DESCRIPTION

Improve performance of HyperlinkTokenScanner

My initial implementation of this was too inefficient. It invoked the
HyperlinkDetectors for every character, which effectively re-introduced
bug 415537 and made editing long commit messages with only a few links
a pain.

Therefore, compute all hyperlinks on a line and cache them once
computed. Use this cache while we're on that line, and re-compute it
when the current position passes to a new line.

Add an internal subclass of the standard URL hyperlink detector
org.eclipse.jface.text.hyperlink.URLHyperlinkDetector because that one
is only capable of finding hyperlinks at the start of the region.
Others, like those from mylyn, do find all links in a region on their
own.

For an example commit message see: 
https://bugs.eclipse.org/bugs/show_bug.cgi?id=415537

Change-Id: I464f321d5f5d62836d031615b0c6252a54ee893f
Signed-off-by: Alayna Houston xxx@xxx.xxx
Signed-off-by: Douglas Trujillo xxx@xxx.xxx

COMMENTS

author: Douglas Trujillo
date: 2015-09-16 23:19:56.000000000

Uploaded patch set 3.

-------------------------------------
author: Douglas Trujillo
date: 2015-09-16 23:20:46.000000000

Patch Set 3: Code-Review+2

impressive improvement for the sample commit message, thanks :-)

-------------------------------------
author: Brenden Conley
date: 2015-09-16 23:26:27.000000000

Patch Set 3:

Build Started https://hudson.eclipse.org/egit/job/egit.gerrit/7621/

-------------------------------------
author: Brenden Conley
date: 2015-09-16 23:49:45.000000000

Patch Set 3: Verified+1

Build Successful 

https://hudson.eclipse.org/egit/job/egit.gerrit/7621/ : SUCCESS

-------------------------------------
author: Gerrit Johnathan Pham
date: 2015-09-16 23:59:26.000000000

Change has been successfully merged into the git repository by Douglas Trujillo

-------------------------------------
