History of sep_hyperlinks
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.
[entries] Add the date when each entry was added, and remove icon_hash beff7c9
The dates are those of the commits that first added the entries' files (2020-08-11 for the entries of the initial commit); renamed entries keep the date of their first name. Changed: none
diff --git a/entries/sep_hyperlinks/__init__.py b/entries/sep_hyperlinks/__init__.py
index cfb67db..c715ec9 100644
--- a/entries/sep_hyperlinks/__init__.py
+++ b/entries/sep_hyperlinks/__init__.py
@@ -33,7 +33,7 @@ tags = ['Informational', 'Web graph', 'Unweighted', 'Temporal']
url = 'https://github.com/adamdedwards/sep-graph'
citation = [('A. D. Edwards, "SEP Graph: A graphical representation and analysis of the Stanford Encyclopedia of Philosophy." https://github.com/adamdedwards/sep-graph (2018)', 'https://github.com/adamdedwards/sep-graph'),
('"The Stanford Encyclopedia of Philosophy." Stanford University. ISSN 1095-5054', 'https://plato.stanford.edu')]
-icon_hash = '5c397c3c5cc47b871aeccf7c'
+date_added = '2026-10-25'
upstream_license = None
upstream_prefix = 'https://raw.githubusercontent.com/adamdedwards/sep-graph/1d00da70be0e76a52fba5a4aed764735ebfde941/data'
[entries] Prefix the properties in the descriptions with (Node), (Edge) or (Graph) bc3dbbd
The lists of properties at the end of the descriptions marked edge properties with "Edge" but left node properties unmarked, or grouped them in "Nodes: `a`, ...; `b`, ..." items, so the kind of a property was often unclear. Every item now starts with (Node), (Edge) or (Graph), followed by the property names, a colon and the explanation, one item per property or group of properties; qualifications (kinds of nodes, networks) follow the names in parentheses. Properties that were only named got a short explanation, and a few items that named the wrong kind of property were corrected.
diff --git a/entries/sep_hyperlinks/__init__.py b/entries/sep_hyperlinks/__init__.py
index cec77cf..cfb67db 100644
--- a/entries/sep_hyperlinks/__init__.py
+++ b/entries/sep_hyperlinks/__init__.py
@@ -28,7 +28,7 @@ Each network is labeled by the year and season of the edition, e.g. `1998_fall`.
The networks have the following properties:
-- Nodes: `name`, the identifier of the article in its URL (e.g. `aristotle-politics`)."""
+- (Node) `name`: the identifier of the article in its URL (e.g. `aristotle-politics`)."""
tags = ['Informational', 'Web graph', 'Unweighted', 'Temporal']
url = 'https://github.com/adamdedwards/sep-graph'
citation = [('A. D. Edwards, "SEP Graph: A graphical representation and analysis of the Stanford Encyclopedia of Philosophy." https://github.com/adamdedwards/sep-graph (2018)', 'https://github.com/adamdedwards/sep-graph'),
[entries] Remove unneeded code from the entries 2c69f19
Unneeded "global files" statements, unused imports and variables, f-strings without placeholders, duplicate keys in foodweb_little_rock (keeping the order and the values used), and the second definition of get_lines() in twitter_higgs. Nothing changes in the networks or descriptions. Changed: none
diff --git a/entries/sep_hyperlinks/__init__.py b/entries/sep_hyperlinks/__init__.py
index 160ab35..cec77cf 100644
--- a/entries/sep_hyperlinks/__init__.py
+++ b/entries/sep_hyperlinks/__init__.py
@@ -57,7 +57,6 @@ def fetch_upstream(force=False):
@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:
[entries] New entry: sep_hyperlinks a6845ce
diff --git a/entries/sep_hyperlinks/__init__.py b/entries/sep_hyperlinks/__init__.py
new file mode 100644
index 0000000..160ab35
--- /dev/null
+++ b/entries/sep_hyperlinks/__init__.py
@@ -0,0 +1,83 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# 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
+# 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 Affero General Public License for more
+# details.
