check-parens: use SBCL reader for 100% accurate paren validation
Replace Python regex-based string/comment stripper with SBCL's actual reader. For each lisp block, feeds the code to read-from-string in a loop (reading all forms). Correctly classifies: package errors (not a paren problem), reader errors (extra/missing closes), EOF (missing closes Handles all Common Lisp reader edge cases: character literals (#\( #\) #\;), block comments, string escaping
This commit is contained in:
@@ -39,4 +39,5 @@ Pre-commit hook:
|
||||
|
||||
== Dependencies
|
||||
|
||||
None (stdlib Python 3).
|
||||
Python 3 + SBCL (for the reader-based validation).
|
||||
SBCL must be at `/usr/bin/sbcl` (the default path).
|
||||
|
||||
@@ -1,14 +1,19 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Check paren balance in #+begin_src lisp blocks of .org files.
|
||||
|
||||
Uses SBCL's actual reader for 100% accuracy.
|
||||
|
||||
Usage: check-parens <file.org> [<file.org> ...]
|
||||
check-parens projects/**/*.org
|
||||
check-parens -v <file.org>
|
||||
|
||||
Exit 0 if all blocks balanced and terminated, 1 otherwise.
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import re
|
||||
import subprocess
|
||||
import tempfile
|
||||
|
||||
|
||||
def check_file(path, verbose):
|
||||
@@ -19,32 +24,15 @@ def check_file(path, verbose):
|
||||
blocks = extract_blocks(lines)
|
||||
ok = True
|
||||
|
||||
for block_start, block_lines in blocks:
|
||||
# Check termination
|
||||
if not is_terminated(block_lines):
|
||||
print(f"{path}: Block starting at line {block_start} — no matching #+end_src")
|
||||
ok = False
|
||||
continue
|
||||
|
||||
# Extract block body (between begin and end markers)
|
||||
body = block_lines[1:-1]
|
||||
for start, body in blocks:
|
||||
if not body:
|
||||
continue
|
||||
|
||||
stripped = strip_strings_and_comments(body)
|
||||
open_parens = stripped.count("(")
|
||||
close_parens = stripped.count(")")
|
||||
diff = open_parens - close_parens
|
||||
|
||||
if diff != 0:
|
||||
show = body[0][:60]
|
||||
if diff > 0:
|
||||
print(f"{path}: Block at line {block_start}: +{diff} (missing {diff} close{'s' if diff > 1 else ''}) — near {show!r}")
|
||||
else:
|
||||
print(f"{path}: Block at line {block_start}: {diff} (extra {-diff} close{'s' if -diff > 1 else ''}) — near {show!r}")
|
||||
if is_reader_error(body):
|
||||
print(f"{path}: Block at line {start}: {is_reader_error(body)}")
|
||||
if verbose:
|
||||
for l in body:
|
||||
print(f" | {l}")
|
||||
for line in body:
|
||||
print(f" | {line}")
|
||||
ok = False
|
||||
|
||||
return ok
|
||||
@@ -69,57 +57,125 @@ END_SRC = re.compile(r"#\+end_src\b", re.IGNORECASE)
|
||||
def extract_blocks(lines):
|
||||
blocks = []
|
||||
start = None
|
||||
block_lines = []
|
||||
buf = None
|
||||
|
||||
for i, line in enumerate(lines, start=1):
|
||||
if start is None:
|
||||
if LISP_BEGIN.match(line.lstrip()):
|
||||
start = i
|
||||
block_lines = [line.rstrip("\n")]
|
||||
buf = []
|
||||
else:
|
||||
block_lines.append(line.rstrip("\n"))
|
||||
if END_SRC.match(line.lstrip()):
|
||||
blocks.append((start, block_lines))
|
||||
blocks.append((start, buf))
|
||||
start = None
|
||||
block_lines = []
|
||||
buf = None
|
||||
else:
|
||||
buf.append(line.rstrip("\n"))
|
||||
|
||||
if start is not None:
|
||||
blocks.append((start, block_lines))
|
||||
blocks.append((start, buf))
|
||||
|
||||
return blocks
|
||||
|
||||
|
||||
def is_terminated(block_lines):
|
||||
return END_SRC.match(block_lines[-1].lstrip()) if block_lines else False
|
||||
SBCL = "/usr/bin/sbcl"
|
||||
CHECKER_LISP = "/tmp/check-parens-reader.lisp"
|
||||
|
||||
# One-time setup: write the checker lisp module
|
||||
CHECKER_SRC = r"""(in-package :cl-user)
|
||||
