blacklight-citeproc 0.0.5 → 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.env +3 -0
- data/.internal_test_app/solr/conf/_rest_managed.json +3 -0
- data/.internal_test_app/solr/conf/admin-extra.html +31 -0
- data/.internal_test_app/solr/conf/currency.xml +67 -0
- data/.internal_test_app/solr/conf/email_url_types.txt +2 -0
- data/.internal_test_app/solr/conf/lang/contractions_ca.txt +8 -0
- data/.internal_test_app/solr/conf/lang/contractions_fr.txt +15 -0
- data/.internal_test_app/solr/conf/lang/contractions_ga.txt +5 -0
- data/.internal_test_app/solr/conf/lang/contractions_it.txt +23 -0
- data/.internal_test_app/solr/conf/lang/hyphenations_ga.txt +5 -0
- data/.internal_test_app/solr/conf/lang/stemdict_nl.txt +6 -0
- data/.internal_test_app/solr/conf/lang/stoptags_ja.txt +420 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ar.txt +125 -0
- data/.internal_test_app/solr/conf/lang/stopwords_bg.txt +193 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ca.txt +220 -0
- data/.internal_test_app/solr/conf/lang/stopwords_cz.txt +172 -0
- data/.internal_test_app/solr/conf/lang/stopwords_da.txt +110 -0
- data/.internal_test_app/solr/conf/lang/stopwords_de.txt +294 -0
- data/.internal_test_app/solr/conf/lang/stopwords_el.txt +78 -0
- data/.internal_test_app/solr/conf/lang/stopwords_en.txt +54 -0
- data/.internal_test_app/solr/conf/lang/stopwords_es.txt +356 -0
- data/.internal_test_app/solr/conf/lang/stopwords_eu.txt +99 -0
- data/.internal_test_app/solr/conf/lang/stopwords_fa.txt +313 -0
- data/.internal_test_app/solr/conf/lang/stopwords_fi.txt +97 -0
- data/.internal_test_app/solr/conf/lang/stopwords_fr.txt +186 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ga.txt +110 -0
- data/.internal_test_app/solr/conf/lang/stopwords_gl.txt +161 -0
- data/.internal_test_app/solr/conf/lang/stopwords_hi.txt +235 -0
- data/.internal_test_app/solr/conf/lang/stopwords_hu.txt +211 -0
- data/.internal_test_app/solr/conf/lang/stopwords_hy.txt +46 -0
- data/.internal_test_app/solr/conf/lang/stopwords_id.txt +359 -0
- data/.internal_test_app/solr/conf/lang/stopwords_it.txt +303 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ja.txt +127 -0
- data/.internal_test_app/solr/conf/lang/stopwords_lv.txt +172 -0
- data/.internal_test_app/solr/conf/lang/stopwords_nl.txt +119 -0
- data/.internal_test_app/solr/conf/lang/stopwords_no.txt +194 -0
- data/.internal_test_app/solr/conf/lang/stopwords_pt.txt +253 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ro.txt +233 -0
- data/.internal_test_app/solr/conf/lang/stopwords_ru.txt +243 -0
- data/.internal_test_app/solr/conf/lang/stopwords_sv.txt +133 -0
- data/.internal_test_app/solr/conf/lang/stopwords_th.txt +119 -0
- data/.internal_test_app/solr/conf/lang/stopwords_tr.txt +212 -0
- data/.internal_test_app/solr/conf/lang/userdict_ja.txt +29 -0
