source: trunk/gsdl/perllib/strings.properties@ 11945

Last change on this file since 11945 was 11945, checked in by kjdon, 18 years ago

added exportcol.noinstall

  • Property svn:keywords set to Author Date Id Revision
File size: 56.7 KB
Line 
1#
2# Resource bundle description
3#
4
5Language.code:en
6Language.name:English
7
8OutputEncoding.unix:iso_8859_1
9OutputEncoding.windows:iso_8859_1
10
11
12#
13# Common output messages
14#
15
16common.cannot_create_file:ERROR: Can't create file %s
17
18common.cannot_find_cfg_file:ERROR: Can't find the configuration file %s
19
20common.cannot_open:ERROR: Can't open %s
21
22common.cannot_open_fail_log:ERROR: Can't open fail log %s
23
24common.cannot_open_output_file:ERROR: Can't open output file %s
25
26common.cannot_read:ERROR: Can't read %s
27
28common.cannot_read_file:ERROR: Can't read file %s
29
30common.general_options:general options (for %s)
31
32common.must_be_implemented:function must be implemented in sub-class
33
34common.options:options
35
36common.processing:processing
37
38common.specific_options:specific options
39
40common.usage:Usage
41
42common.info:info
43
44#
45# Script option descriptions and output messages
46#
47
48scripts.language:Language to display option descriptions in (eg. 'en_US' specifies American English). Requires translations of the option descriptions to exist in the perllib/strings_language-code.rb file.
49
50scripts.xml:Produces the information in an XML form, without 'pretty' comments but with much more detail.
51
52scripts.listall:Lists all items known about.
53scripts.describeall:Display options for all items known about
54
55scripts.both_old_options:WARNING: Both -removeold and -keepold were specified, defaulting to -removeold. Current contents of %s directory will be deleted.
56
57scripts.no_old_options:WARNING: Neither -removeold or -keepold were specified, defaulting to -removeold. Current contents of %s directory will be deleted.
58
59# -- buildcol.pl --
60
61buildcol.archivedir:Where the archives live.
62
63buildcol.builddir:Where to put the built indexes.
64
65buildcol.cachedir:Collection will be temporarily built here before being copied to the build directory.
66
67buildcol.cannot_open_cfg_file:WARNING: Can't open config file for updating: %s
68
69buildcol.collectdir:Collection directory.
70
71buildcol.copying_back_cached_build:Copying back the cached build
72
73buildcol.create_images:Attempt to create default images for new collection. This relies on the Gimp being installed along with relevant perl modules to allow scripting from perl.
74
75buildcol.debug:Print output to STDOUT.
76
77buildcol.desc:PERL script used to build a greenstone collection from GML documents.
78
79buildcol.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed.
80
81buildcol.index:Index to build (will build all in config file if not set).
82
83buildcol.keepold:Will not destroy the current contents of the building directory.
84
85buildcol.maxdocs:Maximum number of documents to build.
86
87buildcol.mode:The parts of the building process to carry out.
88buildcol.mode.all:Do everything.
89buildcol.mode.build_index:Just index the text.
90buildcol.mode.compress_text:Just compress the text.
91buildcol.mode.infodb:Just build the metadata database.
92
93buildcol.no_default_images:Default images will not be generated.
94
95buildcol.no_image_script:WARNING: Image making script could not be found: %s
96
97buildcol.no_strip_html:Do not strip the html tags from the indexed text (only used for mgpp collections).
98
99buildcol.no_text:Don't store compressed text. This option is useful for minimizing the size of the built indexes if you intend always to display the original documents at run time (i.e. you won't be able to retrieve the compressed text version).
100
101buildcol.sections_index_document_metadata:Index document level metadata at section level
102buildcol.sections_index_document_metadata.never:Don't index any document metadata at section level.
103buildcol.sections_index_document_metadata.always:Add all specified document level metadata even if section level metadata of that name exists.
104buildcol.sections_index_document_metadata.unless_section_metadata_exists:Only add document level metadata if no section level metadata of that name exists.
105
106buildcol.out:Filename or handle to print output status to.
107
108buildcol.params:[options] collection-name
109
110buildcol.remove_empty_classifications:Hide empty classifiers and classification nodes (those that contain no documents).
111
112buildcol.removeold:Will remove the old contents of the building directory.
113
114buildcol.unlinked_col_images:Collection images may not be linked correctly.
115
116buildcol.unknown_mode:Unknown mode: %s
117
118buildcol.updating_archive_cache:Updating archive cache
119
120buildcol.verbosity:Controls the quantity of output. 0=none, 3=lots.
121
122
123# -- classinfo.pl --
124
125classinfo.collect:Giving a collection name will make classinfo.pl look in collect/collection-name/perllib/classify first. If the classifier is not found there it will look in the general perllib/classify directory.
126
127classinfo.desc:Prints information about a classifier.
128
129classinfo.general_options:General options are inherited from parent classes of the classifier.
130
131classinfo.info:info
132
133classinfo.no_classifier_name:ERROR: You must provide a classifier name.
134
135classinfo.option_types:Classifiers may take two types of options
136
137classinfo.params:[options] classifier-name
138
139classinfo.passing_options:Options may be passed to any classifier by including them in your collect.cfg configuration file.
140
141classinfo.specific_options:Specific options are defined within the classifier itself, and are available only to this particular classifier.
142
143# -- downloadfrom.pl --
144downloadfrom.cache_dir:The location of the cache directory
145downloadfrom.desc:Downloads files from an external server
146downloadfrom.download_mode:The type of server to download from
147downloadfrom.download_mode.Web:HTTP
148downloadfrom.download_mode.OAI: Open Archives Initiative
149downloadfrom.download_mode.z3950:z3950 server
150downloadfrom.download_mode.SRW:SearchRetrieve Webservice
151downloadfrom.incorrect_mode:download_mode parameter was incorrect.
152downloadfrom.info:Print information about the server, rather than downloading
153downloadfrom.params:[general options] [specific download options]
154
155# -- downloadinfo.pl --
156
157downloadinfo.desc:Prints information about a download module
158downloadinfo.collect:Giving a collection name will make downloadinfo.pl look in collect/collection-name/perllib/downloaders first. If the module is not found there it will look in the general perllib/downloaders directory.
159downloadinfo.params:[options] [download-module]
160downloadinfo.general_options:General options are inherited from parent classes of the download modules.
161downloadinfo.specific_options:Specific options are defined within the download module itself, and are available only to this particular downloader.
162downloadinfo.option_types:Download modules may take two types of options
163
164# -- explode_metadata_database.pl --
165explode.desc:Explode a metadata database
166
167explode.document_field:The metadata element specifying the file name of documents to obtain and include in the collection.
168
169explode.document_prefix:A prefix for the document locations (for use with the document_field option).
170
171explode.document_suffix:A suffix for the document locations (for use with the document_field option).
172
173explode.encoding:Encoding to use when reading in the database file
174explode.metadata_set:Metadata set (namespace) to export all metadata as
175explode.plugin: Plugin to use for exploding
176explode.params: [options] filename
177# -- exportcol.pl --
178
179exportcol.out:Filename or handle to print output status to.
