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.
Wed, 22 Mar 2017 03:47:28 +0100 stablerange: move the subrange cache into our new class
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:47:28 +0100] rev 2127
stablerange: move the subrange cache into our new class This is the first step toward having more logic in that class
Sun, 19 Mar 2017 00:44:31 +0100 depth: extract code dedicated to depth of a merge in its own function
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sun, 19 Mar 2017 00:44:31 +0100] rev 2126
depth: extract code dedicated to depth of a merge in its own function The merge case is more complicated than the regular one, we extract is for the sake of clarity.
Sat, 18 Mar 2017 22:48:26 +0100 stablerange: move 'depth' inside a new 'stablerange' module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Sat, 18 Mar 2017 22:48:26 +0100] rev 2125
stablerange: move 'depth' inside a new 'stablerange' module The stablerange used for discovery requires significant amount of code. There is algorithme, cache, cache persistence, etc. So we create a dedicated module for it. The function is directly moved into a rich class handling cache (for now in memory) because we know we will need it.
Wed, 22 Mar 2017 03:15:58 +0100 obsdiscovery: document the status of the module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:15:58 +0100] rev 2124
obsdiscovery: document the status of the module I figured i would be useful to document what we expect from the code in each module.
Wed, 22 Mar 2017 03:13:15 +0100 split: move the debugcommand into a dedicated module
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:13:15 +0100] rev 2123
split: move the debugcommand into a dedicated module The code related to debugobsstorestat is fairly independant, we move it into its own module.
Wed, 22 Mar 2017 03:00:11 +0100 legacy: move 'debugrecordpruneparents' in the extensions
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Wed, 22 Mar 2017 03:00:11 +0100] rev 2122
legacy: move 'debugrecordpruneparents' in the extensions The transition is a couple of year old now, repository with the old format must be quite hard to find by now.
Thu, 16 Mar 2017 21:16:57 -0400 checks: correct the shebang line filtering for python files
Matt Harbison <matt_harbison@yahoo.com> [Thu, 16 Mar 2017 21:16:57 -0400] rev 2121
checks: correct the shebang line filtering for python files As it is, the only related file is docs/test2rst.py, which was covered by **.py. Not sure if it matters, but most patterns in core tests are for "#!.*?python". (Though there are a couple "#!.*python" tests.)
Thu, 16 Mar 2017 23:17:07 -0400 tests: add glob for Windows
Matt Harbison <matt_harbison@yahoo.com> [Thu, 16 Mar 2017 23:17:07 -0400] rev 2120
tests: add glob for Windows
Tue, 21 Mar 2017 11:58:55 +0100 tests: adds simple test case for heads checking
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 21 Mar 2017 11:58:55 +0100] rev 2119
tests: adds simple test case for heads checking This is the start of some systemic testing of the head superceeding detection mechanism.
Tue, 21 Mar 2017 10:25:12 +0100 tests: move exchange utility in testlib
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 21 Mar 2017 10:25:12 +0100] rev 2118
tests: move exchange utility in testlib We have a testlib directory now lets use it.
Tue, 14 Mar 2017 16:56:48 -0700 exchange: fix some wrong reference to serveronly
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 14 Mar 2017 16:56:48 -0700] rev 2117
exchange: fix some wrong reference to serveronly The function have all moved into 'obsexchange' now, so we do not need (and actually cannot) seek them in 'evolve.serveronly'.
Tue, 14 Mar 2017 15:50:43 -0700 checks: add a test that check MANIFEST.in content
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 14 Mar 2017 15:50:43 -0700] rev 2116
checks: add a test that check MANIFEST.in content This make sure we keep the things updated.
Tue, 14 Mar 2017 15:43:19 -0700 README: add a link to mercurial devel
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 14 Mar 2017 15:43:19 -0700] rev 2115
README: add a link to mercurial devel This will help people to find the mailing list details.
Tue, 14 Mar 2017 15:42:51 -0700 README: tries to improve the title about server only
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 14 Mar 2017 15:42:51 -0700] rev 2114
README: tries to improve the title about server only This seems a bit better.
Tue, 14 Mar 2017 15:42:21 -0700 README: remove mention of make
Pierre-Yves David <pierre-yves.david@ens-lyon.org> [Tue, 14 Mar 2017 15:42:21 -0700] rev 2113
README: remove mention of make Using pip in all cases seems a better direction.
(0) -1000 -300 -100 -50 -30 +30 +50 +100 +300 +1000 +3000 tip