def get_record_ids(argstr, date_from, date_until):
"""Returns the local and external records found for a specific query and timeframe."""
argd = wash_urlargd(parse_qs(argstr), websearch_templates.search_results_default_urlargd)
p = argd.get('p', [])
c = argd.get('c', [])
cc = argd.get('cc', [])
aas = argd.get('aas', [])
f = argd.get('f', [])
so = argd.get('so', [])
sp = argd.get('sp', [])
ot = argd.get('ot', [])
p1 = argd.get('p1', [])
f1 = argd.get('f1', [])
m1 = argd.get('m1', [])
op1 = argd.get('op1', [])
p2 = argd.get('p2', [])
f2 = argd.get('f2', [])
m2 = argd.get('m2', [])
op2 = argd.get('op3', [])
p3 = argd.get('p3', [])
f3 = argd.get('f3', [])
m3 = argd.get('m3', [])
sc = argd.get('sc', [])
d1y, d1m, d1d = _date_to_tuple(date_from)
d2y, d2m, d2d = _date_to_tuple(date_until)
#alerts might contain collections that have been deleted
#check if such collections are in the query, and if yes, do not include them in the search
cc = get_coll_normalised_name(cc)
if not cc and not c: #the alarm was for an entire collection that does not exist anymore
return ([], ([], []))
if c: # some collections were defined in the query
c = [c_norm_name for c_norm_name in [get_coll_normalised_name(c_name) for c_name in c] if c_norm_name] #remove unknown collections from c
if not c: #none of the collection selected in the alert still exist
return ([], ([], []))
washed_colls = wash_colls(cc, c, sc, 0)
hosted_colls = washed_colls[3]
if hosted_colls:
req_args = "p=%s&f=%s&d1d=%s&d1m=%s&d1y=%s&d2d=%s&d2m=%s&d2y=%s&ap=%i" % (p, f, d1d, d1m, d1y, d2d, d2m, d2y, 0)
external_records = calculate_external_records(req_args, [p, p1, p2, p3], f, hosted_colls, CFG_EXTERNAL_COLLECTION_TIMEOUT, CFG_EXTERNAL_COLLECTION_MAXRESULTS_ALERTS)
else:
external_records = ([], [])
recids = perform_request_search(of='id', p=p, c=c, cc=cc, f=f, so=so, sp=sp, ot=ot,
aas=aas, p1=p1, f1=f1, m1=m1, op1=op1, p2=p2, f2=f2,
m2=m2, op2=op2, p3=p3, f3=f3, m3=m3, sc=sc, d1y=d1y,
d1m=d1m, d1d=d1d, d2y=d2y, d2m=d2m, d2d=d2d)
return (recids, external_records)
def get_record_ids(argstr, date_from, date_until):
"""Returns the local and external records found for a specific query and timeframe."""
argd = wash_urlargd(parse_qs(argstr), websearch_templates.search_results_default_urlargd)
p = argd.get('p', [])
c = argd.get('c', [])
cc = argd.get('cc', [])
aas = argd.get('aas', [])
f = argd.get('f', [])
so = argd.get('so', [])
sp = argd.get('sp', [])
ot = argd.get('ot', [])
p1 = argd.get('p1', [])
f1 = argd.get('f1', [])
m1 = argd.get('m1', [])
op1 = argd.get('op1', [])
p2 = argd.get('p2', [])
f2 = argd.get('f2', [])
m2 = argd.get('m2', [])
op2 = argd.get('op3', [])
p3 = argd.get('p3', [])
f3 = argd.get('f3', [])
m3 = argd.get('m3', [])
sc = argd.get('sc', [])
d1y, d1m, d1d = _date_to_tuple(date_from)
d2y, d2m, d2d = _date_to_tuple(date_until)
#alerts might contain collections that have been deleted
#check if such collections are in the query, and if yes, do not include them in the search
cc = get_coll_normalised_name(cc)
if not cc and not c: #the alarm was for an entire collection that does not exist anymore
return ([], ([], []))
if c: # some collections were defined in the query