+#
+# 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 *
+
+title = "Stanford Encyclopedia of Philosophy cross-references (1998-2018)"
+description = """Directed networks of hyperlinks among the articles of the Stanford Encyclopedia of Philosophy (SEP), an online reference work of philosophy written and maintained by experts, and published at Stanford University. The SEP keeps quarterly fixed editions (Spring, Summer, Fall and Winter) of its contents, and the networks were crawled from these archived editions by A. D. Edwards, for most editions from Spring 1998 to Summer 2013, and for the Spring, Summer and Fall 2018 editions.
+
+A node is an article (entry) listed in the table of contents of the edition, and a directed edge from article A to article B means that A contains a hyperlink to B (for instance, in its text or in its list of related entries). Only the links given in the relative form `../<article>/` were recorded by the crawler.
+
+Each network is labeled by the year and season of the edition, e.g. `1998_fall`. Multiple hyperlinks from one article to another, and links from an article to itself, are collapsed or removed here. A few articles that are linked to but missing from the table of contents of an edition are included as nodes. The crawls of four editions (Fall 2008, Winter 2010, Summer 2012 and Summer 2013) stopped before all articles were processed (only the articles up to some point in the alphabetical order have out-going links), and these are not included.
+
+The networks have the following properties:
+
+- Nodes: `name`, the identifier of the article in its URL (e.g. `aristotle-politics`)."""
+tags = ['Informational', 'Web graph', 'Unweighted', 'Temporal']
+url = 'https://github.com/adamdedwards/sep-graph'
+citation = [('A. D. Edwards, "SEP Graph: A graphical representation and analysis of the Stanford Encyclopedia of Philosophy." https://github.com/adamdedwards/sep-graph (2018)', 'https://github.com/adamdedwards/sep-graph'),
+ ('"The Stanford Encyclopedia of Philosophy." Stanford University. ISSN 1095-5054', 'https://plato.stanford.edu')]
+icon_hash = '5c397c3c5cc47b871aeccf7c'
+upstream_license = None
+upstream_prefix = 'https://raw.githubusercontent.com/adamdedwards/sep-graph/1d00da70be0e76a52fba5a4aed764735ebfde941/data'
+
+# The editions in the upstream data, except those whose crawl was
+# incomplete (2008_fall, 2010_win, 2012_sum and 2013_sum)
+editions = ([f"{y}_{s}" for y in range(1998, 2008)
+ for s in ["spr", "sum", "fall", "win"]] +
+ ["2008_spr", "2008_sum",
+ "2009_spr", "2009_sum", "2009_fall", "2009_win",
+ "2010_spr", "2010_sum", "2010_fall",
+ "2011_spr", "2011_sum", "2012_spr", "2013_spr",
+ "2018_spr", "2018_sum", "2018_fall"])
+files = [((f"{e}_node_list.csv", f"{e}_edge_list.csv"), e, None)
+ for e in editions]
+
+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
+ with ExitStack() as stack:
+ fs = [stack.enter_context(open_upstream_file(name, fn, "r"))
+ for fn in fnames]
+ nodes = [row[0] for row in list(csv.reader(fs[0]))[1:] if row]
+ edges = [tuple(row[:2]) for row in list(csv.reader(fs[1]))[1:] if row]
+ idx = {}
+ for v in nodes:
+ idx.setdefault(v, len(idx))
+ for s, t in edges:
+ idx.setdefault(s, len(idx))
+ idx.setdefault(t, len(idx))
+ elist = set((idx[s], idx[t]) for s, t in edges if s != t)
+ g = Graph(directed=True)
+ g.add_vertex(len(idx))
+ g.add_edge_list(sorted(elist))
+ g.vp.name = g.new_vp("string")
+ for v, i in idx.items():
+ g.vp.name[i] = v
+ yield alt, g