Fix: cleanup unused code and comments

pyproject.toml

@@ -59,7 +59,7 @@ license = { text = "MIT" }
 # for a user to run directly from the package.
 [project.scripts] # Optional
 update-contributors = "pyosmeta.cli.update_contributors:main"
-process-reviews = "pyosmeta.cli.process_reviews:main"
+update-reviews = "pyosmeta.cli.process_reviews:main"
 update-review-teams = "pyosmeta.cli.update_review_teams:main"
 
 

src/pyosmeta/__init__.py

@@ -1,6 +1,8 @@
 from .contributors import PersonModel, ProcessContributors
 from .parse_issues import ProcessIssues, ReviewModel
 
+# Trick suggested by flake8 maintainer to ensure the imports above don't
+# get flagged as being "unused"
 __all__ = (
     "ProcessIssues",
     "ReviewModel",

src/pyosmeta/cli/process_reviews.py

@@ -17,82 +17,33 @@
 # ideally this could be passed as a CLI argument with the label we want to
 # search for
 
-
-# import argparse
 import pickle
 
 from pydantic import ValidationError
 
 from pyosmeta import ProcessIssues, ReviewModel
 
-# from pyosmeta.file_io import load_website_yml
-
-
 # TODO: change the template to ask for date accepted format year-month-day
 
 
 def main():
-    # update_all = False
-    # parser = argparse.ArgumentParser(
-    #     description="A CLI script to update pyOpenSci reviews"
-    # )
-    # parser.add_argument(
-    #     "--update",
-    #     type=str,
-    #     help="Will force update review info from GitHub for every review",
-    # )
-    # args = parser.parse_args()
-
-    # if args:
-    #     update_all = True
-    # web_reviews_path = (
-    #     "https://raw.githubusercontent.com/pyOpenSci/"
-    #     "pyopensci.github.io/main/_data/packages.yml"
-    # )
-
     process_review = ProcessIssues(
         org="pyopensci",
         repo_name="software-submission",
         label_name="6/pyOS-approved 🚀🚀🚀",
     )
 
-    # Open web yaml & return dict with package name as key
-    # web_reviews = load_website_yml(key="package_name", url=web_reviews_path)
-
     # Get all issues for approved packages - load as dict
     issues = process_review.return_response()
     accepted_reviews = process_review.parse_issue_header(issues, 45)
 
-    # TODO: clean out extra fields from accepted reviews??
-
-    # Parse through reviews, identify new ones, fix case
-    # TODO - right now i've reverted back to always updating all reviews.
-    # Is there a use-case to only update a new package vs updating everything?
-    # if update_all:
-    # all_reviews = {}
-    # for key, meta in accepted_reviews.items():
-    #     try:
-    #         all_reviews[key.lower()] = ReviewModel(**meta)
-    #     except ValidationError as ve:
-    #         print(ve)
-
-    # else:
-    #     for key, meta in accepted_reviews.items():
-    #         if key.lower() not in all_reviews.keys():
-    #             print("Yay - pyOS has a new package:", key)
-    #             all_reviews[key.lower()] = ReviewModel(**meta)
-
     # Update gh metrics via api for all packages
-    # TODO: this is working but above i made everything a model object
-    # do i want to do that above or just do it all at once below?
     repo_endpoints = process_review.get_repo_endpoints(accepted_reviews)
     all_reviews = process_review.get_gh_metrics(
         repo_endpoints, accepted_reviews
     )
 
-    # Finally populate model objects with review data + metrics
-    # TODO: this is really close - it's erroring when populating date
-    # i suspect in the github metadata
+    # Populate model objects with review data + metrics
     final_reviews = {}
     for key, review in all_reviews.items():
         # First add gh meta to each dict

src/pyosmeta/cli/update_contributors.py

@@ -50,7 +50,7 @@ def main():
     # Populate all existing contribs into model objects
     all_contribs = {}
     for a_contrib in web_contribs:
-        print(a_contrib)
+        print(a_contrib["github_username"])
         try:
             all_contribs[a_contrib["github_username"].lower()] = PersonModel(
                 **a_contrib

src/pyosmeta/cli/update_review_teams.py

@@ -19,17 +19,8 @@
 # TODO: package-wide feature: create no update flag for entries
 # TODO: make sure we can add a 3rd or 4th reviewer - crowsetta has this as
 # will biocypher
-# TODO: make sure to add a current editor boolean to the current editors and
-# emeritus ones.
 
