Work at SourceForge, help us to make it a better place! We have an immediate need for a Support Technician in our San Francisco or Denver office.

Close

[1a207b]: inst / @dataframe / private / df_name2idx.m Maximize Restore History

Download this file

df_name2idx.m    135 lines (125 with data), 4.7 kB

  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
function [idx, nelem, subs, mask] = df_name2idx(names, subs, count, dimname, missingOK=false);
%# This is a helper routine to translate rownames or columnames into
%# real index. Input: names, a char array, and subs, a cell array as
%# produced by subsref and similar. This routine can also detect
%# ranges, two values separated by ':'. On output, subs is
%# 'sanitised' from names, and is either a vector, either a single ':'
%% Copyright (C) 2009-2012 Pascal Dupuis <Pascal.Dupuis@uclouvain.be>
%%
%% This file is part of Octave.
%%
%% Octave is free software; you can redistribute it and/or
%% modify it under the terms of the GNU General Public
%% License as published by the Free Software Foundation;
%% either version 2, or (at your option) any later version.
%%
%% Octave is distributed in the hope that it will be useful,
%% but WITHOUT ANY WARRANTY; without even the implied
%% warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
%% PURPOSE. See the GNU General Public License for more
%% details.
%%
%% You should have received a copy of the GNU General Public
%% License along with Octave; see the file COPYING. If not,
%% write to the Free Software Foundation, 51 Franklin Street -
%% Fifth Floor, Boston, MA 02110-1301, USA.
%#
%# $Id$
%#
if (isempty (subs))
%# not caring about rownames ? Avoid generating an error.
idx = []; nelem = 0; return
endif
if (isa (subs, 'char')),
orig_name = subs;
if (1 == size (subs, 1))
if (strcmp(subs, ':')) %# range operator
idx = 1:count; nelem = count;
return
endif
endif
subs = cellstr (subs);
else
if (~isvector(subs))
%# yes/no ?
%# error("Trying to access column as a matrix");
endif
switch (class (subs))
case {"cell"}
orig_name = char (subs);
case {"dataframe"}
orig_name = "elements indexed by a dataframe";
otherwise
orig_name = num2str (subs);
endswitch
endif
if (isa (subs, 'cell'))
subs = subs(:); idx = []; mask = logical (zeros (size (subs, 1), 1));
%# translate list of variables to list of indices
for indi = (1:size (subs, 1))
%# regexp doesn't like empty patterns
if (isempty (subs{indi})) continue; endif
%# convert from standard pattern to regexp pattern
subs{indi} = regexprep (subs{indi}, '([^\.\\])(\*|\?)', "$1.$2");
%# quote repetition ops at begining of line, otherwise the regexp
%# will stall forever/fail
subs{indi} = regexprep (subs{indi}, \
'^([\*\+\?\{\}\|])', "\\$1");
%# detect | followed by EOL
subs{indi} = regexprep (subs{indi}, '([^\\])\|$', "$1\\|");
if (0 == index (subs{indi}, ':'))
%# if there's no special operator, make match strict
if (isempty (regexp (subs{indi}, '[\.\*\+\?\{\}\(\)\[\]\^\$\\]')))
subs{indi} = ['\b' subs{indi} '\b'];
endif
for indj = (1:min (length (names), count)) %# sanity check
if (~isempty (regexp (names{indj}, subs{indi})))
idx = [idx indj]; mask(indi) = true;
endif
endfor
else
dummy = strsplit (subs{indi}, ':');
ind_start = 1;
if (~isempty (dummy{1}))
ind_start = sscanf (dummy{1}, "%d");
if (isempty (ind_start))
ind_start = 1;
for indj = (1:min(length (names), count)) %# sanity check
if (~isempty (regexp (names{indj}, subs{indi}))),
ind_start = indj; break; %# stop at the first match
endif
endfor
endif
endif
if (isempty (dummy{2}) || strcmp (dummy{2}, 'end'))
ind_stop = count;
else
ind_stop = sscanf(dummy{2}, "%d");
if (isempty (ind_stop))
ind_stop = 1;
for indj = (min (length (names), count):-1:1) %# sanity check
if (~isempty (regexp (names{indj}, subs{indi})))
ind_stop = indj; break; %# stop at the last match
endif
endfor
endif
endif
idx = [idx ind_start:ind_stop];
endif
endfor
if (isempty (idx) && ~missingOK)
dummy = sprintf ("Unknown %s name while searching for %s", ...
dimname, orig_name);
error (dummy);
endif
elseif (isa (subs, 'logical'))
idx = 1:length (subs(:)); idx = reshape (idx, size (subs));
idx(~subs) = []; mask = subs;
elseif (isa (subs, 'dataframe'))
idx = subsindex (subs, 1);
else
idx = subs;
endif
subs = idx;
nelem = length (idx);
endfunction