diff options
Diffstat (limited to 'doc/transliterator.tex')
| -rw-r--r-- | doc/transliterator.tex | 897 |
1 files changed, 897 insertions, 0 deletions
diff --git a/doc/transliterator.tex b/doc/transliterator.tex new file mode 100644 index 0000000..d8e392c --- /dev/null +++ b/doc/transliterator.tex @@ -0,0 +1,897 @@ +\setuppapersize [A5] [A5] + +\definecolor [gutenred] [x=bf221f] % rubrication from digitized_Göttingen Gutenberg bible + +\setupinteraction [ + state=start, + color=gutenred, % rubricate, don’t viridificate + contrastcolor=gutenred, +] + +\setupcombinedlist[content][interaction=text,focus=standard] + +\setupindenting[yes,next,medium] + +%\showgrid +\setuphead[chapter][ + align=middle, + number=no, + style={\rm\tfa\setcharacterkerning[capitals]\WORD}, + before={\blank[5*line]}, + after={\blank[2*line,force]} +] + +\setuphead[section][ + align=middle, + number=no, + style={\rm\setcharacterkerning[capitals]\WORD}, + before={\blank[line,force]}, + after={\blank[line]} +] + +\setuphead[subsection][ + align=middle, + number=no, + style={\tf\sc\word}, + before={\blank[line,force]}, + after={\blank[line]} +] + +\setuplist[chapter][ + alternative=c, + interaction=text, + style={\word\sc}, +] +\setuplist[section,subsection][ + alternative=a, + style=\tfx\italic, + interaction=text, + margin=2em, + numberstyle=, + textstyle=, + numberstyle=\tfx, +] + +\setuplist[subsection][ + margin=4em, +] + +\setuplistalternative + +\definecharacterkerning [capitals] [factor=.05] + +\definefontfeature [default][default][ + protrusion=quality, + expansion=quality, + %mode=node, + script=latn, + onum=yes, + %dlig=yes, + liga=yes, +] + +\definefontfeature [smallcaps] [default] [smcp=yes] +\def\sc{\addff{smallcaps}\setcharacterkerning[capitals]} + +\setupbodyfontenvironment [default] [em=italic] + +\starttypescript [serif] [bukyvede] + \setups [font:fallback:serif] + \definefontsynonym [Serif] [name:Bukyvede] [features=default] + \definefontsynonym [SerifItalic] [name:Bukyvede-Italic] [features=default] +\stoptypescript +\usetypescript [bukyvede] +\definetypeface [hlaholice] [rm] [serif] [bukyvede] [default] [encoding=ec] +\definetypeface [cyrilice] [rm] [serif] [bukyvede] [default] [encoding=ec] +\definetypeface [lmstd] [rm] [serif] [latin-modern] [default] [encoding=texnansi] + +\usetypescriptfile[type-cmu] +\usetypescript[computer-modern-unicode] +\setupbodyfont[computer-modern-unicode,9pt] + +\usetypescript [serif] [hz] [highquality] +\setupalign [hanging,hz] + +\usemodule[bib] +\usemodule[transliterator] + +\setupcite[authoryear][compress=no] + +\setuppublications[% + alternative=apa,% + refcommand=authoryear,% + sorttype=bbl,% + numbering=yes,% + autohang=yes% +]% + +\setuppublicationlist[% + artauthor=\invertedauthor% +] + +% == REFERENCES =============================================================== + +\startpublication[ + k=aks, + t=book, + a={{Birnbaum/Schaeken}}, + y=1999, + n=4, + u=http://www.schaeken.nl/lu/research/online/publications/akslstud/index.htm, + s={Studien}, +] +\author[]{Henrik}[H.]{}{Birnbaum} +\author[]{Jos}[J.]{}{Schaeken} +\pubyear{1999} +\title{Altkirchenslavische Studien} +\volume{2} +\city{München} +\stoppublication + +\startpublication[ + k=bornemann, + t=book, + a={{Bornemann/Risch}}, + y=1978, + n=2, + s={Grammatik}, +] +\author[]{Eduard}[]{}{Bornemann} +\author[]{Ernst}[]{}{Risch} +\pubyear{1978} +\title{Griechische Grammatik} +\city{Frankfurt am Main} +\edition{2.} +\stoppublication + +\startpublication[ + k=bh, + t=book, + a={{Bringhurst}}, + y=2008, + n=4, + s={Bringhurst}, +] +\author[]{Robert}[R]{}{Bringhurst} +\pubyear{2008} +\title{The Elements of Typographic Style} +\edition{3.2} +\city{Point Roberts WA, Vancouver} +\stoppublication + +\startpublication[ + k=dintb, + t=book, + a={{DIN}}, + y=2001, + n=5, + s={DIN}, +] +\editor[]{}[]{}{DIN Deutsches Institut für Normung e.~V.} +\pubyear{2001} +\title{Bibliotheks und Dokumentationswesen} +\city{Berlin/Wien/Zürich} +\stoppublication + +\startpublication[ + k=duden, + t=book, + a={{Drosdowski/Müller/Scholze-Stubenrecht/Wermke}}, + y=1952, + n=1, + s={DUDEN}, +] +\editor[]{Günther}[]{}{Drosdowski} +\editor[]{Wolfgang}[]{}{Müller} +\editor[]{Werner}[]{}{Schulze-Stubenrecht} +\editor[]{Matthias}[]{}{Wermke} +\pubyear{1991} +\title{DUDEN Rechtschreibung der deutschen Sprache} +\city{Mannheim et al} +\edition{20.