source: trunk/nsa1/perllib/plugins/BRSPlug.pm@ 3353

Last change on this file since 3353 was 3353, checked in by sjboddie, 22 years ago

Initial revision
  • Property svn:keywords set to Author Date Id Revision
File size: 25.2 KB
RevLine 
[3353]1
2# plugin which processes an the BBC Sound archive exported in an ASCII format
3
4package BRSPlug;
5
6use BasPlug;
7use ghtml;
8
9sub BEGIN
10{
11 @ISA = ('BasPlug');
12 unshift (@INC, "$ENV{'GSDLCOLLECTDIR'}/perllib");
13}
14
15%Exclude = ();
16
17
18# Note: sext is short for scrollable text
19
20#field_id label disp_type crit_type width height brs_para
21#----------------------------------------------------------------
22#10 sport prdcr text text 30 1 T006
23#1 text sext text 40 16 TEXT
24#16 scol ref text text text 30 1 SCOL
25#19 date text date 10 1 D001
26#25 Item title text text 20 1 T001
27#26 B/W Seqs text text 30 1 S001
28#27 Medium text text 30 1 S002
29#28 shot type text text 30 1 S003
30#29 B/W Prog/Item text text 30 1 S004
31#30 Seqs text text 10 1 S005
32#31 Format text text 30 1 S006
33#32 prog/item text text 30 1 S007
34#35 reg libno text text 30 1 S008
35#36 reg tape no text text 30 1 S009
36#37 C Indicator text text 30 1 S010
37#38 C Holder text text 30 1 T002
38#39 cprd ind text text 30 1 S011
39#40 cprd name text text 30 1 T003
40#44 reference sext text 30 5 R001
41#49 prog num text text 10 1 PRNO
42#59 news title text text 30 1 T005
43#65 cat num text text 10 1 CATN
44#72 Record number text text 30 1 T007
45#73 rx_date text date 10 1 S013
46#74 Music performer text text 30 2 T008
47#75 Composer text text 30 2 T009
48#76 mono/stereo text text 30 1 S014
49#77 music medium text text 30 1 S015
50#82 Sound Tech text text 30 1 S016
51#83 Music publisher text text 30 1 S017
52#84 music tape text text 30 1 T012
53#89 catalogue text text 3 1 CODE
54#104 subcat text text 10 1 SUBC
55#106 prog title text text 40 1 TTLE
56#109 screen type text text 10 1 DOCT
57#110 stock title text text 30 1 T013
58#113 stock ln 4 text text 30 1 T015
59#114 stock lib 1 text text 30 1 S020
60#115 stock lib 2 text text 30 1 S021
61#----------------------------------------------------------------
62
63
64my @brs_field_table
65 = (
66 { field_name => "TTLE", field_id => 106, label => "Prog title",
67 disp_type => "text", crit_type => "text",
68 width => 40, height => 1 },
69 { field_name => "T001", field_id => 25, label => "Item title",
70 disp_type => "text", crit_type => "text",
71 width => 20, height => 1 },
72 { field_name => "T005", field_id => 59, label => "News title",
73 disp_type => "text", crit_type => "text",
74 width => 30, height => 1 },
75 { field_name => "T013", field_id => 110, label => "Stock title",
76 disp_type => "text", crit_type => "text",
77 width => 30, height => 1 },
78 { field_name => "T007", field_id => 72, label => "Record number",
79 disp_type => "text", crit_type => "text",
80 width => 30, height => 1 },
81 { field_name => "TEXT", field_id => 1, label => "Text",
82 disp_type => "scrl", crit_type => "text",
