def test_issue12(t, c_name):
src = '''[
{"id": "1", "c1": 1, "c2": 2, "c3": 3 },
{"id": "2", "c1": 2, "c2": 2, "c3": 3 },
{"id": "3", "c1": 3, "c2": 3, "c3": 3 },
{"id": "4", "c1": 1, "c2": 1, "c3": 1 },
{"id": "5", "c1": 6, "c2": 6, "c3": 6 }
]'''
#dataset.verbose_on() # DEBUG
#dataset.use_strict_dotpath(True) # DEBUG
if dataset.status(c_name) == False:
if not dataset.init(c_name):
err = dataset.error_message()
t.error(f'failed to create {c_name}')
return
objects = json.loads(src)
for obj in objects:
key = obj['id']
if dataset.has_key(c_name, key):
dataset.update(c_name, key, obj)
else:
dataset.create(c_name, key, obj)
f_names = dataset.frames(c_name)
for f_name in f_names:
ok = dataset.delete_frame(c_name, f_name)
if ok == False:
err = dataset.error_message()
t.error(f'Failed to delete {f_name} from {c_name} -> "{err}"')
return
if dataset.has_frame(c_name, f_name) == True:
t.error(
f'Failed to delete frame {c_name} from {c_name}, frame still exists'
)
return
f_name = 'issue12'
dot_paths = [".c1", "c3"]
labels = [".col1", ".col3"]
keys = dataset.keys(c_name)
if not dataset.frame_create(c_name, f_name, keys, dot_paths, labels):
err = dataset.error_message()
t.error(f'failed to create {f_name} from {c_name}, {err}')
if not dataset.has_frame(c_name, f_name):
err = dataset.error_message()
t.error(f'expected frame {f_name} to exists, {err}')
return
f_keys = dataset.frame_keys(c_name, f_name)
if len(f_keys) == 0:
err = dataset.error_message()
t.error(f'expected keys in {f_name}, got zero, {err}')
return
f_objects = dataset.frame_objects(c_name, f_name)
if len(f_objects) == 0:
err = dataset.error_message()
t.error(f'expected objects in {f_name}, got zero, {err}')
return
if not dataset.delete_frame(c_name, f_name):
err = dataset.error_message()
t.error(f'expected to delete {f_name} in {c_name}, {err}')
def make_link_history(collection, resolver, url, note):
"""Make an entry in our link history collection"""
now = datetime.today().isoformat()
# Run checks on both resoler and final URL
try:
target = requests.get(url)
except requests.exceptions.ConnectionError:
target = requests.Response()
target.status_code = 404
target.url = ''
if target.status_code != 200:
print(
f"Target URL {url} returns Error status code {target.status_code}")
if links_differ(target.url, url):
print(f"Target URL '{url}' redirects to '{target.url}'")
try:
get = requests.get(f"https://resolver.library.caltech.edu/{resolver}")
except requests.exceptions.ConnectionError:
get = requests.Response()
get.status_code = 404
get.url = ''
if links_differ(get.url, url):
print(f"Mismatch between expected url '{url}' and actual '{get.url}'")
if get.status_code != 200:
print(
f"Resolver URL ({resolver}) '{get.url}' returns Error status code {get.status_code}"
)
entry = {
"expected-url": url,
"url": get.url,
"modified": now,
"code": get.status_code,
"note": note,
}
# If existing, push into history
if dataset.has_key(collection, resolver):
existing, err = dataset.read(collection, resolver)
if err != "":
print(err)
exit()
if save_history(existing, url, get):
past_history = existing.pop("history")
past_history.append(existing)
entry["history"] = past_history
if not dataset.update(collection, resolver, entry):
print(dataset.error_message())
exit()
else:
entry["history"] = []
if not dataset.create(collection, resolver, entry):
print(dataset.error_message())
exit()
def test_join(t, collection_name):
key = "test_join1"
