1: #!/usr/local/bin/perl -w
2:
3: use strict;
4: use XML::LibXML;
5:
6: use lib '/usr/local/mpiwg/archive';
7: use MPIWGStor;
8:
9: # make output unbuffered
10: $|=1;
11:
12: # program version
13: my $version = "0.1.1 (1.6.2005)";
14: logger("INFO", "makemeta-lib $version");
15:
16: ###########################################
17: # mappings
18:
19: # generic mappings at top level
20: my %gen_map = (
21: 'Device' => 'meta/image-acquisition/device',
22: 'Image_Type' => 'meta/image-acquisition/image-type',
23: 'Production_Comment' => 'meta/image-acquisition/production-comment',
24: 'Postproduction' => 'meta/image-acquisition/production-comment',
25: 'Language' => 'meta/lang'
26: );
27: # sub type switch tag
28: my %type_map = (
29: 'Reference_Type' => 'meta/bib@type'
30: );
31: # sub type mappings
32: my %subtype_map = (
33: 'Book' => {
34: '_name' => 'book',
35: 'Author' => 'meta/bib/author',
36: 'Title' => 'meta/bib/title',
37: 'Year' => 'meta/bib/year',
38: 'Place_Published' => 'meta/bib/city',
39: 'Publisher' => 'meta/bib/publisher',
40: 'Edition' => 'meta/bib/edition'
41: },
42: 'Journal Article' => {
43: '_name' => 'journal-article',
44: 'Author' => 'meta/bib/author',
45: 'Title' => 'meta/bib/title',
46: 'Year' => 'meta/bib/year',
47: 'Secondary_Title' => 'meta/bib/journal',
48: 'Volume' => 'meta/bib/volume',
49: 'Number' => 'meta/bib/issue',
50: 'Pages' => 'meta/bib/pages'
51: },
52: 'In Book' => {
53: '_name' => 'inbook',
54: 'Author' => 'meta/bib/author',
55: 'Title' => 'meta/bib/title',
56: 'Year' => 'meta/bib/year',
57: 'Secondary_Title' => 'meta/bib/book-title',
58: 'Pages' => 'meta/bib/pages'
59: },
60: 'Newspaper Article' => {
61: '_name' => 'newspaper-article',
62: 'Author' => 'meta/bib/author',
63: 'Title' => 'meta/bib/title',
64: 'Year' => 'meta/bib/year',
65: 'Secondary_Title' => 'meta/bib/newspaper',
66: 'Place_Published' => 'meta/bib/city',
67: 'Number' => 'meta/bib/issue-date',
68: 'Pages' => 'meta/bib/pages'
69: },
70: 'Edited Book' => {
71: '_name' => 'edited-book',
72: 'Author' => 'meta/bib/editor',
73: 'Title' => 'meta/bib/title',
74: 'Year' => 'meta/bib/year',
75: 'Place_Published' => 'meta/bib/city',
76: 'Publisher' => 'meta/bib/publisher',
77: 'Edition' => 'meta/bib/edition'
78: },
79: 'Manuscript' => {
80: '_name' => 'manuscript',
81: 'Author' => 'meta/bib/author',
82: 'Title' => 'meta/bib/title',
83: 'Year' => 'meta/bib/year',
84: 'Place_Published' => 'meta/bib/location',
85: }
86: );
87: # language element
88: my $lang_field = 'Language';
89: # languages to iso codes
90: my %lang_map = (
91: 'German' => 'de',
92: 'English' => 'en',
93: 'Italian' => 'it',
94: 'French' => 'fr',
95: 'Latin' => 'la',
96: 'Japanese' => 'ja',
97: 'Spanish' => 'es'
98: );
99: # storage fields
100: my $arch_id_field = 'ID_Archive';
101: my $online_url_field = 'URL';
102:
103: #######################################################
104: # internal parameters
105: #
106:
107: # storage
108: my $lib_arch_dir = '/mpiwg/archive/data/library';
109: my $lib_online_dir = '/mpiwg/online/permanent';
110:
111: # read command line parameters
112: my $args = MPIWGStor::parseargs;
113:
114: # debug level
115: $debug = (exists $$args{'debug'}) ? $$args{'debug'} : 0;
116:
117: # use einstein-cw mode
118: my $cw_mode = (exists $$args{'cw-mode'}) ? $$args{'cw-mode'} : 0;
119:
120: # index.meta namespace (not really implemented!)
