summaryrefslogtreecommitdiff
path: root/cloudinit/config/schema.py
blob: ca7d0d5b904e99f7729b0c3c68f7cb504f751e4f (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
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
# This file is part of cloud-init. See LICENSE file for license information.
"""schema.py: Set of module functions for processing cloud-config schema."""

from __future__ import print_function

from cloudinit import importer
from cloudinit.util import find_modules, read_file_or_url

import argparse
from collections import defaultdict
from copy import deepcopy
import logging
import os
import re
import sys
import yaml

_YAML_MAP = {True: 'true', False: 'false', None: 'null'}
SCHEMA_UNDEFINED = b'UNDEFINED'
CLOUD_CONFIG_HEADER = b'#cloud-config'
SCHEMA_DOC_TMPL = """
{name}
{title_underbar}
**Summary:** {title}

{description}

**Internal name:** ``{id}``

**Module frequency:** {frequency}

**Supported distros:** {distros}

**Config schema**:
{property_doc}
{examples}
"""
SCHEMA_PROPERTY_TMPL = '{prefix}**{prop_name}:** ({type}) {description}'
SCHEMA_EXAMPLES_HEADER = '\n**Examples**::\n\n'
SCHEMA_EXAMPLES_SPACER_TEMPLATE = '\n    # --- Example{0} ---'


class SchemaValidationError(ValueError):
    """Raised when validating a cloud-config file against a schema."""

    def __init__(self, schema_errors=()):
        """Init the exception an n-tuple of schema errors.

        @param schema_errors: An n-tuple of the format:
            ((flat.config.key, msg),)
        """
        self.schema_errors = schema_errors
        error_messages = [
            '{0}: {1}'.format(config_key, message)
            for config_key, message in schema_errors]
        message = "Cloud config schema errors: {0}".format(
            ', '.join(error_messages))
        super(SchemaValidationError, self).__init__(message)


def validate_cloudconfig_schema(config, schema, strict=False):
    """Validate provided config meets the schema definition.

    @param config: Dict of cloud configuration settings validated against
        schema.
    @param schema: jsonschema dict describing the supported schema definition
       for the cloud config module (config.cc_*).
    @param strict: Boolean, when True raise SchemaValidationErrors instead of
       logging warnings.

    @raises: SchemaValidationError when provided config does not validate
        against the provided schema.
    """
    try:
        from jsonschema import Draft4Validator, FormatChecker
    except ImportError:
        logging.debug(
            'Ignoring schema validation. python-jsonschema is not present')
        return
    validator = Draft4Validator(schema, format_checker=FormatChecker())
    errors = ()
    for error in sorted(validator.iter_errors(config), key=lambda e: e.path):
        path = '.'.join([str(p) for p in error.path])
        errors += ((path, error.message),)
    if errors:
        if strict:
            raise SchemaValidationError(errors)
        else:
            messages = ['{0}: {1}'.format(k, msg) for k, msg in errors]
            logging.warning('Invalid config:\n%s', '\n'.join(messages))


def annotated_cloudconfig_file(cloudconfig, original_content, schema_errors):
    """Return contents of the cloud-config file annotated with schema errors.

    @param cloudconfig: YAML-loaded object from the original_content.
    @param original_content: The contents of a cloud-config file
    @param schema_errors: List of tuples from a JSONSchemaValidationError. The
        tuples consist of (schemapath, error_message).
    """
    if not schema_errors:
        return original_content
    schemapaths = _schemapath_for_cloudconfig(cloudconfig, original_content)
    errors_by_line = defaultdict(list)
    error_count = 1
    error_footer = []
    annotated_content = []
    for path, msg in schema_errors:
        errors_by_line[schemapaths[path]].append(msg)
        error_footer.append('# E{0}: {1}'.format(error_count, msg))
        error_count += 1
    lines = original_content.decode().split('\n')
    error_count = 1
    for line_number, line in enumerate(lines):
        errors = errors_by_line[line_number + 1]
        if errors:
            error_label = ','.join(
                ['E{0}'.format(count + error_count)
                 for count in range(0, len(errors))])
            error_count += len(errors)
            annotated_content.append(line + '\t\t# ' + error_label)
        else:
            annotated_content.append(line)
    annotated_content.append(
        '# Errors: -------------\n{0}\n\n'.format('\n'.join(error_footer)))
    return '\n'.join(annotated_content)


def validate_cloudconfig_file(config_path, schema, annotate=False):
    """Validate cloudconfig file adheres to a specific jsonschema.

