\documentclass[11pt,twoside]{article}\makeatletter \IfFileExists{xcolor.sty}% {\RequirePackage{xcolor}}% {\RequirePackage{color}} \usepackage{colortbl} \usepackage{fontspec} \usepackage{xunicode} \catcode`⃥=\active \def⃥{\textbackslash} \catcode`❴=\active \def❴{\{} \catcode`❵=\active \def❵{\}} \def\textJapanese{\fontspec{Kochi Mincho}} \def\textChinese{\fontspec{HAN NOM A}\XeTeXlinebreaklocale "zh"\XeTeXlinebreakskip = 0pt plus 1pt } \def\textKorean{\fontspec{Baekmuk Gulim} } \setmonofont{DejaVu Sans Mono} \DeclareTextSymbol{\textpi}{OML}{25} \usepackage{relsize} \def\textsubscript#1{% \@textsubscript{\selectfont#1}} \def\@textsubscript#1{% {\m@th\ensuremath{_{\mbox{\fontsize\sf@size\z@#1}}}}} \def\textquoted#1{‘#1’} \def\textsmall#1{{\small #1}} \def\textlarge#1{{\large #1}} \def\textoverbar#1{\ensuremath{\overline{#1}}} \def\textgothic#1{{\fontspec{Lucida Blackletter}#1}} \def\textcal#1{{\fontspec{Lucida Calligraphy}#1}} \RequirePackage{array} \def\@testpach{\@chclass \ifnum \@lastchclass=6 \@ne \@chnum \@ne \else \ifnum \@lastchclass=7 5 \else \ifnum \@lastchclass=8 \tw@ \else \ifnum \@lastchclass=9 \thr@@ \else \z@ \ifnum \@lastchclass = 10 \else \edef\@nextchar{\expandafter\string\@nextchar}% \@chnum \if \@nextchar c\z@ \else \if \@nextchar l\@ne \else \if \@nextchar r\tw@ \else \z@ \@chclass \if\@nextchar |\@ne \else \if \@nextchar !6 \else \if \@nextchar @7 \else \if \@nextchar (8 \else \if \@nextchar )9 \else 10 \@chnum \if \@nextchar m\thr@@\else \if \@nextchar p4 \else \if \@nextchar b5 \else \z@ \@chclass \z@ \@preamerr \z@ \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi \fi} \gdef\arraybackslash{\let\\=\@arraycr} \def\textxi{\ensuremath{\xi}} \def\Panel#1#2#3#4{\multicolumn{#3}{){\columncolor{#2}}#4}{#1}} \newcolumntype{L}[1]{){\raggedright\arraybackslash}p{#1}} \newcolumntype{C}[1]{){\centering\arraybackslash}p{#1}} \newcolumntype{R}[1]{){\raggedleft\arraybackslash}p{#1}} \newcolumntype{P}[1]{){\arraybackslash}p{#1}} \newcolumntype{B}[1]{){\arraybackslash}b{#1}} \newcolumntype{M}[1]{){\arraybackslash}m{#1}} \definecolor{label}{gray}{0.75} \def\unusedattribute#1{\sout{\textcolor{label}{#1}}} \DeclareRobustCommand*{\xref}{\hyper@normalise\xref@} \def\xref@#1#2{\hyper@linkurl{#2}{#1}} \def\Div[#1]#2{\section*{#2}} \begingroup \catcode`\_=\active \gdef_#1{\ensuremath{\sb{\mathrm{#1}}}} \endgroup \mathcode`\_=\string"8000 \catcode`\_=12\relax \usepackage[a4paper,twoside,lmargin=1in,rmargin=1in,tmargin=1in,bmargin=1in]{geometry} \usepackage{framed} \definecolor{shadecolor}{gray}{0.95} \usepackage{longtable} \usepackage[normalem]{ulem} \usepackage{fancyvrb} \usepackage{fancyhdr} \usepackage{marginnote} \renewcommand*{\marginfont}{\itshape\footnotesize} \setlength\marginparwidth{.75in} \usepackage{graphicx} \def\Gin@extensions{.pdf,.png,.jpg,.mps,.tif} \pagestyle{fancy} \usepackage[pdftitle={TEI Lite: Encoding for Interchange: an introduction to the TEI — Final revised edition for TEI P5}, pdfauthor={Lou Burnard and C. M. Sperberg-McQueen}]{hyperref} \hyperbaseurl{} \paperwidth210mm \paperheight297mm \def\@pnumwidth{1.55em} \def\@tocrmarg {2.55em} \def\@dotsep{4.5} \setcounter{tocdepth}{3} \clubpenalty=8000 \emergencystretch 3em \hbadness=4000 \hyphenpenalty=400 \pretolerance=750 \tolerance=2000 \vbadness=4000 \widowpenalty=10000 \renewcommand\section{\@startsection {section}{1}{\z@}% {-1.75ex \@plus -0.5ex \@minus -.2ex}% {0.5ex \@plus .2ex}% {\reset@font\Large\bfseries\sffamily}} \renewcommand\subsection{\@startsection{subsection}{2}{\z@}% {-1.75ex\@plus -0.5ex \@minus- .2ex}% {0.5ex \@plus .2ex}% {\reset@font\Large\sffamily}} \renewcommand\subsubsection{\@startsection{subsubsection}{3}{\z@}% {-1.5ex\@plus -0.35ex \@minus -.2ex}% {0.5ex \@plus .2ex}% {\reset@font\large\sffamily}} \renewcommand\paragraph{\@startsection{paragraph}{4}{\z@}% {-1ex \@plus-0.35ex \@minus -0.2ex}% {0.5ex \@plus .2ex}% {\reset@font\normalsize\sffamily}} \renewcommand\subparagraph{\@startsection{subparagraph}{5}{\parindent}% {1.5ex \@plus1ex \@minus .2ex}% {-1em}% {\reset@font\normalsize\bfseries}} \def\l@section#1#2{\addpenalty{\@secpenalty} \addvspace{1.0em plus 1pt} \@tempdima 1.5em \begingroup \parindent \z@ \rightskip \@pnumwidth \parfillskip -\@pnumwidth \bfseries \leavevmode #1\hfil \hbox to\@pnumwidth{\hss #2}\par \endgroup} \def\l@subsection{\@dottedtocline{2}{1.5em}{2.3em}} \def\l@subsubsection{\@dottedtocline{3}{3.8em}{3.2em}} \def\l@paragraph{\@dottedtocline{4}{7.0em}{4.1em}} \def\l@subparagraph{\@dottedtocline{5}{10em}{5em}} \@ifundefined{c@section}{\newcounter{section}}{} \@ifundefined{c@chapter}{\newcounter{chapter}}{} \newif\if@mainmatter \@mainmattertrue \def\chaptername{Chapter} \def\frontmatter{% \pagenumbering{roman} \def\thechapter{\@roman\c@chapter} \def\theHchapter{\alph{chapter}} \def\@chapapp{}% } \def\mainmatter{% \cleardoublepage \def\thechapter{\@arabic\c@chapter} \setcounter{chapter}{0} \setcounter{section}{0} \pagenumbering{arabic} \setcounter{secnumdepth}{6} \def\@chapapp{\chaptername}% \def\theHchapter{\arabic{chapter}} } \def\backmatter{% \cleardoublepage \setcounter{chapter}{0} \setcounter{section}{0} \setcounter{secnumdepth}{0} \def\@chapapp{\appendixname}% \def\thechapter{\@Alph\c@chapter} \def\theHchapter{\Alph{chapter}} \appendix } \newenvironment{bibitemlist}[1]{% \list{\@biblabel{\@arabic\c@enumiv}}% {\settowidth\labelwidth{\@biblabel{#1}}% \leftmargin\labelwidth \advance\leftmargin\labelsep \@openbib@code \usecounter{enumiv}% \let\p@enumiv\@empty \renewcommand\theenumiv{\@arabic\c@enumiv}% }% \sloppy \clubpenalty4000 \@clubpenalty \clubpenalty \widowpenalty4000% \sfcode`\.\@m}% {\def\@noitemerr {\@latex@warning{Empty `bibitemlist' environment}}% \endlist} \def\tableofcontents{\section*{\contentsname}\@starttoc{toc}} \parskip0pt \parindent1em \def\Panel#1#2#3#4{\multicolumn{#3}{){\columncolor{#2}}#4}{#1}} \newenvironment{reflist}{% \begin{raggedright}\begin{list}{} {% \setlength{\topsep}{0pt}% \setlength{\rightmargin}{0.25in}% \setlength{\itemsep}{0pt}% \setlength{\itemindent}{0pt}% \setlength{\parskip}{0pt}% \setlength{\parsep}{2pt}% \def\makelabel##1{\itshape ##1}}% } {\end{list}\end{raggedright}} \newenvironment{sansreflist}{% \begin{raggedright}\begin{list}{} {% \setlength{\topsep}{0pt}% \setlength{\rightmargin}{0.25in}% \setlength{\itemindent}{0pt}% \setlength{\parskip}{0pt}% \setlength{\itemsep}{0pt}% \setlength{\parsep}{2pt}% \def\makelabel##1{\upshape\sffamily ##1}}% } {\end{list}\end{raggedright}} \newenvironment{specHead}[2]% {\vspace{20pt}\hrule\vspace{10pt}% \hypertarget{#1}{}% \markright{#2}% \pdfbookmark[2]{#2}{#1}% \hspace{-0.75in}{\bfseries\fontsize{16pt}{18pt}\selectfont#2}% }{} \@ifundefined{chapter}{% \def\DivI{\section} \def\DivII{\subsection} \def\DivIII{\subsubsection} \def\DivIV{\paragraph} \def\DivV{\subparagraph} \def\DivIStar[#1]#2{\section*{#2}} \def\DivIIStar[#1]#2{\subsection*{#2}} \def\DivIIIStar[#1]#2{\subsubsection*{#2}} \def\DivIVStar[#1]#2{\paragraph*{#2}} \def\DivVStar[#1]#2{\subparagraph*{#2}} }{% \def\DivI{\chapter} \def\DivII{\section} \def\DivIII{\subsection} \def\DivIV{\subsubsection} \def\DivV{\paragraph} \def\DivIStar[#1]#2{\chapter*{#2}} \def\DivIIStar[#1]#2{\section*{#2}} \def\DivIIIStar[#1]#2{\subsection*{#2}} \def\DivIVStar[#1]#2{\subsubsection*{#2}} \def\DivVStar[#1]#2{\paragraph*{#2}} } \def\TheFullDate{August 2012 (revised: 2013-01-17T20:36:37Z)} \def\TheID{\makeatother } \def\TheDate{August 2012} \title{TEI Lite: Encoding for Interchange: an introduction to the TEI — Final revised edition