180exportcol.cddir:The name of the directory that the CD contents are exported to.
181exportcol.cdname:The name of the CD-ROM -- this is what will appear in the start menu once the CD-ROM is installed.
182exportcol.desc:PERL script used to export one or more collections to a Windows CD-ROM.
183exportcol.noinstall:Create a CD-ROM where the library runs directly off the CD-ROM and nothing is installed on the host computer.
184exportcol.params:[options] collection-name1 collection-name2 ...
185exportcol.coll_not_found:Ignoring invalid collection %s: collection not found at %s.
186exportcol.coll_dirs_not_found:Ignoring invalid collection %s: one of the following directories not found:
187exportcol.fail:exportcol.pl failed:
188exportcol.no_valid_colls:No valid collections specified to export.
189exportcol.couldnt_create_dir:Could not create directory %s.
190exportcol.couldnt_create_file:Could not create %s.
191exportcol.instructions:To create a self-installing Windows CD-ROM, write the contents of this folder out to a CD-ROM.
192exportcol.non_exist_files:One or more of the following necessary files and directories does not exist:
193exportcol.success:exportcol.pl succeeded:
194exportcol.output_dir:The exported collections (%s) are in %s.
195exportcol.export_coll_not_installed:The Export to CD-ROM functionality has not been installed.
196
197# -- import.pl --
198
199import.archivedir:Where the converted material ends up.
200
201import.cannot_open_stats_file:WARNING: Couldn't open stats file %s.
202
203import.cannot_open_fail_log:ERROR: Couldn't open fail log %s
204
205import.cannot_sort:WARNING: import.pl cannot sort documents when groupsize > 1. sortmeta option will be ignored.
206
207import.collectdir:Collection directory.
208
209import.complete:Import complete
210
211import.debug:Print imported text to STDOUT.
212
213import.desc:PERL script used to import files into a GML format ready for building.
214
215import.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed.
216
217import.groupsize:Number of import documents to group into one XML file.
218
219import.gzip:Use gzip to compress resulting xml documents (don't forget to include ZIPPlug in your plugin list when building from compressed documents).
220
221import.importdir:Where the original material lives.
222
223import.keepold:Will not destroy the current contents of the archives directory.
224
225import.maxdocs:Maximum number of documents to import.
226
227import.no_plugins_loaded:ERROR: No plugins loaded.
228
229import.OIDtype:The method to use when generating unique identifiers for each document.
230import.OIDtype.hash:Hashes the contents of the file. Document identifier will be the same every time the collection is imported.
231
232import.OIDtype.incremental:A simple document count that is significantly faster than "hash". It is not guaranteed to always assign the same identifier to a given document though and does not allow further documents to be added to existing xml archives.
233
234import.OIDtype.assigned:Uses 'D' plus the value of dc.Identifier as the document identifier. dc.Identifiers should be unique. If no dc.Identifier is assigned to the document, a hash id will be used instead.
235
236import.OIDtype.dirname:Uses 'J' plus the parent directory name as the identifier. This relies on there being only one document per directory, and all directory names being unique. E.g. import/b13as/h15ef/page.html will get an identifier of Jh15ef.
237
238import.saveas:This is to decide the archives format to be generated. The default setting is to GA.
239
240import.saveas.GA:Will generate Greenstone Archive format.
241
242import.saveas.METS:Will generate METS format.
243
244import.out:Filename or handle to print output status to.
245
246import.params:[options] collection-name
247
248import.removeold:Will remove the old contents of the archives directory.
249
250import.removing_archives:Removing current contents of the archives directory...
251
252import.removing_tmpdir:Removing contents of the collection "tmp" directory...
253
254import.sortmeta:Sort documents alphabetically by metadata for building. Search results for boolean queries will be displayed in this order. This will be disabled if groupsize > 1.
255
256import.statsfile:Filename or handle to print import statistics to.
257
258import.stats_backup:Will print stats to STDERR instead.
259
260import.verbosity:Controls the quantity of output. 0=none, 3=lots.
261
262
263# -- export.pl --
264
265export.exportdir:Where the export material ends up.
266
267export.cannot_open_stats_file:WARNING: Couldn't open stats file %s.
268
269export.cannot_open_fail_log:ERROR: Couldn't open fail log %s
270
271export.cannot_sort:WARNING: export.pl cannot sort documents when groupsize > 1. sortmeta option will be ignored.
272
273export.collectdir:Collection directory.
274
275export.complete:Export complete
276
277export.debug:Print exported text to STDOUT.
278
279export.desc:PERL script used to export files in a Greenstone collection to another format.
280
281export.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed. (Default: collectdir/collect/collname/etc/fail.log)
282
283export.groupsize:Number of documents to group into one XML file.
284
285export.gzip:Use gzip to compress resulting xml documents (don't forget to include ZIPPlug in your plugin list when building from compressed documents).
286
287export.importdir:Where the original material lives.
288
289export.keepold:Will not destroy the current contents of the export directory.
290
291export.maxdocs:Maximum number of documents to export.
292
293export.no_plugins_loaded:ERROR: No plugins loaded.
294
295export.OIDtype:The method to use when generating unique identifiers for each document.
296export.OIDtype.hash:Hashes the contents of the file. Document identifier will be the same every time the collection is imported.
297export.OIDtype.incremental:A simple document count that is significantly faster than "hash". It is not guaranteed to always assign the same identifier to a given document though and does not allow further documents to be added to existing xml archives.
298
299export.saveas:Format to export documents as.
300
301export.saveas.DSpace:DSpace Archive format.
302
303export.saveas.METS:METS format using the Greenstone profile.
304
305export.saveas_version:Currently only valid with 'saveas METS', options are 'greenstone', for Greenstone METS, or 'fedora', for Fedora METS.
306
307export.out:Filename or handle to print output status to.
308
309export.params:[options] collection-name1, collection-name2...
310
311export.removeold:Will remove the old contents of the export directory.
312
313export.removing_export:Removing current contents of the export directory...
314
315export.sortmeta:Sort documents alphabetically by metadata for building. This will be disabled if groupsize > 1.
316
317export.statsfile:Filename or handle to print export statistics to.
318
319export.stats_backup:Will print stats to STDERR instead.
320
321export.verbosity:Controls the quantity of output. 0=none, 3=lots.
322
323
324# -- mkcol.pl --
325
326mkcol.about:The about text for the collection.
327
328mkcol.bad_name_cvs:ERROR: No collection can be named CVS as this may interfere with directories created by the CVS versioning system.
329
330mkcol.bad_name_modelcol:ERROR: No collection can be named modelcol as this is the name of the model collection.
331
332mkcol.cannot_find_modelcol:ERROR: Cannot find the model collection %s
333
334mkcol.col_already_exists:ERROR: This collection already exists.
335
336mkcol.collectdir:Directory where new collection will be created.
337
338mkcol.creating_col:Creating the collection %s
339
340mkcol.creator:The collection creator's e-mail address.
341
342mkcol.creator_undefined:ERROR: The creator was not defined. This variable is needed to recognise duplicate collection names.
