def Move_Files_Archive(parameters, curdir, form, user_info=None):
"""DEPRECATED: Use FFT instead."""
MainDir = "%s/files/MainFiles" % curdir
IncludeDir = "%s/files/AdditionalFiles" % curdir
watcheddirs = {'Main' : MainDir, 'Additional' : IncludeDir}
for type, dir in iteritems(watcheddirs):
if os.path.exists(dir):
formats = {}
files = os.listdir(dir)
files.sort()
for file in files:
dummy, filename, extension = decompose_file(file)
if filename not in formats:
formats[filename] = []
formats[filename].append(normalize_format(extension))
# first delete all missing files
bibarchive = BibRecDocs(sysno)
existingBibdocs = bibarchive.list_bibdocs(type)
for existingBibdoc in existingBibdocs:
if bibarchive.get_docname(existingBibdoc.id) not in formats:
existingBibdoc.delete()
# then create/update the new ones
for key in formats.keys():
# instanciate bibdoc object
bibarchive.add_new_file('%s/%s%s' % (dir, key, formats[key]), doctype=type, never_fail=True)
return ""
def _getfile_py(req,
recid=0,
docid=0,
version="",
name="",
docformat="",
ln=CFG_SITE_LANG):
if not recid:
## Let's obtain the recid from the docid
if docid:
try:
bibdoc = BibDoc(docid=docid)
recid = bibdoc.bibrec_links[0]["recid"]
except InvenioBibDocFileError:
return warning_page(
_("An error has happened in trying to retrieve the requested file."
), req, ln)
else:
return warning_page(
_('Not enough information to retrieve the document'), req,
ln)
else:
brd = BibRecDocs(recid)
if not name and docid:
## Let's obtain the name from the docid
try:
name = brd.get_docname(docid)
except InvenioBibDocFileError:
return warning_page(
_("An error has happened in trying to retrieving the requested file."
), req, ln)
docformat = normalize_format(docformat)
redirect_to_url(
req, '%s/%s/%s/files/%s%s?ln=%s%s' %
(CFG_SITE_URL, CFG_SITE_RECORD, recid, name, docformat, ln,
version and 'version=%s' % version or ''),
apache.HTTP_MOVED_PERMANENTLY)
def _getfile_py(req, recid=0, docid=0, version="", name="", docformat="", ln=CFG_SITE_LANG):
if not recid:
## Let's obtain the recid from the docid
if docid:
try:
bibdoc = BibDoc(docid=docid)
recid = bibdoc.bibrec_links[0]["recid"]
except InvenioBibDocFileError:
return warning_page(_("An error has happened in trying to retrieve the requested file."), req, ln)
else:
return warning_page(_('Not enough information to retrieve the document'), req, ln)
else:
brd = BibRecDocs(recid)
if not name and docid:
## Let's obtain the name from the docid
try:
name = brd.get_docname(docid)
except InvenioBibDocFileError:
return warning_page(_("An error has happened in trying to retrieving the requested file."), req, ln)
docformat = normalize_format(docformat)
redirect_to_url(req, '%s/%s/%s/files/%s%s?ln=%s%s' % (CFG_SITE_URL, CFG_SITE_RECORD, recid, name, docformat, ln, version and 'version=%s' % version or ''), apache.HTTP_MOVED_PERMANENTLY)
"""BibFormat element - Prints a links to fulltext
"""
__revision__ = "$Id$"
import re
from invenio.legacy.bibdocfile.api import BibRecDocs, file_strip_ext, normalize_format, compose_format
from invenio.base.i18n import gettext_set_language
from invenio.config import CFG_SITE_URL, CFG_CERN_SITE, CFG_SITE_RECORD, \
CFG_BIBFORMAT_HIDDEN_FILE_FORMATS
from invenio.legacy.bibdocfile.config import CFG_BIBDOCFILE_ICON_SUBFORMAT_RE
from cgi import escape, parse_qs
from six.moves.urllib.parse import urlparse
from os.path import basename
import urllib
_CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS = set(normalize_format(fmt) for fmt in CFG_BIBFORMAT_HIDDEN_FILE_FORMATS)
cern_arxiv_categories = ["astro-ph", "chao-dyn", "cond-mat", "gr-qc",
"hep-ex", "hep-lat", "hep-ph", "hep-th", "math-ph",
"math", "nucl-ex", "nucl-th", "out", "physics",
"quant-ph", "q-alg", "cs", "adap-org", "comp-gas",
"chem-ph", "cs", "math", "neuro-sys", "patt-sol",
"solv-int", "acc-phys", "alg-geom", "ao-sci",
"atom-ph", "cmp-lg", "dg-ga", "funct-an", "mtrl-th",
"plasm-ph", "q-alg", "supr-con"]
def format_element(bfo, style, separator='; ', show_icons='no', focus_on_main_file='no', show_subformat_icons='no'):
"""
This is the default format for formatting fulltext links.
