Skip to content

Propagate custom fetcher_constructor to workflow steps #243

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Dec 6, 2016
Merged

Propagate custom fetcher_constructor to workflow steps #243

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e2876b1
Propagate custom fetcher_constructor to workflow steps, and custom ur…
Dec 6, 2016
4bb09f3
Provide DefaultFetcher. Fix type signature on scandeps.
Dec 6, 2016
cb02a4a
Clean up fetcher_constructor default value.
Dec 6, 2016
60feb6a
Transform list to $graph: list before checking that workflowobj is a …
Dec 6, 2016
88062ea
Merge branch 'master' into custom-urljoin
tetron Dec 6, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 12 additions & 9 deletions cwltool/load_tool.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import re
import urlparse

from schema_salad.ref_resolver import Loader, Fetcher, DefaultFetcher
from schema_salad.ref_resolver import Loader, Fetcher
import schema_salad.validate as validate
from schema_salad.validate import ValidationException
import schema_salad.schema as schema
Expand All @@ -26,7 +26,7 @@

def fetch_document(argsworkflow, # type: Union[Text, dict[Text, Any]]
resolver=None, # type: Callable[[Loader, Union[Text, dict[Text, Any]]], Text]
fetcher_constructor=DefaultFetcher # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
fetcher_constructor=None # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
):
# type: (...) -> Tuple[Loader, Dict[Text, Any], Text]
"""Retrieve a CWL document."""
Expand Down Expand Up @@ -111,23 +111,26 @@ def validate_document(document_loader, # type: Loader
enable_dev=False, # type: bool
strict=True, # type: bool
preprocess_only=False, # type: bool
fetcher_constructor=DefaultFetcher # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
fetcher_constructor=None # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
):
# type: (...) -> Tuple[Loader, Names, Union[Dict[Text, Any], List[Dict[Text, Any]]], Dict[Text, Any], Text]
"""Validate a CWL document."""

if isinstance(workflowobj, list):
workflowobj = {
"$graph": workflowobj
}

if not isinstance(workflowobj, dict):
raise ValueError("workflowjobj must be a dict")

jobobj = None
if "cwl:tool" in workflowobj:
jobobj, _ = document_loader.resolve_all(workflowobj, uri)
uri = urlparse.urljoin(uri, workflowobj["https://w3id.org/cwl/cwl#tool"])
del cast(dict, jobobj)["https://w3id.org/cwl/cwl#tool"]
workflowobj = fetch_document(uri, fetcher_constructor=fetcher_constructor)[1]

if isinstance(workflowobj, list):
workflowobj = {
"$graph": workflowobj
}

fileuri = urlparse.urldefrag(uri)[0]

if "cwlVersion" in workflowobj:
Expand Down Expand Up @@ -235,7 +238,7 @@ def load_tool(argsworkflow, # type: Union[Text, Dict[Text, Any]]
enable_dev=False, # type: bool
strict=True, # type: bool
resolver=None, # type: Callable[[Loader, Union[Text, dict[Text, Any]]], Text]
fetcher_constructor=DefaultFetcher # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
fetcher_constructor=None # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
):
# type: (...) -> Process

Expand Down
6 changes: 3 additions & 3 deletions cwltool/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
from typing import (Union, Any, AnyStr, cast, Callable, Dict, Sequence, Text,
Tuple, Type, IO)

from schema_salad.ref_resolver import Loader, Fetcher, DefaultFetcher
from schema_salad.ref_resolver import Loader, Fetcher
import schema_salad.validate as validate
import schema_salad.jsonld_context
import schema_salad.makedoc
Expand Down Expand Up @@ -516,7 +516,7 @@ def printdeps(obj, document_loader, stdout, relative_deps, uri, basedir=None):
"location": uri} # type: Dict[Text, Any]

def loadref(b, u):
return document_loader.fetch(urlparse.urljoin(b, u))
return document_loader.fetch(document_loader.fetcher.urljoin(b, u))

sf = scandeps(
basedir if basedir else uri, obj, set(("$import", "run")),
Expand Down Expand Up @@ -565,7 +565,7 @@ def main(argsl=None, # type: List[str]
versionfunc=versionstring, # type: Callable[[], Text]
job_order_object=None, # type: Union[Tuple[Dict[Text, Any], Text], int]
make_fs_access=StdFsAccess, # type: Callable[[Text], StdFsAccess]
fetcher_constructor=DefaultFetcher, # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
fetcher_constructor=None, # type: Callable[[Dict[unicode, unicode], requests.sessions.Session], Fetcher]
resolver=tool_resolver
):
# type: (...) -> int
Expand Down
24 changes: 12 additions & 12 deletions cwltool/process.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@
import tempfile
import glob
import urlparse
import pprint
from collections import Iterable
import errno
import shutil
Expand Down Expand Up @@ -640,8 +639,8 @@ def mergedirs(listing):
r.extend(ents.itervalues())
return r

