Simplify one gnarly regex and remove another altogether; add a comment
describing what is going on.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 scripts/lib/kdoc/kdoc_parser.py | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py
index 36c4035343dc..d7fb79a64487 100644
--- a/scripts/lib/kdoc/kdoc_parser.py
+++ b/scripts/lib/kdoc/kdoc_parser.py
@@ -527,23 +527,19 @@ class KernelDoc:
                 dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg)
                 self.push_parameter(ln, decl_type, param, dtype,
                                     arg, declaration_name)
-
+            #
+            # The array-of-pointers case.  Dig the parameter name out from the middle
+            # of the declaration.
+            #
             elif KernRe(r'\(.+\)\s*\[').search(arg):
-                # Array-of-pointers
-
-                arg = arg.replace('#', ',')
-                r = KernRe(r'[^\(]+\(\s*\*\s*([\w\[\].]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)')
+                r = KernRe(r'[^\(]+\(\s*\*\s*' r'([\w.]*?)' r'\s*(\[\s*\w+\s*\]\s*)*\)')
                 if r.match(arg):
                     param = r.group(1)
                 else:
                     self.emit_msg(ln, f"Invalid param: {arg}")
                     param = arg
-
-                dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg)
-
-                self.push_parameter(ln, decl_type, param, dtype,
-                                    arg, declaration_name)
-
+                dtype = arg.replace(param, '')
+                self.push_parameter(ln, decl_type, param, dtype, arg, declaration_name)
             elif arg:
                 #
                 # Clean up extraneous spaces and split the string at commas; the first
-- 
2.50.1

On Tue, 12 Aug 2025 13:57:46 -0600
Jonathan Corbet <corbet@lwn.net> wrote:

> Simplify one gnarly regex and remove another altogether; add a comment
> describing what is going on.
> 
> Signed-off-by: Jonathan Corbet <corbet@lwn.net>
> ---
>  scripts/lib/kdoc/kdoc_parser.py | 18 +++++++-----------
>  1 file changed, 7 insertions(+), 11 deletions(-)
> 
> diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py
> index 36c4035343dc..d7fb79a64487 100644
> --- a/scripts/lib/kdoc/kdoc_parser.py
> +++ b/scripts/lib/kdoc/kdoc_parser.py
> @@ -527,23 +527,19 @@ class KernelDoc:
>                  dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg)
>                  self.push_parameter(ln, decl_type, param, dtype,
>                                      arg, declaration_name)
> -
> +            #
> +            # The array-of-pointers case.  Dig the parameter name out from the middle
> +            # of the declaration.
> +            #
>              elif KernRe(r'\(.+\)\s*\[').search(arg):
> -                # Array-of-pointers
> -
> -                arg = arg.replace('#', ',')

Hmm... if I'm not mistaken, there is(was?) a previous code that replaced
commas by "#". Such statement is needed to catch some corner case.

This like here is(was?) needed to restore the original arg string.

> -                r = KernRe(r'[^\(]+\(\s*\*\s*([\w\[\].]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)')
> +                r = KernRe(r'[^\(]+\(\s*\*\s*' r'([\w.]*?)' r'\s*(\[\s*\w+\s*\]\s*)*\)')

As mentioned on patch 6/7, IMHO doing concats like that at the same line
IMO makes it harder to understand. This works best:

                r = KernRe(r'[^\(]+\(\s*\*\s*'
			   r'([\w.]*?)'
			   r'\s*(\[\s*\w+\s*\]\s*)*\)')


>                  if r.match(arg):
>                      param = r.group(1)
>                  else:
>                      self.emit_msg(ln, f"Invalid param: {arg}")
>                      param = arg
> -
> -                dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg)
> -
> -                self.push_parameter(ln, decl_type, param, dtype,
> -                                    arg, declaration_name)
> -
> +                dtype = arg.replace(param, '')
> +                self.push_parameter(ln, decl_type, param, dtype, arg, declaration_name)
>              elif arg:
>                  #
>                  # Clean up extraneous spaces and split the string at commas; the first



Thanks,
Mauro

Mauro Carvalho Chehab <mchehab+huawei@kernel.org> writes:

> On Tue, 12 Aug 2025 13:57:46 -0600
> Jonathan Corbet <corbet@lwn.net> wrote:
>>              elif KernRe(r'\(.+\)\s*\[').search(arg):
>> -                # Array-of-pointers
>> -
>> -                arg = arg.replace('#', ',')
>
> Hmm... if I'm not mistaken, there is(was?) a previous code that replaced
> commas by "#". Such statement is needed to catch some corner case.
>
> This like here is(was?) needed to restore the original arg string.

That (hackish :) replacement is still there ... but there will be no
commas in anything matched by the regex here, so the restoration is not
needed.  I can add that to the changelog for curious readers in the
future. 

>> -                r = KernRe(r'[^\(]+\(\s*\*\s*([\w\[\].]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)')
>> +                r = KernRe(r'[^\(]+\(\s*\*\s*' r'([\w.]*?)' r'\s*(\[\s*\w+\s*\]\s*)*\)')
>
> As mentioned on patch 6/7, IMHO doing concats like that at the same line
> IMO makes it harder to understand. This works best:
>
>                 r = KernRe(r'[^\(]+\(\s*\*\s*'
> 			   r'([\w.]*?)'
> 			   r'\s*(\[\s*\w+\s*\]\s*)*\)')

I'll do that.

Thanks,

jon