[linux.git] / scripts / spdxcheck.py

#!/usr/bin/env python
# SPDX-License-Identifier: GPL-2.0
# Copyright Thomas Gleixner <[email protected]>

from argparse import ArgumentParser
from ply import lex, yacc
import locale
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.head.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 id not in self.spdx.exceptions:
                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 not os.path.isfile(el.path):
            continue
        with open(el.path, 'rb') as fd:
            parser.parse_lines(fd, 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)
Commit	Line	Data
5385a295 TG	1	#!/usr/bin/env python
	2	# SPDX-License-Identifier: GPL-2.0
	3	# Copyright Thomas Gleixner <[email protected]>
	4
	5	from argparse import ArgumentParser
	6	from ply import lex, yacc
bed95c43	7	import locale
5385a295 TG	8	import traceback
	9	import sys
	10	import git
	11	import re
	12	import os
	13
	14	class ParserException(Exception):
	15	def __init__(self, tok, txt):
	16	self.tok = tok
	17	self.txt = txt
	18
	19	class SPDXException(Exception):
	20	def __init__(self, el, txt):
	21	self.el = el
	22	self.txt = txt
	23
	24	class SPDXdata(object):
	25	def __init__(self):
	26	self.license_files = 0
	27	self.exception_files = 0
	28	self.licenses = [ ]
	29	self.exceptions = { }
	30
	31	# Read the spdx data from the LICENSES directory
	32	def read_spdxdata(repo):
	33
	34	# The subdirectories of LICENSES in the kernel source
	35	license_dirs = [ "preferred", "other", "exceptions" ]
fde5e903	36	lictree = repo.head.commit.tree['LICENSES']
5385a295 TG	37
	38	spdx = SPDXdata()
	39
	40	for d in license_dirs:
	41	for el in lictree[d].traverse():
	42	if not os.path.isfile(el.path):
	43	continue
	44
	45	exception = None
	46	for l in open(el.path).readlines():
	47	if l.startswith('Valid-License-Identifier:'):
	48	lid = l.split(':')[1].strip().upper()
	49	if lid in spdx.licenses:
	50	raise SPDXException(el, 'Duplicate License Identifier: %s' %lid)
	51	else:
	52	spdx.licenses.append(lid)
	53
	54	elif l.startswith('SPDX-Exception-Identifier:'):
	55	exception = l.split(':')[1].strip().upper()
	56	spdx.exceptions[exception] = []
	57
	58	elif l.startswith('SPDX-Licenses:'):
	59	for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','):
	60	if not lic in spdx.licenses:
	61	raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic))
	62	spdx.exceptions[exception].append(lic)
	63
	64	elif l.startswith("License-Text:"):
	65	if exception:
	66	if not len(spdx.exceptions[exception]):
	67	raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid)
	68	spdx.exception_files += 1
	69	else:
	70	spdx.license_files += 1
	71	break
	72	return spdx
	73
	74	class id_parser(object):
	75
	76	reserved = [ 'AND', 'OR', 'WITH' ]
	77	tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved
	78
	79	precedence = ( ('nonassoc', 'AND', 'OR'), )
	80
	81	t_ignore = ' \t'
	82
	83	def __init__(self, spdx):
	84	self.spdx = spdx
	85	self.lasttok = None
	86	self.lastid = None
	87	self.lexer = lex.lex(module = self, reflags = re.UNICODE)
	88	# Initialize the parser. No debug file and no parser rules stored on disk
	89	# The rules are small enough to be generated on the fly
	90	self.parser = yacc.yacc(module = self, write_tables = False, debug = False)
	91	self.lines_checked = 0
	92	self.checked = 0
	93	self.spdx_valid = 0
	94	self.spdx_errors = 0
	95	self.curline = 0
	96	self.deepest = 0
	97
	98	# Validate License and Exception IDs
	99	def validate(self, tok):
	100	id = tok.value.upper()
101	if tok.type == 'ID':
102	if not id in self.spdx.licenses:
103	raise ParserException(tok, 'Invalid License ID')
104	self.lastid = id
105	elif tok.type == 'EXC':
bed95c43	106	if id not in self.spdx.exceptions:
5385a295 TG	107	raise ParserException(tok, 'Invalid Exception ID')
	108	if self.lastid not in self.spdx.exceptions[id]:
	109	raise ParserException(tok, 'Exception not valid for license %s' %self.lastid)
	110	self.lastid = None
	111	elif tok.type != 'WITH':
	112	self.lastid = None
	113
	114	# Lexer functions
	115	def t_RPAR(self, tok):
	116	r'\)'
	117	self.lasttok = tok.type
	118	return tok
	119
	120	def t_LPAR(self, tok):
	121	r'\('
	122	self.lasttok = tok.type
	123	return tok
	124
	125	def t_ID(self, tok):
	126	r'[A-Za-z.0-9\-+]+'
	127
	128	if self.lasttok == 'EXC':
	129	print(tok)
	130	raise ParserException(tok, 'Missing parentheses')
	131
	132	tok.value = tok.value.strip()
	133	val = tok.value.upper()
	134
	135	if val in self.reserved:
	136	tok.type = val
	137	elif self.lasttok == 'WITH':
	138	tok.type = 'EXC'
	139
	140	self.lasttok = tok.type
	141	self.validate(tok)
	142	return tok
	143
	144	def t_error(self, tok):
	145	raise ParserException(tok, 'Invalid token')
	146
	147	def p_expr(self, p):
	148	'''expr : ID
	149	\| ID WITH EXC
	150	\| expr AND expr
	151	\| expr OR expr
	152	\| LPAR expr RPAR'''
	153	pass
	154
	155	def p_error(self, p):
	156	if not p:
	157	raise ParserException(None, 'Unfinished license expression')
	158	else:
	159	raise ParserException(p, 'Syntax error')
	160
	161	def parse(self, expr):
	162	self.lasttok = None
	163	self.lastid = None
	164	self.parser.parse(expr, lexer = self.lexer)
	165
	166	def parse_lines(self, fd, maxlines, fname):
	167	self.checked += 1
	168	self.curline = 0
	169	try:
	170	for line in fd:
171	self.curline += 1
172	if self.curline > maxlines:
173	break
174	self.lines_checked += 1
175	if line.find("SPDX-License-Identifier:") < 0:
176	continue
177	expr = line.split(':')[1].replace('*/', '').strip()
178	self.parse(expr)
179	self.spdx_valid += 1
180	#
181	# Should we check for more SPDX ids in the same file and
182	# complain if there are any?