343
344mkcol.desc:PERL script used to create the directory structure for a new Greenstone collection.
345
346mkcol.doing_replacements:doing replacements for %s
347
348mkcol.long_colname:ERROR: The collection name must be less than 8 characters so compatibility with earlier filesystems can be maintained.
349
350mkcol.maintainer:The collection maintainer's email address (if different from the creator).
351
352mkcol.no_collectdir:ERROR: The collect dir doesn't exist: %s
353
354mkcol.no_colname:ERROR: No collection name was specified.
355
356mkcol.optionfile:Get options from file, useful on systems where long command lines may cause problems.
357
358mkcol.params:[options] collection-name
359
360mkcol.plugin:Perl plugin module to use (there may be multiple plugin entries).
361
362mkcol.public:If this collection has anonymous access.
363mkcol.public.true:Collection is public
364mkcol.public.false:Collection is private
365
366mkcol.quiet:Operate quietly.
367
368mkcol.success:The new collection was created successfully at %s
369
370mkcol.title:The title of the collection.
371
372mkcol.win31compat:Whether or not the named collection directory must conform to Windows 3.1 file conventions or not (i.e. 8 characters long).
373mkcol.win31compat.true:Directory name 8 characters or less
374mkcol.win31compat.false:Directory name any length
375
376# -- pluginfo.pl --
377
378pluginfo.collect:Giving a collection name will make pluginfo.pl look in collect/collection-name/perllib/plugins first. If the plugin is not found there it will look in the general perllib/plugins directory.
379
380pluginfo.desc:Prints information about a plugin.
381
382pluginfo.general_options:General options are inherited from parent classes of the plugin.
383
384pluginfo.info:info
385
386pluginfo.no_plugin_name:ERROR: You must provide a plugin name.
387
388pluginfo.option_types:Plugins may take two types of options
389
390pluginfo.params:[options] plugin-name
391
392pluginfo.passing_options:Options may be passed to any plugin by including them in your collect.cfg configuration file.
393
394pluginfo.specific_options:Specific options are defined within the plugin itself, and are available only to this particular plugin.
395
396
397#
398# Classifier option descriptions
399#
400
401AZCompactList.allvalues:Use all metadata values found.
402
403AZCompactList.desc:Classifier plugin for sorting alphabetically
404
405AZCompactList.doclevel:Level to process document at.
406AZCompactList.doclevel.top:Whole document.
407AZCompactList.doclevel.section:By sections.
408
409AZCompactList.firstvalueonly:Use only the first metadata value found.
410
411AZCompactList.freqsort:Sort by node frequency rather than alpha-numeric.
412
413AZCompactList.maxcompact:Maximum number of documents to be displayed per page.
414
415AZCompactList.metadata:A single Metadata field, or a comma separated list of Metadata fields, used for classification. If a list is specified, the first metadata type that has values will be used. May be used in conjunction with the -firstvalueonly and -allvalues flags, to select only the first value, or all metadata values from the list.
416
417AZCompactList.mincompact:Minimum number of documents to be displayed per page.
418
419AZCompactList.mingroup:The smallest value that will cause a group in the hierarchy to form.
420
421AZCompactList.minnesting:The smallest value that will cause a list to be converted into a nested list.
422
423AZCompactList.recopt:Used in nested metadata such as -metadata Year/Organisation.
424AZCompactList.sort:Metadata field to sort the leaf nodes by.
425
426AZCompactSectionList.desc:Variation on AZCompactList that classifies sections rather than documents. Entries are sorted by section-level metadata.
427
428AZList.desc:Classifier plugin for sorting alphabetically
429
430AZList.metadata:A single Metadata field or a comma separated list of Metadata fields used for classification. Following the order indicated by the list, the first field that contains a Metadata value will be used. List will be sorted by this element.
431
432AZSectionList.desc:Classifier plugin for sorting alphabetically. This is very similar to AZList except it sorts by section level metadata (excluding the top level) instead of just top level metadata. The only change is to the classify() subroutine which must now iterate through each section, adding each to the classification.
433
434BasClas.bad_general_option:The %s classifier uses an incorrect general option (general options are those available to all classifiers). Check your collect.cfg configuration file.
435
436BasClas.builddir:Where to put the built indexes.
437
438BasClas.buttonname:The label for the classifier screen and button in navigation bar. The default is the metadata element specified with -metadata.
439
440BasClas.desc:Base class for all the classifiers.
441
442BasClas.no_metadata_formatting:Don't do any automatic metadata formatting (for sorting.)
443
444BasClas.outhandle:The file handle to write output to.
445
446BasClas.removeprefix:A prefix to ignore in metadata values when sorting.
447
448BasClas.removesuffix:A suffix to ignore in metadata values when sorting.
449
450BasClas.verbosity:Controls the quantity of output. 0=none, 3=lots.
451
452Browse.desc:.
453
454DateList.bymonth:Classify by year and month instead of only year.
455
456DateList.desc:Classifier plugin for sorting by date. By default, sorts by 'Date' metadata. Date is assumed to be in the form yyyymmdd.
457
458DateList.metadata:The metadata that contains the dates to classify by. The format is expected to be yyyymmdd. Can be a comma separated list, in which case the first date found will be used.
459
460DateList.reverse_sort:Sort the documents in reverse chronological order (newest first).
461
462DateList.nogroup:Make each year an individual entry in the horizontal list, instead of spanning years with few entries. (This can also be used with the -bymonth option to make each month a separate entry instead of merging).
463
464DateList.no_special_formatting:Don't display Year and Month information in the document list.
465
466DateList.sort:An extra metadata field to sort by in the case where two documents have the same date.
467
468GenericList.always_bookshelf_last_level:Create a bookshelf icon even if there is only one item in each group at the leaf nodes.
469GenericList.classify_sections:Classify sections instead of documents.
470GenericList.desc:A general and flexible list classifier with most of the abilities of AZCompactList, but with better Unicode, metadata and sorting capabilities.
471GenericList.metadata:Metadata fields used for classification. Use '/' to separate the levels in the hierarchy and ';' to separate metadata fields within each level.
472GenericList.partition_size_within_level:The number of items in each partition (only applies when partition_type_within_level is set to 'constant_size').
473GenericList.partition_type_within_level:The type of partitioning done: either 'per_letter', 'constant_size', or 'none'.
474GenericList.sort_leaf_nodes_using:Metadata fields used for sorting the leaf nodes. Use '|' to separate the metadata groups to stable sort and ';' to separate metadata fields within each group.
475GenericList.use_hlist_for:Metadata fields to use a hlist rather than a vlist. Use ',' to separate the metadata groups and ';' to separate the metadata fields within each group.
476
477HFileHierarchy.desc:Classifier plugin for generating hierarchical classifications based on a supplementary structure file.
478
479Hierarchy.desc:Classifier plugin for generating a hierarchical classification. This may be based on structured metadata, or may use a supplementary structure file (use the -hfile option).
480
481Hierarchy.documents_last:Display document nodes after classifier nodes.
482
483Hierarchy.hfile:Use the specified classification structure file.
484
485Hierarchy.hlist_at_top:Display the first level of the classification horizontally.
