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

Added Obiviews specialized for the handling of nucleotide sequences

Browse Source
This commit is contained in:
Celine Mercier
2016-02-25 09:43:27 +01:00
parent ffc68d448f
commit 4df313c54a
5 changed files with 434 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
python/obitools3/obidms/_obidms.pxd
View File

@ -64,6 +64,15 @@ cdef class OBIView:
cpdef save_and_close(self)
cdef class OBIView_NUC_SEQS(OBIView):
cdef OBIDMS_column ids
cdef OBIDMS_column sequences
cdef OBIDMS_column descriptions
cpdef delete_column(self, str column_name)
cdef class OBIView_line :
cdef index_t index
@ -77,5 +86,7 @@ cdef class OBIDMS:
cpdef close(self)
cpdef OBIView open_view(self, str view_name)
cpdef OBIView new_view(self, str view_name, object view_to_clone=*, list line_selection=*)
cpdef OBIView new_view(self, str view_name, object view_to_clone=*, list line_selection=*, str view_type=*)
cpdef dict read_view_infos(self, str view_name)
cpdef dict read_views(self)

194
python/obitools3/obidms/_obidms.pyx
View File

@ -48,16 +48,26 @@ from ._obidmscolumn_seq cimport OBIDMS_column_seq, \
from ._obidms cimport OBIView, OBIView_line
from .capi.obiview cimport Obiview_p, \
Obiviews_infos_all_p, \
Obiview_infos_p, \
Column_reference_p, \
obi_new_view_nuc_seqs, \
obi_new_view, \
obi_new_view_cloned_from_name, \
obi_new_view_nuc_seqs_cloned_from_name, \
obi_open_view, \
obi_read_views, \
obi_view_delete_column, \
obi_view_add_column, \
obi_view_get_column, \
obi_view_get_pointer_on_column_in_view, \
obi_select_line, \
obi_select_lines, \
obi_save_and_close_view
obi_save_and_close_view, \
VIEW_TYPE_NUC_SEQS, \
NUC_SEQUENCE_COLUMN, \
ID_COLUMN, \
DESCRIPTION_COLUMN
from libc.stdlib cimport malloc
from cpython.pycapsule cimport PyCapsule_New, PyCapsule_GetPointer
@ -380,7 +390,6 @@ cdef class OBIView :
raise Exception("Problem adding a column in a view")
# Store the column pointer
column_pp = obi_view_get_pointer_on_column_in_view(self.pointer, column_name_b)
if column_pp == NULL :
raise Exception("Problem getting a column in a view")
@ -451,6 +460,112 @@ cdef class OBIView :
#############################################
cdef class OBIView_NUC_SEQS(OBIView):
def __init__(self, OBIDMS dms, str view_name, bint new=False, object view_to_clone=None, list line_selection=None):
cdef Obiview_p view = NULL
cdef int i
cdef list col_list
cdef str col_name
cdef OBIDMS_column column
cdef OBIDMS_column_p column_p
cdef OBIDMS_column_p* column_pp
cdef OBIDMS_column_header_p header
cdef index_t* line_selection_p
self.dms = dms
if line_selection is not None :
line_selection_p = <index_t*> malloc((len(line_selection) + 1) * sizeof(index_t))
for i in range(len(line_selection)) :
line_selection_p[i] = line_selection[i] # TODO type problem?
line_selection_p[len(line_selection)] = -1
else :
line_selection_p = NULL
if new :
if view_to_clone is not None :
if type(view_to_clone) == str :
view = obi_new_view_nuc_seqs_cloned_from_name(dms.pointer, str2bytes(view_name), str2bytes(view_to_clone), line_selection_p)
else :
view = obi_new_view_nuc_seqs(dms.pointer, str2bytes(view_name), (<OBIView> view_to_clone).pointer, line_selection_p)
elif view_to_clone is None :
view = obi_new_view_nuc_seqs(dms.pointer, str2bytes(view_name), NULL, line_selection_p)
elif not new :
if view_name is not None :
view = obi_open_view(dms.pointer, str2bytes(view_name))
elif view_name is None :
view = obi_open_view(dms.pointer, NULL)
if view == NULL :
raise Exception("Error creating/opening view")
self.pointer = view
self.name = bytes2str(view.name)
# go through columns to build list and open python object (TODO make separate function?)
self.columns = {}
self.columns_pp = {}
i = 0
while i < view.column_count :
column_pp = <OBIDMS_column_p*> ((view.columns)+i)
column_p = <OBIDMS_column_p> (view.columns)[i]
header = (column_p).header
col_name = bytes2str(header.name)
col_capsule = PyCapsule_New(column_pp, NULL, NULL) # TODO discuss
(self.columns_pp)[col_name] = col_capsule
subclass = OBIDMS_column.get_subclass_type(column_p)
self.columns[col_name] = subclass(self, col_name)
i+=1
self.ids = self.columns[bytes2str(ID_COLUMN)]
