diff --git a/modules/bibedit/lib/bibrecord.py b/modules/bibedit/lib/bibrecord.py
index 53579811c..066fc3eee 100644
--- a/modules/bibedit/lib/bibrecord.py
+++ b/modules/bibedit/lib/bibrecord.py
@@ -1,1525 +1,1538 @@
# -*- coding: utf-8 -*-
##
## This file is part of CDS Invenio.
## Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008 CERN.
##
## CDS Invenio is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 2 of the
## License, or (at your option) any later version.
##
## CDS Invenio is distributed in the hope that it will be useful, but
## WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
## General Public License for more details.
##
## You should have received a copy of the GNU General Public License
## along with CDS Invenio; if not, write to the Free Software Foundation, Inc.,
## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
"""BibRecord - XML MARC processing library for CDS Invenio.
For API, see create_record(), record_get_field_instances() and friends
in the source code of this file in the section entitled INTERFACE.
Note: Does not access the database, the input is MARCXML only."""
### IMPORT INTERESTING MODULES AND XML PARSERS
import re
import sys
try:
import psyco
PSYCO_AVAILABLE = True
except ImportError:
PSYCO_AVAILABLE = False
if sys.hexversion < 0x2040000:
# pylint: disable-msg=W0622
from sets import Set as set
# pylint: enable-msg=W0622
from invenio.bibrecord_config import CFG_MARC21_DTD, \
CFG_BIBRECORD_WARNING_MSGS, CFG_BIBRECORD_DEFAULT_VERBOSE_LEVEL, \
CFG_BIBRECORD_DEFAULT_CORRECT, CFG_BIBRECORD_PARSERS_AVAILABLE, \
InvenioBibRecordParserError, InvenioBibRecordFieldError
from invenio.config import CFG_BIBUPLOAD_EXTERNAL_OAIID_TAG
from invenio.textutils import encode_for_xml
# Some values used for the RXP parsing.
TAG, ATTRS, CHILDREN = 0, 1, 2
# Find out about the best usable parser:
AVAILABLE_PARSERS = []
# Do we remove singletons (empty tags)?
-CFG_BIBRECORD_KEEP_SINGLETONS = False
+# NOTE: this is currently set to True as there are some external workflow
+# exploiting singletons, e.g. bibupload -c used to delete fields, and
+# bibdocfile --fix-marc called on a record where the latest document
+# has been deleted.
+CFG_BIBRECORD_KEEP_SINGLETONS = True
try:
import pyRXP
if 'pyrxp' in CFG_BIBRECORD_PARSERS_AVAILABLE:
AVAILABLE_PARSERS.append('pyrxp')
except ImportError:
pass
try:
import Ft.Xml.Domlette
if '4suite' in CFG_BIBRECORD_PARSERS_AVAILABLE:
AVAILABLE_PARSERS.append('4suite')
except ImportError:
pass
try:
import xml.dom.minidom
import xml.parsers.expat
if 'minidom' in CFG_BIBRECORD_PARSERS_AVAILABLE:
AVAILABLE_PARSERS.append('minidom')
except ImportError:
pass
### INTERFACE / VISIBLE FUNCTIONS
def create_field(subfields=None, ind1=' ', ind2=' ', controlfield_value='',
global_position=-1):
"""
Returns a field created with the provided elements. Global position is
set arbitrary to -1."""
if subfields is None:
subfields = []
ind1, ind2 = _wash_indicators(ind1, ind2)
field = (subfields, ind1, ind2, controlfield_value, global_position)
_check_field_validity(field)
return field
def create_records(marcxml, verbose=CFG_BIBRECORD_DEFAULT_VERBOSE_LEVEL,
- correct=CFG_BIBRECORD_DEFAULT_CORRECT, parser=''):
+ correct=CFG_BIBRECORD_DEFAULT_CORRECT, parser='',
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a list of records from the marcxml description. Returns a
list of objects initiated by the function create_record(). Please
see that function's docstring."""
# Use the DOTALL flag to include newlines.
regex = re.compile('<record.*?>.*?</record>', re.DOTALL)
record_xmls = regex.findall(marcxml)
return [create_record(record_xml, verbose=verbose, correct=correct,
- parser=parser) for record_xml in record_xmls]
+ parser=parser, keep_singletons=keep_singletons) for record_xml in record_xmls]
def create_record(marcxml, verbose=CFG_BIBRECORD_DEFAULT_VERBOSE_LEVEL,
correct=CFG_BIBRECORD_DEFAULT_CORRECT, parser='',
- sort_fields_by_indicators=False):
+ sort_fields_by_indicators=False,
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a record object from the marcxml description.
Uses the best parser available in CFG_BIBRECORD_PARSERS_AVAILABLE or
the parser specified.
The returned object is a tuple (record, status_code, list_of_errors),
where status_code is 0 when there are errors, 1 when no errors.
The return record structure is as follows:
Record := {tag : [Field]}
Field := (Subfields, ind1, ind2, value)
Subfields := [(code, value)]
For example:
______
|record|
------
__________________________|_______________________________________
|record['001'] |record['909'] |record['520'] |
| | | |
[list of fields] [list of fields] [list of fields] ...
| ______|______________ |
|[0] |[0] |[1] | |[0]
___|_____ _____|___ ___|_____ ... ____|____
|Field 001| |Field 909| |Field 909| |Field 520|
--------- --------- --------- ---------
| _______________|_________________ | |
... |[0] |[1] |[2] | ... ...
| | | |
[list of subfields] 'C' '4'
___|__________________________________________
| | |
('a', 'value') ('b', 'value for subfield b') ('a', 'value for another a')
@param marcxml: an XML string representation of the record to create
@param verbose: the level of verbosity: 0 (silent), 1-2 (warnings),
3(strict:stop when errors)
@param correct: 1 to enable correction of marcxml syntax. Else 0.
@return: a tuple (record, status_code, list_of_errors), where status
code is 0 where there are errors, 1 when no errors"""
# Select the appropriate parser.
parser = _select_parser(parser)
try:
if parser == 'pyrxp':
- rec = _create_record_rxp(marcxml, verbose, correct)
+ rec = _create_record_rxp(marcxml, verbose, correct,
+ keep_singletons=keep_singletons)
elif parser == '4suite':
- rec = _create_record_4suite(marcxml)
+ rec = _create_record_4suite(marcxml,
+ keep_singletons=keep_singletons)
elif parser == 'minidom':
- rec = _create_record_minidom(marcxml)
+ rec = _create_record_minidom(marcxml,
+ keep_singletons=keep_singletons)
except InvenioBibRecordParserError, ex1:
return (None, 0, str(ex1))
# _create_record = {
# 'pyrxp': _create_record_rxp,
# '4suite': _create_record_4suite,
# 'minidom': _create_record_minidom,
# }
# try:
# rec = _create_record[parser](marcxml, verbose)
# except InvenioBibRecordParserError, ex1:
# return (None, 0, str(ex1))
if sort_fields_by_indicators:
_record_sort_by_indicators(rec)
errs = []
if correct:
# Correct the structure of the record.
errs = _correct_record(rec)
- return (rec, errs and 0 or 1, errs)
+ return (rec, int(not errs), errs)
def record_get_field_instances(rec, tag="", ind1=" ", ind2=" "):
"""Returns the list of field instances for the specified tag and
indicators of the record (rec).
Returns empty list if not found.
If tag is empty string, returns all fields
Parameters (tag, ind1, ind2) can contain wildcard %.
@param rec: a record structure as returned by create_record()
@param tag: a 3 characters long string
@param ind1: a 1 character long string
@param ind2: a 1 character long string
@param code: a 1 character long string
@return: a list of field tuples (Subfields, ind1, ind2, value,
field_position_global) where subfields is list of (code, value)"""
if not tag:
return rec.items()
else:
out = []
ind1, ind2 = _wash_indicators(ind1, ind2)
if '%' in tag:
# Wildcard in tag. Check all possible
for field_tag in rec:
if _tag_matches_pattern(field_tag, tag):
for possible_field_instance in rec[field_tag]:
if (ind1 in ('%', possible_field_instance[1]) and
ind2 in ('%', possible_field_instance[2])):
out.append(possible_field_instance)
else:
# Completely defined tag. Use dict
for possible_field_instance in rec.get(tag, []):
if (ind1 in ('%', possible_field_instance[1]) and
ind2 in ('%', possible_field_instance[2])):
out.append(possible_field_instance)
return out
def record_add_field(rec, tag, ind1=' ', ind2=' ', controlfield_value='',
subfields=None, field_position_global=None, field_position_local=None):
"""
Adds a new field into the record.
If field_position_global or field_position_local is specified then
this method will insert the new field at the desired position.
Otherwise a global field position will be computed in order to
insert the field at the best position (first we try to keep the
order of the tags and then we insert the field at the end of the
fields with the same tag).
If both field_position_global and field_position_local are present,
then field_position_local takes precedence.
@param rec: the record data structure
@param tag: the tag of the field to be added
@param ind1: the first indicator
@param ind2: the second indicator
@param controlfield_value: the value of the controlfield
@param subfields: the subfields (a list of tuples (code, value))
@param field_position_global: the global field position (record wise)
@param field_position_local: the local field position (tag wise)
@return: the global field position of the newly inserted field or -1 if the
operation failed
"""
error = validate_record_field_positions_global(rec)
if error:
# FIXME one should write a message here
pass
# Clean the parameters.
if subfields is None:
subfields = []
ind1, ind2 = _wash_indicators(ind1, ind2)
if controlfield_value and (ind1 != ' ' or ind2 != ' ' or subfields):
return -1
# Detect field number to be used for insertion:
# Dictionaries for uniqueness.
tag_field_positions_global = {}.fromkeys([field[4]
for field in rec.get(tag, [])])
all_field_positions_global = {}.fromkeys([field[4]
for fields in rec.values()
for field in fields])
if field_position_global is None and field_position_local is None:
# Let's determine the global field position of the new field.
if tag in rec:
try:
field_position_global = max([field[4] for field in rec[tag]]) \
+ 1
except IndexError:
if tag_field_positions_global:
field_position_global = max(tag_field_positions_global) + 1
elif all_field_positions_global:
field_position_global = max(all_field_positions_global) + 1
else:
field_position_global = 1
else:
if tag in ('FMT', 'FFT'):
# Add the new tag to the end of the record.
if tag_field_positions_global:
field_position_global = max(tag_field_positions_global) + 1
elif all_field_positions_global:
field_position_global = max(all_field_positions_global) + 1
else:
field_position_global = 1
else:
# Insert the tag in an ordered way by selecting the
# right global field position.
immediate_lower_tag = '000'
for rec_tag in rec:
if (tag not in ('FMT', 'FFT') and
immediate_lower_tag < rec_tag < tag):
immediate_lower_tag = rec_tag
if immediate_lower_tag == '000':
field_position_global = 1
else:
field_position_global = rec[immediate_lower_tag][-1][4] + 1
field_position_local = len(rec.get(tag, []))
_shift_field_positions_global(rec, field_position_global, 1)
elif field_position_local is not None:
if tag in rec:
if field_position_local >= len(rec[tag]):
field_position_global = rec[tag][-1][4] + 1
else:
field_position_global = rec[tag][field_position_local][4]
_shift_field_positions_global(rec, field_position_global, 1)
else:
if all_field_positions_global:
field_position_global = max(all_field_positions_global) + 1
else:
# Empty record.
field_position_global = 1
elif field_position_global is not None:
# If the user chose an existing global field position, shift all the
# global field positions greater than the input global field position.
if tag not in rec:
if all_field_positions_global:
field_position_global = max(all_field_positions_global) + 1
else:
field_position_global = 1
field_position_local = 0
elif field_position_global < min(tag_field_positions_global):
field_position_global = min(tag_field_positions_global)
_shift_field_positions_global(rec, min(tag_field_positions_global),
1)
field_position_local = 0
elif field_position_global > max(tag_field_positions_global):
field_position_global = max(tag_field_positions_global) + 1
_shift_field_positions_global(rec,
max(tag_field_positions_global) + 1, 1)
field_position_local = len(rec.get(tag, []))
else:
if field_position_global in tag_field_positions_global:
_shift_field_positions_global(rec, field_position_global, 1)
field_position_local = 0
for position, field in enumerate(rec[tag]):
if field[4] == field_position_global + 1:
field_position_local = position
# Create the new field.
newfield = (subfields, ind1, ind2, str(controlfield_value),
field_position_global)
rec.setdefault(tag, []).insert(field_position_local, newfield)
# Return new field number:
return field_position_global
def record_has_field(rec, tag):
"""
Checks if the tag exists in the record.
