Skip to content

GitLab

O
OBITools3
Commit 3b59043e authored by Celine Mercier's avatar Celine Mercier
1 Browse files
Options

Major update: New column type to store sequence qualities. Closes #41

parent ffff91e7
Hide whitespace changes
Inline Side-by-side
Showing with 962 additions and 267 deletions
python/obitools3/commands/import.pyx
View file @ 3b59043e
......@@ -35,7 +35,6 @@ def addOptions(parser):
type=str,
help="Name of the default DMS for reading and writing data")
group.add_argument('--destination-view','-v',
action="store", dest="import:destview",
metavar='<VIEW NAME>',
......@@ -96,12 +95,14 @@ def run(config):
inputs = uopen(config['import']['filename'])
get_quality = False
if config['import']['seqinformat']=='fasta':
iseq = fastaIterator(inputs)
view_type="NUC_SEQS_VIEW"
elif config['import']['seqinformat']=='fastq':
iseq = fastqIterator(inputs)
view_type="NUC_SEQS_VIEW"
get_quality = True
else:
raise RuntimeError('No file format specified')
......@@ -120,13 +121,15 @@ def run(config):
view[i].set_id(seq['id'])
view[i].set_definition(seq['definition'])
view[i].set_sequence(seq['sequence'])
if get_quality :
view[i].set_quality(seq['quality'])
for tag in seq['tags'] :
#print(tag, seq['tags'][tag])
#if seq['tags'][tag] not in NA_list :
view[i][tag] = seq['tags'][tag]
i+=1
#print(view)
#print(i)
print(view.__repr__())
view.save_and_close()
......
python/obitools3/obidms/_obidms.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidms.pxd
View file @ 3b59043e
......@@ -70,6 +70,7 @@ cdef class OBIView_NUC_SEQS(OBIView):
cdef OBIDMS_column ids
cdef OBIDMS_column sequences
cdef OBIDMS_column definitions
cdef OBIDMS_column qualities
cpdef delete_column(self, str column_name)
......
python/obitools3/obidms/_obidms.pyx
View file @ 3b59043e
......@@ -17,6 +17,7 @@ from .capi.obitypes cimport const_char_p, \
OBI_FLOAT, \
OBI_BOOL, \
OBI_CHAR, \
OBI_QUAL, \
OBI_STR, \
OBI_SEQ, \
name_data_type, \
......@@ -43,6 +44,8 @@ from ._obidmscolumn_bool cimport OBIDMS_column_bool, \
from ._obidmscolumn_char cimport OBIDMS_column_char, \
OBIDMS_column_multi_elts_char
from ._obidmscolumn_qual cimport OBIDMS_column_qual
from ._obidmscolumn_str cimport OBIDMS_column_str, \
OBIDMS_column_multi_elts_str
......@@ -71,7 +74,8 @@ from .capi.obiview cimport Obiview_p, \
VIEW_TYPE_NUC_SEQS, \
NUC_SEQUENCE_COLUMN, \
ID_COLUMN, \
DEFINITION_COLUMN
DEFINITION_COLUMN, \
QUALITY_COLUMN
from libc.stdlib cimport malloc
from cpython.pycapsule cimport PyCapsule_New, PyCapsule_GetPointer
......@@ -187,6 +191,11 @@ cdef class OBIDMS_column :
subclass = OBIDMS_column_char
else :
subclass = OBIDMS_column_multi_elts_char
elif col_type == OBI_QUAL :
if col_one_element_per_line :
subclass = OBIDMS_column_qual
# else : # TODO
# subclass = OBIDMS_column_multi_elts_qual
elif col_type == OBI_STR :
if col_one_element_per_line :
subclass = OBIDMS_column_str
......@@ -355,6 +364,8 @@ cdef class OBIView :
data_type = OBI_BOOL
elif type == 'OBI_CHAR' :
data_type = OBI_CHAR
elif type == 'OBI_QUAL' :
data_type = OBI_QUAL
elif type == 'OBI_STR' :
data_type = OBI_STR
elif type == 'OBI_SEQ' :
......@@ -489,6 +500,7 @@ cdef class OBIView_NUC_SEQS(OBIView):
self.ids = self.columns[bytes2str(ID_COLUMN)]
self.sequences = self.columns[bytes2str(NUC_SEQUENCE_COLUMN)]
self.definitions = self.columns[bytes2str(DEFINITION_COLUMN)]
self.qualities = self.columns[bytes2str(QUALITY_COLUMN)]
cpdef delete_column(self, str column_name) :
......@@ -537,6 +549,7 @@ cdef class OBIView_line :
def __setitem__(self, str column_name, object value):
# TODO detect multiple elements (dict type)? put somewhere else? but more risky (in get)
# TODO OBI_QUAL ?
cdef type value_type
cdef str value_obitype
if column_name not in self.view :
......
