obitools/ecopcr
2
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases 3 Wiki Activity

git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@114 60f365c0-8329-0410-b2a4-ec073aeeaa1d

Browse Source
This commit is contained in:
Eric Coissac
2007-09-24 09:48:08 +00:00
parent 6cd1141130
commit bc4c7656c6
15 changed files with 1494 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/libecoPCR/Makefile
+29
View File
@@ -0,0 +1,29 @@
SOURCES = ecoapat.c \
ecodna.c \
ecoError.c \
ecoIOUtils.c \
ecoMalloc.c \
ecorank.c \
ecoseq.c \
ecotax.c \
ecofilter.c \
econame.c
SRCS=$(SOURCES)
OBJECTS= $(patsubst %.c,%.o,$(SOURCES))
LIBFILE= libecoPCR.a
include ../global.mk
all: $(LIBFILE)
clean:
rm -rf $(OBJECTS) $(LIBFILE)
$(LIBFILE): $(OBJECTS)
ar -cr $@ $?
src/libecoPCR/ecoError.c
+9 -1
View File
@@ -2,7 +2,15 @@
#include <stdio.h>
#include <stdlib.h>
/*
* print the message given as argument and exit the program
* @param error error number
* @param message the text explaining what's going on
* @param filename the file source where the program failed
* @param linenumber the line where it has failed
* filename and linenumber are written at pre-processing
* time by a macro
*/
void ecoError(int32_t error,
const char* message,
const char * filename,
src/libecoPCR/ecoIOUtils.c
+15 -12
View File
@@ -16,20 +16,19 @@ int32_t is_big_endian()
int32_t swap_int32_t(int32_t i)
{
return SWAPINT32(i);
}
/**
* Read part of the file
* @param *f the database
* @param recordSize the size to be read
*
* @return buffer
*/
void *read_ecorecord(FILE *f,int32_t *recordSize)
{
static void *buffer =NULL;
@@ -79,10 +78,14 @@ void *read_ecorecord(FILE *f,int32_t *recordSize)
/**
* Open the database and check it's readable
* @param filename name of the database (.sdx, .rdx, .tbx)
* @param sequencecount buffer - pointer to variable storing the number of occurence
* @param abort_on_open_error boolean to define the behaviour in case of error
* while opening the database
* @return FILE type
**/
FILE *open_ecorecorddb(const char *filename,
int32_t *sequencecount,
int32_t abort_on_open_error)
src/libecoPCR/ecoPCR.h
+46 -7
View File
@@ -56,11 +56,11 @@ typedef struct {
} ecotxformat_t;
typedef struct {
int32_t taxid;
int32_t rank;
int32_t parent;
char *name;
typedef struct ecotxnode {
int32_t taxid;
int32_t rank;
struct ecotxnode *parent;
char *name;
} ecotx_t;
typedef struct {
@@ -80,12 +80,42 @@ typedef struct {
char* label[1];
} ecorankidx_t;
/*
*
* Taxonomy name types
*
*/
typedef struct {
int32_t is_scientificname;
int32_t namelength;
int32_t classlength;
int32_t taxid;
char names[1];
} econameformat_t;
typedef struct {
char *name;
char *classname;
int32_t is_scientificname;
struct ecotxnode *taxon;
} econame_t;
typedef struct {
int32_t count;
econame_t names[1];
} econameidx_t;
typedef struct {
ecorankidx_t *ranks;
econameidx_t *names;
ecotxidx_t *taxons;
} ecotaxonomy_t;
/*****************************************************
*
* Function declarations
@@ -175,6 +205,9 @@ ecoseq_t *readnext_ecoseq(FILE *);
ecorankidx_t *read_rankidx(const char *filename);
econameidx_t *read_nameidx(const char *filename,ecotaxonomy_t *taxonomy);
/**
* Read taxonomy data as formated by the ecoPCRFormat.py script.
