def _add_id(self, new_id):
if not os.path.exists(self._dirpath):
os.makedirs(self._dirpath)
enc_id = id_encode(new_id)
if not os.path.isfile(enc_id):
with open(os.path.join(self._dirpath, enc_id), "w") as f:
f.write(new_id)
def _add_id(self, new_id):
if not os.path.exists(self._dirpath):
os.makedirs(self._dirpath)
enc_id = id_encode(new_id)
if not os.path.isfile(enc_id):
with open(os.path.join(self._dirpath, enc_id), "w") as f:
f.write(new_id)
def id_encode(self, id):
"""
The identifier string is cleaned of characters that are expected to occur rarely
in object identifiers but that would cause certain known problems for file systems.
In this step, every UTF-8 octet outside the range of visible ASCII (94 characters
with hexadecimal codes 21-7e) [ASCII] (Cerf, “ASCII format for network interchange,”
October 1969.), as well as the following visible ASCII characters::
" hex 22 < hex 3c ? hex 3f
* hex 2a = hex 3d ^ hex 5e
+ hex 2b > hex 3e | hex 7c
, hex 2c
must be converted to their corresponding 3-character hexadecimal encoding, ^hh,
where ^ is a circumflex and hh is two hex digits. For example, ' ' (space) is
converted to ^20 and '*' to ^2a.
In the second step, the following single-character to single-character conversions
must be done::
/ -> =
: -> +
. -> ,
These are characters that occur quite commonly in opaque identifiers but present
special problems for filesystems. This step avoids requiring them to be hex encoded
(hence expanded to three characters), which keeps the typical ppath reasonably
short. Here are examples of identifier strings after cleaning and after
ppath mapping::
id: ark:/13030/xt12t3
-> ark+=13030=xt12t3
-> ar/k+/=1/30/30/=x/t1/2t/3/
id: http://n2t.info/urn:nbn:se:kb:repos-1
-> http+==n2t,info=urn+nbn+se+kb+repos-1
-> ht/tp/+=/=n/2t/,i/nf/o=/ur/n+/n/bn/+s/e+/kb/+/re/p/os/-1/
id: what-the-*@?#!^!?
-> what-the-^2a@^3f#!^5e!^3f
-> wh/at/-t/he/-^/2a/@^/3f/#!/^5/e!/^3/f/
(From section 3 of the Pairtree specification)
@param id: Encode the given identifier according to the pairtree 0.1 specification
@type id: identifier
@returns: A string of the encoded identifier
"""
return ppath.id_encode(id)
def id_encode(self, id):
"""
The identifier string is cleaned of characters that are expected to occur rarely
in object identifiers but that would cause certain known problems for file systems.
In this step, every UTF-8 octet outside the range of visible ASCII (94 characters
with hexadecimal codes 21-7e) [ASCII] (Cerf, “ASCII format for network interchange,”
October 1969.), as well as the following visible ASCII characters::
" hex 22 < hex 3c ? hex 3f
* hex 2a = hex 3d ^ hex 5e
+ hex 2b > hex 3e | hex 7c
, hex 2c
must be converted to their corresponding 3-character hexadecimal encoding, ^hh,
where ^ is a circumflex and hh is two hex digits. For example, ' ' (space) is
converted to ^20 and '*' to ^2a.
In the second step, the following single-character to single-character conversions
must be done::
/ -> =
: -> +
. -> ,
These are characters that occur quite commonly in opaque identifiers but present
special problems for filesystems. This step avoids requiring them to be hex encoded
(hence expanded to three characters), which keeps the typical ppath reasonably
short. Here are examples of identifier strings after cleaning and after
ppath mapping::
id: ark:/13030/xt12t3
-> ark+=13030=xt12t3
-> ar/k+/=1/30/30/=x/t1/2t/3/
id: http://n2t.info/urn:nbn:se:kb:repos-1
-> http+==n2t,info=urn+nbn+se+kb+repos-1
-> ht/tp/+=/=n/2t/,i/nf/o=/ur/n+/n/bn/+s/e+/kb/+/re/p/os/-1/
id: what-the-*@?#!^!?
-> what-the-^2a@^3f#!^5e!^3f
-> wh/at/-t/he/-^/2a/@^/3f/#!/^5/e!/^3/f/
(From section 3 of the Pairtree specification)
@param id: Encode the given identifier according to the pairtree 0.1 specification
@type id: identifier
@returns: A string of the encoded identifier
"""
return ppath.id_encode(id)
def _exists(self, id):
if os.path.exists(self._dirpath):
return id_encode(id) in os.listdir(self._dirpath)
else:
return False
def _exists(self, id):
if os.path.exists(self._dirpath):
return id_encode(id) in os.listdir(self._dirpath)
else:
return False