@param rec: the record data structure
@param the: field
@return: a boolean
"""
return tag in rec
def record_delete_field(rec, tag, ind1=' ', ind2=' ',
field_position_global=None, field_position_local=None):
"""
If global field position is specified, deletes the field with the
corresponding global field position.
If field_position_local is specified, deletes the field with the
corresponding local field position and tag.
Else deletes all the fields matching tag and optionally ind1 and
ind2.
If both field_position_global and field_position_local are present,
then field_position_local takes precedence.
@param rec: the record data structure
@param tag: the tag of the field to be deleted
@param ind1: the first indicator of the field to be deleted
@param ind2: the second indicator of the field to be deleted
@param field_position_global: the global field position (record wise)
@param field_position_local: the local field position (tag wise)
@return: the list of deleted fields
"""
error = validate_record_field_positions_global(rec)
if error:
# FIXME one should write a message here.
pass
if tag not in rec:
return False
ind1, ind2 = _wash_indicators(ind1, ind2)
deleted = []
newfields = []
if field_position_global is None and field_position_local is None:
# Remove all fields with tag 'tag'.
for field in rec[tag]:
if field[1] != ind1 or field[2] != ind2:
newfields.append(field)
else:
deleted.append(field)
rec[tag] = newfields
elif field_position_global is not None:
# Remove the field with 'field_position_global'.
for field in rec[tag]:
if (field[1] != ind1 and field[2] != ind2 or
field[4] != field_position_global):
newfields.append(field)
else:
deleted.append(field)
rec[tag] = newfields
elif field_position_local is not None:
# Remove the field with 'field_position_local'.
try:
del rec[tag][field_position_local]
except IndexError:
return []
if not rec[tag]:
# Tag is now empty, remove it.
del rec[tag]
return deleted
def record_delete_fields(rec, tag, field_positions_local=None):
"""
Delete all/some fields defined with MARC tag 'tag' from record 'rec'.
@param rec: a record structure.
@type rec: tuple
@param tag: three letter field.
@type tag: string
@param field_position_local: if set, it is the list of local positions
within all the fields with the specified tag, that should be deleted.
If not set all the fields with the specified tag will be deleted.
@type field_position_local: sequence
@return: the list of deleted fields.
@rtype: list
@note: the record is modified in place.
"""
if tag not in rec:
return []
new_fields, deleted_fields = [], []
for position, field in enumerate(rec.get(tag, [])):
if field_positions_local is None or position in field_positions_local:
deleted_fields.append(field)
else:
new_fields.append(field)
if new_fields:
rec[tag] = new_fields
else:
del rec[tag]
return deleted_fields
def record_add_fields(rec, tag, fields, field_position_local=None,
field_position_global=None):
"""
Adds the fields into the record at the required position. The
position is specified by the tag and the field_position_local in
the list of fields.
@param rec: a record structure
@param tag: the tag of the fields
to be moved
@param field_position_local: the field_position_local to which the
field will be inserted. If not specified, appends the fields to
the tag.
@param a: list of fields to be added
@return: -1 if the operation failed, or the field_position_local
if it was successful
"""
if field_position_local is None and field_position_global is None:
for field in fields:
record_add_field(rec, tag, ind1=field[1],
ind2=field[2], subfields=field[0],
controlfield_value=field[3])
else:
fields.reverse()
for field in fields:
record_add_field(rec, tag, ind1=field[1], ind2=field[2],
subfields=field[0], controlfield_value=field[3],
field_position_local=field_position_local,
field_position_global=field_position_global)
return field_position_local
def record_move_fields(rec, tag, field_positions_local,
field_position_local=None):
"""
Moves some fields to the position specified by
'field_position_local'.
@param rec: a record structure as returned by create_record()
@param tag: the tag of the fields to be moved
@param field_positions_local: the positions of the
fields to move
@param field_position_local: insert the field before that
field_position_local. If unspecified, appends the fields
@return: the field_position_local is the operation was successful
"""
fields = record_delete_fields(rec, tag,
field_positions_local=field_positions_local)
return record_add_fields(rec, tag, fields,
field_position_local=field_position_local)
def record_delete_subfield(rec, tag, subfield_code, ind1=' ', ind2=' '):
"""Deletes all subfields with subfield_code in the record."""
ind1, ind2 = _wash_indicators(ind1, ind2)
for field in rec.get(tag, []):
if field[1] == ind1 and field[2] == ind2:
field[0][:] = [subfield for subfield in field[0]
if subfield_code != subfield[0]]
def record_get_field(rec, tag, field_position_global=None,
field_position_local=None):
"""
Returns the the matching field. One has to enter either a global
field position or a local field position.
@return: a list of subfield tuples (subfield code, value).
@rtype: list
"""
if field_position_global is None and field_position_local is None:
raise InvenioBibRecordFieldError("A field position is required to "
"complete this operation.")
elif field_position_global is not None and field_position_local is not None:
raise InvenioBibRecordFieldError("Only one field position is required "
"to complete this operation.")
elif field_position_global:
if not tag in rec:
raise InvenioBibRecordFieldError("No tag '%s' in record." % tag)
for field in rec[tag]:
if field[4] == field_position_global:
return field
raise InvenioBibRecordFieldError("No field has the tag '%s' and the "
"global field position '%d'." % (tag, field_position_global))
else:
try:
return rec[tag][field_position_local]
except KeyError:
raise InvenioBibRecordFieldError("No tag '%s' in record." % tag)
except IndexError:
raise InvenioBibRecordFieldError("No field has the tag '%s' and "
"the local field position '%d'." % (tag, field_position_local))
def record_replace_field(rec, tag, new_field, field_position_global=None,
field_position_local=None):
"""Replaces a field with a new field."""
if field_position_global is None and field_position_local is None:
raise InvenioBibRecordFieldError("A field position is required to "
"complete this operation.")
elif field_position_global is not None and field_position_local is not None:
raise InvenioBibRecordFieldError("Only one field position is required "
"to complete this operation.")
elif field_position_global:
if not tag in rec:
raise InvenioBibRecordFieldError("No tag '%s' in record." % tag)
replaced = False
for position, field in enumerate(rec[tag]):
if field[4] == field_position_global:
rec[tag][position] = new_field
replaced = True
if not replaced:
raise InvenioBibRecordFieldError("No field has the tag '%s' and "
"the global field position '%d'." %
(tag, field_position_global))
else:
try:
rec[tag][field_position_local] = new_field
except KeyError:
raise InvenioBibRecordFieldError("No tag '%s' in record." % tag)
except IndexError:
raise InvenioBibRecordFieldError("No field has the tag '%s' and "
"the local field position '%d'." % (tag, field_position_local))
def record_get_subfields(rec, tag, field_position_global=None,
field_position_local=None):
"""
Returns the subfield of the matching field. One has to enter either a
global field position or a local field position.
@return: a list of subfield tuples (subfield code, value).
@rtype: list
"""
field = record_get_field(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
return field[0]
def record_delete_subfield_from(rec, tag, subfield_position,
field_position_global=None, field_position_local=None):
"""Delete subfield from position specified by tag, field number and
subfield position."""
subfields = record_get_subfields(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
try:
del subfields[subfield_position]
except IndexError:
from invenio.xmlmarc2textmarclib import create_marc_record
recordMarc = create_marc_record(rec, 0, {"text-marc": 1, "aleph-marc": 0})
raise InvenioBibRecordFieldError("The record : %(recordCode)s does not contain the subfield "
"'%(subfieldIndex)s' inside the field (local: '%(fieldIndexLocal)s, global: '%(fieldIndexGlobal)s' ) of tag '%(tag)s'." % \
{"subfieldIndex" : subfield_position, \
"fieldIndexLocal" : str(field_position_local), \
"fieldIndexGlobal" : str(field_position_global), \
"tag" : tag, \
"recordCode" : recordMarc})
if not subfields:
if field_position_global is not None:
for position, field in enumerate(rec[tag]):
if field[4] == field_position_global:
del rec[tag][position]
else:
del rec[tag][field_position_local]
if not rec[tag]:
del rec[tag]
def record_add_subfield_into(rec, tag, subfield_code, value,
subfield_position=None, field_position_global=None,
field_position_local=None):
"""Add subfield into position specified by tag, field number and
optionally by subfield position."""
subfields = record_get_subfields(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
if subfield_position is None:
subfields.append((subfield_code, value))
else:
subfields.insert(subfield_position, (subfield_code, value))
def record_modify_controlfield(rec, tag, controlfield_value,
field_position_global=None, field_position_local=None):
"""Modify controlfield at position specified by tag and field number."""
field = record_get_field(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
new_field = (field[0], field[1], field[2], controlfield_value, field[4])
record_replace_field(rec, tag, new_field,
field_position_global=field_position_global,
field_position_local=field_position_local)
def record_modify_subfield(rec, tag, subfield_code, value, subfield_position,
field_position_global=None, field_position_local=None):
"""Modify subfield at position specified by tag, field number and
subfield position."""
subfields = record_get_subfields(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
try:
subfields[subfield_position] = (subfield_code, value)
except IndexError:
raise InvenioBibRecordFieldError("There is no subfield with position "
"'%d'." % subfield_position)
def record_move_subfield(rec, tag, subfield_position, new_subfield_position,
field_position_global=None, field_position_local=None):
"""Move subfield at position specified by tag, field number and
subfield position to new subfield position."""
subfields = record_get_subfields(rec, tag,
field_position_global=field_position_global,
field_position_local=field_position_local)
try:
subfield = subfields.pop(subfield_position)
subfields.insert(new_subfield_position, subfield)
except IndexError:
raise InvenioBibRecordFieldError("There is no subfield with position "
"'%d'." % subfield_position)
def record_get_field_value(rec, tag, ind1=" ", ind2=" ", code=""):
"""Returns first (string) value that matches specified field
(tag, ind1, ind2, code) of the record (rec).
Returns empty string if not found.
Parameters (tag, ind1, ind2, code) can contain wildcard %.
Difference between wildcard % and empty '':
- Empty char specifies that we are not interested in a field which
has one of the indicator(s)/subfield specified.
- Wildcard specifies that we are interested in getting the value
of the field whatever the indicator(s)/subfield is.
For e.g. consider the following record in MARC:
100C5 $$a val1
555AB $$a val2
555AB val3
555 $$a val4
555A val5
>> record_get_field_value(record, '555', 'A', '', '')
>> "val5"
>> record_get_field_value(record, '555', 'A', '%', '')
>> "val3"
>> record_get_field_value(record, '555', 'A', '%', '%')
>> "val2"
>> record_get_field_value(record, '555', 'A', 'B', '')
>> "val3"
>> record_get_field_value(record, '555', '', 'B', 'a')
>> ""
>> record_get_field_value(record, '555', '', '', 'a')
>> "val4"
>> record_get_field_value(record, '555', '', '', '')
>> ""
>> record_get_field_value(record, '%%%', '%', '%', '%')
>> "val1"
@param rec: a record structure as returned by create_record()
@param tag: a 3 characters long string
@param ind1: a 1 character long string
@param ind2: a 1 character long string
@param code: a 1 character long string
@return: string value (empty if nothing found)"""
# Note: the code is quite redundant for speed reasons (avoid calling
# functions or doing tests inside loops)
ind1, ind2 = _wash_indicators(ind1, ind2)
if '%' in tag:
# Wild card in tag. Must find all corresponding fields
if code == '':
# Code not specified.
for field_tag, fields in rec.items():
if _tag_matches_pattern(field_tag, tag):
for field in fields:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
# Return matching field value if not empty
if field[3]:
return field[3]
elif code == '%':
# Code is wildcard. Take first subfield of first matching field
for field_tag, fields in rec.items():
if _tag_matches_pattern(field_tag, tag):
for field in fields:
if (ind1 in ('%', field[1]) and ind2 in ('%', field[2])
and field[0]):
return field[0][0][1]
else:
# Code is specified. Take corresponding one
for field_tag, fields in rec.items():
if _tag_matches_pattern(field_tag, tag):
for field in fields:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
if subfield[0] == code:
return subfield[1]
else:
# Tag is completely specified. Use tag as dict key
if tag in rec:
if code == '':
# Code not specified.
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
# Return matching field value if not empty
# or return "" empty if not exist.
if field[3]:
return field[3]
elif code == '%':
# Code is wildcard. Take first subfield of first matching field
for field in rec[tag]:
if (ind1 in ('%', field[1]) and ind2 in ('%', field[2]) and
field[0]):
return field[0][0][1]
else:
# Code is specified. Take corresponding one
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
if subfield[0] == code:
return subfield[1]
# Nothing was found
return ""
def record_get_field_values(rec, tag, ind1=" ", ind2=" ", code=""):
"""Returns the list of (string) values for the specified field
(tag, ind1, ind2, code) of the record (rec).
Returns empty list if not found.
Parameters (tag, ind1, ind2, code) can contain wildcard %.
@param rec: a record structure as returned by create_record()
@param tag: a 3 characters long string
@param ind1: a 1 character long string
@param ind2: a 1 character long string
@param code: a 1 character long string
@return: a list of strings"""
tmp = []
ind1, ind2 = _wash_indicators(ind1, ind2)
if '%' in tag:
# Wild card in tag. Must find all corresponding tags and fields
tags = [k for k in rec if _tag_matches_pattern(k, tag)]
if code == '':
# Code not specified. Consider field value (without subfields)
for tag in tags:
for field in rec[tag]:
if (ind1 in ('%', field[1]) and ind2 in ('%', field[2]) and
field[3]):
tmp.append(field[3])
elif code == '%':
# Code is wildcard. Consider all subfields
for tag in tags:
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
tmp.append(subfield[1])
else:
# Code is specified. Consider all corresponding subfields
for tag in tags:
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
if subfield[0] == code:
tmp.append(subfield[1])
else:
# Tag is completely specified. Use tag as dict key
if rec and tag in rec:
if code == '':
# Code not specified. Consider field value (without subfields)
for field in rec[tag]:
if (ind1 in ('%', field[1]) and ind2 in ('%', field[2]) and
field[3]):
tmp.append(field[3])
elif code == '%':
# Code is wildcard. Consider all subfields
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
tmp.append(subfield[1])
else:
# Code is specified. Take corresponding one
for field in rec[tag]:
if ind1 in ('%', field[1]) and ind2 in ('%', field[2]):
for subfield in field[0]:
if subfield[0] == code:
tmp.append(subfield[1])
# If tmp was not set, nothing was found
return tmp
def record_xml_output(rec, tags=None):
"""Generates the XML for record 'rec' and returns it as a string
@rec: record
@tags: list of tags to be printed"""
if tags is None:
tags = []
if isinstance(tags, str):
tags = [tags]
if tags and '001' not in tags:
# Add the missing controlfield.
tags.append('001')
marcxml = ['<record>']
# Add the tag 'tag' to each field in rec[tag]
fields = []
for tag in rec:
if not tags or tag in tags:
for field in rec[tag]:
fields.append((tag, field))
record_order_fields(fields)
for field in fields:
marcxml.append(field_xml_output(field[1], field[0]))
marcxml.append('</record>')
return '\n'.join(marcxml)
def field_get_subfield_instances(field):
"""Returns the list of subfields associated with field 'field'"""
return field[0]
def field_get_subfield_values(field_instance, code):
"""Return subfield CODE values of the field instance FIELD."""
return [subfield_value
for subfield_code, subfield_value in field_instance[0]
if subfield_code == code]
def field_add_subfield(field, code, value):
"""Adds a subfield to field 'field'"""
field[0].append((code, value))
def record_order_fields(rec, fun="_order_by_ord"):
"""Orders field inside record 'rec' according to a function"""
rec.sort(eval(fun))
def field_xml_output(field, tag):
"""Generates the XML for field 'field' and returns it as a string."""
marcxml = []
if field[3]:
marcxml.append(' <controlfield tag="%s">%s</controlfield>' %
(tag, encode_for_xml(field[3])))
else:
marcxml.append(' <datafield tag="%s" ind1="%s" ind2="%s">' %
(tag, field[1], field[2]))
marcxml += [_subfield_xml_output(subfield) for subfield in field[0]]
marcxml.append(' </datafield>')
return '\n'.join(marcxml)
def record_extract_oai_id(record):
"""Returns the OAI ID of the record."""
tag = CFG_BIBUPLOAD_EXTERNAL_OAIID_TAG[0:3]
ind1 = CFG_BIBUPLOAD_EXTERNAL_OAIID_TAG[3]
ind2 = CFG_BIBUPLOAD_EXTERNAL_OAIID_TAG[4]
subfield = CFG_BIBUPLOAD_EXTERNAL_OAIID_TAG[5]
values = record_get_field_values(record, tag, ind1, ind2, subfield)
oai_id_regex = re.compile("oai[a-zA-Z0-9/.:]+")
for value in [value.strip() for value in values]:
if oai_id_regex.match(value):
return value
return ""
def print_rec(rec, format=1, tags=None):
"""prints a record
format = 1 -- XML
format = 2 -- HTML (not implemented)
@tags: list of tags to be printed
"""
if tags is None:
tags = []
if format == 1:
text = record_xml_output(rec, tags)
else:
return ''
return text
def print_recs(listofrec, format=1, tags=None):
"""prints a list of records
format = 1 -- XML
format = 2 -- HTML (not implemented)
@tags: list of tags to be printed
if 'listofrec' is not a list it returns empty string
"""
if tags is None:
tags = []
text = ""
if type(listofrec).__name__ !='list':
return ""
else:
for rec in listofrec:
text = "%s\n%s" % (text, print_rec(rec, format, tags))
return text
def concat(alist):
"""Concats a list of lists"""
newl = []
for l in alist:
newl.extend(l)
return newl
def print_errors(alist):
"""Creates a unique string with the strings in list, using '\n' as
a separator."""
text = ""
for l in alist:
text = '%s\n%s'% (text, l)
return text
def record_find_field(rec, tag, field, strict=False):
"""
Returns the global and local positions of the first occurrence
of the field in a record.
@param rec: A record dictionary structure
@type rec: dictionary
@param tag: The tag of the field to search for
@type tag: string
@param field: A field tuple as returned by create_field()
@type field: tuple
@param strict: A boolean describing the search method. If strict
is False, then the order of the subfields doesn't
matter. Default search method is strict.
@type strict: boolean
@return: A tuple of (global_position, local_position) or a
tuple (None, None) if the field is not present.
@rtype: tuple
@raise InvenioBibRecordFieldError: If the provided field is invalid.
"""
try:
_check_field_validity(field)
except InvenioBibRecordFieldError:
raise
for local_position, field1 in enumerate(rec.get(tag, [])):
if _compare_fields(field, field1, strict):
return (field1[4], local_position)
return (None, None)
def record_strip_empty_volatile_subfields(rec):
"""
Removes unchanged volatile subfields from the record
"""
for tag in rec.keys():
for field in rec[tag]:
field[0][:] = [subfield for subfield in field[0] if subfield[1][:9] != "VOLATILE:"]
def record_strip_empty_fields(rec, tag=None):
"""
Removes empty subfields and fields from the record. If 'tag' is not None, only
a specific tag of the record will be stripped, otherwise the whole record.
@param rec: A record dictionary structure
@type rec: dictionary
@param tag: The tag of the field to strip empty fields from
@type tag: string
"""
# Check whole record
if tag is None:
tags = rec.keys()
for tag in tags:
record_strip_empty_fields(rec, tag)
# Check specific tag of the record
elif tag in rec:
# in case of a controlfield
if tag[:2] == '00':
if len(rec[tag]) == 0 or not rec[tag][0][3]:
del rec[tag]
#in case of a normal field
else:
fields = []
for field in rec[tag]:
subfields = []
for subfield in field[0]:
# check if the subfield has been given a value
if subfield[1]:
subfields.append(subfield)
if len(subfields) > 0:
new_field = create_field(subfields, field[1], field[2],
field[3])
fields.append(new_field)
if len(fields) > 0:
rec[tag] = fields
else:
del rec[tag]
### IMPLEMENTATION / INVISIBLE FUNCTIONS
def _compare_fields(field1, field2, strict=True):
"""
Compares 2 fields. If strict is True, then the order of the
subfield will be taken care of, if not then the order of the
subfields doesn't matter.
@return: True if the field are equivalent, False otherwise.
"""
if strict:
# Return a simple equal test on the field minus the position.
return field1[:4] == field2[:4]
else:
if field1[1:4] != field2[1:4]:
# Different indicators or controlfield value.
return False
else:
# Compare subfields in a loose way.
return set(field1[0]) == set(field2[0])
def _check_field_validity(field):
"""
Checks if a field is well-formed.
@param field: A field tuple as returned by create_field()
@type field: tuple
@raise InvenioBibRecordFieldError: If the field is invalid.
"""
if type(field) not in (list, tuple):
raise InvenioBibRecordFieldError("Field of type '%s' should be either "
"a list or a tuple." % type(field))
if len(field) != 5:
raise InvenioBibRecordFieldError("Field of length '%d' should have 5 "
"elements." % len(field))
if type(field[0]) not in (list, tuple):
raise InvenioBibRecordFieldError("Subfields of type '%s' should be "
"either a list or a tuple." % type(field[0]))
if type(field[1]) is not str:
raise InvenioBibRecordFieldError("Indicator 1 of type '%s' should be "
"a string." % type(field[1]))
if type(field[2]) is not str:
raise InvenioBibRecordFieldError("Indicator 2 of type '%s' should be "
"a string." % type(field[2]))
if type(field[3]) is not str:
raise InvenioBibRecordFieldError("Controlfield value of type '%s' "
"should be a string." % type(field[3]))
if type(field[4]) is not int:
raise InvenioBibRecordFieldError("Global position of type '%s' should "
"be an int." % type(field[4]))
for subfield in field[0]:
if (type(subfield) not in (list, tuple) or
len(subfield) != 2 or
type(subfield[0]) is not str or
type(subfield[1]) is not str):
raise InvenioBibRecordFieldError("Subfields are malformed. "
"Should a list of tuples of 2 strings.")
def _shift_field_positions_global(record, start, delta=1):
"""Shifts all global field positions with global field positions
higher or equal to 'start' from the value 'delta'."""
if not delta:
return
for tag, fields in record.items():
newfields = []
for field in fields:
if field[4] < start:
newfields.append(field)
else:
# Increment the global field position by delta.
newfields.append(tuple(list(field[:4]) + [field[4] + delta]))
record[tag] = newfields
def _tag_matches_pattern(tag, pattern):
"""Returns true if MARC 'tag' matches a 'pattern'.
