def test_generate_columns(self):
"""Test the method generating columns of a given dataset"""
def generate_columns_longer(ds):
""" a much longer implemntation of the column generation"""
from invenio.bibrecord import record_add_field
rec = {}
columns = [[num, "", ""] for num in xrange(ds.num_columns)]
# (number, header, title)
cur_col = 0
for hd in ds.column_headers:
for i in xrange(hd["colspan"]):
columns[cur_col][1] = hd["content"].strip()
cur_col += 1
cur_col = 0
for ct in ds.column_titles:
for i in xrange(ct["colspan"]):
columns[cur_col][2] = ct["content"].strip()
cur_col += 1
for col in columns:
subfields = [("n", str(col[0]))]
if col[2] != "":
subfields.append(("t", col[2]))
if col[1] != "":
subfields.append(("d", col[1]))
record_add_field(rec, "910", subfields = subfields)
return rec
ds = Dataset()
ds.column_headers = [{"content": "header1", "colspan" : 1},
{"content": "header2", "colspan" : 3}]
ds.column_titles = [{"content": "title1", "colspan" : 2},
{"content": "title2", "colspan" : 1}]
ds.num_columns = 6
self.assertEqual(ds.generate_columns(), generate_columns_longer(ds), \
"Incorrectly generated columns")
def test_parse_record(self):
"""Tests building record form the MARC XML"""
rec_string = """<record>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">This is the caption</subfield>
<subfield code="9">HEPDATA</subfield>
</datafield>
<datafield tag="520" ind1=" " ind2=" ">
<subfield code="9">HEPDATA</subfield>
</datafield>
<datafield tag="710" ind1=" " ind2=" ">
<subfield code="g">ATLAS</subfield>
</datafield>
<datafield tag="786" ind1=" " ind2=" ">
<subfield code="w">214657</subfield>
<subfield code="r">arXiv:something</subfield>
<subfield code="h">F1</subfield>
</datafield>
<datafield tag="336" ind1=" " ind2=" ">
<subfield code="t">DATASET</subfield>
</datafield>
<datafield tag="980" ind1=" " ind2=" ">
<subfield code="a">DATA</subfield>
</datafield>
<!-- definitions of columns -->
<datafield tag="911" ind1=" " ind2=" ">
<subfield code="x">1</subfield>
<subfield code="y">2</subfield>
</datafield>
<datafield tag="910" ind1=" " ind2=" ">
<subfield code="t">column title</subfield>
<subfield code="d">column description</subfield>
<subfield code="n">0</subfield>
</datafield>
<datafield tag="910" ind1=" " ind2=" ">
<subfield code="t">title2</subfield>
<subfield code="d">column description</subfield>
<subfield code="n">1</subfield>
</datafield>
<datafield tag="910" ind1=" " ind2=" ">
<subfield code="t">title2</subfield>
<subfield code="d">description2</subfield>
<subfield code="n">2</subfield>
</datafield>
<!-- encoding data qualifiers -->
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="r">1</subfield>
<subfield code="c">0</subfield>
<subfield code="c">1</subfield>
</datafield>
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="k">m</subfield>
<subfield code="v">v</subfield>
<subfield code="c">2</subfield>
</datafield>
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="k">p</subfield>
<subfield code="v">q</subfield>
<subfield code="c">0</subfield>
</datafield>
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="k">w</subfield>
<subfield code="v">g</subfield>
<subfield code="c">1</subfield>
<subfield code="c">2</subfield>
</datafield>
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="r">2</subfield>
<subfield code="c">0</subfield>
<subfield code="c">1</subfield>
</datafield>
<datafield tag="653" ind1="1" ind2=" ">
<subfield code="k">z</subfield>
<subfield code="v">v</subfield>
<subfield code="c">2</subfield>
</datafield>
</record>
"""
rec = bibrecord.create_record(rec_string)
# print "The record string: %s\n" % (str(rec), )
ds = Dataset.create_from_record(rec[0], '(l.', 214657, "")
# print str(ds.data_qualifiers)
self.assertEqual(3, ds.num_columns, \
"Incorrect number of columns has been read")
# asserting column titles:
self.assertEqual(2, len(ds.column_headers), "Incorrect number of headers")
self.assertEqual("column title", ds.column_titles[0]["content"], \
"Incorrect content of the first column")
self.assertEqual(1, ds.column_titles[0]["colspan"], \
"Incorrect colspan of the title of first column")
self.assertEqual("title2", ds.column_titles[1]["content"], \
"Incorrect content of the second and third column")
self.assertEqual(2, ds.column_titles[1]["colspan"], \
"Incorrect colspan of the title of second and " + \
"third column")
# asserting on column descriptions
self.assertEqual(2, len(ds.column_titles), \
"Incorrect number of column titles")
self.assertEqual("column description", ds.column_headers[0]["content"], \
"Incorrect description of the first andsecond" + \
" column")
self.assertEqual(2, ds.column_headers[0]["colspan"], \
"Incorrect colspan of the description first" + \
" and second column")
self.assertEqual("description2", ds.column_headers[1]["content"], \
"Incorrect description of the third column")
self.assertEqual(1, ds.column_headers[1]["colspan"], \
"Incorrect colspan of the description thirdcolumn")
self.assertEqual(3, len(ds.data_qualifiers), \
"Incorrect number of detected dscriptor rows")
existing_qual = []
for q_line in ds.data_qualifiers:
l_pos = 0
for q in q_line:
existing_qual.append((l_pos, q))
l_pos += 1
self.assertTrue((0, {"content": "RE : 1", "colspan" : 2 }) in \
existing_qual)
self.assertTrue((1, {"content": "m : v", "colspan" : 1 }) in \
existing_qual)
self.assertTrue((0, {"content": "p : q", "colspan" : 1 }) in \
existing_qual)
self.assertTrue((1, {"content": "w : g", "colspan" : 2 }) in \
existing_qual)
self.assertTrue((0, {"content": "RE : 2", "colspan" : 2 }) in \
existing_qual)
self.assertTrue((1, {"content": "z : v", "colspan" : 1 }) in \
existing_qual)
# now testing the comparison function ... on the same dataset
ds2 = Dataset.create_from_record(rec[0], '(l.', 214657, "")