486
487Hierarchy.reverse_sort:Sort leaf nodes in reverse order (use with -sort).
488
489Hierarchy.separator:Regular expression used for the separator, if using structured metadata.
490
491Hierarchy.sort:Metadata field to sort leaf nodes by. Leaves will not be sorted if not specified.
492
493Hierarchy.suppressfirstlevel:Ignore the first part of the metadata value. This is useful for metadata where the first element is common, such as the import directory in gsdlsourcefilename.
494
495Hierarchy.suppresslastlevel:Ignore the final part of the metadata value. This is useful for metadata where each value is unique, such as file paths.
496
497HTML.desc:Creates an empty classification that's simply a link to a web page.
498
499HTML.url:The url of the web page to link to.
500
501List.desc:Simple list classifier plugin.
502
503List.metadata:A single Metadata field or a comma separated list of Metadata fields used for classification. Following the order indicated by the list, the first field that contains a Metadata value will be used. List will be sorted by this element, unless -sort is used. If no metadata is specified, then all documents will be included in the list, otherwise only documents that contain a metadata value will be included.
504
505List.sort:Metadata field to sort by. Use '-sort nosort' for no sorting.
506
507Phind.desc:The Phind clasifier plugin.
508
509Phind.language:Language or languages to use building hierarchy. Languages are identified by two-letter country codes like en (English), es (Spanish), and fr (French). Language is a regular expression, so 'en|fr' (English or French) and '..' (match any language) are valid.
510
511Phind.min_occurs:The minimum number of times a phrase must appear in the text to be included in the phrase hierarchy.
512
513Phind.savephrases:If set, the phrase infomation will be stored in the given file as text. It is probably a good idea to use an absolute path.
514
515Phind.suffixmode:The smode parameter to the phrase extraction program. A value of 0 means that stopwords are ignored, and of 1 means that stopwords are used.
516
517Phind.text:The text used to build the phrase hierarchy.
518
519Phind.thesaurus:Name of a thesaurus stored in Phind format in the collection's etc directory.
520
521Phind.title:The metadata field used to describe each document.
522
523Phind.untidy:Don't remove working files.
524
525SectionList.desc:Same as List classifier but includes all sections of document (excluding top level) rather than just top level document itself.
526
527Collage.desc:The Collage classifier plugin.
528
529Collage.geometry:The dimensions of the Collage canvas. For a canvas 600 pixels wide by 400 pixels high, for example, specify geometry as 600x400
530
531Collage.maxDepth:Images for collaging are drawn from mirroring the underlying browse classifier. This controls the maximum depth of the mirroring process.
532
533Collage.maxDisplay:The maximum number of images to show in the collage at any one time.
534
535Collage.imageType:Used to control, by expressing file name extensions, which file types are used in the collage. A list of file name extensions is separated by the percent (%%) symbol.
536
537Collage.bgcolor:The background color of the collage canvas, specified in hexadecimal form (for example #008000 results in a forest green background).
538
539Collage.buttonname:The label for the classifier screen and button in navigation bar.
540
541Collage.refreshDelay:Rate, in milliseconds, that the collage canvas is refreshed.
542
543Collage.isJava2:Used to control which run-time classes of Java are used. More advanced version of Java (i.e. Java 1.2 onwards) include more sophisticated support for controlling transparency in images, this flag helps control what happens, however the built-in Java runtime for some browsers is version 1.1. The applet is designed to, by default, auto-detect which version of Java the browser is running and act accordingly.
544
545Collage.imageMustNotHave:Used to suppress images that should not appear in the collage, such as image buttons that make up the navigation bar.
546
547Collage.caption:Optional captions to display below the collage canvas.
548
549#
550# Plugin option descriptions
551#
552
553ArcPlug.desc:Plugin which recurses through an archives.inf file (i.e. the file generated in the archives directory when an import is done), processing each file it finds.
554
555BasPlug.adding:adding
556
557BasPlug.already_seen:already seen
558
559BasPlug.bad_general_option:The %s plugin uses an incorrect general option (general options are those available to all plugins). Check your collect.cfg configuration file.
560
561BasPlug.block_exp:Files matching this regular expression will be blocked from being passed to any later plugins in the list. This has no real effect other than to prevent lots of warning messages about input files you don't care about. Each plugin might have a default block_exp. e.g. by default HTMLPlug blocks any files with .gif, .jpg, .jpeg, .png or .css file extensions.
562
563BasPlug.associate_ext:Causes files with the same root filename as the document being processed by the plugin AND a filename extension from the comma separated list provided by this argument to be associated with the document being processed rather than handled as a separate list.
564
565BasPlug.could_not_extract_encoding:WARNING: encoding could not be extracted from %s - defaulting to %s
566
567BasPlug.could_not_extract_language:WARNING: language could not be extracted from %s - defaulting to %s
568
569BasPlug.could_not_open_for_reading:could not open %s for reading
570
571BasPlug.no_cover_image:Do not look for a prefix.jpg file (where prefix is the same prefix as the file being processed) and associate it as a cover image.
572
573BasPlug.default_encoding:Use this encoding if -input_encoding is set to 'auto' and the text categorization algorithm fails to extract the encoding or extracts an encoding unsupported by Greenstone. This option can take the same values as -input_encoding.
574
575BasPlug.default_language:If Greenstone fails to work out what language a document is the 'Language' metadata element will be set to this value. The default is 'en' (ISO 639 language symbols are used: en = English). Note that if -input_encoding is not set to 'auto' and -extract_language is not set, all documents will have their 'Language' metadata set to this value.
576
577BasPlug.desc:Base class for all the import plugins.
578
579BasPlug.done_acronym_extract:done extracting acronyms.
580
581BasPlug.done_acronym_markup:done acronym markup.
582
583BasPlug.done_email_extract:done extracting e-mail addresses.
584
585BasPlug.dummy_text:This document has no text.
586
587BasPlug.empty_file:file contains no text
588
589BasPlug.extract_acronyms:Extract acronyms from within text and set as metadata.
590
591BasPlug.extract_email:Extract email addresses as metadata.
592
593BasPlug.extract_historical_years:Extract time-period information from historical documents. This is stored as metadata with the document. There is a search interface for this metadata, which you can include in your collection by adding the statement, "format QueryInterface DateSearch" to your collection configuration file.
594
595BasPlug.extract_language:Identify the language of each document and set 'Language' metadata. Note that this will be done automatically if -input_encoding is 'auto'.
596
597BasPlug.extracting:extracting
598
599BasPlug.extracting_acronyms:extracting acronyms
600
601BasPlug.extract_keyphrases:Extract keyphrases automatically with Kea (default settings).
602
603BasPlug.extract_keyphrases_kea4:Extract keyphrases automatically with Kea 4.0 (default settings). Kea 4.0 is a new version of Kea that has been developed for controlled indexing of documents in the domain of agriculture.
604
605BasPlug.extract_keyphrase_options:Options for keyphrase extraction with Kea. For example: mALIWEB - use ALIWEB extraction model; n5 - extract 5 keyphrase;, eGBK - use GBK encoding.
