From 8fd9dd848a1856c22948c0b18e4ce39a2dcbedc4 Mon Sep 17 00:00:00 2001
From: Aaron Weeden <aaronwee@buffalo.edu>
Date: Wed, 6 Dec 2023 12:06:39 -0500
Subject: [PATCH] Improve performance of validation of filters and raw fields.

---
 CHANGELOG.md              |  1 +
 xdmod_data/__version__.py |  2 +-
 xdmod_data/_validator.py  | 13 +++++++------
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 85942c07..a567f20d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,7 @@
 # xdmod-data Changelog
 
 ## Main development branch
+- Improve performance of validation of filters and raw fields ([\#18](https://github.com/ubccr/xdmod-data/pull/18)).
 - Update tests and testing instructions ([\#14](https://github.com/ubccr/xdmod-data/pull/14)).
 
 ## v1.0.0 (2023-07-21)
diff --git a/xdmod_data/__version__.py b/xdmod_data/__version__.py
index 55cd9ccf..10f5e82c 100644
--- a/xdmod_data/__version__.py
+++ b/xdmod_data/__version__.py
@@ -1,2 +1,2 @@
 __title__ = 'xdmod-data'
-__version__ = '1.0.0'
+__version__ = '1.0.1-beta.1'
diff --git a/xdmod_data/_validator.py b/xdmod_data/_validator.py
index d329b14c..d80f399a 100644
--- a/xdmod_data/_validator.py
+++ b/xdmod_data/_validator.py
@@ -179,10 +179,14 @@ def __validate_filters(data_warehouse, descriptors, realm, filters):
             if isinstance(filter_values, str):
                 filter_values = [filter_values]
             result[dimension_id] = []
+            valid_filter_values = data_warehouse.get_filter_values(
+                realm,
+                dimension,
+            )
             for filter_value in filter_values:
                 new_filter_value = __find_value_in_df(
                     'Filter value',
-                    data_warehouse.get_filter_values(realm, dimension),
+                    valid_filter_values,
                     filter_value,
                 )
                 result[dimension_id].append(new_filter_value)
@@ -214,12 +218,9 @@ def __find_str_in_sequence(value, sequence, label):
 def __validate_raw_fields(data_warehouse, realm, fields):
     try:
         results = []
+        valid_raw_fields = data_warehouse.describe_raw_fields(realm)
         for field in fields:
-            new_field = __find_value_in_df(
-                'Field',
-                data_warehouse.describe_raw_fields(realm),
-                field,
-            )
+            new_field = __find_value_in_df('Field', valid_raw_fields, field)
             results.append(new_field)
         return results
     except TypeError: