source: trunk/gsdl/perllib/strings.rb@ 9156

#
# Resource bundle description
#

Language.code:en
Language.name:English

OutputEncoding.unix:iso_8859_1
OutputEncoding.windows:iso_8859_1


#
# Common output messages
#

common.cannot_create_file:ERROR: Can't create file %s

common.cannot_find_cfg_file:ERROR: Can't find the configuration file %s

common.cannot_open:ERROR: Can't open %s

common.cannot_open_fail_log:ERROR: Can't open fail log %s

common.cannot_open_output_file:ERROR: Can't open output file %s

common.cannot_read:ERROR: Can't read %s

common.cannot_read_file:ERROR: Can't read file %s

common.general_options:general options (for %s)

common.must_be_implemented:function must be implemented in sub-class

common.options:options

common.processing:processing

common.specific_options:specific options

common.usage:Usage


#
# Script option descriptions and output messages
#

scripts.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.

scripts.xml:Produces the information in an XML form, without 'pretty' comments but with much more detail.

scripts.listall:Lists all known plugins instead of details about one given plugin.


# -- buildcol.pl --

buildcol.archivedir:Where the archives live.

buildcol.builddir:Where to put the built indexes.

buildcol.cachedir:Collection will be temporarily built here before being copied to the build directory.

buildcol.cannot_open_cfg_file:WARNING: Can't open config file for updating: %s

buildcol.collectdir:Collection directory.

buildcol.copying_back_cached_build:Copying back the cached build

buildcol.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.

buildcol.debug:Print output to STDOUT.

buildcol.desc:PERL script used to build a greenstone collection from GML documents.

buildcol.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed.

buildcol.index:Index to build (will build all in config file if not set).

buildcol.keepold:Will not destroy the current contents of the building directory.

buildcol.maxdocs:Maximum number of documents to build.

buildcol.mode:The parts of the building process to carry out.
buildcol.mode.all:Do everything.
buildcol.mode.build_index:Just index the text.
buildcol.mode.compress_text:Just compress the text.
buildcol.mode.infodb:Just build the metadata database.

buildcol.no_default_images:Default images will not be generated.

buildcol.no_image_script:WARNING: Image making script could not be found: %s

buildcol.no_strip_html:Do not strip the html tags from the indexed text (only used for mgpp collections).

buildcol.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).

buildcol.out:Filename or handle to print output status to.

buildcol.params:[options] collection-name

buildcol.remove_empty_classifications:Hide empty classifiers and classification nodes (those that contain no documents).

buildcol.unlinked_col_images:Collection images may not be linked correctly.

buildcol.unknown_mode:Unknown mode: %s

buildcol.updating_archive_cache:Updating archive cache

buildcol.verbosity:Controls the quantity of output. 0=none, 3=lots.


# -- classinfo.pl --

classinfo.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.

classinfo.desc:Prints information about a classifier.

classinfo.general_options:General options are inherited from parent classes of the classifier.

classinfo.info:info

classinfo.no_classifier_name:ERROR: You must provide a classifier name.

classinfo.option_types:Classifiers may take two types of options

classinfo.params:[options] classifier-name

classinfo.passing_options:Options may be passed to any classifier by including them in your collect.cfg configuration file.

classinfo.specific_options:Specific options are defined within the classifier itself, and are available only to this particular classifier.

# -- explode_metadata_database.pl --
explode.desc:Explode a metadata database

explode.document_field:The metadata element specifying the file name of documents to obtain and include in the collection.

explode.document_prefix:A prefix for the document locations (for use with the document_field option).

explode.document_suffix:A suffix for the document locations (for use with the document_field option).

