Jean Yomin
New Coder
Python:
import os
import re
import difflib
import pytesseract
import fitz # PyMuPDF
from PIL import Image
from kivy.app import App
from kivy.uix.button import Button
from kivy.uix.boxlayout import BoxLayout
from kivy.uix.textinput import TextInput
from plyer import filechooser
import sqlite3
# Set the TESSDATA_PREFIX environment variable
[CODE=python]import os
import re
import difflib
import pytesseract
import fitz # PyMuPDF
from PIL import Image
from kivy.app import App
from kivy.uix.button import Button
from kivy.uix.boxlayout import BoxLayout
from kivy.uix.textinput import TextInput
from plyer import filechooser
import sqlite3
# Définir l'environnement variable TESSDATA_PREFIX
os.environ['TESSDATA_PREFIX'] = r'C:\\Program Files\\Tesseract-OCR\\tessdata'
# Spécifiez le chemin de l'exécutable Tesseract ici
pytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
def read_words_from_db(db_file):
# Créer une connexion à la base de données SQLite
conn = sqlite3.connect(db_file)
# Créer un curseur
c = conn.cursor()
# Exécuter une requête SQL pour sélectionner tous les mots de la table mots
c.execute('SELECT * FROM mots')
# Récupérer tous les résultats de la requête
words = c.fetchall()
# Fermer la connexion à la base de données
conn.close()
# Retourner la liste des mots
return [word[0] for word in words] # Chaque mot est un tuple, nous voulons juste le mot lui-même
# Votre liste de mots corrects
correct_words_list = read_words_from_db(r"C:\Users\bideg\Desktop\py_fichiers\ma_base_de_donnees.db")
def read_segments_from_db(db_file):
# Créer une connexion à la base de données SQLite
conn = sqlite3.connect(db_file)
# Créer un curseur
c = conn.cursor()
# Exécuter une requête SQL pour sélectionner tous les segments de la table segments
c.execute('SELECT * FROM segments')
# Récupérer tous les résultats de la requête
segments = c.fetchall()
# Fermer la connexion à la base de données
conn.close()
# Retourner le dictionnaire des segments
return {segment: replacement for segment, replacement in segments}
# Votre dictionnaire de remplacements de segments
segment_replacements = read_segments_from_db(r"C:\Users\bideg\Desktop\uncle bernard\ma_base_de_donnees_segments.db")
# Rest of your code...
def pdf_to_img(pdf_file, page_num=0):
doc = fitz.open(pdf_file) # open document
pix = doc.load_page(page_num).get_pixmap() # render page to an image
img_path = f"page_{page_num}.png"
pix.save(img_path)
return img_path
def ocr_core(file):
text = pytesseract.image_to_string(file, lang='fra')
return text
def replace_segments(text):
for segment, replacement in segment_replacements.items():
text = re.sub(segment, replacement, text)
return text
def correct_words(text):
words = text.split()
for i, word in enumerate(words):
# Trouver le mot le plus similaire dans la liste
match = difflib.get_close_matches(word, correct_words_list, n=1, cutoff=0.7)
if match:
# Remplacer le mot par le mot correspondant de la liste
words[i] = match[0]
return ' '.join(words)
class OCRApp(App):
def build(self):
self.title = 'MinyogogƁàsàaOcr'
self.icon = "C:\\Users\\bideg\\Desktop\\fin_de_ocrapp\\icone_app.jpeg"
layout = BoxLayout(orientation='vertical')
upload_button = Button(text='Upload Image',
background_color=[0, 1, 0, 1]) # Vert
upload_button.bind(on_press=self.upload_image)
extract_button = Button(text='Extract Text',
background_color=[1, 0, 0, 1]) # Rouge
extract_button.bind(on_press=self.extract_text)
upload_pdf_button = Button(text='Upload PDF',
background_color=[1, 1, 0, 1]) # Jaune
upload_pdf_button.bind(on_press=self.upload_pdf)
self.page_num_input = TextInput(hint_text='Enter page number')
layout.add_widget(upload_button)
layout.add_widget(extract_button)
layout.add_widget(upload_pdf_button)
layout.add_widget(self.page_num_input)
return layout
def upload_image(self, instance):
filepath = filechooser.open_file(title="Choisissez une image", filters=[("Images", "*.jpg;*.png;*.jpeg")])
if filepath:
self.image_path = filepath[0]
print(f"Image uploaded from {self.image_path}")
def extract_text(self, instance):
if hasattr(self, 'image_path'):
image = Image.open(self.image_path)
result = pytesseract.image_to_string(image, lang='fra')
result = replace_segments(result)
result = correct_words(result)
print(f"Text extracted: {result}")
else:
print("No image found to extract text.")
def upload_pdf(self, instance):
filepath = filechooser.open_file(title="Choose a file", filters=[("PDF", "*.pdf")])
if filepath:
self.pdf_path = filepath[0]
print(f"PDF uploaded from {self.pdf_path}")
page_num_str = self.page_num_input.text.strip()
page_num = int(page_num_str) if page_num_str.isdigit() else 0
img = pdf_to_img(self.pdf_path, page_num)
print(f"Text extracted from page {page_num+1}:")
with open(img, 'rb') as f:
result_img = Image.open(f)
result = ocr_core(result_img)
result = replace_segments(result)
result = correct_words(result)
print(result)
if __name__ == '__main__':
OCRApp().run()# Specify the path to the Tesseract executable here
pytesseract.pytesseract.tesseract_cmd = r'path_to_tesseract.exe'
# Function to read words from the database (anonymized)
def read_words_from_db(db_file):
# [Code to read words from the database]
# List of correct words (anonymized)
correct_words_list = read_words_from_db('path_to_my_database.db')
# Function to read segments from the database (anonymized)
def read_segments_from_db(db_file):
# [Code to read segments from the database]
# Dictionary of segment replacements (anonymized)
segment_replacements = read_segments_from_db('path_to_my_database_segments.db')
# Rest of your code...
# [Insert here the relevant anonymized functions and classes]
# Part 2: Function definitions for the OCR application (anonymized)
def upload_image(self, instance):
# [Code to upload an image from the user's system]
def extract_text(self, instance):
# [Code to extract text from the uploaded image using OCR]
def upload_pdf(self, instance):
# [Code to upload a PDF file from the user's system]
# [Insert the anonymized relevant code snippet here]
if name == 'main':
# [Code to run the OCR application]
[/CODE]
