update according to suggestions

Signed-off-by: Venu Vardhan Reddy Tekula <[email protected]>

grimoire_elk/enriched/gitlabcomments.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2015-2019 Bitergia
+# Copyright (C) 2015-2020 Bitergia
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -19,6 +19,7 @@
 #   Venu Vardhan Reddy Tekula <[email protected]>
 #
 
+
 import logging
 import re
 import collections
@@ -88,12 +89,7 @@ def __init__(self, db_sortinghat=None, db_projects_map=None, json_projects_map=N
         super().__init__(db_sortinghat, db_projects_map, json_projects_map,
                          db_user, db_password, db_host)
 
-        self.users = {}  # cache users
-
         self.studies = []
-        # self.studies.append(self.enrich_geolocation)
-        # self.studies.append(self.enrich_feelings)
-        # self.studies.append(self.enrich_extra_data)
 
     def set_elastic(self, elastic):
         self.elastic = elastic
@@ -147,6 +143,8 @@ def get_sh_identity(self, item, identity_field=None):
         user = item  # by default a specific user dict is expected
         if isinstance(item, dict) and 'data' in item:
             user = item['data'][identity_field]
+        elif identity_field:
+            user = item[identity_field]
 
         if not user:
             return identity
@@ -177,13 +175,13 @@ def get_time_to_first_attention(self, item):
         return None
 
     def get_time_to_merge_request_response(self, item):
-        """Get the first date at which a review was made on the PR by someone
-        other than the user who created the PR
+        """Get the first date at which a review was made on the MR by someone
+        other than the user who created the MR
         """
         review_dates = []
 
         for comment in item['notes_data']:
-            # skip comments of the pull request creator
+            # skip comments of the merge request creator
             if item['author']['username'] == comment['author']['username']:
                 continue
 
@@ -196,12 +194,13 @@ def get_time_to_merge_request_response(self, item):
 
     def __get_reactions(self, item):
         item_reactions = item.get('award_emoji_data', [])
+        reactions_total_count = len(item_reactions)
         if item_reactions:
             reactions_counter = collections.Counter([reaction["name"] for reaction in item_reactions])
             item_reactions = [{"type": reaction, "count": reactions_counter[reaction]} for reaction in
                               reactions_counter]
 
-        return {"reactions": item_reactions}
+        return {"reactions": item_reactions, "reactions_total_count": reactions_total_count}
 
     def __get_rich_issue(self, item):
         rich_issue = {}
@@ -220,41 +219,27 @@ def __get_rich_issue(self, item):
         else:
             rich_issue['time_open_days'] = rich_issue['time_to_close_days']
 
-        rich_issue['user_login'] = issue['author']['username']
-
-        user = issue.get('author', None)
-        if user is not None and user:
-            rich_issue['user_name'] = user['name']
-            rich_issue['author_name'] = user['name']
-            rich_issue["user_domain"] = self.get_email_domain(user['email']) if user.get('email') else None
-            rich_issue['user_org'] = user.get('company', None)
-            rich_issue['user_location'] = user.get('location', None)
-            rich_issue['user_geolocation'] = None
+        author = issue.get('author', None)
+        if author is not None and author:
+            rich_issue['author_login'] = author['username']
+            rich_issue['author_name'] = author['name']
+            rich_issue['author_domain'] = self.get_email_domain(author['email']) if author.get('email') else None
         else:
-            rich_issue['user_name'] = None
-            rich_issue["user_domain"] = None
-            rich_issue['user_org'] = None
-            rich_issue['user_location'] = None
-            rich_issue['user_geolocation'] = None
+            rich_issue['author_login'] = None
             rich_issue['author_name'] = None
+            rich_issue['author_domain'] = None
 
