view scripts/strings/validatestring.m @ 14363:f3d52523cde1

Use Octave coding conventions in all m-file %!test blocks * wavread.m, acosd.m, acot.m, acotd.m, acoth.m, acsc.m, acscd.m, acsch.m, asec.m, asecd.m, asech.m, asind.m, atand.m, cosd.m, cot.m, cotd.m, coth.m, csc.m, cscd.m, csch.m, sec.m, secd.m, sech.m, sind.m, tand.m, accumarray.m, accumdim.m, bitcmp.m, bitget.m, bitset.m, blkdiag.m, cart2pol.m, cart2sph.m, celldisp.m, chop.m, circshift.m, colon.m, common_size.m, cplxpair.m, cumtrapz.m, curl.m, dblquad.m, deal.m, divergence.m, flipdim.m, fliplr.m, flipud.m, genvarname.m, gradient.m, idivide.m, int2str.m, interp1.m, interp1q.m, interp2.m, interp3.m, interpft.m, interpn.m, isa.m, isdir.m, isequal.m, isequalwithequalnans.m, issquare.m, logspace.m, nargchk.m, narginchk.m, nargoutchk.m, nextpow2.m, nthargout.m, num2str.m, pol2cart.m, polyarea.m, postpad.m, prepad.m, profile.m, profshow.m, quadgk.m, quadv.m, randi.m, rat.m, repmat.m, rot90.m, rotdim.m, shift.m, shiftdim.m, sph2cart.m, structfun.m, trapz.m, triplequad.m, convhull.m, dsearch.m, dsearchn.m, griddata3.m, griddatan.m, rectint.m, tsearchn.m, __makeinfo__.m, doc.m, get_first_help_sentence.m, help.m, type.m, unimplemented.m, which.m, imread.m, imwrite.m, dlmwrite.m, fileread.m, is_valid_file_id.m, strread.m, textread.m, textscan.m, commutation_matrix.m, cond.m, condest.m, cross.m, duplication_matrix.m, expm.m, housh.m, isdefinite.m, ishermitian.m, issymmetric.m, logm.m, normest.m, null.m, onenormest.m, orth.m, planerot.m, qzhess.m, rank.m, rref.m, trace.m, vech.m, ans.m, bincoeff.m, bug_report.m, bzip2.m, comma.m, compare_versions.m, computer.m, edit.m, fileparts.m, fullfile.m, getfield.m, gzip.m, info.m, inputname.m, isappdata.m, isdeployed.m, ismac.m, ispc.m, isunix.m, list_primes.m, ls.m, mexext.m, namelengthmax.m, news.m, orderfields.m, paren.m, recycle.m, rmappdata.m, semicolon.m, setappdata.m, setfield.m, substruct.m, symvar.m, ver.m, version.m, warning_ids.m, xor.m, fminbnd.m, fsolve.m, fzero.m, lsqnonneg.m, optimset.m, pqpnonneg.m, sqp.m, matlabroot.m, __gnuplot_drawnow__.m, __plt_get_axis_arg__.m, ancestor.m, cla.m, clf.m, close.m, colorbar.m, colstyle.m, comet3.m, contourc.m, figure.m, gca.m, gcbf.m, gcbo.m, gcf.m, ginput.m, graphics_toolkit.m, gtext.m, hggroup.m, hist.m, hold.m, isfigure.m, ishghandle.m, ishold.m, isocolors.m, isonormals.m, isosurface.m, isprop.m, legend.m, line.m, loglog.m, loglogerr.m, meshgrid.m, ndgrid.m, newplot.m, orient.m, patch.m, plot3.m, plotyy.m, __print_parse_opts__.m, quiver3.m, refreshdata.m, ribbon.m, semilogx.m, semilogxerr.m, semilogy.m, stem.m, stem3.m, subplot.m, title.m, uigetfile.m, view.m, whitebg.m, compan.m, conv.m, deconv.m, mkpp.m, mpoles.m, pchip.m, poly.m, polyaffine.m, polyder.m, polyfit.m, polygcd.m, polyint.m, polyout.m, polyval.m, polyvalm.m, ppder.m, ppint.m, ppjumps.m, ppval.m, residue.m, roots.m, spline.m, intersect.m, ismember.m, powerset.m, setdiff.m, setxor.m, union.m, unique.m, autoreg_matrix.m, bartlett.m, blackman.m, detrend.m, fftconv.m, fftfilt.m, fftshift.m, freqz.m, hamming.m, hanning.m, ifftshift.m, sinc.m, sinetone.m, sinewave.m, unwrap.m, bicg.m, bicgstab.m, gmres.m, gplot.m, nonzeros.m, pcg.m, pcr.m, spaugment.m, spconvert.m, spdiags.m, speye.m, spfun.m, spones.m, sprand.m, sprandsym.m, spstats.m, spy.m, svds.m, treelayout.m, bessel.m, beta.m, betaln.m, factor.m, factorial.m, isprime.m, lcm.m, legendre.m, nchoosek.m, nthroot.m, perms.m, pow2.m, primes.m, reallog.m, realpow.m, realsqrt.m, hadamard.m, hankel.m, hilb.m, invhilb.m, magic.m, rosser.m, vander.m, __finish__.m, center.m, cloglog.m, corr.m, cov.m, gls.m, histc.m, iqr.m, kendall.m, kurtosis.m, logit.m, mahalanobis.m, mean.m, meansq.m, median.m, mode.m, moment.m, ols.m, ppplot.m, prctile.m, probit.m, quantile.m, range.m, ranks.m, run_count.m, runlength.m, skewness.m, spearman.m, statistics.m, std.m, table.m, var.m, zscore.m, betacdf.m, betainv.m, betapdf.m, betarnd.m, binocdf.m, binoinv.m, binopdf.m, binornd.m, cauchy_cdf.m, cauchy_inv.m, cauchy_pdf.m, cauchy_rnd.m, chi2cdf.m, chi2inv.m, chi2pdf.m, chi2rnd.m, discrete_cdf.m, discrete_inv.m, discrete_pdf.m, discrete_rnd.m, empirical_cdf.m, empirical_inv.m, empirical_pdf.m, empirical_rnd.m, expcdf.m, expinv.m, exppdf.m, exprnd.m, fcdf.m, finv.m, fpdf.m, frnd.m, gamcdf.m, gaminv.m, gampdf.m, gamrnd.m, geocdf.m, geoinv.m, geopdf.m, geornd.m, hygecdf.m, hygeinv.m, hygepdf.m, hygernd.m, kolmogorov_smirnov_cdf.m, laplace_cdf.m, laplace_inv.m, laplace_pdf.m, laplace_rnd.m, logistic_cdf.m, logistic_inv.m, logistic_pdf.m, logistic_rnd.m, logncdf.m, logninv.m, lognpdf.m, lognrnd.m, nbincdf.m, nbininv.m, nbinpdf.m, nbinrnd.m, normcdf.m, norminv.m, normpdf.m, normrnd.m, poisscdf.m, poissinv.m, poisspdf.m, poissrnd.m, stdnormal_cdf.m, stdnormal_inv.m, stdnormal_pdf.m, stdnormal_rnd.m, tcdf.m, tinv.m, tpdf.m, trnd.m, unidcdf.m, unidinv.m, unidpdf.m, unidrnd.m, unifcdf.m, unifinv.m, unifpdf.m, unifrnd.m, wblcdf.m, wblinv.m, wblpdf.m, wblrnd.m, kolmogorov_smirnov_test.m, kruskal_wallis_test.m, base2dec.m, bin2dec.m, blanks.m, cstrcat.m, deblank.m, dec2base.m, dec2bin.m, dec2hex.m, findstr.m, hex2dec.m, index.m, isletter.m, mat2str.m, rindex.m, str2num.m, strcat.m, strjust.m, strmatch.m, strsplit.m, strtok.m, strtrim.m, strtrunc.m, substr.m, validatestring.m, demo.m, example.m, fail.m, speed.m, addtodate.m, asctime.m, clock.m, ctime.m, date.m, datenum.m, datetick.m, datevec.m, eomday.m, etime.m, is_leap_year.m, now.m: Use Octave coding conventions in all m-file %!test blocks
author Rik <octave@nomad.inbox5.com>
date Mon, 13 Feb 2012 07:29:44 -0800
parents 72c96de7a403
children bc924baa2c4e
line wrap: on
line source

