obitools/obitools3
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 66 Wiki Activity

Cython API: URI decoding now returns the character string with the

Browse Source 
object path if it could not be opened
This commit is contained in:
Celine Mercier
2018-07-28 17:00:42 +02:00
parent 3e8c187f0b
commit c02c15b93f
1 changed files with 38 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
python/obitools3/uri/decode.pyx
View File

@ -9,6 +9,7 @@ from obitools3.parsers.fasta import fastaNucIterator
from obitools3.parsers.fastq import fastqIterator from obitools3.parsers.fastq import fastqIterator
from obitools3.parsers.tab import tabIterator from obitools3.parsers.tab import tabIterator
from obitools3.parsers.ngsfilter import ngsfilterIterator from obitools3.parsers.ngsfilter import ngsfilterIterator
from obitools3.parsers.embl import emblIterator
from obitools3.parsers.universal import entryIteratorFactory from obitools3.parsers.universal import entryIteratorFactory
from obitools3.dms.obiseq import Nuc_Seq from obitools3.dms.obiseq import Nuc_Seq
@ -66,18 +67,20 @@ def open_dms_element(DMS dms, bytes path,
if not path: if not path:
return (dms,dms) return (dms,dms)
# TODO SHOULD READ AND RETURN PREFIX TO NEW TAXO WITHOUT CREATING ANYTHING
# The URI targets a taxonomy # The URI targets a taxonomy
# dms:dmspath/taxonomy/taxoname[/taxid] # dms:dmspath/taxonomy/taxoname[/taxid]
if path_parts[0]==b"taxonomy": if path_parts[0]==b"taxonomy":
if len(path_parts) > 1: if len(path_parts) > 1:
taxo = Taxonomy.open(dms,path_parts[1]) if Taxonomy.exists(dms, path_parts[1]):
if len(path_parts) == 3: taxo = Taxonomy.open(dms, path_parts[1])
taxon=taxo[int(path_parts[2])] if len(path_parts) == 3:
return (dms,taxon) taxon=taxo[int(path_parts[2])]
elif len(path_parts) > 3: return (dms, taxon)
raise MalformedURIException('Malformed Taxonomy URI') elif len(path_parts) > 3:
return (dms,taxo) raise MalformedURIException('Malformed Taxonomy URI')
else:
return (dms, path_parts[1]) # return prefix for creation eventually
return (dms, taxo)
# The URI targets a view # The URI targets a view
# dms:dmspath/viewname[/columnname|#line|*[/#line|columnname|*[/subcolumn]]] # dms:dmspath/viewname[/columnname|#line|*[/#line|columnname|*[/subcolumn]]]
@ -165,7 +168,7 @@ def open_uri(uri,
create=not input create=not input
scheme = urip.scheme scheme = urip.scheme
error = None error = None
if scheme==b"" or scheme==b"dms" : if scheme==b"" or scheme==b"dms" :
@ -199,18 +202,19 @@ def open_uri(uri,
error=e error=e
if scheme==b"dms" : if scheme==b"dms" :
logger('error','cannot open DMS: %s', uri) logger('Error','cannot open DMS: %s', uri)
raise FileNotFoundError('uri') raise FileNotFoundError('uri')
if not urip.scheme: #if not urip.scheme: # TODO not sure what it was supposed to do but not working as intended
urib=b"file:"+urib # urib=b"file:"+urib
try: try:
file = uopen(tostr(urib)) file = uopen(urib)
logger('info','Opened file : %s', tostr(urib)) logger('info','Opened file: %s', tostr(urib))
except Exception as e: except Exception as e: # TODO discuss: if can't open file, return the character string itself
file = None file = urib
error=e iseq = urib
objclass = bytes
if file is not None: if file is not None:
qualifiers=parse_qs(urip.query) qualifiers=parse_qs(urip.query)
@ -384,6 +388,10 @@ def open_uri(uri,
only=only, only=only,
offset=offset, offset=offset,
noquality=noquality) noquality=noquality)
elif format==b"embl":
iseq = emblIterator(file,
skip=skip,
only=only)
else: else:
raise NotImplementedError('Sequence file format not implemented') raise NotImplementedError('Sequence file format not implemented')
elif seqtype==b"prot": elif seqtype==b"prot":
@ -410,25 +418,22 @@ def open_uri(uri,
skip = skip, skip = skip,
only = only) only = only)
else: else:
iseq,objclass = entryIteratorFactory(file, iseq, objclass = entryIteratorFactory(file,
skip, only, skip, only,
seqtype, seqtype,
offset, offset,
noquality, noquality,
skiperror, skiperror,
header, header,
sep, sep,
dec, dec,
nastring, nastring,
stripwhite, stripwhite,
blanklineskip, blanklineskip,
commentchar) commentchar)
#tmpdms = get_temp_dms() #tmpdms = get_temp_dms()
return (file, iseq, objclass, urib) return (file, iseq, objclass, urib)