83 width => 40, height => 16 },
84
85 { field_name => "T006", field_id => 10, label => "Sport prdcr",
86 disp_type => "text", crit_type => "text",
87 width => 30, height => 1 },
88 { field_name => "SCOL", field_id => 16, label => "Scol ref text",
89 disp_type => "text", crit_type => "text",
90 width => 30, height => 1 },
91 { field_name => "D001", field_id => 19, label => "Date",
92 disp_type => "text", crit_type => "date",
93 width => 10, height => 1 },
94 { field_name => "S001", field_id => 26, label => "B/W Seqs",
95 disp_type => "text", crit_type => "text",
96 width => 30, height => 1 },
97 { field_name => "S002", field_id => 27, label => "Medium",
98 disp_type => "text", crit_type => "text",
99 width => 30, height => 1 },
100 { field_name => "S003", field_id => 28, label => "Shot type",
101 disp_type => "text", crit_type => "text",
102 width => 30, height => 1 },
103 { field_name => "S004", field_id => 29, label => "B/W Prog/Item",
104 disp_type => "text", crit_type => "text",
105 width => 30, height => 1 },
106 { field_name => "S005", field_id => 30, label => "Seqs",
107 disp_type => "text", crit_type => "text",
108 width => 10, height => 1 },
109 { field_name => "S006", field_id => 31, label => "Format",
110 disp_type => "text", crit_type => "text",
111 width => 30, height => 1 },
112 { field_name => "S007", field_id => 32, label => "Prog/item",
113 disp_type => "text", crit_type => "text",
114 width => 30, height => 1 },
115 { field_name => "S008", field_id => 35, label => "Reg libno",
116 disp_type => "text", crit_type => "text",
117 width => 30, height => 1 },
118 { field_name => "S009", field_id => 36, label => "Reg tape no",
119 disp_type => "text", crit_type => "text",
120 width => 30, height => 1 },
121 { field_name => "S010", field_id => 37, label => "C Indicator",
122 disp_type => "text", crit_type => "text",
123 width => 30, height => 1 },
124 { field_name => "T002", field_id => 38, label => "C Holder",
125 disp_type => "text", crit_type => "text",
126 width => 30, height => 1 },
127 { field_name => "S011", field_id => 39, label => "Cprd ind",
128 disp_type => "text", crit_type => "text",
129 width => 30, height => 1 },
130 { field_name => "T003", field_id => 40, label => "Cprd name",
131 disp_type => "text", crit_type => "text",
132 width => 30, height => 1 },
133 { field_name => "R001", field_id => 44, label => "Reference",
134 disp_type => "scrl", crit_type => "text",
135 width => 30, height => 5 },
136 { field_name => "PRNO", field_id => 49, label => "Prog num",
137 disp_type => "text", crit_type => "text",
138 width => 10, height => 1 },
139 { field_name => "CATN", field_id => 65, label => "Cat num",
140 disp_type => "text", crit_type => "text",
141 width => 10, height => 1 },
142 { field_name => "S013", field_id => 73, label => "Rx_date",
143 disp_type => "text", crit_type => "date",
144 width => 10, height => 1 },
145 { field_name => "T008", field_id => 74, label => "Music performer",
146 disp_type => "text", crit_type => "text",
147 width => 30, height => 2 },