python/obitools3/obidms/_obidmscolumn_bool.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidmscolumn_char.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidmscolumn_float.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidmscolumn_int.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidmscolumn_qual.cfiles 0 → 100644
View file @ 3b59043e
../../../src/bloom.h
../../../src/bloom.c
../../../src/char_str_indexer.h
../../../src/char_str_indexer.c
../../../src/crc64.h
../../../src/crc64.c
../../../src/dna_seq_indexer.h
../../../src/dna_seq_indexer.c
../../../src/encode.h
../../../src/encode.c
../../../src/murmurhash2.h
../../../src/murmurhash2.c
../../../src/obi_align.h
../../../src/obi_align.c
../../../src/obiavl.h
../../../src/obiavl.c
../../../src/obiblob_indexer.h
../../../src/obiblob_indexer.c
../../../src/obiblob.h
../../../src/obiblob.c
../../../src/obidebug.h
../../../src/obidms_taxonomy.h
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
../../../src/obidmscolumndir.c
../../../src/obierrno.h
../../../src/obierrno.c
../../../src/obilittlebigman.h
../../../src/obilittlebigman.c
../../../src/obitypes.h
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/uint8_indexer.h
../../../src/uint8_indexer.c
../../../src/utils.h
../../../src/utils.c
python/obitools3/obidms/_obidmscolumn_qual.pxd 0 → 100644
View file @ 3b59043e
#cython: language_level=3
from .capi.obitypes cimport index_t
from ._obidms cimport OBIDMS_column #, OBIDMS_column_multi_elts
cdef class OBIDMS_column_qual(OBIDMS_column):
cpdef object get_line(self, index_t line_nb)
cpdef object get_str_line(self, index_t line_nb)
cpdef set_line(self, index_t line_nb, object value)
cpdef set_str_line(self, index_t line_nb, object value)
# cdef class OBIDMS_column_multi_elts_qual(OBIDMS_column_multi_elts):
# cpdef object get_item(self, index_t line_nb, str element_name)
# cpdef object get_line(self, index_t line_nb)
# cpdef set_item(self, index_t line_nb, str element_name, object value)
python/obitools3/obidms/_obidmscolumn_qual.pyx 0 → 100644
View file @ 3b59043e
#cython: language_level=3
from .capi.obiview cimport obi_column_get_obiqual_char_with_elt_name_in_view, \
obi_column_get_obiqual_char_with_elt_idx_in_view, \
obi_column_set_obiqual_char_with_elt_name_in_view, \
obi_column_set_obiqual_char_with_elt_idx_in_view, \
obi_column_get_obiqual_int_with_elt_name_in_view, \
obi_column_get_obiqual_int_with_elt_idx_in_view, \
obi_column_set_obiqual_int_with_elt_name_in_view, \
obi_column_set_obiqual_int_with_elt_idx_in_view
from .capi.obierrno cimport obi_errno
from .capi.obitypes cimport OBIQual_char_NA, OBIQual_int_NA, const_char_p
from ._obidms cimport OBIView
from obitools3.utils cimport str2bytes, bytes2str
from libc.stdlib cimport free
from libc.string cimport strcmp
from libc.stdint cimport uint8_t
from libc.stdlib cimport malloc
cdef class OBIDMS_column_qual(OBIDMS_column):
cpdef object get_line(self, index_t line_nb):
cdef const uint8_t* value
cdef int value_length
cdef object result
cdef int i
value = obi_column_get_obiqual_int_with_elt_idx_in_view(self.view.pointer, (self.pointer)[0], line_nb, 0, &value_length)
if obi_errno > 0 :
raise IndexError(line_nb)
if value == NULL : # TODO
result = None
else :
result = []
for i in range(value_length) :
result.append(<int>value[i])
return result
cpdef object get_str_line(self, index_t line_nb):
cdef char* value
cdef object result
cdef int i
value = obi_column_get_obiqual_char_with_elt_idx_in_view(self.view.pointer, (self.pointer)[0], line_nb, 0)
if obi_errno > 0 :
raise IndexError(line_nb)
if strcmp(value, OBIQual_char_NA) == 0 :
result = None
else :
result = bytes2str(value)
free(value)
return result
cpdef set_line(self, index_t line_nb, object value):
cdef uint8_t* value_b
cdef int value_length
if value is None :
value_b = NULL # TODO
value_length = 0
else :
value_length = len(value)
value_b = <uint8_t*> malloc(value_length * sizeof(uint8_t))
for i in range(value_length) :
value_b[i] = <uint8_t>value[i]
if obi_column_set_obiqual_int_with_elt_idx_in_view(self.view.pointer, (self.pointer)[0], line_nb, 0, value_b, value_length) < 0:
raise Exception("Problem setting a value in a column")
if value is not None :
free(value_b)
cpdef set_str_line(self, index_t line_nb, object value):
cdef bytes value_b
if value is None :
value_b = OBIQual_char_NA
else :
value_b = str2bytes(value)
if obi_column_set_obiqual_char_with_elt_idx_in_view(self.view.pointer, (self.pointer)[0], line_nb, 0, value_b) < 0:
raise Exception("Problem setting a value in a column")
