- added find_aips_by_file_pronom_id()

- added logic to select aips by pronom id
- minor indent

lib/SLUB/LZA/TA/Command/search.pm

@@ -34,8 +34,6 @@ Examples:
     '$0 search -s copyrighted'
   * Which AIPs were modified in 2021-05-31?
     '$0 search -m 2021-05-31'
-    Which AIPs have at least one invalid file?
-    '$0 search --with-invalid-files'
   * Which AIPs with mkv-files are in archive?
     '$0 search --pronom-format=fmt/569'
 
@@ -97,7 +95,6 @@ sub opt_spec {
         [ 'with-slubarchiv-externalisilid' => 'also returns AIP slubarchiv-externalisilid'],
         [ 'with-slubarchiv-externalworkflow' => 'also returns AIP slubarchiv-externalworkflow'],
         [ 'with-slubarchiv-hasconservationreason' => 'also returns AIP slubarchiv-hasconservationreason'],
-        [ 'with-slubarchiv-lzaid' => 'also returns AIP slubarchiv-lzaid'],
         [ 'with-slubarchiv-lzaid|with-lzaid' => 'also returns lzaid' ],
         [ 'with-slubarchiv-migrated-aip|with-migrated-aip' => 'also returns AIP slubarchiv-migrated-aip'],
         [ 'with-slubarchiv-origin-ais|with-origin-ais' => 'also returns AIP slubarchiv-origin-ais'],
@@ -123,8 +120,6 @@ sub line_result_mapper {
     my ($partial_result, $opt) = @_;
     my %line;
     $line{aipid}= $partial_result->{_source}->{uuid};
-    p($partial_result->{_source});
-    p($opt);
     my @tmd = qw(
         External-Description
         External-Identifier
@@ -161,6 +156,67 @@ sub line_result_mapper {
     \%line;
 }
 
+sub find_aips_by_file_pronom_id {
+    my ($self, $opt, $args) = @_;
+    # index aipfiles needed
+    # find all AIPs where pronom-id like XXX
+    my $pronom_id = $opt->{pronom_id};
+    my $files_query = {
+        query     => {
+            bool => {
+                must =>
+                    [
+                        {
+                            match_phrase => {
+                                join(".", qw(
+                                    METS
+                                    amdSec
+                                    mets:amdSec_dict
+                                    mets:techMD_dict
+                                    mets:mdWrap_dict
+                                    mets:xmlData_dict
+                                    premis:object_dict
+                                    premis:objectCharacteristics_dict
+                                    premis:format_dict
+                                    premis:formatRegistry_dict
+                                    premis:formatRegistryKey
+                                )
+                                ) => "$pronom_id"
+                                #"METS.amdSec.mets:amdSec_dict.mets:techMD_dict.mets:mdWrap_dict.mets:xmlData_dict.premis:object_dict.premis:formatRegistry_dict.premis:formatRegistryKey" => "$pronom_id"
+                                #"premis:formatRegistryKey" => "$pronom_id"
+                            }
+                        }
+                    ],
+
+            }
+
+        },
+        "_source" => {
+            "includes" => 'AIPUUID'
+        }
+    };
+    my $files_response = SLUB::LZA::TA::Archivematica::Elasticsearch::query_elasticsearch(
+        $SLUB::LZA::TA::config{elasticsearchprotocol},
+        $SLUB::LZA::TA::config{elasticsearchhost},
+        $SLUB::LZA::TA::config{elasticsearchport},
+        'aipfiles',   # indexname
+        $files_query, # query_hash ref
+    );
+    if (exists $opt->{debug}) {
+        use Data::Printer;
+        say "------------------------";
+        say "query=",np( $files_query);
+        say "------------------------";
+    }
+    my %aips;
+    #p($files_response->{hits}->{hits});
+    foreach my $match (@{$files_response->{hits}->{hits}}) {
+        my $aip = $match->{_source}->{AIPUUID};
+        $aips{$aip} = 1;
+    }
+    return keys %aips;
+}
+
 sub execute {
     my ($self, $opt, $args) = @_;
     if ($opt->{target_version}) {
@@ -169,56 +225,77 @@ sub execute {
             $SLUB::LZA::TA::config{elasticsearchhost},
             $SLUB::LZA::TA::config{elasticsearchport}
         );
-        exit (0);
+        exit(0);
+    }
+    my $aips_query;
+    my $aips_response;
+    #p($opt);
+    if ($opt->{format} eq 'pronom_id') {
+        $aips_query = SLUB::LZA::TA::Archivematica::Elasticsearch::prepare_query($opt);
+        # replace AIP query with all match
+        my @aips = find_aips_by_file_pronom_id(@_);
+        $aips_query->{query}->{bool}->{must}->{terms}->{uuid} = \@aips;
+    } else {
+        # only index aips needed
+        $aips_query = SLUB::LZA::TA::Archivematica::Elasticsearch::prepare_query($opt);
     }
-    my $query = SLUB::LZA::TA::Archivematica::Elasticsearch::prepare_query($opt);
-    my $response = SLUB::LZA::TA::Archivematica::Elasticsearch::query_elasticsearch(
+    if (exists $opt->{debug}) {
+        use Data::Printer;
+        say "------------------------";
+        say "query=",np( $aips_query);
+        say "------------------------";
+    }
+    #p($aips_query);
+    $aips_response = SLUB::LZA::TA::Archivematica::Elasticsearch::query_elasticsearch(
         $SLUB::LZA::TA::config{elasticsearchprotocol},
         $SLUB::LZA::TA::config{elasticsearchhost},
         $SLUB::LZA::TA::config{elasticsearchport},
-        'aips', # indexname
-        $query, # query_hash ref
+        'aips',      # indexname
+        $aips_query, # query_hash ref
     );
 