def scandeps(base, doc, reffields, urlfields, loadref):
# type: (Text, Any, Set[Text], Set[Text], Callable[[Text, Text], Any]) -> List[Dict[Text, Text]]
def scandeps(base, doc, reffields, urlfields, loadref, urljoin=urlparse.urljoin):
# type: (Text, Any, Set[Text], Set[Text], Callable[[Text, Text], Any], Callable[[Text, Text], Text]) -> List[Dict[Text, Text]]
r = [] # type: List[Dict[Text, Text]]
deps = None # type: Dict[Text, Any]
if isinstance(doc, dict):
Expand All @@ -660,7 +659,7 @@ def scandeps(base, doc, reffields, urlfields, loadref):
if u and not u.startswith("_:"):
deps = {
"class": doc["class"],
"location": urlparse.urljoin(base, u)
"location": urljoin(base, u)
}
if doc["class"] == "Directory" and "listing" in doc:
deps["listing"] = doc["listing"]
Expand All @@ -670,23 +669,23 @@ def scandeps(base, doc, reffields, urlfields, loadref):
r.append(deps)
else:
if doc["class"] == "Directory" and "listing" in doc:
r.extend(scandeps(base, doc["listing"], reffields, urlfields, loadref))
r.extend(scandeps(base, doc["listing"], reffields, urlfields, loadref, urljoin=urljoin))
elif doc["class"] == "File" and "secondaryFiles" in doc:
r.extend(scandeps(base, doc["secondaryFiles"], reffields, urlfields, loadref))
r.extend(scandeps(base, doc["secondaryFiles"], reffields, urlfields, loadref, urljoin=urljoin))

for k, v in doc.iteritems():
if k in reffields:
for u in aslist(v):
if isinstance(u, dict):
r.extend(scandeps(base, u, reffields, urlfields, loadref))
r.extend(scandeps(base, u, reffields, urlfields, loadref, urljoin=urljoin))
else:
sub = loadref(base, u)
subid = urlparse.urljoin(base, u)
subid = urljoin(base, u)
deps = {
"class": "File",
"location": subid
}
sf = scandeps(subid, sub, reffields, urlfields, loadref)
sf = scandeps(subid, sub, reffields, urlfields, loadref, urljoin=urljoin)
if sf:
deps["secondaryFiles"] = sf
deps = nestdir(base, deps)
Expand All @@ -695,19 +694,20 @@ def scandeps(base, doc, reffields, urlfields, loadref):
for u in aslist(v):
deps = {
"class": "File",
"location": urlparse.urljoin(base, u)
"location": urljoin(base, u)
}
deps = nestdir(base, deps)
r.append(deps)
elif k not in ("listing", "secondaryFiles"):
r.extend(scandeps(base, v, reffields, urlfields, loadref))
r.extend(scandeps(base, v, reffields, urlfields, loadref, urljoin=urljoin))
elif isinstance(doc, list):
for d in doc:
r.extend(scandeps(base, d, reffields, urlfields, loadref))
r.extend(scandeps(base, d, reffields, urlfields, loadref, urljoin=urljoin))

if r:
normalizeFilesDirs(r)
r = mergedirs(r)

return r

def compute_checksums(fs_access, fileobj):
Expand Down
3 changes: 2 additions & 1 deletion cwltool/workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,7 +445,8 @@ def __init__(self, toolpath_object, pos, **kwargs):
self.embedded_tool = load_tool(
toolpath_object["run"], kwargs.get("makeTool"), kwargs,
enable_dev=kwargs.get("enable_dev"),
strict=kwargs.get("strict"))
strict=kwargs.get("strict"),
fetcher_constructor=kwargs.get("fetcher_constructor"))
except validate.ValidationException as v:
raise WorkflowException(
u"Tool definition %s failed validation:\n%s" %
Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@
'rdflib-jsonld == 0.3.0',
'html5lib >=0.90, <= 0.9999999',
'shellescape',
'schema-salad >= 1.20.20161122192122, < 2',
'schema-salad >= 1.21.20161206181442, < 2',
'typing >= 3.5.2',
'cwltest >= 1.0.20160907111242'],
test_suite='tests',
Expand Down