:Qg< d dl Z d dlZd dlZd dlZd dlZd dlZd dlZd dlZd dl Z
ddl m Z ddl
mZ ddlmZmZmZmZmZmZmZmZ ddlmZmZmZm Z ej: d Z G d d
e Z y) N )
BaseParser )Table) scale_image scale_pdfsegments_in_bbox text_in_bboxmerge_close_linesget_table_indexcompute_accuracycompute_whitespace)adaptive_threshold
find_lines
find_contours find_jointscamelotc e Zd ZdZdddddddgddddddd d
d fd Zed
Zedd Zd Zd Z d Z
d Z di fdZ y)Latticea- Lattice method of parsing looks for lines between text
to parse the table.
Parameters
----------
table_regions : list, optional (default: None)
List of page regions that may contain tables of the form x1,y1,x2,y2
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
in PDF coordinate space.
table_areas : list, optional (default: None)
List of table area strings of the form x1,y1,x2,y2
where (x1, y1) -> left-top and (x2, y2) -> right-bottom
in PDF coordinate space.
process_background : bool, optional (default: False)
Process background lines.
line_scale : int, optional (default: 15)
Line size scaling factor. The larger the value the smaller
the detected lines. Making it very large will lead to text
being detected as lines.
copy_text : list, optional (default: None)
{'h', 'v'}
Direction in which text in a spanning cell will be copied
over.
shift_text : list, optional (default: ['l', 't'])
{'l', 'r', 't', 'b'}
Direction in which text in a spanning cell will flow.
split_text : bool, optional (default: False)
Split text that spans across multiple cells.
flag_size : bool, optional (default: False)
Flag text based on font size. Useful to detect
super/subscripts. Adds