WebashalarForML's picture
Update utility/utils.py
4e653b1 verified
raw
history blame
18.8 kB
# libraries
import os
from huggingface_hub import InferenceClient
from dotenv import load_dotenv
import json
import re
#import easyocr
from PIL import Image, ImageEnhance, ImageDraw
import cv2
import numpy as np
from paddleocr import PaddleOCR
import logging
# Configure logging
logging.basicConfig(
level=logging.INFO,
handlers=[
logging.StreamHandler() # Remove FileHandler and log only to the console
]
)
# Set the PaddleOCR home directory to a writable location
os.environ['PADDLEOCR_HOME'] = '/tmp/.paddleocr'
RESULT_FOLDER = 'static/results/'
if not os.path.exists('/tmp/.paddleocr'):
os.makedirs(RESULT_FOLDER, exist_ok=True)
# Check if PaddleOCR home directory is writable
if not os.path.exists('/tmp/.paddleocr'):
os.makedirs('/tmp/.paddleocr', exist_ok=True)
logging.info("Created PaddleOCR home directory.")
else:
logging.info("PaddleOCR home directory exists.")
# Load environment variables from .env file
load_dotenv()
# Authenticate with Hugging Face
HFT = os.getenv('HF_TOKEN')
# Initialize the InferenceClient
client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3", token=HFT)
# Specify a custom model storage directory (ensure this path is writable)
#model_storage_directory = '/app/models'
# Create the reader object and set the model storage directory
#reader = easyocr.Reader(['en'], model_storage_directory=model_storage_directory)
def draw_boxes(image, bounds, color='red', width=2):
draw = ImageDraw.Draw(image)
for bound in bounds:
p0, p1, p2, p3 = bound[0]
draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
return image
# Load image using OpenCV
def load_image(image_path):
image = cv2.imread(image_path)
if image is None:
raise ValueError(f"Could not load image from {image_path}. It may be corrupted or the path is incorrect.")
return image
# Function for upscaling image using OpenCV's INTER_CUBIC
def upscale_image(image, scale=2):
height, width = image.shape[:2]
upscaled_image = cv2.resize(image, (width * scale, height * scale), interpolation=cv2.INTER_CUBIC)
return upscaled_image
# Function to denoise the image (reduce noise)
def reduce_noise(image):
return cv2.fastNlMeansDenoisingColored(image, None, 10, 10, 7, 21)
# Function to sharpen the image
def sharpen_image(image):
kernel = np.array([[0, -1, 0],
[-1, 5, -1],
[0, -1, 0]])
sharpened_image = cv2.filter2D(image, -1, kernel)
return sharpened_image
# Function to increase contrast and enhance details without changing color
def enhance_image(image):
pil_img = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
enhancer = ImageEnhance.Contrast(pil_img)
enhanced_image = enhancer.enhance(1.5)
enhanced_image_bgr = cv2.cvtColor(np.array(enhanced_image), cv2.COLOR_RGB2BGR)
return enhanced_image_bgr
# Complete function to process image
def process_image(image_path, scale=2):
# Load the image
image = load_image(image_path)
# Upscale the image
upscaled_image = upscale_image(image, scale)
# Reduce noise
denoised_image = reduce_noise(upscaled_image)
# Sharpen the image
sharpened_image = sharpen_image(denoised_image)
# Enhance the image contrast and details without changing color
final_image = enhance_image(sharpened_image)
return final_image
def ocr_with_paddle(img):
finaltext = ''
#model_dir = os.getenv('PADDLEOCR_MODEL_DIR', '/tmp/.paddleocr')
#ocr = PaddleOCR(lang='en', use_angle_cls=True, det_model_dir=model_dir)
#ocr = PaddleOCR(lang='en', use_angle_cls=True, det_model_dir=os.environ['PADDLEOCR_HOME'])
