Annotation of storage/meta/meta-format.tex, revision 1.11

1.1       casties     1: \documentclass[a4paper]{article}
                      2: 
                      3: \usepackage[latin1]{inputenc}
                      4: \usepackage[T1]{fontenc}
                      5: \usepackage{ae}
                      6: %\usepackage{times}
                      7: %\usepackage{courier}
                      8: 
                      9: % create in-text links black (with PDF)
1.6       casties    10: \usepackage[colorlinks=true,linkcolor=black]{hyperref}
1.1       casties    11: % Format URLs nicely (without PDF)
1.6       casties    12: %\usepackage{url}
1.1       casties    13: 
                     14: 
                     15: \title{A simple metadata format for resource bundles}
                     16: 
1.4       casties    17: \author{Robert Casties, Dirk Wintergrün, Hans-Christoph Liess}
1.1       casties    18: 
1.10      casties    19: \date{V1.0.3 of 11.9.2003}
1.1       casties    20: 
                     21: \begin{document}
                     22: 
                     23: \maketitle
                     24: 
                     25: \tableofcontents
                     26: 
                     27: 
                     28: \section{File and directory names}
                     29: \label{sec:file-directory-names}
                     30: 
                     31: File and directory names should not contain spaces. Allowed characters
                     32: in filenames are only the alphanumeric set a-z, A-Z, 0-9, hyphen
                     33: ``-'', underscore ``\_'' and dot ``.''.
                     34: 
                     35: File and directory paths in the metadata file use the conventional
                     36: Unix file separator slash ``/''.
                     37: 
1.4       casties    38: 
                     39: \section{Metadata files}
                     40: \label{sec:metadata-files}
                     41: 
                     42: The metadata information is stored in the XML format documented below
                     43: in special files in the resource directory. Two forms of metadata
                     44: files are possible:
                     45: \begin{itemize}
                     46: \item a file named \texttt{index.meta} in a directory.
                     47: 
                     48: \item a file named like the data file it describes with an
                     49:   additional extension \texttt{.meta}. For example metadata for the
                     50:   file \texttt{0001.tif} would be in a file \texttt{0001.tif.meta}.
                     51: \end{itemize}
                     52: 
                     53: The resource directory must contain an \texttt{index.meta} file with
                     54: information about the resource as a whole. Other directories can
                     55: contain \texttt{index.meta} files.
                     56: 
                     57: Additional information about single data files that are part of the
                     58: resource can either be put in \texttt{file} tags in the
                     59: \texttt{index.meta} file or in separate \emph{filename}\texttt{.meta}
                     60: files for each data file. Information from the directory level file is
                     61: inherited at the file level.
                     62: 
                     63: 
1.1       casties    64: \section{Resource format}
                     65: \label{sec:mpiwg-doc}
                     66: 
                     67: In this description elements marked ``optional'' need not be supplied
                     68: by the provider of the resource and may be absent in all versions of
                     69: the metadata file. Elements marked ``required'' must be supplied by
                     70: the provider of the resource. Elements marked ``deduced'' can be
                     71: supplied by the provider of the resource but can also be provided by
1.4       casties    72: automatic scripts later in the process, these elements must be present
1.1       casties    73: in the final file.
                     74: 
1.11    ! casties    75: The outer container element is \texttt{resource}. It has the following
        !            76: \textbf{attributes}:
        !            77: 
        !            78: \begin{description}
        !            79: \item[type] sub-type of resource (e.g. ``ECHO'',
        !            80:   ``MPIWG'') -- optional.
        !            81:   
        !            82: \item[version] version number of metadata format (currently 1.0) --
        !            83:   required.
        !            84: \end{description}
        !            85: 
        !            86: \noindent The allowed \textbf{elements} inside \texttt{resource} are:
1.1       casties    87: 
                     88: \begin{description}
                     89: \item[description] An informal textual description of the
                     90:   resource -- optional.
                     91: 
                     92: \item[name] The filename of the resource (name of the directory this
                     93:   file is contained in) -- required.
                     94: 
                     95: \item[creator] The name of the project or person that created the
                     96:   resource -- optional.
1.4       casties    97:   
                     98: \item[archive-creation-date] The time and date the archive collection
                     99:   was created -- deduced.
1.1       casties   100: 
1.4       casties   101: \item[archive-storage-date] The time and date the archive was written
                    102:   to permanent storage -- deduced (must not be set by the user).
1.1       casties   103: 
                    104: \item[archive-path] The full path to the resource directory inside the
1.5       casties   105:   whole archive collection, including the resource directory -- deduced.
1.1       casties   106:   
                    107: \item[derived-from] Container for the description of the original
                    108:   resource if this resource is a modified version of another resource
                    109:   -- optional.
                    110: 
                    111:   \begin{description}
                    112:   \item[archive-path] The full path to the original resource
                    113:     --required.
                    114: 
                    115:   \item[description] An informal textual description of the relation
                    116:   of this resource to the original resource -- optional.
                    117:   \end{description}
                    118:   
                    119: \item[linked-with] Container for the description of another
                    120:   resource when this resource is a linked copy of another resource
                    121:   -- optional.
                    122: 
                    123:   \begin{description}
                    124:   \item[archive-path] The full path to the linked resource
                    125:     --required.
                    126: 
                    127:   \item[description] An informal textual description of the relation
                    128:   of this resource to the linked resource -- optional.
                    129:   \end{description}
                    130:   
                    131: \item[content-type] The content type of this resource -- required.\\
                    132:   The content type enables the choice of tools to manipulate and
                    133:   display the resource. There should be a common list of content
                    134:   types. For digital documents (books, manuscripts) this would be
                    135:   "scanned document", for other image data "scanned
                    136:   images".\footnote{The criterion for documents is a ordered
                    137:     succession of image files (pages) and equal image size and
                    138:     resolution throughout the images of a resource.}
                    139:   
                    140: \item[meta] Additional metadata information about the resource --
                    141:   optional.\\ For a description of additional metadata see below.
                    142: 
                    143: \item[dir] Container for the description of a subdirectory -- required
                    144:   (when there are subdirectories).\\ \texttt{dir} tags should not be
                    145:   nested. Directories at lower levels are identified by their
                    146:   \texttt{path}.
                    147: 
                    148:   \begin{description}
                    149:   \item[description] An informal textual description of the
                    150:     subdirectory -- optional.
                    151: 
                    152:   \item[name] The name of the subdirectory -- required.
                    153:     
                    154:   \item[path] The directory path of this subdirectory relative to the
1.5       casties   155:     resource's root directory (excluding the directory itself) --
                    156:     required (may be empty or omitted if the directory is a direct
                    157:     child of the resource's root directory).
1.1       casties   158:     
                    159:   \item[meta] Additional metadata information about the directory --
                    160:     optional.\\ For a description of additional metadata see below.
                    161:   \end{description}
                    162:   
                    163: \item[file] Container for the description of a file -- deduced.\\
                    164:   \texttt{file} tags should not be nested in \texttt{dir} tags. Files
                    165:   at lower directory levels are identified by their \texttt{path}.
                    166: 
                    167:   \begin{description}
                    168:   \item[description] An informal textual description of the
                    169:     file -- optional.
                    170: 
                    171:   \item[name] The name of the file -- required.
                    172:     
                    173:   \item[path] The directory path of this file relative to the
1.5       casties   174:     resource's root directory (excluding the file itself) -- required
                    175:     (may be empty or omitted if the file is in the resource's root
                    176:     directory).
1.7       casties   177:     
                    178:   \item[date] The file's modification or creation date\footnote{The
                    179:       preferred time and date format is ``YYYY/MM/DD HH:MM:SS''},
                    180:     whichever is more recent -- optional.
1.1       casties   181: 
                    182:   \item[modification-date] The file's modification date -- optional.
                    183: 
                    184:   \item[creation-date] The file's creation date -- optional.
1.7       casties   185:     
1.1       casties   186:   \item[size] The file size -- deduced.
                    187:     
                    188:   \item[mime-type] The file's mime-type -- optional.
                    189: 
                    190:   \item[md5cs] MD5 checksum of the file content -- optional.
                    191:     
                    192:   \item[meta] Additional metadata information about the file --
                    193:     optional. For a description of additional metadata see below.
                    194:   \end{description}
                    195:   
                    196: \end{description}
                    197: 
                    198: 
                    199: 
                    200: \section{Additional metadata}
                    201: \label{sec:additional-metadata}
                    202: 
                    203: All elements with \texttt{meta} tags can contain an arbitrary number
                    204: of additional metadata elements.
