motiejus
/
jgit
1
Fork 0
Code Releases Activity

HistogramDiff: Convert stack recursion to heap managed queue 

Each time the longest common substring is found the diff algorithm
recurses to reprocess the regions before and after the common string.

Large files with many edits can trigger StackOverflowError as the
algorithm attempts to process a deeply split tree of regions. This
is especially prone to happen in servers where the Java stack size
may have been limited to 1M or even 256K.

To keep edits produced in order a queue is used to process edits
in a depth-first strategy.

Change-Id: Iae7260c6934efdffac7c7bee4d3633a8208924f7
This commit is contained in:
Shawn Pearce 2014-07-25 08:17:27 -07:00
parent f3fc379757
commit d11ca1b084
1 changed files with 14 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
org.eclipse.jgit/src/org/eclipse/jgit/diff/HistogramDiff.java
View File

@ -43,6 +43,9 @@
package org.eclipse.jgit.diff;
import java.util.ArrayList;
import java.util.List;
/**
* An extended form of Bram Cohen's patience diff algorithm.
* <p>
@ -130,15 +133,14 @@ public void setMaxChainLength(int maxLen) {
public <S extends Sequence> void diffNonCommon(EditList edits,
HashedSequenceComparator<S> cmp, HashedSequence<S> a,
HashedSequence<S> b, Edit region) {
new State<S>(edits, cmp, a, b).diffReplace(region);
new State<S>(edits, cmp, a, b).diffRegion(region);
}
private class State<S extends Sequence> {
private final HashedSequenceComparator<S> cmp;
private final HashedSequence<S> a;
private final HashedSequence<S> b;
private final List<Edit> queue = new ArrayList<Edit>();
/** Result edits we have determined that must be made to convert a to b. */
final EditList edits;
@ -151,7 +153,13 @@ private class State<S extends Sequence> {
this.edits = edits;
}
void diffReplace(Edit r) {
void diffRegion(Edit r) {
diffReplace(r);
while (!queue.isEmpty())
diff(queue.remove(queue.size() - 1));
}
private void diffReplace(Edit r) {
Edit lcs = new HistogramDiffIndex<S>(maxChainLength, cmp, a, b, r)
.findLongestCommonSequence();
if (lcs != null) {
@ -163,8 +171,8 @@ void diffReplace(Edit r) {
//
edits.add(r);
} else {
diff(r.before(lcs));
diff(r.after(lcs));
queue.add(r.after(lcs));
queue.add(r.before(lcs));
}
} else if (fallback instanceof LowLevelDiffAlgorithm) {