def test_clean_string(self):
seq1 = 'this (is an error)'
seq2 = 'feature/vector'
seq3 = 'ta:tata'
seq4 = 'what (the) hack [this is]'
seq5 = 't a t'
_get_brackets('A')
assert clean_string(seq1)[0] == 'th i s'
assert clean_string(seq2)[1] == 'v e c t o r'
assert clean_string(seq3)[0] == 't a: t a t a'
assert clean_string(seq4)[0] == 'wh a t _ h a c k'
assert clean_string(seq5, segmentized=True)[0] == 't a t'
assert clean_string('a(a', ignore_brackets=False)[0] == 'a ( a'
assert clean_string('a/a', split_entries=False)[0] == 'a / a'
assert clean_string('aa', preparse=[('a', 'b')])[0] == 'bb'
assert clean_string('bb', merge_geminates=False)[0] == 'b b'
assert clean_string('bb', rules={"b": "cd"},
merge_geminates=False)[0] == "cd cd"
def test_clean_string(self):
seq1 = 'this (is an error)'
seq2 = 'feature/vector'
seq3 = 'ta:tata'
seq4 = 'what (the) hack [this is]'
seq5 = 't a t'
_get_brackets('A')
assert clean_string(seq1)[0] == 'th i s'
assert clean_string(seq2)[1] == 'v e c t o r'
assert clean_string(seq3)[0] == 't a: t a t a'
assert clean_string(seq4)[0] == 'wh a t _ h a c k'
assert clean_string(seq5, segmentized=True)[0] == 't a t'
assert clean_string('a(a', ignore_brackets=False)[0] == 'a ( a'
assert clean_string('a/a', split_entries=False)[0] == 'a / a'
assert clean_string('aa', preparse=[('a', 'b')])[0] == 'bb'
assert clean_string('bb', merge_geminates=False)[0] == 'b b'
assert clean_string('bb', rules={"b": "cd"},
merge_geminates=False)[0] == "cd cd"
def test_clean_string():
seq1 = 'this (is an error)'
seq2 = 'feature/vector'
seq3 = 'ta:tata'
seq4 = 'what (the) hack [this is]'
seq5 = 't a t'
_get_brackets('A')
assert clean_string(seq1)[0] == 'th i s'
assert clean_string(seq2)[1] == 'v e c t o r'
assert clean_string(seq3)[0] == 't a: t a t a'
assert clean_string(seq4)[0] == 'wh a t _ h a c k'
assert clean_string(seq5, segmentized=True)[0] == 't a t'
assert clean_string('a(a', ignore_brackets=False)[0] == 'a ( a'
assert clean_string('a/a', split_entries=False)[0] == 'a / a'
def test_sequence(sequence, **keywords):
"""
Test a sequence for compatibility with CLPA and LingPy.
"""
invalid = Counter()
segment_count = Counter()
lingpy_errors = set()
clpa_errors = set()
clpa_repl = defaultdict(set)
general_errors = 0
# clean the string at first, we only take the first item, ignore the rest
try:
segments = clean_string(sequence, **keywords)[0].split(' ')
lingpy_analysis = [
x if y != '0' else '?'
for x, y in zip(segments, tokens2class(segments, 'dolgo'))
]
clpa_analysis, _sounds, _errors = clpa.check_sequence(segments)
general_errors = len(
['?' for x in zip(lingpy_analysis, clpa_analysis) if '?' in x])
except (ValueError, IndexError, AttributeError):
invalid.update([sequence])
segments, clpa_analysis = [], []
if segments:
for a, b, c in zip(segments, lingpy_analysis, clpa_analysis):
if a[0] in clpa.accents:
a = a[1:]
if c[0] in clpa.accents:
c = c[1:]
segment_count.update([a])
if b == '?':
lingpy_errors.add(a)
if c != a:
if c == '?':
clpa_errors.add(a)
else:
clpa_repl[a].add(c)
return (segments, [clpa.segment2clpa(x)
for x in clpa_analysis], invalid, segment_count,
lingpy_errors, clpa_errors, clpa_repl, general_errors)
def simple_profile(wordlist,
ref='ipa',
semi_diacritics='hsʃ̢ɕʂʐʑʒw',
merge_vowels=False,
brackets=None,
splitters='/,;~',
merge_geminates=True,
bad_word="<???>",
bad_sound="<?>",
clts=None,
unknown_sound="!{0}"):
"""
Create an initial Orthography Profile using Lingpy's clean_string procedure.
