Skip to content

Adiciona estratégia para lidar com problemas de padronização de dados durante URL Translation #102

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
pitangainnovare merged 2 commits into from
Jun 16, 2025
Merged

Adiciona estratégia para lidar com problemas de padronização de dados durante URL Translation #102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f38caa2
Atualiza para versão 1.12.1
pitangainnovare Jun 16, 2025
0294700
Cria método para extrair dados, lidando com problemas de padronização
pitangainnovare Jun 16, 2025
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
2 changes: 1 addition & 1 deletion VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
1.12.0
1.12.1
42 changes: 31 additions & 11 deletions metrics/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,18 +277,13 @@ def _process_line(line, utm, log_file):
except Exception as e:
_log_discarded_line(log_file, line, tracker_choices.LOG_FILE_DISCARDED_LINE_REASON_URL_TRANSLATION, str(e))
return False

try:
item_access_data = _extract_item_access_data(log_file.collection.acron3, translated_url)
except Exception as e:
_log_discarded_line(log_file, line, tracker_choices.LOG_FILE_DISCARDED_LINE_REASON_URL_TRANSLATION, str(e))
return False

item_access_data = {
'collection': log_file.collection.acron3,
'scielo_issn': translated_url.get('scielo_issn'),
'pid_v2': standardizer.standardize_pid_v2(translated_url.get('pid_v2')),
'pid_v3': standardizer.standardize_pid_v3(translated_url.get('pid_v3')),
'pid_generic': standardizer.standardize_pid_generic(translated_url.get('pid_generic')),
'media_language': standardizer.standardize_language_code(translated_url.get('media_language')),
'media_format': translated_url.get('media_format'),
'content_type': translated_url.get('content_type'),
}

if not is_valid_item_access_data(item_access_data):
_log_discarded_line(
log_file, line,
Expand Down Expand Up @@ -324,6 +319,31 @@ def _process_line(line, utm, log_file):
return True


def _extract_item_access_data(collection_acron3, translated_url):
"""
Extracts item access data from the translated URL and standardizes it.

Args:
collection_acron3 (str): The acronym of the collection.
translated_url (dict): The translated URL containing metadata.

Returns:
dict: A dictionary containing standardized item access data, or None if the data is invalid.
"""
item_access_data = {
'collection': collection_acron3,
'scielo_issn': translated_url.get('scielo_issn'),
'pid_v2': standardizer.standardize_pid_v2(translated_url.get('pid_v2')),
'pid_v3': standardizer.standardize_pid_v3(translated_url.get('pid_v3')),
'pid_generic': standardizer.standardize_pid_generic(translated_url.get('pid_generic')),
'media_language': standardizer.standardize_language_code(translated_url.get('media_language')),
'media_format': translated_url.get('media_format'),
'content_type': translated_url.get('content_type'),
}

return item_access_data


def _register_item_access(item_access_data, line, jou_id, art_id):
"""
Registers an item access in the database, creating necessary objects if they do not exist.
Expand Down