         assignee = issue.get('assignee', None)
         if assignee is not None and assignee:
             rich_issue['assignee_login'] = assignee['username']
             rich_issue['assignee_name'] = assignee['name']
-            rich_issue["assignee_domain"] = self.get_email_domain(assignee['email']) if assignee.get('email') else None
-            rich_issue['assignee_org'] = assignee.get('company', None)
-            rich_issue['assignee_location'] = assignee.get('location'), None
-            rich_issue['assignee_geolocation'] = None
+            rich_issue['assignee_domain'] = self.get_email_domain(assignee['email']) if assignee.get('email') else None
         else:
-            rich_issue['assignee_name'] = None
             rich_issue['assignee_login'] = None
-            rich_issue["assignee_domain"] = None
-            rich_issue['assignee_org'] = None
-            rich_issue['assignee_location'] = None
-            rich_issue['assignee_geolocation'] = None
+            rich_issue['assignee_name'] = None
+            rich_issue['assignee_domain'] = None
 
-        rich_issue['id'] = issue['id']
+        rich_issue['id'] = str(issue['id'])
         rich_issue['issue_id'] = issue['id']
         rich_issue['issue_id_in_repo'] = issue['web_url'].split("/")[-1]
         rich_issue['repository'] = self.get_project_repository(rich_issue)
@@ -316,42 +301,28 @@ def __get_rich_merge(self, item):
         else:
             rich_mr['time_open_days'] = rich_mr['time_to_close_days']
 
-        rich_mr['user_login'] = merge_request['author']['username']
-
-        user = merge_request.get('author', None)
-        if user is not None and user:
-            rich_mr['user_name'] = user['name']
-            rich_mr['author_name'] = user['name']
-            rich_mr["user_domain"] = self.get_email_domain(user['email']) if user.get('email') else None
-            rich_mr['user_org'] = user.get('company', None)
-            rich_mr['user_location'] = user.get('location', None)
-            rich_mr['user_geolocation'] = None
+        author = merge_request.get('author', None)
+        if author is not None and author:
+            rich_mr['author_login'] = author['username']
+            rich_mr['author_name'] = author['name']
+            rich_mr['author_domain'] = self.get_email_domain(author['email']) if author.get('email') else None
         else:
-            rich_mr['user_name'] = None
-            rich_mr["user_domain"] = None
-            rich_mr['user_org'] = None
-            rich_mr['user_location'] = None
-            rich_mr['user_geolocation'] = None
+            rich_mr['author_login'] = None
             rich_mr['author_name'] = None
+            rich_mr['author_domain'] = None
 
         merged_by = merge_request.get('merged_by', None)
         if merged_by is not None and merged_by:
             rich_mr['merge_author_login'] = merged_by['username']
             rich_mr['merge_author_name'] = merged_by['name']
-            rich_mr["merge_author_domain"] = \
+            rich_mr['merge_author_domain'] = \
                 self.get_email_domain(merged_by['email']) if merged_by.get('email') else None
-            rich_mr['merge_author_org'] = merged_by.get('company', None)
-            rich_mr['merge_author_location'] = merged_by.get('location', None)
-            rich_mr['merge_author_geolocation'] = None
         else:
-            rich_mr['merge_author_name'] = None
             rich_mr['merge_author_login'] = None
-            rich_mr["merge_author_domain"] = None
-            rich_mr['merge_author_org'] = None
-            rich_mr['merge_author_location'] = None
-            rich_mr['merge_author_geolocation'] = None
+            rich_mr['merge_author_name'] = None
+            rich_mr['merge_author_domain'] = None
 
-        rich_mr['id'] = merge_request['id']
+        rich_mr['id'] = str(merge_request['id'])
         rich_mr['merge_id'] = merge_request['id']
         rich_mr['merge_id_in_repo'] = merge_request['web_url'].split("/")[-1]
         rich_mr['repository'] = self.get_project_repository(rich_mr)
@@ -490,7 +461,7 @@ def get_rich_merge_reviews(self, comments, eitem):
 
             self.copy_raw_fields(self.RAW_FIELDS_COPY, eitem, ecomment)
 
