Document Sanitizer

Clean and optimize text for token-efficient AI prompts

Sanitization Options

Whitespace

Remove extra spaces

Multiple spaces to single

Remove extra newlines

3+ newlines to 2

Collapse all newlines

Multiple newlines to single

Trim lines

Remove leading/trailing spaces

Remove empty lines

Delete blank lines

Normalize whitespace

Tabs to spaces, fix line endings

Content

Remove HTML tags

Strip all HTML elements

Remove URLs

Strip http/https links

Remove emails

Strip email addresses

Remove special characters

Keep only alphanumeric

Remove punctuation

Strip .,!? and similar

Remove numbers

Strip all digits

Lowercase all

Convert to lowercase

Input Text

Sanitized Output

Document Sanitizer cleans and optimizes text for token-efficient AI prompts. It removes unnecessary whitespace, special characters, HTML tags, URLs, and other elements that consume tokens without adding value. Token estimates are approximate (~4 chars/token for English).