self.sequences = self.columns[bytes2str(NUC_SEQUENCE_COLUMN)]
self.descriptions = self.columns[bytes2str(DESCRIPTION_COLUMN)]
cpdef delete_column(self, str column_name) :
cdef int i
cdef Obiview_p view
cdef OBIDMS_column column
cdef OBIDMS_column_p column_p
cdef OBIDMS_column_p* column_pp
cdef OBIDMS_column_header_p header
cdef str column_n
if ((column_name == bytes2str(ID_COLUMN)) or (column_name == bytes2str(NUC_SEQUENCE_COLUMN)) or (column_name == bytes2str(DESCRIPTION_COLUMN))) :
raise Exception("Can't delete an obligatory column from a NUC_SEQS view")
view = self.pointer
if obi_view_delete_column(view, str2bytes(column_name)) < 0 :
raise Exception("Problem deleting a column from a view")
# Update the dictionaries of column pointers and column objects, and update pointers in column objects (make function?):
(self.columns).pop(column_name)
(self.columns_pp).pop(column_name)
i = 0
while i < view.column_count :
column_pp = <OBIDMS_column_p*> ((view.columns)+i)
column_p = <OBIDMS_column_p> (view.columns)[i]
header = (column_p).header
col_name = bytes2str(header.name)
col_capsule = PyCapsule_New(column_pp, NULL, NULL)
(self.columns_pp)[col_name] = col_capsule
i+=1
for column_n in self.columns :
(self.columns[column_n]).update_pointer()
#############################################
cdef class OBIView_line :
def __init__(self, OBIView view, index_t line_nb) :
@ -523,9 +638,78 @@ cdef class OBIDMS :
cpdef OBIView open_view(self, str view_name) :
return OBIView(self, view_name)
cdef object view_class
cdef dict view_infos
view_infos = self.read_view_infos(view_name)
if view_infos["view_type"] == bytes2str(VIEW_TYPE_NUC_SEQS) : # TODO not gonna work
view_class = OBIView_NUC_SEQS
else :
view_class = OBIView
return view_class(self, view_name)
cpdef OBIView new_view(self, str view_name, object view_to_clone=None, list line_selection=None, str view_type=None) :
cdef object view_class
if view_type is not None :
if view_type == bytes2str(VIEW_TYPE_NUC_SEQS) : # TODO not gonna work
view_class = OBIView_NUC_SEQS
else :
view_class = OBIView
return view_class(self, view_name, new=True, view_to_clone=view_to_clone, line_selection=line_selection)
cpdef dict read_view_infos(self, str view_name) :
all_views = self.read_views()
return all_views[view_name]
cpdef dict read_views(self) : # TODO function that gets 1 view with name, function that prints the dic and function that prints 1 view. Add column type in col ref
cdef Obiviews_infos_all_p all_views_p
cdef Obiview_infos_p view_p
cdef Column_reference_p column_refs
cdef int nb_views
cdef int i, j
cdef str view_name
cdef str column_name
cdef dict views
cdef bytes name_b
views = {}
all_views_p = obi_read_views(self.pointer)
nb_views = <int> (all_views_p.header).view_count
for i in range(nb_views) :
view_p = (<Obiview_infos_p> (all_views_p.view_infos)) + i
view_name = bytes2str(view_p.name)
views[view_name] = {}
views[view_name]["view_type"] = bytes2str(view_p.view_type)
views[view_name]["column_count"] = <int> view_p.column_count
views[view_name]["line_count"] = <int> view_p.line_count
views[view_name]["view_number"] = <int> view_p.view_number
views[view_name]["created_from"] = bytes2str(view_p.created_from)
views[view_name]["creation_date"] = bytes2str(obi_column_format_date(view_p.creation_date)) # TODO move this function in utils or somethings
if (view_p.all_lines) :
views[view_name]["line_selection"] = None
else :
views[view_name]["line_selection"] = {}
views[view_name]["line_selection"]["column_name"] = bytes2str((view_p.line_selection).column_name)
views[view_name]["line_selection"]["version"] = <int> (view_p.line_selection).version
views[view_name]["column_references"] = {}
column_refs = view_p.column_references
for j in range(views[view_name]["column_count"]) :
column_name = bytes2str((column_refs[j]).column_name)
views[view_name]["column_references"][column_name] = {}
views[view_name]["column_references"][column_name]["version"] = column_refs[j].version
return views
cpdef OBIView new_view(self, str view_name, object view_to_clone=None, list line_selection=None) :
return OBIView(self, view_name, new=True, view_to_clone=view_to_clone, line_selection=line_selection)

