From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AB8JxZo2w2z7ah6je2IKFCgn2n7WMwn4mBMWe6FY0zZ1FR5/NqFQzNFbB5FO8DNzJd+YZbk5F/4S ARC-Seal: i=1; a=rsa-sha256; t=1524750871; cv=none; d=google.com; s=arc-20160816; b=Cikzd4rqjD9YHTG1e3ZQhtXEHD0sZ5W/g3KNvKi8YuEezt0iiejXatR6pDH0+bwoC7 UX7iX9XsQ9WhOFfrG4NG29iKcBWUNcYjkkfELR3FPokGFwLl1SRP+ZgoCL5Kk1rs6tKL 3XuVcL4J+w54ORbDgPvhu8uHz6HAWhnqG+wLxipgXFcayrDyydITrdswa1vcpulj3eCR 938JdueJ4o+Y5BLqWuVgtDsmPpDPJ3j4qJC6azCFaTLiQjazTfj6Myitf88sAdBeBRws azpqC6Q5EM8iXtmmJquDF8/XVO/N5SjyNMlf/zMzOTN0rkjZNKG1bQEvJVkcrj+ucIaU ZPdw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=mime-version:user-agent:references:message-id:in-reply-to:subject :cc:to:from:date:arc-authentication-results; bh=uAGcHZIpsEjA5YRS38/0wKaN+LY907Wufowxm6iG6Q0=; b=WKUUSzGVtCaKk67lzhytWJcEA/knQiD2BRGAa+1q54Ctg0TfHru0loHBaBIrVCXrCm Bix2lpWtvaJJCce74NekVVBa396AD1SKnqA5S8KfLCEGJVrzp/0tV5AOVDpiwbAo2O/A UCCz/iqCr6MJb33z+BVji65vk+xepx4O8A5nLz+1LRyT+m5RMHC3aSXapoBFLodDFJt9 sh427NG1lBA8qI0RCIwG4ynx1alvfkoOAXAG4m6cOOh/B1pYG11Zpie5kkjPe0Ch4d8l /GQY3ty5jsCGENbNpZ9LlUI/dH3SovxMVMRQy0936+6Co77yK0LlbNAru2wxcFyrONB7 PuZw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of tglx@linutronix.de designates 2a01:7a0:2:106d:700::1 as permitted sender) smtp.mailfrom=tglx@linutronix.de Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of tglx@linutronix.de designates 2a01:7a0:2:106d:700::1 as permitted sender) smtp.mailfrom=tglx@linutronix.de Date: Thu, 26 Apr 2018 15:54:27 +0200 (CEST) From: Thomas Gleixner To: Greg Kroah-Hartman cc: LKML , Philippe Ombredanne , Kate Stewart , Jonathan Corbet , Hans Verkuil , Mauro Carvalho Chehab , Christoph Hellwig Subject: [patch V3 7/7] scripts: Add SPDX checker script In-Reply-To: <20180426070246.GL14025@kroah.com> Message-ID: References: <20180425203020.594959448@linutronix.de> <20180425203703.650160358@linutronix.de> <20180426070246.GL14025@kroah.com> User-Agent: Alpine 2.21 (DEB 202 2017-01-01) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1598752952851638430?= X-GMAIL-MSGID: =?utf-8?q?1598817169877786762?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: The SPDX-License-Identifiers are growing in the kernel and so grow expression failures and license IDs are used which have no corresponding license text file in the LICENSES directory. Add a script which gathers information from the LICENSES directory, i.e. the various tags in the licenses and exception files and then scans either input from stdin, which it treats as a single file or if started without arguments it scans the full kernel tree. It checks whether the license expression syntax is correct and also validates whether the license identifiers used in the expressions are available in the LICENSES files. scripts/spdxcheck.py -h usage: spdxcheck.py [-h] [-m MAXLINES] [-v] [path [path ...]] SPDX expression checker positional arguments: path Check path or file. If not given full git tree scan. For stdin use "-" optional arguments: -h, --help show this help message and exit -m MAXLINES, --maxlines MAXLINES Maximum number of lines to scan in a file. Default 15 -v, --verbose Verbose statistics output # scripts/spdxcheck.py - --- v2 -> v3: Changed the input selection so files, directories and the full git tree can be checked. Selection of stdin is now '-' instead of '-s' scripts/spdxcheck.py | 284 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 284 insertions(+) --- /dev/null +++ b/scripts/spdxcheck.py @@ -0,0 +1,284 @@ +#!