Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
docs: kdoc: rework type prototype parsing
process_proto_type() is using a complex regex and a "while True" loop to
split a declaration into chunks and, in the end, count brackets. Switch to
using a simpler regex to just do the split directly, and handle each chunk
as it comes. The result is, IMO, easier to understand and reason about.
The old algorithm would occasionally elide the space between function
parameters; see struct rng_alg->generate(), foe example. The only output
difference is to not elide that space, which is more correct.
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
+25
-18
+25
-18
scripts/lib/kdoc/kdoc_parser.py
+25
-18
scripts/lib/kdoc/kdoc_parser.py
···
1594
1594
1595
1595
# Strip C99-style comments and surrounding whitespace
1596
1596
line = KernRe(r"//.*$", re.S).sub('', line).strip()
1597
+
if not line:
1598
+
return # nothing to see here
1597
1599
1598
1600
# To distinguish preprocessor directive from regular declaration later.
1599
1601
if line.startswith('#'):
1600
1602
line += ";"
1601
-
1602
-
r = KernRe(r'([^\{\};]*)([\{\};])(.*)')
1603
-
while True:
1604
-
if r.search(line):
1605
-
if self.entry.prototype:
1606
-
self.entry.prototype += " "
1607
-
self.entry.prototype += r.group(1) + r.group(2)
1608
-
1609
-
self.entry.brcount += r.group(2).count('{')
1610
-
self.entry.brcount -= r.group(2).count('}')
1611
-
1612
-
if r.group(2) == ';' and self.entry.brcount <= 0:
1603
+
#
1604
+
# Split the declaration on any of { } or ;, and accumulate pieces
1605
+
# until we hit a semicolon while not inside {brackets}
1606
+
#
1607
+
r = KernRe(r'(.*?)([{};])')
1608
+
for chunk in r.split(line):
1609
+
if chunk: # Ignore empty matches
1610
+
self.entry.prototype += chunk
1611
+
#
1612
+
# This cries out for a match statement ... someday after we can
1613
+
# drop Python 3.9 ...
1614
+
#
1615
+
if chunk == '{':
1616
+
self.entry.brcount += 1
1617
+
elif chunk == '}':
1618
+
self.entry.brcount -= 1
1619
+
elif chunk == ';' and self.entry.brcount <= 0:
1613
1620
self.dump_declaration(ln, self.entry.prototype)
1614
1621
self.reset_state(ln)
1615
-
break
1616
-
1617
-
line = r.group(3)
1618
-
else:
1619
-
self.entry.prototype += line
1620
-
break
1622
+
return
1623
+
#
1624
+
# We hit the end of the line while still in the declaration; put
1625
+
# in a space to represent the newline.
1626
+
#
1627
+
self.entry.prototype += ' '
1621
1628
1622
1629
def process_proto(self, ln, line):
1623
1630
"""STATE_PROTO: reading a function/whatever prototype."""