def uppercase(
word: Annotation = Annotation("<token:word>"),
out: Output = Output("<token>:uppercase.upper"),
# some_config_variable: str = Config("uppercase.some_setting")
):
"""Convert to uppercase."""
out.write([val.upper() for val in word.read()])
def diapivot_annotate(
out: Output = Output(
"<token>:hist.diapivot",
description="SALDO IDs corresponding to lemgrams"),
lemgram: Annotation = Annotation("<token>:saldo.lemgram"),
model: Model = Model("hist/diapivot.pickle")):
"""Annotate each lemgram with its corresponding saldo_id according to model.
Args:
out (str, optional): Resulting annotation file.
Defaults to Output("<token>:hist.diapivot", description="SALDO IDs corresponding to lemgrams").
lemgram (str, optional): Existing lemgram annotation. Defaults to Annotation("<token>:saldo.lemgram").
model (str, optional): Crosslink model. Defaults to Model("hist/diapivot.pickle").
"""
lexicon = PivotLexicon(model)
lemgram_annotation = list(lemgram.read())
out_annotation = []
for lemgrams in lemgram_annotation:
saldo_ids = []
for lemgram in lemgrams.split(util.DELIM):
s_i = lexicon.get_exactMatch(lemgram)
if s_i:
saldo_ids += [s_i]
out_annotation.append(util.AFFIX + util.DELIM.join(set(saldo_ids)) +
util.AFFIX if saldo_ids else util.AFFIX)
out.write(out_annotation)
def lix(text: Annotation = Annotation("<text>"),
sentence: Annotation = Annotation("<sentence>"),
word: Annotation = Annotation("<token:word>"),
pos: Annotation = Annotation("<token:pos>"),
out: Output = Output("<text>:readability.lix",
description="LIX values for text chunks"),
skip_pos: List[str] = ["MAD", "MID", "PAD"],
fmt: str = "%.2f"):
"""Create LIX annotation for text."""
# Read annotation files and get parent_children relations
text_children, _orphans = text.get_children(sentence)
word_pos = list(word.read_attributes((word, pos)))
sentence_children, _orphans = sentence.get_children(word)
sentence_children = list(sentence_children)
# Calculate LIX for every text element
lix_annotation = []
for text in text_children:
in_sentences = []
for sentence_index in text:
s = sentence_children[sentence_index]
in_sentences.append(
list(
actual_words([word_pos[token_index] for token_index in s],
skip_pos)))
lix_annotation.append(fmt % lix_calc(in_sentences))
out.write(lix_annotation)
def translate_tag(out: Output, tag: Annotation, mapping: dict = {}):
"""Convert part-of-speech tags, specified by the mapping.
Example mappings: parole_to_suc, suc_to_simple, ...
"""
if isinstance(mapping, str):
mapping = util.tagsets.mappings[mapping]
out.write((mapping.get(t, t) for t in tag.read()))
def find_replace_regex(chunk: Annotation,
out: Output,
find: str = "",
sub: str = ""):
"""Do find and replace in values of annotation using a regular expressions.
N.B: When writing regular expressions in YAML they should be enclosed in single quotes.
"""
out.write((re.sub(find, sub, val) for val in chunk.read()))
def concat2(out: Output,
annotations: List[Annotation] = [Annotation],
separator: str = ""):
"""Concatenate two or more annotations, with an optional separator."""
annotations = [list(a.read()) for a in annotations]
out.write([
separator.join([a[n] for a in annotations])
for (n, _) in enumerate(annotations[0])
])
def msdtag(out: Output = Output(
"<token>:hunpos.msd",
cls="token:msd",
description="Part-of-speeches with morphological descriptions"),
word: Annotation = Annotation("<token:word>"),
sentence: Annotation = Annotation("<sentence>"),
binary: Binary = Binary("[hunpos.binary]"),
model: Model = Model("[hunpos.model]"),
morphtable: Optional[Model] = Model("[hunpos.morphtable]"),
patterns: Optional[Model] = Model("[hunpos.patterns]"),
tag_mapping=None,
encoding: str = util.UTF8):
"""POS/MSD tag using the Hunpos tagger."""
