text-hyphen 1.4.1 → 1.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.standard.yml +5 -0
- data/Code-of-Conduct.md +73 -0
- data/Contributing.md +68 -0
- data/History.md +139 -0
- data/Licence.md +159 -0
- data/Manifest.txt +12 -5
- data/README.md +81 -0
- data/Rakefile +68 -19
- data/bin/ruby-hyphen +0 -0
- data/lib/text/hyphen/language/1.8/de1.rb +1307 -571
- data/lib/text/hyphen/language/1.8/en_us.rb +412 -453
- data/lib/text/hyphen/language/1.8/fr.rb +128 -334
- data/lib/text/hyphen/language/1.8/la.rb +1 -0
- data/lib/text/hyphen/language/1.8/lt.rb +115 -0
- data/lib/text/hyphen/language/1.8/pt.rb +2 -1
- data/lib/text/hyphen/language/1.8/sk.rb +277 -0
- data/lib/text/hyphen/language/1.9/ca.rb +2 -1
- data/lib/text/hyphen/language/1.9/cs.rb +2 -1
- data/lib/text/hyphen/language/1.9/da.rb +2 -1
- data/lib/text/hyphen/language/1.9/de1.rb +1382 -646
- data/lib/text/hyphen/language/1.9/de2.rb +110 -109
- data/lib/text/hyphen/language/1.9/en_uk.rb +2 -1
- data/lib/text/hyphen/language/1.9/en_us.rb +412 -454
- data/lib/text/hyphen/language/1.9/es.rb +2 -1
- data/lib/text/hyphen/language/1.9/et.rb +6 -5
- data/lib/text/hyphen/language/1.9/eu.rb +4 -3
- data/lib/text/hyphen/language/1.9/fi.rb +3 -2
- data/lib/text/hyphen/language/1.9/fr.rb +136 -343
- data/lib/text/hyphen/language/1.9/ga.rb +27 -26
- data/lib/text/hyphen/language/1.9/hr.rb +6 -5
- data/lib/text/hyphen/language/1.9/hsb.rb +3 -2
- data/lib/text/hyphen/language/1.9/hu1.rb +3 -2
- data/lib/text/hyphen/language/1.9/hu2.rb +5 -4
- data/lib/text/hyphen/language/1.9/ia.rb +2 -1
- data/lib/text/hyphen/language/1.9/id.rb +8 -7
- data/lib/text/hyphen/language/1.9/is.rb +2 -1
- data/lib/text/hyphen/language/1.9/it.rb +74 -74
- data/lib/text/hyphen/language/1.9/la.rb +54 -53
- data/lib/text/hyphen/language/1.9/lt.rb +116 -0
- data/lib/text/hyphen/language/1.9/mn.rb +7 -6
- data/lib/text/hyphen/language/1.9/nl.rb +2 -1
- data/lib/text/hyphen/language/1.9/no1.rb +3 -2
- data/lib/text/hyphen/language/1.9/no2.rb +3 -2
- data/lib/text/hyphen/language/1.9/pl.rb +2 -1
- data/lib/text/hyphen/language/1.9/pt.rb +3 -2
- data/lib/text/hyphen/language/1.9/ru.rb +2 -1
- data/lib/text/hyphen/language/1.9/sk.rb +280 -0
- data/lib/text/hyphen/language/1.9/sv.rb +4 -3
- data/lib/text/hyphen/language/cs.rb +1 -1
- data/lib/text/hyphen/language/de.rb +2 -1
- data/lib/text/hyphen/language/de1.rb +1 -1
- data/lib/text/hyphen/language/de2.rb +1 -1
- data/lib/text/hyphen/language/en_us.rb +1 -1
- data/lib/text/hyphen/language/eu.rb +1 -1
- data/lib/text/hyphen/language/fr.rb +1 -1
- data/lib/text/hyphen/language/hu.rb +1 -1
- data/lib/text/hyphen/language/hu1.rb +1 -1
- data/lib/text/hyphen/language/hu2.rb +1 -1
- data/lib/text/hyphen/language/is.rb +1 -1
- data/lib/text/hyphen/language/lt.rb +4 -0
- data/lib/text/hyphen/language/ms.rb +3 -3
- data/lib/text/hyphen/language/nl.rb +1 -1
