created the INL xml parser

2 files changed, 41 insertions, 0 deletions

diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/parsers/INL_xml_parser.py b/parsers/INL_xml_parser.py
new file mode 100644
index 0000000..57ceebd
--- /dev/null
+++ b/parsers/INL_xml_parser.py
@@ -0,0 +1,35 @@
+import xml.etree.cElementTree as ET
+
+
+class INLXmlParser:
+    def __init__(self, lst, path):
+        self.whitelist = lst
+        self.xmlpath = path
+
+    def clearxml(self):
+        xmltree = ET.parse(self.xmlpath)
+        # root ==  list of records
+        root = xmltree.getroot()
+
+        # create new data
+        newTreeRoot = ET.Element('data')
+
+        # scan the datafields in the records and copy to the new one only the tags in the whitelist
+        for record in root:
+            # create new record
+            newRecord = ET.SubElement(newTreeRoot, 'record')
+            for field in record:
+                fieldtag = field.attrib.get('tag')
+                if fieldtag in self.whitelist:
+                    newFieldTag = fieldtag
+                    # tag 700 and 400 are the same
+                    if newFieldTag == '700':
+                        newFieldTag = '400'
+                    newTag = ET.SubElement(newRecord, 'datafield', {'tag': newFieldTag})
+                    for data in field:
+                        subData = ET.SubElement(newTag, data.tag, data.attrib)
+                        subData.text = data.text
+
+        newTree = ET.ElementTree(newTreeRoot)
+        newTree.write('C:/Users/Ilsar/Documents/datahack/outTest.xml')
+        return newTree