def test_urlsafe():
assert h.urlsafe("a b") == "a_b"
assert h.urlsafe("a?b") == "a_b"
assert h.urlsafe("a?&b") == "a_b"
assert h.urlsafe("?a") == "a"
assert h.urlsafe("a?") == "a"
def test_urlsafe():
assert h.urlsafe("a b") == "a_b"
assert h.urlsafe("a?b") == "a_b"
assert h.urlsafe("a?&b") == "a_b"
assert h.urlsafe("?a") == "a"
assert h.urlsafe("a?") == "a"
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "https://archive.org/details/" + itemid,
"availability": availability,
"formats": {}
}
prefix = "https://archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "https://archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
}
}
elif availability == "borrow":
d['borrow_url'] = u"https://openlibrary.org%s/%s/borrow" % (
doc['key'], h.urlsafe(doc.get("title", "untitled")))
loanstatus = web.ctx.site.store.get('ebooks/' + doc['ocaid'],
{'borrowed': 'false'})
d['checkedout'] = (loanstatus['borrowed'] == 'true')
return d
def get_readable_path(site, path, patterns, encoding=None):
"""Returns real_path and readable_path from the given path.
The patterns is a list of (path_regex, type, property_name, default_value)
tuples.
"""
def match(path):
for pat, type, property, default_title in patterns:
m = web.re_compile('^' + pat).match(path)
if m:
prefix = m.group()
extra = web.lstrips(path, prefix)
tokens = extra.split("/", 2)
# `extra` starts with "/". So first token is always empty.
middle = web.listget(tokens, 1, "")
suffix = web.listget(tokens, 2, "")
if suffix:
suffix = "/" + suffix
return type, property, default_title, prefix, middle, suffix
return None, None, None, None, None, None
type, property, default_title, prefix, middle, suffix = match(path)
if type is None:
path = web.safeunicode(path)
return (path, path)
if encoding is not None \
or path.endswith(".json") or path.endswith(".yml") or path.endswith(".rdf"):
key, ext = os.path.splitext(path)
thing = _get_object(site, key)
if thing:
path = thing.key + ext
path = web.safeunicode(path)
return (path, path)
thing = _get_object(site, prefix)
# get_object may handle redirections.
if thing:
prefix = thing.key
if thing and thing.type.key == type:
title = thing.get(property) or default_title
middle = '/' + h.urlsafe(title.strip())
else:
middle = ""
if is_exclusion(thing):
web.ctx.exclude = True
prefix = web.safeunicode(prefix)
middle = web.safeunicode(middle)
suffix = web.safeunicode(suffix)
return (prefix + suffix, prefix + middle + suffix)
def get_readable_path(site, path, patterns, encoding=None):
"""Returns real_path and readable_path from the given path.
The patterns is a list of (path_regex, type, property_name, default_value)
tuples.
"""
def match(path):
for pat, type, property, default_title in patterns:
m = web.re_compile('^' + pat).match(path)
if m:
prefix = m.group()
extra = web.lstrips(path, prefix)
tokens = extra.split("/", 2)
# `extra` starts with "/". So first token is always empty.
middle = web.listget(tokens, 1, "")
suffix = web.listget(tokens, 2, "")
if suffix:
suffix = "/" + suffix
return type, property, default_title, prefix, middle, suffix
return None, None, None, None, None, None
type, property, default_title, prefix, middle, suffix = match(path)
if type is None:
path = web.safeunicode(path)
return (path, path)
if encoding is not None \
or path.endswith(".json") or path.endswith(".yml") or path.endswith(".rdf"):
key, ext = os.path.splitext(path)
thing = _get_object(site, key)
if thing:
path = thing.key + ext
path = web.safeunicode(path)
return (path, path)
thing = _get_object(site, prefix)
# get_object may handle redirections.
if thing:
prefix = thing.key
if thing and thing.type.key == type:
title = thing.get(property) or default_title
middle = '/' + h.urlsafe(title.strip())
else:
middle = ""
prefix = web.safeunicode(prefix)
middle = web.safeunicode(middle)
suffix = web.safeunicode(suffix)
return (prefix + suffix, prefix + middle + suffix)
def _make_url(self, label, suffix, relative=True, **params):
"""Make url of the form $key/$label$suffix?$params."""