if isinstance(tag_mapping, str) and tag_mapping:
tag_mapping = util.tagsets.mappings[tag_mapping]
elif tag_mapping is None or tag_mapping == "":
tag_mapping = {}
pattern_list = []
if patterns:
with open(patterns.path, encoding="utf-8") as pat:
for line in pat:
if line.strip() and not line.startswith("#"):
name, pattern, tags = line.strip().split("\t", 2)
pattern_list.append(
(name, re.compile("^%s$" % pattern), tags))
def replace_word(w):
"""Replace word with alias if word matches a regex pattern."""
for p in pattern_list:
if re.match(p[1], w):
return "[[%s]]" % p[0]
return w
sentences, _orphans = sentence.get_children(word)
token_word = list(word.read())
stdin = SENT_SEP.join(
TOK_SEP.join(
replace_word(token_word[token_index]) for token_index in sent)
for sent in sentences)
args = [model.path]
if morphtable:
args.extend(["-m", morphtable.path])
stdout, _ = util.system.call_binary(binary, args, stdin, encoding=encoding)
out_annotation = word.create_empty_attribute()
for sent, tagged_sent in zip(sentences, stdout.strip().split(SENT_SEP)):
for token_index, tagged_token in zip(
sent,
tagged_sent.strip().split(TOK_SEP)):
tag = tagged_token.strip().split(TAG_SEP)[TAG_COLUMN]
tag = tag_mapping.get(tag, tag)
out_annotation[token_index] = tag
out.write(out_annotation)
def override(chunk: Annotation, repl: Annotation, out: Output):
"""Replace values in 'chunk' with non empty values from 'repl'."""
def empty(val):
if not val:
return True
return val == "|"
repl = list(repl.read())
out.write((repl[n] if not empty(repl[n]) else val
for (n, val) in enumerate(chunk.read())))
def struct_to_token(
attr: Annotation = Annotation("{struct}:{attr}"),
token: Annotation = Annotation("<token>"),
out: Output = Output("<token>:misc.from_struct_{struct}_{attr}")):
"""Convert an attribute on a structural annotation into a token attribute."""
token_parents = token.get_parents(attr)
attr_values = list(attr.read())
out_values = [
attr_values[p] if p is not None else "" for p in token_parents
]
out.write(out_values)
def select(out: Output,
annotation: Annotation,
index: Optional[int] = 0,
separator: Optional[str] = " "):
"""Select a specific index from the values of an annotation.
The given annotation values are separated by 'separator',
by default whitespace, with at least index + 1 elements.
"""
if isinstance(index, str):
index = int(index)
out.write(value.split(separator)[index] for value in annotation.read())
def upostag(out: Output = Output("<token>:misc.upos",
cls="token:upos",
description="Part-of-speeches in UD"),
pos: Annotation = Annotation("<token:pos>")):
"""Convert SUC POS tags to UPOS."""
pos_tags = pos.read()
out_annotation = []
for tag in pos_tags:
out_annotation.append(util.tagsets.pos_to_upos(tag, "swe", "SUC"))
out.write(out_annotation)
def save(self):
"""Save text data and annotation files to disk."""
