blacklight-citeproc 0.0.5 → 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (85) hide show
  1. checksums.yaml +4 -4
  2. data/.env +3 -0
  3. data/.internal_test_app/solr/conf/_rest_managed.json +3 -0
  4. data/.internal_test_app/solr/conf/admin-extra.html +31 -0
  5. data/.internal_test_app/solr/conf/currency.xml +67 -0
  6. data/.internal_test_app/solr/conf/email_url_types.txt +2 -0
  7. data/.internal_test_app/solr/conf/lang/contractions_ca.txt +8 -0
  8. data/.internal_test_app/solr/conf/lang/contractions_fr.txt +15 -0
  9. data/.internal_test_app/solr/conf/lang/contractions_ga.txt +5 -0
  10. data/.internal_test_app/solr/conf/lang/contractions_it.txt +23 -0
  11. data/.internal_test_app/solr/conf/lang/hyphenations_ga.txt +5 -0
  12. data/.internal_test_app/solr/conf/lang/stemdict_nl.txt +6 -0
  13. data/.internal_test_app/solr/conf/lang/stoptags_ja.txt +420 -0
  14. data/.internal_test_app/solr/conf/lang/stopwords_ar.txt +125 -0
  15. data/.internal_test_app/solr/conf/lang/stopwords_bg.txt +193 -0
  16. data/.internal_test_app/solr/conf/lang/stopwords_ca.txt +220 -0
  17. data/.internal_test_app/solr/conf/lang/stopwords_cz.txt +172 -0
  18. data/.internal_test_app/solr/conf/lang/stopwords_da.txt +110 -0
  19. data/.internal_test_app/solr/conf/lang/stopwords_de.txt +294 -0
  20. data/.internal_test_app/solr/conf/lang/stopwords_el.txt +78 -0
  21. data/.internal_test_app/solr/conf/lang/stopwords_en.txt +54 -0
  22. data/.internal_test_app/solr/conf/lang/stopwords_es.txt +356 -0
  23. data/.internal_test_app/solr/conf/lang/stopwords_eu.txt +99 -0
  24. data/.internal_test_app/solr/conf/lang/stopwords_fa.txt +313 -0
  25. data/.internal_test_app/solr/conf/lang/stopwords_fi.txt +97 -0
  26. data/.internal_test_app/solr/conf/lang/stopwords_fr.txt +186 -0
  27. data/.internal_test_app/solr/conf/lang/stopwords_ga.txt +110 -0
  28. data/.internal_test_app/solr/conf/lang/stopwords_gl.txt +161 -0
  29. data/.internal_test_app/solr/conf/lang/stopwords_hi.txt +235 -0
  30. data/.internal_test_app/solr/conf/lang/stopwords_hu.txt +211 -0
  31. data/.internal_test_app/solr/conf/lang/stopwords_hy.txt +46 -0
  32. data/.internal_test_app/solr/conf/lang/stopwords_id.txt +359 -0
  33. data/.internal_test_app/solr/conf/lang/stopwords_it.txt +303 -0
  34. data/.internal_test_app/solr/conf/lang/stopwords_ja.txt +127 -0
  35. data/.internal_test_app/solr/conf/lang/stopwords_lv.txt +172 -0
  36. data/.internal_test_app/solr/conf/lang/stopwords_nl.txt +119 -0
  37. data/.internal_test_app/solr/conf/lang/stopwords_no.txt +194 -0
  38. data/.internal_test_app/solr/conf/lang/stopwords_pt.txt +253 -0
  39. data/.internal_test_app/solr/conf/lang/stopwords_ro.txt +233 -0
  40. data/.internal_test_app/solr/conf/lang/stopwords_ru.txt +243 -0
  41. data/.internal_test_app/solr/conf/lang/stopwords_sv.txt +133 -0
  42. data/.internal_test_app/solr/conf/lang/stopwords_th.txt +119 -0
  43. data/.internal_test_app/solr/conf/lang/stopwords_tr.txt +212 -0
  44. data/.internal_test_app/solr/conf/lang/userdict_ja.txt +29 -0
  45. data/.internal_test_app/solr/conf/mapping-ISOLatin1Accent.txt +246 -0
  46. data/.internal_test_app/solr/conf/protwords.txt +21 -0
  47. data/.internal_test_app/solr/conf/schema.xml +408 -0
  48. data/.internal_test_app/solr/conf/scripts.conf +24 -0