148 { field_name => "T009", field_id => 75, label => "Composer",
149 disp_type => "text", crit_type => "text",
150 width => 30, height => 2 },
151 { field_name => "S014", field_id => 76, label => "Mono/stereo",
152 disp_type => "text", crit_type => "text",
153 width => 30, height => 1 },
154 { field_name => "S015", field_id => 77, label => "Music medium",
155 disp_type => "text", crit_type => "text",
156 width => 30, height => 1 },
157 { field_name => "S016", field_id => 82, label => "Sound Tech",
158 disp_type => "text", crit_type => "text",
159 width => 30, height => 1 },
160 { field_name => "S017", field_id => 83, label => "Music publisher",
161 disp_type => "text", crit_type => "text",
162 width => 30, height => 1 },
163 { field_name => "T012", field_id => 84, label => "Music tape",
164 disp_type => "text", crit_type => "text",
165 width => 30, height => 1 },
166 { field_name => "CODE", field_id => 89, label => "Catalogue",
167 disp_type => "text", crit_type => "text",
168 width => 3, height => 1 },
169 { field_name => "SUBC", field_id => 104, label => "Subcat",
170 disp_type => "text", crit_type => "text",
171 width => 10, height => 1 },
172 { field_name => "DOCT", field_id => 109, label => "Screen type",
173 disp_type => "text", crit_type => "text",
174 width => 10, height => 1 },
175 { field_name => "T015", field_id => 113, label => "Stock ln 4",
176 disp_type => "text", crit_type => "text",
177 width => 30, height => 1 },
178 { field_name => "S020", field_id => 114, label => "Stock lib 1",
179 disp_type => "text", crit_type => "text",
180 width => 30, height => 1 },
181 { field_name => "S021", field_id => 115, label => "Stock lib 2",
182 disp_type => "text", crit_type => "text",
183 width => 30, height => 1 }
184 );
185
186
187my @brs_title_list = ("TTLE", "T001", "T005", "T013", "T007", "zzTI");
188my %cat_num_list = ();
189
190sub new {
191 my ($class) = @_;
192 my $self = new BasPlug ($class, @_);
193
194 return bless $self, $class;
195}
196
197sub get_default_process_exp {
198 my $self = shift (@_);
199
200 return q^(?i)\.brs$^;
201}
202
203my $brs_doc_count = 0;
204my $brs_dot_count = 0;
205my $brs_line_no = 0;
206
207sub brs_error
208{
209 my ($file, $mess, $outhandle) = @_;
210
211 print $outhandle "Malformed BRS recorded at line $brs_line_no in $file:\n";
212 print $outhandle " $mess\n";
213}
214
215sub read_brs_record
216{
217 my ($recordref, $file, $outhandle) = @_;
218
219 my $extra_trigger = '\s*>';
220 my $text_divider = "-" x 78;
221 my $text_end = "..R001";
222
223 # Print "." to signify processing if enough records have been read in
224 $brs_doc_count++;
225 if (($brs_doc_count % 10) == 0)
226 {
227 print $outhandle ".";
228 $brs_dot_count++;
229 print $outhandle "\n" if (($brs_dot_count % 80) == 0);
230 }
231
232 my $brs_rec = undef;
233 my $line = undef;
234
235 # read in the record
236 my @brs_lines = split /\n/, $$recordref;
237
238 while (scalar(@brs_lines)>0)
239 {
240 $line = shift(@brs_lines);
241 $line =~ s/\cM//g;
242
243 $brs_line_no++;
244
