Librarian side fix

conjurer_librarian/search_bot.py

@@ -2,13 +2,13 @@ from queue import Queue, Empty
 from threading import Thread
 q = Queue()
 
-MAXTHREADS = 39
-#MAXTHREADS = 4
+#MAXTHREADS = 39
+MAXTHREADS = 4
 DATABASE_PATH = r'C:\\Database\\chunks_1\\'
 ENCODING = "utf-8"
 CHUNk = "_chunk.txt"
 _sentinel = object()
-
+result_list = []
 #TODO: Doisy wchodzą jako lista krotek (doi, False) - po znalezieniu zaznaczamy na True i potem już nie porównujemy
 #TODO: lista krotek - jeśli wszystkie mają True dajemy terma
 
@@ -35,15 +35,23 @@ def producer(out_q, control_q, filename):
 #TODO: Change doi to tuple list and only put term when all doi are found => (doi, True)
 def consumer(in_q, control_q, doi):
     sentinels = 0
+    for item in doi:
+        result_list.append({"DOI" : item[0], "exists" : False, "data" : item[1]})
     while True:
+        done_check = True
         data = in_q.get()
         if data is _sentinel:
             print("Worker finished")
             sentinels += 1
-        elif doi in data:
-            control_q.put(_sentinel)
-            print(data)
-            print("HIT")
+        else:
+            for item in result_list:
+                if item["DOI"] in data:
+                    print(data)
+                    print("HIT")
+                    item["exists"] = True
+                done_check = done_check and item["exists"]
+            if done_check:
+                control_q.put(_sentinel)
         if sentinels >= MAXTHREADS:
             print("All workers finished")
             break
@@ -51,31 +59,29 @@ def consumer(in_q, control_q, doi):
 
 def search_for_doi(doi):
     threads = []
-    work_q = Queue(maxsize=10000000)
+    work_q = Queue(maxsize=100)
     control_q = Queue()
     t_cons = Thread(target = consumer, args = (work_q, control_q, doi))
     threads.append(t_cons)
     for i in range(0,MAXTHREADS):
-        #filename = "test" + str(i) + CHUNk
+        filename = "test" + str(i) + CHUNk
         filename = str(i) + CHUNk
-        print(filename)
+        #print(filename)
         threads.append(Thread(target = producer, args = (work_q, control_q, filename)))
     for worker in threads:
         worker.start()
     for worker in threads:
         worker.join()
-
-    try:
-        check = control_q.get(block=False)
-        control_q.put(check)
-        return True
-    except Empty:
-        return False
-
+    return result_list
 if __name__ == "__main__":
-    if search_for_doi("10.1002/9781118786352.wbieg0998.pub2"):
-    #if search_for_doi("10.1108/gm-02-2016-0025xx"):        
-        print("found")
-        exit()
-    else:
-        print("Not found")
+    print(search_for_doi([
+        ("10.1002/9781118786352.wbieg0998.pub2","DATA"),
+        ("10.1002/j.2050-0416.2002.tb00563.x","DATA"),
+        ("10.1111/j.1365-2958.1994.tb00448.x","DATA"),
+        ("10.2165/00128415-200309690-00017","DATA"),
+        ("10.5772/48313","DATA"),
+        ("10.15803/ijnc.7.2_419","DATA"),
+        ("10.1051/0004-6361/201321596e","DATA"),
+        ("10.2307/40835941","DATA"),
+        ]))
+