Annotation of storage/meta/meta-format.tex, revision 1.1
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)
! 10: \usepackage[colorlinks=true,linkcolor=black]{hyperref}
! 11: % Format URLs nicely (without PDF)
! 12: %\usepackage{url}
! 13:
! 14:
! 15: \title{A simple metadata format for resource bundles}
! 16:
! 17: \author{Robert Casties, Dirk Wintergrün, Christoph Liess}
! 18:
! 19: \date{V0.2 of \today}
! 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:
! 38: \section{Resource format}
! 39: \label{sec:mpiwg-doc}
! 40:
! 41: In this description elements marked ``optional'' need not be supplied
! 42: by the provider of the resource and may be absent in all versions of
! 43: the metadata file. Elements marked ``required'' must be supplied by
! 44: the provider of the resource. Elements marked ``deduced'' can be
! 45: supplied by the provider of the resource but can also be provided by
! 46: automatic scripts later in the process, the elements must be present
! 47: in the final file.
! 48:
! 49: The outer container is named \texttt{resource}. Sub-types (``ECHO'',
! 50: ``MPIWG'') can be specified if necessary with a \texttt{type}
! 51: parameter. Its sub-elements are:
! 52:
! 53: \begin{description}
! 54: \item[description] An informal textual description of the
! 55: resource -- optional.
! 56:
! 57: \item[name] The filename of the resource (name of the directory this
! 58: file is contained in) -- required.
! 59:
! 60: \item[creator] The name of the project or person that created the
! 61: resource -- optional.
! 62:
! 63: \item[archive-creation-date] The time and date the archive was created
! 64: -- deduced.
! 65:
! 66: \item[archive-path] The full path to the resource directory inside the
! 67: whole archive collection -- deduced.
! 68:
! 69: \item[derived-from] Container for the description of the original
! 70: resource if this resource is a modified version of another resource
! 71: -- optional.
! 72:
! 73: \begin{description}
! 74: \item[archive-path] The full path to the original resource
! 75: --required.
! 76:
! 77: \item[description] An informal textual description of the relation
! 78: of this resource to the original resource -- optional.
! 79: \end{description}
! 80:
! 81: \item[linked-with] Container for the description of another
! 82: resource when this resource is a linked copy of another resource
! 83: -- optional.
! 84:
! 85: \begin{description}
! 86: \item[archive-path] The full path to the linked resource
! 87: --required.
! 88:
! 89: \item[description] An informal textual description of the relation
! 90: of this resource to the linked resource -- optional.
! 91: \end{description}
! 92:
! 93: \item[content-type] The content type of this resource -- required.\\
! 94: The content type enables the choice of tools to manipulate and
! 95: display the resource. There should be a common list of content
! 96: types. For digital documents (books, manuscripts) this would be
! 97: "scanned document", for other image data "scanned
! 98: images".\footnote{The criterion for documents is a ordered
! 99: succession of image files (pages) and equal image size and
! 100: resolution throughout the images of a resource.}
! 101:
! 102: \item[meta] Additional metadata information about the resource --
! 103: optional.\\ For a description of additional metadata see below.
! 104:
! 105: \item[dir] Container for the description of a subdirectory -- required
! 106: (when there are subdirectories).\\ \texttt{dir} tags should not be
! 107: nested. Directories at lower levels are identified by their
! 108: \texttt{path}.
! 109:
! 110: \begin{description}
! 111: \item[description] An informal textual description of the
! 112: subdirectory -- optional.
! 113:
! 114: \item[name] The name of the subdirectory -- required.
! 115:
! 116: \item[path] The directory path of this subdirectory relative to the
! 117: resource's root directory -- required (may be identical to
! 118: \texttt{name} or omitted if the directory is a direct child of the
! 119: resource's root directory).
! 120:
! 121: \item[meta] Additional metadata information about the directory --
! 122: optional.\\ For a description of additional metadata see below.
! 123: \end{description}
! 124:
! 125: \item[file] Container for the description of a file -- deduced.\\
! 126: \texttt{file} tags should not be nested in \texttt{dir} tags. Files
! 127: at lower directory levels are identified by their \texttt{path}.
! 128:
! 129: \begin{description}
! 130: \item[description] An informal textual description of the
! 131: file -- optional.
! 132:
! 133: \item[name] The name of the file -- required.
! 134:
! 135: \item[path] The directory path of this file relative to the
! 136: resource's root directory -- required (may be identical to
! 137: \texttt{name} or omitted if the file is in resource's root
! 138: directory).
! 139:
! 140: \item[modification-date] The file's modification date -- optional.
! 141:
! 142: \item[creation-date] The file's creation date -- optional.
! 143:
! 144: \item[date] The file's creation date if is has not been modified --
! 145: optional.
! 146:
! 147: \item[size] The file size -- deduced.
! 148:
! 149: \item[mime-type] The file's mime-type -- optional.
! 150:
! 151: \item[md5cs] MD5 checksum of the file content -- optional.
! 152:
! 153: \item[meta] Additional metadata information about the file --
! 154: optional. For a description of additional metadata see below.
! 155: \end{description}
! 156:
! 157: \end{description}
! 158:
! 159:
! 160:
! 161: \section{Additional metadata}
! 162: \label{sec:additional-metadata}
! 163:
! 164: All elements with \texttt{meta} tags can contain an arbitrary number
! 165: of additional metadata elements.