245 if ($line =~ m/^\.\.([A-Z]|[0-9]){4}:$/)
246 {
247 my $field_name = substr($line,2,4);
248
249 if ($field_name eq "TEXT")
250 {
251 my $text_above = "";
252 my $text_extra = "";
253 my $text_below = "";
254
255 my $add_mode = "above";
256
257 while (scalar(@brs_lines)>0)
258 {
259 last if ($brs_lines[0] =~ m/^$text_end/);
260
261 $line = shift(@brs_lines);
262 $brs_line_no++;
263
264 if ($line =~ m/^$text_divider/)
265 {
266 $add_mode = "below";
267 next;
268 }
269
270 if ($line =~ m/^$extra_trigger/)
271 {
272 $text_extra .= "$line\n";
273 $add_mode = "below";
274 next;
275 }
276
277 if ($line =~ m/^\.\.([A-Z]|[0-9]){4}:/)
278 {
279 if ($line =~ m/^\.\.TEXT/)
280 {
281 $add_mode = "above";
282 next;
283 }
284 else
285 {
286 brs_error($file, "Unexpected field $line", $outhandle);
287 # put field name back
288 unshift(@brs_lines, $line);
289 $brs_line_no--;
290 last;
291 }
292 }
293
294 if ($line !~ m/^\s+(-){10,}$/)
295 {
296 if ($add_mode eq "above")
297 {
298 $text_above .= "$line ";
299 }
300 else
301 {
302 $text_below .= "$line ";
303 }
304 }
305 }
306
307 $brs_rec->{TEXTA} .= $text_above if ($text_above ne "");
308 $brs_rec->{TEXTB} .= $text_below if ($text_below ne "");
309 $brs_rec->{TEXTE} .= $text_extra if ($text_extra ne "");
310 }
311 elsif ($field_name eq "R001")
312 {
313 # read zz fields until end of record
314
315 while (scalar(@brs_lines)>0)
316 {
317 $line = shift(@brs_lines);
318 $brs_line_no++;
319
320 if ($line =~ m/^(zz[A-Z]+)( +)(.*)/)
321 {
322 my $field_name = $1;
323 my $field_text = $3;
324
325 while (scalar(@brs_lines)>0)
326 {
327 my $line_ahead = $brs_lines[0];
328
329 last if ($line_ahead =~ m/^zz[A-Z]+/);
330
331 $line = shift(@brs_lines);
332 $brs_line_no++;
333
334 $field_text .= $line;
335 }
336
337 if (!defined($brs_rec->{$field_name}))
338 {
339 $brs_rec->{$field_name} = [$field_text];
340 }
341 else
342 {
343 push(@{$brs_rec->{$field_name}},$field_text);
344 }
345 }
346 else
347 {
348 brs_error($file, "Unexpected field $line", $outhandle);
349 }
350 }
351 }
352 else
353 {
354 my $field_entry = "";
355 while ($brs_lines[0] !~ m/^..([A-Z]|[0-9]){4}:$/)
356 {
357 $field_entry .= shift(@brs_lines);
358 $brs_line_no++;
359 last if (scalar(@brs_lines)==0);
360 }
361
362 if (!defined($brs_rec->{$field_name}))
363 {
364 $brs_rec->{$field_name} = $field_entry;
365 }
366 else
367 {
368 brs_error($file, "$field_name already defined.", $outhandle);
369 }
370 }
371 }
372 else
373 {
374 brs_error($file, "Malformed field: $line.", $outhandle);
375 }
376 }
377
378 # format the programme number if required
379 &format_prognum($brs_rec);
380
381 return ($brs_rec);
382}
383
384my $brs_processed_count = 0;
385
386sub brs_full_record_in_html
387{
388 my ($doc_obj,$cursection,$brs_rec) = @_;
389
390 my $html_table = "";
391 my $table_line = "";
392 my $cell_count = 0;
393 my $long_lines = "";
394
395 my $i;
396 for ($i=0; $i<=$#brs_field_table; $i++)
397 {
398 my $field_name = $brs_field_table[$i]->{'field_name'};
399 if (defined($brs_rec->{$field_name}))
400 {