606
607BasPlug.extracting_emails:extracting e-mail addresses
608
609BasPlug.file_has_no_text:ERROR: %s contains no text
610
611BasPlug.first:Comma separated list of first sizes to extract from the text into a metadata field. The field is called 'FirstNNN'.
612
613BasPlug.input_encoding:The encoding of the source documents. Documents will be converted from these encodings and stored internally as utf8.
614BasPlug.input_encoding.ascii:Plain 7 bit ascii. This may be a bit faster than using iso_8859_1. Beware of using this on a collection of documents that may contain characters outside the plain 7 bit ascii set though (e.g. German or French documents containing accents), use iso_8859_1 instead.
615BasPlug.input_encoding.auto:Use text categorization algorithm to automatically identify the encoding of each source document. This will be slower than explicitly setting the encoding but will work where more than one encoding is used within the same collection.
616
617BasPlug.input_encoding.unicode:Just unicode.
618
619BasPlug.input_encoding.utf8:Either utf8 or unicode -- automatically detected.
620
621BasPlug.keyphrases:keyphrases
622
623BasPlug.marking_up_acronyms:marking up acronyms
624
625BasPlug.markup_acronyms:Add acronym metadata into document text.
626
627BasPlug.maximum_century:The maximum named century to be extracted as historical metadata (e.g. 14 will extract all references up to the 14th century).
628
629BasPlug.maximum_year:The maximum historical date to be used as metadata (in a Common Era date, such as 1950).
630
631BasPlug.missing_kea:Error: The Kea software could not be found at %s. Please download Kea %s from http://www.nzdl.org/Kea and install it in this directory.
632
633BasPlug.must_be_implemented:BasPlug::read function must be implemented in sub-class for recursive plugins
634
635BasPlug.no_bibliography:Do not try to block bibliographic dates when extracting historical dates.
636
637BasPlug.process_exp:A perl regular expression to match against filenames. Matching filenames will be processed by this plugin. For example, using '(?i).html?\$' matches all documents ending in .htm or .html (case-insensitive).
638
639BasPlug.read_denied:Read permission denied for %s
640
641BasPlug.separate_cjk:Insert spaces between Chinese/Japanese/Korean characters to make each character a word. Use if text is not segmented.
642
643BasPlug.smart_block:Block files in a smarter way than just looking at filenames.
644
645BasPlug.stems:stems
646
647BasPlug.unsupported_encoding:WARNING: %s appears to be encoded in an unsupported encoding (%s) - using %s
648
649BasPlug.wrong_encoding:WARNING: %s was read using %s encoding but appears to be encoded as %s.
650
651BibTexPlug.desc:BibTexPlug reads bibliography files in BibTex format. BibTexPlug creates a document object for every reference in the file. It is a subclass of SplitPlug, so if there are multiple records, all are read.
652
653BookPlug.desc:Creates multi-level document from document containing <<TOC>> level tags. Metadata for each section is taken from any other tags on the same line as the <<TOC>>. e.g. <<Title>>xxxx<</Title>> sets Title metadata. Everything else between TOC tags is treated as simple html (i.e. no processing of html links or any other HTMLPlug type stuff is done). Expects input files to have a .hb file extension by default (this can be changed by adding a -process_exp option a file with the same name as the hb file but a .jpg extension is taken as the cover image (jpg files are blocked by this plugin). BookPlug is a simplification (and extension) of the HBPlug used by the Humanity Library collections. BookPlug is faster as it expects the input files to be cleaner (The input to the HDL collections contains lots of excess html tags around <<TOC>> tags, uses <<I>> tags to specify images, and simply takes all text between <<TOC>> tags and start of text to be Title metadata). If you're marking up documents to be displayed in the same way as the HDL collections, use this plugin instead of HBPlug.
654
655BRSPlug.desc: BRSPlug deals with the BBC collections. There are three BBC collections we deliver, which are National Sound Archive (nsa), British Film Institute (bfi), and BBC Other (bbcother) (everything does not fit into one of the first two). Four options are provided which are all-build all collections, nsa-build the NSA collections, bfi-build the BFI collections, bbcother-build the OTHER collections.
656
657ConvertToPlug.apply_fribidi:Run the "fribidi" Unicode Bidirectional Algorithm program over the converted file (for right-to-left text).
658ConvertToPlug.convert_to:Plugin converts to TEXT or HTML or various types of Image (e.g. JPEG, GIF, PNG).
659ConvertToPlug.convert_to.auto:Automatically select the format converted too. Format chosen depends on input document type, for example Word will automatically be converted to HTML, whereas PowerPoint will be converted to Greenstone's PagedImage format.
660ConvertToPlug.convert_to.html:HTML format.
661ConvertToPlug.convert_to.text:Plain text format.
662ConvertToPlug.convert_to.pagedimg_jpg:JPEG format.
663ConvertToPlug.convert_to.pagedimg_gif:GIF format.
664ConvertToPlug.convert_to.pagedimg_png:PNG format.
665
666ConvertToPlug.desc:The plugin is inherited by such plugins as WordPlug and PDFPlug. It facilitates the conversion of these document types to either HTML or TEXT by setting up variable that instruct ConvertToBasPlug how to work. It works by dynamically inheriting HTMLPlug or TEXTPlug based on the plugin argument 'convert_to'. If the argument is not present, the default is to inherit HTMLPlug.
667
668ConvertToPlug.use_strings:If set, a simple strings function will be called to extract text if the conversion utility fails.
669
670ConvertToRogPlug.desc:A plugin that inherits from RogPlug.
671
672DBPlug.desc:Uses records from a database as documents.
673
674DBPlug.title_sub:Substitution expression to modify string stored as Title. Used by, for example, PSPlug to remove "Page 1" etc from text used as the title.
675
676DSpacePlug.desc:DSpacePlug reads the DSpace Export collection and its dublin_core metadata file, and convert to GSII compliance format.
677DSpacePlug.first_inorder_ext: This is used to identify the primary stream of DSpace collection document. With this option, the system will treat the defined ext types of document in sequence to look for the possible primary stream.
678DSpacePlug.first_inorder_mime:This is used to identify the primary data stream of DSpace collection document.With this option, the system will treat the defined mime types of document in sequence to look for the possible primary stream.
679DSpacePlug.only_first_doc:This is used to identify the primary data stream of DSpace collection document.With this option, the system will treat the first document in dublic_core metadata file as the possible primary stream.
680
681EMAILPlug.desc:Email plug reads email files. These are named with a simple number (i.e. as they appear in maildir folders) or with the extension .mbx (for mbox mail file format).\nDocument text: The document text consists of all the text after the first blank line in the document.\nMetadata (not Dublin Core!):\n\t\$Headers All the header content (optional, not stored by default)\n\t\$Subject Subject: header\n\t\$To To: header\n\t\$From From: header\n\t\$FromName Name of sender (where available)\n\t\$FromAddr E-mail address of sender\n\t\$DateText Date: header\n\t\$Date Date: header in GSDL format (eg: 19990924)
682
683EMAILPlug.no_attachments:Do not save message attachments.
684
685EMAILPlug.headers:Store email headers as "Headers" metadata.