text = unicodedata.normalize("NFC", "".join(self.text))
Text(self.doc).write(text)
structure = []
header_elements = []
for element in self.data:
is_header = False
spans = []
attributes = {attr: [] for attr in self.data[element]["attrs"]}
for instance in self.data[element]["elements"]:
start, start_subpos, end, end_subpos, _original_element, attrs = instance
spans.append(((start, start_subpos), (end, end_subpos)))
for attr in attributes:
attributes[attr].append(attrs.get(attr, ""))
full_element = "{}.{}".format(self.prefix,
element) if self.prefix else element
if element in self.header_elements:
is_header = True
header_elements.append(full_element)
else:
structure.append(full_element)
# Sort spans and annotations by span position (required by Sparv)
if attributes:
attr_names, attr_values = list(zip(*attributes.items()))
spans, *attr_values = list(
zip(*sorted(zip(spans, *attr_values), key=lambda x: x[0])))
attributes = dict(zip(attr_names, attr_values))
else:
spans.sort()
Output(full_element, doc=self.doc).write(spans)
for attr in attributes:
full_attr = "{}.{}".format(self.prefix,
attr) if self.prefix else attr
Output("{}:{}".format(full_element, full_attr),
doc=self.doc).write(attributes[attr],
allow_newlines=is_header)
if element not in self.header_elements:
structure.append("{}:{}".format(full_element, full_attr))
# Save list of all elements and attributes to a file (needed for export)
SourceStructure(self.doc).write(structure)
if header_elements:
# Save list of all header elements to a file
Headers(self.doc).write(header_elements)
def concat(out: Output,
left: Annotation,
right: Annotation,
separator: str = "",
merge_twins: bool = False):
"""Concatenate values from two annotations, with an optional separator.
If merge_twins is set to True, no concatenation will be done on identical values.
"""
b = list(right.read())
out.write((f"{val_a}{separator}{b[n]}"
if not (merge_twins and val_a == b[n]) else val_a
for (n, val_a) in enumerate(left.read())))
def contextual(out: Output = Output("{chunk}:geo.geo_context", description="Geographical places with coordinates"),
chunk: Annotation = Annotation("{chunk}"),
context: Annotation = Annotation("[geo.context_chunk]"),
ne_type: Annotation = Annotation("swener.ne:swener.type"),
ne_subtype: Annotation = Annotation("swener.ne:swener.subtype"),
ne_name: Annotation = Annotation("swener.ne:swener.name"),
model: Model = Model("[geo.model]"),
method: str = "populous",
language: list = []):
"""Annotate chunks with location data, based on locations contained within the text.
context = text chunk to use for disambiguating places (when applicable).
chunk = text chunk to which the annotation will be added.
"""
model = load_model(model, language=language)
ne_type_annotation = list(ne_type.read())
ne_subtype_annotation = list(ne_subtype.read())
ne_name_annotation = list(ne_name.read())
children_context_chunk, _orphans = context.get_children(chunk)
children_chunk_ne, _orphans = chunk.get_children(ne_type)
out_annotation = chunk.create_empty_attribute()
for chunks in children_context_chunk:
all_locations = [] # TODO: Maybe not needed for anything?
context_locations = []
chunk_locations = defaultdict(list)
for ch in chunks:
for n in children_chunk_ne[ch]:
if ne_type_annotation[n] == "LOC" and "PPL" in ne_subtype_annotation[n]:
location_text = ne_name_annotation[n].replace("\n", " ").replace(" ", " ")
location_data = model.get(location_text.lower())
if location_data:
all_locations.append((location_text, list(location_data)))
context_locations.append((location_text, list(location_data)))
chunk_locations[ch].append((location_text, list(location_data)))
else:
pass
# log.info("No location found for %s" % ne_name_annotation[n].replace("%", "%%"))
chunk_locations = most_populous(chunk_locations)
for c in chunks:
out_annotation[c] = _format_location(chunk_locations.get(c, ()))
out.write(out_annotation)
def number_relative(out: Output = Output("{annotation}:misc.number_rel_{parent}"),
parent: Annotation = Annotation("{parent}"),
child: Annotation = Annotation("{annotation}"),
prefix: str = "",
zfill: bool = False,
start: int = START_DEFAULT):
"""Number chunks by their relative position within a parent."""
parent_children, _orphans = parent.get_children(child)
out.write(("{prefix}{nr:0{length}d}".format(prefix=prefix,
length=len(str(len(parent) - 1 + start))
if zfill else 0,
nr=cnr)
for parent in parent_children
for cnr, _index in enumerate(parent, start)))
def replace_list(chunk: Annotation,
out: Output,
find: str = "",
sub: str = ""):
"""Find and replace annotations.
