check_xsd.py 6.7 KB
Newer Older
canterburym's avatar
canterburym committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
import logging

import glob
import sys
import argparse
from pathlib import Path
from pprint import pprint
import os

from lxml import etree
from xml.etree.ElementTree import ParseError
from xmlschema import XMLSchema, XMLSchemaParseError

def BuildSchemaDictonary (fileList):
    if len(fileList) == 0:
        logging.info("No schema files provided")
        return []

    logging.info("Schema locations:")
    schemaLocations = []
    for schemaFile in fileList:
        try:
            xs = XMLSchema(schemaFile, validation='skip')
canterburym's avatar
canterburym committed
24
            schemaLocations.append((xs.target_namespace, str(Path(schemaFile).resolve())))
canterburym's avatar
canterburym committed
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
            logging.info(" [ {0}  ->  {1} ]".format(xs.default_namespace, schemaFile))
        except ParseError as ex:
            logging.warning (" [ {0} failed to parse:  {1} ]".format(schemaFile, ex))
    return schemaLocations


def BuildSchema (coreFile, fileList = None):
    schemaLocations = []
    if fileList and len(fileList) > 0:
        schemaLocations = BuildSchemaDictonary(fileList)

    coreSchema = XMLSchema(str(Path(coreFile)), locations=schemaLocations)
    return coreSchema

def ValidateSingleFile (schemaFile):
    try:
        xs = XMLSchema(schemaFile, validation='skip')
    except ParseError as ex:
        logging.warning (" [ {0} failed to parse:  {1} ]".format(schemaFile, ex))
        return ex
    return None


def ValidateXSDFiles (fileList):
    if len(fileList) == 0:
        logging.info("No schema files provided")
        return {}
    
    schemaLocations = BuildSchemaDictonary(fileList)
    errors = {}
canterburym's avatar
canterburym committed
55
    schemaDictionary = {}
canterburym's avatar
canterburym committed
56
57
58
59
60
61
62

    logging.info("Schema validation:")
    for schemaFile in fileList:
        try:
            schema = XMLSchema(schemaFile, locations = schemaLocations)
            logging.info(schemaFile + ": OK")
            errors[schemaFile] = []
canterburym's avatar
canterburym committed
63
            schemaDictionary[schema.target_namespace] = schema
canterburym's avatar
canterburym committed
64
65
66
67
68
69
70
        except XMLSchemaParseError as ex:
            if (ex.schema_url) and (ex.schema_url != ex.origin_url):
                logging.info("  Error {1} comes from {0}, suppressing".format(ex.schema_url, ex.message))
                errors[schemaFile] = []
            else:
                logging.warning(schemaFile + ": Failed validation ({0})".format(ex))
                errors[schemaFile] = [ex.message]
canterburym's avatar
canterburym committed
71
    return errors, schemaDictionary
canterburym's avatar
canterburym committed
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94


def ValidateInstanceDocuments (coreFile, supportingSchemas, instanceDocs):
    if (instanceDocs is None) or len(instanceDocs) == 0:
        logging.warning ("No instance documents provided")
        return []

    schema = BuildSchema(coreFile, supportingSchemas)
    errors = []
    for instanceDoc in instanceDocs:
        try:
            schema.validate(instanceDoc)
            logging.info ("{0} passed validation".format(instanceDoc))
        except Exception as ex:
            logging.error ("{0} failed validation: {1}".format(instanceDoc, ex))
    return errors
    


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument("-v", "--verbosity", help="verbosity level", action="count", default=0)
    parser.add_argument("input", help="include a directory or file", action="append", nargs="+")
canterburym's avatar
canterburym committed
95
    parser.add_argument("-p", "--primaryNamespace", help="Primary schema namespace for instance doc validation")
canterburym's avatar
canterburym committed
96
97
98
99
100
101
102
103
104
    args = parser.parse_args()

    logging.getLogger().setLevel(logging.WARNING)
    if (args.verbosity >= 1):
        logging.getLogger().setLevel(logging.INFO)
    if (args.verbosity >= 2):
        logging.getLogger().setLevel(logging.DEBUG)
        logging.debug("Very verbose selected")

