def filter_marcrec(marcrec, main_field=bconfig.CFG_MAIN_FIELD, others=bconfig.CFG_OTHER_FIELDS):
"""Remove the unwanted fields and returns xml."""
if isinstance(main_field, six.string_types):
main_field = [main_field]
if isinstance(others, six.string_types):
others = [others]
key_map = ["001"]
for field in main_field + others:
tag, ind1, ind2 = _parse_marc_code(field)
key_map.append(tag)
return bibrecord.print_rec(marcrec, 1, tags=key_map)
def filter_marcrec(marcrec, main_field=bconfig.CFG_MAIN_FIELD,
others=bconfig.CFG_OTHER_FIELDS):
"""Remove the unwanted fields and returns xml."""
if isinstance(main_field, six.string_types):
main_field = [main_field]
if isinstance(others, six.string_types):
others = [others]
key_map = ['001']
for field in main_field + others:
tag, ind1, ind2 = _parse_marc_code(field)
key_map.append(tag)
return bibrecord.print_rec(marcrec, 1, tags=key_map)
def create_xml(recid, texkey):
""" Create the marcxml snippet with the new texkey
@param recid: recid of the record to be updated
@type: int
@param texkey: texkey that has been generated
@type: str
@return: marcxml with the fields to be record_add_field
@rtype: str
"""
record = {}
record_add_field(record, '001', controlfield_value=str(recid))
subfields_toadd = [('a', texkey), ('9', 'INSPIRETeX')]
record_add_field(record, tag='035', subfields=subfields_toadd)
return print_rec(record)
def create_xml(recid, texkey):
"""Create the marcxml snippet with the new texkey.
:param recid: recid of the record to be updated
:type: int
:param texkey: texkey that has been generated
:type: str
:return: marcxml with the fields to be record_add_field
:rtype: str
"""
record = {}
record_add_field(record, '001', controlfield_value=str(recid))
subfields_toadd = [('a', texkey), ('9', 'INSPIRETeX')]
record_add_field(record, tag='035', subfields=subfields_toadd)
return print_rec(record)
def add_record_cnum(recid, uid):
"""
Check if the record has already a cnum. If not generate a new one
and return the result
@param recid: recid of the record under check. Used to retrieve cache file
@type recid: int
@param uid: id of the user. Used to retrieve cache file
@type uid: int
@return: None if cnum already present, new cnum otherwise
@rtype: None or string
"""
# Import placed here to avoid circular dependency
from invenio.modules.sequencegenerator.cnum import CnumSeq, ConferenceNoStartDateError
record_revision, record, pending_changes, deactivated_hp_changes, \
undo_list, redo_list = get_cache_contents(recid, uid)[1:]
record_strip_empty_volatile_subfields(record)
# Check if record already has a cnum
tag_111__g_content = record_get_field_value(record, "111", " ", " ", "g")
if tag_111__g_content:
return
else:
cnum_seq = CnumSeq()
try:
new_cnum = cnum_seq.next_value(xml_record=wash_for_xml(print_rec(record)))
except ConferenceNoStartDateError:
return None
field_add_subfield(record['111'][0], 'g', new_cnum)
update_cache_contents(recid, uid, record_revision,
record,
pending_changes,
deactivated_hp_changes,
undo_list, redo_list)
return new_cnum
def add_record_cnum(recid, uid):
"""
Check if the record has already a cnum. If not generate a new one
and return the result
@param recid: recid of the record under check. Used to retrieve cache file
@type recid: int
@param uid: id of the user. Used to retrieve cache file
@type uid: int
@return: None if cnum already present, new cnum otherwise
@rtype: None or string
"""
# Import placed here to avoid circular dependency
from invenio.modules.sequencegenerator.cnum import CnumSeq, ConferenceNoStartDateError
record_revision, record, pending_changes, deactivated_hp_changes, \
undo_list, redo_list = get_cache_contents(recid, uid)[1:]
record_strip_empty_volatile_subfields(record)
# Check if record already has a cnum
tag_111__g_content = record_get_field_value(record, "111", " ", " ", "g")
if tag_111__g_content:
return
else:
cnum_seq = CnumSeq()
try:
new_cnum = cnum_seq.next_value(xml_record=wash_for_xml(print_rec(record)))
except ConferenceNoStartDateError:
return None
field_add_subfield(record['111'][0], 'g', new_cnum)
update_cache_contents(recid, uid, record_revision,
record,
pending_changes,
deactivated_hp_changes,
undo_list, redo_list)
return new_cnum
def move_drafts_articles_to_ready(journal_name, issue):
"""
Move draft articles to their final "collection".
