bigindex-solr 1.2.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (100) hide show
  1. data/.document +5 -0
  2. data/.gitignore +8 -0
  3. data/MIT-LICENSE +20 -0
  4. data/README.rdoc +73 -0
  5. data/Rakefile +49 -0
  6. data/VERSION +1 -0
  7. data/bigindex-solr.gemspec +141 -0
  8. data/examples/bigindex.yml +9 -0
  9. data/install.rb +17 -0
  10. data/lib/bigindex-solr.rb +32 -0
  11. data/lib/bigindex-solr/tasks.rb +3 -0
  12. data/lib/tasks/bigindex_solr.rake +55 -0
  13. data/schema.xml +126 -0
  14. data/solr/CHANGES.txt +562 -0
  15. data/solr/LICENSE.txt +608 -0
  16. data/solr/NOTICE.txt +57 -0
  17. data/solr/etc/jetty.xml +206 -0
  18. data/solr/etc/webdefault.xml +379 -0
  19. data/solr/lib/commons-codec-1.3.jar +0 -0
  20. data/solr/lib/commons-csv-0.1-SNAPSHOT.jar +0 -0
  21. data/solr/lib/commons-fileupload-1.2.jar +0 -0
  22. data/solr/lib/commons-io-1.2.jar +0 -0
  23. data/solr/lib/easymock.jar +0 -0
  24. data/solr/lib/jetty-6.1.3.jar +0 -0
  25. data/solr/lib/jetty-util-6.1.3.jar +0 -0
  26. data/solr/lib/jsp-2.1/ant-1.6.5.jar +0 -0
  27. data/solr/lib/jsp-2.1/core-3.1.1.jar +0 -0
  28. data/solr/lib/jsp-2.1/jsp-2.1.jar +0 -0
  29. data/solr/lib/jsp-2.1/jsp-api-2.1.jar +0 -0
  30. data/solr/lib/lucene-analyzers-2007-05-20_00-04-53.jar +0 -0
  31. data/solr/lib/lucene-core-2007-05-20_00-04-53.jar +0 -0
  32. data/solr/lib/lucene-highlighter-2007-05-20_00-04-53.jar +0 -0
  33. data/solr/lib/lucene-snowball-2007-05-20_00-04-53.jar +0 -0
  34. data/solr/lib/lucene-spellchecker-2007-05-20_00-04-53.jar +0 -0
  35. data/solr/lib/servlet-api-2.4.jar +0 -0
  36. data/solr/lib/servlet-api-2.5-6.1.3.jar +0 -0
  37. data/solr/lib/xpp3-1.1.3.4.O.jar +0 -0
  38. data/solr/solr/README.txt +52 -0
  39. data/solr/solr/bin/abc +176 -0
  40. data/solr/solr/bin/abo +176 -0
  41. data/solr/solr/bin/backup +108 -0
  42. data/solr/solr/bin/backupcleaner +142 -0
  43. data/solr/solr/bin/commit +128 -0
  44. data/solr/solr/bin/optimize +129 -0
  45. data/solr/solr/bin/readercycle +129 -0
  46. data/solr/solr/bin/rsyncd-disable +77 -0
  47. data/solr/solr/bin/rsyncd-enable +76 -0
  48. data/solr/solr/bin/rsyncd-start +145 -0
  49. data/solr/solr/bin/rsyncd-stop +105 -0
  50. data/solr/solr/bin/scripts-util +83 -0
  51. data/solr/solr/bin/snapcleaner +148 -0
  52. data/solr/solr/bin/snapinstaller +168 -0
  53. data/solr/solr/bin/snappuller +248 -0
  54. data/solr/solr/bin/snappuller-disable +77 -0
  55. data/solr/solr/bin/snappuller-enable +77 -0
  56. data/solr/solr/bin/snapshooter +109 -0
  57. data/solr/solr/conf/admin-extra.html +31 -0
  58. data/solr/solr/conf/protwords.txt +21 -0
  59. data/solr/solr/conf/schema.xml +126 -0
  60. data/solr/solr/conf/scripts.conf +24 -0
  61. data/solr/solr/conf/solrconfig.xml +458 -0
  62. data/solr/solr/conf/stopwords.txt +57 -0
  63. data/solr/solr/conf/synonyms.txt +31 -0
  64. data/solr/solr/conf/xslt/example.xsl +132 -0
  65. data/solr/solr/conf/xslt/example_atom.xsl +63 -0
  66. data/solr/solr/conf/xslt/example_rss.xsl +62 -0
  67. data/solr/solr/data/development/index/_a.fdt +0 -0
  68. data/solr/solr/data/development/index/_a.fdx +0 -0
  69. data/solr/solr/data/development/index/_a.fnm +2 -0
  70. data/solr/solr/data/development/index/_a.frq +1 -0
  71. data/solr/solr/data/development/index/_a.nrm +1 -0
  72. data/solr/solr/data/development/index/_a.prx +0 -0
  73. data/solr/solr/data/development/index/_a.tii +0 -0
  74. data/solr/solr/data/development/index/_a.tis +0 -0
  75. data/solr/solr/data/development/index/_a_1.del +0 -0
  76. data/solr/solr/data/development/index/_b.fdt +0 -0
  77. data/solr/solr/data/development/index/_b.fdx +0 -0
  78. data/solr/solr/data/development/index/_b.fnm +2 -0
  79. data/solr/solr/data/development/index/_b.frq +0 -0
  80. data/solr/solr/data/development/index/_b.nrm +1 -0
  81. data/solr/solr/data/development/index/_b.prx +0 -0
  82. data/solr/solr/data/development/index/_b.tii +0 -0
  83. data/solr/solr/data/development/index/_b.tis +0 -0
  84. data/solr/solr/data/development/index/_b_1.del +0 -0
  85. data/solr/solr/data/development/index/_c.fdt +0 -0
  86. data/solr/solr/data/development/index/_c.fdx +0 -0
  87. data/solr/solr/data/development/index/_c.fnm +2 -0
  88. data/solr/solr/data/development/index/_c.frq +1 -0
  89. data/solr/solr/data/development/index/_c.nrm +1 -0
  90. data/solr/solr/data/development/index/_c.prx +0 -0
  91. data/solr/solr/data/development/index/_c.tii +0 -0
  92. data/solr/solr/data/development/index/_c.tis +0 -0
  93. data/solr/solr/data/development/index/_c_1.del +0 -0
  94. data/solr/solr/data/development/index/segments.gen +0 -0
  95. data/solr/solr/data/development/index/segments_q +0 -0
  96. data/solr/start.jar +0 -0
  97. data/solr/webapps/solr.war +0 -0
  98. data/spec/bigindex-solr_spec.rb +7 -0
  99. data/spec/spec_helper.rb +9 -0
  100. metadata +163 -0
@@ -0,0 +1,108 @@
1
+ #!/bin/bash
2
+ #
3
+ # Licensed to the Apache Software Foundation (ASF) under one or more
4
+ # contributor license agreements. See the NOTICE file distributed with
5
+ # this work for additional information regarding copyright ownership.
6
+ # The ASF licenses this file to You under the Apache License, Version 2.0
7
+ # (the "License"); you may not use this file except in compliance with
8
+ # the License. You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+ #
18
+ # Shell script to make a backup of a Solr Lucene collection.
19
+
20
+ orig_dir=$(pwd)
21
+ cd ${0%/*}/..
22
+ solr_root=$(pwd)
23
+ cd ${orig_dir}
24
+
25
+ unset data_dir user verbose debug
26
+ . ${solr_root}/bin/scripts-util
27
+
28
+ # set up variables
29
+ prog=${0##*/}
30
+ log=${solr_root}/logs/${prog}.log
31
+
32
+ # define usage string
33
+ USAGE="\
34
+ usage: $prog [-d dir] [-u username] [-v]
35
+ -d specify directory holding index data
36
+ -u specify user to sudo to before running script
37
+ -v increase verbosity
38
+ -V output debugging info
39
+ "
40
+
41
+ # parse args
42
+ while getopts d:u:vV OPTION
43
+ do
44
+ case $OPTION in
45
+ d)
46
+ data_dir="$OPTARG"
47
+ ;;
48
+ u)
49
+ user="$OPTARG"
50
+ ;;
51
+ v)
52
+ verbose="v"
53
+ ;;
54
+ V)
55
+ debug="V"
56
+ ;;
57
+ *)
58
+ echo "$USAGE"
59
+ exit 1
60
+ esac
61
+ done
62
+
63
+ [[ -n $debug ]] && set -x
64
+
65
+ # use default value for data_dir if not specified
66
+ # relative path starts at ${solr_root}
67
+ if [[ -z ${data_dir} ]]
68
+ then
69
+ data_dir=${solr_root}/data
70
+ elif [[ "`echo ${data_dir}|cut -c1`" != "/" ]]
71
+ then
72
+ data_dir=${solr_root}/${data_dir}
73
+ fi
74
+
75
+ fixUser "$@"
76
+
77
+ start=`date +"%s"`
78
+
79
+ logMessage started by $oldwhoami
80
+ logMessage command: $0 $@
81
+
82
+ name=backup.`date +"%Y%m%d%H%M%S"`
83
+ temp=temp-${name}
84
+
85
+ if [[ -d ${data_dir}/${name} ]]
86
+ then
87
+ logMessage backup directory ${data_dir}/${name} already exists
88
+ logExit aborted 1
89
+ fi
90
+
91
+ if [[ -d ${data_dir}/${temp} ]]
92
+ then
93
+ logMessage backingup of ${data_dir}/${name} in progress
94
+ logExit aborted 1
95
+ fi
96
+
97
+ # clean up after INT/TERM
98
+ trap 'echo cleaning up, please wait ...;/bin/rm -rf ${data_dir}/${name} ${data_dir}/${temp};logExit aborted 13' INT TERM
99
+
100
+ logMessage making backup ${data_dir}/${name}
101
+
102
+ # make a backup using hard links into temporary location
103
+ # then move it into place atomically
104
+ cp -lr ${data_dir}/index ${data_dir}/${temp}
105
+ mv ${data_dir}/${temp} ${data_dir}/${name}
106
+
107
+ logExit ended 0
108
+
@@ -0,0 +1,142 @@
1
+ #!/bin/bash
2
+ #
3
+ # Licensed to the Apache Software Foundation (ASF) under one or more
4
+ # contributor license agreements. See the NOTICE file distributed with
5
+ # this work for additional information regarding copyright ownership.
6
+ # The ASF licenses this file to You under the Apache License, Version 2.0
7
+ # (the "License"); you may not use this file except in compliance with
8
+ # the License. You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+ #
18
+ # Shell script to clean up backups of a Solr Lucene collection.
19
+
20
+ orig_dir=$(pwd)
21
+ cd ${0%/*}/..
22
+ solr_root=$(pwd)
23
+ cd ${orig_dir}
24
+
25
+ unset days num data_dir user verbose debug
26
+ . ${solr_root}/bin/scripts-util
27
+
28
+ # set up variables
29
+ prog=${0##*/}
30
+ log=${solr_root}/logs/${prog}.log
31
+
32
+ # define usage string
33
+ USAGE="\
34
+ usage: $prog -D <days> | -N <num> [-d dir] [-u username] [-v]
35
+ -D <days> cleanup backups more than <days> days old
36
+ -N <num> keep the most recent <num> number of backups and
37
+ cleanup up the remaining ones that are not being pulled
38
+ -d specify directory holding index data
39
+ -u specify user to sudo to before running script
40
+ -v increase verbosity
41
+ -V output debugging info
42
+ "
43
+
44
+ # parse args
45
+ while getopts D:N:d:u:vV OPTION
46
+ do
47
+ case $OPTION in
48
+ D)
49
+ days="$OPTARG"
50
+ ;;
51
+ N)
52
+ num="$OPTARG"
53
+ ;;
54
+ d)
55
+ data_dir="$OPTARG"
56
+ ;;
57
+ u)
58
+ user="$OPTARG"
59
+ ;;
60
+ v)
61
+ verbose="v"
62
+ ;;
63
+ V)
64
+ debug="V"
65
+ ;;
66
+ *)
67
+ echo "$USAGE"
68
+ exit 1
69
+ esac
70
+ done
71
+
72
+ [[ -n $debug ]] && set -x
73
+
74
+ if [[ -z ${days} && -z ${num} ]]
75
+ then
76
+ echo "$USAGE"
77
+ exit 1
78
+ fi
79
+
80
+ fixUser "$@"
81
+
82
+ # use default value for data_dir if not specified
83
+ # relative path starts at ${solr_root}
84
+ if [[ -z ${data_dir} ]]
85
+ then
86
+ data_dir=${solr_root}/data
87
+ elif [[ "`echo ${data_dir}|cut -c1`" != "/" ]]
88
+ then
89
+ data_dir=${solr_root}/${data_dir}
90
+ fi
91
+
92
+ function remove
93
+ {
94
+ logMessage removing backup $1
95
+ /bin/rm -rf $1
96
+ }
97
+
98
+ start=`date +"%s"`
99
+
100
+ logMessage started by $oldwhoami
101
+ logMessage command: $0 $@
102
+
103
+ # trap control-c
104
+ trap 'echo "caught INT/TERM, exiting now but partial cleanup may have already occured";logExit aborted 13' INT TERM
105
+
106
+ if [[ -n ${days} ]]
107
+ then
108
+ #is maxdepth supported?
