diff options
Diffstat (limited to 'bh20sequploader')
-rw-r--r-- | bh20sequploader/bh20seq-schema.yml | 5 | ||||
-rw-r--r-- | bh20sequploader/qc_fasta.py | 4 | ||||
-rw-r--r-- | bh20sequploader/qc_metadata.py | 26 |
3 files changed, 3 insertions, 32 deletions
diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index a072bd7..8a22db1 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -169,11 +169,6 @@ $graph: virus: virusSchema? technology: technologySchema submitter: submitterSchema - submission: - type: string - jsonldPredicate: - _id: "@id" - #_type: "@id" id: doc: The subject (eg the fasta/fastq file) that the metadata describes type: string? diff --git a/bh20sequploader/qc_fasta.py b/bh20sequploader/qc_fasta.py index e3d4fe7..e47d66b 100644 --- a/bh20sequploader/qc_fasta.py +++ b/bh20sequploader/qc_fasta.py @@ -21,8 +21,8 @@ def qc_fasta(sequence): raise ValueError("FASTA file contains multiple entries") break sequence.seek(0) - return "reads.fastq" - elif seq_type == "text/fastq": return "sequence.fasta" + elif seq_type == "text/fastq": + return "reads.fastq" else: raise ValueError("Sequence file does not look like FASTA or FASTQ") diff --git a/bh20sequploader/qc_metadata.py b/bh20sequploader/qc_metadata.py index 38edcaa..e477f21 100644 --- a/bh20sequploader/qc_metadata.py +++ b/bh20sequploader/qc_metadata.py @@ -5,21 +5,10 @@ import pkg_resources import logging import traceback -class CustomFetcher(schema_salad.ref_resolver.DefaultFetcher): - def check_exists(sup, url): - if url.startswith("keep:"): - return True - else: - return super().check_exists(url) - - def supported_schemes(self): # type: () -> List[str] - return ["file", "http", "https", "mailto", "keep"] - - def qc_metadata(metadatafile): schema_resource = pkg_resources.resource_stream(__name__, "bh20seq-schema.yml") cache = {"https://raw.githubusercontent.com/arvados/bh20-seq-resource/master/bh20sequploader/bh20seq-schema.yml": schema_resource.read().decode("utf-8")} - (loader, + (document_loader, avsc_names, schema_metadata, metaschema_loader) = schema_salad.schema.load_schema("https://raw.githubusercontent.com/arvados/bh20-seq-resource/master/bh20sequploader/bh20seq-schema.yml", cache=cache) @@ -28,19 +17,6 @@ def qc_metadata(metadatafile): print(avsc_names) return False - document_loader = schema_salad.ref_resolver.Loader( - loader.ctx, - schemagraph=loader.graph, - foreign_properties=loader.foreign_properties, - idx=loader.idx, - cache=loader.cache, - fetcher_constructor=CustomFetcher, - skip_schemas=loader.skip_schemas, - url_fields=loader.url_fields, - allow_attachments=loader.allow_attachments, - session=loader.session, - ) - try: doc, metadata = schema_salad.schema.load_and_validate(document_loader, avsc_names, metadatafile, True) return True |