To do so we rely on the convention that an admin-chosen keyword
must be removed from the metadata
"""
protected_datafields = ['100', '245', '246', '520', '590', '700']
keyword_to_remove = get_journal_draft_keyword_to_remove(journal_name)
collections_to_refresh = {}
indexes_to_refresh = get_journal_index_to_refresh_on_release(journal_name)
bibindex_indexes_params = []
if indexes_to_refresh:
bibindex_indexes_params = ['-w', ','.join(indexes_to_refresh)]
categories = get_journal_categories(journal_name, issue)
task_sequence_id = str(bibtask_allocate_sequenceid())
for category in categories:
articles = get_journal_articles(journal_name, issue, category)
for order, recids in iteritems(articles):
for recid in recids:
record_xml = format_record(recid, of='xm')
if not record_xml:
continue
new_record_xml_path = os.path.join(CFG_TMPSHAREDDIR,
'webjournal_publish_' + \
str(recid) + '.xml')
if os.path.exists(new_record_xml_path):
# Do not modify twice
continue
record_struc = create_record(record_xml)
record = record_struc[0]
new_record = update_draft_record_metadata(record,
protected_datafields,
keyword_to_remove)
new_record_xml = print_rec(new_record)
if new_record_xml.find(keyword_to_remove) >= 0:
new_record_xml = new_record_xml.replace(keyword_to_remove, '')
# Write to file
new_record_xml_file = file(new_record_xml_path, 'w')
new_record_xml_file.write(new_record_xml)
new_record_xml_file.close()
# Submit
task_low_level_submission('bibupload',
'WebJournal',
'-c', new_record_xml_path,
'-I', task_sequence_id)
task_low_level_submission('bibindex',
'WebJournal',
'-i', str(recid),
'-I', task_sequence_id,
*bibindex_indexes_params)
for collection in get_all_collections_of_a_record(recid):
collections_to_refresh[collection] = ''
# Refresh collections
collections_to_refresh.update([(c, '') for c in get_journal_collection_to_refresh_on_release(journal_name)])
for collection in collections_to_refresh.keys():
task_low_level_submission('webcoll',
'WebJournal',
'-f', '-P', '2', '-p', '1', '-c', collection,
'-I', task_sequence_id)
def move_drafts_articles_to_ready(journal_name, issue):
"""
Move draft articles to their final "collection".
To do so we rely on the convention that an admin-chosen keyword
must be removed from the metadata
"""
protected_datafields = ['100', '245', '246', '520', '590', '700']
keyword_to_remove = get_journal_draft_keyword_to_remove(journal_name)
collections_to_refresh = {}
indexes_to_refresh = get_journal_index_to_refresh_on_release(journal_name)
bibindex_indexes_params = []
if indexes_to_refresh:
bibindex_indexes_params = ['-w', ','.join(indexes_to_refresh)]
categories = get_journal_categories(journal_name, issue)
task_sequence_id = str(bibtask_allocate_sequenceid())
for category in categories:
articles = get_journal_articles(journal_name, issue, category)
for order, recids in iteritems(articles):
for recid in recids:
record_xml = format_record(recid, of='xm')
if not record_xml:
continue
new_record_xml_path = os.path.join(CFG_TMPSHAREDDIR,
'webjournal_publish_' + \
str(recid) + '.xml')
if os.path.exists(new_record_xml_path):
# Do not modify twice
continue
record_struc = create_record(record_xml)
record = record_struc[0]
new_record = update_draft_record_metadata(record,
protected_datafields,
keyword_to_remove)
new_record_xml = print_rec(new_record)
if new_record_xml.find(keyword_to_remove) >= 0:
new_record_xml = new_record_xml.replace(keyword_to_remove, '')
# Write to file
new_record_xml_file = file(new_record_xml_path, 'w')
new_record_xml_file.write(new_record_xml)
new_record_xml_file.close()
# Submit
task_low_level_submission('bibupload',
'WebJournal',
'-c', new_record_xml_path,
'-I', task_sequence_id)
task_low_level_submission('bibindex',
'WebJournal',
'-i', str(recid),
'-I', task_sequence_id,
*bibindex_indexes_params)
for collection in get_all_collections_of_a_record(recid):
collections_to_refresh[collection] = ''
# Refresh collections
collections_to_refresh.update([(c, '') for c in get_journal_collection_to_refresh_on_release(journal_name)])
for collection in collections_to_refresh.keys():
task_low_level_submission('webcoll',
'WebJournal',
'-f', '-P', '2', '-p', '1', '-c', collection,
'-I', task_sequence_id)
