summaryrefslogtreecommitdiffstats
path: root/src/arrow/r/R/feather.R
blob: 70a270bbe0249625957f8d97224c5c4ee51e59f8 (plain)
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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

#' Write data in the Feather format
#'
#' Feather provides binary columnar serialization for data frames.
#' It is designed to make reading and writing data frames efficient,
#' and to make sharing data across data analysis languages easy.
#' This function writes both the original, limited specification of the format
#' and the version 2 specification, which is the Apache Arrow IPC file format.
#'
#' @param x `data.frame`, [RecordBatch], or [Table]
#' @param sink A string file path, URI, or [OutputStream], or path in a file
#' system (`SubTreeFileSystem`)
#' @param version integer Feather file version. Version 2 is the current.
#' Version 1 is the more limited legacy format.
#' @param chunk_size For V2 files, the number of rows that each chunk of data
#' should have in the file. Use a smaller `chunk_size` when you need faster
#' random row access. Default is 64K. This option is not supported for V1.
#' @param compression Name of compression codec to use, if any. Default is
#' "lz4" if LZ4 is available in your build of the Arrow C++ library, otherwise
#' "uncompressed". "zstd" is the other available codec and generally has better
#' compression ratios in exchange for slower read and write performance
#' See [codec_is_available()]. This option is not supported for V1.
#' @param compression_level If `compression` is "zstd", you may
#' specify an integer compression level. If omitted, the compression codec's
#' default compression level is used.
#'
#' @return The input `x`, invisibly. Note that if `sink` is an [OutputStream],
#' the stream will be left open.
#' @export
#' @seealso [RecordBatchWriter] for lower-level access to writing Arrow IPC data.
#' @seealso [Schema] for information about schemas and metadata handling.
#' @examplesIf arrow_available()
#' tf <- tempfile()
#' on.exit(unlink(tf))
#' write_feather(mtcars, tf)
#' @include arrow-package.R
write_feather <- function(x,
                          sink,
                          version = 2,
                          chunk_size = 65536L,
                          compression = c("default", "lz4", "uncompressed", "zstd"),
                          compression_level = NULL) {
  # Handle and validate options before touching data
  version <- as.integer(version)
  assert_that(version %in% 1:2)
  compression <- match.arg(compression)
  chunk_size <- as.integer(chunk_size)
  assert_that(chunk_size > 0)
  if (compression == "default") {
    if (version == 2 && codec_is_available("lz4")) {
      compression <- "lz4"
    } else {
      compression <- "uncompressed"
    }
  }
  if (is.null(compression_level)) {
    # Use -1 as sentinal for "default"
    compression_level <- -1L
  }
  compression_level <- as.integer(compression_level)
  # Now make sure that options make sense together
  if (version == 1) {
    if (chunk_size != 65536L) {
      stop("Feather version 1 does not support the 'chunk_size' option", call. = FALSE)
    }
    if (compression != "uncompressed") {
      stop("Feather version 1 does not support the 'compression' option", call. = FALSE)
    }
    if (compression_level != -1L) {
      stop("Feather version 1 does not support the 'compression_level' option", call. = FALSE)
    }
  }
  if (compression != "zstd" && compression_level != -1L) {
    stop("Can only specify a 'compression_level' when 'compression' is 'zstd'", call. = FALSE)
  }
  # Finally, add 1 to version because 2 means V1 and 3 means V2 :shrug:
  version <- version + 1L

  # "lz4" is the convenience
  if (compression == "lz4") {
    compression <- "lz4_frame"
  }

  compression <- compression_from_name(compression)

  x_out <- x
  if (is.data.frame(x) || inherits(x, "RecordBatch")) {
    x <- Table$create(x)
  }

  assert_that(is_writable_table(x))

  if (!inherits(sink, "OutputStream")) {
    sink <- make_output_stream(sink)
    on.exit(sink$close())
  }
  ipc___WriteFeather__Table(sink, x, version, chunk_size, compression, compression_level)
  invisible(x_out)
}

#' Read a Feather file
#'
#' Feather provides binary columnar serialization for data frames.
#' It is designed to make reading and writing data frames efficient,
#' and to make sharing data across data analysis languages easy.
#' This function reads both the original, limited specification of the format
#' and the version 2 specification, which is the Apache Arrow IPC file format.
#'
#' @inheritParams read_ipc_stream
#' @inheritParams read_delim_arrow
#' @param ... additional parameters, passed to [make_readable_file()].
#'
#' @return A `data.frame` if `as_data_frame` is `TRUE` (the default), or an
#' Arrow [Table] otherwise
#'
#' @export
#' @seealso [FeatherReader] and [RecordBatchReader] for lower-level access to reading Arrow IPC data.
#' @examplesIf arrow_available()
#' tf <- tempfile()
#' on.exit(unlink(tf))
#' write_feather(mtcars, tf)
#' df <- read_feather(tf)
#' dim(df)
#' # Can select columns
#' df <- read_feather(tf, col_select = starts_with("d"))
read_feather <- function(file, col_select = NULL, as_data_frame = TRUE, ...) {
  if (!inherits(file, "RandomAccessFile")) {
    file <- make_readable_file(file, ...)
    on.exit(file$close())
  }
  reader <- FeatherReader$create(file)

  col_select <- enquo(col_select)
  columns <- if (!quo_is_null(col_select)) {
    vars_select(names(reader), !!col_select)
  }

  out <- tryCatch(
    reader$Read(columns),
    error = read_compressed_error
  )

  if (isTRUE(as_data_frame)) {
    out <- as.data.frame(out)
  }
  out
}

#' @title FeatherReader class
#' @rdname FeatherReader
#' @name FeatherReader
#' @docType class
#' @usage NULL
#' @format NULL
#' @description This class enables you to interact with Feather files. Create
#' one to connect to a file or other InputStream, and call `Read()` on it to
#' make an `arrow::Table`. See its usage in [`read_feather()`].
#'
#' @section Factory:
#'
#' The `FeatherReader$create()` factory method instantiates the object and
#' takes the following argument:
#'
#' - `file` an Arrow file connection object inheriting from `RandomAccessFile`.
#'
#' @section Methods:
#'
#' - `$Read(columns)`: Returns a `Table` of the selected columns, a vector of
#'   integer indices
#' - `$column_names`: Active binding, returns the column names in the Feather file
#' - `$schema`: Active binding, returns the schema of the Feather file
#' - `$version`: Active binding, returns `1` or `2`, according to the Feather
#'   file version
#'
#' @export
#' @include arrow-package.R
FeatherReader <- R6Class("FeatherReader",
  inherit = ArrowObject,
  public = list(
    Read = function(columns) {
      ipc___feather___Reader__Read(self, columns)
    },
    print = function(...) {
      cat("FeatherReader:\n")
      print(self$schema)
      invisible(self)
    }
  ),
  active = list(
    # versions are officially 2 for V1 and 3 for V2 :shrug:
    version = function() ipc___feather___Reader__version(self) - 1L,
    column_names = function() names(self$schema),
    schema = function() ipc___feather___Reader__schema(self)
  )
)

#' @export
names.FeatherReader <- function(x) x$column_names

FeatherReader$create <- function(file) {
  assert_is(file, "RandomAccessFile")
  ipc___feather___Reader__Open(file)
}