- data/.internal_test_app/solr/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/.internal_test_app/solr/conf/protwords.txt +21 -0
- data/.internal_test_app/solr/conf/schema.xml +408 -0
- data/.internal_test_app/solr/conf/scripts.conf +24 -0
- data/.internal_test_app/solr/conf/solrconfig.xml +1287 -0
- data/.internal_test_app/solr/conf/spellings.txt +2 -0
- data/.internal_test_app/solr/conf/stopwords.txt +14 -0
- data/.internal_test_app/solr/conf/stopwords_en.txt +58 -0
- data/.internal_test_app/solr/conf/synonyms.txt +13 -0
- data/.internal_test_app/solr/conf/update-script.js +115 -0
- data/.internal_test_app/solr/conf/velocity/browse.vm +32 -0
- data/.internal_test_app/solr/conf/velocity/dropit.js +0 -0
- data/.internal_test_app/solr/conf/velocity/facet_doc_type.vm +2 -0
- data/.internal_test_app/solr/conf/velocity/facet_text_shingles.vm +12 -0
- data/.internal_test_app/solr/conf/velocity/facets.vm +24 -0
- data/.internal_test_app/solr/conf/velocity/footer.vm +29 -0
- data/.internal_test_app/solr/conf/velocity/head.vm +290 -0
- data/.internal_test_app/solr/conf/velocity/hit.vm +77 -0
- data/.internal_test_app/solr/conf/velocity/img/english_640.png +0 -0
- data/.internal_test_app/solr/conf/velocity/img/france_640.png +0 -0
- data/.internal_test_app/solr/conf/velocity/img/germany_640.png +0 -0
- data/.internal_test_app/solr/conf/velocity/img/globe_256.png +0 -0
- data/.internal_test_app/solr/conf/velocity/jquery.tx3-tag-cloud.js +0 -0
- data/.internal_test_app/solr/conf/velocity/js/dropit.js +97 -0
- data/.internal_test_app/solr/conf/velocity/js/jquery.autocomplete.js +763 -0
- data/.internal_test_app/solr/conf/velocity/js/jquery.tx3-tag-cloud.js +70 -0
- data/.internal_test_app/solr/conf/velocity/layout.vm +42 -0
- data/.internal_test_app/solr/conf/velocity/macros.vm +16 -0
- data/.internal_test_app/solr/conf/velocity/mime_type_lists.vm +68 -0
- data/.internal_test_app/solr/conf/velocity/results.vm +20 -0
- data/.internal_test_app/solr/conf/velocity/results_list.vm +21 -0
- data/.internal_test_app/solr/conf/xslt/example.xsl +132 -0
- data/.internal_test_app/solr/conf/xslt/example_atom.xsl +67 -0
- data/.internal_test_app/solr/conf/xslt/example_rss.xsl +66 -0
- data/.internal_test_app/solr/conf/xslt/luke.xsl +337 -0
- data/Dockerfile +43 -0
- data/README.md +3 -0
- data/bin/entrypoint.sh +8 -0
- data/docker-compose.yml +33 -0
- data/lib/blacklight/citeproc/version.rb +1 -1
- metadata +83 -2
@@ -0,0 +1,133 @@
|
|
1
|
+
| From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/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 Swedish 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 text sample.
|
15
|
+
|
16
|
+
| Swedish stop words occasionally exhibit homonym clashes. For example
|
17
|
+
| så = so, but also seed. These are indicated clearly below.