Parameters
----------
wordlist : ~lingpy.basic.wordlist.Wordlist
A wordlist from which you want to derive an initial
orthography profile.
ref : str (default="ipa")
The name of the reference column in which the words are stored.
semi_diacritics : str
Indicate characters which can occur both as "diacritics" (second part
in a sound) or alone.
merge_vowels : bool (default=True)
Indicate whether consecutive vowels should be merged.
brackets : dict
A dictionary with opening brackets as key and closing brackets as
values. Defaults to a pre-defined set of frequently occurring brackets.
splitters : str
The characters which force the automatic splitting of an entry.
clts : dict (default=None)
A dictionary(like) object that converts a given source sound into a
potential target sound, using the get()-method of the dictionary.
Normally, we think of a CLTS instance here (that is: a cross-linguistic
transcription system as defined in the pyclts package).
bad_word : str (default="«???»")
Indicate how words that could not be parsed should be handled. Note
that both "bad_word" and "bad_sound" are format-strings, so you can add
formatting information here.
bad_sound : str (default="«?»")
Indicate how sounds that could not be converted to a sound class be
handled. Note that both "bad_word" and "bad_sound" are format-strings,
so you can add formatting information here.
unknown_sound : str (default="!{0}")
If with_clts is set to True, use this string to indicate that sounds
are classified as "unknown sound" in the CLTS framework.
Returns
-------
profile : generator
A generator of tuples (three items), indicating the segment, its frequency,
the conversion to sound classes in the Dolgopolsky sound-class model,
and the unicode-codepoints.
"""
clts = clts or {}
nulls = set()
bad_words = set()
brackets = brackets or "([{『（₍⁽«)]}）』⁾₎"
profile = defaultdict(int)
words = [wordlist[idx, ref] for idx in wordlist]
for word in pb(words, desc='iterating over words'):
if isinstance(word, list):
word = ' '.join(word)
cleaned_string = clean_string(word,
semi_diacritics=semi_diacritics,
merge_vowels=merge_vowels,
brackets=None,
ignore_brackets=False,
split_entries=False,
preparse=None,
rules=None,
merge_geminates=merge_geminates)[0]
# retain whole word if there are splitters in the word
if [x for x in cleaned_string if x in brackets + splitters]:
profile[word] += 1
bad_words.add(word)
else:
for segment in cleaned_string.split(' '):
profile[segment] += 1
for segment in [x for x in word if x not in cleaned_string]:
profile[segment] += 1
nulls.add(segment)
for s, f in pb(sorted(profile.items(), key=lambda x: x[1], reverse=True),
desc='preparing profile'):
sclass = token2class(s, 'dolgo')
if s in bad_words:
ipa = bad_word.format(s)
elif sclass == '0' and s not in nulls:
ipa = bad_sound.format(s)
elif s in nulls:
ipa = 'NULL'
elif clts:
sound = clts.get(s, False)
if not sound:
ipa = '!' + s
else:
ipa = text_type(sound)
else:
ipa = s
yield s, ipa, text_type(f), codepoint(s)
def context_profile(wordlist,
ref='ipa',
col="doculect",
semi_diacritics='hsʃ̢ɕʂʐʑʒw',
merge_vowels=False,
brackets=None,
splitters='/,;~',
merge_geminates=True,
clts=False,
bad_word="<???>",
bad_sound="<?>",
unknown_sound="!{0}",
examples=2,
max_entries=100):
"""
Create an advanced Orthography Profile with context and doculect information.
