File: arg_parse_ctd_support.h

package info (click to toggle)
seqan2 2.4.0%2Bdfsg-11~bpo9%2B1
  • links: PTS, VCS
  • area: main
  • in suites: stretch-backports
  • size: 223,500 kB
  • sloc: cpp: 256,886; ansic: 91,672; python: 8,339; sh: 995; xml: 570; makefile: 251; awk: 51
file content (594 lines) | stat: -rw-r--r-- 21,576 bytes parent folder | download | duplicates (4)
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
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
// ==========================================================================
//                 SeqAn - The Library for Sequence Analysis
// ==========================================================================
// Copyright (c) 2006-2018, Knut Reinert, FU Berlin
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are met:
//
//     * Redistributions of source code must retain the above copyright
//       notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above copyright
//       notice, this list of conditions and the following disclaimer in the
//       documentation and/or other materials provided with the distribution.
//     * Neither the name of Knut Reinert or the FU Berlin nor the names of
//       its contributors may be used to endorse or promote products derived
//       from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL KNUT REINERT OR THE FU BERLIN BE LIABLE
// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
// LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
// OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
// DAMAGE.
//
// ==========================================================================
// Author: Bjoern Kahlert <Bjoern.Kahlert@fu-berlin.de>
// Author: Stephan Aiche <stephan.aiche@fu-berlin.de>
// ==========================================================================

#ifndef SEQAN_INCLUDE_SEQAN_ARG_PARSE_ARG_PARSE_CTD_SUPPORT_H_
#define SEQAN_INCLUDE_SEQAN_ARG_PARSE_ARG_PARSE_CTD_SUPPORT_H_

#include <seqan/sequence.h>

#include <seqan/arg_parse/xml_support.h>
#include <seqan/arg_parse/argument_parser.h>
#include <seqan/arg_parse/arg_parse_doc.h>

#include <fstream>

namespace seqan {

// ----------------------------------------------------------------------------
// Function _toText()
// ----------------------------------------------------------------------------
// Removes formatting (\fI, \fB, and \fP).
template <typename TSequence>
TSequence _toText(TSequence const & input)
{
    TSequence buffer = xmlEscape(input);
    TSequence result;
    String<TSequence> openTags;

    typedef typename Iterator<TSequence const, Standard>::Type TIterator;
    TIterator endIt = end(input, Standard());
    for (TIterator it = begin(input, Standard()); it != endIt; goNext(it))
    {
        if (*it == '\\')
        {
            // Handle escape sequence, we interpret only "\-", "\fI", and "\fB".
            goNext(it);
            SEQAN_ASSERT_NOT(it == endIt);
            if (*it == '-')
            {
                appendValue(result, *it);
            }
            else if (*it == 'f')
            {
                goNext(it);
                SEQAN_ASSERT_NOT(it == endIt);
                if (*it == 'I')
                {
                    appendValue(openTags, "i");
                }
                else if (*it == 'B')
                {
                    appendValue(openTags, "b");
                }
                else if (*it == 'P')
                {
                    SEQAN_ASSERT_NOT(empty(openTags));
                    eraseBack(openTags);
                }
                else
                {
                    append(result, "\\f");
                    appendValue(result, *it);
                }
            }
            else
            {
                appendValue(result, '\\');
                appendValue(result, *it);
            }
        }
        else
        {
            appendValue(result, *it);
        }
    }

    return result;
}

// ----------------------------------------------------------------------------
// Function _join()
// ----------------------------------------------------------------------------

template <typename TValue>
inline std::string
_join(std::vector<TValue> const & v, std::string const & delimiter)
{
    typedef typename std::vector<TValue>::const_iterator TStringSetIterator;

    std::stringstream joined;
    for (TStringSetIterator it = v.begin(); it != v.end(); ++it)
    {
        if (it != v.begin())
            joined << delimiter;
        joined << *it;
    }
    return joined.str();
}