# TODO OR NOT?
# cdef class OBIDMS_column_multi_elts_qual(OBIDMS_column_multi_elts):
#
#
# cpdef object get_item(self, index_t line_nb, str element_name):
# cdef const uint8_t* value
# cdef int value_length
# cdef object result
# cdef int i
# value = obi_column_get_obiqual_int_with_elt_name_in_view(self.view.pointer, (self.pointer)[0], line_nb, str2bytes(element_name), &value_length)
# if obi_errno > 0 :
# raise IndexError(line_nb, element_name)
# if value == NULL: # TODO
# result = None
# else :
# result = []
# for i in range(value_length) :
# result.append(<int>value[i])
# return result
#
# # cpdef object get_str_item(self, index_t line_nb, str element_name):
# # pass
# # cdef char* value
# # cdef object result
# # value = obi_column_get_obiseq_with_elt_name_in_view(self.view.pointer, (self.pointer)[0], line_nb, str2bytes(element_name))
# # if obi_errno > 0 :
# # raise IndexError(line_nb, element_name)
# # if strcmp(value, OBISeq_NA) == 0 :
# # result = None
# # else :
# # result = bytes2str(value)
# # free(value)
# # return result
#
# cpdef object get_line(self, index_t line_nb) :
# pass
# # cdef char* value
# # cdef object value_in_result
# # cdef dict result
# # cdef index_t i
# # cdef bint all_NA
# # result = {}
# # all_NA = True
# # for i in range(self.nb_elements_per_line) :
# # value = obi_column_get_obiseq_with_elt_idx_in_view(self.view.pointer, (self.pointer)[0], line_nb, i)
# # if obi_errno > 0 :
# # raise IndexError(line_nb)
# # if strcmp(value, OBISeq_NA) == 0 :
# # value_in_result = None
# # else :
# # value_in_result = bytes2str(value)
# # free(value)
# # result[self.elements_names[i]] = value_in_result
# # if all_NA and (value_in_result is not None) :
# # all_NA = False
# # if all_NA :
# # result = None
# # return result
#
# cpdef set_item(self, index_t line_nb, str element_name, object value):
# pass
# # cdef bytes value_b
# # if value is None :
# # value_b = OBISeq_NA
# # else :
# # value_b = str2bytes(value)
# # if obi_column_set_obiseq_with_elt_name_in_view(self.view.pointer, (self.pointer)[0], line_nb, str2bytes(element_name), value_b) < 0:
# # raise Exception("Problem setting a value in a column")
# #
python/obitools3/obidms/_obidmscolumn_seq.cfiles
View file @ 3b59043e
......@@ -23,8 +23,22 @@
../../../src/obidms_taxonomy.c
../../../src/obidms.h
../../../src/obidms.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_idx.h
../../../src/obidmscolumn_idx.c
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_qual.h
../../../src/obidmscolumn_qual.c
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h
../../../src/obidmscolumn.h
../../../src/obidmscolumn.c
../../../src/obidmscolumndir.h
......@@ -37,19 +51,9 @@
../../../src/obitypes.c
../../../src/obiview.h
../../../src/obiview.c
../../../src/utils.h
../../../src/utils.c
../../../src/sse_banded_LCS_alignment.h
../../../src/sse_banded_LCS_alignment.c
../../../src/obidmscolumn_bool.c
../../../src/obidmscolumn_bool.h
../../../src/obidmscolumn_char.c
../../../src/obidmscolumn_char.h
../../../src/obidmscolumn_float.c
../../../src/obidmscolumn_float.h
../../../src/obidmscolumn_int.c
../../../src/obidmscolumn_int.h
../../../src/obidmscolumn_seq.c
../../../src/obidmscolumn_seq.h
../../../src/obidmscolumn_str.c
../../../src/obidmscolumn_str.h</