class MarcReader(JsonReader):
"""
Reader class that understands MARC21 as base format
"""
@staticmethod
def split_blob(blob):
"""
Splits the blob using <record.*?>.*?</record> as pattern.
Note 1: Taken from invenio.bibrecord:create_records
Note 2: Use the DOTALL flag to include newlines.
"""
import re
regex = re.compile("<record.*?>.*?</record>", re.DOTALL)
return regex.findall(blob)
def _prepare_blob(self):
"""
Transforms the blob into rec_tree structure to use it in the standar
translation phase inside C{JsonReader}
"""
self.rec_tree = CoolDict()
try:
if self.blob_wrapper.schema.lower().startswith("file:"):
self.blob_wrapper.blob = open(self.blob_wrapper.blob_file_name, "r").read()
if self.blob_wrapper.schema.lower() in ["recstruct"]:
self.__create_rectree_from_recstruct()
elif self.blob_wrapper.schema.lower() in ["xml", "file:xml"]:
# TODO: Implement translation directrly from xml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
except AttributeError:
# Assume marcxml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
def __create_rectree_from_recstruct(self):
"""
Using rectruct as base format it creates the intermediate structure that
_translate will use.
"""
for key, values in self.blob_wrapper.blob.iteritems():
if key < "010" and key.isdigit():
# Control field, it assumes controlfields are numeric only
self.rec_tree[key] = CoolList([value[3] for value in values])
else:
for value in values:
field = CoolDict()
for subfield in value[0]:
field.extend(subfield[0], subfield[1])
self.rec_tree.extend((key + value[1] + value[2]).replace(" ", "_"), field)
class MarcReader(JsonReader):
"""
Reader class that understands MARC21 as base format
"""
@staticmethod
def split_blob(blob, schema):
"""
Splits the blob using <record.*?>.*?</record> as pattern.
Note 1: Taken from invenio.bibrecord:create_records
Note 2: Use the DOTALL flag to include newlines.
"""
import re
regex = re.compile('<record.*?>.*?</record>', re.DOTALL)
return regex.findall(blob)
def _prepare_blob(self):
"""
Transforms the blob into rec_tree structure to use it in the standar
translation phase inside C{JsonReader}
"""
self.rec_tree = CoolDict()
try:
if self.blob_wrapper.schema.lower().startswith('file:'):
self.blob_wrapper.blob = open(self.blob_wrapper.blob_file_name,
'r').read()
if self.blob_wrapper.schema.lower() in ['recstruct']:
self.__create_rectree_from_recstruct()
elif self.blob_wrapper.schema.lower() in ['xml', 'file:xml']:
#TODO: Implement translation directrly from xml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(
self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
except AttributeError:
#Assume marcxml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
def __create_rectree_from_recstruct(self):
"""
Using rectruct as base format it creates the intermediate structure that
_translate will use.
"""
for key, values in self.blob_wrapper.blob.iteritems():
if key < '010' and key.isdigit():
#Control field, it assumes controlfields are numeric only
self.rec_tree[key] = CoolList([value[3] for value in values])
else:
for value in values:
field = CoolDict()
for subfield in value[0]:
field.extend(subfield[0], subfield[1])
self.rec_tree.extend(
(key + value[1] + value[2]).replace(' ', '_'), field)
def __create_rectree_from_recstruct(self):
"""
Using rectruct as base format it creates the intermediate structure that
_translate will use.
"""
for key, values in self.blob_wrapper.blob.iteritems():
if key < '010' and key.isdigit():
#Control field, it assumes controlfields are numeric only
self.rec_tree[key] = CoolList([value[3] for value in values])
else:
for value in values:
field = CoolDict()
for subfield in value[0]:
field.extend(subfield[0], subfield[1])
self.rec_tree.extend((key + value[1] + value[2]).replace(' ', '_'), field)
def __create_rectree_from_recstruct(self):
"""
Using rectruct as base format it creates the intermediate structure that
_translate will use.