121: my $namespace = "";
122:
123:
124: my $xml_changed = 0;
125: my $errcnt = 0;
126: my $warncnt = 0;
127:
128: #######################################################
129: # check parameters that were passed to the program
130: #
131: my $infile = $$args{'path'};
132: if (! $infile) {
133: logger("ABORT", "no input file given!");
134: exit 1;
135: }
136: # strip double slashes
137: $infile =~ s/\/\//\//;
138: if (! -f $infile) {
139: logger("ABORT", "input file \'$infile\' doesn't exist!");
140: exit 1;
141: }
142:
143:
144: #######################################################
145: # subroutines
146: #
147:
148: sub find_cw_dir {
149: my ($input_node) = @_;
150: my $src_dir = find_online_dir($input_node, '/mpiwg/archive/data/library/inbox/zwischen_backup');
151: my $dest_id = $input_node->findvalue("fm:$arch_id_field");
152: if (! $dest_id) {
153: logger('ERROR', "no ID field for einstein-cw entry");
154: $errcnt++;
155: return;
156: }
157: my $dir = "$lib_arch_dir/$dest_id";
158: logger('DEBUG', "moving $src_dir to $dir");
159: if (rename $src_dir, $dir) {
160: if (-d $dir) {
161: logger('DEBUG', "directory $dir OK");
162: return $dir;
163: }
164: } else {
165: logger('ABORT', "unable to rename directory $src_dir to $dir!");
166: exit 1;
167: }
168: return;
169: }
170:
171: sub find_online_dir {
172: my ($input_node, $base_dir) = @_;
173: $base_dir = $lib_online_dir unless ($base_dir);
174:
175: my $online_url = $input_node->findvalue("fm:$online_url_field");
176: if ($online_url =~ /fn=permanent\/(.+)\/pageimg/) {
177: my $online_dir = $1;
178: #logger("DEBUG", "dir: $base_dir/$online_dir");
179: my $dir = "$base_dir/$online_dir";
180: if (-d $dir) {
181: logger('DEBUG', "directory $dir exists");
182: return $dir;
183: }
184: }
185: return;
186: }
187:
188: sub find_arch_dir {
189: my ($input_node) = @_;
190: my $dir = "";
191:
192: my $bib_dir = $input_node->findvalue("fm:$arch_id_field");
193: #logger('DEBUG', "bibdir: $bib_dir");
194: if ($bib_dir) {
195: $dir = "$lib_arch_dir/$bib_dir";
196: if (-d $dir) {
197: logger('DEBUG', "directory $dir exists");
198: return $dir;
199: }
200: }
201: return;
202: }
203:
204:
205: sub convert_bib {
206: my ($input_node, $index_root, $index_doc) = @_;
207: my $cnt = 0;
208: my $type = "";
209: my $type_path = "";
210:
211: # process general stuff first
212: foreach my $n ($input_node->getChildNodes()) {
213: my $name = $n->nodeName();
214: my $val = $n->textContent();
215: #logger('DEBUG', " NODE: $name = '$val'");
216: if (exists $gen_map{$name}) {
217: # is a general field
218: if ($name eq $lang_field) {
219: # language field -> convert to iso code
220: if (exists $lang_map{$val}) {
221: $val = $lang_map{$val};
222: } else {
223: logger('ERROR', "unknown language: $val! skipping...");
224: $errcnt++;
225: return 0;
226: }
227: }
228: create_element_path($gen_map{$name}, $index_root, $namespace)
229: ->appendTextNode($val);
230: $cnt++;
231: } elsif (exists $type_map{$name}) {
232: # is a type field
233: $type_path = $type_map{$name};
234: $type = $val;
235: # check with known types
236: if (exists $subtype_map{$val}) {
237: my $indextype = $subtype_map{$val}->{'_name'};
238: create_element_path("$type_path=$indextype", $index_root, $namespace);
239: $cnt++;
240: } else {
241: logger('ERROR', 'unknown bib type $val! skipping...');
242: $errcnt++;
243: return 0;
244: }
245: }
246: }
247: # process sub type fields
248: if ($type) {
249: foreach my $n ($input_node->getChildNodes()) {
250: my $name = $n->nodeName();
251: my $val = $n->textContent();
