summaryrefslogtreecommitdiff
path: root/bin/FOCUS/Parser/FOCUSParser.pm
blob: b2061a660a4e0f32822f1bbbcf8a36daca358164 (plain)
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
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
#########################################################################
# A Simple Parser for automating the specializations crated in FOCUS.
#
# @author Arvind S. Krishna <arvindk@dre.vanderbilt.edu>
#
# $Id$
#
# This parser, parses the specialization file given as an input argument
# and *individually* visits the tags in a pre-determined order to weave
# in the specializations.
# NOTE: This parser will make N passes over the file, where N equals
# to the number of tags defined in the specialization file. This
# approach is intentional as it servers current needs. Future versions
# may enhance this parser and Visit methods to be more intelligent.
###########################################################################
package FOCUSParser;

# for MY own preferences!
use strict;

# XML related operations
use XML::DOM;

# Generic file operations
use FileHandle;

# Creating files and renaming them
use File::Copy;

# Creating directories
use File::Path;

############################################
# GLOBAL CONSTANTS
###########################################
my $FOCUS_PREPEND_TAG = "\/\/@@ ";

####################################################################
# banner: A function that returns the FOCUS banner transformation
# for just clarity purpose only.
###################################################################
sub FOCUS_banner_start
{
  my $banner_str = "// Code woven by FOCUS:\n";
  return $banner_str;
}

sub FOCUS_banner_end
{
  my $banner_str = "// END Code woven by FOCUS\n";
  return $banner_str;
}

#########################################################################
# Visit_ADD: Visit a add element defined in the transform.
# In particular look for the hook defined: search it in the source file
# and add the data in the <data> tags into the file starting from the
# hook, but not including the hook.
##########################################################################
sub Visit_Add
{
  my ($add, $copy_file_name) = @_;

  # Open the copy and transform it
  open (IN, "+<". $copy_file_name) ||
    die "cannot open file: " . $copy_file_name;

  # To update a file in place, we use the temporary
  # file idiom. Perl says this is the best way to
  # do this!
  my $copy_file_tmp = $copy_file_name . "tmp";
  open (OUT, ">". $copy_file_tmp) ||
    die "cannot open temporary file for modying file:" . $copy_file_name;

  # get the hook element defined in the add element
  my $hook = $add->getElementsByTagName ('hook');

  # ensure length of hook == 1;
  if ($hook->getLength != 1)
  {
    print "Assertion Error: An <add> element can have only \
           one <hook> definition";

    # clean up
    close (IN);
    close (OUT);

    # Diagnostic comment
    print " [failure]... Reverting changes \n";

    unlink ($copy_file_name);
    unlink ($copy_file_name . "tmp");
    exit (1);
  }

  # Check if the hook is present in the file at all
  my $hook_str = $hook->item(0)->getFirstChild->getNodeValue;
  chomp ($hook_str);

  #//@@ For now, due to problem with the hook string
  my $search_str = $hook_str;

  while (<IN>)
  {
    if (/$search_str/)
    {
      # Do not remove the hook! It needs to be present
      print OUT $_;

      # FOCUS banner start
      print OUT FOCUS_banner_start;

      # parse <data> ... </data> elements for this add tag
      my @data_list = $add->getElementsByTagName ('data');
      foreach my $data (@data_list)
      {
	my $data_item = $data->getFirstChild->getNodeValue;
	chomp ($data_item);

	# Insert the item
	print OUT "$data_item \n";
      }

      # FOCUS banner end
      print OUT FOCUS_banner_end;
    }
    else
    {  print OUT $_; }
  }

  # Everything went well!
  close (IN);
  close (OUT);

  # replace in place the old file with the new one
  rename ($copy_file_tmp, $copy_file_name);
}

###########################################################################
# Visit_Remove: Visit a <remove> element defined in the transform.
# In particular look for the hook defined: search it in the source file
# and remove the element's value from the source file being searched.
############################################################################
sub Visit_Remove
{
  my ($remove, $copy_file_name) = @_;

  # obtain the data to be removed
  my $search = $remove->getFirstChild->getNodeValue;
  chomp ($search);

  # Open the copy and transform it
  open (IN, "+<" . $copy_file_name) ||
    die "cannot open file: " . $copy_file_name;

  # Update the file in place
  my $copy_file_name_tmp = $copy_file_name . "tmp";
  open (OUT, ">". $copy_file_name_tmp) ||
    die "cannot open temporary file for modying file:" . $copy_file_name;;

  # Removing something is same as search and replace. Replace with ""
  my $replace = "";

  foreach my $line (<IN>)
  {
    if ($line =~/$search/)
    {
      # We do not print the banner information
      # as we have removed something and
      # print the banner will be redundant!