686
687EMAILPlug.split_exp:A perl regular expression used to split files containing many messages into individual documents.
688
689ExcelPlug.desc:A plugin for importing Microsoft Excel files.
690
691FOXPlug.desc:Plugin to process a Foxbase dbt file. This plugin provides the basic functionality to read in the dbt and dbf files and process each record. This general plugin should be overridden for a particular database to process the appropriate fields in the file.
692
693GAPlug.desc:Processes GreenstoneArchive XML documents. Note that this plugin does no syntax checking (though the XML::Parser module tests for well-formedness). It's assumed that the GreenstoneArchive files conform to their DTD.
694
695GISBasPlug.extract_placenames:Extract placenames from within text and set as metadata. Requires GIS extension to Greenstone.
696
697GISBasPlug.gazetteer:Gazetteer to use to extract placenames from within text and set as metadata. Requires GIS extension to Greenstone.
698
699GISBasPlug.place_list:When extracting placements, include list of placenames at start of the document. Requires GIS extension to Greenstone.
700
701GMLPlug.desc:Plugin which processes a GML format document assumes that gml tags are all in lower-case.
702
703HBPlug.desc:Plugin which processes an HTML book directory. This plugin is used by the Humanity Library collections and does not handle input encodings other than ascii or extended ascii. This code is kind of ugly and could no doubt be made to run faster, by leaving it in this state I hope to encourage people to make their collections use HBSPlug instead ;-)\n\nUse HBSPlug if creating a new collection and marking up files like the Humanity Library collections. HBSPlug accepts all input encodings but expects the marked up files to be cleaner than those used by the Humanity Library collections
704
705HTMLPlug.assoc_files:Perl regular expression of file extensions to associate with html documents.
706
707HTMLPlug.desc:This plugin processes HTML files
708
709HTMLPlug.description_tags:Split document into sub-sections where <Section> tags occur. Note that by setting this option you implicitly set -no_metadata, as all metadata should be included within the <Section> tags. Also, '-keep_head' will have no effect when this option is set.
710
711HTMLPlug.file_is_url:Set if input filenames make up url of original source documents e.g. if a web mirroring tool was used to create the import directory structure.
712
713HTMLPlug.hunt_creator_metadata:Find as much metadata as possible on authorship and place it in the 'Creator' field. Requires the -metadata_fields flag.
714
715HTMLPlug.keep_head:Don't remove headers from html files.
716
717HTMLPlug.metadata_fields:Comma separated list of metadata fields to attempt to extract. Use 'tag<tagname>' to have the contents of the first <tagname> pair put in a metadata element called 'tagname'. Capitalise this as you want the metadata capitalised in Greenstone, since the tag extraction is case insensitive.
718
719HTMLPlug.no_metadata:Don't attempt to extract any metadata from files.
720
721HTMLPlug.no_strip_metadata_html:Comma separated list of metadata names, or 'all'. Used with -description_tags, it prevents stripping of HTML tags from the values for the specified metadata.
722
723HTMLPlug.nolinks:Don't make any attempt to trap links (setting this flag may improve speed of building/importing but any relative links within documents will be broken).
724
725HTMLPlug.rename_assoc_files:Renames files associated with documents (e.g. images). Also creates much shallower directory structure (useful when creating collections to go on cd-rom).
726
727HTMLPlug.sectionalise_using_h_tags:Automatically create a sectioned document using h1, h2, ... hX tags.
728
729HTMLPlug.title_sub:Substitution expression to modify string stored as Title. Used by, for example, PDFPlug to remove "Page 1", etc from text used as the title.
730
731ImagePlug.converttotype:Convert main image to format 's'.
732
733ImagePlug.desc:This plugin processes images, adding basic metadata
734
735ImagePlug.minimumsize:Ignore images smaller than n bytes.
736
737ImagePlug.noscaleup:Don't scale up small images when making thumbnails.
738
739ImagePlug.screenviewsize:If set, makes an image of size n for screen display and sets Screen, ScreenSize, ScreenWidth and ScreenHeight metadata. By default it is not set.
740
741ImagePlug.screenviewtype:If -screenviewsize is set, this sets the screen display image type.
742
743ImagePlug.thumbnailsize:Make thumbnails of size nxn.
744
745ImagePlug.thumbnailtype:Make thumbnails in format 's'.
746
747IndexPlug.desc:This recursive plugin processes an index.txt file. The index.txt file should contain the list of files to be included in the collection followed by any extra metadata to be associated with each file.\n\nThe index.txt file should be formatted as follows: The first line may be a key (beginning with key:) to name the metadata fields (e.g. key: Subject Organization Date). The following lines will contain a filename followed by the value that metadata entry is to be set to. (e.g. 'irma/iw097e 3.2 unesco 1993' will associate the metadata Subject=3.2, Organization=unesco, and Date=1993 with the file irma/iw097e if the above key line was used)\n\nNote that if any of the metadata fields use the Hierarchy classifier plugin then the value they're set to should correspond to the first field (the descriptor) in the appropriate classification file.\n\nMetadata values may be named separately using a tag (e.g. <Subject>3.2) and this will override any name given to them by the key line. If there's no key line any unnamed metadata value will be named 'Subject'.
748
749ISISPlug.desc:This plugin processes CDS/ISIS databases. For each CDS/ISIS database processed, three files must exist in the collection's import folder: the Master file (.mst), the Field Definition Table (.fdt), and the Cross-Reference File (.xrf).
750
751ISISPlug.subfield_separator:The string used to separate subfields in CDS/ISIS database records.
752
753ISISPlug.entry_separator:The string used to separate multiple values for single metadata fields in CDS/ISIS database records.
754
755LaTeXPlug.desc:Plugin for LaTeX documents.
756
757MACROPlug.desc:Creates simple single-level document. Adds Title metadata of first line of text (up to 100 characters long).
758
759MARCPlug.desc:Basic MARC plugin.
760
761MARCPlug.metadata_mapping:Name of file that includes mapping details from MARC values to Greenstone metadata names. Defaults to 'marctodc.txt' found in the site's etc directory.
762
763MetadataPass.desc:On-the-side base class to BasPlug that supports metadata plugins utilise metadata_read pass of import.pl
764GISBasPlug.desc: On-the-side base class to BasPlug that supports GIS capabilities
765
766NULPlug.desc:Dummy (.nul) file plugin. Used with the files produced by exploding metadata database files.
767
768NULPlug.assoc_field:Name of a metadata field that will be set for each nul file.
769OAIPlug.desc:Basic Open Archives Initiative (OAI) plugin.
770
771OggVorbisPlug.add_technical_metadata:Add technical (eg. bitrate) metadata.
772
773OggVorbisPlug.desc:A plugin for importing Ogg Vorbis audio files.
774
775OpenDocumentPlug.desc:Plugin for OASIS OpenDocument format documents (used by OpenOffice 2.0)
776
777PagedImgPlug.desc:Plugin for documents made up of a sequence of images, with optional OCR text for each image.
778
779PagedImgPlug.documenttype:Set the document type (used for display)
780PagedImgPlug.documenttype.paged:Paged documents have next and previous arrows and a 'go to page X' box
781PagedImgPlug.documenttype.hierarchy:Hierarchical documents have a table of contents
782
783PagedImgPlug.headerpage:Add a top level header page (that contains no image) to each document.
