Updating the library to Python 3

README.md

@@ -12,6 +12,20 @@ Eg: ~/cvpath/data/sample/a.pdf is parsed by
 ```bash
 cvscan parse --name data/sample/a
 ```
+Output of parsing the sample inside data/sample is also provided in the `output.json` file.
+
+## Installing NLTK related packages.
+You can either download all the NLTK packages are choose only the ones listed below to use the cvscan library.
+
+```
+import nltk
+nltk.download('punkt')
+nltk.download('averaged_perceptron_tagger')
+nltk.download('universal_tagset')
+nltk.download('maxent_ne_chunker')
+nltk.download('words')
+nltk.download('stopwords')
+```
 
 Data Manipulations
 ===============

cvscan/__init__.py

@@ -4,19 +4,18 @@
 Main program
 
 """
+import os
 
-import converter
-import annotations_parser
-import details_parser as dp
-import language_parser as lp
-import json
-import dirpath
-import configurations
+from cvscan import converter
+from cvscan import annotations_parser
+from cvscan import details_parser as dp
+from cvscan import language_parser as lp
+from cvscan import dirpath
+from cvscan import configurations
 
 class Cvscan():
     def __init__(self, name, path = dirpath.RESUMEPATH):
-        self.path = path + '/' + name + '.pdf'
-        self.path = name + '.pdf'
+        self.path = os.path.join(path, name)
 
         if self.exists():
             self.extract()
@@ -56,7 +55,7 @@ def parse(self):
 
     # TODO: Add more fetch here
     def show(self):
-        return json.dumps({
+        return {
             "name" : self.name,
             "experience" : self.experience,
             "address" : self.address,
@@ -71,4 +70,4 @@ def show(self):
             "qualifications" : self.qualifications,
             "qualifications_info" : self.degree_info,
             "extra_info" : self.extra_info
-        })
+        }

cvscan/annotations_parser.py

@@ -39,10 +39,10 @@ def fetch_pdf_urls(file_name):
           if type(link_object) is not dict:
             link_object = link_object.resolve()
           if link_object['A']['URI']:
-            links.append(link_object['A']['URI'])
+            links.append(link_object['A']['URI'].decode())
     file_pointer.close()
     return links
 
-  except Exception, exception_instance:
+  except Exception as exception_instance:
     logging.error('Error while fetching URLs : '+str(exception_instance))
-    return ''
+    return []

cvscan/cli/cli.py

@@ -80,7 +80,7 @@ def add(org,skill,job,qual,extra):
         _job = _job.split(':')
         jobs[_job[0]] = _job[1]
       except Exception:
-        print "Something wnet wrong: " + Exception
+        print("Something wnet wrong: " + Exception)
     do.add_jobs(jobs)
   if qual:
     do.add_qualifications(qual.split(','))
@@ -128,4 +128,4 @@ def remove(org,skill,job,qual,extra):
   if qual:
     do.remove_qualifications(qual.split(','))
   if extra:
-    do.remove_extra(extra.split(','))
+    do.remove_extra(extra.split(','))

cvscan/converter.py

@@ -7,14 +7,14 @@
 import re
 import logging
 
-import configurations as regex
+from cvscan import configurations as regex
 
 # for converting pdfs to text
 from pdfminer.converter import TextConverter
 from pdfminer.layout import LAParams
 from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
 from pdfminer.pdfpage import PDFPage
-from cStringIO import StringIO
+from io import StringIO
 
 logging.basicConfig(level=logging.DEBUG)
 
@@ -33,10 +33,8 @@ def pdf_to_txt(file_name):
     # Setting up pdf reader
     pdf_resource_manager = PDFResourceManager()
     return_string = StringIO()
-    codec = 'utf-8'
     laparams = LAParams()
-    device = TextConverter(pdf_resource_manager, return_string, codec=codec, \
-      laparams=laparams)
+    device = TextConverter(pdf_resource_manager, return_string, laparams=laparams)
     interpreter = PDFPageInterpreter(pdf_resource_manager, device)
 
     for page in PDFPage.get_pages(file_pointer, set(), maxpages=0, password="",
@@ -55,8 +53,8 @@ def pdf_to_txt(file_name):
     pdf_txt = pdf_txt.replace("\r", "\n")
     pdf_txt = re.sub(regex.bullet, " ", pdf_txt)
 
-    return pdf_txt.decode('ascii', errors='ignore')
+    return pdf_txt
 
-  except Exception, exception_instance:
+  except Exception as exception_instance:
     logging.error('Error converting pdf to txt: '+str(exception_instance))
     return ''

cvscan/data/extra/extra

@@ -1,2 +0,0 @@
-(lp0
-.

