def wordless_msg_box_path_not_exist_confirm(main, path):
reply = QMessageBox.question(
main, main.tr('Path Not Exist'),
main.tr(f'''
{main.settings_global['styles']['style_dialog']}
<body>
<div>The specified path "{path}" does not exist.</div>
<div>Do you want to create the directory?</div>
</body>
'''), QMessageBox.Yes | QMessageBox.No,
QMessageBox.No)
if reply == QMessageBox.Yes:
wordless_checking_misc.check_dir(path)
return reply
def open_files(self):
if os.path.exists(
self.main.settings_custom['import']['files']['default_path']):
default_dir = self.main.settings_custom['import']['files'][
'default_path']
else:
default_dir = self.main.settings_default['import']['files'][
'default_path']
file_paths = QFileDialog.getOpenFileNames(
self.main, self.tr('Open File(s)'),
wordless_checking_misc.check_dir(default_dir),
';;'.join(self.main.settings_global['file_types']['files']),
self.main.settings_global['file_types']['files'][-1])[0]
if file_paths:
self.main.wordless_files.add_files(file_paths)
def export_list(self, settings):
default_dir = self.main.settings_custom['export'][settings]['default_path']
file_path = QFileDialog.getSaveFileName(self.main,
self.tr('Export to File'),
wordless_checking_misc.check_dir(default_dir),
self.tr('Text File (*.txt)'))[0]
if file_path:
encoding = self.main.settings_custom['export'][settings]['default_encoding']
with open(file_path, 'w', encoding = encoding) as f:
for item in self.get_items():
f.write(item + '\n')
wordless_msg_box.wordless_msg_box_export_list(self.main, file_path)
self.main.settings_custom['export'][settings]['default_path'] = os.path.normpath(os.path.dirname(file_path))
def export_all(self, rows_export=[]):
def set_cell_styles(cell, item, item_type='item'):
if item_type == 'header_horizontal':
cell.font = openpyxl.styles.Font(name=item.font().family(),
size=8,
bold=True,
color='FFFFFF')
if self.header_orientation == 'horizontal':
cell.fill = openpyxl.styles.PatternFill(fill_type='solid',
fgColor='5C88C5')
else:
cell.fill = openpyxl.styles.PatternFill(fill_type='solid',
fgColor='888888')
elif item_type == 'header_vertical':
cell.font = openpyxl.styles.Font(name=item.font().family(),
size=8,
bold=True,
color='FFFFFF')
cell.fill = openpyxl.styles.PatternFill(fill_type='solid',
fgColor='5C88C5')
else:
cell.font = openpyxl.styles.Font(name=item.font().family(),
size=8,
color='292929')
cell.alignment = openpyxl.styles.Alignment(horizontal='center',
vertical='center',
wrap_text=True)
default_dir = self.main.settings_custom['export']['tables'][
'default_path']
(file_path, file_type) = QFileDialog.getSaveFileName(
self, self.tr('Export Table'),
wordless_checking_misc.check_dir(default_dir), ';;'.join(
self.main.settings_global['file_types']['export_tables']),
self.main.settings_custom['export']['tables']['default_type'])
if file_path:
if file_type == self.tr('Excel Workbook (*.xlsx)'):
workbook = openpyxl.Workbook()
worksheet = workbook.active
worksheet.freeze_panes = 'B2'
dpi_horizontal = QApplication.primaryScreen(
).logicalDotsPerInchX()
dpi_vertical = QApplication.primaryScreen(
).logicalDotsPerInchY()
if not rows_export:
rows_export = list(range(self.rowCount()))
if self.header_orientation == 'horizontal':
# Horizontal Headers
for col in range(self.columnCount()):
worksheet.cell(
1, 1 +
col).value = self.horizontalHeaderItem(col).text()
set_cell_styles(worksheet.cell(1, 1 + col),
self.horizontalHeaderItem(col),
item_type='header_horizontal')
worksheet.column_dimensions[
openpyxl.utils.get_column_letter(
1 + col)].width = self.horizontalHeader(
).sectionSize(col) / dpi_horizontal * 13 + 3
# Cells
for row_cell, row_item in enumerate(rows_export):
for col in range(self.columnCount()):
worksheet.cell(2 + row_cell,
1 + col).value = self.item(
row_item, col).text()
set_cell_styles(
worksheet.cell(2 + row_cell, 1 + col),
self.item(row_item, col))
else:
# Horizontal Headers
for col in range(self.columnCount()):
worksheet.cell(
1, 2 +
col).value = self.horizontalHeaderItem(col).text()
set_cell_styles(worksheet.cell(1, 2 + col),
self.horizontalHeaderItem(col),
item_type='header_horizontal')
