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
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
|
# -*- coding: utf-8 -*-
class Author
def initialize(name,surname,email,contacted1,contacted2)
@name = name
@surname = surname
@email = email
# this mostly means if email has been recently checked
@contacted1 = contacted1
# this means if we made more cooperation with author,
# exchanging patches etc.
@contacted2 = contacted2
end
attr_reader :name, :surname, :email
end
class Language
def initialize(language_hash)
@use_new_loader = language_hash["use_new_loader"]
@use_old_patterns = language_hash["use_old_patterns"]
@use_old_patterns_comment = language_hash["use_old_patterns_comment"]
@filename_old_patterns = language_hash["filename_old_patterns"]
@filename_old_patterns_other = language_hash["filename_old_patterns_other"]
@code = language_hash["code"]
@name = language_hash["name"]
@synonyms = language_hash["synonyms"]
@hyphenmin = language_hash["hyphenmin"]
@encoding = language_hash["encoding"]
@exceptions = language_hash["exceptions"]
@message = language_hash["message"]
@description_s = language_hash["description_s"]
@description_l = language_hash["description_l"]
@version = language_hash["version"]
@licence = language_hash["licence"]
@authors = language_hash["authors"]
@has_quotes = false
@has_dashes = false
if @synonyms==nil then @synonyms = [] end
end
def set_quotes
@has_quotes = true
end
def set_dashes
@has_dashes = true
end
# TODO: simplify this (reduce duplication)
def get_exceptions
if @exceptions1 == nil
filename = "../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex";
lines = IO.readlines(filename, '.').join("")
exceptions = lines.gsub(/%.*/,'');
if (exceptions.index('\hyphenation') != nil)
@exceptions1 = exceptions.gsub(/.*\\hyphenation\s*\{(.*?)\}.*/m,'\1').
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
else
@exceptions1 = ""
end
end
return @exceptions1
end
def get_patterns
if @patterns == nil
filename = "../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex"
lines = IO.readlines(filename, '.').join("")
@patterns = lines.gsub(/%.*/,'').
gsub(/.*\\patterns\s*\{(.*?)\}.*/m,'\1').
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
if @code == 'eo' then
@patterns = lines.gsub(/%.*/,'').
gsub(/.*\\patterns\s*\{(.*)\}.*/m,'\1').
#
gsub(/\\adj\{(.*?)\}/m,'\1a. \1aj. \1ajn. \1an. \1e.').
gsub(/\\nom\{(.*?)\}/m,'\1a. \1aj. \1ajn. \1an. \1e. \1o. \1oj. \1ojn. \1on.').
gsub(/\\ver\{(.*?)\}/m,'\1as. \1i. \1is. \1os. \1u. \1us.').
#
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
end
end
return @patterns
end
def get_comments_and_licence
if @comments_and_licence == nil then
filename = File.expand_path("../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex");
lines = IO.readlines(filename, '.').join("")
@comments_and_licence = lines.
gsub(/(.*)\\patterns.*/m,'\1')
end
return @comments_and_licence
end
# def lc_characters
# if @lc_characters == nil
# lc_characters = Hash.new
# p = self.patterns
# p.each do |pattern|
# end
# end
# return @lc_characters
# end
attr_reader :use_new_loader, :use_old_patterns, :use_old_patterns_comment, :filename_old_patterns
attr_reader :code, :name, :synonyms, :hyphenmin, :encoding, :exceptions, :message
attr_reader :description_s, :description_l, :version
attr_reader :licence, :authors
attr_reader :has_quotes, :has_dashes
# this hack is needed for Serbian
attr_writer :code
end
class Authors < Hash
@@list = []
def initialize
authors = {
#authors = {
"donald_knuth" => ["Donald", "Knuth", nil, false, false],
"peter_heslin" => ["Peter", "Heslin", nil, false, false],
"dimitrios_filippou" => ["Dimitrios", "Filippou", "dimitrios{dot}filippou{at}riotinto{dot}com", true, true],
"claudio_beccari" => ["Claudio", "Beccari","claudio{dot}beccari{at}gmail{dot}com", true, true],
"juan_aguirregabiria" => ["Juan M.", "Aguirregabiria", "juanmari{dot}aguirregabiria{at}ehu.es", true, true],
"igor_marinovic" => ["Igor", "Marinović", "marinowski{at}gmail.com", true, true],
"tilla_fick" => ["Tilla", "Fick", "fick{dot}tilla{at}gmail{dot}com", true, true],
"chris_swanepoel" => ["Chris", "Swanepoel", "cj{at}swanepoel{dot}net", true, true],
"matjaz_vrecko" => ["Matjaž", "Vrečko", "matjaz{at}mg-soft{dot}si", true, true],
"goncal_badenes" => ["Gonçal", "Badenes", "g{dot}badenes{at}ieee.org", false, false],
"pavel_sevecek" => ["Pavel", "Ševeček", "pavel{at}lingea{dot}cz", false, false],
# email doesn't work
"jana_chlebikova" => ["Jana", "Chlebíková", "chlebikj{at}dcs{dot}fmph{dot}uniba{dot}sk", false, false],
"yannis_haralambous" => ["Yannis", "Haralambous", "yannis{dot}haralambous{at}telecom-bretagne{dot}eu", true, false],
"frank_jensen" => ["Frank", "Jensen", "frank{dot}jensen{at}hugin{dot}com", true, true],
"sergei_pokrovsky" => ["Sergei", "Pokrovsky", "sergio{dot}pokrovskij{at}gmail{dot}com", true, true],
"javier_bezos" => ["Javier", "Bezos", "jbezos{at}tex-tipografia{dot}com", true, true],
"een_saar" => ["Enn", "Saar", "saar{at}aai{dot}ee", false, false],
"dejan_muhamedagic" => ["Dejan", "Muhamedagić", "dejan{at}hello-penguin{dot}com", true, true],
"brian_wilson" => ["Brian", "Wilson", "bountonw{at}gmail{dot}com", true, true],
"arthur_reutenauer" => ["Arthur", "Reutenauer", "arthur{dot}reutenauer{at}normalesup{dot}org", true, true],
"mojca_miklavec" => ["Mojca", "Miklavec", "mojca{dot}miklavec{dot}lists{at}gmail{dot}com", true, true],
"santhosh_thottingal" => ["Santhosh", "Thottingal", "santhosh{dot}thottingal{at}gmail{dot}com>", true, true],
# email doesn't work
"yves_codet" => ["Yves", "Codet", "ycodet{at}club-internet{dot}fr", true, true],
"rune_kleveland" => ["Rune", "Kleveland", nil, false, false],
# email doesn't work
"ole_michael_selberg" => ["Ole Michael", "Selberg", "o{dot}m{dot}selberg{at}c2i{dot}net", true, true],
"dorjgotov_batmunkh" => ["Dorjgotov", "Batmunkh", "bataak{at}gmail{dot}com", true, true],
"nazar_annagurban" => ["Nazar", "Annagurban", "nazartm{at}gmail{dot}com", false, false],
"jan_michael_rynning" => ["Jan Michael", "Rynning", nil, false, false],
"eduard_werner" => ["Eduard", "Werner", "edi{dot}werner{at}gmx{dot}de", false, false],
"werner_lemberg" => ["Werner", "Lemberg", "wl{at}gnu{dot}org", true, true],
# email doesn't work
"pedro_j_de_rezende" => ["Pedro J.", "de Rezende", "rezende{at}ddc{dot}unicamp{dot}br", false, false],
"j_joao_dias_almeida" => ["J. Joao", "Dias Almeida", "jj{at}di{dot}uminho{dot}pt"],
# email doesn't work
"piet_tutelaers" => ["Piet", "Tutelaers", "p{dot}t{dot}h{dot}tutelaers{at}tue{dot}nl", false, false],
"vytas_statulevicius" => ["Vytas", "Statulevičius", "vytas{at}vtex{dot}nl", false, false],
"sigitas_tolusis" => ["Sigitas", "Tolušis", "sigitas{at}vtex{dot}lt", false, false],
"janis_vilims" => ["Janis", "Vilims", "jvilims{at}apollo{dot}lv", false, false],
"joerg_knappen" => ["Jörg", "Knappen", "jknappen{at}web{dot}de", true, true],
"medeni_shemde" => ["Medeni", "Shemdê", nil, false, false],
"terry_mart" => ["Terry", "Mart", "mart{at}kph{dot}uni-mainz{dot}de", false, false],
# email doesn't work
"jorgen_pind" => ["Jorgen", "Pind", "jorgen{at}lexis{dot}hi{dot}is", false, false],
"marteinn_sverrisson" => ["Marteinn", "Sverrisson", nil, false, false],
# email doesn't work
"kristinn_gylfason" => ["Kristinn", "Gylfason", "kristgy{at}ieee{dot}org", false, false],
# email doesn't work
"kevin_p_scannell" => ["Kevin P.", "Scannell", "scanell{at}slu{dot}edu", false, false],
# email doesn't work
"peter_kleiweg" => ["Peter", "Kleiweg", "p{dot}c{dot}c{dot}kleiweg{at}rug{dot}nl", false, false],
"hanna_kolodziejska" => ["Hanna", "Kołodziejska", nil, false, false],
"boguslaw_jackowski" => ["Bogusław", "Jackowski", nil, true, true],
"marek_rycko" => ["Marek", "Ryćko", nil, false, false],
"vladimir_volovich" => ["Vladimir", "Volovich", nil, true, true], # TODO add e-mail address
"alexander_i_lebedev" => ["Alexander I.", "Lebedev", "swan{at}scon155{dot}phys{dot}msu{dot}su", false, false], # Not sure were 'I' belongs
# first email doesn't work
"maksym_polyakov" => ["Maksym", "Polyakov", "polyama{at}auburn{dot}edu", false, false], # Second e-mail address in ukrhypmp.tex: mpoliak@i.com.ua
"adrian_rezus" => ["Adrian", "Rezus", "adriaan{at}\{sci,cs\}{dot}kun{dot}nl", false, false],
# email doesn't work
"sahak_petrosyan" => ["Sahak", "Petrosyan", "sahak{at}mit{dot}edu", true, true], # I think "true, true" is right. Arthur
"dominik_wujastyk" => ["Dominik", "Wujastyk", "wujastyk{at}gmail{dot}com", false, false],
"graham_toal" => ["Graham", "Toal", nil, false, false],
"donald_e_knuth" => ["Donald E.", "Knuth", nil, false, false], # Don doesn't use e-mail ;-)
"gerard_d_c_kuiken" => ["Gerard D.C.", "Kuiken", nil, false, false],
"pierre_mackay" => ["P. A.", "MacKay", nil, true, true],
"h_turgut_uyar" => ["H. Turgut", "Uyar", "uyar{at}itu{dot}edu{tr}", true, true],
# email doesn't work
"s_ekin_kocabas" => ["S. Ekin", "Kocabas", "kocabas{at}stanford{dot}edu", true, true],
"bence_nagy" => ["Bence", "Nagy", "nagybence{at}tipogral{dot}hu", true, true],
"kauko_saarinen" => ["Kauko", "Saarinen", nil, false, false],
"fred_karlsson" => ["Fred", "Karlsson", nil, false, false],
"rene_bastian" => ["René", "Bastian", nil, false, false], # TODO make contact
"daniel_flipo" => ["Daniel", "Flipo", nil, false, false], # TODO make contact
"bernard_gaulle" => ["Bernard", "Gaulle", nil, false, false], # Deceased...
"theppitak_karoonboonyanan" => ["Theppitak", "Karoonboonyanan", "theppitak{at}gmail{dot}com", true, true],
"levan_shoshiashvili" => ["Levan", "Shoshiashvili", "shoshia{at}hotmail{dot}com", true, true],
# email doesn't work
"javier_mugica" => ["Javier", "Múgica", "javier{at}digi21{dot}eu", true, true],
"georgi_boshnakov" => ["Georgi", "Boshnakov", "georgi{dot}boshnakov{at}manchester{dot}ac{dot}uk", true, true],
"mike_kroutikov" => ["Mike", "Kroutikov", "pgmmpk{at}gmail{dot}com", true, true],
"aleksandr_andreev" => ["Aleksandr", "Andreev", "", true, true],
"maksim_salau" => ["Maksim", "Salau", "maksim{dot}salau{at}gmail{dot}com", true, false],
"wie_ming_ang" => ["Wie-Ming", "Cittānurakkho Bhikkhu", "wiemingang{at}gmail{dot}com", true, true]
}
#
authors.each do |a|
author = Author.new(a[1][0], a[1][1], a[1][2], a[1][3], a[1][4])
@@list.push(author)
self[a[0]] = author
end
end
end
# "use_new_loader"
# => true - create a new file and use that one
# => false - use "filename_old_patterns" in language.dat
# "filename_old_patterns"
# => [string] - the name used in language.dat if "use_new_loader" is false
# "eightbitfilename"
# => [string] - if set, load another file for 8-bit engines
# "code"
# => [string] - used in filenames, needs to conform to the standard
# "name"
# => [string] -
# "synonyms" => [],
# "hyphenmin" => [],
# "encoding" => nil,
# "exceptions" => false,
# "message" => nil,
class Languages < Hash
@@list = []