48
python/obitools3/obidms/capi/obiview.pxd
View File

@ -3,15 +3,21 @@
from .obitypes cimport const_char_p, \
OBIType_t, \
obiversion_t, \
index_t
index_t, \
time_t
from ..capi.obidms cimport OBIDMS_p
from ..capi.obidmscolumn cimport OBIDMS_column_p
cdef extern from "obiview.h" nogil:
extern const_char_p VIEW_TYPE_NUC_SEQS
extern const_char_p NUC_SEQUENCE_COLUMN
extern const_char_p ID_COLUMN
extern const_char_p DESCRIPTION_COLUMN
struct Column_reference_t :
char column_name
const_char_p column_name
obiversion_t version
ctypedef Column_reference_t* Column_reference_p
@ -31,12 +37,48 @@ cdef extern from "obiview.h" nogil:
ctypedef Obiview_t* Obiview_p
struct Obiview_infos_t :
int view_number
int column_count
index_t line_count
const_char_p name
const_char_p created_from
time_t creation_date
bint all_lines
Column_reference_t line_selection
Column_reference_p column_references
const_char_p view_type
ctypedef Obiview_infos_t* Obiview_infos_p
struct Obiviews_header_t :
size_t header_size
size_t views_size
int view_count
ctypedef Obiviews_header_t* Obiviews_header_p
struct Obiviews_infos_all_t :
Obiviews_header_p header
Obiview_infos_p view_infos
ctypedef Obiviews_infos_all_t* Obiviews_infos_all_p
Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const_char_p view_name, Obiview_p view_to_clone, index_t* line_selection)
Obiview_p obi_new_view(OBIDMS_p dms, const_char_p view_name, Obiview_p view_to_clone, index_t* line_selection)
Obiview_p obi_new_view_cloned_from_name(OBIDMS_p dms, const char* view_name, const char* view_to_clone_name, index_t* line_selection)
Obiview_p obi_new_view_cloned_from_name(OBIDMS_p dms, const_char_p view_name, const_char_p view_to_clone_name, index_t* line_selection)
Obiview_p obi_new_view_nuc_seqs_cloned_from_name(OBIDMS_p dms, const_char_p view_name, const_char_p view_to_clone_name, index_t* line_selection)
Obiview_p obi_open_view(OBIDMS_p dms, const_char_p view_name)
Obiviews_infos_all_p obi_read_views(OBIDMS_p dms)
int obi_view_add_column(Obiview_p view,
const_char_p column_name,
obiversion_t version_number,