// ----------------------------------------------------------------------------
// Function _getPrefixedOptionName()
// ----------------------------------------------------------------------------

inline std::string
_getPrefixedOptionName(ArgParseOption const & opt)
{
    std::string optName = "";
    if (!empty(opt.longName))
        optName = "--" + opt.longName;
    else
        optName = "-" + opt.shortName;

    return optName;
}

// ----------------------------------------------------------------------------
// Function _getOptionName()
// ----------------------------------------------------------------------------

inline std::string
_getOptionName(ArgParseOption const & opt)
{
    if (!empty(opt.longName))
        return opt.longName;
    else
        return opt.shortName;
}

// ----------------------------------------------------------------------------
// Function _getRestrictions()
// ----------------------------------------------------------------------------
inline void
_getRestrictions(std::vector<std::string> & restrictions, ArgParseArgument const & opt)
{
    // we only extract non-file restrictions
    if (isOutputFileArgument(opt) || isInputFileArgument(opt) || isInputPrefixArgument(opt) || isOutputPrefixArgument(opt))
    {
        return;
    }
    else if (isBooleanArgument(opt))
    {
        appendValue(restrictions, "true,false");
        return;
    }
    if (length(opt.validValues) != 0)
    {
        for (std::vector<std::string>::const_iterator valid = opt.validValues.begin();
             valid != opt.validValues.end();
             ++valid)
        {
            appendValue(restrictions, *valid);
        }
    }
    else
    {
        std::string minMaxRestriction = "";
        if (opt.minValue != "")
        {
            append(minMaxRestriction, opt.minValue);
            append(minMaxRestriction, ":");
        }
        if (opt.maxValue != "")
        {
            if (minMaxRestriction == "")
                append(minMaxRestriction, ":");
            append(minMaxRestriction, opt.maxValue);
        }

        if (minMaxRestriction != "")
            appendValue(restrictions, minMaxRestriction);
    }
}

// ----------------------------------------------------------------------------
// Function _addValidValuesRestrictions()
// ----------------------------------------------------------------------------

inline void
_getSupportedFormats(std::vector<std::string> & supported_formats, ArgParseArgument const & opt)
{
    // we check only file arguments
    if (!(isOutputFileArgument(opt) || isInputFileArgument(opt) || isInputPrefixArgument(opt) || isOutputPrefixArgument(opt)))
        return;

    if (length(opt.validValues) != 0)
    {
        std::string filetype;
        for (std::vector<std::string>::const_iterator valid = opt.validValues.begin();
             valid != opt.validValues.end();
             ++valid)
        {
            SEQAN_ASSERT_NOT(empty(*valid));

            filetype = "*";

            // ensure . as separator between * and file-extension
            if (value(*valid, 0) != '.')
                appendValue(filetype, '.');

            append(filetype, *valid);
            appendValue(supported_formats, filetype);
        }
    }
}

// ----------------------------------------------------------------------------
// Function _includeInCTD()
// ----------------------------------------------------------------------------

/*
 * returns true if this option should be included in the ctd
 */
inline bool
_includeInCTD(ArgParseOption const & opt)
{
    return !(opt.longName == "help" || opt.longName == "version" || opt.longName == "write-ctd" || opt.longName == "export-help" || (opt.shortName == "" && opt.longName == ""));
}

// ----------------------------------------------------------------------------
// Function _indent()
// ----------------------------------------------------------------------------

inline std::string _indent(const int currentIndent)
{
    std::string indent = "";
    for (int i = 0; i < currentIndent; ++i)
        indent += "\t";
    return indent;
}

// ----------------------------------------------------------------------------
// Function _writeCLIElement()
// ----------------------------------------------------------------------------
inline void _writeCLIElement(std::ostream & ctdfile, int currentIndent, std::string const & optionIdentifier, std::string const & ref_name, bool isList)
{
    ctdfile << _indent(currentIndent)
            << "<clielement optionIdentifier=\"" << optionIdentifier
            << "\" isList=\"" << (isList ? "true" : "false") << "\">\n";

    ctdfile << _indent(currentIndent + 1) << "<mapping referenceName=\"" << ref_name << "\" />\n";

    ctdfile << _indent(currentIndent) << "</clielement>\n";
}

// ----------------------------------------------------------------------------
// Function _getManual()
// ----------------------------------------------------------------------------
inline std::string _getManual(ArgumentParser const & me)
{
    std::stringstream manual;
    for (unsigned i = 0; i < me._description.size(); ++i)
    {
        manual << _toText(me._description[i]) << std::endl;
    }
    return manual.str();
}

