summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/doc/latex/greek-fontenc/lgrenc-test.tex
blob: 724bbef72dbbae2ec8482736bb8353bb7a416ce0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
\documentclass{article}

% Test with various LGR-encoded fonts:
\usepackage%
{lmodern}  % uses CB Fonts for Greek
% {gfsartemisia}
% {gfsbaskerville}
% [default]{gfsbodoni}
% [default]{gfscomplutum}
% {gfsdidot}
% [default]{gfsneohellenic}
% {lmodern} \usepackage{gfsporson} \renewcommand*\rmdefault{porson}
% [default]{gfssolomos}
% {kerkis} % lacks some chars (\Stigma, \Sampi, double quotes)
% {teubner}
% \renewcommand{\ttdefault}{txtt}

\usepackage{parskip}
\usepackage{textcomp}
\usepackage[LGR,T1]{fontenc}

% With XeTeX/LuaTeX, use Unicode for Latin script:
\ifdefined\luatexversion \usepackage{fontspec}\else
  \ifdefined\XeTeXrevision \usepackage{fontspec}\else
    \usepackage[utf8]{inputenc}
  \fi
\fi
% This is experimental. The general advise is not to mix fontenc and fontspec.
% One problem is that xunicode makes \nobreakspace font encoding specific
% We provide a default:
\DeclareTextCommandDefault{\nobreakspace}{\leavevmode\nobreak\ }

% PDF hyperlinks:
\usepackage[pdfencoding=auto]{hyperref}
\usepackage{bookmark}
\hypersetup{colorlinks=true,linkcolor=blue,urlcolor=blue,pdfencoding=auto}

% font encoding switch declarations:
\newcommand{\LGR}{\fontencoding{LGR}\selectfont}
\newcommand{\Latin}{\fontencoding{\encodingdefault}\selectfont}


\begin{document}

\title{Test LGR font encoding definitions}
\author{Günter Milde}
% \date{}
\maketitle

The file lgrenc.def provides a comprehensive set of macros to typeset Greek
with LGR encoded fonts. It works for both, monotonic and polytonic Greek,
independent of the \emph{Babel} package.

The example from \texttt{usage.tex} in \emph{babel-greek} input
using the LICR macros:

\begin{quote}
  \LGR 
  \textTau\'\textiota{}
  \textphi\'\texteta\textiota\textfinalsigma\texterotimatiko{}
  \<\textIota\textdelta\`\textomega\textnu{}
  \>\textepsilon\textnu\texttheta\'\textepsilon\textdelta\textepsilon{}
  \textpi\textalpha\~\textiota\textdelta\'\'
  \>\textepsilon\textlambda\textepsilon\textupsilon\texttheta\'\textepsilon\textrho\textalpha\textnu\\
  \texttau\`\textalpha\textfinalsigma{}
  \textpi\textlambda\texteta\textautosigma\'\textiota\textomicron\textnu{}
  \textNu\'\textupsilon\textmu\textphi\textalpha\textfinalsigma{}
  \textautosigma\texttau\textepsilon\textphi\textalpha\textnu\textomicron\~\textupsilon\textautosigma\textalpha\textnu{},
  \textSigma\'\textomega\textautosigma\texttau\textrho\textalpha\texttau\textepsilon{},\\
  \>\textepsilon\textrho\~\textomega\textnu{}
  \'\textalpha\textpi\~\texteta\textlambda\texttheta\textepsilon\textfinalsigma{}
  \textepsilon\>\textupsilon\texttheta\'\textupsilon\textfinalsigma\texterotimatiko{}

\end{quote}

\section{Symbols}

See the source file \href{lgrenc-test.tex}{lgrenc-test.tex} for the macros
used to access the symbols.

\subsection{Generic text symbols}

Latin:
+ - = < > -- --- \textbraceleft{} [ () ] \textbraceright{}
%
\textbackslash{}
\textbar{}
\textperthousand{}
\textpertenthousand{}
\textvisiblespace{}

LGR:
\LGR
+ - = \textless{} \textgreater{} -- ---
\textbraceleft{} [ () ] \textbraceright{}
%
\textbackslash{} \textbar{}
\textperthousand{}
% \textpertenthousand{}
\textvisiblespace{}
\Latin (Per-mille symbol is missing in LGR.)

