fix in read.dna and change in write.dna

[ape.git] / R / read.GenBank.R

diff --git a/R/read.GenBank.R b/R/read.GenBank.R
index e84213b895351736dea0061c0c7579b357cba6c6..23bf4db16773a0878373f11e73ef0046c8ab8c1e 100644 (file)
--- a/R/read.GenBank.R
+++ b/R/read.GenBank.R
@@ -1,14 +1,15 @@
-## read.GenBank.R (2007-06-27)
+## read.GenBank.R (2012-02-17)
 
 ##   Read DNA Sequences from GenBank via Internet
 
-## Copyright 2002-2007 Emmanuel Paradis
+## Copyright 2002-2012 Emmanuel Paradis
 
 ## This file is part of the R-package `ape'.
 ## See the file ../COPYING for licensing issues.
 
-read.GenBank <- function(access.nb, seq.names = access.nb,
-                         species.names = TRUE, as.character = FALSE)
+read.GenBank <-
+    function(access.nb, seq.names = access.nb, species.names = TRUE,
+             gene.names = FALSE, as.character = FALSE)
 {
     N <- length(access.nb)
     ## If there are more than 400 sequences, we need to break down the
@@ -21,13 +22,12 @@ read.GenBank <- function(access.nb, seq.names = access.nb,
         if (i == nrequest) b <- N
         URL <- paste("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=",
                      paste(access.nb[a:b], collapse = ","),
-                     "&rettype=gb", sep = "")
+                     "&rettype=gb&retmode=text", sep = "")
         X <- c(X, scan(file = URL, what = "", sep = "\n", quiet = TRUE))
     }
     FI <- grep("^ {0,}ORIGIN", X) + 1
     LA <- which(X == "//") - 1
-    obj <- list()
-    length(obj) <- N
+    obj <- vector("list", N)
     for (i in 1:N) {
         ## remove all spaces and digits
         tmp <- gsub("[[:digit:] ]", "", X[FI[i]:LA[i]])
@@ -39,8 +39,15 @@ read.GenBank <- function(access.nb, seq.names = access.nb,
         tmp <- character(N)
         sp <- grep("ORGANISM", X)
         for (i in 1:N)
-          tmp[i] <- unlist(strsplit(X[sp[i]], " +ORGANISM +"))[2]
+            tmp[i] <- unlist(strsplit(X[sp[i]], " +ORGANISM +"))[2]
         attr(obj, "species") <- gsub(" ", "_", tmp)
     }
+    if (gene.names) {
+        tmp <- character(N)
+        sp <- grep(" +gene +<", X)
+        for (i in 1:N)
+            tmp[i] <- unlist(strsplit(X[sp[i + 1L]], " +/gene=\""))[2]
+        attr(obj, "gene") <- gsub("\"$", "", tmp)
+    }
     obj
 }