def initialize
languages = [
# --------------------------------------
# languages with no hyphenation patterns
# --------------------------------------
# arabic
{
"code" => "ar",
"name" => "arabic",
"use_new_loader" => false,
"use_old_patterns" => false,
"filename_old_patterns" => "zerohyph.tex",
# "hyphenmin" => [], # not needed
"encoding" => nil,
"exceptions" => false,
"message" => nil,
# TODO
"description_s" => "(No) Arabic hyphenation patterns",
"description_l" => [
#......................................................................#
"Prevent hyphenation in Arabic.",
],
},
# farsi
# =persian
{
"code" => "fa",
"name" => "farsi", "synonyms" => ["persian"],
"use_new_loader" => false,
"use_old_patterns" => false,
"filename_old_patterns" => "zerohyph.tex",
# "hyphenmin" => [], # not needed
"encoding" => nil,
"exceptions" => false,
"message" => nil,
# TODO
"description_s" => "(No) Persian hyphenation patterns",
"description_l" => [
#......................................................................#
"Prevent hyphenation in Persian.",
],
},
# -------------------------------
# special patterns, not converted
# -------------------------------
# ibycus ibyhyph.tex
{
"code" => "grc-x-ibycus",
"name" => "ibycus",
"use_new_loader" => false,
"use_old_patterns" => true,
"filename_old_patterns" => "ibyhyph.tex",
"hyphenmin" => [2,2],
"encoding" => nil,
"exceptions" => false,
"message" => "Ancient Greek hyphenation patterns for Ibycus encoding (v3.0)",
# "authors" => ["peter_heslin"],
"version" => 3.0,
},
# ----------------------------
# languages using old patterns
# ----------------------------
# greek
# =polygreek
{
"code" => "el-polyton",
"name" => "greek", "synonyms" => ["polygreek"],
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grphyph5.tex",
# left/right hyphen min for Greek can be as low as one (1),
# but for aesthetic reasons keep them at 2/2.
# Dimitrios Filippou
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
"message" => "Hyphenation patterns for multi-accent (polytonic) Modern Greek",
"version" => "5.0",
"last_modified" => "2008-06-06",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Polytonic Modern Greek hyphenation patterns",
# # #.....................................................................#
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Modern Greek in polytonic spelling.",
# "The pattern file used for 8-bit engines is grphyph5.tex that is",
# "not part of hyph-utf8. Patterns in UTF-8 use two code positions for",
# "each of the vowels with acute accent (a.k.a tonos, oxia), e.g.,",
# "U+03AC, U+1F71 for alpha.",
# ],
},
# monogreek
{
"code" => "el-monoton",
"name" => "monogreek",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grmhyph5.tex",
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
"message" => "Hyphenation patterns for uni-accent (monotonic) Modern Greek",
"version" => "5.0",
"last_modified" => "2008-06-06",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Monotonic Modern Greek hyphenation patterns",
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Modern Greek in monotonic spelling.",
# "The pattern file used for 8-bit engines is grmhyph5.tex, in Babel's LGR encoding,",
# "that is not part of hyph-utf8.",
# "Patterns in UTF-8 use two code positions for each of the vowels with acute accent",
# "(a.k.a tonos, oxia), e.g., U+03AD, U+1F73 for epsilon.",
# ],
"description_s" => "Modern Greek hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Modern Greek in monotonic and polytonic",
"spelling in LGR and UTF-8 encodings. Patterns in UTF-8 use two code",
"positions for each of the vowels with acute accent (a.k.a tonos,",
"oxia), e.g., U+03AC, U+1F71 for alpha.",
],
},
# ancientgreek
{
"code" => "grc",
"name" => "ancientgreek",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grahyph5.tex",
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => false,
"message" => "Hyphenation patterns for Ancient Greek",
"version" => "5.0",
"last_modified" => "2016-05-12",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Ancient Greek hyphenation patterns",
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Ancient Greek.",
# "The pattern file used for 8-bit engines is grahyph5.tex, in Babel's LGR encoding,",
# "that is not part of hyph-utf8.",
# "Patterns in UTF-8 use two code positions for each of the vowels with acute accent",
# "(a.k.a tonos, oxia), e.g., U+03AE, U+1F75 for eta.",
# ],
"description_s" => "Ancient Greek hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Ancient Greek in LGR and UTF-8 encodings,",
"including support for (obsolete) Ibycus font encoding.",
"Patterns in UTF-8 use two code positions for each of the vowels with",
"acute accent (a.k.a tonos, oxia), e.g., U+03AE, U+1F75 for eta.",
],
},
# coptic
{
"code" => "cop",
"name" => "coptic",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "TODO: automatic conversion could be done, but was too complicated; leave for later.",
"filename_old_patterns" => "copthyph.tex",
"hyphenmin" => [1,1], # polyglossia TODO: no documentation found
"encoding" => nil,
"exceptions" => false,
"message" => "Coptic hyphenation patterns",
"version" => nil,
"last_modified" => "2004-10-03",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "LPPL",
"description_s" => "Coptic hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Coptic in UTF-8 encoding",
"as well as in ASCII-based encoding for 8-bit engines.",
"The latter can only be used with special Coptic fonts (like CBcoptic).",
"The patterns are considered experimental.",
],
},
# german
{
"code" => "de-1901",
"name" => "german",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Kept for the sake of backward compatibility, but newer and better patterns by WL are available.",
"filename_old_patterns" => "dehypht.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (traditional orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_s" => "German hyphenation patterns in traditional spelling",
# "description_l" => [
# "Hyphenation patterns for German in traditional spelling, in T1/EC and UTF-8 encoding.",
# "Patterns encoded in UTF-8 are provided by a separate package.",
# ],
"description_s" => "German hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for German in T1/EC and UTF-8 encodings,",
"for traditional and reformed spelling, including Swiss German.",
"The package includes the latest patterns from dehyph-exptl",
"(known to TeX under names 'german', 'ngerman' and 'swissgerman'),",
"however 8-bit engines still load old versions of patterns",
"for 'german' and 'ngerman' for backward-compatibility reasons.",
"Swiss German patterns are suitable for Swiss Standard German",
"(Hochdeutsch) not the Alemannic dialects spoken in Switzerland",
"(Schwyzerduetsch).",
"There are no known patterns for written Schwyzerduetsch.",
]
},
# ngerman
{
"code" => "de-1996",
"name" => "ngerman",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Kept for the sake of backward compatibility, but newer and better patterns by WL are available.",
"filename_old_patterns" => "dehyphn.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (reformed orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_s" => "German hyphenation patterns in reformed spelling",
# "description_l" => [
# "Hyphenation patterns for German in reformed spelling, in T1/EC and UTF-8 encoding.",
# "Patterns encoded in UTF-8 are provided by a separate package.",
# ],
},
# swissgerman
{
"code" => "de-ch-1901",
"name" => "swissgerman",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Swiss-German hyphenation patterns (traditional orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_l" => "German hyphenation patterns, traditional spelling in Switzerland.",
# "description_s" => [
# "Hyphenation patterns for German in traditional spelling as used in Switzerland, in T1/EC and UTF-8.",
# "These patterns are suitable for Standard German (Hochdeutsch), not the Alemannic dialects",
# "spoken in Switzerland (Schwyzerdütsch). There are no patterns for written Schwyzerdütsch",
# "we know of.",
# ],
},
# russian
{
"code" => "ru",
"name" => "russian",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "The old system allows choosing patterns and encodings manually. That mechanism needs to be implemented first in this package, so we still fall back on old system.",
"filename_old_patterns" => "ruhyphen.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => false,
"message" => "Russian hyphenation patterns",
"version" => nil,
"last_modified" => "2003-03-10", # Date of the patterns proper, not the support files
"type" => "dictionary",
"authors" => ["alexander_i_lebedev", "werner_lemberg", "vladimir_volovich"],
"licence" => "LPPL",
"description_s" => "Russian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Russian in T2A and UTF-8 encodings.",
"For 8-bit engines, the 'ruhyphen' package provides a number of",
"different pattern sets, as well as different (8-bit) encodings, that",
"can be chosen at format-generation time. The UTF-8 version only",
"provides the default pattern set. A mechanism similar to the one used",
"for 8-bit patterns may be implemented in the future.",
],
},
# ukrainian
{
"code" => "uk",
"name" => "ukrainian",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "The old system allows choosing patterns and encodings manually. That mechanism needs to be implemented first in this package, so we still fall back on old system.",
"filename_old_patterns" => "ukrhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => false,
"message" => "Ukrainian hyphenation patterns",
"version" => nil,
"last_modified" => "2001-05-10", # Date of the patterns proper
# "type" => "rules", # TODO: it is not really clear
"authors" => ["maksym_polyakov", "werner_lemberg", "vladimir_volovich"],
"licence" => "LPPL",
"description_s" => "Ukrainian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Ukrainian in T2A and UTF-8 encodings.",
"For 8-bit engines, the 'ukrhyph' package provides a number of",
"different pattern sets, as well as different (8-bit) encodings, that",
"can be chosen at format-generation time. The UTF-8 version only",
"provides the default pattern set. A mechanism similar to the one used",
"for 8-bit patterns may be implemented in the future.",
],
},
# ----------------------------
# languages using new patterns
# ----------------------------
# afrikaans
{
"code" => "af",
"name" => "afrikaans",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [1,2], # in babel: 2,2
"encoding" => "ec",
"exceptions" => true,
"message" => "Afrikaans hyphenation patterns",
"version" => "1.0",
"last_modified" => "2013-10-08",
"type" => "dictionary",
"authors" => [ "tilla_fick", "chris_swanepoel" ],
"email" => [ "hyphen{at}rekenaar{dot}net" ],
"licence" => "LPPL",
"description_s" => "Afrikaans hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Afrikaans in T1/EC and UTF-8 encodings.",
"OpenOffice includes older patterns created by a different author,",
"but the patterns packaged with TeX are considered superior in quality.",
# "Word list used to generate patterns with opatgen might be released in future.",
],
},
# catalan
{
"code" => "ca",
"name" => "catalan",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "cahyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Catalan hyphenation patterns",
"version" => "1.11",
"last_modified" => "2003-07-15",
"type" => "rules", # not only rules, also patgen, but it is a good approximation
"authors" => [ "goncal_badenes" ],
"licence" => "LPPL",
"description_s" => "Catalan hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Catalan in T1/EC and UTF-8 encodings.",
],
},
# czech
{
"code" => "cs",
"name" => "czech",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "czhyph.tex",
"filename_old_patterns_other" => ["czhyphen.tex","czhyphen.ex"],
# Both Czech and Slovak: \lefthyphenmin=2, \righthyphenmin=3
# Typographical rules allow \righthyphenmin=2 when typesetting in a
# narrow column (newspapers etc.).
# (used to be 2,2)
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => true,
"message" => "Czech hyphenation patterns (Pavel Sevecek, v3, 1995)",
"version" => "3",
# guessing based on CTAN/macros/cstex/base/csplain.tar.gz:
# 1998-12-17 (patterns)
# 1995-08-23 (exceptions)
# but patterns claim 1995
"last_modified" => "1995", # todo: no date
"type" => "dictionary",
"authors" => [ "pavel_sevecek" ],
"licence" => "GPL",
"description_s" => "Czech hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Czech in T1/EC and UTF-8 encodings.",
"Original patterns 'czhyphen' are still distributed in the 'csplain'",
"package and loaded with ISO Latin 2 encoding (IL2).",
# however hyph-utf8 could also be used for that
],
},
# slovak
{
"code" => "sk",
"name" => "slovak",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "skhyph.tex",
"filename_old_patterns_other" => ["skhyphen.tex","skhyphen.ex"],
# see czech
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => true,
"message" => "Slovak hyphenation patterns (Jana Chlebikova, 1992)",
"version" => "2",
"last_modified" => "1992-04-24",
"type" => "dictionary",
"authors" => [ "jana_chlebikova" ],
"licence" => "GPL",
"description_s" => "Slovak hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Slovak in T1/EC and UTF-8 encodings.",
"Original patterns 'skhyphen' are still distributed in the 'csplain'",
"package and loaded with ISO Latin 2 encoding (IL2).",
# however hyph-utf8 could also be used for that
],
},
# welsh
{
"code" => "cy",
"name" => "welsh",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "cyhyph.tex",
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => false,
"message" => "Welsh hyphenation patterns",
"version" => nil,
"last_modified" => "1996",
"type" => "dictionary",
"authors" => [ "yannis_haralambous" ],
"licence" => "LPPL",
"description_s" => "Welsh hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Welsh in T1/EC and UTF-8 encodings.",
],
},
# danish
{
"code" => "da",
"name" => "danish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "dkhyph.tex",
"filename_old_patterns_other" => ["dkcommon.tex", "dkspecial.tex"],
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Danish hyphenation patterns",
"version" => nil,
"last_modified" => "2011-01-11",
"type" => "dictionary",
"authors" => [ "frank_jensen" ],
"licence" => "LPPL",
"description_s" => "Danish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Danish in T1/EC and UTF-8 encodings.",
],
},
# esperanto
{
"code" => "eo",
"name" => "esperanto",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "eohyph.tex",
"hyphenmin" => [2,2],
"encoding" => "il3", # TODO
"exceptions" => false,
"message" => "Esperanto hyphenation patterns",
"version" => nil,
"last_modified" => "1999-08-10",
"type" => "rules",
"authors" => [ "sergei_pokrovsky" ],
"licence" => "LPPL",
"description_s" => "Esperanto hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Esperanto ISO Latin 3 and UTF-8 encodings.",
"Note that TeX distributions don't ship any suitable fonts in Latin 3",
"encoding, so unless you create your own font support or want to use",
"MlTeX, using native Unicode engines is highly recommended.",
# "Hyphenation patterns for Esperanto ISO Latin 3 and UTF-8 encodings.",
# "Note that TeX distributions usually don't ship any suitable fonts in",
# "Latin 3 encoding, so unless you create your own font support or want",
# "to use MlTeX, using native UTF-8 engines is highly recommended.",
],
},
# spanish
# =espanol
{
"code" => "es",
"name" => "spanish", "synonyms" => ["espanol"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "eshyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Spanish hyphenation patterns",
"version" => "4.7",
"last_modified" => "2015-11-12",
"type" => "dictionary",
"authors" => [ "javier_bezos" ],
"licence" => "MIT/X11",
"description_s" => "Spanish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Spanish in T1/EC and UTF-8 encodings.",
],
},
# basque
{
"code" => "eu",
"name" => "basque",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "bahyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Basque hyphenation patterns",
"version" => nil,
"last_modified" => "2008-06-26",
"type" => "rules",
"authors" => [ "juan_aguirregabiria" ],
"licence" => "other-free", # "public-check",
"description_s" => "Basque hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Basque in T1/EC and UTF-8 encodings.",
