History of bibsonomy
The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.
[pipeline] Fix KONECT entity files, seekable upstream files and archive formats 2f6e19f
- konect.py: each ent.<net>.<entity>.<attr> file becomes a vertex property on the side of the entity it describes (per-vertex or per-edge files), instead of all of them being written from vertex 0 into `meta` (which put e.g. the item names of bibsonomy and reuters on the wrong nodes); only leading "%" lines are comments. - open_upstream_file(..., seekable=True) returns a seekable file (via a temporary file) for readers that need one (openpyxl, scipy.io.loadmat, zipfile), replacing the per-entry BytesIO copies. - .xz files can be read again; .xz, .rar and .7z downloads are stored as they are, and "x.tar.xz:", "x.rar:" and "x.7z:" member access works (with py7zr or the 7z command); caches in the previous layouts are still read. - parsers.py: vprops_from_txt matches rows by name for graphs keyed by name; the Wikimedia dump readers (stub histories, SQL tables) are shared helpers; new read_doc (tables of Word documents via LibreOffice) and read_epanet (EPANET water network files) readers. - The entries' workarounds are removed (all parse identically).
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index b8c59d0..c1833dc 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -46,24 +46,7 @@ def parse(alts=None):
fs = [stack.enter_context(open_upstream_file(name, fn, "rb")) for fn in fnames]
g = parse_graph(fs, fmt, directed=False)
- # The generic KONECT parser writes both entity name files from
- # vertex 0 onwards; the tags are the first (left) partition, followed
- # by the items
- del g.vp["meta"]
+ # KONECT names the items "publications"
g.vp.is_item = g.vp.is_publication
del g.vp["is_publication"]
- g.vp.name = g.new_vp("string")
- names = {}
- with open_upstream_file(name, fnames[0], "rb") as f:
- with tarfile.open(fileobj=f, mode="r|bz2") as tf:
- for m in tf:
- for kind in ["tag", "item"]:
- if m.name.endswith(f".{kind}.name"):
- names[kind] = [l.decode("utf8").strip() for l
- in tf.extractfile(m)]
- N1 = len(names["tag"])
- assert N1 + len(names["item"]) == g.num_vertices()
- assert not g.vp.is_item.a[:N1].any() and g.vp.is_item.a[N1:].all()
- for i, x in enumerate(names["tag"] + names["item"]):
- g.vp.name[i] = x
yield alt, g
[entries] Fix parse bugs and improve descriptions and metadata 6bb6851
- parse fixes from the review of the descriptions, e.g. us_patents (directed), celegans_2019 (synapse direction), ecoli_transcription and yeast_transcription (regulator to target), bitcoin (direction, phantom node), ego_social (Google+ features and circles), scotus_majority, arxiv_authors and social_location (as in SNAP), caida_as, dnc, dom, mist, reuters and bibsonomy (names on the right nodes), uci_zoo - every description now states explicitly what the nodes and edges represent; corrected titles, years, tags, citations and licences - the "Hypergraph" tag is removed; very large entries are marked `huge = True` (see --skip-huge) - ICON ids of partial duplicates added (hiv_transmission, congress_bills, openflights, dutch_school)
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 5b7b04a..b8c59d0 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -18,9 +18,8 @@
from .. import *
-title = "BibSonomy"
-description = """Three bipartite networks that make up the BibSonomy folksonomy, representing the tag-publication, user-publication, and user-tag networks. The date of this snapshot is uncertain.[^icon]
-[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
+title = "BibSonomy tag assignments (2005-2009)"
+description = """The bipartite tag–item network of the BibSonomy social bookmark and publication management system, as distributed by KONECT, from the official BibSonomy dump. Nodes are 204,673 tags and 767,447 items (vertex property `is_item`), the latter being 487,304 publications and 280,143 bookmarks, and each edge is a tag assignment, connecting a tag to an item it was assigned to; since an item can be tagged several times with the same tag, the network contains multiple edges. The vertex property `name` gives the tag, or the item identifier in the dump (of the form "bibtex:ID" or "bookmark:ID"). The edges are annotated with the time of the tag assignment; almost all of them are between 2005 and the end of 2009, with a few earlier ones (from 1989 on). The exact date of this snapshot is uncertain."""
tags = ['Informational', 'Folksonomy', 'Unweighted', 'Multigraph', 'Timestamps']
url = 'http://konect.cc/networks/bibsonomy-2ti'
citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'https://doi.org/10.1007/s00778-010-0208-4')]
@@ -46,4 +45,25 @@ def parse(alts=None):
with ExitStack() as stack:
fs = [stack.enter_context(open_upstream_file(name, fn, "rb")) for fn in fnames]
g = parse_graph(fs, fmt, directed=False)
+
+ # The generic KONECT parser writes both entity name files from
+ # vertex 0 onwards; the tags are the first (left) partition, followed
+ # by the items
+ del g.vp["meta"]
+ g.vp.is_item = g.vp.is_publication
+ del g.vp["is_publication"]
+ g.vp.name = g.new_vp("string")
+ names = {}
+ with open_upstream_file(name, fnames[0], "rb") as f:
+ with tarfile.open(fileobj=f, mode="r|bz2") as tf:
+ for m in tf:
+ for kind in ["tag", "item"]:
+ if m.name.endswith(f".{kind}.name"):
+ names[kind] = [l.decode("utf8").strip() for l
+ in tf.extractfile(m)]
+ N1 = len(names["tag"])
+ assert N1 + len(names["item"]) == g.num_vertices()
+ assert not g.vp.is_item.a[:N1].any() and g.vp.is_item.a[N1:].all()
+ for i, x in enumerate(names["tag"] + names["item"]):
+ g.vp.name[i] = x
yield alt, g
Update copyright information 73a4f0d
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 945bb19..5b7b04a 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2020-2024 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2026 Tiago de Paula Peixoto <tiago@skewed.de>
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU Affero General Public License as published by the Free
Update copyright information 3d288ea
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 947a00c..945bb19 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2020-2023 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2024 Tiago de Paula Peixoto <tiago@skewed.de>
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU Affero General Public License as published by the Free
Update copyright information 8d005ae
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 94dfe84..947a00c 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2021 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2023 Tiago de Paula Peixoto <tiago@skewed.de>
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU Affero General Public License as published by the Free
Update copyright info db2efcc
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 7cf28bf..94dfe84 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -1,7 +1,7 @@
#! /usr/bin/env python
# -*- coding: utf-8 -*-
#
-# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2021 Tiago de Paula Peixoto <tiago@skewed.de>
#
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU Affero General Public License as published by the Free
Un-orphan KONECT datasets 894eba5
KONECT has been brought back from the dead for the time being.