|
18
|
+
|
19
|
+
och | and
|
20
|
+
det | it, this/that
|
21
|
+
att | to (with infinitive)
|
22
|
+
i | in, at
|
23
|
+
en | a
|
24
|
+
jag | I
|
25
|
+
hon | she
|
26
|
+
som | who, that
|
27
|
+
han | he
|
28
|
+
på | on
|
29
|
+
den | it, this/that
|
30
|
+
med | with
|
31
|
+
var | where, each
|
32
|
+
sig | him(self) etc
|
33
|
+
för | for
|
34
|
+
så | so (also: seed)
|
35
|
+
till | to
|
36
|
+
är | is
|
37
|
+
men | but
|
38
|
+
ett | a
|
39
|
+
om | if; around, about
|
40
|
+
hade | had
|
41
|
+
de | they, these/those
|
42
|
+
av | of
|
43
|
+
icke | not, no
|
44
|
+
mig | me
|
45
|
+
du | you
|
46
|
+
henne | her
|
47
|
+
då | then, when
|
48
|
+
sin | his
|
49
|
+
nu | now
|
50
|
+
har | have
|
51
|
+
inte | inte någon = no one
|
52
|
+
hans | his
|
53
|
+
honom | him
|
54
|
+
skulle | 'sake'
|
55
|
+
hennes | her
|
56
|
+
där | there
|
57
|
+
min | my
|
58
|
+
man | one (pronoun)
|
59
|
+
ej | nor
|
60
|
+
vid | at, by, on (also: vast)
|
61
|
+
kunde | could
|
62
|
+
något | some etc
|
63
|
+
från | from, off
|
64
|
+
ut | out
|
65
|
+
när | when
|
66
|
+
efter | after, behind
|
67
|
+
upp | up
|
68
|
+
vi | we
|
69
|
+
dem | them
|
70
|
+
vara | be
|
71
|
+
vad | what
|
72
|
+
över | over
|
73
|
+
än | than
|
74
|
+
dig | you
|
75
|
+
kan | can
|
76
|
+
sina | his
|
77
|
+
här | here
|
78
|
+
ha | have
|
79
|
+
mot | towards
|
80
|
+
alla | all
|
81
|
+
under | under (also: wonder)
|
82
|
+
någon | some etc
|
83
|
+
eller | or (else)