canterburym's avatar
canterburym committed
105

canterburym's avatar
canterburym committed
106
107
    logging.debug(f"Path: {args.input}")
    includeFileList = []
canterburym's avatar
canterburym committed
108
    includeInstanceDocList = []
canterburym's avatar
canterburym committed
109
110
111
112
113
114
115
116
117
118
    for path in args.input[0]:
        p = Path(path)
        if not p.exists():
            logging.error(f"Include path {path} not found")
            exit(1)
        if p.is_dir():
            logging.debug(f"Expanding directory")
            for g in glob.glob(os.path.join(str(p), "*.xsd")):
                logging.info(f">Including {g}")
                includeFileList.append(g)
canterburym's avatar
canterburym committed
119
120
121
            for g in glob.glob(os.path.join(str(p), "*.xml")):
                logging.info(f">Including instance doc {g}")
                includeInstanceDocList.append(g)
canterburym's avatar
canterburym committed
122
        else:
canterburym's avatar
canterburym committed
123
124
125
126
127
128
129
            logging.info(f">Including {p.absolute()}")
            if str(p.absolute()).endswith('.xml'):
                includeInstanceDocList.append(str(p.absolute()))
            elif str(p.absolute()).endswith('.xsd'):
                includeFileList.append(str(p.absolute()))
            else:
                logging.warning(f'Ignoring file {p.absolute()}')
canterburym's avatar
canterburym committed
130
    
canterburym's avatar
canterburym committed
131
132
133
134
    if len(includeInstanceDocList) and (args.primaryNamespace is None):
        print("Cannot validate instance documents without specifying a primary namespace (use -h for usage guidelines)")
        exit(-1)

canterburym's avatar
canterburym committed
135
136
    syntaxErrors = 0
    
canterburym's avatar
canterburym committed
137
    print ("=============================")
canterburym's avatar
canterburym committed
138
139
140
141
142
143
144
145
146
147
148
149
150
151
    print ("XSD syntax checks:")
    print ("-----------------------------")
    for file in includeFileList:
        error = ValidateSingleFile(file)
        if (error):
            print (f"  {file} : Syntax error [{error}]")
            syntaxErrors += 1
        else:
            print (f"  {file} : OK")

    print ("-----------------------------")
    if (syntaxErrors > 0):
        print (f"{syntaxErrors} syntax errors detected")
        exit(syntaxErrors)
canterburym's avatar
canterburym committed
152
153
    else:
        print ("0 syntax errors detected")
canterburym's avatar
canterburym committed
154

canterburym's avatar
canterburym committed
155
    results, schemaDict = ValidateXSDFiles(includeFileList)
canterburym's avatar
canterburym committed
156
    
canterburym's avatar
canterburym committed
157
    print ("=============================")
canterburym's avatar
canterburym committed
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    print ("XSD build checks:")
    print ("-----------------------------")
    errorCount = 0
    for fileName, errors in results.items():
        if len(errors) > 0:
            errorCount += len(errors)
            print (f"  {fileName}: {len(errors)} errors")
            for error in errors:
                if isinstance(error, XMLSchemaParseError):
                    print (error.msg)
                else:
                    print (f"      {str(error.strip())}")
        else:
            print (f"  {fileName}: OK")

    print ("-----------------------------")
    print (f"{errorCount} build errors detected")
canterburym's avatar
canterburym committed
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
    if (errorCount > 0):
        exit(errorCount)

    print ("=============================")
    print ("Instance document checks")
    print ("-----------------------------")
    errorCount = 0

    primarySchema = schemaDict[args.primaryNamespace]
    for instanceDoc in includeInstanceDocList:
        try:
            results = primarySchema.validate(instanceDoc)
            print (f"  {instanceDoc} : OK")
        except Exception as ex:
            errorCount += 1
            print (f"  {instanceDoc} : {str(ex)}")
    print ("-----------------------------")
    print (f"{errorCount} instance doc errors detected")
    print ("=============================")
    exit(errorCount)