explode.encoding:Encoding to use when reading in the database file
explode.filename_field:Field to use for filenames for the generated null files (if no document_field or that field is empty)
explode.metadata_set:Metadata set (namespace) to export all metadata as
explode.plugin: Plugin to use for exploding
explode.params: [options] filename
# -- exportcol.pl --

exportcol.out:Filename or handle to print output status to.
exportcol.cdname:The name of the CD-ROM -- this is what will appear in the start menu once the CD-ROM is installed.
exportcol.desc:PERL script used to export one or more collections to a Windows CD-ROM. 
exportcol.params:[options] collection-name1 collection-name2 ...
exportcol.coll_not_found:Ignoring invalid collection %s: collection not found at %s.
exportcol.coll_dirs_not_found:Ignoring invalid collection %s: one of the following directories not found:
exportcol.fail:exportcol.pl failed:
exportcol.no_valid_colls:No valid collections specified to export.
exportcol.couldnt_create_dir:Could not create directory %s.
exportcol.couldnt_create_file:Could not create %s.
exportcol.instructions:To create a self-installing Windows CD-ROM, write the contents of this folder out to a CD-ROM.
exportcol.non_exist_files:One or more of the following necessary files and directories does not exist:
exportcol.success:exportcol.pl succeeded:
exportcol.output_dir:The exported collections (%s) are in %s.
exportcol.export_coll_not_installed:The Export to CD-ROM functionality has not been installed.

# -- import.pl --

import.archivedir:Where the converted material ends up.

import.cannot_open_stats_file:WARNING: Couldn't open stats file %s.

import.cannot_open_fail_log:ERROR: Couldn't open fail log %s

import.cannot_sort:WARNING: import.pl cannot sort documents when groupsize > 1. sortmeta option will be ignored.

import.collectdir:Collection directory.

import.complete:Import complete

import.debug:Print imported text to STDOUT.

import.desc:PERL script used to import files into a GML format ready for building.

import.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed.

import.groupsize:Number of import documents to group into one XML file.

import.gzip:Use gzip to compress resulting xml documents (don't forget to include ZIPPlug in your plugin list when building from compressed documents).

import.importdir:Where the original material lives.

import.keepold:Will not destroy the current contents of the archives directory (the default).

import.maxdocs:Maximum number of documents to import.

import.no_plugins_loaded:ERROR: No plugins loaded.

import.OIDtype:The method to use when generating unique identifiers for each document.
import.OIDtype.hash:Hashes the contents of the file. Document identifier will be the same every time the collection is imported.

import.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.

import.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.

import.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.

import.saveas:This is to decide the archives format to be generated. The default setting is to GA.

import.saveas.GA:Will generate Greenstone Archive format.

import.saveas.METS:Will generate METS format.

import.out:Filename or handle to print output status to.

import.params:[options] collection-name

import.removeold:Will remove the old contents of the archives directory -- use with care.

import.removing_archives:Removing current contents of the archives directory...

import.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.

import.statsfile:Filename or handle to print import statistics to.

import.stats_backup:Will print stats to STDERR instead.

import.verbosity:Controls the quantity of output. 0=none, 3=lots.


# -- export.pl --

export.exportdir:Where the export material ends up.

export.cannot_open_stats_file:WARNING: Couldn't open stats file %s.

export.cannot_open_fail_log:ERROR: Couldn't open fail log %s

export.cannot_sort:WARNING: export.pl cannot sort documents when groupsize > 1. sortmeta option will be ignored.

export.collectdir:Collection directory.

export.complete:Export complete

export.debug:Print exported text to STDOUT.

export.desc:PERL script used to import files into a GML format ready for building.

export.faillog:Fail log filename. This log receives the filenames of any files which fail to be processed.

export.groupsize:Number of import documents to group into one XML file.

export.gzip:Use gzip to compress resulting xml documents (don't forget to include ZIPPlug in your plugin list when building from compressed documents).

export.importdir:Where the original material lives.

export.keepold:Will not destroy the current contents of the export directory (the default).

export.maxdocs:Maximum number of documents to import.

export.no_plugins_loaded:ERROR: No plugins loaded.

export.OIDtype:The method to use when generating unique identifiers for each document.
export.OIDtype.hash:Hashes the contents of the file. Document identifier will be the same every time the collection is imported.
export.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.

export.saveas:This is to decide the export format to be generated. The default setting is to METS.

export.saveas.DSpace:Will generate DSpace Archive format.

export.saveas.METS:Will generate METS format.

export.out:Filename or handle to print output status to.

export.params:[options] collection-name

export.removeold:Will remove the old contents of the export directory -- use with care.

export.removing_export:Removing current contents of the export directory...

export.sortmeta:Sort documents alphabetically by metadata for building. This will be disabled if groupsize > 1.

export.statsfile:Filename or handle to print export statistics to.

export.stats_backup:Will print stats to STDERR instead.

export.verbosity:Controls the quantity of output. 0=none, 3=lots.