401 my $field_label = $brs_field_table[$i]->{'label'};
402 my $field_value = $brs_rec->{$field_name};
403
404 # these fields get their own line
405 if ($field_label =~ /^(Prog|Item|News|Stock) title$/) {
406 my $safe_value = $field_value;
407 &ghtml::urlsafe ($safe_value);
408 $long_lines .= "<tr valign=top><td><b>$field_label:</b></td><td colspan=5>";
409 $long_lines .= "<a href=\"_httpquerytitle_&q=$safe_value\">$field_value</a></td></tr>\n";
410 $long_lines .= "$field_value</td></tr>\n";
411
412 } else {
413
414 if (($cell_count>0) && ($cell_count%3 == 0))
415 {
416 $html_table .= "\n<tr valign=top>\n$table_line\n</tr>\n";
417 $table_line = "";
418 }
419 $cell_count++;
420 if ($field_name eq "D001") # a Dublin core style date
421 {
422 my @mon_convert
423 = ("Jan", "Feb", "Mar", "Apr", "May", "Jun",
424 "Jul", "Aug", "Sep", "Oct", "Nov", "Dec");
425
426 my ($year,$monnum,$day)
427 = ($field_value =~ m/(\d{4})(\d{2})(\d{2})/);
428 my $moneng = $mon_convert[$monnum-1];
429
430 $field_value = "$day $moneng $year";
431
432 } elsif ($field_name eq "PRNO") {
433 my $safe_value = $field_value;
434 &ghtml::urlsafe ($safe_value);
435 $field_value = "<a href=\"_httpqueryprogname_&q=$safe_value\">$field_value</a>";
436
437 } elsif ($field_name eq "CATN") {
438 my $safe_value = $field_value;
439 &ghtml::urlsafe ($safe_value);
440 $field_value = "<a href=\"_httpquerycatnum_&q=$safe_value\">$field_value</a>";
441
442 } elsif ($field_name eq "T003") {
443 my $safe_value = $field_value;
444 &ghtml::urlsafe ($safe_value);
445 $field_value = "<a href=\"_httpqueryzzabn_&q=$safe_value\">$field_value</a>";
446 }
447
448 $table_line .= "<td><b>$field_label:</b></td><td>$field_value</td>\n";
449 }
450 }
451 }
452
453 if ($cell_count%3 != 0) {
454 $table_line .= "<td colspan=" . (3-($cell_count%3))*2 . "></td>";
455 }
456
457 $html_table .= "\n<tr>\n$table_line\n</tr>\n";
458 $html_table = "<table>\n$long_lines$html_table\n</table>\n";
459
460 $doc_obj->add_utf8_text($cursection, $html_table);
461}
462
463sub process_brs_record
464{
465 my ($processor, $brs_rec, $file, $outhandle) = @_;
466
467 if (defined($brs_rec))
468 {
469
470 # only include those records in the chosen subcats - these lines
471 # should be commented out to build the entire collection
472
473 # National Sound Archive collection
474 if (!defined ($brs_rec->{'SUBC'}) ||
475 $brs_rec->{'SUBC'} !~ /^(RADCOMP|RADIOX|RADPROG|RADNEWS|BDSPROG|UNCATRAD|RADIOREF|WILDSOUND)$/) {
476 return;
477 }
478
479 # British Film Institute collection
480# if (!defined ($brs_rec->{'SUBC'}) ||
481# $brs_rec->{'SUBC'} !~ /^(LONPROG|NEWS)$/) {
482# return;
483# }
484
485 # "the rest" collection
486# if (!defined ($brs_rec->{'SUBC'}) ||
487# $brs_rec->{'SUBC'} =~ /^(LONPROG|NEWS|RADCOMP|RADIOX|RADPROG|RADNEWS|BDSPROG|UNCATRAD|RADIOREF)$/) {
488# return;
489# }
490
491 # don't include the secret stuff ;-)
492 if (defined ($brs_rec->{'SUBC'}) && $brs_rec->{'SUBC'} eq "HISTORY") {
493 print STDERR "excluding secret stuff - line $brs_line_no\n";
494 return;
495 }