784
785PagedImgPlug.screenview:Produce a screenview image for each image, and set Screen, ScreenSize, ScreenWidth and ScreenHeight metadata.
786
787PagedImgPlug.screenviewsize:Make screenview images of size nxn.
788
789PagedImgPlug.screenviewtype:Make screenview images in format 's'.
790
791PagedImgPlug.thumbnail:Produce a thumbnail for each image
792
793PDFPlug.allowimagesonly:Allow PDF files with no extractable text. Avoids the need to have -complex set. Only useful with convert_to html.
794PDFPlug.complex:Create more complex output. With this option set the output html will look much more like the original PDF file. For this to function properly you Ghostscript installed (for *nix gs should be on your path while for windows you must have gswin32c.exe on your path).
795
796PDFPlug.desc:Reasonably with-it pdf plugin.
797
798PDFPlug.nohidden:Prevent pdftohtml from attempting to extract hidden text. This is only useful if the -complex option is also set.
799
800PDFPlug.noimages:Don't attempt to extract images from PDF.
801
802PDFPlug.use_sections:Create a separate section for each page of the PDF file.
803
804PDFPlug.zoom:The factor by which to zoom the PDF for output (this is only useful if -complex is set).
805
806PPTPlug.desc:A plugin for importing Microsoft PowerPoint files.
807
808PPTPlug.windows_scripting:Use MicroSoft Windows scripting technology (Visual Basic for Applications) to get PPT to convert document to various image types (e.g. JPEG,PNG,GIF) rather than rely on the open source package ppttohtml.
809
810PSPlug.desc:This is a \"poor man's\" ps to text converter. If you are serious, consider using the PRESCRIPT package, which is available for download at http://www.nzdl.org/html/software.html
811
812PSPlug.extract_date:Extract date from PS header.
813
814PSPlug.extract_pages:Extract pages from PS header.
815
816PSPlug.extract_title:Extract title from PS header.
817
818RealMediaPlug.desc:A plugin for processing Real Media files.
819
820RecPlug.desc:RecPlug is a plugin which recurses through directories processing each file it finds.
821
822RecPlug.recheck_directories:After the files in an import directory have been processed, re-read the directory to discover any new files created.
823
824RecPlug.use_metadata_files:Read metadata from metadata XML files.
825
826ReferPlug.desc:ReferPlug reads bibliography files in Refer format.
827
828ReferPlug.longdesc:ReferPlug reads bibliography files in Refer format.\nBy Gordon W. Paynter (gwp\@cs.waikato.ac.nz), November 2000\n\nLoosely based on hcibib2Plug by Steve Jones (stevej\@cs.waikato.ac.nz). Which was based on EMAILPlug by Gordon Paynter (gwp\@cs.waikato.ac.nz). Which was based on old versions of HTMLplug and HCIBIBPlugby by Stefan Boddie and others -- it's hard to tell what came from where, now.\n\nReferPlug creates a document object for every reference in the file. It is a subclass of SplitPlug, so if there are multiple records, all are read.\n\nDocument text:\n\tThe document text consists of the reference in Refer format.\nMetadata:\n\t\$Creator \%A Author name\n\t\$Title \%T Title of article of book\n\t\$Journal \%J Title of Journal\n\t\$Booktitle \%B Title of book containing the publication\n\t\$Report \%R Type of Report, paper or thesis\n\t\$Volume \%V Volume Number of Journal\n\t\$Number \%N Number of Journal within Volume\n\t\$Editor \%E Editor name\n\t\$Pages \%P Page Number of article\n\t\$Publisher \%I Name of Publisher\n\t\$Publisheraddr \%C Publisher's address\n\t\$Date \%D Date of publication\n\t\$Keywords \%K Keywords associated with publication\n\t\$Abstract \%X Abstract of publication\n\t\$Copyright\t\%* Copyright information for the article
829
830RogPlug.desc:Creates simple single-level documents from .rog or .mdb files.
831
832RTFPlug.desc:Plugin for importing Rich Text Format files.
833
834SRCPlug.desc:Filename is currently used for Title ( optionally minus some prefix ). Current languages:\ntext: READMEs/Makefiles\nC/C++ (currently extracts #include statements and C++ class decls)\nPerl (currently only done as text)\nShell (currently only done as text)
835
836SRCPlug.remove_prefix:Remove this leading pattern from the filename (eg -remove_prefix /tmp/XX/src/). The default is to remove the whole path from the filename.
837
838SplitPlug.desc:SplitPlug is a plugin for splitting input files into segments that will then be individually processed. This plugin should not be called directly. Instead, if you need to process input files that contain several documents, you should write a plugin with a process function that will handle one of those documents and have it inherit from SplitPlug. See ReferPlug for an example.
839
840SplitPlug.split_exp:A perl regular expression to split input files into segments.
841
842StructuredHTMLPlug.delete_toc:Remove any table of contents, list of figures etc from the converted HTML file. Styles for these are specified by the toc_header option.
843
844StructuredHTMLPlug.title_header:possible user-defined styles for the title header.
845
846StructuredHTMLPlug.level1_header:possible user-defined styles for the level1 header in the HTML document (equivalent to <h1>).
847
848StructuredHTMLPlug.level2_header:possible user-defined styles for the level2 header in the HTML document (equivalent to <h2>).
849
850StructuredHTMLPlug.level3_header:possible user-defined styles for the level3 header in the HTML document (equivalent to <h3>).
851
852StructuredHTMLPlug.toc_header:possible user-defined header styles for the table of contents, table of figures etc, to be removed if delete_toc is set.
853
854TEXTPlug.desc:Creates simple single-level document. Adds Title metadata of first line of text (up to 100 characters long).
855
856TEXTPlug.title_sub:Substitution expression to modify string stored as Title. Used by, for example, PSPlug to remove "Page 1" etc from text used as the title.
857
858UnknownPlug.assoc_field:Name of the metadata field that will hold the associated file's name.
859
860UnknownPlug.desc:This is a simple Plugin for importing files in formats that Greenstone doesn't know anything about. A fictional document will be created for every such file, and the file itself will be passed to Greenstone as the \"associated file\" of the document.
861
862UnknownPlug.file_format:Type of the file (e.g. MPEG, MIDI, ...)
863
864UnknownPlug.mime_type:Mime type of the file (e.g. image/gif).
865
866UnknownPlug.process_extension:Process files with this file extension. This option is an alternative to process_exp that is simpler to use but less flexible.
867
868UnknownPlug.srcicon:Specify a macro name (without underscores) to use as srcicon metadata.
869
870MP3Plug.desc:Plugin for processing MP3 files.
871
872MP3Plug.assoc_images:Use Google image search to locate images related to MP3 file based on ID3 Title and Artist metadata.
873
874MP3Plug.applet_metadata:Used to store [applet] metadata for each document that contains the necessary HTML for an MP3 audio player applet to play that file.
875
876MP3Plug.metadata_fields:Comma separated list of metadata fields to extract (assuming present) in an MP3 file. Use \"*\" to extract all the fields.