'pattern' is plain text, with % as wildcard
Both parameters must be 3 characters long strings.
For e.g.
>> _tag_matches_pattern("909", "909") -> True
>> _tag_matches_pattern("909", "9%9") -> True
>> _tag_matches_pattern("909", "9%8") -> False
@param tag: a 3 characters long string
@param pattern: a 3 characters long string
@return: False or True"""
for char1, char2 in zip(tag, pattern):
if char2 not in ('%', char1):
return False
return True
def validate_record_field_positions_global(record):
"""
Checks if the global field positions in the record are valid ie no
duplicate global field positions and local field positions in the
list of fields are ascending.
@param record: the record data structure
@return: the first error found as a string or None if no error was found
"""
all_fields = []
for tag, fields in record.items():
previous_field_position_global = -1
for field in fields:
if field[4] < previous_field_position_global:
return "Non ascending global field positions in tag '%s'." % tag
previous_field_position_global = field[4]
if field[4] in all_fields:
return ("Duplicate global field position '%d' in tag '%s'" %
(field[4], tag))
def _record_sort_by_indicators(record):
"""Sorts the fields inside the record by indicators."""
for tag, fields in record.items():
record[tag] = _fields_sort_by_indicators(fields)
def _fields_sort_by_indicators(fields):
"""Sorts a set of fields by their indicators. Returns a sorted list
with correct global field positions."""
field_dict = {}
field_positions_global = []
for field in fields:
field_dict.setdefault(field[1:3], []).append(field)
field_positions_global.append(field[4])
indicators = field_dict.keys()
indicators.sort()
field_list = []
for indicator in indicators:
for field in field_dict[indicator]:
field_list.append(field[:4] + (field_positions_global.pop(0),))
return field_list
def _select_parser(parser=None):
"""Selects the more relevant parser based on the parsers available
and on the parser desired by the user."""
if not AVAILABLE_PARSERS:
# No parser is available. This is bad.
return None
if parser is None or parser not in AVAILABLE_PARSERS:
# Return the best available parser.
return AVAILABLE_PARSERS[0]
else:
return parser
def _create_record_rxp(marcxml, verbose=CFG_BIBRECORD_DEFAULT_VERBOSE_LEVEL,
- correct=CFG_BIBRECORD_DEFAULT_CORRECT):
+ correct=CFG_BIBRECORD_DEFAULT_CORRECT,
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a record object using the RXP parser.
If verbose>3 then the parser will be strict and will stop in case of
well-formedness errors or DTD errors.
If verbose=0, the parser will not give warnings.
If 0 < verbose <= 3, the parser will not give errors, but will warn
the user about possible mistakes
correct != 0 -> We will try to correct errors such as missing
attributes
correct = 0 -> there will not be any attempt to correct errors"""
if correct:
# Note that with pyRXP < 1.13 a memory leak has been found
# involving DTD parsing. So enable correction only if you have
# pyRXP 1.13 or greater.
marcxml = ('<?xml version="1.0" encoding="UTF-8"?>\n'
'<!DOCTYPE collection SYSTEM "file://%s">\n'
'<collection>\n%s\n</collection>' % (CFG_MARC21_DTD, marcxml))
# Create the pyRXP parser.
pyrxp_parser = pyRXP.Parser(ErrorOnValidityErrors=0, ProcessDTD=1,
ErrorOnUnquotedAttributeValues=0, srcName='string input')
if verbose > 3:
pyrxp_parser.ErrorOnValidityErrors = 1
pyrxp_parser.ErrorOnUnquotedAttributeValues = 1
try:
root = pyrxp_parser.parse(marcxml)
except pyRXP.error, ex1:
raise InvenioBibRecordParserError(str(ex1))
# If record is enclosed in a collection tag, extract it.
if root[TAG] == 'collection':
children = _get_children_by_tag_name_rxp(root, 'record')
if not children:
return {}
root = children[0]
record = {}
# This is needed because of the record_xml_output function, where we
# need to know the order of the fields.
field_position_global = 1
# Consider the control fields.
for controlfield in _get_children_by_tag_name_rxp(root, 'controlfield'):
if controlfield[CHILDREN]:
value = ''.join([n for n in controlfield[CHILDREN]])
# Construct the field tuple.
field = ([], ' ', ' ', value, field_position_global)
record.setdefault(controlfield[ATTRS]['tag'], []).append(field)
field_position_global += 1
- elif CFG_BIBRECORD_KEEP_SINGLETONS:
+ elif keep_singletons:
field = ([], ' ', ' ', '', field_position_global)
record.setdefault(controlfield[ATTRS]['tag'], []).append(field)
field_position_global += 1
# Consider the data fields.
for datafield in _get_children_by_tag_name_rxp(root, 'datafield'):
subfields = []
for subfield in _get_children_by_tag_name_rxp(datafield, 'subfield'):
if subfield[CHILDREN]:
value = ''.join([n for n in subfield[CHILDREN]])
subfields.append((subfield[ATTRS].get('code', '!'), value))
- elif CFG_BIBRECORD_KEEP_SINGLETONS:
+ elif keep_singletons:
subfields.append((subfield[ATTRS].get('code', '!'), ''))
- if subfields or CFG_BIBRECORD_KEEP_SINGLETONS:
+ if subfields or keep_singletons:
# Create the field.
tag = datafield[ATTRS].get('tag', '!')
ind1 = datafield[ATTRS].get('ind1', '!')
ind2 = datafield[ATTRS].get('ind2', '!')
ind1, ind2 = _wash_indicators(ind1, ind2)
# Construct the field tuple.
field = (subfields, ind1, ind2, '', field_position_global)
record.setdefault(tag, []).append(field)
field_position_global += 1
return record
-def _create_record_from_document(document):
+def _create_record_from_document(document,
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a record from the document (of type
xml.dom.minidom.Document or Ft.Xml.Domlette.Document)."""
root = None
for node in document.childNodes:
if node.nodeType == node.ELEMENT_NODE:
root = node
break
if root is None:
return {}
if root.tagName == 'collection':
children = _get_children_by_tag_name(root, 'record')
if not children:
return {}
root = children[0]
field_position_global = 1
record = {}
for controlfield in _get_children_by_tag_name(root, "controlfield"):
tag = controlfield.getAttributeNS(None, "tag").encode('utf-8')
text_nodes = controlfield.childNodes
value = ''.join([n.data for n in text_nodes]).encode("utf-8")
- if value or CFG_BIBRECORD_KEEP_SINGLETONS:
+ if value or keep_singletons:
field = ([], " ", " ", value, field_position_global)
record.setdefault(tag, []).append(field)
field_position_global += 1
for datafield in _get_children_by_tag_name(root, "datafield"):
subfields = []
for subfield in _get_children_by_tag_name(datafield, "subfield"):
text_nodes = subfield.childNodes
value = ''.join([n.data for n in text_nodes]).encode("utf-8")
- if value or CFG_BIBRECORD_KEEP_SINGLETONS:
+ if value or keep_singletons:
code = subfield.getAttributeNS(None, 'code').encode("utf-8")
subfields.append((code or '!', value))
- if subfields or CFG_BIBRECORD_KEEP_SINGLETONS:
+ if subfields or keep_singletons:
tag = datafield.getAttributeNS(None, "tag").encode("utf-8") or '!'
ind1 = datafield.getAttributeNS(None, "ind1").encode("utf-8")
ind2 = datafield.getAttributeNS(None, "ind2").encode("utf-8")
ind1, ind2 = _wash_indicators(ind1, ind2)
field = (subfields, ind1, ind2, "", field_position_global)
record.setdefault(tag, []).append(field)
field_position_global += 1
return record
-def _create_record_minidom(marcxml):
+def _create_record_minidom(marcxml,
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a record using minidom."""
try:
dom = xml.dom.minidom.parseString(marcxml)
except xml.parsers.expat.ExpatError, ex1:
raise InvenioBibRecordParserError(str(ex1))
- return _create_record_from_document(dom)
+ return _create_record_from_document(dom, keep_singletons=keep_singletons)
-def _create_record_4suite(marcxml):
+def _create_record_4suite(marcxml,
+ keep_singletons=CFG_BIBRECORD_KEEP_SINGLETONS):
"""Creates a record using the 4suite parser."""
try:
dom = Ft.Xml.Domlette.NonvalidatingReader.parseString(marcxml,
"urn:dummy")
except Ft.Xml.ReaderException, ex1:
raise InvenioBibRecordParserError(ex1.message)
- return _create_record_from_document(dom)
+ return _create_record_from_document(dom, keep_singletons=keep_singletons)
def _concat(alist):
"""Concats a list of lists"""
return [element for single_list in alist for element in single_list]
def _subfield_xml_output(subfield):
"""Generates the XML for a subfield object and return it as a string"""
return ' <subfield code="%s">%s</subfield>' % (subfield[0],
encode_for_xml(subfield[1]))
def _order_by_ord(field1, field2):
"""Function used to order the fields according to their ord value"""
return cmp(field1[1][4], field2[1][4])
def _get_children_by_tag_name(node, name):
"""Retrieves all children from node 'node' with name 'name' and
returns them as a list."""
try:
return [child for child in node.childNodes if child.nodeName == name]
except TypeError:
return []
def _get_children_by_tag_name_rxp(node, name):
"""Retrieves all children from 'children' with tag name 'tag' and
returns them as a list.
children is a list returned by the RXP parser"""
try:
return [child for child in node[CHILDREN] if child[TAG] == name]
except TypeError:
return []
def _wash_indicators(*indicators):
"""
Washes the values of the indicators. An empty string or an
underscore is replaced by a blank space.
@param indicators: a series of indicators to be washed
@return: a list of washed indicators
"""
return [indicator in ('', '_') and ' ' or indicator
for indicator in indicators]
def _correct_record(record):
"""
Checks and corrects the structure of the record.
@param record: the record data structure
@return: a list of errors found
"""
errors = []
for tag in record.keys():
upper_bound = '999'
n = len(tag)
if n > 3:
i = n - 3
while i > 0:
upper_bound = '%s%s' % ('0', upper_bound)
i -= 1
# Missing tag. Replace it with dummy tag '000'.
if tag == '!':
errors.append((1, '(field number(s): ' +
str([f[4] for f in record[tag]]) + ')'))
record['000'] = record.pop(tag)
tag = '000'
elif not ('001' <= tag <= upper_bound or tag in ('FMT', 'FFT')):
errors.append(2)
record['000'] = record.pop(tag)
tag = '000'
fields = []
for field in record[tag]:
# Datafield without any subfield.
if field[0] == [] and field[3] == '':
errors.append((8, '(field number: ' + str(field[4]) + ')'))
subfields = []
for subfield in field[0]:
if subfield[0] == '!':
errors.append((3, '(field number: ' + str(field[4]) + ')'))
newsub = ('', subfield[1])
else:
newsub = subfield
subfields.append(newsub)
if field[1] == '!':
errors.append((4, '(field number: ' + str(field[4]) + ')'))
ind1 = " "
else:
ind1 = field[1]
if field[2] == '!':
errors.append((5, '(field number: ' + str(field[4]) + ')'))
ind2 = " "
else:
ind2 = field[2]
fields.append((subfields, ind1, ind2, field[3], field[4]))
record[tag] = fields
return errors
def _warning(code):
"""It returns a warning message of code 'code'.