  49. data/.internal_test_app/solr/conf/solrconfig.xml +1287 -0
  50. data/.internal_test_app/solr/conf/spellings.txt +2 -0
  51. data/.internal_test_app/solr/conf/stopwords.txt +14 -0
  52. data/.internal_test_app/solr/conf/stopwords_en.txt +58 -0
  53. data/.internal_test_app/solr/conf/synonyms.txt +13 -0
  54. data/.internal_test_app/solr/conf/update-script.js +115 -0
  55. data/.internal_test_app/solr/conf/velocity/browse.vm +32 -0
  56. data/.internal_test_app/solr/conf/velocity/dropit.js +0 -0
  57. data/.internal_test_app/solr/conf/velocity/facet_doc_type.vm +2 -0
  58. data/.internal_test_app/solr/conf/velocity/facet_text_shingles.vm +12 -0
  59. data/.internal_test_app/solr/conf/velocity/facets.vm +24 -0
  60. data/.internal_test_app/solr/conf/velocity/footer.vm +29 -0
  61. data/.internal_test_app/solr/conf/velocity/head.vm +290 -0
  62. data/.internal_test_app/solr/conf/velocity/hit.vm +77 -0
  63. data/.internal_test_app/solr/conf/velocity/img/english_640.png +0 -0
  64. data/.internal_test_app/solr/conf/velocity/img/france_640.png +0 -0
  65. data/.internal_test_app/solr/conf/velocity/img/germany_640.png +0 -0
  66. data/.internal_test_app/solr/conf/velocity/img/globe_256.png +0 -0
  67. data/.internal_test_app/solr/conf/velocity/jquery.tx3-tag-cloud.js +0 -0
  68. data/.internal_test_app/solr/conf/velocity/js/dropit.js +97 -0
  69. data/.internal_test_app/solr/conf/velocity/js/jquery.autocomplete.js +763 -0
  70. data/.internal_test_app/solr/conf/velocity/js/jquery.tx3-tag-cloud.js +70 -0
  71. data/.internal_test_app/solr/conf/velocity/layout.vm +42 -0
  72. data/.internal_test_app/solr/conf/velocity/macros.vm +16 -0
  73. data/.internal_test_app/solr/conf/velocity/mime_type_lists.vm +68 -0
  74. data/.internal_test_app/solr/conf/velocity/results.vm +20 -0
  75. data/.internal_test_app/solr/conf/velocity/results_list.vm +21 -0
  76. data/.internal_test_app/solr/conf/xslt/example.xsl +132 -0
  77. data/.internal_test_app/solr/conf/xslt/example_atom.xsl +67 -0
  78. data/.internal_test_app/solr/conf/xslt/example_rss.xsl +66 -0
  79. data/.internal_test_app/solr/conf/xslt/luke.xsl +337 -0
  80. data/Dockerfile +43 -0
  81. data/README.md +3 -0
  82. data/bin/entrypoint.sh +8 -0
  83. data/docker-compose.yml +33 -0
  84. data/lib/blacklight/citeproc/version.rb +1 -1
  85. metadata +83 -2
@@ -0,0 +1,127 @@
1
+ #
2
+ # This file defines a stopword set for Japanese.
3
+ #
4
+ # This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
5
+ # Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
6
+ # for frequency lists, etc. that can be useful for making your own set (if desired)
7
+ #
8
+ # Note that there is an overlap between these stopwords and the terms stopped when used
9
+ # in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
10
+ # that comments are not allowed on the same line as stopwords.
11
+ #
12
+ # Also note that stopping is done in a case-insensitive manner. Change your StopFilter
13
+ # configuration if you need case-sensitive stopping. Lastly, note that stopping is done
14
+ # using the same character width as the entries in this file. Since this StopFilter is
15
+ # normally done after a CJKWidthFilter in your chain, you would usually want your romaji
16
+ # entries to be in half-width and your kana entries to be in full-width.