|
84
|
+
allt | all
|
85
|
+
mycket | much
|
86
|
+
sedan | since
|
87
|
+
ju | why
|
88
|
+
denna | this/that
|
89
|
+
själv | myself, yourself etc
|
90
|
+
detta | this/that
|
91
|
+
åt | to
|
92
|
+
utan | without
|
93
|
+
varit | was
|
94
|
+
hur | how
|
95
|
+
ingen | no
|
96
|
+
mitt | my
|
97
|
+
ni | you
|
98
|
+
bli | to be, become
|
99
|
+
blev | from bli
|
100
|
+
oss | us
|
101
|
+
din | thy
|
102
|
+
dessa | these/those
|
103
|
+
några | some etc
|
104
|
+
deras | their
|
105
|
+
blir | from bli
|
106
|
+
mina | my
|
107
|
+
samma | (the) same
|
108
|
+
vilken | who, that
|
109
|
+
er | you, your
|
110
|
+
sådan | such a
|
111
|
+
vår | our
|
112
|
+
blivit | from bli
|
113
|
+
dess | its
|
114
|
+
inom | within
|
115
|
+
mellan | between
|
116
|
+
sådant | such a
|
117
|
+
varför | why
|
118
|
+
varje | each
|
119
|
+
vilka | who, that
|
120
|
+
ditt | thy
|
121
|
+
vem | who
|
122
|
+
vilket | who, that
|
123
|
+
sitta | his
|
124
|
+
sådana | such a
|
125
|
+
vart | each
|
126
|
+
dina | thy
|
127
|
+
vars | whose
|
128
|
+
vårt | our
|
129
|
+
våra | our
|
130
|
+
ert | your
|
131
|
+
era | your
|
132
|
+
vilkas | whose
|
133
|
+
|
@@ -0,0 +1,119 @@
|
|
1
|
+
# Thai stopwords from:
|
2
|
+
# "Opinion Detection in Thai Political News Columns
|
3
|
+
# Based on Subjectivity Analysis"
|
4
|
+
# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
|
5
|
+
ไว้
|
6
|
+
ไม่
|
7
|
+
ไป
|
8
|
+
ได้
|
9
|
+
ให้
|
10
|
+
ใน
|
11
|
+
โดย
|
12
|
+
แห่ง
|
13
|
+
แล้ว
|
14
|
+
และ
|
15
|
+
แรก
|
16
|
+
แบบ
|
17
|
+
แต่
|
18
|
+
เอง
|
19
|
+
เห็น
|
20
|
+
เลย
|
21
|
+
เริ่ม
|
22
|
+
เรา
|
23
|
+
เมื่อ
|
24
|
+
เพื่อ
|
25
|
+
เพราะ
|
26
|
+
เป็นการ
|
27
|
+
เป็น
|
28
|
+
เปิดเผย
|
29
|
+
เปิด
|
30
|
+
เนื่องจาก
|
31
|
+
เดียวกัน
|
32
|
+
เดียว
|
33
|
+
เช่น
|
34
|
+
เฉพาะ
|
35
|
+
เคย
|
36
|
+
เข้า
|
37
|
+
เขา
|
38
|
+
อีก
|
39
|
+
อาจ
|
40
|
+
อะไร
|
41
|
+
ออก
|
42
|
+
อย่าง
|
43
|
+
อยู่
|
44
|
+
อยาก
|
45
|
+
หาก
|
46
|
+
หลาย
|
47
|
+
หลังจาก
|
48
|
+
หลัง
|
49
|
+
หรือ
|
50
|
+
หนึ่ง
|
51
|
+
ส่วน
|
52
|
+
ส่ง
|
53
|
+
สุด
|
54
|
+
สําหรับ
|
55
|
+
ว่า
|
56
|
+
วัน
|
57
|
+
ลง
|
58
|
+
ร่วม
|
59
|
+
ราย
|
60
|
+
รับ
|
61
|
+
ระหว่าง
|
62
|
+
รวม
|
63
|
+
ยัง
|
64
|
+
มี
|
65
|
+
มาก
|
66
|
+
มา
|
67
|
+
พร้อม
|
68
|
+
พบ
|
69
|
+
ผ่าน
|
70
|
+
ผล
|
71
|
+
บาง
|
72
|
+
น่า
|
73
|
+
นี้
|
74
|
+
นํา
|
75
|
+
นั้น
|
76
|
+
นัก
|
77
|
+
นอกจาก
|
78
|
+
ทุก
|
79
|
+
ที่สุด
|
80
|
+
ที่
|
81
|
+
ทําให้
|
82
|
+
ทํา
|
83
|
