def test_too_large_file(self):
"""It should raise JobError if the data file is too large.
If the data file is larger than MAX_CONTENT_LENGTH then the async
background job push_to_datastore should raise JobError
(ckanserviceprovider will catch this exception and return an error to
the client).
"""
self.register_urls()
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
# Override the source_url (already mocked by self.register_urls()
# above) with another mock response, this one mocks a response body
# that's bigger than MAX_CONTENT_LENGTH.
source_url = 'http://www.source.org/static/file'
size = jobs.MAX_CONTENT_LENGTH + 1
httpretty.register_uri(
httpretty.GET, source_url,
body='a' * size,
content_type='application/json',
forcing_headers={
'content-length': None
})
jobs.push_to_datastore('fake_id', data, True)
def test_too_large_file(self):
"""It should raise JobError if the data file is too large.
If the data file is larger than MAX_CONTENT_LENGTH then the async
background job push_to_datastore should raise JobError
(ckanserviceprovider will catch this exception and return an error to
the client).
"""
self.register_urls()
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
# Override the source_url (already mocked by self.register_urls()
# above) with another mock response, this one mocks a response body
# that's bigger than MAX_CONTENT_LENGTH.
source_url = "http://www.source.org/static/file"
size = jobs.MAX_CONTENT_LENGTH + 1
httpretty.register_uri(
httpretty.GET, source_url, body="a" * size, content_length=size, content_type="application/json"
)
jobs.push_to_datastore("fake_id", data, True)
def test_simple_csv(self):
self.register_urls()
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
jobs.push_to_datastore("fake_id", data)
def test_simple_csv(self):
self.register_urls()
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
jobs.push_to_datastore('fake_id', data)
def test_simple_xls(self):
"""Test successfully fetching and parsing a simple XLS file.
When given dry_run=True and a resource with a simple XLS (Excel) file
the push_to_datastore job should fetch and parse the file and return
the right headers and data rows from the file.
"""
self.register_urls('simple.xls', 'xls', 'application/vnd.ms-excel')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{'type': 'timestamp', 'id': u'date'},
{'type': 'numeric', 'id': u'temperature'},
{'type': 'text', 'id': u'place'}])
assert_equal(len(results), 6)
assert_equal(results[0],
{u'date': datetime.datetime(2011, 1, 1, 0, 0),
u'place': u'Galway', u'temperature': 1})
def test_simple_xls(self):
"""Test successfully fetching and parsing a simple XLS file.
When given dry_run=True and a resource with a simple XLS (Excel) file
the push_to_datastore job should fetch and parse the file and return
the right headers and data rows from the file.
"""
self.register_urls("simple.xls", "xls", "application/vnd.ms-excel")
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
results = list(results)
assert_equal(
headers,
[
{"type": "timestamp", "id": u"date"},
{"type": "numeric", "id": u"temperature"},
{"type": "text", "id": u"place"},
],
)
assert_equal(len(results), 6)
assert_equal(results[0], {u"date": datetime.datetime(2011, 1, 1, 0, 0), u"place": u"Galway", u"temperature": 1})
def test_real_csv(self):
self.register_urls('october_2011.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{'type': 'text', 'id': u'Directorate'},
{'type': 'text', 'id': u'Service Area'},
{'type': 'text', 'id': u'Expenditure Category'},
{'type': 'timestamp', 'id': u'Payment Date'},
{'type': 'text', 'id': u'Supplier Name'},
{'type': 'numeric', 'id': u'Internal Ref'},
{'type': 'text', 'id': u'Capital/ Revenue'},
{'type': 'text', 'id': u'Cost Centre'},
{'type': 'text', 'id': u'Cost Centre Description'},
{'type': 'numeric', 'id': u'Grand Total'}])
assert_equal(len(results), 230)
assert_equal(results[0],
{u'Directorate': u'Adult and Culture',
u'Service Area': u'Ad Serv-Welfare Rights- ',
u'Expenditure Category': u'Supplies & Services',
u'Cost Centre Description': u'WELFARE RIGHTS WORKERS M',
u'Capital/ Revenue': u'Revenue',
u'Grand Total': 828.0,
u'Payment Date': datetime.datetime(2011, 10, 24, 0, 0),
u'Internal Ref': 5277184,
u'Cost Centre': u'1MR48',
u'Supplier Name': u'ALBANY OFFICE FURNITURE SOLUTIONS'})
def test_do_not_push_when_same_hash(self):
source_url, res_url = self.register_urls()
httpretty.register_uri(httpretty.POST, res_url,
body=json.dumps({
'success': True,
'result': {
'id': '32h4345k34h5l345',
'name': 'short name',
'url': source_url,
'format': 'csv',
'hash': '0ccb75d277ec2da41faae58642e3fb11'
}
}),
content_type='application/json')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
res = jobs.push_to_datastore('fake_id', data, True)
# res should be None because we didn't get to the part that
# returns something
assert not res, res
def test_bad_scheme(self):
"""It should raise HTTPError(JobError) if the resource.url is an
invalid scheme.