for TEI P5} \author{Lou Burnard and C. M. Sperberg-McQueen}\let\tabcellsep& \catcode`\&=12\relax \makeatletter \makeatletter \thispagestyle{empty} \markright{\@title}\markboth{\@title}{\@author} \renewcommand\small{\@setfontsize\small{9pt}{11pt}\abovedisplayskip 8.5\p@ plus3\p@ minus4\p@ \belowdisplayskip \abovedisplayskip \abovedisplayshortskip \z@ plus2\p@ \belowdisplayshortskip 4\p@ plus2\p@ minus2\p@ \def\@listi{\leftmargin\leftmargini \topsep 2\p@ plus1\p@ minus1\p@ \parsep 2\p@ plus\p@ minus\p@ \itemsep 1pt} } \makeatother \fvset{frame=single,numberblanklines=false,xleftmargin=5mm,xrightmargin=5mm} \fancyhf{} \setlength{\headheight}{14pt} \fancyhead[LE]{\bfseries\leftmark} \fancyhead[RO]{\bfseries\rightmark} \fancyfoot[RO]{} \fancyfoot[CO]{\thepage} \fancyfoot[LO]{\TheID} \fancyfoot[LE]{} \fancyfoot[CE]{\thepage} \fancyfoot[RE]{\TheID} \hypersetup{linkbordercolor=0.75 0.75 0.75,urlbordercolor=0.75 0.75 0.75,bookmarksnumbered=true} \fancypagestyle{plain}{\fancyhead{}\renewcommand{\headrulewidth}{0pt}}\makeatother \begin{document} \catcode`\$=12\relax \catcode`\^=12\relax \catcode`\#=12\relax \catcode`\%=12\relax \frontmatter \begin{titlepage} \title{TEI Lite: Encoding for Interchange: an introduction to the TEI — Final revised edition for TEI P5}\author{Lou Burnard and C. M. Sperberg-McQueen} \maketitle \date{August 2012} \end{titlepage} \cleardoublepage \DivIStar[Prefatory note]{Prefatory note}\label{U5-pref}\par TEI Lite was the name adopted for what the TEI editors originally conceived of as a simple demonstration of how the TEI (Text Encoding Initiative) encoding scheme might be adopted to meet 90% of the needs of 90% of the TEI user community. In retrospect, it was predictable that many people should imagine TEI Lite to be all there is to TEI, or find TEI Lite to be far too heavy for their needs.\par The original TEI Lite (1996) was based largely on observations of existing and previous practice in the encoding of texts, particularly as manifest in the collections of the \xref{http://ota.ahds.ac.uk}{Oxford Text Archive} and other collections of the period. It is therefore unsurprising that it seems to have become, if not a \textit{de facto} standard, at least a common point of departure for electronic text centres and encoding projects world wide. Maybe the fact that we actually produced this shortish, readable, manual for it also helped.\par Early adopters of TEI Lite included a number of Electronic Text Centers and digital library initiatives. It was also adopted as the basis for some early TEI-conformant authoring systems, and as the basis for introductory tutorials, many of them in languages other than English (see further the list of legacy versions at \url{http://www.tei-c.org/Lite/}).\par In 2002, following the publication of TEI P4 , the XML version of the TEI Guidelines, which uses the generation of TEI Lite as an example of the TEI modification mechanism, the opportunity was taken to produce a lightly revised XML-conformant version. In 2006, a more substantially revised version based on TEI P5 was produced; this reflected the many changes between TEI P4 and TEI P5, but was not otherwise significantly different. In 2012, the TEI Technical Council, decided that a final revision should be undertaken to ensure that the documentation remained consistent with the latest (2.1) release of TEI P5. This version uses a recently added mechanism in the TEI customization architecture, which permits a customization to define only the TEI elements to be included in a schema, rather than the elements to be excluded from it. As such it is probably more resilient to change than earlier versions. \begin{raggedleft}Lou Burnard, August 2012\end{raggedleft} \mainmatter \par This document provides an introduction to the recommendations of the Text Encoding Initiative (TEI), by describing a specific subset of the full TEI encoding scheme. The scheme documented here can be used to encode a wide variety of commonly encountered textual features, in such a way as to maximize the usability of electronic transcriptions and to facilitate their interchange among scholars using different computer systems. It is fully compatible with the full TEI scheme, as defined by TEI document P5, \textit{Guidelines for Electronic Text Encoding and Interchange}, as of February 2006, and available from the TEI Consortium website at \url{http://www.tei-c.org}. \DivI[Introduction]{Introduction}\label{U5-Intro}\par The Text Encoding Initiative (TEI) Guidelines are addressed to anyone who wants to interchange information stored in an electronic form. They emphasize the interchange of textual information, but other forms of information such as images and sound are also addressed. The Guidelines are equally applicable in the creation of new resources and in the interchange of existing ones.\par The Guidelines provide a means of making explicit certain features of a text in such a way as to aid the processing of that text by computer software running on different machines. This process of making explicit we call \emph{markup} or \emph{encoding}. Any textual representation on a computer uses some form of markup; the TEI came into being partly because of the enormous variety of mutually incomprehensible encoding schemes currently besetting scholarship, and partly because of the expanding range of scholarly uses now being identified for texts in electronic form.\par The TEI Guidelines describe an encoding scheme which can be expressed using a number of different formal languages. The first editions of the Guidelines used the \emph{Standard Generalized Markup Language} (SGML); since 2002, this has been replaced by the use of the Extensible Markup Language (XML). These markup languages have in common the definition of text in terms of \emph{elements} and \emph{attributes}, and rules governing their appearance within a text. The TEI's use of XML is ambitious in its complexity and generality, but it is fundamentally no different from that of any other XML markup scheme, and so any general-purpose XML-aware software is able to process TEI-conformant texts.\par Since 2001, the TEI has been a community initiative supported by an international membership consortium. It was originally an international research project sponsored by the Association for Computers and the Humanities, the Association for Computational Linguistics, and the Association for Literary and Linguistic Computing, with substantial funding over its first five years from the U.S. National Endowment for the Humanities, Directorate General XIII of the Commission of the European Communities, the Andrew W. Mellon Foundation, the Social Science and Humanities Research Council of Canada and others. The Guidelines were first published in May 1994, after six years of development involving many hundreds of scholars from different academic disciplines worldwide. During the years that followed, the Guidelines became increasingly influential in the development of the digital library, in the language industries, and even in the development of the World Wide Web itself. The TEI Consortium was set up in January 2001, and a year later produced an edition of the Guidelines entirely revised for XML compatibility. In 2004, it set about a major revision of the Guidelines to take full advantage of new schema languages, the first release of which appeared in 2005. This revision of the TEI Lite document conforms to version 2.1 of this most recent edition of the Guidelines, TEI P5, released in June 2012.