summaryrefslogtreecommitdiff
path: root/python/samba/ms_schema.py
blob: 4946636cbd47223760d8ff86f824ccab07411c98 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
# create schema.ldif (as a string) from WSPP documentation
#
# based on minschema.py and minschema_wspp
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

from __future__ import print_function
"""Generate LDIF from WSPP documentation."""

import re
import base64
import uuid
from samba.compat import string_types

bitFields = {}

# ADTS: 2.2.9
# bit positions as labeled in the docs
bitFields["searchflags"] = {
    'fATTINDEX': 31,         # IX
    'fPDNTATTINDEX': 30,     # PI
    'fANR': 29,  # AR
    'fPRESERVEONDELETE': 28,         # PR
    'fCOPY': 27,     # CP
    'fTUPLEINDEX': 26,       # TP
    'fSUBTREEATTINDEX': 25,  # ST
    'fCONFIDENTIAL': 24,     # CF
    'fCONFIDENTAIL': 24,  # typo
    'fNEVERVALUEAUDIT': 23,  # NV
    'fRODCAttribute': 22,    # RO


    # missing in ADTS but required by LDIF
    'fRODCFilteredAttribute': 22,    # RO
    'fRODCFILTEREDATTRIBUTE': 22,  # case
    'fEXTENDEDLINKTRACKING': 21,  # XL
    'fBASEONLY': 20,  # BO
    'fPARTITIONSECRET': 19,  # SE
}

# ADTS: 2.2.10
bitFields["systemflags"] = {
    'FLAG_ATTR_NOT_REPLICATED': 31, 'FLAG_CR_NTDS_NC': 31,     # NR
    'FLAG_ATTR_REQ_PARTIAL_SET_MEMBER': 30, 'FLAG_CR_NTDS_DOMAIN': 30,     # PS
    'FLAG_ATTR_IS_CONSTRUCTED': 29, 'FLAG_CR_NTDS_NOT_GC_REPLICATED': 29,     # CS
    'FLAG_ATTR_IS_OPERATIONAL': 28,     # OP
    'FLAG_SCHEMA_BASE_OBJECT': 27,     # BS
    'FLAG_ATTR_IS_RDN': 26,     # RD
    'FLAG_DISALLOW_MOVE_ON_DELETE': 6,     # DE
    'FLAG_DOMAIN_DISALLOW_MOVE': 5,     # DM
    'FLAG_DOMAIN_DISALLOW_RENAME': 4,     # DR
    'FLAG_CONFIG_ALLOW_LIMITED_MOVE': 3,     # AL
    'FLAG_CONFIG_ALLOW_MOVE': 2,     # AM
    'FLAG_CONFIG_ALLOW_RENAME': 1,     # AR
    'FLAG_DISALLOW_DELETE': 0     # DD
}

# ADTS: 2.2.11
bitFields["schemaflagsex"] = {
    'FLAG_ATTR_IS_CRITICAL': 31
}

# ADTS: 3.1.1.2.2.2
oMObjectClassBER = {
    '1.3.12.2.1011.28.0.702': base64.b64encode(b'\x2B\x0C\x02\x87\x73\x1C\x00\x85\x3E').decode('utf8'),
    '1.2.840.113556.1.1.1.12': base64.b64encode(b'\x2A\x86\x48\x86\xF7\x14\x01\x01\x01\x0C').decode('utf8'),
    '2.6.6.1.2.5.11.29': base64.b64encode(b'\x56\x06\x01\x02\x05\x0B\x1D').decode('utf8'),
    '1.2.840.113556.1.1.1.11': base64.b64encode(b'\x2A\x86\x48\x86\xF7\x14\x01\x01\x01\x0B').decode('utf8'),
    '1.3.12.2.1011.28.0.714': base64.b64encode(b'\x2B\x0C\x02\x87\x73\x1C\x00\x85\x4A').decode('utf8'),
    '1.3.12.2.1011.28.0.732': base64.b64encode(b'\x2B\x0C\x02\x87\x73\x1C\x00\x85\x5C').decode('utf8'),
    '1.2.840.113556.1.1.1.6': base64.b64encode(b'\x2A\x86\x48\x86\xF7\x14\x01\x01\x01\x06').decode('utf8')
}

# separated by commas in docs, and must be broken up
multivalued_attrs = set(["auxiliaryclass", "maycontain", "mustcontain", "posssuperiors",
                         "systemauxiliaryclass", "systemmaycontain", "systemmustcontain",
                         "systemposssuperiors"])


def __read_folded_line(f, buffer):
    """ reads a line from an LDIF file, unfolding it"""
    line = buffer

    while True:
        l = f.readline()

        if l[:1] == " ":
            # continued line

            # cannot fold an empty line
            assert(line != "" and line != "\n")

            # preserves '\n '
            line = line + l
        else:
            # non-continued line
            if line == "":
                line = l

                if l == "":
                    # eof, definitely won't be folded
                    break
            else:
                # marks end of a folded line
                # line contains the now unfolded line
                # buffer contains the start of the next possibly folded line
                buffer = l
                break

    return (line, buffer)


def __read_raw_entries(f):
    """reads an LDIF entry, only unfolding lines"""
    import sys

