The get_pred_html in rapid_doc.model.table.rapid_table_self.table_matcher.main.TableMatch does not add spaces between words in a table cell. Below is a fix, hopefully someone will merge it with the code.
def get_pred_html(
self,
pred_structures: List[str],
matched_index: Dict[int, List[int]],
ocr_contents: List[Tuple[str, float]],
):
end_html = []
td_index = 0
for tag in pred_structures:
if "</td>" not in tag:
end_html.append(tag)
continue
if "<td></td>" == tag:
end_html.extend("<td>")
if td_index in matched_index.keys():
b_with = False
if (
"<b>" in ocr_contents[matched_index[td_index][0]]
and len(matched_index[td_index]) > 1
):
b_with = True
end_html.extend("<b>")
contents = [] # Bug fixing line
for i, td_index_index in enumerate(matched_index[td_index]):
content = ocr_contents[td_index_index][0]
if len(matched_index[td_index]) > 1:
if len(content) == 0:
continue
if content[0] == " ":
content = content[1:]
if "<b>" in content:
content = content[3:]
if "</b>" in content:
content = content[:-4]
if len(content) == 0:
continue
if i != len(matched_index[td_index]) - 1 and " " != content[-1]:
# content += " " #用字符级别的框，每个字符都会多空格
content += ""
contents.append(content) # Bug fixing line
# end_html.extend(content) #Bug fixing removed line
end_html.extend(' '.join(contents)) # Bug fixing line
if b_with:
end_html.extend("</b>")
if "<td></td>" == tag:
end_html.append("</td>")
else:
end_html.append(tag)
td_index += 1
# Filter <thead></thead><tbody></tbody> elements
filter_elements = ["<thead>", "</thead>", "<tbody>", "</tbody>"]
end_html = [v for v in end_html if v not in filter_elements]
return "".join(end_html), end_html
The get_pred_html in rapid_doc.model.table.rapid_table_self.table_matcher.main.TableMatch does not add spaces between words in a table cell. Below is a fix, hopefully someone will merge it with the code.
def get_pred_html(
self,
pred_structures: List[str],
matched_index: Dict[int, List[int]],
ocr_contents: List[Tuple[str, float]],
):