159
src/obiview.c
View File

@ -209,6 +209,50 @@ int create_obiview_file(int dms_file_descriptor)
**********************************************************************/
Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const char* view_name, Obiview_p view_to_clone, index_t* line_selection)
{
Obiview_p view;
if (view_to_clone != NULL)
{ // TODO check that the view to clone is already a NUC_SEQS view (discuss possibility of transforming type of a view)
if (strcmp(view_to_clone->view_type, VIEW_TYPE_NUC_SEQS))
{
obi_set_errno(OBIVIEW_ERROR);
obidebug(1, "Trying to clone a non-NUC SEQS view to create a NUC SEQS view");
return NULL;
}
}
view = obi_new_view(dms, view_name, view_to_clone, line_selection);
strcpy(view->view_type, VIEW_TYPE_NUC_SEQS);
if (view_to_clone == NULL)
{
// Adding sequence column
if (obi_view_add_column(view, NUC_SEQUENCE_COLUMN, -1, OBI_SEQ, 0, 1, NUC_SEQUENCE_COLUMN, NUC_SEQUENCE_AVL, "Nucleotide sequences", true) < 0)
{
obidebug(1, "Error adding an obligatory column in a nucleotide sequences view");
return NULL;
}
// Adding id column
if (obi_view_add_column(view, ID_COLUMN, -1, OBI_STR, 0, 1, ID_COLUMN, ID_AVL, "Ids", true) < 0)
{
obidebug(1, "Error adding an obligatory column in a nucleotide sequences view");
return NULL;
}
// Adding description column
if (obi_view_add_column(view, DESCRIPTION_COLUMN, -1, OBI_STR, 0, 1, DESCRIPTION_COLUMN, DESCRIPTION_AVL, "Descriptions", true) < 0)
{
obidebug(1, "Error adding an obligatory column in a nucleotide sequences view");
return NULL;
}
}
return view;
}
Obiview_p obi_new_view(OBIDMS_p dms, const char* view_name, Obiview_p view_to_clone, index_t* line_selection)
{
Obiview_p view;
@ -297,6 +341,7 @@ Obiview_p obi_new_view(OBIDMS_p dms, const char* view_name, Obiview_p view_to_cl
}
}
strcpy(view->view_type, view_to_clone->view_type);
strcpy(view->created_from, view_to_clone->name);
view->new_line_selection = NULL;
}
@ -308,8 +353,9 @@ Obiview_p obi_new_view(OBIDMS_p dms, const char* view_name, Obiview_p view_to_cl
view->line_count = 0;
view->line_selection = NULL;
view->new_line_selection = NULL;
(view->created_from)[0] = '\0';
//view->columns = NULL; TODO
(view->created_from)[0] = '\0';
(view->view_type)[0] = '\0';
//view->columns = NULL; TODO
}
strcpy(view->name, view_name);
@ -328,6 +374,25 @@ Obiview_p obi_new_view_cloned_from_name(OBIDMS_p dms, const char* view_name, con
if (view_to_clone == NULL)
return NULL;
view = obi_new_view(dms, view_name, view_to_clone, line_selection);
obi_close_view(view_to_clone);
return view;
}
Obiview_p obi_new_view_nuc_seqs_cloned_from_name(OBIDMS_p dms, const char* view_name, const char* view_to_clone_name, index_t* line_selection)
{
Obiview_p view;
Obiview_p view_to_clone;
view_to_clone = obi_open_view(dms, view_to_clone_name);
if (view_to_clone == NULL)
return NULL;
view = obi_new_view_nuc_seqs(dms, view_name, view_to_clone, line_selection);
obi_close_view(view_to_clone);
return view;
}
@ -466,6 +531,7 @@ Obiview_p obi_open_view(OBIDMS_p dms, const char* view_name)
view->line_count = view_infos->line_count;
strcpy(view->created_from, view_infos->created_from);
strcpy(view->name, view_infos->name);
strcpy(view->view_type, view_infos->view_type);
// Open the columns to read
for (i=0; i<(view_infos->column_count); i++)
@ -493,6 +559,91 @@ Obiview_p obi_open_view(OBIDMS_p dms, const char* view_name)
}
Obiviews_infos_all_p obi_read_views(OBIDMS_p dms)
{
char* view_file_name;
int obiview_file_descriptor;
size_t header_size;
Obiviews_header_p header;
Obiview_infos_p view_infos;
Obiviews_infos_all_p views;
view_file_name = build_obiview_file_name();
if (view_file_name == NULL)
return NULL;
// Open view file, read header size and map header and views
obiview_file_descriptor = openat(dms->dir_fd, view_file_name, O_RDWR, 0777);
if (obiview_file_descriptor < 0)
{ // No views yet
free(view_file_name);
return NULL;
}
free(view_file_name);
// Read the header size
if (read(obiview_file_descriptor, &header_size, sizeof(size_t)) < ((ssize_t) sizeof(size_t)))
{
obi_set_errno(OBIVIEW_ERROR);
obidebug(1, "\nError reading the header size of an obiview file (trying to open a view when there are none?)");
close(obiview_file_descriptor);
return NULL;
}
// Map the header
header = mmap(NULL,
header_size,
PROT_READ | PROT_WRITE,
MAP_SHARED,
obiview_file_descriptor,
0
);
if (header == MAP_FAILED)
{
obi_set_errno(OBIVIEW_ERROR);
obidebug(1, "\nError mmapping an obiview file header");
close(obiview_file_descriptor);
return NULL;
}
// Map the views
view_infos = mmap(NULL,
header->views_size,
PROT_READ | PROT_WRITE,
MAP_SHARED,
obiview_file_descriptor,
header_size
);
if (view_infos == MAP_FAILED)
{
obi_set_errno(OBIVIEW_ERROR);
obidebug(1, "\nError mmapping the views from an obiview file");
munmap(header, header_size);
close(obiview_file_descriptor);
return NULL;
}
views = (Obiviews_infos_all_p) malloc(sizeof(Obiviews_infos_all_t));
if (views == NULL)
{
obi_set_errno(OBIVIEW_ERROR);
obidebug(1, "\nError mmapping the views from an obiview file");
munmap(view_infos, header->views_size);
munmap(header, header_size);
close(obiview_file_descriptor);
return NULL;
}
views->header = header;
views->view_infos = view_infos;
close(obiview_file_descriptor);
return views;
}
int obi_view_add_column(Obiview_p view,
const char* column_name,
obiversion_t version_number,
@ -605,6 +756,8 @@ int obi_view_delete_column(Obiview_p view, const char* column_name)
int i;
bool found;
// TODO check that not deleting an obligatory column?
// Check that the view is not read-only
if (view->read_only)
{
@ -879,6 +1032,8 @@ int obi_save_view(Obiview_p view)
view_infos->creation_date = time(NULL);
strcpy(view_infos->created_from, view->created_from);
strcpy(view_infos->name, view->name);
strcpy(view_infos->view_type, view->view_type);
// Store reference for the line selection associated with that view
if (view->new_line_selection != NULL)
{