\par At the outset of its work, the overall goals of the TEI were defined by the closing statement of a planning conference held at Vassar College, N.Y., in November, 1987; these Poughkeepsie Principles were further elaborated in a series of design documents. The Guidelines, say these design documents, should: \begin{itemize} \item suffice to represent the textual features needed for research; \item be simple, clear, and concrete; \item be easy for researchers to use without special-purpose software; \item allow the rigorous definition and efficient processing of texts; \item provide for user-defined extensions; \item conform to existing and emergent standards. \end{itemize} \par The world of scholarship is large and diverse. For the Guidelines to have wide acceptability, it was important to ensure that: \begin{enumerate} \item the common core of textual features be easily shared; \item additional specialist features be easy to add to (or remove from) a text; \item multiple parallel encodings of the same feature should be possible; \item the richness of markup should be user-defined, with a very small minimal requirement; \item adequate documentation of the text and its encoding should be provided. \end{enumerate}\par The present document describes a manageable selection from the extensive set of elements and recommendations resulting from those design goals, which is called \textit{TEI Lite}.\par In selecting from the several hundred elements defined by the full TEI scheme, we have tried to identify a useful starter set, comprising the elements which almost every user should know about. Experience working with TEI Lite will be invaluable in understanding the full TEI scheme and in knowing how to integrate specialized parts of it into the general TEI framework.\par Our goals in defining this subset may be summarized as follows: \begin{itemize} \item it should be able to handle adequately a reasonably wide variety of texts, at the level of detail found in existing practice (as demonstrated in, for example, the holdings of the Oxford Text Archive); \item it should be useful for the production of new documents (such as this one) as well as the encoding of existing texts; \item it should be usable with a wide range of existing XML software; \item it should be a pure subset of the full TEI scheme and defined using the customizaticon methods described in the TEI Guidelines; \item it should be as small and simple as is consistent with the other goals. \end{itemize} The reader may judge our success in meeting these goals for him or herself.\par Although we have tried to make this document self-contained, as suits a tutorial text, the reader should be aware that it does not cover every detail of the TEI encoding scheme. All of the elements described here are fully documented in the TEI Guidelines themselves, which should be consulted for authoritative reference information on these, and on the many others which are not described here. Some basic knowledge of XML is assumed. \DivI[A Short Example]{A Short Example}\label{U5-eg}\par We begin with a short example, intended to show what happens when a passage of prose is typed into a computer by someone with little sense of the purpose of mark-up, or the potential of electronic texts. In an ideal world, such output might be generated by a very accurate optical scanner. It attempts to be faithful to the appearance of the printed text, by retaining the original line breaks, by introducing blanks to represent the layout of the original headings and page breaks, and so forth. Where characters not available on the keyboard are needed (such as the accented letter \emph{a} in \emph{faàl} or the long dash), it attempts to mimic their appearance.\par \par\bgroup\ttfamily\small\selectfont \vskip 10pt\begin{shaded} \obeylines\obeyspaces CHAPTER 38 READER, I married him. A quiet wedding we had: he and I, the par- son and clerk, were alone present. When we got back from church, I went into the kitchen of the manor-house, where Mary was cooking the dinner, and John cleaning the knives, and I said -- 'Mary, I have been married to Mr Rochester this morning.' The housekeeper and her husband were of that decent, phlegmatic order of people, to whom one may at any time safely communicate a remarkable piece of news without incurring the danger of having one's ears pierced by some shrill ejaculation and subsequently stunned by a torrent of wordy wonderment. Mary did look up, and she did stare at me; the ladle with which she was basting a pair of chickens roasting at the fire, did for some three minutes hang suspended in air, and for the same space of time John's knives also had rest from the polishing process; but Mary, bending again over the roast, said only -- 'Have you, miss? Well, for sure!' A short time after she pursued, 'I seed you go out with the master, but I didn't know you were gone to church to be wed'; and she basted away. John, when I turned to him, was grinning from ear to ear. 'I telled Mary how it would be,' he said: 'I knew what Mr Ed- ward' (John was an old servant, and had known his master when he was the cadet of the house, therefore he often gave him his Christian name) -- 'I knew what Mr Edward would do; and I was certain he would not wait long either: and he's done right, for aught I know. I wish you joy, miss!' and he politely pulled his forelock. 'Thank you, John. Mr Rochester told me to give you and Mary this.' I put into his hand a five-pound note. Without waiting to hear more, I left the kitchen. In passing the door of that sanctum some time after, I caught the words -- 'She'll happen do better for him nor ony o' t' grand ladies.' And again, 'If she ben't one o' th' handsomest, she's noan faa⃥l, and varry good-natured; and i' his een she's fair beautiful, onybody may see that.' I wrote to Moor House and to Cambridge immediately, to say what I had done: fully explaining also why I had thus acted. Diana and 474 JANE EYRE 475 Mary approved the step unreservedly. Diana announced that she would just give me time to get over the honeymoon, and then she would come and see me. 'She had better not wait till then, Jane,' said Mr Rochester, when I read her letter to him; 'if she does, she will be too late, for our honey- moon will shine our life long: its beams will only fade over your grave or mine.' How St John received the news I don't know: he never answered the letter in which I communicated it: yet six months after he wrote to me, without, however, mentioning Mr Rochester's name or allud- ing to my marriage. His letter was then calm, and though very serious, kind. He has maintained a regular, though not very frequent correspond- ence ever since: he hopes I am happy, and trusts I am not of those who live without God in the world, and only mind earthly things. \end{shaded} \par\egroup \par This transcription suffers from a number of shortcomings: \begin{itemize} \item the page numbers and running titles are intermingled with the text in a way which makes it difficult for software to disentangle them; \item no distinction is made between single quotation marks and apostrophe, so it is difficult to know exactly which passages are in direct speech; \item the preservation of the copy text's hyphenation means that simple-minded search programs will not find the broken words; \item the accented letter in \emph{faàl} and the long dash have been rendered by ad hoc keying conventions which follow no