comparison mercurial/context.py @ 23085:e9165c18f8df stable

status: make 'hg status --rev' faster when there are deleted files

In order not to avoid listing files as both added and deleted, for
example, we check for every file in the manifest if it is in the
_list_ of deleted files. This can get quite slow when there are many
deleted files. Change it to a set to make the containment check
faster. On a somewhat contrived example of the Mozilla repo with the
entire testing/ directory deleted (~14k files), this makes
'hg status --rev .^' go from 26s to 2s.

23084:3ef893520a85

        mf1 = other._manifestmatches(match, s)
        mf2 = self._manifestmatches(match, s)

        modified, added, clean = [], [], []
        deleted, unknown, ignored = s[3], s[4], s[5]
        withflags = mf1.withflags() | mf2.withflags()
        for fn, mf2node in mf2.iteritems():
            if fn in mf1:
                if (fn not in deleted and
                    ((fn in withflags and mf1.flags(fn) != mf2.flags(fn)) or
                     (mf1[fn] != mf2node and
                      (mf2node or self[fn].cmp(other[fn]))))):
                    modified.append(fn)
                elif listclean:
                    clean.append(fn)
                del mf1[fn]
            elif fn not in deleted:
                added.append(fn)
        removed = mf1.keys()
        if removed:
            # need to filter files if they are already reported as removed
            unknown = [fn for fn in unknown if fn not in mf1]

23085:e9165c18f8df

        mf1 = other._manifestmatches(match, s)
        mf2 = self._manifestmatches(match, s)

        modified, added, clean = [], [], []
        deleted, unknown, ignored = s[3], s[4], s[5]
        deletedset = set(deleted)
        withflags = mf1.withflags() | mf2.withflags()
        for fn, mf2node in mf2.iteritems():
            if fn in mf1:
                if (fn not in deletedset and
                    ((fn in withflags and mf1.flags(fn) != mf2.flags(fn)) or
                     (mf1[fn] != mf2node and
                      (mf2node or self[fn].cmp(other[fn]))))):
                    modified.append(fn)
                elif listclean:
                    clean.append(fn)
                del mf1[fn]
            elif fn not in deletedset:
                added.append(fn)
        removed = mf1.keys()
        if removed:
            # need to filter files if they are already reported as removed
            unknown = [fn for fn in unknown if fn not in mf1]