Skip to content

GitLab

Unverified Commit a288b572 authored by myhloli's avatar myhloli Committed by GitHub
Browse files

Merge pull request #112 from icecraft/feat/not_return_equation_span 

feat: not return equation in txt mode
parents 5c046cca e7ba4a66
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 19 deletions
magic_pdf/pdf_parse_union_core.py
View file @ a288b572
......@@ -59,25 +59,7 @@ def txt_spans_extract(pdf_page, inline_equations, interline_equations):
bbox = span["bbox"]
if float_equal(bbox[0], bbox[2]) or float_equal(bbox[1], bbox[3]):
continue
if span.get('type') == ContentType.InlineEquation:
spans.append(
{
"bbox": list(span["bbox"]),
"content": span["latex"],
"type": ContentType.InlineEquation,
"score": 1.0,
}
)
elif span.get('type') == ContentType.InterlineEquation:
spans.append(
{
"bbox": list(span["bbox"]),
"content": span["latex"],
"type": ContentType.InterlineEquation,
"score": 1.0,
}
)
else:
if span.get('type') not in (ContentType.InlineEquation, ContentType.InterlineEquation):
spans.append(
{
"bbox": list(span["bbox"]),
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment