[linux-block.git] / scripts / spdxcheck.py

#!/usr/bin/env python
# SPDX-License-Identifier: GPL-2.0
# Copyright Thomas Gleixner <tglx@linutronix.de>

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)
Commit	Line	Data
5385a295 TG	1	#!/usr/bin/env python
	2	# SPDX-License-Identifier: GPL-2.0
	3	# Copyright Thomas Gleixner <tglx@linutronix.de>
	4
	5	from argparse import ArgumentParser
	6	from ply import lex, yacc
	7	import traceback
	8	import sys
	9	import git
	10	import re
	11	import os
	12
	13	class ParserException(Exception):
	14	def __init__(self, tok, txt):
	15	self.tok = tok
	16	self.txt = txt
	17
	18	class SPDXException(Exception):
	19	def __init__(self, el, txt):
	20	self.el = el
	21	self.txt = txt
	22
	23	class SPDXdata(object):
	24	def __init__(self):
	25	self.license_files = 0
	26	self.exception_files = 0
	27	self.licenses = [ ]
	28	self.exceptions = { }
	29
	30	# Read the spdx data from the LICENSES directory
	31	def read_spdxdata(repo):
	32
	33	# The subdirectories of LICENSES in the kernel source
	34	license_dirs = [ "preferred", "other", "exceptions" ]
	35	lictree = repo.heads.master.commit.tree['LICENSES']
	36
	37	spdx = SPDXdata()
	38
	39	for d in license_dirs:
	40	for el in lictree[d].traverse():
	41	if not os.path.isfile(el.path):
	42	continue
	43
	44	exception = None
	45	for l in open(el.path).readlines():
	46	if l.startswith('Valid-License-Identifier:'):
	47	lid = l.split(':')[1].strip().upper()
	48	if lid in spdx.licenses:
	49	raise SPDXException(el, 'Duplicate License Identifier: %s' %lid)
	50	else:
	51	spdx.licenses.append(lid)
	52
	53	elif l.startswith('SPDX-Exception-Identifier:'):
	54	exception = l.split(':')[1].strip().upper()
	55	spdx.exceptions[exception] = []
	56
	57	elif l.startswith('SPDX-Licenses:'):
	58	for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','):
	59	if not lic in spdx.licenses:
	60	raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic))
	61	spdx.exceptions[exception].append(lic)
	62
	63	elif l.startswith("License-Text:"):
	64	if exception:
65	if not len(spdx.exceptions[exception]):
66	raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid)
67	spdx.exception_files += 1
68	else:
69	spdx.license_files += 1
70	break
71	return spdx
72
73	class id_parser(object):
74
75	reserved = [ 'AND', 'OR', 'WITH' ]
76	tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved
77
78	precedence = ( ('nonassoc', 'AND', 'OR'), )
79
80	t_ignore = ' \t'
81
82	def __init__(self, spdx):
83	self.spdx = spdx
84	self.lasttok = None
85	self.lastid = None
86	self.lexer = lex.lex(module = self, reflags = re.UNICODE)
87	# Initialize the parser. No debug file and no parser rules stored on disk
88	# The rules are small enough to be generated on the fly
89	self.parser = yacc.yacc(module = self, write_tables = False, debug = False)
90	self.lines_checked = 0
91	self.checked = 0
92	self.spdx_valid = 0
93	self.spdx_errors = 0
94	self.curline = 0
95	self.deepest = 0
96
97	# Validate License and Exception IDs
98	def validate(self, tok):
99	id = tok.value.upper()
100	if tok.type == 'ID':
101	if not id in self.spdx.licenses:
102	raise ParserException(tok, 'Invalid License ID')
103	self.lastid = id
104	elif tok.type == 'EXC':
105	if not self.spdx.exceptions.has_key(id):
106	raise ParserException(tok, 'Invalid Exception ID')
107	if self.lastid not in self.spdx.exceptions[id]:
108	raise ParserException(tok, 'Exception not valid for license %s' %self.lastid)
109	self.lastid = None
110	elif tok.type != 'WITH':
111	self.lastid = None
112
113	# Lexer functions
114	def t_RPAR(self, tok):
115	r'\)'
116	self.lasttok = tok.type
117	return tok
118
119	def t_LPAR(self, tok):
120	r'\('
121	self.lasttok = tok.type
122	return tok
123
124	def t_ID(self, tok):
125	r'[A-Za-z.0-9\-+]+'
126
127	if self.lasttok == 'EXC':
128	print(tok)
129	raise ParserException(tok, 'Missing parentheses')
130
131	tok.value = tok.value.strip()
132	val = tok.value.upper()
133
134	if val in self.reserved:
135	tok.type = val
136	elif self.lasttok == 'WITH':
137	tok.type = 'EXC'
138
139	self.lasttok = tok.type
140	self.validate(tok)
141	return tok
142
143	def t_error(self, tok):
144	raise ParserException(tok, 'Invalid token')
145
146	def p_expr(self, p):
147	'''expr : ID
148	\| ID WITH EXC
149	\| expr AND expr
150	\| expr OR expr
151	\| LPAR expr RPAR'''
152	pass
153
154	def p_error(self, p):
155	if not p:
156	raise ParserException(None, 'Unfinished license expression')
157	else:
158	raise ParserException(p, 'Syntax error')
159
160	def parse(self, expr):
161	self.lasttok = None
162	self.lastid = None
163	self.parser.parse(expr, lexer = self.lexer)
164
165	def parse_lines(self, fd, maxlines, fname):
166	self.checked += 1
167	self.curline = 0
168	try:
169	for line in fd:
170	self.curline += 1
171	if self.curline > maxlines:
172	break
173	self.lines_checked += 1
174	if line.find("SPDX-License-Identifier:") < 0:
175	continue
176	expr = line.split(':')[1].replace('*/', '').strip()
177	self.parse(expr)
178	self.spdx_valid += 1
179	#
180	# Should we check for more SPDX ids in the same file and
181	# complain if there are any?
182	#
183	break
184
185	except ParserException as pe:
186	if pe.tok:
187	col = line.find(expr) + pe.tok.lexpos
188	tok = pe.tok.value
189	sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok))
190	else:
191	sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt))
192	self.spdx_errors += 1
193
194	def scan_git_tree(tree):
195	for el in tree.traverse():
196	# Exclude stuff which would make pointless noise
197	# FIXME: Put this somewhere more sensible
198	if el.path.startswith("LICENSES"):
199	continue
200	if el.path.find("license-rules.rst") >= 0:
201	continue
202	if el.path == 'scripts/checkpatch.pl':
203	continue
204	if not os.path.isfile(el.path):
205	continue
206	parser.parse_lines(open(el.path), args.maxlines, el.path)
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)