/[webpac2]/trunk/conf/ffcasopisi/modify.pl
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Annotation of /trunk/conf/ffcasopisi/modify.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1278 - (hide annotations)
Thu Aug 27 17:32:11 2009 UTC (14 years, 9 months ago) by mglavica
File MIME type: text/plain
File size: 6851 byte(s)
journals data conversion (final conversion done with this version)

1 mglavica 1268 # this is pseudo hash/yaml format for regex mappings
2    
3     11
4     '*'
5 mglavica 1273 'regex:^\s+' => ''
6 mglavica 1268
7     102
8     '*'
9     'regex:^AL$' => 'aa'
10 mglavica 1273 'regex:^AM$' => 'ai'
11     'regex:^AR$' => 'ag'
12 mglavica 1268 'regex:^AT$' => 'au'
13     'regex:^AU$' => 'at'
14 mglavica 1273 'regex:^AUT$' => ''
15     'regex:^B$' => ''
16 mglavica 1268 'regex:^BA$' => 'bn'
17 mglavica 1273 'regex:^BA; HR$' => ''
18     'regex:^BE$' => 'be'
19 mglavica 1268 'regex:^BG$' => 'bu'
20     'regex:^BH$' => 'ba'
21     'regex:^ BH$' => 'ba'
22 mglavica 1273 'regex:^BiH$' => 'ba'
23     'regex:^BIH$' => 'ba'
24 mglavica 1268 'regex:^BL$' => 'bu'
25 mglavica 1273 'regex:^BO$' => 'bo'
26 mglavica 1268 'regex:^BOS$' => 'bn'
27     'regex:^CA$' => 'cn'
28 mglavica 1273 'regex:^CAN$' => 'cn'
29 mglavica 1268 'regex:^CG$' => 'cg'
30     'regex:^CH$' => 'sz'
31 mglavica 1273 'regex:^CRO$' => 'ci'
32     'regex:^CS$' => 'yu'
33     'regex:^CU$' => 'cu'
34 mglavica 1268 'regex:^CZ$' => 'xr'
35     'regex:^D$' => 'gw'
36 mglavica 1273 'regex:^De$' => 'gw'
37 mglavica 1268 'regex:^DE$' => 'gw'
38 mglavica 1273 'regex:^DE/AT$' => ''
39     'regex:^DEU$' => 'gw'
40     'regex:^DK$' => 'dk'
41     'regex:^DU$' => ''
42     'regex:^EG$' => 'ua'
43     'regex:^EN$' => 'uk'
44     'regex:^Eng$' => 'uk'
45     'regex:^ENG$' => 'uk'
46 mglavica 1268 'regex:^ES$' => 'sp'
47 mglavica 1273 'regex:^ET$' => ''
48     'regex:^EU$' => ''
49     'regex:^F$' => ''
50     'regex:^FI$' => 'fi'
51     'regex:^FIN$' => 'fi'
52 mglavica 1268 'regex:^FR$' => 'fr'
53 mglavica 1273 'regex:^FRA$' => 'fr'
54 mglavica 1268 'regex:^GB$' => 'uk'
55 mglavica 1273 'regex:^GBR$' => 'uk'
56     'regex:^GE$' => 'gw'
57     'regex:^GER$' => 'gw'
58     'regex:^hr$' => 'ci'
59 mglavica 1268 'regex:^Hr$' => 'ci'
60     'regex:^HR$' => 'ci'
61 mglavica 1273 'regex:^HR-IT$' => ''
62     'regex:^HR; IT$' => ''
63     'regex:^HRV$' => 'ci'
64     'regex:^HR, YU$' => ''
65 mglavica 1268 'regex:^HU$' => 'hu'
66 mglavica 1273 'regex:^I$' => ''
67     'regex:^IN$' => 'ii'
68     'regex:^IR$' => 'ir'
69 mglavica 1268 'regex:^IT$' => 'it'
70 mglavica 1273 'regex:^ITA$' => 'it'
71     'regex:^IZ$' => ''
72     'regex:^JA$' => 'jp'
73     'regex:^JAP$' => 'jp'
74 mglavica 1268 'regex:^JU$' => 'yu'
75 mglavica 1273 'regex:^Jugoslavija$' => ''
76     'regex:^KR$' => 'ko'
77     'regex:^LV$' => 'lv'
78     'regex:^MA$' => 'mr'
79 mglavica 1268 'regex:^MK$' => 'xn'
80 mglavica 1273 'regex:^MT$' => 'mm'
81     'regex:^MX$' => 'mx'
82 mglavica 1268 'regex:^NL$' => 'ne'
83 mglavica 1273 'regex:^NO$' => 'no'
84 mglavica 1278 'regex:^.panjolska$' => 'sp'
85 mglavica 1268 'regex:^Pl$' => 'pl'
86     'regex:^PL$' => 'pl'
87 mglavica 1273 'regex:^PT$' => 'po'
88 mglavica 1268 'regex:^RF$' => 'ru'