Quotes:
%
\Latin \guillemotleft{}a\guillemotright{}
\LGR \guillemotleft{}a\guillemotright{},
%
\Latin \textquoteleft{}a\textquoteright{}
\LGR \textquoteleft{}a\textquoteright{},
%
\Latin \textquotedblleft{}a\textquotedblright{}
\LGR \textquotedblleft{}a\textquotedblright{}
\Latin (double quotes wrong with Kerkis fonts),

\begin{quote}
  Single quotes need special attention to prevent conversion to accents.
  Test the input conventions:
  \LGR \textquoteleft{}a\textquoteright{} ``a'' \``a\'' \`\`a\'\'
  \Latin but not \LGR `a' 'e' "i"\Latin

  Single guillemots and base-quotes
  (\guilsinglleft{}a\guilsinglright{}
   \quotedblbase{}a\textquotedblright{}
   \quotesinglbase{}a\textquoteright{})
  are missing in LGR.
\end{quote}

Ligature break up: AY fi \LGR AU "i $\mapsto$
\Latin A\textcompwordmark{}Y f\textcompwordmark i
\LGR   A\textcompwordmark{}U "\textcompwordmark i


\Latin Spacing accent chars:
%
\Latin \textasciicircum a
\LGR \textasciicircum a \textasciicircum i % using textsym glyph
%
\Latin \textasciitilde a
\LGR \textasciitilde a \textasciitilde i
%
\Latin \textasciibreve a
\LGR \textasciibreve a \textasciibreve i
%
\Latin \textasciimacron a
\LGR \textasciimacron a \textasciimacron i
%
\Latin \textasciidieresis a
\LGR \textasciidieresis a \textasciidieresis i
%
\Latin \textasciiacute a
\LGR \textasciiacute a \textasciiacute i
%
\Latin \textasciigrave a
\LGR \textasciigrave a \textasciigrave i

\Latin Symbols for SI-units:
\Latin 5\,\textmu{}m, 5\,k\textohm{};
\LGR   5\,\textmu{}{\Latin m}, 5\,{\Latin k}\textohm{}

\Latin Letter schwa and Euro symbol: % \textschwa (needs e.g. T3)
\LGR \textschwa{}, \texteuro{}
\Latin

Some symbol definitions expect a Latin font.\emph{ babel-greek} redefines
them with \verb|\latintext|, however this macro is not guaranteed to be
defined, so it should not be used in a font encoding definition file. The
textcomp.sty package provides coyright, registered, and trademark symbols
for use with any font encodings. (Like any other Latin character, the
``sharp s'' (\ss) is not save to use when LGR is the active font encoding.)

Latin:
\textcopyright{}
\textregistered{}
\texttrademark{}
\SS{} (uppercase of \ss).

LGR (with textcomp):
\LGR
\textcopyright{}
\textregistered{}
\texttrademark{}
\SS{} (\Latin uppercase of \LGR \ss).
\Latin

\subsection{Greek alphabet}

Greek letters via Latin transcription and LICR macros:

\LGR
\MakeUppercase{a b g d e z h j i k l m n x o p r s t u f q y w}

a b g d e z h j i k l m n x o p r sv t u f q y w

\textAlpha{} \textBeta{} \textGamma{} \textDelta{} \textEpsilon{}
\textZeta{} \textEta{} \textTheta{} \textIota{} \textKappa{}
\textLambda{} \textMu{} \textNu{} \textXi{} \textOmicron{} \textPi{}
\textRho{} \textSigma{} \textTau{} \textUpsilon{} \textPhi{}
\textChi{} \textPsi{} \textOmega{}

\textalpha{} \textbeta{} \textgamma{} \textdelta{} \textepsilon{}
\textzeta{} \texteta{} \texttheta{} \textiota{} \textkappa{}
\textlambda{} \textmu{} \textnu{} \textxi{} \textomicron{} \textpi{}
\textrho{} \textsigma{} \texttau{} \textupsilon{}
\textphi{} \textchi{} \textpsi{} \textomega{}

\Latin The small sigma is set with a different
glyph if it ends a word:

\LGR \textsigma{}      \Latin textsigma        \\
\LGR \textfinalsigma{} \Latin textfinalsigma or textvarsigma

In the Latin transcription, the letter `s' stands for \verb|\textautosigma|
which automatically chooses the glyph according to the position.