When possible, it returns only the main file(s) (+ link to
def get_files(bfo, distinguish_main_and_additional_files=True,
include_subformat_icons=False):
"""
Returns the files available for the given record.
Returned structure is a tuple (parsed_urls, old_versions, additionals):
- parsed_urls: contains categorized URLS (see details below)
- old_versions: set to True if we can have access to old versions
- additionals: set to True if we have other documents than the 'main' document
Parameter 'include_subformat_icons' decides if subformat
considered as icons should be returned
'parsed_urls' is a dictionary in the form::
{'main_urls' : {'Main' : [('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/aFile.pdf', 'aFile', 'PDF'),
('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/aFile.gif', 'aFile', 'GIF')],
'Additional': [('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/bFile.pdf', 'bFile', 'PDF')]},
'other_urls': [('http://externalurl.com/aFile.pdf', 'Fulltext'), # url(8564_u), description(8564_z/y)
('http://externalurl.com/bFile.pdf', 'Fulltext')],
'cern_urls' : [('http://cern.ch/aFile.pdf', 'Fulltext'), # url(8564_u), description(8564_z/y)
('http://cern.ch/bFile.pdf', 'Fulltext')],
}
Some notes about returned structure:
- key 'cern_urls' is only available on CERN site
- keys in main_url dictionaries are defined by the BibDoc.
- older versions are not part of the parsed urls
- returns only main files when possible, that is when doctypes
make a distinction between 'Main' files and other
files. Otherwise returns all the files as main. This is only
enabled if distinguish_main_and_additional_files is set to True
"""
CFG_SITE_URL = current_app.config['CFG_SITE_URL']
CFG_CERN_SITE = current_app.config['CFG_CERN_SITE']
CFG_BIBFORMAT_HIDDEN_FILE_FORMATS = current_app.config['CFG_BIBFORMAT_HIDDEN_FILE_FORMATS']
_CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS = set(normalize_format(fmt) for fmt in CFG_BIBFORMAT_HIDDEN_FILE_FORMATS)
_ = gettext_set_language(bfo.lang)
urls = bfo.fields("8564_")
bibarchive = BibRecDocs(bfo.recID)
old_versions = False # We can provide link to older files. Will be
# set to True if older files are found.
additionals = False # We have additional files. Will be set to
# True if additional files are found.
# Prepare object to return
parsed_urls = {'main_urls':{}, # Urls hosted by Invenio (bibdocs)
'others_urls':[] # External urls
}
if CFG_CERN_SITE:
parsed_urls['cern_urls'] = [] # cern.ch urls
# Doctypes can of any type, but when there is one file marked as
# 'Main', we consider that there is a distinction between "main"
# and "additional" files. Otherwise they will all be considered
# equally as main files
distinct_main_and_additional_files = False
if len(bibarchive.list_bibdocs(doctype='Main')) > 0 and \
distinguish_main_and_additional_files:
distinct_main_and_additional_files = True
# Parse URLs
for complete_url in urls:
if complete_url.has_key('u'):
url = complete_url['u']
(dummy, host, path, dummy, params, dummy) = urlparse(url)
subformat = complete_url.get('x', '')
filename = urllib.unquote(basename(path))
name = file_strip_ext(filename)
url_format = filename[len(name):]
if url_format.startswith('.'):
url_format = url_format[1:]
if compose_format(url_format, subformat) in _CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS:
## This format should be hidden.
continue
descr = _("Fulltext")
if complete_url.has_key('y'):
descr = complete_url['y']
if descr == 'Fulltext':
descr = _("Fulltext")
if not url.startswith(CFG_SITE_URL): # Not a bibdoc?
if not descr: # For not bibdoc let's have a description
# Display the URL in full:
descr = url
if CFG_CERN_SITE and 'cern.ch' in host and \
('/setlink?' in url or \
'cms' in host or \
'documents.cern.ch' in url or \
'doc.cern.ch' in url or \
'preprints.cern.ch' in url):
url_params_dict = dict([part.split('=') for part in params.split('&') if len(part.split('=')) == 2])
if url_params_dict.has_key('categ') and \
(url_params_dict['categ'].split('.', 1)[0] in cern_arxiv_categories) and \
url_params_dict.has_key('id'):
# Old arXiv links, used to be handled by
# setlink. Provide direct links to arXiv
for file_format, label in [('pdf', "PDF")]:#,
#('ps', "PS"),
#('e-print', "Source (generally TeX or LaTeX)"),
#('abs', "Abstract")]:
url = "http://arxiv.org/%(format)s/%(category)s/%(id)s" % \
{'format': file_format,
'category': url_params_dict['categ'],
'id': url_params_dict['id']}
parsed_urls['others_urls'].append((url, "%s/%s %s" % \
(url_params_dict['categ'],
url_params_dict['id'],
label)))
else:
parsed_urls['others_urls'].append((url, descr)) # external url
else: # It's a bibdoc!