+
ทาง
|
84
|
+
ทั้งนี้
|
85
|
+
ทั้ง
|
86
|
+
ถ้า
|
87
|
+
ถูก
|
88
|
+
ถึง
|
89
|
+
ต้อง
|
90
|
+
ต่างๆ
|
91
|
+
ต่าง
|
92
|
+
ต่อ
|
93
|
+
ตาม
|
94
|
+
ตั้งแต่
|
95
|
+
ตั้ง
|
96
|
+
ด้าน
|
97
|
+
ด้วย
|
98
|
+
ดัง
|
99
|
+
ซึ่ง
|
100
|
+
ช่วง
|
101
|
+
จึง
|
102
|
+
จาก
|
103
|
+
จัด
|
104
|
+
จะ
|
105
|
+
คือ
|
106
|
+
ความ
|
107
|
+
ครั้ง
|
108
|
+
คง
|
109
|
+
ขึ้น
|
110
|
+
ของ
|
111
|
+
ขอ
|
112
|
+
ขณะ
|
113
|
+
ก่อน
|
114
|
+
ก็
|
115
|
+
การ
|
116
|
+
กับ
|
117
|
+
กัน
|
118
|
+
กว่า
|
119
|
+
กล่าว
|
@@ -0,0 +1,212 @@
|
|
1
|
+
# Turkish stopwords from LUCENE-559
|
2
|
+
# merged with the list from "Information Retrieval on Turkish Texts"
|
3
|
+
# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
|
4
|
+
acaba
|
5
|
+
altmış
|
6
|
+
altı
|
7
|
+
ama
|
8
|
+
ancak
|
9
|
+
arada
|
10
|
+
aslında
|
11
|
+
ayrıca
|
12
|
+
bana
|
13
|
+
bazı
|
14
|
+
belki
|
15
|
+
ben
|
16
|
+
benden
|
17
|
+
beni
|
18
|
+
benim
|
19
|
+
beri
|
20
|
+
beş
|
21
|
+
bile
|
22
|
+
bin
|
23
|
+
bir
|
24
|
+
birçok
|
25
|
+
biri
|
26
|
+
birkaç
|
27
|
+
birkez
|
28
|
+
birşey
|
29
|
+
birşeyi
|
30
|
+
biz
|
31
|
+
bize
|
32
|
+
bizden
|
33
|
+
bizi
|
34
|
+
bizim
|
35
|
+
böyle
|
36
|
+
böylece
|
37
|
+
bu
|
38
|
+
buna
|
39
|
+
bunda
|
40
|
+
bundan
|
41
|
+
bunlar
|
42
|
+
bunları
|
43
|
+
bunların
|
44
|
+
bunu
|
45
|
+
bunun
|
46
|
+
burada
|
47
|
+
çok
|
48
|
+
çünkü
|
49
|
+
da
|
50
|
+
daha
|
51
|
+
dahi
|
52
|
+
de
|
53
|
+
defa
|
54
|
+
değil
|
55
|
+
diğer
|
56
|
+
diye
|
57
|
+
doksan
|
58
|
+
dokuz
|
59
|
+
dolayı
|
60
|
+
dolayısıyla
|
61
|
+
dört
|
62
|
+
edecek
|
63
|
+
eden
|
64
|
+
ederek
|
65
|
+
edilecek
|
66
|
+
ediliyor
|
67
|
+
edilmesi
|
68
|
+
ediyor
|
69
|
+
eğer
|
70
|
+
elli
|
71
|
+
en
|
72
|
+
etmesi
|
73
|
+
etti
|
74
|
+
ettiği
|
75
|
+
ettiğini
|
76
|
+
gibi
|
77
|
+
göre
|
78
|
+
halen
|
79
|
+
hangi
|
80
|
+
hatta
|
81
|
+
hem
|
82
|
+
henüz
|
83
|
+
hep
|
84
|
+
hepsi
|
85
|
+
her
|
86
|
+
herhangi
|
87
|
+
herkesin
|
88
|
+
hiç
|
89
|
+
hiçbir
|
90
|
+
için
|
91
|
+
iki
|
92
|
+
ile
|
93
|
+
ilgili
|
94
|
+
ise
|
95
|
+
işte
|
96
|
+
itibaren
|
97
|
+
itibariyle
|
98
|
+
kadar
|
99
|
+
karşın
|
100
|
+
katrilyon
|
101
|
+
kendi
|
102
|
+
kendilerine
|
103
|
+
kendini
|
104
|
+
kendisi
|
105
|
+
kendisine
|
106
|
+
kendisini
|
107
|
+
kez
|
108
|
+
ki
|
109
|
+
kim
|
110
|
+
kimden
|
111
|
+
kime
|
112
|
+
kimi
|
113
|
+
kimse
|
114
|
+
kırk
|
115
|
+
milyar
|
116
|
+
milyon
|
117
|
+
mu
|
118
|
+