                    205: 
1.4       casties   206: \subsection{Language}
                    207: \label{sec:lang}
                    208: 
                    209: The language of a resource (e.g. a text) can be specified with a
                    210: \texttt{lang} tag. Languages have to be described using the
                    211: international codes for the representation of names of languages
                    212: either in two-letter form (ISO 639-1) or in three-letter form (ISO
                    213: 639-2).  The entire catalogue of languages is documented on the page
                    214: 
                    215: \url{http://www.loc.gov/standards/iso639-2/englangn.html}
                    216: 
1.1       casties   217: 
                    218: \subsection{DRI}
                    219: \label{sec:dri}
                    220: 
                    221: The \emph{digital resource identifier} for the resource is specified
1.4       casties   222: in a \texttt{dri} element. Digital resource identifiers are documented
1.1       casties   223: on the page
                    224: 
                    225: \url{http://pythia.mpiwg-berlin.mpg.de/projects/standards/dri}.
                    226: 
                    227: 
1.4       casties   228: 
                    229: \subsection{Collection context}
                    230: \label{sec:collection-context}
                    231: 
                    232: The context of a resource as part of a collection or part of a project can be
1.5       casties   233: specified in the \texttt{context} element. All elements in the
                    234: container can appear multiple times.
1.4       casties   235: 
                    236: \begin{description}
1.5       casties   237: \item[context] information on collection or project context.
1.4       casties   238: 
1.5       casties   239:   \begin{description}
                    240:   \item[link] URL to additional context information.
                    241:     
                    242:   \item[name] Textual description of project or collection.
                    243:   \end{description}
1.4       casties   244: \end{description}
1.5       casties   245: 
1.4       casties   246: 
                    247: 
                    248: 
1.1       casties   249: \subsection{Bibliographic information}
                    250: \label{sec:bibliographic-data}
                    251: 
1.5       casties   252: Bibliographic information is presented in a \texttt{bib} container with
1.1       casties   253: a \texttt{type} parameter, giving the type of bibliographic resource.
1.4       casties   254: The \texttt{type} field can be repeated as a tag in the container.
                    255: 
1.5       casties   256: The format is based on the ECHO scheme for bibliographic data (cf.
                    257: content workflow), the MPIWG ``Projektbibliografie'' and the format of
                    258: the commonly used program ``EndNote''.
                    259: 
1.4       casties   260: 
                    261: \subsubsection{Book}
                    262: 
                    263: \begin{description}
                    264: 
                    265: \item [bib type="book"] a published book.
                    266: 
                    267:   \begin{description}
                    268:   \item [author] The author of the book.
                    269:   \item [year] The year of publication.
                    270:   \item [title] Title of the book.
                    271:   \item [series-editor] Name of the series editor, if the book appears
                    272:     in a series.
                    273:   \item [series-title] Title of the serie, if the book appears in a
                    274:     series.
                    275:   \item [series-volume] Volume number, if the book appears in a
                    276:     series.
                    277:   \item [number-of-pages] Number of pages of the entire book.
                    278:   \item [city] City where the book was published.
                    279:   \item [publisher] Name of the publishing company
                    280:   \item [edition] Edition of the book (e.g. third edition)
                    281:   \item [number-of-volumes] Number of volumes, if the the book is
                    282:     published in multiple volumes.
                    283:   \item [translator] Name of the translator.
                    284:   \item [isbn-issn]
                    285:   \end{description}
                    286: \end{description}
                    287: 
                    288: \subsubsection{In Book}
                    289: 
                    290: \begin{description}
                    291: \item [bib type="inbook"] an article as part of a book.
                    292: 
                    293:   \begin{description}
                    294:   \item [author] The author of the book.
                    295:   \item [year] The year of publication.
                    296:   \item [title] Title of the article.
                    297:   \item [editor] Name of the book's editor.
                    298:   \item [book-title] Title of the book.
                    299:   \item [series-volume] Volume number, if the book appears in a
                    300:     series.
                    301:   \item [pages] Number of pages of the article.
                    302:   \item [city] City where the book was published.
                    303:   \item [publisher] Name of the publishing company
                    304:   \item [edition] Edition of the book (e. g. third edition)
                    305:   \item [series-author] Name of the series editor, if the book appears
                    306:     in a series.