logging.info(f"PADDLEOCR_HOME: {os.environ['PADDLEOCR_HOME']}")
ocr = PaddleOCR(
lang='en',
use_angle_cls=True,
det_model_dir=os.path.join(os.environ['PADDLEOCR_HOME'], 'whl/det'),
rec_model_dir=os.path.join(os.environ['PADDLEOCR_HOME'], 'whl/rec/en/en_PP-OCRv4_rec_infer'),
cls_model_dir=os.path.join(os.environ['PADDLEOCR_HOME'], 'whl/cls/ch_ppocr_mobile_v2.0_cls_infer')
)
result = ocr.ocr(img)
for i in range(len(result[0])):
text = result[0][i][1][0]
finaltext += ' ' + text
return finaltext
def extract_text_from_images(image_paths):
all_extracted_texts = {}
all_extracted_imgs = {}
for image_path in image_paths:
try:
# Enhance the image before OCR
enhanced_image = process_image(image_path, scale=2)
# Draw boxes on the processed image (optional, requires bounds)
img_result = Image.fromarray(enhanced_image)
result_image_path = os.path.join(RESULT_FOLDER, f'result_{os.path.basename(image_path)}')
img_result.save(result_image_path) # Save the processed image
# Perform OCR on the enhanced image
result = ocr_with_paddle(enhanced_image)
all_extracted_texts[image_path] = result
all_extracted_imgs[image_path] = result_image_path
except ValueError as ve:
print(f"Error processing image {image_path}: {ve}")
continue # Continue to the next image if there's an error
# Convert to JSON-compatible structure
all_extracted_imgs_json = {str(k): str(v) for k, v in all_extracted_imgs.items()}
return all_extracted_texts, all_extracted_imgs_json
# Function to call the Gemma model and process the output as Json
def Data_Extractor(data, client=client):
text = f'''Act as a Text extractor for the following text given in text: {data}
extract text in the following output JSON string:
{{
"Name": ["Identify and Extract All the person's name from the text."],
"Designation": ["Extract All the designation or job title mentioned in the text."],
"Company": ["Extract All the company or organization name if mentioned."],
"Contact": ["Extract All phone number, including country codes if present."],
"Address": ["Extract All the full postal address or location mentioned in the text."],
"Email": ["Identify and Extract All valid email addresses mentioned in the text else 'Not found'."],
"Link": ["Identify and Extract any website URLs or social media links present in the text."]
}}
Output:
'''
# Call the API for inference
response = client.text_generation(text, max_new_tokens=600)#, temperature=0.4, top_k=50, top_p=0.9, repetition_penalty=1.2)
print("parse in text ---:",response)
# Convert the response text to JSON
try:
json_data = json.loads(response)
return json_data
except json.JSONDecodeError as e:
return {"error": f"Error decoding JSON: {e}"}
# For have text compatible to the llm
def json_to_llm_str(textJson):
str=''
for file,item in textJson.items():
str+=item + ' '
return str
# Define the RE for extracting the contact details like number, mail , portfolio, website etc
def extract_contact_details(text):
# Regex patterns
# Phone numbers with at least 5 digits in any segment
combined_phone_regex = re.compile(r'''
(?:
#(?:(?:\+91[-.\s]?)?\d{5}[-.\s]?\d{5})|(?:\+?\d{1,3})?[-.\s()]?\d{5,}[-.\s()]?\d{5,}[-.\s()]?\d{1,9} | /^[\.-)( ]*([0-9]{3})[\.-)( ]*([0-9]{3})[\.-)( ]*([0-9]{4})$/ |
\+1\s\(\d{3}\)\s\d{3}-\d{4} | # USA/Canada Intl +1 (XXX) XXX-XXXX
\(\d{3}\)\s\d{3}-\d{4} | # USA/Canada STD (XXX) XXX-XXXX
\(\d{3}\)\s\d{3}\s\d{4} | # USA/Canada (XXX) XXX XXXX
\(\d{3}\)\s\d{3}\s\d{3} | # USA/Canada (XXX) XXX XXX
\+1\d{10} | # +1 XXXXXXXXXX
\d{10} | # XXXXXXXXXX