- data/lib/text/hyphen/language/no.rb +1 -1
- data/lib/text/hyphen/language/sk.rb +4 -0
- data/lib/text/hyphen/language.rb +45 -45
- data/lib/text/hyphen.rb +139 -97
- data/lib/text-hyphen.rb +1 -1
- data/test/data/bug_9807_latin1.rb +2 -2
- data/test/data/bug_9807_utf-8.rb +1 -1
- data/test/test_bugs.rb +14 -13
- data/test/test_text_hyphen.rb +31 -21
- metadata +146 -96
- data/.autotest +0 -23
- data/.gemtest +0 -0
- data/History.rdoc +0 -99
- data/License.rdoc +0 -159
- data/README.rdoc +0 -95
- data/text-hyphen.gemspec +0 -51
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Irish Gaelic
|
3
4
|
# Converted from the TeX hyphenation/gahyph.tex file, by Kevin P. Scannell
|
4
5
|
# <scannell@slu.edu> (2004).
|
@@ -13,37 +14,37 @@
|
|
13
14
|
# modify it under the terms of the GNU General Public License
|
14
15
|
# as published by the Free Software Foundation; either version 2
|
15
16
|
# of the License, or (at your option) any later version.
|
16
|
-
#
|
17
|
+
#
|
17
18
|
# This program is distributed in the hope that it will be useful,
|
18
19
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
19
20
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
20
21
|
# GNU General Public License for more details.
|
21
|
-
#
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
22
|
+
#
|
23
|
+
# %% ====================================================================
|
24
|
+
# %% @TeX-hyphen-file{
|
25
|
+
# %% author = "Kevin P. Scannell",
|
26
|
+
# %% version = "1.0",
|
27
|
+
# %% date = "23 January 2004",
|
28
|
+
# %% time = "15:46:12 CST",
|
29
|
+
# %% filename = "gahyph.tex",
|
30
|
+
# %% email = "scannell@slu.edu",
|
31
|
+
# %% codetable = "ISO/ASCII",
|
32
|
+
# %% keywords = "TeX, hyphen, Irish, Gaeilge",
|
33
|
+
# %% supported = "yes",
|
34
|
+
# %% abstract = "Hyphenation patterns for Irish (Gaeilge)",
|
35
|
+
# %% docstring = "This file contains the hyphenation patterns
|
36
|
+
# %% for the Irish language",
|
37
|
+
# %% }
|
38
|
+
# %% ====================================================================
|
38
39
|
#
|
39
40
|
# See the web page http://borel.slu.edu/fleiscin/index.html
|
40
41
|
# for more information on how these patterns were generated.
|
41
|
-
#
|
42
|
-
# Please report incorrect hyphenations to the author at the
|
42
|
+
#
|
43
|
+
# Please report incorrect hyphenations to the author at the
|
43
44
|
# email address above.
|
44
|
-
#message{Hyphenation patterns `gahyph.tex' Version 1.0 <2004/01/22>}
|
45
|
+
# message{Hyphenation patterns `gahyph.tex' Version 1.0 <2004/01/22>}
|
45
46
|
#++
|
46
|
-
require
|
47
|
+
require "text/hyphen/language"
|
47
48
|
|
48
49
|
Text::Hyphen::Language::GA = Text::Hyphen::Language.new do |lang|
|
49
50
|
lang.encoding "UTF-8"
|
@@ -593,10 +594,10 @@ veant5 vear3 vearn6 3v4ei veil5b v3eo véar6 véis5 véist6 5v6ial 3v4ini vios5
