Add a script to consolidate all of the TM learnsets and fix some regex strings

Co-authored-by: Copilot <copilot@github.com>

Python_tasks/consolidate_tmlearnset.py

@@ -0,0 +1,53 @@
+import json
+import os
+import re
+
+
+def consolidate_tmlearnset():
+    """
+    Consolidates all individual TMLearnset JSON files into a single file.
+    Format: { monsno: { formno_0: data, formno_1: data, ... } }
+    """
+    # Define paths
+    tmlearnset_folder = os.path.join(os.path.dirname(__file__), '..', 'TMLearnset')
+    output_file = os.path.join(os.path.dirname(__file__), '..', '3.0Input', 'TMLearnset_consolidated.json')
+
+    # Dictionary to store consolidated data
+    consolidated_data = {}
+
+    # Iterate through all JSON files in the TMLearnset folder
+    for filename in sorted(os.listdir(tmlearnset_folder)):
+        if filename.endswith('.json'):
+            # Extract monsno and formno from filename using regex
+            match = re.match(r'monsno_(\d+)_formno_(\d+)\.json', filename)
+            if match:
+                monsno = match.group(1)
+                formno = match.group(2)
+
+                # Read the file
+                file_path = os.path.join(tmlearnset_folder, filename)
+                with open(file_path, 'r', encoding='utf-8') as f:
+                    file_data = json.load(f)
+
+                # Initialize monsno entry if it doesn't exist
+                if monsno not in consolidated_data:
+                    consolidated_data[monsno] = {}
+
+                # Add formno data
+                consolidated_data[monsno][f'formno_{formno}'] = file_data
+
+    # Sort the dictionary by monsno (as integers)
+    sorted_consolidated_data = {}
+    for monsno in sorted(consolidated_data.keys(), key=int):
+        sorted_consolidated_data[monsno] = consolidated_data[monsno]
+
+    # Write to output file
+    with open(output_file, 'w', encoding='utf-8') as f:
+        json.dump(sorted_consolidated_data, f, indent=2)
+
+    print(f"Successfully consolidated {len(consolidated_data)} Pokémon entries into {output_file}")
+    print(f"Total files processed: {sum(len(forms) for forms in consolidated_data.values())}")
+
+
+if __name__ == "__main__":
+    consolidate_tmlearnset()

Python_tasks/constants.py

@@ -273,7 +273,7 @@ KG_TO_LBS_CONSTANT = 0.453592
 FT_TO_CM_CONSTANT = 30.48
 IN_TO_CM_CONSTANT = 2.54
 
-TEAM_REGEX = "Team \d+"
+TEAM_REGEX = r"Team \d+"
 LDVAL_PATTERN = r"_LDVAL\(@(.*),\s?([1-9][0-9]*)\)"
 TRAINER_PATTERN = r"_TRAINER_BTL_SET\s*\(\s*('?[^']+'?|@\w+|\d+)\s*,\s*('?[^']+'?|@\w+|\d+)\s*\)"
 MULTI_TRAINER_PATTERN = r"_TRAINER_MULTI_BTL_SET\s*\(\s*((?:'[^']*'|@\w+|\d+)\s*(?:,\s*(?:'[^']*'|@\w+|\d+)\s*)*)\)"

Python_tasks/convert_lmpt_data.py

@@ -15,6 +15,7 @@ from pokemonUtils import (get_diff_form_dictionary,
                           get_pokemon_from_trainer_info,
                           get_pokemon_id_from_name, get_pokemon_name,
                           isSpecialPokemon, get_form_pokemon_personal_id)
+from consolidate_tmlearnset import consolidate_tmlearnset
 
 # Get the repo file path for cleaner path generating
 repo_file_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
@@ -758,6 +759,9 @@ if __name__ == "__main__":
     diff_forms, NAME_MAP = get_diff_form_dictionary()
     getPokedexInfo()
 
+    if constants.GAME_MODE == constants.GAME_MODE_3:
+        consolidate_tmlearnset()
+
     mid_time = time.time()
     print("Middle Execution time:", mid_time - start_time, "seconds")
     getEncounterData("mons_no")

Python_tasks/pokemonUtils.py

@@ -269,9 +269,9 @@ def slugify(value, pokeapi=False):
     """
     initial_value = value
     value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
-    value = re.sub('[^\w\s-]', '', value).strip().lower()
+    value = re.sub(r"[^\w\s-]", '', value).strip().lower()
     if pokeapi == False:
-        return re.sub('[-\s]+', '-', value)
+        return re.sub(r'[-\s]+', '-', value)
 
     if ' ' in value or "-" in value:
         # Split the string at the last space
@@ -289,7 +289,7 @@ def slugify(value, pokeapi=False):
             value = '-'.join([parts[1], parts[0]])
             return value
 
-    return re.sub('[-\s]+', '-', value)
+    return re.sub(r'[-\s]+', '-', value)
 
 def isSpecialPokemon(current_pokemon_name):
     """