Parameters
----------
wordlist : ~lingpy.basic.wordlist.Wordlist
A wordlist from which you want to derive an initial
orthography profile.
ref : str (default="ipa")
The name of the reference column in which the words are stored.
col : str (default="doculect")
Indicate in which column the information on the language variety is
stored.
semi_diacritics : str
Indicate characters which can occur both as "diacritics" (second part
in a sound) or alone.
merge_vowels : bool (default=True)
Indicate whether consecutive vowels should be merged.
brackets : dict
A dictionary with opening brackets as key and closing brackets as
values. Defaults to a pre-defined set of frequently occurring brackets.
splitters : str
The characters which force the automatic splitting of an entry.
clts : dict (default=None)
A dictionary(like) object that converts a given source sound into a
potential target sound, using the get()-method of the dictionary.
Normally, we think of a CLTS instance here (that is: a cross-linguistic
transcription system as defined in the pyclts package).
bad_word : str (default="«???»")
Indicate how words that could not be parsed should be handled. Note
that both "bad_word" and "bad_sound" are format-strings, so you can add
formatting information here.
bad_sound : str (default="«?»")
Indicate how sounds that could not be converted to a sound class be
handled. Note that both "bad_word" and "bad_sound" are format-strings,
so you can add formatting information here.
unknown_sound : str (default="!{0}")
If with_clts is set to True, use this string to indicate that sounds
are classified as "unknown sound" in the CLTS framework.
examples : int(default=2)
Indicate the number of examples that should be printed out.
Returns
-------
profile : generator
A generator of tuples (three items), indicating the segment, its frequency,
the conversion to sound classes in the Dolgopolsky sound-class model,
and the unicode-codepoints.
"""
clts_ = clts or {}
nulls = set()
bad_words = set()
brackets = brackets or "([{『（₍⁽«)]}）』⁾₎"
profile = defaultdict(list)
errors = set()
for idx, word, language in pb(wordlist.iter_rows(ref, col),
desc='iter words',
total=len(wordlist)):
log.info('processing {0}-{1}'.format(idx, word))
if isinstance(word, list):
word = ' '.join(word)
if word.strip():
try:
cleaned_string = clean_string(
word,
semi_diacritics=semi_diacritics,
merge_vowels=merge_vowels,
brackets=None,
ignore_brackets=False,
split_entries=False,
preparse=None,
rules=None,
merge_geminates=merge_geminates)[0].split(' ')
# retain whole word if there are splitters in the word
if [x for x in cleaned_string if x in brackets + splitters]:
profile[word] += [(language, word)]
bad_words.add(word)
else:
context_pre = ['^'] + (len(cleaned_string) - 1) * ['']
context_post = (len(cleaned_string) - 1) * [''] + ['$']
for ctxA, ctxB, segment in zip(context_pre, context_post,
cleaned_string):
profile[ctxA + segment + ctxB] += [(language, word)]
for segment in [
x for x in word
if x not in ' '.join(cleaned_string)
]:
profile[segment] += [(language, word)]
nulls.add(segment)
except:
errors.add(idx)
log.warn('problem parsing {0}'.format(word))
for s in '^$':
yield s, 'NULL', '', '', '', ''
for idx, (s, entries) in pb(enumerate(
sorted(profile.items(), key=lambda x: len(x[1]), reverse=True)),
desc='yielding entries',
total=len(profile)):
sclass = token2class(s.strip('^$'), 'dolgo')
words, langs = [l[1] for l in entries
][:max_entries], [l[0] for l in entries][:max_entries]
languages = ', '.join(
sorted(set(langs), key=lambda x: langs.count(x), reverse=True))
frequency = str(len(langs))
codepoints = codepoint(s)
examples_ = ', '.join(
sorted(set(words), key=lambda x: words.count(x),
reverse=True)[:examples])
if s in bad_words:
ipa = bad_word.format(s)
elif sclass == '0':
ipa = bad_sound.format(s)
elif s in nulls:
ipa = 'NULL'
elif clts_:
sound = clts_.get(s.strip('^$'), False)
if not sound:
ipa = '!' + s.strip('^$')
else:
ipa = text_type(sound)
else:
ipa = s.strip('^$')
yield s, ipa, examples_, languages, frequency, codepoints
def tokenizer(self):
from lingpy.sequence.sound_classes import clean_string
return lambda _, s, **kw: clean_string(s)