// ----------------------------------------------------------------------------
// Function _toValidGKNTypeSpecifier()
// ----------------------------------------------------------------------------
// TODO(dadi): similar to  _typeToString() function. Differs only in the case of bool, integer, int64 and types
//.            that has underscores in them. hyphens are used instead of underscores. e.g. input-file instead
//             of input_file. This should be removed and _typeToString() should be used instead once GKN is
//             modified to accept the results of _typeToString() functions directly.

inline std::string _toValidGKNTypeSpecifier(ArgParseArgument const & me)
{
    switch (me._argumentType)
    {
        case ArgParseArgument::BOOL:
            return "string";

        case ArgParseArgument::INTEGER:
            return "int";

        case ArgParseArgument::INT64:
            return "int";

        case ArgParseArgument::INPUT_FILE:
            return "input-file";

        case ArgParseArgument::OUTPUT_FILE:
            return "output-file";

        case ArgParseArgument::INPUT_PREFIX:
            return "input-prefix";

        case ArgParseArgument::OUTPUT_PREFIX:
            return "output-prefix";

        case ArgParseArgument::INPUT_DIRECTORY:
            return "input-prefix";

        case ArgParseArgument::OUTPUT_DIRECTORY:
            return "output-prefix";

        default:
            return _typeToString(me);
    }
}

// ----------------------------------------------------------------------------
// Function writeCTD()
// ----------------------------------------------------------------------------

// TODO(holtgrew): Change argument order.

/*!
 * @fn ArgumentParser#writeCTD
 * @headerfile <seqan/arg_parse.h>\
 * @brief Export the app's interface description to a .ctd file.
 *
 * @signature bool writeCTD(parser[, stream]);
 *
 * @param[in]  parser The ArgumentParser to write the CTD file for.
 * @param[out] stream A <tt>std::ostream</tt> to write to.  If omitted an output file with the name form the
 *                    "write-ctd" parameter of the parser is used.
 *
 * @return bool <tt>true</tt> on success, <tt>false</tt> on failure.
 */

inline bool
writeCTD(ArgumentParser const & me, std::ostream & ctdfile)
{
    typedef ArgumentParser::TOptionMap::const_iterator   TOptionMapIterator;
    typedef ArgumentParser::TArgumentMapSize TArgumentMapSize;

    int currentIndent = 1;

    std::string toolname(toCString(xmlEscape(getAppName(me))));

    // remove "_" in the tool name and make the following letter uppercase
    std::string class_name;
    bool upcase = true;
    for (unsigned i = 0; i < toolname.size(); ++i)
    {
        if (toolname[i] == '_')
        {
            upcase = true;
            continue;
        }
        class_name.push_back(toolname[i]);
        if (upcase)
            class_name[class_name.size() - 1] = toupper(toolname[i]);
        upcase = false;
    }

    ctdfile << "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n";
    ctdfile << "<tool name=\"" << class_name << "\" version=\"" << xmlEscape(getVersion(me)) << "\" docurl=\"http://www.seqan.de\" category=\"" << xmlEscape(getCategory(me)) << "\" ctdVersion=\"1.7\">\n";
    ctdfile << _indent(currentIndent) << "<executableName>" << toolname << "</executableName>\n";
    ctdfile << _indent(currentIndent) << "<description>" << xmlEscape(getShortDescription(me)) << "</description>\n";
    ctdfile << _indent(currentIndent) << "<manual>" << xmlEscape(_getManual(me)) << "</manual>\n"; // TODO(aiche): as soon as we have a more sophisticated documentation embedded into the CmdParser, we should at this here
    ctdfile << _indent(currentIndent++) << "<cli>\n";

