def inspect_discourse_ilg(path, number=None):
"""
Generate a list of AnnotationTypes for a specified text file for parsing
it as an interlinear gloss text file
Parameters
----------
path : str
Full path to text file
number : int, optional
Number of lines per gloss, if not supplied, it is auto-detected
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the text file
"""
trans_delimiters = ['.', ';', ',']
lines = {}
if os.path.isdir(path):
numbers = {}
for root, subdirs, files in os.walk(path):
for filename in files:
if not filename.lower().endswith('.txt'):
continue
p = os.path.join(root, filename)
lines[p] = text_to_lines(p)
numbers[p] = calculate_lines_per_gloss(lines[p])
number = most_frequent_value(numbers)
else:
lines[path] = text_to_lines(path)
number = calculate_lines_per_gloss(lines[path])
p = path
annotation_types = []
for i in range(number):
name = 'Line {}'.format(i + 1)
if i == 0:
att = Attribute('spelling', 'spelling', 'Spelling')
a = AnnotationType(name,
None,
None,
anchor=True,
token=False,
attribute=att)
else:
labels = lines[p][i][1]
cat = Attribute.guess_type(labels, trans_delimiters)
att = Attribute(Attribute.sanitize_name(name), cat, name)
a = AnnotationType(name,
None,
annotation_types[0].name,
token=False,
attribute=att)
if cat == 'tier' and a.trans_delimiter is None:
for l in labels:
for delim in trans_delimiters:
if delim in l:
a.trans_delimiter = delim
break
if a.trans_delimiter is not None:
break
a.add(lines[p][i][1], save=False)
annotation_types.append(a)
for k, v in lines.items():
if k == p:
continue
for i in range(number):
labels = lines[k][i][1]
annotation_types[i].add(labels, save=False)
return annotation_types
def inspect_discourse_textgrid(path):
"""
Generate a list of AnnotationTypes for a specified TextGrid file
Parameters
----------
path : str
Full path to TextGrid file
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the TextGrid file
"""
trans_delimiters = ['.', ' ', ';', ',']
textgrids = []
if os.path.isdir(path):
for root, subdirs, files in os.walk(path):
for filename in files:
if not filename.lower().endswith('.textgrid'):
continue
textgrids.append(os.path.join(root, filename))
else:
textgrids.append(path)
anno_types = []
for t in textgrids:
tg = load_textgrid(t)
spellings, segments, attributes = guess_tiers(tg)
if len(segments) == 0:
base = None
else:
base = segments[0]
if len(spellings) == 0:
anchor = None
else:
anchor = spellings[0]
interval_tiers = [x for x in tg.tiers if isinstance(x, IntervalTier)]
if len(anno_types) == 0:
for ti in interval_tiers:
if ti.name in spellings:
a = AnnotationType(ti.name,
base,
None,
anchor=True,
token=False)
elif ti.name in segments:
a = AnnotationType(ti.name,
None,
anchor,
base=True,
token=True)
else:
labels = uniqueLabels(ti)
cat = Attribute.guess_type(labels, trans_delimiters)
att = Attribute(Attribute.sanitize_name(ti.name), cat,
ti.name)
a = AnnotationType(ti.name,
None,
anchor,
token=False,
attribute=att)
if cat == 'tier':
for l in labels:
for delim in trans_delimiters:
if delim in l:
a.trans_delimiter = delim
break
if a.trans_delimiter is not None:
break
a.add((x.mark for x in ti), save=False)
anno_types.append(a)
else:
if len(anno_types) != len(interval_tiers):
raise (PCTError(
"The TextGrids must have the same number of tiers."))
for i, ti in enumerate(interval_tiers):
anno_types[i].add((x.mark for x in ti), save=False)
return anno_types
def inspect_discourse_textgrid(path):
"""
Generate a list of AnnotationTypes for a specified TextGrid file
Parameters
----------
path : str
Full path to TextGrid file
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the TextGrid file
"""
trans_delimiters = ['.',' ', ';', ',']
textgrids = []
if os.path.isdir(path):
for root, subdirs, files in os.walk(path):
for filename in files:
if not filename.lower().endswith('.textgrid'):
continue
textgrids.append(os.path.join(root,filename))
else:
textgrids.append(path)
anno_types = []
for t in textgrids:
tg = load_textgrid(t)
spellings, segments, attributes = guess_tiers(tg)
if len(segments) == 0:
base = None
else:
base = segments[0]
if len(spellings) == 0:
anchor = None
else:
anchor = spellings[0]
interval_tiers = [x for x in tg.tiers if isinstance(x, IntervalTier)]
if len(anno_types) == 0:
for ti in interval_tiers:
if ti.name in spellings:
a = AnnotationType(ti.name, base, None, anchor = True, token = False)
elif ti.name in segments:
a = AnnotationType(ti.name, None, anchor, base = True, token = True)
else:
labels = uniqueLabels(ti)
cat = Attribute.guess_type(labels, trans_delimiters)
att = Attribute(Attribute.sanitize_name(ti.name), cat, ti.name)
a = AnnotationType(ti.name, None, anchor, token = False, attribute = att)
if cat == 'tier':
for l in labels:
for delim in trans_delimiters:
if delim in l:
a.trans_delimiter = delim
break
if a.trans_delimiter is not None:
break
a.add((x.mark for x in ti), save = False)
anno_types.append(a)
else:
if len(anno_types) != len(interval_tiers):
raise(PCTError("The TextGrids must have the same number of tiers."))