-            # Copy data from the enriched pull
+            # Copy data from the enriched merge request
             ecomment['merge_labels'] = eitem['merge_labels']
             ecomment['merge_id'] = eitem['merge_id']
             ecomment['merge_id_in_repo'] = eitem['merge_id_in_repo']

schema/gitlabcomments_issues.csv

@@ -15,6 +15,7 @@ author_domain,keyword,true,"Domain associated to the author in SortingHat profil
 author_gender,keyword,true,"Author gender, based on her name (disabled by default)."
 author_gender_acc,long,true,"Author gender accuracy (disabled by default)."
 author_id,keyword,true,"Author ID from SortingHat."
+author_login,keyword,true,"Author's login name from GitLab."
 author_multi_org_names,keyword,true,"List of the author organizations from SortingHat profile."
 author_name,keyword,true,"Author name."
 author_org_name,keyword,true,"Author organization name."
@@ -48,8 +49,9 @@ metadata__updated_on,date,true,"Date when the item was updated on its original d
 origin,keyword,true,"The original URL from which the repository was retrieved from."
 project,keyword,true,"Project name."
 project_1,keyword,true,"Used if more than one project levels are allowed in the project hierarchy."
-reactions.count,long,true,"The number of reactions to comment/issue."
-reactions.type,keyword,true,"The name of reaction to comment/issue."
+reactions.count,long,true,"Number of reactions of a given type."
+reactions.type,keyword,true,"Name of reaction to comment/issue."
+reactions_total_count,long,true,"Total number of reactions to comment/issue."
 repository,keyword,true,"Repository name."
 sub_type,keyword,true,"Type of the comment (issue comment)."
 tag,keyword,true,"Perceval tag."
@@ -58,6 +60,4 @@ time_to_close_days,float,true,"Time to close an issue counted in days."
 time_to_first_attention,float,true,"Time to first attention to an issue counted in days."
 title_analyzed,text,true,"Issue title split by by terms to allow searching."
 url,keyword,true,"Url of the issue/comment."
-user_login,keyword,true,"User's login name from GitLab."
-user_name,keyword,true,"User's name."
 uuid,keyword,true,"Perceval UUID."

schema/gitlabcomments_merges.csv

@@ -4,6 +4,7 @@ author_domain,keyword,true,"Domain associated to the author in SortingHat profil
 author_gender,keyword,true,"Author gender, based on her name (disabled by default)."
 author_gender_acc,long,true,"Author gender accuracy (disabled by default)."
 author_id,keyword,true,"Author ID from SortingHat."
+author_login,keyword,true,"Author's login name from GitLab."
 author_multi_org_names,keyword,true,"List of the author organizations from SortingHat profile."
 author_name,keyword,true,"Author name."
 author_org_name,keyword,true,"Author organization name."
@@ -54,8 +55,9 @@ num_versions,long,true,"Number of versions"
 origin,keyword,true,"The original URL from which the repository was retrieved from."
 project,keyword,true,"Project name."
 project_1,keyword,true,"Used if more than one project levels are allowed in the project hierarchy."
-reactions.count,long,true,"The number of reactions to comment/merge request."
-reactions.type,keyword,true,"The name of reaction to comment/merge request."
+reactions.count,long,true,"Number of reactions of a given type."
+reactions.type,keyword,true,"Name of reaction to comment/issue."
+reactions_total_count,long,true,"Total number of reactions to comment/issue."
 repository,keyword,true,"Repository name."
 sub_type,keyword,true,"Type of the comment (merge request comment)."
 tag,keyword,true,"Perceval tag."
@@ -64,6 +66,4 @@ time_to_close_days,float,true,"Time to close a merge request counted in days."
 time_to_merge_request_response,float,true,"Time to merge a merge request counted in days."
 title_analyzed,text,true,"Issue title split by by terms to allow searching."
 url,keyword,true,"Url of the merge request/comment."
-user_login,keyword,true,"User's login name from GitLab."
-user_name,keyword,true,"User's name."
 uuid,keyword,true,"Perceval UUID."

tests/test_gitlabcomments.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2015-2019 Bitergia
+# Copyright (C) 2015-2020 Bitergia
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -58,7 +58,6 @@ def test_raw_to_enrich(self):
 
         self.assertGreater(result['raw'], 0)
         self.assertGreater(result['enrich'], 0)
-        # self.assertEqual(result['raw'], result['enrich'])
 
         enrich_backend = self.connectors[self.connector][2]()
 
