Skip to content

Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance

fix NPE in QuickCrawlLink_p if param doesn't contain crawl url

regerbac302bfe43b
diff --git a/htroot/QuickCrawlLink_p.java b/htroot/QuickCrawlLink_p.java
index 3e7158a44..35b8d1aa0 100644
--- a/htroot/QuickCrawlLink_p.java
+++ b/htroot/QuickCrawlLink_p.java
@@ -62,56 +62,55 @@ public class QuickCrawlLink_p {
final serverObjects prop = new serverObjects();
final Switchboard sb = (Switchboard) env;
- // get segment
- Segment indexSegment = sb.index;
+ int port = sb.getConfigInt("port", 8090);
- if (post == null) {
- // send back usage example
- prop.put("mode", "0");
-
- // get the http host header
+ // get the http host header
+ if (header.containsKey(HeaderFramework.HOST)) {
final String hostSocket = header.get(HeaderFramework.HOST);
-
- //String host = hostSocket;
- int port = 80;
- final int pos = hostSocket.indexOf(':',0);
+ final int pos = hostSocket.indexOf(':', 0);
if (pos != -1) {
port = NumberTools.parseIntDecSubstring(hostSocket, pos + 1);
- //host = hostSocket.substring(0, pos);
}
+ }
+ prop.put("mode_host", Domains.LOCALHOST);
+ prop.put("mode_port", port);
- prop.put("mode_host", Domains.LOCALHOST);
- prop.put("mode_port", port);
-
+ if (post == null) {
+ // send back usage example
+ prop.put("mode", "0");
return prop;
}
- prop.put("mode", "1");
// get the URL
String crawlingStart = post.get("url",null);
- crawlingStart = UTF8.decodeURL(crawlingStart);
-
- // get the browser title
- final String title = post.get("title",null);
-
- // get other parameters if set
- final String crawlingMustMatch = post.get("mustmatch", CrawlProfile.MATCH_ALL_STRING);
- final String crawlingMustNotMatch = post.get("mustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
- final int CrawlingDepth = post.getInt("crawlingDepth", 0);
- final boolean crawlingQ = post.get("crawlingQ", "").equals("on");
- final boolean followFrames = post.get("followFrames", "").equals("on");
- final boolean obeyHtmlRobotsNoindex = post.get("obeyHtmlRobotsNoindex", "").equals("on");
- final boolean obeyHtmlRobotsNofollow = post.get("obeyHtmlRobotsNofollow", "").equals("on");
- final boolean indexText = post.get("indexText", "off").equals("on");
- final boolean indexMedia = post.get("indexMedia", "off").equals("on");
- final boolean storeHTCache = post.get("storeHTCache", "").equals("on");
- final boolean remoteIndexing = post.get("crawlOrder", "").equals("on");
- final String collection = post.get("collection", "user");
-
- prop.put("mode_url", (crawlingStart == null) ? "unknown" : crawlingStart);
- prop.putHTML("mode_title", (title == null) ? "unknown" : title);
if (crawlingStart != null) {
+ prop.put("mode", "1");
+ crawlingStart = UTF8.decodeURL(crawlingStart);
+
+ // get segment
+ Segment indexSegment = sb.index;
+
+ // get the browser title
+ final String title = post.get("title", null);
+
+ // get other parameters if set
+ final String crawlingMustMatch = post.get("mustmatch", CrawlProfile.MATCH_ALL_STRING);
+ final String crawlingMustNotMatch = post.get("mustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
+ final int CrawlingDepth = post.getInt("crawlingDepth", 0);
+ final boolean crawlingQ = post.get("crawlingQ", "").equals("on");
+ final boolean followFrames = post.get("followFrames", "").equals("on");
+ final boolean obeyHtmlRobotsNoindex = post.get("obeyHtmlRobotsNoindex", "").equals("on");
+ final boolean obeyHtmlRobotsNofollow = post.get("obeyHtmlRobotsNofollow", "").equals("on");
+ final boolean indexText = post.get("indexText", "off").equals("on");
+ final boolean indexMedia = post.get("indexMedia", "off").equals("on");
+ final boolean storeHTCache = post.get("storeHTCache", "").equals("on");
+ final boolean remoteIndexing = post.get("crawlOrder", "").equals("on");
+ final String collection = post.get("collection", "user");
+
+ prop.put("mode_url", (crawlingStart == null) ? "unknown" : crawlingStart);
+ prop.putHTML("mode_title", (title == null) ? "unknown" : title);
+
crawlingStart = crawlingStart.trim();
try {crawlingStart = new DigestURL(crawlingStart).toNormalform(true);} catch (final MalformedURLException e1) {}