    # will not match options after the attribute type
    attr_type_re = re.compile("^([A-Za-z]+[A-Za-z0-9-]*):")

    buffer = ""

    while True:
        entry = []

        while True:
            (l, buffer) = __read_folded_line(f, buffer)

            if l[:1] == "#":
                continue

            if l == "\n" or l == "":
                break

            m = attr_type_re.match(l)

            if m:
                if l[-1:] == "\n":
                    l = l[:-1]

                entry.append(l)
            else:
                print("Invalid line: %s" % l, end=' ', file=sys.stderr)
                sys.exit(1)

        if len(entry):
            yield entry

        if l == "":
            break


def fix_dn(dn):
    """fix a string DN to use ${SCHEMADN}"""

    # folding?
    if dn.find("<RootDomainDN>") != -1:
        dn = dn.replace("\n ", "")
        dn = dn.replace(" ", "")
        return dn.replace("CN=Schema,CN=Configuration,<RootDomainDN>", "${SCHEMADN}")
    elif dn.endswith("DC=X"):
        return dn.replace("CN=Schema,CN=Configuration,DC=X", "${SCHEMADN}")
    elif dn.endswith("CN=X"):
        return dn.replace("CN=Schema,CN=Configuration,CN=X", "${SCHEMADN}")
    else:
        return dn


def __convert_bitfield(key, value):
    """Evaluate the OR expression in 'value'"""
    assert(isinstance(value, string_types))

    value = value.replace("\n ", "")
    value = value.replace(" ", "")

    try:
        # some attributes already have numeric values
        o = int(value)
    except ValueError:
        o = 0
        flags = value.split("|")
        for f in flags:
            bitpos = bitFields[key][f]
            o = o | (1 << (31 - bitpos))

    return str(o)


def __write_ldif_one(entry):
    """Write out entry as LDIF"""
    out = []

    for l in entry:
        if isinstance(l[1], string_types):
            vl = [l[1]]
        else:
            vl = l[1]

        if l[2]:
            out.append("%s:: %s" % (l[0], l[1]))
            continue

        for v in vl:
            out.append("%s: %s" % (l[0], v))

    return "\n".join(out)


def __transform_entry(entry, objectClass):
    """Perform transformations required to convert the LDIF-like schema
       file entries to LDIF, including Samba-specific stuff."""

    entry = [l.split(":", 1) for l in entry]

    cn = ""
    skip_dn = skip_objectclass = skip_admin_description = skip_admin_display_name = False

    for l in entry:
        if l[1].startswith(': '):
            l.append(True)
            l[1] = l[1][2:]
        else:
            l.append(False)

        key = l[0].lower()
        l[1] = l[1].lstrip()
        l[1] = l[1].rstrip()

        if not cn and key == "cn":
            cn = l[1]

        if key in multivalued_attrs:
            # unlike LDIF, these are comma-separated
            l[1] = l[1].replace("\n ", "")
            l[1] = l[1].replace(" ", "")

            l[1] = l[1].split(",")

        if key in bitFields:
            l[1] = __convert_bitfield(key, l[1])

        if key == "omobjectclass":
            if not l[2]:
                l[1] = oMObjectClassBER[l[1].strip()]
                l[2] = True

        if isinstance(l[1], string_types):
            l[1] = fix_dn(l[1])

        if key == 'dn':
            skip_dn = True
            dn = l[1]

        if key == 'objectclass':
            skip_objectclass = True
        elif key == 'admindisplayname':
            skip_admin_display_name = True
        elif key == 'admindescription':
            skip_admin_description = True

    assert(cn)

    header = []
    if not skip_dn:
        header.append(["dn", "CN=%s,${SCHEMADN}" % cn, False])
    else:
        header.append(["dn", dn, False])

    if not skip_objectclass:
        header.append(["objectClass", ["top", objectClass], False])
    if not skip_admin_description:
        header.append(["adminDescription", cn, False])
    if not skip_admin_display_name:
        header.append(["adminDisplayName", cn, False])

    header.append(["objectGUID", str(uuid.uuid4()), False])

    entry = header + [x for x in entry if x[0].lower() not in set(['dn', 'changetype', 'objectcategory'])]

    return entry


def __parse_schema_file(filename, objectClass):
    """Load and transform a schema file."""

    out = []

    from io import open
    f = open(filename, "r", encoding='latin-1')
    for entry in __read_raw_entries(f):
        out.append(__write_ldif_one(__transform_entry(entry, objectClass)))

    return "\n\n".join(out)


def read_ms_schema(attr_file, classes_file, dump_attributes=True, dump_classes=True, debug=False):
    """Read WSPP documentation-derived schema files."""

    attr_ldif = ""
    classes_ldif = ""

    if dump_attributes:
        attr_ldif = __parse_schema_file(attr_file, "attributeSchema")
    if dump_classes:
        classes_ldif = __parse_schema_file(classes_file, "classSchema")

    return attr_ldif + "\n\n" + classes_ldif + "\n\n"


if __name__ == '__main__':
    import sys

    try:
        attr_file = sys.argv[1]
        classes_file = sys.argv[2]
    except IndexError:
        print("Usage: %s attr-file.txt classes-file.txt" % (sys.argv[0]), file=sys.stderr)
        sys.exit(1)

    print(read_ms_schema(attr_file, classes_file))