## Copyright (C) 2008-2012 Bill Denney
##
## 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 3 of the License, 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, see
## <http://www.gnu.org/licenses/>.

## -*- texinfo -*-
## @deftypefn  {Function File} {@var{validstr} =} validatestring (@var{str}, @var{strarray})
## @deftypefnx {Function File} {@var{validstr} =} validatestring (@var{str}, @var{strarray}, @var{funcname})
## @deftypefnx {Function File} {@var{validstr} =} validatestring (@var{str}, @var{strarray}, @var{funcname}, @var{varname})
## @deftypefnx {Function File} {@var{validstr} =} validatestring (@dots{}, @var{position})
## Verify that @var{str} is an element, or substring of an element, in
## @var{strarray}.
##
## When @var{str} is a character string to be tested, and @var{strarray} is a
## cellstr of valid values, then @var{validstr} will be the validated form
## of @var{str} where validation is defined as @var{str} being a member
## or substring of @var{validstr}.  This is useful for both verifying
## and expanding short options, such as "r", to their longer forms, such as
## "red".  If @var{str} is a substring of @var{validstr}, and there are
## multiple matches, the shortest match will be returned if all matches are
## substrings of each other.  Otherwise, an error will be raised because the
## expansion of @var{str} is ambiguous.  All comparisons are case insensitive.
##
## The additional inputs @var{funcname}, @var{varname}, and @var{position}
## are optional and will make any generated validation error message more
## specific.
##
## Examples:
## @c Set example in small font to prevent overfull line
##
## @smallexample
## @group
## validatestring ("r", @{"red", "green", "blue"@})
## @result{} "red"
##
## validatestring ("b", @{"red", "green", "blue", "black"@})
## @result{} error: validatestring: multiple unique matches were found for 'b':
##    blue, black
## @end group
## @end smallexample
## 
## @seealso{strcmp, strcmpi}
## @end deftypefn

