X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/cabf89d1fd8b40a2624d101a95c6587bfdd91fed..44c93373e97da98645d41ae8f09c6eef6788bb26:/sdk/cwl/arvados_cwl/runner.py diff --git a/sdk/cwl/arvados_cwl/runner.py b/sdk/cwl/arvados_cwl/runner.py index f064531165..38e2c4d806 100644 --- a/sdk/cwl/arvados_cwl/runner.py +++ b/sdk/cwl/arvados_cwl/runner.py @@ -31,8 +31,7 @@ import cwltool.workflow from cwltool.process import (scandeps, UnsupportedRequirement, normalizeFilesDirs, shortname, Process, fill_in_defaults) from cwltool.load_tool import fetch_document -from cwltool.pathmapper import adjustFileObjs, adjustDirObjs, visit_class -from cwltool.utils import aslist +from cwltool.utils import aslist, adjustFileObjs, adjustDirObjs, visit_class from cwltool.builder import substitute from cwltool.pack import pack from cwltool.update import INTERNAL_VERSION @@ -41,7 +40,7 @@ import schema_salad.validate as validate import arvados.collection from .util import collectionUUID -import ruamel.yaml as yaml +from ruamel.yaml import YAML from ruamel.yaml.comments import CommentedMap, CommentedSeq import arvados_cwl.arvdocker @@ -106,7 +105,8 @@ def make_builder(joborder, hints, requirements, runtimeContext, metadata): outdir="", # type: Text tmpdir="", # type: Text stagedir="", # type: Text - cwlVersion=metadata.get("http://commonwl.org/cwltool#original_cwlVersion") or metadata.get("cwlVersion") + cwlVersion=metadata.get("http://commonwl.org/cwltool#original_cwlVersion") or metadata.get("cwlVersion"), + container_engine="docker" ) def search_schemadef(name, reqs): @@ -184,7 +184,10 @@ def set_secondary(fsaccess, builder, inputschema, secondaryspec, primary, discov elif isinstance(pattern, dict): specs.append(pattern) elif isinstance(pattern, str): - specs.append({"pattern": pattern}) + if builder.cwlVersion == "v1.0": + specs.append({"pattern": pattern, "required": True}) + else: + specs.append({"pattern": pattern, "required": sf.get("required")}) else: raise SourceLine(primary["secondaryFiles"], i, validate.ValidationException).makeError( "Expression must return list, object, string or null") @@ -193,7 +196,12 @@ def set_secondary(fsaccess, builder, inputschema, secondaryspec, primary, discov for i, sf in enumerate(specs): if isinstance(sf, dict): if sf.get("class") == "File": - pattern = sf["basename"] + pattern = None + if sf.get("location") is None: + raise SourceLine(primary["secondaryFiles"], i, validate.ValidationException).makeError( + "File object is missing 'location': %s" % sf) + sfpath = sf["location"] + required = True else: pattern = sf["pattern"] required = sf.get("required") @@ -204,11 +212,16 @@ def set_secondary(fsaccess, builder, inputschema, secondaryspec, primary, discov raise SourceLine(primary["secondaryFiles"], i, validate.ValidationException).makeError( "Expression must return list, object, string or null") - sfpath = substitute(primary["location"], pattern) + if pattern is not None: + sfpath = substitute(primary["location"], pattern) + required = builder.do_eval(required, context=primary) if fsaccess.exists(sfpath): - found.append({"location": sfpath, "class": "File"}) + if pattern is not None: + found.append({"location": sfpath, "class": "File"}) + else: + found.append(sf) elif required: raise SourceLine(primary["secondaryFiles"], i, validate.ValidationException).makeError( "Required secondary file '%s' does not exist" % sfpath) @@ -252,7 +265,8 @@ def upload_dependencies(arvrunner, name, document_loader, textIO = StringIO(text.decode('utf-8')) else: textIO = StringIO(text) - return yaml.safe_load(textIO) + yamlloader = YAML(typ='safe', pure=True) + return yamlloader.load(textIO) else: return {} @@ -270,9 +284,10 @@ def upload_dependencies(arvrunner, name, document_loader, metadata = scanobj sc_result = scandeps(uri, scanobj, - loadref_fields, - set(("$include", "$schemas", "location")), - loadref, urljoin=document_loader.fetcher.urljoin) + loadref_fields, + set(("$include", "$schemas", "location")), + loadref, urljoin=document_loader.fetcher.urljoin, + nestdirs=False) sc = [] uuids = {} @@ -428,7 +443,8 @@ def upload_dependencies(arvrunner, name, document_loader, if "$schemas" in workflowobj: sch = CommentedSeq() for s in workflowobj["$schemas"]: - sch.append(mapper.mapper(s).resolved) + if s in mapper: + sch.append(mapper.mapper(s).resolved) workflowobj["$schemas"] = sch return mapper @@ -444,9 +460,16 @@ def upload_docker(arvrunner, tool): # TODO: can be supported by containers API, but not jobs API. raise SourceLine(docker_req, "dockerOutputDirectory", UnsupportedRequirement).makeError( "Option 'dockerOutputDirectory' of DockerRequirement not supported.") - arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, docker_req, True, arvrunner.project_uuid) + arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, docker_req, True, arvrunner.project_uuid, + arvrunner.runtimeContext.force_docker_pull, + arvrunner.runtimeContext.tmp_outdir_prefix, + arvrunner.runtimeContext.match_local_docker) else: - arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, {"dockerPull": "arvados/jobs:"+__version__}, True, arvrunner.project_uuid) + arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, {"dockerPull": "arvados/jobs:"+__version__}, + True, arvrunner.project_uuid, + arvrunner.runtimeContext.force_docker_pull, + arvrunner.runtimeContext.tmp_outdir_prefix, + arvrunner.runtimeContext.match_local_docker) elif isinstance(tool, cwltool.workflow.Workflow): for s in tool.steps: upload_docker(arvrunner, s.embedded_tool) @@ -466,7 +489,7 @@ def packed_workflow(arvrunner, tool, merged_map): def visit(v, cur_id): if isinstance(v, dict): - if v.get("class") in ("CommandLineTool", "Workflow"): + if v.get("class") in ("CommandLineTool", "Workflow", "ExpressionTool"): if tool.metadata["cwlVersion"] == "v1.0" and "id" not in v: raise SourceLine(v, None, Exception).makeError("Embedded process object is missing required 'id' field, add an 'id' or use to cwlVersion: v1.1") if "id" in v: @@ -474,12 +497,17 @@ def packed_workflow(arvrunner, tool, merged_map): if "path" in v and "location" not in v: v["location"] = v["path"] del v["path"] - if "location" in v and not v["location"].startswith("keep:"): - v["location"] = merged_map[cur_id].resolved[v["location"]] - if "location" in v and v["location"] in merged_map[cur_id].secondaryFiles: - v["secondaryFiles"] = merged_map[cur_id].secondaryFiles[v["location"]] + if "location" in v and cur_id in merged_map: + if v["location"] in merged_map[cur_id].resolved: + v["location"] = merged_map[cur_id].resolved[v["location"]] + if v["location"] in merged_map[cur_id].secondaryFiles: + v["secondaryFiles"] = merged_map[cur_id].secondaryFiles[v["location"]] if v.get("class") == "DockerRequirement": - v["http://arvados.org/cwl#dockerCollectionPDH"] = arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, v, True, arvrunner.project_uuid) + v["http://arvados.org/cwl#dockerCollectionPDH"] = arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, v, True, + arvrunner.project_uuid, + arvrunner.runtimeContext.force_docker_pull, + arvrunner.runtimeContext.tmp_outdir_prefix, + arvrunner.runtimeContext.match_local_docker) for l in v: visit(v[l], cur_id) if isinstance(v, list): @@ -584,7 +612,10 @@ def arvados_jobs_image(arvrunner, img): """Determine if the right arvados/jobs image version is available. If not, try to pull and upload it.""" try: - return arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, {"dockerPull": img}, True, arvrunner.project_uuid) + return arvados_cwl.arvdocker.arv_docker_get_image(arvrunner.api, {"dockerPull": img}, True, arvrunner.project_uuid, + arvrunner.runtimeContext.force_docker_pull, + arvrunner.runtimeContext.tmp_outdir_prefix, + arvrunner.runtimeContext.match_local_docker) except Exception as e: raise Exception("Docker image %s is not available\n%s" % (img, e) )