877
878W3ImgPlug.aggressiveness:Range of related text extraction techniques to use.
879W3ImgPlug.aggressiveness.1:Filename, path, ALT text only.
880W3ImgPlug.aggressiveness.2:All of 1, plus caption where available.
881W3ImgPlug.aggressiveness.3:All of 2, plus near paragraphs where available.
882W3ImgPlug.aggressiveness.4:All of 3, plus previous headers (<h1>, <h2>...) where available.
883W3ImgPlug.aggressiveness.5:All of 4, plus textual references where available.
884W3ImgPlug.aggressiveness.6:All of 4, plus page metatags (title, keywords, etc).
885W3ImgPlug.aggressiveness.7:All of 6, 5 and 4 combined.
886W3ImgPlug.aggressiveness.8:All of 7, plus repeat caption, filename, etc (raise ranking of more relevant results).
887W3ImgPlug.aggressiveness.9:All of 1, plus full text of source page.
888
889W3ImgPlug.caption_length:Maximum length of captions (in characters).
890
891W3ImgPlug.convert_params:Additional parameters for ImageMagicK convert on thumbnail creation. For example, '-raise' will give a three dimensional effect to thumbnail images.
892
893W3ImgPlug.desc:A plugin for extracting images and associated text from webpages.
894
895W3ImgPlug.document_text:Add image text as document:text (otherwise IndexedText metadata field).
896
897W3ImgPlug.index_pages:Index the pages along with the images. Otherwise reference the pages at the source URL.
898
899W3ImgPlug.max_near_text:Maximum characters near images to extract.
900
901W3ImgPlug.min_height:Pixels. Skip images shorter than this.
902
903W3ImgPlug.min_near_text:Minimum characters of near text or caption to extract.
904
905W3ImgPlug.min_size:Bytes. Skip images smaller than this.
906
907W3ImgPlug.min_width:Pixels. Skip images narrower than this.
908
909W3ImgPlug.neartext_length:Target length of near text (in characters).
910
911W3ImgPlug.no_cache_images:Don't cache images (point to URL of original).
912
913W3ImgPlug.smallpage_threshold:Images on pages smaller than this (bytes) will have the page (title, keywords, etc) meta-data added.
914
915W3ImgPlug.textrefs_threshold:Threshold for textual references. Lower values mean the algorithm is less strict.
916
917W3ImgPlug.thumb_size:Max thumbnail size. Both width and height.
918
919WordPlug.desc:A plugin for importing Microsoft Word documents.
920
921WordPlug.windows_scripting:Use MicroSoft Windows scripting technology (Visual Basic for Applications) to get Word to convert document to HTML rather than rely on the open source package WvWare. Causes Word application to open on screen if not already running.
922
923WordPlug.metadata_fields: This is to retrieve metadata from the HTML document converted by VB scripting. It allows users to define comma separated list of metadata fields to attempt to extract. Use 'tag<tagname>' to have the contents of the first <tagname> pair put in a metadata element called 'tagname'. Capitalise this as you want the metadata capitalised in Greenstone, since the tag extraction is case insensitive
924
925XMLPlug.desc:Base class for XML plugins.
926
927XMLPlug.xslt:Transform a matching input document with the XSLT in the named file. A relative filename is assumed to be in the collection's file area, for instance etc/mods2dc.xsl.
928ZIPPlug.desc:Plugin which handles compressed and/or archived input formats currently handled formats and file extensions are:\ngzip (.gz, .z, .tgz, .taz)\nbzip (.bz)\nbzip2 (.bz2)\nzip (.zip .jar)\ntar (.tar)\n\nThis plugin relies on the following utilities being present (if trying to process the corresponding formats):\ngunzip (for gzip)\nbunzip (for bzip)\nbunzip2 \nunzip (for zip)\ntar (for tar)
929
930#
931# Download module option descriptions
932#
933
934BasDownload.desc:BasDownload
935
936OAIDownload.desc:OAIDownload
937OAIDownload.url_disp:Source URL
938OAIDownload.url:Source URL
939OAIDownload.set_disp:Set
940OAIDownload.set:Set
941OAIDownload.get_doc_disp:Get document
942OAIDownload.get_doc:Maximum number of records to download
943OAIDownload.max_records_disp:Max records
944OAIDownload.max_records:Max records
945
946SRWDownload.desc:SRWDownload
947
948WebDownload.desc:WebDownload
949WebDownload.url:Source URL
950WebDownload.url_disp:Source URL
951WebDownload.depth:How many hyperlinks deep to go when downloading
952WebDownload.depth_disp:Download Depth
953WebDownload.below:Only mirror files below this URL
954WebDownload.below_disp:Only mirror files below this URL
955WebDownload.within:Only mirror files within the same site
956WebDownload.within_disp:Only mirror files within the same site
957WebDownload.html_only:ignore associated files e.g images and stylesheets
958WebDownload.html_only_disp:Download only HTML files
959
960WgetDownload.desc: Base class that handles calls to wget
961WgetDownload.proxy_on:Proxy on
962WgetDownload.proxy_host:Proxy host
963WgetDownload.proxy_port:Proxy port
964WgetDownload.user_name:User name
965WgetDownload.user_password:User password
966
967Z3950Download.desc:Z3950Download
968Z3950Download.host:Host
969Z3950Download.host_disp:Host
970Z3950Download.port:Port
971Z3950Download.port_disp:Port
972Z3950Download.database:Database
973Z3950Download.database_disp:Database
974Z3950Download.find:Find
975Z3950Download.find_disp:Find
976Z3950Download.max_records:Max Records
977Z3950Download.max_records_disp:Max Records
978
979#
980# Perl module strings
981#
982
983classify.could_not_find_classifier:ERROR: Could not find classifier \"%s\"
984
985plugin.could_not_find_plugin:ERROR: Could not find plugin \"%s\"
986
987plugin.including_archive:including the contents of 1 ZIP/TAR archive
988
989plugin.including_archives:including the contents of %d ZIP/TAR archives
990
991plugin.kill_file:Process killed by .kill file
992
993plugin.n_considered:%d documents were considered for processing
994
995plugin.n_included:%d were processed and included in the collection
996
997plugin.n_rejected:%d were rejected
998
999plugin.n_unrecognised:%d were unrecognised
1000
1001plugin.no_plugin_could_process:WARNING: No plugin could process %s
1002
1003plugin.no_plugin_could_recognise:WARNING: No plugin could recognise %s
1004
1005plugin.no_plugin_could_process_this_file:no plugin could process this file
1006
1007plugin.no_plugin_could_recognise_this_file:no plugin could recognise this file
1008
1009plugin.one_considered:1 document was considered for processing
1010
1011plugin.one_included:1 was processed and included in the collection
1012
1013plugin.one_rejected:1 was rejected
1014
1015plugin.one_unrecognised:1 was unrecognised
1016
1017plugin.see_faillog:See %s for a list of unrecognised and/or rejected documents
1018
1019PrintUsage.default:Default
1020
1021PrintUsage.required:REQUIRED
Note: See TracBrowser for help on using the repository browser.