Wed, 22 Mar 2017 17:52:08 +0100 stablerange: stop using '.index' in debugstablerange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:52:08 +0100] rev 2157
stablerange: stop using '.index' in debugstablerange We now access '[1]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:48:39 +0100 stablerange: make sure nobody use the 'stablekey' property outside the class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:48:39 +0100] rev 2156
stablerange: make sure nobody use the 'stablekey' property outside the class
Wed, 22 Mar 2017 17:47:09 +0100 stablerange: make sure nobody use '.head' anymore
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:47:09 +0100] rev 2155
stablerange: make sure nobody use '.head' anymore We rename the attribute for good measure.
Wed, 22 Mar 2017 17:45:39 +0100 stablerange: stop using '.head' inside the class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:45:39 +0100] rev 2154
stablerange: stop using '.head' inside the class We now access '[0]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:45:21 +0100 stablerange: stop using '.head' in '_slicesrangeat'
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:45:21 +0100] rev 2153
stablerange: stop using '.head' in '_slicesrangeat' We now access '[0]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:44:10 +0100 stablerange: stop using '.head' in '_slicepoint'
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:44:10 +0100] rev 2152
stablerange: stop using '.head' in '_slicepoint' We now access '[0]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:43:36 +0100 stablerange: stop using '.head' in rangelength
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:43:36 +0100] rev 2151
stablerange: stop using '.head' in rangelength We now access '[0]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:43:18 +0100 stablerange: stop using '.head' in debugstablerange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:43:18 +0100] rev 2150
stablerange: stop using '.head' in debugstablerange We now access '[0]' as we'll do with the future tuple.
Wed, 22 Mar 2017 17:38:28 +0100 stablerange: remove node unused 'node' property
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:38:28 +0100] rev 2149
stablerange: remove node unused 'node' property Close to killing that object.
Wed, 22 Mar 2017 17:35:08 +0100 stablerange: stop using '.node' in __repr__
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:35:08 +0100] rev 2148
stablerange: stop using '.node' in __repr__ This remove the last user to this method.
Wed, 22 Mar 2017 17:33:41 +0100 stablerange: change the key to use the revision number
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 17:33:41 +0100] rev 2147
stablerange: change the key to use the revision number Using node is more stable but for now do not have on disk caching and revision number should be find in memory. This makes the data used for the file cache closer to what it will be when we use tuple. We might reintroduce node in the future but let us keep it simple for now.
Wed, 22 Mar 2017 06:05:44 +0100 stablerange: stop using '.node' in _queryrange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 06:05:44 +0100] rev 2146
stablerange: stop using '.node' in _queryrange We access the range-head revision number by index and convert it on site.
Wed, 22 Mar 2017 06:05:32 +0100 stablerange: stop using '.node' in debugstablerange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 06:05:32 +0100] rev 2145
stablerange: stop using '.node' in debugstablerange We access the range-head revision number by index and convert it on site.
Wed, 22 Mar 2017 06:04:30 +0100 stablerange: stop using '.node' in findmissingrange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 06:04:30 +0100] rev 2144
stablerange: stop using '.node' in findmissingrange We access the range-head revision number by index and convert it on site.
Wed, 22 Mar 2017 06:03:57 +0100 stablerange: stop using '.node' in obshashrange
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 06:03:57 +0100] rev 2143
stablerange: stop using '.node' in obshashrange We access the range-head revision number by index and convert it on site.
Wed, 22 Mar 2017 06:02:45 +0100 stablerange: stop using '.node' in subrangesclosure
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 06:02:45 +0100] rev 2142
stablerange: stop using '.node' in subrangesclosure We access the range-head revision number by index and convert it on site.
Wed, 22 Mar 2017 05:15:49 +0100 stablerange: have the class behave as a tuple
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:15:49 +0100] rev 2141
stablerange: have the class behave as a tuple If we want people to use a tuple, we should offer them a tuple. This should help update most of the code iteratively.
