-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
78 changed files
with
3,143 additions
and
3,306 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,212 @@ | ||
#=============================================================================# | ||
# Copyright 2022 Matthew D. Steele <[email protected]> # | ||
# # | ||
# This file is part of Annalog. # | ||
# # | ||
# Annalog is free software: you can redistribute it and/or modify it under # | ||
# the terms of the GNU General Public License as published by the Free # | ||
# Software Foundation, either version 3 of the License, or (at your option) # | ||
# any later version. # | ||
# # | ||
# Annalog is distributed in the hope that it will be useful, but WITHOUT ANY # | ||
# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS # | ||
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more # | ||
# details. # | ||
# # | ||
# You should have received a copy of the GNU General Public License along # | ||
# with Annalog. If not, see <http://www.gnu.org/licenses/>. # | ||
#=============================================================================# | ||
|
||
import os | ||
import sys | ||
|
||
#=============================================================================# | ||
|
||
MAX_PAIRS = 0xfd - 0x80 | ||
|
||
HEADER = """\ | ||
;;; This file was generated by text2asm. | ||
.INCLUDE "../../src/charmap.inc" | ||
.INCLUDE "../../src/dialog.inc" | ||
;;;=========================================================================;;; | ||
""" | ||
|
||
FOOTER = """\ | ||
;;;=========================================================================;;; | ||
""" | ||
|
||
#=============================================================================# | ||
|
||
def parse_text(data): | ||
text = [] | ||
current_chars = [] | ||
original_size = 0 | ||
def finish_string(): | ||
if not current_chars: return | ||
string = ''.join(current_chars) | ||
current_chars.clear() | ||
text.append(('b', string)) | ||
while data: | ||
if data.startswith('{'): | ||
i = data.find('}') | ||
finish_string() | ||
constant = data[1:i] | ||
data = data[i + 1:] | ||
text.append(('c', constant)) | ||
original_size += 1 | ||
elif data.startswith('['): | ||
i = data.find(']') | ||
finish_string() | ||
pair = data[1:i] | ||
data = data[i + 1:] | ||
assert len(pair) == 4 | ||
text.append(('p', (int(pair[:2], 16), int(pair[2:], 16)))) | ||
original_size += 2 | ||
else: | ||
char = data[0] | ||
data = data[1:] | ||
current_chars.append(char) | ||
original_size += 1 | ||
finish_string() | ||
return (text, original_size) | ||
|
||
def parse_input_file(filepath): | ||
texts = {} | ||
current_text_name = None | ||
current_text_data = '' | ||
original_size = 0 | ||
for line in open(filepath): | ||
line = line.rstrip('\n') | ||
if current_text_name is not None: | ||
current_text_data += line | ||
if line.endswith('#') or line.endswith('%'): | ||
(text, size) = parse_text(current_text_data) | ||
texts[current_text_name] = text | ||
original_size += size | ||
current_text_name = None | ||
current_text_data = '' | ||
else: | ||
current_text_data += '$' | ||
else: | ||
if not line: continue | ||
elif line.startswith('#'): continue | ||
elif line.startswith('@'): | ||
current_text_name = line[1:] | ||
else: | ||
raise ValueError('bad line: ' + repr(line)) | ||
assert current_text_name is None | ||
return (texts, original_size) | ||
|
||
def compute_pairs(texts): | ||
forced_pairs = set() | ||
pair_counts = {} | ||
for text in texts.values(): | ||
for kind, value in text: | ||
if kind == 'p': | ||
forced_pairs.add(value) | ||
elif kind == 'b': | ||
for i in range(0, len(value) - 1): | ||
pair = value[i:i + 2] | ||