# "Generating scripts for these rule-based patterns is included in hyph-utf8."
],
},
# french
# =patois
# =francais
{
"code" => "fr",
"name" => "french", "synonyms" => ["patois","francais"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "frhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "French hyphenation patterns",
"version" => "2.13",
"last_modified" => "2016-05-12",
"type" => "rules",
"authors" => ["daniel_flipo", "bernard_gaulle", "arthur_reutenauer"],
"email" => ["cesure-l{at}gutenberg{dot}eu{dot}org"],
"licence" => "MIT",
"description_s" => "French hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for French in T1/EC and UTF-8 encodings.",
]
},
# galician
{
"code" => "gl",
"name" => "galician",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "glhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Galician hyphenation patterns",
"version" => "2.4",
"last_modified" => "2010-04-23",
"type" => "rules",
"authors" => ["javier_mugica"],
"licence" => "LPPL", # Status maintained
"description_s" => "Galician hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Galician in T1/EC and UTF-8 encodings.",
# "Generated automatically from the mkpattern utility.",
]
},
# estonian
{
"code" => "et",
"name" => "estonian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "ethyph.tex",
"hyphenmin" => [2,3], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Estonian hyphenation patterns",
"version" => nil,
"last_modified" => "2004-04-13",
"type" => "dictionary",
"authors" => [ "een_saar" ],
"licence" => "LPPL|MIT", # Dual MIT-LPPL
"description_s" => "Estonian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Estonian in T1/EC and UTF-8 encodings.",
],
},
# finnish
{
"code" => "fi",
"name" => "finnish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "fihyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Finnish hyphenation patterns",
"version" => "2.2",
"last_modified" => "1989-03-08",
"type" => "rules",
"authors" => ["kauko_saarinen", "fred_karlsson"],
"licence" => "other-free",
"description_s" => "Finnish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Finnish in T1/EC and UTF-8 encodings.",
],
},
# croatian
{
"code" => "hr",
"name" => "croatian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "hrhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Croatian hyphenation patterns",
"version" => nil,
"last_modified" => "1996-03-19",
"type" => "dictionary",
"authors" => [ "igor_marinovic" ],
"licence" => "LPPL",
"description_s" => "Croatian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Croatian in T1/EC and UTF-8 encodings.",
],
},
# hungarian
{
"code" => "hu",
"name" => "hungarian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "huhyphn.tex",
"hyphenmin" => [2,2], # polyglossia
"encoding" => "ec",
"exceptions" => false,
"message" => "Hungarian hyphenation patterns (v20110815)",
# https://github.com/nagybence/huhyphn/
"version" => "v20110815",
"last_modified" => "2011-08-15", # actually, it is "2009-06-12" or older for contents; we probably want to check/fix this
"type" => "dictionary",
"authors" => ["bence_nagy"],
"licence" => "MPL 1.1/GPL 2.0/LGPL 2.1", # TODO
"description_s" => "Hungarian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Hungarian in T1/EC and UTF-8 encodings.",
# TODO: same comment as for Irish: I'm slightly reluctant to put URL addresses here.
"From https://github.com/nagybence/huhyphn/."
],
},
# armenian
# Sahak Petrosyan <sahak at mit dot edu>
{
"code" => "hy",
"name" => "armenian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [1,2], # taken from Hyphenator.js; check the value
"encoding" => nil,
"exceptions" => false,
"message" => "Armenian hyphenation patterns",
"version" => nil,
"last_modified" => "2010-05",
"type" => "rules",
"authors" => ["sahak_petrosyan"],
"licence" => "LGPL",
"description_s" => "Armenian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Armenian for Unicode engines.",
# "Auto-generated from a script included in hyph-utf8.",
],
},
# interlingua
{
"code" => "ia",
"name" => "interlingua",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "iahyphen.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for Interlingua",
"version" => "0.2c",
"last_modified" => "2005-06-28",
"type" => "dictionary",
"authors" => ["peter_kleiweg"],
"licence" => "LPPL", # TODO Status maintained
"description_s" => "Interlingua hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Interlingua in ASCII encoding.",
],
},
# indonesian
{
"code" => "id",
"name" => "indonesian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "inhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ascii",
"exceptions" => true,
"message" => "Indonesian hyphenation patterns",
"version" => "1.3",
"last_modified" => "1997-09-19",
"type" => "rules",
"authors" => ["joerg_knappen", "terry_mart"],
"licence" => "GPL",
"description_s" => "Indonesian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Indonesian (Bahasa Indonesia) in ASCII",
"encoding. They are probably also usable for Malay (Bahasa Melayu).",
],
},
# icelandic
{
"code" => "is",
"name" => "icelandic",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "icehyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Icelandic hyphenation patterns",
"version" => nil,
"last_modified" => "2004-03-02",
"type" => "dictionary",
# TODO: I'm not sure that the last two names are relevant, I don't find the source of Marteinn Sverrisson
"authors" => ["jorgen_pind", "marteinn_sverrisson", "kristinn_gylfason"],
"licence" => "LPPL",
"description_s" => "Icelandic hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Icelandic in T1/EC and UTF-8 encodings.",
],
},
# irish
{
"code" => "ga",
"name" => "irish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "gahyph.tex",
"hyphenmin" => [2,3], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Irish hyphenation patterns",
"version" => "1.0",
"last_modified" => "2004-01-22",
"type" => "dictionary",
"authors" => ["kevin_p_scannell"],
"licence" => "GPL",
"description_s" => "Irish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Irish (Gaeilge) in T1/EC and UTF-8 encodings.",
"Visit http://borel.slu.edu/fleiscin/index.html for more information.",
# TODO: I'm slightly reluctant to put URL here
],
},
# italian
{
"code" => "it",
"name" => "italian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "ithyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ascii",
"exceptions" => false,
"message" => "Italian hyphenation patterns",
"version" => "4.9",
"last_modified" => "2014-04-22",
"type" => "rules", # TODO: we might want to check that, but it seems unlikely that patgen was used
"authors" => ["claudio_beccari"],
"licence" => "LPPL", # Status: maintained!
"description_s" => "Italian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Italian in ASCII encoding.",
# supposed to be ...
"Compliant with the Recommendation UNI 6461 on hyphenation",
"issued by the Italian Standards Institution",
"(Ente Nazionale di Unificazione UNI).",
# "Implements Recommendation UNI 6461 issued by the Italian Standards Institution",
# "(Ente Nazionale di Unificazione UNI).",
],
},
# romansh
{
"code" => "rm",
"name" => "romansh",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2], # todo
"encoding" => "ascii",
"exceptions" => false,
"message" => "Romansh hyphenation patterns",
"version" => "1.1",
"last_modified" => "2012-04-10",
"type" => "rules",
"authors" => ["claudio_beccari"],
"licence" => "LPPL", # Status: maintained!
"description_s" => "Romansh hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Romansh in ASCII encoding.",
"They are supposed to comply with the rules indicated by the Lia",
"Rumantscha (Romansh language society).",
],
},
# friulan
{
"code" => "fur",
"name" => "friulan", "synonyms" => [],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Friulan hyphenation patterns",
"version" => "1.1",
"last_modified" => "2012-04-10",
"type" => "rules",
"authors" => ["claudio_beccari"],
"licence" => "LPPL", # Status: maintained!
"description_s" => "Friulan hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Friulan in ASCII encoding.",
"They are supposed to comply with the common spelling of the",
"Friulan (Furlan) language as fixed by the Regional Law N.15/96",
"dated November 6, 1996 and its following amendments.",
],
},
# piedmontese
{
"code" => "pms",
"name" => "piedmontese",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2],
"encoding" => "ascii",
"exceptions" => false,
"message" => "Piedmontese hyphenation patterns",
"version" => "1.0",
"last_modified" => "2013-02-14",
"type" => "rules",
"authors" => ["claudio_beccari"],
"licence" => "LPPL", # Status: maintained!
"description_s" => "Piedmontese hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Piedmontese in ASCII encoding.",
"Compliant with 'Gramatica dla lengua piemonteisa' by Camillo Brero.",
],
},
# kurmanji
{
"code" => "kmr",
"name" => "kurmanji",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "kmrhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Kurmanji hyphenation patterns (v. 1.0 2009/06/29 JKn and MSh)",
"version" => "1.0",
"last_modified" => "2009-06-29",
"type" => "dictionary",
"authors" => ["joerg_knappen", "medeni_shemde"],
"licence" => "LPPL", # Status: maintained!
