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

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

Browse Source
This commit is contained in:
Celine Mercier
2016-05-20 16:45:22 +02:00
parent ffff91e76c
commit 3b59043ea8
33 changed files with 962 additions and 267 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
src/char_str_indexer.c
View File

@ -14,6 +14,7 @@
#include <stdio.h>
#include <math.h>
#include "char_str_indexer.h"
#include "obiblob.h"
#include "obiblob_indexer.h"
#include "obidebug.h"
@ -25,24 +26,16 @@
Obi_blob_p obi_str_to_blob(const char* value)
{
Obi_blob_p value_b;
int32_t length;
int32_t length;
// Compute the number of bytes on which the value will be encoded
length = strlen(value) + 1; // +1 to store \0 at the end (makes retrieving faster)
value_b = obi_blob((byte_t*)value, ELEMENT_SIZE_STR, length, length);
if (value_b == NULL)
{
obidebug(1, "\nError encoding a character string in a blob");
return NULL;
}
return value_b;
return obi_blob((byte_t*)value, ELEMENT_SIZE_STR, length, length);
}
char* obi_blob_to_str(Obi_blob_p value_b)
const char* obi_blob_to_str(Obi_blob_p value_b)
{
return value_b->value;
}
@ -67,7 +60,7 @@ index_t obi_index_char_str(Obi_indexer_p indexer, const char* value)
}
char* obi_retrieve_char_str(Obi_indexer_p indexer, index_t idx)
const char* obi_retrieve_char_str(Obi_indexer_p indexer, index_t idx)
{
Obi_blob_p value_b;

4
src/char_str_indexer.h
View File

@ -35,7 +35,7 @@
* @since October 2015
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
Obi_blob_p obi_str_to_blob(char* value);
Obi_blob_p obi_str_to_blob(const char* value);
/**
@ -80,7 +80,7 @@ index_t obi_index_char_str(Obi_indexer_p indexer, const char* value);
* @since April 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_retrieve_char_str(Obi_indexer_p indexer, index_t idx);
const char* obi_retrieve_char_str(Obi_indexer_p indexer, index_t idx);
#endif /* CHAR_STR_INDEXER_H_ */

1
src/dna_seq_indexer.c
View File

@ -14,6 +14,7 @@
#include <stdio.h>
#include <math.h>
#include "dna_seq_indexer.h"
#include "obiblob.h"
#include "obiblob_indexer.h"
#include "obidebug.h"

2
src/obiblob.h
View File

@ -23,6 +23,8 @@
#define ELEMENT_SIZE_STR (8) /**< The size of an element from a value of type character string.
*/
#define ELEMENT_SIZE_UINT8 (8) /**< The size of an element from a value of type uint8_t.
*/
#define ELEMENT_SIZE_SEQ_2 (2) /**< The size of an element from a value of type DNA sequence encoded on 2 bits.
*/
#define ELEMENT_SIZE_SEQ_4 (4) /**< The size of an element from a value of type DNA sequence encoded on 4 bits.