Find string must match whole annotation.
find and sub are whitespace separated lists of words to replace and their replacement.
"""
find = find.split()
sub = sub.split()
if len(find) != len(sub):
raise util.SparvErrorMessage(
"Find and sub must have the same number of words.")
translate = dict((f, s) for (f, s) in zip(find, sub))
out.write((translate.get(val, val) for val in chunk.read()))
def ufeatstag(out: Output = Output(
"<token>:misc.ufeats",
cls="token:ufeats",
description="Universal morphological features"),
pos: Annotation = Annotation("<token:pos>"),
msd: Annotation = Annotation("<token:msd>")):
"""Convert SUC MSD tags to universal features."""
pos_tags = pos.read()
msd_tags = msd.read()
out_annotation = []
for pos_tag, msd_tag in zip(pos_tags, msd_tags):
feats = util.tagsets.suc_to_feats(pos_tag, msd_tag)
out_annotation.append(util.cwbset(feats))
out.write(out_annotation)
def postag(out: Output = Output("<token>:hunpos.pos",
cls="token:pos",
description="Part-of-speech tags"),
msd: Annotation = Annotation("<token>:hunpos.msd")):
"""Extract POS from MSD."""
from sparv.modules.misc import misc
misc.select(out, msd, index=0, separator=".")
def swefn_words(out: Output = Output("<token>:lexical_classes.swefn",
description="Lexical classes for tokens from SweFN"),
model: Model = Model("[lexical_classes.swefn_word_model]"),
saldoids: Annotation = Annotation("<token:sense>"),
pos: Annotation = Annotation("<token:pos>"),
pos_limit: List[str] = ["NN", "VB", "JJ", "AB"],
disambiguate: bool = True,
connect_ids: bool = False,
delimiter: str = util.DELIM,
affix: str = util.AFFIX,
scoresep: str = util.SCORESEP,
lexicon=None):
"""Swefn specific wrapper for annotate_words. See annotate_words for more info."""
# SweFN annotation function
def annotate_swefn(saldo_ids, lexicon, connect_IDs=False, scoresep=util.SCORESEP):
swefnid = set()
if saldo_ids:
for sid in saldo_ids:
if connect_IDs:
swefnid = swefnid.union(set(i + scoresep + sid for i in lexicon.lookup(sid, default=set())))
else:
swefnid = swefnid.union(lexicon.lookup(sid, default=set()))
return sorted(swefnid)
annotate_words(out, model, saldoids, pos, annotate_swefn, pos_limit=pos_limit, disambiguate=disambiguate,
connect_ids=connect_ids, delimiter=delimiter, affix=affix, scoresep=scoresep, lexicon=lexicon)
def blingbring_words(out: Output = Output("<token>:lexical_classes.blingbring",
description="Lexical classes for tokens from Blingbring"),
model: Model = Model("[lexical_classes.bb_word_model]"),
saldoids: Annotation = Annotation("<token:sense>"),
pos: Annotation = Annotation("<token:pos>"),
pos_limit: List[str] = ["NN", "VB", "JJ", "AB"],
class_set: str = "bring",
disambiguate: bool = True,
connect_ids: bool = False,
delimiter: str = util.DELIM,
affix: str = util.AFFIX,
scoresep: str = util.SCORESEP,
lexicon=None):
"""Blingbring specific wrapper for annotate_words. See annotate_words for more info."""
