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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
|
#' Compare two character vectors elementwise
#'
#' Its printed output is similar to calling `diff -u` at the command
#' line.
#'
#' @param old First character vector.
#' @param new Second character vector.
#' @param max_dist Maximum distance to consider, or `Inf` for no limit.
#' If the LCS edit distance is larger than this, then the function
#' throws an error with class `"cli_diff_max_dist"`. (If you specify
#' `Inf` the real limit is `.Machine$integer.max` but to reach this the
#' function would have to run a very long time.)
#' @return A list that is a `cli_diff_chr` object, with a `format()` and a
#' `print()` method. You can also access its members:
#' * `old` and `new` are the original inputs,
#' * `lcs` is a data frame of LCS edit that transform `old` into `new`.
#'
#' The `lcs` data frame has the following columns:
#' * `operation`: one of `"match"`, `"delete"` or `"insert"`.
#' * `offset`: offset in `old` for matches and deletions, offset in `new`
#' for insertions.
#' * `length`: length of the operation, i.e. number of matching, deleted
#' or inserted elements.
#' * `old_offset`: offset in `old` _after_ the operation.
#' * `new_offset`: offset in `new` _after_ the operation.
#'
#' @family diff functions in cli
#' @seealso The diffobj package for a much more comprehensive set of
#' `diff`-like tools.
#' @export
#' @examples
#' letters2 <- c("P", "R", "E", letters, "P", "O", "S", "T")
#' letters2[11:16] <- c("M", "I", "D", "D", "L", "E")
#' diff_chr(letters, letters2)
diff_chr <- function(old, new, max_dist = Inf) {
stopifnot(
is.character(old),
is.character(new),
max_dist == Inf || is_count(max_dist)
)
max_dist2 <- as_max_dist(max_dist)
lcs <- .Call(clic_diff_chr, old, new, max_dist2)
if (max_dist2 != 0 && lcs[[4]] == max_dist2) {
throw(cli_error(
"Diff edit distance is larger than the limit.",
"i" = "The edit distance limit is {max_dist}.",
.data = list(max_dist = max_dist),
.class = "cli_diff_max_dist"
))
}
op <- c("match", "delete", "insert")[lcs[[1]]]
lcs <- data.frame(
stringsAsFactors = FALSE,
operation = op,
offset = lcs[[2]],
length = lcs[[3]],
old_offset = cumsum(ifelse(op == "insert", 0, lcs[[3]])),
new_offset = cumsum(ifelse(op == "delete", 0, lcs[[3]]))
)
ret <- structure(
list(old = old, new = new, lcs = lcs),
class = c("cli_diff_chr", "cli_diff", "list")
)
ret
}
#' Compare two character strings, character by character
#'
#' Characters are defined by UTF-8 graphemes.
#'
#' @param old First string, must not be `NA`.
#' @param new Second string, must not be `NA`.
#' @inheritParams diff_chr
#' @return A list that is a `cli_diff_str` object and also a
#' `cli_diff_chr` object, see [diff_str] for the details about its
#' structure.
#'
#' @family diff functions in cli
#' @seealso The diffobj package for a much more comprehensive set of
#' `diff`-like tools.
#'
#' @export
#' @examples
#' str1 <- "abcdefghijklmnopqrstuvwxyz"
#' str2 <- "PREabcdefgMIDDLEnopqrstuvwxyzPOST"
#' diff_str(str1, str2)
diff_str <- function(old, new, max_dist = Inf) {
stopifnot(
is_string(old),
is_string(new)
# max_dist is checked in diff_chr
)
old1 <- utf8_graphemes(old)[[1]]
new1 <- utf8_graphemes(new)[[1]]
ret <- diff_chr(old1, new1, max_dist)
class(ret) <- c("cli_diff_str", class(ret))
ret
}
#' @export
format.cli_diff_chr <- function(x, context = 3L, ...) {
stopifnot(context == Inf || is_count(context))
if (length(list(...)) > 0) {
warning("Extra arguments were ignored in `format.cli_diff_chr()`.")