(ckanserviceprovider will catch this exception and return an error to
the client).
"""
self.register_urls(source_url='invalid://example.com')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
jobs.push_to_datastore('fake_id', data, True)
def test_too_large_file(self):
self.register_urls()
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
source_url = 'http://www.source.org/static/file'
size = jobs.MAX_CONTENT_LENGTH + 1
httpretty.register_uri(
httpretty.GET, source_url,
body='a' * size,
content_length=size,
content_type='application/json')
jobs.push_to_datastore('fake_id', data, True)
def test_content_length_string(self):
"""If the Content-Length header value is a string, just ignore it.
"""
self.register_urls()
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
source_url = 'http://www.source.org/static/file'
httpretty.register_uri(
httpretty.GET, source_url,
body='aaaaa',
content_type='application/json',
forcing_headers={
'Content-Length': 'some string'
})
jobs.push_to_datastore('fake_id', data, True)
def test_mostly_numbers(self):
self.register_urls('mixedGLB.csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 19)
assert_equal(len(results), 133)
def test_long_file(self):
self.register_urls('long.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 1)
assert_equal(len(results), 4000)
def test_real_csv(self):
"""Test fetching and parsing a more realistic CSV file.
When given dry_run=True and a resource with a CSV file, the
push_to_datastore job should return the right headers and rows from the
CSV file.
"""
self.register_urls("october_2011.csv", "csv")
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
results = list(results)
assert_equal(
headers,
[
{"type": "text", "id": u"Directorate"},
{"type": "text", "id": u"Service Area"},
{"type": "text", "id": u"Expenditure Category"},
{"type": "timestamp", "id": u"Payment Date"},
{"type": "text", "id": u"Supplier Name"},
{"type": "numeric", "id": u"Internal Ref"},
{"type": "text", "id": u"Capital/ Revenue"},
{"type": "text", "id": u"Cost Centre"},
{"type": "text", "id": u"Cost Centre Description"},
{"type": "numeric", "id": u"Grand Total"},
],
)
assert_equal(len(results), 230)
assert_equal(
results[0],
{
u"Directorate": u"Adult and Culture",
u"Service Area": u"Ad Serv-Welfare Rights- ",
u"Expenditure Category": u"Supplies & Services",
u"Cost Centre Description": u"WELFARE RIGHTS WORKERS M",
u"Capital/ Revenue": u"Revenue",
u"Grand Total": 828.0,
u"Payment Date": datetime.datetime(2011, 10, 24, 0, 0),
u"Internal Ref": 5277184,
u"Cost Centre": u"1MR48",
u"Supplier Name": u"ALBANY OFFICE FURNITURE SOLUTIONS",
},
)
def test_weird_header(self):
self.register_urls('weird_head_padding.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 11)
assert_equal(len(results), 82)
assert_equal(headers[1]['id'].strip(), u'1985')
assert_equal(results[1]['column_0'].strip(), u'Gefäßchirurgie')
def test_delete_404(self):
self.register_urls()
datastore_del_url = 'http://www.ckan.org/api/3/action/datastore_delete'
httpretty.register_uri(httpretty.POST, datastore_del_url,
status=404,
body=json.dumps({'success': False}),
content_type='application/json')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
def test_mostly_numbers(self):
"""Test fetching and parsing a CSV file that contains mostly numbers.
When given dry_run=True and a resource with a CSV file that contains
mostly numbers the push_to_datastore job should return the right
headers and rows from the CSV file.
