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

Taxonomy: new functions to find taxa by name

Browse Source
This commit is contained in:
Celine Mercier
2020-10-30 10:45:20 +01:00
parent b9b4cec5b5
commit 112e12cab0
7 changed files with 174 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/obidms_taxonomy.c
View File

@ -3649,6 +3649,18 @@ ecotx_t* obi_taxo_get_taxon_with_taxid(OBIDMS_taxonomy_p taxonomy, int32_t taxid
}
char* obi_taxo_get_name_from_name_idx(OBIDMS_taxonomy_p taxonomy, int32_t idx)
{
return (((taxonomy->names)->names)[idx]).name;
}
ecotx_t* obi_taxo_get_taxon_from_name_idx(OBIDMS_taxonomy_p taxonomy, int32_t idx)
{
return (((taxonomy->names)->names)[idx]).taxon;
}
int obi_taxo_is_taxon_under_taxid(ecotx_t* taxon, int32_t other_taxid) // TODO discuss that this doesn't work with deprecated taxids
{
ecotx_t* next_parent;

45
src/obidms_taxonomy.h
View File

@ -447,8 +447,51 @@ ecotx_t* obi_taxo_get_superkingdom(ecotx_t* taxon, OBIDMS_taxonomy_p taxonomy);
const char* obi_taxo_rank_index_to_label(int32_t rank_idx, ecorankidx_t* ranks);
// TODO
/**
* @brief Function checking whether a taxid is included in a subset of the taxonomy.
*
* @param taxonomy A pointer on the taxonomy structure.
* @param restrict_to_taxids An array of taxids. The researched taxid must be under at least one of those array taxids.
* @param count Number of taxids in restrict_to_taxids.
* @param taxid The taxid to check.
*
* @returns A value indicating whether the taxid is included in the chosen subset of the taxonomy.
* @retval 0 if the taxid is not included in the subset of the taxonomy.
* @retval 1 if the taxid is included in the subset of the taxonomy.
*
* @since October 2020
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
int obi_taxo_is_taxid_included(OBIDMS_taxonomy_p taxonomy,
int32_t* restrict_to_taxids,
int32_t count,
int32_t taxid);
/**
* @brief Function returning the name of a taxon from its index in the taxonomy name index (econameidx_t).
*
* @param taxonomy A pointer on the taxonomy structure.
* @param idx The index at which the name is in the taxonomy name index (econameidx_t).
*
* @returns The taxon name.
*
* @since October 2020
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
char* obi_taxo_get_name_from_name_idx(OBIDMS_taxonomy_p taxonomy, int32_t idx);
/**
* @brief Function returning a taxon structure from its index in the taxonomy name index (econameidx_t).
*
* @param taxonomy A pointer on the taxonomy structure.
* @param idx The index at which the taxon is in the taxonomy name index (econameidx_t).
*
* @returns The taxon structure.
*
* @since October 2020
* @author Celine Mercier (celine.mercier@metabarcoding.org)
*/
ecotx_t* obi_taxo_get_taxon_from_name_idx(OBIDMS_taxonomy_p taxonomy, int32_t idx);