}
chunks <- get_diff_chunks(x$lcs, context = context)
out <- lapply(
seq_len(nrow(chunks)),
format_chunk,
x = x,
chunks = chunks,
context = context
)
ret <- as.character(unlist(out))
if (context == Inf && length(ret) > 0) ret <- ret[-1]
ret
}
get_diff_chunks <- function(lcs, context = 3L) {
# the number of chunks is the number of non-matching sequences if
# context == 0, but short matching parts do not separate chunks
runs <- rle(lcs$operation != "match" | lcs$length <= 2 * context)
nchunks <- sum(runs$values)
# special case for a single match chunk
if (nrow(lcs) == 1 && lcs$operation == "match") {
nchunks <- if (context == Inf) 1 else 0
}
chunks <- data.frame(
op_begin = integer(nchunks), # first op in chunk
op_length = integer(nchunks), # number of operations in chunk
old_begin = integer(nchunks), # first line from `old` in chunk
old_length = integer(nchunks), # number of lines from `old` in chunk
new_begin = integer(nchunks), # first line from `new` in chunk
new_length = integer(nchunks) # number of lines from `new` in chunk
)
if (nchunks == 0) return(chunks)
# infer some data about the original diff input
old_off <- c(0, lcs$old_offset)
new_off <- c(0, lcs$new_offset)
old_size <- old_off[length(old_off)]
new_size <- new_off[length(new_off)]
old_empty <- old_size == 0
new_empty <- new_size == 0
# avoid working with Inf
if (context == Inf) context <- max(old_size, new_size)
# chunk starts at operation number sum(length) before it, plus 1, but
# at the end we change this to include the context chunks are well
chunks$op_begin <- c(0, cumsum(runs$lengths))[which(runs$values)] + 1
chunks$op_length <- runs$lengths[runs$values]
# `old` positions are from `old_off`, but need to fix the boundaries
chunks$old_begin <- old_off[chunks$op_begin] - context + 1
chunks$old_begin[chunks$old_begin <= 1] <- if (old_empty) 0 else 1
old_end <- old_off[chunks$op_begin + chunks$op_length] + context
old_end[old_end > old_size] <- old_size
chunks$old_length <- old_end - chunks$old_begin + 1
# `new` positions are similar
chunks$new_begin <- new_off[chunks$op_begin] - context + 1
chunks$new_begin[chunks$new_begin <= 1] <- if (new_empty) 0 else 1
new_end <- new_off[chunks$op_begin + chunks$op_length] + context
new_end[new_end > new_size] <- new_size
chunks$new_length <- new_end - chunks$new_begin + 1
# change to include context chunks
if (context > 0) {
# calculae the end before updating the begin
op_end <- chunks$op_begin + chunks$op_length - 1 + 1
op_end[op_end > nrow(lcs)] <- nrow(lcs)
chunks$op_begin <- chunks$op_begin - 1
chunks$op_begin[chunks$op_begin == 0] <- 1
chunks$op_length <- op_end - chunks$op_begin + 1
}
chunks
}
format_chunk <- function(x, chunks, num, context) {
hdr <- paste0(
"@@ -",
chunks$old_begin[num],
if ((l <- chunks$old_length[num]) != 1) paste0(",", l),
" +",
chunks$new_begin[num],
if ((l <- chunks$new_length[num]) != 1) paste0(",", l),
" @@"
)
from <- chunks$op_begin[num]
to <- chunks$op_begin[num] + chunks$op_length[num] - 1
lines <- lapply(from:to, function(i) {
op <- x$lcs$operation[i]
off <- x$lcs$offset[i]
len <- x$lcs$length[i]
if (op == "match") {
if (len > context) {
if (i == from) {
# start later
off <- off + len - context
len <- context
} else {
# finish earlier
len <- context
}
}
paste0(" ", x$old[off + 1:len])
} else if (op == "delete") {
col_blue(paste0("-", x$old[off + 1:len]))
} else if (op == "insert") {
col_green(paste0("+", x$new[off + 1:len]))
}
})
c(hdr, lines)
}
#' @export
print.cli_diff_chr <- function(x, ...) {
writeLines(format(x, ...))
}
#' @export
format.cli_diff_str <- function(x, ...) {
if (length(list(...)) > 0) {
warning("Extra arguments were ignored in `format.cli_diff_chr()`.")
}
if (num_ansi_colors() == 1) {
format_diff_str_nocolor(x, ...)
} else {
format_diff_str_color(x, ...)
}
}
format_diff_str_color <- function(x, ...) {
out <- lapply(seq_len(nrow(x$lcs)), function(i) {
op <- x$lcs$operation[i]
off <- x$lcs$offset[i]
len <- x$lcs$length[i]
if (op == "match") {
paste0(x$old[off + 1:len], collapse = "")
} else if (op == "delete") {
bg_blue(col_black(paste0(x$old[off + 1:len], collapse = "")))
} else if (op == "insert") {
bg_green(col_black(paste0(x$new[off + 1:len], collapse = "")))
}
})
paste(out, collapse = "")
}
format_diff_str_nocolor <- function(x, ...) {
out <- lapply(seq_len(nrow(x$lcs)), function(i) {
op <- x$lcs$operation[i]
off <- x$lcs$offset[i]
len <- x$lcs$length[i]
if (op == "match") {
paste0(x$old[off + 1:len], collapse = "")
} else if (op == "delete") {
paste0(c("[-", x$old[off + 1:len], "-]"), collapse = "")
} else if (op == "insert") {
paste0(c("{+", x$new[off + 1:len], "+}"), collapse = "")
}
})
paste(out, collapse = "")
}
as_max_dist <- function(max_dist) {
if (max_dist == Inf) {
0L
} else {
as.integer(max_dist + 1L)
}
}
|