496
497
498 my $doc_obj = new doc ($file, "indexed_doc");
499 $brs_processed_count++;
500
501 my $cursection = $doc_obj->get_top_section();
502
503 my $found_match = "no";
504
505 my $pot_title;
506 foreach $pot_title ( @brs_title_list )
507 {
508 if (defined ($brs_rec->{$pot_title}))
509 {
510 my $title = "";
511
512 if ($pot_title =~ m/^zz/)
513 {
514 my $zz_join = join(" ", @{$brs_rec->{$pot_title}});
515 my @zz_split = split(" ", $zz_join);
516 map { $title .= "$_ " if ($_ !~ m/^xx/); } @zz_split;
517 }
518 else
519 {
520 $title = $brs_rec->{$pot_title};
521 }
522
523 my $tl_ref = $doc_obj->get_metadata ($cursection, "Title");
524
525 if (scalar(@$tl_ref==0))
526 {
527 $doc_obj->add_utf8_metadata ($cursection, "Title", $title);
528 }
529 else
530 {
531 my $exists = "no";
532
533 map { $exists = "yes" if ($title eq $_); } @$tl_ref;
534 if ($exists eq "no")
535 {
536 $doc_obj->add_utf8_metadata($cursection, "Title", $title);
537 }
538 }
539 $found_match = "yes";
540 }
541 }
542 if ($found_match eq "no")
543 {
544 if (defined($brs_rec->{TEXTA}))
545 {
546 my $sub_title = substr($brs_rec->{TEXTA},0,60) . " ... ";
547 $doc_obj->add_utf8_metadata ($cursection, "Title", $sub_title);
548 }
549 elsif (defined($brs_rec->{TEXTB}))
550 {
551 my $sub_title = substr($brs_rec->{TEXTB},0,60) . " ... ";
552 $doc_obj->add_utf8_metadata ($cursection, "Title", $sub_title);
553 }
554 else
555 {
556 print $outhandle " No title or text for record ending at line ";
557 print $outhandle $brs_line_no-1, " ";
558 }
559 }
560
561 if (defined($brs_rec->{'T001'})) # item title
562 {
563 $doc_obj->add_utf8_metadata ($cursection, "ItemTitle", $brs_rec->{'T001'});
564 }
565
566 if (defined($brs_rec->{'D001'})) # date
567 {
568 $doc_obj->add_utf8_metadata ($cursection, "Date", $brs_rec->{'D001'});
569 }
570 else
571 {
572 print $outhandle " No date for record ending at line ";
573 print $outhandle $brs_line_no-1, " ";
574 }
575
576 if (defined($brs_rec->{'PRNO'})) # programme number
577 {
578 $doc_obj->add_utf8_metadata ($cursection, "ProgNumber", $brs_rec->{'PRNO'});
579 }
580
581 if (defined($brs_rec->{'CATN'})) # catalogue number
582 {
583 $doc_obj->add_utf8_metadata ($cursection, "CatNum", $brs_rec->{'CATN'});
584 }
585
586 # zzAN, zzAB and T003 fields
587 if (defined($brs_rec->{'zzAB'}) || defined($brs_rec->{'zzAN'}) || defined($brs_rec->{'T003'}))
588 {
589 my $zzabn = "";
590 if (defined($brs_rec->{'zzAB'})) {
591 foreach my $a (@{$brs_rec->{'zzAB'}}) {
592 $a =~ s/[^a-zA-Z0-9]//g;
593 $zzabn .= " " . $a;
594 }
595 }
596 if (defined($brs_rec->{'zzAN'})) {
597 foreach my $a (@{$brs_rec->{'zzAN'}}) {
598 $a =~ s/[^a-zA-Z0-9]//g;
599 $zzabn .= " " . $a;
600 }
601 }
602 if (defined($brs_rec->{'T003'})) {
603 my $value = $brs_rec->{'T003'};
604 $value =~ s/[^a-zA-Z0-9]//g;
605 $zzabn .= " " . $value;
606 }
607 print STDERR "zzabn: '$zzabn'\n";
608 $doc_obj->add_utf8_metadata ($cursection, "zzabn", $zzabn);
609 }
610
611 if (defined($brs_rec->{zzN}))
612 {
613 my $name;
614 foreach $name (@{$brs_rec->{zzN}})
