1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
## write.nexus.data.R (2018-06-23)
## Write Character Data in NEXUS Format
## Copyright 2006-2015 Johan Nylander, Emmanuel Paradis, 2018 Thomas Guillerme
## This file is part of the R-package `ape'.
## See the file ../COPYING for licensing issues.
write.nexus.data <-
function(x, file, format = "dna", datablock = TRUE,
interleaved = TRUE, charsperline = NULL,
gap = NULL, missing = NULL)
{
### TODO: Standard data, mixed data, nice indent
format <- match.arg(toupper(format), c("DNA", "PROTEIN", "STANDARD", "CONTINUOUS"))
if (inherits(x, "DNAbin") && format != "DNA") {
format <- "DNA"
warning("object 'x' is of class DNAbin: format forced to DNA")
}
if (inherits(x, "AAbin") && format != "PROTEIN") {
format <- "PROTEIN"
warning("object 'x' is of class AAbin: format forced to PROTEIN")
}
indent <- " " # Two blanks
maxtax <- 5 # Max nr of taxon names to be printed on a line
defcharsperline <- 80 # Default nr of characters per line if interleaved
defgap <- "-" # Default gap character
defmissing <- "?" # Default missing data character
if (is.matrix(x)) {
if (inherits(x, "DNAbin")) x <- as.list(x) else {
xbak <- x
x <- vector("list", nrow(xbak))
for (i in seq_along(x)) x[[i]] <- xbak[i, ]
names(x) <- rownames(xbak)
rm(xbak)
}
}
ntax <- length(x)
nchars <- length(x[[1]])
zz <- file(file, "w")
if (is.null(names(x))) names(x) <- as.character(1:ntax)
fcat <- function(..., file = zz)
cat(..., file = file, sep = "", append = TRUE)
find.max.length <- function(x) max(nchar(x))
print.matrix <- function(x, dindent = " ", collapse = "") {
Names <- names(x)
printlength <- find.max.length(Names) + 2
if (!interleaved) {
for (i in seq_along(x)) {
sequence <- paste(x[[i]], collapse = collapse)
taxon <- Names[i]
thestring <- sprintf("%-*s%s%s", printlength, taxon, dindent, sequence)
fcat(indent, indent, thestring, "\n")
}
} else {
ntimes <- ceiling(nchars/charsperline)
start <- 1
end <- charsperline
for (j in seq_len(ntimes)) {
for (i in seq_along(x)) {
sequence <- paste(x[[i]][start:end], collapse = collapse)
taxon <- Names[i]
thestring <- sprintf("%-*s%s%s", printlength, taxon, dindent, sequence)
fcat(indent, indent, thestring, "\n")
}
if (j < ntimes) fcat("\n")
start <- start + charsperline
end <- end + charsperline
if (end > nchars) end <- nchars
}
}
}
if (inherits(x, "DNAbin") || inherits(x, "AAbin")) x <- as.character(x)
fcat("#NEXUS\n[Data written by write.nexus.data.R, ", date(), "]\n")
NCHAR <- paste("NCHAR=", nchars, sep = "")
NTAX <- paste0("NTAX=", ntax)
DATATYPE <- paste0("DATATYPE=", format) # fix by Robin Cristofari (2015-02-04)
if (is.null(charsperline)) {
if (nchars <= defcharsperline) {
charsperline <- nchars
interleaved <- FALSE
} else charsperline <- defcharsperline
}
if (is.null(missing)) missing <- defmissing
MISSING <- paste0("MISSING=", missing)
if (is.null(gap)) gap <- defgap
GAP <- paste0("GAP=", gap)
INTERLEAVE <- if (interleaved) "INTERLEAVE=YES" else "INTERLEAVE=NO"
if (datablock) {
fcat("BEGIN DATA;\n")
fcat(indent, "DIMENSIONS ", NTAX, " ", NCHAR, ";\n")
## <FIXME> only DNA and PROTEIN is supported for the moment, so the
## following 'if' is not needed
## if (format %in% c("DNA", "PROTEIN")) # from Francois Michonneau (2009-10-02)
if(format != "STANDARD") {
fcat(indent, "FORMAT", " ", DATATYPE, " ", MISSING, " ", GAP, " ", INTERLEAVE, ";\n")
} else {
fcat(indent, "FORMAT", " ", DATATYPE, " ", MISSING, " ", GAP, " ", INTERLEAVE, " symbols=\"0123456789\";\n")
}
## </FIXME>
fcat(indent, "MATRIX\n")
if(format != "CONTINUOUS") {
print.matrix(x)
} else {
print.matrix(x, collapse = "\t")
}
fcat(indent, ";\nEND;\n\n")
} else {
fcat("BEGIN TAXA;\n")
fcat(indent, "DIMENSIONS", " ", NTAX, ";\n")
fcat(indent, "TAXLABELS\n")
fcat(indent, indent)
j <- 0
for (i in seq_len(ntax)) {
fcat(names(x[i]), " ")
j <- j + 1
if (j == maxtax) {
fcat("\n", indent, indent)
j <- 0
}
}
fcat("\n", indent, ";\n")
fcat("END;\n\nBEGIN CHARACTERS;\n")
fcat(indent, "DIMENSIONS", " ", NCHAR, ";\n")
## <FIXME> only DNA and PROTEIN is supported for the moment, so the
## following 'if' is not needed
## if (format %in% c("DNA", "PROTEIN"))
if(format != "STANDARD") {
fcat(indent, "FORMAT", " ", MISSING, " ", GAP, " ", DATATYPE, " ", INTERLEAVE, ";\n")
} else {
fcat(indent, "FORMAT", " ", MISSING, " ", GAP, " ", DATATYPE, " ", INTERLEAVE, " symbols=\"0123456789\";\n")
}
## </FIXME>
fcat(indent,"MATRIX\n")
if(format != "CONTINUOUS") {
print.matrix(x)
} else {
print.matrix(x, collapse = "\t")
}
fcat(indent, ";\nEND;\n\n")
}
close(zz)
}
|