obj1 = {"one": 1}
obj2 = {"two": 2}
if dataset.status(collection_name) == False:
t.error("Failed, collection status is False,", collection_name)
return
ok = dataset.has_key(collection_name, key)
err = ''
if ok == True:
ok = dataset.update(collection_nane, key, obj1)
else:
ok = dataset.create(collection_name, key, obj1)
if ok == False:
err = dataset.error_message()
t.error(
f'Failed, could not add record for test ({collection_name}, {key}, {obj1}), {err}'
)
return
if dataset.join(collection_name, key, obj2, overwrite=False) == False:
err = dataset.error_message()
t.error(
f'Failed, join for {collection_name}, {key}, {obj2}, overwrite = False -> {err}'
)
obj_result, err = dataset.read(collection_name, key)
if err != '':
t.error(f'Unexpected error for {key} in {collection_name}, {err}')
if obj_result.get('one') != 1:
t.error(f'Failed to join append key {key}, {obj_result}')
if obj_result.get("two") != 2:
t.error(f'Failed to join append key {key}, {obj_result}')
obj2['one'] = 3
obj2['two'] = 3
obj2['three'] = 3
if dataset.join(collection_name, key, obj2, overwrite=True) == False:
err = dataset.error_message()
t.error(
f'Failed to join overwrite {collection_name}, {key}, {obj2}, overwrite = True -> {err}'
)
obj_result, err = dataset.read(collection_name, key)
if err != '':
t.error(f'Unexpected error for {key} in {collection_name}, {err}')
for k in obj_result:
if k != '_Key' and obj_result[k] != 3:
t.error('Failed to update value in join overwrite', k, obj_result)
def match_codemeta():
collection = "github_records.ds"
keys = dataset.keys(collection)
for k in keys:
existing, err = dataset.read(collection, k)
if err != "":
print(f"Unexpected error on read: {err}")
if "completed" not in existing:
print("Processing new record ", k)
if dataset.attachments(collection, k) != "":
dataset.detach(collection, k)
# Update CaltechDATA
token = os.environ["TINDTOK"]
infile = open("codemeta.json", "r")
try:
meta = json.load(infile)
except:
print("Invalid json file - Skipping forever ", k)
else:
standardized = codemeta_to_datacite(meta)
# Check that all records have a GitHub subject tag
add = True
for s in standardized["subjects"]:
if s["subject"] == "Github":
add = False
if s["subject"] == "GitHub":
add = False
if add == True:
standardized["subjects"].append({"subject": "GitHub"})
response = caltechdata_edit(token, k, standardized, {}, {}, True)
print(response)
os.system("rm codemeta.json")
existing["completed"] = "True"
if not dataset.update(collection, k, existing):
err = dataset.error_message()
print(f"Unexpected error on read: {err}")
def migrate_attachment(c_name, key):
obj, err = dataset.read(c_name, key)
obj_path = dataset.path(c_name, key).replace(key + ".json", "")
tarball = os.path.join(obj_path, key + ".tar")
if os.path.exists(tarball):
tar = tarfile.open(tarball)
tar.extractall()
tar.close()
files = os.listdir()
# Prune _Attachment from object and resave
if "_Attachments" in obj:
del obj["_Attachments"]
err = dataset.update(c_name, key, obj)
if err != "":
print(f"Can't remove _Attachments metadata, {err}")
sys.exit(1)
for fname in files:
print(".", end="")
reattach(c_name, key, "v0.0.0", fname)
os.remove(fname)
# NOTE: if all re-attached then we need to remove tarball too
os.remove(tarball)
sys.stdout.flush()
def read_records(data, current, collection):
# read records in 'hits' structure
for record in data:
rid = str(record["id"])
metadata = record["metadata"]