183	#
184	break
185
186	except ParserException as pe:
187	if pe.tok:
188	col = line.find(expr) + pe.tok.lexpos
189	tok = pe.tok.value
190	sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok))
191	else:
192	sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt))
193	self.spdx_errors += 1
194
195	def scan_git_tree(tree):
196	for el in tree.traverse():
197	# Exclude stuff which would make pointless noise
198	# FIXME: Put this somewhere more sensible
199	if el.path.startswith("LICENSES"):
200	continue
201	if el.path.find("license-rules.rst") >= 0:
202	continue
5385a295 TG	203	if not os.path.isfile(el.path):
5385a295 TG	204	continue
bed95c43 JC	205	with open(el.path, 'rb') as fd:
bed95c43 JC	206	parser.parse_lines(fd, args.maxlines, el.path)
5385a295 TG	207
	208	def scan_git_subtree(tree, path):
	209	for p in path.strip('/').split('/'):
	210	tree = tree[p]
	211	scan_git_tree(tree)
	212
	213	if __name__ == '__main__':
	214
	215	ap = ArgumentParser(description='SPDX expression checker')
	216	ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"')
	217	ap.add_argument('-m', '--maxlines', type=int, default=15,
	218	help='Maximum number of lines to scan in a file. Default 15')
	219	ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output')
	220	args = ap.parse_args()
	221
	222	# Sanity check path arguments
	223	if '-' in args.path and len(args.path) > 1:
	224	sys.stderr.write('stdin input "-" must be the only path argument\n')
	225	sys.exit(1)
	226
	227	try:
	228	# Use git to get the valid license expressions
	229	repo = git.Repo(os.getcwd())
	230	assert not repo.bare
	231
	232	# Initialize SPDX data
	233	spdx = read_spdxdata(repo)
	234
	235	# Initilize the parser
	236	parser = id_parser(spdx)
	237
	238	except SPDXException as se:
	239	if se.el:
	240	sys.stderr.write('%s: %s\n' %(se.el.path, se.txt))
	241	else:
	242	sys.stderr.write('%s\n' %se.txt)
	243	sys.exit(1)
	244
	245	except Exception as ex:
	246	sys.stderr.write('FAIL: %s\n' %ex)
	247	sys.stderr.write('%s\n' %traceback.format_exc())
	248	sys.exit(1)
	249
	250	try:
	251	if len(args.path) and args.path[0] == '-':
	252	parser.parse_lines(sys.stdin, args.maxlines, '-')
	253	else:
	254	if args.path:
	255	for p in args.path:
	256	if os.path.isfile(p):
	257	parser.parse_lines(open(p), args.maxlines, p)
	258	elif os.path.isdir(p):
	259	scan_git_subtree(repo.head.reference.commit.tree, p)
	260	else:
	261	sys.stderr.write('path %s does not exist\n' %p)
	262	sys.exit(1)
	263	else:
	264	# Full git tree scan
	265	scan_git_tree(repo.head.commit.tree)
	266
	267	if args.verbose:
	268	sys.stderr.write('\n')
	269	sys.stderr.write('License files: %12d\n' %spdx.license_files)
	270	sys.stderr.write('Exception files: %12d\n' %spdx.exception_files)
271	sys.stderr.write('License IDs %12d\n' %len(spdx.licenses))
272	sys.stderr.write('Exception IDs %12d\n' %len(spdx.exceptions))
273	sys.stderr.write('\n')
274	sys.stderr.write('Files checked: %12d\n' %parser.checked)
275	sys.stderr.write('Lines checked: %12d\n' %parser.lines_checked)
276	sys.stderr.write('Files with SPDX: %12d\n' %parser.spdx_valid)
277	sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors)
278
279	sys.exit(0)
280
281	except Exception as ex:
282	sys.stderr.write('FAIL: %s\n' %ex)
283	sys.stderr.write('%s\n' %traceback.format_exc())
284	sys.exit(1)