modified the regex

Dockerfile

@@ -1,18 +1,45 @@
-#FROM python:3.7.2
-FROM python:3.8.2
+# Use Python 3.8 base image
+FROM python:3.12
 
+# Install system dependencies (for spaCy and its dependencies)
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    python3-dev \
+    libatlas-base-dev \
+    gfortran \
+    curl \
+    git \
+    wget
 
-RUN pip install --upgrade pip
+# Upgrade pip, setuptools, and wheel (to ensure we're using the latest version)
+RUN pip install --upgrade pip setuptools wheel
+
+# Install spaCy (make sure the compatible version with Python 3.8 is installed)
+RUN pip3 install spacy==3.7.5  # Change this to a specific compatible version, e.g. 2.2.4
+
+# Download the necessary spaCy language model (en_core_web_sm)
+RUN python -m spacy download en_core_web_sm
+
+# Install required Python dependencies
 RUN pip3 install tqdm
 RUN pip3 install Cython
-RUN pip3 install xaif_eval==0.0.9
+RUN pip install xaif_eval==0.0.9
 RUN pip3 install markdown2
 RUN pip3 install flask-cors
 
 
 
+# Copy the application files into the container
 COPY . /app
+
+# Set the working directory to /app
 WORKDIR /app
+
+# Install additional Python dependencies from requirements.txt
 RUN pip install -r requirements.txt
-EXPOSE 5005
-CMD python ./main.py
+
+# Expose port 5008 for the Flask app
+EXPOSE 5008
+
+# Set the default command to run the application
+CMD ["python", "./main.py"]

main.py

@@ -47,4 +47,4 @@ def segmenter_defult():
 
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=int("5005"), debug=False)	  
+    app.run(host="0.0.0.0", port=int("5008"), debug=False)	  

src/segmenter.py

@@ -6,6 +6,10 @@
 import re
 from flask import json
 import logging
+import spacy
+
+# Load the pre-trained spaCy model for English
+nlp = spacy.load("en_core_web_sm")
 from src.data import Data
 from xaif_eval import xaif
 from src.templates import SegmenterOutput
@@ -19,10 +23,10 @@ def __init__(self,file_obj):
 		self.file_obj.save(self.f_name)
 		file = open(self.f_name,'r')
 
-	def get_segments(self, input_text): # regex
-		"""Segmenter that avoids splitting within decimal numbers and abbreviations."""
-		pattern = r'(?<!\d)\s*[.!?]\s+(?!\w\.)'
-		return re.split(pattern, input_text)
+	def get_segments(self, input_text):
+		"""Split input text into sentences using spaCy's sentence segmentation."""
+		doc = nlp(input_text)  # Process the input text using spaCy
+		return [sent.text.strip() for sent in doc.sents]  # Return sentences, stripping any extra spaces
 
 	def is_valid_json(self):
 		''' check if the file is valid json