czech support added

SnowballC/DESCRIPTION

@@ -8,13 +8,18 @@ Authors@R: person("Milan", "Bouchet-Valat", email="[email protected]",
 Description: An R interface to the C 'libstemmer' library that implements
   Porter's word stemming algorithm for collapsing words to a common
   root to aid comparison of vocabulary. Currently supported languages are
-  Arabic, Basque, Catalan, Danish, Dutch, English, Finnish, French, German, Greek,
-  Hindi, Hungarian, Indonesian, Irish, Italian, Lithuanian, Nepali,
-  Norwegian, Portuguese, Romanian, Russian, Spanish, Swedish, Tamil
+  Danish, Dutch, English, Finnish, French, German, Hungarian, Italian,
+  Norwegian, Portuguese, Romanian, Russian, Spanish, Swedish
   and Turkish.
 License: BSD_3_clause + file LICENSE
-Copyright: Dr Martin Porter (2001) and Richard Boulton (2004, 2005)
-  for the 'libstemmer' C library,
-  and Milan Bouchet-Valat (2013) for the R package contents.
+Copyright: Dr Martin Porter (2001) and Richard Boulton (2004, 2005) for
+        the 'libstemmer' C library, and Milan Bouchet-Valat (2013) for
+        the R package contents.
 URL: https://github.com/nalimilan/R.TeMiS
 BugReports: https://github.com/nalimilan/R.TeMiS/issues
+NeedsCompilation: yes
+Packaged: 2020-04-01 16:24:55 UTC; milan
+Author: Milan Bouchet-Valat [aut, cre]
+Maintainer: Milan Bouchet-Valat <[email protected]>
+Repository: CRAN
+Date/Publication: 2020-04-01 16:50:02 UTC

