Remove crawl_type from optimize_pages bg job

webrecorder · Feb 18, 2025 · 1986ea6 · 1986ea6
1 parent 87f22dd
commit 1986ea6
Show file tree

Hide file tree

Showing 6 changed files with 3 additions and 16 deletions.
diff --git a/backend/btrixcloud/background_jobs.py b/backend/btrixcloud/background_jobs.py
@@ -427,14 +427,12 @@ async def create_re_add_org_pages_job(
 
     async def create_optimize_crawl_pages_job(
         self,
-        crawl_type: Optional[str] = None,
         existing_job_id: Optional[str] = None,
     ):
         """Create job to optimize crawl pages"""
 
         try:
             job_id = await self.crawl_manager.run_optimize_pages_job(
-                crawl_type=crawl_type,
                 existing_job_id=existing_job_id,
             )
             if existing_job_id:
@@ -453,7 +451,6 @@ async def create_optimize_crawl_pages_job(
             else:
                 optimize_pages_job = OptimizePagesJob(
                     id=job_id,
-                    crawl_type=crawl_type,
                     started=dt_now(),
                 )
 
@@ -661,7 +658,6 @@ async def retry_background_job(
 
         if job.type == BgJobType.OPTIMIZE_PAGES:
             await self.create_optimize_crawl_pages_job(
-                job.crawl_type,
                 existing_job_id=job_id,
             )
             return {"success": True}

diff --git a/backend/btrixcloud/crawlmanager.py b/backend/btrixcloud/crawlmanager.py
@@ -169,7 +169,6 @@ async def run_re_add_org_pages_job(
 
     async def run_optimize_pages_job(
         self,
-        crawl_type: Optional[str] = None,
         existing_job_id: Optional[str] = None,
     ) -> str:
         """run job to recalculate storage stats for the org"""
@@ -183,7 +182,6 @@ async def run_optimize_pages_job(
             job_id,
             job_type=BgJobType.OPTIMIZE_PAGES.value,
             migration_job=True,
-            crawl_type=crawl_type,
         )
 
     async def _run_bg_job_with_ops_classes(

diff --git a/backend/btrixcloud/main_bg.py b/backend/btrixcloud/main_bg.py
@@ -33,7 +33,7 @@ async def main():
     # Run job (generic)
     if job_type == BgJobType.OPTIMIZE_PAGES:
         try:
-            await page_ops.optimize_crawl_pages(version=2, crawl_type=crawl_type)
+            await page_ops.optimize_crawl_pages(version=2)
             return 0
         # pylint: disable=broad-exception-caught
         except Exception:

diff --git a/backend/btrixcloud/migrations/migration_0042_page_filenames.py b/backend/btrixcloud/migrations/migration_0042_page_filenames.py
@@ -31,9 +31,7 @@ async def migrate_up(self):
             return
 
         try:
-            await self.background_job_ops.create_optimize_crawl_pages_job(
-                crawl_type="crawl"
-            )
+            await self.background_job_ops.create_optimize_crawl_pages_job()
         # pylint: disable=broad-exception-caught
         except Exception as err:
             print(

diff --git a/backend/btrixcloud/models.py b/backend/btrixcloud/models.py
@@ -2607,7 +2607,6 @@ class OptimizePagesJob(BackgroundJob):
     """Model for tracking jobs to optimize pages across all orgs"""
 
     type: Literal[BgJobType.OPTIMIZE_PAGES] = BgJobType.OPTIMIZE_PAGES
-    crawl_type: Optional[str] = None
 
 
 # ============================================================================

diff --git a/backend/btrixcloud/pages.py b/backend/btrixcloud/pages.py
@@ -978,15 +978,11 @@ async def set_archived_item_page_counts(self, crawl_id: str):
             {"$set": {"uniquePageCount": unique_page_count, "pageCount": page_count}},
         )
 
-    async def optimize_crawl_pages(
-        self, version: int = 2, crawl_type: Optional[str] = None
-    ):
+    async def optimize_crawl_pages(self, version: int = 2):
         """Iterate through crawls, optimizing pages"""
         while True:
             # Pull new crawl and set isMigrating
             match_query = {"version": {"$ne": version}, "isMigrating": {"$ne": True}}
-            if crawl_type in ("crawl", "upload"):
-                match_query["type"] = crawl_type
 
             next_crawl = await self.crawls.find_one_and_update(
                 match_query, {"$set": {"isMigrating": True}}