Skip to content

修改為目前版本g2butf8 #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lauct wants to merge 1 commit into
base: master
Choose a base branch
from
Open

修改為目前版本g2butf8 #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions nnyConvert.xcodeproj/project.pbxproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,6 @@
GCC_WARN_ABOUT_RETURN_TYPE = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
MACOSX_DEPLOYMENT_TARGET = "";
ONLY_ACTIVE_ARCH = YES;
SDKROOT = macosx;
};
Expand All @@ -264,7 +263,6 @@
GCC_WARN_ABOUT_RETURN_TYPE = YES;
GCC_WARN_UNINITIALIZED_AUTOS = YES;
GCC_WARN_UNUSED_VARIABLE = YES;
MACOSX_DEPLOYMENT_TARGET = "";
ONLY_ACTIVE_ARCH = YES;
SDKROOT = macosx;
};
Expand All @@ -273,6 +271,7 @@
34E6684315EA40A200B42A4A /* Debug */ = {
isa = XCBuildConfiguration;
buildSettings = {
ARCHS = "$(NATIVE_ARCH_ACTUAL)";
COMBINE_HIDPI_IMAGES = YES;
GCC_PRECOMPILE_PREFIX_HEADER = YES;
GCC_PREFIX_HEADER = "nnyConvert/nnyConvert-Prefix.pch";
Expand All @@ -286,6 +285,7 @@
34E6684415EA40A200B42A4A /* Release */ = {
isa = XCBuildConfiguration;
buildSettings = {
ARCHS = "$(NATIVE_ARCH_ACTUAL)";
COMBINE_HIDPI_IMAGES = YES;
GCC_PRECOMPILE_PREFIX_HEADER = YES;
GCC_PREFIX_HEADER = "nnyConvert/nnyConvert-Prefix.pch";
Expand Down
1 change: 1 addition & 0 deletions nnyConvert/dic_tw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1410,4 +1410,5 @@ def dic_tw():
u"索馬裏":u"索馬利亞",
u"肯尼亞":u"肯亞",
u"肯雅":u"肯亞",
u"註意":u"注意"
};
107 changes: 32 additions & 75 deletions nnyConvert/g2butf8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,33 +42,6 @@ def getEncodingByContent(content):
detector.feed(content)
detector.close()
return detector.result["encoding"]

# get user define dictionary
def getUserDic(filename):
user_dic= {}
if os.path.exists(filename):
f_encoding = getEncoding(filename)
if f_encoding == None:
print (u"抱歉, 未能正確判斷自定字典編碼！\n\n");
else:
fpr = open(filename, 'r');
lines = fpr.readlines();
fpr.close();

if lines[0].startswith(codecs.BOM_UTF8 ):
lines[0] = lines[0].lstrip(codecs.BOM_UTF8 );

for line in lines:
line = line.decode(f_encoding);
words = line.split('=')
key = words[0].lstrip().rstrip();
value = words[1].lstrip().rstrip();
user_dic[key] = value;

return user_dic

#user dictionary file
user_dic_file = 'userdic.txt'

# start error message

Expand All @@ -91,55 +64,39 @@ def getUserDic(filename):


def convertFile(target_file):
user_dic= {}
if os.path.exists(target_file):
f_encoding = getEncoding(target_file)
print u"正在轉換", target_file, u" 編碼為: ", f_encoding
if f_encoding == None:
print (u"抱歉, 未能正確判斷編碼！\n\n");
else:
result_content = u''
original_content = u''
fp = open(target_file, 'r')
original_content = fp.read()
fp.close()
f_encoding = getEncoding(target_file)
print u"正在轉換", target_file, u" 編碼為: ", f_encoding
if f_encoding == None:
print (u"抱歉, 未能正確判斷編碼！\n\n");
else:
result_content = u''
original_content = u''
fp = open(target_file, 'r')
original_content = fp.read()
fp.close()

if original_content.startswith( codecs.BOM_UTF8 ):
original_content.lstrip( codecs.BOM_UTF8);

if original_content.startswith( codecs.BOM_UTF8 ):
original_content = original_content.lstrip( codecs.BOM_UTF8);

utf8content=original_content.decode(f_encoding)

newcontent = jtof(utf8content)
lines = newcontent.splitlines();
for line in lines:
line = convertVocabulary(line, dic_tw());

if os.path.getsize(target_file) > 0:
# do backup
backup_file = target_file + '.bak'
shutil.copy2(target_file, backup_file)
fpw = open(target_file, 'w')
if not newcontent.startswith(codecs.BOM_UTF8.decode( "utf8" )):
fpw.write(codecs.BOM_UTF8)

pathdir =os.path.dirname(os.path.abspath(target_file));
user_dic_pathname = pathdir +os.path.sep+user_dic_file;

if os.path.exists(user_dic_pathname):
user_dic = getUserDic(user_dic_pathname);
if len(user_dic) > 0:
for line in lines:
line = convertVocabulary(line, user_dic);

for line in lines:
line = convertVocabulary(line, user_dic);
fpw.write(line.encode('UTF-8'))
fpw.write("\n");
fpw.close();

print (MSG_CONVERT_FINISH)
else:
print MSG_NO_CONVERT
utf8content=original_content.decode(f_encoding, 'ignore')



newcontent = jtof(utf8content)
newcontent = convertVocabulary(newcontent, dic_tw());
if os.path.getsize(target_file) > 0:
# do backup
backup_file = target_file + '.bak'
shutil.copy2(target_file, backup_file)
fpw = open(target_file, 'w')
if not newcontent.startswith(codecs.BOM_UTF8.decode( "utf8" )):
fpw.write(codecs.BOM_UTF8)
fpw.write(newcontent.encode('UTF-8'))
fpw.close();

print (MSG_CONVERT_FINISH)
else:
print MSG_NO_CONVERT


if __name__ == "__main__":
Expand Down
4 changes: 2 additions & 2 deletions nnyConvert/userdic.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
������=������
�Y�o=�Y�v
李潤成=李潤城
頭發=頭髮