\+44\s\d{4}\s\d{6} | # UK Intl +44 XXXX XXXXXX
\+44\s\d{3}\s\d{3}\s\d{4} | # UK Intl +44 XXX XXX XXXX
0\d{4}\s\d{6} | # UK STD 0XXXX XXXXXX
0\d{3}\s\d{3}\s\d{4} | # UK STD 0XXX XXX XXXX
\+44\d{10} | # +44 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+61\s\d\s\d{4}\s\d{4} | # Australia Intl +61 X XXXX XXXX
0\d\s\d{4}\s\d{4} | # Australia STD 0X XXXX XXXX
\+61\d{9} | # +61 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+91\s\d{5}-\d{5} | # India Intl +91 XXXXX-XXXXX
\+91\s\d{4}-\d{6} | # India Intl +91 XXXX-XXXXXX
\+91\s\d{10} | # India Intl +91 XXXXXXXXXX
0\d{2}-\d{7} | # India STD 0XX-XXXXXXX
\+91\d{10} | # +91 XXXXXXXXXX
\+49\s\d{4}\s\d{8} | # Germany Intl +49 XXXX XXXXXXXX
\+49\s\d{3}\s\d{7} | # Germany Intl +49 XXX XXXXXXX
0\d{3}\s\d{8} | # Germany STD 0XXX XXXXXXXX
\+49\d{12} | # +49 XXXXXXXXXXXX
\+49\d{10} | # +49 XXXXXXXXXX
0\d{11} | # 0XXXXXXXXXXX
\+86\s\d{3}\s\d{4}\s\d{4} | # China Intl +86 XXX XXXX XXXX
0\d{3}\s\d{4}\s\d{4} | # China STD 0XXX XXXX XXXX
\+86\d{11} | # +86 XXXXXXXXXXX
\+81\s\d\s\d{4}\s\d{4} | # Japan Intl +81 X XXXX XXXX
\+81\s\d{2}\s\d{4}\s\d{4} | # Japan Intl +81 XX XXXX XXXX
0\d\s\d{4}\s\d{4} | # Japan STD 0X XXXX XXXX
\+81\d{10} | # +81 XXXXXXXXXX
\+81\d{9} | # +81 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+55\s\d{2}\s\d{5}-\d{4} | # Brazil Intl +55 XX XXXXX-XXXX
\+55\s\d{2}\s\d{4}-\d{4} | # Brazil Intl +55 XX XXXX-XXXX
0\d{2}\s\d{4}\s\d{4} | # Brazil STD 0XX XXXX XXXX
\+55\d{11} | # +55 XXXXXXXXXXX
\+55\d{10} | # +55 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+33\s\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} | # France Intl +33 X XX XX XX XX
0\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} | # France STD 0X XX XX XX XX
\+33\d{9} | # +33 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+7\s\d{3}\s\d{3}-\d{2}-\d{2} | # Russia Intl +7 XXX XXX-XX-XX
8\s\d{3}\s\d{3}-\d{2}-\d{2} | # Russia STD 8 XXX XXX-XX-XX
\+7\d{10} | # +7 XXXXXXXXXX
8\d{10} | # 8 XXXXXXXXXX
\+27\s\d{2}\s\d{3}\s\d{4} | # South Africa Intl +27 XX XXX XXXX
0\d{2}\s\d{3}\s\d{4} | # South Africa STD 0XX XXX XXXX
\+27\d{9} | # +27 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+52\s\d{3}\s\d{3}\s\d{4} | # Mexico Intl +52 XXX XXX XXXX
\+52\s\d{2}\s\d{4}\s\d{4} | # Mexico Intl +52 XX XXXX XXXX
01\s\d{3}\s\d{4} | # Mexico STD 01 XXX XXXX
\+52\d{10} | # +52 XXXXXXXXXX
01\d{7} | # 01 XXXXXXX
\+234\s\d{3}\s\d{3}\s\d{4} | # Nigeria Intl +234 XXX XXX XXXX
0\d{3}\s\d{3}\s\d{4} | # Nigeria STD 0XXX XXX XXXX
\+234\d{10} | # +234 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+971\s\d\s\d{3}\s\d{4} | # UAE Intl +971 X XXX XXXX
0\d\s\d{3}\s\d{4} | # UAE STD 0X XXX XXXX
\+971\d{8} | # +971 XXXXXXXX
0\d{8} | # 0XXXXXXXX
\+54\s9\s\d{3}\s\d{3}\s\d{4} | # Argentina Intl +54 9 XXX XXX XXXX
\+54\s\d{1}\s\d{4}\s\d{4} | # Argentina Intl +54 X XXXX XXXX
0\d{3}\s\d{4} | # Argentina STD 0XXX XXXX
\+54\d{10} | # +54 9 XXXXXXXXXX
\+54\d{9} | # +54 XXXXXXXXX
0\d{7} | # 0XXXXXXX
\+966\s\d\s\d{3}\s\d{4} | # Saudi Intl +966 X XXX XXXX
0\d\s\d{3}\s\d{4} | # Saudi STD 0X XXX XXXX
\+966\d{8} | # +966 XXXXXXXX
0\d{8} | # 0XXXXXXXX
\+1\d{10} | # +1 XXXXXXXXXX
\+1\s\d{3}\s\d{3}\s\d{4} | # +1 XXX XXX XXXX
\d{5}\s\d{5} | # XXXXX XXXXX
\d{10} | # XXXXXXXXXX
\+44\d{10} | # +44 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+61\d{9} | # +61 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+91\d{10} | # +91 XXXXXXXXXX
\+49\d{12} | # +49 XXXXXXXXXXXX
\+49\d{10} | # +49 XXXXXXXXXX
0\d{11} | # 0XXXXXXXXXXX
\+86\d{11} | # +86 XXXXXXXXXXX