SnowballC/MD5

@@ -0,0 +1,95 @@
+0bac4b0072731204c1d7d25b54f71b16 *DESCRIPTION
+99bc125b0a438dba3cfa01fb9a9e8fd6 *LICENSE
+b61e83bbd759e889c8887424337e1823 *NAMESPACE
+eada0b70de71c203bf751e6521ff0d8c *NEWS
+b513ed2bf584d2785c2587a213650138 *R/stem.R
+846e2cc06cc63146a7db4324e70d37f7 *inst/words.R
+6450f60353bf64dfb3fb27f7b47a287d *inst/words/arabic.RData
+a4b699a8607bdd110d01bb7166a91b8d *inst/words/basque.RData
+11eae93b28980e558d1cadffac9f3654 *inst/words/catalan.RData
+4d22f94310122d16d0255a271a3fac7c *inst/words/danish.RData
+70b0d424c87664a50f05f3305be9badf *inst/words/dutch.RData
+8b99334b63f76f5a5d1cd1eee84a8c0c *inst/words/english.RData
+2575910382189eb55832547ba9506436 *inst/words/finnish.RData
+12b44b31e52db934da4aee2fd8f51d87 *inst/words/french.RData
+d7de4275726019815bf21446355beeb8 *inst/words/german.RData
+8f219a61aedc4b183a640c4be7b4c76e *inst/words/greek.RData
+5fe61461702aca290f3edc4f9fc0f9fe *inst/words/hindi.RData
+507e68c5b9ea43119c394614ae2a0f82 *inst/words/hungarian.RData
+79973d5437212d6fcd1fa4685ca21658 *inst/words/indonesian.RData
+c32b0b7607daff0f5e6bcf7cb658e22c *inst/words/irish.RData
+085956d37b512c5af95654d4d5afa6d1 *inst/words/italian.RData
+0f484d0bce7dcb3c828ca018b4727a3f *inst/words/lithuanian.RData
+1a35c9562b0e90015ba6996d019610fb *inst/words/nepali.RData
+d7b7b8a277d8335880c34755c12f15a0 *inst/words/norwegian.RData
+3918bfa0f782c6698f8fdbf78a0a41af *inst/words/porter.RData
+8853c24d92a950f48d9cac6f809afabc *inst/words/portuguese.RData
+7c195efe6cfda0f07d6c36e5b0773e83 *inst/words/romanian.RData
+6fdbb7f751b657898f1f0a4936357fef *inst/words/russian.RData
+2c6a01db0ccb42de4e4e67a49f14e83b *inst/words/spanish.RData
+bbcd85a9eb03ecbd409b1f942aa10d5b *inst/words/swedish.RData
+c17e17cedd554ab4f32f98927c86f18d *inst/words/tamil.RData
+123e76d7593bddd3bcf1365a5b6f16ef *inst/words/turkish.RData
+5834354a58bc2954926203a024097284 *man/getStemLanguages.Rd
+6470f197eb9ade66ef751a437b3aa55c *man/wordStem.Rd
+5164d6c8dddffcef63ffde83bd0787ea *src/SnowballC_init.c
+afecf06b1a49f45c0ae5e7966e1f55e8 *src/api.c
+3463c7786b95691c5ea34988c7e6dcd0 *src/api.h
+5cbdbe434d6f76bbf13c3a6f34d0fffc *src/header.h
+e15a358acc0b1263cbf0518a78954e62 *src/libstemmer.h
+dfd1562c0fec4117b918348d894a1b35 *src/libstemmer_utf8.c
+025a309bfcb95d86b0ff68dc1c4e4539 *src/modules_utf8.h
+8507d877fc894bfe04a001977ee0ec29 *src/stem.c
+956228113294ed2d1fbe9dec0c4a42a0 *src/stem_UTF_8_arabic.c
+460b9f5afb49daa57e0f5cef4d84eda5 *src/stem_UTF_8_arabic.h
+d1bf2b3177cb826adaa252591222d1ba *src/stem_UTF_8_basque.c
+f135c596760d9c329b47d7ec8f7f71b3 *src/stem_UTF_8_basque.h
+2ebbe4fe036716fe9bf38de246fe1ae9 *src/stem_UTF_8_catalan.c
+e4ca693bab46d574ad486804325ec636 *src/stem_UTF_8_catalan.h
+4cf66919bc01331e31d0801e0f3515df *src/stem_UTF_8_danish.c
+9d8c04c78d17512fd3d2fd2701ef2c33 *src/stem_UTF_8_danish.h
+9db37371b26d49a947bc5922ad1e1936 *src/stem_UTF_8_dutch.c
+9657e245e0ec26c5119f197715d6b2c1 *src/stem_UTF_8_dutch.h
+cfa8d04cd2f1367dc19d42beaedbb4c6 *src/stem_UTF_8_english.c
+4daca332253f79e2506c17418da55c4a *src/stem_UTF_8_english.h
+de413e13cb9d433bf68ccfdddd01d1f4 *src/stem_UTF_8_finnish.c
+8e5464d364b4fd5cc740ce2e627d7c00 *src/stem_UTF_8_finnish.h
+cfdd9d3675d18568ba128dfee83939d4 *src/stem_UTF_8_french.c
+9dd4d964c9358f42e820f257d134e9ad *src/stem_UTF_8_french.h
+2b32b5c597c71c8b141668a1ab14b434 *src/stem_UTF_8_german.c
+0f4cac0536d0f6cdd7b2e582e5ac33dd *src/stem_UTF_8_german.h
+22a12029a7ea789ee4170ab596ee3f03 *src/stem_UTF_8_greek.c
+ea580524124dd3ae77e68417fbee3723 *src/stem_UTF_8_greek.h
+312f3185d4837bdb246503e909111f99 *src/stem_UTF_8_hindi.c
+e9ab5fe76115b14e3a251d3c06ffe81c *src/stem_UTF_8_hindi.h
+85ee76a5d5f91ce9c96dd3e8ae52288e *src/stem_UTF_8_hungarian.c
+97a0d9193bef54e403784071964d924a *src/stem_UTF_8_hungarian.h
+e49d051339f151bf3b7b10cbc1917ce8 *src/stem_UTF_8_indonesian.c
+7bb3f1a5438ad8fd8c3ab354d397c40a *src/stem_UTF_8_indonesian.h
+a3441812d039944ebfa1b8be2b9b29b2 *src/stem_UTF_8_irish.c
+752c9cf7652b89feb273458920abc94a *src/stem_UTF_8_irish.h
+0940415ef1f91a2d55f025e1d9d4df36 *src/stem_UTF_8_italian.c
+c224a7446e7986fec86ed0ad7449e856 *src/stem_UTF_8_italian.h
+31244e47a86893031925f1419e580d77 *src/stem_UTF_8_lithuanian.c
+632acac6c0d7f10ef1e39a0a57b9d445 *src/stem_UTF_8_lithuanian.h
+326362b4041651ab48cade91b4c2fb50 *src/stem_UTF_8_nepali.c
+7a2ac6ace976b699a14e8fb9d5bf00a8 *src/stem_UTF_8_nepali.h
+72bf7dead71e4c00481ee0bd92807d20 *src/stem_UTF_8_norwegian.c
+08b6829e3354f59d6629b6bdd49ead1e *src/stem_UTF_8_norwegian.h
+9be9e96031d19ae095d287600707c47a *src/stem_UTF_8_porter.c
+42ea7000a622500a6ce68f09de87da4d *src/stem_UTF_8_porter.h
+6015a36e930ff9cde2bf7c2c42ef90fb *src/stem_UTF_8_portuguese.c
+4d7ed06b33625652a5228cb210930b5b *src/stem_UTF_8_portuguese.h
+b8fce9a4018def8d3ec1a391a05c94ab *src/stem_UTF_8_romanian.c
+717f5ec945418cd8ba6746bcab956f1c *src/stem_UTF_8_romanian.h
+5db796a1a35e624105c81903ee90ebfd *src/stem_UTF_8_russian.c
+9f360b012038fdbda068173dcfaba488 *src/stem_UTF_8_russian.h
+2b70e877ee62a279813265e96be629b4 *src/stem_UTF_8_spanish.c
+c2c303e630b5406e19454c6384c97cb2 *src/stem_UTF_8_spanish.h
+91087c38378307455f8d449ae234f56d *src/stem_UTF_8_swedish.c
+3ee381e1eb59aae7afe35096f5b21b0c *src/stem_UTF_8_swedish.h
+3ac8cd386e94f3c842c39f508f7c9742 *src/stem_UTF_8_tamil.c
+6ea3905ce441aaf3e404043de3aca905 *src/stem_UTF_8_tamil.h
+7bc4e7d4635c856ca611c6776bdeef0e *src/stem_UTF_8_turkish.c
+5cd0f8a6ac45238e47cc6dd815b59c52 *src/stem_UTF_8_turkish.h
+cebf1e3b0913b6950638712a55a4fcd1 *src/utilities.c

