def test_get_versioned_url():
get_test_providers(
's3://openfmri/tarballs'
) # to verify having credentials to access openfmri via S3
for url_pref in ('http://openfmri.s3.amazonaws.com',
'https://s3.amazonaws.com/openfmri'):
eq_(get_versioned_url(url_pref + "/tarballs/ds001_raw.tgz"),
url_pref + "/tarballs/ds001_raw.tgz?versionId=null")
eq_(get_versioned_url(url_pref + "/tarballs/ds001_raw.tgz?param=1"),
url_pref + "/tarballs/ds001_raw.tgz?param=1&versionId=null")
# We don't duplicate the version if it already exists.
eq_(
get_versioned_url(url_pref +
"/tarballs/ds001_raw.tgz?versionId=null"),
url_pref + "/tarballs/ds001_raw.tgz?versionId=null")
# something is wrong there
#print(get_versioned_url("http://openfmri.s3.amazonaws.com/ds001/demographics.txt"))
eq_(get_versioned_url("someurl"),
"someurl") # should just return original one
assert_raises(RuntimeError,
get_versioned_url,
"someurl",
guarantee_versioned=True)
# TODO: on a bucket without versioning
url = "http://datalad-test0-nonversioned.s3.amazonaws.com/2versions-removed-recreated.txt"
eq_(get_versioned_url(url), url)
eq_(get_versioned_url(url, return_all=True), [url])
assert_raises(NotImplementedError, get_versioned_url, "s3://buga")
urls = get_versioned_url(
"http://datalad-test0-versioned.s3.amazonaws.com/2versions-removed-recreated.txt",
return_all=True,
verify=True)
eq_(len(set(urls)), len(urls)) # all unique
for url in urls:
# so we didn't grab other files along with the same prefix
ok_startswith(
url,
'http://datalad-test0-versioned.s3.amazonaws.com/2versions-removed-recreated.txt?versionId='
)
# Update a versioned URL with a newer version tag.
url_3ver = "http://datalad-test0-versioned.s3.amazonaws.com/3versions-allversioned.txt"
url_3ver_input = url_3ver + "?versionId=b.qCuh7Sg58VIYj8TVHzbRS97EvejzEl"
eq_(get_versioned_url(url_3ver_input), url_3ver_input)
eq_(get_versioned_url(url_3ver_input, update=True),
url_3ver + "?versionId=Kvuind11HZh._dCPaDAb0OY9dRrQoTMn")
def test_version_url_deleted():
get_test_providers('s3://datalad-test0-versioned/', reload=True) # to verify having credentials to access
# openfmri via S3
# it existed and then was removed
fpath = "1version-removed.txt"
url = "http://datalad-test0-versioned.s3.amazonaws.com/%s" % fpath
turl = "http://datalad-test0-versioned.s3.amazonaws.com/%s" \
"?versionId=eZ5Hgwo8azfBv3QT7aW9dmm2sbLUY.QP" % fpath
eq_(get_versioned_url(url), turl)
def test_get_versioned_url_anon():
# The one without any authenticator, was crashing.
# Also it triggered another bug about having . in the bucket name
url_on = "http://openneuro.org.s3.amazonaws.com/ds000001/dataset_description.json"
url_on_versioned = get_versioned_url(url_on)
ok_startswith(url_on_versioned, url_on + "?versionId=")
def __call__(dataset,
urlfile,
urlformat,
filenameformat,
input_type="ext",
exclude_autometa=None,
meta=None,
message=None,
dry_run=False,
fast=False,
ifexists=None,
missing_value=None,
save=True,
version_urls=False):
