def _to_doc(docfields):
doc = {}
for key in docfields:
value = docfields[key]
key = util.decode(key)
if isinstance(value, list):
value = list(map(util.decode, value))
else:
value = util.decode(value)
if key == "tag" and not isinstance(value, list):
value = [value]
doc[key] = value
return doc
def test_index_pprint_default(capsys, index_one):
index_one.pprint()
docid = list(index_one)[0]["id"]
expected = "id: " + util.decode(docid) + "\n"
out, err = capsys.readouterr()
assert not err
assert out.startswith(expected)
def test_index_pprint_default(capsys, index_one):
index_one.pprint()
docid = list(index_one)[0]["id"]
expected = "id: " + util.decode(docid) + "\n"
out, err = capsys.readouterr()
assert not err
assert out.startswith(expected)
def conf():
try:
c = configparser.SafeConfigParser()
except AttributeError:
c = configparser.ConfigParser()
c.add_section("main")
c.set("main", "data", util.decode("/app/data"))
return c
def _add(writer, **kwargs):
assert "text" not in kwargs
_no_update = kwargs.pop("_no_update", False)
if not kwargs.get("id"):
kwargs["id"] = schema.identifier(kwargs)
text = []
if "tag" in kwargs:
tags = kwargs["tag"]
if not isinstance(tags, (list, tuple)):
tags = tags.split(",")
tags = list(filter(None, [t.strip() for t in tags]))
text.extend(tags * 4) # include in text, and weight high
kwargs["tag"] = tags
if "content" in kwargs:
text.append(kwargs["content"].strip())
kwargs["text"] = " ".join(text)
if not _no_update:
kwargs["updated"] = datetime.now(pytz.utc)
kwargs = dict((k, util.decode(util.strip(kwargs[k]))) for k in kwargs)
writer.update_document(**kwargs)
def test_decode_iso88591():
bs = "café".encode("iso-8859-1")
with pytest.raises(UnicodeDecodeError):
bs.decode("utf8")
assert util.decode(bs) == "café"
def test_decode_utf8():
bs = "चतरस".encode("utf8")
assert isinstance(bs, six.binary_type)
s = util.decode(bs)
assert isinstance(s, six.text_type)
assert s == "चतरस"
def test_decode_ascii():
bs = "asdf".encode("ascii")
assert isinstance(bs, six.binary_type)
s = util.decode(bs)
assert isinstance(s, six.text_type)
assert s == "asdf"
def test_decode_nonstr():
assert util.decode(0) == 0