88
src/obidmscolumn_qual.c
View File

@ -6,7 +6,7 @@
* @file obidsmcolumn_qual.c
* @author Celine Mercier
* @date May 4th 2016
* @brief Functions handling OBIColumns containing data in the form of indices referring to sequence quality arrays.
* @brief Functions handling OBIColumns containing data in the form of indices referring to sequence qualities.
*/
@ -14,9 +14,10 @@
#include <stdio.h>
#include <stdint.h>
#include "obidmscolumn_qual.h"
#include "obidmscolumn.h"
#include "obitypes.h"
#include "obidmscolumn_str.c"
#include "uint8_indexer.h"
/**********************************************************************
@ -26,38 +27,83 @@
**********************************************************************/
int obi_column_set_obiqual_char_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, const char* value)
{ // TODO discuss
return obi_column_set_obistr_with_elt_idx(column, line_nb, element_idx, value);
{
uint8_t* int_value;
int int_value_length;
int i;
int ret_value;
int_value_length = strlen(value);
int_value = (uint8_t*) malloc(int_value_length * sizeof(uint8_t));
// Convert in uint8_t array to index in that format
for (i=0; i<int_value_length; i++)
int_value[i] = ((uint8_t)(value[i])) - QUALITY_ASCII_BASE;
ret_value = obi_column_set_obiqual_int_with_elt_idx(column, line_nb, element_idx, int_value, int_value_length);
free(int_value);
return ret_value;
}
int obi_column_set_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, const uint8_t* value)
int obi_column_set_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, const uint8_t* value, int value_length)
{
char* value_char;
index_t idx;
char* new_indexer_name;
// Transform the int array into a char array
// Length??
//value_char = ;
if (obi_column_prepare_to_set_value(column, line_nb) < 0)
return -1;
obi_column_set_obiqual_char_with_elt_idx(column, line_nb, element_idx, value_char)
// Add the value in the indexer
idx = obi_index_uint8(column->indexer, value, value_length);
if (idx == -1) // An error occurred
{
if (obi_errno == OBI_READ_ONLY_INDEXER_ERROR)
{
// If the error is that the indexer is read-only, clone it
new_indexer_name = obi_build_indexer_name((column->header)->name, (column->header)->version);
if (new_indexer_name == NULL)
return -1;
column->indexer = obi_clone_indexer(column->indexer, new_indexer_name); // TODO Need to lock this somehow?
// Add the value in the new indexer
idx = obi_index_uint8(column->indexer, value, value_length);
if (idx == -1)
return -1;
}
else
return -1;
}
// Add the value's index in the column
*(((index_t*) (column->data)) + (line_nb * ((column->header)->nb_elements_per_line)) + element_idx) = idx;
return 0;
}
char* obi_column_get_obiqual_char_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx)
{ // TODO discuss
char* value;
{
char* value;
const uint8_t* int_value;
int int_value_length;
int i;
value = obi_column_get_obistr_with_elt_idx(column, line_nb, element_idx);
if (strcmp(value, OBIStr_NA) == 0)
return OBIQual_char_NA;
int_value = obi_column_get_obiqual_int_with_elt_idx(column, line_nb, element_idx, &int_value_length);
value = (char*) malloc((int_value_length + 1) * sizeof(char));
// Encode int quality to char quality
for (i=0; i<int_value_length; i++)
value[i] = (char)(int_value[i] + QUALITY_ASCII_BASE);
value[i] = '\0';
return value;
}
uint8_t* obi_column_get_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx) // TODO const? (mapped)
const uint8_t* obi_column_get_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, int* value_length)
{
index_t idx;
@ -70,7 +116,7 @@ uint8_t* obi_column_get_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t
if (idx == OBIIdx_NA)
return OBIQual_int_NA;
return obi_retrieve_quality_int(column->indexer, idx);
return obi_retrieve_uint8(column->indexer, idx, value_length);
}
@ -84,13 +130,13 @@ int obi_column_set_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t li
}
int obi_column_set_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, uint8_t* value)
int obi_column_set_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, const uint8_t* value, int value_length)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return -1;
return obi_column_set_obiqual_int_with_elt_idx(column, line_nb, element_idx, value);
return obi_column_set_obiqual_int_with_elt_idx(column, line_nb, element_idx, value, value_length);
}
@ -104,12 +150,12 @@ char* obi_column_get_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t
}
uint8_t* obi_column_get_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name) // TODO const? (mapped)
const uint8_t* obi_column_get_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, int* value_length)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return OBIQual_int_NA;
return obi_column_get_obiqual_int_with_elt_idx(column, line_nb, element_idx);
return obi_column_get_obiqual_int_with_elt_idx(column, line_nb, element_idx, value_length);
}

