def altconcat(*args):
"""
Returns ``[a00, a01, a02, ..., a10, a11, a12, ...]``
>>> ''.join(altconcat('abc', 'ABC'))
'aAbBcC'
>>> ''.join(altconcat('abcd', 'ABC'))
'aAbBcCd'
>>> ''.join(altconcat('abc', 'ABCD'))
'aAbBcCD'
"""
skip = object()
return [elem
for lst in izip_longest(*args, fillvalue=skip)
for elem in lst if elem is not skip]
def altconcat(*args):
"""
Returns ``[a00, a01, a02, ..., a10, a11, a12, ...]``
>>> ''.join(altconcat('abc', 'ABC'))
'aAbBcC'
>>> ''.join(altconcat('abcd', 'ABC'))
'aAbBcCd'
>>> ''.join(altconcat('abc', 'ABCD'))
'aAbBcCD'
"""
skip = object()
return [
elem for lst in izip_longest(*args, fillvalue=skip) for elem in lst
if elem is not skip
]
def as_dict(self):
"""
Turn a MARC record into a dictionary, which is used for ``as_json``.
"""
record = {}
record['leader'] = self.leader
record['fields'] = []
for field in self:
if field.is_control_field():
record['fields'].append({field.tag: field.data})
else:
fd = {}
fd['subfields'] = []
fd['ind1'] = field.indicator1
fd['ind2'] = field.indicator2
for tag, value in izip_longest(*[iter(field.subfields)] * 2):
fd['subfields'].append({tag: value})
record['fields'].append({field.tag: fd})
return record # as dict
def as_dict(self):
"""
Turn a MARC record into a dictionary, which is used for ``as_json``.
"""
record = {}
record['leader'] = self.leader
record['fields'] = []
for field in self:
if field.is_control_field():
record['fields'].append({field.tag: field.data})
else:
fd = {}
fd['subfields'] = []
fd['ind1'] = field.indicator1
fd['ind2'] = field.indicator2
for tag, value in izip_longest(*[iter(field.subfields)] * 2):
fd['subfields'].append({tag: value})
record['fields'].append({field.tag: fd})
return record # as dict
def transpose_to_ldj(record):
json_record = {}
json_record['_LEADER'] = record.leader
json_record['_FORMAT'] = "MarcXchange"
json_record['_TYPE'] = "Bibliographic"
for field in record:
if isint(field.tag):
if field.is_control_field():
json_record[field.tag] = [field.data]
else:
ind = "".join(field.indicators).replace(" ", "_")
ind_obj = []
for k, v in izip_longest(*[iter(field.subfields)] * 2):
if "." in ind:
ind = ind.replace(".", "_")
if "." in k or k.isspace():
k = "_"
ind_obj.append({k: v})
if not field.tag in json_record:
json_record[field.tag] = []
json_record[field.tag].append({ind: ind_obj})
return json_record
def xor(self, other):
return self._bitwise(
izip_longest(self.array, other.array, fillvalue=0),
lambda x, y: x ^ y)
def grouped(items):
args = [iter(items)] * 3
return izip_longest(fillvalue='', *args)
def grouper(iterable, n, fillvalue=None):
""" Collect data into fixed-length chunks or blocks """
# grouper('ABCDEFG', 3, 'x') --> ABC DEF Gxx
args = [iter(iterable)] * n
return izip_longest(*args, fillvalue=fillvalue)
def grouped(items):
args = [iter(items)] * 3
return izip_longest(fillvalue='', *args)
def cldf(dataset, concepticon, **kw):
language_map = {
l['NAME']: l['GLOTTOCODE'] or None
for l in dataset.languages
}
concept_map = {
c.english: c.concepticon_id
for c in dataset.conceptlist.concepts.values()
}
concept_map[
'year'] = '1226' # dunno why this is missing, it's 200 words...
wordlists = list(read_csv(dataset))
cogsets = defaultdict(lambda: defaultdict(list))
for wl in wordlists:
for concept, (words, cogids) in wl.words.items():
if len(cogids) == 1:
cogsets[concept][cogids[0]].append(words[0])
with CldfDataset((
'ID',
'Language_ID',
'Language_name',
'Parameter_ID',
'Parameter_name',
'Value',
'Segments',
'Source',
'Comment',
), dataset) as ds:
ds.sources.add(getEvoBibAsSource(SOURCE))
cognates = []
for wl in wordlists:
#print(wl.language)
for concept, (words, cogids) in wl.words.items():
if len(cogids) > 1:
if len(words) < len(cogids):
if len(words) == 1:
if ':' in words[0]:
words = words[0].split(':')
if ',' in words[0]:
words = words[0].split(',')
assert len(words) >= len(cogids)
assert (wl.language, concept) in COGSET_MAP
if len(words) > len(cogids):
assert (wl.language, concept) in COGSET_MAP
if (wl.language, concept) in COGSET_MAP:
word_to_cogid = COGSET_MAP[(wl.language, concept)]
else:
word_to_cogid = dict(izip_longest(words, cogids))
for i, word in enumerate(words):
if word.startswith('(') and word.endswith(')'):
word = word[1:-1].strip()
wid = '%s-%s-%s' % (slug(
wl.language), slug(concept), i + 1)
ds.add_row([
wid,
'',
wl.language,
concept_map.get(concept, ''),
concept,
word,
clean_string(word, splitters='?')[0],
SOURCE,
'',
])
if word_to_cogid.get(word):
cognates.append([
wid,
ds.name,
word,
'%s-%s' % (slug(concept), word_to_cogid[word]),
False,
'expert',
SOURCE,
'',
'',
'',
])
dataset.cognates.extend(
iter_alignments(ds, cognates, column='Segments'))
def combine(self, pattern, variable):
"""Combine a pattern and variable parts to be a line string again."""
inter_zip = izip_longest(variable, pattern, fillvalue='')
interleaved = [elt for pair in inter_zip for elt in pair]
return ''.join(interleaved)
def excepts(self, *other):
return self._bitwise(
izip_longest(self.array, *[o.array for o in other], fillvalue=0),
lambda x, y: x & ~y)
def union(self, *other):
return self._bitwise(
izip_longest(self.array, *[o.array for o in other], fillvalue=0),
lambda x, y: x | y)
def union(self, *other):
return self._bitwise(
izip_longest(self.array, *[o.array for o in other], fillvalue=0),
lambda x, y: x | y)
def combine(self, pattern, variable):
"""Combine a pattern and variable parts to be a line string again."""
inter_zip = izip_longest(variable, pattern, fillvalue='')
interleaved = [elt for pair in inter_zip for elt in pair]
return ''.join(interleaved)
def excepts(self, *other):
return self._bitwise(
izip_longest(self.array, *[o.array for o in other], fillvalue=0),
lambda x, y: x & ~y)
def xor(self, other):
return self._bitwise(izip_longest(self.array, other.array, fillvalue=0),
lambda x, y: x ^ y)
