summaryrefslogtreecommitdiff
path: root/extras/analyze_texts.py
blob: 36d804135605b0111fbed9edb6523c857a5a8291 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
#!/usr/bin/python
#author: Bryan Bishop <kanzure@gmail.com>
#date: 2012-01-06
#analyze texts, how many commands are unknown?
import extract_maps
import analyze_incbins #for asm
try:
    from pretty_map_headers import map_name_cleaner, txt_bytes, spacing, constant_abbreviation_bytes
except Exception, exc: pass
from operator import itemgetter
import sys
debug = False #set to True to increase logging output

#how many times is each command byte called?
totals = {}
total_text_commands = 0
should_be_total = 0

def get_text_pointer(texts_pointer, text_id):
    if type(texts_pointer) == str: texts_pointer = int(texts_pointer, 16)
    if type(text_id) == str: text_id = int(text_id)

    byte1 = ord(extract_maps.rom[texts_pointer + ((text_id - 1) * 2)])
    byte2 = ord(extract_maps.rom[texts_pointer + ((text_id - 1) * 2) + 1])
    pointer = (byte1 + (byte2 << 8))

    return pointer

def how_many_until(byte, starting):
    index = extract_maps.rom.find(byte, starting)
    return index-starting

def print_command_debug_info(command_byte, text_id, text_pointer, map_id):
    if debug:
        print "byte is " + str(command_byte) + " on text #" + str(text_id) + " at " + hex(text_pointer) + " on map " + str(map_id) + " (" + extract_maps.map_headers[map_id]["name"] + ")"

def add_command_byte_to_totals(byte):
    global totals
    if not byte in totals.keys(): totals[byte] = 1
    else: totals[byte] += 1

def process_00_subcommands(start_address, end_address):
    """split this text up into multiple lines
    based on subcommands ending each line"""
    lines = {}
    subsection = extract_maps.rom[start_address:end_address+1]

    line_count = 0
    current_line = []
    for pbyte in subsection:
        byte = ord(pbyte)
        current_line.append(byte)
        if  byte == 0x4f or byte == 0x51 or byte == 0x55:
            lines[line_count] = current_line
            current_line = []
            line_count += 1

    #don't forget the last line
    lines[line_count] = current_line
    line_count += 1
    return lines

def parse_text_script(text_pointer, text_id, map_id, txfar=False):
    global total_text_commands
    offset = text_pointer
    commands = {}
    command_counter = 0
    
    end = False
    while not end:
        command = {}
        command_byte = ord(extract_maps.rom[offset])
        
        print_command_debug_info(command_byte, text_id, text_pointer, map_id)
        if  command_byte == 0:
            #read until $57, $50 or $58
            jump57 = how_many_until(chr(0x57), offset)
            jump50 = how_many_until(chr(0x50), offset)
            jump58 = how_many_until(chr(0x58), offset)
            
            #whichever command comes first
            jump = min([jump57, jump50, jump58])

            end_address = offset + jump - 1 #we want the address before $57

            command = {"type": command_byte,
                       "start_address": offset,
                       "end_address": end_address,
                       "size": jump,
                       "lines": process_00_subcommands(offset+1, end_address),
                      }

            offset += jump
        elif command_byte == 0x17:
            #TX_FAR [pointer][bank]
            pointer_byte1 = ord(extract_maps.rom[offset+1])
            pointer_byte2 = ord(extract_maps.rom[offset+2])
            pointer_bank = ord(extract_maps.rom[offset+3])

            pointer = (pointer_byte1 + (pointer_byte2 << 8))
            pointer = extract_maps.calculate_pointer(pointer, pointer_bank)

            command = {"type": command_byte,
                       "start_address": offset,
                       "end_address": offset + 3, #last byte belonging to this command
                       "pointer": pointer, #parameter
                      }

            offset += 3 + 1
        elif command_byte == 0x50 or command_byte == 0x57 or command_byte == 0x58: #end text
            command = {"type": command_byte,
                       "start_address": offset,
                       "end_address": offset,
                      }

            #this byte simply indicates to end the script
            end = True
            
            #this byte simply indicates to end the script
            if command_byte == 0x50 and ord(extract_maps.rom[offset+1]) == 0x50: #$50$50 means end completely
                end = True
                commands[command_counter+1] = command