      # replace <search> with <replace>
      $line =~ s/$search/$replace/;

      print OUT $line;
    }
    else { print OUT $line; }
  }

  # Everything went well!
  close (IN);
  close (OUT);

  # replace in place the old file with the new one
  rename ($copy_file_name_tmp, $copy_file_name);
}

#########################################################################
# Visit_Substitute: Visit a <substitute> element defined in the transform.
# In particular look for the <search> element and replace it with the
# <replace> element.
#########################################################################
sub Visit_Substitute
{
  my ($substitute, $copy_file_name) = @_;

  # Open the copy and transform it
  open (IN, "+<". $copy_file_name) ||
    die "cannot open file: " . $copy_file_name;

  # To update a file in place, we use the temporary
  # file idiom. Perl says this is the best way to
  # do this!
  my $copy_file_name_tmp = $copy_file_name . "tmp";
  open (OUT, ">". $copy_file_name . "tmp") ||
    die "cannot open temporary file for modying file:" . $copy_file_name;;

  # check if the match-line keyword is set or not
  my $match_line = $substitute->getAttribute('match-line');

  # <search> .... </search>
  my $search_list = $substitute->getElementsByTagName ('search');

  # ensure length of search == 1;
  if ($search_list->getLength != 1 ||
      $search_list->getLength == 0)
  {
    print "Assertion Error: A <substitute> element can have only \
          one <search> element";
    close (IN);
    close (OUT);

    # Dianostic comment
    print " [failure] reverting changes \n";

    unlink ($copy_file_name);
    unlink ($copy_file_name_tmp);
    exit (1);
  }

  # <replace> .... </replace>
  my $replace_list = $substitute->getElementsByTagName ('replace');
  if ($replace_list->getLength != 1 ||
      $replace_list->getLength == 0)
  {
    print "Assertion Error: A <substitute> element can have only \
           one <replace> element";
    close (IN);
    close (OUT);
    unlink ($copy_file_name);
    unlink ($copy_file_name_tmp);
    exit (1);
  }

  # <search> and <replace> element values
  my $search = $search_list->item(0)->getFirstChild->getNodeValue;
  my $replace = $replace_list->item(0)->getFirstChild->getNodeValue;

  # remove spaces
  chomp ($search);
  chomp ($replace);

  # Search and replace string in the file
  foreach my $line (<IN>)
  {
    # Check if the match line attribute is set. If so then
    # ignore word boundaries. If not, honor word boundaries.
    my $line_matched = 0;
    if (! $match_line)
    {
      if ($line =~/\b$search\b/)
      {
        $line_matched = 1;
      }
    }
    else
    {
      if ($line =~ /$search/)
      {
        $line_matched = 1;
      }
    }

    # Check if the line matched
    if ($line_matched)
    {
      # FOCUS banner start
      print OUT FOCUS_banner_start;

      # replace <search> with <replace>
      # Caveat: What if <search> occures multiple
      # times in the line? Here is how we handle
      # it
      $line =~ s/$search/$replace/g;

      print OUT $line;

      # FOCUS banner end
      print OUT FOCUS_banner_end;
    }
    else { print OUT $line; }
  }

  # everything went well!
  close (IN);
  close (OUT);

  # replace in place the old file with the new one
  rename ($copy_file_name_tmp, $copy_file_name);
}

#########################################################################
# Visit_Comment: Visit the comment-region hooks defined in the
# source code and comment out all code between start and finish of that
# region
#########################################################################
sub Visit_Comment
{
  my ($comment, $copy_file_name) = @_;