|
|
593
594
|
vir5 virg6 v6íc v3la 3vol4 volt3 vuít5 x3ac x5ai x5aí
|
594
595
|
PATTERNS
|
595
596
|
|
596
|
-
|
597
|
-
|
598
|
-
|
599
|
-
|
597
|
+
# See the web page cited above for descriptions of these ambiguities.
|
598
|
+
# These cover capitalized versions, *including* eclipsed capitals
|
599
|
+
# 2004-01-25: 46 of them coming from 23 classes modulo
|
600
|
+
# lenition/eclipsis
|
600
601
|
lang.exceptions <<-EXCEPTIONS
|
601
602
|
bhrachtaí mbrachtaí cháintí gcáintí cheiltí gceiltí chistí gcistí choirtí
|
602
603
|
gcoirtí chreataí gcreataí dhoirteá dhoirtear dhoirtí doirtear ndoirteá
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Croatian
|
3
4
|
# Converted from the TeX hyphenation/bahyph.tex file, by Marinovi\'c Igor
|
4
5
|
# (1994 - 1996).
|
@@ -6,19 +7,19 @@
|
|
6
7
|
# The original copyright holds and is reproduced in the source to this file.
|
7
8
|
# The Ruby version of these patterns are copyright 2004 Austin Ziegler.
|
8
9
|
#--
|
9
|
-
# Hyphenation patterns for Croatian language words for use with
|
10
|
-
# T1 encoding, which is supported in DC fonts.
|
10
|
+
# Hyphenation patterns for Croatian language words for use with
|
11
|
+
# T1 encoding, which is supported in DC fonts.
|
11
12
|
# These can also be used with OT1 encoding.
|
12
13
|
#
|
13
|
-
# The first version was realized in late 1994.
|
14
|
+
# The first version was realized in late 1994.
|
14
15
|
# Second, much more improved version was realized in the beginning of 1996.
|
15
16
|
# Date of the last change: 19.03.1996.
|
16
17
|
#
|
17
18
|
# Marinovi\'c Igor
|
18
19
|
# migor@student.math.hr
|
19
|
-
#
|
20
|
+
#
|
20
21
|
#++
|
21
|
-
require
|
22
|
+
require "text/hyphen/language"
|
22
23
|
|
23
24
|
Text::Hyphen::Language::HR = Text::Hyphen::Language.new do |lang|
|
24
25
|
encoding "UTF-8"
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Upper Sorbian
|
3
4
|
# Converted from the TeX hyphenation/bahyph.tex file, by E. Werner (1997).
|
4
5
|
#
|
@@ -12,10 +13,10 @@
|
|
12
13
|
# \message{Hyphenation patterns for Upper Sorbian, E. Werner}
|
13
14
|
# \message{Completely new revision 1997, March 22}
|
14
15
|
#++
|
15
|
-
require
|
16
|
+
require "text/hyphen/language"
|
16
17
|
|
17
18
|
Text::Hyphen::Language::HSB = Text::Hyphen::Language.new do |lang|
|
18
|
-
|
19
|
+
lang.encoding "UTF-8"
|
19
20
|
lang.patterns <<-PATTERNS
|
20
21
|
% ě
|
21
22
|
8ě
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Hungarian
|
3
4
|
# Converted from the TeX hyphenation/huhyph.tex 3.12 file,
|
4
5
|
# by MIKL\'OS Dezs\H o and MAYER Gyula from 1989 - 1998.
|
@@ -30,11 +31,11 @@
|
|
30
31
|
# MHSz10 p.8-9. földolgozatlan; cf. p.62.
|
31
32
|
#++
|
32
33
|
|
33
|
-
require
|
34
|
+
require "text/hyphen/language"
|
34
35
|
|
35
36
|
Text::Hyphen::Language::HU1 = Text::Hyphen::Language.new do |lang|
|
36
37
|
lang.encoding "UTF-8"
|
37
|
-
lang.isocode =
|
38
|
+
lang.isocode = "hu"
|
38
39
|
lang.patterns <<-PATTERNS
|
39
40
|
% 1C(s/z/y)V (V <> y)
