cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-19 00:26:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Update tests and convert to stock unittest

Browse source 
For these simple tests Python's built-in unittest framework is more than enough.
No additional dependencies are required.

Added some more test cases with "special" characters to test the escaping code
better.
This commit is contained in:
Dennis Camera 2025-02-18 10:13:27 +01:00
parent 0bd3fa63b8
commit 17b826a6d3
5 changed files with 120 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

44
code/test_files/robots.json
View file

@ -278,5 +278,47 @@
"function": "Scrapes data for search engine and LLMs.",
"frequency": "No information.",
"description": "Retrieves data used for You.com web search engine and LLMs."
},
"crawler.with.dots": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression dots need to be escaped."
},
"star***crawler": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression stars need to be escaped."
},
"Is this a crawler?": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression spaces and question marks need to be escaped."
},
"a[mazing]{42}(robot)": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression parantheses, braces, etc. need to be escaped."
},
"2^32$": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression RE anchor characters need to be escaped."
},
"curl|sudo bash": {
"operator": "Test suite",
"respect": "No",
"function": "To ensure the code works correctly.",
"frequency": "No information.",
"description": "When used in the .htaccess regular expression pipes need to be escaped."
}
}
}