  # check for the comment region tags and
  # comment out the region
  my $start_hook_tag = $comment->getElementsByTagName ('start-hook');
  my $end_hook_tag   = $comment->getElementsByTagName ('end-hook');

  if ($start_hook_tag->getLength != 1 ||
      $end_hook_tag->getLength != 1)
  {
    print "Assertion Error: A <comment> element can have only \
           one pair of <start-hook> and <end-hook> tags";
    unlink ($copy_file_name);
    exit (1);
  }

  my $start = $start_hook_tag->item(0)->getFirstChild->getNodeValue;
  my $end =   $end_hook_tag->item(0)->getFirstChild->getNodeValue;

  # What are we looking for:
  # We need to start from "//" . FOCUS_PREPEND_TAG . $hook
  # i.e. //[[@ <blah blah>
  # This will be the format for both start and end
  # //@@ Problems with the hook string
  my $start_hook = $FOCUS_PREPEND_TAG . $start;
  my $end_hook   = $FOCUS_PREPEND_TAG . $end;

  # Open the copy and transform it
  open (IN, "+<". $copy_file_name) ||
    die "cannot open file: " . $copy_file_name;

  my $copy_file_name_tmp = $copy_file_name . "tmp";
  open (OUT, ">". $copy_file_name_tmp) ||
    die "cannot open temporary file for modying file:" . $copy_file_name;

  my $start_commenting = 0;
  while (<IN>)
  {
    if (! /$start_hook/ &&
        ! /$end_hook/)
    {
      if ($start_commenting)
      { print OUT "// " . $_; }
      else
      { print OUT $_; }
    }
    else
    {
      if (/$start_hook/)
      {
        $start_commenting = 1;
        print OUT $_; # print start hook!
      }
      else
      {
        $start_commenting = 0;
        print OUT $_; # print end hook!
      }
    }
  }

  # everything went well!
  close (IN);
  close (OUT);

  rename ($copy_file_name_tmp, $copy_file_name);
}

###############################################################
# Visit_Copy: visit the <copy> tags and weave the code into the
# source file. In particular, open the source file specified
# in the file-source tag. Search for the start hook and
# copy until the end hook is reached.
###############################################################
sub Visit_Copy
{
  my ($copy_tag, $copy_file_name, $default_module_name, $prefix_path) = @_;

  # Check if a file name has been specified
  my $dest_file_tag = $copy_tag->getElementsByTagName ('source');

  if (! $dest_file_tag)
  {
    print "Error: <copy-from-source> does not have the <file> tag..";
    print "aborting \n";
    exit 1;
  }

  if ($dest_file_tag->getLength != 1)
  {
    print "Assertion Error: A <copy-from-source> element can have only \
           one <source> tag from which to copy elements";
    exit (1);
  }

  my $dest_file_name = $dest_file_tag->item(0)->getFirstChild->getNodeValue;

  #Check if the file exists and one is able to access it
  $dest_file_name = $prefix_path . "/" . $default_module_name . "/" . $dest_file_name;

  open (DEST, "<". $dest_file_name) ||
   die "cannot open $dest_file_name \n Wrong <file> tag within <copy-from-source> exiting" ;

  # check for the start and end tags within the target file where
  # one needs to start copying from
  my $start_tag = $copy_tag->getElementsByTagName ('copy-hook-start');
  my $end_tag   = $copy_tag->getElementsByTagName ('copy-hook-end');

  if (! $start_tag || ! $end_tag)
  {
    print "Assertion Error: A <copy> element should have a \
           <copy-hook-start> tag and <copy-hook-end> tag \n";
    exit (1);
  }

  # Get the <dest-hook> tag that indicates the destination where the
  # code between the start and end tags will be placed.
  my $dest_hook_tag   = $copy_tag->getElementsByTagName ('dest-hook');
  if (! $dest_hook_tag)
  {
    print "Assertion Error: <copy-from-source> should have a <dest-hook> \
           tag that dictates where in the source file the code should be \
           placed. \n";
    exit (1);
  }

  # Remove any starting and trailing white spaces
  chomp ($dest_hook_tag);

  # We have everything we need! Do the copy
  my $start_tag_name = $start_tag->item(0)->getFirstChild->getNodeValue;
  my $end_tag_name   = $end_tag->item(0)->getFirstChild->getNodeValue;
  my $dest_tag_name  = $dest_hook_tag->item(0)->getFirstChild->getNodeValue;

