1 | #!/bin/sh
|
---|
2 |
|
---|
3 | # Install Antiword to be able to extract text from .doc
|
---|
4 | cd /tmp
|
---|
5 | wget http://www.winfield.demon.nl/linux/antiword-0.37.tar.gz
|
---|
6 | tar xvzf antiword-0.37.tar.gz
|
---|
7 | cd antiword-0.37
|
---|
8 | make
|
---|
9 | cd ..
|
---|
10 |
|
---|
11 | # Install pdfmine to be able to extract text from .pdf
|
---|
12 | wget http://pypi.python.org/packages/source/p/pdfminer/pdfminer-20110515.tar.gz
|
---|
13 | tar xvzf pdfminer-20110515.tar.gz
|
---|
14 | cd pdfminer-20110515
|
---|
15 | python setup.py install
|
---|
16 | cd ..
|
---|
17 |
|
---|
18 | # Install pyth to be able to extract text from .rtf
|
---|
19 | wget http://pypi.python.org/packages/source/p/pyth/pyth-0.5.6.tar.gz
|
---|
20 | tar xvzf pyth-0.5.6.tar.gz
|
---|
21 | cd pyth-0.5.6
|
---|
22 | python setup.py install
|
---|
23 | cd ..
|
---|
24 |
|
---|
25 | # Install xlrd to be able to extract text from .xls
|
---|
26 | wget http://pypi.python.org/packages/source/x/xlrd/xlrd-0.9.2.tar.gz
|
---|
27 | tar xvzf xlrd-0.9.2.tar.gz
|
---|
28 | cd xlrd-0.9.2
|
---|
29 | python setup.py install
|
---|
30 | cd ~/
|
---|
31 |
|
---|
32 | # Install other dependencies for Solr/Sunburnt
|
---|
33 | apt-get install python-httplib2
|
---|
34 | apt-get install python-pip
|
---|
35 | apt-get install libxml2 libxslt-dev libxml2-dev
|
---|
36 | pip install lxml==3.0.2
|
---|
37 |
|
---|
38 | # Install Solr
|
---|
39 | # @Todo: Deploymen in Production server: install at other place
|
---|
40 | wget http://mirror.reverse.net/pub/apache/lucene/solr/4.3.1/solr-4.3.1.tgz
|
---|
41 | tar xvzf solr-4.3.1.tgz
|
---|
42 | cd solr-4.3.1/
|
---|
43 | mv example solr
|
---|
44 | cd solr/solr/collection1/conf
|
---|
45 |
|
---|
46 | # Configure Solr according to Eden
|
---|
47 | sed -i 's|<dataDir>${solr.data.dir:}</dataDir>|<dataDir>'$HOME'/web2py/applications/eden/indices</dataDir>|' solrconfig.xml
|
---|
48 | sed -i 's|<field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>|<field name="filetype" type="text_general" indexed="true" stored="true"/>|' schema.xml
|
---|
49 |
|
---|
50 | sed -i 's|<field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>|field name="tablename" type="text_general" indexed="true" stored="true"/>|' schema.xml
|
---|
51 |
|
---|
52 | sed -i 's|<field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />|<field name="filename" type="text_general" indexed="true" stored="true"/>|' schema.xml
|
---|
53 |
|
---|
54 | sed -i 's|<copyField source="features" dest="text"/>|<copyField source="filetype" dest="text"/>|' schema.xml
|
---|
55 |
|
---|
56 | sed -i 's|<copyField source="includes" dest="text"/>|<copyField source="filename" dest="text"/>|' schema.xml
|
---|
57 |
|
---|
58 | cd /tmp
|
---|
59 | # Install sunburnt
|
---|
60 | apt-get install git
|
---|
61 | git clone http://github.com/tow/sunburnt.git
|
---|
62 | cd sunburnt
|
---|
63 | python setup.py install
|
---|
64 |
|
---|