} +\stoppublication + +\startpublication[ + k=kirschbaum, + t=book, + a={{Kirschbaum}}, + y=2001, + n=3, + s={Grammatik}, +] +\author[]{Ernst Georg}[]{}{Kirschbaum} +\pubyear{2001} +\title{Grammatik der russischen Sprache} +\city{Berlin} +\stoppublication + +\startpublication[ + k=iso, + t=inbook, + a={{ISO}}, + y=1995, + n=6, + s={ISO~9}, +] +\editor[]{}[]{}{{{\sc iso} International Organization for Standardization}} +\pubyear{1995} +\title{Information and documentation -- Transliteration of Cyrillic characters into Latin characters -- Slavic and non-Slavic languages} +\edition{2.} +\crossref{dintb} +\pages{230--245} +\stoppublication + +%============================================================================== + +\setupframed[ + frame=off, + align=normal, + location=top, +] + +\defineframed[displayouter][ + location=top, + align={normal,verytolerant}, + frame=off, + style=\tfx, +] +\defineframed[displayinner][displayouter][ + offset=1ex, + width=.47\textwidth, +] + +\definenumber[excnt] +\setnumber[excnt][1] + +% This should rather be done using key-value args but I'm too lazy now. +% 1: mode; 2: hyphenate original; 3: hyphenate transliteration; +% 4: font for original; 5: caption; 6: original text. +\def\trlex#1#2#3#4#5#6{% + \setuplocalinterlinespace[line=8pt]% + \startplacefigure [ + location=force, + title={\type{[mode=#1,hyphenate=#3]}\hskip 1em{\italic #5}} + ]% + \displayouter{% + \displayinner{% + \setupbodyfont[#4]% + \tfx + %\setuptolerance[verytolerant, stretch] + \setuptolerance[verytolerant] + \unskip\language[#2]#6\par + }% + \displayinner{% + \tfx + \transliterate[mode=#1,hyphenate=#3]{#6\par}% + } + } + \stopplacefigure + \incrementnumber[excnt]% +} + +\defineframedtext[CenteredText][width=fit,frame=off,align=middle] + +\usemodule[int-load] +\loadsetups[t-transliterator.xml] + + +\setupwhitespace[medium] +\language[en] + +\starttext + +\setuppagenumbering[state=stop] + +\blank[3cm,force] + + +%\showframe +\startstandardmakeup[location=middle] + +\setuplayout[width=middle] +\raggedcenter +\vfill + {\setupbodyfont[19pt] + {\em The} + \blank [2*big] + {\tfc\sc transliterator} + \blank [2*big] + {\em for \CONTEXT} + \blank [9*big] + {\tfa\sc manual} + } +\vfill +\stopstandardmakeup + +\startstandardmakeup +\vfill +\framed [frame=off,topframe=on] {% +\tfxx\ss\setupinterlinespace[small]% +\startlines +The {\em Transliterator} module and mini-manual, +by Philipp Gesang, Radebeul. +Mail any patches or suggestions to + +{\tt philipp -dot- gesang -at- alumni -dot- uni-heidelberg -dot- de} +\useurl[me][https://phi-gamma.net] +\from[me]% +\stoplines +} +\stopstandardmakeup + +\setuppagenumbering[% + location=middle, + state=start, + style=\tfc +] + +\setuppagenumber[number=1] +\completecontent +\chapter{Usage and Functionality} +\section{Overview} +The Transliterator provides two commands: \type{\setuptransliterator} +preferably goes into the preamble and allows for global configuration. +The Transliterator is invoked locally by \type{\transliterate} which does the +actual transliteration of text passages. + +\setup{setuptransliterator} + +\setup{transliterate} + +\section{Loading and Configuring the Module} +In order to use the Transliterator in a document we put the following somewhere before +\type{\starttext}. +\starttyping +\usemodule[transliterator] +\stoptyping +Although it has some defaults already set at this point they will most likely +not correspond to what is needed in the document. +To override the presets we use the command \type{\setuptransliterator[#1]}. +It takes a comma separated list of two key-value pairs: \type{mode} and +\type{hyphenate}. +Through {\em mode} we specify the transliteration method. +By the time of this writing this can be one of the following set: + +\startplacetable[location=top,title=Transliteration modes.] + \tfx + \starttabulate[|l|p|] + \HL + \NC mode \NC description \NC\NR + \HL + \NC \type{all} \NC {\sc iso}~9 complete \NC\NR + \NC \type{bg_de} \NC Bulgarian, German „scientific“ transliteration\NC\NR + \NC \type{gr} \NC transliteration for Greek \NC\NR + \NC \type{gr_n} \NC transliteration for Greek obeying nasalizations \NC\NR + \NC \type{iso9_ocs} \NC == \type{all} plus non-{\sc iso} additions for Old (Church) Slavonic \NC\NR + \NC \type{ocs} \NC “scientific” transliteration for Old (Church) Slavonic\NC\NR + \NC \type{ocs_cz} \NC Czech transcription for Old (Church) Slavonic\NC\NR + \NC \type{ocs_gla} \NC “scientific” transliteration for Old (Church) Slavonic / Glagolitic alphabet\NC\NR + \NC \type{ru} \NC {\sc iso}~9 Russian \NC\NR + \NC \type{ru_cz} \NC Czech transcription for Russian\NC\NR + \NC \type{ru_old} \NC {\sc iso}~9 Russian plus pre-1918 chars (the default)\NC\NR + \NC \type{ru_transcript_de} \NC German transcription for Russian \NC\NR + \NC \type{ru_transcript_en} \NC English transcription for Russian \NC\NR + \NC \type{sr_tocy} \NC Serbian, Latin to Cyrillic \NC\NR + \NC \type{sr_tolt} \NC Serbian, Cyrillic to Latin \NC\NR + \HL + \stoptabulate +\stopplacetable + + +{\em Nota bene}: The description at this point only serves as a placeholder as the +transliteration modes are discussed in detail later in this document. + +Through the \type{hyphenate} argument it is possible to adjust the language +that is used for hyphenation. +Specifying \type{\setuptransliterator[hyphenate=nl]} will let every transliterated +part of the document be processed according to dutch rules, leaving the overall +\type{\language[#1]} configuration unchanged for the rest of the content. + +Another argument, \type{deficient_font} can be used in +combination with the modes \type{all}, \type{ru_old} and +\type{iso9_ocs}. It lets you circumvent the deficiency that some +fonts show concerning the characters that {\sc iso}~9 assigns to +cyrillic “ь” and “ъ”. Set it to {\em true} to enable it. + +The actual transliteration is done using the macro +\type{\transliterate[#1]} \type{{#2}}. +The second argument takes the raw string in the original language that we want +to process, while the first, optional argument accepts local adjustments for +\type{mode} and \type{hyphenate}. +Thus, we would typeset one of Epicuros' sayings like this: +{\setuptolerance[verytolerant] +\starttyping +\transliterate[mode=gr]{κακὸν ἀνάγκη, ἀλλ' οὐδεμία ἀνάγκη ζῆν + μετὰ ἀνάγκης} +\stoptyping +\noindentation which yields \quotation{\transliterate[mode=gr]{κακὸν ἀνάγκη, ἀλλ' οὐδεμία ἀνάγκη ζῆν +μετὰ ἀνάγκης}} in the {\sc pdf} output. +} +Alternatively there is an environment, \type{\starttransliterate[#1]}, as well, +that takes the same arguments. + +There are two special switches for the {\em Serbian} patterns, +\type{hinting} and \type{sr_exceptions}, allowing for a little +more fine-tuning. +If activated, hinting provides the special character “\type{*}” as +a means to indicate positions, where the sequences “lj” and “nj” +are to be treated as separate consonants. +E.~g. \type{\transliterate[mode=sr_tocy]{in*jekcija}} is +correctly transliterated as \transliterate[mode=sr_tocy]{in*jekcija}, +and not \transliterate[mode=sr_tocy,sr_exceptions=no]{injekcija}. +Likewise, further exceptions that are internally represented as +a lookup table can be toggled off or on by the +\type{sr_exceptions} switch. +This pertains to words like “nadživeti” (result: \transliterate[mode=sr_tocy]{nadživeti}) +but may lead to accidental false positives in cases that the +module author didn’t foresee. +By default both hinting and lexical exceptions are set to +\type{yes}. + +For orientation purposes the Transliterator comes with two macros that allow +for closer inspection of the internal tables. +\type{\showOneTranslitTab{#1}} outputs, obviously, a single table; their +identifiers +can be found in the \type{trans_} +\type{tables_*.lua} files in the transliterator +directory. +The lazy alternative is \type{\showTranslitTabs} which prints all registered +tables in a row nicely formatted as indexable sections. +(Be warned, this may take some time.) + +\chapter{Introduction} + +\hfil\framed[width=\hsize,align=left]{% + \inframed[bottomframe=on]{\it What's all this, then?