"description_s" => "Kurmanji hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Kurmanji (Northern Kurdish) as spoken in",
"Turkey and by the Kurdish diaspora in Europe, in T1/EC and UTF-8",
"encodings."
],
},
# latin
{
"code" => "la",
"name" => "latin",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "lahyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Latin hyphenation patterns",
"version" => "3.2a",
"last_modified" => "2014-06-04", # patterns (behaviour) last modified on 2010-06-01
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "LPPL",
"description_s" => "Latin hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Latin in T1/EC and UTF-8 encodings,",
"mainly in modern spelling (u when u is needed and v when v is needed),",
"medieval spelling with the ligatures \\ae and \\oe and the (uncial)",
"lowercase 'v' written as a 'u' is also supported. Apparently",
"there is no conflict between the patterns of modern Latin and",
"those of medieval Latin.",
],
},
# classiclatin
{
"code" => "la-x-classic",
"name" => "classiclatin",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2],
"encoding" => "ascii",
"exceptions" => false,
"message" => "Classical Latin hyphenation patterns",
"version" => "1.2",
"last_modified" => "2014-10-06",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "LPPL",
"description_s" => "Classical Latin hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for the Classical Latin in T1/EC and UTF-8",
"encodings. Classical Latin hyphenation patterns are different from",
"those of 'plain' Latin, the latter being more adapted to modern Latin.",
],
},
# liturgicallatin
{
"code" => "la-x-liturgic",
"name" => "liturgicallatin",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Liturgical Latin hyphenation patterns",
"version" => "1.040",
"last_modified" => "2016-05-19",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "MIT",
"description_s" => "Liturgical Latin hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for the Liturgical Latin in T1/EC and UTF-8",
"encodings.",
],
},
# lithuanian
{
"code" => "lt",
"name" => "lithuanian",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2],
"encoding" => "l7x",
"exceptions" => false,
"message" => "Lithuanian hyphenation patterns",
"version" => nil,
"last_modified" => "2002-11-20", # 1992-03-04, for the content?
"authors" => ["vytas_statulevicius", "yannis_haralambous", "sigitas_tolusis"],
# "licence" => "LPPL",
"description_s" => "Lithuanian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Lithuanian in L7X and UTF-8 encodings.",
# "Designed for \\lefthyphenmin and \\righthyphenmin set to 2.",
"\\lefthyphenmin and \\righthyphenmin have to be at least 2.",
# "Changing them to 1 according to grammatical rules from 1997",
# "would require to review and maybe rebuild the patterns."
],
},
# latvian
{
"code" => "lv",
"name" => "latvian",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2],
"encoding" => "l7x",
"exceptions" => false,
"message" => "Latvian hyphenation patterns",
"version" => "0.3",
"last_modified" => "2005-09-14",
"type" => "dictionary",
"authors" => ["janis_vilims"],
"licence" => "LGPL",
"description_s" => "Latvian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Latvian in L7X and UTF-8 encodings.",
],
},
# dutch
{
"code" => "nl",
"name" => "dutch",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "nehyph96.tex",
# quoting Hans Hagen:
# patterns generated with 2,2 (so don't go less) but use prefered values 2,3 (educational publishers want 4,5 -)
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => true,
"message" => "Dutch hyphenation patterns",
"version" => "1.1",
"last_modified" => "1996-11",
"type" => "dictionary",
"authors" => ["piet_tutelaers"],
"licence" => "LPPL",
"description_s" => "Dutch hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Dutch in T1/EC and UTF-8 encodings.",
# "\\lefthyphenmin and \\righthyphenmin must both be > 1.",
"These patterns don't handle cases like 'menuutje' > 'menu-tje',",
"and don't hyphenate words that have different hyphenations according",
"to their meaning."
],
},
# occitan
{
"code" => "oc",
"name" => "occitan",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Occitan hyphenation patterns",
"version" => "0.1",
"last_modified" => "2016-02-04",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "LPPL",
"description_s" => "Occitan hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Occitan in T1/EC and UTF-8 encodings.",
"They are supposed to be valid for all the Occitan variants",
"spoken and written in the wide area called 'Occitanie' by the French.",
"It ranges from the Val d'Aran within Catalunya, to the South Western",
"Italian Alps encompassing the southern half of the French pentagon.",
],
},
# polish
{
"code" => "pl",
"name" => "polish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "plhyph.tex",
#{}"hyphenmin" => [1,1],
"hyphenmin" => [2,2],
"encoding" => "qx",
"exceptions" => true,
"message" => "Polish hyphenation patterns",
"version" => "3.0a",
"last_modified" => "1995-06-17",
"type" => "dictionary",
"authors" => ["hanna_kolodziejska", "boguslaw_jackowski", "marek_rycko"],
"licence" => "public", # TODO Knuthian type
"description_s" => "Polish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Polish in QX and UTF-8 encodings.",
"These patterns are also used by Polish TeX formats MeX and LaMeX.",
],
},
# portuguese
# =portuges
{
"code" => "pt",
"name" => "portuguese", "synonyms" => ["portuges"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "pthyph.tex",
"hyphenmin" => [2,3], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Portuguese hyphenation patterns",
"version" => "1.0",
"last_modified" => "1996-07-21",
"type" => "rules", # TODO: we could create a generating script
"authors" => ["pedro_j_de_rezende", "j_joao_dias_almeida"],
"licence" => "BSD-3",
"description_s" => "Portuguese hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Portuguese in T1/EC and UTF-8 encodings.",
],
},
# pinyin
{
"code" => "zh-latn-pinyin",
"name" => "pinyin",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "pyhyph.tex",
"hyphenmin" => [1,1],
"encoding" => "ec",
"exceptions" => false,
"message" => "Hyphenation patterns for unaccented pinyin syllables (CJK 4.8.0)",
"version" => "4.8.0",
"last_modified" => "2008-05-22",
"type" => "rules", # TODO: we could create a generating script
"authors" => ["werner_lemberg"],
"licence" => "GPL",
"description_s" => "Chinese pinyin hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for unaccented transliterated Mandarin Chinese",
"(pinyin) in T1/EC and UTF-8 encodings.",
],
},
# romanian
{
"code" => "ro",
"name" => "romanian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "rohyphen.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Romanian hyphenation patterns", # : `rohyphen' 1.1 <29.10.1996>
"version" => "1.1R",
"last_modified" => "1996-11-07",
"type" => "dictionary",
"authors" => ["adrian_rezus"],
"description_s" => "Romanian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Romanian in T1/EC and UTF-8 encodings.",
"The UTF-8 patterns use U+0219 for the character 's with comma accent'",
"and U+021B for 't with comma accent', but we may consider using U+015F",
"and U+0163 as well in the future.",
# "Generated by PatGen2-output hyphen-level 9.",
],
},
# slovenian
# =slovene
{
"code" => "sl",
"name" => "slovenian", "synonyms" => ["slovene"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "sihyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Slovenian hyphenation patterns",
"version" => "2.3",
"last_modified" => "1997-15-04",
"type" => "dictionary",
"authors" => [ "matjaz_vrecko" ],
"licence" => "LPPL",
"description_s" => "Slovenian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Slovenian in T1/EC and UTF-8 encodings.",
],
},
# uppersorbian
{
"code" => "hsb",
"name" => "uppersorbian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "sorhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => true,