    @param config_path: Path to the yaml cloud-config file to parse.
    @param schema: Dict describing a valid jsonschema to validate against.
    @param annotate: Boolean set True to print original config file with error
        annotations on the offending lines.

    @raises SchemaValidationError containing any of schema_errors encountered.
    @raises RuntimeError when config_path does not exist.
    """
    if not os.path.exists(config_path):
        raise RuntimeError('Configfile {0} does not exist'.format(config_path))
    content = read_file_or_url('file://{0}'.format(config_path)).contents
    if not content.startswith(CLOUD_CONFIG_HEADER):
        errors = (
            ('header', 'File {0} needs to begin with "{1}"'.format(
                config_path, CLOUD_CONFIG_HEADER.decode())),)
        raise SchemaValidationError(errors)

    try:
        cloudconfig = yaml.safe_load(content)
    except yaml.parser.ParserError as e:
        errors = (
            ('format', 'File {0} is not valid yaml. {1}'.format(
                config_path, str(e))),)
        raise SchemaValidationError(errors)

    try:
        validate_cloudconfig_schema(
            cloudconfig, schema, strict=True)
    except SchemaValidationError as e:
        if annotate:
            print(annotated_cloudconfig_file(
                cloudconfig, content, e.schema_errors))
        raise


def _schemapath_for_cloudconfig(config, original_content):
    """Return a dictionary mapping schemapath to original_content line number.

    @param config: The yaml.loaded config dictionary of a cloud-config file.
    @param original_content: The simple file content of the cloud-config file
    """
    # FIXME Doesn't handle multi-line lists or multi-line strings
    content_lines = original_content.decode().split('\n')
    schema_line_numbers = {}
    list_index = 0
    RE_YAML_INDENT = r'^(\s*)'
    scopes = []
    for line_number, line in enumerate(content_lines):
        indent_depth = len(re.match(RE_YAML_INDENT, line).groups()[0])
        line = line.strip()
        if not line or line.startswith('#'):
            continue
        if scopes:
            previous_depth, path_prefix = scopes[-1]
        else:
            previous_depth = -1
            path_prefix = ''
        if line.startswith('- '):
            key = str(list_index)
            value = line[1:]
            list_index += 1
        else:
            list_index = 0
            key, value = line.split(':', 1)
        while indent_depth <= previous_depth:
            if scopes:
                previous_depth, path_prefix = scopes.pop()
            else:
                previous_depth = -1
                path_prefix = ''
        if path_prefix:
            key = path_prefix + '.' + key
        scopes.append((indent_depth, key))
        if value:
            value = value.strip()
            if value.startswith('['):
                scopes.append((indent_depth + 2, key + '.0'))
                for inner_list_index in range(0, len(yaml.safe_load(value))):
                    list_key = key + '.' + str(inner_list_index)
                    schema_line_numbers[list_key] = line_number + 1
        schema_line_numbers[key] = line_number + 1
    return schema_line_numbers


def _get_property_type(property_dict):
    """Return a string representing a property type from a given jsonschema."""
    property_type = property_dict.get('type', SCHEMA_UNDEFINED)
    if property_type == SCHEMA_UNDEFINED and property_dict.get('enum'):
        property_type = [
            str(_YAML_MAP.get(k, k)) for k in property_dict['enum']]
    if isinstance(property_type, list):
        property_type = '/'.join(property_type)
    items = property_dict.get('items', {})
    sub_property_type = items.get('type', '')
    # Collect each item type
    for sub_item in items.get('oneOf', {}):
        if sub_property_type:
            sub_property_type += '/'
        sub_property_type += '(' + _get_property_type(sub_item) + ')'
    if sub_property_type:
        return '{0} of {1}'.format(property_type, sub_property_type)
    return property_type