} + \blank[medium] + {\sc Graham Chapman} +} +\blank[2*big] + +\noindentation At the first glance, {\em transliteration} -- the accurate representation of letters from one +alphabet in another -- seems obsolete after the advent of Unicode +which made its way even into \TeX\ lately. +Why not just go on and write down everything in the original script? +But still there are lots of situations where transliteration is desirable, +e.~g. some scholarly habits might prescribe it in the main text with citations in +footnotes left in the original alphabet; or transliteration might alleviate +comparison within one language that happens to be written in different scripts; +finally, including text in a foreign script might be impossible if there is no +appropriate font which fits the main text. +However, it is still most convenient for the writer to keep the +untransliterated original in the document source as this allows for reusing it in +another context where different transliterations rules might apply. +The Transliterator module is meant to provide both: have the original in the +source and a transliteration only in the final document. + +Another way of handling foreign languages is {\em transcription}. +It aims at producing some representation that does not rely on symbolisms +alien to the language and thus to be at least \quotation{pronouncable} +without further know\-ledge. +As transcription methods are language specific and highly idiosyncratic they +complicate the restoration of the original phrase because information may be lost. +The Transliterator provides means of transcription as well but in most cases +you should refrain from using them (\type{[mode=ru_transcript_en]}, +\type{[mode=ru_transcript_de]}). + +For Cyrillic scripts the best quality is achieved using the standardized +transliteration according to {\sc iso~9}.\footnote{\cite[authoryear][iso].} +This method not only covers all contemporary languages that are written in +a variety of Cyrillic but provides a bijective mapping on latin characters as +well. +Consequently, you can unambiguously revert the transliteration into +its original form which was impossible with previous versions of {\sc +iso}~9 because +they contained several exceptions depending on the original language. +Although fifteen years old it has not yet made its way into scholarly +publications at large so it might not immediately look familiar.\footnote{ + A hasty glance at the latest issues of around 20~journals in a local library + revealed that 2~of them actually are using {\sc iso}~9, these are {\em Przegląd + wschodni} as of Nr. X, 3 (2008) and {\em Kwartalnik historyczny} as of CXVI, + 3 (2009); the latter even contains a table on p.~218 showing a subset of the + {\sc iso}~9 transliteration rules. +} +The diacritics are not identical to the \quotation{scientific} +transliteration used in Slavic studies but as long as your editor does not +enforce its traditional method you should always prefer {\sc iso}~9 +(\type{[mode=ru]}, \type{[mode=ru_old]}, \type{[mode=all]}). + +But {\sc iso}~9, too, has its shortcomings. +It has no definitions for historical forms of the cyrillic script like +pre-XVIII-century Russian and Old (Church) Slavonic while those are covered by +the scholarly transliterations. +To amend the situation the Transliterator provides an extension to {\sc +iso}~9 for +Old Slavonic containing the glyphs +\startluacode +local translit = thirddata.translit +environment.loadluafile("trans_tables_scntfc") +local cnt, len = 0, 0 +for i,j in pairs(translit.ocs_add_low) do + len = len + 1 +end + +for k,v in pairs(translit.ocs_add_low) do + cnt = cnt + 1 + context.bgroup() + context.setupbodyfont({"cyrilice"}) + context(k) + context.egroup() + if cnt < len -1 then + context(", ") + elseif cnt < len then + context("\\ and ") + end +end +\stopluacode +\ taken from the scientific transliteration (\type{[mode=iso9_ocs]}). +If you prefer more coherency you might want to use pure \quotation{scientific} +transliteration (\type{[mode=ocs]}). +This method is complemented by \type{[mode=ocs_gla]}, the only option the +Transliterator offers for the Glagolitic alphabet; they can be used consistently +along each other as they were taken from the same +book.