"message" => "Upper Sorbian hyphenation patterns (E. Werner)",
# \message{Hyphenation patterns for Upper Sorbian, E. Werner}
# \message{Completely new revision 1997, March 22}
"version" => nil,
"last_modified" => "1997-03-22",
"authors" => ["eduard_werner"],
"type" => "dictionary",
"licence" => "LPPL",
"description_s" => "Upper Sorbian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Upper Sorbian in T1/EC and UTF-8 encodings.",
],
},
# swedish
{
"code" => "sv",
"name" => "swedish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "svhyph.tex",
"hyphenmin" => [2,2], # patters say it could be 1,2; babel says 2,2 - double check
"encoding" => "ec",
"exceptions" => false,
"message" => "Swedish hyphenation patterns (Jan Michael Rynning, 1994-03-03)",
# "version" => "1994-03-03", # that is what author used in message
"version" => nil,
"last_modified" => "1994-03-03",
"type" => "dictionary",
"authors" => ["jan_michael_rynning"],
"licence" => "LPPL",
"description_s" => "Swedish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Swedish in T1/EC and UTF-8 encodings.",
],
},
# turkmen
{
"code" => "tk",
"name" => "turkmen",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Turkmen hyphenation patterns",
"version" => "0.1",
"last_modified" => "2010-03-16",
"type" => "dictionary",
"authors" => [ "nazar_annagurban" ],
"licence" => "public",
"description_s" => "Turkmen hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Turkmen in T1/EC and UTF-8 encodings.",
],
},
# turkish
{
"code" => "tr",
"name" => "turkish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "tkhyph.tex",
"hyphenmin" => [2,2], # polyglossia
"encoding" => "ec",
"exceptions" => false,
"message" => "Turkish hyphenation patterns",
"version" => nil,
"last_modified" => "2008-06-28",
"type" => "rules",
"authors" => ["pierre_mackay", "h_turgut_uyar", "s_ekin_kocabas", "mojca_miklavec"],
"licence" => "LPPL",
"description_s" => "Turkish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Turkish in T1/EC and UTF-8 encodings.",
# "Auto-generated from a script included in the distribution.",
"The patterns for Turkish were first produced for the Ottoman Texts",
"Project in 1987 and were suitable for both Modern Turkish and Ottoman",
"Turkish in Latin script, however the required character set didn't fit",
"into EC encoding, so support for Ottoman Turkish had to be dropped to",
"keep compatibility with 8-bit engines.",
]
},
# ukenglish
{
"code" => "en-gb",
"name" => "ukenglish", "synonyms" => ["british", "UKenglish"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "ukhyphen.tex",
"hyphenmin" => [2,3], # confirmed, same as what Knuth says
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for British English",
"version" => "1.0a", # FIXME a much older comment says 2.0?
"last_modified" => "2005-10-18",
"type" => "dictionary",
"authors" => ["dominik_wujastyk", "graham_toal"],
"licence" => "other-free", # TODO Knuth-like
# (This will be uncommented during reimplementation)
# "description_s" => "British English hyphenation patterns",
# "description_l" => [
# "Hyphenation patterns for British English in ASCII encoding.",
# ],
"description_s" => "English hyphenation patterns",
"description_l" => [
#......................................................................#
"Additional hyphenation patterns for American and British",
"English in ASCII encoding. The American English patterns",
"(usenglishmax) greatly extend the standard patterns from Knuth",
"to find many additional hyphenation points. British English",
"hyphenation is completely different from US English, so has its",
"own set of patterns.",
],
},
# (US english)
# usenglishmax
{
"code" => "en-us",
"name" => "usenglishmax",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "ushyphmax.tex",
"hyphenmin" => [2,3], # confirmed, same as what Knuth says
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for American English",
"version" => nil,
"last_modified" => "1990-03-01", # 8-bit file also has version 2005-05-30.
"type" => "dictionary",
"authors" => ["donald_e_knuth", "gerard_d_c_kuiken"],
"licence" => "other-free",
# (This will be uncommented during reimplementation)
# "description_s" => "American English hyphenation patterns",
# "description_l" => [
# "Hyphenation patterns for American English in ASCII encoding.",
# ],
},
# US english
# {
# "code" => "en-us-x-knuth",
# "name" => "english",
# "use_new_loader" => false,
# "use_old_patterns" => false,
# "filename_old_patterns" => "hyphen.tex",
# "hyphenmin" => [2,3], # confirmed, same as what Knuth says
# "encoding" => "ascii",
# "exceptions" => true,
# "message" => "Hyphenation patterns for American English",
# },
# TODO: FIXME!!!
# serbian
{
"code" => "sh-latn",
"name" => "serbian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "shhyphl.tex",
# It is allowed to leave one character at the end of the row.
# However, if you think that it is graphicaly not very
# pleasant these patterns will work well with \lefthyphenmin=2.
# \lefthyphenmin=1 \righthyphenmin=2
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => true,
"message" => "Serbian hyphenation patterns in Latin script",
# only for serbian
"version" => "2.02",
"last_modified" => "2008-06-22",
"type" => "dictionary",
"authors" => [ "dejan_muhamedagic" ],
"licence" => "LPPL",
# for both scripts
"description_s" => "Serbian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Serbian in T1/EC, T2A and UTF-8 encodings.",
"For 8-bit engines the patterns are available separately as 'serbian'",
"in T1/EC encoding for Latin script and 'serbianc' in T2A encoding for",
"Cyrillic script. Unicode engines should only use 'serbian'",
"which has patterns in both scripts combined.",
],
},
# serbianc
{
"code" => "sh-cyrl",
"name" => "serbianc",
"use_new_loader" => true,
"use_old_patterns" => false,
# "filename_old_patterns" => "srhyphc.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => true,
"message" => "Serbian hyphenation patterns in Cyrillic script",
},
# mongolian (used to be mongolian2a)
{
"code" => "mn-cyrl",
"name" => "mongolian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "mnhyphn.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => false,
"message" => "(New) Mongolian hyphenation patterns",
# only for this one
"version" => "1.2",
"last_modified" => "2010-04-03",
"type" => "dictionary",
"authors" => [ "dorjgotov_batmunkh" ],
"licence" => "LPPL",
# for both
"description_s" => "Mongolian hyphenation patterns in Cyrillic script",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Mongolian in T2A, LMC and UTF-8 encodings.",
"LMC encoding is used in MonTeX. The package includes two sets of",
"patterns that will hopefully be merged in future.",
],
},
# mongolianlmc xu-mnhyph.tex (used to be mongolian)
{
"code" => "mn-cyrl-x-lmc",
"name" => "mongolianlmc",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "mnhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "lmc",
"exceptions" => false,
"message" => "Mongolian hyphenation patterns",
},
# bulgarian
{
"code" => "bg",
"name" => "bulgarian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "bghyphen.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "t2a",
"exceptions" => false,
"message" => "Bulgarian hyphenation patterns",
"version" => "1.7",
"last_modified" => "2008-06",
"type" => "pattern",
"authors" => [ "georgi_boshnakov" ],
"licence" => "LPPL",
"description_s" => "Bulgarian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Bulgarian in T2A and UTF-8 encodings.",
],
},
# sanskrit
{
"code" => "sa",
"name" => "sanskrit",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,3], # polyglossia
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Sanskrit hyphenation patterns (v0.6, 2011/09/14)",
"version" => "0.6",
"last_modified" => "2011-09-14",
"type" => "rules",
"authors" => ["yves_codet"],
"licence" => "free", # You may freely use, copy, modify and/or distribute this file.