# -- mkcol.pl --

mkcol.about:The about text for the collection.

mkcol.bad_name_cvs:ERROR: No collection can be named CVS as this may interfere with directories created by the CVS versioning system.

mkcol.bad_name_modelcol:ERROR: No collection can be named modelcol as this is the name of the model collection.

mkcol.cannot_find_modelcol:ERROR: Cannot find the model collection %s

mkcol.col_already_exists:ERROR: This collection already exists.

mkcol.collectdir:Directory where new collection will be created.

mkcol.creating_col:Creating the collection %s

mkcol.creator:The collection creator's e-mail address.

mkcol.creator_undefined:ERROR: The creator was not defined. This variable is needed to recognise duplicate collection names.

mkcol.desc:PERL script used to create the directory structure for a new Greenstone collection.

mkcol.doing_replacements:doing replacements for %s

mkcol.long_colname:ERROR: The collection name must be less than 8 characters so compatibility with earlier filesystems can be maintained.

mkcol.maintainer:The collection maintainer's email address (if different from the creator).

mkcol.no_collectdir:ERROR: The collect dir doesn't exist: %s

mkcol.no_colname:ERROR: No collection name was specified.

mkcol.optionfile:Get options from file, useful on systems where long command lines may cause problems.

mkcol.params:[options] collection-name

mkcol.plugin:Perl plugin module to use (there may be multiple plugin entries).

mkcol.public:If this collection has anonymous access (true/false).

mkcol.quiet:Operate quietly.

mkcol.success:The new collection was created successfully at %s

mkcol.title:The title of the collection.

mkcol.win31compat:Whether or not the named collection directory must conform to Windows 3.1 file conventions or not (i.e. 8 characters long).

# -- pluginfo.pl --

pluginfo.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.

pluginfo.desc:Prints information about a plugin.

pluginfo.general_options:General options are inherited from parent classes of the plugin.

pluginfo.info:info

pluginfo.no_plugin_name:ERROR: You must provide a plugin name.

pluginfo.option_types:Plugins may take two types of options

pluginfo.params:[options] plugin-name

pluginfo.passing_options:Options may be passed to any plugin by including them in your collect.cfg configuration file.

pluginfo.specific_options:Specific options are defined within the plugin itself, and are available only to this particular plugin.


#
# Classifier option descriptions
#
AutoHierarchy.desc:Classifier plugin for generating a hierarchical classification based on structured metadata, without the need for a supplementary file.

AutoHierarchy.separator:Regular expression used for the separator

AutoHierarchy.suppresslastlevel:Ignore the final part of the metadata value. This is useful for metadata where each value is unique, such as file paths.

AZCompactList.allvalues:Use all metadata values found.

AZCompactList.desc:Classifier plugin for sorting alphabetically

AZCompactList.doclevel:Level to process document at.
AZCompactList.doclevel.top:Whole document.
AZCompactList.doclevel.section:By sections.

AZCompactList.firstvalueonly:Use only the first metadata value found.

AZCompactList.freqsort:Sort by node frequency rather than alpha-numeric.

AZCompactList.maxcompact:Maximum number of documents to be displayed per page.

AZCompactList.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.

AZCompactList.mincompact:Minimum number of documents to be displayed per page.

AZCompactList.mingroup:The smallest value that will cause a group in the hierarchy to form.

AZCompactList.minnesting:The smallest value that will cause a list to be converted into a nested list.

AZCompactList.recopt:Used in nested metadata such as -metadata Year/Organisation.
AZCompactList.sort:Metadata field to sort the child nodes by.