615 {
616 $doc_obj->add_utf8_metadata ($cursection, "People", $name);
617 }
618 }
619
620 brs_full_record_in_html($doc_obj,$cursection,$brs_rec);
621
622 if (defined($brs_rec->{TEXTA}))
623 {
624
625 my $desc_texta = "<h3>Description</h3>$brs_rec->{TEXTA}";
626 $doc_obj->add_utf8_text ($cursection, $desc_texta);
627
628 if (defined($brs_rec->{TEXTE}))
629 {
630 my $raw_texte = $brs_rec->{TEXTE};
631 $raw_texte =~ s/^\s*>\s*/<li>/mg;
632
633 my $test_empty = $raw_texte;
634 $test_empty =~ s/(<li>)+//g;
635
636 if ($test_empty ne "")
637 {
638 my $desc_texte = $raw_texte;
639 $desc_texte =~ s/^<li>(.*)$/<li><i>$1<\/i>/mg;
640 $desc_texte = "<p>Additional:<ul>$desc_texte</ul>";
641 $doc_obj->add_utf8_text ($cursection, $desc_texte);
642 }
643 }
644 }
645
646 if (defined($brs_rec->{TEXTB}))
647 {
648 my $desc_textb = "<h3>Comments</h3>$brs_rec->{TEXTB}";
649 $doc_obj->add_utf8_text($cursection, $desc_textb);
650 }
651
652 my $full_text = "";
653 $full_text .= "$brs_rec->{TEXTA}\n" if (defined($brs_rec->{TEXTA}));
654 $full_text .= "$brs_rec->{TEXTE}\n" if (defined($brs_rec->{TEXTE}));
655 $full_text .= "$brs_rec->{TEXTB}\n" if (defined($brs_rec->{TEXTB}));
656
657 my @zz_list = ( "zzPG", "zzLO", "zzN" );
658 my $zz;
659 foreach $zz ( @zz_list)
660 {
661 if (defined($brs_rec->{$zz}))
662 {
663 my $filtered_text = "";
664
665 my $name;
666 foreach $name (@{$brs_rec->{$zz}})
667 {
668 my @split_zz = split(' ',$name);
669 map { $filtered_text .= "$_ " if ($_ =~ m/^xx/) } @split_zz
670 }
671
672 $full_text .= "$filtered_text\n";
673 }
674 }
675
676 # format zz fields (tail end of record)
677 my $zz_html = "<table>\n";
678
679 my $pot_zz;
680 foreach $pot_zz (keys %{$brs_rec})
681 {
682 if ($pot_zz =~ m/^zz/)
683 {
684 my $zz = $pot_zz;
685 my $name;
686 foreach $name (@{$brs_rec->{$zz}})
687 {
688 if ($zz eq "zzN") {
689 my $safe_name = $name;
690 &ghtml::urlsafe ($safe_name);
691 $zz_html .= "<tr><td><b>$zz:</b></td><td><a href=\"_httpquerypeople_&q=$safe_name\">$name</a></td></tr>\n";
692 } elsif ($zz =~ /^zzA[BN]$/) {
693 my $safe_name = $name;
694 &ghtml::urlsafe ($safe_name);
695 $zz_html .= "<tr><td><b>$zz:</b></td><td><a href=\"_httpqueryzzabn_&q=$safe_name\">$name</a></td></tr>\n";
696
697 } else {
698 $zz_html .= "<tr><td><b>$zz:</b></td><td>$name</td></tr>\n";
699 }
700 }
701 }
702 }
703 $zz_html .= "</table>\n";
704 $doc_obj->add_utf8_text($cursection, $zz_html);
705
706 # add OID - we'll use the catalog number (hoping it's unique)
707 my $cat_num = $brs_rec->{'CATN'};
708 if (!defined $cat_num) {
709 die "bugger!!\n";
710 }
711 if (defined ($cat_num_list{$cat_num})) {
712 print $outhandle "WARNING: catalog number $cat_num used more than once\n";
713 }
714 $doc_obj->set_OID ("bbc" . $cat_num);
715 $cat_num_list{$cat_num} = 1;
716
717 # process the document
718 $processor->process($doc_obj);
719 }
720 else
721 {
722 print $outhandle "BRS record empty\n";
723 }
724
725}
726
727sub read {
728 my $self = shift (@_);
729 my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
