From ec346106c399256529db6ac9b534c0e8a48019ab Mon Sep 17 00:00:00 2001
From: "Mark A. Miller" <MAM@lbl.gov>
Date: Thu, 12 Sep 2024 12:17:36 -0400
Subject: [PATCH 1/2] new PR class in github_wrapper

---
 .gitignore                                    |  3 +
 Makefile                                      |  7 ++-
 .../wrappers/general/github_wrapper.py        | 59 ++++++++++++++++---
 3 files changed, 59 insertions(+), 10 deletions(-)

diff --git a/.gitignore b/.gitignore
index a8f9868..bd8763b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,6 @@
+.idea/
+*.sqlite
+
 *.pem
 db/
 proddb/
diff --git a/Makefile b/Makefile
index 667f7af..c22b7f9 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,8 @@
 RUN = poetry run
 CURATE = $(RUN) curategpt
 
-DB_PATH = stagedb
+#DB_PATH = stagedb
+DB_PATH = db
 
 ONTS = cl uberon obi go envo hp mp mondo po to oba agro fbbt nbo chebi vo peco maxo
 TRACKERS = cl uberon obi  envo hp mondo go
@@ -118,4 +119,8 @@ load-github-maxo:
 list:
 	$(CURATE) collections list -p $(DB_PATH)
 
+load-github-mixs:
+	$(CURATE) -v view index -p $(DB_PATH) -c gh_mixs -m openai:  --view github --init-with "{repo: GenomicsStandardsConsortium/mixs}"
 
+load-github-nmdc-schema-issues-prs:
+	$(CURATE) -v view index -p $(DB_PATH) -c gh_nmdc -m openai:  --view github --init-with "{repo: microbiomedata/nmdc-schema}"
diff --git a/src/curate_gpt/wrappers/general/github_wrapper.py b/src/curate_gpt/wrappers/general/github_wrapper.py
index 12c4a6f..25aa0c7 100644
--- a/src/curate_gpt/wrappers/general/github_wrapper.py
+++ b/src/curate_gpt/wrappers/general/github_wrapper.py
@@ -22,6 +22,20 @@ class Comment(BaseModel):
     body: str = None
 
 
+class PullRequest(BaseModel):
+    model_config = ConfigDict(protected_namespaces=())
+    id: str
+    number: int = None
+    title: str = None
+    user: str = None
+    labels: List[str] = None
+    state: str = None
+    assignees: List[str] = None
+    created_at: str = None
+    body: str = None
+    comments: List[Comment] = None
+
+
 class Issue(BaseModel):
     model_config = ConfigDict(protected_namespaces=())
     id: str
@@ -38,6 +52,18 @@ class Issue(BaseModel):
     comments: List[Comment] = None
 
 
+def pr_comments(self, pr_number: str) -> Iterator[Dict]:
+    session = self.session
+    url = f"https://api.github.com/repos/{self.owner}/{self.repo}/pulls/{pr_number}/comments"
+    params = {"per_page": 100}
+
+    while url:
+        response = session.get(url, headers=self.headers, params=params)
+        response.raise_for_status()
+        yield from response.json()
+        url = response.links.get("next", {}).get("url")
+
+
 def get_token(token: str = None) -> Optional[str]:
     if token:
         return token
@@ -101,7 +127,7 @@ def repo_description(self) -> str:
         return self._repo_description
 
     def external_search(
-        self, text: str, expand: bool = True, limit=None, token: str = None, **kwargs
+            self, text: str, expand: bool = True, limit=None, token: str = None, **kwargs
     ) -> List[Dict]:
         token = get_token(token)
         if limit is None:
@@ -146,11 +172,11 @@ def external_search(
         return all_issues
 
     def objects(
-        self,
-        collection: str = None,
-        object_ids: Optional[Iterable[str]] = None,
-        token: str = None,
-        **kwargs,
+            self,
+            collection: str = None,
+            object_ids: Optional[Iterable[str]] = None,
+            token: str = None,
+            **kwargs,
     ) -> Iterator[Dict]:
         session = self.session
         token = get_token(token)
@@ -161,7 +187,7 @@ def objects(
             sleep(5)
         logger.debug(f"Header: {headers}")
         params = {
-            "state": "all",  # To fetch both open and closed issues
+            "state": "all",  # To fetch both open and closed issues and PRs
             "per_page": 100,  # Fetch 100 results per page (max allowed)
         }
 
@@ -171,10 +197,14 @@ def objects(
             issues = response.json()
             for issue in issues:
                 issue_number = issue.get("number")
-                issue["comments"] = list(self.issue_comments(issue_number))
+                # Fetch both issue comments and PR comments
+                if "pull_request" in issue:
+                    issue["comments"] = list(self.pr_comments(issue_number))
+                else:
+                    issue["comments"] = list(self.issue_comments(issue_number))
                 issue_obj = self.transform_issue(issue)
                 yield issue_obj.dict()
-            # Check if there are more pages to process
+                # Check if there are more pages to process
             url = response.links.get("next", {}).get("url")
             if not response.from_cache:
                 sleep(0.2)
@@ -219,3 +249,14 @@ def transform_issue(self, obj: Dict) -> Issue:
             ],
         )
         return issue
+
+    def pr_comments(self, pr_number: str) -> Iterator[Dict]:
+        session = self.session
+        url = f"https://api.github.com/repos/{self.owner}/{self.repo}/pulls/{pr_number}/comments"
+        params = {"per_page": 100}
+
+        while url:
+            response = session.get(url, headers=self.headers, params=params)
+            response.raise_for_status()
+            yield from response.json()
+            url = response.links.get("next", {}).get("url")

From f8dfb20a0a0b6ac23c2d97fcd96083502e7440ff Mon Sep 17 00:00:00 2001
From: "Mark A. Miller" <MAM@lbl.gov>
Date: Thu, 12 Sep 2024 12:18:55 -0400
Subject: [PATCH 2/2] revert DB_PATH

---
 Makefile | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index c22b7f9..c5fa393 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,7 @@
 RUN = poetry run
 CURATE = $(RUN) curategpt
 
-#DB_PATH = stagedb
-DB_PATH = db
+DB_PATH = stagedb
 
 ONTS = cl uberon obi go envo hp mp mondo po to oba agro fbbt nbo chebi vo peco maxo
 TRACKERS = cl uberon obi  envo hp mondo go