AZCompactSectionList.desc:Variation on AZCompactList that classifies sections rather than documents. Entries are sorted by section-level metadata.

AZList.desc:Classifier plugin for sorting alphabetically

AZList.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.

AZSectionList.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.

BasClas.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.

BasClas.builddir:Where to put the built indexes.

BasClas.buttonname:The label for the classifier screen and button in navigation bar.

BasClas.desc:Base class for all the classifiers.

BasClas.metadata.deft:Metadata element specified with -metadata.

BasClas.outhandle:The file handle to write output to.

BasClas.removeprefix:A prefix to ignore in metadata values when sorting.

BasClas.removesuffix:A suffix to ignore in metadata values when sorting.

BasClas.verbosity:Controls the quantity of output. 0=none, 3=lots.

Browse.desc:.

DateList.bymonth:Classify by year and month instead of only year.

DateList.desc:Classifier plugin for sorting by date. By default, sorts by 'Date' metadata. Date is assumed to be in the form yyyymmdd.

DateList.metadata:The metadata that contains the dates to classify by. The format is expected to be yyyymmdd.

DateList.reverse_sort:Sort the documents in reverse chronological order (newest first).

DateList.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).

DateList.sort:An extra metadata field to sort by in the case where two documents have the same date.

Hierarchy.desc:Classifier plugin for generating hierarchical classifications based on a supplementary structure file.

Hierarchy.hfile:The classification structure file.

Hierarchy.hlist_at_top:Display the first level of the classification horizontally.

Hierarchy.metadata:Metadata field used for classification. List will be sorted by this element, unless -sort is used.

Hierarchy.reverse_sort:Sort leaf nodes in reverse order (use with -sort).
Hierarchy.sort:Metadata field to sort by. Use '-sort nosort' for no sorting.

HTML.desc:Creates an empty classification that's simply a link to a web page.

HTML.url:The url of the web page to link to.

List.desc:Simple list classifier plugin.

List.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.

List.sort:Metadata field to sort by. Use '-sort nosort' for no sorting. 

Phind.desc:The Phind clasifier plugin.

Phind.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.

Phind.min_occurs:The minimum number of times a phrase must appear in the text to be included in the phrase hierarchy.

Phind.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.

Phind.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.

Phind.text:The text used to build the phrase hierarchy.

Phind.thesaurus:Name of a thesaurus stored in Phind format in the collection's etc directory.

Phind.title:The metadata field used to describe each document.

Phind.untidy:Don't remove working files.

SectionList.desc:Same as List classifier but includes all sections of document (excluding top level) rather than just top level document itself.

Collage.desc:The Collage classifier plugin.

Collage.geometry:The dimensions of the Collage canvas. For a canvas 600 pixels wide by 400 pixels high, for example, specify geometry as 600x400

Collage.maxDepth:Images for collaging are drawn from mirroring the underlying browse classifier. This controls the maximum depth of the mirroring process.

Collage.maxDisplay:The maximum number of images to show in the collage at any one time.

Collage.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.

Collage.bgcolor:The background color of the collage canvas, specified in hexadecimal form (for example #008000 results in a forest green background).

Collage.refreshDelay:Rate, in milliseconds, that the collage canvas is refreshed.

Collage.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.

Collage.imageMustNotHave:Used to suppress images that should not appear in the collage, such as image buttons that make up the navigation bar.

Collage.caption:Optional captions to display below the collage canvas.

#
# Plugin option descriptions
#

ArcPlug.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.

BasPlug.adding:adding

BasPlug.already_seen:already seen

BasPlug.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.

BasPlug.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.

BasPlug.could_not_extract_encoding:WARNING: encoding could not be extracted from %s - defaulting to %s

BasPlug.could_not_extract_language:WARNING: language could not be extracted from %s - defaulting to %s

BasPlug.could_not_open_for_reading:could not open %s for reading

BasPlug.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.

BasPlug.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.

BasPlug.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.

BasPlug.desc:Base class for all the import plugins.

BasPlug.done_acronym_extract:done extracting acronyms.

BasPlug.done_acronym_markup:done acronym markup.