download = False # Flag for downloading files
# Do we need to download?
if "electronic_location_and_access" in metadata:
# Get information about already backed up files:
existing_size = []
existing_names = []
if rid in current:
# Get existing files
attachments = dataset.attachments(collection, rid)
for a in attachments:
split = a.split(" ")
#Handle file names with spaces; size will always be last
size = split[-1]
name = a.replace(f' {size}', '')
existing_names.append(name)
existing_size.append(size)
# Look at all files
count = len(metadata["electronic_location_and_access"])
dl = 0
for erecord in metadata["electronic_location_and_access"]:
# Check if file has been downloaded
size = erecord["file_size"]
name = erecord["electronic_name"][0]
if size in existing_size and name in existing_names:
dl = dl + 1
if dl == count:
print(
"files already downloaded ",
existing_size,
existing_names,
)
download = False
else:
print("file mismatch ", existing_size, existing_names, dl,
count)
download = True
# Save results in dataset
print("Saving record " + rid)
if rid in current:
print('Update')
update = dataset.update(collection, rid, record)
if update == False:
print(
f"Failed, could not create record: {dataset.error_message()}"
)
exit()
else:
create = dataset.create(collection, rid, record)
print('CREATED', create, rid)
if create == False:
print(
f"Failed, could not create record: {dataset.error_message()}"
)
exit()
if download == True:
files = []
print("Downloading files for ", rid)
for erecord in metadata["electronic_location_and_access"]:
f = download_file(erecord, rid)
if f != None:
files.append(f)
print(files)
print("Attaching files")
if len(files) != 0:
err = dataset.attach(collection, rid, files)
if err == False:
print(f"Failed on attach {dataset.error_message()}")
exit()
for f in files:
if f != None:
os.remove(f)
def get_crossref_refs(prefix, done=False, new=True):
# New=True will download everything from scratch and delete any existing records
collection = "crossref_refs.ds"
if new == True:
if os.path.exists(collection) == True:
shutil.rmtree(collection)
if os.path.isdir(collection) == False:
if not dataset.init(collection):
print("Dataset failed to init collection")
exit()
base_url = (
"https://api.eventdata.crossref.org/v1/[email protected]&source=crossref&obj-id.prefix="
+ prefix)
collected = dataset.has_key(collection, "captured")
cursor = ""
count = 0
while cursor != None:
if collected == True:
date, err = dataset.read(collection, "captured")
if err != "":
print("error on read: " + err)
date = date["captured"]
print(date)
url = base_url + "&from-collected-date=" + date
else:
url = base_url
if cursor != "":
url = url + "&cursor=" + cursor
print(url)
r = requests.get(url)
records = r.json()
if records["status"] == "failed":
print(records)
break
for rec in records["message"]["events"]:
# Save results in dataset
print(count, rec["id"])
count = count + 1 # Just for prettyness
if not dataset.create(collection, rec["id"], rec):
err = dataset.error_message()
print("Error in saving record: " + err)
if cursor == records["message"]["next-cursor"]:
# Catches bug where we get the same curser back at end of results
break
if records["message"]["total-results"] > count:
cursor = records["message"]["next-cursor"]
else:
cursor = None
if collected == True:
date, err = dataset.read(collection, "captured")
if err != "":
print("Error in reading date: " + err)
date = date["captured"]
# Check Deleted
cursor = ""
while cursor != None:
del_url = "https://api.eventdata.crossref.org/v1/events/[email protected]&source=crossref"
full = del_url + "&from-collected-date=" + date + "&cursor=" + cursor
r = requests.get(full)
records = r.json()
for rec in records["message"]["events"]:
# Delete results in dataset
print("Deleted: ", rec["id"])
if not dataset.delete(collection, rec["id"]):
err = dataset.error_message()
print(f"Unexpected error on read: {err}")
cursor = records["message"]["next-cursor"]
# Check Edited
cursor = ""
while cursor != None:
del_url = "https://api.eventdata.crossref.org/v1/events/[email protected]&source=crossref"
full = del_url + "&from-collected-date=" + date + "&cursor=" + cursor
r = requests.get(full)
records = r.json()
for rec in records["message"]["events"]:
# Update results in dataset
print("Update: ", rec["id"])
if not dataset.update(collection, rec["id"], rec):
err = dataset.error_message()
print(f"Unexpected error on write: {err}")
cursor = records["message"]["next-cursor"]
if done:
date = datetime.date.today().isoformat()
record = {"captured": date}
if dataset.has_key(collection, "captured"):
if not dataset.update(collection, "captured", record):
err = dataset.error_message()
print(f"Unexpected error on update: {err}")
else:
if not dataset.create(collection, "captured", record):
err = dataset.error_message()
print(f"Unexpected error on create: {err}")