\subsection{Additional Greek symbols}

\LGR \textkoppa{}     \Latin textkoppa                 \\ % ϟ
\LGR \textqoppa{}     \Latin textqoppa (archaic koppa) \\ % ϙ
\LGR \textQoppa{}     \Latin textQoppa (archaic Koppa) \\ % Ϙ
\LGR \textstigma{}    \Latin textstigma                \\ % ϛ
\LGR \textvarstigma{} \Latin textvarstigma \\ % no separate Unicode character
\LGR \textStigma{}    \Latin textStigma (Sigma-Tau-Ligature in CB-fonts)%
\footnote{the name ``stigma'' originally applied to a medieval sigma-tau
          ligature, whose shape was confusably similar to the cursive
          digamma}                      \\ % Ϛ
\LGR \textsampi{}     \Latin textsampi  \\ % ϡ
\LGR \textSampi{}     \Latin textSampi  \\ % Ϡ
\LGR \textdigamma{} \Latin textdigamma  \\ % ϝ (\digamma used by amsmath!)
\LGR \textDigamma{} \Latin textDigamma  \\ % Ϝ
% numeral signs: http://en.wikipedia.org/wiki/Greek_numerals
\LGR \textnumeralsigngreek{}  \Latin textnumeralsigngreek (Dexia keraia) \\ % ʹ
\LGR \textnumeralsignlowergreek{} \Latin textnumeralsignlowergreek
                                         (Aristeri keraia)\\ % ͵

\Latin Mathematical notation sometimes uses variant shapes for pi ($\varpi$),
kappa (\emph{no TeX symbol available}), rho ($\varrho$), and theta
($\vartheta$). These variations have no syntactic meaning in Greek text and
are not given code-points in the LGR encoding. Some Greek text fonts use
variant shapes in place of the ``regular'' ones.

\section{Diacritics}

Capital Greek letters have Greek diacritics (except the dialytika) to the
left (instead of above) and drop them in UPPERCASE. This is implemented for
all combinations for which a pre-composed Unicode character exists (but not,
e.g., \LGR \~A\Latin).

% When a word is written entirely in capital letters, diacritics are
% never used; the word Ἢ (or), is an exception to this rule because of
% the need to distinguish it from the nominative feminine article Η.

Different conventions exist for the treatment of the sub-iota with uppercase
letters. The CB-Fonts use a capital Iota ``index''.

LaTeX standard accents (Latin, Greek, Greek Capitals)
$\mapsto$ UPPERCASE

\`{a} \'{a} \~{a} \"{a} \^{a} \={a} \H{a} \.{a} \r{a} \u{a} \v{a}
\b{a} \c{a} \d{a} \k{a}
$\mapsto$ \MakeUppercase{%
\`{a} \'{a} \~{a} \"{a} \^{a} \={a} \H{a} \.{a} \r{a} \u{a} \v{a}
\b{a} \c{a} \d{a} \k{a}
}

\LGR
\`{a} \'{a} \~{a} \"{a} \^{a} \={a} \H{a} \.{a} \r{a} \u{a} \v{a}
\b{a} \c{a} \d{a}
$\mapsto$ \MakeUppercase{%
\`{a} \'{a} \~{a} \"{a} \^{a} \={a} \H{a} \.{a} \r{a} \u{a} \v{a}
\b{a} \c{a} \d{a}
}

\`{A} \'{A} \~{A} \"{A} \^{A} \={A} \H{A} \.{A} \r{A} \u{A} \v{A}
\b{A} \c{A} \d{A}
$\mapsto$ \MakeUppercase{%
\`{A} \'{A} \~{A} \"{A} \^{A} \={A} \H{A} \.{A} \r{A} \u{A} \v{A}
\b{A} \c{A} \d{A}
}

\Latin
The comma-below (\verb|\k|) is not defined in LGR.