  # First we add the FOCUS prepend tags
  $start_tag_name = $FOCUS_PREPEND_TAG . $start_tag_name;
  $end_tag_name   = $FOCUS_PREPEND_TAG . $end_tag_name;
  $dest_tag_name  = $FOCUS_PREPEND_TAG . $dest_tag_name;

  # Step 1: Iterate over the target file till the
  # dest-hook is found in that file
  my $copy_file_name_tmp = $copy_file_name . "tmp";
  open (OUT, ">". $copy_file_name_tmp) ||
    die "cannot open temporary file for modying file:" . $copy_file_name;
  open (IN, "<" . $copy_file_name) ||
    die "cannot open file $copy_file_name specified in the <file> tag \n";

  my $dest_tag_found = 0; #check if tag matched
  foreach my $line (<IN>)
  {
    if ($line =~ /$dest_tag_name/)
    { $dest_tag_found = 1; print OUT $line; last; }

    print OUT $line;
  }
  close (IN);

  # If we reached the end of file before finding the tag!
  if (! $dest_tag_found)
  {
    print "\n Error: <dest-hook> tag missing in file .. aborting \n";
    close (DEST);
    close (IN);
    close (OUT);
    unlink ($copy_file_name_tmp);
    exit (1);
  }

  # Step 2: Now look in the destination file and look for the hooks
  # where one needs to copy. There could be multiple places where the
  # hook can be present. E.g.
  # .......
  # //@@ COPY_START_HOOK
  # ....
  # ....
  # //@@ COPY_END_HOOK
  # ....
  # ....
  # //@@ COPY_START_HOOK
  # ....
  # ....
  # //@@ COPY_END_HOOK
  # Handle this case

  my $line_matched = 0;
  my $start_copying = 0; # initially do not copy
  foreach my $line (<DEST>)
  {
    # Check if the line matches the start tag
    if ($line =~/$start_tag_name/)
    {
      $line_matched += 1;
      $start_copying = 1;
    }
    else
    {
      # Check if the line matches the end tag
      if ($line =~/$end_tag_name/)
      {
        # check if the start tag matched!
        if (! $line_matched)
        {
          print "Assertion error: <copy-hook-end> tag misplaced with \
                 the <copy-hoook-source> \n";
          close (DEST);
          close (IN);
          close (OUT);
          unlink ($copy_file_name_tmp);
          exit (1);
        }

        # decrement the count for nested tags
        $line_matched -= 1;
        if (! $line_matched )
          { $start_copying = 0; }
      }
      else
      {
        # Print out the line
        if ($start_copying)
          { print OUT $line; }
      }
    }
  }

  # At the end of this loop line_matched should be 0
  if ($line_matched)
  {
    print "Error: in $dest_file_name, number of <copy-hook-source> tags \
           did not match the number of <copy-hook-end> tags. Reverting \
           changes. \n";
    close (DEST);
    close (IN);
    close (OUT);
    unlink ($copy_file_name_tmp);
    exit (1);
  }

  # Step 3: Now copy data after the tag in the original file onto the destination
  # file.
  open (IN, "<" . $copy_file_name) ||
    die "cannot open file $copy_file_name specified in the <file> tag \n";
  $dest_tag_found = 0; #used as a flag
  foreach my $line (<IN>)
  {
    if ($dest_tag_found)
    { print OUT $line; }

    # If the hook is found, then don't write the hook onto OUT
    # as it would have been written earlier
    if (! $dest_tag_found &&
        $line =~ /$dest_tag_name/)
      { $dest_tag_found = 1; }
  }

  # Normal exit path
  close (IN);
  close (OUT);
  close (DEST);

  # Rename the tmp file to the file modified
  rename ($copy_file_name_tmp, $copy_file_name);
}

#################################################################
# commit_files: A procedure to commit all the copy files that
# were specialized back to the orginal files.
#################################################################
sub commit_files
{
  my ($path_name, $output_path_name, @files) = @_;

  # iterate over the file_name_list
  foreach my $file (@files)
  {
    # <file name="....">
    my $file_name = $file->getAttribute('name');

