Merge pull request #976 from NASA-IMPACT/975-fix-flake8-problems-to-g…

…et-pre-commit-passing

Fix fake flake8 issues

config/settings/production.py

@@ -70,11 +70,11 @@
 # ------------------------
 STATICFILES_STORAGE = "sde_indexing_helper.utils.storages.StaticRootS3Boto3Storage"
 COLLECTFAST_STRATEGY = "collectfast.strategies.boto3.Boto3Strategy"
-STATIC_URL = f"https://{aws_s3_domain}/static/"
+STATIC_URL = f"https://{aws_s3_domain}/static/"  # noqa: E231
 # MEDIA
 # ------------------------------------------------------------------------------
 DEFAULT_FILE_STORAGE = "sde_indexing_helper.utils.storages.MediaRootS3Boto3Storage"
-MEDIA_URL = f"https://{aws_s3_domain}/media/"
+MEDIA_URL = f"https://{aws_s3_domain}/media/"  # noqa: E231
 
 # EMAIL
 # ------------------------------------------------------------------------------

config_generation/db_to_xml_file_based.py

@@ -98,7 +98,7 @@ def update_or_add_element_value(
         parent_element = xml_root if not parent_element_name else xml_root.find(parent_element_name)
 
         if parent_element is None:
-            raise ValueError(f"Parent element '{parent_element_name}' not found in XML.")
+            raise ValueError(f"Parent element '{parent_element_name}' not found in XML.")  # noqa: E713
 
         existing_element = parent_element.find(element_name)
         if not add_duplicate and existing_element:

feedback/models.py

@@ -33,7 +33,7 @@ def format_notification_message(self):
         Returns a formatted notification message containing details from this Feedback instance.
         """
         notification_message = (
-            f"<!here> New Feedback Received : \n"
+            f"<!here> New Feedback Received : \n"  # noqa: E203
             f"Name: {self.name}\n"
             f"Email: {self.email}\n"
             f"Subject: {self.subject}\n"

scraper/url_grouper.py

@@ -42,10 +42,12 @@
     output_file.write(f"<h1>{BASE_URL}</h1>\n")
     output_file.write("<ul>\n")
     for key, value in my_dict.items():
-        output_file.write(f'<li><a href="{PROTOCOL}://{BASE_URL}{key}" target=_blank>{key}</a>\n')
+        output_file.write(f'<li><a href="{PROTOCOL}://{BASE_URL}{key}" target=_blank>{key}</a>\n')  # noqa: E231
         output_file.write("<ul>\n")
         for item in value:
-            output_file.write(f'<li><a href="{PROTOCOL}://{BASE_URL}{key}/{item}" target=_blank>{item}</a></li>\n')
+            output_file.write(
+                f'<li><a href="{PROTOCOL}://{BASE_URL}{key}/{item}" target=_blank>{item}</a></li>\n'  # noqa: E231
+            )
         output_file.write("</ul>\n")
         output_file.write("</li>\n")
     output_file.write("</ul>\n")

scripts/ej/create_ej_dump.py

@@ -1,6 +1,7 @@
 """
 inferences are supplied by the classification model. the contact point is Bishwas
-cmr is supplied by running https://github.com/NASA-IMPACT/llm-app-EJ-classifier/blob/develop/scripts/data_processing/download_cmr.py
+cmr is supplied by running
+github.com/NASA-IMPACT/llm-app-EJ-classifier/blob/develop/scripts/data_processing/download_cmr.py
 move to the serve like this: scp ej_dump_20240814_143036.json  sde:/home/ec2-user/sde_indexing_helper/backups/
 """
 

scripts/find_redirects_solar_urls.py

@@ -43,9 +43,9 @@ def csv_to_dict_list(file_path):
             scraped_title = soup.find("title").text.strip() if soup.find("title") else ""
         except (AssertionError, Exception) as parse_error:
             scraped_title = ""
-            print(f"Error parsing URL {url_info['url']}: {parse_error}")
+            print(f"Error parsing URL {url_info['url']}: {parse_error}")  # noqa: F821
     except requests.RequestException as e:
-        print(f"Error fetching URL {url_info['url']}: {e}")
+        print(f"Error fetching URL {url_info['url']}: {e}")  # noqa: F821
         response_url = ""
         scraped_title = ""
 

scripts/quality_and_indexing/restore_deleted_files.py

@@ -1,5 +1,6 @@
 """
-you need to run this script in the root of the repository that from which the file was deleted, in this case the root of the sinequa_configs repository.
+you need to run this script in the root of the repository that from which the file was deleted,
+in this case the root of the sinequa_configs repository.
 """
 
 import subprocess

sde_collections/admin.py

@@ -154,7 +154,7 @@ def export_as_csv(self, request, queryset):
         field_names = [field.name for field in meta.fields]
 
         response = HttpResponse(content_type="text/csv")
-        response["Content-Disposition"] = f"attachment; filename={meta}.csv"
+        response["Content-Disposition"] = f"attachment; filename={meta}.csv"  # noqa: E702
         writer = csv.writer(response)
 
         writer.writerow(field_names)

sde_collections/models/collection.py

@@ -4,7 +4,6 @@
 import requests
 from django.contrib.auth import get_user_model
 from django.db import models
-from django.db.models import Q
 from django.db.models.signals import post_save
 from django.dispatch import receiver
 from model_utils import FieldTracker
@@ -130,7 +129,7 @@ def tree_root(self) -> str:
 