"""
self.register_urls("mixedGLB.csv")
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
results = list(results)
assert_equal(len(headers), 19)
assert_equal(len(results), 133)
def test_long_file(self):
"""Test fetching and parsing a long CSV file.
When given dry_run=True and a resource with a long CSV file the
push_to_datastore job should return the right number of headers and
rows from the CSV file.
"""
self.register_urls("long.csv", "csv")
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
results = list(results)
assert_equal(len(headers), 1)
assert_equal(len(results), 4000)
def test_simple_csv(self):
self.register_urls()
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{'type': 'timestamp', 'id': u'date'},
{'type': 'numeric', 'id': u'temperature'},
{'type': 'text', 'id': u'place'}])
assert_equal(len(results), 6)
assert_equal(results[0],
{u'date': datetime.datetime(2011, 1, 1, 0, 0), u'place': u'Galway', u'temperature': 1})
def test_do_not_push_when_same_hash(self):
"""A file should not be pushed if it hasn't changed.
If a resource's file has already been added to the datastore and then
the datapusher's push_to_datastore job fetchess and parses it again
and the file has not changed, then push_to_datastore should return
None rather than parsing the file and returning headers and rows.
FIXME:
This relies on a return statement early in the push_to_datastore
function, this doesn't seem like a great way to test that the file
was not pushed.
"""
source_url, res_url = self.register_urls()
httpretty.register_uri(
httpretty.POST,
res_url,
body=json.dumps(
{
"success": True,
"result": {
"id": "32h4345k34h5l345",
"name": "short name",
"url": source_url,
"format": "csv",
"hash": "0ccb75d277ec2da41faae58642e3fb11",
},
}
),
content_type="application/json",
)
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
res = jobs.push_to_datastore("fake_id", data, True)
# res should be None because we didn't get to the part that
# returns something
assert not res, res
def test_do_not_push_when_same_hash(self):
"""A file should not be pushed if it hasn't changed.
If a resource's file has already been added to the datastore and then
the datapusher's push_to_datastore job fetchess and parses it again
and the file has not changed, then push_to_datastore should return
None rather than parsing the file and returning headers and rows.
FIXME:
This relies on a return statement early in the push_to_datastore
function, this doesn't seem like a great way to test that the file
was not pushed.
"""
source_url, res_url = self.register_urls()
httpretty.register_uri(
httpretty.POST, res_url,
body=json.dumps({
'success': True,
'result': {
'id': '32h4345k34h5l345',
'name': 'short name',
'url': source_url,
'format': 'csv',
'hash': '0ccb75d277ec2da41faae58642e3fb11'
}
}),
content_type='application/json')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
res = jobs.push_to_datastore('fake_id', data, True)
# res should be None because we didn't get to the part that
# returns something
assert not res, res
def test_weird_header(self):
"""Test fetching and parsing a CSV file with "weird" header padding.
When given dry_run=True and a resource with a CSV file with weird
header padding the push_to_datastore job should return the right
headers and rows from the CSV file.
"""
self.register_urls("weird_head_padding.csv", "csv")
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
results = list(results)
assert_equal(len(headers), 9)
assert_equal(len(results), 82)
assert_equal(headers[0]["id"].strip(), u"1985")
assert_equal(results[1]["1993"].strip(), u"379")
def test_delete_404(self):
self.register_urls()
# Override the mocked datastore_delete URL with another mock response
# that returns a 404.
datastore_del_url = "http://www.ckan.org/api/3/action/datastore_delete"
httpretty.register_uri(
httpretty.POST,
datastore_del_url,
status=404,
body=json.dumps({"success": False}),
content_type="application/json",
)
data = {
"api_key": self.api_key,
"job_type": "push_to_datastore",
"metadata": {"ckan_url": "http://%s/" % self.host, "resource_id": self.resource_id},
}
headers, results = jobs.push_to_datastore("fake_id", data, True)
def test_mostly_numbers(self):
"""Test fetching and parsing a CSV file that contains mostly numbers.
When given dry_run=True and a resource with a CSV file that contains
mostly numbers the push_to_datastore job should return the right
headers and rows from the CSV file.
"""
self.register_urls('mixedGLB.csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 19)
assert_equal(len(results), 133)
def test_long_file(self):
"""Test fetching and parsing a long CSV file.