standard pattern and will be processed correctly only if the transcriber remembers to mention them in the documentation; \item paragraph divisions are marked only by the use of white space, and hard carriage returns have been introduced at the end of each line. Consequently, if the size of type used to print the text changes, reformatting will be problematic. \end{itemize} \par We now present the same passage, as it might be encoded using the TEI Guidelines. As we shall see, there are many ways in which this encoding could be extended, but as a minimum, the TEI approach allows us to represent the following distinctions: \begin{itemize} \item Paragraph and chapter divisions are now marked explicitly. \item Apostrophes are distinguished from quotation marks; direct speech is explicitly marked. \item The accented letter and the long dash are correctly represented. \item Page divisions have been marked with an empty element alone. \item The lineation of the original has not been retained and words broken by typographic accident at the end of a line have been re-assembled without comment. \item For convenience of proof reading, a new line has been introduced at the start of each paragraph, but the indentation is removed. \end{itemize} \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{pb}\hspace*{6pt}n="{474}"/>}\mbox{}\newline {<\textbf{div}\hspace*{6pt}type="{chapter}"\hspace*{6pt}n="{38}">}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}Reader, I married him. A quiet wedding we had: he and I, the parson and clerk, were alone\mbox{}\newline \hspace*{6pt}\hspace*{6pt} present. When we got back from church, I went into the kitchen of the manor-house, where\mbox{}\newline \hspace*{6pt}\hspace*{6pt} Mary was cooking the dinner, and John cleaning the knives, and I said —{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{q}>}Mary, I have been married to Mr Rochester this morning.{} The housekeeper and her\mbox{}\newline \hspace*{6pt}\hspace*{6pt} husband were of that decent, phlegmatic order of people, to whom one may at any time safely\mbox{}\newline \hspace*{6pt}\hspace*{6pt} communicate a remarkable piece of news without incurring the danger of having one's ears\mbox{}\newline \hspace*{6pt}\hspace*{6pt} pierced by some shrill ejaculation and subsequently stunned by a torrent of wordy\mbox{}\newline \hspace*{6pt}\hspace*{6pt} wonderment. Mary did look up, and she did stare at me; the ladle with which she was basting\mbox{}\newline \hspace*{6pt}\hspace*{6pt} a pair of chickens roasting at the fire, did for some three minutes hang suspended in air,\mbox{}\newline \hspace*{6pt}\hspace*{6pt} and for the same space of time John's knives also had rest from the polishing process; but\mbox{}\newline \hspace*{6pt}\hspace*{6pt} Mary, bending again over the roast, said only —{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{q}>}Have you, miss? Well, for sure!{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}A short time after she pursued, {<\textbf{q}>}I seed you go out with the master, but I didn't know\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} you were gone to church to be wed{}; and she basted away. John, when I turned to him, was\mbox{}\newline \hspace*{6pt}\hspace*{6pt} grinning from ear to ear. {<\textbf{q}>}I telled Mary how it would be,{} he said: {<\textbf{q}>}I knew what Mr\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} Edward{} (John was an old servant, and had known his master when he was the cadet of the\mbox{}\newline \hspace*{6pt}\hspace*{6pt} house, therefore he often gave him his Christian name) — {<\textbf{q}>}I knew what Mr Edward would do;\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} and I was certain he would not wait long either: and he's done right, for aught I know. I\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} wish you joy, miss!{} and he politely pulled his forelock.{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{q}>}Thank you, John. Mr Rochester told me to give you and Mary this.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}I put into his hand a five-pound note. Without waiting to hear more, I left the kitchen.\mbox{}\newline \hspace*{6pt}\hspace*{6pt} In passing the door of that sanctum some time after, I caught the words —{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{q}>}She'll happen do better for him nor ony o' t' grand ladies.{} And again, {<\textbf{q}>}If she\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} ben't one o' th' handsomest, she's noan faàl, and varry good-natured; and i' his een she's\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} fair beautiful, onybody may see that.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}I wrote to Moor House and to Cambridge immediately, to say what I had done: fully\mbox{}\newline \hspace*{6pt}\hspace*{6pt} explaining also why I had thus acted. Diana and {<\textbf{pb}\hspace*{6pt}n="{475}"/>} Mary approved the step\mbox{}\newline \hspace*{6pt}\hspace*{6pt} unreservedly. Diana announced that she would just give me time to get over the honeymoon,\mbox{}\newline \hspace*{6pt}\hspace*{6pt} and then she would come and see me.{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{q}>}She had better not wait till then, Jane,{} said Mr Rochester, when I read her letter\mbox{}\newline \hspace*{6pt}\hspace*{6pt} to him; {<\textbf{q}>}if she does, she will be too late, for our honeymoon will shine our life long:\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} its beams will only fade over your grave or mine.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}How St John received the news I don't know: he never answered the letter in which I\mbox{}\newline \hspace*{6pt}\hspace*{6pt} communicated it: yet six months after he wrote to me, without, however, mentioning Mr\mbox{}\newline \hspace*{6pt}\hspace*{6pt} Rochester's name or alluding to my marriage. His letter was then calm, and though very\mbox{}\newline \hspace*{6pt}\hspace*{6pt} serious, kind. He has maintained a regular, though not very frequent correspondence ever\mbox{}\newline \hspace*{6pt}\hspace*{6pt} since: he hopes I am happy, and trusts I am not of those who live without God in the world,\mbox{}\newline \hspace*{6pt}\hspace*{6pt} and only mind earthly things.{}\mbox{}\newline {}\end{shaded}\egroup\par \par This particular encoding represents a set of choices or priorities. As a trivial example, note that in the second example, end-of-line hyphenation has been silently removed. Conceivably Brontë (or her printer) intended the word honeymoon to appear as honey-moon on its second appearance, though this seems unlikely: our decision to focus on Brontë's text, rather than on the printing of it in this particular edition, makes it impossible to be certain. This is an instance of the fundamental \textit{selectivity} of any encoding. An encoding makes explicit only those textual features of importance to the encoder. It is not difficult to think of ways in which the encoding of even this short passage might readily be extended. For example: \begin{itemize} \item a regularized form of the passages in dialect could be provided; \item footnotes glossing or commenting on any passage could be added; \item pointers linking parts of this text to others could be added; \item proper names of various kinds could be distinguished from the surrounding text; \item detailed bibliographic information about the text's provenance and context could be prefixed to