                    307:   \item [series-title] Title of the series, if the book appears in a
                    308:     series.
                    309:   \item [number-of-volumes] Number of volumes, if the the book is
                    310:     published in multiple volumes.
                    311:   \item [translator] Name of the translator
                    312:   \item [isbn-issn]
                    313:   \end{description}
                    314: \end{description}
                    315: 
                    316: \subsubsection{Proceedings}
                    317: 
                    318: \begin{description}
                    319: \item [bib type="proceedings"] a conference proceedings publication.
                    320: 
                    321:   \begin{description}
                    322:   \item [author] The author of the article.
                    323:   \item [year] The year of publication.
                    324:   \item [title] Title of the article.
                    325:   \item [editor] Name of the book's editor.
                    326:   \item [conference-name] Name of the conference the proceedings are
                    327:     related to.
                    328:   \item [volume] Volume number.
                    329:   \item [pages] Number of pages of the article.
                    330:   \item [date] Date of the conference the proceedings are related to.
                    331:   \item [conference]-location City where the conference was held.
                    332:   \item [publisher] Name of the publishing company
                    333:   \item [edition] Edition of the book (e. g. third edition)
                    334:   \item [series-editor] Name of the series editor, if the book appears
                    335:     in a series.
                    336:   \item [series-title] Title of the series, if the book appears in a
                    337:     series.
                    338:   \item [number-of-volumes] Number of volumes, if the the book is
                    339:     published as multiple volumes.
                    340:   \item [isbn-issn]
                    341:   \end{description}
                    342: \end{description}
                    343: 
                    344: \subsubsection{Edited Book}
                    345: 
                    346: \begin{description}
                    347: \item[bib type="edited-book"] a book that is the edition of another
                    348:   work.
                    349: 
                    350:   \begin{description}
                    351:   \item [editor] Name of the editor of the book.
                    352:   \item [year] The year of publication.
                    353:   \item [title] Title of the book.
                    354:   \item [series-editor] Name of the editor of the series the book is
                    355:     part of.
                    356:   \item [series-title] Title of the series, if the book is part of a
                    357:     series.
                    358:   \item [series-volume] Volume number, if the book appears in a series.
                    359:   \item [number-of-pages] Number of pages of the article.
                    360:   \item [city] City where the book was published.
                    361:   \item [publisher] Name of the publishing company
                    362:   \item [edition] Information about the edition (e.g. ``Repr. of the London ed. 1652'')
                    363:   \item [number-of-volumes] Number of volumes, if the the book is
                    364:     published as multiple volumes.
                    365:   \item [isbn-issn]
                    366:   \end{description}
                    367: \end{description}
                    368: 
                    369: \subsubsection{Journal Article}
                    370: 
                    371: \begin{description}
                    372: \item [bib type="journal-article"] an article in a scientific journal.
                    373:   \begin{description}
                    374:   \item [author] The author of the article.
                    375:   \item [year] The year of publication.
                    376:   \item [title] Title of the article.
                    377:   \item [journal] Name of the journal.
                    378:   \item [volume] Volume number, if the journal appears in a series.
                    379:   \item [issue] Number of the issue the article is part of.
                    380:   \item [pages] Number of pages of the article.
                    381:   \item [alternate-journal] Alternate Journal
                    382:   \item [isbn-issn]
                    383:   \end{description}
                    384: \end{description}
                    385: 
                    386: \subsubsection{Magazine Article}
                    387: 
                    388: \begin{description}
                    389: \item [bib type="magazine-article"] an article in a popular magazine.
                    390:   \begin{description}
                    391:   \item [author] The author of the book.
                    392:   \item [year] The year of publication.
                    393:   \item [title] Title of the article.
                    394:   \item [magazine] Name of the magazine.
                    395:   \item [volume] Volume number, if the book appears in a series.
                    396:   \item [issue-number] Number of the issue the article is part of.
                    397:   \item [pages Number] of pages of the article.
                    398:   \item [date] Date when the article appeared.
                    399:   \end{description}
                    400: \end{description}
                    401: 
                    402: \subsubsection{Newspaper Article}
                    403: 
                    404: \begin{description}
                    405: \item [bib type="newspaper-article"] an article in a newspaper.
                    406:   \begin{description}
                    407:   \item [author] The author of the article.