@@ -67,37 +66,40 @@ def test_raw_to_enrich(self):
         self.assertEqual(item['category'], 'issue')
         self.assertNotEqual(eitem['issue_state'], 'closed')
         self.assertEqual(eitem['issue_labels'], ['UI', 'enhancement', 'feature'])
+        self.assertEqual(eitem['reactions_total_count'], 1)
         self.assertEqual(eitem['reactions'][0]['type'], 'thumbsdown')
         self.assertEqual(eitem['reactions'][0]['count'], 1)
-        # self.assertEqual(eitem['time_open_days'], 63.74)
+        self.assertEqual(eitem['issue_id_in_repo'], '25')
+        self.assertEqual(eitem['issue_created_at'], '2020-04-07T11:31:36.167Z')
 
         item = self.items[1]
         eitem = enrich_backend.get_rich_item(item)
         self.assertEqual(item['category'], 'merge_request')
         self.assertEqual(eitem['merge_state'], 'closed')
         self.assertEqual(eitem['merge_labels'], [])
+        self.assertEqual(eitem['reactions_total_count'], 0)
         self.assertEqual(eitem['reactions'], [])
         self.assertNotIn(eitem['time_to_merge_request_response'], eitem)
         self.assertEqual(eitem['time_to_close_days'], eitem['time_open_days'])
+        self.assertEqual(eitem['merge_id_in_repo'], '41')
+        self.assertEqual(eitem['merge_created_at'], '2020-04-20T19:17:54.576Z')
 
         item = self.items[2]
         eitem = enrich_backend.get_rich_item(item)
         self.assertEqual(item['category'], 'merge_request')
         self.assertEqual(eitem['merge_state'], 'merged')
+        self.assertEqual(eitem['reactions_total_count'], 1)
         self.assertEqual(eitem['reactions'][0]['type'], 'rocket')
         self.assertEqual(eitem['reactions'][0]['count'], 1)
-        # self.assertEqual(eitem['time_open_days'], 49.04)
 
         item = self.items[3]
         eitem = enrich_backend.get_rich_item(item)
         self.assertEqual(item['category'], 'issue')
         self.assertEqual(eitem['issue_state'], 'closed')
-        self.assertEqual(eitem['user_name'], 'Shashank Priyadarshi')
-        self.assertIsNone(eitem['user_domain'])
-        self.assertIsNone(eitem['user_org'])
         self.assertEqual(eitem['author_name'], 'Shashank Priyadarshi')
+        self.assertIsNone(eitem['author_domain'])
         self.assertIsNone(eitem['assignee_domain'])
-        self.assertIsNone(eitem['assignee_org'])
+        self.assertEqual(eitem['reactions_total_count'], 0)
         self.assertEqual(eitem['reactions'], [])
         self.assertEqual(eitem['time_to_first_attention'], 13.07)
         self.assertEqual(eitem['time_to_close_days'], eitem['time_open_days'])
@@ -106,14 +108,9 @@ def test_raw_to_enrich(self):
         eitem = enrich_backend.get_rich_item(item)
         self.assertEqual(item['category'], 'merge_request')
         self.assertEqual(eitem['merge_state'], 'merged')
-        self.assertEqual(eitem['user_name'], 'Vaishnav')
-        self.assertIsNone(eitem['user_domain'])
-        self.assertIsNone(eitem['user_org'])
-        self.assertIsNone(eitem['user_location'])
-        self.assertIsNone(eitem['user_location'])
         self.assertEqual(eitem['author_name'], 'Vaishnav')
+        self.assertIsNone(eitem['author_domain'])
         self.assertIsNone(eitem['merge_author_domain'])
-        self.assertIsNone(eitem['merge_author_org'])
         self.assertEqual(eitem['num_versions'], 1)
         self.assertEqual(eitem['num_merge_comments'], 3)
         self.assertEqual(eitem['time_to_merge_request_response'], 0)