5/25/2020

install poppler in ubuntu

Try to this command:

sudo apt-get update -y
sudo apt-get install -y poppler-utils

😁

5/19/2020

Ways to sort list of dictionaries by values in Python – Using lambda function


.
#example list
dict_list = [{ "idx":1, "value1":32.44, "value2":123.2}, { "idx":2, "value1":32.414, "value2":133.2}, { "idx":3, "value1":32.244, "value2":113.2}]

#sort by ascending order
sorted_dict_list = sorted(dict_list, key = lambda i: i['value1'])
#sort by descending order
r_sorted_dict_list = sorted(dict_list, key = lambda i: i['value1'],reverse=True)

#show result
print(sorted_dict_list)
# [{'idx': 3, 'value1': 32.244, 'value2': 113.2}, {'idx': 2, 'value1': 32.414, 'value2': 133.2}, {'idx': 1, 'value1': 32.44, 'value2': 123.2}]

print(r_sorted_dict_list)
# [{'idx': 1, 'value1': 32.44, 'value2': 123.2}, {'idx': 2, 'value1': 32.414, 'value2': 133.2}, {'idx': 3, 'value1': 32.244, 'value2': 113.2}]
.


5/15/2020

multi-thread example python source code

The code generate 10 multi threads for running single_function.
If you have look the pid in result, thread is finished by quickly proceeded.

..
import queue
from concurrent.futures import ThreadPoolExecutor

#function for thread
def single_function(input, pid, out_queue):
total = 0
for i in range(0,input):
for j in range(0, input):
for k in range(0, input):
total = total + 1

out_queue.put( {'index':pid, 'result':total })
#run thread
my_queue = queue.Queue()
with ThreadPoolExecutor(max_workers=10) as executor:
for pid in range(0, 10):
executor.submit(single_function, 100, pid, my_queue)
#get result of each thread
result = {}
while not my_queue.empty():
get = my_queue.get()
print(get)

#finish all thread
..

result

{'index': 1, 'result': 1000000}
{'index': 3, 'result': 1000000}
{'index': 2, 'result': 1000000}
{'index': 0, 'result': 1000000}
{'index': 5, 'result': 1000000}
{'index': 4, 'result': 1000000}
{'index': 8, 'result': 1000000}
{'index': 6, 'result': 1000000}
{'index': 9, 'result': 1000000}
{'index': 7, 'result': 1000000}

5/02/2020

get image rect list from pdf

extract all image rect list from pdf using pymupdf
look at the sample code

..

#pip install PyMuPDF
#document : https://pymupdf.readthedocs.io/en/latest/

#pip install opencv-python
#github : https://github.com/skvark/opencv-python

import fitz

img_bbox = []
doc1 =fitz.open('test.pdf')
page1 = doc1[0] #first page

d = page1.getText("dict")
blocks = d["blocks"]
imgblocks = [b for b in blocks if b["type"] == 1]
for v in imgblocks:
[x1, y1, x2, y2] = v['bbox']
#print(x1, y1, x2, y2)
img_bbox.append({'left':int(x1), 'top':int(y1), 'right':int(x2), 'bottom':int(y2)})
..

4/23/2020

remove all image from pdf file, python source code

input
output


PyMuPDF is needed
pip install PyMuPDF
..

def remove_img_on_pdf(idoc, page):
#image list
img_list = idoc.getPageImageList(page)
con_list = idoc[page]._getContents()

# xref 274 is the only /Contents object of the page (could be
for i in con_list:
c = idoc._getXrefStream(i) # read the stream source
#print(c)
if c != None:
for v in img_list:
arr = bytes(v[7], 'utf-8')
r = c.find(arr) # try find the image display command
if r != -1:
cnew = c.replace(arr, b"")
idoc._updateStream(i, cnew)
c = idoc._getXrefStream(i)
return idoc


doc=fitz.open('example.PDF')
rdoc = remove_img_on_pdf(doc, 0) #first page
rdoc.save('no_img_example.PDF')
..

reference : https://github.com/pymupdf/PyMuPDF/issues/338



4/16/2020

Python OpenCV Image to byte string for json transfer

code :
import cv2
import base64
import json
import numpy as np

######################################################
#read image
img = cv2.imread('./code_backup/test_img.jpg')
#cv2 to string
image_string = cv2.imencode('.jpg', img)[1]
image_string = base64.b64encode(image_string).decode()
#make string image dict
dict = {'img':image_string}
#save dict to json file
with open('./code_backup/cv2string.json', 'w') as fp:
json.dump(dict, fp, indent=5)
######################################################


######################################################
#read json
response = json.loads(open('./code_backup/cv2string.json', 'r').read())
#get image string
string = response['img']
#convert string to image
jpg_original = base64.b64decode(string)
jpg_as_np = np.frombuffer(jpg_original, dtype=np.uint8)
img = cv2.imdecode(jpg_as_np, flags=1)
#show image
cv2.imshow('show image', img)
cv2.waitKey(0)
######################################################
..

this is input image

this is summarised json file
{ "img": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/2wBDAQICAgICAgUDAwUKBwYHCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgr/wAARCAFoAeADASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwD2BP8Ag34/4JIE4P7I4/8AC617/wCTqsJ/wb4/8EiTx/wyR/5fWv8A/wAnV9nPH2x+FSwx14/t6vc+i+r4f+Q+Mk/4N7P+CQ+P+TRx/wC ........."
}

4/03/2020

Example python code for : Download s3 object as opencv image in memory and upload too

Just see the code
It's not difficult.

...

...
import cv2
import numpy as np
...

def lambda_handler(event, context):
# TODO implement
bucket_name = event['Records'][0]['s3']['bucket']['name']
s3_path = event['Records'][0]['s3']['object']['key']
#download object
obj = s3_client.get_object(Bucket=bucket_name, Key=s3_path)
#obj to cv2
nparr = np.frombuffer(obj['Body'].read(), np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
#simple image processing
reimg = cv2.resize(img, (100,100) )
#cv2 to string
image_string = cv2.imencode('.png', reimg)[1].tostring()
#upload
s3_client.put_object(Bucket='thum-prj-output', Key = s3_path, Body=image_string)
...

...