use shared.path_join

Author: TimidRobot

dev/create_gcs_query_plan.py

@@ -116,7 +116,7 @@ def sort_tools(url):
 
 def get_tool_urls():
     LOGGER.info("Loading CC Legal Tool paths and adding prefix")
-    file_path = os.path.join(PATHS["data"], "legal-tool-paths.txt")
+    file_path = shared.path_join(PATHS["data"], "legal-tool-paths.txt")
     prefix = "//creativecommons.org/"
     tool_urls = []
     with open(file_path, "r") as file_obj:
@@ -128,14 +128,14 @@ def get_tool_urls():
 
 
 def load_countries():
-    file_path = os.path.join(PATHS["data"], "gcs_country_collection.yaml")
+    file_path = shared.path_join(PATHS["data"], "gcs_country_collection.yaml")
     with open(file_path, "r") as file_obj:
         countries = yaml.safe_load(file_obj)
     return countries
 
 
 def load_languages():
-    file_path = os.path.join(PATHS["data"], "gcs_language_collection.yaml")
+    file_path = shared.path_join(PATHS["data"], "gcs_language_collection.yaml")
     with open(file_path, "r") as file_obj:
         languages = yaml.safe_load(file_obj)
     return languages
@@ -202,7 +202,7 @@ def create_query_plan(tool_urls, countries, languages):
 
 def save_plan(plan):
     LOGGER.info("Saving Google query plan to CSV")
-    file_path = os.path.join(PATHS["data"], "gcs_query_plan.csv")
+    file_path = shared.path_join(PATHS["data"], "gcs_query_plan.csv")
     fieldnames = [
         "TOOL_URL",
         "TOOL_IDENTIFIER",

dev/prioritize_tools.py

@@ -39,7 +39,7 @@
 
 def get_tool_urls():
     LOGGER.info("Loading CC Legal Tool paths and adding prefix")
-    file_path = os.path.join(PATHS["data"], "legal-tool-paths.txt")
+    file_path = shared.path_join(PATHS["data"], "legal-tool-paths.txt")
     prefix = "//creativecommons.org/"
     tool_urls = []
     with open(file_path, "r") as file_obj:
@@ -110,7 +110,7 @@ def sort_tools(path):
 
 def save_tools_list(tool_urls):
     LOGGER.info("Saving prioritized CC Legal Tool URLs")
-    file_path = os.path.join(PATHS["data"], "prioritized-tool-urls.txt")
+    file_path = shared.path_join(PATHS["data"], "prioritized-tool-urls.txt")
     tool_urls.append("")  # ensure file has end of file newline
     with open(file_path, "w") as file_obj:
         file_obj.writelines("\n".join(tool_urls))

scripts/1-fetch/gcs_fetch.py

@@ -143,7 +143,7 @@ def get_last_completed_plan_index():
 
 def load_plan():
     plan = []
-    file_path = os.path.join(PATHS["data"], "gcs_query_plan.csv")
+    file_path = shared.path_join(PATHS["data"], "gcs_query_plan.csv")
     with open(file_path, "r", newline="") as file_obj:
         plan = list(csv.DictReader(file_obj, dialect="unix"))
     return plan

scripts/shared.py

@@ -32,18 +32,18 @@ def setup(current_file):
     # Paths
     paths = {}
     paths["repo"] = os.path.dirname(path_join(__file__, ".."))
-    paths["dotenv"] = os.path.join(paths["repo"], ".env")
+    paths["dotenv"] = path_join(paths["repo"], ".env")
     paths["data"] = os.path.dirname(
         os.path.abspath(os.path.realpath(current_file))
     )
     current_phase = os.path.basename(
         os.path.dirname(os.path.abspath(os.path.realpath(current_file)))
     )
-    paths["data"] = os.path.join(paths["repo"], "data")
-    data_quarter = os.path.join(paths["data"], f"{quarter}")
+    paths["data"] = path_join(paths["repo"], "data")
+    data_quarter = path_join(paths["data"], f"{quarter}")
     for phase in ["1-fetch", "2-process", "3-report"]:
-        paths[f"data_{phase}"] = os.path.join(data_quarter, phase)
-    paths["data_phase"] = os.path.join(data_quarter, current_phase)
+        paths[f"data_{phase}"] = path_join(data_quarter, phase)
+    paths["data_phase"] = path_join(data_quarter, current_phase)
 
     paths["data_quarter"] = data_quarter
 
@@ -141,7 +141,7 @@ def update_readme(
     """
     Update the README.md file with the generated images and descriptions.
     """
-    readme_path = os.path.join(paths["data"], args.quarter, "README.md")
+    readme_path = path_join(paths["data"], args.quarter, "README.md")
 
     # Define section markers for each data source
     section_marker_start = f"<!-- {data_source} Start -->"