|
40
41
|
% 1C(f/h/s/z)y occurs at the end of names, so I added some of them
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Hungarian
|
3
4
|
# Converted from the TeX hyphenation/huhyphn.tex file, by NAGY Bence
|
4
5
|
# <huhyphn@tipogral.hu>.
|
@@ -11,15 +12,15 @@
|
|
11
12
|
# Copyright (C) 2003, NAGY Bence <huhyphn@tipogral.hu>
|
12
13
|
# This file can be distributed under the terms of the
|
13
14
|
# GNU General Public License version 2.
|
14
|
-
#
|
15
|
-
|
15
|
+
#
|
16
|
+
|
16
17
|
#++
|
17
18
|
|
18
|
-
require
|
19
|
+
require "text/hyphen/language"
|
19
20
|
|
20
21
|
Text::Hyphen::Language::HU2 = Text::Hyphen::Language.new do |lang|
|
21
22
|
lang.encoding "UTF-8"
|
22
|
-
lang.isocode
|
23
|
+
lang.isocode "hu"
|
23
24
|
lang.patterns <<-PATTERNS
|
24
25
|
.a2 .adás1s .ae1 .agyon1 .al1eg .al1e2m .al1e2s .al1ér .al1is .al1os .arc1c
|
25
26
|
.ar2c3ho .atmo1 .az1a2 .az1ám .aze2 .á2 .ál1a2 .ál1e .ál1é2 .ál1i .ál1ok
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Interlingua
|
3
4
|
# Converted from the TeX hyphenation/iahyph.tex file, Version 0.2b.
|
4
5
|
# Released 3 July 2001, Created by Peter Kleiweg, kleiweg@let.rug.nl
|
@@ -16,7 +17,7 @@
|
|
16
17
|
#
|
17
18
|
# About Interlingua: http://www.interlingua.com/
|
18
19
|
#++
|
19
|
-
require
|
20
|
+
require "text/hyphen/language"
|
20
21
|
|
21
22
|
Text::Hyphen::Language::IA = Text::Hyphen::Language.new do |lang|
|
22
23
|
lang.encoding "UTF-8"
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby
|
3
4
|
# id (Indonesian) and ms (Malay)
|
4
5
|
# Converted from the TeX hyphenation/inhyph.tex file, by Jörg Knappen and
|
@@ -7,19 +8,19 @@
|
|
7
8
|
# The original copyright holds and is reproduced in the source to this file.
|
8
9
|
# The Ruby version of these patterns are copyright 2004 Austin Ziegler.
|
9
10
|
#--
|
10
|
-
# inhyph.tex
|
11
|
+
# inhyph.tex
|
11
12
|
# Version 1.3 19-SEP-1997
|
12
13
|
#
|
13
14
|
# Hyphenation patterns for bahasa indonesia (probably also usable
|
14
15
|
# for bahasa melayu)
|
15
16
|
#
|
16
17
|
# (c) Copyright 1996, 1997 Jörg Knappen and Terry Mart
|
17
|
-
#
|
18
|
-
# This patterns are free software according to the GNU General Public
|
18
|
+
#
|
19
|
+
# This patterns are free software according to the GNU General Public
|
19
20
|
# licence version 2, June 1991.
|
20
21
|
#
|
21
22
|
# Please read the GNU licence for details. If you don't receive a GNU
|
22
|
-
# licence with these patterns, you can obtain it from
|
23
|
+
# licence with these patterns, you can obtain it from
|
23
24
|
#
|
24
25
|
# Free Software Foundation, Inc.
|
25
26
|
# 675 Mass Ave, Cambridge, MA 02139, USA
|
@@ -50,7 +51,7 @@
|
|
50
51
|
# email : mart@kph.uni-mainz.de
|
51
52
|
#
|
52
53
|
#++
|
53
|
-
require
|
54
|
+
require "text/hyphen/language"
|
54
55
|
|
55
56
|
Text::Hyphen::Language::ID = Text::Hyphen::Language.new do |lang|
|
56
57
|
lang.encoding "UTF-8"
|
@@ -78,8 +79,8 @@ a2ir % ber-air
|
|
78
79
|
% Don't overload the exception list...