17
+ #
18
+
19
+
20
+
21
+
22
+
23
+
24
+
25
+
26
+
27
+
28
+
29
+
30
+ ある
31
+ いる
32
+
33
+ する
34
+ から
35
+
36
+ こと
37
+ として
38
+
39
+
40
+ れる
41
+ など
42
+ なっ
43
+ ない
44
+ この
45
+ ため
46
+ その
47
+ あっ
48
+ よう
49
+ また
50
+ もの
51
+ という
52
+ あり
53
+ まで
54
+ られ
55
+ なる
56
+
57
+
58
+
59
+ これ
60
+ によって
61
+ により
62
+ おり
63
+ より
64
+ による
65
+
66
+ なり
67
+ られる
68
+ において
69
+
70
+ なかっ
71
+ なく
72
+ しかし
73
+ について
74
+
75
+ だっ
76
+ その後
77
+ できる
78
+ それ
79
+
80
+ ので
81
+ なお
82
+ のみ
83
+ でき
84
+
85
+
86
+ における
87
+ および
88
+ いう
89
+ さらに
90
+ でも
91
+
92
+ たり
93
+ その他
94
+ に関する
95
+ たち
96
+ ます
97
+
98
+ なら
99
+ に対して
100
+ 特に
101
+ せる
102
+ 及び
103
+ これら
104
+ とき
105
+ では
106
+ にて
107
+ ほか
108
+ ながら
109
+ うち
110
+ そして
111
+ とともに
112
+ ただし
113
+ かつて
114
+ それぞれ
115
+ または
116
+
117
+ ほど
118
+ ものの
119
+ に対する
120
+ ほとんど
121
+ と共に
122
+ といった
123
+ です
124
+ とも
125
+ ところ
126
+ ここ
127
+ ##### End of file
@@ -0,0 +1,172 @@
1
+ # Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
2
+ # the original list of over 800 forms was refined:
3
+ # pronouns, adverbs, interjections were removed
4
+ #
5
+ # prepositions
6
+ aiz
7
+ ap
8
+ ar
9
+ apakš
10
+ ārpus
11
+ augšpus
12
+ bez
13
+ caur
14
+ dēļ
15
+ gar
16
+ iekš
17
+ iz
18
+ kopš
19
+ labad
20
+ lejpus
21
+ līdz
22
+ no
23
+ otrpus
24
+ pa
25
+ par
26
+ pār
27
+ pēc
28
+ pie
29
+ pirms
30
+ pret
31
+ priekš
32
+ starp
33
+ šaipus
34
+ uz
35
+ viņpus
36
+ virs
37
+ virspus
38
+ zem
39
+ apakšpus
40
+ # Conjunctions
41
+ un
42
+ bet
43
+ jo
44
+ ja
45
+ ka
46
+ lai
47
+ tomēr
48
+ tikko
49
+ turpretī
50
+ arī
51
+ kaut
52
+ gan
53
+ tādēļ
54
+
55
+ ne
56
+ tikvien
57
+ vien
58
+
59
+ ir
60
+ te
61
+ vai
62
+ kamēr
63
+ # Particles
64
+ ar
65
+ diezin
66
+ droši
67
+ diemžēl
68
+ nebūt
69
+ ik
70
+ it
71
+ taču
72
+ nu
73
+ pat
74
+ tiklab
75
+ iekšpus
76
+ nedz
77
+ tik
78
+ nevis
79
+ turpretim
80
+ jeb
81
+ iekam
82
+ iekām
83
+ iekāms
84
+ kolīdz
85
+ līdzko
86
+ tiklīdz
87
+ jebšu
88
+ tālab
89
+ tāpēc
90
+ nekā
91
+ itin
92
+
93
+ jau
94
+ jel
95
+
96
+ nezin
97
+ tad
98
+ tikai
99
+ vis
100
+ tak
101
+ iekams
102
+ vien
103
+ # modal verbs
104
+ būt
105
+ biju
106
+ biji
107
+ bija
108
+ bijām
109
+ bijāt
110
+ esmu
111
+ esi
112
+ esam
113
+ esat
114
+ būšu
115
+ būsi
116
+ būs
117
+ būsim
118
+ būsiet
119
+ tikt
120
+ tiku
121
+ tiki
122
+ tika
123
+ tikām
124
+ tikāt
125
+ tieku
126
+ tiec
127
+ tiek
128
+ tiekam
129
+ tiekat
130
+ tikšu
131
+ tiks
132
+ tiksim
133
+ tiksiet
134
+ tapt
135
+ tapi
136
+ tapāt
137
+ topat
138
+ tapšu
139
+ tapsi
140
+ taps
141
+ tapsim
142
+ tapsiet
143
+ kļūt
144
+ kļuvu
145
+ kļuvi
146
+ kļuva
147
+ kļuvām
148
+ kļuvāt
149
+ kļūstu
150
+ kļūsti
151
+ kļūst
152
+ kļūstam
153
+ kļūstat
154
+ kļūšu
155
+ kļūsi
156
+ kļūs
157
+ kļūsim
158
+ kļūsiet
159
+ # verbs
160
+ varēt
161
+ varēju
162
+ varējām
163
+ varēšu
164
+ varēsim
165
+ var
166
+ varēji
167
+ varējāt
168
+ varēsi
169
+ varēsiet
170
+ varat
171
+ varēja
172
+ varēs
@@ -0,0 +1,119 @@
1
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
2
+ | This file is distributed under the BSD License.