29
src/obiview.h
View File

@ -30,6 +30,19 @@
*/
#define OBIVIEW_FILE_NAME "obiviews"
#define VIEW_TYPE_MAX_NAME (1024)
#define VIEW_TYPE_NUC_SEQS "NUC_SEQS_VIEW"
#define NUC_SEQUENCE_COLUMN "NUC_SEQ"
#define NUC_SEQUENCE_AVL "NUC_SEQ_AVL"
#define ID_COLUMN "ID"
#define ID_AVL "ID_AVL"
#define DESCRIPTION_COLUMN "DESCRIPTION"
#define DESCRIPTION_AVL "DESCRIPTION_AVL"
#define LINES_COLUMN_NAME "LINES"
@ -69,6 +82,8 @@ typedef struct Obiview {
int view_number;
char view_type[VIEW_TYPE_MAX_NAME+1];
} Obiview_t, *Obiview_p;
@ -94,6 +109,8 @@ typedef struct Obiview_infos {
Column_reference_t column_references[MAX_NB_OPENED_COLUMNS];
char view_type[VIEW_TYPE_MAX_NAME+1];
} Obiview_infos_t, *Obiview_infos_p;
@ -110,20 +127,26 @@ typedef struct Obiviews_header {
/**
* @brief .
*/
typedef struct Obiviews { // not used
typedef struct Obiviews_infos_all {
Obiviews_header_p header;
Obiview_infos_p views;
Obiview_infos_p view_infos;
} Obiviews_t, *Obiviews_p;
} Obiviews_infos_all_t, *Obiviews_infos_all_p;
Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const char* view_name, Obiview_p view_to_clone, index_t* line_selection);
Obiview_p obi_new_view(OBIDMS_p dms, const char* view_name, Obiview_p view_to_clone, index_t* line_selection);
Obiview_p obi_new_view_cloned_from_name(OBIDMS_p dms, const char* view_name, const char* view_to_clone_name, index_t* line_selection);
Obiview_p obi_new_view_nuc_seqs_cloned_from_name(OBIDMS_p dms, const char* view_name, const char* view_to_clone_name, index_t* line_selection);
Obiview_p obi_open_view(OBIDMS_p dms, const char* view_name);
Obiviews_infos_all_p obi_read_views(OBIDMS_p dms);
int obi_view_add_column(Obiview_p view,
const char* column_name,
obiversion_t version_number,