blob: 798fc50a267f21836ae47ebd03e039fe22f1b913 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
|
#!/bin/sh
cmd="$1"
shift
do_download() {
dir="$1"
msk="$2"
nquire -lst ftp.ncbi.nlm.nih.gov "$dir" |
grep "$msk" |
skip-if-file-exists | tee /dev/stderr |
nquire -asp ftp.ncbi.nlm.nih.gov "$dir"
}
prepare_book_list() {
echo "<OpenAccessSubset>"
while IFS=$'\t' read pth titl pblshr dt accn upd
do
if [ -n "$accn" ]
then
echo " <Book>"
echo " <Accn>$accn</Accn>"
echo " <Path>$pth</Path>"
echo " <Title>$titl</Title>"
echo " </Book>"
fi
done
echo "</OpenAccessSubset>"
}
case "$cmd" in
-h | -help | --help | help )
cat <<EOF
USAGE: $0
pmc-oa | pmc-bioc | bioconcepts | generif | meshtree | oa-list | oa-book | carotene
EOF
exit 0
;;
pmc-oa | -pmc-oa )
do_download "pub/pmc/oa_bulk" "xml.tar.gz"
exit 0
;;
pmc-bioc | -pmc-bioc )
do_download "pub/wilbur/BioC-PMC" "xml_unicode.tar.gz"
exit 0
;;
bioconcepts | -bioconcepts )
do_download "pub/lu/PubTatorCentral" "chemical2pubtatorcentral.gz"
do_download "pub/lu/PubTatorCentral" "disease2pubtatorcentral.gz"
do_download "pub/lu/PubTatorCentral" "gene2pubtatorcentral.gz"
exit 0
;;
generif | -generif | generifs | -generifs )
do_download "gene/GeneRIF" "generifs_basic.gz"
do_download "gene/DATA" "gene_info.gz"
if [ ! -f "geneconv.xml" ]
then
gunzip -c gene_info.gz |
grep -v NEWENTRY |
grep -v GeneID |
cut -f 2,3,9 |
transmute -t2x -set Set -rec Rec Code Name Desc |
transmute -format indent > geneconv.xml
fi
if [ ! -f "genename.txt" ]
then
cat geneconv.xml |
xtract -pattern Rec -element Code Name > genename.txt
fi
exit 0
;;
meshtree | -meshtree )
if [ ! -f "desc2021.xml" ]
then
echo "desc2021.xml"
nquire -dwn "ftp://nlmpubs.nlm.nih.gov" "online/mesh/MESH_FILES/xmlmesh" "desc2021.zip"
unzip -qq desc2021.zip
rm desc2021.zip
chmod og-wx desc2021.xml
chmod u-x desc2021.xml
fi
if [ ! -f "pa2021.xml" ]
then
echo "pa2021.xml"
nquire -dwn "ftp://nlmpubs.nlm.nih.gov" "online/mesh/MESH_FILES/xmlmesh" "pa2021.xml"
fi
if [ ! -f "qual2021.xml" ]
then
echo "qual2021.xml"
nquire -dwn "ftp://nlmpubs.nlm.nih.gov" "online/mesh/MESH_FILES/xmlmesh" "qual2021.xml"
fi
if [ ! -f "supp2021.xml" ]
then
echo "supp2021.xml"
nquire -dwn "ftp://nlmpubs.nlm.nih.gov" "online/mesh/MESH_FILES/xmlmesh" "supp2021.zip"
unzip -qq supp2021.zip
rm supp2021.zip
chmod og-wx supp2021.xml
chmod u-x supp2021.xml
fi
if [ ! -f "meshconv.xml" ]
then
cat supp2021.xml |
xtract -wrp "Set,Rec" -pattern SupplementalRecord \
-if "SupplementalRecord@SCRClass" -eq 1 \
-or "SupplementalRecord@SCRClass" -eq 3 \
-wrp "Code" -element "SupplementalRecord/SupplementalRecordUI" \
-wrp "Name" -encode "SupplementalRecordName/String" \
-wrp "Term" -encode "Term/String" > meshtemp.xml
cat desc2021.xml |
xtract -wrp "Set,Rec" -pattern DescriptorRecord \
-wrp "Code" -element "DescriptorRecord/DescriptorUI" \
-wrp "Name" -first "DescriptorName/String" \
-wrp "Term" -encode "Term/String" \
-wrp "Tree" -element "TreeNumberList/TreeNumber" >> meshtemp.xml
cat meshtemp.xml | xtract -wrp Set -pattern Rec -sort Code |
transmute -format indent > meshconv.xml
rm meshtemp.xml
fi
if [ ! -f "meshtree.txt" ]
then
cat meshconv.xml |