                    408:   \item [year] The year of publication.
                    409:   \item [title] Title of the article.
                    410:   \item [Newspaper] Name of the newspaper the article appeared in.
                    411:   \item [pages] Number of pages of the article.
                    412:   \item [issue-date] Date of the issue the article is part of.
                    413:   \item [city] City of the newspaper.
                    414:   \end{description}
                    415: \end{description}
                    416: 
                    417: \subsubsection{Thesis}
                    418: 
                    419: \begin{description}
                    420: \item [bib type="thesis"] a master/doctorate/etc. thesis.
                    421:   \begin{description}
                    422:   \item [author] The author of the thesis.
                    423:   \item [year] The year of publication.
                    424:   \item [title] Title of the thesis.
                    425:   \item [academic-department] Name of the academic department where
                    426:     the thesis was handed in.
                    427:   \item [number-of-pages] Number of pages of the thesis.
                    428:   \item [city] City where the thesis was published.
                    429:   \item [University] Name of the university where the thesis was
                    430:     handed in.
                    431:   \item [isbn-issn]
                    432:   \end{description}
                    433: \end{description}
                    434: 
                    435: \subsubsection{Report}
                    436: 
                    437: \begin{description}
                    438: \item [bib type="report"] a scientific report.
                    439:   \begin{description}
                    440:   \item [author] The author of the report.
                    441:   \item [year] The year of publication.
                    442:   \item [title] Title of the report.
                    443:   \item [pages] Number of pages of the report.
                    444:   \item [date] Date when the report appeared.
                    445:   \item [city] City where the book was published.
                    446:   \item [institution] Institution where the report was produced.
                    447:   \item [type] Type of report.
                    448:   \item [report-number] Report number.
                    449:   \end{description}
                    450: \end{description}
                    451: 
1.5       casties   452: \subsubsection{Manuscript}
                    453: 
                    454: \begin{description}
                    455: \item [bib type="manuscript"] a handwritten/typewritten manuscript.
                    456: 
                    457:   \begin{description}
                    458:   \item [title] Title of the manuscript.
                    459:   \item [author] The author of the text.
                    460:   \item [location] Name of the library where the manuscript is
                    461:     currently located.
                    462:   \item [year] The year or century of publication.
                    463:   \item [pages] Number of pages of the manuscript.
                    464:   \item [signature] Signature of the manuscript.
                    465:   \item [editorial-remarks] Remarks related to the online
                    466:     publication of the manuscript. This could be notes about
                    467:     annotations etc.
                    468:   \item [description] This can be any kind of description.
                    469:   \item [keywords] Keywords related to the manuscript.
                    470:   \end{description}
                    471: \end{description}
                    472: 
                    473: 
1.4       casties   474: \subsubsection{Generic}
                    475: 
                    476: \begin{description}
                    477: \item [bib type="generic"] a generic bibliographic type. This type
                    478:   should only be used in rare cases.
                    479:   \begin{description}
                    480:   \item [author]
                    481:   \item [year]
                    482:   \item [title]
                    483:   \item [secondary-author]
                    484:   \item [secondary-title]
                    485:   \item [volume]
                    486:   \item [number]
                    487:   \item [pages]
                    488:   \item [date]
                    489:   \item [place-published]
                    490:   \item [publisher]
                    491:   \item [edition]
                    492:   \item [tertiary author]
                    493:   \item [tertiary-title]
                    494:   \item [number-of-volumes]
                    495:   \item [type-of-work]
                    496:   \item [subsidiary author]
                    497:   \item [alternate-title]
                    498:   \item [isbn-issn]
                    499:   \item [call-number]
                    500:   \item [label]
                    501:   \item [keywords]
                    502:   \item [abstract]
                    503:   \item [notes]
                    504:   \item [url]
1.5       casties   505:   \end{description}
1.4       casties   506: \end{description}
                    507: 
                    508: 
                    509: \subsection{Architectural drawings}
                    510: \label{sec:doc}
                    511: 
                    512: Specific information for architectural drawings is presented in a
1.5       casties   513: \texttt{doc} container with an additional \texttt{type} attribute
                    514: giving the type of drawing. All elements inside the container can
                    515: appear multiple times.
1.4       casties   516: 
                    517: \begin{description}
1.5       casties   518: 
                    519: \item[doc type="Architectural Drawing"] architectural drawing.
                    520: 
                    521:   \begin{description}
                    522:   \item [person] last name and first name of a person, separated by a
                    523:     comma. A further common name for the person can be put infront,
                    524:     separated by a semicolon.
                    525:   \item [location] Name of a place in its common notation. This can be
                    526:     a city or a institution.
                    527:   \item [date] This can be a year (or several years, separated by
                    528:     commas) or a period (1706-1714). Years are noted with four digits.
                    529:   \item [object] Short description of an object or signatures.
                    530:   \item [keywords] Keywords related to the object.
                    531: \end{description}
1.4       casties   532: \end{description}
1.1       casties   533: 
                    534: 
1.10      casties   535: \subsection{Document structure (table of contents)}
1.1       casties   536: \label{sec:toc}
                    537: 
1.4       casties   538: Information on the structure of a document like the division into
                    539: parts and chapters in the way of a table of contents is presented in a
                    540: \texttt{toc} container. 
                    541: 
                    542: The scheme allows multiple logical pages on a single page image
                    543: as it is often the case with scanned books or manuscripts. The scheme
                    544: also allows for ``loose'' numbering schemes with roman, arabic or
                    545: other page numbers consecutively or mixed and changes in the numbering
                    546: within the document.
                    547: 
                    548: The flexibility comes from the fact that no additional assumptions
                    549: about the mapping between logical pages and page images are made in
                    550: the format. All mapping information is specified by the user.
                    551: 
                    552: The logical page numbering or naming that can be presented to the user
                    553: is specified in the \texttt{name} tags while the physical numbering of
                    554: the page images is specified in the \texttt{index} or \texttt{url}
                    555: tags.
1.1       casties   556: 
1.4       casties   557: \begin{description}
1.5       casties   558: \item[toc] container for document structure
                    559: 
1.4       casties   560:   \begin{description}
1.5       casties   561:   \item[page] describes a single logical page
                    562: 
                    563:     \begin{description}
                    564:     \item[name] the ``name'' of the logical page. This can be any string
                    565:       like a page number (arabic, roman, etc.) or a special designation
                    566:       like ``Table 5''.
                    567:       
                    568:     \item[index] the \texttt{digilib} index number\footnote{The index
                    569:         number for digilib is the index in the alphabetical order of the
                    570:         scan file names.} of the scan image of the page.
                    571:       
                    572:     \item[url] alternatively to the \texttt{digilib} index number the
                    573:       full URL of the scan image of the page can be used.
                    574:     \end{description}
1.4       casties   575:     
1.5       casties   576:   \item[chapter] describes a section or chapter of the text.
                    577:     \texttt{chapter} elements can be nested.
1.1       casties   578: 
1.4       casties   579:     \begin{description}
1.5       casties   580:     \item[name] the title of the chapter or section.
                    581:       
                    582:     \item[start] the beginning of a page range (usually the first page
                    583:       of the chapter). The \texttt{start} element has an optional
                    584:       \texttt{increment} attribute to indicate the number of logical
                    585:       pages on a scan image.\footnote{This information is only needed by
                    586:         additional tools that try to generate lists of all page and
                    587:         image numbers.}
                    588: 
                    589:       \begin{description}
                    590:       \item[name] the ``name'' of the first page (see \texttt{page}).
                    591:         
                    592:       \item[index] the index of the first page (see \texttt{page}).
                    593:         
                    594:       \item[url] the URL of the first page (see \texttt{page}).
                    595:       \end{description}
                    596:       
                    597:     \item[end] the end of a page range (usually the last page of the
                    598:       chapter).
                    599: 
                    600:       \begin{description}
                    601:       \item[name] the ``name'' of the last page (see \texttt{page}).
                    602:         
                    603:       \item[index] the index of the last page (see \texttt{page}).
                    604:         
                    605:       \item[url] the URL of the last page (see \texttt{page}).
                    606:       \end{description}
                    607:       
                    608:     \item[page] alternative (and additional) to
                    609:       \texttt{start}/\texttt{end} page ranges single \texttt{page}
                    610:       elements can be used inside \texttt{chapter}.