                #also save the next byte, before we quit
                commands[command_counter+1]["start_address"] += 1
                commands[command_counter+1]["end_address"] += 1
                add_command_byte_to_totals(command_byte)
            elif command_byte == 0x50: #only end if we started with $0
                if len(commands.keys()) > 0:
                    if commands[0]["type"] == 0x0: end = True
            elif command_byte == 0x57 or command_byte == 0x58: #end completely
                end = True
                offset += 1 #go past this 0x50
        elif command_byte == 0x1:
            #01 = text from RAM. [01][2-byte pointer]
            size = 3 #total size, including the command byte
            pointer_byte1 = ord(extract_maps.rom[offset+1])
            pointer_byte2 = ord(extract_maps.rom[offset+2])
            
            command = {"type": command_byte,
                       "start_address": offset+1,
                       "end_address": offset+2, #last byte belonging to this command
                       "pointer": [pointer_byte1, pointer_byte2], #RAM pointer
                      }
            
            #view near these bytes
            #subsection = extract_maps.rom[offset:offset+size+1] #peak ahead
            #for x in subsection:
            #    print hex(ord(x))
            #print "--"

            offset += 2 + 1 #go to the next byte

            #use this to look at the surrounding bytes
            if debug:
                print "next command is: " + hex(ord(extract_maps.rom[offset])) + " ... we are at command number: " + str(command_counter) + " near " + hex(offset) + " on map_id=" + str(map_id) + " for text_id=" + str(text_id) + " and txfar(recursion)=" + str(txfar)
        elif command_byte == 0x7:
            #07 = shift texts 1 row above (2nd line becomes 1st line); address for next text = 2nd line. [07]
            size = 1
            command = {"type": command_byte,
                       "start_address": offset,
                       "end_address": offset,
                      }
            offset += 1
        elif command_byte == 0x3:
            #03 = set new address in RAM for text. [03][2-byte RAM address]
            size = 3
            command = {"type": command_byte, "start_address": offset, "end_address": offset+2}
            offset += size
        elif command_byte == 0x4: #draw box
            #04 = draw box. [04][2-Byte pointer][height Y][width X]
            size = 5 #including the command
            command = {
                        "type": command_byte,
                        "start_address": offset,
                        "end_address": offset + size,
                        "pointer_bytes": [ord(extract_maps.rom[offset+1]), ord(extract_maps.rom[offset+2])],
                        "y": ord(extract_maps.rom[offset+3]),
                        "x": ord(extract_maps.rom[offset+4]),
                      }
            offset += size + 1
        elif command_byte == 0x5:
            #05 = write text starting at 2nd line of text-box. [05][text][ending command]
            #read until $57, $50 or $58
            jump57 = how_many_until(chr(0x57), offset)
            jump50 = how_many_until(chr(0x50), offset)
            jump58 = how_many_until(chr(0x58), offset)
            
            #whichever command comes first
            jump = min([jump57, jump50, jump58])

            end_address = offset + jump - 1 #we want the address before $57

            command = {"type": command_byte,
                       "start_address": offset,
                       "end_address": end_address,
                       "size": jump,
                       "lines": process_00_subcommands(offset+1, end_address),
                      }
            offset = end_address + 1
        elif command_byte == 0x6:
            #06 = wait for keypress A or B (put blinking arrow in textbox). [06]
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x7:
            #07 = shift texts 1 row above (2nd line becomes 1st line); address for next text = 2nd line. [07]
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x8:
            #08 = asm until whenever
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
            end = True
        elif command_byte == 0x9:
            #09 = write hex-to-dec number from RAM to textbox [09][2-byte RAM address][byte bbbbcccc]
            #  bbbb = how many bytes to read (read number is big-endian)
            #  cccc = how many digits display (decimal)
            #(note: max of decimal digits is 7,i.e. max number correctly displayable is 9999999)
            ram_address_byte1 = ord(extract_maps.rom[offset+1])
            ram_address_byte2 = ord(extract_maps.rom[offset+2])
            read_byte = ord(extract_maps.rom[offset+3])

            command = {
                        "type": command_byte,
                        "address": [ram_address_byte1, ram_address_byte2],
                        "read_byte": read_byte, #split this up when we make a macro for this
                      }

