no more unexpecteds

project.Makefile

@@ -112,7 +112,7 @@ local/with_shuttles_yq.yaml: local/with_shuttles.yaml
 	yq -i '(.classes.[].slot_usage.[] | select(.name=="chem_administration") | .examples) = [{"value": "agar [CHEBI:2509];2018-05-11|agar [CHEBI:2509];2018-05-22"}, {"value": "agar [CHEBI:2509];2018-05"}]' $@
 
 # use yq to add patterns with a secondary condition like mutivalued
-	yq -i '(.classes.[].slot_usage.[] | select(.range == "GeolocationValue")  | .pattern) = "^[-+]?([1-8]?\d(\.\d+)?|90(\.0+)?)\s[-+]?(180(\.0+)?|((1[0-7]\d)|([1-9]?\d))(\.\d+)?)$$"' $@
+	yq -i '(.classes.[].slot_usage.[] | select(.range == "GeolocationValue")  | .pattern) = "^[-+]?([1-8]?\d(\.\d{1,8})?|90(\.0{1,8})?)\s[-+]?(180(\.0{1,8})?|((1[0-7]\d)|([1-9]?\d))(\.\d{1,8})?)$$"' $@
 	yq -i '(.classes.[].slot_usage.[] | select(.range == "GeolocationValue")  | .range) = "string"' $@
 
 	yq -i '(.classes.[].slot_usage.[] | select(.range == "QuantityValue") | .pattern) = "^[-+]?[0-9]*\.?[0-9]+ +\S.*$$"' $@
@@ -209,6 +209,8 @@ local/nmdc.yaml
 
 src/nmdc_submission_schema/schema/nmdc_submission_schema.yaml: local/with_modifications.yaml project/thirdparty/GoldEcosystemTree.json
 	$(RUN) inject-gold-pathway-terms -g $(word 2,$^) -i $< -o $@
+	#cp $< $@
+
 # remove the multivalued true annotation from these gloabl slot definitions for the sake of linkml-convert
 #   esp to tsv? and dumping to SQLite?
 # follow the .string_serialization=="{text};{float} {unit}" and .multivalued == true pattern?

sheets_and_friends/tsv_in/modifications_long.tsv

@@ -66,6 +66,7 @@ JgiMgInterface|JgiMgLrInterface	dna_sample_format	replace_attribute	required			t
 JgiMgInterface|JgiMgLrInterface	dna_sample_format	replace_attribute	recommended			false
 JgiMgInterface|JgiMgLrInterface	dna_sample_name	replace_attribute	required			true
 JgiMgInterface|JgiMgLrInterface	dna_sample_name	replace_attribute	recommended			false
+JgiMgInterface|JgiMgLrInterface	dna_sample_name	replace_attribute	pattern			^[_a-zA-Z0-9-]*$
 JgiMgInterface|JgiMgLrInterface	dna_seq_project	replace_attribute	required			true
 JgiMgInterface|JgiMgLrInterface	dna_seq_project	replace_attribute	recommended			false
 JgiMgInterface|JgiMgLrInterface	dna_seq_project_name	replace_attribute	required			true
@@ -191,6 +192,7 @@ JgiMtInterface	rna_sample_format	replace_attribute	required			true
 JgiMtInterface	rna_sample_format	replace_attribute	recommended			false
 JgiMtInterface	rna_sample_name	replace_attribute	required			true
 JgiMtInterface	rna_sample_name	replace_attribute	recommended			false
+JgiMtInterface	rna_sample_name	replace_attribute	pattern			^[_a-zA-Z0-9-]*$
 JgiMtInterface	rna_seq_project	replace_attribute	required			true
 JgiMtInterface	rna_seq_project	replace_attribute	recommended			false
 JgiMtInterface	rna_seq_project_name	replace_attribute	required			true

