Add plant_pol_robertson

entries/plant_pol_robertson/__init__.py

+#! /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 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 *
+from openpyxl import load_workbook
+import pandas
+import shutil
+import subprocess
+import tempfile
+
+title = "Robertson plant-pollinator web"
+description = """A bipartite network of plants and pollinators, from southwestern Illinois, USA[^icon]
+[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
+tags = ['Biological', 'Food web', 'Unweighted']
+url = 'https://iwdb.nceas.ucsb.edu/html/robertson_1929.html'
+citation = [('C. Robertson, "Flowers and insects: lists of visitors to four hundred and fifty-three flowers." Carlinville, IL, USA, C. Robertson. (1929)', 'https://www.google.com/search?q=C.+Robertson%2C+"Flowers+and+insects%3A+lists+of+visitors+to+four+hundred+and+fifty-three+flowers."+Carlinville%2C+IL%2C+USA%2C+C.+Robertson.+(1929)&oq=C.+Robertson%2C+"Flowers+and+insects%3A+lists+of+visitors+to+four+hundred+and+fifty-three+flowers."+Carlinville%2C+IL%2C+USA%2C+C.+Robertson.+(1929)')]
+icon_hash = '56a85c8e26855e083a2f790b'
+ustream_license = None
+upstream_prefix = 'https://iwdb.nceas.ucsb.edu/data/plant_pollinator/excel'
+files = [('robertson_1929.xls', None, None)]
+
+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]
+
+
+            with tempfile.TemporaryDirectory(dir="./cache/temp") as tdir:
+                with open(f"{tdir}/dump.xls", "wb") as fw:
+                    shutil.copyfileobj(fs[0], fw)
+                subprocess.run(["localc", "--convert-to", "xlsx",
+                                f"dump.xls"], cwd=tdir, check=True)
+                wb = load_workbook(f"{tdir}/dump.xlsx", read_only=True)
+
+            g = Graph(directed=False)
+            g.vp.name = g.new_vp("string")
+            g.vp.family = g.new_vp("string")
+            g.vp.order = g.new_vp("string")
+            g.vp.is_pollinator = g.new_vp("bool")
+            vs = {}
+
+            m = pandas.DataFrame(wb.active.values).values
+            for i in range(0, 15265):
+                pname, pfam, polname, polorder, polfam = m[i + 1, :5]
+                if pname not in vs:
+                    v = g.add_vertex()
+                    g.vp.name[v] = pname
+                    g.vp.family[v] = pfam
+                    vs[pname] = v
+                else:
+                    v = vs[pname]
+                if polname not in vs:
+                    u = g.add_vertex()
+                    g.vp.name[u] = polname
+                    g.vp.family[u] = polfam
+                    g.vp.order[u] = polorder
+                    g.vp.is_pollinator[u] = True
+                    vs[polname] = u
+                else:
+                    u = vs[polname]
+                e = g.add_edge(v, u)
+
+        yield alt, g