assigned = False
for doc in bibarchive.list_bibdocs():
if int(doc.get_latest_version()) > 1:
old_versions = True
if True in [f.get_full_name().startswith(filename) \
for f in doc.list_all_files()]:
assigned = True
if not include_subformat_icons and \
CFG_BIBDOCFILE_ICON_SUBFORMAT_RE.match(subformat):
# This is an icon and we want to skip it
continue
if not doc.get_doctype(bfo.recID) == 'Main' and \
distinct_main_and_additional_files == True:
# In that case we record that there are
# additional files, but don't add them to
# returned structure.
additionals = True
else:
if not descr:
descr = _('Fulltext')
if not parsed_urls['main_urls'].has_key(descr):
parsed_urls['main_urls'][descr] = []
params_dict = parse_qs(params)
if 'subformat' in params_dict:
url_format += ' (%s)' % params_dict['subformat'][0]
parsed_urls['main_urls'][descr].append((url, name, url_format))
if not assigned: # Url is not a bibdoc :-S
if not descr:
descr = filename
parsed_urls['others_urls'].append((url, descr)) # Let's put it in a general other url
return (parsed_urls, old_versions, additionals)
def get_files(bfo,
distinguish_main_and_additional_files=True,
include_subformat_icons=False):
"""
Returns the files available for the given record.
Returned structure is a tuple (parsed_urls, old_versions, additionals):
- parsed_urls: contains categorized URLS (see details below)
- old_versions: set to True if we can have access to old versions
- additionals: set to True if we have other documents than the 'main' document
Parameter 'include_subformat_icons' decides if subformat
considered as icons should be returned
'parsed_urls' is a dictionary in the form::
{'main_urls' : {'Main' : [('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/aFile.pdf', 'aFile', 'PDF'),
('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/aFile.gif', 'aFile', 'GIF')],
'Additional': [('http://CFG_SITE_URL/CFG_SITE_RECORD/1/files/bFile.pdf', 'bFile', 'PDF')]},
'other_urls': [('http://externalurl.com/aFile.pdf', 'Fulltext'), # url(8564_u), description(8564_z/y)
('http://externalurl.com/bFile.pdf', 'Fulltext')],
'cern_urls' : [('http://cern.ch/aFile.pdf', 'Fulltext'), # url(8564_u), description(8564_z/y)
('http://cern.ch/bFile.pdf', 'Fulltext')],
}
Some notes about returned structure:
- key 'cern_urls' is only available on CERN site
- keys in main_url dictionaries are defined by the BibDoc.
- older versions are not part of the parsed urls
- returns only main files when possible, that is when doctypes
make a distinction between 'Main' files and other
files. Otherwise returns all the files as main. This is only
enabled if distinguish_main_and_additional_files is set to True
"""
CFG_SITE_URL = current_app.config['CFG_SITE_URL']
CFG_CERN_SITE = current_app.config['CFG_CERN_SITE']
CFG_BIBFORMAT_HIDDEN_FILE_FORMATS = current_app.config[
'CFG_BIBFORMAT_HIDDEN_FILE_FORMATS']
_CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS = set(
normalize_format(fmt) for fmt in CFG_BIBFORMAT_HIDDEN_FILE_FORMATS)
_ = gettext_set_language(bfo.lang)
urls = bfo.fields("8564_")
bibarchive = BibRecDocs(bfo.recID)
old_versions = False # We can provide link to older files. Will be
# set to True if older files are found.
additionals = False # We have additional files. Will be set to
# True if additional files are found.
# Prepare object to return
parsed_urls = {
'main_urls': {}, # Urls hosted by Invenio (bibdocs)
'others_urls': [] # External urls
}
if CFG_CERN_SITE:
parsed_urls['cern_urls'] = [] # cern.ch urls
# Doctypes can of any type, but when there is one file marked as
# 'Main', we consider that there is a distinction between "main"
# and "additional" files. Otherwise they will all be considered
# equally as main files
distinct_main_and_additional_files = False
if len(bibarchive.list_bibdocs(doctype='Main')) > 0 and \
distinguish_main_and_additional_files:
distinct_main_and_additional_files = True
# Parse URLs
for complete_url in urls:
if complete_url.has_key('u'):
url = complete_url['u']
(dummy, host, path, dummy, params, dummy) = urlparse(url)
subformat = complete_url.get('x', '')
filename = urllib.unquote(basename(path))
name = file_strip_ext(filename)
url_format = filename[len(name):]
if url_format.startswith('.'):
url_format = url_format[1:]
if compose_format(
url_format, subformat
) in _CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS:
## This format should be hidden.
continue
descr = _("Fulltext")
if complete_url.has_key('y'):
descr = complete_url['y']
if descr == 'Fulltext':
descr = _("Fulltext")
if not url.startswith(CFG_SITE_URL): # Not a bibdoc?
