def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
corpus = read_corpus_with_unannotated(args)
tcache = TimestampCache()
output_dir = get_output_dir(args, default_overwrite=True)
commit_info = None
for k in corpus:
old_doc = corpus[k]
new_doc = copy.deepcopy(old_doc)
span = Span.merge_all(args.spans)
_split_edu(tcache, k, new_doc, args.spans)
diffs = _mini_diff(k, old_doc, new_doc, span)
print("\n".join(diffs).encode('utf-8'), file=sys.stderr)
save_document(output_dir, k, new_doc)
# for commit message generation
commit_info = CommitInfo(key=k,
annotator=args.annotator,
before=old_doc,
after=new_doc,
span=span)
if commit_info and not args.no_commit_msg:
print("-----8<------")
print(commit_msg(commit_info))
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
output_dir = get_output_dir(args)
augmented = read_augmented_corpus(args)
corpus = read_corpus_with_unannotated(args)
renames = compute_renames(corpus, augmented)
# iterate on annotated versions
for key, tgt_doc in sorted(corpus.items()):
print('<== weaving {} ==>'.format(key), file=sys.stderr) # DEBUG
# locate augmented version
ukey = unannotated_key(key)
try:
src_doc = augmented[ukey]
except KeyError:
print('Cannot find augmented version of {}'.format(str(ukey)))
raise
# weave
new_tgt_doc = _weave_docs(renames, src_doc, tgt_doc)
save_document(output_dir, key, new_tgt_doc)
print('<== done ==>', file=sys.stderr) # DEBUG
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
corpus = read_corpus_with_unannotated(args)
tcache = TimestampCache()
output_dir = get_output_dir(args, default_overwrite=True)
commit_info = None
for k in corpus:
old_doc = corpus[k]
new_doc = copy.deepcopy(old_doc)
_merge_edus(tcache, args.span, new_doc)
diffs = _mini_diff(k, old_doc, new_doc, args.span)
print("\n".join(diffs).encode('utf-8'), file=sys.stderr)
save_document(output_dir, k, new_doc)
# for commit message generation
commit_info = CommitInfo(key=k,
annotator=args.annotator,
before=old_doc,
after=new_doc,
span=args.span)
announce_output_dir(output_dir)
if commit_info and not args.no_commit_msg:
print("-----8<------")
print(commit_msg(commit_info))
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
output_dir = get_output_dir(args)
augmented = read_augmented_corpus(args)
corpus = read_corpus_with_unannotated(args)
renames = compute_renames(corpus, augmented)
# iterate on annotated versions
for key, tgt_doc in sorted(corpus.items()):
print('<== weaving {} ==>'.format(key), file=sys.stderr) # DEBUG
# locate augmented version
ukey = unannotated_key(key)
try:
src_doc = augmented[ukey]
except KeyError:
print('Cannot find augmented version of {}'.format(str(ukey)))
raise
# weave
new_tgt_doc = _weave_docs(renames, src_doc, tgt_doc, args.gen)
save_document(output_dir, key, new_tgt_doc)
print('<== done ==>', file=sys.stderr) # DEBUG
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
corpus = read_corpus_with_unannotated(args)
postags = educe.stac.postag.read_tags(corpus, args.corpus)
tcache = TimestampCache()
output_dir = get_output_dir(args, default_overwrite=True)
families = collections.defaultdict(list)
discourse_subcorpus = {}
for k in corpus:
fam = (k.doc, k.subdoc)
families[fam].append(k)
if k.stage == 'discourse':
discourse_subcorpus[fam] = k
for fam in sorted(families):
print(family_banner(fam[0], fam[1], families[fam]))
disc_k = discourse_subcorpus[fam]
doc = corpus[disc_k]
turns, warn_turns = turns_with_final_emoticons(doc, postags[disc_k])
warnings = []
if warn_turns:
warnings.append("Note: These turns have emoticon-only EDUs that "
"I dare not touch because they either "
"participate in relations or CDUs: ")
warnings.extend(" " + doc.text(x.text_span()) for x in warn_turns)
warnings.append("If the "
"relations can be removed, or the CDUs reduced, "
"please do this by hand and re-run the script:")
if not turns:
warnings.append("Skipping %s (and related); no offending emoticons"
% disc_k)
print("\n".join(warnings))
if not turns:
continue
turn_spans = [x.text_span() for x in turns]
for k in families[fam]:
doc = copy.deepcopy(corpus[k])
tags = postags[k]
merge_final_emoticons(tcache, turn_spans, doc, tags)
if k == discourse_subcorpus[fam]:
for turn_span in turn_spans:
print(show_diff(corpus[k], doc, span=turn_span))
print()
save_document(output_dir, k, doc)
tcache.reset()
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
corpus = read_corpus_with_unannotated(args)
postags = educe.stac.postag.read_tags(corpus, args.corpus)
tcache = TimestampCache()
output_dir = get_output_dir(args, default_overwrite=True)
families = collections.defaultdict(list)
discourse_subcorpus = {}
for k in corpus:
fam = (k.doc, k.subdoc)
families[fam].append(k)
if k.stage == 'discourse':
discourse_subcorpus[fam] = k
for fam in sorted(families):
print(family_banner(fam[0], fam[1], families[fam]))
disc_k = discourse_subcorpus[fam]
doc = corpus[disc_k]
turns, warn_turns = turns_with_final_emoticons(doc, postags[disc_k])
warnings = []
if warn_turns:
warnings.append("Note: These turns have emoticon-only EDUs that "
"I dare not touch because they either "
"participate in relations or CDUs: ")
warnings.extend(" " + doc.text(x.text_span()) for x in warn_turns)
warnings.append("If the "
"relations can be removed, or the CDUs reduced, "
"please do this by hand and re-run the script:")
if not turns:
warnings.append(
"Skipping %s (and related); no offending emoticons" % disc_k)
print("\n".join(warnings))
if not turns:
continue
turn_spans = [x.text_span() for x in turns]
for k in families[fam]:
doc = copy.deepcopy(corpus[k])
tags = postags[k]
merge_final_emoticons(tcache, turn_spans, doc, tags)
if k == discourse_subcorpus[fam]:
for turn_span in turn_spans:
print(show_diff(corpus[k], doc, span=turn_span))
print()
save_document(output_dir, k, doc)
tcache.reset()
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
output_dir = get_output_dir(args)
augmented = read_augmented_corpus(args)
corpus = read_corpus_with_unannotated(args)
renames = compute_renames(corpus, augmented)
for key in corpus:
ukey = unannotated_key(key)
new_tgt_doc = _weave_docs(renames, augmented[ukey], corpus[key])
save_document(output_dir, key, new_tgt_doc)
announce_output_dir(output_dir)
def main(args):
"""
Subcommand main.
You shouldn't need to call this yourself if you're using
`config_argparser`
"""
output_dir = get_output_dir(args)
augmented = read_augmented_corpus(args)
corpus = read_corpus_with_unannotated(args)
renames = compute_renames(corpus, augmented)
for key in corpus:
ukey = unannotated_key(key)
new_tgt_doc = _weave_docs(renames, augmented[ukey], corpus[key])
save_document(output_dir, key, new_tgt_doc)
announce_output_dir(output_dir)
