Updates 2023 (#36)

.github/workflows/auto_update_stat_images.yml

@@ -71,6 +71,7 @@ jobs:
         MORE_REPOS: ${{ secrets.MORE_REPOS }}
         ONLY_INCLUDED: ${{ secrets.ONLY_INCLUDED }}
         EXCLUDED_COLLAB_REPOS: ${{ secrets.EXCLUDED_COLLAB_REPOS }}
+        MORE_COLLAB_REPOS: ${{ secrets.MORE_COLLAB_REPOS }}
 
     # Commits all changed files to the repository
     - name: Commit to the repo

.github/workflows/non_auto_generate_stat_images.yml

@@ -74,6 +74,7 @@ jobs:
         MORE_REPOS: ${{ secrets.MORE_REPOS }}
         ONLY_INCLUDED: ${{ secrets.ONLY_INCLUDED }}
         EXCLUDED_COLLAB_REPOS: ${{ secrets.EXCLUDED_COLLAB_REPOS }}
+        MORE_COLLAB_REPOS: ${{ secrets.MORE_COLLAB_REPOS }}
 
     # Commits all changed files to the repository
     - name: Commit to the repo

README.md

@@ -173,18 +173,29 @@ Generate daily updated visualizations of user and repository statistics from the
   * example:
     * `4`
 * ### Optional Secret *Name*: `EXCLUDED_COLLAB_REPOS`
-  For excluding collaborative repositories from being included in the average contribution statistics
+  For excluding collaborative repositories from being included in the average contribution statistics calculations
     - for example, such as for when 
-      - contributions are included in a collaborative repo, but it is not one of your projects
-      - someone deletes and re-adds the entire codebase a few times
-      - your performance is not fairly represented
-      - ninjas
+      - contributions are made to a collaborative repo, but it is not one of your projects (open-source typo fix, etc)
+      - someone deletes and re-adds the entire codebase a few times too many
+      - your or someone else's performance is not fairly represented - missing data bias 
+      - pirates, ninjas, etc.
 
   **Instructions**:
   * enter *Value* in the following format (separated by commas):
     * `[owner/repo],[owner/repo],...,[owner/repo]`
   * example:
-    * `jstrieb/github-stats,rahul-jha98/github-stats-transparent,idiotWu/stats`
+    * `tera_open_source/bit_typo_fix,peer_repo/no_git_co_author_credit,dude_collab/email_not_reg_on_github,mars/attacks`
+* ### Optional Secret *Name*: `MORE_COLLAB_REPOS`
+    For including collaborative repositories that are otherwise not included in the average contribution statistics calculations
+    - for example, such as when
+      - nobody even bothered to join the repository as a collaborator let alone contribute anything
+      - the repository is imported and because it is ghosted none of the collaborators are represented in the scraping
+
+  **Instructions**:
+  * enter *Value* in the following format (separated by commas):
+    * `[owner/repo],[owner/repo],...,[owner/repo]`
+  * example:
+    * `large_A+_collab_project/ghosted,larger_A++_project/slave_status,import_collabs/no_other_contributions_no_collabs`
 * ### Optional Secret *Name*: `STORE_REPO_VIEWS`
   Boolean for storing generated repository view statistic visualization data beyond the 14 day-limit GitHub API allows 
     - `true` by default

src/db/db.json

@@ -4,4 +4,4 @@
     "to": "0000-00-00",
     "from": "0000-00-00"
   }
-}
+}

src/env_vars.py

@@ -32,7 +32,8 @@ def __init__(self,
                  more_collaborators: Optional[str] = getenv("MORE_COLLABS"),
                  manually_added_repos: Optional[str] = getenv("MORE_REPOS"),
                  only_included_repos: Optional[str] = getenv("ONLY_INCLUDED"),
-                 exclude_collab_repos: Optional[str] = getenv("EXCLUDED_COLLAB_REPOS")):
+                 exclude_collab_repos: Optional[str] = getenv("EXCLUDED_COLLAB_REPOS"),
+                 more_collab_repos: Optional[str] = getenv("MORE_COLLAB_REPOS")):
         self.__db = GitRepoStatsDB()
 
         self.username = username
@@ -148,6 +149,13 @@ def __init__(self,
                 {x.strip() for x in exclude_collab_repos.split(",")}
             )
 
+        if more_collab_repos is None:
+            self.more_collab_repos = set()
+        else:
+            self.more_collab_repos = (
+                {x.strip() for x in more_collab_repos.split(",")}
+            )
+
     def set_views(self, views: any) -> None:
         self.repo_views += int(views)
         environ["REPO_VIEWS"] = str(self.repo_views)

src/generate_images.py

@@ -70,16 +70,21 @@ async def generate_overview(self) -> None:
             output = f.read()
 
