Skip to content
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

merge dev to staging: prevent indexing empty file #400

Merged
merged 6 commits into from
Jul 29, 2024
Merged

merge dev to staging: prevent indexing empty file #400

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
73f6398
bulk update handle case where name field value has too many * chars
lizkrznarich May 1, 2024
ea1f523
Merge pull request #397 from ror-community/handle-error-multiple-lang…
lizkrznarich May 1, 2024
a0fe3a6
add error and sys exit if dump zip contains a directory
lizkrznarich Jul 25, 2024
3713bcc
Merge pull request #398 from ror-community/dump-index-error-if-extra-dir
lizkrznarich Jul 25, 2024
5687759
pass msg back to view in case of error
lizkrznarich Jul 25, 2024
b7b9aff
Merge pull request #399 from ror-community/dump-index-error-if-extra-dir
lizkrznarich Jul 25, 2024
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
29 changes: 17 additions & 12 deletions rorapi/common/csv_create.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,21 +54,26 @@ def new_record_from_csv(csv_data, version):
if csv_data['names.types.' + v]:
for n in csv_data['names.types.' + v].strip(';').split(';'):
if LANG_DELIMITER in n:
name_val, lang = n.split("*")
if lang:
lang_errors, lang_code = get_lang_code(lang.strip())
if lang_errors:
errors.append("Could not convert language value to ISO code: {}".format(lang))
if n.count(LANG_DELIMITER) == 1:
name_val, lang = n.split("*")
if lang:
lang_errors, lang_code = get_lang_code(lang.strip())
if lang_errors:
errors.append("Could not convert language value to ISO code: {}".format(lang))
else:
name_val = None
lang_code = None
errors.append("Could not parse name value {} in names.types.{} because it contains multiple {} lang delimiter chars.".format(n, v, LANG_DELIMITER))
else:
name_val = n
lang_code = None

name_obj = {
"types": [v],
"value": name_val.strip(),
"lang": lang_code
}
temp_names.append(name_obj)
if name_val:
name_obj = {
"types": [v],
"value": name_val.strip(),
"lang": lang_code
}
temp_names.append(name_obj)
print("temp names 1:")
print(temp_names)
name_vals = [n['value'] for n in temp_names]
Expand Down
23 changes: 13 additions & 10 deletions rorapi/common/csv_update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,18 +247,21 @@ def update_record_from_csv(csv_data, version):
"lang": None
}
if LANG_DELIMITER in val:
print("has lang delim")
name_val, lang = val.split("*")
vals_obj["value"] = name_val.strip()
if lang:
lang_errors, lang_code = get_lang_code(lang.strip())
if lang_errors:
errors.append("Could not convert language value to ISO code: {}".format(lang))
else:
vals_obj["lang"] = lang_code
if val.count(LANG_DELIMITER) == 1:
name_val, lang = val.split("*")
vals_obj["value"] = name_val.strip()
if lang:
lang_errors, lang_code = get_lang_code(lang.strip())
if lang_errors:
errors.append("Could not convert language value to ISO code: {}".format(lang))
else:
vals_obj["lang"] = lang_code
else:
errors.append("Could not parse name value {} in names.types.{} because it contains multiple {} lang delimiter chars.".format(val, t, LANG_DELIMITER))
else:
vals_obj["value"] = val.strip()
vals_obj_list.append(vals_obj)
if vals_obj["value"]:
vals_obj_list.append(vals_obj)
actions_values[k] = vals_obj_list
print("updated actions values")
print(actions_values)
Expand Down
12 changes: 9 additions & 3 deletions rorapi/management/commands/getrordump.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ def get_ror_dump_sha(filename, use_test_data, github_headers):
except:
return None