96
src/obiview.h
View File

@ -30,54 +30,56 @@
#include "obiblob.h"
#define OBIVIEW_NAME_MAX_LENGTH (249) /**< The maximum length of an OBIDMS view name, without the extension.
*/
#define VIEW_TYPE_MAX_LENGTH (1024) /**< The maximum length of the type name of a view.
*/
#define LINES_COLUMN_NAME "LINES" /**< The name of the column containing the line selections
* in all views.
*/
#define VIEW_TYPE_NUC_SEQS "NUC_SEQS_VIEW" /**< The type name of views based on nucleotide sequences
* and their metadata.
*/
#define NUC_SEQUENCE_COLUMN "NUC_SEQ" /**< The name of the column containing the nucleotide sequences
* in NUC_SEQS_VIEW views.
*/
#define ID_COLUMN "ID" /**< The name of the column containing the sequence identifiers
* in NUC_SEQS_VIEW views.
*/
#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.
*/
#define REVERSE_QUALITY_COLUMN "REVERSE_QUALITY" /**< The name of the column containing the sequence qualities
* of the reverse read (generated by ngsfilter, used by alignpairedend).
*/
#define OBIVIEW_NAME_MAX_LENGTH (249) /**< The maximum length of an OBIDMS view name, without the extension.
*/
#define VIEW_TYPE_MAX_LENGTH (1024) /**< The maximum length of the type name of a view.
*/
#define LINES_COLUMN_NAME "LINES" /**< The name of the column containing the line selections
* in all views.
*/
#define VIEW_TYPE_NUC_SEQS "NUC_SEQS_VIEW" /**< The type name of views based on nucleotide sequences
* and their metadata.
*/
#define NUC_SEQUENCE_COLUMN "NUC_SEQ" /**< The name of the column containing the nucleotide sequences
* in NUC_SEQS_VIEW views.
*/
#define ID_COLUMN "ID" /**< The name of the column containing the sequence identifiers
* in NUC_SEQS_VIEW views.
*/
#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.
*/
#define REVERSE_QUALITY_COLUMN "REVERSE_QUALITY" /**< The name of the column containing the sequence qualities
* of the reverse read (generated by ngsfilter, used by alignpairedend).
*/
#define REVERSE_SEQUENCE_COLUMN "REVERSE_SEQUENCE" /**< The name of the column containing the sequence
* of the reverse read (generated by ngsfilter, used by alignpairedend).
*/
#define QUALITY_COLUMN "QUALITY" /**< The name of the column containing the sequence qualities
* in NUC_SEQS_VIEW views.
*/
#define COUNT_COLUMN "COUNT" /**< The name of the column containing the sequence counts
* in NUC_SEQS_VIEW views.
*/
#define TAXID_COLUMN "TAXID" /**< The name of the column containing the taxids. TODO subtype of INT column?
*/
#define MERGED_TAXID_COLUMN "MERGED_TAXID" /**< The name of the column containing the merged taxids information.
*/
#define MERGED_PREFIX "MERGED_" /**< The prefix to prepend to column names when merging informations during obi uniq.
*/
#define TAXID_DIST_COLUMN "TAXID_DIST" /**< The name of the column containing a dictionary of taxid:[list of ids] when merging informations during obi uniq.
*/
#define MERGED_COLUMN "MERGED" /**< The name of the column containing a list of ids when merging informations during obi uniq.
*/
#define ID_PREFIX "seq" /**< The default prefix of sequence identifiers in automatic ID columns.
*/
#define PREDICATE_KEY "predicates" /**< The key used in the json-formatted view comments to store predicates.
*/
* of the reverse read (generated by ngsfilter, used by alignpairedend).
*/
#define QUALITY_COLUMN "QUALITY" /**< The name of the column containing the sequence qualities
* in NUC_SEQS_VIEW views.
*/
#define COUNT_COLUMN "COUNT" /**< The name of the column containing the sequence counts
* in NUC_SEQS_VIEW views.
*/
#define SCIENTIFIC_NAME_COLUMN "SCIENTIFIC_NAME" /**< The name of the column containing the taxon scientific name.
*/
#define TAXID_COLUMN "TAXID" /**< The name of the column containing the taxids. TODO subtype of INT column?
*/
#define MERGED_TAXID_COLUMN "MERGED_TAXID" /**< The name of the column containing the merged taxids information.
*/
#define MERGED_PREFIX "MERGED_" /**< The prefix to prepend to column names when merging informations during obi uniq.
*/
#define TAXID_DIST_COLUMN "TAXID_DIST" /**< The name of the column containing a dictionary of taxid:[list of ids] when merging informations during obi uniq.
*/
#define MERGED_COLUMN "MERGED" /**< The name of the column containing a list of ids when merging informations during obi uniq.
*/
#define ID_PREFIX "seq" /**< The default prefix of sequence identifiers in automatic ID columns.
*/
#define PREDICATE_KEY "predicates" /**< The key used in the json-formatted view comments to store predicates.
*/
/**