mü
|
119
|
+
mı
|
120
|
+
nasıl
|
121
|
+
ne
|
122
|
+
neden
|
123
|
+
nedenle
|
124
|
+
nerde
|
125
|
+
nerede
|
126
|
+
nereye
|
127
|
+
niye
|
128
|
+
niçin
|
129
|
+
o
|
130
|
+
olan
|
131
|
+
olarak
|
132
|
+
oldu
|
133
|
+
olduğu
|
134
|
+
olduğunu
|
135
|
+
olduklarını
|
136
|
+
olmadı
|
137
|
+
olmadığı
|
138
|
+
olmak
|
139
|
+
olması
|
140
|
+
olmayan
|
141
|
+
olmaz
|
142
|
+
olsa
|
143
|
+
olsun
|
144
|
+
olup
|
145
|
+
olur
|
146
|
+
olursa
|
147
|
+
oluyor
|
148
|
+
on
|
149
|
+
ona
|
150
|
+
ondan
|
151
|
+
onlar
|
152
|
+
onlardan
|
153
|
+
onları
|
154
|
+
onların
|
155
|
+
onu
|
156
|
+
onun
|
157
|
+
otuz
|
158
|
+
oysa
|
159
|
+
öyle
|
160
|
+
pek
|
161
|
+
rağmen
|
162
|
+
sadece
|
163
|
+
sanki
|
164
|
+
sekiz
|
165
|
+
seksen
|
166
|
+
sen
|
167
|
+
senden
|
168
|
+
seni
|
169
|
+
senin
|
170
|
+
siz
|
171
|
+
sizden
|
172
|
+
sizi
|
173
|
+
sizin
|
174
|
+
şey
|
175
|
+
şeyden
|
176
|
+
şeyi
|
177
|
+
şeyler
|
178
|
+
şöyle
|
179
|
+
şu
|
180
|
+
şuna
|
181
|
+
şunda
|
182
|
+
şundan
|
183
|
+
şunları
|
184
|
+
şunu
|
185
|
+
tarafından
|
186
|
+
trilyon
|
187
|
+
tüm
|
188
|
+
üç
|
189
|
+
üzere
|
190
|
+
var
|
191
|
+
vardı
|
192
|
+
ve
|
193
|
+
veya
|
194
|
+
ya
|
195
|
+
yani
|
196
|
+
yapacak
|
197
|
+
yapılan
|
198
|
+
yapılması
|
199
|
+
yapıyor
|
200
|
+
yapmak
|
201
|
+
yaptı
|
202
|
+
yaptığı
|
203
|
+
yaptığını
|
204
|
+
yaptıkları
|
205
|
+
yedi
|
206
|
+
yerine
|
207
|
+
yetmiş
|
208
|
+
yine
|
209
|
+
yirmi
|
210
|
+
yoksa
|
211
|
+
yüz
|
212
|
+
zaten
|
@@ -0,0 +1,29 @@
|
|
1
|
+
#
|
2
|
+
# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
|
3
|
+
#
|
4
|
+
# Add entries to this file in order to override the statistical model in terms
|
5
|
+
# of segmentation, readings and part-of-speech tags. Notice that entries do
|
6
|
+
# not have weights since they are always used when found. This is by-design
|
7
|
+
# in order to maximize ease-of-use.
|
8
|
+
#
|
9
|
+
# Entries are defined using the following CSV format:
|
10
|
+
# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
|
11
|
+
#
|
12
|
+
# Notice that a single half-width space separates tokens and readings, and
|
13
|
+
# that the number tokens and readings must match exactly.
|
14
|
+
#
|
15
|
+
# Also notice that multiple entries with the same <text> is undefined.
|
16
|
+
#
|
17
|
+
# Whitespace only lines are ignored. Comments are not allowed on entry lines.
|
18
|
+
#
|
19
|
+
|
20
|
+
# Custom segmentation for kanji compounds
|
