Dustin/jp_text_parsing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

try to get languages more in sync in the scripts.

Browse Source
This commit is contained in:
Nitsud Yarg 2026-05-22 17:41:11 -07:00
parent b866b308a0
commit fe803f174e
1 changed files with 73 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

126
getting_dialog.py
View File

@ -74,63 +74,83 @@ e_name_data = Path(f"YGO_2020/main/howto_db/howtoplay_{language_code}.bin").read
language_code = 'J'
j_name_data = Path(f"YGO_2020/main/howto_db/howtoplay_{language_code}.bin").read_bytes() # Get all the bytes
scripts = {}
def getScriptData():
offset = struct.unpack("<Q", script_data[0:8])[0] # 11914
titlecount = struct.unpack("<I", script_data[8:12])[0] # 307
scriptblockcount = struct.unpack("<I", script_data[12:16])[0] # 7340
titleStartPos = list()
titleEndPos = list()
titleOffset = list()
for p in range(titlecount):
i = p * 16
titleStartPos.append(struct.unpack("<I", script_data[i:i+4])[0])
titleEndPos.append(struct.unpack("<I", script_data[i+4:i+8])[0])
titleOffset.append(struct.unpack("<Q", script_data[i+8:i+16])[0])
## 307 items? Is that good
script_titles = list()
for o in range(len(titleOffset)):
start = titleOffset[o]
end = read_until_space(start,script_data)
script_titles.append(script_data[start:end].decode("utf-8"))
print( script_data[start:end].decode("utf-8") )
## Script Data extraction!
for p in range(titlecount):
#scripts[script_titles[p]] = {"title":script_titles[p], "blocks" : list()}
if script_titles[p] == '':
continue
if scripts.get(script_titles[p]) == None:
scripts[script_titles[p]] = {}
script_block = {}
blockCount = titleEndPos[p] - titleStartPos[p] #+1
#start = offset + titleOffset[p] + titleStartPos[p]
for j in range(blockCount):
seeker = offset + titleStartPos[p] * 32 + j * 32
start_char = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_char, script_data)
script_block['character'] = script_data[start_char:end].decode('utf-8')
index = f"{j}_{language_code}_{script_block['character']}"
seeker = seeker + 8
start_arg1 = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_arg1, script_data)
script_block['arg1'] = script_data[start_arg1:end].decode('utf-8')
seeker = seeker + 8
start_arg2 = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_arg2, script_data)
script_block['arg2'] = script_data[start_arg2:end].decode('utf-8')
seeker = seeker + 8
start_text = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_text, script_data) ## These strings seem to always start with /0x00
script_block['text'] = script_data[start_text:end].decode('utf-8')
if script_block['text'] != '':
if scripts[script_titles[p]].get(index) == None:
scripts[script_titles[p]][index] = {}
scripts[script_titles[p]][index]['arg1'] = script_block['arg1']
scripts[script_titles[p]][index]['arg2'] = script_block['arg2']
scripts[script_titles[p]][index]['text'] = script_block['text']
#scripts[p]['blocks'].append(script_block.copy())
print(script_block)
language_code = 'J'
script_data = Path(f"YGO_2020/main/scriptdata_{language_code}.bin").read_bytes() # Get all the bytes
getScriptData()
language_code = 'E'
script_data = Path(f"YGO_2020/main/scriptdata_{language_code}.bin").read_bytes() # Get all the bytes
getScriptData()
print('again?')
offset = struct.unpack("<Q", script_data[0:8])[0] # 11914
titlecount = struct.unpack("<I", script_data[8:12])[0] # 307
scriptblockcount = struct.unpack("<I", script_data[12:16])[0] # 7340
titleStartPos = list()
titleEndPos = list()
titleOffset = list()
for p in range(titlecount):
i = p * 16
titleStartPos.append(struct.unpack("<I", script_data[i:i+4])[0])
titleEndPos.append(struct.unpack("<I", script_data[i+4:i+8])[0])
titleOffset.append(struct.unpack("<Q", script_data[i+8:i+16])[0])
## 307 items? Is that good
script_titles = list()
for o in range(len(titleOffset)):
start = titleOffset[o]
end = read_until_space(start,script_data)
script_titles.append(script_data[start:end].decode("utf-8"))
print( script_data[start:end].decode("utf-8") )
## Script Data extraction!
scripts = {}
for p in range(titlecount):
scripts[p] = {"title":script_titles[p], "blocks" : list()}
script_block = {}
blockCount = titleEndPos[p] - titleStartPos[p] #+1
#start = offset + titleOffset[p] + titleStartPos[p]
for j in range(blockCount):
seeker = offset + titleStartPos[p] * 32 + j * 32
start_char = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_char, script_data)
script_block['character'] = script_data[start_char:end].decode('utf-8')
seeker = seeker + 8
start_arg1 = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_arg1, script_data)
script_block['arg1'] = script_data[start_arg1:end].decode('utf-8')
seeker = seeker + 8
start_arg2 = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_arg2, script_data)
script_block['arg2'] = script_data[start_arg2:end].decode('utf-8')
seeker = seeker + 8
start_text = struct.unpack("<Q", script_data[seeker:seeker+8])[0]
end = read_until_space(start_text, script_data) ## These strings seem to always start with /0x00
script_block['text'] = script_data[start_text:end].decode('utf-8')
scripts[p]['blocks'].append(script_block.copy())
print(script_block)
with open(f"scripts_dump_{language_code}.json", "w", encoding="utf-8") as outfile:
with open(f"scripts_dump.json", "w", encoding="utf-8") as outfile:
json.dump(scripts, outfile, ensure_ascii=False, indent=2)
exit()