Fix Sample Scripts and Data (#199)

* Change schema_name -> schema in sample_table_programmatic_source.csv * Update schema_name -> schema in sample_data_loader * Change name -> full_name in sample_user.csv * Change name -> full_name in sample_data_loader.py * Retrigger CLA Check
amundsen-io · Feb 25, 2020 · 6d5ffa4 · 6d5ffa4
1 parent 6c4bd0b
commit 6d5ffa4
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 11 deletions.
diff --git a/example/sample_data/sample_table_programmatic_source.csv b/example/sample_data/sample_table_programmatic_source.csv
@@ -1,4 +1,4 @@
-database,cluster,schema_name,name,description,tags,description_source
+database,cluster,schema,name,description,tags,description_source
 hive,gold,test_schema,test_table1,"**Size**: 50T\n\n**Monthly Cost**: $5000","expensive","s3_crawler"
 dynamo,gold,test_schema,test_table2,"**Size**: 1T\n\n**Monthly Cost**: $50","cheap","s3_crawler"
 hive,gold,test_schema,test_table1,"### Quality Report:\n --- \n Ipsus enom. Ipsus enom ipsus lorenum.\n ---\n[![Build Status](https://api.travis-ci.com/lyft/amundsendatabuilder.svg?branch=master)](https://travis-ci.com/lyft/amundsendatabuilder)","low_quality","quality_service"
diff --git a/example/sample_data/sample_user.csv b/example/sample_data/sample_user.csv
@@ -1,4 +1,4 @@
-email,first_name,last_name,name,github_username,team_name,employee_type,manager_email,slack_id
+email,first_name,last_name,full_name,github_username,team_name,employee_type,manager_email,slack_id
 [email protected],Roald,Amundsen,"Roald Amundsen",lyft,"Team Amundsen",sailor,"[email protected]",ramundzn
 [email protected],Christopher,Columbus,"Christopher Columbus",ChristopherColumbusFAKE,"Team Amundsen",sailor,"[email protected]",chrisc
-[email protected],  Buzz,       Aldrin,"Buzz Aldrin",BuzzAldrinFAKE,"Team Amundsen",astronaut,"[email protected]",buzz
+[email protected],Buzz,Aldrin,"Buzz Aldrin",BuzzAldrinFAKE,"Team Amundsen",astronaut,"[email protected]",buzz
diff --git a/example/scripts/sample_data_loader.py b/example/scripts/sample_data_loader.py
@@ -190,7 +190,7 @@ def load_user_data_from_csv(file_name):
                     '(email VARCHAR(64) NOT NULL , '
                     'first_name VARCHAR(64) NOT NULL , '
                     'last_name VARCHAR(64) NOT NULL , '
-                    'name VARCHAR(64) NOT NULL , '
+                    'full_name VARCHAR(64) NOT NULL , '
                     'github_username VARCHAR(64) NOT NULL , '
                     'team_name VARCHAR(64) NOT NULL, '
                     'employee_type VARCHAR(64) NOT NULL,'
@@ -202,15 +202,15 @@ def load_user_data_from_csv(file_name):
             to_db = [(i['email'],
                       i['first_name'],
                       i['last_name'],
-                      i['name'],
+                      i['full_name'],
                       i['github_username'],
                       i['team_name'],
                       i['employee_type'],
                       i['manager_email'],
                       i['slack_id']) for i in dr]
 
         cur.executemany("INSERT INTO test_user_metadata ("
-                        "email, first_name, last_name, name, github_username, "
+                        "email, first_name, last_name, full_name, github_username, "
                         "team_name, employee_type, "
                         "manager_email, slack_id ) VALUES "
                         "(?, ?, ?, ?, ?, ?, ?, ?, ?);", to_db)
@@ -434,7 +434,7 @@ def create_last_updated_job():
         'publisher.neo4j.{}'.format(neo4j_csv_publisher.NEO4J_PASSWORD):
             neo4j_password,
         'publisher.neo4j.{}'.format(neo4j_csv_publisher.JOB_PUBLISH_TAG):
-            'unique_lastupdated_tag',  # should use unique tag here like {ds}
+            'unique_last_updated_tag',  # should use unique tag here like {ds}
     })
 
     job = DefaultJob(conf=job_config,
@@ -543,7 +543,7 @@ def _load_csv(self):
         for column_dict in self.columns:
             db = column_dict['database']
             cluster = column_dict['cluster']
-            schema = column_dict['schema_name']
+            schema = column_dict['schema']
             table = column_dict['table_name']
             id = self._get_key(db, cluster, schema, table)
             column = ColumnMetadata(
@@ -562,15 +562,15 @@ def _load_csv(self):
         for table_dict in tables:
             db = table_dict['database']
             cluster = table_dict['cluster']
-            schema = table_dict['schema_name']
+            schema = table_dict['schema']
             table = table_dict['name']
             id = self._get_key(db, cluster, schema, table)
             columns = parsed_columns[id]
             if columns is None:
                 columns = []
             table = TableMetadata(database=table_dict['database'],
                                   cluster=table_dict['cluster'],
-                                  schema_name=table_dict['schema_name'],
+                                  schema=table_dict['schema'],
                                   name=table_dict['name'],
                                   description=table_dict['description'],
                                   columns=columns,
@@ -732,7 +732,7 @@ def create_table_column_job(table_path, column_path):
             with user, a, b, c, read, own, follow, manager
             where user.full_name is not null
             return user.email as email, user.first_name as first_name, user.last_name as last_name,
-            user.full_name as name, user.github_username as github_username, user.team_name as team_name,
+            user.full_name as full_name, user.github_username as github_username, user.team_name as team_name,
             user.employee_type as employee_type, manager.email as manager_email, user.slack_id as slack_id,
             user.is_active as is_active,
             REDUCE(sum_r = 0, r in COLLECT(DISTINCT read)| sum_r + r.read_count) AS total_read,