if not descr: # For not bibdoc let's have a description
# Display the URL in full:
descr = url
if CFG_CERN_SITE and 'cern.ch' in host and \
('/setlink?' in url or \
'cms' in host or \
'documents.cern.ch' in url or \
'doc.cern.ch' in url or \
'preprints.cern.ch' in url):
url_params_dict = dict([
part.split('=') for part in params.split('&')
if len(part.split('=')) == 2
])
if url_params_dict.has_key('categ') and \
(url_params_dict['categ'].split('.', 1)[0] in cern_arxiv_categories) and \
url_params_dict.has_key('id'):
# Old arXiv links, used to be handled by
# setlink. Provide direct links to arXiv
for file_format, label in [('pdf', "PDF")]: #,
#('ps', "PS"),
#('e-print', "Source (generally TeX or LaTeX)"),
#('abs', "Abstract")]:
url = "http://arxiv.org/%(format)s/%(category)s/%(id)s" % \
{'format': file_format,
'category': url_params_dict['categ'],
'id': url_params_dict['id']}
parsed_urls['others_urls'].append((url, "%s/%s %s" % \
(url_params_dict['categ'],
url_params_dict['id'],
label)))
else:
parsed_urls['others_urls'].append(
(url, descr)) # external url
else: # It's a bibdoc!
assigned = False
for doc in bibarchive.list_bibdocs():
if int(doc.get_latest_version()) > 1:
old_versions = True
if True in [f.get_full_name().startswith(filename) \
for f in doc.list_all_files()]:
assigned = True
if not include_subformat_icons and \
CFG_BIBDOCFILE_ICON_SUBFORMAT_RE.match(subformat):
# This is an icon and we want to skip it
continue
if not doc.get_doctype(bfo.recID) == 'Main' and \
distinct_main_and_additional_files == True:
# In that case we record that there are
# additional files, but don't add them to
# returned structure.
additionals = True
else:
if not descr:
descr = _('Fulltext')
if not parsed_urls['main_urls'].has_key(descr):
parsed_urls['main_urls'][descr] = []
params_dict = parse_qs(params)
if 'subformat' in params_dict:
url_format += ' (%s)' % params_dict[
'subformat'][0]
parsed_urls['main_urls'][descr].append(
(url, name, url_format))
if not assigned: # Url is not a bibdoc :-S
if not descr:
descr = filename
parsed_urls['others_urls'].append(
(url, descr)) # Let's put it in a general other url
return (parsed_urls, old_versions, additionals)
import re
from invenio.legacy.bibdocfile.api import BibRecDocs, file_strip_ext, normalize_format, compose_format
from invenio.base.i18n import gettext_set_language
from invenio.config import CFG_SITE_URL, CFG_BASE_URL, CFG_CERN_SITE, CFG_SITE_RECORD, \
CFG_BIBFORMAT_HIDDEN_FILE_FORMATS
from invenio.legacy.bibdocfile.config import CFG_BIBDOCFILE_ICON_SUBFORMAT_RE
from invenio.utils.url import get_relative_url
from cgi import escape, parse_qs
from six.moves.urllib.parse import urlparse
from os.path import basename
import urllib
_CFG_NORMALIZED_BIBFORMAT_HIDDEN_FILE_FORMATS = set(
normalize_format(fmt) for fmt in CFG_BIBFORMAT_HIDDEN_FILE_FORMATS)
_CFG_BIBFORMAT_HIDDEN_DOCTYPES = ['Plot']
if CFG_CERN_SITE:
_CFG_BIBFORMAT_HIDDEN_DOCTYPES.append('arXiv')
cern_arxiv_categories = [
"astro-ph", "chao-dyn", "cond-mat", "gr-qc", "hep-ex", "hep-lat", "hep-ph",
"hep-th", "math-ph", "math", "nucl-ex", "nucl-th", "out", "physics",
"quant-ph", "q-alg", "cs", "adap-org", "comp-gas", "chem-ph", "cs", "math",
"neuro-sys", "patt-sol", "solv-int", "acc-phys", "alg-geom", "ao-sci",
"atom-ph", "cmp-lg", "dg-ga", "funct-an", "mtrl-th", "plasm-ph", "q-alg",
"supr-con"
]
