File size: 3,974 Bytes
3dd785b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
from settings import char_remove
import re
import json
import logging
logging.basicConfig(filename='app.log', level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
def remove_na(string):
for char in char_remove:
string = string.replace(char, "")
return string
def save_json(text, filename):
filename = filename+".json"
with open(filename, "w", encoding='utf-8') as outfile:
json.dump(text, outfile, ensure_ascii=False)
return filename
def format_polygon(polygon):
if not polygon:
return "N/A"
return ", ".join(["[{}, {}]".format(p.x, p.y) for p in polygon])
def filter_tables(input_string, table_numbers):
# Splitting the input_string into tables
tables = re.split(r"Table # \d+", input_string)[1:] # we start from 1 to exclude the initial empty string
json_tables = {}
table_counter = 1
for table_number in table_numbers:
# Picking the specific table
table_str = tables[table_number]
# Extracting cell coordinates and contents
cells = re.findall(r"Cell\[(\d+)\]\[(\d+)\] has content '(.*?)'", table_str)
# Find the number of rows and columns
num_rows = max([int(cell[0]) for cell in cells]) + 1
num_cols = max([int(cell[1]) for cell in cells]) + 1
# Initialize table with empty strings
table = [["" for _ in range(num_cols)] for _ in range(num_rows)]
# Fill table based on cell coordinates
for cell in cells:
row, col, content = int(cell[0]), int(cell[1]), cell[2]
table[row][col] = content
# Adding table to the dictionary
json_tables[f"table_{table_counter}"] = table
# Increment the table counter
table_counter += 1
# Converting the dictionary to a JSON string
json_string = json.dumps(json_tables)
return json_string
def extract_text_within_range(input_string, x_range, y_range):
pattern = r"Line # \d+ text '([^']*)' within bounding polygon '(\[[\d.]+, [\d.]+\], \[[\d.]+, [\d.]+\], \[[\d.]+, [\d.]+\], \[[\d.]+, [\d.]+\])'"
matches = re.findall(pattern, input_string)
output = []
for text, polygon_str in matches:
polygon = eval(polygon_str) # Convert string to list of coordinates
for (x, y) in polygon:
if x_range[0] <= x <= x_range[1] and y_range[0] <= y <= y_range[1]:
output.append(text)
break # If any coordinate is within range, add the text to the output
return output
def merge_strings(input_string, input_coords, extract_coords):
lines1 = input_string.split('\n')
lines2 = input_coords.split('\n')
# Filter out empty lines and strip leading/trailing whitespaces
lines2 = [line.strip() for line in lines2 if line.strip()]
logging.info(lines2)
# Creating dictionaries to store the key-value pairs
dict1 = {line.split(": ")[0]: line.split(": ")[1] for line in lines1}
dict2 = {line.split(": ")[0]: line.split(": ")[1] for line in lines2}
# Updating the values in dict1 with the ones from dict2 if they share the same key
for key in dict1.keys():
if key in dict2:
dict1[key] = dict2[key]
for key, coord_str in dict1.items():
if coord_str.startswith('('): # check if the string represents a tuple
# Parse coordinates
coords = eval(coord_str)
# Convert coordinates into x and y ranges
x_range = (coords[0][0], coords[1][0])
y_range = (coords[0][1], coords[1][1])
# Use the function to extract the text
text = extract_text_within_range(extract_coords, x_range, y_range)
# Update the dictionary with the extracted text or '-||-' if empty
dict1[key] = ', '.join(text) if text else '-||-'
# Constructing the updated string1
input_string = '\n'.join([f"{key}: {value}" for key, value in dict1.items()])
return input_string |