[all] update refresh-copyright to handle UTF BOM markers

refresh-copyright

@@ -12,6 +12,8 @@ EXTENSIONS = ('.c', '.cpp', '.h', '.nsi', '.rc')
 START_YEAR = 2017
 CURRENT_YEAR = datetime.date.today().year
 
+UTF8_BOM = '\ufeff'
+
 reignore = re.compile('^vendor/|.*/shader/|.*/d3d12.h$')
 recopyright = re.compile(r'\A/\*.*?\*/\s+', re.DOTALL)
 
@@ -36,6 +38,24 @@ with this program; if not, write to the Free Software Foundation, Inc., 59
 Temple Place, Suite 330, Boston, MA 02111-1307 USA''']
 
 
+def read_utf8_preserve_bom(file):
+    with open(file, encoding='utf-8') as f:
+        data = f.read()
+
+    has_bom = data.startswith(UTF8_BOM)
+    if has_bom:
+        data = data[len(UTF8_BOM):]
+
+    return data, has_bom
+
+
+def write_utf8_preserve_bom(file, data, has_bom):
+    with open(file, 'w', encoding='utf-8') as f:
+        if has_bom:
+            f.write(UTF8_BOM)
+        f.write(data)
+
+
 def make_comment_block():
     lines = ['/**']
     lines += [' * ' + line for line in header]
@@ -59,11 +79,11 @@ def gen_c_literal():
 
 def update_c_style(file, copyright):
     print(f'Updating copyright for {file}...')
-    with open(file, encoding='utf-8') as f:
+
-        data = recopyright.sub('', f.read())
+    data, has_bom = read_utf8_preserve_bom(file)
-    with open(file, 'w', encoding='utf-8') as f:
+    data = recopyright.sub('', data)
-        f.write(copyright)
+
-        f.write(data)
+    write_utf8_preserve_bom(file, copyright + data, has_bom)
 
 
 def update_config_c(file):
@@ -73,8 +93,9 @@ def update_config_c(file):
 
     print(f'Refresh embedded copyright string in {file}...')
 
-    with open(file, encoding='utf-8') as f:
+    data, has_bom = read_utf8_preserve_bom(file)
-        for line in f:
+
+    for line in data.splitlines(keepends=True):
         if '// BEGIN LICENSE BLOCK' in line:
             prefix.append(line)
             current = []
@@ -84,10 +105,8 @@ def update_config_c(file):
         else:
             current.append(line)
 
-    with open(file, 'w', encoding='utf-8') as f:
+    data = ''.join(prefix) + gen_c_literal() + ''.join(suffix)
-        f.writelines(prefix)
+    write_utf8_preserve_bom(file, data, has_bom)
-        f.write(gen_c_literal())
-        f.writelines(suffix)
 
 
 def appstring_license():
@@ -105,31 +124,36 @@ def appstring_license():
 
 def update_appstrings(file):
     print(f'Refresh app string in {file}...')
-    lines = []
 
-    with open(file, encoding='utf-8') as f:
+    data, has_bom = read_utf8_preserve_bom(file)
-        f = iter(f)
+
+    lines = []
+    f = iter(data.splitlines(keepends=True))
+
     for line in f:
         lines.append(line)
+
         if 'LG_COPYRIGHT_STR' in line:
             next(f)
             lines.append(f'  "{copyright}";\n')
+
         elif 'LG_WEBSITE_STR' in line:
             next(f)
             lines.append(f'  "{project_url}";\n')
+
         elif 'LG_LICENSE_STR' in line:
             lines += [f'{line}\n' for line in appstring_license()]
             for line in f:
                 if '";' in line:
                     break
 
-    with open(file, 'w', encoding='utf-8') as f:
+    write_utf8_preserve_bom(file, ''.join(lines), has_bom)
-        f.writelines(lines)
 
 
 def main():
     comment_block = make_comment_block()
     files = subprocess.check_output(['git', '-C', PROJECT, 'ls-files', '-z']).decode('utf-8').split('\0')
+
     for file in files:
         if reignore.match(file):
             continue
@@ -139,5 +163,6 @@ def main():
     update_config_c(os.path.join(PROJECT, 'client', 'src', 'config.c'))
     update_appstrings(os.path.join(PROJECT, 'common', 'src', 'appstrings.c'))
 
+
 if __name__ == '__main__':
     main()