Index: trunk/src/@xmltree/private/xml_findstr.c =================================================================== --- trunk/src/@xmltree/private/xml_findstr.c (revision 820) +++ trunk/src/@xmltree/private/xml_findstr.c (revision 925) @@ -2,18 +2,25 @@ /* - Differences with matlab built-in findstr: + * $Id: xml_findstr.c 6480 2015-06-13 01:08:30Z guillaume $ + * Guillaume Flandin + */ + +/* + Differences with built-in findstr: - allows to search only the n first occurences of a pattern - allows to search only in a substring (given an index of the beginning) - Matlab hack: + MATLAB hack: - doesn't use mxGetString to prevent a copy of the string. - - assumes Matlab stores strings as unsigned short (Unicode 16 bits) + - assumes MATLAB stores strings as unsigned short (Unicode 16 bits) matrix.h: typedef uint16_T mxChar; - (that's the case for Matlab 5.* and 6.* but Matlab 4.* stores strings - as double) + (that's the case for MATLAB 5.*, 6.* and 7.* but MATLAB 4.* stores + strings as double and GNU Octave as char, see src/mxarray.h) */ /* Comment the following line to use standard mxGetString (slower) */ +#if !defined (HAVE_OCTAVE) #define __HACK_MXCHAR__ +#endif void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) { @@ -28,18 +35,18 @@ mxArray *out = NULL; - /* Check for proper number of arguments. */ + /* Check for proper number of arguments. */ if ((nrhs == 0) || (nrhs == 1)) - mexErrMsgTxt("Not enough input arguments."); + mexErrMsgTxt("Not enough input arguments."); else if (nrhs > 4) - mexErrMsgTxt("Too many input arguments."); + mexErrMsgTxt("Too many input arguments."); else if (nlhs > 1) mexErrMsgTxt("Too many output arguments."); /* The input TEXT must be a string */ - if (!mxIsChar(prhs[0])) - mexErrMsgTxt("Inputs must be character arrays."); - stext = mxGetM(prhs[0]) * mxGetN(prhs[0]); + if (!mxIsChar(prhs[0])) + mexErrMsgTxt("Inputs must be character arrays."); + stext = mxGetM(prhs[0]) * mxGetN(prhs[0]); #ifdef __HACK_MXCHAR__ - text = mxGetData(prhs[0]); + text = mxGetData(prhs[0]); #else text = mxCalloc(stext+1, sizeof(char)); @@ -48,31 +55,31 @@ /* The input PATTERN must be a string */ - if (!mxIsChar(prhs[1])) - mexErrMsgTxt("Inputs must be character arrays."); + if (!mxIsChar(prhs[1])) + mexErrMsgTxt("Inputs must be character arrays."); spattern = mxGetM(prhs[1]) * mxGetN(prhs[1]); #ifdef __HACK_MXCHAR__ - pattern = mxGetData(prhs[1]); + pattern = mxGetData(prhs[1]); #else pattern = mxCalloc(spattern+1, sizeof(char)); - mxGetString(prhs[1], pattern, spattern+1); + mxGetString(prhs[1], pattern, spattern+1); #endif - /* The input INDEX must be an integer */ - if (nrhs > 2) { - if ((!mxIsNumeric(prhs[2]) || (mxGetM(prhs[2]) * mxGetN(prhs[2]) != 1))) - mexErrMsgTxt("Index input must be an integer."); - ind = (unsigned int)mxGetScalar(prhs[2]); - if (ind < 1) - mexErrMsgTxt("Index must be greater than 1."); - } - - /* The input OCCUR must be an integer */ - if (nrhs == 4) { - if ((!mxIsNumeric(prhs[3]) || (mxGetM(prhs[3]) * mxGetN(prhs[3]) != 1))) - mexErrMsgTxt("Index input must be an integer."); - nboccur = (unsigned int)mxGetScalar(prhs[3]); - } - - /* Find pattern in text */ + /* The input INDEX must be an integer */ + if (nrhs > 2) { + if ((!mxIsNumeric(prhs[2]) || (mxGetM(prhs[2]) * mxGetN(prhs[2]) != 1))) + mexErrMsgTxt("Index input must be an integer."); + ind = (unsigned int)mxGetScalar(prhs[2]); + if (ind < 1) + mexErrMsgTxt("Index must be greater than 1."); + } + + /* The input OCCUR must be an integer */ + if (nrhs == 4) { + if ((!mxIsNumeric(prhs[3]) || (mxGetM(prhs[3]) * mxGetN(prhs[3]) != 1))) + mexErrMsgTxt("Index input must be an integer."); + nboccur = (unsigned int)mxGetScalar(prhs[3]); + } + + /* Find pattern in text */ for (i=ind-1;i -% $Id: xml_findstr.m 2271 2008-09-30 21:19:47Z guillaume $ +% Guillaume Flandin +% $Id: xml_findstr.m 4460 2011-09-05 14:52:16Z guillaume $ %error(sprintf('Missing MEX-file: %s', mfilename)); Index: trunk/src/@xmltree/private/xml_parser.m =================================================================== --- trunk/src/@xmltree/private/xml_parser.m (revision 820) +++ trunk/src/@xmltree/private/xml_parser.m (revision 925) @@ -5,17 +5,20 @@ % xmlstr - XML string to parse % tree - tree structure corresponding to the XML file -%_______________________________________________________________________ -% -% xml_parser.m is an XML 1.0 (http://www.w3.org/TR/REC-xml) parser -% written in Matlab. It aims to be fully conforming. It is currently not -% a validating XML processor. +%__________________________________________________________________________ +% +% xml_parser.m is an XML 1.0 (http://www.w3.org/TR/REC-xml) parser. +% It aims to be fully conforming. It is currently not a validating +% XML processor. % % A description of the tree structure provided in output is detailed in % the header of this m-file. -%_______________________________________________________________________ -% @(#)xml_parser.m Guillaume Flandin 2002/04/04 - -% XML Processor for MATLAB (The Mathworks, Inc.). -% Copyright (C) 2002-2003 Guillaume Flandin +%__________________________________________________________________________ +% Copyright (C) 2002-2015 http://www.artefact.tk/ + +% Guillaume Flandin +% $Id: xml_parser.m 6480 2015-06-13 01:08:30Z guillaume $ + +% XML Processor for GNU Octave and MATLAB (The Mathworks, Inc.) +% Copyright (C) 2002-2015 Guillaume Flandin % % This program is free software; you can redistribute it and/or @@ -32,5 +35,5 @@ % along with this program; if not, write to the Free Software % Foundation Inc, 59 Temple Pl. - Suite 330, Boston, MA 02111-1307, USA. -%----------------------------------------------------------------------- +%-------------------------------------------------------------------------- % Suggestions for improvement and fixes are always welcome, although no @@ -39,16 +42,16 @@ % Check also the latest developments on the following webpage: % -%----------------------------------------------------------------------- +%-------------------------------------------------------------------------- % The implementation of this XML parser is much inspired from a -% Javascript parser available at - -% A mex-file xml_findstr.c is also required, to encompass some -% limitations of the built-in findstr Matlab function. +% Javascript parser that used to be available at + +% A C-MEX file xml_findstr.c is also required, to encompass some +% limitations of the built-in FINDSTR function. % Compile it on your architecture using 'mex -O xml_findstr.c' command % if the compiled version for your system is not provided. -% If this function behaves badly (crash or wrong results), comment the -% line '#define __HACK_MXCHAR__' in xml_findstr.c and compile it again. -%----------------------------------------------------------------------- +% If this function does not behave as expected, comment the line +% '#define __HACK_MXCHAR__' in xml_findstr.c and compile it again. +%-------------------------------------------------------------------------- % Structure of the output tree: @@ -91,5 +94,5 @@ % |_ uid: double % -%----------------------------------------------------------------------- +%-------------------------------------------------------------------------- % TODO/BUG/FEATURES: @@ -103,5 +106,5 @@ % - xml_findstr is indeed xml_strfind according to Mathworks vocabulary % - problem with entities: do we need to convert them here? (é) -%----------------------------------------------------------------------- +%-------------------------------------------------------------------------- %- XML string to parse and number of tags read @@ -109,9 +112,9 @@ %- Check input arguments -error(nargchk(1,1,nargin)); +%error(nargchk(1,1,nargin)); if isempty(xmlstr) - error('[XML] Not enough parameters.') -elseif ~isstr(xmlstr) | sum(size(xmlstr)>1)>1 - error('[XML] Input must be a string.') + error('[XML] Not enough parameters.') +elseif ~ischar(xmlstr) || sum(size(xmlstr)>1)>1 + error('[XML] Input must be a string.') end @@ -137,285 +140,282 @@ clear global xmlstring Xparse_count xtree; -%======================================================================= +%========================================================================== % SUBFUNCTIONS -%----------------------------------------------------------------------- +%-------------------------------------------------------------------------- function frag = compile(frag) - global xmlstring xtree Xparse_count; - - while 1, - if length(xmlstring)<=frag.str | ... - (frag.str == length(xmlstring)-1 & strcmp(xmlstring(frag.str:end),' ')) - return - end - TagStart = xml_findstr(xmlstring,'<',frag.str,1); - if isempty(TagStart) - %- Character data - error(sprintf(['[XML] Unknown data at the end of the XML file.\n' ... - ' Please send me your XML file at Guillaume@artefact.tk'])); - xtree{Xparse_count} = chardata; - xtree{Xparse_count}.value = erode(entity(xmlstring(frag.str:end))); - xtree{Xparse_count}.parent = frag.parent; - xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; - frag.str = ''; - elseif TagStart > frag.str - if strcmp(xmlstring(frag.str:TagStart-1),' ') - %- A single white space before a tag (ignore) - frag.str = TagStart; - else - %- Character data - xtree{Xparse_count} = chardata; - xtree{Xparse_count}.value = erode(entity(xmlstring(frag.str:TagStart-1))); - xtree{Xparse_count}.parent = frag.parent; - xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; - frag.str = TagStart; - end - else - if strcmp(xmlstring(frag.str+1),'?') - %- Processing instruction - frag = tag_pi(frag); - else - if length(xmlstring)-frag.str>4 & strcmp(xmlstring(frag.str+1:frag.str+3),'!--') - %- Comment - frag = tag_comment(frag); - else - if length(xmlstring)-frag.str>9 & strcmp(xmlstring(frag.str+1:frag.str+8),'![CDATA[') - %- Litteral data - frag = tag_cdata(frag); - else - %- A tag element (empty (<.../>) or not) - if ~isempty(frag.end) - endmk = ['/' frag.end '>']; - else - endmk = '/>'; - end - if strcmp(xmlstring(frag.str+1:frag.str+length(frag.end)+2),endmk) | ... - strcmp(strip(xmlstring(frag.str+1:frag.str+length(frag.end)+2)),endmk) - frag.str = frag.str + length(frag.end)+3; - return - else - frag = tag_element(frag); - end - end - end - end - end - end - -%----------------------------------------------------------------------- + global xmlstring xtree Xparse_count; + + while 1, + if length(xmlstring)<=frag.str || ... + (frag.str == length(xmlstring)-1 && strcmp(xmlstring(frag.str:end),' ')) + return + end + TagStart = xml_findstr(xmlstring,'<',frag.str,1); + if isempty(TagStart) + %- Character data + error('[XML] Unknown data at the end of the XML file.'); + Xparse_count = Xparse_count + 1; + xtree{Xparse_count} = chardata; + xtree{Xparse_count}.value = erode(entity(xmlstring(frag.str:end))); + xtree{Xparse_count}.parent = frag.parent; + xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; + frag.str = ''; + elseif TagStart > frag.str + if strcmp(xmlstring(frag.str:TagStart-1),' ') + %- A single white space before a tag (ignore) + frag.str = TagStart; + else + %- Character data + Xparse_count = Xparse_count + 1; + xtree{Xparse_count} = chardata; + xtree{Xparse_count}.value = erode(entity(xmlstring(frag.str:TagStart-1))); + xtree{Xparse_count}.parent = frag.parent; + xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; + frag.str = TagStart; + end + else + if strcmp(xmlstring(frag.str+1),'?') + %- Processing instruction + frag = tag_pi(frag); + else + if length(xmlstring)-frag.str>4 && strcmp(xmlstring(frag.str+1:frag.str+3),'!