Additional Greek diacritics

\LGR
\<{a} \>{e} \<\`{i} \'"i \`"i \~"i \`\>{h} \'<{o}  \'>{o} \~\<{u} \~\>{w}
$\mapsto$ \MakeUppercase{%
\<{a} \>{e} \<\`{i} \'"i \`"i \~"i \`\>{h} \'<{o}  \'>{o} \~\<{u} \~\>{w}
}

% The dialytika is not used on Initial letters ("'I \"`I \~"I)
\<{A} \>{E} \<\`{I} \'"I \"`I \~"I \`\>{H} \'<{O}  \'>{O} \~\<{U} \~\>{W}
$\mapsto$ \MakeUppercase{%
\<{A} \>{E} \<\`{I} \'"I \"`I \~"I \`\>{H} \'<{O}  \'>{O} \~\<{U} \~\>{W}
}

\Latin Input variants and their conversion with MakeUppercase:%

\begin{quote}
\LGR

\~>a \>\~a \~\>{a}, \~<a \<\~a \<~a \~\<a \~<a,
\>\~{h} \~>h \>~h \>\~h \~>h \~>h|, \~<h \<\~h,
\>\~i \~>i, \~<i \<\~i, \~"i \"\~i \"~i,\\
\>\~u \~>u, \~<u \<\~u, \~"u \"\~u,
\>w, \<w, \>\~w \~>w, \~<w \<\~w.

\MakeUppercase{
\~>a \>\~a \~\>{a}, \~<a \<\~a \<~a \~\<a \~<a,
\>\~{h} \~>h \>~h \>\~h \~>h \~>h|, \~<h \<\~h,
\>\~i \~>i, \~<i \<\~i, \~"i \"\~i \"~i,\\
\>\~u \~>u, \~<u \<\~u, \~"u \"\~u,
\>w, \<w, \>\~w \~>w, \~<w \<\~w.
}

\<{\textalpha} \>{\textepsilon} \"'{\textiota} \`>\texteta{}
\'<{\textomicron} \~<{\textupsilon} \~>{\textomega}
\<{\textAlpha} \>{\textEpsilon} \"{\textIota} \`>\textEta{}
\'<{\textOmicron} \~<{\textUpsilon} \~>{\textOmega}
\\
\MakeUppercase{%
  \<{\textalpha} \>{\textepsilon} \"'{\textiota} \`\>\texteta{}
  \'<{\textomicron} \~<{\textupsilon} \~>{\textomega}.
  \<{\textAlpha} \>{\textEpsilon} \"{\textIota} \`>\textEta{}
  \'<{\textOmicron} \~<{\textUpsilon} \~>{\textOmega}
}

 \<'A \<\'A \'<A \'\<A $\mapsto$ \MakeUppercase{\<'A \<\'A \'<A \'\<A}.

\end{quote}

\Latin The tilde character can be used in combined accents.
However, in documents not defining the Babel language \emph{greek} or
\emph{polutonikogreek}, it will produce a
no-break space if converted with \verb|\MakeUppercase|:

\LGR \"~i \<~i \"~u \<~u \`>u $\mapsto$
\LGR \MakeUppercase{\"~i \<~i \"~u \<~u \`>u}
\\
\Latin Use the tilde-accent macro:
\LGR "\~i \~"u $\mapsto$ \MakeUppercase{\"\~i \~"u}.

\Latin Accent macros can start with \verb|\a| instead of \verb|\| when the
short form is redefined, e.\,g. inside a \emph{tabbing} environment.
This also works for the new-defined Dasia and Psili shortcuts:
\LGR \a<\textalpha{} \a>\textomega.

\Latin Combinations with named accents:
\LGR \accdasia'a \accdasia`a \accdasia\~a.

\Latin The dialytika must be kept in UPPERCASE, e.\,g.
% from http://diacritics.typo.cz/index.php?id=70 μαΐστρος -> ΜΑΪΣΤΡΟΣ.
\LGR ma\"'istros $\mapsto$ \MakeUppercase{ma\"'istros}
\Latin or % from teubner  εὐζωΐα -> ΕΥΖΩΪΑ.
\LGR e\>uzw\'"ia $\mapsto$ \MakeUppercase{e\>uzw\'"ia}.

