qb20nh · February 4, 2022 17:14 · Feb 4, 2022
diff --git a/.\read_file_skip_bytes.py b/.\read_file_skip_bytes.py
@@ -0,0 +1,61 @@
+from time import sleep, time
+import os
+
+
+def binary_search(condition, low, high):
+    if callable(condition) and high > low:
+        mid = int((high + low) / 2)
+
+        res = condition(mid)
+
+        if res == 0:
+            return mid
+
+        elif res < 0:
+            return binary_search(condition, low, mid - 1)
+
+        else:
+            return binary_search(condition, mid + 1, high)
+
+
+def find_json_property(idx):
+    print(f'seeking to {idx}')
+    file.seek(idx)
+
+    read_success = False
+    preview_bytes = 1024
+    read_content = None
+    offset = 0
+    while not read_success:
+        file.seek(idx+offset)
+        try:
+            read_content = file.read(preview_bytes).decode("utf-8")
+            read_success = True
+        except Exception:
+            offset += 1
+
+    print(f'content: {read_content}')
+    target = 2500000000
+    print('querying DB for property songID') # query db here
+    sleep(1)  # assume every query takes about 1 second
+    if abs(idx - target) <= preview_bytes:  # change this to json property match result
+        return 0
+    elif idx > target:
+        return -1
+    else:
+        return 1
+
+
+file_path = "C:/json/song_data_file.json" # replace this with your file location
+
+start_time = time()
+
+size_in_bytes = os.path.getsize(file_path)
+print(f'file size: {size_in_bytes}')
+file = open(file_path, 'rb')
+result = binary_search(find_json_property, 0, size_in_bytes)
+
+end_time = time()
+
+print(f'found at {result}')
+print(f'elapsed {end_time-start_time}')
No results found