36
src/obidmscolumn_qual.h
View File

@ -6,7 +6,7 @@
* @file obidsmcolumn_qual.h
* @author Celine Mercier
* @date May 4th 2016
* @brief Header file for the functions handling OBIColumns containing data in the form of indices referring to sequence quality arrays.
* @brief Header file for the functions handling OBIColumns containing data in the form of indices referring to sequence qualities.
*/
@ -22,6 +22,12 @@
#include "obitypes.h"
#define QUALITY_ASCII_BASE (33) /**< The ASCII base of sequence quality.
* Used to convert sequence qualities from characters to integers
* and the other way around.
*/
/**
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line.
@ -56,7 +62,8 @@ int obi_column_set_obiqual_char_with_elt_idx(OBIDMS_column_p column, index_t lin
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be set.
* @param element_idx The index of the element that should be set in the line.
* @param value The value that should be set, in the integer format.
* @param value The value that should be set, in the integer array format.
* @param value_length The length of the integer array.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
@ -65,7 +72,7 @@ int obi_column_set_obiqual_char_with_elt_idx(OBIDMS_column_p column, index_t lin
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, uint8_t* value);
int obi_column_set_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, const uint8_t* value, int value_length);
/**
@ -79,7 +86,7 @@ int obi_column_set_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line
* @param element_idx The index of the element that should be recovered in the line.
*
* @returns The recovered value, in the character string format.
* @retval OBIQual_NA the NA value of the type if an error occurred and obi_errno is set.
* @retval OBIQual_str_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
@ -96,14 +103,15 @@ char* obi_column_get_obiqual_char_with_elt_idx(OBIDMS_column_p column, index_t l
* @param column A pointer as returned by obi_create_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_idx The index of the element that should be recovered in the line.
* @param value_length A pointer on an integer to store the length of the integer array recovered.
*
* @returns The recovered value, in the integer format.
* @retval OBIQual_NA the NA value of the type if an error occurred and obi_errno is set.
* @returns The recovered value, in the integer array format.
* @retval OBIQual_int_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
uint8_t* obi_column_get_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx);
const uint8_t* obi_column_get_obiqual_int_with_elt_idx(OBIDMS_column_p column, index_t line_nb, index_t element_idx, int* value_length);
/**
@ -133,7 +141,7 @@ int obi_column_set_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t li
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line.
*
* This function is for quality scores in the integer format.
* This function is for quality scores in the integer array format.
*
* @warning Pointers returned by obi_open_column() don't allow writing.
*
@ -141,6 +149,7 @@ int obi_column_set_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t li
* @param line_nb The number of the line where the value should be set.
* @param element_name The name of the element that should be set in the line.
* @param value The value that should be set, in the integer format.
* @param value_length The length of the integer array.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
@ -149,7 +158,7 @@ int obi_column_set_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t li
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, uint8_t* value);
int obi_column_set_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, const uint8_t* value, int value_length);
/**
@ -163,7 +172,7 @@ int obi_column_set_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t lin
* @param element_name The name of the element that should be recovered in the line.
*
* @returns The recovered value, in the character string format.
* @retval OBIQual_NA the NA value of the type if an error occurred and obi_errno is set.
* @retval OBIQual_str_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
@ -175,19 +184,20 @@ char* obi_column_get_obiqual_char_with_elt_name(OBIDMS_column_p column, index_t
* @brief Recovers a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line.
*
* This function returns quality scores in the integer format.
* This function returns quality scores in the integer array format.
*
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_name The name of the element that should be recovered in the line.
* @param value_length A pointer on an integer to store the length of the integer array recovered.
*
* @returns The recovered value, in the integer format.
* @retval OBIQual_NA the NA value of the type if an error occurred and obi_errno is set.
* @retval OBIQual_int_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
utin8_t* obi_column_get_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name);
const uint8_t* obi_column_get_obiqual_int_with_elt_name(OBIDMS_column_p column, index_t line_nb, const char* element_name, int* value_length);
#endif /* OBIDMSCOLUMN_QUAL_H_ */

11
src/obidmscolumn_str.c
View File

@ -29,17 +29,6 @@ int obi_column_set_obistr_with_elt_idx(OBIDMS_column_p column, index_t line_nb,
index_t idx;
char* new_indexer_name;
// TODO
// size_t i;
// uint8_t q;
// for (i=0;i<=strlen(value);i++)
// {
// if ()
// q = ((uint8_t) value[i]) - 33;
// fprintf(stderr, "\n%c == %u", value[i], q);
// }
if (obi_column_prepare_to_set_value(column, line_nb) < 0)
return -1;