/usr/bin/env python +# SPDX-License-Identifier: GPL2.0 +# Copyright Thomas Gleixner + +from argparse import ArgumentParser +from ply import lex, yacc +import traceback +import sys +import git +import re +import os + +class ParserException(Exception): + def __init__(self, tok, txt): + self.tok = tok + self.txt = txt + +class SPDXException(Exception): + def __init__(self, el, txt): + self.el = el + self.txt = txt + +class SPDXdata(object): + def __init__(self): + self.license_files = 0 + self.exception_files = 0 + self.licenses = [ ] + self.exceptions = { } + +# Read the spdx data from the LICENSES directory +def read_spdxdata(repo): + + # The subdirectories of LICENSES in the kernel source + license_dirs = [ "preferred", "other", "exceptions" ] + lictree = repo.heads.master.commit.tree['LICENSES'] + + spdx = SPDXdata() + + for d in license_dirs: + for el in lictree[d].traverse(): + if not os.path.isfile(el.path): + continue + + exception = None + for l in open(el.path).readlines(): + if l.startswith('Valid-License-Identifier:'): + lid = l.split(':')[1].strip().upper() + if lid in spdx.licenses: + raise SPDXException(el, 'Duplicate License Identifier: %s' %lid) + else: + spdx.licenses.append(lid) + + elif l.startswith('SPDX-Exception-Identifier:'): + exception = l.split(':')[1].strip().upper() + spdx.exceptions[exception] = [] + + elif l.startswith('SPDX-Licenses:'): + for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','): + if not lic in spdx.licenses: + raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic)) + spdx.exceptions[exception].append(lic) + + elif l.startswith("License-Text:"): + if exception: + if not len(spdx.exceptions[exception]): + raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid) + spdx.exception_files += 1 + else: + spdx.license_files += 1 + break + return spdx + +class id_parser(object): + + reserved = [ 'AND', 'OR', 'WITH' ] + tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved + + precedence = ( ('nonassoc', 'AND', 'OR'), ) + + t_ignore = ' \t' + + def __init__(self, spdx): + self.spdx = spdx + self.lasttok = None + self.lastid = None + self.lexer = lex.lex(module = self, reflags = re.UNICODE) + # Initialize the parser. No debug file and no parser rules stored on disk + # The rules are small enough to be generated on the fly + self.parser = yacc.yacc(module = self, write_tables = False, debug = False) + self.lines_checked = 0 + self.checked = 0 + self.spdx_valid = 0 + self.spdx_errors = 0 + self.curline = 0 + self.deepest = 0 + + # Validate License and Exception IDs + def validate(self, tok): + id = tok.value.upper() + if tok.type == 'ID': + if not id in self.spdx.licenses: + raise ParserException(tok, 'Invalid License ID') + self.lastid = id + elif tok.type == 'EXC': + if not self.spdx.exceptions.has_key(id): + raise ParserException(tok, 'Invalid Exception ID') + if self.lastid not in self.spdx.exceptions[id]: + raise ParserException(tok, 'Exception not valid for license %s' %self.lastid) + self.lastid = None + elif tok.type != 'WITH': + self.lastid = None + + # Lexer functions + def t_RPAR(self, tok): + r'\)' + self.lasttok = tok.type + return tok + + def t_LPAR(self, tok): + r'\(' + self.lasttok = tok.type + return tok + + def t_ID(self, tok): + r'[A-Za-z.0-9\-+]+' + + if self.lasttok == 'EXC': + print(tok) + raise ParserException(tok, 'Missing parentheses') + + tok.value = tok.value.strip() + val = tok.value.upper() + + if val in self.reserved: + tok.type = val + elif self.lasttok == 'WITH': + tok.type = 'EXC' + + self.lasttok = tok.type + self.validate(tok) + return tok + + def t_error(self, tok): + raise ParserException(tok, 'Invalid token') + + def p_expr(self, p): + '''expr : ID + | ID WITH EXC + | expr AND expr + | expr