\Latin This is implemented for all input variants of diacritics with
dialytika:

\LGR \"i \"'i \"`i \"\~i \"u \"'u \"`u \"\~u $\mapsto$
\MakeUppercase{\"i \"'i \"`i \"\~i \"u \"'u \"`u \"\~u},

\Latin
Tonos and dasia mark a \emph{hiatus} (break-up of a diphthong) if
placed on the first vowel of a diphthong ({\LGR \'ai, \'au, \'ei}). A
dialytika must be placed on the second vowel if they are dropped: \LGR
(\MakeUppercase{\'ai, \'au, \'ei}).

% from teubner: άυλος/ΑΫΛΟΣ
\'aulos $\mapsto$ \MakeUppercase{\'aulos},
\>'aulos $\mapsto$ \MakeUppercase{\>'aulos},
% from http://diacritics.typo.cz/index.php?id=69  μάινα -> ΜΑΪΝΑ
m\'aina $\mapsto$ \MakeUppercase{m\'aina},
% from  http://de.wikipedia.org/wiki/Neugriechische_Orthographie#Das_Trema
% κέικ, ἀυπνία/αϋπνία
k\'eik, $\mapsto$ \MakeUppercase{k\'eik}
\>aupn\'ia $\mapsto$ \MakeUppercase{\>aupn\'ia}

\Latin Test the auto-hiatus feature for side-effects:

\LGR \MakeUppercase{\'a b}: \Latin keep space after A.

\LGR
\newcommand\md{\textcompwordmark}
\newcommand\MU{\MakeUppercase}

  \md \MU{ AO    AY    AI    AU    RA    OA    UA    DU}    [ \\
\<\md \MU{ \<AO  \<AY  \<AI  \<AU  \<RA  \<OA  U\<A  D\<U}  [ \\
\>\md \MU{ \>AO  \>AY  \>AI  \>AU  \>RA  \>OA  U\>A  D\>U}  [ \\
\>'\md\MU{ \>'AO \>'AY \>'AI \>'AU \>'RA \>'OA U\>'A D\>'U} [ \\
\'\md \MU{ \'AO  \'AY  \'AI  \'AU  \'RA  \'OA  U\'A  D\'U}  [ \\
\>`\md\MU{ \>`AO \>`AY \>`AI \>`AU \>`RA \>`OA U\>`A D\>`U} [ \\
\<'\md\MU{ \<'AO \<'AY \<'AI \<'AU \<'RA \<'OA U\<'A D\<'U} [ \\
\`\md \MU{ \`AO  \`AY  \`AI  \`AU  \`RA  \`OA  U\`A  D\`U}  [ \\
\<`\md\MU{ \<`AO \<`AY \<`AI \<`AU \<`RA \<`OA U\<`A D\<`U} [ \\
\~\md \MU{ \~AO  \~AY  \~AI  \~AU  \~RA  \~OA  U\~A  D\~U}  [ \\
\~>\md\MU{ \~>AO \~>AY \~>AI \~>AU \~>RA \~>OA U\~>A D\~>U} [ \\
\~<\md\MU{ \~<AO \~<AY \~<AI \~<AU \~<RA \~<OA U\~<A D\~<U} [ \\
\~<\md\MU{ \~<ao \~<ay \~<ai \~<au \~<ra \~<oa u\~<a d\~<u} [ \\
\"\md \MU{ AO    AY    A\"I  A\"U  RA    OA    \"UA  DU}    [ \\
\"\md \MU{ \"AO  \"AY  \"AI  \"AU  \"RA  \"OA  U\"A  D\"U}  [ \\
\"~\md\MU{ \~"AO \~"AY \~"AI \~"AU \~"RA \~"OA U\~"A D\~"U} [ \\


\Latin
Rows 3 \ldots 7: Look-ahead (to check for a hiatus) breaks kerning before A
with Tonos or Psili.

% \'AA \'AB \'AG \'AD \'AE \'AZ \'AH \'AJ \'AI \'AK \'AL \'AM \'AN \'AX
% \'AO \'AP \'AR \'AS \'AC \'AT \'AU \'AF \'AQ \'AY \'AW

Rows 15 and 16: Like in any font encoding, there is no kerning for
non-defined accent-letter-combinations (dialytica on \LGR A O D\Latin).

\Latin

Downcasing should keep diacritics (of course, it cannot regenerate
``manually" dropped ones):
\LGR 'A \"I \"U \~<A $\mapsto$ \MakeLowercase{\'A \"I \"U \~<A}

\end{document}