added a list of explicit organizations

Author: lakshmanaram

cvscan/__init__.py

@@ -59,7 +59,7 @@ def show(self):
             "phone_numbers" : self.phone_numbers,
             "emails" : self.emails,
             "urls" : self.URLs,
-            "skills" : self.skills,
+            # "skills" : self.skills,
             "jobs" : self.job_positions,
             "job category" : self.category,
             "employers" : self.employers,

cvscan/data/job_positions/scraping_jobs.py

@@ -20,7 +20,7 @@
   job_categories = ws.__getitem__("D")
   for title,category in zip(job_titles[1:],job_categories[1:]):
     if title.value:
-      jobs[title.value] = category.value
+      jobs[title.value.lower()] = category.value.lower()
 
   with open('positions','wb') as fp:
     pickle.dump(jobs,fp)

cvscan/data/organizations/explicit_organizations

@@ -0,0 +1,6 @@
+(lp0
+S'Skcript'
+p1
+aS'Hasura'
+p2
+a.

cvscan/language_parser.py

@@ -143,9 +143,8 @@ def fetch_employers_util(resume_text, job_positions, organizations, priority):
           lines_back -= 1
         end += 1
       line = temp_resume[start:end].lower()
-
       for org in organizations:
-        if org.lower() in line:
+        if org.lower() in line and org.lower() not in job_positions:
           if 'present' in line:
             if org.lower().capitalize() in employers:
               employers.remove(org.lower().capitalize())
@@ -185,7 +184,18 @@ def fetch_employers(resume_text, job_positions):
     organizations,False)
   current_employers.extend(cur_emps)
   employers.extend(emps)
+
+  with open(dirpath.PKGPATH + 
+    '/data/organizations/explicit_organizations') as fp:
+    organizations = pickle.load(fp)
 
+  cur_emps,emps = fetch_employers_util(resume_text, job_positions,
+    organizations,True)
+  current_employers.extend([emp for emp in cur_emps 
+    if emp not in current_employers])
+  employers.extend([emp for emp in emps 
+    if emp not in employers])
+
   return current_employers,employers