def MakeStrDic(psp_jp_files, pc_cn_files, report):
if len(psp_jp_files) != len(pc_cn_files):
print('File num not match')
input()
return
dst_dic = dict()
match_dic = dict()
for fn_jp, fn_cn in zip(psp_jp_files, pc_cn_files):
if Common.BaseName(fn_jp) != Common.BaseName(fn_cn):
print('Filename not match: {} {}'.format(fn_jp, fn_cn))
input()
exit(1)
jp_group_list = []
fname = Common.BaseName(fn_cn)
print('process jp cn: {}'.format(fname))
jp = open(fn_jp, 'r', encoding='utf16')
cn = open(fn_cn, 'r', encoding='utf16')
lines = jp.readlines()
jp_lines = [line.rstrip('\n') for line in lines if line != '' and line != '\n']
lines = cn.readlines()
cn_lines = [line.rstrip('\n') for line in lines if line != '' and line != '\n']
if len(jp_lines) != len(cn_lines):
input('Line num not match: {}'.format(Common.BaseName(fn_jp)))
exit(1)
for jp_line, cn_line in zip(jp_lines, cn_lines):
offset, size, jp_text = Common.ParseWQSGLine(jp_line)
offset, size, cn_text = Common.ParseWQSGLine(cn_line)
if (not jp_text) and (not cn_text):
continue
jp_group = Common.SplitString(jp_text)
cn_group = Common.SplitString(cn_text)
if len(jp_group) != len(cn_group):
log = 'Group not match {}:{}--{}'.format(fname, jp_text, cn_text)
print(log)
report.write(log + '\n')
continue
jp_group_list += jp_group
for key, value in zip(jp_group, cn_group):
dst_dic[key] = value
match_dic[fname] = jp_group_list
jp.close()
cn.close()
return dst_dic, match_dic
def CompareLength(psp_jp_files, pc_cn_files, report):
if len(psp_jp_files) != len(pc_cn_files):
print('File num not match')
input()
return
for fn_jp, fn_cn in zip(psp_jp_files, pc_cn_files):
if Common.BaseName(fn_jp) != Common.BaseName(fn_cn):
print('Filename not match: {} {}'.format(fn_jp, fn_cn))
input()
exit(1)
fname = Common.BaseName(fn_cn)
print('process jp cn: {}'.format(fname))
jp = open(fn_jp, 'r', encoding='utf16')
cn = open(fn_cn, 'r', encoding='utf16')
lines = jp.readlines()
jp_lines = [
line.rstrip('\n') for line in lines if line != '' and line != '\n'
]
lines = cn.readlines()
cn_lines = [
line.rstrip('\n') for line in lines if line != '' and line != '\n'
]
if len(jp_lines) != len(cn_lines):
input('Line num not match: {}'.format(Common.BaseName(fn_jp)))
exit(1)
for jp_line, cn_line in zip(jp_lines, cn_lines):
offset, size, jp_text = Common.ParseWQSGLine(jp_line)
offset, size, cn_text = Common.ParseWQSGLine(cn_line)
if (not jp_text) and (not cn_text):
continue
if len(jp_text) < len(cn_text):
report.write('{} > {} -- {}\n'.format(fname, jp_text, cn_text))
# jp_group = Common.SplitString(jp_text)
# cn_group = Common.SplitString(cn_text)
jp.close()
cn.close()
def CheckOnePair(fn_jp, fn_cn, report):
jp = open(fn_jp, 'r', encoding='utf16')
cn = open(fn_cn, 'r', encoding='utf16')
lines = jp.readlines()
jp_lines = [line for line in lines if line != '' and line != '\n']
lines = cn.readlines()
cn_lines = [line for line in lines if line != '' and line != '\n']
if len(cn_lines) != len(jp_lines):
log = 'Line num not match:{}\n'.format(Common.BaseName(fn_jp))
report.write(log)
return
for jp_line, cn_line in zip(jp_lines, cn_lines):
offset, size, jp_text = Common.ParseWQSGLine(jp_line.rstrip('\n'))
offset, size, cn_text = Common.ParseWQSGLine(cn_line.rstrip('\n'))
jp_group_count = len(Common.SplitString(jp_text))
cn_group_count = len(Common.SplitString(cn_text))
if jp_group_count != cn_group_count:
log = 'Group num not match: {}:{}\t{}:{}\n'.format(
fn_jp, jp_text, fn_cn, cn_text)
report.write(log)
jp.close()
cn.close()
def ReadVitaGroups(vita_fn_list):
dst_list = []
for fn in vita_fn_list:
fname = Common.BaseName(fn)
print('process vita txt: {}'.format(fname))
src = open(fn, 'r', encoding='utf16')
_lines = src.readlines()
lines = [
line.rstrip('\n') for line in _lines if line != '' and line != '\n'
]
for line in lines:
offset, size, text = Common.ParseWQSGLine(line)
if not text:
continue
group = Common.SplitString(text)
for string in group:
if IsAlNum(string):
continue
if len(string) >= 2 and \
((IsAlNum(string[0]) and (not IsAlNum(string[1]))) or
((not IsAlNum(string[0])) and IsAlNum(string[1]))) and \
(string[0] != ' ' and string[1] != ' '):
# this was originally prevent junk chars to be added
# since now the vita text is pretty better with almost no junk chars
# I just log it out and comment this line
# continue
print('alpha string:{}'.format(string))
dst_list.append((fname, string))
src.close()
return dst_list
