lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-07-18 05:27:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

* ExtractorXML.java

Browse Source 
shouldExtract() - use getContentReplayPrefixString() for <?xml check
This commit is contained in:
nlevitt
2011-04-22 00:42:09 +00:00
parent a2eaa9d6ac
commit c9c74b5c28
1 changed files with 7 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
+7 -13
View File
@@ -77,19 +77,13 @@ public class ExtractorXML extends ContentExtractor {
return true;
}
try {
// check if content starts with xml preamble "<?xml" and does not
// contain "<!doctype html" or "<html" early in the content
ReplayCharSequence cs = curi.getRecorder().getContentReplayCharSequence();
String contentStartingChunk = cs.subSequence(0, Math.min(cs.length(), 400)).toString();
if (contentStartingChunk.matches("(?is)[\\ufeff]?<\\?xml\\s.*")
&& !contentStartingChunk.matches("(?is).*(?:<!doctype\\s+html|<html[>\\s]).*")) {
return true;
}
} catch (IOException e) {
logger.severe(curi + " - failed getting ReplayCharSequence: " + e);
return false;
}
// check if content starts with xml preamble "<?xml" and does not
// contain "<!doctype html" or "<html" early in the content
String contentStartingChunk = curi.getRecorder().getContentReplayPrefixString(400);
if (contentStartingChunk.matches("(?is)[\\ufeff]?<\\?xml\\s.*")
&& !contentStartingChunk.matches("(?is).*(?:<!doctype\\s+html|<html[>\\s]).*")) {
return true;
}
return false;
}