Merge pull request #86 from Hazannovich/remove_old_processed_files

Remove old processed files

run_first.py

@@ -3,22 +3,39 @@
 from scripts.ResumeProcessor import ResumeProcessor
 from scripts.JobDescriptionProcessor import JobDescriptionProcessor
 import logging
-
+import os
 logging.basicConfig(filename='app.log', filemode='w',
                     level=logging.DEBUG,
                     format='%(name)s - %(levelname)s - %(message)s')
 
+PROCESSED_RESUMES_PATH = "Data/Processed/Resumes"
+PROCESSED_JOB_DESCRIPTIONS_PATH = "Data/Processed/JobDescription"
 
 def read_json(filename):
     with open(filename) as f:
         data = json.load(f)
     return data
 
+def remove_old_files(files_path):
+
+    for filename in os.listdir(files_path):
+        try:
+            file_path = os.path.join(files_path, filename)
+
+            if os.path.isfile(file_path):
+                os.remove(file_path)
+        except Exception as e:  
+            logging.error(f"Error deleting {file_path}:\n{e}")
+
+    logging.info("Deleted old files from "+files_path)
+
 
 logging.info('Started to read from Data/Resumes')
 try:
     # Check if there are resumes present or not.
     # If present then parse it.
+    remove_old_files(PROCESSED_RESUMES_PATH)
+
     file_names = get_filenames_from_dir("Data/Resumes")
     logging.info('Reading from Data/Resumes is now complete.')
 except:
@@ -40,6 +57,8 @@ def read_json(filename):
 try:
     # Check if there are resumes present or not.
     # If present then parse it.
+    remove_old_files(PROCESSED_JOB_DESCRIPTIONS_PATH)
+
     file_names = get_filenames_from_dir("Data/JobDescription")
     logging.info('Reading from Data/JobDescription is now complete.')
 except:

streamlit_app.py

@@ -140,9 +140,14 @@ def tokenize_string(input_string):
 
 resume_names = get_filenames_from_dir("Data/Processed/Resumes")
 
-st.write("There are", len(resume_names),
+output = 0
+
+if len(resume_names) > 1:
+    st.write("There are", len(resume_names),
          " resumes present. Please select one from the menu below:")
-output = st.slider('Select Resume Number', 0, len(resume_names)-1, 2)
+    output = st.slider('Select Resume Number', 0, len(resume_names)-1, 0)
+else:
+    st.write("There is 1 resume present")
 
 avs.add_vertical_space(5)
 
@@ -199,10 +204,14 @@ def tokenize_string(input_string):
 
 job_descriptions = get_filenames_from_dir("Data/Processed/JobDescription")
 
-st.write("There are", len(job_descriptions),
+output = 0
+if len(job_descriptions) > 1:
+    st.write("There are", len(job_descriptions),
          " resumes present. Please select one from the menu below:")
-output = st.slider('Select Job Description Number',
-                   0, len(job_descriptions)-1, 2)
+    output = st.slider('Select Job Description Number',
+                    0, len(job_descriptions)-1, 0)
+else:
+    st.write("There is 1 job description present")
 
 avs.add_vertical_space(5)