If code = (cd, str) it returns the warning message of code 'cd'
and appends str at the end"""
if isinstance(code, str):
return code
message = ''
if isinstance(code, tuple):
if isinstance(code[0], str):
message = code[1]
code = code[0]
return CFG_BIBRECORD_WARNING_MSGS.get(code, '') + message
def _warnings(alist):
"""Applies the function _warning() to every element in l."""
return [_warning(element) for element in alist]
def _compare_lists(list1, list2, custom_cmp):
"""Compares twolists using given comparing function
@param list1: first list to compare
@param list2: second list to compare
@param custom_cmp: a function taking two arguments (element of
list 1, element of list 2) and
@return: True or False depending if the values are the same"""
if len(list1) != len(list2):
return False
for element1, element2 in zip(list1, list2):
if not custom_cmp(element1, element2):
return False
return True
if PSYCO_AVAILABLE:
psyco.bind(_correct_record)
psyco.bind(_create_record_4suite)
psyco.bind(_create_record_rxp)
psyco.bind(_create_record_minidom)
psyco.bind(field_get_subfield_values)
psyco.bind(create_records)
psyco.bind(create_record)
psyco.bind(record_get_field_instances)
psyco.bind(record_get_field_value)
psyco.bind(record_get_field_values)
diff --git a/modules/bibedit/lib/bibrecord_tests.py b/modules/bibedit/lib/bibrecord_tests.py
index 54ca9eff3..509b8a0e6 100644
--- a/modules/bibedit/lib/bibrecord_tests.py
+++ b/modules/bibedit/lib/bibrecord_tests.py
@@ -1,1540 +1,1543 @@
# -*- coding: utf-8 -*-
##
## This file is part of CDS Invenio.
## Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008 CERN.
##
## CDS Invenio is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 2 of the
## License, or (at your option) any later version.
##
## CDS Invenio is distributed in the hope that it will be useful, but
## WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
## General Public License for more details.
##
## You should have received a copy of the GNU General Public License
## along with CDS Invenio; if not, write to the Free Software Foundation, Inc.,
## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
"""
The BibRecord test suite.
"""
import unittest
from invenio.config import CFG_TMPDIR
from invenio import bibrecord, bibrecord_config
from invenio.testutils import make_test_suite, run_test_suite
try:
import pyRXP
parser_pyrxp_available = True
except ImportError:
parser_pyrxp_available = False
try:
import Ft.Xml.Domlette
parser_4suite_available = True
except ImportError:
parser_4suite_available = False
try:
import xml.dom.minidom
import xml.parsers.expat
parser_minidom_available = True
except ImportError:
parser_minidom_available = False
class BibRecordSuccessTest(unittest.TestCase):
""" bibrecord - demo file parsing test """
def setUp(self):
"""Initialize stuff"""
f = open(CFG_TMPDIR + '/demobibdata.xml', 'r')
xmltext = f.read()
f.close()
self.recs = [rec[0] for rec in bibrecord.create_records(xmltext)]
def test_records_created(self):
""" bibrecord - demo file how many records are created """
self.assertEqual(104, len(self.recs))
def test_tags_created(self):
""" bibrecord - demo file which tags are created """
## check if the tags are correct
tags = ['003', '005', '020', '024', '035', '037', '041', '080', '088',
'100', '242', '245', '246', '250', '260', '269', '270', '300',
'340', '490', '500', '502', '520', '590', '595', '650', '653',
'690', '694', '695', '700', '710', '720', '773', '856', '859',
'901', '909', '916', '960', '961', '962', '963', '964', '970',
'980', '999', 'FFT']
t = []
for rec in self.recs:
t.extend(rec.keys())
t.sort()
#eliminate the elements repeated
tt = []
for x in t:
if not x in tt:
tt.append(x)
self.assertEqual(tags, tt)
def test_fields_created(self):
"""bibrecord - demo file how many fields are created"""
## check if the number of fields for each record is correct
fields = [14, 14, 8, 11, 11, 12, 11, 15, 10, 18, 14, 16, 10, 9, 15, 10,
11, 11, 11, 9, 11, 11, 10, 9, 9, 9, 10, 9, 10, 10, 8, 9, 8,
9, 14, 13, 14, 14, 15, 12, 12, 12, 15, 14, 12, 16, 16, 15,
15, 14, 16, 15, 15, 15, 16, 15, 16, 15, 15, 16, 15, 14, 14,
15, 12, 13, 11, 15, 8, 11, 14, 13, 12, 13, 6, 6, 25, 24, 27,
26, 26, 24, 26, 27, 25, 28, 24, 23, 27, 25, 25, 26, 26, 24,
19, 26, 25, 22, 9, 8, 9, 9, 8, 7]
cr = []
ret = []
for rec in self.recs:
cr.append(len(rec.values()))
ret.append(rec)
self.assertEqual(fields, cr)
def test_create_record_with_collection_tag(self):
""" bibrecord - create_record() for single record in collection"""
xmltext = """
<collection>
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
</record>
</collection>
"""
record = bibrecord.create_record(xmltext)
record1 = bibrecord.create_records(xmltext)[0]
self.assertEqual(record1, record)
class BibRecordParsersTest(unittest.TestCase):
""" bibrecord - testing the creation of records with different parsers"""
def setUp(self):
"""Initialize stuff"""
self.xmltext = """
<!-- A first comment -->
<collection>
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<!-- A second comment -->
<subfield code="a">eng</subfield>
</datafield>
</record>
</collection>
"""
self.expected_record = {
'001': [([], ' ', ' ', '33', 1)],
'041': [([('a', 'eng')], ' ', ' ', '', 2)]
}
if parser_pyrxp_available:
def test_pyRXP(self):
""" bibrecord - create_record() with pyRXP """
record = bibrecord._create_record_rxp(self.xmltext)
self.assertEqual(record, self.expected_record)
if parser_4suite_available:
def test_4suite(self):
""" bibrecord - create_record() with 4suite """
record = bibrecord._create_record_4suite(self.xmltext)
self.assertEqual(record, self.expected_record)
if parser_minidom_available:
def test_minidom(self):
""" bibrecord - create_record() with minidom """
record = bibrecord._create_record_minidom(self.xmltext)
self.assertEqual(record, self.expected_record)
class BibRecordBadInputTreatmentTest(unittest.TestCase):
""" bibrecord - testing for bad input treatment """
def test_empty_collection(self):
"""bibrecord - empty collection"""
xml_error0 = """<collection></collection>"""
rec = bibrecord.create_record(xml_error0)[0]
self.assertEqual(rec, {})
records = bibrecord.create_records(xml_error0)
self.assertEqual(len(records), 0)
def test_wrong_attribute(self):
"""bibrecord - bad input subfield \'cde\' instead of \'code\'"""
ws = bibrecord.CFG_BIBRECORD_WARNING_MSGS
xml_error1 = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe, John</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield cde="a">On the foo and bar</subfield>
</datafield>
</record>
"""
e = bibrecord.create_record(xml_error1, 1, 1)[2]
ee =''
for i in e:
if type(i).__name__ == 'str':
if i.count(ws[3])>0:
ee = i
self.assertEqual(bibrecord._warning((3, '(field number: 4)')), ee)
def test_missing_attribute(self):
""" bibrecord - bad input missing \"tag\" """
ws = bibrecord.CFG_BIBRECORD_WARNING_MSGS
xml_error2 = """
<record>
<controlfield tag="001">33</controlfield>
<datafield ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe, John</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">On the foo and bar</subfield>
</datafield>
</record>
"""
e = bibrecord.create_record(xml_error2, 1, 1)[2]
ee = ''
for i in e:
if type(i).__name__ == 'str':
if i.count(ws[1])>0:
ee = i
self.assertEqual(bibrecord._warning((1, '(field number(s): [2])')), ee)
def test_empty_datafield(self):
""" bibrecord - bad input no subfield """
ws = bibrecord.CFG_BIBRECORD_WARNING_MSGS
xml_error3 = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe, John</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">On the foo and bar</subfield>
</datafield>
</record>
"""
e = bibrecord.create_record(xml_error3, 1, 1)[2]
ee = ''
for i in e:
if type(i).__name__ == 'str':
if i.count(ws[8])>0:
ee = i
self.assertEqual(bibrecord._warning((8, '(field number: 2)')), ee)
def test_missing_tag(self):
"""bibrecord - bad input missing end \"tag\" """
ws = bibrecord.CFG_BIBRECORD_WARNING_MSGS
xml_error4 = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe, John</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">On the foo and bar</subfield>
</record>
"""
e = bibrecord.create_record(xml_error4, 1, 1)[2]
ee = ''
for i in e:
if type(i).__name__ == 'str':
if i.count(ws[99])>0:
ee = i
self.assertEqual(bibrecord._warning((99, '(Tagname : datafield)')), ee)
class BibRecordAccentedUnicodeLettersTest(unittest.TestCase):
""" bibrecord - testing accented UTF-8 letters """
def setUp(self):
"""Initialize stuff"""
self.xml_example_record = """<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Döè1, John</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, J>ohn</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">Пушкин</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>"""
self.rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
def test_accented_unicode_characters(self):
"""bibrecord - accented Unicode letters"""
self.assertEqual(self.xml_example_record,
bibrecord.record_xml_output(self.rec))
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "100", " ", " "),
[([('a', 'Döè1, John')], " ", " ", "", 3), ([('a', 'Doe2, J>ohn'), ('b', 'editor')], " ", " ", "", 4)])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "245", " ", "1"),
[([('a', 'Пушкин')], " ", '1', "", 5)])
class BibRecordGettingFieldValuesTest(unittest.TestCase):
""" bibrecord - testing for getting field/subfield values """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe1, John</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_get_field_instances(self):
"""bibrecord - getting field instances"""
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "100", " ", " "),
[([('a', 'Doe1, John')], " ", " ", "", 3), ([('a', 'Doe2, John'), ('b', 'editor')], " ", " ", "", 4)])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "", " ", " "),
[('245', [([('a', 'On the foo and bar1')], " ", '1', "", 5), ([('a', 'On the foo and bar2')], " ", '2', "", 6)]), ('001', [([], " ", " ", '33', 1)]), ('100', [([('a', 'Doe1, John')], " ", " ", "", 3), ([('a', 'Doe2, John'), ('b', 'editor')], " ", " ", "", 4)]), ('041', [([('a', 'eng')], " ", " ", "", 2)])])
def test_get_field_values(self):
"""bibrecord - getting field values"""
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "a"),
['Doe1, John', 'Doe2, John'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "b"),
['editor'])
def test_get_field_value(self):
"""bibrecord - getting first field value"""
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", " ", "a"),
'Doe1, John')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", " ", "b"),
'editor')
def test_get_subfield_values(self):
"""bibrecord - getting subfield values"""
fi1, fi2 = bibrecord.record_get_field_instances(self.rec, "100", " ", " ")
self.assertEqual(bibrecord.field_get_subfield_values(fi1, "b"), [])
self.assertEqual(bibrecord.field_get_subfield_values(fi2, "b"), ["editor"])
class BibRecordGettingFieldValuesViaWildcardsTest(unittest.TestCase):
""" bibrecord - testing for getting field/subfield values via wildcards """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">1</controlfield>
<datafield tag="100" ind1="C" ind2="5">
<subfield code="a">val1</subfield>
</datafield>
<datafield tag="555" ind1="A" ind2="B">
<subfield code="a">val2</subfield>
</datafield>
<datafield tag="555" ind1="A" ind2=" ">
<subfield code="a">val3</subfield>
</datafield>
<datafield tag="555" ind1=" " ind2=" ">
<subfield code="a">val4a</subfield>
<subfield code="b">val4b</subfield>
</datafield>
<datafield tag="555" ind1=" " ind2="B">
<subfield code="a">val5</subfield>
</datafield>
<datafield tag="556" ind1="A" ind2="C">
<subfield code="a">val6</subfield>
</datafield>
<datafield tag="556" ind1="A" ind2=" ">
<subfield code="a">val7a</subfield>
<subfield code="b">val7b</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_get_field_instances_via_wildcard(self):
"""bibrecord - getting field instances via wildcards"""
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "100", " ", " "),
[])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "100", "%", " "),
[])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "100", "%", "%"),
[([('a', 'val1')], 'C', '5', "", 2)])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "55%", "A", "%"),
[([('a', 'val2')], 'A', 'B', "", 3),
([('a', 'val3')], 'A', " ", "", 4),
([('a', 'val6')], 'A', 'C', "", 7),
([('a', 'val7a'), ('b', 'val7b')], 'A', " ", "", 8)])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "55%", "A", " "),
[([('a', 'val3')], 'A', " ", "", 4),