     @property
     def server_url_secret_prod(self) -> str:
-        base_url = "https://sciencediscoveryengine.nasa.gov"
+        base_url = "https://sciencediscoveryengine.nasa.gov"  # noqa: E231
         payload = {
             "name": "secret-prod",
             "scope": "All",
@@ -144,7 +143,7 @@ def server_url_secret_prod(self) -> str:
 
     @property
     def server_url_prod(self) -> str:
-        base_url = "https://sciencediscoveryengine.nasa.gov"
+        base_url = "https://sciencediscoveryengine.nasa.gov"  # noqa: E231
         payload = {
             "name": "query-smd-primary",
             "scope": "All",
@@ -371,13 +370,12 @@ def candidate_urls_count(self) -> int:
 
     @property
     def sinequa_configuration(self) -> str:
-        return (
-            f"https://github.com/NASA-IMPACT/sde-backend/blob/production/sources/SDE/{self.config_folder}/default.xml"
-        )
+        URL = f"https://github.com/NASA-IMPACT/sde-backend/blob/production/sources/SDE/{self.config_folder}/default.xml"  # noqa: E231, E501
+        return URL
 
     @property
     def github_issue_link(self) -> str:
-        return f"https://github.com/NASA-IMPACT/sde-project/issues/{self.github_issue_number}"
+        return f"https://github.com/NASA-IMPACT/sde-project/issues/{self.github_issue_number}"  # noqa: E231
 
     @classmethod
     def _fetch_json_results(cls, url):

sde_collections/models/pattern.py

@@ -143,7 +143,7 @@ def validate_title_pattern(title_pattern_string):
 
         if element_type == "xpath":
             if not is_valid_xpath(element_value):
-                raise ValidationError(f"'xpath:{element_value}' is not a valid xpath.")
+                raise ValidationError(f"'xpath:{element_value}' is not a valid xpath.")  # noqa: E231
         elif element_type == "brace":
             try:
                 is_valid_fstring(element_value)

sde_collections/utils/health_check.py

@@ -127,12 +127,12 @@ def create_exclude_pattern_report(match_pattern, url):
 
         # check with http://
         if match_pattern.find("http://") == -1:
-            url = f"http://{match_pattern}"
+            url = f"http://{match_pattern}"  # noqa: E231
             if url in candidate_urls_sinequa:
                 exclude_pattern_report.append(create_exclude_pattern_report(match_pattern, url))
 
         if match_pattern.find("https://") == -1:
-            url = f"https://{match_pattern}"
+            url = f"https://{match_pattern}"  # noqa: E231
             if url in candidate_urls_sinequa:
                 exclude_pattern_report.append(create_exclude_pattern_report(match_pattern, url))
         else:

sde_collections/utils/slack_utils.py

@@ -90,7 +90,7 @@
 def format_slack_message(name, details, collection_id):
     message_template = details["message"]
     tags = " ".join([f"<{user}>" for user in details["tags"]])
-    link = f"https://sde-indexing-helper.nasa-impact.net/{collection_id}/"
+    link = f"https://sde-indexing-helper.nasa-impact.net/{collection_id}/"  # noqa: E231
     linked_name = f"<{link}|{name}>"
     return tags + " " + message_template.format(name=linked_name)
 
@@ -101,5 +101,5 @@ def send_slack_message(message):
     response = requests.post(webhook_url, json=payload)
     if response.status_code != 200:
         raise ValueError(
-            f"Request to Slack returned an error {response.status_code}, the response is:\n{response.text}"
+            f"Request to Slack returned an error {response.status_code}, the response is:\n{response.text}"  # noqa: E231, E501
         )

sde_collections/utils/title_resolver.py

@@ -32,7 +32,7 @@ def is_valid_fstring(pattern: str) -> bool:
             if node.value.id not in context:
                 variables_allowed = ", ".join([key for key in context.keys()])
                 raise ValueError(
-                    f"Variable '{node.value.id}' not allowed in f-string pattern."
+                    f"Variable '{node.value.id}' not allowed in f-string pattern."  # noqa: E713
                     f" Allowed variables are: {variables_allowed}"
                 )