OR expr + | LPAR expr RPAR''' + pass + + def p_error(self, p): + if not p: + raise ParserException(None, 'Unfinished license expression') + else: + raise ParserException(p, 'Syntax error') + + def parse(self, expr): + self.lasttok = None + self.lastid = None + self.parser.parse(expr, lexer = self.lexer) + + def parse_lines(self, fd, maxlines, fname): + self.checked += 1 + self.curline = 0 + try: + for line in fd: + self.curline += 1 + if self.curline > maxlines: + break + self.lines_checked += 1 + if line.find("SPDX-License-Identifier:") < 0: + continue + expr = line.split(':')[1].replace('*/', '').strip() + self.parse(expr) + self.spdx_valid += 1 + # + # Should we check for more SPDX ids in the same file and + # complain if there are any? + # + break + + except ParserException as pe: + if pe.tok: + col = line.find(expr) + pe.tok.lexpos + tok = pe.tok.value + sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok)) + else: + sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt)) + self.spdx_errors += 1 + +def scan_git_tree(tree): + for el in tree.traverse(): + # Exclude stuff which would make pointless noise + # FIXME: Put this somewhere more sensible + if el.path.startswith("LICENSES"): + continue + if el.path.find("license-rules.rst") >= 0: + continue + if el.path == 'scripts/checkpatch.pl': + continue + if not os.path.isfile(el.path): + continue + parser.parse_lines(open(el.path), args.maxlines, el.path) + +def scan_git_subtree(tree, path): + for p in path.strip('/').split('/'): + tree = tree[p] + scan_git_tree(tree) + +if __name__ == '__main__': + + ap = ArgumentParser(description='SPDX expression checker') + ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"') + ap.add_argument('-m', '--maxlines', type=int, default=15, + help='Maximum number of lines to scan in a file. Default 15') + ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output') + args = ap.parse_args() + + # Sanity check path arguments + if '-' in args.path and len(args.path) > 1: + sys.stderr.write('stdin input "-" must be the only path argument\n') + sys.exit(1) + + try: + # Use git to get the valid license expressions + repo = git.Repo(os.getcwd()) + assert not repo.bare + + # Initialize SPDX data + spdx = read_spdxdata(repo) + + # Initilize the parser + parser = id_parser(spdx) + + except SPDXException as se: + if se.el: + sys.stderr.write('%s: %s\n' %(se.el.path, se.txt)) + else: + sys.stderr.write('%s\n' %se.txt) + sys.exit(1) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1) + + try: + if len(args.path) and args.path[0] == '-': + parser.parse_lines(sys.stdin, args.maxlines, '-') + else: + if args.path: + for p in args.path: + if os.path.isfile(p): + parser.parse_lines(open(p), args.maxlines, p) + elif os.path.isdir(p): + scan_git_subtree(repo.head.reference.commit.tree, p) + else: + sys.stderr.write('path %s does not exist\n' %p) + sys.exit(1) + else: + # Full git tree scan + scan_git_tree(repo.head.commit.tree) + + if args.verbose: + sys.stderr.write('\n') + sys.stderr.write('License files: %12d\n' %spdx.license_files) + sys.stderr.write('Exception files: %12d\n' %spdx.exception_files) + sys.stderr.write('License IDs %12d\n' %len(spdx.licenses)) + sys.stderr.write('Exception IDs %12d\n' %len(spdx.exceptions)) + sys.stderr.write('\n') + sys.stderr.write('Files checked: %12d\n' %parser.checked) + sys.stderr.write('Lines checked: %12d\n' %parser.lines_checked) + sys.stderr.write('Files with SPDX: %12d\n' %parser.spdx_valid) + sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors) + + sys.exit(0) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1)