Handle 503 Gateway errors better. Pubchem ignore_chems updated to only 404s. Build_all retries set at 3 and 10 min

Author: jjacobson95

build/build_all.py

@@ -60,6 +60,7 @@ def run_docker_cmd(cmd_arr,filename):
         Essentially a wrapper for 'docker run'. Also provides output.
         '''
         retries=3
+        delays = [3 * 60, 10 * 60]  # 3 minutes, 10 minutes
         print('running...'+filename)
         env = os.environ.copy()
         if 'SYNAPSE_AUTH_TOKEN' not in env.keys():
@@ -80,21 +81,13 @@ def run_docker_cmd(cmd_arr,filename):
             else:
                 print(f"[{filename}] failed (exit {res.returncode}).")
                 if attempt < retries:
-                    print("Retrying...")
+                    delay = delays[attempt - 1]
+                    print(f"[{filename}] waiting {delay//60} minutes before retrying...")
                     print(cmd)
+                    time.sleep(delay)
             attempt += 1
         raise RuntimeError(f"{filename} failed after {retries} attempts")
-                
-            
-        # cmd = docker_run+cmd_arr
-        # print(cmd)
-        # # res = subprocess.run(cmd,stdout=subprocess.PIPE,stderr=subprocess.PIPE)
-        # res = subprocess.run(cmd, stdout=sys.stdout, stderr=sys.stderr)
-        # if res.returncode !=0:
-        #     print(res.stderr)
-        #     exit(filename+' file failed')
-        # else:
-        #     print(filename+' retrieved')
+
 
 
     def process_docker(datasets):

build/utils/pubchem_retrieval.py

@@ -55,9 +55,10 @@ def fetch_url(url, retries=3, backoff_factor=1):
         try:
             response = requests.get(url, timeout=10)
             if response.status_code == 200:
-                return response.json()
-            else:
-                raise Exception(f"Failed to fetch {url}, Status Code: {response.status_code}")
+              return response.json()
+            if response.status_code == 404:          # permanent, no existing CID/name
+                raise FileNotFoundError("404")
+            raise Exception(f"Failed to fetch {url}, Status Code: {response.status_code}")
         except Exception as exc:
             if attempt < retries:
                 wait = backoff_factor * (2 ** attempt)
@@ -104,11 +105,15 @@ def retrieve_drug_info(compound, ignore_chems, isname=True):
             try:
                 data = future.result()
                 results[key] = data
-            except Exception as exc:
-                print(f'{compound} generated an exception: {exc}')
+                
+            except FileNotFoundError:                # only 404s are added
+                print(f"{compound} not found in PubChem. Adding to ignore list.")
                 with open(ignore_chems, "a") as f:
                     f.write(f"{compound}\n")
                 return None
+            except Exception as exc:                 # transient error, don't blacklist
+                print(f"{compound} generated a transient exception: {exc}")
+                return None
 
     if all(key in results for key in ["properties", "synonyms"]):
         properties = results["properties"]['PropertyTable']['Properties'][0]