From 74aab8a42c479cdeeda9371dbd591a19d070c48e Mon Sep 17 00:00:00 2001
From: Daniele Nicolodi <daniele@grinta.net>
Date: Sat, 11 Jan 2025 17:13:14 +0100
Subject: docs: Add a test to validate URLs in markdown/Users.md

Avoid piling up dead URLs.
---
 docs/meson.build      |  4 +++-
 docs/validatelinks.py | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)
 create mode 100644 docs/validatelinks.py

(limited to 'docs')

diff --git a/docs/meson.build b/docs/meson.build
index 3ad12b7fd..0ce884062 100644
--- a/docs/meson.build
+++ b/docs/meson.build
@@ -1,7 +1,7 @@
 project('Meson documentation', version: '1.0')
 
 yaml_modname = get_option('unsafe_yaml') ? 'yaml' : 'strictyaml'
-py = import('python').find_installation('python3', modules: [yaml_modname], required: false)
+py = import('python').find_installation('python3', modules: [yaml_modname, 'aiohttp'], required: false)
 if not py.found()
     error(f'Cannot build documentation without yaml support')
 endif
@@ -145,3 +145,5 @@ run_target('upload',
     ],
     depends: documentation,
 )
+
+test('validate_links', find_program('./validatelinks.py'), args: meson.current_source_dir() / 'markdown' / 'Users.md')
diff --git a/docs/validatelinks.py b/docs/validatelinks.py
new file mode 100644
index 000000000..69544ab0e
--- /dev/null
+++ b/docs/validatelinks.py
@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+
+# SPDX-License-Identifier: Apache-2.0
+# Copyright 2025 The Meson development team
+
+import sys
+import re
+import aiohttp
+import asyncio
+
+LINK = re.compile(r'\[(?P<name>[A-Za-z0-9 ]+)\]\((?P<url>.*?)\)')
+
+
+async def fetch(session, name, url, timeout):
+    try:
+        async with session.get(url, timeout=timeout) as r:
+            if not r.ok:
+                return (name, url, r.status)
+    except Exception as e:
+        return (name, url, str(e))
+
+
+async def main(filename):
+    with open(filename) as f:
+        text = f.read()
+        timeout = aiohttp.ClientTimeout(total=60)
+        async with aiohttp.ClientSession() as session:
+            tasks = []
+            for link in LINK.finditer(text):
+                name, url = link.groups()
+                task = asyncio.ensure_future(fetch(session, name, url, timeout))
+                tasks.append(task)
+            responses = asyncio.gather(*tasks)
+            errors = [r for r in await responses if r is not None]
+        for name, url, result in errors:
+            print(f'"{name}" {url} {result}')
+        if errors:
+            sys.exit(1)
+
+
+if __name__ == '__main__':
+    asyncio.run(main(sys.argv[1]))
-- 
cgit v1.2.3