(defpackage :cp-check (:use :cl))
|
||||
(in-package :cp-check)
|
||||
(defun read-file (path)
|
||||
(with-open-file (s path :external-format :utf-8)
|
||||
(let ((buf (make-string (file-length s))))
|
||||
(read-sequence buf s)
|
||||
buf)))
|
||||
(defun check (path)
|
||||
(handler-case
|
||||
(let* ((str (read-file path))
|
||||
(end (length str))
|
||||
(pos 0))
|
||||
(loop
|
||||
(multiple-value-bind (form new-pos)
|
||||
(read-from-string str nil nil :start pos)
|
||||
(when (null form)
|
||||
(return :OK))
|
||||
(setf pos new-pos))))
|
||||
(sb-int:simple-reader-package-error (c)
|
||||
(declare (ignore c))
|
||||
:PACKAGE-ERROR)
|
||||
(sb-int:simple-reader-error (c)
|
||||
(format nil "READER-ERROR: ~a" c))
|
||||
(end-of-file (c)
|
||||
(format nil "EOF: ~a" c))
|
||||
(error (c)
|
||||
(declare (ignore c))
|
||||
:OTHER-ERROR)))
|
||||
"""
|
||||
|
||||
if not os.path.exists(CHECKER_LISP):
|
||||
with open(CHECKER_LISP, "w") as f:
|
||||
f.write(CHECKER_SRC)
|
||||
|
||||
|
||||
def strip_strings_and_comments(lines):
|
||||
parens = []
|
||||
for line in lines:
|
||||
i = 0
|
||||
while i < len(line):
|
||||
c = line[i]
|
||||
if c == '"':
|
||||
i += 1
|
||||
while i < len(line):
|
||||
ec = line[i]
|
||||
if ec == '\\' and i + 1 < len(line):
|
||||
i += 2
|
||||
elif ec == '"':
|
||||
i += 1
|
||||
break
|
||||
else:
|
||||
i += 1
|
||||
elif c == ';':
|
||||
break
|
||||
elif c == '(':
|
||||
parens.append(c)
|
||||
i += 1
|
||||
elif c == ')':
|
||||
parens.append(c)
|
||||
i += 1
|
||||
else:
|
||||
i += 1
|
||||
return "".join(parens)
|
||||
def parse_result(output):
|
||||
"""Parse SBCL output to determine if there's a paren error."""
|
||||
output = output.strip()
|
||||
if not output:
|
||||
return None
|
||||
|
||||
# SBCL may print warnings before the result on separate lines.
|
||||
# Find the last non-style-warning line that contains our result token.
|
||||
for line in reversed(output.split("\n")):
|
||||
line = line.strip()
|
||||
if line.startswith(";") or line.startswith("#<"):
|
||||
continue
|
||||
if line == ":OK" or line.endswith(":OK"):
|
||||
return None
|
||||
if line.startswith(":PACKAGE-ERROR") or line.endswith(":PACKAGE-ERROR"):
|
||||
return None
|
||||
if line.startswith(":OTHER-ERROR") or line.endswith(":OTHER-ERROR"):
|
||||
return "unbalanced parentheses (unknown error)"
|
||||
if "READER-ERROR:" in line:
|
||||
msg = line.split("READER-ERROR:", 1)[1].strip()
|
||||
if "unmatched close parenthesis" in msg:
|
||||
return "unbalanced (extra close parenthesis)"
|
||||
return f"unbalanced ({msg[:60]})"
|
||||
if "EOF:" in line:
|
||||
return "unbalanced (missing close parenthesis)"
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def is_reader_error(code_lines):
|
||||
"""Feed code to SBCL's reader via temp file. Returns error string or None."""
|
||||
code = "\n".join(code_lines)
|
||||
if not code.strip():
|
||||
return None
|
||||
|
||||
if not os.path.exists(SBCL):
|
||||
return f"SBCL not found at {SBCL}"
|
||||
|
||||
with tempfile.NamedTemporaryFile(mode="w", suffix=".lisp", delete=False) as f:
|
||||
f.write(code)
|
||||
temp_path = f.name
|
||||
|
||||
try:
|
||||
# Use --no-userinit and --disable-debugger to suppress all interactive output
|
||||
result = subprocess.run(
|
||||
[SBCL, "--noinform", "--no-userinit", "--disable-debugger",
|
||||
"--quit", "--load", CHECKER_LISP,
|
||||
"--eval", f'(print (cp-check::check "{temp_path}"))'],
|
||||
capture_output=True, text=True, timeout=10
|
||||
)
|
||||
return parse_result(result.stdout)
|
||||
except subprocess.TimeoutExpired:
|
||||
return "TIMEOUT (sbcl hung)"
|
||||
finally:
|
||||
try:
|
||||
os.unlink(temp_path)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
Reference in New Issue
Block a user