def _get_property_doc(schema, prefix='    '):
    """Return restructured text describing the supported schema properties."""
    new_prefix = prefix + '    '
    properties = []
    for prop_key, prop_config in schema.get('properties', {}).items():
        # Define prop_name and dscription for SCHEMA_PROPERTY_TMPL
        description = prop_config.get('description', '')
        properties.append(SCHEMA_PROPERTY_TMPL.format(
            prefix=prefix,
            prop_name=prop_key,
            type=_get_property_type(prop_config),
            description=description.replace('\n', '')))
        if 'properties' in prop_config:
            properties.append(
                _get_property_doc(prop_config, prefix=new_prefix))
    return '\n\n'.join(properties)


def _get_schema_examples(schema, prefix=''):
    """Return restructured text describing the schema examples if present."""
    examples = schema.get('examples')
    if not examples:
        return ''
    rst_content = SCHEMA_EXAMPLES_HEADER
    for count, example in enumerate(examples):
        # Python2.6 is missing textwrapper.indent
        lines = example.split('\n')
        indented_lines = ['    {0}'.format(line) for line in lines]
        if rst_content != SCHEMA_EXAMPLES_HEADER:
            indented_lines.insert(
                0, SCHEMA_EXAMPLES_SPACER_TEMPLATE.format(count + 1))
        rst_content += '\n'.join(indented_lines)
    return rst_content


def get_schema_doc(schema):
    """Return reStructured text rendering the provided jsonschema.

    @param schema: Dict of jsonschema to render.
    @raise KeyError: If schema lacks an expected key.
    """
    schema_copy = deepcopy(schema)
    schema_copy['property_doc'] = _get_property_doc(schema)
    schema_copy['examples'] = _get_schema_examples(schema)
    schema_copy['distros'] = ', '.join(schema['distros'])
    # Need an underbar of the same length as the name
    schema_copy['title_underbar'] = re.sub(r'.', '-', schema['name'])
    return SCHEMA_DOC_TMPL.format(**schema_copy)


FULL_SCHEMA = None


def get_schema():
    """Return jsonschema coalesced from all cc_* cloud-config module."""
    global FULL_SCHEMA
    if FULL_SCHEMA:
        return FULL_SCHEMA
    full_schema = {
        '$schema': 'http://json-schema.org/draft-04/schema#',
        'id': 'cloud-config-schema', 'allOf': []}

    configs_dir = os.path.dirname(os.path.abspath(__file__))
    potential_handlers = find_modules(configs_dir)
    for (fname, mod_name) in potential_handlers.items():
        mod_locs, looked_locs = importer.find_module(
            mod_name, ['cloudinit.config'], ['schema'])
        if mod_locs:
            mod = importer.import_module(mod_locs[0])
            full_schema['allOf'].append(mod.schema)
    FULL_SCHEMA = full_schema
    return full_schema


def error(message):
    print(message, file=sys.stderr)
    sys.exit(1)


def get_parser(parser=None):
    """Return a parser for supported cmdline arguments."""
    if not parser:
        parser = argparse.ArgumentParser(
            prog='cloudconfig-schema',
            description='Validate cloud-config files or document schema')
    parser.add_argument('-c', '--config-file',
                        help='Path of the cloud-config yaml file to validate')
    parser.add_argument('-d', '--doc', action="store_true", default=False,
                        help='Print schema documentation')
    parser.add_argument('--annotate', action="store_true", default=False,
                        help='Annotate existing cloud-config file with errors')
    return parser


def handle_schema_args(name, args):
    """Handle provided schema args and perform the appropriate actions."""
    exclusive_args = [args.config_file, args.doc]
    if not any(exclusive_args) or all(exclusive_args):
        error('Expected either --config-file argument or --doc')
    full_schema = get_schema()
    if args.config_file:
        try:
            validate_cloudconfig_file(
                args.config_file, full_schema, args.annotate)
        except (SchemaValidationError, RuntimeError) as e:
            if not args.annotate:
                error(str(e))
        else:
            print("Valid cloud-config file {0}".format(args.config_file))
    if args.doc:
        for subschema in full_schema['allOf']:
            print(get_schema_doc(subschema))


def main():
    """Tool to validate schema of a cloud-config file or print schema docs."""
    parser = get_parser()
    handle_schema_args('cloudconfig-schema', parser.parse_args())
    return 0


if __name__ == '__main__':
    sys.exit(main())

# vi: ts=4 expandtab