pm
@@ -224,7 +224,7 @@ sub parse_excel_format {
                } elsif ($format =~ s/^([^A-Z\|]+)(\|[A-Z]{1,2}\|)/$2/) {
                        $prefix .= $1 if ($display);
                } else {
-                       print STDERR "unparsed format: $format\n";
+                       #print STDERR "unparsed format: $format\n";
                        $prefix .= $format;
                        $format = "";
                }