From d818ce3109b43ea9325cd557e31b495e1ec91d72 Mon Sep 17 00:00:00 2001
From: Yasha Bubnov <yasha.bubnov@wolt.com>
Date: Thu, 7 Nov 2024 15:27:35 +0100
Subject: [PATCH] Update library to support python 3.12 and pandas>=2.0

This patch fixes a unescaped string symbols, like "\s", which are
raising SyntaxError in Python 3.12 by replacing strings with raw
strings.

Also patch changes series iteration `iteritems()`, which was removed
in Pandas>=2.0 and replaces it with `iloc` iterator, which is available
in both, Pandas<2.0 and Pandas>=2.0

Patch also bumps version of the library to 0.3.7.
---
 pandas_schema/schema.py     | 2 +-
 pandas_schema/validation.py | 4 ++--
 pandas_schema/version.py    | 2 +-
 test/test_validation.py     | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/pandas_schema/schema.py b/pandas_schema/schema.py
index 0648d6c..e0471ee 100644
--- a/pandas_schema/schema.py
+++ b/pandas_schema/schema.py
@@ -64,7 +64,7 @@ def validate(self, df: pd.DataFrame, columns: typing.List[str] = None) -> typing
         # We associate the column objects in the schema with data frame series either by name or by position, depending
         # on the value of self.ordered
         if self.ordered:
-            series = [x[1] for x in df.iteritems()]
+            series = [df.iloc[:, i] for i in range(len(df.columns))]
             column_pairs = zip(series, self.columns)
         else:
             column_pairs = []
diff --git a/pandas_schema/validation.py b/pandas_schema/validation.py
index 5f7c763..95c7d6f 100644
--- a/pandas_schema/validation.py
+++ b/pandas_schema/validation.py
@@ -329,7 +329,7 @@ def default_message(self):
         return 'contains trailing whitespace'
 
     def validate(self, series: pd.Series) -> pd.Series:
-        return ~series.astype(str).str.contains('\s+$')
+        return ~series.astype(str).str.contains(r'\s+$')
 
 
 class LeadingWhitespaceValidation(_SeriesValidation):
@@ -345,7 +345,7 @@ def default_message(self):
         return 'contains leading whitespace'
 
     def validate(self, series: pd.Series) -> pd.Series:
-        return ~series.astype(str).str.contains('^\s+')
+        return ~series.astype(str).str.contains(r'^\s+')
 
 
 class IsDistinctValidation(_SeriesValidation):
diff --git a/pandas_schema/version.py b/pandas_schema/version.py
index 4596d03..d93912e 100644
--- a/pandas_schema/version.py
+++ b/pandas_schema/version.py
@@ -1 +1 @@
-__version__ = '0.3.6'
+__version__ = '0.3.7'
diff --git a/test/test_validation.py b/test/test_validation.py
index fc40100..4bb4d8c 100644
--- a/test/test_validation.py
+++ b/test/test_validation.py
@@ -345,7 +345,7 @@ def test_invalid_dates(self):
 
 class StringRegexMatch(ValidationTestBase):
     def setUp(self):
-        self.validator = MatchesPatternValidation('^.+\.txt$')
+        self.validator = MatchesPatternValidation(r'^.+\.txt$')
 
     def test_valid_strings(self):
         self.validate_and_compare(
@@ -408,7 +408,7 @@ class CompiledRegexMatch(ValidationTestBase):
     """
 
     def setUp(self):
-        self.validator = MatchesPatternValidation(re.compile('^.+\.txt$', re.IGNORECASE))
+        self.validator = MatchesPatternValidation(re.compile(r'^.+\.txt$', re.IGNORECASE))
 
     def test_valid_strings(self):
         self.validate_and_compare(