From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from lists.gentoo.org (pigeon.gentoo.org [208.92.234.80]) by finch.gentoo.org (Postfix) with ESMTP id 44F22138A48 for ; Sun, 2 Nov 2014 00:18:39 +0000 (UTC) Received: from pigeon.gentoo.org (localhost [127.0.0.1]) by pigeon.gentoo.org (Postfix) with SMTP id 87868E0B21; Sun, 2 Nov 2014 00:18:38 +0000 (UTC) Received: from smtp.gentoo.org (smtp.gentoo.org [140.211.166.183]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by pigeon.gentoo.org (Postfix) with ESMTPS id 0011EE0B02 for ; Sun, 2 Nov 2014 00:18:37 +0000 (UTC) Received: from localhost.localdomain (ip70-181-96-121.oc.oc.cox.net [70.181.96.121]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) (Authenticated sender: zmedico) by smtp.gentoo.org (Postfix) with ESMTPSA id E3E593402EC; Sun, 2 Nov 2014 00:18:36 +0000 (UTC) From: Zac Medico To: gentoo-portage-dev@lists.gentoo.org Cc: Zac Medico Subject: [gentoo-portage-dev] [PATCH 2/5] Add IndexStreamIterator and MultiIterGroupBy. Date: Sat, 1 Nov 2014 17:18:29 -0700 Message-Id: <1414887509-21930-1-git-send-email-zmedico@gentoo.org> X-Mailer: git-send-email 2.0.4 In-Reply-To: <1414881983-19877-3-git-send-email-zmedico@gentoo.org> References: <1414881983-19877-3-git-send-email-zmedico@gentoo.org> Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-Id: Gentoo Linux mail X-BeenThere: gentoo-portage-dev@lists.gentoo.org Reply-to: gentoo-portage-dev@lists.gentoo.org X-Archives-Salt: f5483568-366b-4706-9807-f996073a5f46 X-Archives-Hash: 4051b185aef575060dec3ba83f2301fe 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 --- This updated patch includes a logic fix to ensure that all buffered objects are yielded when all of the iterators are exhausted. pym/portage/cache/index/IndexStreamIterator.py | 27 +++++++++ pym/portage/util/iterators/MultiIterGroupBy.py | 82 ++++++++++++++++++++++++++ pym/portage/util/iterators/__init__.py | 2 + 3 files changed, 111 insertions(+) create mode 100644 pym/portage/cache/index/IndexStreamIterator.py create mode 100644 pym/portage/util/iterators/MultiIterGroupBy.py create mode 100644 pym/portage/util/iterators/__init__.py 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..ece7a4c --- /dev/null +++ b/pym/portage/util/iterators/MultiIterGroupBy.py @@ -0,0 +1,82 @@ +# Copyright 2014 Gentoo Foundation +# Distributed under the terms of the GNU General Public License v2 + +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): + + progress = [] + iterators = self._iterators[:] + for index in iterators: + progress.append(None) + + key_map = {} + eof = [] + key_getter = self._key + if key_getter is None: + key_getter = lambda x: x + max_progress = None + + while iterators: + min_progress = None + for i, index in enumerate(iterators): + + if max_progress is not None and \ + max_progress == progress[i] and \ + min_progress is not None and \ + max_progress != min_progress: + # This one has the most progress, + # so allow the others to catch up. + continue + + for entry in index: + progress[i] = key_getter(entry) + key_group = key_map.get(key_getter(entry)) + if key_group is None: + key_group = [] + key_map[key_getter(entry)] = key_group + + key_group.append(entry) + + if min_progress is None or \ + key_getter(entry) < min_progress: + min_progress = key_getter(entry) + + if max_progress is None or \ + key_getter(entry) >= max_progress: + max_progress = key_getter(entry) + # This one has the most progress, + # so allow the others to catch up. + break + + else: + eof.append(i) + + if eof: + for i in reversed(eof): + del iterators[i] + del progress[i] + del eof[:] + + yield_these = [] + for k in key_map: + if not iterators or k <= min_progress: + yield_these.append(k) + + if yield_these: + yield_these.sort() + for k in yield_these: + yield key_map.pop(k) 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 -- 2.0.4