([('a', 'val7a'), ('b', 'val7b')], 'A', " ", "", 8)])
self.assertEqual(bibrecord.record_get_field_instances(self.rec, "556", "A", " "),
[([('a', 'val7a'), ('b', 'val7b')], 'A', " ", "", 8)])
def test_get_field_values_via_wildcard(self):
"""bibrecord - getting field values via wildcards"""
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", " ", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", "%", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", "%", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", "%", "z"),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "%"),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "a"),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", " ", "a"),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", "%", "a"),
['val1'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", "%", "%", "%"),
['val1'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", "%", "a"),
['val2', 'val3', 'val6', 'val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", " ", "a"),
['val3', 'val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "556", "A", " ", "a"),
['val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "555", " ", " ", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "555", " ", " ", "z"),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "555", " ", " ", "%"),
['val4a', 'val4b'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", " ", " ", "b"),
['val4b'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "%", "%", "b"),
['val4b', 'val7b'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", " ", "b"),
['val7b'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", "%", "b"),
['val7b'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", " ", "a"),
['val3', 'val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "A", "%", "a"),
['val2', 'val3', 'val6', 'val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", "%", "%", "a"),
['val2', 'val3', 'val4a', 'val5', 'val6', 'val7a'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "55%", " ", " ", "a"),
['val4a'])
def test_get_field_value_via_wildcard(self):
"""bibrecord - getting first field value via wildcards"""
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", " ", " "),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", "%", " ", " "),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", "%", " "),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", "%", "%", " "),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", " ", "%"),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", " ", " ", "a"),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", "%", " ", "a"),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", "%", "%", "a"),
'val1')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "100", "%", "%", "%"),
'val1')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", "%", "a"),
'val2')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", " ", "a"),
'val3')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "556", "A", " ", "a"),
'val7a')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "555", " ", " ", " "),
'')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "555", " ", " ", "%"),
'val4a')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", " ", " ", "b"),
'val4b')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "%", "%", "b"),
'val4b')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", " ", "b"),
'val7b')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", "%", "b"),
'val7b')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", " ", "a"),
'val3')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "A", "%", "a"),
'val2')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", "%", "%", "a"),
'val2')
self.assertEqual(bibrecord.record_get_field_value(self.rec, "55%", " ", " ", "a"),
'val4a')
class BibRecordAddFieldTest(unittest.TestCase):
""" bibrecord - testing adding field """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe1, John</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_add_controlfield(self):
"""bibrecord - adding controlfield"""
field_position_global_1 = bibrecord.record_add_field(self.rec, "003",
controlfield_value="SzGeCERN")
field_position_global_2 = bibrecord.record_add_field(self.rec, "004",
controlfield_value="Test")
self.assertEqual(field_position_global_1, 2)
self.assertEqual(field_position_global_2, 3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "003", " ", " ", ""),
['SzGeCERN'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "004", " ", " ", ""),
['Test'])
def test_add_datafield(self):
"""bibrecord - adding datafield"""
field_position_global_1 = bibrecord.record_add_field(self.rec, "100",
subfields=[('a', 'Doe3, John')])
field_position_global_2 = bibrecord.record_add_field(self.rec, "100",
subfields= [('a', 'Doe4, John'), ('b', 'editor')])
self.assertEqual(field_position_global_1, 5)
self.assertEqual(field_position_global_2, 6)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "a"),
['Doe1, John', 'Doe2, John', 'Doe3, John', 'Doe4, John'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "b"),
['editor', 'editor'])
def test_add_controlfield_on_desired_position(self):
"""bibrecord - adding controlfield on desired position"""
field_position_global_1 = bibrecord.record_add_field(self.rec, "005",
controlfield_value="Foo",
field_position_global=0)
field_position_global_2 = bibrecord.record_add_field(self.rec, "006",
controlfield_value="Bar",
field_position_global=0)
self.assertEqual(field_position_global_1, 7)
self.assertEqual(field_position_global_2, 8)
def test_add_datafield_on_desired_position_field_position_global(self):
"""bibrecord - adding datafield on desired global field position"""
field_position_global_1 = bibrecord.record_add_field(self.rec, "100",
subfields=[('a', 'Doe3, John')], field_position_global=0)
field_position_global_2 = bibrecord.record_add_field(self.rec, "100",
subfields=[('a', 'Doe4, John'), ('b', 'editor')], field_position_global=0)
self.assertEqual(field_position_global_1, 3)
self.assertEqual(field_position_global_2, 3)
def test_add_datafield_on_desired_position_field_position_local(self):
"""bibrecord - adding datafield on desired local field position"""
field_position_global_1 = bibrecord.record_add_field(self.rec, "100",
subfields=[('a', 'Doe3, John')], field_position_local=0)
field_position_global_2 = bibrecord.record_add_field(self.rec, "100",
subfields=[('a', 'Doe4, John'), ('b', 'editor')],
field_position_local=2)
self.assertEqual(field_position_global_1, 3)
self.assertEqual(field_position_global_2, 5)
class BibRecordManageMultipleFieldsTest(unittest.TestCase):
""" bibrecord - testing the management of multiple fields """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">subfield1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">subfield2</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">subfield3</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">subfield4</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_delete_multiple_datafields(self):
"""bibrecord - deleting multiple datafields"""
self.fields = bibrecord.record_delete_fields(self.rec, '245', [1, 2])
self.assertEqual(self.fields[0],
([('a', 'subfield2')], ' ', ' ', '', 3))
self.assertEqual(self.fields[1],
([('a', 'subfield3')], ' ', ' ', '', 4))
def test_add_multiple_datafields_default_index(self):
"""bibrecord - adding multiple fields with the default index"""
fields = [([('a', 'subfield5')], ' ', ' ', '', 4),
([('a', 'subfield6')], ' ', ' ', '', 19)]
index = bibrecord.record_add_fields(self.rec, '245', fields)
self.assertEqual(index, None)
self.assertEqual(self.rec['245'][-2],
([('a', 'subfield5')], ' ', ' ', '', 6))
self.assertEqual(self.rec['245'][-1],
([('a', 'subfield6')], ' ', ' ', '', 7))
def test_add_multiple_datafields_with_index(self):
"""bibrecord - adding multiple fields with an index"""
fields = [([('a', 'subfield5')], ' ', ' ', '', 4),
([('a', 'subfield6')], ' ', ' ', '', 19)]
index = bibrecord.record_add_fields(self.rec, '245', fields,
field_position_local=0)
self.assertEqual(index, 0)
self.assertEqual(self.rec['245'][0],
([('a', 'subfield5')], ' ', ' ', '', 2))
self.assertEqual(self.rec['245'][1],
([('a', 'subfield6')], ' ', ' ', '', 3))
self.assertEqual(self.rec['245'][2],
([('a', 'subfield1')], ' ', ' ', '', 4))
def test_move_multiple_fields(self):
"""bibrecord - move multiple fields"""
bibrecord.record_move_fields(self.rec, '245', [1, 3])
self.assertEqual(self.rec['245'][0],
([('a', 'subfield1')], ' ', ' ', '', 2))
self.assertEqual(self.rec['245'][1],
([('a', 'subfield3')], ' ', ' ', '', 4))
self.assertEqual(self.rec['245'][2],
([('a', 'subfield2')], ' ', ' ', '', 5))
self.assertEqual(self.rec['245'][3],
([('a', 'subfield4')], ' ', ' ', '', 6))
class BibRecordDeleteFieldTest(unittest.TestCase):
""" bibrecord - testing field deletion """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe1, John</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
xml_example_record_empty = """
<record>
</record>
"""
self.rec_empty = bibrecord.create_record(xml_example_record_empty, 1, 1)[0]
def test_delete_controlfield(self):
"""bibrecord - deleting controlfield"""
bibrecord.record_delete_field(self.rec, "001", " ", " ")
self.assertEqual(bibrecord.record_get_field_values(self.rec, "001", " ", " ", " "),
[])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "b"),
['editor'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "2", "a"),
['On the foo and bar2'])
def test_delete_datafield(self):
"""bibrecord - deleting datafield"""
bibrecord.record_delete_field(self.rec, "100", " ", " ")
self.assertEqual(bibrecord.record_get_field_values(self.rec, "001", " ", " ", ""),
['33'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "b"),
[])
bibrecord.record_delete_field(self.rec, "245", " ", " ")
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "1", "a"),
['On the foo and bar1'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "2", "a"),
['On the foo and bar2'])
bibrecord.record_delete_field(self.rec, "245", " ", "2")
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "1", "a"),
['On the foo and bar1'])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "2", "a"),
[])
def test_add_delete_add_field_to_empty_record(self):
"""bibrecord - adding, deleting, and adding back a field to an empty record"""
field_position_global_1 = bibrecord.record_add_field(self.rec_empty, "003",
controlfield_value="SzGeCERN")
self.assertEqual(field_position_global_1, 1)
self.assertEqual(bibrecord.record_get_field_values(self.rec_empty, "003", " ", " ", ""),
['SzGeCERN'])
bibrecord.record_delete_field(self.rec_empty, "003", " ", " ")
self.assertEqual(bibrecord.record_get_field_values(self.rec_empty, "003", " ", " ", ""),
[])
field_position_global_1 = bibrecord.record_add_field(self.rec_empty, "003",
controlfield_value="SzGeCERN2")
self.assertEqual(field_position_global_1, 1)
self.assertEqual(bibrecord.record_get_field_values(self.rec_empty, "003", " ", " ", ""),
['SzGeCERN2'])
class BibRecordDeleteFieldFromTest(unittest.TestCase):
""" bibrecord - testing field deletion from position"""
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe1, John</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_delete_field_from(self):
"""bibrecord - deleting field from position"""
bibrecord.record_delete_field(self.rec, "100", field_position_global=4)
self.assertEqual(self.rec['100'], [([('a', 'Doe1, John')], ' ', ' ', '', 3)])
bibrecord.record_delete_field(self.rec, "100", field_position_global=3)
self.failIf(self.rec.has_key('100'))
bibrecord.record_delete_field(self.rec, "001", field_position_global=1)
bibrecord.record_delete_field(self.rec, "245", field_position_global=6)
self.failIf(self.rec.has_key('001'))
self.assertEqual(self.rec['245'], [([('a', 'On the foo and bar1')], ' ', '1', '', 5)])
# Some crash tests
bibrecord.record_delete_field(self.rec, '999', field_position_global=1)
bibrecord.record_delete_field(self.rec, '245', field_position_global=999)
class BibRecordAddSubfieldIntoTest(unittest.TestCase):
""" bibrecord - testing subfield addition """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_add_subfield_into(self):
"""bibrecord - adding subfield into position"""
bibrecord.record_add_subfield_into(self.rec, "100", "b", "Samekniv",
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "b"),
['editor', 'Samekniv'])
bibrecord.record_add_subfield_into(self.rec, "245", "x", "Elgokse",