21
|
+
日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
|
22
|
+
関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
|
23
|
+
|
24
|
+
# Custom segmentation for compound katakana
|
25
|
+
トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
|
26
|
+
ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
|
27
|
+
|
28
|
+
# Custom reading for former sumo wrestler
|
29
|
+
朝青龍,朝青龍,アサショウリュウ,カスタム人名
|
@@ -0,0 +1,246 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
# Syntax:
|
14
|
+
# "source" => "target"
|
15
|
+
# "source".length() > 0 (source cannot be empty.)
|
16
|
+
# "target".length() >= 0 (target can be empty.)
|
17
|
+
|
18
|
+
# example:
|
19
|
+
# "??" => "A"
|
20
|
+
# "\u00C0" => "A"
|
21
|
+
# "\u00C0" => "\u0041"
|
22
|
+
# "??" => "ss"
|
23
|
+
# "\t" => " "
|
24
|
+
# "\n" => ""
|
25
|
+
|
26
|
+
# ?? => A
|
27
|
+
"\u00C0" => "A"
|
28
|
+
|
29
|
+
# ?? => A
|
30
|
+
"\u00C1" => "A"
|
31
|
+
|
32
|
+
# ?? => A
|
33
|
+
"\u00C2" => "A"
|
34
|
+
|
35
|
+
# ?? => A
|
36
|
+
"\u00C3" => "A"
|
37
|
+
|
38
|
+
# ?? => A
|
39
|
+
"\u00C4" => "A"
|
40
|
+
|
41
|
+
# ?? => A
|
42
|
+
"\u00C5" => "A"
|
43
|
+
|
44
|
+
# ?? => AE
|
45
|
+
"\u00C6" => "AE"
|
46
|
+
|
47
|
+
# ?? => C
|
48
|
+
"\u00C7" => "C"
|
49
|
+
|
50
|
+
# ?? => E
|
51
|
+
"\u00C8" => "E"
|
52
|
+
|
53
|
+
# ?? => E
|
54
|
+
"\u00C9" => "E"
|
55
|
+
|
56
|
+
# ?? => E
|
57
|
+
"\u00CA" => "E"
|
58
|
+
|
59
|
+
# ?? => E
|
60
|
+
"\u00CB" => "E"
|
61
|
+
|
62
|
+
# ?? => I
|
63
|
+
"\u00CC" => "I"
|
64
|
+
|
65
|
+
# ?? => I
|
66
|
+
"\u00CD" => "I"
|
67
|
+
|
68
|
+
# ?? => I
|
69
|
+
"\u00CE" => "I"
|
70
|
+
|
71
|
+
# ?? => I
|
72
|
+
"\u00CF" => "I"
|
73
|
+
|
74
|
+
# ?? => IJ
|
75
|
+
"\u0132" => "IJ"
|
76
|
+
|
77
|
+
# ?? => D
|
78
|
+
"\u00D0" => "D"
|
79
|
+
|
80
|
+
# ?? => N
|
81
|
+
"\u00D1" => "N"
|
82
|
+
|
83
|
+
# ?? => O
|
84
|
+
"\u00D2" => "O"
|
85
|
+
|
86
|
+
# ?? => O
|
87
|
+
"\u00D3" => "O"
|
88
|
+
|
89
|
+
# ?? => O
|
90
|
+
"\u00D4" => "O"
|
91
|
+
|
92
|
+
# ?? => O
|
93
|
+
"\u00D5" => "O"
|
94
|
+
|
95
|
+
# ?? => O
|
96
|
+
"\u00D6" => "O"
|
97
|
+
|
98
|
+
# ?? => O
|
99
|
+
"\u00D8" => "O"
|
100
|
+
|
101
|
+
# ?? => OE
|
102
|
+
"\u0152" => "OE"
|
103
|
+
|
104
|
+
# ??
|
105
|
+
"\u00DE" => "TH"
|
106
|
+
|
107
|
+
# ?? => U
|
108
|
+
"\u00D9" => "U"
|
109
|
+
|
110
|
+
# ?? => U
|
111
|
+
"\u00DA" => "U"
|
112
|
+
|
113
|
+
# ?? => U
|
114
|
+
"\u00DB" => "U"
|
115
|
+
|
116
|
+
# ?? => U
|