Wed, 22 Mar 2017 05:44:39 +0100 obshashrange: extract computation back into the discovery module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:44:39 +0100] rev 2140
obshashrange: extract computation back into the discovery module This obshash is related to discovery and it seems more appropriate to have to live there. This remove the last large piece of logic from the class. We'll now be able to slowly turn it into a tuple.
Wed, 22 Mar 2017 05:36:45 +0100 obshashrange: use a small utility function to access the obshash
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:36:45 +0100] rev 2139
obshashrange: use a small utility function to access the obshash If we want the object to disappear we needs the top level code to stop accessing its attribute.
Wed, 22 Mar 2017 05:32:25 +0100 debugstablerange: minor code reformat
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:32:25 +0100] rev 2138
debugstablerange: minor code reformat The content of that list will become more complex as we drop the object so we make sure to have one value per line for clarity.
Wed, 22 Mar 2017 05:09:21 +0100 stablerange: move the subrangesclosure inside the module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 05:09:21 +0100] rev 2137
stablerange: move the subrangesclosure inside the module This seems more suitable and open the way to simple update of how we build things without too much impact outside the module. The debug command is still in the 'obsdiscovery' module because it also deal to obshash and I'm not sure of were this should live yet.
Sun, 19 Mar 2017 05:33:52 +0100 stablerange: compute subranges from parent when possible
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 05:33:52 +0100] rev 2136
stablerange: compute subranges from parent when possible Unless we are a merge, we can infer the standard subranges of a range by reusing the subranger of its parent. We update the implementation to do so. We still needs the "old way" for merge. We move that code in a dedicated function for the sake of simplicity.
Wed, 22 Mar 2017 04:27:42 +0100 stablerange: add an official warmup function
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 04:27:42 +0100] rev 2135
stablerange: add an official warmup function The function is responsible for making sure we have the necessary data for a sets of heads. For now this only warm the depth cache. More will follow soon. Such explicite warmup will be usefull for on disck caching as an early point of writing will be easier.
Sun, 19 Mar 2017 04:47:31 +0100 stablerange: remove now unnecessary setter
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:47:31 +0100] rev 2134
stablerange: remove now unnecessary setter The class is handling all computations and cache access by itself now. So we can drop this method.
Sun, 19 Mar 2017 04:45:28 +0100 stablerange: directly perform slicing in the getting method
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:45:28 +0100] rev 2133
stablerange: directly perform slicing in the getting method Now that all necessary functions are available, we simply apply the standard slicing on cache miss and proceed.
Sun, 19 Mar 2017 04:43:33 +0100 stablerange: move standard slice point definition in main class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:43:33 +0100] rev 2132
stablerange: move standard slice point definition in main class More migration of code away from the doomed individual class.
Sun, 19 Mar 2017 04:39:00 +0100 stablerange: move the slicing method on the central class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 04:39:00 +0100] rev 2131
stablerange: move the slicing method on the central class We migrate code away for the individual range class.
Sun, 19 Mar 2017 03:07:01 +0100 stablerange: move the range class in the new module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 03:07:01 +0100] rev 2130
stablerange: move the range class in the new module Our ultimate goal is to remove this class for performance reason. however for now, it contains most of the code we care about so we migrate it as a block first.
Sun, 19 Mar 2017 03:06:53 +0100 stablesort: move into the stablerange module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 03:06:53 +0100] rev 2129
stablesort: move into the stablerange module The stable range rely on the stable sort so it make senses to move it there. Will need direct access to it in the future.
Wed, 22 Mar 2017 03:49:40 +0100 subranges: migrate handling of single element range
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:49:40 +0100] rev 2128
subranges: migrate handling of single element range This is the simplest case by far, so we start with that one. We still use the rich object as an argument, but we'll do our best to not relying on that. This is important for performance reason.
(0) -1000 -300 -100 -50 -30 +30 +50 +100 +300 +1000 +3000 tip