From 6e7baa12619e8b51218bcefb2c6dd75525eb7387 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Thu, 15 Jul 2021 03:33:19 +0200
Subject: cdx reshape: only include hits

---
 extra/cdx/cdx_reshape.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'extra/cdx')

diff --git a/extra/cdx/cdx_reshape.py b/extra/cdx/cdx_reshape.py
index 6b3d6e5..28b6fc0 100644
--- a/extra/cdx/cdx_reshape.py
+++ b/extra/cdx/cdx_reshape.py
@@ -9,8 +9,7 @@ by_url = {}
 for line in fileinput.input():
     line = line.strip()
     doc = json.loads(line)
-    last = doc.get("summary", {}).get("last", "")
-    if not last:
+    if doc.get("numRows") == 0:
         continue
     by_url[doc["line"]] = doc
 
-- 
cgit v1.2.3