-
Notifications
You must be signed in to change notification settings - Fork 0
Add batch linter and harden echo usage #3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,167 @@ | ||
| #!/usr/bin/env python3 | ||
| """Simple batch file linter. | ||
|
|
||
| Performs basic static analysis specific to Windows CMD batch syntax. In addition | ||
| to unsafe ``echo`` patterns, the linter checks for the following problems: | ||
|
|
||
| * unmatched parentheses and percent expansions | ||
| * unclosed quotation marks | ||
| * improper ``for`` loop structure | ||
| * suspicious ``if`` syntax | ||
| * missing ``=`` on ``set`` commands | ||
| * references to nonexistent ``goto``/``call`` labels | ||
| """ | ||
| import re | ||
| import sys | ||
| from pathlib import Path | ||
|
|
||
|
|
||
| def lint(path: Path) -> int: | ||
| lines = path.read_text(errors="ignore").splitlines() | ||
| errors: list[tuple[int, str]] = [] | ||
| stack: list[int] = [] | ||
| labels: dict[str, int] = {} | ||
| refs: list[tuple[int, str]] = [] | ||
|
|
||
| for lineno, raw in enumerate(lines, 1): | ||
| line = raw | ||
| stripped = line.lstrip() | ||
| if stripped.startswith("REM") or stripped.startswith("::"): | ||
| continue | ||
|
|
||
| # label definition | ||
| m = re.match(r":([A-Za-z0-9_.$?-]+)\b(.*)", stripped) | ||
| if m: | ||
| name = m.group(1).lower() | ||
| if name in labels: | ||
| errors.append((lineno, f"duplicate label :{name} (first at {labels[name]})")) | ||
| else: | ||
| labels[name] = lineno | ||
| rest = m.group(2).lstrip() | ||
| if not rest: | ||
| continue | ||
| line = rest | ||
| stripped = line.lstrip() | ||
|
|
||
| # check unsafe echo usage anywhere in the line | ||
| low = line.lower() | ||
| if "echo(" not in low: | ||
| m = re.search(r"(?i)(?:^|[\s>&|])echo[ .]", line) | ||
| if m: | ||
| after = line[m.end():] | ||
| if "%" in after: | ||
| errors.append((lineno, "use echo( for safe output")) | ||
|
|
||
| # unescape caret escapes | ||
| res = "" | ||
| esc = False | ||
| for ch in line: | ||
| if esc: | ||
| esc = False | ||
| elif ch == "^": | ||
| esc = True | ||
| continue | ||
| res += ch | ||
| line_u = res | ||
|
|
||
| # remove quoted segments and track unmatched quotes | ||
| in_q = False | ||
| prev = "" | ||
| tmp = "" | ||
| for ch in line_u: | ||
| if ch == '"' and prev != "\\": | ||
| in_q = not in_q | ||
| elif not in_q: | ||
| tmp += ch | ||
| prev = ch | ||
| if in_q: | ||
| errors.append((lineno, 'unmatched "')) | ||
|
|
||
| # check for/goto/if/set patterns within unquoted text | ||
| tmp_low = tmp.lower() | ||
|
|
||
| if tmp_low.startswith('for'): | ||
| if '%%' not in tmp: | ||
| errors.append((lineno, 'for loop variable must use %%')) | ||
| if ' in ' not in tmp_low or ' do' not in tmp_low: | ||
| errors.append((lineno, 'for loop missing IN or DO')) | ||
|
|
||
| if tmp_low.startswith('if'): | ||
| if not any(op in tmp_low for op in ['==', ' equ ', ' neq ', ' lss ', | ||
| ' gtr ', ' leq ', ' geq ', | ||
| ' exist ', ' defined ', | ||
| ' errorlevel ']): | ||
| errors.append((lineno, 'suspicious if syntax')) | ||
|
|
||
| if line_u.lstrip().lower().startswith('set ') and not line_u.lstrip().lower().startswith('setlocal'): | ||
| low_u = line_u.lower() | ||
| if '=' not in line_u and '/p' not in low_u and '/a' not in low_u: | ||
| errors.append((lineno, 'set without =')) | ||
|
|
||
| mg = re.search(r"(?i)\bgoto\s+(:?\w+)", tmp) | ||
| if mg: | ||
| lbl = mg.group(1) | ||
| if lbl.startswith(':'): | ||
| lbl = lbl[1:] | ||
| refs.append((lineno, lbl.lower())) | ||
|
|
||
| mc = re.search(r"(?i)\bcall\s+(:[A-Za-z0-9_.$?-]+)", tmp) | ||
| if mc: | ||
| refs.append((lineno, mc.group(1)[1:].lower())) | ||
|
|
||
| # core syntax checks: parentheses and percent expansions | ||
| j = 0 | ||
| while j < len(tmp): | ||
| ch = tmp[j] | ||
| if ch == '(': | ||
| seg = tmp[max(0, j - 5):j].lower() | ||
| if not seg.endswith('echo'): | ||
| stack.append(lineno) | ||
| elif ch == ')': | ||
| if stack: | ||
| stack.pop() | ||
| else: | ||
| errors.append((lineno, 'unmatched )')) | ||
| elif ch == '%': | ||
| if j + 1 < len(tmp) and tmp[j + 1] == '%': | ||
| j += 2 | ||
| continue | ||
| if j + 1 < len(tmp) and tmp[j + 1] in '*0123456789': | ||
| j += 2 | ||
| continue | ||
| if j + 1 < len(tmp) and tmp[j + 1] == '~': | ||
| k = j + 2 | ||
| while k < len(tmp) and tmp[k].isalpha(): | ||
| k += 1 | ||
| if k < len(tmp) and tmp[k].isdigit(): | ||
| j = k + 1 | ||
| continue | ||
| k = tmp.find('%', j + 1) | ||
| if k == -1: | ||
| errors.append((lineno, 'unmatched %')) | ||
| break | ||
| j = k + 1 | ||
| continue | ||
| j += 1 | ||
|
|
||
| for ln in stack: | ||
| errors.append((ln, 'unmatched (')) | ||
|
|
||
| for ln, label in refs: | ||
| if label not in labels and label.lower() != 'eof': | ||
| errors.append((ln, f'unknown label :{label}')) | ||
|
|
||
| for ln, msg in errors: | ||
| print(f"{path}:{ln}: {msg}") | ||
| return 1 if errors else 0 | ||
|
|
||
|
|
||
| def main(argv): | ||
| if len(argv) != 2: | ||
| print("Usage: lint_batch.py <file.bat>") | ||
| return 1 | ||
| return lint(Path(argv[1])) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| sys.exit(main(sys.argv)) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
[P1] Replace shell-incompatible comment
The newly added comment in the Python version detection section starts with
#, but#is not a comment prefix in Windows batch files. Whenpyproject.tomlis present this line executes as a command, printing'#' is not recognized as an internal or external commandand settingERRORLEVELto 9009 before the PowerShell call. That spurious failure can cause later logic that checkserrorlevelto misbehave. UseREMor::for comments instead.Useful? React with 👍 / 👎.