if pair not in pair_counts: | ||
pair_counts[pair] = 0 | ||
pair_counts[pair] += 1 | ||
sorted_counts = sorted(pair_counts.items(), key=lambda item: -item[1]) | ||
best_pairs = [pair for pair, count in sorted_counts if count > 2] | ||
return sorted(forced_pairs) + best_pairs[:MAX_PAIRS - len(forced_pairs)] | ||
|
||
def compress_text(text, dictionary): | ||
compressed_size = 0 | ||
result_lines = [] | ||
current_line = [] | ||
current_chars = [] | ||
def finish_string(): | ||
if not current_chars: return | ||
string = ''.join(current_chars) | ||
current_chars.clear() | ||
current_line.append(f'"{string}"') | ||
def finish_line(): | ||
finish_string() | ||
if not current_line: return | ||
line = ', '.join(current_line) | ||
current_line.clear() | ||
result_lines.append(f' .byte {line}\n') | ||
for kind, value in text: | ||
if kind == 'b': | ||
while len(value) >= 2: | ||
pair = value[:2] | ||
i = dictionary.get(pair) | ||
if i is not None: | ||
value = value[2:] | ||
finish_string() | ||
current_line.append(f'${i + 0x80:02x}') | ||
compressed_size += 1 | ||
if '$' in pair: finish_line() | ||
else: | ||
char = value[0] | ||
value = value[1:] | ||
current_chars.append(char) | ||
compressed_size += 1 | ||
if char == '$': finish_line() | ||
if value: | ||
current_chars.append(value) | ||
compressed_size += len(value) | ||
if value.endswith('$'): finish_line() | ||
elif kind == 'c': | ||
finish_string() | ||
current_line.append(value) | ||
compressed_size += 1 | ||
elif kind == 'p': | ||
i = dictionary[value] | ||
finish_string() | ||
current_line.append(f'${i + 0x80:02x}') | ||
compressed_size += 1 | ||
else: assert False | ||
finish_line() | ||
return (''.join(result_lines), compressed_size) | ||
|
||
def write_output_file(bank, pairs, texts, original_data_size): | ||
compressed_data_size = 0 | ||
sys.stdout.write(HEADER) | ||
sys.stdout.write(f'.SEGMENT "PRGA_{bank}"\n\n') | ||
sys.stdout.write(f'.EXPORT DataA_{bank}_Strings_u8_arr2_arr\n') | ||
sys.stdout.write(f'.PROC DataA_{bank}_Strings_u8_arr2_arr\n') | ||
for pair in pairs: | ||
if isinstance(pair, str): | ||
sys.stdout.write(f' .byte "{pair}"\n') | ||
else: | ||
sys.stdout.write(f' .byte ${pair[0]:02x}, ${pair[1]:02x}\n') | ||
compressed_data_size += 2 | ||
sys.stdout.write(f'.ENDPROC\n') | ||
dictionary = {pair: i for i, pair in enumerate(pairs)} | ||
for name, text in sorted(texts.items()): | ||
sys.stdout.write(f'\n.EXPORT DataA_{bank}_{name}_u8_arr\n') | ||
sys.stdout.write(f'.PROC DataA_{bank}_{name}_u8_arr\n') | ||
(compressed_asm, compressed_size) = compress_text(text, dictionary) | ||
sys.stdout.write(compressed_asm) | ||
sys.stdout.write(f'.ENDPROC\n') | ||
compressed_data_size += compressed_size | ||
sys.stdout.write(f'\n;;; Original size = {original_data_size:4x}\n') | ||
sys.stdout.write(f';;; Compressed size = {compressed_data_size:4x}\n') | ||
saved = original_data_size - compressed_data_size | ||
sys.stdout.write(f';;; Bytes saved = {saved:4x}\n') | ||
percent = int(round(100 * (1 - compressed_data_size / original_data_size))) | ||
sys.stdout.write(f';;; Percent saved = {percent:3d}%\n') | ||
sys.stdout.write(FOOTER) | ||
|
||
def run(filepath): | ||
filename = os.path.split(filepath)[1] | ||
bank = os.path.splitext(filename)[0].capitalize() | ||
(texts, original_size) = parse_input_file(filepath) | ||
pairs = compute_pairs(texts) | ||
write_output_file(bank, pairs, texts, original_size) | ||
|
||
#=============================================================================# | ||
|
||
if __name__ == '__main__': | ||
run(sys.argv[1]) | ||
|
||
#=============================================================================# |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.