            offset += 4 + 1
        elif command_byte == 0xB:
            #0B = sound_86 (Hiro obtains ITEM)[same as 0F]
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xE:
            #0E = sound_91 (learnt something)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xF:
            #0F = sound_86 (given rare candy)[same as 0B]
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x10:
            #10 = sound_89 (PKMN successfully caught)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x11:
            #11 = sound_94 (Hiro gives OAK the PARCEL)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x12:
            #12 = sound_9A (successfully caught)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x13:
            #13 = sound_98 (song heard when "new data will be added for..")
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x14:
            #14 = MonCry (Nidorina)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x15:
            #14 = MonCry (Pidgeot)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x16:
            #14 = MonCry (Dewgong)
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x19:
            #19 = play a 'bump' noise
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x1F:
            #1F = play some pokemon's roar, don't know which..
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x20:
            #20 = oddish roar?
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x3F:
            #3F = some other roar
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x9D:
            #9D = a roar or some other sound, four times in quick succession
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0x76:
            #76 = another roar
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xCA:
            #CA = stop music, start this other song that i can't name
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xF6:
            #F6 = play a 'blurp blurp' noise.. like something is increasing
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xFA:
            #FA = change music to champion song?
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xFE:
            #FE = another roar, kinda glitchy?
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        elif command_byte == 0xFF:
            #FF = change music to a specific song that i don't know the name of
            command = {"type": command_byte, "start_address": offset, "end_address": offset}
            offset += 1
        else:
            #if len(commands) > 0:
            #   print "Unknown text command " + hex(command_byte) + " at " + hex(offset) + ", script began with " + hex(commands[0]["type"])
            if debug:
                print "Unknown text command at " + hex(offset) + " - command: " + hex(ord(extract_maps.rom[offset])) + " on map_id=" + str(map_id) + " text_id=" + str(text_id)
            
            #end at the first unknown command
            end = True
        add_command_byte_to_totals(command_byte)

        commands[command_counter] = command
        command_counter += 1
    total_text_commands += len(commands)
    return commands

def analyze_texts():
    global should_be_total

    texts = {}
    for map_id in extract_maps.map_headers:
        if map_id in extract_maps.bad_maps: continue #skip
        map2 = extract_maps.map_headers[map_id]
        map2["texts"] = {}
        referenced_texts = map2["referenced_texts"]
        should_be_total += len(referenced_texts)
        texts_pointer = int(map2["texts_pointer"], 16)
        
        #print "Checking texts on... map_id=" + str(map_id) + " and len(referenced_texts)=" + str(len(referenced_texts))
        for text_id in referenced_texts:
            text_pointer = get_text_pointer(texts_pointer, text_id)
            if 0x4000 <= text_pointer <= 0x7fff: #only care about bank when it's between 4000-7fff
                text_pointer = extract_maps.calculate_pointer(text_pointer, int(map2["bank"], 16))
            #print "Working on map id=" + str(map2["id"]) + " and text id=" + str(text_id)
            #print "for map_id=" + str(map_id) + " texts_pointer=" + hex(texts_pointer) + " text_id=" + str(text_id) + " the pointer=" + hex(text_pointer)
            commands = parse_text_script(text_pointer, text_id, map_id)

            #process TX_FARs
            for command_id in commands:
                #skip commands starting with an unknown command byte
                if len(commands[command_id]) == 0: continue

                if commands[command_id]["type"] == 0x17:
                    TX_FAR = parse_text_script(commands[command_id]["pointer"], text_id, map_id, txfar=True)
                    if debug:
                        if len(TX_FAR.keys()) > 0:
                            #print "TX_FAR object: " + str(TX_FAR)
                            print "processing a TX_FAR at " + hex(commands[command_id]["pointer"]) + "... first byte is: " + str(ord(extract_maps.rom[commands[command_id]["pointer"]])) + " .. offset: " + hex(commands[command_id]["pointer"])
                            ##sys.exit(0)

                    commands[command_id]["TX_FAR"] = TX_FAR
                    #map2["texts"][text_id][command_id]["TX_FAR"] = parse_text_script(command["pointer"], text_id, map_id)
            map2["texts"][text_id] = commands

        texts[map_id] = map2["texts"]
        extract_maps.map_headers[map_id]["texts"] = map2["texts"]
    return texts

def find_missing_08s(all_texts):
    """determines which $08s have yet to be inserted
    based on their start addresses"""
    missing_08s = 0
    for map_id in all_texts.keys():
        for text_id in all_texts[map_id].keys():
            for line_id in all_texts[map_id][text_id].keys():
                if not line_id == 0:
                    current_line = all_texts[map_id][text_id][line_id]
                    if "type" in current_line.keys():
                        if current_line["type"] == 0x8:
                            missing_08s += 1
                            print "missing $08 on map_id=" + str(map_id) + " text_id=" + str(text_id) + " line_id=" + str(line_id) + " at " + hex(current_line["start_address"])
    return missing_08s

def text_pretty_printer_at(start_address, label="SomeLabel"):
    commands = parse_text_script(start_address, None, None)
    needs_to_begin_with_0 = False
    
    wanted_command = None
    if needs_to_begin_with_0:
        wanted_command = None
        for command_id in commands:
            command = commands[command_id]
            if command["type"] == 0:
                wanted_command = command_id
    
        if wanted_command == None:
            raise "error: address did not start with a $0 text"
    
