Merge pull request #1141 from tripal/1040-tv3-gff3_performance

Much improved GFF3 loader
tripal · Jan 4, 2021 · 35885f1 · 35885f1
2 parents 95e3d45 + a4be52d
commit 35885f1
Show file tree

Hide file tree

Showing 32 changed files with 5,002 additions and 1,937 deletions.
diff --git a/docs/user_guide/example_genomics/genomes_genes.rst b/docs/user_guide/example_genomics/genomes_genes.rst
@@ -39,27 +39,54 @@ You should see output similar to the following:
 
 ::
 
-  Tripal Job Launcher
-  Running as user 'administrator'
-  -------------------
-  2018-06-29 18:00:50: There are 1 jobs queued.
-  2018-06-29 18:00:50: Job ID 8.
-  2018-06-29 18:00:50: Calling: tripal_run_importer(12)
-
-  Running 'Chado GFF3 File Loader' importer
-  NOTE: Loading of file is performed using a database transaction.
-  If it fails or is terminated prematurely then all insertions and
-  updates are rolled back and will not be found in the database
-
-  Opening /var/www/html/sites/default/files/tripal/users/1/Citrus_sinensis-orange1.1g015632m.g.gff3
-  Percent complete: 100.00%. Memory: 32,211,360 bytes.
-  Adding protein sequences if CDS exist and no proteins in GFF...
-  Setting ranks of children...
-
-  Done.
+    2020-10-02 21:53:18
+    Tripal Job Launcher
+    Running as user 'admin'
+    -------------------
+    2020-10-02 21:53:18: There are 1 jobs queued.
+    2020-10-02 21:53:18: Job ID 1310.
+    2020-10-02 21:53:18: Calling: tripal_run_importer(123)
+
+    Running 'Chado GFF3 File Loader' importer
+    NOTE: Loading of file is performed using a database transaction.
+    If it fails or is terminated prematurely then all insertions and
+    updates are rolled back and will not be found in the database
+
+    Opening /var/www/html/sites/default/files/tripal/users/1/Citrus_sinensis-orange1.1g015632m.g.gff3
+    Opening temporary cache file: /tmp/TripalGFF3Import_aUgoru
+    Step  1 of 26: Caching GFF3 file...
+    Step  2 of 26: Find existing landmarks...
+    Step  3 of 26: Insert new landmarks (if needed)...
+    Step  4 of 26: Find missing proteins...
+    Step  5 of 26: Add missing proteins to list of features...
+    Step  6 of 26: Find existing features...
+    Step  7 of 26: Clear attributes of existing features...
+    Step  8 of 26: Processing 135 features...
+    Step  9 of 26: Get new feature IDs...
+    Step 10 of 26: Insert locations...
+    Step 11 of 26: Associate parents and children...
+    Step 12 of 26: Calculate child ranks...
+    Step 13 of 26: Add child-parent relationships...
+    Step 14 of 26: Insert properties...
+    Step 15 of 26: Find synonyms (aliases)...
+    Step 16 of 26: Insert new synonyms (aliases)...
+    Step 17 of 26: Insert feature synonyms (aliases)...
+    Step 18 of 26: Find cross references...
+    Step 19 of 26: Insert new cross references...
+    Step 20 of 26: Get new cross references IDs...
+    Step 21 of 26: Insert feature cross references...
+    Step 22 of 26: Insert feature ontology terms...
+    Step 23 of 26: Insert 'derives_from' relationships...
+    Step 24 of 26: Insert Targets...
+    Step 25 of 26: Associate features with analysis....              
+    Step 26 of 26: Adding sequences data (Skipped: none available)...
+
+    Done.
+    Committing Transaction...
+
+    Remapping Chado Controlled vocabularies to Tripal Terms...
+    Done.
 
-  Remapping Chado Controlled vocabularies to Tripal Terms...
-  Done.
 
