$ gnpm install mutationobserver-shim
Note: the svg swapped the working browsers; IE8 works while IE7 fails 1 test
A polyfill for the MutationObserver API (can I use?). The polyfill is more cause we can than should (with subtree at any rate)... It's async and uses a recursive timeout fallback (default checks changes every 30ms + runtime) instead of using the deprecated DOM3 MutationEvents so theoretically can support virtually any environment.
$ npm install mutationobserver-shim
$ bower install MutationObserver-shim
<script src="//cdn.jsdelivr.net/npm/mutationobserver-shim/dist/mutationobserver.min.js"></script>
setTimeout (every ~30 ms) rather than using a setImmediate polyfill; so calls will be made less frequently and likely with more data than the standard MutationObserver. In addition, it can miss changes that occur and then are lost in the interval window.innerHTML will call childList observer listeners with several mutations with only 1 addedNode or removed node per mutation. With the standard you would have 1 call with multiple nodes in addedNodes and removedNodes node lists.childList and subtree changes in node order (eg first element gets swapped with last) should fire a addedNode and removedNode mutation but the correct node may not always be identified.addedNodes and removedNodes are arrays instead of NodeListsoldValue is always called with attribute changesnextSibling and previousSibling correctfullness is questionable (hard to know if the order of appended items). I'd suggest not relying on them anyway (my tests are extremely permissive with these attributes)Currently supports the following MutationObserverInit properties:
style attribute may not be matched in ie<8.textNodes values and not, like in webkit, where setting .innerHTML will add a characterData mutation.By default, the polyfill will check observed nodes about 25 times per second (30 ms interval) for mutations. Try running these jsperf.com tests and the JSLitmus tests in the test suite for usage performance tests. It may be worthwile to adapt MutationObserver._period based on UA or heuristics (todo).
From my tests observing any size element without subtree enabled is relatively cheap. Although I've optimized the subtree check to the best of my abilities it can be costly on large trees. You can draw your own conclusions based on the JSLitmus and jsperf tests noting that you can expect the mo to do its check 28+ times a second (by default).
Although supported, I'd recommend against watching attributes on the subtree on large structures, as the check is complex and expensive on terrible hardware like my phone :(
The included minified file has been tuned for performance.
I've tested and verified compatibility in the following browsers + these Sauce browsers
Try running the test suite and see some simple example usage:
See http://dev.opera.com/articles/view/mutation-observers-tutorial/ for some sample usage.
Copyright 2013 - present © cnpmjs.org | Home |