! 166:
! 167:
! 168: \subsection{DRI}
! 169: \label{sec:dri}
! 170:
! 171: The \emph{digital resource identifier} for the resource is specified
! 172: with a \texttt{dri} tag. Digital resource identifiers are documented
! 173: on the page
! 174:
! 175: \url{http://pythia.mpiwg-berlin.mpg.de/projects/standards/dri}.
! 176:
! 177:
! 178: \subsection{Bibliographic information}
! 179: \label{sec:bibliographic-data}
! 180:
! 181: Bibliographic information in the format of the ECHO scheme for
! 182: bibliographic data (cf. content workflow) or the MPIWG
! 183: ``Projektbibliografie'' is presented in a \texttt{bib} container with
! 184: a \texttt{type} parameter, giving the type of bibliographic resource.
! 185: The \texttt{type} field is repeated as a tag in the container. The
! 186: tags have the variable ``human-readable'' field names.
! 187:
! 188:
! 189: \subsection{Information on the document structure (table of contents)}
! 190: \label{sec:toc}
! 191:
! 192: Document structure information like a table of contents for a scanned
! 193: document is presented in a \texttt{toc} container. The format to be
! 194: used has to be further specified. The format could be based on the so
! 195: called ``LiSe-XML'' format. For a detailed description and an
! 196: exemplary set of TOC information see:
! 197:
! 198: \url{http://pythia.mpiwg-berlin.mpg.de/toolserver/TS_lise}
! 199:
! 200: \url{http://pythia.mpiwg-berlin.mpg.de/toolserver/TSlise/lise_downloads/deimel1929.xml}
! 201:
! 202:
! 203: \subsection{Information on scanned images}
! 204: \label{sec:inform-scann-imag}
! 205:
! 206: Image files representing scanned images can have an \texttt{img}
! 207: container tag with information about the scan resolution and the size
! 208: of the original image. This information is used by the
! 209: \texttt{digilib} image viewing tool.
! 210:
! 211: Required is one of three possible sets of tags:
! 212:
! 213: \begin{description}
! 214: \item[original-size-x] The width of the original image. The unit of
! 215: measure can be contained as parameter \texttt{unit}, the default is
! 216: meter ``m''. The width to be considered is the total width of the
! 217: scanned area.
! 218:
! 219: \item[original-size-y] The height of the original image.
! 220:
! 221: \item[original-pixel-x] The width of the hi-res scan in pixels.
! 222:
! 223: \item[original-pixel-y] The height of the hi-res scan in pixels.
! 224: \end{description}
! 225:
! 226: or
! 227:
! 228: \begin{description}
! 229: \item[original-dpi-x] The resolution of the hi-res scan in its width
! 230: in pixels per inch.
! 231:
! 232: \item[original-dpi-y] The resolution of the hi-res scan in its height
! 233: in pixels per inch.
! 234: \end{description}
! 235:
! 236: or
! 237:
! 238: \begin{description}
! 239: \item[original-dpi] The resolution of the hi-res scan in pixels per
! 240: inch if the resolutions in width and height are the same.
! 241: \end{description}
! 242:
! 243:
! 244: \subsection{Access restrictions}
! 245: \label{sec:access-restrictions}
! 246:
! 247: If the access to a resource is restricted for technical or legal
! 248: reasons then the restrictions can be put in a
! 249: \texttt{access-restrictions} container. The format of the information
! 250: inside the container has to be further specified.
! 251:
! 252:
! 253: \section{Sample metadata file for an ECHO resource}
! 254:
! 255: The following is the sample structure for a scanned document resource.
! 256:
! 257: \begin{verbatim}
! 258: <resource type="ECHO">
! 259: <description></description>
! 260: <name>fleck.1980</name>
! 261: <creator>University of Bern</creator>
! 262: <archive-creation-date></archive-creation-date>
! 263: <archive-path>ubern/wiss-theorie</archive-path>
! 264: <content-type>scanned images</content-type>
! 265: <meta>
! 266: <dri>echo23a45e2329x</dri>
! 267: <bib type="book">
! 268: <author>Fleck, Ludwik</author>
! 269: <year>1980</year>
! 270: <title>Entstehung und Entwicklung einer
! 271: wissenschaftlichen Tatsache</title>
! 272: <series_editor></series_editor>
! 273: <series_title></series_title>
! 274: <series_volume></series_volume>
! 275: <number_of_pages></number_of_pages>
! 276: <city>Frankfurt am Main</city>
! 277: <publisher>Suhrkamp</publisher>
! 278: <edition></edition>
! 279: <number_of_volumes></number_of_volumes>
! 280: <translator></translator>
! 281: <isbn></isbn>
! 282: <keywords>Wissenschaftstheorie, Fleck, Tatsache</keywords>
! 283: <abstract></abstract>
! 284: </bib>
! 285: </meta>
! 286: <dir>
! 287: <description>Scanned images (300dpi)</description>
! 288: <name>img</name>
! 289: <path></path>
! 290: <meta></meta>
! 291: </dir>
! 292: </echo-resource>
! 293: \end{verbatim}
! 294:
! 295: \end{document}
! 296:
! 297: %%% Local Variables:
! 298: %%% mode: latex
! 299: %%% TeX-master: t
! 300: %%% End:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>