--') + %- Comment + frag = tag_comment(frag); + else + if length(xmlstring)-frag.str>9 && strcmp(xmlstring(frag.str+1:frag.str+8),'![CDATA[') + %- Litteral data + frag = tag_cdata(frag); + else + %- A tag element (empty (<.../>) or not) + if ~isempty(frag.end) + endmk = ['/' frag.end '>']; + else + endmk = '/>'; + end + if strcmp(xmlstring(frag.str+1:frag.str+length(frag.end)+2),endmk) || ... + strcmp(strip(xmlstring(frag.str+1:frag.str+length(frag.end)+2)),endmk) + frag.str = frag.str + length(frag.end)+3; + return + else + frag = tag_element(frag); + end + end + end + end + end + end + +%-------------------------------------------------------------------------- function frag = tag_element(frag) - global xmlstring xtree Xparse_count; - close = xml_findstr(xmlstring,'>',frag.str,1); - if isempty(close) - error('[XML] Tag < opened but not closed.'); - else - empty = strcmp(xmlstring(close-1:close),'/>'); - if empty - close = close - 1; - end - starttag = normalize(xmlstring(frag.str+1:close-1)); - nextspace = xml_findstr(starttag,' ',1,1); - attribs = ''; - if isempty(nextspace) - name = starttag; - else - name = starttag(1:nextspace-1); - attribs = starttag(nextspace+1:end); - end - xtree{Xparse_count} = element; - xtree{Xparse_count}.name = strip(name); - if frag.parent - xtree{Xparse_count}.parent = frag.parent; - xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; - end - if length(attribs) > 0 - xtree{Xparse_count}.attributes = attribution(attribs); - end - if ~empty - contents = fragment; - contents.str = close+1; - contents.end = name; - contents.parent = Xparse_count; - contents = compile(contents); - frag.str = contents.str; - else - frag.str = close+2; - end - end - -%----------------------------------------------------------------------- + global xmlstring xtree Xparse_count; + close = xml_findstr(xmlstring,'>',frag.str,1); + if isempty(close) + error('[XML] Tag < opened but not closed.'); + else + empty = strcmp(xmlstring(close-1:close),'/>'); + if empty + close = close - 1; + end + starttag = normalize(xmlstring(frag.str+1:close-1)); + nextspace = xml_findstr(starttag,' ',1,1); + attribs = ''; + if isempty(nextspace) + name = starttag; + else + name = starttag(1:nextspace-1); + attribs = starttag(nextspace+1:end); + end + Xparse_count = Xparse_count + 1; + xtree{Xparse_count} = element; + xtree{Xparse_count}.name = strip(name); + if frag.parent + xtree{Xparse_count}.parent = frag.parent; + xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; + end + if ~isempty(attribs) + xtree{Xparse_count}.attributes = attribution(attribs); + end + if ~empty + contents = fragment; + contents.str = close+1; + contents.end = name; + contents.parent = Xparse_count; + contents = compile(contents); + frag.str = contents.str; + else + frag.str = close+2; + end + end + +%-------------------------------------------------------------------------- function frag = tag_pi(frag) - global xmlstring xtree Xparse_count; - close = xml_findstr(xmlstring,'?>',frag.str,1); - if isempty(close) - warning('[XML] Tag close | nextspace == frag.str+2 - xtree{Xparse_count}.value = erode(xmlstring(frag.str+2:close-1)); - else - xtree{Xparse_count}.value = erode(xmlstring(nextspace+1:close-1)); - xtree{Xparse_count}.target = erode(xmlstring(frag.str+2:nextspace)); - end - if frag.parent - xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; - xtree{Xparse_count}.parent = frag.parent; - end - frag.str = close+2; - end - -%----------------------------------------------------------------------- + global xmlstring xtree Xparse_count; + close = xml_findstr(xmlstring,'?>',frag.str,1); + if isempty(close) + warning('[XML] Tag close || nextspace == frag.str+2 + xtree{Xparse_count}.value = erode(xmlstring(frag.str+2:close-1)); + else + xtree{Xparse_count}.value = erode(xmlstring(nextspace+1:close-1)); + xtree{Xparse_count}.target = erode(xmlstring(frag.str+2:nextspace)); + end + if frag.parent + xtree{frag.parent}.contents = [xtree{frag.parent}.contents Xparse_count]; + xtree{Xparse_count}.parent = frag.parent; + end + frag.str = close+2; + end + +%-------------------------------------------------------------------------- function frag = tag_comment(frag) - global xmlstring xtree Xparse_count; - close = xml_findstr(xmlstring,'-->',frag.str,1); - if isempty(close) - warning('[XML] Tag ',frag.str,1); + if isempty(close) + warning('[XML] Tag