)?(?:
# later publication: id=$16
# Is a later publication: id=$18
my(@refs)=($2,$5,$8,$11,$13,$16,$18);
- $rec{"refs"}=[];
while (@refs) {
push(@{$rec{"refs"}},$_) if defined ($_=shift @refs);
}
+ $score+=+10 if defined $5; # basionym: id=$5
+ $score+=-10 if defined $13; # Is a basionym: id=$13
+ $score+=- 4 if defined $16; # later publication: id=$16
+ $score+=+ 4 if defined $18; # Is a later publication: id=$18
}
+ $score+=+9 if $rec{"Publ. Author"}=~/^\s*\(/;
+ $rec{"score"}=$score;
if ($attrsbody) {
failed($file);
return;
@@ -180,18 +147,15 @@ my( $entry )=@_;
process_file($entry) if -f $entry;
}
-%OWNS=();
-
foreach (@ARGV)
{ process_entry($_); }
-my($id);
-for $id (keys %DB) {
+for my $id (keys %DB) {
my($refid);
my(@refs);
for $refid (@{$DB{$id}{"refs"}}) {
if (!exists $DB{$refid}) {
- warn "Undefined ref id \"$refid\" from id \"$id\"" if $D;
+ print "Undefined ref id \"$refid\" from id \"$id\"\n" if $D>=1;
next;
}
next if $id eq $refid; # self-ref
@@ -201,127 +165,95 @@ for $id (keys %DB) {
$DB{$id}{"refs"}=\@refs;
}
-print Data::Dumper->Dump([\%DB],["%DB"]) if $D;
+print Data::Dumper->Dump([\%DB],["%DB"]) if $D>=2;
-%OWNS=map { $_=>[] } keys(%DB);
+my %OWNS=map { $_=>$DB{$_}{"refs"}; } keys(%DB);
+my %NAMES=();
-for $id (keys %OWNS) {
- my($refid);
- for $refid (@{$DB{$id}{"refs"}}) {
+for my $id (keys %DB) {
+ $NAMES{$DB{$id}{"name"}}=[] if !exists $NAMES{$DB{$id}{"name"}};
+ push @{$NAMES{$DB{$id}{"name"}}},$id;
+ }
+
+for my $id (keys %DB) {
+ next if !exists $OWNS{$id};
+ my @queue=($id,@{$OWNS{$id}});
+ $OWNS{$id}=[];
+ while (my $refid=shift @queue) {
+ if (exists $NAMES{$DB{$refid}{"name"}}) {
+ push(@queue,@{$NAMES{$DB{$refid}{"name"}}});
+ delete $NAMES{$DB{$refid}{"name"}};
+ }
+ next if $refid eq $id;
next if !exists $OWNS{$refid};
- push(@{$OWNS{$id}},$refid,@{$OWNS{$refid}});
+ push @queue,@{$OWNS{$refid}};
delete $OWNS{$refid};
+ print "processed connect id=$id <- refid=$refid\n" if $D>=1;
+ push @{$OWNS{$id}},$refid;
}
}
-print Data::Dumper->Dump([\%OWNS],["%OWNS"]) if $D;
-
-#foreach $key (keys %DB) {
-# $DB{$key}{"Publication"}=extract_year($DB{$key}{"Publication"})." ::: ".$DB{$key}{"Publication"}
-# if (exists($DB{$key}{"Publication"}));
-# }
+print Data::Dumper->Dump([\%OWNS],["%OWNS"]) if $D>=2;
foreach $key (keys %OWNS) {
my(@keys)=@{$OWNS{$key}};
delete($OWNS{$key});
unshift(@keys,$key);
- @keys=sort { extract_year($DB{$b}{"Publication"}) <=> extract_year($DB{$a}{"Publication"}); } @keys;
+# @keys=sort { $DB{$a}{"score"} <=> $DB{$b}{"score"}
+# || extract_year($DB{$b}{"Publication"}) <=> extract_year($DB{$a}{"Publication"}); } @keys;
+ @keys=sort { $DB{$a}{"name"} cmp $DB{$b}{"name"}; } @keys;
my($pkey)=shift(@keys);
$OWNS{$pkey}=\@keys;
}
-sub print_header
-{
-my($header)=@_;
-
- print OUT
-"
-
-
-Kewensis $header
-
-
-
-
-\n";
-}
+my($db_driver,$db_host,$db_user,$db_pwd,$DB_PWD,$db_name,$db);
+my($tb_tree);
-sub OUT_flush
-{
- print OUT "\n";
- close(OUT);
-}
+$db_driver="mysql";
+$db_host="";
+$db_user="short";