field_position_global=4)
bibrecord.record_add_subfield_into(self.rec, "245", "x", "Fiskeflue",
subfield_position=0, field_position_global=4)
bibrecord.record_add_subfield_into(self.rec, "245", "z", "Ulriken",
subfield_position=2, field_position_global=4)
bibrecord.record_add_subfield_into(self.rec, "245", "z",
"Stortinget", subfield_position=999, field_position_global=4)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "1", "%"),
['Fiskeflue', 'On the foo and bar1', 'Ulriken', 'Elgokse', 'Stortinget'])
# Some crash tests
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_add_subfield_into, self.rec, "187", "x", "Crash",
field_position_global=1)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_add_subfield_into, self.rec, "245", "x", "Crash",
field_position_global=999)
class BibRecordModifyControlfieldTest(unittest.TestCase):
""" bibrecord - testing controlfield modification """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<controlfield tag="005">A Foo's Tale</controlfield>
<controlfield tag="008">Skeech Skeech</controlfield>
<controlfield tag="008">Whoop Whoop</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_modify_controlfield(self):
"""bibrecord - modify controlfield"""
bibrecord.record_modify_controlfield(self.rec, "001", "34",
field_position_global=1)
bibrecord.record_modify_controlfield(self.rec, "008", "Foo Foo",
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "001"), ["34"])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "005"), ["A Foo's Tale"])
self.assertEqual(bibrecord.record_get_field_values(self.rec, "008"), ["Foo Foo", "Whoop Whoop"])
# Some crash tests
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_controlfield, self.rec, "187", "Crash",
field_position_global=1)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_controlfield, self.rec, "008", "Test",
field_position_global=10)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_controlfield, self.rec, "245", "Burn",
field_position_global=5)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "2", "%"),
["On the foo and bar2"])
class BibRecordModifySubfieldTest(unittest.TestCase):
""" bibrecord - testing subfield modification """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
<subfield code="b">On writing unit tests</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_modify_subfield(self):
"""bibrecord - modify subfield"""
bibrecord.record_modify_subfield(self.rec, "245", "a", "Holmenkollen",
0, field_position_global=4)
bibrecord.record_modify_subfield(self.rec, "245", "x", "Brann", 1,
field_position_global=4)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "245", " ", "1", "%"),
['Holmenkollen', 'Brann'])
# Some crash tests
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_subfield, self.rec, "187", "x", "Crash", 0,
field_position_global=1)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_subfield, self.rec, "245", "x", "Burn", 1,
field_position_global=999)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_modify_subfield, self.rec, "245", "a", "Burn",
999, field_position_global=4)
class BibRecordDeleteSubfieldFromTest(unittest.TestCase):
""" bibrecord - testing subfield deletion """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
<subfield code="z">Skal vi danse?</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_delete_subfield_from(self):
"""bibrecord - delete subfield from position"""
bibrecord.record_delete_subfield_from(self.rec, "100", 2,
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "z"),
[])
bibrecord.record_delete_subfield_from(self.rec, "100", 0,
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "%"),
['editor'])
bibrecord.record_delete_subfield_from(self.rec, "100", 0,
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "%"),
[])
# Some crash tests
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_delete_subfield_from, self.rec, "187", 0,
field_position_global=1)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_delete_subfield_from, self.rec, "245", 0,
field_position_global=999)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_delete_subfield_from, self.rec, "245", 999,
field_position_global=4)
class BibRecordDeleteSubfieldTest(unittest.TestCase):
""" bibrecord - testing subfield deletion """
def setUp(self):
"""Initialize stuff"""
self.xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
<subfield code="z">Skal vi danse?</subfield>
<subfield code="a">Doe3, Zbigniew</subfield>
<subfield code="d">Doe4, Joachim</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="2">
<subfield code="a">On the foo and bar2</subfield>
</datafield>
<datafield tag="246" ind1="1" ind2="2">
<subfield code="c">On the foo and bar1</subfield>
</datafield>
<datafield tag="246" ind1="1" ind2="2">
<subfield code="c">On the foo and bar2</subfield>
</datafield>
</record>
"""
def test_simple_removals(self):
""" bibrecord - delete subfield by its code"""
# testing a simple removals where all the fields are removed
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
bibrecord.record_delete_subfield(rec, "041", "b") # nothing should change
self.assertEqual(rec["041"][0][0], [("a", "eng")])
bibrecord.record_delete_subfield(rec, "041", "a")
self.assertEqual(rec["041"][0][0], [])
def test_indices_important(self):
""" bibrecord - delete subfield where indices are important"""
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
bibrecord.record_delete_subfield(rec, "245", "a", " ", "1")
self.assertEqual(rec["245"][0][0], [])
self.assertEqual(rec["245"][1][0], [("a", "On the foo and bar2")])
bibrecord.record_delete_subfield(rec, "245", "a", " ", "2")
self.assertEqual(rec["245"][1][0], [])
def test_remove_some(self):
""" bibrecord - delete subfield when some should be preserved and some removed"""
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
bibrecord.record_delete_subfield(rec, "100", "a", " ", " ")
self.assertEqual(rec["100"][0][0], [("b", "editor"), ("z", "Skal vi danse?"), ("d", "Doe4, Joachim")])
def test_more_fields(self):
""" bibrecord - delete subfield where more fits criteria"""
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
bibrecord.record_delete_subfield(rec, "246", "c", "1", "2")
self.assertEqual(rec["246"][1][0], [])
self.assertEqual(rec["246"][0][0], [])
def test_nonexisting_removals(self):
""" bibrecord - delete subfield that does not exist """
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
# further preparation
bibrecord.record_delete_subfield(rec, "100", "a", " ", " ")
self.assertEqual(rec["100"][0][0], [("b", "editor"), ("z", "Skal vi danse?"), ("d", "Doe4, Joachim")])
#the real tests begin
# 1) removing the subfield from an empty list of subfields
bibrecord.record_delete_subfield(rec, "246", "c", "1", "2")
self.assertEqual(rec["246"][1][0], [])
self.assertEqual(rec["246"][0][0], [])
bibrecord.record_delete_subfield(rec, "246", "8", "1", "2")
self.assertEqual(rec["246"][1][0], [])
self.assertEqual(rec["246"][0][0], [])
# 2) removing a subfield from a field that has some subfields but none has an appropriate code
bibrecord.record_delete_subfield(rec, "100", "a", " ", " ")
self.assertEqual(rec["100"][0][0], [("b", "editor"), ("z", "Skal vi danse?"), ("d", "Doe4, Joachim")])
bibrecord.record_delete_subfield(rec, "100", "e", " ", " ")
self.assertEqual(rec["100"][0][0], [("b", "editor"), ("z", "Skal vi danse?"), ("d", "Doe4, Joachim")])
class BibRecordMoveSubfieldTest(unittest.TestCase):
""" bibrecord - testing subfield moving """
def setUp(self):
"""Initialize stuff"""
xml_example_record = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Doe2, John</subfield>
<subfield code="b">editor</subfield>
<subfield code="c">fisk</subfield>
<subfield code="d">eple</subfield>
<subfield code="e">hammer</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2="1">
<subfield code="a">On the foo and bar1</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml_example_record, 1, 1)[0]
def test_move_subfield(self):
"""bibrecord - move subfields"""
bibrecord.record_move_subfield(self.rec, "100", 2, 4,
field_position_global=3)
bibrecord.record_move_subfield(self.rec, "100", 1, 0,
field_position_global=3)
bibrecord.record_move_subfield(self.rec, "100", 2, 999,
field_position_global=3)
self.assertEqual(bibrecord.record_get_field_values(self.rec, "100", " ", " ", "%"),
['editor', 'Doe2, John', 'hammer', 'fisk', 'eple'])
# Some crash tests
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_move_subfield, self.rec, "187", 0, 1,
field_position_global=3)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_move_subfield, self.rec, "100", 1, 0,
field_position_global=999)
self.assertRaises(bibrecord.InvenioBibRecordFieldError,
bibrecord.record_move_subfield, self.rec, "100", 999, 0,
field_position_global=3)
class BibRecordSpecialTagParsingTest(unittest.TestCase):
""" bibrecord - parsing special tags (FMT, FFT)"""
def setUp(self):
"""setting up example records"""
self.xml_example_record_with_fmt = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="FMT" ind1=" " ind2=" ">
<subfield code="f">HB</subfield>
<subfield code="g">Let us see if this gets inserted well.</subfield>
</datafield>
</record>
"""
self.xml_example_record_with_fft = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="FFT" ind1=" " ind2=" ">
<subfield code="a">file:///foo.pdf</subfield>
<subfield code="a">http://bar.com/baz.ps.gz</subfield>
</datafield>
</record>
"""
self.xml_example_record_with_xyz = """
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="041" ind1=" " ind2=" ">
<subfield code="a">eng</subfield>
</datafield>
<datafield tag="XYZ" ind1=" " ind2=" ">
<subfield code="f">HB</subfield>
<subfield code="g">Let us see if this gets inserted well.</subfield>
</datafield>
</record>
"""
def test_parsing_file_containing_fmt_special_tag_with_correcting(self):
"""bibrecord - parsing special FMT tag, correcting on"""
rec = bibrecord.create_record(self.xml_example_record_with_fmt, 1, 1)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'FMT': [([('f', 'HB'), ('g', 'Let us see if this gets inserted well.')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FMT", " ", " ", "f"),
['HB'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FMT", " ", " ", "g"),
['Let us see if this gets inserted well.'])
def test_parsing_file_containing_fmt_special_tag_without_correcting(self):
"""bibrecord - parsing special FMT tag, correcting off"""
rec = bibrecord.create_record(self.xml_example_record_with_fmt, 1, 0)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'FMT': [([('f', 'HB'), ('g', 'Let us see if this gets inserted well.')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FMT", " ", " ", "f"),
['HB'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FMT", " ", " ", "g"),
['Let us see if this gets inserted well.'])
def test_parsing_file_containing_fft_special_tag_with_correcting(self):
"""bibrecord - parsing special FFT tag, correcting on"""
rec = bibrecord.create_record(self.xml_example_record_with_fft, 1, 1)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'FFT': [([('a', 'file:///foo.pdf'), ('a', 'http://bar.com/baz.ps.gz')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FFT", " ", " ", "a"),
['file:///foo.pdf', 'http://bar.com/baz.ps.gz'])
def test_parsing_file_containing_fft_special_tag_without_correcting(self):
"""bibrecord - parsing special FFT tag, correcting off"""
rec = bibrecord.create_record(self.xml_example_record_with_fft, 1, 0)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'FFT': [([('a', 'file:///foo.pdf'), ('a', 'http://bar.com/baz.ps.gz')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "FFT", " ", " ", "a"),
['file:///foo.pdf', 'http://bar.com/baz.ps.gz'])
def test_parsing_file_containing_xyz_special_tag_with_correcting(self):
"""bibrecord - parsing unrecognized special XYZ tag, correcting on"""
# XYZ should not get accepted when correcting is on; should get changed to 000
rec = bibrecord.create_record(self.xml_example_record_with_xyz, 1, 1)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'000': [([('f', 'HB'), ('g', 'Let us see if this gets inserted well.')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "XYZ", " ", " ", "f"),
[])
self.assertEqual(bibrecord.record_get_field_values(rec, "XYZ", " ", " ", "g"),
[])
self.assertEqual(bibrecord.record_get_field_values(rec, "000", " ", " ", "f"),
['HB'])
self.assertEqual(bibrecord.record_get_field_values(rec, "000", " ", " ", "g"),
['Let us see if this gets inserted well.'])