if label is not None:
u = self.key + "/" + h.urlsafe(label) + suffix
else:
u = self.key + suffix
if params:
u += '?' + urllib.parse.urlencode(params)
if not relative:
u = _get_ol_base_url() + u
return u
def get_readitem(self, iaid, orig_iaid, orig_ekey, wkey, status,
publish_date):
meta = self.iaid_to_meta.get(iaid)
if meta is None:
return None
collections = meta.get("collection", [])
if status == 'missing':
return None
if (status.startswith('restricted') or status
== 'checked out') and not self.options.get('show_all_items'):
return None
edition = self.iaid_to_ed.get(iaid)
ekey = edition.get('key', '')
if status == 'full access':
itemURL = 'http://www.archive.org/stream/%s' % (iaid)
else:
# this could be rewrit in terms of iaid...
itemURL = u'http://openlibrary.org%s/%s/borrow' % (
ekey, helpers.urlsafe(edition.get('title', 'untitled')))
result = {
# XXX add lastUpdate
'enumcron': False,
'match': 'exact' if iaid == orig_iaid else 'similar',
'status': status,
'fromRecord': orig_ekey,
'ol-edition-id': key_to_olid(ekey),
'ol-work-id': key_to_olid(wkey),
'publishDate': publish_date,
'contributor': '',
'itemURL': itemURL,
}
if edition.get('covers'):
cover_id = edition['covers'][0]
# can be rewrit in terms of iaid
# XXX covers url from yaml?
result['cover'] = {
"small":
"http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium":
"http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large":
"http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
return result
def get_readitem(self, iaid, orig_iaid, orig_ekey, wkey, status, publish_date):
meta = self.iaid_to_meta.get(iaid)
if meta is None:
return None
collections = meta.get("collection", [])
if status == 'missing':
return None
if (status.startswith('restricted') or status == 'checked out') and not self.options.get('show_all_items'):
return None
edition = self.iaid_to_ed.get(iaid)
ekey = edition.get('key', '')
if status == 'full access':
itemURL = 'http://www.archive.org/stream/%s' % (iaid)
else:
# this could be rewrit in terms of iaid...
itemURL = u'http://openlibrary.org%s/%s/borrow' % (ekey,
helpers.urlsafe(edition.get('title',
'untitled')))
result = {
# XXX add lastUpdate
'enumcron': False,
'match': 'exact' if iaid == orig_iaid else 'similar',
'status': status,
'fromRecord': orig_ekey,
'ol-edition-id': key_to_olid(ekey),
'ol-work-id': key_to_olid(wkey),
'publishDate': publish_date,
'contributor': '',
'itemURL': itemURL,
}
if edition.get('covers'):
cover_id = edition['covers'][0]
# can be rewrit in terms of iaid
# XXX covers url from yaml?
result['cover'] = {
"small": "http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
return result
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "http://www.archive.org/details/" + itemid,
"availability": availability
}
prefix = "http://www.archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "http://www.archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
},
"djvu": {
"url": prefix + ".djvu",
"permission": "open"
}
}
elif availability == "borrow":
d['borrow_url'] = u"http://openlibrary.org%s/%s/borrow" % (
doc['key'], h.urlsafe(doc.get("title", "untitled")))
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
else:
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
return d
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "http://www.archive.org/details/" + itemid,
"availability": availability
}
prefix = "http://www.archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "http://www.archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
},
"djvu": {
"url": prefix + ".djvu",
"permission": "open"
}
}
elif availability == "borrow":
d['borrow_url'] = u"http://openlibrary.org%s/%s/borrow" % (doc['key'], h.urlsafe(doc.get("title", "untitled")))
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
else:
d['formats'] = {
"djvu": {
"url": prefix + ".djvu",
"permission": "restricted"
}
}
return d
def ebook(doc):
itemid = doc['ocaid']
availability = get_ia_availability(itemid)
d = {
"preview_url": "https://archive.org/details/" + itemid,
"availability": availability,
"formats": {}
}
prefix = "https://archive.org/download/%s/%s" % (itemid, itemid)
if availability == 'full':
d["read_url"] = "https://archive.org/stream/%s" % (itemid)
d['formats'] = {
"pdf": {
"url": prefix + ".pdf"
},
"epub": {
"url": prefix + ".epub"
},
"text": {
"url": prefix + "_djvu.txt"
}
}
elif availability == "borrow":
d['borrow_url'] = u"https://openlibrary.org%s/%s/borrow" % (doc['key'], h.urlsafe(doc.get("title", "untitled")))
loanstatus = web.ctx.site.store.get('ebooks/' + doc['ocaid'], {'borrowed': 'false'})
d['checkedout'] = (loanstatus['borrowed'] == 'true')
return d
def get_readable_edition_item(edition, work, user_inlibrary, initial_edition):
ocaid = edition.get('ocaid', False)
if not ocaid:
return None
subjects = work.get_subjects()
if not subjects:
return None
metaxml = ia.get_meta_xml(ocaid)
collections = metaxml.get("collection", [])
status = ''
if 'lendinglibrary' in collections:
if not 'Lending library' in subjects:
return None
status = 'lendable'
elif 'inlibrary' in collections:
if not 'In library' in subjects:
return None
if not user_inlibrary:
return None
status = 'lendable'
elif 'printdisabled' in collections:
status = 'restricted'
return None
else:
status = 'full access'
if status == 'full access':
itemURL = "http://www.archive.org/stream/%s" % (ocaid)
else:
itemURL = u"http://openlibrary.org%s/%s/borrow" % (
edition['key'], helpers.urlsafe(edition.get("title", "untitled")))
if status == 'lendable':
loanstatus = web.ctx.site.store.get('ebooks' + edition['key'],
{'borrowed': 'false'})
if loanstatus['borrowed'] == 'true':
status = 'checked out'
if edition['key'] == initial_edition['key']:
match = 'exact'
else:
match = 'similar'
result = {
'enumcron': False,
# 'orig': 'University of California'
# 'htid': ''
# 'lastUpdate: "" # XXX from edition.last_modified (datetime)
'match': match,
'status': status,
'fromRecord': initial_edition['key'],
'ol-edition-id': key_to_olid(edition['key']),
'ol-work-id': key_to_olid(work['key']),
'contributor': 'contributor',
'itemURL': itemURL,
}
if edition.get('covers'):
cover_id = edition['covers'][0]