+#$DB_PWD=$ENV{"HOME"}."/priv/mysql.${db_user}.pwd";
+$db_pwd="short";
+$db_name="short";
+$tb_tree="kewensis_tree";
-if (defined $maxsize) {
- my($fileno)=-1;
- my($filename,$fileid);
- foreach $owner (sort keys %OWNS) {
- my( $child );
-
- if ($fileno<0 || tell(OUT)>=$maxsize) {
- OUT_flush() if ($fileno>=0);
- $fileid=sprintf("%04d",++$fileno);
- $filename="kew-$fileid.html";
- open(OUT,">$filename") or die "Cannot open \"$filename\": $!";
- print_header("chunk $fileid");
- }
-
- if ($debugmatch) {
- print STDERR "($owner):";
- foreach $child (@{$OWNS{$owner}})
- { print STDERR " ($child)"; }
- print STDERR "\n";
- }
- print OUT format_record("","
\n",%{$DB{$owner}});
- if (@{$OWNS{$owner}}) {
- print OUT "\n";
- foreach $child (@{$OWNS{$owner}})
- { print OUT format_record("","
\n",%{$DB{$child}}); }
- print OUT "
\n";
- }
- print OUT "\n";
- $DB{$owner}{"_filename"}=$filename;
- }
- OUT_flush();
- open(OUT,">kew-index.html") or die "Cannot open \"kew-index.html\": $!";
- print_header("Index");
- }
-else {
- open(OUT,">kewensis.html") or die "Cannot open \"kewensis.html\": $!";
- print_header("Full");
- }
+$db=DBI->connect("DBI:$db_driver:database=$db_name;host=$db_host",$db_user,$db_pwd) or die "Database open fail: $!";
-sub format_href
+sub db_do
{
-my($preinsert,$postinsert,%rec)=@_;
+my( $cmd )=@_;
- return htmlquote(rec_to_name(%rec));
+ $db->do($cmd) or die("SQL command \"$cmd\" failed: $!");
}
-my($printrecref)=(defined $maxsize ? \&format_href : \&format_record );
-
-foreach $owner (sort keys %OWNS) {
-my( $child );
-
- print OUT "";
- print OUT "" if defined $maxsize;
- print OUT &{$printrecref}("","",%{$DB{$owner}});
- print OUT "" if defined $maxsize;
- print OUT "
";
- if (@{$OWNS{$owner}}) {
- print OUT "\n";
- foreach $child (@{$OWNS{$owner}}) {
- print OUT "- ";
- print OUT &{$printrecref}("","",%{$DB{$child}});
- print OUT "
\n";
- }
- print OUT "
";
+eval { &db_do("drop table $tb_tree") };
+
+&db_do("create table $tb_tree ("
+ ."id char(10) not null,"
+ ."family_id char(10) not null,"
+ ."family_order int not null,"
+ ."name varchar(100) not null,"
+ ."PublAuthor text null,"
+ ."Publication text null,"
+ ."html text null"
+ .")");
+
+&db_do("alter table $tb_tree add unique (id)");
+&db_do("alter table $tb_tree add index (name)");
+&db_do("alter table $tb_tree add unique (family_id,family_order)");
+
+my $insert_tb_tree=$db->prepare("insert into $tb_tree (id,family_id,family_order,name,PublAuthor,Publication,html) values (?,?,?,?,?,?,?)")
+ or die "Prepare fail: $!";
+
+foreach $owner (sort { $DB{$b}{"name"} cmp $DB{$a}{"name"}; } keys %OWNS) {
+ my @family=@{$OWNS{$owner}};
+ unshift(@family,$owner);
+ my $family_id=$DB{$owner}{"id"};
+ for my $family_order (0..$#family) {
+ my $id=$family[$family_order];
+ print "insert:$id,".$DB{$id}{"name"}."\n" if $D>=2;
+ $insert_tb_tree->execute($id,$family_id,$family_order,
+ $DB{$id}{"name"},$DB{$id}{"Publ. Author"},$DB{$id}{"Publication"},$DB{$id}{"html"}
+ ) or die "SQL insert failure: $!";
}
- print OUT "\n";
}
-OUT_flush();