it; \item a linguistic analysis of the passage into sentences, clauses, words, etc., could be provided, each unit being associated with appropriate category codes; \item the text could be segmented into narrative or discourse units; \item systematic analysis or interpretation of the text could be included in the encoding, with potentially complex alignment or linkage between the text and the analysis, or between the text and one or more translations of it; \item passages in the text could be linked to images or sound held on other media. \end{itemize} \par TEI-recommended ways of carrying out most of these are described in the remainder of this document. The TEI scheme as a whole also provides for an enormous range of other possibilities, of which we cite only a few: \begin{itemize} \item detailed analysis of the components of names; \item detailed meta-information providing thesaurus-style information about the text's origins or topics; \item information about the printing history or manuscript variations exhibited by a particular series of versions of the text. \end{itemize} For recommendations on these and many other possibilities, the full Guidelines should be consulted. \DivI[The Structure of a TEI Text]{The Structure of a TEI Text}\label{U5-struc}\par All TEI-conformant texts contain (a) a \emph{TEI header} (marked up as a element) and (b) the transcription of the text proper (marked up as a element). These two elements are combined together to form a single element, which must be declared within the TEI namespace\footnote{A \emph{namespace} is an XML concept. Its function is to identify the vocabulary from which a group of element names are drawn, using a standard identifier resembling a web address. The namespace for all TEI elements is \texttt{http://www.tei-c.org/ns/1.0}}. \par The TEI header provides information analogous to that provided by the title page of a printed text. It has up to four parts: a bibliographic description of the machine-readable text, a description of the way it has been encoded, a non-bibliographic description of the text (a \emph{text profile}), and a revision history. The header is described in more detail in section \textit{\hyperref[U5-header]{19. The Electronic Title Page}}.\par A TEI text may be \emph{unitary} (a single work) or \emph{composite} (a collection of single works, such as an anthology). In either case, the text may have an optional \emph{front} or \emph{back}. In between is the \emph{body} of the text, which, in the case of a composite text, may consist of \emph{group}s, each containing more groups or texts.\par A unitary text will be encoded using an overall structure like this: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{TEI} xmlns="http://www.tei-c.org/ns/1.0">}\mbox{}\newline \hspace*{6pt}{<\textbf{teiHeader}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{front}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{body}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{back}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \par A composite text also has an optional front and back. In between occur one or more groups of texts, each with its own optional front and back matter. A composite text will thus be encoded using an overall structure like this: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{TEI} xmlns="http://www.tei-c.org/ns/1.0">}\mbox{}\newline \hspace*{6pt}{<\textbf{teiHeader}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{front}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{group}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{front}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{body}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{back}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{front}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{body}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{back}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{back}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \par It is also possible to define a composite of complete TEI texts, each with its own header. Such a collection is known as a \emph{TEI corpus}, and may itself have a header: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{teiCorpus} xmlns="http://www.tei-c.org/ns/1.0">}\mbox{}\newline \hspace*{6pt}{<\textbf{teiHeader}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{TEI} xmlns="http://www.tei-c.org/ns/1.0">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{teiHeader}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{TEI} xmlns="http://www.tei-c.org/ns/1.0">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{teiHeader}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{text}>}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \noindent It is also possible to create a composite of corpora -- that is, one element may contain many nested elements rather than many nested elements, to any depth considered necessary.\par In the remainder of this document, we discuss chiefly simple text structures. The discussion in each case consists of a short list of relevant TEI \emph{elements} with a brief definition of each, followed by definitions for any \emph{attributes} specific to that element, and a reference to any \emph{classes} of which the element is a member. These references are linked to full specifications for each object, as given in the TEI \textit{Guidelines}. In most cases, short examples are also given.\par For example, here are the elements discussed so far: \begin{sansreflist} \item [\textbf{}] (TEI document) contains a single TEI-conformant document, comprising a TEI header and a text, either in isolation or as part of a element. \item [\textbf{}] (TEI Header) supplies the descriptive and declarative information making up an electronic title page prefixed to every TEI-conformant text. \item [\textbf{}] contains a single text of any kind, whether unitary or composite, for example a poem or drama, a collection of essays, a novel, a dictionary, or a corpus sample. \item [\textbf{}] contains the whole of a TEI encoded corpus, comprising a single corpus header and one or more TEI elements, each containing a single text header and a text. \end{sansreflist} \DivI[Encoding the Body]{Encoding the Body}\label{U5-body}\par As indicated above, a simple TEI document at the textual level consists of the following elements: \begin{sansreflist} \item [\textbf{}] (front matter) contains any prefatory matter (headers, title page, prefaces, dedications, etc.) found at the start of a document, before the main body. \item [\textbf{}] contains the body of a composite text, grouping together a sequence of distinct texts (or groups of such texts) which are regarded as a unit for some purpose, for example the collected works of an author, a sequence of prose essays, etc. \item [\textbf{}] (text body) contains the whole body of a single unitary text, excluding any front or back matter. \item [\textbf{}] (back matter) contains any appendixes, etc. following the main part of a text. \end{sansreflist} Elements specific to front and back matter are described below in section \textit{\hyperref[U5-fronbac]{18. Front and Back Matter}}. In this section we discuss the elements making up the body of a text. \DivII[Text Division Elements]{Text Division Elements}\label{divs}\par The body of a prose text may be just a series of paragraphs, or these paragraphs may be grouped together into chapters, sections, subsections, etc. Each paragraph is tagged using the