worksheet.column_dimensions[
openpyxl.utils.get_column_letter(
2 + col)].width = self.horizontalHeader(
).sectionSize(col) / dpi_horizontal * 13 + 3
worksheet.column_dimensions[
openpyxl.utils.get_column_letter(
1)].width = self.verticalHeader().width(
) / dpi_horizontal * 13 + 3
# Vertical Headers
for row_cell, row_item in enumerate(rows_export):
worksheet.cell(2 + row_cell,
1).value = self.verticalHeaderItem(
row_item).text()
set_cell_styles(worksheet.cell(2 + row_cell, 1),
self.verticalHeaderItem(row_item),
item_type='header_vertical')
# Cells
for row_cell, row_item in enumerate(rows_export):
for col in range(self.columnCount()):
worksheet.cell(2 + row_cell,
2 + col).value = self.item(
row_item, col).text()
set_cell_styles(
worksheet.cell(2 + row_cell, 2 + col),
self.item(row_item, col))
# Row Height
worksheet.row_dimensions[1].height = self.horizontalHeader(
).height() / dpi_vertical * 72
for i, _ in enumerate(worksheet.rows):
worksheet.row_dimensions[
2 + i].height = self.verticalHeader().sectionSize(
0) / dpi_vertical * 72
# Borders
border = openpyxl.styles.Side(border_style='thin',
color='292929')
for row, _ in enumerate(worksheet.rows):
for col, _ in enumerate(worksheet.columns):
worksheet.cell(row + 1, col +
1).border = openpyxl.styles.Border(
left=border,
right=border,
top=border,
bottom=border)
workbook.save(file_path)
elif file_type == self.tr('CSV File (*.csv)'):
encoding = self.main.settings_custom['export']['tables'][
'default_encoding']
with open(file_path, 'w', encoding=encoding, newline='') as f:
csv_writer = csv.writer(f)
if not rows_export:
rows_export = list(range(self.rowCount()))
if self.header_orientation == 'horizontal':
# Horizontal Headers
csv_writer.writerow([
self.horizontalHeaderItem(col).text().strip()
for col in range(self.columnCount())
])
# Cells
for row in rows_export:
csv_writer.writerow([
self.item(row, col).text().strip()
for col in range(self.columnCount())
])
else:
# Horizontal Headers
csv_writer.writerow([''] + [
self.horizontalHeaderItem(col).text().strip()
for col in range(self.columnCount())
])
# Vertical Headers & Cells
for row in rows_export:
csv_writer.writerow(
[self.verticalHeaderItem(row).text().strip()] +
[
self.item(row, col).text().strip()
for col in range(self.columnCount())
])
self.main.settings_custom['export']['tables'][
'default_path'] = os.path.normpath(os.path.dirname(file_path))
self.main.settings_custom['export']['tables'][
'default_type'] = file_type
wordless_msg_box.wordless_msg_box_export_table(
self.main, file_path)
def add_files(self):
new_files = []
files_detection_failed_encoding = []
files_detection_failed_text_type = []
files_detection_failed_lang = []
if self.file_paths:
len_file_paths = len(self.file_paths)
for i, file_path in enumerate(self.file_paths):
self.progress_updated.emit(
self.tr(f'Loading files ... ({i + 1}/{len_file_paths})'))
default_dir = wordless_checking_misc.check_dir(
self.main.settings_custom['import']['temp_files']
['default_path'])
default_encoding = self.main.settings_custom['import'][
'temp_files']['default_encoding']
file_path = wordless_misc.get_abs_path(file_path)
file_name, file_ext = os.path.splitext(
os.path.basename(file_path))
file_ext = file_ext.lower()
# Text Files
if file_ext == '.txt':
(new_file, detection_success_encoding,
detection_success_text_type, detection_success_lang
) = self.main.wordless_files._new_file(file_path)
new_files.append(new_file)
if not detection_success_encoding:
files_detection_failed_encoding.append(
new_file['path'])
if not detection_success_text_type:
files_detection_failed_text_type.append(
new_file['path'])
if not detection_success_lang:
files_detection_failed_lang.append(new_file['path'])
else:
if file_ext in ['.docx', '.xlsx', '.xls']:
new_path = wordless_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
# Word Documents
if file_ext == '.docx':
lines = []
with open(new_path, 'w',
encoding=default_encoding) as f:
doc = docx.Document(file_path)
for block in self.iter_block_items(doc):
if type(block
) == docx.text.paragraph.Paragraph:
f.write(f'{block.text}\n')
