Bad export filenames

[FraterCRC]

Bug description

If you have a model with name in any other than english language you get filename '_{id}' which will not be exported

it is obvious from this code
def get_filename(model_name: str, model_id: int, skip_id: bool = False) -> str:
slug = secure_filename(model_name)
filename = slug if skip_id else f"{slug}_{model_id}"
return filename if slug else str(model_id)

How to reproduce the bug

1. Go to charts
2. Сreate chart "Пивко"
3. Try to import the chart
4. You get file with name _{id} in charts folder of zip archive
5. Files with names starting with _ and - are not imported

Screenshots/recordings

No response

Superset version

master / latest-dev

Python version

3.9

Node version

16

Browser

Safari

Additional context

Suggest to do smthing like:

def get_filename(model_name: str, model_id: int, skip_id: bool = False) -> str:
slug = secure_filename(model_name)
slug = slug.replace('-', '').lstrip()
filename = f"{slug}_{model_id}" if slug else "{model_id}"
return filename

Checklist

• I have searched Superset docs and Slack and didn't find a solution to my problem.
• I have searched the GitHub issue tracker and didn't find a similar bug report.
• I have checked Superset's logs for errors and if I found a relevant Python stacktrace, I included it here as text in the "additional context" section.

[dosubot]

Hey @FraterCRC! I'm here to help you with any bugs, questions, or contributions you have for Superset. Let's tackle this together!

To address the issue where non-English model names result in filenames like '_{id}' that are not exported, you can modify the get_filename function to handle non-English characters more gracefully. Here's an improved version of the function:

import unicodedata
import re
from werkzeug.utils import secure_filename

def slugify(value: str) -> str:
    value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii')
    value = re.sub(r'[^\w\s-]', '', value).strip().lower()
    return re.sub(r'[-\s]+', '-', value)

def get_filename(model_name: str, model_id: int, skip_id: bool = False) -> str:
    slug = slugify(model_name)
    filename = slug if skip_id else f"{slug}_{model_id}"
    return filename if slug else str(model_id)

This slugify function normalizes the string to ASCII, removes non-word characters, and replaces spaces and hyphens with a single hyphen. This should handle non-English characters more gracefully and avoid the issue of filenames like '_{id}'.

In the context of Superset, you can see that the get_filename function is used in the ExportDashboardsCommand class to generate filenames for exported dashboards. By modifying the get_filename function as shown above, you can ensure that non-English model names are handled correctly when exporting dashboards ^[1][2].

To continue talking to Dosu, mention @dosu.

[rusackas]

Assigning to @yousoph since she's been taking stock of what is/isn't being exported properly.

[sfirke]

Looks closely related to #22118, see the discussion in comments there - is @EugeneTorap still actively contributing to Superset?