3
+ | See http://snowball.tartarus.org/license.php
4
+ | Also see http://www.opensource.org/licenses/bsd-license.html
5
+ | - Encoding was converted to UTF-8.
6
+ | - This notice was added.
7
+ |
8
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
9
+
10
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
11
+ | word is at the start of a line.
12
+
13
+ | This is a ranked list (commonest to rarest) of stopwords derived from
14
+ | a large sample of Dutch text.
15
+
16
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
17
+ | clearly below.
18
+
19
+ de | the
20
+ en | and
21
+ van | of, from
22
+ ik | I, the ego
23
+ te | (1) chez, at etc, (2) to, (3) too
24
+ dat | that, which
25
+ die | that, those, who, which
26
+ in | in, inside
27
+ een | a, an, one
28
+ hij | he
29
+ het | the, it
30
+ niet | not, nothing, naught
31
+ zijn | (1) to be, being, (2) his, one's, its
32
+ is | is
33
+ was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
34
+ op | on, upon, at, in, up, used up
35
+ aan | on, upon, to (as dative)
36
+ met | with, by
37
+ als | like, such as, when
38
+ voor | (1) before, in front of, (2) furrow
39
+ had | had, past tense all persons sing. of 'hebben' (have)
40
+ er | there
41
+ maar | but, only
42
+ om | round, about, for etc
43
+ hem | him
44
+ dan | then
45
+ zou | should/would, past tense all persons sing. of 'zullen'
46
+ of | or, whether, if
47
+ wat | what, something, anything
48
+ mijn | possessive and noun 'mine'
49
+ men | people, 'one'
50
+ dit | this
51
+ zo | so, thus, in this way
52
+ door | through by
53
+ over | over, across
54
+ ze | she, her, they, them
55
+ zich | oneself
56
+ bij | (1) a bee, (2) by, near, at
57
+ ook | also, too
58
+ tot | till, until
59
+ je | you
60
+ mij | me
61
+ uit | out of, from
62
+ der | Old Dutch form of 'van der' still found in surnames
63
+ daar | (1) there, (2) because
64
+ haar | (1) her, their, them, (2) hair
65
+ naar | (1) unpleasant, unwell etc, (2) towards, (3) as
66
+ heb | present first person sing. of 'to have'
67
+ hoe | how, why
68
+ heeft | present third person sing. of 'to have'
69
+ hebben | 'to have' and various parts thereof
70
+ deze | this
71
+ u | you
72
+ want | (1) for, (2) mitten, (3) rigging
73
+ nog | yet, still
74
+ zal | 'shall', first and third person sing. of verb 'zullen' (will)
75
+ me | me
76
+ zij | she, they
77
+ nu | now
78
+ ge | 'thou', still used in Belgium and south Netherlands
79
+ geen | none
80
+ omdat | because
81
+ iets | something, somewhat
82
+ worden | to become, grow, get
83
+ toch | yet, still
84
+ al | all, every, each
85
+ waren | (1) 'were' (2) to wander, (3) wares, (3)
86
+ veel | much, many
87
+ meer | (1) more, (2) lake
88
+ doen | to do, to make
89
+ toen | then, when
90
+ moet | noun 'spot/mote' and present form of 'to must'
91
+ ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
92
+ zonder | without
93
+ kan | noun 'can' and present form of 'to be able'
94
+ hun | their, them
95
+ dus | so, consequently
96
+ alles | all, everything, anything
97
+ onder | under, beneath
98
+ ja | yes, of course
99
+ eens | once, one day
100
+ hier | here
101
+ wie | who
102
+ werd | imperfect third person sing. of 'become'
103
+ altijd | always
104
+ doch | yet, but etc
105
+ wordt | present third person sing. of 'become'
106
+ wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
107
+ kunnen | to be able
108
+ ons | us/our
109
+ zelf | self
110
+ tegen | against, towards, at
111
+ na | after, near
112
+ reeds | already
113
+ wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
114
+ kon | could; past tense of 'to be able'
115
+ niets | nothing
116
+ uw | your
117
+ iemand | somebody
118
+ geweest | been; past participle of 'be'
119
+ andere | other
@@ -0,0 +1,194 @@
1
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
2
+ | This file is distributed under the BSD License.
3
+ | See http://snowball.tartarus.org/license.php
4
+ | Also see http://www.opensource.org/licenses/bsd-license.html
5
+ | - Encoding was converted to UTF-8.
6
+ | - This notice was added.
7
+ |
8
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
9
+
10
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
11
+ | word is at the start of a line.
12
+
13
+ | This stop word list is for the dominant bokmål dialect. Words unique
14
+ | to nynorsk are marked *.
