utage: mission key generation and name finding

should be compatible with bingo's xdusuitecsharp

utage/names.py

@@ -0,0 +1,83 @@
+import csv
+import json
+import io
+import os
+import re
+
+from functools import partial
+from glob import glob
+from multiprocessing import Pool
+
+def update_names(dir_in, old_path, languages):
+	names = extract_names(dir_in)
+
+	# we have to update japanese like the rest because CustomData exists
+	# and POKELABO deleted the wedding gear event stuff from the game files
+	for x in languages:
+		langfile = os.path.join(old_path, "nametranslations_{}.json".format(x))
+		if os.path.isfile(langfile):
+			with open(langfile, "r") as lang_file:
+				lang_dict = json.load(lang_file)
+			if x == "jpn":
+				out_dict = dict(zip(names, names)).update(lang_dict)
+			else:
+				out_dict = dict.fromkeys(names, "").update(lang_dict)
+		elif x == "jpn": # bootstrap
+			out_dict = dict(zip(names, names))
+		else:
+			out_dict = dict.fromkeys(names, "")
+
+		with io.open(langfile, "w", newline='\n') as lang_file: # you're using git right
+			json.dump(lang_dict, lang_file, ensure_ascii=False, indent='\t', sort_keys=True)
+
+def extract_names(dir_in):
+	char_tsv_path = os.path.join(dir_in, "Diva", "Settings", "Character.tsv")
+
+	if not os.path.isfile(char_tsv_path):
+		raise FileNotFoundError("Character.tsv not found")
+
+	names, sets = read_char_tsv(char_tsv_path)
+
+	files = [f for f in glob(os.path.join(dir_in, "**/*.tsv"), recursive=True) if re.search(r'/[0-9]{9}\.tsv$', f)]
+	if len(files) == 0:
+		raise FileNotFoundError("No valid files found in directory: " + dir_in)
+
+	# tfw gil
+	# it's still faster on my machine so i'm keeping it
+	read_partial = partial(read_mission, char_names=names, char_sets=sets)
+	with Pool() as p:
+		new_names = p.map(read_partial, files)
+	for x in new_names:
+		names.update(x)
+
+	return names
+
+def read_char_tsv(char_tsv_path):
+	char_names = set()
+	char_sets = set()
+
+	with open(char_tsv_path, "r") as char_tsv_file:
+		char_tsv = csv.DictReader(char_tsv_file, delimiter="\t", quotechar="\"")
+
+		for row in char_tsv:
+			if row['CharacterName'].startswith("//"):
+				continue
+			if row['CharacterName'] and row['NameText'] and row['CharacterName'].strip() and row['NameText'].strip():
+				char_names.add(row['NameText'])
+				char_sets.add(row['CharacterName'])
+
+	return char_names, char_sets
+
+def read_mission(tsv_path, char_names, char_sets):
+	new_names = set()
+	with open(tsv_path, "r") as tsv_file:
+		tsv = csv.DictReader(tsv_file, delimiter="\t", quotechar="\"")
+		if ('Arg1' not in tsv.fieldnames) or ('Text' not in tsv.fieldnames) or ('Command' not in tsv.fieldnames):
+			return new_names
+		for row in tsv:
+			if row['Command'] and row['Command'].startswith("//"):
+				continue
+			if row['Text'] and row['Arg1']:
+				if (row['Arg1'] not in char_names) and (row['Arg1'] not in char_sets):
+					new_names.add(row['Arg1'])
+	return new_names