updated readme; cleaned code

4dn-dcic · Apr 5, 2017 · 3c80792 · 3c80792
1 parent 5204f53
commit 3c80792
Show file tree

Hide file tree

Showing 28 changed files with 36 additions and 34 deletions.
diff --git a/R/px_chr1_col.R b/R/px_chr1_col.R
@@ -12,7 +12,7 @@
 #' res = px_chr1_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_chr1_col(filename)
 #' print(res)
 #'

diff --git a/R/px_chr2_col.R b/R/px_chr2_col.R
@@ -12,7 +12,7 @@
 #' res = px_chr2_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_chr2_col(filename)
 #' print(res)
 #'

diff --git a/R/px_endpos1_col.R b/R/px_endpos1_col.R
@@ -12,7 +12,7 @@
 #' res = px_endpos1_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_endpos1_col(filename)
 #' print(res)
 #'

diff --git a/R/px_endpos2_col.R b/R/px_endpos2_col.R
@@ -12,7 +12,7 @@
 #' res = px_endpos2_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_endpos2_col(filename)
 #' print(res)
 #'

diff --git a/R/px_exists.R b/R/px_exists.R
@@ -13,7 +13,7 @@
 #' res = px_exists(filename, key)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' key = "10|20"
 #' res = px_exists(filename, key)
 #' print(res)

diff --git a/R/px_keylist.R b/R/px_keylist.R
@@ -11,7 +11,7 @@
 #' res = px_keylist(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_keylist(filename)
 #' print(res)
 #'

diff --git a/R/px_query.R b/R/px_query.R
@@ -32,7 +32,7 @@
 #' res = px_query(filename, querystr, autoflip=TRUE)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz", package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz", package="Rpairix")
 #' querystr = "10:1-1000000|20"
 #' res = px_query(filename, querystr)
 #' print(res)

diff --git a/R/px_seq1list.R b/R/px_seq1list.R
@@ -11,7 +11,7 @@
 #' res = px_seq1list(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_seq1list(filename)
 #' print(res)
 px_seq1list<-function(filename){

diff --git a/R/px_seq2list.R b/R/px_seq2list.R
@@ -11,7 +11,7 @@
 #' res = px_seq2list(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_seq2list(filename)
 #' print(res)
 px_seq2list<-function(filename){

diff --git a/R/px_seqlist.R b/R/px_seqlist.R
@@ -11,7 +11,7 @@
 #' res = px_seqlist(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_seqlist(filename)
 #' print(res)
 px_seqlist<-function(filename){

diff --git a/R/px_startpos1_col.R b/R/px_startpos1_col.R
@@ -12,7 +12,7 @@
 #' res = px_startpos1_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_startpos1_col(filename)
 #' print(res)
 #'

diff --git a/R/px_startpos2_col.R b/R/px_startpos2_col.R
@@ -12,7 +12,7 @@
 #' res = px_startpos2_col(filename)
 #' print(res)
 #'
-#' filename = system.file(".","merged_nodup.tab.chrblock_sorted.txt.gz",package="Rpairix")
+#' filename = system.file(".","merged_nodups.space.chrblock_sorted.subsample1.txt.gz",package="Rpairix")
 #' res = px_startpos2_col(filename)
 #' print(res)
 #'