#
# Loop through the keys, fetch the record and append a _Key: "deposit" to
# each object.
#
c_name = "people.ds"
keys = dataset.keys(c_name)
#print(f"DEBUG Keys: {keys}")
for key in keys:
print(f"Fixing key {key}")
data, err = dataset.read(c_name, key)
if err != "":
print(f"Error read {c_name} -> {key}, {err}")
sys.exit(1)
# Make fieldname lower case
dt = datetime.now().strftime('%Y-%m-%d %H:%I:%S')
obj = {
"_Key": key,
"_State": "deposit",
"_Updated": f"{dt}",
"_Created": f"{dt}"
}
for field in data:
fkey = field.lower()
if not ' ' in fkey:
obj[fkey] = data[field]
err = dataset.update(c_name, key, obj)
if err != "":
print(f"Error write {c_name} -> {key}, {err}")
sys.exit(1)
# crawl docs_dir and ingest files into data collection.
for path, folders, files in os.walk(docs_dir):
#log.print(f"Processing {path}")
for filename in files:
if filename.endswith(".md"):
f_name = os.path.join(path, filename)
log.print(f"Ingesting {f_name}")
metadata = frontmatter(f_name)
with open(f_name) as f:
src = f.read()
if "id" in metadata:
key = str(metadata["id"])
if dataset.has_key(c_name, key):
err = dataset.update(c_name, key, {
"metadata": metadata,
"content": f_name,
"src": src
})
else:
err = dataset.create(c_name, key, {
"metadata": metadata,
"content": f_name,
"src": src
})
if err != "":
log.fatal(err)
else:
log.print(f"Warning, no front matter for {f_name}")
# for each dataset record render appropriate HTML pages
keys = dataset.keys(c_name)
keys = dataset.keys(profile_ds)
labels = ["orcid", "creator_id"]
dot_paths = [".orcid", ".creator_id"]
all_metadata = get_records(dot_paths, "profile", profile_ds, keys, labels)
for profile in all_metadata:
if "creator_id" in profile:
idv = profile["creator_id"]
else:
print("ERROR", profile)
for person in people:
if person["Authors_ID"] != "":
if person["Authors_ID"] == idv:
if person["ORCID"] == "":
person["ORCID"] = profile["orcid"]
dataset.update(import_coll, person["CL_PEOPLE_ID"], person)
print("Updated ", person["CL_PEOPLE_ID"])
elif person["ORCID"] != profile["orcid"]:
print(
"Inconsistent ORCIDS for ",
person["CL_PEOPLE_ID"],
person["ORCID"],
"CaltechAUTHORS",
profile["orcid"],
)
# TODO - port to python
# Run on command line
# dataset frame -all imported.ds gsheet-sync ._Key .ORCID
# dataset frame-labels imported.ds gsheet-sync "CL_PEOPLE_ID" "ORCID"
# dataset sync-send imported.ds gsheet-sync 1ZI3-XvQ_3rLcKrF-4FBa2tEInIdQfOnGJ9L_NmhmoGs CaltechPEOPLE
}
#assert schema40.validate(metadata)
#Debugging if this fails
#v = schema40.validator.validate(metadata)
#errors = sorted(v.iter_errors(instance), key=lambda e: e.path)
#for error in errors:
# print(error.message)
xml = schema40.tostring(metadata)
result = d.metadata_post(xml)
identifier = result.split('(')[1].split(')')[0]
d.doi_post(identifier, inputv['url'])
print('Completed ' + identifier)
inputv['doi'] = identifier
err = dataset.update(collection, key, inputv)
token = os.environ['MAILTOK']
email = inputv['email']
url = inputv['url']
send_simple_message(token, email, identifier, url)
else:
print("Web archiving is not complete for " + inputv['name'])
dot_exprs =\
['.email','.url','.title','.author','.affiliation','.orcid','.license','.prefix','.archive_complete','.doi']
column_names = [
'email', 'url', 'title', 'author', 'affiliation', 'orcid', 'license',
def aggregate_usage(usage_collection, month_collection):
keys = dataset.keys(usage_collection)
keys.remove("end-date")
for k in progressbar(keys):
record, err = dataset.read(usage_collection, k)
if err != "":
print(err)
use = {}
views = {}
for usage in record["performance"]:
split = usage["period"].split("-")
month = split[0] + "-" + split[1]
for u in usage["instance"]:
metric = u["metric-type"]
if metric == "unique-dataset-requests":
if month in use:
use[month] += u["count"]
else:
use[month] = u["count"]
if metric == "unique-dataset-investigations":
if month in views:
views[month] += u["count"]
else:
views[month] = u["count"]
# Strip non-counter stuff
record.pop("_Key")
record.pop("grand-total-unique-requests")
