Add string parsing

pyresparser/resume_parser.py

@@ -36,10 +36,15 @@ def __init__(
             'total_experience': None,
         }
         self.__resume = resume
-        if not isinstance(self.__resume, io.BytesIO):
-            ext = os.path.splitext(self.__resume)[1].split('.')[1]
+
+        if isinstance(self.__resume, str):
+            ext = ''
         else:
-            ext = self.__resume.name.split('.')[1]
+            if not isinstance(self.__resume, io.BytesIO):
+                ext = os.path.splitext(self.__resume)[1].split('.')[1]
+            else:
+                ext = self.__resume.name.split('.')[1]
+
         self.__text_raw = utils.extract_text(self.__resume, '.' + ext)
         self.__text = ' '.join(self.__text_raw.split())
         self.__nlp = nlp(self.__text)

pyresparser/utils.py

@@ -153,6 +153,10 @@ def extract_text_from_doc(doc_path):
         return ' '
 
 
+def extract_text_from_string(string):
+    ''' Helper function to return input string for testing '''
+    return string
+
 def extract_text(file_path, extension):
     '''
     Wrapper function to detect the file extension and call text
@@ -162,13 +166,17 @@ def extract_text(file_path, extension):
     :param extension: extension of file `file_name`
     '''
     text = ''
+
     if extension == '.pdf':
         for page in extract_text_from_pdf(file_path):
             text += ' ' + page
     elif extension == '.docx':
         text = extract_text_from_docx(file_path)
     elif extension == '.doc':
         text = extract_text_from_doc(file_path)
+    else:
+        text = extract_text_from_string(file_path)
+
     return text
 
 

test_name.py → test/test_pyresparser.py

@@ -6,6 +6,7 @@
 import urllib
 from urllib.request import Request, urlopen
 from pyresparser import ResumeParser
+from pathlib import Path
 
 def get_remote_data():
     try:
@@ -21,9 +22,9 @@ def get_remote_data():
         return 'File not found. Please provide correct URL for resume file.'
 
 def get_local_data():
-    data = ResumeParser('OmkarResume.pdf').get_extracted_data()
+    data = ResumeParser(str(Path(__file__).parent.resolve() / 'fixtures/OmkarResume.pdf')).get_extracted_data()
     return data
-        
+
 def test_remote_name():
     data = get_remote_data()
     assert 'Omkar Pathak' == data[0]['name']
@@ -32,10 +33,25 @@ def test_remote_phone_number():
     data = get_remote_data()
     assert '8087996634' == data[0]['mobile_number']
 
-def test_local_name():
+def test_local_skills():
     data = get_local_data()
-    assert 'Omkar Pathak' == data['name']
+    assert 'C++' in data['skills']
 
 def test_local_phone_number():
     data = get_local_data()
     assert '8087996634' == data['mobile_number']
+
+def test_extract_string():
+
+    string = (f"Joe Bloggs email: [email protected] \n"
+              f"Professional Experience \n"
+              f"Microsoft \n Jan 2017 - Mar 2020 \n"
+              f"Analyst \n"
+              f"Created monthly Excel and Powerpoint reports highlighting KPIs in a clear and simple format. \n"
+              f"Used predictive modelling to detect patterns in customer behaviour using Python. \n"
+              f"Education \n"
+              f"University of Oxford \n"
+              f"BSc in Computer Science \n")
+
+    data = ResumeParser(string).get_extracted_data()
+    assert 'Excel' in data['skills']