Skip to content

Commit a89dbb8

Browse files
committed
Add translate additional examples #589
1 parent d1c791c commit a89dbb8

28 files changed

+1300
-1089
lines changed

metafacture-runner/src/main/dist/examples/gnd/crisscross-connections/Ts1-Tg1-without-crisscross.flux

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -10,12 +10,11 @@ as-lines|
1010
catch-object-exception|
1111
decode-pica|
1212
batch-log(batchsize="100000")|
13-
morph(FLUX_DIR + "extract.xml")|
13+
fix(FLUX_DIR + "extract.fix")|
1414
stream-to-triples(redirect="true")|
1515
sort-triples(by="subject")|
1616
collect-triples|
17-
morph(FLUX_DIR + "output.xml")|
17+
fix(FLUX_DIR + "output.fix")|
1818
batch-log(batchsize="100000")|
19-
stream-to-triples|
20-
template("${o}")|
19+
encode-csv(noquotes="true",separator=";")|
2120
write(out);
Lines changed: 216 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,216 @@
1+
do put_macro("gndPersonCombinedLabel") # in contrast to morph this is not normalizing utf 8
2+
paste("$[field].@combinedLabel","$[field].P", "$[field].a", "~, ", "$[field].d", join_char:"")
3+
replace_all("$[field].@combinedLabel",", $","")
4+
if exists("$[field].c")
5+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].c")
6+
end
7+
copy_field("$[field].n","$[field].add.$append")
8+
copy_field("$[field].l","$[field].add.$append")
9+
copy_field("$[field].g","$[field].add.$append")
10+
join_field("$[field].add",", ")
11+
replace_all("$[field].add","^(.*)$"," <$1>")
12+
if exists("$[field].add")
13+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
14+
end
15+
copy_field("$[field].@combinedLabel", "$[out]")
16+
end
17+
18+
do put_macro("gndCorporationCombinedLabel") # in contrast to morph this is not normalizing utf 8
19+
if any_equal("@type","b")
20+
copy_field("$[field].n","$[field].add.$append")
21+
copy_field("$[field].l","$[field].add.$append")
22+
copy_field("$[field].g","$[field].add.$append")
23+
join_field("$[field].add",", ")
24+
replace_all("$[field].add","^(.*)$"," <$1>")
25+
copy_field("$[field].a","$[field].@combinedLabel")
26+
if exists("$[field].add")
27+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
28+
end
29+
if exists("$[field].b")
30+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "~ / ", "$[field].b", join_char:"")
31+
end
32+
copy_field("$[field].@combinedLabel", "$[out]")
33+
end
34+
end
35+
36+
do put_macro("gndConferenceCombinedLabel") # in contrast to morph this is not normalizing utf 8
37+
if any_equal("@type","f")
38+
copy_field("$[field].g","$[field].add.$append")
39+
copy_field("$[field].n","$[field].add.$append")
40+
copy_field("$[field].d","$[field].add.$append")
41+
copy_field("$[field].c","$[field].add.$append")
42+
join_field("$[field].add",", ")
43+
replace_all("$[field].add","^(.*)$"," <$1>")
44+
if exists("$[field].b")
45+
paste("$[field].@combinedLabel", "$[field].a", "~ / ", "$[field].b", join_char:"")
46+
else
47+
copy_field("$[field].a","$[field].@combinedLabel")
48+
end
49+
if exists("$[field].add")
50+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
51+
end
52+
copy_field("$[field].@combinedLabel", "$[out]")
53+
end
54+
end
55+
56+
57+
do put_macro("gndGeolocationCombinedLabel") # in contrast to morph this is not normalizing utf 8
58+
if any_equal("@type","g")
59+
copy_field("$[field].z","$[field].add.$append")
60+
copy_field("$[field].g","$[field].add.$append")
61+
join_field("$[field].add",", ")
62+
replace_all("$[field].add","^(.*)$"," <$1>")
63+
if exists("$[field].b")
64+
paste("$[field].@combinedLabel", "$[field].a", "~ / ", "$[field].x", join_char:"")
65+
else
66+
copy_field("$[field].a","$[field].@combinedLabel")
67+
end
68+
if exists("$[field].add")
69+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
70+
end
71+
copy_field("$[field].@combinedLabel", "$[out]")
72+
end
73+
end
74+
75+
do put_macro("gndSubjectCombinedLabel") # in contrast to morph this is not normalizing utf 8
76+
if any_equal("@type","s")
77+
copy_field("$[field].g","$[field].add.$append")
78+
join_field("$[field].add",", ")
79+
replace_all("$[field].add","^(.*)$"," <$1>")
80+
copy_field("$[field].a","$[field].@combinedLabel")
81+
if exists("$[field].add")
82+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
83+
end
84+
