Changeset 32159 for main/trunk/greenstone2

Timestamp:

2018-03-13T15:59:21+13:00 (6 years ago)

Author:

ak19

Message:

incremental building was not being incremental when no metadata was assigned to any of the files (as happens with our docs for quick test collections). A default metadata.xml is present, but 'empty' in that it contains no FileSet elements with metadata elements assigned to FileName elements. But we still want incremental behaviour. The idea was to write out an entry into archiveinf-src.db for each metadata.xml processed, not just for each meta.xml file actually referencing a doc, as BasePlugout was doing so far on a per doc basis. Kathy come up with the actual infrastructure that can make it work (to ensure all the necessary objects are available), Dr Bainbridge approved this, and it's now been added into the code.

Location:

main/trunk/greenstone2/perllib

Files:

• plugins/MetadataXMLPlugin.pm (modified) (2 diffs)
• plugouts/BasePlugout.pm (modified) (2 diffs)

main/trunk/greenstone2/perllib/plugins/MetadataXMLPlugin.pm

@@ -252 +252 @@
     $self->{'metadata-file'} = $file;
     $self->{'metadata-filename'} = $filename;
-    
+    
     my $outhandle = $self->{'outhandle'};
     
     print STDERR "\n<Processing n='$file' p='MetadataXMLPlugin'>\n" if ($gli);
     print $outhandle "MetadataXMLPlugin: processing $file\n" if ($self->{'verbosity'})> 1;
+
+    # In order to prevent blind reprocessing of the same old docs upon *incremental* building
+    # whenever we encounter a default empty metadata.xml that has no content defined (attaches
+    # no meta), we write an entry for *each* metadata.xml into archiveinf-src.db
+    print $outhandle "MetadataXMLPlugin: writing an entry for this metadata.xml into archiveinf-src.db\n" if ($self->{'verbosity'})> 1;
+    $processor->add_metaxml_file_entry_to_archiveinfsrc($filename); # pass in the full filename, like BasePlugout::archiveinf_db() does
+
+    
     # add the file to the block list so that it won't be processed in read, as we will do all we can with it here
     $self->block_raw_filename($block_hash,$filename);
@@ -277 +285 @@
     return -1; #error
     }
-
+    
     return 1;
 

main/trunk/greenstone2/perllib/plugouts/BasePlugout.pm

@@ -1001 +1001 @@
     }  
 
-    # meta files not set in reverese entry, but need to set the metadata flag
+    # meta files not set in reverse entry, but need to set the metadata flag
     if (defined $doc_obj->get_meta_files()) {
     foreach my $meta_file_rec(@{$doc_obj->get_meta_files()}) {
@@ -1008 +1008 @@
     }
     }
+}
+
+# This sub is called for every metadata.xml accepted for processing by by MetdataXMLPlugin
+# and adds an entry into archiveinf-src.db for that file in the form:
+#   [@THISCOLLECTPATH@/import/metadata.xml]
+#   <meta-file>1
+# This prevents blind reprocessing of the same old docs upon *incremental* building whenever
+# we encounter a default empty metadata.xml that has no actual <FileSet> content defined.
+sub add_metaxml_file_entry_to_archiveinfsrc {
+    my $self = shift (@_);
+    my ($full_file) = @_;
+    
+    print STDERR "**** Adding metaxml file entry for full_file: $full_file\n";
+    my $working_info = $self->{'output_info'};
+    $working_info->set_meta_file_flag($full_file);
 }