Added sample_uuid, sample_lims methods to st::api::lims

Patched st::api::lims::samplesheet to allow for scalar attributes
ending with 's'. Previously the values of attributes with names
ending with 's' were automatically converted to lists. In fact,
this was necessary only for comma-separated strings of email addresses.
The part of code that deals with email addresses was changed to
work on attributes with names starting with 'email' rather than
ending with 's'. Prior to applying this patch the value of the
new sample_lims attribute was returned as a list when a samplesheet
was used as a source of LIMS data.

Updated tests and test data.

MANIFEST

@@ -661,6 +661,7 @@ t/data/run_params/runParameters.hiseqx.xml
 t/data/run_params/runParameters.miseq.xml
 t/data/run_params/RunParameters.novaseq.xp.lite.xml
 t/data/run_params/RunParameters.novaseqx.prod.xml
+t/data/samplesheet/data4merge.csv
 t/data/samplesheet/samplesheet_7753.csv
 t/data/samplesheet/samplesheet_27483.csv
 t/data/samplesheet/samplesheet_33990.csv

lib/st/api/lims.pm

@@ -118,6 +118,8 @@ Readonly::Hash   my  %METHODS_PER_CATEGORY => {
                       /],
 
     'sample'       => [qw/ sample_id
+                           sample_uuid
+                           sample_lims
                            sample_name
                            organism_taxon_id
                            organism

lib/st/api/lims/samplesheet.pm

@@ -315,7 +315,7 @@ for my $m ( st::api::lims->driver_method_list_short(__PACKAGE__->meta->get_attri
           if (defined $value && $value eq q[]) {
             $value = undef;
           }
-          if ($m =~ /s$/smx) {
+          if ($m =~ /^email_addresses/smx) {
             my @temp = $value ? split $SAMPLESHEET_ARRAY_SEPARATOR, $value : ();
             $value = \@temp;
           } elsif ($m eq 'required_insert_size_range') {

t/40-st-lims-ml_warehouse-drivers.t

@@ -140,7 +140,7 @@ qr/No record retrieved for st::api::lims::ml_warehouse\w* id_flowcell_lims 22043
 };
 
 subtest 'lane-level driver from run-level driver' => sub {
-  plan tests => 108;
+  plan tests => 124;
 
   my $count = 0;
         for my $p ($mlwh_d, $mlwh_auto_d, $mlwh_auto_d, $mlwh_alt_d) {
@@ -169,6 +169,8 @@ subtest 'lane-level driver from run-level driver' => sub {
   ok (!$d->study_name, 'no study name');
   ok (!$d->sample_id, 'no sample_id');
   ok (!$d->sample_supplier_name, 'no supplier name');
+  ok (!$d->sample_uuid, 'no sample uuid');
+  ok (!$d->sample_lims, 'no sample lims');
   ok (!$d->sample_cohort, 'no cohort');
   ok (!$d->sample_donor_id, 'no donor id');
   is ($d->default_tag_sequence, undef, 'first index sequence undefined');
@@ -184,6 +186,8 @@ subtest 'lane-level driver from run-level driver' => sub {
   ok(!$lims1->sample_consent_withdrawn(), 'sample consent not withdrawn');
   is ($lims1->sample_id, 7283, 'sample id');
   is ($lims1->sample_supplier_name, 'sample_33', 'supplier name');
+  is ($lims1->sample_uuid, 'fdb13110-6a55-11e4-8e19-68b59977951c', 'sample uuid');
+  is ($lims1->sample_lims, 'CLARITY', 'sample lims');
   is ($lims1->sample_cohort, 'plan2', 'cohort');
   is ($lims1->sample_donor_id, 'd5678', 'donor id');
   is ($lims1->purpose, 'qc', 'purpose');
@@ -276,7 +280,7 @@ sub _add2query {
 }
 
 subtest 'lane and tag level drivers' => sub {
-  plan tests => 136;
+  plan tests => 152;
 