copy_field("$[field].@combinedLabel", "$[out]")
85+
end
86+
end
87+
88+
do put_macro("gndWorkCombinedLabel") # in contrast to morph this is not normalizing utf 8
89+
if any_equal("@type","u")
90+
copy_field("$[field].f","$[field].add.$append")
91+
copy_field("$[field].g","$[field].add.$append")
92+
copy_field("$[field].n","$[field].add.$append")
93+
join_field("$[field].add",", ")
94+
replace_all("$[field].add","^(.*)$"," <$1>")
95+
if exists("$[field].p")
96+
paste("$[field].@combinedLabel", "$[field].a", "~ / ", "$[field].p", join_char:"")
97+
else
98+
copy_field("$[field].a","$[field].@combinedLabel")
99+
end
100+
if exists("$[field].add")
101+
paste("$[field].@combinedLabel", "$[field].@combinedLabel", "$[field].add", join_char:"")
102+
end
103+
copy_field("$[field].@combinedLabel", "$[out]")
104+
end
105+
end
106+
107+
copy_field("[email protected]","@type")
108+
substring("@type","1","1")
109+
110+
# pn
111+
do list(path:"028A","var":"PERSONNAME")
112+
call_macro("gndPersonCombinedLabel",field:"PERSONNAME",out:"@name")
113+
end
114+
do list(path:"028@","var":"PERSONNAME")
115+
call_macro("gndPersonCombinedLabel",field:"PERSONNAME",out:"@syn.$append")
116+
end
117+
118+
do list(path:"029A","var":"CORPORATIONNAME")
119+
call_macro("gndCorporationCombinedLabel",field:"CORPORATIONNAME",out:"@name")
120+
end
121+
do list(path:"029@","var":"CORPORATIONNAME")
122+
call_macro("gndCorporationCombinedLabel",field:"CORPORATIONNAME",out:"@syn.$append")
123+
end
124+
125+
#f
126+
do list(path:"030A","var":"CONFERENCENAME")
127+
call_macro("gndConferenceCombinedLabel",field:"CONFERENCENAME",out:"@name")
128+
end
129+
do list(path:"030@","var":"CONFERENCENAME")
130+
call_macro("gndConferenceCombinedLabel",field:"CONFERENCENAME",out:"@syn.$append")
131+
end
132+
133+
#s
134+
do list(path:"065A","var":"GEONAME")
135+
call_macro("gndGeolocationCombinedLabel",field:"GEONAME",out:"@name")
136+
end
137+
do list(path:"065@","var":"GEONAME")
138+
call_macro("gndGeolocationCombinedLabel",field:"GEONAME",out:"@syn.$append")
139+
end
140+
141+
# g
142+
do list(path:"041A","var":"SUBJECTNAME")
143+
call_macro("gndSubjectCombinedLabel",field:"SUBJECTNAME",out:"@name")
144+
end
145+
do list(path:"041@","var":"SUBJECTNAME")
146+
call_macro("gndSubjectCombinedLabel",field:"SUBJECTNAME",out:"@syn.$append")
147+
end
148+
149+
#u
150+
do list(path:"022A","var":"WORKNAME")
151+
call_macro("gndWorkCombinedLabel",field:"WORKNAME",out:"@name")
152+
end
153+
do list(path:"022@","var":"WORKNAME")
154+
call_macro("gndWorkCombinedLabel",field:"WORKNAME",out:"@syn.$append")
155+
end
156+
157+
# copy_field("008A.a","teilbest")
158+
159+
do list(path:"041A*|041A","var":"$i") # Until https://github.com/metafacture/metafacture-core/issues/651 is fixed one hass to add "041A"
160+
trim("$i.9")
161+
to_var("$i.9","ref")
162+
if exists("$i.9")
163+
add_field("{to:$[ref]}refed","")
164+
end
165+
end
166+
167+
copy_field("@name","gnd.name")
168+
copy_field("[email protected]","gnd.katlevel")
169+
substring("gnd.katlevel","2","1")
170+
copy_field("[email protected]","gnd.satzart")
171+
substring("gnd.satzart","0","2")
172+
173+
# copy_field("[email protected]","gnd.id")
174+
copy_field("007K.0","gnd.nid")
175+
do list(path:"042A", "var":"$i")
176+
do list(path:"$i.a","var":"$a")
177+
copy_field("$a","gnd.sys.$append")
178+
end
179+
end
180+
replace_all("gnd.sys.*",";",",")
181+
join_field("gnd.sys"," | ")
182+
unless exists("gnd.sys")
183+
add_field("gnd.sys","")
184+
end
185+
186+
do list(path:"004B", "var":"$i")
187+
do list(path:"$i.a","var":"$a")
188+
copy_field("$a","gnd.ent.$append")
189+
end
190+
end
191+
join_field("gnd.ent"," | ")
192+
unless exists("gnd.ent")
193+
add_field("gnd.ent","")
194+
end
195+
196+
197+
copy_field("@syn","gnd.syn")
198+
join_field("gnd.syn"," | ")
199+
unless exists("gnd.syn")
200+
add_field("gnd.syn","")
201+
end
202+
203+
unless any_match("004B.a", "gib|gio|giw")
204+
copy_field("004B.a","filter1")
205+
end
206+
207+
if any_match("[email protected]", "Ts1|Tg1")
208+
copy_field("[email protected]","filter2")
209+
end
210+
211+
unless exists("037G.c")
212+
add_field("filter3","ok")
213+
end
214+
215+
216+
retain("{to*","gnd","filter*","@*")

0 commit comments

Comments
 (0)