2
src/obitypes.h
View File

@ -25,7 +25,7 @@
#define OBISeq_NA ("\0") /**< NA value for the type OBI_SEQ */ // TODO discuss
#define OBIStr_NA ("\0") /**< NA value for the type OBI_STR */ // TODO discuss
#define OBIQual_char_NA ("\0") /**< NA value for the type OBI_QUAL if the quality is in character string format */ // TODO test and discuss
#define OBIQual_int_NA ("\0") /**< NA value for the type OBI_QUAL if the quality is in integer format */ // TODO test and discuss
#define OBIQual_int_NA (NULL) /**< NA value for the type OBI_QUAL if the quality is in integer format */ // TODO test and discuss
/**

81
src/obiview.c
View File

@ -24,6 +24,7 @@
#include "obidmscolumn_char.h"
#include "obidmscolumn_float.h"
#include "obidmscolumn_int.h"
#include "obidmscolumn_qual.h"
#include "obidmscolumn_seq.h"
#include "obidmscolumn_str.h"
#include "obierrno.h"
@ -600,8 +601,6 @@ Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const char* view_name, Obiview_p v
if (view_to_clone == NULL)
{
// TODO Add quality column?
// Adding sequence column
if (obi_view_add_column(view, NUC_SEQUENCE_COLUMN, -1, OBI_SEQ, 0, 1, NUC_SEQUENCE_COLUMN, "", "Nucleotide sequences", true) < 0)
{
@ -620,6 +619,12 @@ Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const char* view_name, Obiview_p v
obidebug(1, "Error adding an obligatory column in a nucleotide sequences view");
return NULL;
}
// Adding quality column
if (obi_view_add_column(view, QUALITY_COLUMN, -1, OBI_QUAL, 0, 1, QUALITY_COLUMN, "", "Sequence qualities", true) < 0)
{
obidebug(1, "Error adding an obligatory column in a nucleotide sequences view");
return NULL;
}
}
return view;
@ -1490,6 +1495,78 @@ obiint_t obi_column_get_obiint_with_elt_name_in_view(Obiview_p view, OBIDMS_colu
/****************************************/
/*********** FOR QUAL COLUMNS ***********/
int obi_column_set_obiqual_char_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, const char* value)
{
if (prepare_to_set_value_in_column(view, &column, &line_nb) < 0)
return -1;
return obi_column_set_obiqual_char_with_elt_idx(column, line_nb, element_idx, value);
}
int obi_column_set_obiqual_int_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, const uint8_t* value, int value_length)
{
if (prepare_to_set_value_in_column(view, &column, &line_nb) < 0)
return -1;
return obi_column_set_obiqual_int_with_elt_idx(column, line_nb, element_idx, value, value_length);
}
char* obi_column_get_obiqual_char_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx)
{
if (prepare_to_get_value_from_column(view, &line_nb) < 0)
return OBIQual_char_NA;
return obi_column_get_obiqual_char_with_elt_idx(column, line_nb, element_idx);
}
const uint8_t* obi_column_get_obiqual_int_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, int* value_length)
{
if (prepare_to_get_value_from_column(view, &line_nb) < 0)
return OBIQual_int_NA;
return obi_column_get_obiqual_int_with_elt_idx(column, line_nb, element_idx, value_length);
}
int obi_column_set_obiqual_char_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, const char* value)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return -1;
return obi_column_set_obiqual_char_with_elt_idx_in_view(view, column, line_nb, element_idx, value);
}
int obi_column_set_obiqual_int_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, const uint8_t* value, int value_length)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return -1;
return obi_column_set_obiqual_int_with_elt_idx_in_view(view, column, line_nb, element_idx, value, value_length);
}
char* obi_column_get_obiqual_char_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return OBIQual_char_NA;
return obi_column_get_obiqual_char_with_elt_idx_in_view(view, column, line_nb, element_idx);
}
const uint8_t* obi_column_get_obiqual_int_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, int* value_length)
{
index_t element_idx = obi_column_get_element_index_from_name(column, element_name);
if (element_idx == OBIIdx_NA)
return OBIQual_int_NA;
return obi_column_get_obiqual_int_with_elt_idx_in_view(view, column, line_nb, element_idx, value_length);
}
/****************************************/
/*********** FOR SEQ COLUMNS ***********/
int obi_column_set_obiseq_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, const char* value)