# pos_limit="NN VB JJ AB" | None
if class_set not in ["bring", "roget_head", "roget_subsection", "roget_section", "roget_class"]:
log.warning("Class '%s' not available. Fallback to 'bring'.")
class_set = "bring"
# Blingbring annotation function
def annotate_bring(saldo_ids, lexicon, connect_IDs=False, scoresep=util.SCORESEP):
rogetid = set()
if saldo_ids:
for sid in saldo_ids:
if connect_IDs:
rogetid = rogetid.union(set(i + scoresep + sid for i in lexicon.lookup(sid, default=set())))
else:
rogetid = rogetid.union(lexicon.lookup(sid, default=dict()).get(class_set, set()))
return sorted(rogetid)
annotate_words(out, model, saldoids, pos, annotate_bring, pos_limit=pos_limit, disambiguate=disambiguate,
class_set=class_set, connect_ids=connect_ids, delimiter=delimiter, affix=affix, scoresep=scoresep,
lexicon=lexicon)
def annotate(
lang: Language = Language(),
model: Model = Model("[treetagger.model]"),
tt_binary: Binary = Binary("[treetagger.binary]"),
out_upos: Output = Output("<token>:treetagger.upos",
cls="token:upos",
description="Part-of-speeches in UD"),
out_pos: Output = Output(
"<token>:treetagger.pos",
cls="token:pos",
description="Part-of-speeches from TreeTagger"),
out_baseform: Output = Output("<token>:treetagger.baseform",
description="Baseforms from TreeTagger"),
word: Annotation = Annotation("<token:word>"),
sentence: Annotation = Annotation("<sentence>"),
encoding: str = util.UTF8):
"""POS/MSD tag and lemmatize using TreeTagger."""
sentences, _orphans = sentence.get_children(word)
word_annotation = list(word.read())
stdin = SENT_SEP.join(
TOK_SEP.join(word_annotation[token_index] for token_index in sent)
for sent in sentences)
args = ["-token", "-lemma", "-no-unknown", "-eos-tag", "<eos>", model.path]
stdout, stderr = util.system.call_binary(tt_binary,
args,
stdin,
encoding=encoding)
log.debug("Message from TreeTagger:\n%s", stderr)
# Write pos and upos annotations.
out_upos_annotation = word.create_empty_attribute()
out_pos_annotation = word.create_empty_attribute()
for sent, tagged_sent in zip(sentences, stdout.strip().split(SENT_SEP)):
for token_id, tagged_token in zip(sent,
tagged_sent.strip().split(TOK_SEP)):
tag = tagged_token.strip().split(TAG_SEP)[TAG_COLUMN]
out_pos_annotation[token_id] = tag
out_upos_annotation[token_id] = util.tagsets.pos_to_upos(
tag, lang, TAG_SETS.get(lang))
out_pos.write(out_pos_annotation)
out_upos.write(out_upos_annotation)
# Write lemma annotations.
out_lemma_annotation = word.create_empty_attribute()
for sent, tagged_sent in zip(sentences, stdout.strip().split(SENT_SEP)):
for token_id, tagged_token in zip(sent,
tagged_sent.strip().split(TOK_SEP)):
lem = tagged_token.strip().split(TAG_SEP)[LEM_COLUMN]
out_lemma_annotation[token_id] = lem
out_baseform.write(out_lemma_annotation)
def process_output(word: Annotation, out: Output, stdout, in_sentences,
saldo_annotation, prob_format, default_prob):
"""Parse WSD output and write annotation."""