    // the unix way 1st the options
    for (TOptionMapIterator optionMapIterator = me.optionMap.begin();
         optionMapIterator != me.optionMap.end();
         ++optionMapIterator)
    {
        ArgParseOption const & opt = *optionMapIterator;

        // exclude hidden
        if (isHidden(opt))
            continue;

        std::string optionIdentifier = _getPrefixedOptionName(opt);
        std::string refName = toolname + "." + _getOptionName(opt);

        if (_includeInCTD(opt))
        {
            _writeCLIElement(ctdfile, currentIndent, optionIdentifier, refName, isListArgument(opt));
        }
    }

    // add a warning to the CTD that arguments are hard to interpret by the users
    if (me.argumentList.size() > 0u)
    {
        ctdfile << _indent(currentIndent)
                << "<!-- Following clielements are arguments."
                << " You should consider providing a help text to ease understanding. -->\n";
    }
    // then the arguments
    for (TArgumentMapSize argIdx = 0; argIdx != me.argumentList.size(); ++argIdx)
    {
        // arguments do not have an option identifier
        std::string optionIdentifier = "";
        std::stringstream refName;
        refName << toolname << "." << "argument-" << argIdx;
        _writeCLIElement(ctdfile, currentIndent, optionIdentifier, refName.str(), isListArgument(me.argumentList[argIdx]));
    }

    ctdfile << _indent(--currentIndent) << "</cli>\n";
    ctdfile << _indent(currentIndent++) << "<PARAMETERS version=\"1.6.2\" xsi:noNamespaceSchemaLocation=\"http://open-ms.sourceforge.net/schemas/Param_1_6_2.xsd\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\">\n";
    ctdfile << _indent(currentIndent++) << "<NODE name=\"" << toolname << "\" description=\"" << xmlEscape(getShortDescription(me)) << "\">\n";

    for (TOptionMapIterator optionMapIterator = me.optionMap.begin();
         optionMapIterator != me.optionMap.end();
         ++optionMapIterator)
    {
        ArgParseOption const & opt = *optionMapIterator;

        // exclude help, version, etc.
        if (!_includeInCTD(opt))
            continue;

        // exclude hidden
        if (isHidden(opt))
            continue;

        // prefer short name for options
        std::string optionName = _getOptionName(opt);

        std::string type = _toValidGKNTypeSpecifier(opt);

        // set up restrictions
        std::vector<std::string> restrictions;
        _getRestrictions(restrictions, opt);

        // set up supported formats
        // add *.* to supported_formats if none is specified AND the type of the argument is a
        // prefix type. This is important for KNIME nodes as they require similar file types
        // to connect one node to the other. In this particular case any file is aproprate
        // since we are talking about prefixes.
        std::vector<std::string> supported_formats;
        _getSupportedFormats(supported_formats, opt);
        if (empty(supported_formats) && (type=="input-prefix" || type=="output-prefix" ))
            supported_formats.push_back("*.*");

        ctdfile << _indent(currentIndent)
                << "<ITEM" << (isListArgument(opt) ? "LIST" : "") << " name=\"" << xmlEscape(optionName) << "\"";

        // handle the value field
        if (isListArgument(opt))
            ctdfile << " ";
        else
            ctdfile << " value=\"" << xmlEscape(_join(opt.defaultValue, ",")) << "\" ";

        ctdfile << "type=\"" << type << "\" "
                << "description=\"" << xmlEscape(_toText(opt._helpText)) << "\" ";

        if (!empty(restrictions))
            ctdfile << "restrictions=\"" << xmlEscape(_join(restrictions, ",")) << "\" ";
        if (!empty(supported_formats))
            ctdfile << "supported_formats=\"" << xmlEscape(_join(supported_formats, ",")) << "\" ";

        ctdfile << "required=\"" << (isRequired(opt) ? "true" : "false") << "\" ";
        ctdfile << "advanced=\"" << (isAdvanced(opt) ? "true" : "false") << "\" ";