\footnote{\cite[authoryear][aks] p.~77 \cite[url][aks].} + +As far as I know there is no standardized transliteration for Greek so I had to +resort to the one that is used in scholarly literature. +Its main drawback is that it has no representation for diacritics apart from +(rough) breathing, but it respects specific rules for diphthongs and vowels in +initial positions (\type{[mode=gr]}). +There is one alternative mode for those who prefer their {\em γ} phonetically +resolved to /{\em n}/ before velars ({\em γ}, {\em κ}, {\em χ} and {\em ξ}; +\type{[mode=gr_n]}). + +Concerning the hyphenation within transliterated passages the default is set to +to \type{[hyphenate=cs]} (Czech) which produces reasonable results when using +\type{all}, \type{iso9_ocs} or \type{ru_cz}. +For stuff like the English and German transcription use their respective native +hyphenation.\footnote{% + You'll have to specify this through \type{\setuptransliterator} + or locally because the default hyphenation is {\em not} the same as your + documents'. +} +However, as there is no hyphenation pattern I know of that closely resembles the +transliteration of Greek you might have to resort to putting \type{\discretionary} +hyphens when line breaking does not satisfy. + +The Transliterator as a whole is nothing more than a bunch of dictionaries +containing substitution rules for tokens that may occur in the text. +These tokens may be single characters or strings of more than one character. +As there is no simple way to impose order onto those dictionaries the rules for +one transliteration method are, if needed, distributed over more than one table +which will be applied successively to ensure that multi-character rules +are processed first. + + +\setupfloats[spacebefore=small,spaceafter=small] +\startplacetable[location=left,title={ + Processing time for corpus {\language[cs]Evgenij Onegin} according to + GNU time(1) and the \CONTEXT\ stats. +}] + \starttabulate[|l|cg(.)|cg(.)|] + \HL%····················································% + \NC mode \NC time(1) in $s$ \NC \CONTEXT \NC \NR + \NC <none> \NC 8.98 \NC 8.82 \NC \NR + \NC \type{all} \NC 8.37 \NC 8.25 \NC \NR + \NC \type{ru_cz} \NC 8.61 \NC 8.48 \NC \NR + \NC \type{ru_transcript_en} \NC 9.26 \NC 9.10 \NC \NR + \NC \type{ru_transcript_de} \NC 14.83 \NC 14.71 \NC \NR + \HL%····················································% + \stoptabulate +\stopplacetable +\setuptolerance[tolerant] +Following suggestions from the mailing list, the Transliterator uses {\em LPeg} +when substituting. +This means a huge speed improvement for most substitution modes when compared +to the older mechanism that used \type{string.gsub} iteratively. +In ordinary use when transliterating single words or short phrases the +Transliterator should have little impact on document processing time at large, +with the exception of the German transcription mode, perhaps.\footnote{ + The problem lies within the rule set for the German transcription which + dictates different instructions depending on the environment of a character; + these may conflict, i.~e. it is impossible to substitute a character stream + in a single run as some rules may apply only to the result of previous rule. + Let me know if there's a way to tell LPeg to backtrack to the last character + of a match and not to continue on the next. +} +Transliterating (and typesetting in MKIV) \transliterate{Александр Пушкин}'s verse novel +\transliterate{Евгений Онегин}, a corpus of about 27000 words, in +\type{[mode=all]} shows little to no delay at all. +In fact, typesetting cyrillic letters with russian hyphenation seems slow +things down so much that transliteration may be faster and uses slightly less +memory.\footnote{% + On an IBM T43: \tt 2.6.32-ARCH \#1 SMP PREEMPT Tue Feb 9 14:46:08 UTC 2010 + i686 Intel(R) Pentium(R) M processor 1.60GHz GenuineIntel GNU/Linux. +} + + + + +\chapter[ex]{Examples} +\section{Cyrillic scripts} +\subsection{{\sc iso}~9 and derivatives} + +Several transliteration rules are either strictly {\sc iso}~9 compliant +(\type{ru}, \type{ru_old}, \type{all}) or contain {\sc iso}~9 as a +subset (\type{iso9_ocs}).