194
src/obiview.h
View File

@ -17,6 +17,7 @@
#include <stdlib.h>
#include <errno.h>
#include <stdio.h>
#include <stdint.h>
#include <stdbool.h>
#include <time.h>
#include <math.h>
@ -50,6 +51,9 @@
#define DEFINITION_COLUMN "DEFINITION" /**< The name of the column containing the sequence definitions
* in NUC_SEQS_VIEW views.
*/
#define QUALITY_COLUMN "QUALITY" /**< The name of the column containing the sequence qualities
* in NUC_SEQS_VIEW views.
*/
/**
@ -215,6 +219,7 @@ Obiview_p obi_new_view_cloned_from_name(OBIDMS_p dms, const char* view_name, con
* - NUC_SEQUENCE_COLUMN where nucleotide sequences are stored
* - ID_COLUMN where sequence identifiers are stored
* - DEFINITION_COLUMN where sequence definitions are stored
* - QUALITY_COLUMN where sequence qualities are stored
*
* @param dms A pointer on the OBIDMS.
* @param view_name The unique name of the view.
@ -246,6 +251,7 @@ Obiview_p obi_new_view_nuc_seqs(OBIDMS_p dms, const char* view_name, Obiview_p v
* - NUC_SEQUENCE_COLUMN where nucleotide sequences are stored
* - ID_COLUMN where sequence identifiers are stored
* - DEFINITION_COLUMN where sequence definitions are stored
* - QUALITY_COLUMN where sequence qualities are stored
*
* @param dms A pointer on the OBIDMS.
* @param view_name The unique name of the new view.
@ -803,6 +809,194 @@ int obi_column_set_obiint_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p
obiint_t obi_column_get_obiint_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name);
/**
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function is for qualities in the character string format.
*
* @warning Pointers returned by obi_open_column() don't allow writing.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be set.
* @param element_idx The index of the element that should be set in the line.
* @param value The value that should be set, in the character string format.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
* @retval -1 if an error occurred.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_char_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, const char* value);
/**
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function is for qualities in the integer format.
*
* @warning Pointers returned by obi_open_column() don't allow writing.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be set.
* @param element_idx The index of the element that should be set in the line.
* @param value The value that should be set, in the integer array format.
* @param value_length The length of the integer array.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
* @retval -1 if an error occurred.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_int_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, const uint8_t* value, int value_length);
/**
* @brief Recovers a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function returns quality scores in the character string format.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_idx The index of the element that should be recovered in the line.
*
* @returns The recovered value, in the character string format.
* @retval OBIQual_str_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_column_get_obiqual_char_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx);
/**
* @brief Recovers a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function returns quality scores in the integer format.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_idx The index of the element that should be recovered in the line.
* @param value_length A pointer on an integer to store the length of the integer array recovered.
*
* @returns The recovered value, in the integer array format.
* @retval OBIQual_int_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
const uint8_t* obi_column_get_obiqual_int_with_elt_idx_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, index_t element_idx, int* value_length);
/**
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function is for quality scores in the character string format.
*
* @warning Pointers returned by obi_open_column() don't allow writing.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be set.
* @param element_name The name of the element that should be set in the line.
* @param value The value that should be set, in the character string format.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
* @retval -1 if an error occurred.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_char_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, const char* value);
/**
* @brief Sets a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function is for quality scores in the integer array format.
*
* @warning Pointers returned by obi_open_column() don't allow writing.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be set.
* @param element_name The name of the element that should be set in the line.
* @param value The value that should be set, in the integer format.
* @param value_length The length of the integer array.
*
* @returns An integer value indicating the success of the operation.
* @retval 0 on success.
* @retval -1 if an error occurred.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_column_set_obiqual_int_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, const uint8_t* value, int value_length);
/**
* @brief Recovers a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function returns quality scores in the character string format.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_name The name of the element that should be recovered in the line.
*
* @returns The recovered value, in the character string format.
* @retval OBIQual_str_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_column_get_obiqual_char_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name);
/**
* @brief Recovers a value in an OBIDMS column containing data in the form of indices referring
* to sequence qualities handled by an indexer, and using the index of the element in the column's line,
* in the context of a view.
*
* This function returns quality scores in the integer array format.
*
* @param view A pointer on the opened view.
* @param column A pointer as returned by obi_create_column() or obi_clone_column().
* @param line_nb The number of the line where the value should be recovered.
* @param element_name The name of the element that should be recovered in the line.
* @param value_length A pointer on an integer to store the length of the integer array recovered.
*
* @returns The recovered value, in the integer format.
* @retval OBIQual_int_NA the NA value of the type if an error occurred and obi_errno is set.
*
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
const uint8_t* obi_column_get_obiqual_int_with_elt_name_in_view(Obiview_p view, OBIDMS_column_p column, index_t line_nb, const char* element_name, int* value_length);
/**
* @brief Sets a value in an OBIDMS column containing data with the type OBI_SEQ, using the index of the element in the line,
* in the context of a view.