252: #logger('DEBUG', " NODE: $name = '$val'");
253: if (exists $subtype_map{$type}->{$name}) {
254: create_element_path($subtype_map{$type}->{$name}, $index_root, $namespace)
255: ->appendTextNode($val);
256: $cnt++;
257: }
258: }
259: }
260: return $cnt;
261: }
262:
263:
264:
265: sub process_all_fm_entries {
266: my ($input_root) = @_;
267: my $cnt = 0;
268:
269: foreach my $n ($input_root->findnodes('fm:ROW')) {
270: logger('INFO', "processing entry $cnt ...");
271: process_fm_entry($n);
272: }
273: }
274:
275:
276: sub process_fm_entry {
277: my ($input_node) = @_;
278: my $index_doc = XML::LibXML::Document->createDocument('1.0', 'UTF-8');
279: my $index_root = $index_doc->createElementNS($namespace, 'resource');
280: $index_root->addChild($index_doc->createAttributeNS($namespace, 'version', '1.1'));
281: $index_root->addChild($index_doc->createAttributeNS($namespace, 'type', 'MPIWG'));
282: $index_doc->setDocumentElement($index_root);
283:
284: # try to find the document directory
285: my $doc_dir = "";
286: if ($cw_mode) {
287: $doc_dir = find_cw_dir($input_node);
288: } else {
289: $doc_dir = find_arch_dir($input_node);
290: }
291: if (! $doc_dir) {
292: logger('ERROR', "document directory not found! skipping...");
293: $errcnt++;
294: return;
295: }
296:
297: # add standard stuff to index.meta
298: my ($docname, $docpath) = split_file_path($doc_dir);
299: # name and date
300: create_text_path('name', $docname, $index_root, $namespace);
301: create_text_path('archive-path', $doc_dir, $index_root, $namespace);
302: create_text_path('archive-creation-date', stime(time), $index_root, $namespace);
303: create_text_path('creator', 'digigroup', $index_root, $namespace);
304: create_text_path('description', 'a scanned document', $index_root, $namespace);
305: # acquisition
306: create_text_path('meta/acquisition/date', stime(time), $index_root, $namespace);
307: create_text_path('meta/acquisition/provider/provider-id', 'digigroup', $index_root, $namespace);
308: create_text_path('meta/acquisition/provider/address', 'Max Planck Institute for the History of Science', $index_root, $namespace);
309: # media
310: create_text_path('media-type', 'image', $index_root, $namespace);
311: create_text_path('meta/content-type', 'scanned document', $index_root, $namespace);
312:
313: # convert bib entries
314: my $cnt = convert_bib($input_node, $index_root, $index_doc);
315: if ($cnt == 0) {
316: # error or nothing to convert
317: logger('ERROR', "no bibliographic metadata!");
318: $errcnt++;
319: return;
320: }
321:
322: # write new index.meta file
323: write_xml($index_doc, "$doc_dir/index.meta");
324:
325: }
326:
327:
328:
329:
330:
331: #######################################################
332: # Main
333: #
334:
335: # load filemaker xml dump
336: my ($input_doc, $input_root) = read_xml($infile);
337: # set namespace prefix
338: my $fm_namespace = $input_root->namespaceURI();
339: $input_root->setNamespace($fm_namespace, 'fm', 1);
340:
341: process_all_fm_entries($input_root);
342:
343:
344: logger("INFO", "$warncnt warnings");
345: logger("INFO", "$errcnt errors");
346: if ($errcnt > 0) {
347: logger("ABORT", "there were errors!");
348: exit 1;
349: } else {
350: logger("DONE", "done something successfully!");
351: }
352:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/cvs/cvsweb/icons/back.gif){kind=icon}
Return to makemeta-lib.pl CVS log ![[TXT]](/cvs/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvs/cvsweb/icons/dir.gif){kind=icon}
Up to [Repository] / foxridge-archiver