cvscan/data/sample/output.json

@@ -0,0 +1,224 @@
+{
+    "address":{
+        "district":"Chennai",
+        "pincode":"",
+        "state":"Tamil Nadu"
+    },
+    "current_employers":[
+        "Delta force",
+        "Software developer application developer",
+        "National institute"
+    ],
+    "emails":[
+        "[email protected]"
+    ],
+    "employers":[
+        "Nit",
+        "Algorithmic",
+        "Analysis",
+        "Mac",
+        "Computer networks Exchange student",
+        "Institute of mathematical sciences",
+        "Steganography multimedia systems",
+        "project Delta force",
+        "National institute"
+    ],
+    "experience":5,
+    "extra_info":[
+
+    ],
+    "job category":"Other",
+    "jobs":[
+        "Programmer",
+        "Application developer",
+        "Independent",
+        "Student",
+        "Research",
+        "Software developer",
+        "Member"
+    ],
+    "name":"Lakshmanaram",
+    "phone_numbers":"+919043804100",
+    "qualifications":[
+        "B.Tech"
+    ],
+    "qualifications_info":[
+        "IN COMPUTER SCIENCE AND"
+    ],
+    "skills":[
+        "C",
+        "Databases",
+        "Engineering",
+        "Java",
+        "Linux",
+        "Management",
+        "Operating Systems",
+        "Research",
+        "SQL",
+        "Unix",
+        "ACM",
+        "API",
+        "Active",
+        "Activities",
+        "Adaptive",
+        "Advanced",
+        "Algorithms",
+        "Analysis",
+        "Android",
+        "Android Development",
+        "Android Studio",
+        "Apache",
+        "Apache Spark",
+        "App",
+        "Application",
+        "Applications",
+        "Architecture",
+        "Article",
+        "Audience",
+        "Award",
+        "Awards",
+        "Bash",
+        "Bronze",
+        "C",
+        "COM",
+        "Calls",
+        "Challenge",
+        "Chennai",
+        "Circuit",
+        "Circuit Design",
+        "Club",
+        "Code",
+        "Codes",
+        "Competitive",
+        "Computer Science",
+        "Contests",
+        "Core",
+        "Coursework",
+        "Cycle",
+        "Data",
+        "Data Structures",
+        "Database",
+        "Databases",
+        "Delta",
+        "Design",
+        "Design Analysis",
+        "Designing",
+        "Developer",
+        "Easy",
+        "Education",
+        "Engineering",
+        "Exp",
+        "Expert",
+        "Featured",
+        "Festivals",
+        "Git",
+        "Github",
+        "Gmail",
+        "Gold",
+        "Google",
+        "Graph Theory",
+        "Hobbies",
+        "Hosted",
+        "IO",
+        "Independent",
+        "India",
+        "Input",
+        "Institute",
+        "Integrations",
+        "Java",
+        "Languages",
+        "Learning",
+        "Lines",
+        "LinkedIn",
+        "Links",
+        "Linux",
+        "Logic",
+        "Mac",
+        "Machine Learning",
+        "Management",
+        "Medals",
+        "Mobile",
+        "Mobile Applications",
+        "Multimedia",
+        "N",
+        "National",
+        "ODD",
+        "ONE",
+        "Octave",
+        "Open Source",
+        "Operating",
+        "Operating Systems",
+        "Part",
+        "Participants",
+        "Play",
+        "Premier",
+        "Problems",
+        "Professors",
+        "Programming",
+        "Programming Languages",
+        "Puzzles",
+        "Python",
+        "PH",
+        "QR",
+        "Rating",
+        "Reduce",
+        "Registration",
+        "Related",
+        "Related Activities",
+        "Research",
+        "Review",
+        "Robotics",
+        "SQL",
+        "STARS",
+        "Science",
+        "Session",
+        "Set",
+        "Shell",
+        "Silver",
+        "Skills",
+        "Software",
+        "Source",
+        "Spark",
+        "Special",
+        "Special Interest",
+        "Steganography",
+        "Store",
+        "Structures",
+        "Studio",
+        "Sudoku",
+        "Systems",
+        "Talk",
+        "Teams",
+        "Techno",
+        "Technology",
+        "Template",
+        "Terminal",
+        "Theory",
+        "Track Changes",
+        "Trending",
+        "Tutorials",
+        "Ubuntu",
+        "Undergraduate",
+        "Unix",
+        "Vocabulary",
+        "Weekly",
+        "Word",
+        "World"
+    ],
+    "urls":[
+        "mailto:[email protected]",
+        "https://github.com/lakshmanaram",
+        "https://in.linkedin.com/in/lakshmanaram",
+        "https://www.hackerrank.com/lakshmanaram",
+        "http://codeforces.com/profile/henry_colebrooke",
+        "https://www.codechef.com/users/suicune",
+        "https://github.com/lakshmanaram/incor",
+        "http://incor.readthedocs.io/en/latest/",
+        "https://github.com/lakshmanaram/Steganography",
+        "http://asp.eurasipjournals.springeropen.com/articles/10.1155/2010/876946",
+        "https://github.com/lakshmanaram/Pragyan-app",
+        "https://play.google.com/store/apps/details?id=org.pragyan.pragyantshirtapp&hl=en",
+        "https://github.com/badarsh2/Sudocabulary",
+        "http://www.omgubuntu.co.uk/2016/08/learn-new-word-terminal"
+    ]
+}