BasPlug.done_email_extract:done extracting e-mail addresses.

BasPlug.dummy_text:This document has no text.

BasPlug.empty_file:file contains no text

BasPlug.extract_acronyms:Extract acronyms from within text and set as metadata.

BasPlug.extract_email:Extract email addresses as metadata.

BasPlug.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.

BasPlug.extract_language:Identify the language of each document and set 'Language' metadata. Note that this will be done automatically if -input_encoding is 'auto'.

BasPlug.extracting:extracting

BasPlug.extracting_acronyms:extracting acronyms

BasPlug.extract_keyphrases:Extract keyphrases automatically with Kea (default settings).

BasPlug.extract_keyphrase_options:Options for keyphrase extraction with Kea. For example: mALIWEB - use ALIWEB extraction model; n5 - extract 5 keyphrase;, eGBK - use GBK encoding.

BasPlug.extracting_emails:extracting e-mail addresses

BasPlug.file_has_no_text:ERROR: %s contains no text

BasPlug.first:Comma separated list of first sizes to extract from the text into a metadata field. The field is called 'FirstNNN'.

BasPlug.input_encoding:The encoding of the source documents. Documents will be converted from these encodings and stored internally as utf8.
BasPlug.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.
BasPlug.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.
BasPlug.input_encoding.unicode:Just unicode.
BasPlug.input_encoding.utf8:Either utf8 or unicode -- automatically detected.

BasPlug.keyphrases:keyphrases

BasPlug.marking_up_acronyms:marking up acronyms

BasPlug.markup_acronyms:Add acronym metadata into document text.

BasPlug.maximum_century:The maximum named century to be extracted as historical metadata (e.g. 14 will extract all references up to the 14th century).

BasPlug.maximum_year:The maximum historical date to be used as metadata (in a Common Era date, such as 1950).

BasPlug.must_be_implemented:BasPlug::read function must be implemented in sub-class for recursive plugins

BasPlug.no_bibliography:Do not try to block bibliographic dates when extracting historical dates.

BasPlug.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).

BasPlug.read_denied:Read permission denied for %s

BasPlug.smart_block:Block files in a smarter way than just looking at filenames.

BasPlug.stems:stems

BasPlug.unsupported_encoding:WARNING: %s appears to be encoded in an unsupported encoding (%s) - using %s

BasPlug.wrong_encoding:WARNING: %s was read using %s encoding but appears to be encoded as %s.

BibTexPlug.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.

BookPlug.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.

ConvertToPlug.convert_to:Plugin converts to TEXT or HTML.
ConvertToPlug.convert_to.html:HTML format.
ConvertToPlug.convert_to.text:Plain text format.

ConvertToPlug.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.

ConvertToPlug.use_strings:If set, a simple strings function will be called to extract text if the conversion utility fails.

ConvertToRogPlug.desc:A plugin that inherits from RogPlug.

DBPlug.desc:Uses records from a database as documents.

DBPlug.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.

EMAILPlug.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)

EMAILPlug.no_attachments:Do not save message attachments.

EMAILPlug.headers:Store email headers as "Headers" metadata.

EMAILPlug.split_exp:A perl regular expression used to split files containing many messages into individual documents.

ExcelPlug.desc:A plugin for importing Microsoft Excel files.

FOXPlug.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.

GAPlug.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.

GMLPlug.desc:Plugin which processes a GML format document assumes that gml tags are all in lower-case.

HBPlug.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

HTMLPlug.assoc_files:Perl regular expression of file extensions to associate with html documents.

HTMLPlug.desc:This plugin processes HTML files

HTMLPlug.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.

HTMLPlug.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.

HTMLPlug.hunt_creator_metadata:Find as much metadata as possible on authorship and place it in the 'Creator' field. Requires the -metadata_fields flag.

HTMLPlug.keep_head:Don't remove headers from html files.

HTMLPlug.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.

HTMLPlug.no_metadata:Don't attempt to extract any metadata from files.

HTMLPlug.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.

HTMLPlug.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).

HTMLPlug.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).