# Temporarily work around gh-2269.
url_file = urlfile
url_format, filename_format = urlformat, filenameformat
from requests.exceptions import RequestException
from datalad.distribution.add import Add
from datalad.distribution.create import Create
from datalad.distribution.dataset import Dataset, require_dataset
from datalad.interface.results import get_status_dict
from datalad.support.annexrepo import AnnexRepo
lgr = logging.getLogger("datalad.plugin.addurls")
dataset = require_dataset(dataset, check_installed=False)
if dataset.repo and not isinstance(dataset.repo, AnnexRepo):
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message="not an annex repo")
return
if input_type == "ext":
extension = os.path.splitext(url_file)[1]
input_type = "json" if extension == ".json" else "csv"
with open(url_file) as fd:
try:
rows, subpaths = extract(fd, input_type, url_format,
filename_format, exclude_autometa,
meta, dry_run, missing_value)
except (ValueError, RequestException) as exc:
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message=exc_str(exc))
return
if len(rows) != len(set(row["filename"] for row in rows)):
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message=("There are file name collisions; "
"consider using {_repindex}"))
return
if dry_run:
for subpath in subpaths:
lgr.info("Would create a subdataset at %s", subpath)
for row in rows:
lgr.info("Would download %s to %s", row["url"],
os.path.join(dataset.path, row["filename"]))
lgr.info(
"Metadata: %s",
sorted(u"{}={}".format(k, v)
for k, v in row["meta_args"].items()))
yield get_status_dict(action="addurls",
ds=dataset,
status="ok",
message="dry-run finished")
return
if not dataset.repo:
# Populate a new dataset with the URLs.
for r in dataset.create(result_xfm=None,
return_type='generator',
save=save):
yield r
annex_options = ["--fast"] if fast else []
for spath in subpaths:
if os.path.exists(os.path.join(dataset.path, spath)):
lgr.warning("Not creating subdataset at existing path: %s",
spath)
else:
for r in dataset.create(spath,
result_xfm=None,
return_type='generator',
save=save):
yield r
for row in rows:
# Add additional information that we'll need for various
# operations.
filename_abs = os.path.join(dataset.path, row["filename"])
if row["subpath"]:
ds_current = Dataset(os.path.join(dataset.path,
row["subpath"]))
ds_filename = os.path.relpath(filename_abs, ds_current.path)
else:
ds_current = dataset
ds_filename = row["filename"]
row.update({
"filename_abs": filename_abs,
"ds": ds_current,
"ds_filename": ds_filename
})
if version_urls:
num_urls = len(rows)
log_progress(lgr.info,
"addurls_versionurls",
"Versioning %d URLs",
num_urls,
label="Versioning URLs",
total=num_urls,
unit=" URLs")
for row in rows:
url = row["url"]
try:
row["url"] = get_versioned_url(url)
except (ValueError, NotImplementedError) as exc:
# We don't expect this to happen because get_versioned_url
# should return the original URL if it isn't an S3 bucket.
# It only raises exceptions if it doesn't know how to
# handle the scheme for what looks like an S3 bucket.
lgr.warning("error getting version of %s: %s", row["url"],
exc_str(exc))
log_progress(lgr.info,
"addurls_versionurls",
"Versioned result for %s: %s",
url,
row["url"],
update=1,
increment=True)
log_progress(lgr.info, "addurls_versionurls",
"Finished versioning URLs")
files_to_add = set()
for r in add_urls(rows, ifexists=ifexists, options=annex_options):
if r["status"] == "ok":
files_to_add.add(r["path"])
yield r
msg = message or """\
[DATALAD] add files from URLs
url_file='{}'
url_format='{}'
filename_format='{}'""".format(url_file, url_format, filename_format)
if files_to_add:
for r in dataset.add(files_to_add, save=False):
yield r
meta_rows = [r for r in rows if r["filename_abs"] in files_to_add]
for r in add_meta(meta_rows):
yield r
# Save here rather than the add call above to trigger a metadata
# commit on the git-annex branch.
if save:
for r in dataset.save(message=msg, recursive=True):
yield r
def __call__(dataset, urlfile, urlformat, filenameformat,
input_type="ext", exclude_autometa=None, meta=None,
message=None, dry_run=False, fast=False, ifexists=None,
missing_value=None, save=True, version_urls=False):