# XXX covers url from yaml?
result['cover'] = {
"small": "http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
return result
def get_readable_edition_item(edition, work, user_inlibrary, initial_edition):
ocaid = edition.get('ocaid', False)
if not ocaid:
return None
subjects = work.get_subjects()
if not subjects:
return None
metaxml = ia.get_meta_xml(ocaid)
collections = metaxml.get("collection", [])
status = ''
if 'lendinglibrary' in collections:
if not 'Lending library' in subjects:
return None
status = 'lendable'
elif 'inlibrary' in collections:
if not 'In library' in subjects:
return None
if not user_inlibrary:
return None
status = 'lendable'
elif 'printdisabled' in collections:
status = 'restricted'
return None
else:
status = 'full access'
if status == 'full access':
itemURL = "http://www.archive.org/stream/%s" % (ocaid)
else:
itemURL = u"http://openlibrary.org%s/%s/borrow" % (edition['key'],
helpers.urlsafe(edition.get("title",
"untitled")))
if status == 'lendable':
loanstatus = web.ctx.site.store.get('ebooks' + edition['key'], {'borrowed': 'false'})
if loanstatus['borrowed'] == 'true':
status = 'checked out'
if edition['key'] == initial_edition['key']:
match = 'exact'
else:
match = 'similar'
result = {
'enumcron': False,
# 'orig': 'University of California'
# 'htid': ''
# 'lastUpdate: "" # XXX from edition.last_modified (datetime)
'match': match,
'status': status,
'fromRecord': initial_edition['key'],
'ol-edition-id': key_to_olid(edition['key']),
'ol-work-id': key_to_olid(work['key']),
'contributor': 'contributor',
'itemURL': itemURL,
}
if edition.get('covers'):
cover_id = edition['covers'][0]
# XXX covers url from yaml?
result['cover'] = {
"small": "http://covers.openlibrary.org/b/id/%s-S.jpg" % cover_id,
"medium": "http://covers.openlibrary.org/b/id/%s-M.jpg" % cover_id,
"large": "http://covers.openlibrary.org/b/id/%s-L.jpg" % cover_id,
}
return result
def get_readable_path(site, path, patterns, encoding=None):
"""Returns real_path and readable_path from the given path.
The patterns is a list of (path_regex, type, property_name, default_value)
tuples.
"""
def match(path):
for pat, type, property, default_title in patterns:
m = web.re_compile('^' + pat).match(path)
if m:
prefix = m.group()
extra = web.lstrips(path, prefix)
tokens = extra.split("/", 2)
# `extra` starts with "/". So first token is always empty.
middle = web.listget(tokens, 1, "")
suffix = web.listget(tokens, 2, "")
if suffix:
suffix = "/" + suffix
return type, property, default_title, prefix, middle, suffix
return None, None, None, None, None, None
type, property, default_title, prefix, middle, suffix = match(path)
if type is None:
path = web.safeunicode(path)
return (path, path)
if encoding is not None \
or path.endswith(".json") or path.endswith(".yml") or path.endswith(".rdf"):
key, ext = os.path.splitext(path)
thing = _get_object(site, key)
if thing:
path = thing.key + ext
path = web.safeunicode(path)
return (path, path)
thing = _get_object(site, prefix)
# XXX For a 1-week trial ~Oct 23 2019
# if ?edition qualifier present on work url, redirect patron to
# "best" representative edition
if thing.key.startswith('/works/'):
i = web.input(edition="")
if i.edition:
ed = thing.get_representative_edition()
if ed:
raise web.seeother(ed)
# get_object may handle redirections.
if thing:
prefix = thing.key
if thing and thing.type.key == type:
title = thing.get(property) or default_title
middle = '/' + h.urlsafe(title.strip())
else:
middle = ""
prefix = web.safeunicode(prefix)
middle = web.safeunicode(middle)
suffix = web.safeunicode(suffix)
return (prefix + suffix, prefix + middle + suffix)