730 my $outhandle = $self->{'outhandle'};
731
732 my $filename = &util::filename_cat($base_dir, $file);
733# return 0 if $self->{'block_exp'} ne "" && $filename =~ /$self->{'block_exp'}/;
734 if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
735 return undef;
736 }
737# my $plugin_name = ref ($self);
738 $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
739
740 # create a new document
741# my $doc_obj = new doc ($filename, "indexed_doc");
742
743 # read in file ($text will be in utf8)
744# my $text = "";
745# $self->read_file ($filename, \$text);
746
747# if ($text !~ /\w/) {
748# print $outhandle "$plugin_name: ERROR: $file contains no text\n" if $self->{'verbosity'};
749# return 0;
750# }
751
752 # text is always plain ascii
753 undef $/;
754 open (FILE, $filename) || die;
755 my $text = <FILE>;
756 close FILE;
757 $/ = "\n";
758
759
760 # include any metadata passed in from previous plugins
761 # note that this metadata is associated with the top level section
762# $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
763
764 print $outhandle "BBC Sound Archive Plug for BRS format: processing $file\n"
765 if $self->{'verbosity'} > 1;
766
767 my @records = split /\*\*\* BRS DOCUMENT BOUNDARY \*\*\*\s+/, $text;
768 $text = "";
769
770 foreach $record (@records) {
771 next if $record !~ /\w/; # first record will be empty
772 my $brs_rec = &read_brs_record(\$record, $file, $self->{'outhandle'});
773 &process_brs_record ($processor, $brs_rec, $file, $self->{'outhandle'});
774 }
775
776 print $outhandle "\nNumber of BRS records = $brs_doc_count\n";
777 print $outhandle "Number of BRS records processed = $brs_processed_count\n";
778
779 return 1; # processed the file
780}
781
782sub end {
783 my $self = shift (@_);
784 my ($processor) = @_;
785
786 $processor->close_file_output() if defined $processor;
787}
788
789sub format_prognum {
790 my ($brs_rec) = @_;
791
792 return unless defined $brs_rec->{'PRNO'};
793
794 my $old_num = $brs_rec->{'PRNO'};
795
796 if (defined $brs_rec->{'magazine'}) {
797 if ($brs_rec->{'PRNO'} =~ /^\S\S /) { # space at position 3
798 if ($brs_rec->{'magazine'} =~ /(\d+)/) {
799 # algorithm A
800 my $magnumber = $1;
801 $brs_rec->{'PRNO'} =~ /(\S\S) (\S\S)(\S+)/;
802 $brs_rec->{'PRNO'} = $2 . $1 . $3 . $magnumber;
803 } else {
804 # common algorithm
805 $brs_rec->{'PRNO'} =~ /(\S\S) (\S\S)(\S+)/;
806 $brs_rec->{'PRNO'} = $2 . $1 . $3;
807 }
808 }
809 } else {
810 if ($brs_rec->{'PRNO'} =~ /^\S\S / && $brs_rec->{'PRNO'} !~ /:/) { # space at position 3 and no colon
811 # common algorithm
812 $brs_rec->{'PRNO'} =~ /(\S\S) (\S\S)(\S+)/;
813 $brs_rec->{'PRNO'} = $2 . $1 . $3;
814 } elsif ($brs_rec->{'PRNO'} =~ /^(\S):(\S\S) (\S\S)(\S+)/) { # colon at position 2 and space at position 5
815 # algorithm B
816 $brs_rec->{'PRNO'} = $3 . $2 . $4 . $1;
817 }
818 }
819
820# if ($brs_rec->{'PRNO'} ne $old_num) {
821# print STDERR "\n$old_num ... " . $brs_rec->{'PRNO'} . "\n";
822# }
823}
824
8251;
Note: See TracBrowser for help on using the repository browser.