def get_ror_dump_zip(filename, use_test_data, github_headers):
def get_ror_dump_zip(self, filename, use_test_data, github_headers):
sha = get_ror_dump_sha(filename, use_test_data, github_headers)
if sha:
if use_test_data:
Expand All @@ -46,9 +46,14 @@ def get_ror_dump_zip(filename, use_test_data, github_headers):
file_decoded = base64.b64decode(response_json['content'])
with open(filename + '.zip', 'wb') as zip_file:
zip_file.write(file_decoded)
with zipfile.ZipFile(zip_file.name, 'r') as ror_zip:
filenames = ror_zip.namelist()
dir_names = [f for f in filenames if ('json' not in f and 'csv' not in f)]
if dir_names:
raise SystemExit(f"Dump zip has extra directory and cannot be indexed")
return zip_file.name
except:
return None
raise SystemExit(f"Something went wrong saving zip file")

class Command(BaseCommand):
help = 'Downloads a specified ROR data dump from Github'
Expand All @@ -61,4 +66,5 @@ def handle(self, *args, **options):
github_headers = AUTH_HEADERS
else:
github_headers = HEADERS
ror_dump_zip = get_ror_dump_zip(filename, use_test_data, github_headers)
ror_dump_zip = get_ror_dump_zip(self, filename, use_test_data, github_headers)

37 changes: 20 additions & 17 deletions rorapi/management/commands/indexrordump.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,23 +114,26 @@ def handle(self, *args, **options):
for file in unzipped_files:
if file.endswith(".json"):
json_files.append(file)
for json_file in json_files:
index = None
json_path = os.path.join(DATA['WORKING_DIR'], filename, '') + json_file
if 'schema_v2' in json_file and (options['schema']==2 or options['schema'] is None):
self.stdout.write('Loading JSON')
with open(json_path, 'r') as it:
dataset = json.load(it)
self.stdout.write('Indexing ROR dataset ' + json_file)
index = ES_VARS['INDEX_V2']
index_dump(self, json_file, index, dataset)
if 'schema_v2' not in json_file and (options['schema']==1 or options['schema'] is None):
self.stdout.write('Loading JSON')
with open(json_path, 'r') as it:
dataset = json.load(it)
self.stdout.write('Indexing ROR dataset ' + json_file)
index = ES_VARS['INDEX_V1']
index_dump(self, json_file, index, dataset)
if json_files:
for json_file in json_files:
index = None
json_path = os.path.join(DATA['WORKING_DIR'], filename, '') + json_file
if 'schema_v2' in json_file and (options['schema']==2 or options['schema'] is None):
self.stdout.write('Loading JSON')
with open(json_path, 'r') as it:
dataset = json.load(it)
self.stdout.write('Indexing ROR dataset ' + json_file)
index = ES_VARS['INDEX_V2']
index_dump(self, json_file, index, dataset)
if 'schema_v2' not in json_file and (options['schema']==1 or options['schema'] is None):
self.stdout.write('Loading JSON')
with open(json_path, 'r') as it:
dataset = json.load(it)
self.stdout.write('Indexing ROR dataset ' + json_file)
index = ES_VARS['INDEX_V1']
index_dump(self, json_file, index, dataset)
else:
self.stdout.write("ROR data dump does not contain any JSON files")

else:
self.stdout.write("ROR data dump zip file does not exist")
13 changes: 8 additions & 5 deletions rorapi/management/commands/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,11 +52,14 @@ def handle(self, *args, **options):
sha = get_ror_dump_sha(filename, use_test_data)

if sha:
GetRorDumpCommand().handle(*args, **options)
DeleteIndexCommand().handle(*args, **options)
CreateIndexCommand().handle(*args, **options)
IndexRorDumpCommand().handle(*args, **options)
msg = 'SUCCESS: ROR dataset {} indexed in version {}. Using test repo: {}'.format(filename, str(options['schema']), str(use_test_data))
try:
GetRorDumpCommand().handle(*args, **options)
DeleteIndexCommand().handle(*args, **options)
CreateIndexCommand().handle(*args, **options)
IndexRorDumpCommand().handle(*args, **options)
msg = 'SUCCESS: ROR dataset {} indexed in version {}. Using test repo: {}'.format(filename, str(options['schema']), str(use_test_data))
except:
msg = 'ERROR: Could not index ROR data dump. Check API logs for details.'
else:
msg = 'ERROR: ROR dataset for file {} not found. '.format(filename) \
+'Please generate the data dump first.'
Expand Down
Loading