HTMLPlug.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.

ImagePlug.converttotype:Convert main image to format 's'.

ImagePlug.desc:This plugin processes images, adding basic metadata

ImagePlug.minimumsize:Ignore images smaller than n bytes.

ImagePlug.noscaleup:Don't scale up small images when making thumbnails.

ImagePlug.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.

ImagePlug.screenviewtype:If -screenviewsize is set, this sets the screen display image type.

ImagePlug.thumbnailsize:Make thumbnails of size nxn.

ImagePlug.thumbnailtype:Make thumbnails in format 's'.

IndexPlug.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'.

ISISPlug.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).

ISISPlug.subfield_separator:The string used to separate subfields in CDS/ISIS database records.

ISISPlug.entry_separator:The string used to separate multiple values for single metadata fields in CDS/ISIS database records.

LaTeXPlug.desc:Plugin for LaTeX documents.

MACROPlug.desc:Creates simple single-level document. Adds Title metadata of first line of text (up to 100 characters long).

MARCPlug.desc:Basic MARC plugin.

MARCPlug.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.

NULPlug.desc:Dummy (.nul) file plugin. Used with the files produced by exploding metadata database files.

OAIPlug.desc:Basic Open Archives Initiate (OAI) plugin.

OggVorbisPlug.add_technical_metadata:Add technical (eg. bitrate) metadata.

OggVorbisPlug.desc:A plugin for importing Ogg Vorbis audio files.

PagedImgPlug.desc:Plugin for documents made up of a sequence of images, with optional OCR text for each image.

PagedImgPlug.documenttype:Set the document type (used for display)
PagedImgPlug.documenttype.paged:Paged documents have next and previous arrows and a 'go to page X' box
PagedImgPlug.documenttype.hierarchy:Hierarchical documents have a table of contents

PagedImgPlug.headerpage:Add a top level header page (that contains no image) to each document.

PagedImgPlug.screenview:Produce a screenview image for each image, and set Screen, ScreenSize, ScreenWidth and ScreenHeight metadata.

PagedImgPlug.screenviewsize:Make screenview images of size nxn.

PagedImgPlug.screenviewtype:Make screenview images in format 's'.

PagedImgPlug.thumbnail:Produce a thumbnail for each image

PDFPlug.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).

PDFPlug.desc:Reasonably with-it pdf plugin.

PDFPlug.nohidden:Prevent pdftohtml from attempting to extract hidden text. This is only useful if the -complex option is also set.

PDFPlug.noimages:Don't attempt to extract images from PDF.

PDFPlug.use_sections:Create a separate section for each page of the PDF file.

PDFPlug.zoom:The factor by which to zoom the PDF for output (this is only useful if -complex is set).

PPTPlug.desc:A plugin for importing Microsoft PowerPoint files.

PSPlug.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

PSPlug.extract_date:Extract date from PS header.

PSPlug.extract_pages:Extract pages from PS header.

PSPlug.extract_title:Extract title from PS header.

RecPlug.desc:RecPlug is a plugin which recurses through directories processing each file it finds.

RecPlug.recheck_directories:After the files in an import directory have been processed, re-read the directory to discover any new files created.

RecPlug.use_metadata_files:Read metadata from metadata XML files.

ReferPlug.desc:ReferPlug reads bibliography files in Refer format.

ReferPlug.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

RogPlug.desc:Creates simple single-level documents from .rog or .mdb files.

RTFPlug.desc:Plugin for importing Rich Text Format files.

SRCPlug.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)

SRCPlug.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.

SplitPlug.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.

SplitPlug.split_exp:A perl regular expression to split input files into segments.

TEXTPlug.desc:Creates simple single-level document. Adds Title metadata of first line of text (up to 100 characters long).

TEXTPlug.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.

UnknownPlug.assoc_field:Name of the metadata field that will hold the associated file's name.

UnknownPlug.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.

UnknownPlug.file_type:Type of the file (e.g. MPEG, MIDI, ...)

UnknownPlug.mime_type:Mime type of the file (e.g. image/gif).

MP3Plug.desc:Plugin for processing MP3 files.