60
src/uint8_indexer.c
View File

@ -1,19 +1,21 @@
/****************************************************************************
* Sequence quality scores indexing functions *
* Uint8 indexing functions *
****************************************************************************/
/**
* @file quality_indexer.c
* @file uint8_indexer.c
* @author Celine Mercier
* @date May 4th 2016
* @brief Functions handling the indexing and retrieval of sequence quality scores.
* @brief Functions handling the indexing and retrieval of uint8 arrays.
*/
#include <stdlib.h>
#include <stdio.h>
#include <stdint.h>
#include <math.h>
#include "uint8_indexer.h"
#include "obiblob.h"
#include "obiblob_indexer.h"
#include "obidebug.h"
@ -23,60 +25,25 @@
#define DEBUG_LEVEL 0 // TODO has to be defined somewhere else (cython compil flag?)
Obi_blob_p obi_uint8_to_blob(const char* quality)
Obi_blob_p obi_uint8_to_blob(const uint8_t* value, int value_length)
{
Obi_blob_p value_b;
int32_t length_encoded_seq; // length of the encoded sequence in bytes
int32_t seq_length;
byte_t* encoded_seq;
seq_length = strlen(seq);
// Check if just ATGC and encode accordingly
if (only_ATGC(seq))
{
// Compute the length (in bytes) of the encoded sequence
length_encoded_seq = ceil((double) seq_length / (double) 4.0);
// Encode
encoded_seq = encode_seq_on_2_bits(seq, seq_length);
if (encoded_seq == NULL)
return NULL;
value_b = obi_blob(encoded_seq, ELEMENT_SIZE_SEQ_2, length_encoded_seq, seq_length);
}
else
{
// Compute the length (in bytes) of the encoded sequence
length_encoded_seq = ceil((double) seq_length / (double) 2.0);
// Encode
encoded_seq = encode_seq_on_4_bits(seq, seq_length);
if (encoded_seq == NULL)
return NULL;
value_b = obi_blob(encoded_seq, ELEMENT_SIZE_SEQ_4, length_encoded_seq, seq_length);
}
free(encoded_seq);
return value_b;
return obi_blob((byte_t*)value, ELEMENT_SIZE_UINT8, value_length, value_length);
}
char* obi_blob_to_quality_char(Obi_blob_p value_b)
const uint8_t* obi_blob_to_uint8(Obi_blob_p value_b)
{
// Decode
if (value_b->element_size == 2)
return decode_seq_on_2_bits(value_b->value, value_b->length_decoded_value);
else
return decode_seq_on_4_bits(value_b->value, value_b->length_decoded_value);
return ((uint8_t*) (value_b->value));
}
index_t obi_index_quality_char(Obi_indexer_p indexer, const char* value)
index_t obi_index_uint8(Obi_indexer_p indexer, const uint8_t* value, int value_length)
{
Obi_blob_p value_b;
index_t idx;
// Encode value
value_b = obi_seq_to_blob(value);
value_b = obi_uint8_to_blob(value, value_length);
if (value_b == NULL)
return -1;
@ -89,7 +56,7 @@ index_t obi_index_quality_char(Obi_indexer_p indexer, const char* value)
}
char* obi_retrieve_dna_seq(Obi_indexer_p indexer, index_t idx)
const uint8_t* obi_retrieve_uint8(Obi_indexer_p indexer, index_t idx, int* value_length)
{
Obi_blob_p value_b;
@ -97,6 +64,7 @@ char* obi_retrieve_dna_seq(Obi_indexer_p indexer, index_t idx)
value_b = obi_indexer_get(indexer, idx);
// Return decoded sequence
return obi_blob_to_seq(value_b);
*value_length = value_b->length_decoded_value;
return obi_blob_to_uint8(value_b);
}