    # output_path == input_path then do an in place
    # substitution.
    if ($output_path_name eq $path_name)
    {
      rename ($path_name . "/" . $file_name . "copy",
              $path_name . "/" . $file_name);
    }
    else
    {
      # Check if the path_name exists. The path name
      # corresponds to a directory. So create it if it does
      # not exist.
      if (! -d $output_path_name)
      {
        #@@? Need to revert the *copy files?
        mkpath ($output_path_name, 0, 0744) ||
          die "cannot create $output_path_name: commit files failed! \n";
      }

      # move the specialized file to the output directory
      rename ($path_name . "/" . $file_name . "copy",
              $output_path_name . "/" . $file_name);
    }
  }
}

#### Main ########################################################
# Specialize_Component
# procedure to execute the transformations specified in the
# specialization file
##################################################################
sub Specialize_Components
{
  # Get the command line arguments
  my ($prefix_path, $spl_file, $output_prefix) = @_;

  my $parser = XML::DOM::Parser->new();
  my $doc = $parser->parsefile($spl_file);

  # Check if the prefix path ends with a / or not
  # if it does not then manually add the / to it
  my $last = substr ($prefix_path, -1);
  if ($last ne "/")
  { $prefix_path = $prefix_path . "/"; }

  # Entry Point: <transform> element
  foreach my $transform ($doc->getElementsByTagName('transform'))
  {
    # <module tags>
    foreach my $module ($transform->getElementsByTagName('module'))
    {
      # Complete path name to the module
      my $module_name = $module->getAttribute('name');
      my $path_name = $prefix_path . $module_name;

      # <file tags>
      my @files = $module->getElementsByTagName('file');
      foreach my $file (@files)
      {
	# <file name="....">
	my $file_name = $file->getAttribute('name');

	# Rather than modifying the files directly, make a local
	# copy of the files and then transform them and commit
	# if there is a file called foo we make a file foo_copy
	my $file_path_copy = $path_name . "/" . $file_name . "copy";
	my $file_path_name = $path_name . "/" . $file_name;

	copy ($file_path_name, $file_path_copy);

	# Diagnostic comment
	print "Instrumenting $file_name ..........";

        # <comment> ... </comment>
        my @comment_list = $file->getElementsByTagName ('comment');
        foreach my $comment (@comment_list)
        { Visit_Comment ($comment, $file_path_copy); }

        # <copy-from-source> ... </copy-from-source>
        my @copy_from_source_files =
          $file->getElementsByTagName ('copy-from-source');
        foreach my $copy_from_source (@copy_from_source_files)
        {
          Visit_Copy ($copy_from_source,
                      $file_path_copy,
                      $module_name,
                      $prefix_path);
        }

	# <remove> ... </remove>
	my @remove_list = $file->getElementsByTagName ('remove');
        foreach my $remove (@remove_list)
	{ Visit_Remove ($remove, $file_path_copy); }

	# <substitute ... </substitute>
	my @substitute_list = $file->getElementsByTagName ('substitute');
	foreach my $substitute (@substitute_list)
	{ Visit_Substitute ($substitute, $file_path_copy); }

	# <add> <hook> ...... </hook> <add>
	my @add_list = $file->getElementsByTagName ('add');
	foreach my $add (@add_list)
	{ Visit_Add ($add, $file_path_copy); }

	# Everything went well.. Print success
	print " [done] \n";
      }
    }

    # At this point all the specializations in all the modules have
    # succeeded. It is at this point that we need to commit the
    # specializations in each of the modules. That is move the temporary
    # file that we created to the main file that was specialized.
    # This also means that we need another loop and do the same thing
    # as above....
    # <module tags>
    foreach my $module ($transform->getElementsByTagName('module'))
    {
      # Complete path name to the module
      my $module_name = $module->getAttribute('name');
      my $path_name = $prefix_path . $module_name;

      # Output path name: append output_prefix to the
      # current module name. Append "/" to create a
      # directory like /foo/bar/baz/
      my $output_path = $output_prefix . "/" . $module_name;

      # <file tags>
      my @files = $module->getElementsByTagName('file');

      # commit the files
      commit_files ($path_name, $output_path, @files);
    }
  }
}

####
# Requiured for a module
####
1;