89 mglavica 1273 'regex:^RM$' => 'rm'
90 mglavica 1268 'regex:^RO$' => 'rm'
91 mglavica 1273 'regex:^ROM$' => 'rm'
92 mglavica 1268 'regex:^RU$' => 'ru'
93 mglavica 1273 'regex:^RUM$' => 'ru'
94     'regex:^SAD$' => 'us'
95     'regex:^SC$' => 'se'
96     'regex:^SCC$' => ''
97     'regex:^SCG$' => ''
98     'regex:^SE$' => 'sw'
99 mglavica 1268 'regex:^SI$' => 'xv'
100 mglavica 1273 'regex:^SiCG$' => ''
101     'regex:^SICG$' => ''
102 mglavica 1268 'regex:^SK$' => 'xo'
103     'regex:^SL$' => 'sl'
104 mglavica 1273 'regex:^SLO$' => 'sl'
105     'regex:^SLV$' => ''
106     'regex:^SP$' => ''
107 mglavica 1268 'regex:^SR$' => 'sr'
108 mglavica 1273 'regex:^Srbija$' => 'sr'
109     'regex:^SRBIJA$' => 'sr'
110     'regex:^SS$' => ''
111     'regex:^SU$' => ''
112 mglavica 1268 'regex:^SW$' => 'sw'
113 mglavica 1273 'regex:^SZ$' => ''
114     'regex:^TN$' => 'ti'
115     'regex:^TR$' => 'tu'
116 mglavica 1268 'regex:^UA$' => 'un'
117     'regex:^UK$' => 'uk'
118 mglavica 1273 'regex:^us$' => 'us'
119 mglavica 1268 'regex:^US$' => 'us'
120     'regex:^USA$' => 'us'
121 mglavica 1273 'regex:^Vojvodina$' => 'sr'
122 mglavica 1268 'regex:^YU$' => 'yu'
123 mglavica 1273 'regex:^YU;CS$' => ''
124     'regex:^YUG$' => 'yu'
125     'regex:^YU, HR$' => ''
126     'regex:^YU, HR$' => ''
127     'regex:^YU/HR$' => ''
128     'regex:^YU, SI$' => ''
129     'regex:^YU, Srbija$' => ''
130 mglavica 1278 'regex:^YU .SRBIJA.$' => ''
131 mglavica 1273 'regex:^YU, SRBIJA$' => ''
132 mglavica 1268
133 mglavica 1273
134 mglavica 1268 200
135     '*'
136     '^e' => ' : '
137     '^d' => ' = '
138     '^k' => ' : '
139 mglavica 1273
140 mglavica 1268 210
141 mglavica 1273 '*'
142     ' : ' => ' :^b'
143     ' ; ' => ' ;^a'
144     '^c' => ' :^b'
145     '^d' => ',^c'
146     '^c'
147     'regex:^\s+' => ''
148 mglavica 1268 ' - ' => '-'
149     ' -' => '-'
150     '- ' => '-'
151     ', ' => '-'
152     '.' => ''
153 mglavica 1273 '_ _' => '--'
154    
155    
156 mglavica 1268 326
157 mglavica 1273 'regex:^1$' => '|'
158     'regex:^1.$' => '|'
159     'regex:^10$' => '10'
160     'regex:^10.$' => '10'
161 mglavica 1268 'regex:^10g$' => '10'
162     'regex:^12$' => 'm1'
163 mglavica 1278 'regex:^1-2 broja godi.nje$' => 'g2'
164     'regex:^12g ..uvez:1953-1957...uvez:1958-1961.$' => '|'
165 mglavica 1273 'regex:^19g$' => '19'
166     'regex:^1g$' => '|'
167     'regex:^1m$' => '|'
168 mglavica 1278 'regex:^26.godi.nje$' => '|'
169 mglavica 1273 'regex:^2g$' => '|'
170 mglavica 1278 'regex:^2. godi.nje 2 broja$' => 'g2'
171 mglavica 1273 'regex:^3.$' => '|'
172 mglavica 1278 'regex:^35.1996.$' => '|'
173 mglavica 1273 'regex:^3g$' => '|'
174     'regex:^4.$' => '|'
175     'regex:^4g$' => '|'
176     'regex:^52$' => '|'
177     'regex:^64$' => '|'
178     'regex:^6g$' => '|'
179 mglavica 1278 'regex:^.etvrtgodi.nje$' => 'g4'
180 mglavica 1273 'regex:^dg$' => '|'
181     'regex:^Dva puta tjedno utorkom i subotom$' => 't2us'
182 mglavica 1278 'regex:^Dvogodi.njak$' => '2g'
183 mglavica 1273 'regex:^g$' => '|'
184     'regex:^g1$' => 'g1'
185     'regex:^g1.$' => 'g1'
186     'regex:^g10$' => '10'
187     'regex:^g 10$' => '10'
188     'regex:^g11$' => '11'
189     'regex:^g12$' => 'm1'
190 mglavica 1278 'regex:^g1godi.njak$' => 'g1'
191     'regex:^g1 godi.njak$' => 'g1'
192     'regex:^g1.godi.njak.$' => 'g1'
193 mglavica 1273 'regex:^g1 nr$' => 'nr'
194     'regex:^g1- nr$' => 'nr'
195 mglavica 1278 'regex:^g1. nr$' => 'nr'
196     'regex:^g1.nr.$' => 'nr'
197 mglavica 1273 'regex:^g2$' => 'g2'
198     'regex:^g2.$' => 'g2'
199     'regex:^g2 $' => 'g2'
200     'regex:^g2.$' => 'g2'
201     'regex:^g20$' => '20'
202 mglavica 1278 'regex:^g24$' => 'm2'
203 mglavica 1273 'regex:^g26$' => '26'
204 mglavica 1278 'regex:^g2.godi.nje 2 broja.$' => 'g2'
205     'regex:^g2 polugodi.njak$' => 'g2'
206     'regex:^g2.polugodi.njak.$' => 'g2'
207 mglavica 1273 'regex:^g3$' => 'g3'
208     'regex:^g3.$' => 'g3'
209     'regex:^g3.$' => 'g3'
210 mglavica 1278 'regex:^g3 .etveromjese.nik$' => 'g3'
211     'regex:^g3.godi.nje 3 broja.$' => 'g3'
212     'regex:^g3.tromjese.nik.$' => 'g3'
213 mglavica 1273 'regex:^g4$' => 'g4'
214     'regex:^g4.$' => 'g4'
215     'regex:^g4.$' => 'g4'
216     'regex:^g4-5$' => 'g4'
217 mglavica 1278 'regex:^g4 tromjese.nik$' => 'g4'
218 mglavica 1273 'regex:^g4.tromjese.+$' => 'g4'
219     'regex:^g5$' => 'g5'
220     'regex:^g5.$' => 'g5'
221     'regex:^g50$' => '|'
222 mglavica 1278 'regex:^g5.godi.nje 5 brojeva.$' => 'g5'
223 mglavica 1273 'regex:^g6$' => 'g6'
224 mglavica 1268 'regex:^ g6$' => 'g6'
225 mglavica 1273 'regex:^g6.$' => 'g6'
226 mglavica 1278 'regex:^g6 dvomjese.nik$' => 'g6'
227     'regex:^g6.dvomjese.nik.$' => 'g6'
228     'regex:^g6 polugodi.njak$' => 'g6'
229 mglavica 1273 'regex:^g8$' => 'g8'
230     'regex:^g9$' => 'g9'
231     'regex:^g9.$' => 'g9'
232     'regex:^gm1$' => '|'
233     'regex:^gm4$' => '|'
234     'regex:^gnepoznato$' => '|'
235 mglavica 1268 'regex:^gnr$' => 'nr'
236 mglavica 1278 'regex:^Godi.nje$' => 'g1'
237     'regex:^godi.nje 4 broja$' => 'g4'
238 mglavica 1273 'regex:^Izlazi neredovito$' => 'nr'
239     'regex:^m1$' => 'm1'
240     'regex:^m1.$' => 'm1'
241 mglavica 1268 'regex:^m12$' => 'm1'
242 mglavica 1278 'regex:^m1.mjese.nik.$' => 'm1'
243 mglavica 1273 'regex:^m2$' => 'm2'
244     'regex:^m2.dvotjednik.$' => 'm2'
245     'regex:^m3$' => 'm3'
246     'regex:^m4$' => 't1'
247     'regex:^Neredovito$' => 'nr'
248     'regex:^nr$' => 'nr'
249     'regex:^nr $' => 'nr'
250     'regex:^nr.$' => 'nr'
251     'regex:^Nr$' => 'nr'
252     'regex:^NR$' => 'nr'
253 mglavica 1278 'regex:^nr .kvartalno.$' => 'nr'
254 mglavica 1273 'regex:^nr neredovito$' => 'nr'
255     'regex:^nr.neredovito.$' => 'nr'
256     'regex:^od 1993 g4, do 1993 g2$' => '|'
257     'regex:^Polutjedno$' => 't2'
258     'regex:^t1$' => 't1'
259 mglavica 1268 'regex:^tjednik$' => 't1'
260     'regex:^Tjednik$' => 't1'
261 mglavica 1278 'regex:^Tri puta mjese.no$' => 'm3'
262     'regex:^tromjese.nik$' => 'g4'
263     'regex:^Tromjese.nik$' => 'g4'
264     'regex:^Tromjese.no$' => 'g4'
265    
266     421
267     '*'
268     'regex:^' => '^a'
269    
270     675
271     '*'
272     'regex:^' => '^a'
273    
274     702
275     '*'
276     '^b' => ', '
277     '^d' => ', '
278     '^f' => ', '
279    
280     865
281     '*'
282     'regex:^' => '^u'

  ViewVC Help
Powered by ViewVC 1.1.26