def test_parsing_file_containing_xyz_special_tag_without_correcting(self):
"""bibrecord - parsing unrecognized special XYZ tag, correcting off"""
# XYZ should get accepted without correcting
rec = bibrecord.create_record(self.xml_example_record_with_xyz, 1, 0)[0]
self.assertEqual(rec,
{u'001': [([], " ", " ", '33', 1)],
'XYZ': [([('f', 'HB'), ('g', 'Let us see if this gets inserted well.')], " ", " ", "", 3)],
'041': [([('a', 'eng')], " ", " ", "", 2)]})
self.assertEqual(bibrecord.record_get_field_values(rec, "041", " ", " ", "a"),
['eng'])
self.assertEqual(bibrecord.record_get_field_values(rec, "XYZ", " ", " ", "f"),
['HB'])
self.assertEqual(bibrecord.record_get_field_values(rec, "XYZ", " ", " ", "g"),
['Let us see if this gets inserted well.'])
class BibRecordPrintingTest(unittest.TestCase):
""" bibrecord - testing for printing record """
def setUp(self):
"""Initialize stuff"""
self.xml_example_record = """
<record>
<controlfield tag="001">81</controlfield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">TEST-ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">Test ti</subfield>
</datafield>
</record>"""
self.xml_example_record_short = """
<record>
<controlfield tag="001">81</controlfield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">TEST-ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">ARTICLE-2006-001</subfield>
</datafield>
</record>"""
self.xml_example_multi_records = """
<record>
<controlfield tag="001">81</controlfield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">TEST-ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="245" ind1=" " ind2=" ">
<subfield code="a">Test ti</subfield>
</datafield>
</record>
<record>
<controlfield tag="001">82</controlfield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Author, t</subfield>
</datafield>
</record>"""
self.xml_example_multi_records_short = """
<record>
<controlfield tag="001">81</controlfield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">TEST-ARTICLE-2006-001</subfield>
</datafield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">ARTICLE-2006-001</subfield>
</datafield>
</record>
<record>
<controlfield tag="001">82</controlfield>
</record>"""
def test_record_xml_output(self):
"""bibrecord - xml output"""
rec = bibrecord.create_record(self.xml_example_record, 1, 1)[0]
rec_short = bibrecord.create_record(self.xml_example_record_short, 1, 1)[0]
self.assertEqual(bibrecord.create_record(bibrecord.record_xml_output(rec, tags=[]), 1, 1)[0], rec)
self.assertEqual(bibrecord.create_record(bibrecord.record_xml_output(rec, tags=["001", "037"]), 1, 1)[0], rec_short)
self.assertEqual(bibrecord.create_record(bibrecord.record_xml_output(rec, tags=["037"]), 1, 1)[0], rec_short)
class BibRecordCreateFieldTest(unittest.TestCase):
""" bibrecord - testing for creating field """
def test_create_valid_field(self):
"""bibrecord - create and check a valid field"""
bibrecord.create_field()
bibrecord.create_field([('a', 'testa'), ('b', 'testb')], '2', 'n',
'controlfield', 15)
def test_invalid_field_raises_exception(self):
"""bibrecord - exception raised when creating an invalid field"""
# Invalid subfields.
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, 'subfields', '1', '2', 'controlfield', 10)
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, ('1', 'value'), '1', '2', 'controlfield', 10)
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [('value')], '1', '2', 'controlfield', 10)
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [('1', 'value', '2')], '1', '2', 'controlfield', 10)
# Invalid indicators.
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [], 1, '2', 'controlfield', 10)
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [], '1', 2, 'controlfield', 10)
# Invalid controlfield value
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [], '1', '2', 13, 10)
# Invalid global position
self.assertRaises(bibrecord_config.InvenioBibRecordFieldError,
bibrecord.create_field, [], '1', '2', 'controlfield', 'position')
def test_compare_fields(self):
"""bibrecord - compare fields"""
# Identical
field0 = ([('a', 'test')], '1', '2', '', 0)
field1 = ([('a', 'test')], '1', '2', '', 3)
self.assertEqual(True,
bibrecord._compare_fields(field0, field1, strict=True))
self.assertEqual(True,
bibrecord._compare_fields(field0, field1, strict=False))
# Order of the subfields changed.
field0 = ([('a', 'testa'), ('b', 'testb')], '1', '2', '', 0)
field1 = ([('b', 'testb'), ('a', 'testa')], '1', '2', '', 3)
self.assertEqual(False,
bibrecord._compare_fields(field0, field1, strict=True))
self.assertEqual(True,
bibrecord._compare_fields(field0, field1, strict=False))
# Different
field0 = ([], '3', '2', '', 0)
field1 = ([], '1', '2', '', 3)
self.assertEqual(False,
bibrecord._compare_fields(field0, field1, strict=True))
self.assertEqual(False,
bibrecord._compare_fields(field0, field1, strict=False))
class BibRecordFindFieldTest(unittest.TestCase):
""" bibrecord - testing for finding field """
def setUp(self):
"""Initialize stuff"""
xml = """
<record>
<controlfield tag="001">81</controlfield>
<datafield tag="037" ind1=" " ind2=" ">
<subfield code="a">TEST-ARTICLE-2006-001</subfield>
<subfield code="b">ARTICLE-2007-001</subfield>
</datafield>
</record>
"""
self.rec = bibrecord.create_record(xml)[0]
self.field0 = self.rec['001'][0]
self.field1 = self.rec['037'][0]
self.field2 = (
[self.field1[0][1], self.field1[0][0]],
self.field1[1],
self.field1[2],
self.field1[3],
self.field1[4],
)
def test_finding_field_strict(self):
"""bibrecord - test finding field strict"""
self.assertEqual((1, 0),
bibrecord.record_find_field(self.rec, '001', self.field0,
strict=True))
self.assertEqual((2, 0),
bibrecord.record_find_field(self.rec, '037', self.field1,
strict=True))
self.assertEqual((None, None),
bibrecord.record_find_field(self.rec, '037', self.field2,
strict=True))
def test_finding_field_loose(self):
"""bibrecord - test finding field loose"""
self.assertEqual((1, 0),
bibrecord.record_find_field(self.rec, '001', self.field0,
strict=False))
self.assertEqual((2, 0),
bibrecord.record_find_field(self.rec, '037', self.field1,
strict=False))
self.assertEqual((2, 0),
bibrecord.record_find_field(self.rec, '037', self.field2,
strict=False))
class BibRecordSingletonTest(unittest.TestCase):
""" bibrecord - testing singleton removal """
def setUp(self):
"""Initialize stuff"""
self.xml = """<collection>
<record>
<controlfield tag="001">33</controlfield>
<controlfield tag="002" />
<datafield tag="99" ind1=" " ind2=" "/>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a" />
</datafield>
<datafield tag="100" ind1=" " ind2=" ">
<subfield code="a">Some value</subfield>
</datafield>
<tagname />
</record>
<record />
<collection>"""
self.rec_expected = {
'001': [([], ' ', ' ', '33', 1)],
'100': [([('a', 'Some value')], ' ', ' ', '', 2)],
}
if parser_minidom_available:
def test_singleton_removal_minidom(self):
- """bibrecord - singleton removal with minidom"""
+ """bibrecord - enforcing singleton removal with minidom"""
rec = bibrecord.create_records(self.xml, verbose=1,
- correct=1, parser='minidom')[0][0]
+ correct=1, parser='minidom',
+ keep_singletons=False)[0][0]
self.assertEqual(rec, self.rec_expected)
if parser_4suite_available:
def test_singleton_removal_4suite(self):
- """bibrecord - singleton removal with 4suite"""
+ """bibrecord - enforcing singleton removal with 4suite"""
rec = bibrecord.create_records(self.xml, verbose=1,
- correct=1, parser='4suite')[0][0]
+ correct=1, parser='4suite',
+ keep_singletons=False)[0][0]
self.assertEqual(rec, self.rec_expected)
if parser_pyrxp_available:
def test_singleton_removal_pyrxp(self):
- """bibrecord - singleton removal with pyrxp"""
+ """bibrecord - enforcing singleton removal with pyrxp"""
rec = bibrecord.create_records(self.xml, verbose=1,
- correct=1, parser='pyrxp')[0][0]
+ correct=1, parser='pyrxp',
+ keep_singletons=False)[0][0]
self.assertEqual(rec, self.rec_expected)
class BibRecordNumCharRefTest(unittest.TestCase):
""" bibrecord - testing numerical character reference expansion"""
def setUp(self):
"""Initialize stuff"""
self.xml = """<?xml version="1.0" encoding="UTF-8"?>
<record>
<controlfield tag="001">33</controlfield>
<datafield tag="123" ind1=" " ind2=" ">
<subfield code="a">Σ & Σ</subfield>
<subfield code="a">use &amp; in XML</subfield>
</datafield>
</record>"""
self.rec_expected = {
'001': [([], ' ', ' ', '33', 1)],
'123': [([('a', '\xce\xa3 & \xce\xa3'), ('a', 'use & in XML'),], ' ', ' ', '', 2)],
}
if parser_minidom_available:
def test_numcharref_expansion_minidom(self):
"""bibrecord - numcharref expansion with minidom"""
rec = bibrecord.create_records(self.xml, verbose=1,
correct=1, parser='minidom')[0][0]
self.assertEqual(rec, self.rec_expected)
if parser_4suite_available:
def test_numcharref_expansion_4suite(self):
"""bibrecord - numcharref expansion with 4suite"""
rec = bibrecord.create_records(self.xml, verbose=1,
correct=1, parser='4suite')[0][0]
self.assertEqual(rec, self.rec_expected)
if parser_pyrxp_available:
def test_numcharref_expansion_pyrxp(self):
"""bibrecord - but *no* numcharref expansion with pyrxp (see notes)
FIXME: pyRXP does not seem to like num char ref entities,
so this test is mostly left here in a TDD style in order
to remind us of this fact. If we want to fix this
situation, then we should probably use pyRXPU that uses
Unicode strings internally, hence it is num char ref
friendly. Maybe we should use pyRXPU by default, if
performance is acceptable, or maybe we should introduce a
flag to govern this behaviour.
"""
rec = bibrecord.create_records(self.xml, verbose=1,
correct=1, parser='pyrxp')[0][0]
#self.assertEqual(rec, self.rec_expected)
self.assertEqual(rec, None)
TEST_SUITE = make_test_suite(
BibRecordSuccessTest,
BibRecordParsersTest,
BibRecordBadInputTreatmentTest,
BibRecordGettingFieldValuesTest,
BibRecordGettingFieldValuesViaWildcardsTest,
BibRecordAddFieldTest,
BibRecordDeleteFieldTest,
BibRecordManageMultipleFieldsTest,
BibRecordDeleteFieldFromTest,
BibRecordAddSubfieldIntoTest,
BibRecordModifyControlfieldTest,
BibRecordModifySubfieldTest,
BibRecordDeleteSubfieldFromTest,
BibRecordMoveSubfieldTest,
BibRecordAccentedUnicodeLettersTest,
BibRecordSpecialTagParsingTest,
BibRecordPrintingTest,
BibRecordCreateFieldTest,
BibRecordFindFieldTest,
BibRecordDeleteSubfieldTest,
BibRecordSingletonTest,
BibRecordNumCharRefTest
)
if __name__ == '__main__':
run_test_suite(TEST_SUITE)