From 85719df1dbb8c956e071096e1300b1548c7bf2df Mon Sep 17 00:00:00 2001
From: niclaz <83479948+niclaz@users.noreply.github.com>
Date: Wed, 28 Aug 2024 21:39:03 +0200
Subject: [PATCH] Extending the caption section of schema - regex to include
 URLs in index.yaml

Following up on this error:
https://github.com/web3privacy/data/actions/runs/10602350927/job/29384187270

Investigated to find that the error was because the caption entry of a speaker had many URL links within then, so breaking the configuration - added the following regex to the pattern for caption:


```
'^((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)'
```

Tested the regex expression in https://regex101.com/ first to ensure it worked with url format
---
 schema/index.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/schema/index.yaml b/schema/index.yaml
index ed1b0de..15c7ecd 100644
--- a/schema/index.yaml
+++ b/schema/index.yaml
@@ -116,6 +116,7 @@ $defs:
         type: string
       caption:
         type: string
+        pattern: '^((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)'
       country:
         type: string
         pattern: '^[a-z]{2}$'
@@ -214,4 +215,4 @@ properties:
   research:
     type: array
     items:
-      $ref: "#/$defs/research"
\ No newline at end of file
+      $ref: "#/$defs/research"