MP3Plug.assoc_images:Use google image search to locate images related to MP3 file based on ID3 Title and Artist metadata.

MP3Plug.assoc_images:Used to store [applet] metadata for each document that contains the necessary HTML for an MP3 audio player applet to play that file.

MP3Plug.metadata_fields:Comma separated list of metadata fields to extract (assuming present) in an MP3 file. Use \"*\" to extract all the fields.

W3ImgPlug.aggressiveness:Range of related text extraction techniques to use.
W3ImgPlug.aggressiveness.1:Filename, path, ALT text only.
W3ImgPlug.aggressiveness.2:All of 1, plus caption where available.
W3ImgPlug.aggressiveness.3:All of 2, plus near paragraphs where available.
W3ImgPlug.aggressiveness.4:All of 3, plus previous headers (<h1>, <h2>...) where available.
W3ImgPlug.aggressiveness.5:All of 4, plus textual references where available.
W3ImgPlug.aggressiveness.6:All of 4, plus page metatags (title, keywords, etc).
W3ImgPlug.aggressiveness.7:All of 6, 5 and 4 combined.
W3ImgPlug.aggressiveness.8:All of 7, plus repeat caption, filename, etc (raise ranking of more relevant results).
W3ImgPlug.aggressiveness.9:All of 1, plus full text of source page.

W3ImgPlug.caption_length:Maximum length of captions (in characters).

W3ImgPlug.convert_params:Additional parameters for ImageMagicK convert on thumbnail creation. For example, '-raise' will give a three dimensional effect to thumbnail images.

W3ImgPlug.desc:A plugin for extracting images and associated text from webpages.

W3ImgPlug.document_text:Add image text as document:text (otherwise IndexedText metadata field).

W3ImgPlug.index_pages:Index the pages along with the images. Otherwise reference the pages at the source URL.

W3ImgPlug.max_near_text:Maximum characters near images to extract.

W3ImgPlug.min_height:Pixels. Skip images shorter than this.

W3ImgPlug.min_near_text:Minimum characters of near text or caption to extract.

W3ImgPlug.min_size:Bytes. Skip images smaller than this.

W3ImgPlug.min_width:Pixels. Skip images narrower than this.

W3ImgPlug.neartext_length:Target length of near text (in characters).

W3ImgPlug.no_cache_images:Don't cache images (point to URL of original).

W3ImgPlug.smallpage_threshold:Images on pages smaller than this (bytes) will have the page (title, keywords, etc) meta-data added.

W3ImgPlug.textrefs_threshold:Threshold for textual references. Lower values mean the algorithm is less strict.

W3ImgPlug.thumb_size:Max thumbnail size. Both width and height.

WordPlug.desc:A plugin for importing Microsoft Word documents.

XMLPlug.desc:Base class for XML plugins.

ZIPPlug.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)


#
# Perl module strings
#

classify.could_not_find_classifier:ERROR: Could not find classifier \"%s\"

plugin.could_not_find_plugin:ERROR: Could not find plugin \"%s\"

plugin.including_archive:including the contents of 1 ZIP/TAR archive

plugin.including_archives:including the contents of %d ZIP/TAR archives

plugin.kill_file:Process killed by .kill file

plugin.n_considered:%d documents were considered for processing

plugin.n_included:%d were processed and included in the collection

plugin.n_rejected:%d were rejected

plugin.n_unrecognised:%d were unrecognised

plugin.no_plugin_could_process:WARNING: No plugin could process %s

plugin.no_plugin_could_recognise:WARNING: No plugin could recognise %s

plugin.no_plugin_could_process_this_file:no plugin could process this file

plugin.no_plugin_could_recognise_this_file:no plugin could recognise this file

plugin.one_considered:1 document was considered for processing

plugin.one_included:1 was processed and included in the collection

plugin.one_rejected:1 was rejected

plugin.one_unrecognised:1 was unrecognised

plugin.see_faillog:See %s for a list of unrecognised and/or rejected documents

PrintUsage.default:Default

PrintUsage.required:REQUIRED