 .. note::
 

diff --git a/legacy/tripal_feature/tripal_feature.module b/legacy/tripal_feature/tripal_feature.module
@@ -307,8 +307,7 @@ function tripal_feature_theme($existing, $type, $theme, $path) {
   return $items;
 }
 /**
- * Implements hook_job_describe_args() in order to describe the various feature jobs
- * to the tripal jobs interface.
+ * Implements hook_job_describe_args()
  *
  * @ingroup tripal_legacy_feature
  */

diff --git a/legacy/tripal_pub/tripal_pub.module b/legacy/tripal_pub/tripal_pub.module
@@ -305,9 +305,6 @@ function tripal_pub_form_alter(&$form, &$form_state, $form_id) {
 /**
  * Implements hook_job_describe_args().
  *
- * @param $callback
- * @param $args
- *
  * @ingroup tripal_legacy_pub
  */
 function tripal_pub_job_describe_args($callback, $args) {

diff --git a/tests/tripal_chado/data/empty_landmarks.fasta b/tests/tripal_chado/data/empty_landmarks.fasta
@@ -0,0 +1,41 @@
+>Contig10036
+
+>Contig1
+
+>Contig0
+
+>Contig100
+
+>Contig10022
+
+>Contig10023
+
+>Contig10035
+
+>Contig1001
+
+>Contig10012
+
+>Contig1002
+
+>Contig10026
+
+>Contig10018
+
+>Contig1003
+
+>Contig10030
+
+>Contig10
+
+>Contig10011
+
+>Contig10005
+
+>Contig10002
+
+>Contig1000
+
+>Contig10000
+
+>Contig10001
diff --git a/tests/tripal_chado/data/gff_duplicate_ids.gff b/tests/tripal_chado/data/gff_duplicate_ids.gff
diff --git a/tests/tripal_chado/data/gff_invalidstartend.gff b/tests/tripal_chado/data/gff_invalidstartend.gff
@@ -0,0 +1,4 @@
+##gff-version 3
+Contig0	FRAEX38873_v2	gene	44054	16315	.	+	.	ID=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010;biotype=protein_coding
+Contig0	FRAEX38873_v2	mRNA	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010.1;Parent=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010.1;biotype=protein_coding;AED=0.05
+Contig0	FRAEX38873_v2	polypeptide	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010.1.3_test_protein;Parent=FRAEX38873_v2_000000010.1
diff --git a/tests/tripal_chado/data/gff_phase.gff b/tests/tripal_chado/data/gff_phase.gff
@@ -0,0 +1,6 @@
+##gff-version 3
+Contig0	FRAEX38873_v2	gene	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010;biotype=protein_coding
+Contig0	FRAEX38873_v2	mRNA	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010.1;Parent=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010.1;biotype=protein_coding;AED=0.05
+Contig0	FRAEX38873_v2	five_prime_UTR	16315	16557	.	+	.	ID=FRAEX38873_v2_000000010.1.5utr1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	exon	16315	16967	.	+	.	ID=FRAEX38873_v2_000000010.1.exon1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	CDS	16558	16967	.	+	1	ID=FRAEX38873_v2_000000010.1.cds1;Parent=FRAEX38873_v2_000000010.1
diff --git a/tests/tripal_chado/data/gff_phase_invalid_character.gff b/tests/tripal_chado/data/gff_phase_invalid_character.gff
@@ -0,0 +1,6 @@
+##gff-version 3
+Contig0	FRAEX38873_v2	gene	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010;biotype=protein_coding
+Contig0	FRAEX38873_v2	mRNA	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010.1;Parent=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010.1;biotype=protein_coding;AED=0.05
+Contig0	FRAEX38873_v2	five_prime_UTR	16315	16557	.	+	.	ID=FRAEX38873_v2_000000010.1.5utr1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	exon	16315	16967	.	+	.	ID=FRAEX38873_v2_000000010.1.exon1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	CDS	16558	16967	.	+	a	ID=FRAEX38873_v2_000000010.1.cds1;Parent=FRAEX38873_v2_000000010.1
diff --git a/tests/tripal_chado/data/gff_phase_invalid_number.gff b/tests/tripal_chado/data/gff_phase_invalid_number.gff
@@ -0,0 +1,6 @@
+##gff-version 3
+Contig0	FRAEX38873_v2	gene	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010;biotype=protein_coding
+Contig0	FRAEX38873_v2	mRNA	16315	44054	.	+	.	ID=FRAEX38873_v2_000000010.1;Parent=FRAEX38873_v2_000000010;Name=FRAEX38873_v2_000000010.1;biotype=protein_coding;AED=0.05
+Contig0	FRAEX38873_v2	five_prime_UTR	16315	16557	.	+	.	ID=FRAEX38873_v2_000000010.1.5utr1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	exon	16315	16967	.	+	.	ID=FRAEX38873_v2_000000010.1.exon1;Parent=FRAEX38873_v2_000000010.1
+Contig0	FRAEX38873_v2	CDS	16558	16967	.	+	3	ID=FRAEX38873_v2_000000010.1.cds1;Parent=FRAEX38873_v2_000000010.1