This commit is contained in:
Bel LaPointe
2023-02-20 09:01:53 -07:00
parent 43ee3d53d2
commit faa336fca4

View File

@@ -36,6 +36,7 @@ class Chars:
result[-1].merge_in(char) result[-1].merge_in(char)
else: else:
result.append(Chars([char], self.page)) result.append(Chars([char], self.page))
# TODO remove headers, footers; maybe median font size vs. max of cluster?
result = [i for i in result if i.n > 2] result = [i for i in result if i.n > 2]
# merge all vertically overlapping boxes # merge all vertically overlapping boxes