Skip to content
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

Add config delimiter #70

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
+30 −5
Open

Add config delimiter #70

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
398b223
Add delimiter
Ez-and Dec 30, 2024
209a632
Add CustomDialect
Ez-and Dec 30, 2024
2902bad
Add delimiter CSV GUI
Ez-and Dec 30, 2024
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
14 changes: 14 additions & 0 deletions parser_2gis/gui/settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,20 @@ def gui_settings(config: Configuration) -> None:
default=config.writer.csv.remove_duplicates,
checkbox_color=sg.theme_input_background_color(), enable_events=True),
],
[
sg.Column([
[
sg.Text('Разделитель CSV'),
]
], expand_x=True, pad=0),
sg.Column([
[
sg.Input(size=(3, 1), justification='center', key='-WRITER.CSV.DELIMITER-',
tooltip='Символ-разделитель колонок в CSV.',
default_text = config.writer.csv.delimiter),
],
], element_justification='right', pad=0),
],
[
sg.Column([
[
Expand Down
2 changes: 2 additions & 0 deletions parser_2gis/writer/options.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,13 +16,15 @@ class CSVOptions(BaseModel):
remove_empty_columns: Remove empty columns after parsing process finished.
remove_duplicates: Remove duplicates after parsing process finished.
join_char: Char for joining complex values.
delimiter: CSV char-delimiter
"""
add_rubrics: bool = True
add_comments: bool = True
columns_per_entity: int = Field(3, gt=0, le=5)
remove_empty_columns: bool = True
remove_duplicates: bool = True
join_char: str = '; '
delimiter: str = ','


class WriterOptions(BaseModel):
Expand Down
19 changes: 14 additions & 5 deletions parser_2gis/writer/writers/csv_writer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,15 @@

class CSVWriter(FileWriter):
"""Writer to CSV table."""
@property
def _dialect(self) -> csv.Dialect:
class CustomDialect(csv.Dialect):
delimiter = self._options.csv.delimiter
quoting = csv.QUOTE_MINIMAL
lineterminator = "\n"
quotechar= '"'
return CustomDialect

@property
def _type_names(self) -> dict[str, str]:
return {
Expand Down Expand Up @@ -76,7 +85,7 @@ def _writerow(self, row: dict[str, Any]) -> None:

def __enter__(self) -> CSVWriter:
super().__enter__()
self._writer = csv.DictWriter(self._file, self._data_mapping.keys())
self._writer = csv.DictWriter(self._file, self._data_mapping.keys(), dialect=self._dialect)
self._writer.writerow(self._data_mapping) # Write header
self._wrote_count = 0
return self
Expand All @@ -98,9 +107,9 @@ def _remove_empty_columns(self) -> None:

# Looking for empty columns
with self._open_file(self._file_path, 'r') as f_csv:
csv_reader = csv.DictReader(f_csv, self._data_mapping.keys()) # type: ignore
csv_reader = csv.DictReader(f_csv, self._data_mapping.keys(), dialect=self._dialect) # type: ignore
next(csv_reader, None) # Skip header
for row in csv.DictReader(f_csv, self._data_mapping.keys()): # type: ignore
for row in csv.DictReader(f_csv, self._data_mapping.keys(), dialect=self._dialect): # type: ignore
for column_name in complex_columns_count.keys():
if row[column_name] != '':
complex_columns_count[column_name] += 1
Expand All @@ -124,8 +133,8 @@ def _remove_empty_columns(self) -> None:

with self._open_file(tmp_csv_name, 'w') as f_tmp_csv, \
self._open_file(self._file_path, 'r') as f_csv:
csv_writer = csv.DictWriter(f_tmp_csv, new_data_mapping.keys()) # type: ignore
csv_reader = csv.DictReader(f_csv, self._data_mapping.keys()) # type: ignore
csv_writer = csv.DictWriter(f_tmp_csv, new_data_mapping.keys(), dialect=self._dialect) # type: ignore
csv_reader = csv.DictReader(f_csv, self._data_mapping.keys(), dialect=self._dialect) # type: ignore
csv_writer.writerow(new_data_mapping) # Write new header
next(csv_reader, None) # Skip header

Expand Down