"""
for key, values in self.blob_wrapper.blob.iteritems():
if key < '010' and key.isdigit():
#Control field, it assumes controlfields are numeric only
self.rec_tree[key] = CoolList([value[3] for value in values])
else:
for value in values:
field = CoolDict()
for subfield in value[0]:
field.extend(subfield[0], subfield[1])
self.rec_tree.extend(
(key + value[1] + value[2]).replace(' ', '_'), field)
def test_cool_list_and_dict(self):
"""Bibfield Utils, CoolList and CoolDict - Unit tests"""
d = CoolDict()
l = CoolList()
d['a'] = l
self.assertTrue(d.consumed)
l.append(1)
l.append(2)
d['a'] = l
self.assertFalse(d.consumed)
d['b'] = CoolList([{'a':1}, {'a':2}])
self.assertFalse(d.consumed)
[v for dummy_k, v in d.iteritems()]
self.assertFalse(d.consumed)
[i for i in d['a']]
[v for i in d['b'] for dummy_k, v in i.iteritems()]
self.assertTrue(d.consumed)
def test_cool_list_and_dict(self):
"""Bibfield Utils, CoolList and CoolDict - Unit tests"""
d = CoolDict()
l = CoolList()
d['a'] = l
self.assertTrue(d.consumed)
l.append(1)
l.append(2)
d['a'] = l
self.assertFalse(d.consumed)
d['b'] = CoolList([{'a': 1}, {'a': 2}])
self.assertFalse(d.consumed)
[v for dummy_k, v in d.iteritems()]
self.assertFalse(d.consumed)
[i for i in d['a']]
[v for i in d['b'] for dummy_k, v in i.iteritems()]
self.assertTrue(d.consumed)
def test_cool_dict(self):
"""Bibfield Utils, CoolDict - Unit tests"""
d = CoolDict()
d['a'] = 1
d['b'] = 2
d['c'] = 3
self.assertFalse(d.consumed)
d['a']
self.assertFalse(d.consumed)
[v for dummy_k, v in d.iteritems()]
self.assertTrue(d.consumed)
d['b'] = {'d': 1}
self.assertFalse(d.consumed)
d['b']
self.assertFalse(d.consumed)
[v for dummy_k, v in d['b'].iteritems()]
self.assertTrue(d.consumed)
d.extend('a', 11)
self.assertFalse(d.consumed)
self.assertTrue(isinstance(d['a'], CoolList))
[i for i in d['a']]
self.assertTrue(d.consumed)
def test_cool_dict(self):
"""Bibfield Utils, CoolDict - Unit tests"""
d = CoolDict()
d["a"] = 1
d["b"] = 2
d["c"] = 3
self.assertFalse(d.consumed)
d["a"]
self.assertFalse(d.consumed)
[v for dummy_k, v in d.iteritems()]
self.assertTrue(d.consumed)
d["b"] = {"d": 1}
self.assertFalse(d.consumed)
d["b"]
self.assertFalse(d.consumed)
[v for dummy_k, v in d["b"].iteritems()]
self.assertTrue(d.consumed)
d.extend("a", 11)
self.assertFalse(d.consumed)
self.assertTrue(isinstance(d["a"], CoolList))
[i for i in d["a"]]
self.assertTrue(d.consumed)
def test_cool_dict(self):
"""Bibfield Utils, CoolDict - Unit tests"""
d = CoolDict()
d['a'] = 1
d['b'] = 2
d['c'] = 3
self.assertFalse(d.consumed)
d['a']
self.assertFalse(d.consumed)
[v for dummy_k, v in d.iteritems()]
self.assertTrue(d.consumed)
d['b'] = {'d': 1}
self.assertFalse(d.consumed)
d['b']
self.assertFalse(d.consumed)
[v for dummy_k, v in d['b'].iteritems()]
self.assertTrue(d.consumed)
d.extend('a', 11)
self.assertFalse(d.consumed)
self.assertTrue(isinstance(d['a'], CoolList))
[i for i in d['a']]
self.assertTrue(d.consumed)
def _prepare_blob(self):
"""
Transforms the blob into rec_tree structure to use it in the standar
translation phase inside C{JsonReader}
"""
self.rec_tree = CoolDict()
try:
if self.blob_wrapper.schema.lower().startswith('file:'):
self.blob_wrapper.blob = open(self.blob_wrapper.blob_file_name,
'r').read()
if self.blob_wrapper.schema.lower() in ['recstruct']:
self.__create_rectree_from_recstruct()
elif self.blob_wrapper.schema.lower() in ['xml', 'file:xml']:
#TODO: Implement translation directrly from xml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(
self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
except AttributeError:
#Assume marcxml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
def _prepare_blob(self):
"""
Transforms the blob into rec_tree structure to use it in the standar
translation phase inside C{JsonReader}
"""
self.rec_tree = CoolDict()
try:
if self.blob_wrapper.schema.lower().startswith('file:'):
self.blob_wrapper.blob = open(self.blob_wrapper.blob_file_name, 'r').read()
if self.blob_wrapper.schema.lower() in ['recstruct']:
self.__create_rectree_from_recstruct()
elif self.blob_wrapper.schema.lower() in ['xml', 'file:xml']:
#TODO: Implement translation directrly from xml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
except AttributeError:
#Assume marcxml
from invenio.bibrecord import create_record
self.blob_wrapper.blob = create_record(self.blob_wrapper.blob)[0]
self.__create_rectree_from_recstruct()
