github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-18 12:58:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Update grobid.py (#16298)

Browse Source 
there is a case where "coords" does not exist in the "sentence"
therefore, the "split(";")" will lead to error.

we can fix that by adding "if sentence.get("coords") is not None:" 

the resulting empty "sbboxes" from this scenario will raise error at
"sbboxes[0]["page"]" because sbboxes are empty.

the PDF from https://pubmed.ncbi.nlm.nih.gov/23970373/ can replicate
those errors.
This commit is contained in:
Alireza Kashani 2024-01-22 23:03:58 +01:00 committed by GitHub
parent fbe592a5ce
commit d1b4ead87c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
libs/community/langchain_community/document_loaders/parsers/grobid.py
View File

@ -59,19 +59,20 @@ class GrobidParser(BaseBlobParser):
for i, sentence in enumerate(paragraph.find_all("s")): for i, sentence in enumerate(paragraph.find_all("s")):
paragraph_text.append(sentence.text) paragraph_text.append(sentence.text)
sbboxes = [] sbboxes = []
for bbox in sentence.get("coords").split(";"): if sentence.get("coords") is not None:
box = bbox.split(",") for bbox in sentence.get("coords").split(";"):
sbboxes.append( box = bbox.split(",")
{ sbboxes.append(
"page": box[0], {
"x": box[1], "page": box[0],
"y": box[2], "x": box[1],
"h": box[3], "y": box[2],
"w": box[4], "h": box[3],
} "w": box[4],
) }
chunk_bboxes.append(sbboxes) )
if segment_sentences is True: chunk_bboxes.append(sbboxes)
if (segment_sentences is True) and (len(sbboxes) > 0):
fpage, lpage = sbboxes[0]["page"], sbboxes[-1]["page"] fpage, lpage = sbboxes[0]["page"], sbboxes[-1]["page"]
sentence_dict = { sentence_dict = {
"text": sentence.text, "text": sentence.text,