record.pop("grand-total-unique-investigations")
# go across months
for view in views:
split = view.split("-")
date_obj = datetime(int(split[0]), int(split[1]), 1)
d_range = get_month_day_range(date_obj)
performance = [
{
"period": {
"begin-date": d_range[0].date().isoformat(),
"end-date": d_range[1].date().isoformat(),
},
"instance": [],
}
]
v = views[view]
performance[0]["instance"].append(
{
"count": v,
"metric-type": "unique-dataset-investigations",
"access-method": "regular",
}
)
# Handle when we have both views and uses in a given month
if view in use:
u = use[view]
performance[0]["instance"].append(
{
"count": u,
"metric-type": "unique-dataset-requests",
"access-method": "regular",
}
)
existing, err = dataset.read(month_collection, view)
if err != "":
print(err)
record["performance"] = performance
existing["report-datasets"].append(record)
if not dataset.update(month_collection, view, existing):
err = dataset.error_message()
print(err)
for use_date in use:
# We only have use-only records left to handle
if use_date not in views:
u = use[use_date]
split = use_date.split("-")
date_obj = datetime(int(split[0]), int(split[1]), 1)
d_range = get_month_day_range(date_obj)
performance = [
{
"period": {
"begin-date": d_range[0].date().isoformat(),
"end-date": d_range[1].date().isoformat(),
},
"instance": [
{
"count": u,
"metric-type": "unique-dataset-requests",
"access-method": "regular",
}
],
}
]
existing, err = dataset.read(month_collection, view)
if err != "":
print(err)
record["performance"] = performance
existing["report-datasets"].append(record)
if not dataset.update(month_collection, view, existing):
err = dataset.error_message()
print(err)
def get_usage(usage_collection, mapping, token):
"""Collect usage into a usage object for items in CaltechDATA"""
# Find time periods
datev, err = dataset.read(usage_collection, "end-date")
new_start = datetime.fromtimestamp(datev["end-date"])
now = datetime.now().timestamp()
# minutes in range
minutes_diff = math.ceil(
(datetime.fromtimestamp(now) - new_start).total_seconds() / 60.0
)
# Get number of visitors since last harvest
stats_url_base = "https://stats.tind.io/index.php?module=API&method=Live.getCounters&idSite=1161&format=JSON"
token_s = "&token_auth=" + token
stats_url = f"{stats_url_base}{token_s}&lastMinutes={minutes_diff}"
response = requests.get(stats_url)
if response.status_code != 200:
print(response.text)
print(stats_url)
visitors = response.json()[0]["visits"]
print(visitors)
visit_url_base = "https://stats.tind.io/index.php?module=API&method=Live.getLastVisitsDetails&idSite=1161&format=json&filter_limit=1000"
print("Getting usage")
usage = []
# We will page through visitors in chunks of 1000
chunks = math.ceil(int(visitors) / 1000)
if chunks > 1:
url = visit_url_base + token_s + "&filter_limit=1000"
process_visits(url, mapping)
for c in progressbar(range(chunks)):
url = f"{visit_url_base}{token_s}&filter_limit=1000&filter_offset={c*1000}"
usage += process_visits(url, mapping)
else:
url = f"{visit_url_base}{token_s}&filter_limit={visitors}"
usage = process_visits(url, mapping)
print("Writing usage")
for use in progressbar(usage):
date = use["date"]
if "downloads" in use and "views" in use:
records = use["views"].union(use["downloads"])
elif "views" in use:
records = use["views"]
else:
records = use["downloads"]
for rec in records:
data, err = dataset.read(usage_collection, rec)
if err == "":
# We only track usage from live records
instance = {"instance": [], "period": date}
if "views" in use:
if rec in use["views"]:
instance["instance"].append(
{
"access-method": "regular",
"count": 1,
"metric-type": "unique-dataset-investigations",
}
)
# print(data,rec)
data["grand-total-unique-investigations"] += 1
if "downloads" in use:
if rec in use["downloads"]:
instance["instance"].append(
{
"access-method": "regular",
"count": 1,
"metric-type": "unique-dataset-requests",
}
)
data["grand-total-unique-requests"] += 1
data["performance"].append(instance)
dataset.update(usage_collection, rec, data)
dataset.update(usage_collection, "end-date", {"end-date": now})