   my $lims_id = 16249;
   my $id_run  = 45678;
@@ -323,6 +327,8 @@ subtest 'lane and tag level drivers' => sub {
   is (scalar $lims->children, 9, 'tag zero - nine-long children list');
   is ($lims->spiked_phix_tag_index, 168, 'spike index');
   ok (!$lims->sample_supplier_name, 'no supplier name');
+  ok (!$lims->sample_uuid, 'no sample uuid');
+  ok (!$lims->sample_lims, 'no sample lims'); 
   ok (!$lims->sample_cohort, 'no cohort');
   ok (!$lims->sample_donor_id, 'no donor id');
   is ($lims->default_tag_sequence, undef, 'first index sequence undefined');
@@ -340,6 +346,8 @@ subtest 'lane and tag level drivers' => sub {
   ok (!$lims->is_control, 'tag 2 is not control');
   is ($lims->sample_id, 1092803, 'sample id');
   is ($lims->sample_supplier_name, 'sample_33', 'supplier name');
+  is ($lims->sample_uuid, 'f44b2ec0-6f67-11e4-a268-68b59977951c', 'sample uuid');
+  is ($lims->sample_lims, 'SQSCP', 'sample lims');
   is ($lims->sample_cohort, 'plan1', 'cohort');
   is ($lims->sample_donor_id, '5678', 'donor id');
   is ($lims->default_tag_sequence, 'CGATGT', 'first index sequence');

t/40-st-lims-samplesheet.t

@@ -1,6 +1,6 @@
 use strict;
 use warnings;
-use Test::More tests => 11;
+use Test::More tests => 12;
 use Test::Exception;
 use Test::Warn;
 use File::Slurp;
@@ -397,4 +397,26 @@ subtest 'dual index default' => sub {
   is($p->default_tagtwo_sequence, undef, 'no second index');
 };
 
+subtest 'sample uuid and LIMS id' => sub {
+  plan tests => 10;
+
+  my $path = 't/data/samplesheet/4pool4libs_extended.csv';
+  my $ss = st::api::lims::samplesheet->new(id_run => 6946, position => 1, path => $path);
+  ok (!$ss->is_pool, 'lane 1 is not a pool'); 
+  is ($ss->sample_uuid, 'c46e1810-e8aa-11e2-aafd-68b59976a382', 'sample uuid');
+  is ($ss->sample_lims, 'SQSCP', 'sample lims');
+  $ss = st::api::lims::samplesheet->new(id_run => 6946, position => 6, path => $path);
+  ok ($ss->is_pool, 'lane 6 is a pool');
+  is ($ss->sample_uuid, undef, 'sample uuid is not defined');
+  is ($ss->sample_lims, undef, 'sample lims is not defined');
+  my @plexes = $ss->children();
+  is ($plexes[0]->sample_uuid, '62a06c60-2139-11e3-b2c2-68b59976a382',
+    'sample uuid for a plex');
+  is ($plexes[0]->sample_lims, 'SQSCP', 'sample lims for a plex');
+  $ss = st::api::lims::samplesheet->new(
+    id_run => 6946, position => 6, tag_index => 0, path => $path);
+  is ($ss->sample_uuid, undef, 'sample uuid is not defined');
+  is ($ss->sample_lims, undef, 'sample lims is not defined'); 
+};
+
 1;

t/40-st-lims.t

@@ -5,7 +5,7 @@ use Test::Exception;
 use Test::Warn;
 use Moose::Meta::Class;
 
-my $num_delegated_methods = 45;
+my $num_delegated_methods = 47;
 
 use_ok('st::api::lims');
 
@@ -133,7 +133,7 @@ subtest 'Setting return value for primary attributes' => sub {
 };
 
 subtest 'Run-level object via samplesheet driver' => sub {
-  plan tests => 36;
+  plan tests => 40;
 
   my $path = 't/data/samplesheet/miseq_default.csv';
 
@@ -176,6 +176,8 @@ subtest 'Run-level object via samplesheet driver' => sub {
   is ($plexes[0]->id_run, 10262, 'id_run of the first plexe set correctly from Experiment Name');
   is ($plexes[0]->library_id, 7583411, 'library_id of the first plex');
   is ($plexes[0]->sample_name, 'LIA_1', 'sample_name of the first plex');
+  is ($plexes[0]->sample_uuid, undef, 'sample_uuid of the first plex');
+  is ($plexes[0]->sample_lims, undef, 'sample_lims of the first plex');
   is ($plexes[0]->sample_id, undef, 'sample_id of the first plex in undefined');
   is ($plexes[0]->is_pool, 0, 'is_pool false on plex level');
   is ($plexes[0]->is_control, undef, 'is_control false on for a plex');
@@ -187,10 +189,12 @@ subtest 'Run-level object via samplesheet driver' => sub {
   is ($plexes[95]->tag_sequence, 'GTCTTGGC', 'tag sequence of the last plex');
   is ($plexes[95]->library_id, 7583506, 'library_id of the last plex');
   is ($plexes[95]->sample_name, 'LIA_96', 'sample_name of the last plex');
+  is ($plexes[95]->sample_uuid, undef, 'sample_uuid of the last plex');
+  is ($plexes[95]->sample_lims, undef, 'sample_lims of the last plex');
 };
 
 subtest 'Lane-level and tag zero objects via samplesheet driver' => sub {
-  plan tests => 20;
+  plan tests => 24;
 
   my $path = 't/data/samplesheet/miseq_default.csv';
 
