We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 846e4ec commit 58044b1Copy full SHA for 58044b1
pdftotree/TreeExtract.py
@@ -335,6 +335,7 @@ def get_char_boundaries(self, mention):
335
def get_html_others(self, tag: str, box: List[float], page_num: int) -> Element:
336
element = self.doc.createElement("div")
337
element.setAttribute("class", "ocrx_block")
338
+ # element.setAttribute("pdftotree", tag)
339
top, left, bottom, right = tuple([int(x) for x in box])
340
element.setAttribute("title", f"bbox {left} {top} {right} {bottom}")
341
elems: List[LTTextLine] = get_mentions_within_bbox(
0 commit comments