"description_s" => "Sanskrit hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Sanskrit and Prakrit in transliteration,",
"and in Devanagari, Bengali, Kannada, Malayalam and Telugu scripts",
"for Unicode engines.",
],
},
# norwegian
{
"code" => "no",
"name" => "norwegian", # TODO: fixme
"use_new_loader" => false,
"use_old_patterns" => false,
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Norwegian hyphenation patterns",
},
# norsk
{
"code" => "nb",
"name" => "bokmal", "synonyms" => ["norwegian", "norsk"],
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Norwegian Bokmal hyphenation patterns",
"version" => nil,
"last_modified" => "2012-05-18",
"type" => "dictionary",
"authors" => [ "rune_kleveland", "ole_michael_selberg" ],
"licence" => "free", # TODO
"description_s" => "Norwegian Bokmal and Nynorsk hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Norwegian Bokmal and Nynorsk in T1/EC and",
"UTF-8 encodings.",
],
},
# nynorsk
{
"code" => "nn",
"name" => "nynorsk",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Norwegian Nynorsk hyphenation patterns",
},
#####
# assamese
{
"code" => "as",
"name" => "assamese",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Assamese hyphenation patterns",
# this is true for all Indic patterns
"version" => "0.9.0",
"last_modified" => "2016-01-16",
"type" => "rules",
"authors" => ["santhosh_thottingal"],
"licence" => "MIT",
"description_s" => "Indic hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Assamese, Bengali, Gujarati, Hindi, Kannada,",
"Malayalam, Marathi, Oriya, Panjabi, Tamil and Telugu for Unicode",
"engines.",
],
},
# bengali
{
"code" => "bn",
"name" => "bengali",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Bengali hyphenation patterns",
},
# gujarati
{
"code" => "gu",
"name" => "gujarati",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Gujarati hyphenation patterns",
},
# hindi
{
"code" => "hi",
"name" => "hindi",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Hindi hyphenation patterns",
},
# kannada
{
"code" => "kn",
"name" => "kannada",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Kannada hyphenation patterns",
},
# malayalam
{
"code" => "ml",
"name" => "malayalam",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Malayalam hyphenation patterns",
},
# marathi
{
"code" => "mr",
"name" => "marathi",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Marathi hyphenation patterns",
},
# oriya
{
"code" => "or",
"name" => "oriya",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Oriya hyphenation patterns",
},
# panjabi
{
"code" => "pa",
"name" => "panjabi",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Panjabi hyphenation patterns",
},
# tamil
{
"code" => "ta",
"name" => "tamil",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Tamil hyphenation patterns",
},
# telugu
{
"code" => "te",
"name" => "telugu",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Telugu hyphenation patterns",
},
# thai
{
"code" => "th",
"name" => "thai",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,3],
"encoding" => "lth",
"exceptions" => false,
"message" => "Thai hyphenation patterns",
"version" => nil,
"last_modified" => "2015-05-07",
"type" => "dictionary",
"authors" => [ "theppitak_karoonboonyanan" ],
"licence" => "LPPL",
"description_s" => "Thai hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Thai in LTH and UTF-8 encodings.",
],
},
# lao
#{
# "code" => "lo",
# "name" => "lao",
# "use_new_loader" => true,
# "use_old_patterns" => false,
# "hyphenmin" => [1,1], # TODO
# "encoding" => nil, # no patterns for 8-bit engines
# "exceptions" => false,
# "message" => "Lao hyphenation patterns",
#
# "version" => nil,
# "last_modified" => "2010-05-19",
# "type" => "rules",
# "authors" => [ "brian_wilson", "arthur_reutenauer", "mojca_miklavec" ],
# "licence" => "other-free",
# "description_s" => "Lao hyphenation patterns",
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Lao language for Unicode engines.",
# "Current version is experimental and gives bad results.",
# ],
#},
# pan-Ethiopic
{
"code" => "mul-ethi",
"name" => "ethiopic", "synonyms" => ["amharic", "geez"],
"version" => nil,
"last_modified" => "2011-01-10",
"authors" => ["arthur_reutenauer", "mojca_miklavec"],
"licence" => "public-ask", # TODO
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1],
"encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Pan-Ethiopic hyphenation patterns",
"description_s" => "Hyphenation patterns for Ethiopic scripts",
"description_l" => [
#......................................................................#
"Hyphenation patterns for languages written using the Ethiopic script",
"for Unicode engines. They are not supposed to be linguistically",
"relevant in all cases and should, for proper typography, be replaced",
"by files tailored to individual languages.",
],
},
# georgian
{
"code" => "ka",
"name" => "georgian",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,2],
"encoding" => "t8m",
"exceptions" => false,
"message" => "Georgian hyphenation patterns",
"version" => "0.3",
"last_modified" => "2013-04-15",
"type" => "dictionary",
"authors" => [ "levan_shoshiashvili" ],
"licence" => "LPPL",
"description_s" => "Georgian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Georgian in T8M, T8K and UTF-8 encodings.",
],
},
# Church Slavonic
{
"code" => "cu",
"name" => "churchslavonic",
"use_new_loader" => true,
"hyphenmin" => [1, 2],
"encoding" => nil,
"exceptions" => true,
"message" => "Church Slavonic hyphenation patterns",
"version" => nil,
"last_modified" => "2016-04-16",
"type" => "machine learning",
"authors" => ["mike_kroutikov", "aleksandr_andreev"],
"licence" => "MIT",
"description_s" => "Church Slavonic hyphenation patterns",
"description_l" => [
"Hyphenation patterns for Church Slavonic in UTF-8 encoding",
],
},
# Belarusian
{
"code" => "be",
"name" => "belarusian",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2],
"encoding" => "t2a",
"message" => "Belarusian hyphenation patterns",
"version" => nil,
"last_modified" => "2016-09-29",
"type" => "rules",
"authors" => ["maksim_salau"],
"licence" => "MIT",
"description_s" => "Belarusian hyphenation patterns",
"description_l" => [
"Belarusian hyphenation patterns in T2A and UTF-8 encodings"
],
},
# Pali
{
"code" => "pi",
"name" => "pali",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1, 2],
# no encoding
"message" => "Pali hyphenation patterns",
# no version number
"last_modified" => "2018-06-29",
"type" => "rules",
"authors" => ["wie_ming_ang"],
"licence" => "MIT",
"description_s" => "Pali hyphenation patterns",
"description_l" => [
"Pali hyphenation patterns in UTF-8 encoding",
],
},
# dumylang -> dumyhyph.tex
# nohyphenation -> zerohyph.tex
# arabic -> zerohyph.tex
# farsi zerohyph.tex
# =persian
]
# TODO: do not hardcode this list; auto-generate it instead
languages_with_quotes = ['af', 'be', 'fr', 'fur', 'it', 'oc', 'pms', 'rm', 'uk', 'zh-latn-pinyin']
languages_with_dashes = ['af', 'be', 'pt', 'ru', 'tk', 'uk']
languages.each do |l|
language = Language.new(l)
if languages_with_quotes.include?(language.code) then
language.set_quotes()
end
if languages_with_dashes.include?(language.code) then
language.set_dashes()
end
@@list.push(language)
self[language.code] = language
end
end
def list
return @@list
end
end
|