| durin42 |
| hg-reviewers |
This is important for usability when tools are slow or numerous.
| Automatic diff as part of commit; lint not applicable. |
| Automatic diff as part of commit; unit tests not applicable. |
| error, | error, | ||||
| mdiff, | mdiff, | ||||
| merge, | merge, | ||||
| obsolete, | obsolete, | ||||
| pycompat, | pycompat, | ||||
| registrar, | registrar, | ||||
| scmutil, | scmutil, | ||||
| util, | util, | ||||
| worker, | |||||
| ) | ) | ||||
| # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for | # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for | ||||
| # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should | # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should | ||||
| # be specifying the version(s) of Mercurial they are tested with, or | # be specifying the version(s) of Mercurial they are tested with, or | ||||
| # leave the attribute unspecified. | # leave the attribute unspecified. | ||||
| testedwith = 'ships-with-hg-core' | testedwith = 'ships-with-hg-core' | ||||
| raise error.Abort(_('cannot specify both "--rev" and "--all"')) | raise error.Abort(_('cannot specify both "--rev" and "--all"')) | ||||
| opts['rev'] = ['not public() and not obsolete()'] | opts['rev'] = ['not public() and not obsolete()'] | ||||
| opts['working_dir'] = True | opts['working_dir'] = True | ||||
| with repo.wlock(), repo.lock(), repo.transaction('fix'): | with repo.wlock(), repo.lock(), repo.transaction('fix'): | ||||
| revstofix = getrevstofix(ui, repo, opts) | revstofix = getrevstofix(ui, repo, opts) | ||||
| basectxs = getbasectxs(repo, opts, revstofix) | basectxs = getbasectxs(repo, opts, revstofix) | ||||
| workqueue, numitems = getworkqueue(ui, repo, pats, opts, revstofix, | workqueue, numitems = getworkqueue(ui, repo, pats, opts, revstofix, | ||||
| basectxs) | basectxs) | ||||
| filedata = collections.defaultdict(dict) | |||||
| replacements = {} | |||||
| fixers = getfixers(ui) | fixers = getfixers(ui) | ||||
| # Some day this loop can become a worker pool, but for now it's easier | |||||
| # to fix everything serially in topological order. | # There are no data dependencies between the workers fixing each file | ||||
| for rev, path in sorted(workqueue): | # revision, so we can use all available parallelism. | ||||
| def getfixes(items): | |||||
| for rev, path in items: | |||||
| ctx = repo[rev] | ctx = repo[rev] | ||||
| olddata = ctx[path].data() | olddata = ctx[path].data() | ||||
| newdata = fixfile(ui, opts, fixers, ctx, path, basectxs[rev]) | newdata = fixfile(ui, opts, fixers, ctx, path, basectxs[rev]) | ||||
| if newdata != olddata: | # Don't waste memory/time passing unchanged content back, but | ||||
| # produce one result per item either way. | |||||
| yield (rev, path, newdata if newdata != olddata else None) | |||||
| results = worker.worker(ui, 1.0, getfixes, tuple(), workqueue) | |||||
| # We have to hold on to the data for each successor revision in memory | |||||
| # until all its parents are committed. We ensure this by committing and | |||||
| # freeing memory for the revisions in some topological order. This | |||||
| # leaves a little bit of memory efficiency on the table, but also makes | |||||
| # the tests deterministic. It might also be considered a feature since | |||||
| # it makes the results more easily reproducible. | |||||
| filedata = collections.defaultdict(dict) | |||||
| replacements = {} | |||||
| commitorder = sorted(revstofix, reverse=True) | |||||
| for rev, path, newdata in results: | |||||
| if newdata is not None: | |||||
| filedata[rev][path] = newdata | filedata[rev][path] = newdata | ||||
| numitems[rev] -= 1 | numitems[rev] -= 1 | ||||
| if not numitems[rev]: | # Apply the fixes for this and any other revisions that are ready | ||||
| # and sitting at the front of the queue. Using a loop here prevents | |||||
| # the queue from being blocked by the first revision to be ready out | |||||
| # of order. | |||||
| while commitorder and not numitems[commitorder[-1]]: | |||||
| rev = commitorder.pop() | |||||
| ctx = repo[rev] | |||||
| if rev == wdirrev: | if rev == wdirrev: | ||||
| writeworkingdir(repo, ctx, filedata[rev], replacements) | writeworkingdir(repo, ctx, filedata[rev], replacements) | ||||
| else: | else: | ||||
| replacerev(ui, repo, ctx, filedata[rev], replacements) | replacerev(ui, repo, ctx, filedata[rev], replacements) | ||||
| del filedata[rev] | del filedata[rev] | ||||
| replacements = {prec: [succ] for prec, succ in replacements.iteritems()} | replacements = {prec: [succ] for prec, succ in replacements.iteritems()} | ||||
| scmutil.cleanupnodes(repo, replacements, 'fix', fixphase=True) | scmutil.cleanupnodes(repo, replacements, 'fix', fixphase=True) | ||||
| def getworkqueue(ui, repo, pats, opts, revstofix, basectxs): | def getworkqueue(ui, repo, pats, opts, revstofix, basectxs): | ||||
| """"Constructs the list of files to be fixed at specific revisions | """"Constructs the list of files to be fixed at specific revisions | ||||
| It is up to the caller how to consume the work items, and the only | It is up to the caller how to consume the work items, and the only | ||||
| dependence between them is that replacement revisions must be committed in | dependence between them is that replacement revisions must be committed in | ||||
| topological order. Each work item represents a file in the working copy or | topological order. Each work item represents a file in the working copy or | ||||
| in some revision that should be fixed and written back to the working copy | in some revision that should be fixed and written back to the working copy | ||||
| or into a replacement revision. | or into a replacement revision. | ||||
| Work items for the same revision are grouped together, so that a worker | |||||
| pool starting with the first N items in parallel is likely to finish the | |||||
| first revision's work before other revisions. This can allow us to write | |||||
| the result to disk and reduce memory footprint. At time of writing, the | |||||
| partition strategy in worker.py seems favorable to this. We also sort the | |||||
| items by ascending revision number to match the order in which we commit | |||||
| the fixes later. | |||||
| """ | """ | ||||
| workqueue = [] | workqueue = [] | ||||
| numitems = collections.defaultdict(int) | numitems = collections.defaultdict(int) | ||||
| maxfilesize = ui.configbytes('fix', 'maxfilesize') | maxfilesize = ui.configbytes('fix', 'maxfilesize') | ||||
| for rev in revstofix: | for rev in sorted(revstofix): | ||||
| fixctx = repo[rev] | fixctx = repo[rev] | ||||
| match = scmutil.match(fixctx, pats, opts) | match = scmutil.match(fixctx, pats, opts) | ||||
| for path in pathstofix(ui, repo, pats, opts, match, basectxs[rev], | for path in pathstofix(ui, repo, pats, opts, match, basectxs[rev], | ||||
| fixctx): | fixctx): | ||||
| if path not in fixctx: | if path not in fixctx: | ||||
| continue | continue | ||||
| fctx = fixctx[path] | fctx = fixctx[path] | ||||
| if fctx.islink(): | if fctx.islink(): | ||||