| |
| R version 3.6.2 Patched (2020-02-12 r77795) -- "Dark and Stormy Night" |
| Copyright (C) 2020 The R Foundation for Statistical Computing |
| Platform: x86_64-pc-linux-gnu (64-bit) |
| |
| R is free software and comes with ABSOLUTELY NO WARRANTY. |
| You are welcome to redistribute it under certain conditions. |
| Type 'license()' or 'licence()' for distribution details. |
| |
| R is a collaborative project with many contributors. |
| Type 'contributors()' for more information and |
| 'citation()' on how to cite R or R packages in publications. |
| |
| Type 'demo()' for some demos, 'help()' for on-line help, or |
| 'help.start()' for an HTML browser interface to help. |
| Type 'q()' to quit R. |
| |
| > ## tests of boundary cases in read.table() |
| > |
| > ## force standard handling for character cols |
| > options(stringsAsFactors=TRUE) |
| > |
| > # empty file |
| > file.create("foo1") |
| [1] TRUE |
| > try(read.table("foo1")) # fails |
| Error in read.table("foo1") : no lines available in input |
| > read.table("foo1", col.names=LETTERS[1:4]) |
| [1] A B C D |
| <0 rows> (or 0-length row.names) |
| > unlink("foo1") |
| > |
| > # header only |
| > cat("head\n", file = "foo2") |
| > read.table("foo2") |
| V1 |
| 1 head |
| > try(read.table("foo2", header=TRUE)) # fails in 1.2.3 |
| [1] head |
| <0 rows> (or 0-length row.names) |
| > unlink("foo2") |
| > # header detection |
| > cat("head\n", 1:2, "\n", 3:4, "\n", file = "foo3") |
| > read.table("foo3", header=TRUE) |
| head |
| 1 2 |
| 3 4 |
| > read.table("foo3", header=TRUE, col.names="V1") |
| V1 |
| 1 2 |
| 3 4 |
| > read.table("foo3", header=TRUE, row.names=1) |
| head |
| 1 2 |
| 3 4 |
| > read.table("foo3", header=TRUE, row.names="row.names") |
| head |
| 1 2 |
| 3 4 |
| > read.table("foo3", header=TRUE, row.names="head") # fails in 1.2.3 |
| row.names |
| 2 1 |
| 4 3 |
| > |
| > # wrong col.names |
| > try(read.table("foo3", header=TRUE, col.names=letters[1:4])) |
| Error in scan(file = file, what = what, sep = sep, quote = quote, dec = dec, : |
| line 1 did not have 4 elements |
| In addition: Warning message: |
| In read.table("foo3", header = TRUE, col.names = letters[1:4]) : |
| header and 'col.names' are of different lengths |
| > unlink("foo3") |
| > |
| > # incomplete last line |
| > cat("head\n", 1:2, "\n", 3:4, file = "foo4") |
| > read.table("foo4", header=TRUE) |
| head |
| 1 2 |
| 3 4 |
| Warning message: |
| In read.table("foo4", header = TRUE) : |
| incomplete final line found by readTableHeader on 'foo4' |
| > unlink("foo4") |
| > |
| > # blank last line |
| > cat("head\n\n", 1:2, "\n", 3:4, "\n\n", file = "foo5") |
| > read.table("foo5", header=TRUE) |
| head |
| 1 2 |
| 3 4 |
| > |
| > # test of fill |
| > read.table("foo5", header=FALSE, fill=TRUE, blank.lines.skip=FALSE) # fails in 1.2.3 |
| V1 V2 |
| 1 head NA |
| 2 NA |
| 3 1 2 |
| 4 3 4 |
| 5 NA |
| > unlink("foo5") |
| > |
| > cat("head\n", 1:2, "\n", 3:5, "\n", 6:9, "\n", file = "foo6") |
| > try(read.table("foo6", header=TRUE)) |
| Error in read.table("foo6", header = TRUE) : |
| more columns than column names |
| > try(read.table("foo6", header=TRUE, fill=TRUE)) |
| Error in read.table("foo6", header = TRUE, fill = TRUE) : |
| more columns than column names |
| > read.table("foo6", header=FALSE, fill=TRUE) |
| V1 V2 V3 V4 |
| 1 head NA NA NA |
| 2 1 2 NA NA |
| 3 3 4 5 NA |
| 4 6 7 8 9 |
| > unlink("foo6") |
| > |
| > # test of type conversion in 1.4.0 and later. |
| > cat("A B C D E F\n", |
| + "1 1 1.1 1.1+0i NA F abc\n", |
| + "2 NA NA NA NA NA NA\n", |
| + "3 1 2 3 NA TRUE def\n", |