15
+
16
+ | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
17
+
18
+ og | and
19
+ i | in
20
+ jeg | I
21
+ det | it/this/that
22
+ at | to (w. inf.)
23
+ en | a/an
24
+ et | a/an
25
+ den | it/this/that
26
+ til | to
27
+ er | is/am/are
28
+ som | who/that
29
+ på | on
30
+ de | they / you(formal)
31
+ med | with
32
+ han | he
33
+ av | of
34
+ ikke | not
35
+ ikkje | not *
36
+ der | there
37
+ så | so
38
+ var | was/were
39
+ meg | me
40
+ seg | you
41
+ men | but
42
+ ett | one
43
+ har | have
44
+ om | about
45
+ vi | we
46
+ min | my
47
+ mitt | my
48
+ ha | have
49
+ hadde | had
50
+ hun | she
51
+ nå | now
52
+ over | over
53
+ da | when/as
54
+ ved | by/know
55
+ fra | from
56
+ du | you
57
+ ut | out
58
+ sin | your
59
+ dem | them
60
+ oss | us
61
+ opp | up
62
+ man | you/one
63
+ kan | can
64
+ hans | his
65
+ hvor | where
66
+ eller | or
67
+ hva | what
68
+ skal | shall/must
69
+ selv | self (reflective)
70
+ sjøl | self (reflective)
71
+ her | here
72
+ alle | all
73
+ vil | will
74
+ bli | become
75
+ ble | became
76
+ blei | became *
77
+ blitt | have become
78
+ kunne | could
79
+ inn | in
80
+ når | when
81
+ være | be
82
+ kom | come
83
+ noen | some
84
+ noe | some
85
+ ville | would
86
+ dere | you
87
+ som | who/which/that
88
+ deres | their/theirs
89
+ kun | only/just
90
+ ja | yes
91
+ etter | after
92
+ ned | down
93
+ skulle | should
94
+ denne | this
95
+ for | for/because
96
+ deg | you
97
+ si | hers/his
98
+ sine | hers/his
99
+ sitt | hers/his
100
+ mot | against
101
+ å | to
102
+ meget | much
103
+ hvorfor | why
104
+ dette | this
105
+ disse | these/those
106
+ uten | without
107
+ hvordan | how
108
+ ingen | none
109
+ din | your
110
+ ditt | your
111
+ blir | become
112
+ samme | same
113
+ hvilken | which
114
+ hvilke | which (plural)
115
+ sånn | such a
116
+ inni | inside/within
117
+ mellom | between
118
+ vår | our
119
+ hver | each
120
+ hvem | who
121
+ vors | us/ours
122
+ hvis | whose
123
+ både | both
124
+ bare | only/just
125
+ enn | than
126
+ fordi | as/because
127
+ før | before
128
+ mange | many
129
+ også | also
130
+ slik | just
131
+ vært | been
132
+ være | to be
133
+ båe | both *
134
+ begge | both
135
+ siden | since
136
+ dykk | your *
137
+ dykkar | yours *
138
+ dei | they *
139
+ deira | them *
140
+ deires | theirs *
141
+ deim | them *
142
+ di | your (fem.) *
143
+ då | as/when *
144
+ eg | I *
145
+ ein | a/an *
146
+ eit | a/an *
147
+ eitt | a/an *
148
+ elles | or *
149
+ honom | he *
150
+ hjå | at *
151
+ ho | she *
152
+ hoe | she *
153
+ henne | her
154
+ hennar | her/hers
155
+ hennes | hers
156
+ hoss | how *
157
+ hossen | how *
158
+ ikkje | not *
159
+ ingi | noone *
160
+ inkje | noone *
161
+ korleis | how *
162
+ korso | how *
163
+ kva | what/which *
164
+ kvar | where *
165
+ kvarhelst | where *
166
+ kven | who/whom *
167
+ kvi | why *
168
+ kvifor | why *
169
+ me | we *
170
+ medan | while *
171
+ mi | my *
172
+ mine | my *
173
+ mykje | much *
174
+ no | now *
175
+ nokon | some (masc./neut.) *
176
+ noka | some (fem.) *
177
+ nokor | some *
178
+ noko | some *
179
+ nokre | some *
180
+ si | his/hers *
181
+ sia | since *
182
+ sidan | since *
183
+ so | so *
184
+ somt | some *
185
+ somme | some *
186
+ um | about*
187
+ upp | up *
188
+ vere | be *
189
+ vore | was *
190
+ verte | become *
191
+ vort | become *
192
+ varte | became *
193
+ vart | became *
194
+