source: trunk/gsdl/perllib/strings.rb@ 5764

#
# Common output messages
#

common.cannot_create_file:ERROR: Can't create file

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

common.cannot_open:ERROR: Can't open

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

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

common.cannot_read:ERROR: Can't read

common.cannot_read_file:ERROR: Can't read file

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.


# -- buildcol.pl --

buildcol.allclassifications:Don't remove empty classifications.

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

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

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.unlinked_col_images:Collection images may not be linked correctly.

buildcol.unknown_mode:Unknown mode

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.


# -- import.pl --

import.archivedir:Where the converted material ends up.

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

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

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.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. 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.


# -- 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

mkcol.col_already_exists:ERROR: This collection already exists.

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

mkcol.creating_col:Creating the collection

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

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

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

mkcol.title:The title of the collection.


# -- 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
#

AZCompactList.buttonname:Button name for this classification.

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

AZCompactList.metadata:Metadata field used for classification. List will be sorted by this element.
AZCompactList.metadata.deft:Metadata element specified with -metadata.
AZCompactList.maxcompact:Maximum number of documents to be displayed per page.

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.onlyfirst:Control whether all or only first metadata value used from array of metadata.

AZCompactList.recopt:Used in nested metadata such as -metadata Year/Organisation.
AZCompactList.removeprefix:A prefix to ignore in the Metadata values for the field when sorting.
AZCompactList.removesuffix:A suffix to ignore in the Metadata values for the field when sorting.
AZCompactSectionList.desc:Variation on AZCompactList that classifies sections rather than documents. Entries are sorted by section-level metadata.
AZList.buttonname:Button name for this classification.

AZList.desc:Classifier plugin for sorting alphabetically

AZList.metadata:Metadata field used for classification. List will be sorted by this element.

AZList.removeprefix:A prefix to ignore in the Metadata values for the field when sorting.

AZList.removesuffix:A suffix to ignore in the Metadata values for the field when sorting.

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.desc:Base class for all the classifiers.

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

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

Browse.desc:

DateList.bymonth:Classify by year and month.

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

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

DateList.nogroupyears:Make each year an individual entry in the horizontal list. (ie, don't have 1920-1922 type classification nodes).

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

Hierarchy.buttonname:Title field for this classification.

Hierarchy.desc:Classifier plugin for generating hierarchical classifications.

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

HTML.buttonname:The title field for this classification.

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.buttonname:Button name for this classification.

List.desc:Simple list classifier plugin.

List.metadata:Metadata field used for classification. List will be sorted by this element.

List.sort:Metadata field to sort by. If not set, sorts in build (random) order.

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

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.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.


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

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\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.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.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.

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. &gt;Subject&lt;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'.

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.

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

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.use_metadata_files:Read metadata from metadata XML files.

ReferPlug.desc: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:Mime type of the file (e.g. image/gif).

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.no_plugin_could_process:WARNING: No plugin could process %s

plugin.no_plugin_could_process_this_file:no plugin could process 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.see_faillog:See %s for a list of rejected documents

PrintUsage.default:Default

PrintUsage.required:REQUIRED