tag. The

element is used to represent any such grouping of paragraphs. \begin{sansreflist} \item [\textbf{

}] (paragraph) marks paragraphs in prose. \item [\textbf{

}] (text division) contains a subdivision of the front, body, or back of a text. \end{sansreflist} \par The {type} attribute on the
element may be used to supply a conventional name for this category of text division, or otherwise distinguish them. Typical values might be book, chapter, section, part, poem, song, etc. For a given project, it will usually be advisable to define and adhere to a specific list of such values. \par A
element may itself contain further, nested,
s, thus mimicking the traditional structure of a book, which can be decomposed hierarchically into units such as parts, containing chapters, containing sections, and so on. TEI texts in general conform to this simple hierarchic model.\par The {xml:id} attribute may be used to supply a unique identifier for the division, which may be used for cross references or other links to it, such as a commentary, as further discussed in section \textit{\hyperref[U5-ptrs]{8. Cross References and Links}}. It is often useful to provide an {xml:id} attribute for every major structural unit in a text, and to derive its values in some systematic way, for example by appending a section number to a short code for the title of the work in question, as in the examples below. It is particularly useful to supply such identifiers if the resource concerned is to be made available over the web, since they make it much easier for other web-based applications to link directly to the corresponding parts of your text. \par The {n} attribute may be used to supply (additionally or alternatively) a short mnemonic name or number for a division, or any other element. If a conventional form of reference or abbreviation for the parts of a work already exists (such as the book/chapter/verse pattern of Biblical citations), the {n} attribute is the place to record it; unlike the identifier supplied by {xml:id}, it does not need to be unique.\par The {xml:lang} attribute may be used to specify the language of the division. Languages are identified by an internationally defined code, as further discussed in section \textit{\hyperref[z636]{6.3. Foreign Words or Expressions}} below.\par The {rend} attribute may be used to supply information about the rendition (appearance) of a division, or any other element, as further discussed in section \textit{\hyperref[U5-hilites]{6. Marking Highlighted Phrases}} below. As with the {type} attribute, a project will often find it useful to predefine the possible values for this attribute, but TEI Lite does not constrain it in anyway. \par These four attributes, {xml:id}, {n}, {xml:lang}, and {rend} are so widely useful that they are allowed on any element in any TEI schema: they are \emph{global attributes}. Other global attributes defined in the TEI Lite scheme are discussed in section \textit{\hyperref[xatts]{8.3. Special kinds of Linking}}.\par The value of every {xml:id} attribute should be unique within a document. One simple way of ensuring that this is so is to make it reflect the hierarchic structure of the document. For example, Smith's \textit{Wealth of Nations} as first published consists of five books, each of which is divided into chapters, while some chapters are further subdivided into parts. We might define {xml:id} values for this structure as follows: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{body}>}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN1}"\hspace*{6pt}n="{I}"\hspace*{6pt}type="{book}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN101}"\hspace*{6pt}n="{I.1}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN102}"\hspace*{6pt}n="{I.2}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN110}"\hspace*{6pt}n="{I.10}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN1101}"\hspace*{6pt}n="{I.10.1}"\hspace*{6pt}type="{part}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN1102}"\hspace*{6pt}n="{I.10.2}"\hspace*{6pt}type="{part}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{WN2}"\hspace*{6pt}n="{II}"\hspace*{6pt}type="{book}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \par A different numbering scheme may be used for {xml:id} and {n} attributes: this is often useful where a canonical reference scheme is used which does not tally with the structure of the work. For example, in a novel divided into books each containing chapters, where the chapters are numbered sequentially through the whole work, rather than within each book, one might use a scheme such as the following: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{body}>}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS01}"\hspace*{6pt}n="{1}"\hspace*{6pt}type="{volume}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS011}"\hspace*{6pt}n="{1}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS012}"\hspace*{6pt}n="{2}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS02}"\hspace*{6pt}n="{2}"\hspace*{6pt}type="{volume}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS021}"\hspace*{6pt}n="{3}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{TS022}"\hspace*{6pt}n="{4}"\hspace*{6pt}type="{chapter}">}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \noindent Here the work has two volumes, each containing two chapters. The chapters are numbered conventionally 1 to 4, but the {xml:id} values specified allow them to be regarded additionally as if they were numbered 1.1, 1.2, 2.1, 2.2. \DivII[Headings and Closings]{Headings and Closings}\label{h25}\par Every
may have a title or heading at its start, and (less commonly) a trailer such as End of Chapter 1 at its end. The following elements may be used to transcribe them: \begin{sansreflist} \item [\textbf{}] (heading) contains any type of heading, for example the title of a section, or the heading of a list, glossary, manuscript description, etc. \item [\textbf{}] contains a closing title or footer appearing at the end of a division of a text. \end{sansreflist} Some other elements which may be necessary at the beginning or ending of text divisions are discussed below in section \textit{\hyperref[h52]{18.1.2. Prefatory Matter}}.\par Whether or not headings and trailers are included in a transcription is a matter for the individual transcriber to decide. Where a heading is completely regular (for example Chapter 1) or may be automatically constructed from attribute values (e.g. \texttt{
}), it may be omitted; where it contains otherwise unrecoverable text it should always be included. For example, the start of Hardy's \textit{Under the Greenwood Tree} might be encoded as follows: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{div}\hspace*{6pt}xml:id="{UGT1}"\hspace*{6pt}n="{Winter}"\hspace*{6pt}type="{Part}">}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}xml:id="{UGT11}"\hspace*{6pt}n="{1}"\hspace*{6pt}type="{Chapter}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{head}>}Mellstock-Lane{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{p}>}To dwellers in a wood almost every species of tree ... {}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \DivII[Prose, Verse and Drama]{Prose, Verse and Drama}\label{vedr}\par As in the Bronte example above, the paragraphs making up a textual division are tagged with the

