From 3638e16c2e046d0b92feae504e8e8c1588b8cee9 Mon Sep 17 00:00:00 2001 From: luccioman Date: Sat, 13 Jan 2018 12:07:56 +0100 Subject: [PATCH] More comprehensive log on rejected recrawls caused by date constraint --- source/net/yacy/crawler/CrawlStacker.java | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/source/net/yacy/crawler/CrawlStacker.java b/source/net/yacy/crawler/CrawlStacker.java index e0b293c7b4..4a02db462d 100644 --- a/source/net/yacy/crawler/CrawlStacker.java +++ b/source/net/yacy/crawler/CrawlStacker.java @@ -455,7 +455,9 @@ public String checkAcceptanceInitially(final DigestURL url, final CrawlProfile p CrawlStacker.log.fine("RE-CRAWL of URL '" + urlstring + "': this url was crawled " + ((System.currentTimeMillis() - oldDate.longValue()) / 60000 / 60 / 24) + " days ago."); } else { - return CRAWL_REJECT_REASON_DOUBLE_IN_PREFIX + ": local index, oldDate = " + ISO8601Formatter.FORMATTER.format(new Date(oldDate)); + return CRAWL_REJECT_REASON_DOUBLE_IN_PREFIX + ": local index, recrawl rejected. Document date = " + + ISO8601Formatter.FORMATTER.format(new Date(oldDate)) + " is not older than crawl profile recrawl minimum date = " + + ISO8601Formatter.FORMATTER.format(new Date(profile.recrawlIfOlder())); } return null;