 """
-
-# TODO - Case sensitivity is an issue with my validation using set
-#     - jointly
-# - Jointly
-# - devicely
-# - Devicely
-# - sevivi
 import os
 
 from pydantic import ValidationError
@@ -45,8 +36,6 @@ def get_clean_user(username: str) -> str:
 
 
 def main():
-    # TODO: move refresh contribs and contribs dict attr to
-    # processContribs and remove this module altogether
     process_contribs = ProcessContributors([])
 
     # Two pickle files are outputs of the two other scripts
@@ -129,7 +118,6 @@ def main():
 
     # Export to yaml
     contribs_ls = [model.model_dump() for model in contribs.values()]
-    # Getting error dumping packages
     pkgs_ls = [model.model_dump() for model in packages.values()]
 
     clean_export_yml(contribs_ls, os.path.join("_data", "contributors.yml"))

src/pyosmeta/contributors.py

@@ -13,11 +13,11 @@
     field_serializer,
     field_validator,
 )
-from typing import Dict, List, Optional, Set, Tuple, Union
+from typing import List, Optional, Set, Tuple, Union
 
 
 class UrlValidatorMixin:
-    # Check fields is false because this is being inherited by two diff classes
+    # Check fields is false given mixin is used by two diff classes
     @field_validator(
         "website", "documentation", mode="before", check_fields=False
     )
@@ -69,7 +69,6 @@ def _check_url(url: str) -> bool:
 
 
 class PersonModel(BaseModel, UrlValidatorMixin):
-    # Make sure model populates both aliases and original attr name
     model_config = ConfigDict(
         populate_by_name=True,
         str_strip_whitespace=True,
@@ -158,7 +157,6 @@ def clean_strings(cls, string: str) -> str:
 
         """
         if isinstance(string, str):
-            # Remove "\r\n" from the string value
             string = re.sub(r"[\r\n]", "", string)
         return string
 
@@ -220,47 +218,6 @@ def get_token(self) -> str:
         load_dotenv()
         return os.environ["GITHUB_TOKEN"]
 
-    # TODO - This utility is used across all scripts.
-    def clean_list(self, a_list: Union[str, List[str]]) -> List[str]:
-        """Helper function that takes an input object as a list or string.
-        If it is a list containing none, it returns an empty list
-        if it is a string is returns the string as a list
-        removes 'None' if that is in the list. and returns
-            either an empty clean list of the list as is."""
-
-        if isinstance(a_list, str):
-            a_list = [a_list]
-        elif not a_list:
-            a_list = []
-        # Remove None from list
-        a_list = list(filter(lambda x: x, a_list))
-        return a_list
-
-    # TODO - There is likely a better way to do this. If it returns an
-    # empty list then we know there are no new vals... so it likely can
-    # return a single thing
-    def unique_new_vals(
-        self, a_list: List[str], a_item: List[str]
-    ) -> Tuple[bool, Optional[List[str]]]:
-        """Checks two objects either a list and string or two lists
-        and evaluates whether there are differences between them.
-
-        Returns
-        -------
-        Tuple
-            Containing a boolean representing whether there are difference
-            or not and a list containing new value if there are differences.
-
-        """
-
-        default = (False, None)
-        list_lower = [al.lower() for al in a_list]
-        item_lower = [ai.lower() for ai in a_item]
-        diff = list(set(item_lower) - set(list_lower))
-        if len(diff) > 0:
-            default = (True, diff)
-        return default
-
     def check_contrib_type(self, json_file: str):
         """
         Determine the type of contribution the person
@@ -323,6 +280,7 @@ def load_json(self, json_path: str) -> dict:
             print(ae)
         return json.loads(response.text)
 