59
src/uint8_indexer.h
View File

@ -1,17 +1,17 @@
/****************************************************************************
* DNA sequence indexer header file *
* uint8 indexer header file *
****************************************************************************/
/**
* @file dna_seq_indexer.h
* @file uint8_indexer.h
* @author Celine Mercier
* @date April 12th 2016
* @brief Header file for the functions handling the indexing of DNA sequences.
* @date May 4th 2016
* @brief Header file for the functions handling the indexing of uint8 arrays.
*/
#ifndef DNA_SEQ_INDEXER_H_
#define DNA_SEQ_INDEXER_H_
#ifndef UINT8_INDEXER_H_
#define UINT8_INDEXER_H_
#include <stdlib.h>
@ -24,64 +24,69 @@
/**
* @brief Converts a DNA sequence to a blob.
* @brief Converts an uint8 array to a blob.
*
* @warning The blob must be freed by the caller.
*
* @param value The DNA sequence to convert.
* @param value The uint8 array to convert.
* @param value_length The length of the uint8 array to convert.
*
* @returns A pointer to the blob created.
* @returns A pointer on the blob created.
* @retval NULL if an error occurred.
*
* @since November 2015
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
Obi_blob_p obi_seq_to_blob(const char* seq);
Obi_blob_p obi_uint8_to_blob(const uint8_t* value, int value_length);
/**
* @brief Converts a blob to a DNA sequence.
* @brief Converts a blob to an uint8 array.
*
* @warning The array returned is mapped.
*
* @param value_b The blob to convert.
*
* @returns A pointer to the DNA sequence contained in the blob.
* @returns A pointer on the uint8 array contained in the blob.
* @retval NULL if an error occurred.
*
* @since November 2015
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_blob_to_seq(Obi_blob_p value_b);
const uint8_t* obi_blob_to_uint8(Obi_blob_p value_b);
/**
* @brief Stores a DNA sequence in an indexer and returns the index.
* @brief Stores an uint8 array in an indexer and returns the index.
*
* @param indexer The indexer structure.
* @param value The DNA sequence to index.
* @param value The uint8 array to index.
* @param value_length The length of the uint8 array to index.
*
* @returns The index referring to the stored DNA sequence in the indexer.
* @returns The index referring to the stored uint8 array in the indexer.
*
* @since April 2016
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
index_t obi_index_dna_seq(Obi_indexer_p indexer, const char* value);
index_t obi_index_uint8(Obi_indexer_p indexer, const uint8_t* value, int value_length);
/**
* @brief Retrieves a DNA sequence from an indexer.
* @brief Retrieves an uint8 array from an indexer.
*
* @warning The DNA sequence returned must be freed by the caller.
* @warning The array returned is mapped.
*
* @param indexer The indexer structure.
* @param idx The index referring to the DNA sequence to retrieve in the indexer.
* @param idx The index referring to the uint8 array to retrieve in the indexer.
* @param value_length A pointer on an integer to store the length of the array retrieved.
*
* @returns A pointer on the DNA sequence.
* @returns A pointer on the uint8 array.
*
* @since April 2016
* @since May 2016
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_retrieve_dna_seq(Obi_indexer_p indexer, index_t idx);
const uint8_t* obi_retrieve_uint8(Obi_indexer_p indexer, index_t idx, int* value_length);
#endif /* DNA_SEQ_INDEXER_H_ */
#endif /* UINT8_INDEXER_H_ */