out_annotation = word.create_empty_attribute()
# Split output into sentences
out_sentences = stdout.strip()
out_sentences = out_sentences.split("\t".join(
["_", "_", "_", "_", SENT_SEP, "_", "_"]))
out_sentences = [i for i in out_sentences if i]
# Split output into tokens
for out_sent, in_sent in zip(out_sentences, in_sentences):
out_tokens = [t for t in out_sent.split("\n") if t]
for (out_tok, in_tok) in zip(out_tokens, in_sent):
out_prob = out_tok.split("\t")[6]
out_prob = [i for i in out_prob.split("|") if i != "_"]
out_meanings = [
i for i in out_tok.split("\t")[5].split("|") if i != "_"
]
saldo = [
i for i in saldo_annotation[in_tok].strip(util.AFFIX).split(
util.DELIM) if i
]
new_saldo = []
if out_prob:
for meaning in saldo:
if meaning in out_meanings:
i = out_meanings.index(meaning)
new_saldo.append((meaning, float(out_prob[i])))
else:
new_saldo.append((meaning, default_prob))
else:
new_saldo = [(meaning, default_prob) for meaning in saldo]
# Sort by probability
new_saldo.sort(key=lambda x: (-x[1], x[0]))
# Format probability according to prob_format
new_saldo = [
saldo + prob_format % prob if prob_format else saldo
for saldo, prob in new_saldo
]
out_annotation[in_tok] = util.cwbset(new_saldo)
out.write(out_annotation)
def ids(doc: Document = Document(),
annotation: Annotation = Annotation("{annotation}"),
out: Output = Output("{annotation}:misc.id",
description="Unique ID for {annotation}"),
docid: AnnotationData = AnnotationData("<docid>"),
prefix: str = ""):
"""Create unique IDs for every span of an existing annotation."""
docid = docid.read()
prefix = prefix + docid
ann = list(annotation.read())
out_annotation = []
# Use doc name and annotation name as seed for the IDs
_reset_id("{}/{}".format(doc, annotation), len(ann))
for _ in ann:
new_id = _make_id(prefix, out_annotation)
out_annotation.append(new_id)
out.write(out_annotation)
def nominal_ratio(text: Annotation = Annotation("<text>"),
pos: Annotation = Annotation("<token:pos>"),
out: Output = Output(
"<text>:readability.nk",
description="Nominal ratios for text chunks"),
noun_pos: List[str] = ["NN", "PP", "PC"],
verb_pos: List[str] = ["PN", "AB", "VB"],
fmt: str = "%.2f"):
"""Create nominal ratio annotation for text."""
text_children, _orphans = text.get_children(pos)
pos_annotation = list(pos.read())
# Calculate OVIX for every text element
nk_annotation = []
for text in text_children:
in_pos = [pos_annotation[token_index] for token_index in text]
nk_annotation.append(fmt %
nominal_ratio_calc(in_pos, noun_pos, verb_pos))
out.write(nk_annotation)
def number_by_attribute(out: Output = Output("{annotation}:misc.number_by_{attribute}"),
chunk: Annotation = Annotation("{annotation}:{attribute}"),
prefix: str = "",
zfill: bool = False,
start: int = START_DEFAULT):
"""Number chunks, with the order determined by an attribute."""
def _order(_index, value):
return _natural_sorting(value)
_read_chunks_and_write_new_ordering(out, chunk, _order, prefix, zfill, start)
def ovix(text: Annotation = Annotation("<text>"),
word: Annotation = Annotation("<token:word>"),
pos: Annotation = Annotation("<token:pos>"),
out: Output = Output("<text>:readability.ovix",
description="OVIX values for text chunks"),
skip_pos: List[str] = ["MAD", "MID", "PAD"],
fmt: str = "%.2f"):
"""Create OVIX annotation for text."""
text_children, _orphans = text.get_children(word)
word_pos = list(word.read_attributes((word, pos)))
# Calculate OVIX for every text element
ovix_annotation = []
for text in text_children:
in_words = list(
actual_words([word_pos[token_index] for token_index in text],
skip_pos))
ovix_annotation.append(fmt % ovix_calc(in_words))
out.write(ovix_annotation)
def metadata(out: Output = Output("{chunk}:geo.geo_metadata", description="Geographical places with coordinates"),
chunk: Annotation = Annotation("{chunk}"),
source: Annotation = Annotation("[geo.metadata_source]"),
model: Model = Model("[geo.model]"),
method: str = "populous",
language: list = []):
"""Get location data based on metadata containing location names."""