     my @result = map {
         line_result_mapper($_, $opt);
-    } @{$response->{hits}->{hits} };
+    } @{$aips_response->{hits}->{hits}};
     my @headers = sort keys %{$result[0]};
-    my $aip_only = List::Util::none {$_ =~ m/^with/} keys %{ $opt };
+    my $aip_only = List::Util::none {$_ =~ m/^with/} keys %{$opt};
     if (!exists $opt->{output_format}) {
         if ($aip_only) {
             $opt->{output_format} = 'output_as_csv'
-        } else {
+        }
+        else {
             $opt->{output_format} = 'output_as_rsv';
         }
     }
 
     if ($opt->{output_format} eq 'output_as_csv') {
         binmode(STDOUT, ':encoding(UTF-8)');
-            say join(",", @headers);
-            say join("\n", map {
-                my $line = $_;
-                my $res_line = join(
-                    ",",
-                    map { $line->{$_} } @headers
-                );
-                $res_line;
-            } @result
+        say join(",", @headers);
+        say join("\n", map {
+            my $line = $_;
+            my $res_line = join(
+                ",",
+                map {$line->{$_}} @headers
             );
-    } elsif ($opt->{output_format} eq 'output_as_rsv') {
-            binmode(STDOUT, ':bytes');
-            print join(CHR_VALUE_TERMINATOR, @headers).CHR_VALUE_TERMINATOR;
-            print CHR_ROW_TERMINATOR;
-            print join("", map {
-                my $line = $_;
-                my $res_line = join("", map { $line->{$_}.CHR_VALUE_TERMINATOR } @headers
-                );
-                $res_line.CHR_ROW_TERMINATOR;
-            } @result
+            $res_line;
+        } @result
+        );
+    }
+    elsif ($opt->{output_format} eq 'output_as_rsv') {
+        binmode(STDOUT, ':bytes');
+        print join(CHR_VALUE_TERMINATOR, @headers) . CHR_VALUE_TERMINATOR;
+        print CHR_ROW_TERMINATOR;
+        print join("", map {
+            my $line = $_;
+            my $res_line = join("", map {$line->{$_} . CHR_VALUE_TERMINATOR} @headers
             );
-            binmode(STDOUT, ':encoding(UTF-8)');
-    } elsif ($opt->{output_format} eq 'output_as_raw') {
-        say np($response);
+            $res_line . CHR_ROW_TERMINATOR;
+        } @result
+        );
+        binmode(STDOUT, ':encoding(UTF-8)');
+    }
+    elsif ($opt->{output_format} eq 'output_as_raw') {
+        say np($aips_response);
     }
     return 1;
 }