| + sep = "", file = "foo7") |
| > (res <- read.table("foo7")) |
| A B C D E F |
| 1 1 1.1 1.1+0i NA FALSE abc |
| 2 NA NA NA NA NA <NA> |
| 3 1 2.0 3.0+0i NA TRUE def |
| > sapply(res, typeof) |
| A B C D E F |
| "integer" "double" "complex" "logical" "logical" "integer" |
| > sapply(res, class) |
| A B C D E F |
| "integer" "numeric" "complex" "logical" "logical" "factor" |
| > (res2 <- read.table("foo7", |
| + colClasses = c("character", rep("numeric", 2), |
| + "complex", "integer", "logical", "character"))) |
| A B C D E F |
| 1 1 1.1 1.1+0i NA FALSE abc |
| 2 NA NA NA NA NA <NA> |
| 3 1 2.0 3.0+0i NA TRUE def |
| > sapply(res2, typeof) |
| A B C D E F |
| "double" "double" "complex" "integer" "logical" "character" |
| > sapply(res2, class) |
| A B C D E F |
| "numeric" "numeric" "complex" "integer" "logical" "character" |
| > unlink("foo7") |
| > |
| > # should be logical |
| > type.convert(character(0)) |
| logical(0) |
| > |
| > # test of comments in data files |
| > cat("# a test file", |
| + "# line 2", |
| + "# line 3", |
| + "# line 4", |
| + "# line 5", |
| + "## now the header", |
| + " a b c", |
| + "# some more comments", |
| + "1 2 3", |
| + "4 5 6# this is the second data row of the file", |
| + " # some more comments", |
| + "7 8 9", |
| + "# trailing comment\n", |
| + file= "ex.data", sep="\n") |
| > read.table("ex.data", header = T) |
| a b c |
| 1 1 2 3 |
| 2 4 5 6 |
| 3 7 8 9 |
| > unlink("ex.data") |
| > |
| > ## comment chars in headers |
| > cat("x1\tx#2\tx3\n1\t2\t2\n2\t3\t3\n", file = "test.dat") |
| > read.table("test.dat", header=T, comment.char="") |
| x1 x.2 x3 |
| 1 1 2 2 |
| 2 2 3 3 |
| > unlink("test.dat") |
| > |
| > cat('#comment\n\n#another\n#\n#\n', |
| + 'C1\tC2\tC3\n"Panel"\t"Area Examined"\t"# Blemishes"\n', |
| + '"1"\t"0.8"\t"3"\n', '"2"\t"0.6"\t"2"\n', '"3"\t"0.8"\t"3"\n', |
| + file = "test.dat", sep="") |
| > read.table("test.dat") |
| V1 V2 V3 |
| 1 C1 C2 C3 |
| 2 Panel Area Examined # Blemishes |
| 3 1 0.8 3 |
| 4 2 0.6 2 |
| 5 3 0.8 3 |
| > unlink("test.dat") |
| > |
| > cat('%comment\n\n%another\n%\n%\n', |
| + 'C1\tC2\tC3\n"Panel"\t"Area Examined"\t"% Blemishes"\n', |
| + '"1"\t"0.8"\t"3"\n', '"2"\t"0.6"\t"2"\n', '"3"\t"0.8"\t"3"\n', |
| + file = "test.dat", sep="") |
| > read.table("test.dat", comment.char = "%") |
| V1 V2 V3 |
| 1 C1 C2 C3 |
| 2 Panel Area Examined % Blemishes |
| 3 1 0.8 3 |
| 4 2 0.6 2 |
| 5 3 0.8 3 |
| > unlink("test.dat") |
| > |
| > ## test on Windows Unicode file |
| > con <- file(file.path(Sys.getenv("SRCDIR"), "WinUnicode.dat"), |
| + encoding="UCS-2LE") |
| > scan(con, 0, quiet=TRUE) |
| [1] 1 2 3 4 5 6 7 8 |
| > close(con) |
| > |
| > ## tests of allowEscape |
| > x <- "1 2 3 \\ab\\c" |
| > writeLines(x, "test.dat") |
| > readLines("test.dat") |
| [1] "1 2 3 \\ab\\c" |
| > scan("test.dat", "", allowEscapes=TRUE) |
| Read 4 items |
| [1] "1" "2" "3" "\abc" |
| > scan("test.dat", "", allowEscapes=FALSE) |
| Read 4 items |
| [1] "1" "2" "3" "\\ab\\c" |
| > read.table("test.dat", header=FALSE, allowEscapes=TRUE) |
| V1 V2 V3 V4 |
| 1 1 2 3 \abc |
| > read.table("test.dat", header=FALSE, allowEscapes=FALSE) |
| V1 V2 V3 V4 |
| 1 1 2 3 \\ab\\c |
| > x <- c("TEST", 1, 2, "\\b", 4, 5, "\\040", "\\x20", |
| + "c:\\spencer\\tests", |
| + "\\t", "\\n", "\\r") |
| > writeLines(x, "test.dat") |
| > read.table("test.dat", allowEscapes=FALSE, header = TRUE) |
| TEST |
| 1 1 |
| 2 2 |
| 3 \\b |
| 4 4 |
| 5 5 |
| 6 \\040 |
| 7 \\x20 |
| 8 c:\\spencer\\tests |
| 9 \\t |
| 10 \\n |
| 11 \\r |
| > unlink("test.dat") |
| > ## end of tests |
| > |
