def add_charcut_diff(self,
trg_str: str,
reference: str,
match_size: numbers.Integral = 3,
alt_norm: bool = False,
mt_label: str = "MT:",
ref_label: str = "Ref:") -> None:
aligned_segs = charcut.load_input_segs(cand_segs=[trg_str],
ref_segs=[reference])
styled_ops = [
charcut.compare_segments(cand, ref, match_size)
for seg_id, _, _, cand, ref in aligned_segs
]
seg_scores = list(charcut.score_all(aligned_segs, styled_ops,
alt_norm))
# doc_cost = sum(cost for cost, _ in seg_scores)
# doc_div = sum(div for _, div in seg_scores)
self.html_contents.append(
charcut.segs2html(aligned_segs[0],
styled_ops[0],
seg_scores[0],
mt_label=mt_label,
ref_label=ref_label,
use_id_col=False))
def conclude_report(self) -> None:
if self.hyp_sents:
html_filename = os.path.join(self.report_path, "charcut.html")
utils.make_parent_dir(html_filename)
args = utils.ArgClass(html_output_file=html_filename,
match_size=self.match_size,
alt_norm=self.alt_norm)
aligned_segs = charcut.load_input_segs(cand_segs=self.hyp_sents,
ref_segs=self.ref_sents,
src_segs=self.src_sents)
charcut.run_on(aligned_segs, args)
self.hyp_sents, self.ref_sents, self.src_sents = [], [], []
def on_end_inference(self):
if self.hyp_sents:
html_filename = f"{self.report_path}/charcut.html"
util.make_parent_dir(html_filename)
args = util.ArgClass(html_output_file=html_filename,
match_size=self.match_size,
alt_norm=self.alt_norm)
aligned_segs = charcut.load_input_segs(cand_segs=self.hyp_sents,
ref_segs=self.ref_sents,
src_segs=self.src_sents)
charcut.run_on(aligned_segs, args)
self.hyp_sents, self.ref_sents, self.src_sents = [], [], []