\footnote{% + Unfortunately \CONTEXT\ still lacks language files for some of them + so please excuse the inadequate hyphenation in these cases.% +} + +\trlex{ru}{ru}{cs}{computer-modern-unicode}{% + Transliteration rules for the contemporary russian alphabet.% +}{% + В~ворота гостиницы губернского города NN въехала довольно красивая рессорная + небольшая бричка, в~какой ездят холостяки: отставные подполковники, + штабс-капитаны, помещики, имеющие около сотни душ крестьян, — словом, все те, + которых называют господами средней руки. + В~бричке сидел господин, не красавец, но и~не дурной наружности, ни слишком + толст, ни слишком тонок; нельзя сказать, чтобы стар, однако ж~и~не так чтобы + слишком молод. +} + +\trlex{ru_old}{ru}{cs}{computer-modern-unicode}{% + With aditional characters for pre-1981 Russian orthography (100~per + cent {\sc iso}~9).% +}{% + А~сведется віра, убьютъ сотцкого в~селѣ, ино тебѣ взяти полтіна, а~не + сотцкого, + ино четырѣ гривны, а~намъ віръ не таити в~Новѣгородѣ; а~о~убіствѣ віръ нѣтъ. + А~что волости, честны король, новгородцкіе, ино тебѣ не держати своими мужи, + а~держати мужми новогородцкими. + А~что пошлина в~Торжку и~на Волоцѣ, тівунъ свои держати на своеи чясті, + а~Новугороду на своеи чясти посадника держаті. + А~се волости новогородцкіе: Волокъ со всѣми волостми, Торжокъ, Бѣжіці, + Городець + Палець, Шіпинъ, Мелеця, Егна, Заволочье, Тиръ, Пермь, Печера, Югра, Вологда + с~волостмі. +} + +\trlex{all}{ru}{cs}{computer-modern-unicode}{% + The complete cyrillic mapping from {\sc iso}~9; transliterating Belarusian.% +}{% + Беларуская мова, мова беларусаў, уваходзіць у~сям’ю індаеўрапейскіх моў, яе + славянскай групы і~ўсходнеславянскіх моваў падгрупы, на якой размаўляюць + у~Беларусі і~па ўсім свеце, галоўным чынам у~Расіі, Украіне, Польшчы. + Б.~м. падзяляе шмат граматычных і~лексічных уласцівасцяў з~іншымі + ўсходнеславянскімі мовамі (гл. таксама: Іншыя назвы беларускай мовы і~Узаемныя + ўплывы усходнеславянскіх моваў). +} + +\trlex{all}{uk}{cs}{computer-modern-unicode}{% + The complete cyrillic mapping from {\sc iso}~9; transliterating Ukrainian.% +}{% + Украї́нська мова (застарілі назви -- руська мова, проста мова […]) -- + слов'янська мова, державна в~Україні та одна з~трьох «офіційних мов на рівних + засадах» у~не\-ви\-зна\-ній Придністровській Молдавській Республіці. + За різними оцінками загалом у~світі українською мовою говорить від 41~млн. + до 45~млн. осіб, вона входить до третього десятка найпоширеніших мов + світу. +} + +\trlex{all}{ru}{cs}{computer-modern-unicode}{% + The complete cyrillic mapping from {\sc iso}~9; transliterating Serbian.% +}{% + Српски језик је један од словенских језика из породице индоевропских језика. + Први писани споменици у~српској редакцији старословенског језика потичу из XI + и~XII века. + Српски језик је стандардни језик у~службеној употреби у~Србији, Босни + и~Херцеговини и~Црној Гори, а~у~употреби је и~у другим земљама гдје живе + Срби, међу осталима и~у~Хрватској. +} + +\trlex{iso9_ocs}{ru}{cs}{cyrilice}{% + Transliteration rules according to {\sc iso}~9 with additions for Old (Church) + Slavonic.% +}{% + Что сѧ дѣѥтѣ по вѣремьнемь~: то ѿидето по вѣрьмьнемь~: приказано бѹдѣте + добрымъ людѣмъ~: а любо грамотою ѹтвѣрдѧть~: како то бѹдѣте всемъ вѣдомъ~: + или кто посль живыи ѡстанѣть сѧ~: того лѣт͠ коли алъбрахтъ~: влд͠ка ризкии + ѹмьрлъ~: ѹздѹмалъ кнѧзѣ смольнескыи~: мьстиславъ~: двд͠въ сн͠ъ~: прислалъ въ + ригѹ своѥго лѹчьшего попа~: ѥрьмея~: и съ нимь ѹмьна мѹжа пантелья~: + исвоѥго горда смольнеска~: та два была послъмь ѹ ризѣ~: из ригы ѥхали на + гочкыи берьго~: тамо твердити миръ~: +} + +\subsection{“Scientific” transliteration} +These transliterations are widely used among scholars, mainly linguists and, to +a lesser extent, historians. +They comprise large character sets in order to represent the original text +adequately and facilitate comparison of texts of the same language written in +different scripts; they are not, however, as easily reversible as {\sc +iso}~9. + +\trlex{ocs}{ru}{cs}{cyrilice}{% + Transliteration for Old Slavonic used in Slavic studies, taken from the + excellent book of \cite [authoryear][aks].