|
79
80
|
PATTERNS
|
80
81
|
|
81
|
-
|
82
|
-
|
82
|
+
# Exeptions to the above rules, specially words beginning in ber... and
|
83
|
+
# ter..
|
83
84
|
lang.exceptions <<-EXCEPTIONS
|
84
85
|
be-ra-be be-ra-hi be-rak be-ran-da be-ran-dal be-rang be-ra-ngas-an
|
85
86
|
be-rang-sang be-ra-ngus be-ra-ni be-ran-tak-an be-ran-tam be-ran-tas
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Icelandic
|
3
4
|
# Converted from the TeX hyphenation/bahyph.tex file, by Jorgen Pind
|
4
5
|
# (1987).
|
@@ -52,7 +53,7 @@
|
|
52
53
|
# e.g. that if one wants to use, say, umlaut marks over u or a it is
|
53
54
|
# necessary to write \" a (space before a) or \"{a} instead of PLAINS \"a.
|
54
55
|
#++
|
55
|
-
require
|
56
|
+
require "text/hyphen/language"
|
56
57
|
|
57
58
|
Text::Hyphen::Language::IS = Text::Hyphen::Language.new do |lang|
|
58
59
|
lang.encoding "UTF-8"
|
@@ -4,7 +4,7 @@
|
|
4
4
|
# The original copyright holds and is reproduced in the source to this file.
|
5
5
|
# The Ruby version of these patterns are copyright 2004 Austin Ziegler.
|
6
6
|
#--
|
7
|
-
|
7
|
+
# %%%%%%%%%%%%%%%%%%%%%%%%%% file ithyph.tex %%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
8
8
|
#
|
9
9
|
# Prepared by Claudio Beccari e-mail claudio.beccari@polito.it
|
10
10
|
#
|
@@ -30,7 +30,7 @@
|
|
30
30
|
#
|
31
31
|
# See comments at the end of the file after the \endinput line
|
32
32
|
#++
|
33
|
-
require
|
33
|
+
require "text/hyphen/language"
|
34
34
|
|
35
35
|
Text::Hyphen::Language::IT = Text::Hyphen::Language.new do |lang|
|
36
36
|
lang.encoding "UTF-8"
|
@@ -60,75 +60,75 @@ t2t3s 2tv 2tw t2z 2tzk tz2s 2t. 2t'. 2t'' 1v 2vc v2l v2r 2vv 2v. 2v'. 2v''