SnowballC/src/modules_utf8.h

@@ -12,6 +12,7 @@
 #include "stem_UTF_8_arabic.h"
 #include "stem_UTF_8_basque.h"
 #include "stem_UTF_8_catalan.h"
+#include "stem_UTF_8_czech.h"
 #include "stem_UTF_8_danish.h"
 #include "stem_UTF_8_dutch.h"
 #include "stem_UTF_8_english.h"
@@ -66,6 +67,9 @@ static const struct stemmer_modules modules[] = {
   {"ca", ENC_UTF_8, catalan_UTF_8_create_env, catalan_UTF_8_close_env, catalan_UTF_8_stem},
   {"cat", ENC_UTF_8, catalan_UTF_8_create_env, catalan_UTF_8_close_env, catalan_UTF_8_stem},
   {"catalan", ENC_UTF_8, catalan_UTF_8_create_env, catalan_UTF_8_close_env, catalan_UTF_8_stem},
+  {"cz", ENC_UTF_8, czech_UTF_8_create_env, czech_UTF_8_close_env, czech_UTF_8_stem},
+  {"cze", ENC_UTF_8, czech_UTF_8_create_env, czech_UTF_8_close_env, czech_UTF_8_stem},
+  {"czech", ENC_UTF_8, czech_UTF_8_create_env, czech_UTF_8_close_env, czech_UTF_8_stem},
   {"da", ENC_UTF_8, danish_UTF_8_create_env, danish_UTF_8_close_env, danish_UTF_8_stem},
   {"dan", ENC_UTF_8, danish_UTF_8_create_env, danish_UTF_8_close_env, danish_UTF_8_stem},
   {"danish", ENC_UTF_8, danish_UTF_8_create_env, danish_UTF_8_close_env, danish_UTF_8_stem},
@@ -147,6 +151,7 @@ static const char * algorithm_names[] = {
   "arabic", 
   "basque", 
   "catalan", 
+  "czech", 
   "danish", 
   "dutch", 
   "english",