c = [c_norm_name for c_norm_name in [get_coll_normalised_name(c_name) for c_name in c] if c_norm_name] #remove unknown collections from c
if not c: #none of the collection selected in the alert still exist
return ([], ([], []))
washed_colls = wash_colls(cc, c, sc, 0)
hosted_colls = washed_colls[3]
if hosted_colls:
req_args = "p=%s&f=%s&d1d=%s&d1m=%s&d1y=%s&d2d=%s&d2m=%s&d2y=%s&ap=%i" % (p, f, d1d, d1m, d1y, d2d, d2m, d2y, 0)
external_records = calculate_external_records(req_args, [p, p1, p2, p3], f, hosted_colls, CFG_EXTERNAL_COLLECTION_TIMEOUT, CFG_EXTERNAL_COLLECTION_MAXRESULTS_ALERTS)
else:
external_records = ([], [])
recids = perform_request_search(of='id', p=p, c=c, cc=cc, f=f, so=so, sp=sp, ot=ot,
aas=aas, p1=p1, f1=f1, m1=m1, op1=op1, p2=p2, f2=f2,
m2=m2, op2=op2, p3=p3, f3=f3, m3=m3, sc=sc, d1y=d1y,
d1m=d1m, d1d=d1d, d2y=d2y, d2m=d2m, d2d=d2d)
return (recids, external_records)
def display_collection(req, c, aas, verbose, ln, em=""):
"""Display search interface page for collection c by looking
in the collection cache."""
_ = gettext_set_language(ln)
req.argd = drop_default_urlargd({'aas': aas, 'verbose': verbose, 'ln': ln, 'em' : em},
search_interface_default_urlargd)
if em != "":
em = em.split(",")
# get user ID:
try:
uid = getUid(req)
user_preferences = {}
if uid == -1:
return page_not_authorized(req, "../",
text="You are not authorized to view this collection",
navmenuid='search')
elif uid > 0:
user_preferences = get_user_preferences(uid)
except Error:
register_exception(req=req, alert_admin=True)
return page(title=_("Internal Error"),
body=create_error_box(req, verbose=verbose, ln=ln),
description="%s - Internal Error" % CFG_SITE_NAME,
keywords="%s, Internal Error" % CFG_SITE_NAME,
language=ln,
req=req,
navmenuid='search')
# deduce collection id:
normalised_name = get_coll_normalised_name(c)
colID = get_colID(normalised_name)
if type(colID) is not int:
page_body = '<p>' + (_("Sorry, collection %s does not seem to exist.") % ('<strong>' + str(c) + '</strong>')) + '</p>'
page_body = '<p>' + (_("You may want to start browsing from %s.") % ('<a href="' + CFG_SITE_URL + '?ln=' + ln + '">' + get_coll_i18nname(CFG_SITE_NAME, ln) + '</a>')) + '</p>'
if req.header_only:
raise apache.SERVER_RETURN, apache.HTTP_NOT_FOUND
return page(title=_("Collection %s Not Found") % cgi.escape(c),
body=page_body,
description=(CFG_SITE_NAME + ' - ' + _("Not found") + ': ' + cgi.escape(str(c))),
keywords="%s" % CFG_SITE_NAME,
uid=uid,
language=ln,
req=req,
navmenuid='search')
if normalised_name != c:
redirect_to_url(req, normalised_name, apache.HTTP_MOVED_PERMANENTLY)
# start display:
req.content_type = "text/html"
req.send_http_header()
c_body, c_navtrail, c_portalbox_lt, c_portalbox_rt, c_portalbox_tp, c_portalbox_te, \
c_last_updated = perform_display_collection(colID, c, aas, ln, em,
user_preferences.get('websearch_helpbox', 1))
if em == "" or EM_REPOSITORY["body"] in em:
try:
title = get_coll_i18nname(c, ln)
except:
title = ""
else:
title = ""
show_title_p = True
body_css_classes = []
if c == CFG_SITE_NAME:
# Do not display title on home collection
show_title_p = False
body_css_classes.append('home')
if len(collection_reclist_cache.cache.keys()) == 1:
# if there is only one collection defined, do not print its
# title on the page as it would be displayed repetitively.
show_title_p = False
if aas == -1:
show_title_p = False
if CFG_INSPIRE_SITE == 1:
# INSPIRE should never show title, but instead use css to
# style collections
show_title_p = False
body_css_classes.append(nmtoken_from_string(c))
# RSS:
rssurl = CFG_SITE_URL + '/rss'
rssurl_params = []
if c != CFG_SITE_NAME:
rssurl_params.append('cc=' + quote(c))
if ln != CFG_SITE_LANG and \
c in CFG_WEBSEARCH_RSS_I18N_COLLECTIONS:
rssurl_params.append('ln=' + ln)
if rssurl_params:
rssurl += '?' + '&'.join(rssurl_params)
if 'hb' in CFG_WEBSEARCH_USE_MATHJAX_FOR_FORMATS:
metaheaderadd = get_mathjax_header(req.is_https())
else:
metaheaderadd = ''
return page(title=title,
body=c_body,
navtrail=c_navtrail,
description="%s - %s" % (CFG_SITE_NAME, c),
keywords="%s, %s" % (CFG_SITE_NAME, c),
metaheaderadd=metaheaderadd,
uid=uid,
language=ln,
req=req,
cdspageboxlefttopadd=c_portalbox_lt,
cdspageboxrighttopadd=c_portalbox_rt,
titleprologue=c_portalbox_tp,
titleepilogue=c_portalbox_te,
lastupdated=c_last_updated,
navmenuid='search',
rssurl=rssurl,
body_css_classes=body_css_classes,
show_title_p=show_title_p,
show_header=em == "" or EM_REPOSITORY["header"] in em,
show_footer=em == "" or EM_REPOSITORY["footer"] in em)
def display_collection(req, c, aas, verbose, ln, em=""):
"""Display search interface page for collection c by looking
in the collection cache."""
_ = gettext_set_language(ln)
req.argd = drop_default_urlargd({'aas': aas, 'verbose': verbose, 'ln': ln, 'em' : em},
search_interface_default_urlargd)
if em != "":
em = em.split(",")
# get user ID:
try:
uid = getUid(req)
user_preferences = {}
if uid == -1:
return page_not_authorized(req, "../",
text="You are not authorized to view this collection",
navmenuid='search')
elif uid > 0:
user_preferences = get_user_preferences(uid)
except Error:
register_exception(req=req, alert_admin=True)
return page(title=_("Internal Error"),
body=create_error_box(req, verbose=verbose, ln=ln),
description="%s - Internal Error" % CFG_SITE_NAME,
keywords="%s, Internal Error" % CFG_SITE_NAME,
language=ln,
req=req,
navmenuid='search')
# start display:
req.content_type = "text/html"
req.send_http_header()
# deduce collection id:
colID = get_colID(get_coll_normalised_name(c))
if type(colID) is not int:
page_body = '<p>' + (_("Sorry, collection %s does not seem to exist.") % ('<strong>' + str(c) + '</strong>')) + '</p>'
page_body = '<p>' + (_("You may want to start browsing from %s.") % ('<a href="' + CFG_SITE_URL + '?ln=' + ln + '">' + get_coll_i18nname(CFG_SITE_NAME, ln) + '</a>')) + '</p>'
if req.header_only:
raise apache.SERVER_RETURN, apache.HTTP_NOT_FOUND
return page(title=_("Collection %s Not Found") % cgi.escape(c),
body=page_body,
description=(CFG_SITE_NAME + ' - ' + _("Not found") + ': ' + cgi.escape(str(c))),
keywords="%s" % CFG_SITE_NAME,
uid=uid,
language=ln,
req=req,
navmenuid='search')
c_body, c_navtrail, c_portalbox_lt, c_portalbox_rt, c_portalbox_tp, c_portalbox_te, \
c_last_updated = perform_display_collection(colID, c, aas, ln, em,
user_preferences.get('websearch_helpbox', 1))
if em == "" or EM_REPOSITORY["body"] in em:
try:
title = get_coll_i18nname(c, ln)
except:
title = ""
else:
title = ""
show_title_p = True
body_css_classes = []
if c == CFG_SITE_NAME:
# Do not display title on home collection
show_title_p = False
body_css_classes.append('home')
if len(collection_reclist_cache.cache.keys()) == 1:
# if there is only one collection defined, do not print its
# title on the page as it would be displayed repetitively.
show_title_p = False
if aas == -1:
show_title_p = False
if CFG_INSPIRE_SITE == 1:
# INSPIRE should never show title, but instead use css to
# style collections
show_title_p = False
body_css_classes.append(nmtoken_from_string(c))
# RSS:
rssurl = CFG_SITE_URL + '/rss'
rssurl_params = []
if c != CFG_SITE_NAME:
rssurl_params.append('cc=' + quote(c))
if ln != CFG_SITE_LANG and \
c in CFG_WEBSEARCH_RSS_I18N_COLLECTIONS:
rssurl_params.append('ln=' + ln)
if rssurl_params:
rssurl += '?' + '&'.join(rssurl_params)
if 'hb' in CFG_WEBSEARCH_USE_MATHJAX_FOR_FORMATS:
metaheaderadd = get_mathjax_header(req.is_https())
else:
metaheaderadd = ''
return page(title=title,
body=c_body,
navtrail=c_navtrail,
description="%s - %s" % (CFG_SITE_NAME, c),
keywords="%s, %s" % (CFG_SITE_NAME, c),
metaheaderadd=metaheaderadd,
uid=uid,
language=ln,
req=req,
cdspageboxlefttopadd=c_portalbox_lt,
cdspageboxrighttopadd=c_portalbox_rt,
titleprologue=c_portalbox_tp,
titleepilogue=c_portalbox_te,
lastupdated=c_last_updated,
navmenuid='search',
rssurl=rssurl,
body_css_classes=body_css_classes,
show_title_p=show_title_p,
show_header=em == "" or EM_REPOSITORY["header"] in em,
show_footer=em == "" or EM_REPOSITORY["footer"] in em)
def display_collection(req, c, aas, verbose, ln):
"""Display search interface page for collection c by looking
in the collection cache."""
_ = gettext_set_language(ln)
req.argd = drop_default_urlargd({
'aas': aas,
'verbose': verbose,
'ln': ln
}, search_interface_default_urlargd)
# get user ID:
try:
uid = getUid(req)
user_preferences = {}
if uid == -1:
return page_not_authorized(
req,
"../",
text="You are not authorized to view this collection",
navmenuid='search')
elif uid > 0:
user_preferences = get_user_preferences(uid)
except Error:
register_exception(req=req, alert_admin=True)
return page(title=_("Internal Error"),
body=create_error_box(req, verbose=verbose, ln=ln),
description="%s - Internal Error" % CFG_SITE_NAME,
keywords="%s, Internal Error" % CFG_SITE_NAME,
language=ln,
req=req,
navmenuid='search')
# start display:
req.content_type = "text/html"
req.send_http_header()
# deduce collection id:
colID = get_colID(get_coll_normalised_name(c))
if type(colID) is not int:
page_body = '<p>' + (
_("Sorry, collection %s does not seem to exist.") %
('<strong>' + str(c) + '</strong>')) + '</p>'
page_body = '<p>' + (
_("You may want to start browsing from %s.") %
('<a href="' + CFG_SITE_URL + '?ln=' + ln + '">' +
get_coll_i18nname(CFG_SITE_NAME, ln) + '</a>')) + '</p>'
if req.header_only:
raise apache.SERVER_RETURN, apache.HTTP_NOT_FOUND
return page(title=_("Collection %s Not Found") % cgi.escape(c),
body=page_body,
description=(CFG_SITE_NAME + ' - ' + _("Not found") +
': ' + cgi.escape(str(c))),
keywords="%s" % CFG_SITE_NAME,
uid=uid,
language=ln,
req=req,
navmenuid='search')
# wash `aas' argument:
if not os.path.exists("%s/collections/%d/body-as=%d-ln=%s.html" % \