\+81\d{10} | # +81 XXXXXXXXXX
\+81\d{9} | # +81 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+55\d{11} | # +55 XXXXXXXXXXX
\+55\d{10} | # +55 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+33\d{9} | # +33 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX
\+7\d{10} | # +7 XXXXXXXXXX
8\d{10} | # 8 XXXXXXXXXX
\+27\d{9} | # +27 XXXXXXXXX
0\d{9} | # 0XXXXXXXXX (South Africa STD)
\+52\d{10} | # +52 XXXXXXXXXX
01\d{7} | # 01 XXXXXXX
\+234\d{10} | # +234 XXXXXXXXXX
0\d{10} | # 0XXXXXXXXXX
\+971\d{8} | # +971 XXXXXXXX
0\d{8} | # 0XXXXXXXX
\+54\s9\s\d{10} | # +54 9 XXXXXXXXXX
\+54\d{9} | # +54 XXXXXXXXX
0\d{7} | # 0XXXXXXX
\+966\d{8} | # +966 XXXXXXXX
0\d{8} # 0XXXXXXXX
\+\d{3}-\d{3}-\d{4}
)
''',re.VERBOSE)
# Email regex
email_regex = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b')
# Profile links regex, updated to avoid conflicts with email domains
#link_regex = re.compile(r'\b(?:https?://)?(?:www\.)?(?:linkedin\.com|github\.com|indeed\.com|[A-Za-z0-9-]+\.[A-Za-z]{2,})[\w./?-]*\b')
#link_regex = re.compile(r'\b(?:https?://)?(?:www\.)?[a-zA-Z0-9-]+\.(?:[a-zA-Z]{2,})(?:\.[a-zA-Z]{2,})?(?:\.[a-zA-Z]{2,})?(?:[/\w.-]*)*[\w/?&=-]*\b')
link_regex = re.compile(r'\b(?:https?:\/\/)?(?:www\.)[a-zA-Z0-9-]+\.(?:com|co\.in|co|io|org|net|edu|gov|mil|int|uk|us|in|de|au|app|tech|xyz|info|biz|fr|dev)\b')
# Find all matches in the text
phone_numbers = [num for num in combined_phone_regex.findall(text) if len(num) >= 5]
print("phone_numbers--->",phone_numbers)
emails = email_regex.findall(text)
links_RE = [link for link in link_regex.findall(text) if len(link)>=11]
# Remove profile links that might conflict with emails
links_RE = [link for link in links_RE if not any(email in link for email in emails)]
return {
"phone_numbers": phone_numbers,
"emails": emails,
"links_RE": links_RE
}
# preprocessing the data
def process_extracted_text(extracted_text):
# Load JSON data
data = json.dumps(extracted_text, indent=4)
data = json.loads(data)
# Create a single dictionary to hold combined results
combined_results = {
"phone_numbers": [],
"emails": [],
"links_RE": []
}
# Process each text entry
for filename, text in data.items():
contact_details = extract_contact_details(text)
# Extend combined results with the details from this file
combined_results["phone_numbers"].extend(contact_details["phone_numbers"])
combined_results["emails"].extend(contact_details["emails"])
combined_results["links_RE"].extend(contact_details["links_RE"])
# Convert the combined results to JSON
#combined_results_json = json.dumps(combined_results, indent=4)
combined_results_json = combined_results
# Print the final JSON results
print("Combined contact details in JSON format:")
print(combined_results_json)
return combined_results_json
# Process the model output for parsed result
def process_resume_data(LLMdata,cont_data,extracted_text):
# Initialize the processed data dictionary
processed_data = {
"name": [LLMdata.get('Name', 'Not found')],
"contact_number": [LLMdata.get('Contact', 'Not found')],
"Designation":[LLMdata.get('Designation', 'Not found')],
"email": [LLMdata.get("Email", 'Not found')],
"Location": [LLMdata.get('Address', 'Not found')],
"Link": [LLMdata.get('Link', 'Not found')],
"Company":[LLMdata.get('Company', 'Not found')],
"extracted_text": extracted_text
}
processed_data['email'].extend(cont_data.get("emails", []))
processed_data['contact_number'].extend(cont_data.get("phone_numbers", []))
processed_data['Link'].extend(cont_data.get("links_RE", []))
return processed_data