        // Write out tags attribute.
        if (!opt.tags.empty())
        {
            ctdfile << "tags=\"";
            for (unsigned i = 0; i < length(opt.tags); ++i)
            {
                if (i > 0)
                    ctdfile << ",";
                ctdfile << opt.tags[i];
            }
            ctdfile << "\" ";
        }

        if (isListArgument(opt))
        {
            ctdfile << ">\n";
            for (size_t i = 0; i < length(opt.defaultValue); ++i)
            {
                ctdfile << _indent(currentIndent + 1) << "<LISTITEM value=\"" << xmlEscape(opt.defaultValue[i]) << "\"/>\n";
            }
            ctdfile << _indent(currentIndent) << "</ITEMLIST>\n";
        }
        else
        {
            ctdfile << "/>\n";
        }
    }

    for (TArgumentMapSize argIdx = 0; argIdx != me.argumentList.size(); ++argIdx)
    {
        ArgParseArgument arg = me.argumentList[argIdx];

        // prefer short name for options
        std::stringstream argumentNameStream;
        argumentNameStream << "argument-" << argIdx;
        std::string optionName = argumentNameStream.str();

        std::string type = _toValidGKNTypeSpecifier(arg);

        // set up restrictions
        std::vector<std::string> restrictions;
        _getRestrictions(restrictions, arg);

        // set up supported formats
        // add *.* to supported_formats if none is specified AND the type of the argument is a
        // prefix type. This is important for KNIME nodes as they require similar file types
        // to connect one node to the other. In this particular case any file is aproprate
        // since we are talking about prefixes.
        std::vector<std::string> supported_formats;
        _getSupportedFormats(supported_formats, arg);
        if (empty(supported_formats) && (type=="input-prefix" || type=="output-prefix" ))
            supported_formats.push_back("*.*");


        ctdfile << _indent(currentIndent)
                << "<ITEM" << (isListArgument(arg) ? "LIST" : "") << " name=\"" << xmlEscape(optionName) << "\" "
                << (isListArgument(arg) ? " " : "value=\"\" ")
                << "type=\"" << type << "\" "
                << "description=\"" << xmlEscape(_toText(arg._helpText)) << "\" "; // it will be "" in most cases but we try
        if (!empty(restrictions))
            ctdfile << "restrictions=\"" << xmlEscape(_join(restrictions, ",")) << "\" ";
        if (!empty(supported_formats))
            ctdfile << "supported_formats=\"" << xmlEscape(_join(supported_formats, ",")) << "\" ";

        ctdfile << "required=\"true\" ";
        ctdfile << "advanced=\"false\" ";

        // Write out tags attribute.
        if (!arg.tags.empty())
        {
            ctdfile << "tags=\"";
            for (unsigned i = 0; i < length(arg.tags.size()); ++i)
            {
                if (i > 0)
                    ctdfile << ",";
                ctdfile << arg.tags[i];
            }
            ctdfile << "\" ";
        }

        ctdfile << "/>\n";
    }

    ctdfile << _indent(--currentIndent) << "</NODE>\n";
    ctdfile << _indent(--currentIndent) << "</PARAMETERS>\n";
    ctdfile << "</tool>" << std::endl;

    return true;
}

inline bool
writeCTD(ArgumentParser const & me)
{
    // create file [appname].ctd in working directory
    std::string ctdfilename;
    getOptionValue(ctdfilename, me, "write-ctd");

    std::ofstream ctdfile;
    ctdfile.open(toCString(ctdfilename));

    if (!ctdfile.is_open())
    {
        std::cerr << getAppName(me) << ": Unable to create ctd file: " << ctdfilename << std::endl;
        return false;
    }

    writeCTD(me, ctdfile);

    ctdfile.close();
    return true;
}

} // namespace seqan

#endif // SEQAN_INCLUDE_SEQAN_ARG_PARSE_ARG_PARSE_CTD_SUPPORT_H_