From 652781137f3856fef98e3063766f9f3b1a984a2e Mon Sep 17 00:00:00 2001
From: roy lewin <roy.lewin@gmail.com>
Date: Thu, 22 Sep 2016 01:43:21 +0300
Subject: Added xml_reader.py, and edited INL_xml_parser to work on a
 per-record basis

---
 parsers/INL_xml_parser.py | 47 +++++++++++++++++++++++------------------------
 1 file changed, 23 insertions(+), 24 deletions(-)

(limited to 'parsers/INL_xml_parser.py')

diff --git a/parsers/INL_xml_parser.py b/parsers/INL_xml_parser.py
index 2ea9a9b..512d46e 100644
--- a/parsers/INL_xml_parser.py
+++ b/parsers/INL_xml_parser.py
@@ -1,34 +1,33 @@
-import xml.etree.cElementTree as ET
+try:
+    import xml.etree.cElementTree as ET
+except ImportError:
+    import xml.etree.ElementTree as ET
+
+KNOWN_FIELD_TAGS = ['100', '110', '151']
 
 
 class INLXmlParser:
-    def __init__(self, lst, path):
-        self.whitelist = lst
-        self.xmlpath = path
+    def __init__(self, reader, whitelist=None):
+        self.reader = reader
+        self.whitelist = whitelist or KNOWN_FIELD_TAGS
 
     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
+        # # 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 self.reader:
+            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)
         return newTree
-- 
cgit v1.2.3