change the xml cleaner to set tags as ###.*

5 files changed, 34 insertions, 39 deletions

diff --git a/.gitignore b/.gitignore
index 5e64fdb..7e99e36 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,16 +1 @@
-# User-specific stuff:
-.idea/workspace.xml
-.idea/tasks.xml
-.idea/dictionaries
-.idea/vcs.xml
-.idea/jsLibraryMappings.xml
-
-# Sensitive or high-churn files:
-.idea/dataSources.ids
-.idea/dataSources.xml
-.idea/dataSources.local.xml
-.idea/sqlDataSources.xml
-.idea/dynamic.xml
-.idea/uiDesigner.xml
-
 *.pyc
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
index de9bbc8..8e8cee7 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -1,4 +1,14 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 2.7.10 (C:\Python27\python.exe)" project-jdk-type="Python SDK" />
+  <component name="ProjectLevelVcsManager" settingsEditedManually="false">
+    <OptionsSetting value="true" id="Add" />
+    <OptionsSetting value="true" id="Remove" />
+    <OptionsSetting value="true" id="Checkout" />
+    <OptionsSetting value="true" id="Update" />
+    <OptionsSetting value="true" id="Status" />
+    <OptionsSetting value="true" id="Edit" />
+    <ConfirmationsSetting value="0" id="Add" />
+    <ConfirmationsSetting value="0" id="Remove" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.5.2 (C:\Users\Ilsar\Anaconda3\python.exe)" project-jdk-type="Python SDK" />
 </project>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
index 9a7bd2d..405d108 100644
--- a/.idea/modules.xml
+++ b/.idea/modules.xml
@@ -2,7 +2,7 @@
 <project version="4">
   <component name="ProjectModuleManager">
     <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/lib2wiki.iml" filepath="$PROJECT_DIR$/.idea/lib2wiki.iml" />
+      <module fileurl="file://$PROJECT_DIR$/.idea/parser.iml" filepath="$PROJECT_DIR$/.idea/parser.iml" />
     </modules>
   </component>
 </project>
\ No newline at end of file
diff --git a/.idea/lib2wiki.iml b/.idea/parser.iml
index 6711606..6f63a63 100644
--- a/.idea/lib2wiki.iml
+++ b/.idea/parser.iml
@@ -6,6 +6,7 @@
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="TestRunnerService">
-    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+    <option name="projectConfiguration" value="Nosetests" />
+    <option name="PROJECT_TEST_RUNNER" value="Nosetests" />
   </component>
 </module>
\ No newline at end of file
diff --git a/parsers/INL_xml_parser.py b/parsers/INL_xml_parser.py
index 2ea9a9b..671d2d9 100644
--- a/parsers/INL_xml_parser.py
+++ b/parsers/INL_xml_parser.py
@@ -6,29 +6,28 @@ class INLXmlParser:
         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')
+    #expects to get a record as ElementTree
+    def clearxml(self, record):
+        # root ==  list of tags
+        root = record.getroot()
 
         # 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'
+        # create new record
+        newRecord = ET.Element('record')
+        for field in root:
+            fieldtag = field.attrib.get('tag')
+            if fieldtag in self.whitelist:
+                tempTag = fieldtag
+                # tag 700 and 400 are the same
+                if tempTag == '700':
+                    tempTag = '400'
+                for data in field:
+                    newFieldTag = tempTag
+                    newFieldTag +='.'
+                    newFieldTag += data.attrib.get('code')
                     newTag = ET.SubElement(newRecord, 'datafield', {'tag': newFieldTag})
-                    for data in field:
-                        subData = ET.SubElement(newTag, data.tag, data.attrib)
-                        subData.text = data.text
+                    newTag.text = data.text
 
-        newTree = ET.ElementTree(newTreeRoot)
-        return newTree
+        newRecordTree = ET.ElementTree(newRecord)
+        return newRecordTree