1.4       casties   611:     \end{description}
                    612:   \end{description}
                    613: \end{description}
                    614: 
                    615: %%\url{http://pythia.mpiwg-berlin.mpg.de/toolserver/TS_lise}
1.1       casties   616: 
                    617: 
1.10      casties   618: \subsection{Scanned images}
1.1       casties   619: \label{sec:inform-scann-imag}
                    620: 
                    621: Image files representing scanned images can have an \texttt{img}
                    622: container tag with information about the scan resolution and the size
                    623: of the original image. This information is used by the
                    624: \texttt{digilib} image viewing tool.
                    625: 
                    626: Required is one of three possible sets of tags:
                    627: 
                    628: \begin{description}
1.5       casties   629: \item[img] digital image information.
1.1       casties   630: 
1.5       casties   631:   \begin{description}
                    632:   \item[original-size-x] The width of the original image. The unit of
                    633:     measure can be contained as parameter \texttt{unit}, the default
                    634:     is meter ``m''. The width to be considered is the total width of
                    635:     the scanned area.
                    636:     
                    637:   \item[original-size-y] The height of the original image.
                    638:     
                    639:   \item[original-pixel-x] The width of the hi-res scan in pixels.
                    640:     
                    641:   \item[original-pixel-y] The height of the hi-res scan in pixels.
                    642:   \end{description}
1.1       casties   643: \end{description}
                    644: 
                    645: or
                    646: 
                    647: \begin{description}
1.5       casties   648: \item[img] digital image information.
                    649: 
                    650:   \begin{description}
                    651:   \item[original-dpi-x] The resolution of the hi-res scan in its width
                    652:     in pixels per inch.
1.1       casties   653: 
1.5       casties   654:   \item[original-dpi-y] The resolution of the hi-res scan in its height
                    655:     in pixels per inch.
                    656:   \end{description}
1.1       casties   657: \end{description}
                    658: 
                    659: or
                    660: 
                    661: \begin{description}
1.5       casties   662: \item[img] digital image information.
                    663: 
                    664:   \begin{description}
                    665:   \item[original-dpi] The resolution of the hi-res scan in pixels per
                    666:     inch if the resolutions in width and height are the same.
                    667:   \end{description}
1.1       casties   668: \end{description}
1.7       casties   669: 
                    670: 
1.10      casties   671: 
                    672: \subsection{Image acquisition}
                    673: \label{sec:inform-about-image}
                    674: 
                    675: A description of the technology used in the process of producing a
                    676: digital image.
                    677: 
                    678: \begin{description}
                    679: \item[image-acquisition] description of the image production process
                    680:   \begin{description}
                    681:   \item[device] acquisition device (e.g. ``flatbed scanner'')
                    682: 
                    683:   \item[image-type] type and color-depth of the image (e.g. ``RGB 24
                    684:     bit'')
                    685: 
                    686:   \item[postproduction] additional operations on the image
                    687:     (e.g. ``sharpening, color correction'')
                    688: 
                    689:   \item[production-comment] additional textual information about the
                    690:     production process
                    691:   \end{description}
                    692: \end{description}
                    693: 
                    694: 
1.7       casties   695: \subsection{Full text with images}
                    696: \label{sec:full-text-with}
                    697: 
1.8       casties   698: Full text in a XML format will be specified with a
                    699: \texttt{content-type} ``fulltext''.
                    700: 
                    701: The relation between the full text and optional images of
                    702: whole pages or parts of pages must be specified in a
                    703: \texttt{text-tool} container.
                    704: 
                    705: \begin{description}
                    706: \item[text-tool] representation of full text with images
                    707: 
                    708:   \begin{description}
                    709:   \item[text-file] the file name of the full text file (with path
                    710:     inside document directory)
                    711: 
                    712:   \item[page-images] the directory name of the directory containig the
                    713:     page image files (with path
                    714:     inside document directory)
                    715: 
                    716:   \item[xslt-file] the file name of an additional XSL transformation
                    717:     file
                    718: 
                    719:   \item[text-config] container for configuration options
1.10      casties   720:     \begin{description}
                    721:     \item[container-tag] the name of the text root element (default
                    722:       ``text'')
                    723:       
                    724:     \item[ref-element-tag] the name of the element that is used as
                    725:       unit of reference when results are presented
1.8       casties   726:     
1.10      casties   727:     \item[pagebreak-tag] the name of the element that indicates page
                    728:       breaks (default ``pb'')
                    729:     \end{description}
1.8       casties   730:   \end{description}
                    731: \end{description}
1.7       casties   732: 
1.1       casties   733: 
                    734: 
                    735: \subsection{Access restrictions}
                    736: \label{sec:access-restrictions}
                    737: 
                    738: If the access to a resource is restricted for technical or legal
                    739: reasons then the restrictions can be put in a
                    740: \texttt{access-restrictions} container. The format of the information
                    741: inside the container has to be further specified.
