This repository was archived by the owner on Apr 2, 2025. It is now read-only.
File tree Expand file tree Collapse file tree 1 file changed +20
-11
lines changed
Expand file tree Collapse file tree 1 file changed +20
-11
lines changed Original file line number Diff line number Diff line change 1818from urllib .request import urlopen
1919
2020import numpy as np
21- import pandas as pd
2221from pdfminer .converter import PDFPageAggregator
2322from pdfminer .layout import LAParams
2423from pdfminer .layout import LTAnno
@@ -165,17 +164,27 @@ def validate_input(kwargs, flavor="lattice"):
165164
166165
167166def remove_extra (kwargs , flavor = "lattice" ):
167+ """Remove extra key - value pairs from a kwargs dictionary.
168+
169+ Parameters
170+ ----------
171+ kwargs : [type]
172+ [description]
173+ flavor : str, optional
174+ [description], by default "lattice"
175+
176+ Returns
177+ -------
178+ [type]
179+ [description]
180+
181+ """
168182 parser_kwargs = flavor_to_kwargs [flavor ]
169- # s.difference(t): new set with elements in s but not in t
170- isec = set (kwargs .keys ()).difference (set (parser_kwargs ))
171- if flavor == "lattice" :
172- for key in kwargs .keys ():
173- if key in stream_kwargs :
174- kwargs .pop (key )
175- else :
176- for key in kwargs .keys ():
177- if key in lattice_kwargs :
178- kwargs .pop (key )
183+ # Avoid "dictionary changed size during iteration"
184+ kwargs_keys = list (kwargs .keys ())
185+ for key in kwargs_keys :
186+ if key not in parser_kwargs :
187+ kwargs .pop (key )
179188 return kwargs
180189
181190
You can’t perform that action at this time.
0 commit comments