\footnote{% + This one and both of the following Czech transliterations, although + elegantly dealing with hard and weak signs by taking characters from the + Cyrillic alphabet, are not unquestioned from a typographical point of + view: + \quotation{If contrasting faces are used for phonetic transcriptions and + main text, each entire phonetic word or passage, not just the individual + phonetic characters, should be set in the chosen phonetic face. Patchwork + typography, in which the letters of a single word come from different faces + and fonts, is a sign of typographic failure. […] + Such mixtures are almost sure to fail unless all the fonts involved have + been designed as a single family.} + (\cite [authoryear][bh]) + From this follows that it is advisably to reconsider your font whether it indeed + provides the needed glyphs from Russian as well. + }% +}{% + Се начнемъ повѣсть сию. + По потопѣ . первиє снве Ноєви . раздѣлиша землю . Симъ . Хамъ . Афетъ . и~ꙗсѧ + въстокъ . Симови Персида . Ватрь . тоже и~до Индикиꙗ в~долготу и~в~ширину [и + до Нирокоуриа] ꙗкоже рещи ѿ въстока и~до полуденьꙗ . и~Суриꙗ . + и~Индиа по Єфратъ рѣку . Вавилонъ . Кордуна . Асурѧне . Мисопотамира . + Аравиꙗ . старѣишаꙗ . Єлмаисъ . Инди . Равиꙗ . на всѧ Д. +} + +\trlex{ru_cz}{ru}{cs}{computer-modern-unicode}{% + Czech phonetic transcription for contemporary Russian.% +}{% + Прошло семь лет после 12-го года. Взволнованное историческое море Европы + улеглось в свои берега. Оно казалось затихшим; но таинственные силы, + двигающие человечество (таинственные потому, что законы, определяющие их + движение, неизвестны нам), продолжали свое действие. + Несмотря на то, что поверхность исторического моря казалась неподвижною, так + же непрерывно, как движение времени, двигалось человечество. Слагались, + разлагались различные группы людских сцеплений; подготовлялись причины + образования и~разложения государств, перемещений народов.% +} + +\trlex{ocs_cz}{ru}{cs}{cyrilice}{% + Czech phonetic transcription for Old Slavonic (superset of the corresponding + Russian transcription). +}{% + Убьеть мужь мужа, то мьстить брату брата, или сынови отца, любо отцю сына, + или братучаду, любо сестрину сынови; аще не будеть кто мьстіѧ, то 40 гривенъ + ꙁа голову; аще будеть русинъ, любо гридинъ, любо купчина, любо іѧбетник, любо + мечникъ, аще иꙁъгои будеть, любо словенинъ, то 40 гривенъ положити ꙁа нь. +} + +\subsection{Serbian} +The tables for converting Serbian text between Cyrillic and Latin +alphabets are \type{sr_tolt} and \type{sr_tocy}. +\trlex{sr_tolt}{sr}{hr}{computer-modern-unicode}{% + Transliteration ћирилица \rightarrow\ латиница.% +}{% + Српски језик је један од словенских језика из породице + индоевропских језика. Први писани споменици у српској редакцији + старословенског језика потичу из XI и XII века. + + Српски језик је стандардни језик у службеној употреби у Србији, + Босни и Херцеговини и Црној Гори, а у употреби је и у другим + земљама где живе Срби, међу осталима и у Хрватској.% +} + +\trlex{sr_tocy}{hr}{sr}{computer-modern-unicode}{% + Transliteration latinica \rightarrow\ ćirilica.% +}{% + Srpski jezik je jedan od slovenskih jezika iz porodice + indoevropskih jezika. Prvi pisani spomenici u srpskoj + redakciji staroslovenskog jezika potiču iz XI i XII veka. + + Srpski jezik je standardni jezik u službenoj upotrebi u Srbiji, + Bosni i Hercegovini i Crnoj Gori, a u upotrebi je i u drugim + zemljama gde žive Srbi, među ostalima i u Hrvatskoj.% +} + +\subsection{Bulgarian} + +\trlex{bg_de}{bg}{cs}{computer-modern-unicode}{% + German scientific transliteration for Bulgarian (based on old {\sc + iso}~9 standard).% +}{% + Българският език е индоевропейски език от групата на + южнославянските езици. Той е официалният език на Република + България и един от 23-те официални езика на Европейския съюз. +} + +\subsection{Legacy national transcriptions} +At the moment there are tables for “old school” transcription into three +languages: English (via \type{ru_transcript_en}), German +(\type{ru_transcript_de}) and Czech (\type{ocs_cz}). +At least the German one is almost unreadable if used with +strings longer than two words. +As we have the bijective {\sc iso}~9 mapping at hand there should be no reason at all +to use any of them. + +\trlex{ru_transcript_en}{ru}{en}{computer-modern-unicode}{% + English transcription for contemporary Russian.