geomodel = load_model(model, language=language)
same_target_source = chunk.split()[0] == source.split()[0]
chunk_annotation = list(chunk.read())
source_annotation = list(source.read())
# If location source and target chunk are not the same, we need
# to find the parent/child relations between them.
if not same_target_source:
target_source_parents = list(source.get_parents(chunk))
chunk_locations = {}
for i, _ in enumerate(chunk_annotation):
if same_target_source:
location_source = source_annotation[i]
else:
location_source = source_annotation[target_source_parents[i]] if target_source_parents[
i] is not None else None
if location_source:
location_data = geomodel.get(location_source.strip().lower())
if location_data:
chunk_locations[i] = [(location_source, list(location_data))]
else:
chunk_locations[i] = []
chunk_locations = most_populous(chunk_locations)
out_annotation = chunk.create_empty_attribute()
for c in chunk_locations:
out_annotation[c] = _format_location(chunk_locations.get(c, ()))
out.write(out_annotation)
def _read_chunks_and_write_new_ordering(out: Output, chunk: Annotation, order, prefix="", zfill=False,
start=START_DEFAULT):
"""Common function called by other numbering functions."""
new_order = defaultdict(list)
in_annotation = list(chunk.read())
for i, val in enumerate(in_annotation):
val = order(i, val)
new_order[val].append(i)
out_annotation = chunk.create_empty_attribute()
nr_digits = len(str(len(new_order) - 1 + start))
for nr, key in enumerate(sorted(new_order), start):
for index in new_order[key]:
out_annotation[index] = "{prefix}{nr:0{length}d}".format(prefix=prefix,
length=nr_digits if zfill else 0,
nr=nr)
out.write(out_annotation)
def number_by_position(out: Output = Output("{annotation}:misc.number_position"),
chunk: Annotation = Annotation("{annotation}"),
prefix: str = "",
zfill: bool = False,
start: int = START_DEFAULT):
"""Number chunks by their position."""
spans = list(chunk.read_spans())
def _order(index, _value):
return spans[index]
_read_chunks_and_write_new_ordering(out, chunk, _order, prefix, zfill, start)
def dateformat(
in_from: Annotation = Annotation("[dateformat.datetime_from]"),
in_to: Optional[Annotation] = Annotation("[dateformat.datetime_to]"),
out_from: Output = Output(
"[dateformat.out_annotation]:dateformat.datefrom",
description="From-dates"),
out_to: Optional[Output] = Output(
"[dateformat.out_annotation]:dateformat.dateto",
description="To-dates"),
informat: str = Config("dateformat.datetime_informat"),
outformat: str = Config("dateformat.date_outformat"),
splitter: Optional[str] = Config("dateformat.splitter", None),
regex: Optional[str] = Config("dateformat.regex", None)):
"""Convert existing dates/times to specified date output format.
http://docs.python.org/library/datetime.html#strftime-and-strptime-behavior
Args:
in_from (str, optional): Annotation containing from-dates (and times).
Defaults to Annotation("[dateformat.datetime_from]").
in_to (Optional[str], optional): Annotation containing to-dates.
Defaults to Annotation("[dateformat.datetime_to]").
out_from (str, optional): Annotation with from-times to be written.
Defaults to Output("[dateformat.out_annotation]:dateformat.datefrom",description="From-dates").
out_to (Optional[str], optional): Annotation with to-times to be written.
Defaults to Output("[dateformat.out_annotation]:dateformat.dateto",description="To-dates").
informat (str, optional): Format of the in_from and in_to dates/times.
Several formats can be specified separated by |. They will be tried in order.
Defaults to Config("dateformat.datetime_informat").
outformat (str, optional): Desired format of the out_from and out_to dates.
Several formats can be specified separated by |. They will be tied to their respective in-format.
Defaults to Config("dateformat.date_outformat", "%Y%m%d").
splitter (str, optional): One or more characters separating two dates in 'in_from',
treating them as from-date and to-date. Defaults to Config("dateformat.splitter", None).
regex (str, optional): Regular expression with a catching group whose content will be used in the parsing
instead of the whole string. Defaults to Config("dateformat.regex", None).
"""
_formatter(in_from, in_to, out_from, out_to, informat, outformat, splitter,
regex)