+    # TODO: check is i'm using the contrib type part of this method ?
     def process_json_file(self, json_file: str) -> Tuple[str, List]:
         """Deserialize a JSON file from a URL and cleanup data
 
@@ -497,105 +455,3 @@ def combine_users(self, repoDict: dict, webDict: dict) -> dict:
                 print("New user found. Adding: ", gh_user)
                 webDict[gh_user] = repoDict[gh_user]
         return webDict
-
-    # # TODO: i think i can remove this method
-    # def add_new_user(self, gh_user: str) -> dict:
-    #     """Add a new user to the contrib file using gh username
-
-    #     This method does a few things.
-    #     1. Adds a new template entry for the user w no values populated
-    #     2. Gets user metadata from the user's github profile
-    #     3. Updates their contrib entry with the gh data
-
-    #     Parameters
-    #     ----------
-    #     gh_user : str
-    #         String representing the GitHub username
-
-    #     Returns
-    #     -------
-    #     Dict
-    #         Username is the key and the updated github profile info is
-    #         contained in the dict.
-
-    #     """
-
-    #     new = {}
-    #     # Rather than this template i can use the person_model
-    #     new[gh_user] = self.create_contrib_template()
-    #     gh_data = self.get_gh_data([gh_user])
-    #     # Update their metadata in the dict and return
-    #     updated_data = self.update_contrib_data(new, gh_data)
-    #     return updated_data
-
-    def get_gh_data(
-        self, contribs: Union[Dict[str, str], List]
-    ) -> dict[str, str]:
-        """Parses through each GitHub username and hits the GitHub
-        API to grab user information.
-
-        Parameters
-        ----------
-        contribs : dict
-            Dict containing all current contrib info
-
-        Returns
-        -------
-            Dict
-            A dict of updated user data via a list of github usernames
-        """
-        all_user_info = {}
-        for gh_user in contribs:
-            print("Getting github data for: ", gh_user)
-            # If the user already has a name in the dict, don't update
-            # Important to allow us to update names to ensure correct spelling,
-            # etc on website
-            if isinstance(contribs, list):
-                aname = None
-            else:
-                aname = contribs[gh_user]["name"]
-
-            all_user_info[gh_user] = self.get_user_info(gh_user, aname)
-        return all_user_info
-
-    # Shouldn't need this anymore with pydantic
-    # def update_contrib_data(self, contrib_data: dict, gh_data: dict):
-    #     """Update contributor data from the GH API return.
-
-    #     Use the GitHub API to grab user profile data such as twitter handle,
-    #     mastodon, website, email and location and update contributor
-    #     information. GitHub profile data is the source of truth source for
-    #     contributor metadata.
-
-    #     Parameters
-    #     ----------
-    #     contrib_data : dict
-    #         A dict containing contributor data to be updated
-    #     gh_data : dict
-    #         Updated contributor data pulled from github API
-
-    #     Returns
-    #     -------
-    #     dict
-    #         Dictionary containing updated contributor data.
-    #     """
-
-    #     for i, gh_name in enumerate(contrib_data.keys()):
-    #         print(i, gh_name)
-    #         # Update the key:value pairs for data pulled from GitHub
-    #         for akey in self.update_keys:
-    #             if akey == "website":
-    #                 url = gh_data[gh_name][gh_name][akey]
-    #                 # Fix the url format and check to see if it works online
-    #                 url = self.format_url(url)
-    #                 # It url is valid, add to dict
-    #                 if self._check_url(url):
-    #                     contrib_data[gh_name][akey] = url
-    #                 else:
-    #                     contrib_data[gh_name][akey] = ""
-    #             else:
-    #                 contrib_data[gh_name][akey] = gh_data[gh_name][gh_name][
-    #                     akey
-    #                 ]
-
-    #     return contrib_data