diff --git a/README.md b/README.md
@@ -173,9 +173,9 @@ px_get_column_names(filename)
 > querystr = "chr10:1-3000000|chr20"
 > res = px_query(filename,querystr)
 > print(res)
-                   V1    V2      V3    V4      V5 V6 V7
-1 SRR1658581.51740952 chr10  157600 chr20  167993  -  -
-2 SRR1658581.33457260 chr10 2559777 chr20 7888262  -  +
+               readID  chr1    pos1  chr2    pos2 strand1 strand2
+1 SRR1658581.51740952 chr10  157600 chr20  167993       -       -
+2 SRR1658581.33457260 chr10 2559777 chr20 7888262       -       +
 >
 > # line-count-only
 > n = px_query(filename,querystr, linecount.only=TRUE)
@@ -186,9 +186,9 @@ px_get_column_names(filename)
 > px_query("inst/test_4dn.pairs.gz","chr20|chr10:1-3000000")
 data frame with 0 columns and 0 rows
 > px_query("inst/test_4dn.pairs.gz","chr20|chr10:1-3000000", autoflip=TRUE)
-                   V1    V2      V3    V4      V5 V6 V7
-1 SRR1658581.51740952 chr10  157600 chr20  167993  -  -
-2 SRR1658581.33457260 chr10 2559777 chr20 7888262  -  +
+               readID  chr1    pos1  chr2    pos2 strand1 strand2
+1 SRR1658581.51740952 chr10  157600 chr20  167993       -       -
+2 SRR1658581.33457260 chr10 2559777 chr20 7888262       -       +
 > px_query("inst/test_4dn.pairs.gz","chr20|chr10:1-3000000", linecount.only=TRUE)
 [1] 0
 > px_query("inst/test_4dn.pairs.gz","chr20|chr10:1-3000000", autoflip=TRUE, linecount.only=TRUE)
@@ -238,6 +238,10 @@ data frame with 0 columns and 0 rows
 > # checking if the file is 1D-indexed or 2D-indexed
 > px_check_dim("inst/test_4dn.pairs.gz")
 [1] 2
+>
+> # get column names
+> px_get_column_names("inst/test_4dn.pairs.gz")
+[1] "readID"  "chr1"    "pos1"    "chr2"    "pos2"    "strand1" "strand2"
 ```
 
 

diff --git a/inst/merged_nodup.tab.chrblock_sorted.txt.gz b/inst/merged_nodup.tab.chrblock_sorted.txt.gz
diff --git a/inst/merged_nodup.tab.chrblock_sorted.txt.gz.px2 b/inst/merged_nodup.tab.chrblock_sorted.txt.gz.px2
diff --git a/man/px_chr1_col.Rd b/man/px_chr1_col.Rd
diff --git a/man/px_chr2_col.Rd b/man/px_chr2_col.Rd
diff --git a/man/px_endpos1_col.Rd b/man/px_endpos1_col.Rd
diff --git a/man/px_endpos2_col.Rd b/man/px_endpos2_col.Rd
diff --git a/man/px_exists.Rd b/man/px_exists.Rd
diff --git a/man/px_keylist.Rd b/man/px_keylist.Rd
diff --git a/man/px_query.Rd b/man/px_query.Rd
diff --git a/man/px_seq1list.Rd b/man/px_seq1list.Rd
diff --git a/man/px_seq2list.Rd b/man/px_seq2list.Rd
diff --git a/man/px_seqlist.Rd b/man/px_seqlist.Rd
diff --git a/man/px_startpos1_col.Rd b/man/px_startpos1_col.Rd
diff --git a/man/px_startpos2_col.Rd b/man/px_startpos2_col.Rd
diff --git a/src/rpairixlib.c b/src/rpairixlib.c
@@ -290,10 +290,6 @@ SEXP get_lines(SEXP _r_pfn, SEXP _r_pquerystr, SEXP _r_pnquery, SEXP _r_pn){
    PROTECT(_r_presultstr = allocVector(VECSXP, *pn));
    int flag=0;
 
-   int len=-1;
-   char *s;
-   int k=0;
-
    pairix_t *tb = load(*pfn);
 
    int ncols=0; 
@@ -303,6 +299,8 @@ SEXP get_lines(SEXP _r_pfn, SEXP _r_pquerystr, SEXP _r_pnquery, SEXP _r_pn){
      int i, ires=0;  // i is index for querystr, ires is index for result line
      for(i=0;i<*pnquery;i++){
        ti_iter_t iter = ti_querys_2d(tb, pquerystr[i]);
+       char *s;
+       int len=-1,k=0;
        while ((s = ti_read(tb, iter, &len)) != 0) {
          int j,start=0,m=0; // j is position on result line, start is start position of the current column, m is the index of the current column
          if(ncols==0) for(j=0;j<=len;j++) if(s[j]==pconf->delimiter||s[j]==0) ncols++;