sheets_and_friends/tsv_in/validation_converter.tsv

@@ -7,7 +7,7 @@ from_val	from_type	to_type	to_val	len
 {float}-{float}	MIxS string serialization	DH pattern regex	^[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?\s*-\s*[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?$	
 {float}|{float}-{float}	MIxS string serialization	DH pattern regex	^[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?(\s*-\s*[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?)?$	
 {integer}	MIxS string serialization	DH datatype	integer	7
-{lat lon}	linkml string_serialization	DH pattern regex	^[-+]?([1-8]?\d(\.\d+)?|90(\.0+)?)\s[-+]?(180(\.0+)?|((1[0-7]\d)|([1-9]?\d))(\.\d+)?)$	86
+{lat lon}	linkml string_serialization	DH pattern regex	^[-+]?([1-8]?\d(\.\d{1,8})?|90(\.0{1,8})?)\s[-+]?(180(\.0{1,8})?|((1[0-7]\d)|([1-9]?\d))(\.\d{1,8})?)$	86
 {termLabel} {[termID]}	MIxS string serialization	DH pattern regex	^\S+.*\S+ \[[a-zA-Z]{2,}:\d+\]$	
 {termLabel} {[termID]}; {timestamp}	MIxS string serialization	DH pattern regex	^\S+.*\S+ \[[a-zA-Z]{2,}:\d+\]; ([\+-]?\d{4}(?!\d{2}\b))((-?)((0[1-9]|1[0-2])(\3([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6])))([T\s]((([01]\d|2[0-3])((:?)[0-5]\d)?|24\:?00)([\.,]\d+(?!:))?)?(\17[0-5]\d([\.,]\d+)?)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?)?)?$	314
 {termLabel} {[termID]};{timestamp}	MIxS string serialization	DH pattern regex	^\S+.*\S+ \[[a-zA-Z]{2,}:\d+\];([\+-]?\d{4}(?!\d{2}\b))((-?)((0[1-9]|1[0-2])(\3([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6])))([T\s]((([01]\d|2[0-3])((:?)[0-5]\d)?|24\:?00)([\.,]\d+(?!:))?)?(\17[0-5]\d([\.,]\d+)?)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?)?)?$	313
@@ -24,7 +24,7 @@ ControlledIdentifiedTermValue	linkml range	DH datatype	string
 ControlledTermValue	linkml range	DH datatype	string	
 ControlledTermValue	linkml range	DH pattern regex	^\S+.*\S+ \[[a-zA-Z]{2,}:\d+\]$	
 GeolocationValue	linkml range	DH datatype	string	
-GeolocationValue	linkml range	DH pattern regex	^[-+]?([1-8]?\d(\.\d+)?|90(\.0+)?)\s[-+]?(180(\.0+)?|((1[0-7]\d)|([1-9]?\d))(\.\d+)?)$	
+GeolocationValue	linkml range	DH pattern regex	^[-+]?([1-8]?\d(\.\d{1,8})?|90(\.0{1,8})?)\s[-+]?(180(\.0{1,8})?|((1[0-7]\d)|([1-9]?\d))(\.\d{1,8})?)$	
 OntologyClass	linkml range	DH datatype	string	
 QuantityValue	linkml range	DH datatype	string	
 TextValue	linkml range	DH datatype	string	

src/data/unexpected_pass/SampleData-jgi_mg_data-colon-dna_sample_name.yaml → src/data/invalid/SampleData-jgi_mg_data-colon-dna_sample_name.yaml

@@ -11,7 +11,7 @@ jgi_mg_data:
     dna_project_contact: xxx
     dna_samp_id: xxx
     dna_sample_format: DNAStable
-    dna_sample_name: DNA:0546789 # contains colon and should not be allowed 'a-z, A-Z, 0-9, - and _ only'
+    dna_sample_name: DNA:0546789 # description says "Sample names must ... contain a-z, A-Z, 0-9, - and _ only." but there's no patten constraint
     dna_seq_project: xxx
     dna_seq_project_name: xxx
     dna_seq_project_pi: xxx

src/data/unexpected_pass/SampleData-jgi_mt_data-illegal-rna_seq_project.yaml → src/data/valid/SampleData-jgi_mt_data-discouraged-small-value-rna_volume.yaml

@@ -1,6 +1,6 @@
 jgi_mt_data:
-  - analysis_type:
-      - metatranscriptomics
+  - samp_name: sample name
+    source_mat_id: MPI:012345
     dnase_rna: "no"
     proposal_rna: '504000'
     rna_concentration: 100.3
@@ -12,9 +12,9 @@ jgi_mt_data:
     rna_samp_id: '123456'
     rna_sample_format: MDA reaction buffer
     rna_sample_name: JGI_lagoon_14343
-    rna_seq_project: An RNA Sequencing Project # Values will be prefilled by NMDC. Appears to accept any string.
+    rna_seq_project: '123456789'
     rna_seq_project_name: JGI Lagoon metatranscritpomics
     rna_seq_project_pi: Patty Smith
-    rna_volume: 25.1
-    samp_name: sample name
-    source_mat_id: MPI:012345
+    rna_volume: 5.1 # comments say "This form accepts values < 25, but JGI may refuse to process them unless permission has been granted by a project manager" but minimum_value says 0
+    analysis_type:
+      - metatranscriptomics