def get_wos_refs(new=True):
# New=True will download everything from scratch and delete any existing records
collection = "all_wos.ds"
if new == True:
if os.path.exists(collection) == True:
shutil.rmtree(collection)
if os.path.isdir(collection) == False:
ok = dataset.init(collection)
if ok == False:
print("Dataset failed to init collection")
exit()
# Get access token from WOS sed as environment variable with source token.bash
token = os.environ["WOSTOK"]
headers = {"X-ApiKey": token, "Content-type": "application/json"}
# Run query to get scope of records
base_url = "https://api.clarivate.com/api/wos/?databaseId=WOK"
collected = dataset.has_key(collection, "captured")
if collected == True:
date = dataset.read(collection, "captured")
date = date[0]["captured"]
date = datetime.fromisoformat(date)
current = datetime.today()
diff = current - date
base_url = base_url + "&loadTimeSpan=" + str(diff.days) + "D"
date = datetime.today().isoformat()
record = {"captured": date}
if dataset.has_key(collection, "captured"):
err = dataset.update(collection, "captured", record)
if err != "":
print(f"Unexpected error on update: {err}")
else:
err = dataset.create(collection, "captured", record)
if err != "":
print(f"Unexpected error on create: {err}")
query = "OG=(California Institute of Technology)"
query = urllib.parse.quote_plus(query)
url = base_url + "&usrQuery=" + query + "&count=100&firstRecord=1"
response = requests.get(url, headers=headers)
response = response.json()
record_count = response["QueryResult"]["RecordsFound"]
print(record_count, " Records from WOS")
query_id = response["QueryResult"]["QueryID"]
try:
records = response["Data"]["Records"]["records"]["REC"]
except:
print(response)
write_records(records, collection)
# We have saved the first 100 records
record_start = 101
record_count = record_count - 100
query_url = "https://api.clarivate.com/api/wos/query/"
while record_count > 0:
print(record_count)
print(len(records), "records")
if record_count > 100:
url = (
query_url
+ str(query_id)
+ "?count=100&firstRecord="
+ str(record_start)
)
response = requests.get(url, headers=headers)
response = response.json()
try:
records = response["Records"]["records"]["REC"]
except:
print(response)
write_records(records, collection)
record_start = record_start + 100
record_count = record_count - 100
else:
url = (
query_url
+ str(query_id)
+ "?count="
+ str(record_count)
+ "&firstRecord="
+ str(record_start)
)
response = requests.get(url, headers=headers)
response = response.json()
records = response["Records"]["records"]["REC"]
write_records(records, collection)
record_count = 0
print("Downloaded all records ")
def test_attachments(t, collection_name):
t.print("Testing attach, attachments, detach and prune")
# Generate two files to attach.
with open('a1.txt', 'w') as text_file:
text_file.write('This is file a1')
with open('a2.txt', 'w') as text_file:
text_file.write('This is file a2')
filenames = ['a1.txt', 'a2.txt']
if dataset.status(collection_name) == False:
t.error("Failed,", collection_name, "missing")
return
keys = dataset.keys(collection_name)
if len(keys) < 1:
t.error("Failed,", collection_name, "should have keys")
return
key = keys[0]
if dataset.attach(collection_name, key, filenames) == False:
err = dataset.error_message()
t.error("Failed, to attach files for", collection_name, key, filenames,
', ', err)
return
l = dataset.attachments(collection_name, key)
if len(l) != 2:
t.error("Failed, expected two attachments for", collection_name, key,
"got", l)
return
#Check that attachments arn't impacted by update
if dataset.update(collection_name, key, {"testing": "update"}) == False:
err = dataset.error_message()
t.error("Failed, to update record", collection_name, key, err)
return
l = dataset.attachments(collection_name, key)
if len(l) != 2:
t.error("Failed, expected two attachments after update for",
collection_name, key, "got", l)
return
if os.path.exists(filenames[0]):
os.remove(filenames[0])
if os.path.exists(filenames[1]):
os.remove(filenames[1])
