Add additional flag to ignore tables in data comparison

andrikoz · Jan 19, 2021 · 225de1f · 225de1f
1 parent 325db7a
commit 225de1f
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 4 deletions.
diff --git a/pgdatadiff/main.py b/pgdatadiff/main.py
@@ -1,6 +1,6 @@
 """
 Usage:
-  pgdatadiff --firstdb=<firstconnectionstring> --seconddb=<secondconnectionstring> [--only-data|--only-sequences] [--count-only] [--chunk-size=<size>]
+  pgdatadiff --firstdb=<firstconnectionstring> --seconddb=<secondconnectionstring> [--only-data|--only-sequences] [--count-only] [--chunk-size=<size>] [--exclude-tables=<table1,table2>]
   pgdatadiff --version
 
 Options:
@@ -10,6 +10,7 @@
   --seconddb=postgres://postgres:password@localhost/seconddb         The connection string of the second DB
   --only-data        Only compare data, exclude sequences
   --only-sequences   Only compare seqences, exclude data
+  --exclude-tables=""   Exclude tables from data comparison         Must be a comma separated string [default: empty string]
   --count-only       Do a quick test based on counts alone
   --chunk-size=10000       The chunk size when comparing data [default: 10000]
 """
@@ -33,7 +34,8 @@ def main():
 
     differ = DBDiff(first_db_connection_string, second_db_connection_string,
                     chunk_size=arguments['--chunk-size'],
-                    count_only=arguments['--count-only'])
+                    count_only=arguments['--count-only'],
+                    exclude_tables=arguments['--exclude-tables'])
 
     if not arguments['--only-sequences']:
         if differ.diff_all_table_data():

diff --git a/pgdatadiff/pgdatadiff.py b/pgdatadiff/pgdatadiff.py
@@ -1,6 +1,6 @@
 import warnings
 
-from fabulous.color import bold, green, red
+from fabulous.color import bold, green, red, yellow
 from halo import Halo
 from sqlalchemy import exc as sa_exc
 from sqlalchemy.engine import create_engine
@@ -19,7 +19,7 @@ def make_session(connection_string):
 
 class DBDiff(object):
 
-    def __init__(self, firstdb, seconddb, chunk_size=10000, count_only=False):
+    def __init__(self, firstdb, seconddb, chunk_size=10000, count_only=False, exclude_tables=""):
         firstsession, firstengine = make_session(firstdb)
         secondsession, secondengine = make_session(seconddb)
         self.firstsession = firstsession
@@ -32,6 +32,7 @@ def __init__(self, firstdb, seconddb, chunk_size=10000, count_only=False):
         self.secondinspector = inspect(secondengine)
         self.chunk_size = int(chunk_size)
         self.count_only = count_only
+        self.exclude_tables = exclude_tables.split(',')
 
     def diff_table_data(self, tablename):
         try:
@@ -142,6 +143,9 @@ def diff_all_table_data(self):
             tables = sorted(
                 self.firstinspector.get_table_names(schema="public"))
             for table in tables:
+                if table in self.exclude_tables:
+                    print(bold(yellow(f"Ignoring table {table}")))
+                    continue
                 with Halo(
                         text=f"Analysing table {table}. "
                              f"[{tables.index(table) + 1}/{len(tables)}]",