% +}{% + Прошло семь лет после 12-го года. Взволнованное историческое море Европы + улеглось в свои берега. Оно казалось затихшим; но таинственные силы, + двигающие человечество (таинственные потому, что законы, определяющие их + движение, неизвестны нам), продолжали свое действие. + Несмотря на то, что поверхность исторического моря казалась неподвижною, так + же непрерывно, как движение времени, двигалось человечество. Слагались, + разлагались различные группы людских сцеплений; подготовлялись причины + образования и~разложения государств, перемещений народов.% +} + +\trlex{ru_transcript_de}{ru}{deo}{computer-modern-unicode}{% + German transcription for contemporary Russian.\footnote{% + Following \cite[authoryear][duden] p.~82; all the canonical rules are + implemented save one: {\em -его} and {\em -ого} should resolve to {\em + -ewo} and {\em -owo} respectively iff genitive endings. + As this is a grammatical rather than graphetical criterion writing a + substitution algorithm would amount to do natural language parsing. + To make things worse this rule is phonetically confused as it would not + take care of other contexts where {\em г} in those patterns is articulated + as /{\em v}/ like for instance in {\em сегодня} (which is a historical + genitive, though …). + So even if this could be implemented it would not be advisable to use such + a rule.% + }% +}{% + Прошло семь лет после 12-го года. Взволнованное историческое море Европы + улеглось в свои берега. Оно казалось затихшим; но таинственные силы, + двигающие человечество (таинственные потому, что законы, определяющие их + движение, неизвестны нам), продолжали свое действие. + Несмотря на то, что поверхность исторического моря казалась неподвижною, так + же непрерывно, как движение времени, двигалось человечество. Слагались, + разлагались различные группы людских сцеплений; подготовлялись причины + образования и~разложения государств, перемещений народов.% +} + +\section{Glagolitic} +\trlex{ocs_gla}{ru}{cs}{hlaholice}{% + “Scientific” transliteration for Old Slavonic written in the Glagolitic + alphabet as used in \cite[authoryear][aks].% +}{% + [ⰲⰾ] + ⰰⰴⱏⰻⰽⱁ ⱍⰽ҃ⱏ ⱄⰻ ⱈⱁⱋⰵⱅⱏ ⱃⰰⰸ[ⱁⱃⰻⱅ] + ⰻ ⰸⰰⰽⱁⱀⱏ ⰿⰰⱀⰰⱄⱅⱏⰻⱃⱏⱄⰽⰻ: [ⰻⰶⰵ] + ⱅⱏⰻ ⱆⱄⱅⰰⰲⰻ჻ Ⱃⰵⱍⰵ ⰶⰵ ⰻⰳⱆⰿ[ⱏ] [ⱀⱏ] + ⰽⰰⰽⱁ ⱈⱁⱋⰵⱅⱏ ⱃⰰⰸⱁⱃⰻⱅⰻ ⰸⰰⰽ[ⱁⱀⱏ] + [.] [ⰰ] ⰵⱄⱅⱏ· ⱍⱃⱏⰲⰻ⁖ ⰻ [ⰿ] [..........] + [..] ⰿⱏ ⱀⰵ ⰿⱁⰶⰵⰿⱏ ⱄⰵⰳⱁ ⱅⱃⱏⱂⱑⱅ[ⰻ] + [ⰴⰰ] ⰾⱆⰱⱁ ⱄⰵⰳⱁ ⰻⰿⱑⰻ ⱄⱏⰴⱑ჻ ⰰ ⰿⱏⰻ ⱁ + [ⱅⰻ]ⰴⰵⰿⱏ: ⰾⱆⰱⱁ ⱄⰵⰳⱁ ⱂⱆⱄⱅⰻ: ⰴⰰ ⱁⱅ + [ⰻⰴ]ⰵⱅⱏ ⰻⰶⰵ ⰵⱄⱅⱏ ⱂⱃⰻⱎⱏⰾⱏ: ⱄ[ⰵ] +} + +\section{Greek} +The Transliterator offers two modes for handling Greek: \type{gr} and +\type{gr_n}. +They differ only on one aspect. +\type{gr} transliterates the canonical Greek alphabet as well as the +special glyphs Digamma, Quoppa and Sampi. +\type{gr_n} behaves exactly the same way except that nasalization is observed +such that \type{γ+[γ|κ]} yields \type{n+[g|k]}. + +\trlex{gr}{agr}{de}{computer-modern-unicode}{% + Transliteration for Greek -- standard. +}{% + οἴνῳ δὲ κάρτα προσκέαται, καί σφι οὐκ ἐμέσαι ἔξεστι, οὐκὶ οὐρῆσαι ἀντίον + ἄλλου. + ταῦτα μέν νυν οὕτω φυλάσσεται, μεθυσκόμενοι δὲ ἐώθασι βουλεύεσθαι τὰ + σπουδαιέστατα τῶν πρηγμάτων: τὸ δ᾽ ἂν ἅδῃ σφι βουλευομένοισι, τοῦτο τῇ + ὑστεραίῃ νήφουσι προτιθεῖ ὁ στέγαρχος, ἐν τοῦ ἂν ἐόντες βουλεύωνται, καὶ ἢν + μὲν + ἅδῃ καὶ νήφουσι, χρέωνται αὐτῷ, ἢν δὲμὴ ἅδῃ, μετιεῖσι. τὰ δ᾽ ἂν νήφοντες + προβουλεύσωνται, μεθυσκόμενοι ἐπιδιαγινώσκουσι. +}% + +\trlex{gr_n}{agr}{de}{computer-modern-unicode}{% + Transliteration for Greek -- alternative respecting nasalization. +}{% + ταῦτα καὶ νεωτέρῳ καὶ πρεσβυτέρῳ ὅτῳ ἂν ἐντυγχάνω ποιήσω, καὶ ξένῳ καὶ ἀστῷ, + μᾶλλον δὲ τοῖς ἀστοῖς, ὅσῳ μου ἐγγυτέρω ἐστὲ γένει. +}% + + +\chapter{References} +%\cite[authoryear][iso] +\nocite[duden] +\nocite[bornemann] +\nocite[kirschbaum] +\nocite[iso] +\nocite[aks] +\nocite[dintb] +\placepublications [criterium=all] + +\stoptext +% vim:ft=context |