         name = await self.__stats.name
-        name += "'" if name[-1] == "s" else "'s"
-        if len(name) > MAX_NAME_LEN:
+        if len(name + ("'" if name[-1].lower() == "s" else "'s")) > MAX_NAME_LEN:
             names = name.split(' ')
-            if len(names) == 1:
-                name = names[0]
-            elif len(names[0][0] + '. ' + names[-1]) > MAX_NAME_LEN:
-                name = names[0] + "'" if names[0][-1] == "s" else "'s"
+            if len(names) == 1 or len(names[0][0] + '. ' + names[-1] +
+                                      ("'" if names[-1][-1].lower() == "s" else "'s")) > MAX_NAME_LEN:
+                if self.__stats.environment_vars.username + \
+                       ("'" if self.__stats.environment_vars.username[-1].lower() == "s" else "'s") > MAX_NAME_LEN:
+                    name = self.__stats.environment_vars.username + \
+                           ("'" if self.__stats.environment_vars.username[-1].lower() == "s" else "'s")
+                else:
+                    name = ' '.join([name[0] + '.' for name in names])
+                    name = name.strip()[:min(len(name), MAX_NAME_LEN - 2)] + "'s"
             else:
-                name = names[0][0] + '. ' + names[-1]
-            name = name if len(name) <= MAX_NAME_LEN else name[:MAX_NAME_LEN-2] + '..'
+                name = names[0][0] + '. ' + names[-1] + ("'" if names[-1][-1].lower() == "s" else "'s")
+        else:
+            name += "'" if name[-1].lower() == "s" else "'s"
         output = sub("{{ name }}",
                      name,
                      output)

src/github_repo_stats.py

@@ -40,11 +40,13 @@ def __init__(self,
         self._avg_percent: Optional[str] = None
         self._views: Optional[int] = None
         self._collaborators: Optional[int] = None
+        self._collaborator_set: Optional[Set[str]] = None
         self._contributors: Optional[Set[str]] = None
         self._views_from_date: Optional[str] = None
         self._pull_requests: Optional[int] = None
         self._issues: Optional[int] = None
         self._empty_repos: Optional[Set[str]] = None
+        self._collab_repos: Optional[Set[str]] = None
 
     async def to_str(self) -> str:
         """
@@ -368,6 +370,9 @@ async def lines_changed(self) -> Tuple[int, int]:
         """
         if self._users_lines_changed is not None:
             return self._users_lines_changed
+        _, ghosted_collab_repos = await self.raw_collaborators()
+        slave_status_repos = self.environment_vars.more_collab_repos
+
         contributor_set = set()
         repo_total_changes_arr = []
         author_contribution_percentages = []
@@ -404,9 +409,9 @@ async def lines_changed(self) -> Tuple[int, int]:
             author_total_additions += author_additions
             author_total_deletions += author_deletions
 
-            # calculate average author's contributions to each repository with more than one contributor
-            if repo not in self.environment_vars.exclude_collab_repos and \
-                    (author_additions + author_deletions) > 0 and other_authors_total_changes > 0:
+            # calculate average author's contributions to each repository with more than one contributor (or should be)
+            if repo not in self.environment_vars.exclude_collab_repos and (author_additions + author_deletions) > 0 \
+                    and (other_authors_total_changes > 0 or repo in ghosted_collab_repos | slave_status_repos):
                 repo_total_changes = other_authors_total_changes + author_additions + author_deletions
                 author_contribution_percentages.append((author_additions + author_deletions) / repo_total_changes)
                 repo_total_changes_arr.append(repo_total_changes)
@@ -484,24 +489,33 @@ async def views_from_date(self) -> str:
         assert self._views_from_date is not None
         return self._views_from_date
 
-    @property
-    async def collaborators(self) -> int:
-        """
-        :return: count of total collaborators to user's repositories
-        """
-        if self._collaborators is not None:
-            return self._collaborators
+    async def raw_collaborators(self) -> (Set, Set):
+        if self._collaborator_set is not None and self._collab_repos is not None:
+            return self._collaborator_set, self._collab_repos
 
-        collaborator_set = set()
+        self._collaborator_set = set()
+        self._collab_repos = set()
 
         for repo in await self.repos:
             r = await self.queries\
                 .query_rest(f"/repos/{repo}/collaborators")
 
             for obj in r:
                 if isinstance(obj, dict):
-                    collaborator_set.add(obj.get("login"))
+                    self._collaborator_set.add(obj.get("login"))
+                    self._collab_repos.add(repo)
+
+        return self._collaborator_set, self._collab_repos
+
+    @property
+    async def collaborators(self) -> int:
+        """
+        :return: count of total collaborators to user's repositories
+        """
+        if self._collaborators is not None:
+            return self._collaborators
 
+        collaborator_set, _ = await self.raw_collaborators()
         collaborators = max(0, len(collaborator_set.union(await self.contributors)) - 1)
         self._collaborators = self.environment_vars.more_collaborators + collaborators
         return self._collaborators

test/git_stats_test.py

@@ -31,6 +31,7 @@
 MORE_REPOS = getenv("MORE_REPOS")  # or enter: "[owner/repo],...,[owner/repo]"
 ONLY_INCLUDED = getenv("ONLY_INCLUDED")  # or enter: "[owner/repo],..."
 EXCLUDED_COLLAB_REPOS = getenv("EXCLUDED_COLLAB_REPOS")  # or enter: "[owner/repo],..."
+MORE_COLLAB_REPOS = getenv("MORE_COLLAB_REPOS")  # or enter: "[owner/repo],..."
 
 
 async def main() -> None:
@@ -61,7 +62,8 @@ async def main() -> None:
                 more_collaborators=MORE_COLLABS,
                 manually_added_repos=MORE_REPOS,
                 only_included_repos=ONLY_INCLUDED,
-                exclude_collab_repos=EXCLUDED_COLLAB_REPOS),
+                exclude_collab_repos=EXCLUDED_COLLAB_REPOS,
+                more_collab_repos=MORE_COLLAB_REPOS),
             session=session)
         print(await stats.to_str())