for i, ti in enumerate(interval_tiers):
anno_types[i].add((x.mark for x in ti), save = False)
return anno_types
def inspect_discourse_ilg(path, number = None):
"""
Generate a list of AnnotationTypes for a specified text file for parsing
it as an interlinear gloss text file
Parameters
----------
path : str
Full path to text file
number : int, optional
Number of lines per gloss, if not supplied, it is auto-detected
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the text file
"""
trans_delimiters = ['.', ';', ',']
lines = {}
if os.path.isdir(path):
numbers = {}
for root, subdirs, files in os.walk(path):
for filename in files:
if not filename.lower().endswith('.txt'):
continue
p = os.path.join(root, filename)
lines[p] = text_to_lines(p)
numbers[p] = calculate_lines_per_gloss(lines[p])
number = most_frequent_value(numbers)
else:
lines[path] = text_to_lines(path)
number = calculate_lines_per_gloss(lines[path])
p = path
annotation_types = []
for i in range(number):
name = 'Line {}'.format(i+1)
if i == 0:
att = Attribute('spelling','spelling','Spelling')
a = AnnotationType(name, None, None, anchor = True, token = False, attribute = att)
else:
labels = lines[p][i][1]
cat = Attribute.guess_type(labels, trans_delimiters)
att = Attribute(Attribute.sanitize_name(name), cat, name)
a = AnnotationType(name, None, annotation_types[0].name, token = False, attribute = att)
if cat == 'tier' and a.trans_delimiter is None:
for l in labels:
for delim in trans_delimiters:
if delim in l:
a.trans_delimiter = delim
break
if a.trans_delimiter is not None:
break
a.add(lines[p][i][1], save = False)
annotation_types.append(a)
for k,v in lines.items():
if k == p:
continue
for i in range(number):
labels = lines[k][i][1]
annotation_types[i].add(labels, save = False)
return annotation_types
def inspect_csv(path, num_lines = 10, coldelim = None, transdelim = None):
"""
Generate a list of AnnotationTypes for a specified text file for parsing
it as a column-delimited file
Parameters
----------
path : str
Full path to text file
num_lines: int, optional
The number of lines to parse from the file
coldelim: str, optional
A prespecified column delimiter to use, will autodetect if not
supplied
transdelim : list, optional
A prespecfied set of transcription delimiters to look for, will
autodetect if not supplied
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the text file
"""
if coldelim is not None:
common_delimiters = [coldelim]
else:
common_delimiters = [',','\t',':','|']
if transdelim is not None:
trans_delimiters = [transdelim]
else:
trans_delimiters = ['.',' ', ';', ',']
with open(path,'r', encoding='utf-8') as f:
lines = []
head = f.readline().strip()
for line in f.readlines():
lines.append(line.strip())
#for i in range(num_lines):
# line = f.readline()
# if not line:
# break
# lines.append(line)
best = ''
num = 1
for d in common_delimiters:
trial = len(head.split(d))
if trial > num:
num = trial
best = d
if best == '':
raise(DelimiterError('The column delimiter specified did not create multiple columns.'))
head = head.split(best)
vals = {h: list() for h in head}
for line in lines:
l = line.strip().split(best)
if len(l) != len(head):
raise(PCTError('{}, {}'.format(l,head)))
for i in range(len(head)):
vals[head[i]].append(l[i])
atts = list()
for h in head:
cat = Attribute.guess_type(vals[h][:num_lines], trans_delimiters)
att = Attribute(Attribute.sanitize_name(h), cat, h)
a = AnnotationType(h, None, None, token = False, attribute = att)
if cat == 'tier':
for t in trans_delimiters:
if t in vals[h][0]:
a.trans_delimiter = t
break
a.add(vals[h], save = False)
atts.append(a)
return atts, best
def inspect_csv(path, num_lines = 10, coldelim = None, transdelim = None):
"""
Generate a list of AnnotationTypes for a specified text file for parsing
it as a column-delimited file
Parameters
----------
path : str
Full path to text file
num_lines: int, optional
The number of lines to parse from the file
coldelim: str, optional
A prespecified column delimiter to use, will autodetect if not
supplied
transdelim : list, optional
A prespecfied set of transcription delimiters to look for, will
autodetect if not supplied
Returns
-------
list of AnnotationTypes
Autodetected AnnotationTypes for the text file
"""
if coldelim is not None:
common_delimiters = [coldelim]
else:
common_delimiters = [',','\t',':','|']
if transdelim is not None:
trans_delimiters = [transdelim]
else:
trans_delimiters = ['.',' ', ';', ',']
with open(path,'r', encoding='utf-8') as f:
lines = []
head = f.readline().strip()
for line in f.readlines():
lines.append(line.strip())
#for i in range(num_lines):
# line = f.readline()
# if not line:
# break
# lines.append(line)
best = ''
num = 1
for d in common_delimiters:
trial = len(head.split(d))
if trial > num:
num = trial
best = d
if best == '':
raise(DelimiterError('The column delimiter specified did not create multiple columns.'))
head = head.split(best)
vals = {h: list() for h in head}
for line in lines:
l = line.strip().split(best)
if len(l) != len(head):
raise(PCTError('{}, {}'.format(l,head)))
for i in range(len(head)):
vals[head[i]].append(l[i])
atts = list()
for h in head:
cat = Attribute.guess_type(vals[h][:num_lines], trans_delimiters)
att = Attribute(Attribute.sanitize_name(h), cat, h)
a = AnnotationType(h, None, None, token = False, attribute = att)
if cat == 'tier':
for t in trans_delimiters:
if t in vals[h][0]:
a.trans_delimiter = t
break
a.add(vals[h], save = False)
atts.append(a)
return atts, best
