Mercurial > hg > octave-lyh
annotate scripts/io/textscan.m @ 11191:01ddaedd6ad5
Reverse changeset b1f4bdc276b6. Use all lower case for "uniformoutput" option.
| author | Rik <octave@nomad.inbox5.com> |
|---|---|
| date | Thu, 04 Nov 2010 12:18:08 -0700 |
| parents | 224c80da37c5 |
| children | c776f063fefe |
| rev | line source |
|---|---|
| 11141 | 1 ## Copyright (C) 2010 Ben Abbott <bpabbott@mac.com> |
| 2 ## | |
| 3 ## This file is part of Octave. | |
| 4 ## | |
| 5 ## Octave is free software; you can redistribute it and/or modify it | |
| 6 ## under the terms of the GNU General Public License as published by | |
| 7 ## the Free Software Foundation; either version 3 of the License, or (at | |
| 8 ## your option) any later version. | |
| 9 ## | |
| 10 ## Octave is distributed in the hope that it will be useful, but | |
| 11 ## WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 12 ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 13 ## General Public License for more details. | |
| 14 ## | |
| 15 ## You should have received a copy of the GNU General Public License | |
| 16 ## along with Octave; see the file COPYING. If not, see | |
| 17 ## <http://www.gnu.org/licenses/>. | |
| 18 | |
| 19 ## -*- texinfo -*- | |
| 20 ## @deftypefn {Function File} {@var{c} =} textscan (@var{fid}, @var{format}) | |
| 21 ## @deftypefnx {Function File} {@var{c} =} textscan (@var{fid}, @var{format}, @ | |
| 22 ## @var{n}) | |
| 23 ## @deftypefnx {Function File} {@var{c} =} textscan (@var{fid}, @var{format}, @ | |
| 24 ## @var{param}, @var{value}, @dots{}) | |
| 25 ## @deftypefnx {Function File} {@var{c} =} textscan (@var{fid}, @var{format}, @ | |
| 26 ## @var{n}, @var{param}, @var{value}, @dots{}) | |
| 27 ## @deftypefnx {Function File} {@var{a} =} textscan (@var{str}, @dots{}) | |
| 28 ## @deftypefnx {Function File} {[@var{a}, @var{position}] =} textscan (@dots{}) | |
| 29 ## Read data from a text file. | |
| 30 ## | |
| 31 ## The file associated with @var{fid} is read and parsed according to @var{format}. | |
| 32 ## The function behaves like @code{strread} except it works by parsing a file | |
| 33 ## instead of a string. See the documentation of @code{strread} for details. | |
| 34 ## In addition to the options supported by @code{strread}, this function | |
| 35 ## supports one more: | |
| 36 ## @itemize | |
| 37 ## @item "headerlines": | |
| 38 ## @end itemize | |
| 39 ## The first @var{value} number of lines of @var{str} are skipped. | |
| 40 ## | |
| 41 ## The optional input, @var{n}, specifes the number of lines to be read from | |
| 42 ## the file, associated with @var{fid}. | |
| 43 ## | |
| 44 ## The output, @var{c}, is a cell array whose length is given by the number | |
| 45 ## of format specifiers. | |
| 46 ## | |
| 47 ## The second output, @var{position}, provides the position, in characters, | |
| 48 ## from the beginning of the file. | |
| 49 ## | |
| 50 ## @seealso{dlmread, fscanf, load, strread, textread} | |
| 51 ## @end deftypefn | |
| 52 | |
| 53 function [c, p] = textscan (fid, formatstr, varargin) | |
| 54 | |
| 55 ## Check input | |
| 56 if (nargin < 1) | |
| 57 print_usage (); | |
| 58 elseif (nargin == 1 || isempty (formatstr)) | |
| 59 formatstr = "%f"; | |
| 60 endif | |
| 61 | |
| 62 if (nargin > 2 && isnumeric (varargin{1})) | |
| 63 nlines = varargin{1}; | |
| 64 args = varargin(2:end); | |
| 65 else | |
| 66 nlines = Inf; | |
| 67 args = varargin; | |
| 68 endif | |
| 69 | |
| 70 if (! any (strcmpi (args, "emptyvalue"))) | |
| 71 ## Matlab returns NaNs for missing values | |
| 72 args{end+1} = "emptyvalue"; | |
| 73 args{end+1} = NaN; | |
| 74 endif | |
| 75 | |
| 76 if (isa (fid, "double") && fid > 0 || ischar (fid)) | |
| 77 if (ischar (formatstr)) | |
| 78 if (ischar (fid)) | |
| 79 if (nargout == 2) | |
| 80 error ("textscan: cannot provide postion information for character input") | |
| 81 endif | |
| 82 str = fid; | |
| 83 else | |
| 84 ## Maybe skip header lines | |
| 85 headerlines = find (strcmpi (args, "headerlines"), 1); | |
| 86 if (! isempty (headerlines)) | |
| 87 fskipl (fid, headerlines); | |
| 88 args(headerlines:headerlines+1) = []; | |
| 89 endif | |
| 90 if (isfinite (nlines)) | |
| 91 str = ""; | |
| 92 for n = 1:nlines | |
| 93 str = strcat (str, fgets (fid)); | |
| 94 endfor | |
| 95 else | |
| 96 str = fread (fid, "char=>char").'; | |
| 97 endif | |
| 98 endif | |
| 99 | |
| 100 ## Determine the number of data fields | |
| 101 num_fields = numel (strfind (formatstr, "%")) - ... | |
| 102 numel (idx_star = strfind (formatstr, "%*")); | |
| 103 | |
| 104 ## Call strread to make it do the real work | |
| 105 c = cell (1, num_fields); | |
| 106 [c{:}] = strread (str, formatstr, args{:}); | |
| 107 | |
| 108 if (ischar (fid) && isfinite (nlines)) | |
|
11191
01ddaedd6ad5
Reverse changeset b1f4bdc276b6. Use all lower case for "uniformoutput" option.
Rik <octave@nomad.inbox5.com>
parents:
11141
diff
changeset
|
109 c = cellfun (@(x) x(1:nlines), c, "uniformoutput", false); |
| 11141 | 110 endif |
| 111 | |
| 112 if (nargout == 2) | |
| 113 p = ftell (fid); | |
| 114 endif | |
| 115 | |
| 116 else | |
| 117 error ("textscan: second input must be a format specification"); | |
| 118 endif | |
| 119 else | |
| 120 error ("textscan: expecting first argument to be a file id or character string"); | |
| 121 endif | |
| 122 | |
| 123 endfunction | |
| 124 | |
| 125 %!test | |
| 126 %! str = "1, 2, 3, 4\n 5, , , 8\n 9, 10, 11, 12"; | |
| 127 %! fmtstr = "%f %d %f %s"; | |
| 128 %! c = textscan (str, fmtstr, 2, "delimiter", ",", "emptyvalue", -Inf); | |
| 129 %! assert (isequal (c{1}, [1;5])) | |
| 130 %! assert (length (c{1}), 2); | |
| 131 %! assert (iscellstr (c{4})) | |
| 132 %! assert (isequal (c{3}, [3; -Inf])) | |
| 133 | |
| 134 %!test | |
| 135 %! b = [10:10:100]; | |
| 136 %! b = [b; 8*b/5]; | |
| 137 %! str = sprintf ("%g miles/hr = %g kilometers/hr\n", b); | |
| 138 %! fmt = "%f miles/hr = %f kilometers/hr"; | |
| 139 %! c = textscan (str, fmt); | |
| 140 %! assert (b(1,:)', c{1}) | |
| 141 %! assert (b(2,:)', c{2}) | |
| 142 | |
| 143 |