From 9182b3dfcafc767217b00bc22ddeb855ad85b407 Mon Sep 17 00:00:00 2001 From: Michael Peter Christen Date: Thu, 5 Aug 2021 09:18:05 +0200 Subject: [PATCH] enhanced default value --- htroot/Crawler_p.java | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/htroot/Crawler_p.java b/htroot/Crawler_p.java index 93d8728ab..55c417784 100644 --- a/htroot/Crawler_p.java +++ b/htroot/Crawler_p.java @@ -366,7 +366,7 @@ public class Crawler_p { boolean obeyHtmlRobotsNofollow = "on".equals(post.get("obeyHtmlRobotsNofollow", "false")); env.setConfig("obeyHtmlRobotsNofollow", obeyHtmlRobotsNofollow); - final boolean indexText = "on".equals(post.get("indexText", "false")); + final boolean indexText = "on".equals(post.get("indexText", "on")); env.setConfig("indexText", indexText); final boolean indexMedia = "on".equals(post.get("indexMedia", "false")); @@ -536,12 +536,12 @@ public class Crawler_p { try { if (newcrawlingdepth > 0) { if (fullDomain) { - /* Crawl is restricted to start domains or sub-paths : we have to get all the start links now. + /* Crawl is restricted to start domains or sub-paths : we have to get all the start links now. * Otherwise we can get them asynchronously later, thus allowing to handle more efficiently large start crawlingFiles */ hyperlinks_from_file = crawlingFileStart(crawlingFile, timezoneOffset, crawlingFileContent); newcrawlingMustMatch = CrawlProfile.siteFilter(hyperlinks_from_file); } else if (subPath) { - /* Crawl is restricted to start domains or sub-paths : we have to get all the start links now. + /* Crawl is restricted to start domains or sub-paths : we have to get all the start links now. * Otherwise we can get them asynchronously later, thus allowing to handle more efficiently large start crawlingFiles */ hyperlinks_from_file = crawlingFileStart(crawlingFile, timezoneOffset, crawlingFileContent); newcrawlingMustMatch = CrawlProfile.subpathFilter(hyperlinks_from_file); @@ -770,7 +770,7 @@ public class Crawler_p { /* * PPM LF - MH + MH (min/max)