## Author: Bill Denney <bill@denney.ws>

function str = validatestring (str, strarray, varargin)

  if (nargin < 2 || nargin > 5)
    print_usage ();
  endif

  position = 0;
  ## Process input arguments
  if (! isempty (varargin) && isnumeric (varargin{end}))
    position = varargin{end};
    varargin(end) = [];
  endif
  
  funcname = varname = "";
  char_idx = cellfun ("isclass", varargin, "char");
  n_chararg = sum (char_idx);
  if (n_chararg > 2)
    error ("validatestring: invalid number of character inputs (3)");
  elseif (n_chararg == 2)
    [funcname, varname] = deal (varargin{char_idx});
  elseif (n_chararg == 1)
    funcname = varargin{char_idx};
  endif

  ## Check the inputs
  if (! ischar (str))
    error ("validatestring: STR must be a character string");
  elseif (! isrow (str))
    error ("validatestring: STR must be a single row vector");
  elseif (! iscellstr (strarray))
    error ("validatestring: STRARRAY must be a cellstr");
  elseif (! isempty (funcname) && ! isrow (funcname))
    error ("validatestring: FUNCNAME must be a single row vector");
  elseif (! isempty (varname) && ! isrow (varname))
    error ("validatestring: VARNAME must be a single row vector");
  elseif (position < 0)
    error ("validatestring: POSITION must be >= 0");
  endif

  ## Make static part of error string that uses funcname, varname, and position
  errstr = "";
  if (! isempty (funcname))
    errstr = sprintf ("Function: %s ", funcname);
  endif
  if (! isempty (varname))
    errstr = sprintf ("%sVariable: %s ", errstr, varname);
  endif
  if (position > 0)
    errstr = sprintf ("%sArgument position %d ", errstr, position);
  endif
  if (! isempty (errstr))
    errstr(end:end+1) = ":\n";
  endif

  matches = strncmpi (str, strarray(:), numel (str));
  nmatches = sum (matches);
  if (nmatches == 0)
    error ("validatestring: %s'%s' does not match any of\n%s", errstr, str,
           sprintf ("%s, ", strarray{:})(1:end-2));
  elseif (nmatches == 1)
    str = strarray{matches};
  else
    ## Are the matches substrings of each other?
    ## If true, choose the shortest.  If not, raise an error.
    match_idx = find (matches);
    match_len = cellfun ("length", strarray(match_idx));
    [min_len, min_idx] = min (match_len); 
    short_str = strarray{match_idx(min_idx)};
    submatch = strncmpi (short_str, strarray(match_idx), min_len);    
    if (all (submatch))
      str = short_str;
    else
      error ("validatestring: %smultiple unique matches were found for '%s':\n%s",
             errstr, str, sprintf ("%s, ", strarray{match_idx})(1:end-2));
    endif
  endif

endfunction


%!shared strarray
%! strarray = {"octave" "Oct" "octopus" "octaves"};
%!assert (validatestring ("octave", strarray), "octave")
%!assert (validatestring ("oct", strarray), "Oct")
%!assert (validatestring ("octa", strarray), "octave")
%! strarray = {"abc1" "def" "abc2"};
%!assert (validatestring ("d", strarray), "def")

%!error <'xyz' does not match any> validatestring ("xyz", strarray)
%!error <Function: DUMMY_TEST> validatestring ("xyz", strarray, "DUMMY_TEST")
%!error <Function: DUMMY_TEST Variable: DUMMY_VAR:> validatestring ("xyz", strarray, "DUMMY_TEST", "DUMMY_VAR")
%!error <Function: DUMMY_TEST Variable: DUMMY_VAR Argument position 5> validatestring ("xyz", strarray, "DUMMY_TEST", "DUMMY_VAR", 5)
%!error <multiple unique matches were found for 'abc'> validatestring ("abc", strarray)

%% Test input validation
%!error validatestring ("xyz")
%!error validatestring ("xyz", {"xyz"}, "3", "4", 5, 6)
%!error <invalid number of character inputs> validatestring ("xyz", {"xyz"}, "3", "4", "5")
%!error <STR must be a character string> validatestring (1, {"xyz"}, "3", "4", 5)
%!error <STR must be a single row vector> validatestring ("xyz".', {"xyz"}, "3", "4", 5)
%!error <STRARRAY must be a cellstr> validatestring ("xyz", "xyz", "3", "4", 5)
%!error <FUNCNAME must be a single row vector> validatestring ("xyz", {"xyz"}, "33".', "4", 5)
%!error <VARNAME must be a single row vector> validatestring ("xyz", {"xyz"}, "3", "44".', 5)
%!error <POSITION must be> validatestring ("xyz", {"xyz"}, "3", "4", -5)