@@ -189,8 +222,11 @@ ecorankidx_t *read_rankidx(const char *filename);
ecotxidx_t *read_taxonomyidx(const char *filename);
ecotaxonomy_t *read_taxonomy(const char *prefix);
ecotaxonomy_t *read_taxonomy(const char *prefix,int32_t readAlternativeName);
ecotx_t *eco_findtaxonbytaxid(ecotaxonomy_t *taxonomy, int32_t taxid);
int eco_isundertaxon(ecotx_t *taxon, int other_taxid);
ecoseq_t *ecoseq_iterator(const char *prefix);
@@ -227,4 +263,7 @@ ecotx_t *eco_getfamily(ecotx_t *taxon,ecotaxonomy_t *taxonomy);
ecotx_t *eco_getkingdom(ecotx_t *taxon,ecotaxonomy_t *taxonomy);
ecotx_t *eco_getsuperkingdom(ecotx_t *taxon,ecotaxonomy_t *taxonomy);
int eco_is_taxid_ignored(int32_t *ignored_taxid, int32_t tab_len, int32_t taxid);
int eco_is_taxid_included(ecotaxonomy_t *taxonomy, int32_t *included_taxid, int32_t tab_len, int32_t taxid);
#endif /*ECOPCR_H_*/
src/libecoPCR/ecofilter.c
+19
View File
@@ -0,0 +1,19 @@
#include "ecoPCR.h"
int eco_is_taxid_included( ecotaxonomy_t *taxonomy,
int32_t *restricted_taxid,
int32_t tab_len,
int32_t taxid)
{
int i;
ecotx_t *taxon;
taxon = eco_findtaxonbytaxid(taxonomy, taxid);
for (i=0; i < tab_len; i++)
if ( (taxon->taxid == restricted_taxid[i]) ||
(eco_isundertaxon(taxon, restricted_taxid[i])) )
return 1;
return 0;
}
src/libecoPCR/econame.c
+61
View File
@@ -0,0 +1,61 @@
#include "ecoPCR.h"
#include <string.h>
#include <stdlib.h>
static econame_t *readnext_econame(FILE *f,econame_t *name,ecotaxonomy_t *taxonomy);
econameidx_t *read_nameidx(const char *filename,ecotaxonomy_t *taxonomy)
{
int32_t count;
FILE *f;
econameidx_t *indexname;
int32_t i;
f = open_ecorecorddb(filename,&count,1);
indexname = (econameidx_t*) ECOMALLOC(sizeof(econameidx_t) + sizeof(econame_t) * (count-1),"Allocate names");
indexname->count=count;
for (i=0; i < count; i++){
readnext_econame(f,(indexname->names)+i,taxonomy);
}
return indexname;
}
econame_t *readnext_econame(FILE *f,econame_t *name,ecotaxonomy_t *taxonomy)
{
econameformat_t *raw;
int32_t rs;
raw = read_ecorecord(f,&rs);
if (!raw)
return NULL;
if (is_big_endian())
{
raw->is_scientificname = swap_int32_t(raw->is_scientificname);
raw->namelength = swap_int32_t(raw->namelength);
raw->classlength = swap_int32_t(raw->classlength);
raw->taxid = swap_int32_t(raw->taxid);
}
name->is_scientificname=raw->is_scientificname;
name->name = ECOMALLOC((raw->namelength+1) * sizeof(char),"Allocate name");
strncpy(name->name,raw->names,raw->namelength);
name->name[raw->namelength]=0;
name->classname = ECOMALLOC((raw->classlength+1) * sizeof(char),"Allocate classname");
strncpy(name->classname,(raw->names+raw->namelength),raw->classlength);
name->classname[raw->classlength]=0;
name->taxon = taxonomy->taxons->taxon + raw->taxid;
return name;
}
src/libecoPCR/ecoseq.c
+12 -3
View File
@@ -79,7 +79,9 @@ ecoseq_t *new_ecoseq_with_data( char *AC,
}
/**
* ?? used ??