# First try detaching one file.
if dataset.detach(collection_name, key, [filenames[1]]) == False:
err = dataset.error_message()
t.error("Failed, expected True for", collection_name, key,
filenames[1], ', ', err)
if os.path.exists(filenames[1]):
os.remove(filenames[1])
else:
t.error("Failed to detch", filenames[1], "from", collection_name, key)
# Test explicit filenames detch
if dataset.detach(collection_name, key, filenames) == False:
err = dataset.error_message()
t.error("Failed, expected True for", collection_name, key, filenames,
', ', err)
for fname in filenames:
if os.path.exists(fname):
os.remove(fname)
else:
t.error("Failed, expected", fname, "to be detached from",
collection_name, key)
# Test detaching all files
if dataset.detach(collection_name, key, []) == False:
err = dataset.error_message()
t.error("Failed, expected True for (detaching all)", collection_name,
key, ', ', err)
for fname in filenames:
if os.path.exists(fname):
os.remove(fname)
else:
t.error("Failed, expected", fname, "for detaching all from",
collection_name, key)
if dataset.prune(collection_name, key, [filenames[0]]) == False:
err = dataset.error_messag()
t.error("Failed, expected True for prune", collection_name, key,
[filenames[0]], ', ', err)
l = dataset.attachments(collection_name, key)
if len(l) != 1:
t.error("Failed, expected one file after prune for", collection_name,
key, [filenames[0]], "got", l)
if dataset.prune(collection_name, key, []) == False:
err = dataset.error_message()
t.error("Failed, expected True for prune (all)", collection_name, key,
', ', err)
l = dataset.attachments(collection_name, key)
if len(l) != 0:
t.error("Failed, expected zero files after prune for", collection_name,
key, "got", l)
def test_basic(t, collection_name):
'''test_basic(collection_name) runs tests on basic CRUD ops'''
# Setup a test record
key = "2488"
value = {
"title":
"Twenty Thousand Leagues Under the Seas: An Underwater Tour of the World",
"formats": ["epub", "kindle", "plain text"],
"authors": [{
"given": "Jules",
"family": "Verne"
}],
"url": "https://www.gutenberg.org/ebooks/2488"
}
# We should have an empty collection, we will create our test record.
if dataset.create(collection_name, key, value) == False:
err = dataset.error_message()
t.error(f'create({collection_name}, {key}, {value}) failed, {err}')
return
# Check to see that we have only one record
key_count = dataset.count(collection_name)
if key_count != 1:
t.error(f"Failed, expected count to be 1, got {key_count}")
# Do a minimal test to see if the record looks like it has content
keyList = dataset.keys(collection_name)
rec, err = dataset.read(collection_name, key)
if err != "":
t.error(f"Unexpected error for {key} in {collection_name}, {err}")
for k, v in value.items():
if not isinstance(v, list):
if k in rec and rec[k] == v:
t.print("OK, found", k, " -> ", v)
else:
t.error(f"epxected {rec[k]} got {v}")
else:
if k == "formats" or k == "authors":
t.print("OK, expected lists for", k, " -> ", v)
else:
t.error(f"Failed, expected {k} with list v, got {v}")
# Test updating record
value["verified"] = True
if dataset.update(collection_name, key, value) == False:
err = dataset.error_message()
t.error(f"update({collection_name}, {key}, {value}) failed, {err}")
rec, err = dataset.read(collection_name, key)
if err != "":
t.error(f"Unexpected error for {key} in {collection_name}, {err}")
for k, v in value.items():
if not isinstance(v, list):
if k in rec and rec[k] == v:
t.print("OK, found", k, " -> ", v)
else:
t.error("expected {rec[k]} got {v} for key {k}")
else:
if k == "formats" or k == "authors":
t.print("OK, expected lists for", k, " -> ", v)
else:
t.error("Failed, expected {k} with a list for v, got {v}")
# Test path to record
expected_s = "/".join(
[collection_name, "pairtree", "24", "88", (key + ".json")])
expected_l = len(expected_s)
p = dataset.path(collection_name, key)
if len(p) != expected_l:
t.error("Failed, expected length", expected_l, "got", len(p))
if p != expected_s:
t.error("Failed, expected", expected_s, "got", p)
# Test listing records
l = dataset.list(collection_name, [key])
if len(l) != 1:
t.error(
f"list({collection_name}, [{key}]) failed, list should return an array of one record, got",
l)
return
# test deleting a record
if dataset.delete(collection_name, key) == False:
err = dataset.error_message()
t.error("Failed, could not delete record", key, ", ", err)