# Temporarily work around gh-2269.
url_file = urlfile
url_format, filename_format = urlformat, filenameformat
from requests.exceptions import RequestException
from datalad.distribution.dataset import Dataset, require_dataset
from datalad.interface.results import get_status_dict
from datalad.support.annexrepo import AnnexRepo
lgr = logging.getLogger("datalad.plugin.addurls")
dataset = require_dataset(dataset, check_installed=False)
if dataset.repo and not isinstance(dataset.repo, AnnexRepo):
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message="not an annex repo")
return
if input_type == "ext":
extension = os.path.splitext(url_file)[1]
input_type = "json" if extension == ".json" else "csv"
with open(url_file) as fd:
try:
rows, subpaths = extract(fd, input_type,
url_format, filename_format,
exclude_autometa, meta,
dry_run,
missing_value)
except (ValueError, RequestException) as exc:
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message=exc_str(exc))
return
if len(rows) != len(set(row["filename"] for row in rows)):
yield get_status_dict(action="addurls",
ds=dataset,
status="error",
message=("There are file name collisions; "
"consider using {_repindex}"))
return
if dry_run:
for subpath in subpaths:
lgr.info("Would create a subdataset at %s", subpath)
for row in rows:
lgr.info("Would download %s to %s",
row["url"],
os.path.join(dataset.path, row["filename"]))
lgr.info("Metadata: %s",
sorted(u"{}={}".format(k, v)
for k, v in row["meta_args"].items()))
yield get_status_dict(action="addurls",
ds=dataset,
status="ok",
message="dry-run finished")
return
if not dataset.repo:
# Populate a new dataset with the URLs.
for r in dataset.create(result_xfm=None,
return_type='generator'):
yield r
annex_options = ["--fast"] if fast else []
for spath in subpaths:
if os.path.exists(os.path.join(dataset.path, spath)):
lgr.warning(
"Not creating subdataset at existing path: %s",
spath)
else:
for r in dataset.create(spath, result_xfm=None,
return_type='generator'):
yield r
for row in rows:
# Add additional information that we'll need for various
# operations.
filename_abs = os.path.join(dataset.path, row["filename"])
if row["subpath"]:
ds_current = Dataset(os.path.join(dataset.path,
row["subpath"]))
ds_filename = os.path.relpath(filename_abs, ds_current.path)
else:
ds_current = dataset
ds_filename = row["filename"]
row.update({"filename_abs": filename_abs,
"ds": ds_current,
"ds_filename": ds_filename})
if version_urls:
num_urls = len(rows)
log_progress(lgr.info, "addurls_versionurls",
"Versioning %d URLs", num_urls,
label="Versioning URLs",
total=num_urls, unit=" URLs")
for row in rows:
url = row["url"]
try:
row["url"] = get_versioned_url(url)
except (ValueError, NotImplementedError) as exc:
# We don't expect this to happen because get_versioned_url
# should return the original URL if it isn't an S3 bucket.
# It only raises exceptions if it doesn't know how to
# handle the scheme for what looks like an S3 bucket.
lgr.warning("error getting version of %s: %s",
row["url"], exc_str(exc))
log_progress(lgr.info, "addurls_versionurls",
"Versioned result for %s: %s", url, row["url"],
update=1, increment=True)
log_progress(lgr.info, "addurls_versionurls", "Finished versioning URLs")
files_to_add = set()
for r in add_urls(rows, ifexists=ifexists, options=annex_options):
if r["status"] == "ok":
files_to_add.add(r["path"])
yield r
msg = message or """\
[DATALAD] add files from URLs
url_file='{}'
url_format='{}'
filename_format='{}'""".format(url_file, url_format, filename_format)
if files_to_add:
meta_rows = [r for r in rows if r["filename_abs"] in files_to_add]
for r in add_meta(meta_rows):
yield r
if save:
for r in dataset.save(path=files_to_add, message=msg, recursive=True):
yield r