**/
FILE *open_ecoseqdb(const char *filename,
int32_t *sequencecount)
{
@@ -140,6 +142,13 @@ ecoseq_t *readnext_ecoseq(FILE *f)
return seq;
}
/**
* Open the sequences database (.sdx file)
* @param prefix name of the database (radical without extension)
* @param index integer
*
* @return file object
*/
FILE *open_seqfile(const char *prefix,int32_t index)
{
char filename_buffer[1024];
@@ -153,7 +162,7 @@ FILE *open_seqfile(const char *prefix,int32_t index)
prefix,
index);
fprintf(stderr,"Coucou %s\n",filename_buffer);
fprintf(stderr,"# Coucou %s\n",filename_buffer);
if (filename_length >= 1024)
@@ -164,7 +173,7 @@ FILE *open_seqfile(const char *prefix,int32_t index)
input=open_ecorecorddb(filename_buffer,&seqcount,0);
if (input)
fprintf(stderr,"Reading file %s containing %d sequences...\n",
fprintf(stderr,"# Reading file %s containing %d sequences...\n",
filename_buffer,
seqcount);
src/libecoPCR/ecotax.c
+95 -18
View File
@@ -5,7 +5,11 @@
static ecotx_t *readnext_ecotaxon(FILE *f,ecotx_t *taxon);
/**
* Open the taxonomy database
* @param pointer to the database (.tdx file)
* @return a ecotxidx_t structure
*/
ecotxidx_t *read_taxonomyidx(const char *filename)
{
int32_t count;
@@ -18,14 +22,15 @@ ecotxidx_t *read_taxonomyidx(const char *filename)
index = (ecotxidx_t*) ECOMALLOC(sizeof(ecotxidx_t) + sizeof(ecotx_t) * (count-1),
"Allocate taxonomy");
index->count=count;
for (i=0; i < count; i++)
index->count=count;
for (i=0; i < count; i++){
readnext_ecotaxon(f,&(index->taxon[i]));
index->taxon[i].parent=index->taxon + (int32_t)index->taxon[i].parent;
}
return index;
}
int32_t delete_taxonomy(ecotxidx_t *index)
{
int32_t i;
@@ -61,6 +66,15 @@ int32_t delete_taxon(ecotx_t *taxon)
return 1;
}
/**
* Read the database for a given taxon a save the data
* into the taxon structure(if any found)
* @param *f pointer to FILE type returned by fopen
* @param *taxon pointer to the structure
*
* @return a ecotx_t structure if any taxon found else NULL
*/
ecotx_t *readnext_ecotaxon(FILE *f,ecotx_t *taxon)
{
@@ -80,7 +94,7 @@ ecotx_t *readnext_ecotaxon(FILE *f,ecotx_t *taxon)
raw->taxid = swap_int32_t(raw->taxid);
}
taxon->parent = raw->parent;
taxon->parent = (ecotx_t*)raw->parent;
taxon->taxid = raw->taxid;
taxon->rank = raw->rank;
@@ -88,12 +102,12 @@ ecotx_t *readnext_ecotaxon(FILE *f,ecotx_t *taxon)
"Allocate taxon scientific name");
strncpy(taxon->name,raw->name,raw->namelength);
return taxon;
}
ecotaxonomy_t *read_taxonomy(const char *prefix)
ecotaxonomy_t *read_taxonomy(const char *prefix,int32_t readAlternativeName)
{
ecotaxonomy_t *tax;
char *filename;
@@ -115,10 +129,19 @@ ecotaxonomy_t *read_taxonomy(const char *prefix)
tax->taxons = read_taxonomyidx(filename);
if (readAlternativeName)
{
snprintf(filename,buffsize,"%s.ndx",prefix);
tax->names=read_nameidx(filename,tax);
}
else
tax->names=NULL;
return tax;
}
int32_t delete_ecotaxonomy(ecotaxonomy_t *taxonomy)
{
if (taxonomy)
@@ -138,20 +161,19 @@ int32_t delete_ecotaxonomy(ecotaxonomy_t *taxonomy)
}
ecotx_t *eco_findtaxonatrank(ecotx_t *taxon,
