From 62efd328d2233f4ee7f9abe2f075bbdf3e122f95 Mon Sep 17 00:00:00 2001
From: Michael Tenetko <tenetko@users.noreply.github.com>
Date: Mon, 2 Dec 2024 22:40:47 +0300
Subject: [PATCH] (fix) made changes in add_q5011_2t so that it correctly works
 with different date formats

---
 add_q5011_2t.py | 83 +++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 73 insertions(+), 10 deletions(-)

diff --git a/add_q5011_2t.py b/add_q5011_2t.py
index 525d098..f1fc873 100644
--- a/add_q5011_2t.py
+++ b/add_q5011_2t.py
@@ -2,14 +2,15 @@
 import pandas as pd
 import psycopg2
 import zipfile
-import datetime
+from datetime import datetime
 
 from glob import glob
 
 
 class Q5011_2TUpdater:
-    Q5011_2T_DATETIME_FORMAT = "%Y/%m/%d %H:%M:%S"  # 2024/09/04 07:07:06
-    ISO_DATETIME_FORMAT = "%Y-%m-%d %H:%M:%S"
+    IVDATE1_DATETIME_FORMAT = "%d.%m.%Y %H:%M:%S"  # 02.05.2022 15:16:18
+    ISO_DATETIME_FORMAT = "%Y-%m-%d %H:%M:%S"  # 2022-05-02 15:04:09
+
     def __init__(self):
         self.config = self.get_config()
 
@@ -18,9 +19,33 @@ def get_config(self):
             return json.load(input_file)
 
     def get_dataframe(self, file_name):
-        return pd.read_excel(file_name)
+        df = pd.read_excel(file_name)
+        df = df.astype({"Q5011_2T": "str"})
+
+        return df
+
+    def is_month_incorrect(self, dataframe):
+        first_row = dataframe.iloc[0]
+        ivdate = first_row["IVDate1"]
+        ivdate = datetime.strptime(ivdate, self.IVDATE1_DATETIME_FORMAT)
+
+        for _, row in dataframe.iterrows():
+            recruiting_date = row["Q5011_2T"]
+            if pd.isna(recruiting_date) or recruiting_date == "nan":
+                continue
+
+            recruiting_date_month = int(recruiting_date[5:7])
+
+            if ivdate.month != recruiting_date_month:
+                return True
+
+            else:
+                return False
+
+        return False
+
+    def update_table(self, dataframe, month_is_incorrect):
 
-    def update_table(self, dataframe):
         with psycopg2.connect(
             host=self.config["db_host"],
             dbname=self.config["db_name"],
@@ -29,8 +54,20 @@ def update_table(self, dataframe):
         ) as conn:
             with conn.cursor() as cur:
                 for _, row in dataframe.iterrows():
-                    recruiting_date = datetime.strptime(row["Q5011_2T"], self.Q5011_2T_DATETIME_FORMAT)
-                    recruiting_date = datetime.strftime(recruiting_date, self.ISO_DATETIME_FORMAT)
+                    recruiting_date = row["Q5011_2T"]
+                    # 2024/09/04 07:07:06
+                    # 2024-09-04 07:07:06
+
+                    ivdate1 = row["IVDate1"]
+                    ivdate1 = datetime.strptime(ivdate1, self.IVDATE1_DATETIME_FORMAT)
+                    ivdate1 = datetime.strftime(ivdate1, self.ISO_DATETIME_FORMAT)
+
+                    if pd.isna(recruiting_date) or recruiting_date == "nan":
+                        recruiting_date = ivdate1
+
+                    elif month_is_incorrect:
+                        recruiting_date = self.make_fixed_recruiting_date(recruiting_date)
+
                     query_parameters = {
                         "id": row["ID"],
                         "q5011_2t": recruiting_date,
@@ -45,15 +82,41 @@ def update_table(self, dataframe):
                     )
                 conn.commit()
 
+    def make_fixed_recruiting_date(self, recruiting_date):
+        month = recruiting_date[5:7]
+        new_month = self.get_new_month(month)
+
+        rd_year = recruiting_date[:4]
+        rd_day_and_time = recruiting_date[8:]
+
+        new_recruiting_date = f"{rd_year}-{new_month}-{rd_day_and_time}"
+
+        return new_recruiting_date
+
+    def get_new_month(self, month):
+        month = int(month) + 1
+        month = f"{month:02d}"
+
+        return month
+
     def run(self):
         for file_name in glob("./xlsx/*.zip"):
             print(file_name[7:])
-            with zipfile.ZipFile(file_name, 'r') as zip:
+            with zipfile.ZipFile(file_name, "r") as zip:
                 with zip.open(zip.namelist()[0]) as excel_file:
                     dataframe = self.get_dataframe(excel_file)
-                    self.update_table(dataframe)
+                    month_is_incorrect = self.is_month_incorrect(dataframe)
+                    self.update_table(dataframe, month_is_incorrect)
+
+    def run_excel(self):
+        for file_name in glob("./xlsx/*.xlsx"):
+            print(file_name[7:])
+            dataframe = self.get_dataframe(file_name)
+            month_is_incorrect = self.is_month_incorrect(dataframe)
+            self.update_table(dataframe, month_is_incorrect)
 
 
 if __name__ == "__main__":
     u = Q5011_2TUpdater()
-    u.run()
\ No newline at end of file
+    u.run_excel()
+    # u.run()
\ No newline at end of file