elif type(block) == docx.table.Table:
for row in self.iter_visual_cells(
block):
cells = []
for cell in row:
cells.append(' '.join([
item.text for item in
self.iter_cell_items(cell)
]))
f.write('\t'.join(cells) + '\n')
# Excel Workbooks
elif file_ext == '.xlsx':
with open(new_path, 'w',
encoding=default_encoding) as f:
workbook = openpyxl.load_workbook(
file_path, data_only=True)
for worksheet_name in workbook.sheetnames:
worksheet = workbook[worksheet_name]
for row in worksheet.rows:
f.write('\t'.join([(
cell.value if cell.value != None
else '') for cell in row]) + '\n')
elif file_ext == '.xls':
with open(new_path, 'w',
encoding=default_encoding) as f:
workbook = xlrd.open_workbook(file_path)
for i_sheet in range(workbook.nsheets):
worksheet = workbook.sheet_by_index(
i_sheet)
for row in range(worksheet.nrows):
f.write('\t'.join([
worksheet.cell_value(row, col)
for col in range(worksheet.ncols)
]) + '\n')
new_paths = [new_path]
else:
# Detect encoding
if self.main.settings_custom['files'][
'auto_detection_settings']['detect_encodings']:
encoding_code, _ = wordless_detection.detect_encoding(
self.main, file_path)
else:
encoding_code = self.main.settings_custom[
'encoding_detection']['default_settings'][
'default_encoding']
# CSV Files
if file_ext == '.csv':
new_path = wordless_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
with open(file_path,
'r',
newline='',
encoding=encoding_code) as f_csv:
csv_reader = csv.reader(f_csv)
for row in csv_reader:
f.write('\t'.join(row) + '\n')
new_paths = [new_path]
# HTML Files
elif file_ext in ['.htm', '.html']:
with open(file_path, 'r',
encoding=encoding_code) as f:
soup = bs4.BeautifulSoup(f.read(), 'lxml')
new_path = wordless_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
f.write(soup.get_text())
new_paths = [new_path]
# Translation Memory Files
elif file_ext == '.tmx':
lines_src = []
lines_target = []
with open(file_path, 'r',
encoding=encoding_code) as f:
soup = bs4.BeautifulSoup(f.read(), 'lxml-xml')
for tu in soup.find_all('tu'):
seg_src, seg_target = tu.find_all('seg')
lines_src.append(seg_src.get_text())
lines_target.append(seg_target.get_text())
path_src = wordless_checking_misc.check_new_path(
os.path.join(default_dir,
f'{file_name}_source.txt'))
path_target = wordless_checking_misc.check_new_path(
os.path.join(default_dir,
f'{file_name}_target.txt'))
with open(path_src, 'w',
encoding=default_encoding) as f:
f.write('\n'.join(lines_src))
f.write('\n')
with open(path_target,
'w',
encoding=default_encoding) as f:
f.write('\n'.join(lines_target))
f.write('\n')
new_paths = [path_src, path_target]
# Lyrics Files
elif file_ext == '.lrc':
lyrics = {}
with open(file_path, 'r',
encoding=encoding_code) as f:
for line in f:
time_tags = []
line = line.strip()
# Strip time tags
while re.search(r'^\[[^\]]+?\]', line):
time_tags.append(
re.search(r'^\[[^\]]+?\]',
line).group())
line = line[len(time_tags[-1]):].strip(
)
# Strip word time tags
line = re.sub(r'<[^>]+?>', r'', line)
line = re.sub(r'\s{2,}', r' ',
line).strip()
for time_tag in time_tags:
if re.search(
r'^\[[0-9]{2}:[0-5][0-9]\.[0-9]{2}\]$',
time_tag):
lyrics[time_tag] = line
new_path = wordless_checking_misc.check_new_path(
os.path.join(default_dir, f'{file_name}.txt'))
with open(new_path, 'w',
encoding=default_encoding) as f:
for _, lyrics in sorted(lyrics.items()):
f.write(f'{lyrics}\n')
new_paths = [new_path]
for new_path in new_paths:
(new_file, detection_success_encoding,
detection_success_text_type, detection_success_lang
) = self.main.wordless_files._new_file(new_path)
new_files.append(new_file)
if not detection_success_encoding:
files_detection_failed_encoding.append(
new_file['path'])
if not detection_success_text_type:
files_detection_failed_text_type.append(
new_file['path'])
if not detection_success_lang:
files_detection_failed_lang.append(
new_file['path'])
self.main.settings_custom['import']['files'][
'default_path'] = wordless_misc.get_abs_path(
os.path.dirname(self.file_paths[0]))
self.files_added.emit(new_files, files_detection_failed_encoding,
files_detection_failed_text_type,
files_detection_failed_lang)