tag. In poetic or dramatic texts different tags are needed, to represent verse lines and stanzas in the first case, or individual speeches and stage directions in the second. : \begin{sansreflist} \item [\textbf{}] (verse line) contains a single, possibly incomplete, line of verse. \item [\textbf{}] (line group) contains one or more verse lines functioning as a formal unit, e.g. a stanza, refrain, verse paragraph, etc. \item [\textbf{}] (speech) contains an individual speech in a performance text, or a passage presented as such in a prose or verse text. \item [\textbf{}] contains a specialized form of heading or label, giving the name of one or more speakers in a dramatic text or fragment. \item [\textbf{}] (stage direction) contains any kind of stage direction within a dramatic text or fragment. \end{sansreflist} \par Here, for example, is the start of a poetic text in which verse lines and stanzas are tagged: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{lg}\hspace*{6pt}n="{I}">}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}I Sing the progresse of a\mbox{}\newline \hspace*{6pt}\hspace*{6pt} deathlesse soule,{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}Whom Fate, with God made, but doth not controule,{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}Plac'd in\mbox{}\newline \hspace*{6pt}\hspace*{6pt} most shapes; all times before the law{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}Yoak'd us, and when, and since, in this I\mbox{}\newline \hspace*{6pt}\hspace*{6pt} sing.{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}And the great world to his aged evening;{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}From infant morne, through manly\mbox{}\newline \hspace*{6pt}\hspace*{6pt} noone I draw.{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}What the gold Chaldee, of silver Persian saw,{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}Greeke brass, or\mbox{}\newline \hspace*{6pt}\hspace*{6pt} Roman iron, is in this one;{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}A worke t'out weare Seths pillars, bricke and\mbox{}\newline \hspace*{6pt}\hspace*{6pt} stone,{}\mbox{}\newline \hspace*{6pt}{<\textbf{l}>}And (holy writs excepted) made to yeeld to none,{}\mbox{}\newline {}\end{shaded}\egroup\par \par Note that the element marks verse lines, not typographic lines: the original lineation of the first few lines above has not therefore been made explicit by this encoding, and may be lost. The element described in section \textit{\hyperref[U5-pln]{5. Page and Line Numbers}} might additionally be used to mark typographic lines if so desired. \par Here is the end of a famous dramatic text, in which speeches and stage directions are marked: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Vladimir{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}Pull on your trousers.{}\mbox{}\newline {}\mbox{}\newline {<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Estragon{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}You want me to pull off my trousers?{}\mbox{}\newline {}\mbox{}\newline {<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Vladimir{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}Pull {<\textbf{emph}>}on{} your trousers.{}\mbox{}\newline {}\mbox{}\newline {<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Vladimir{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{stage}>}(realizing his trousers are down){}.\mbox{}\newline \hspace*{6pt}\hspace*{6pt} True{}\mbox{}\newline {}\mbox{}\newline {<\textbf{stage}>}He pulls up his trousers{}\mbox{}\newline {<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Vladimir{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}Well? Shall we go?{}\mbox{}\newline {}\mbox{}\newline {<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}{<\textbf{speaker}>}Estragon{}\mbox{}\newline \hspace*{6pt}{<\textbf{p}>}Yes, let's go.{}\mbox{}\newline {}\mbox{}\newline {<\textbf{stage}>}They do not move.{}\end{shaded}\egroup\par \noindent \par Note that the (stage direction) element can appear either within a speech or between speeches. The ("speech") element contains, following an optional element indicating who is speaking, either paragraphs (if the speech is in prose) or verse lines or stanzas as in the next example. In this case, it is quite common to find that verse lines are split between speakers. The easiest way of encoding this is to use the {part} attribute to indicate that the lines so fragmented are incomplete : \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{div}\hspace*{6pt}type="{Act}"\hspace*{6pt}n="{I}">}\mbox{}\newline \hspace*{6pt}{<\textbf{head}>}ACT I{}\mbox{}\newline \hspace*{6pt}{<\textbf{div}\hspace*{6pt}type="{Scene}"\hspace*{6pt}n="{1}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{head}>}SCENE I{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{stage}\hspace*{6pt}rend="{italic}">} Enter Barnardo and Francisco, two Sentinels, at several doors{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Barn{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}\hspace*{6pt}part="{Y}">}Who's there?{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Fran{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}Nay, answer me. Stand and unfold yourself.{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Barn{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}\hspace*{6pt}part="{I}">}Long live the King!{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Fran{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}\hspace*{6pt}part="{M}">}Barnardo?{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Barn{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}\hspace*{6pt}part="{F}">}He.{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Fran{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}You come most carefully upon your hour.{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \par The same mechanism may be applied to stanzas which are divided between two speakers: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{div}>}\mbox{}\newline \hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}First voice{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{lg}\hspace*{6pt}type="{stanza}"\hspace*{6pt}part="{I}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}But why drives on that ship so fast{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}Withouten wave or wind?{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{sp}>}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Second Voice{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{lg}\hspace*{6pt}part="{F}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}The air is cut away before.{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}{<\textbf{l}>}And closes from behind.{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \begin{it}\end{it}\mbox{}\newline {}\end{shaded}\egroup\par \noindent \par The element can also be used for dialogue presented in a prose work as if it were drama, as in the next example, which also demonstrates the use of the {who} attribute to bear a code identifying the speaker of the piece of dialogue concerned: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{div}>}\mbox{}\newline \hspace*{6pt}{<\textbf{sp}\hspace*{6pt}who="{#OPI}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}The reverend Doctor Opimian{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{p}>}I do not think I have named a single unpresentable fish.