    #start with zero please
    byte_count = 0

    first_line = True
    for this_command in commands.keys():
        if not "lines" in commands[this_command].keys(): continue
        lines = commands[this_command]["lines"]
    
        #add the ending byte to the last line- always seems $57
        lines[len(lines.keys())-1].append(commands[1]["type"])
    
        if first_line:
            output  = "\n"
            output += label + ": ; " + hex(start_address) + "\n"
            first_line = False

        first = True #first byte
        for line_id in lines:
            line = lines[line_id]
            output += spacing + "db "
            if first and needs_to_begin_with_0:
                output += "$0, "
                first = False
         
            quotes_open = False
            first_byte = True
            was_byte = False
            for byte in line:
                if byte in txt_bytes:
                    if not quotes_open and not first_byte: #start text
                        output += ", \""
                        quotes_open = True
                        first_byte = False
                    if not quotes_open and first_byte: #start text
                        output += "\""
                        quotes_open = True
                    output += txt_bytes[byte]
                elif byte in constant_abbreviation_bytes:
                    if quotes_open:
                        output += "\""
                        quotes_open = False
                    if not first_byte:
                        output += ", "
                    output += constant_abbreviation_bytes[byte]
                else:
                    if quotes_open:
                        output += "\""
                        quotes_open = False
    
                    #if you want the ending byte on the last line
                    #if not (byte == 0x57 or byte == 0x50 or byte == 0x58):
                    if not first_byte:
                        output += ", "
    
                    output += "$" + hex(byte)[2:]
                    was_byte = True
    
                    #add a comma unless it's the end of the line
                    #if byte_count+1 != len(line):
                    #    output += ", "
    
                first_byte = False
                byte_count += 1
            #close final quotes
            if quotes_open:
                output += "\""
                quotes_open = False
    
            output += "\n"

    #output += "\n"
    output += "; " + hex(start_address + byte_count)
    print output
    return (output, byte_count)

def is_label_in_asm(label):
    for line in analyze_incbins.asm:
        if label in line:
            if line[0:len(label)] == label:
                return True
    return False

def find_undone_texts():
    usable_table = {}
    if analyze_incbins.asm == None:
        analyze_incbins.load_asm()

    for map_id in extract_maps.map_headers:
        #skip bad maps
        if map_id in extract_maps.bad_maps: continue

        map2 = extract_maps.map_headers[map_id]
        name = map_name_cleaner(map2["name"], None)[:-2] + "Text"

        for text_id in map2["referenced_texts"]:
            label = name + str(text_id)

            if len(extract_maps.map_headers[map_id]["texts"][text_id].keys()) == 0: continue
            if len(extract_maps.map_headers[map_id]["texts"][text_id][0].keys()) == 0: continue

            try:
                address = extract_maps.map_headers[map_id]["texts"][text_id][0]["start_address"]
            except:
                address = extract_maps.map_headers[map_id]["texts"][text_id][1]["start_address"]
            
            if not is_label_in_asm(label):
                print label + " map_id=" + str(map_id) + " text_id=" + str(text_id) + " at " + hex(address) + " byte is: " + hex(ord(extract_maps.rom[address]))
                if not address in usable_table.keys():
                    usable_table[address] = 1
                else:
                    usable_table[address] += 1

    print "\n\n which ones are priority?"
    sorted_results =  sorted(usable_table.iteritems(), key=itemgetter(1), reverse=True)
    for result in sorted_results:
        print str(result[1]) + " times: " + hex(result[0])

if __name__ == "__main__":
    extract_maps.load_rom()
    extract_maps.load_map_pointers()
    extract_maps.read_all_map_headers()
    text_output = analyze_texts()
    #print text_output

    missing_08s = find_missing_08s(text_output)

    print "\n\n---- stats ----\n\n"
    
    popular_text_commands = sorted(totals.iteritems(), key=itemgetter(1), reverse=True)
    #convert the first values (command byte) to hex
    for popular_item in popular_text_commands:
        print hex(popular_item[0]) + " was used " + str(popular_item[1]) + " times."
    #print "popular text commands: " + str(popular_text_commands)
    
    print "total text commands: " + str(total_text_commands)
    print "total text scripts: " + str(should_be_total)
    print "missing 08s: " + str(missing_08s)
    print "\n\n"

    #text_pretty_printer_at(0x800b1)
    find_undone_texts()