int32_t rankidx,
ecotaxonomy_t *taxonomy)
int32_t rankidx)
{
ecotx_t *current_taxon;
ecotx_t *next_taxon;
current_taxon = taxon;
next_taxon = &(taxonomy->taxons->taxon[current_taxon->parent]);
next_taxon = current_taxon->parent;
while ((current_taxon!=next_taxon) &&
while ((current_taxon!=next_taxon) && // I' am the root node
(current_taxon->rank!=rankidx))
{
current_taxon = next_taxon;
next_taxon = &(taxonomy->taxons->taxon[current_taxon->parent]);
next_taxon = current_taxon->parent;
}
if (current_taxon->rank==rankidx)
@@ -160,6 +182,61 @@ ecotx_t *eco_findtaxonatrank(ecotx_t *taxon,
return NULL;
}
/**
* Get back information concerning a taxon from a taxonomic id
* @param *taxonomy the taxonomy database
* @param taxid the taxonomic id
*
* @result a ecotx_t structure containing the taxonimic information
**/
ecotx_t *eco_findtaxonbytaxid(ecotaxonomy_t *taxonomy,
int32_t taxid)
{
ecotx_t *current_taxon;
int32_t taxoncount;
int32_t i;
taxoncount=taxonomy->taxons->count;
for (current_taxon=taxonomy->taxons->taxon,
i=0;
i < taxoncount;
i++,
current_taxon++){
if (current_taxon->taxid==taxid){
return current_taxon;
}
}
return (ecotx_t*)NULL;
}
/**
* Find out if taxon is son of other taxon (identified by its taxid)
* @param *taxon son taxon
* @param parent_taxid taxonomic id of the other taxon
*
* @return 1 is the other taxid math a parent taxid, else 0
**/
int eco_isundertaxon(ecotx_t *taxon,
int other_taxid)
{
ecotx_t *next_parent;
next_parent = taxon->parent;
while ( (other_taxid != next_parent->taxid) &&
(strcmp(next_parent->name, "root")) )
{
next_parent = next_parent->parent;
}
if (other_taxid == next_parent->taxid)
return 1;
else
return 0;
}
ecotx_t *eco_getspecies(ecotx_t *taxon,
ecotaxonomy_t *taxonomy)
{
@@ -175,7 +252,7 @@ ecotx_t *eco_getspecies(ecotx_t *taxon,
if (!tax || rankindex < 0)
ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
return eco_findtaxonatrank(taxon,rankindex,tax);
return eco_findtaxonatrank(taxon,rankindex);
}
ecotx_t *eco_getgenus(ecotx_t *taxon,
@@ -193,7 +270,7 @@ ecotx_t *eco_getgenus(ecotx_t *taxon,
if (!tax || rankindex < 0)
ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
return eco_findtaxonatrank(taxon,rankindex,tax);
return eco_findtaxonatrank(taxon,rankindex);
}
@@ -212,7 +289,7 @@ ecotx_t *eco_getfamily(ecotx_t *taxon,
if (!tax || rankindex < 0)
ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
return eco_findtaxonatrank(taxon,rankindex,tax);
return eco_findtaxonatrank(taxon,rankindex);
}
ecotx_t *eco_getkingdom(ecotx_t *taxon,
@@ -230,7 +307,7 @@ ecotx_t *eco_getkingdom(ecotx_t *taxon,
if (!tax || rankindex < 0)
ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
return eco_findtaxonatrank(taxon,rankindex,tax);
return eco_findtaxonatrank(taxon,rankindex);
}
ecotx_t *eco_getsuperkingdom(ecotx_t *taxon,
@@ -248,5 +325,5 @@ ecotx_t *eco_getsuperkingdom(ecotx_t *taxon,
if (!tax || rankindex < 0)
ECOERROR(ECO_ASSERT_ERROR,"No taxonomy defined");
return eco_findtaxonatrank(taxon,rankindex,tax);
return eco_findtaxonatrank(taxon,rankindex);
}