|
|
60
60
|
PATTERNS
|
61
61
|
end
|
62
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
|
-
|
63
|
+
# Information
|
64
|
+
# ON ITALIAN HYPHENATION
|
65
|
+
#
|
66
|
+
# I have been working on patterns for the Italian language since 1987; in
|
67
|
+
# 1992 I published
|
68
|
+
#
|
69
|
+
# C. Beccari, "Computer aided hyphenation for Italian and Modern Latin",
|
70
|
+
# TUG vol. 13, n. 1, pp. 23-33 (1992)
|
71
|
+
#
|
72
|
+
# which contained a set of patterns that allowed hyphenation for both
|
73
|
+
# Italian and Latin; a slightly modified version of the patterns published
|
74
|
+
# in the above paper is contained in LAHYPH.TEX available on the CTAN
|
75
|
+
# archives.
|
76
|
+
#
|
77
|
+
# This minor revision has been tested with an enlarged set of difficult
|
78
|
+
# Italian words so as to comply with a larger number of technical words
|
79
|
+
# with foreign roots. The overall number of patterns is slightly reduced,
|
80
|
+
# but its strength is increased. As with the previous release hyathi are
|
81
|
+
# not hyphenated in order to cope with the habits of Italian readers.
|
82
|
+
# Similarly single vowel internal syllables are avoided.
|
83
|
+
#
|
84
|
+
# As the previous versions, this new set of patterns does not contain any
|
85
|
+
# accented character so that the hyphenation algorithm behaves properly in
|
86
|
+
# both cases, that is with OT1 and T1 encodings. With the former encoding
|
87
|
+
# fonts do not contain accented characters, while with the latter accented
|
88
|
+
# characters are present and sequences such as à map directly to slot "E0
|
89
|
+
# that contains "agrave".
|
90
|
+
#
|
91
|
+
# Of course if you use T1 encoded fonts you get the full power of the
|
92
|
+
# hyphenation algorithm, while if you use OT1 encoded fonts you miss some
|
93
|
+
# possible break points; this is not a big inconvenience in Italian
|
94
|
+
# because:
|
95
|
+
#
|
96
|
+
# 1) The Regulation UNI 6015 on accents specifies that compulsory accents
|
97
|
+
# appear only on the ending vowel of oxitone words; this means that it
|
98
|
+
# is almost indifferent to have or to miss the T1 encoded fonts because
|
99
|
+
# the only difference consists in how TeX evaluates the end of the
|
100
|
+
# word; in practice if you have these special facilities you get
|
101
|
+
# "qua-li-tà", while if you miss them, you get "qua-lità" (assuming
|
102
|
+
# that \righthyphenmin > 1).
|
103
|
+
#
|
104
|
+
# 2) Optional accents are so rare in Italian, that if you absolutely want
|
105
|
+
# to use them in those rare instances, and you miss the T1 encoding
|
106
|
+
# facilities, you should also provide explicit discretionary hyphens as
|
107
|
+
# in "sé\-gui\-to".
|
108
|
+
#
|
109
|
+
# There is no explicit hyphenation exception list because these patterns
|
110
|
+
# proved to hyphenate correctly a very large set of words suitably chosen
|
111
|
+
# in order to test them in the most heavy circumstances; these patterns
|
112
|
+
# were used in the preparation of a number of books and no errors were
|
113
|
+
# discovered.
|
114
|
+
#
|
115
|
+
# Nevertheless if you frequently use technical terms that you want
|
116
|
+
# hyphenated differently from what is normally done (for example if you
|
117
|
+
# prefer etymological hyphenation of prefixed and/or suffixed words) you
|
118
|
+
# should insert a specific hyphenation list in the preamble of your
|
119
|
+
# document, for example:
|
120
|
+
#
|
121
|
+
# \hyphenation{su-per-in-dut-to-re su-per-in-dut-to-ri}
|
122
|
+
#
|
123
|
+
# If you use, as you should, the italan option of the babel package, then
|
124
|
+
# you have available the active charater " that allows you to put
|
125
|
+
# a discretionary break at a word boundary of a compound word while
|
126
|
+
# maintaning the hyphenation algorithm on the rest of the word.
|
127
|
+
#
|
128
|
+
# Please, read the babel package documentation.
|
129
|
+
#
|
130
|
+
# Should you find any word that gets hyphenated in a wrong way, please,
|
131
|
+
# AFTER CHECKING ON A RELIABLE MODERN DICTIONARY, report to the author,
|
132
|
+
# preferably by e-mail.
|
133
|
+
#
|
134
|
+
# Happy multilingual typesetting!
|
@@ -1,4 +1,5 @@
|
|
1
1
|
