lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-26 07:35:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #452 from internetarchive/handle-nulls-in-content-length-header

Browse Source 
FetchHTTP: Handle null characters in the Content-Length header
This commit is contained in:
Alex Osborne
2022-01-17 16:20:12 +09:00
committed by GitHub
parent aa4f0f9933 a3d651ba46
commit d40a025692
1 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/src/main/java/org/archive/modules/fetcher/FetchHTTP.java
+11 -2
View File
@@ -685,8 +685,17 @@ public class FetchHTTP extends Processor implements Lifecycle {
long contentLength = -1l;
Header h = response.getLastHeader("content-length");
if (h != null && h.getValue().trim().length()>0) {
contentLength = Long.parseLong(h.getValue());
if (h != null) {
// browsers ignore everything after a null character and some buggy web servers rely on this
String contentLengthHeader = StringUtils.substringBefore(h.getValue(), "\0").trim();
if (!contentLengthHeader.isEmpty()) {
try {
contentLength = Long.parseLong(contentLengthHeader);
} catch (NumberFormatException e) {
cleanup(curi, e, "invalid content-length header", S_CONNECT_LOST);
return;
}
}
}
try {
if (!req.request.isAborted()) {