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{sp}\hspace*{6pt}who="{#GRM}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}Mr Gryll{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{p}>}Bream, Doctor: there is not much to be said for bream.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline \hspace*{6pt}{<\textbf{sp}\hspace*{6pt}who="{#OPI}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{speaker}>}The Reverend Doctor Opimian{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{p}>}On the contrary, sir, I think there is much to be said for him. In the first\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} place....{}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{p}>}Fish, Miss Gryll -- I could discourse to you on fish by the hour: but for the present I\mbox{}\newline \hspace*{6pt}\hspace*{6pt}\hspace*{6pt}\hspace*{6pt} will forbear.{}\mbox{}\newline \hspace*{6pt}{}\mbox{}\newline {}\end{shaded}\egroup\par \noindent Here the {who} attribute values (\texttt{#OPI} etc.) are links, pointing to a list of the characters in the novel, each of which has an identifier: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{list}>}\mbox{}\newline \hspace*{6pt}{<\textbf{head}>}Characters in the novel{}\mbox{}\newline \hspace*{6pt}{<\textbf{item}\hspace*{6pt}xml:id="{OPI}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{name}>}Dr Opimian{} : named for the famous Roman fine wine{}\mbox{}\newline \hspace*{6pt}{<\textbf{item}\hspace*{6pt}xml:id="{GRM}">}\mbox{}\newline \hspace*{6pt}\hspace*{6pt}{<\textbf{name}>}Mr Gryll{} : named for the mythical Gryllus, one of Ulysses'\mbox{}\newline \hspace*{6pt}\hspace*{6pt} sailors transformed by Circe into a pig, who argues that he was happier in that state than\mbox{}\newline \hspace*{6pt}\hspace*{6pt} as a man{}\mbox{}\newline {}\end{shaded}\egroup\par \DivI[Page and Line Numbers]{Page and Line Numbers}\label{U5-pln}\par Page and line breaks etc. may be marked with the following elements. \begin{sansreflist} \item [\textbf{}] (page break) marks the boundary between one page of a text and the next in a standard reference system. \item [\textbf{}] (line break) marks the start of a new (typographic) line in some edition or version of a text. \item [\textbf{}] marks a boundary point separating any kind of section of a text, typically but not necessarily indicating a point at which some part of a standard reference system changes, where the change is not represented by a structural element. \end{sansreflist} These elements mark a single point in the text, not a span of text. The global {n} attribute should be used to supply the number of the page or line beginning at the tag. \par When working from a paginated original, it is often useful to record its pagination, if only to simplify later proof-reading. It is also useful for synchronizing an encoded text with a set of page images. Recording the line breaks may be useful for similar reasons. \par If features such as pagination or lineation are marked for more than one edition, specify the edition in question using the {ed} attribute, and supply as many tags are necessary. For example, in the following passage we indicate where the page breaks occur in two different editions ({ED1} and {ED2}) \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{p}>}I wrote to Moor House and to Cambridge immediately, to say what I had done: fully\mbox{}\newline explaining also why I had thus acted. Diana and {<\textbf{pb}\hspace*{6pt}ed="{ED1}"\hspace*{6pt}n="{475}"/>} Mary approved the step\mbox{}\newline unreservedly. Diana announced that she would {<\textbf{pb}\hspace*{6pt}ed="{ED2}"\hspace*{6pt}n="{485}"/>}just give me time to get\mbox{}\newline over the honeymoon, and then she would come and see me.{}\end{shaded}\egroup\par \par A special attribute {break} may be used to indicate whether or not this empty element is considered as a word-breaking, irrespective of any adjacent whitespace. For example, in the following encoded sample: \par The and elements are special cases of the general class of \emph{milestone} elements which mark reference points within a text. The generic element can mark any kind of reference point: for example, a column break, the start of a new kind of section not otherwise tagged, or in general any significant change in the text not marked by an XML element. The names used for types of unit and for editions referred to by the {ed} and {unit} attributes may be chosen freely, but should be documented in the header element (see \textit{\hyperref[refsdecl]{19.2.3. Reference and Classification Declarations}}). The element may be used to replace the others, or the others may be used as a set; they should not be mixed arbitrarily. \DivI[Marking Highlighted Phrases]{Marking Highlighted Phrases}\label{U5-hilites} \DivII[Changes of Typeface, etc.]{Changes of Typeface, etc.}\label{faces}\par Highlighted words or phrases are those made visibly different from the rest of the text, typically by a change of type font, handwriting style, ink colour etc., which is intended to draw the reader's attention to some associated change.\par The global {rend} attribute can be attached to any element, and used wherever necessary to specify details of the highlighting used for it in the source. For example, a heading rendered in bold might be tagged \texttt{}, and one in italic \texttt{}.\par The values to be used for the {rend} attribute are not specified by the TEI Guidelines, since they will depend entirely on the needs of the particular project. Some typical values might include \texttt{italic}, \texttt{bold} etc. for font variations; \texttt{center}, \texttt{right} etc. for alignment; \texttt{large}, \texttt{small} etc. for size; \texttt{smallcaps}, \texttt{allcaps} etc. for type variants and so on. Several such words may be used in combination as necessary, but no formal syntax is proposed. The full TEI Guidelines provide more rigorous mechanisms, using other W3C standards such as CSS, as an alternative to the use of {rend}. \par It is not always possible or desirable to interpret the reasons for such changes of rendering in a text. In such cases, the element may be used to mark a sequence of highlighted text without making any claim as to its status. \begin{sansreflist} \item [\textbf{}] (highlighted) marks a word or phrase as graphically distinct from the surrounding text, for reasons concerning which no claim is made. \end{sansreflist} \par In the following example, the use of a distinct typeface for the subheading and for the included name are recorded but not interpreted: \par\bgroup\ttfamily\small\selectfont \begin{shaded}\noindent\mbox{}{<\textbf{p}>}\mbox{}\newline \hspace*{6pt}{<\textbf{hi}\hspace*{6pt}rend="{gothic}">}And this Indenture further\mbox{}\newline \hspace*{6pt}\hspace*{6pt} witnesseth{} that the said {<\textbf{hi}\hspace*{6pt}rend="{italic}">}Walter Shandy{}, merchant, in\mbox{}\newline consideration of the said intended marriage ...\mbox{}\newline {}\end{shaded}\egroup\par \par Alternatively, where the cause for the highlighting can be identified with confidence, a number of other, more specific, elements are available. \begin{sansreflist} \item [\textbf{}] (emphasized) marks words or phrases which are stressed or emphasized for linguistic or rhetorical effect. \item [\textbf{}] (foreign) identifies a word or phrase as belonging to some language other than that of the surrounding text. \item [\textbf{}] identifies a phrase or word used to provide a gloss or definition for some other word or phrase. \item [\textbf{