When given dry_run=True and a resource with a long CSV file the
push_to_datastore job should return the right number of headers and
rows from the CSV file.
"""
self.register_urls('long.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 1)
assert_equal(len(results), 4000)
def test_simple_ssv(self):
"""Test successfully fetching and parsing a simple SSV file.
When given dry_run=True and a resource with a simple SSV
(semicolon-separated values) file the push_to_datastore job should
fetch and parse the file and return the right headers and data rows
from the file.
"""
self.register_urls('simple.ssv', 'csv', 'application/csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{
'type': 'timestamp',
'id': u'date'
}, {
'type': 'numeric',
'id': u'temperature'
}, {
'type': 'text',
'id': u'place'
}])
assert_equal(len(results), 6)
assert_equal(
results[0], {
u'date': datetime.datetime(2011, 1, 1, 0, 0),
u'place': u'Galway',
u'temperature': 1
})
def test_weird_header(self):
"""Test fetching and parsing a CSV file with "weird" header padding.
When given dry_run=True and a resource with a CSV file with weird
header padding the push_to_datastore job should return the right
headers and rows from the CSV file.
"""
self.register_urls('weird_head_padding.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 9)
assert_equal(len(results), 82)
assert_equal(headers[0]['id'].strip(), u'1985')
assert_equal(results[1]['1993'].strip(), u'379')
def test_weird_header(self):
"""Test fetching and parsing a CSV file with "weird" header padding.
When given dry_run=True and a resource with a CSV file with weird
header padding the push_to_datastore job should return the right
headers and rows from the CSV file.
"""
self.register_urls('weird_head_padding.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(len(headers), 9)
assert_equal(len(results), 82)
assert_equal(headers[0]['id'].strip(), u'1985')
assert_equal(results[1]['1993'].strip(), u'379')
def test_csv_with_html_content_type(self):
"""Test successfully fetching and parsing a simple CSV file when the
content type specified is text/html not csv.
"""
self.register_urls(content_type="text/html")
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{'type': 'timestamp', 'id': 'date'},
{'type': 'numeric', 'id': 'temperature'},
{'type': 'text', 'id': 'place'}])
assert_equal(len(results), 6)
assert_equal(
results[0],
{'date': datetime.datetime(2011, 1, 1, 0, 0), 'place': 'Galway',
'temperature': 1})
def test_real_csv(self):
"""Test fetching and parsing a more realistic CSV file.
When given dry_run=True and a resource with a CSV file, the
push_to_datastore job should return the right headers and rows from the
CSV file.
"""
self.register_urls('october_2011.csv', 'csv')
data = {
'api_key': self.api_key,
'job_type': 'push_to_datastore',
'metadata': {
'ckan_url': 'http://%s/' % self.host,
'resource_id': self.resource_id
}
}
headers, results = jobs.push_to_datastore('fake_id', data, True)
results = list(results)
assert_equal(headers, [{
'type': 'text',
'id': u'Directorate'
}, {
'type': 'text',
'id': u'Service Area'
}, {
'type': 'text',
'id': u'Expenditure Category'
}, {
'type': 'timestamp',
'id': u'Payment Date'
}, {
'type': 'text',
'id': u'Supplier Name'
}, {
'type': 'numeric',
'id': u'Internal Ref'
}, {
'type': 'text',
'id': u'Capital/ Revenue'
}, {
'type': 'text',
'id': u'Cost Centre'
}, {
'type': 'text',
'id': u'Cost Centre Description'
}, {
'type': 'numeric',
'id': u'Grand Total'
}])
assert_equal(len(results), 230)
assert_equal(
results[0], {
u'Directorate': u'Adult and Culture',
u'Service Area': u'Ad Serv-Welfare Rights- ',
u'Expenditure Category': u'Supplies & Services',
u'Cost Centre Description': u'WELFARE RIGHTS WORKERS M',
u'Capital/ Revenue': u'Revenue',
u'Grand Total': 828.0,
u'Payment Date': datetime.datetime(2011, 10, 24, 0, 0),
u'Internal Ref': 5277184,
u'Cost Centre': u'1MR48',
u'Supplier Name': u'ALBANY OFFICE FURNITURE SOLUTIONS'
})