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index d7b660f..7cf28bf 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -26,7 +26,6 @@ url = 'http://konect.cc/networks/bibsonomy-2ti'
citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'https://doi.org/10.1007/s00778-010-0208-4')]
icon_hash = '5759d0c1bd3e93b53c6955f1'
upstream_prefix = 'http://konect.cc/files'
-orphan = True
files = [('download.tsv.bibsonomy-2ti.tar.bz2', None, 'konect')]
def fetch_upstream(force=False):
Update citations to use DOIs e878874
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 6660669..d7b660f 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -23,7 +23,7 @@ description = """Three bipartite networks that make up the BibSonomy folksonomy,
[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
tags = ['Informational', 'Folksonomy', 'Unweighted', 'Multigraph', 'Timestamps']
url = 'http://konect.cc/networks/bibsonomy-2ti'
-citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf')]
+citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'https://doi.org/10.1007/s00778-010-0208-4')]
icon_hash = '5759d0c1bd3e93b53c6955f1'
upstream_prefix = 'http://konect.cc/files'
orphan = True
Add support for 'orphan' datasets and tag konect entries e330b80
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index be8ce53..6660669 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -26,6 +26,7 @@ url = 'http://konect.cc/networks/bibsonomy-2ti'
citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf')]
icon_hash = '5759d0c1bd3e93b53c6955f1'
upstream_prefix = 'http://konect.cc/files'
+orphan = True
files = [('download.tsv.bibsonomy-2ti.tar.bz2', None, 'konect')]
def fetch_upstream(force=False):
Change license from GPLv3 to AGPLv3 d754be5
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 9a02b9a..be8ce53 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -3,18 +3,18 @@
#
# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
#
-# You should have received a copy of the GNU General Public License
-# along with this program. If not, see <http://www.gnu.org/licenses/>.
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
from .. import *
Add explicit attribution to descriptions obtained from ICON 1645314
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
index 0f8416d..9a02b9a 100644
--- a/entries/bibsonomy/__init__.py
+++ b/entries/bibsonomy/__init__.py
@@ -19,7 +19,8 @@
from .. import *
title = "BibSonomy"
-description = "Three bipartite networks that make up the BibSonomy folksonomy, representing the tag-publication, user-publication, and user-tag networks. The date of this snapshot is uncertain."
+description = """Three bipartite networks that make up the BibSonomy folksonomy, representing the tag-publication, user-publication, and user-tag networks. The date of this snapshot is uncertain.[^icon]
+[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
tags = ['Informational', 'Folksonomy', 'Unweighted', 'Multigraph', 'Timestamps']
url = 'http://konect.cc/networks/bibsonomy-2ti'
citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf')]
Initial commit cc85872
diff --git a/entries/bibsonomy/__init__.py b/entries/bibsonomy/__init__.py
new file mode 100644
index 0000000..0f8416d
--- /dev/null
+++ b/entries/bibsonomy/__init__.py
@@ -0,0 +1,48 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+from .. import *
+
+title = "BibSonomy"
+description = "Three bipartite networks that make up the BibSonomy folksonomy, representing the tag-publication, user-publication, and user-tag networks. The date of this snapshot is uncertain."
+tags = ['Informational', 'Folksonomy', 'Unweighted', 'Multigraph', 'Timestamps']
+url = 'http://konect.cc/networks/bibsonomy-2ti'
+citation = [('D. Benz et al., "The social bookmark and publication management system BibSonomy." The VLDB Journal 19(6),849-875 (2010)', 'http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf')]
+icon_hash = '5759d0c1bd3e93b53c6955f1'
+upstream_prefix = 'http://konect.cc/files'
+files = [('download.tsv.bibsonomy-2ti.tar.bz2', None, 'konect')]
+
+def fetch_upstream(force=False):
+ return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+ force)
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+ global files
+ name = __name__.split(".")[-1]
+ for fnames, alt, fmt in files:
+ if alts is not None and alt not in alts:
+ continue
+ if isinstance(fnames, str):
+ fnames = [fnames]
+ with ExitStack() as stack:
+ fs = [stack.enter_context(open_upstream_file(name, fn, "rb")) for fn in fnames]
+ g = parse_graph(fs, fmt, directed=False)
+ yield alt, g