# -*- encoding: utf-8 -*-
|
2
|
+
|
2
3
|
# Hyphenation patterns for Text::Hyphen in Ruby: Latin
|
3
4
|
# Converted from the TeX hyphenation/lahyph.tex file, by Claudio Beccari
|
4
5
|
# (1999 - 2001).
|
@@ -44,9 +45,9 @@
|
|
44
45
|
#
|
45
46
|
# Information after \endinput.
|
46
47
|
#
|
47
|
-
#message{Latin Hyphenation Patterns `lahyph' Version 3.0b <2001/11/21>}
|
48
|
+
# message{Latin Hyphenation Patterns `lahyph' Version 3.0b <2001/11/21>}
|
48
49
|
#++
|
49
|
-
require
|
50
|
+
require "text/hyphen/language"
|
50
51
|
|
51
52
|
Text::Hyphen::Language::LA = Text::Hyphen::Language.new do |lang|
|
52
53
|
lang.encoding "UTF-8"
|
@@ -81,54 +82,54 @@ o2r1ue o2r1ui o2r1uo o2r1uu u2r1ua u2r1ue u2r1ui u2r1uo u2r1uu
|
|
81
82
|
PATTERNS
|
82
83
|
end
|
83
84
|
|
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
|
-
|
85
|
+
# For documentation see:
|
86
|
+
#
|
87
|
+
# C. Beccari, "Computer aided hyphenation for Italian and Modern Latin",
|
88
|
+
# TUG vol. 13, n. 1, pp. 23-33 (1992)
|
89
|
+
#
|
90
|
+
# see also
|
91
|
+
#
|
92
|
+
# C. Beccari, "Typesetting of ancient languages",
|
93
|
+
# TUG vol.15, n.1, pp. 9-16 (1994)
|
94
|
+
#
|
95
|
+
# In the former paper the code was described as being contained in file
|
96
|
+
# ITALAT.TEX; this is substantially the same code, but the file has been
|
97
|
+
# renamed LAHYPH.TEX in accordance with the ISO name for Latin and the
|
98
|
+
# convention that all hyphenation pattern file names should be formed by the
|
99
|
+
# agglutination of two letter language ISO code and the abbreviation HYPH.
|
100
|
+
#
|
101
|
+
# A corresponding file (ITHYPH.TEX) has been extracted in order to eliminate
|
102
|
+
# the (few) patterns specific to Latin and leave those specific to Italian;
|
103
|
+
# ITHYPH.TEX has been further extended with many new patterns in order to
|
104
|
+
# cope with the many neologisms and technical terms with foreign roots.
|
105
|
+
#
|
106
|
+
# Should you find any word that gets hyphenated in a wrong way, please, AFTER
|
107
|
+
# CHECKING ON A RELIABLE MODERN DICTIONARY, report to the author, preferably
|
108
|
+
# by e-mail. Please do not report about wrong break points concerning
|
109
|
+
# prefixes and/or suffixes; see at the bottom of this file.
|
110
|
+
#
|
111
|
+
# Compared with the previous versions, this file has been extended so as to
|
112
|
+
# cope also with the medieval Latin spelling, where the letter `V' played the
|
113
|
+
# roles of both `U' and `V', as in the Roman times, save that the Romans used
|
114
|
+
# only capitals. In the middle ages the availability of soft writing supports
|
115
|
+
# and the necessity of copying books with a reasonable speed, several scripts
|
116
|
+
# evolved in (practically) all of which there was a lower case alphabet
|
117
|
+
# different from the upper case one, and where the lower case `v' had the
|
118
|
+
# rounded shape of our modern lower case `u', and where the Latin diphthongs
|
119
|
+
# `AE' and `OE', both in upper and lower case, where written as ligatures,
|
120
|
+
# not to mention the habit of substituting them with their sound, that is a
|
121
|
+
# simple `E'.
|
122
|
+
#
|
123
|
+
# According to Leon Battista Alberti, who in 1466 wrote a book on
|
124
|
+
# cryptography where he thoroughly analyzed the hyphenation of the Latin
|
125
|
+
# language of his (still medieval) times, the differences from the Tuscan
|
126
|
+
# language (the Italian language, as it was named at his time) were very
|
127
|
+
# limited, in particular for what concerns the handling of the ascending and
|
128
|
+
# descending diphthongs; in central and northern Europe, and later on in
|
129
|
+
# North America, the Scholars perceived the above diphthongs as made of two
|
130
|
+
# distinct vowels; the hyphenation of medieval Latin, therefore, was quite
|
131
|
+
# different in the northern countries compared to the southern ones, at least
|
132
|
+
# for what concerns these diphthongs. If you need hyphenation patterns for
|
133
|
+
# medieval Latin that suite you better according to the habits of northern
|
134
|
+
# Europe you should resort to the hyphenation patterns prepared by Yannis
|
135
|
+
# Haralambous (TUGboat, vol.13 n.4 (1992)).
|