1 | """ |
---|
2 | Generic XML reader |
---|
3 | """ |
---|
4 | ############################################################################ |
---|
5 | #This software was developed by the University of Tennessee as part of the |
---|
6 | #Distributed Data Analysis of Neutron Scattering Experiments (DANSE) |
---|
7 | #project funded by the US National Science Foundation. |
---|
8 | #If you use DANSE applications to do scientific research that leads to |
---|
9 | #publication, we ask that you acknowledge the use of the software with the |
---|
10 | #following sentence: |
---|
11 | #This work benefited from DANSE software developed under NSF award DMR-0520547. |
---|
12 | #copyright 2008,2009 University of Tennessee |
---|
13 | ############################################################################# |
---|
14 | |
---|
15 | from lxml import etree |
---|
16 | parser = etree.ETCompatXMLParser(remove_comments=True, remove_pis=False) |
---|
17 | |
---|
18 | class XMLreader(): |
---|
19 | |
---|
20 | xml = None |
---|
21 | xmldoc = None |
---|
22 | xmlroot = None |
---|
23 | schema = None |
---|
24 | schemadoc = None |
---|
25 | processingInstructions = None |
---|
26 | |
---|
27 | def __init__(self, xml = None, schema = None, root = None): |
---|
28 | self.xml = xml |
---|
29 | self.schema = schema |
---|
30 | self.processingInstructions = {} |
---|
31 | if xml is not None: |
---|
32 | self.setXMLFile(xml, root) |
---|
33 | else: |
---|
34 | self.xmldoc = None |
---|
35 | self.xmlroot = None |
---|
36 | if schema is not None: |
---|
37 | self.setSchema(schema) |
---|
38 | else: |
---|
39 | self.schemadoc = None |
---|
40 | |
---|
41 | def reader(self): |
---|
42 | """ |
---|
43 | Read in an XML file into memory and return an lxml dictionary |
---|
44 | """ |
---|
45 | if self.validateXML(): |
---|
46 | self.xmldoc = etree.parse(self.xml, parser = parser) |
---|
47 | else: |
---|
48 | raise etree.ValidationError(self, self.findInvalidXML()) |
---|
49 | return self.xmldoc |
---|
50 | |
---|
51 | def setXMLFile(self, xml, root = None): |
---|
52 | """ |
---|
53 | Set the XML file and parse |
---|
54 | """ |
---|
55 | try: |
---|
56 | self.xml = xml |
---|
57 | self.xmldoc = etree.parse(self.xml, parser = parser) |
---|
58 | self.xmlroot = self.xmldoc.getroot() |
---|
59 | except Exception: |
---|
60 | self.xml = None |
---|
61 | self.xmldoc = None |
---|
62 | self.xmlroot = None |
---|
63 | |
---|
64 | def setSchema(self, schema): |
---|
65 | """ |
---|
66 | Set the schema file and parse |
---|
67 | """ |
---|
68 | try: |
---|
69 | self.schema = schema |
---|
70 | self.schemadoc = etree.parse(self.schema, parser = parser) |
---|
71 | except Exception: |
---|
72 | self.schema = None |
---|
73 | self.schemadoc = None |
---|
74 | |
---|
75 | def validateXML(self): |
---|
76 | """ |
---|
77 | Checks to see if the XML file meets the schema |
---|
78 | """ |
---|
79 | valid = True |
---|
80 | if self.schema is not None: |
---|
81 | self.parseSchemaAndDoc() |
---|
82 | schemaCheck = etree.XMLSchema(self.schemadoc) |
---|
83 | valid = schemaCheck.validate(self.xmldoc) |
---|
84 | return valid |
---|
85 | |
---|
86 | def findInvalidXML(self): |
---|
87 | """ |
---|
88 | Finds the first offending element that should not be present in XML file |
---|
89 | """ |
---|
90 | firstError = "" |
---|
91 | self.parseSchemaAndDoc() |
---|
92 | schema = etree.XMLSchema(self.schemadoc) |
---|
93 | try: |
---|
94 | firstError = schema.assertValid(self.xmldoc) |
---|
95 | except etree.DocumentInvalid as e: |
---|
96 | firstError = str(e) |
---|
97 | return firstError |
---|
98 | |
---|
99 | def parseSchemaAndDoc(self): |
---|
100 | """ |
---|
101 | Creates a dictionary of the parsed schema and xml files. |
---|
102 | """ |
---|
103 | self.setXMLFile(self.xml) |
---|
104 | self.setSchema(self.schema) |
---|
105 | |
---|
106 | def toString(self, etreeElement): |
---|
107 | """ |
---|
108 | Converts and etree element into a string |
---|
109 | """ |
---|
110 | return etree.tostring(etreeElement) |
---|
111 | |
---|
112 | def setProcessingInstructions(self): |
---|
113 | """ |
---|
114 | Take out all processing instructions and create a dictionary from them |
---|
115 | """ |
---|
116 | dic = {} |
---|
117 | pi = self.xmlroot.getprevious() |
---|
118 | while pi is not None: |
---|
119 | attr = {} |
---|
120 | pi_name = "" |
---|
121 | pi_string = self.toString(pi) |
---|
122 | if isinstance(pi_string, str): |
---|
123 | pi_string = pi_string.replace("<?", "").replace("?>", "") |
---|
124 | split = pi_string.split(" ", 1) |
---|
125 | pi_name = split[0] |
---|
126 | attr = split[1] |
---|
127 | new_pi_name = self._create_unique_key(dic, pi_name) |
---|
128 | dic[new_pi_name] = attr |
---|
129 | pi = pi.getprevious() |
---|
130 | self.processingInstructions = dic |
---|
131 | |
---|
132 | def _create_unique_key(self, dictionary, name, i = 0): |
---|
133 | """ |
---|
134 | Create a unique key value for any dictionary to prevent overwriting |
---|
135 | Recurses until a unique key value is found. |
---|
136 | |
---|
137 | :param dictionary: A dictionary with any number of entries |
---|
138 | :param name: The index of the item to be added to dictionary |
---|
139 | :param i: The number to be appended to the name, starts at 0 |
---|
140 | """ |
---|
141 | if dictionary.get(name) is not None: |
---|
142 | i += 1 |
---|
143 | name = name.split("_")[0] |
---|
144 | name += "_{0}".format(i) |
---|
145 | name = self._create_unique_key(dictionary, name, i) |
---|
146 | return name |
---|
147 | |
---|
148 | |
---|