117
|
+
"\u00DC" => "U"
|
118
|
+
|
119
|
+
# ?? => Y
|
120
|
+
"\u00DD" => "Y"
|
121
|
+
|
122
|
+
# ?? => Y
|
123
|
+
"\u0178" => "Y"
|
124
|
+
|
125
|
+
# ?? => a
|
126
|
+
"\u00E0" => "a"
|
127
|
+
|
128
|
+
# ?? => a
|
129
|
+
"\u00E1" => "a"
|
130
|
+
|
131
|
+
# ?? => a
|
132
|
+
"\u00E2" => "a"
|
133
|
+
|
134
|
+
# ?? => a
|
135
|
+
"\u00E3" => "a"
|
136
|
+
|
137
|
+
# ?? => a
|
138
|
+
"\u00E4" => "a"
|
139
|
+
|
140
|
+
# ?? => a
|
141
|
+
"\u00E5" => "a"
|
142
|
+
|
143
|
+
# ?? => ae
|
144
|
+
"\u00E6" => "ae"
|
145
|
+
|
146
|
+
# ?? => c
|
147
|
+
"\u00E7" => "c"
|
148
|
+
|
149
|
+
# ?? => e
|
150
|
+
"\u00E8" => "e"
|
151
|
+
|
152
|
+
# ?? => e
|
153
|
+
"\u00E9" => "e"
|
154
|
+
|
155
|
+
# ?? => e
|
156
|
+
"\u00EA" => "e"
|
157
|
+
|
158
|
+
# ?? => e
|
159
|
+
"\u00EB" => "e"
|
160
|
+
|
161
|
+
# ?? => i
|
162
|
+
"\u00EC" => "i"
|
163
|
+
|
164
|
+
# ?? => i
|
165
|
+
"\u00ED" => "i"
|
166
|
+
|
167
|
+
# ?? => i
|
168
|
+
"\u00EE" => "i"
|
169
|
+
|
170
|
+
# ?? => i
|
171
|
+
"\u00EF" => "i"
|
172
|
+
|
173
|
+
# ?? => ij
|
174
|
+
"\u0133" => "ij"
|
175
|
+
|
176
|
+
# ?? => d
|
177
|
+
"\u00F0" => "d"
|
178
|
+
|
179
|
+
# ?? => n
|
180
|
+
"\u00F1" => "n"
|
181
|
+
|
182
|
+
# ?? => o
|
183
|
+
"\u00F2" => "o"
|
184
|
+
|
185
|
+
# ?? => o
|
186
|
+
"\u00F3" => "o"
|
187
|
+
|
188
|
+
# ?? => o
|
189
|
+
"\u00F4" => "o"
|
190
|
+
|
191
|
+
# ?? => o
|
192
|
+
"\u00F5" => "o"
|
193
|
+
|
194
|
+
# ?? => o
|
195
|
+
"\u00F6" => "o"
|
196
|
+
|
197
|
+
# ?? => o
|
198
|
+
"\u00F8" => "o"
|
199
|
+
|
200
|
+
# ?? => oe
|
201
|
+
"\u0153" => "oe"
|
202
|
+
|
203
|
+
# ?? => ss
|
204
|
+
"\u00DF" => "ss"
|
205
|
+
|
206
|
+
# ?? => th
|
207
|
+
"\u00FE" => "th"
|
208
|
+
|
209
|
+
# ?? => u
|
210
|
+
"\u00F9" => "u"
|
211
|
+
|
212
|
+
# ?? => u
|
213
|
+
"\u00FA" => "u"
|
214
|
+
|
215
|
+
# ?? => u
|
216
|
+
"\u00FB" => "u"
|
217
|
+
|
218
|
+
# ?? => u
|
219
|
+
"\u00FC" => "u"
|
220
|
+
|
221
|
+
# ?? => y
|
222
|
+
"\u00FD" => "y"
|
223
|
+
|
224
|
+
# ?? => y
|
225
|
+
"\u00FF" => "y"
|
226
|
+
|
227
|
+
# ??? => ff
|
228
|
+
"\uFB00" => "ff"
|
229
|
+
|
230
|
+
# ??? => fi
|
231
|
+
"\uFB01" => "fi"
|
232
|
+
|
233
|
+
# ??? => fl
|
234
|
+
"\uFB02" => "fl"
|
235
|
+
|
236
|
+
# ??? => ffi
|
237
|
+
"\uFB03" => "ffi"
|
238
|
+
|
239
|
+
# ??? => ffl
|
240
|
+
"\uFB04" => "ffl"
|
241
|
+
|
242
|
+
# ??? => ft
|
243
|
+
"\uFB05" => "ft"
|
244
|
+
|
245
|
+
# ??? => st
|
246
|
+
"\uFB06" => "st"
|