@@ -217,13 +221,15 @@ subtest 'Lane-level and tag zero objects via samplesheet driver' => sub {
     is (scalar $ss->children, 96, '96 plexes returned');
     is ($ss->library_id, undef, 'library_id undefined');
     is ($ss->sample_name, undef, 'sample name is undefined');
+    is ($ss->sample_uuid, undef, 'sample uuid is undefined');
+    is ($ss->sample_lims, undef, 'sample lims is undefined');
     is ($ss->default_tag_sequence, undef, 'default tag sequence undefined');
     is ($ss->tag_sequence, undef, 'tag sequence undefined');
   }
 };
 
 subtest 'Plex-level objects via samplesheet driver' => sub {
-  plan tests => 10;
+  plan tests => 12;
 
   my $path = 't/data/samplesheet/miseq_default.csv';
   my $l;
@@ -244,6 +250,8 @@ subtest 'Plex-level objects via samplesheet driver' => sub {
     'tag sequence is the same as default tag sequence');
   is ($l->library_id, 7583413, 'library id is correct');
   is ($l->sample_name, 'LIA_3', 'sample name is correct');
+  is ($l->sample_uuid, undef, 'sample uuid is undefined');
+  is ($l->sample_lims, undef, 'sample lims is undefined');
   is (scalar $l->children, 0, 'zero children returned'); 
 };
 
@@ -284,7 +292,7 @@ subtest 'Samplesheet driver for a one-component composition' => sub {
 };
 
 subtest 'Samplesheet driver for arbitrary compositions' => sub {
-  plan tests => 75;
+  plan tests => 93;
 
   my $path = 't/data/samplesheet/novaseq_multirun.csv';
   local $ENV{NPG_CACHED_SAMPLESHEET_FILE} = $path;
@@ -305,6 +313,8 @@ subtest 'Samplesheet driver for arbitrary compositions' => sub {
     is($o->default_tagtwo_sequence, 'CCAACAGA', 'tag2 sequence');
     is($o->default_library_type, 'HiSeqX PCR free', 'library type');
     is($o->sample_name, '7592352', 'sample name');
+    is($o->sample_uuid, undef, 'sample uuid');
+    is($o->sample_lims, undef, 'sample lims');
     is($o->study_name, 'UK Study', 'study name');
     is($o->library_name, '22802061', 'library name');
     is($o->reference_genome, 'Homo_sapiens (GRCh38_15_plus_hs38d1) [minimap2]',
@@ -342,6 +352,28 @@ subtest 'Samplesheet driver for arbitrary compositions' => sub {
   is ($ss->id_run, 28780, 'correct run id');
   is ($ss->position, 2, 'correct position');
   is ($ss->tag_index, 4, 'correct tag_index');
+
+  $path = 't/data/samplesheet/data4merge.csv';
+  local $ENV{NPG_CACHED_SAMPLESHEET_FILE} = $path;
+
+  $rpt_list = '26480:1:9;26480:2:9';
+  $ss=st::api::lims->new(rpt_list => $rpt_list);
+  is ($ss->sample_uuid, '673165ec-f8c6-11e0-8838-68b59976a382',
+    'sample uuid for a composition');
+  is ($ss->sample_lims, 'CLARITY', 'sample lims for a composition');
+
+  $rpt_list = '26480:3:9;26480:4:9';
+  $ss=st::api::lims->new(rpt_list => $rpt_list);
+  is ($ss->sample_uuid, 'b6ea25f0-f8cc-11e0-8838-68b59976a382',
+    'sample uuid for a composition');
+  is ($ss->sample_lims, 'Traction', 'sample lims for a composition');
+
+  $rpt_list = '26480:1:9;26480:2:9;26480:3:9;26480:4:9';
+  $ss=st::api::lims->new(rpt_list => $rpt_list);
+  is ($ss->sample_uuid, undef, 'sample uuid for a composition is undefined ' .
+    'since the values for individual components differ');
+  is ($ss->sample_lims, undef, 'sample lims for a composition is undefined ' .
+    'since the values for individual components differ');
 };
 
 subtest 'Dual index' => sub {

t/data/fixtures_stlims_wh/000-Sample.yml

@@ -5,7 +5,7 @@
   created: 2009-07-01 16:23:00
   deleted_at: ~
   description: ~
-  id_lims: SQSCP
+  id_lims: CLARITY
   id_sample_lims: 7283
   cohort: plan2
   donor_id: d5678