(CFG_CACHEDIR, colID, aas, ln)):
# nonexistent `aas' asked for, fall back to Simple Search:
aas = 0
# display collection interface page:
try:
filedesc = open("%s/collections/%d/navtrail-as=%d-ln=%s.html" % \
(CFG_CACHEDIR, colID, aas, ln), "r")
c_navtrail = filedesc.read()
filedesc.close()
except:
c_navtrail = ""
try:
filedesc = open("%s/collections/%d/body-as=%d-ln=%s.html" % \
(CFG_CACHEDIR, colID, aas, ln), "r")
c_body = filedesc.read()
filedesc.close()
except:
c_body = ""
try:
filedesc = open("%s/collections/%d/portalbox-tp-ln=%s.html" % \
(CFG_CACHEDIR, colID, ln), "r")
c_portalbox_tp = filedesc.read()
filedesc.close()
except:
c_portalbox_tp = ""
try:
filedesc = open("%s/collections/%d/portalbox-te-ln=%s.html" % \
(CFG_CACHEDIR, colID, ln), "r")
c_portalbox_te = filedesc.read()
filedesc.close()
except:
c_portalbox_te = ""
try:
filedesc = open("%s/collections/%d/portalbox-lt-ln=%s.html" % \
(CFG_CACHEDIR, colID, ln), "r")
c_portalbox_lt = filedesc.read()
filedesc.close()
except:
c_portalbox_lt = ""
try:
# show help boxes (usually located in "tr", "top right")
# if users have not banned them in their preferences:
c_portalbox_rt = ""
if user_preferences.get('websearch_helpbox', 1) > 0:
filedesc = open("%s/collections/%d/portalbox-rt-ln=%s.html" % \
(CFG_CACHEDIR, colID, ln), "r")
c_portalbox_rt = filedesc.read()
filedesc.close()
except:
c_portalbox_rt = ""
try:
filedesc = open("%s/collections/%d/last-updated-ln=%s.html" % \
(CFG_CACHEDIR, colID, ln), "r")
c_last_updated = filedesc.read()
filedesc.close()
except:
c_last_updated = ""
try:
title = get_coll_i18nname(c, ln)
except:
title = ""
show_title_p = True
body_css_classes = []
if c == CFG_SITE_NAME:
# Do not display title on home collection
show_title_p = False
body_css_classes.append('home')
if len(collection_reclist_cache.cache.keys()) == 1:
# if there is only one collection defined, do not print its
# title on the page as it would be displayed repetitively.
show_title_p = False
if aas == -1:
show_title_p = False
if CFG_INSPIRE_SITE == 1:
# INSPIRE should never show title, but instead use css to
# style collections
show_title_p = False
body_css_classes.append(nmtoken_from_string(c))
# RSS:
rssurl = CFG_SITE_URL + '/rss'
rssurl_params = []
if c != CFG_SITE_NAME:
rssurl_params.append('cc=' + quote(c))
if ln != CFG_SITE_LANG and \
c in CFG_WEBSEARCH_RSS_I18N_COLLECTIONS:
rssurl_params.append('ln=' + ln)
if rssurl_params:
rssurl += '?' + '&'.join(rssurl_params)
if 'hb' in CFG_WEBSEARCH_USE_MATHJAX_FOR_FORMATS:
metaheaderadd = get_mathjax_header(req.is_https())
else:
metaheaderadd = ''
return page(title=title,
body=c_body,
navtrail=c_navtrail,
description="%s - %s" % (CFG_SITE_NAME, c),
keywords="%s, %s" % (CFG_SITE_NAME, c),
metaheaderadd=metaheaderadd,
uid=uid,
language=ln,
req=req,
cdspageboxlefttopadd=c_portalbox_lt,
cdspageboxrighttopadd=c_portalbox_rt,
titleprologue=c_portalbox_tp,
titleepilogue=c_portalbox_te,
lastupdated=c_last_updated,
navmenuid='search',
rssurl=rssurl,
body_css_classes=body_css_classes,
show_title_p=show_title_p)
