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

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.
*/
/**