                    742: 
                    743: 
1.4       casties   744: \section{Sample metadata files for ECHO resources}
1.1       casties   745: 
1.5       casties   746: The following is a sample metadata index file for a directory containig a
                    747: scanned document.
                    748: 
                    749: \begin{small}
1.1       casties   750: \begin{verbatim}
1.11    ! casties   751: <resource type="ECHO" version="1.0">
1.5       casties   752:   <description>Fleck, 1980</description>
                    753:   <name>fleck.1980</name>
                    754:   <creator>University of Bern</creator>
                    755:   <archive-path>ubern/wiss-theorie</archive-path>
                    756:   <content-type>scanned images</content-type>
                    757:   <meta>
                    758:     <dri>echo23a45e2329x</dri>
                    759:     <lang>ger</lang>
                    760:     <bib type="book">
                    761:       <author>Fleck, Ludwik</author>
                    762:       <year>1980</year>
                    763:       <title>Entstehung und Entwicklung einer 
                    764:              wissenschaftlichen Tatsache</title>
                    765:       <series-editor></series-editor>
                    766:       <series-title></series-title>
                    767:       <series-volume></series-volume>
                    768:       <number-of-pages></number-of-pages>
                    769:       <city>Frankfurt am Main</city>
                    770:       <publisher>Suhrkamp</publisher>
                    771:       <edition></edition>
                    772:       <number-of-volumes></number-of-volumes>
                    773:       <translator></translator>
                    774:       <isbn-issn></isbn-issn>
                    775:       <keywords>Wissenschaftstheorie, Fleck, Tatsache</keywords>
                    776:       <abstract></abstract>
                    777:     </bib>
                    778:   </meta>
                    779:   <dir>
                    780:      <description>Scanned images (300dpi)</description>
                    781:      <name>img</name>
                    782:   </dir>
1.4       casties   783: </resource>
                    784: \end{verbatim}
1.5       casties   785: \end{small}
1.4       casties   786: 
1.5       casties   787: The following is a sample metadata file for a single image of an
                    788: architectural drawing.
1.4       casties   789: 
1.5       casties   790: \begin{small}
1.4       casties   791: \begin{verbatim}
1.11    ! casties   792: <resource type="ECHO" version="1.0">
1.5       casties   793:   <creator>Bibliotheca Hertziana</creator>
                    794:   <content-type>scanned images</content-type>
                    795:   <file>
                    796:     <name>00000271-asl-160-r-full.tif</name>
                    797:     <meta>
                    798:       <img>
                    799:         <original-dpi>315</original-dpi>
                    800:       </img>
                    801:       <dri>echo45a67bc4367d</dri>
                    802:       <lang>ita</lang>
                    803:       <doc type="Architectural Drawing">
                    804:         <person>Ciolli, Giacomo</person>
                    805:         <person>Urban VIII; Barberini, Maffeo</person>
                    806:         <location>Accademia di San Luca</location>
                    807:         <location>Roma</location>
                    808:         <date>1706</date>
                    809:         <object>Concorso Clementino</object>
                    810:         <object>Fontana Pubblica</object>
                    811:         <object>Brunnen</object>
                    812:         <object>ASL 160</object>
                    813:         <keywords></keywords>
                    814:       </doc>
                    815:       <context>
                    816:          <url>http://colosseum.biblhertz.it:8080/Lineamenta/
                    817:          1033478408.39/1035196181.35/1035196204.09/1035394121.83
                    818:          </url>
                    819:       </context>
                    820:     </meta>
                    821:   </file>
1.2       casties   822: </resource>
1.1       casties   823: \end{verbatim}
1.5       casties   824: \end{small}
1.1       casties   825: 
                    826: \end{document}
                    827: 
                    828: %%% Local Variables: 
                    829: %%% mode: latex
                    830: %%% TeX-master: t
                    831: %%% End: 

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>