commit: 7bc992a02c89c6c3f76b09bfc978c104fb1c2b9a Author: Zac Medico <zmedico <AT> gentoo <DOT> org> AuthorDate: Sat Nov 1 15:03:26 2014 +0000 Commit: Zac Medico <zmedico <AT> gentoo <DOT> org> CommitDate: Sun Dec 7 23:10:48 2014 +0000 URL: http://sources.gentoo.org/gitweb/?p=proj/portage.git;a=commit;h=7bc992a0
Add IndexStreamIterator and MultiIterGroupBy. This IndexStreamIterator class can be used together with the pkg_desc_index_line_read function to read an index file incrementally as a stream. The MultiIterGroupBy class can be used to iterate over multiple IndexStreamIterator instances at once, incrementally grouping results for a particular package from multiple indices, while limiting the amount of any given index that must be in memory at once. Both of these classes are used by the IndexedPortdb class in the next patch of this series. X-Gentoo-Bug: 525718 X-Gentoo-Bug-URL: https://bugs.gentoo.org/show_bug.cgi?id=525718 --- pym/portage/cache/index/IndexStreamIterator.py | 27 ++++++++ pym/portage/util/iterators/MultiIterGroupBy.py | 94 ++++++++++++++++++++++++++ pym/portage/util/iterators/__init__.py | 2 + 3 files changed, 123 insertions(+) diff --git a/pym/portage/cache/index/IndexStreamIterator.py b/pym/portage/cache/index/IndexStreamIterator.py new file mode 100644 index 0000000..972aee1 --- /dev/null +++ b/pym/portage/cache/index/IndexStreamIterator.py @@ -0,0 +1,27 @@ +# Copyright 2014 Gentoo Foundation +# Distributed under the terms of the GNU General Public License v2 + +class IndexStreamIterator(object): + + def __init__(self, f, parser): + + self.parser = parser + self._file = f + + def close(self): + + if self._file is not None: + self._file.close() + self._file = None + + def __iter__(self): + + try: + + for line in self._file: + node = self.parser(line) + if node is not None: + yield node + + finally: + self.close() diff --git a/pym/portage/util/iterators/MultiIterGroupBy.py b/pym/portage/util/iterators/MultiIterGroupBy.py new file mode 100644 index 0000000..2c31f26 --- /dev/null +++ b/pym/portage/util/iterators/MultiIterGroupBy.py @@ -0,0 +1,94 @@ +# Copyright 2014 Gentoo Foundation +# Distributed under the terms of the GNU General Public License v2 + +import bisect + +class MultiIterGroupBy(object): + """ + This class functions similarly to the itertools.groupby function, + except that it takes multiple source iterators as input. The source + iterators must yield objects in sorted order. A group is yielded as + soon as the progress of all iterators reaches a state which + guarantees that there can not be any remaining (unseen) elements of + the group. This is useful for incremental display of grouped search + results. + """ + + def __init__(self, iterators, key=None): + self._iterators = iterators + self._key = key + + def __iter__(self): + + trackers = [] + for iterator in self._iterators: + trackers.append(_IteratorTracker(iterator)) + + key_map = {} + key_list = [] + eof = [] + key_getter = self._key + if key_getter is None: + key_getter = lambda x: x + min_progress = None + + while trackers: + + for tracker in trackers: + + if tracker.current is not None and \ + tracker.current != min_progress: + # The trackers are sorted by progress, so the + # remaining trackers are guaranteed to have + # sufficient progress. + break + + # In order to avoid over-buffering (waste of memory), + # only grab a single entry. + try: + entry = next(tracker.iterator) + except StopIteration: + eof.append(tracker) + else: + tracker.current = key_getter(entry) + key_group = key_map.get(tracker.current) + if key_group is None: + key_group = [] + key_map[tracker.current] = key_group + bisect.insort(key_list, tracker.current) + key_group.append(entry) + + if eof: + for tracker in eof: + trackers.remove(tracker) + del eof[:] + + if trackers: + trackers.sort() + min_progress = trackers[0].current + # yield if key <= min_progress + i = bisect.bisect_right(key_list, min_progress) + yield_these = key_list[:i] + del key_list[:i] + else: + yield_these = key_list + key_list = [] + + if yield_these: + for k in yield_these: + yield key_map.pop(k) + +class _IteratorTracker(object): + + __slots__ = ('current', 'iterator') + + def __init__(self, iterator): + + self.iterator = iterator + self.current = None + + def __lt__(self, other): + if self.current is None: + return other.current is not None + return other.current is not None and \ + self.current < other.current diff --git a/pym/portage/util/iterators/__init__.py b/pym/portage/util/iterators/__init__.py new file mode 100644 index 0000000..7cd880e --- /dev/null +++ b/pym/portage/util/iterators/__init__.py @@ -0,0 +1,2 @@ +# Copyright 2014 Gentoo Foundation +# Distributed under the terms of the GNU General Public License v2