xtract -pattern Rec -if Tree -element Code -sep "," -element Tree > meshtree.txt
fi
if [ ! -f "meshname.txt" ]
then
cat meshconv.xml |
xtract -pattern Rec -if Name -element Code -sep "," -element Name > meshname.txt
fi
if [ ! -f "chemconv.xml" ]
then
cat supp2021.xml |
xtract -wrp "Set,Rec" -pattern SupplementalRecord \
-if "SupplementalRecord@SCRClass" -eq 1 \
-wrp "Code" -element "SupplementalRecord/SupplementalRecordUI" \
-wrp "Name" -encode "SupplementalRecordName/String" \
-wrp "Term" -encode "Term/String" > chemtemp.xml
cat desc2021.xml |
xtract -wrp "Set,Rec" -pattern DescriptorRecord \
-if TreeNumber -starts-with D \
-wrp "Code" -element "DescriptorRecord/DescriptorUI" \
-wrp "Name" -first "DescriptorName/String" \
-wrp "Term" -encode "Term/String" \
-wrp "Tree" -element "TreeNumberList/TreeNumber" >> chemtemp.xml
cat chemtemp.xml | xtract -wrp Set -pattern Rec -sort Code |
transmute -format indent > chemconv.xml
rm chemtemp.xml
fi
if [ ! -f "diszconv.xml" ]
then
cat supp2021.xml |
xtract -wrp "Set,Rec" -pattern SupplementalRecord \
-if "SupplementalRecord@SCRClass" -eq 3 \
-wrp "Code" -element "SupplementalRecord/SupplementalRecordUI" \
-wrp "Name" -encode "SupplementalRecordName/String" \
-wrp "Term" -encode "Term/String" > disztemp.xml
cat desc2021.xml |
xtract -wrp "Set,Rec" -pattern DescriptorRecord \
-if TreeNumber -starts-with C \
-wrp "Code" -element "DescriptorRecord/DescriptorUI" \
-wrp "Name" -first "DescriptorName/String" \
-wrp "Term" -encode "Term/String" \
-wrp "Tree" -element "TreeNumberList/TreeNumber" >> disztemp.xml
cat disztemp.xml | xtract -wrp Set -pattern Rec -sort Code |
transmute -format indent > diszconv.xml
rm disztemp.xml
fi
exit 0
;;
oa-list | -oa-list )
if [ ! -f "books.xml" ]
then
nquire -ftp ftp.ncbi.nlm.nih.gov pub/litarch file_list.txt |
prepare_book_list > books.xml
fi
exit 0
;;
oa-book | -oa-book )
accn="$1"
shift
if [ ! -f "books.xml" ]
then
nquire -ftp ftp.ncbi.nlm.nih.gov pub/litarch file_list.txt |
prepare_book_list > books.xml
fi
cat books.xml |
xtract -pattern Book -if Accn -equals "$accn" -element Path |
while read pth
do
if [ ! -f "$pth" ]
then
nquire -dwn ftp.ncbi.nlm.nih.gov "pub/litarch" "$pth"
fi
done
exit 0
;;
carotene | -carotene )
if [ ! -f "carotene.xml" ]
then
nquire -asp ftp.ncbi.nlm.nih.gov "entrez/entrezdirect/samples" "carotene.xml.zip"
unzip -qq carotene.xml.zip
rm carotene.xml.zip
fi
exit 0
;;
-natural-earth )
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/cultural/ne_10m_admin_0_countries.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/cultural/ne_10m_admin_0_disputed_areas.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/cultural/ne_10m_admin_1_states_provinces.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/physical/ne_10m_geography_marine_polys.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/physical/ne_10m_lakes.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/physical/ne_10m_minor_islands.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/physical/ne_10m_reefs.zip"
curl -Ls -O "https://www.naturalearthdata.com/http//www.naturalearthdata.com/download/10m/physical/ne_10m_rivers_lake_centerlines.zip"
exit 0
;;
* )
break
;;
esac
|