# Delimiter candidates tab

![Discover metadata from a text file Input tab](/files/ydHOT1mh0HWsBv7ohScF)

Enter the delimiter candidates you want to use in the file scan in the **Delimiter candidates** field of the **Delimiter candidates** tab. The delimiter candidates can be one or more characters. The step tests each candidate and all combinations of the candidates to find the most accurate match. For example, you may receive a file from two sources where the first source uses a comma delimiter and the second source uses a semi-colon delimiter. The step can determine the data structure of both files.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.pentaho.com/pdia-data-integration/10.2-data-integration/pdi-transformation-steps-reference-overview/discover-metadata-from-a-text-file/options-discover-metadata-from-a-text-file-step/delimiter-candidates-tab.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.