From 8e4cac078904749db02be4125d4cfb324dfd607b Mon Sep 17 00:00:00 2001
From: Daniel Svitan <daniel.svitan.team7274dev@gmail.com>
Date: Fri, 18 Apr 2025 19:33:26 +0200
Subject: [PATCH] :zap: Adds parsing 2022 pdf results

---
 get_data.py | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/get_data.py b/get_data.py
index e371c65..8c84a58 100644
--- a/get_data.py
+++ b/get_data.py
@@ -44,8 +44,10 @@ if ok.lower() == "n":
 
 
 counties = ["BA", "TT", "TN", "NR", "ZA", "BB", "PO", "KE"]
-semifull_counties = ["Bratislavský kraj", "Trnavský kraj", "Trenčianský kraj", "Nitriansky kraj",
+counties2023 = ["Bratislavský kraj", "Trnavský kraj", "Trenčianský kraj", "Nitriansky kraj",
                      "Žilinský kraj", "Banskobystrický kraj", "Prešovský kraj", "Košický kraj"]
+counties2022 = ["Bratislavský", "Trnavský", "Trenčiansky", "Nitriansky",
+                     "Žilinský", "Banskobystrický", "Prešovský", "Košický"]
 
 
 def extract_2024(cat_str: str, lines: List[str]):
@@ -71,16 +73,26 @@ def extract_2024(cat_str: str, lines: List[str]):
 def extract_2023(lines: List[str]):
     results = []
 
-    for i in range(len(lines)):
-        line = lines[i]
-        if line[0:2] not in ["2.", "3.", "4.", "5.", "6."]:
+    for line in lines:
+        if line not in counties2023:
             continue
 
-        if lines[i-1] not in semifull_counties:
-            print("County not recognized: ", lines[i-1])
+        results.append(counties[counties2023.index(line)])
+        if len(results) == 5:
+            return results
+
+    return results
+
+
+def extract_2022(lines: List[str]):
+    results = []
+
+    for line in lines:
+        word = line.strip().split(" ")[-1].strip()
+        if word not in counties2022:
             continue
 
-        results.append(counties[semifull_counties.index(lines[i-1])])
+        results.append(counties[counties2022.index(word)])
         if len(results) == 5:
             return results
 
@@ -108,7 +120,7 @@ for pdf in pdfs:
     cat = int(max(matches[0]))
     cat_str = f"{cat:>02}"
 
-    if year != 2023:
+    if year != 2022:
         continue
 
     id = f"{year}-{cat_str}"
@@ -130,6 +142,8 @@ for pdf in pdfs:
             results = extract_2024(cat_str, lines)
         case 2023:
             results = extract_2023(lines)
+        case 2022:
+            results = extract_2022(lines)
     print("got results: ", results)
 
     exit(0)