109
+ find ${data_dir} -maxdepth 0 -name foobar >/dev/null 2>&1
110
+ if [ $? = 0 ]; then
111
+ maxdepth="-maxdepth 1"
112
+ else
113
+ unset maxdepth
114
+ fi
115
+
116
+ logMessage cleaning up backups more than ${days} days old
117
+ for i in `find ${data_dir} ${maxdepth} -name 'backup.*' -mtime +${days} -print`
118
+ do
119
+ remove $i
120
+ done
121
+ elif [[ -n ${num} ]]
122
+ then
123
+ logMessage cleaning up all backups except for the most recent ${num} ones
124
+ unset backups count
125
+ backups=`ls -cd ${data_dir}/backup.* 2>/dev/null`
126
+ if [[ $? == 0 ]]
127
+ then
128
+ count=`echo $backups|wc -w`
129
+ startpos=`expr $num + 1`
130
+ if [[ $count -gt $num ]]
131
+ then
132
+ for i in `echo $backups|cut -f${startpos}- -d" "`
133
+ do
134
+ remove $i
135
+ done
136
+ fi
137
+ fi
138
+ fi
139
+
140
+ logExit ended 0
141
+
142
+
@@ -0,0 +1,128 @@
1
+ #!/bin/bash
2
+ #
3
+ # Licensed to the Apache Software Foundation (ASF) under one or more
4
+ # contributor license agreements. See the NOTICE file distributed with
5
+ # this work for additional information regarding copyright ownership.
6
+ # The ASF licenses this file to You under the Apache License, Version 2.0
7
+ # (the "License"); you may not use this file except in compliance with
8
+ # the License. You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+ #
18
+ # Shell script to force a commit of all changes since last commit
19
+ # for a Solr server
20
+
21
+ orig_dir=$(pwd)
22
+ cd ${0%/*}/..
23
+ solr_root=$(pwd)
24
+ cd ${orig_dir}
25
+ curl_url=""
26
+
27
+ unset solr_hostname solr_port webapp_name user verbose debug solr_url
28
+ . ${solr_root}/bin/scripts-util
29
+
30
+ # set up variables
31
+ prog=${0##*/}
32
+ log=${solr_root}/logs/${prog}.log
33
+
34
+ # define usage string
35
+ USAGE="\
36
+ usage: $prog [-h hostname] [-p port] [-w webapp_name] [-u username] [-U url] [-v] [-V]
37
+ -h specify Solr hostname (defaults to localhost)
38
+ -p specify Solr port number
39
+ -w specify name of Solr webapp (defaults to solr)
40
+ -u specify user to sudo to before running script
41
+ -U specify full update url (overrides -h,-p,-w parameters)
42
+ -v increase verbosity
43
+ -V output debugging info
44
+ "
45
+
46
+ # parse args
47
+ while getopts h:p:w:u:U:vV OPTION
48
+ do
49
+ case $OPTION in
50
+ h)
51
+ solr_hostname="$OPTARG"
52
+ ;;
53
+ p)
54
+ solr_port="$OPTARG"
55
+ ;;
56
+ w)
57
+ webapp_name="$OPTARG"
58
+ ;;
59
+ u)
60
+ user="$OPTARG"
61
+ ;;
62
+ U)
63
+ solr_url="$OPTARG"
64
+ ;;
65
+ v)
66
+ verbose="v"
67
+ ;;
68
+ V)
69
+ debug="V"
70
+ ;;
71
+ *)
72
+ echo "$USAGE"
73
+ exit 1
74
+ esac
75
+ done
76
+
77
+ [[ -n $debug ]] && set -x
78
+
79
+ if [[ -n ${solr_url} ]]
80
+ then
81
+ curl_url=${solr_url}
82
+ else
83
+ if [[ -z ${solr_port} ]]
84
+ then
85
+ echo "Solr port number missing in $confFile or command line."
86
+ echo "$USAGE"
87
+ exit 1
88
+ fi
89
+
90
+ # use default hostname if not specified
91
+ if [[ -z ${solr_hostname} ]]
92
+ then
93
+ solr_hostname=localhost
94
+ fi
95
+
96
+ # use default webapp name if not specified
97
+ if [[ -z ${webapp_name} ]]
98
+ then
99
+ webapp_name=solr
100
+ fi
101
+ curl_url=http://${solr_hostname}:${solr_port}/${webapp_name}/update
102
+ fi
103
+
104
+ fixUser "$@"
105
+
106
+ start=`date +"%s"`
107
+
108
+ logMessage started by $oldwhoami
109
+ logMessage command: $0 $@
110
+
111
+ rs=`curl ${curl_url} -s -H 'Content-type:text/xml; charset=utf-8' -d "<commit/>"`
112
+ if [[ $? != 0 ]]
113
+ then
114
+ logMessage failed to connect to Solr server at ${curl_url}
115
+ logMessage commit failed
116
+ logExit failed 1
117
+ fi
118
+
119
+ # check status of commit request
120
+ echo $rs | grep '<result.*status="0"' > /dev/null 2>&1
121
+ if [[ $? != 0 ]]
122
+ then
123
+ logMessage commit request to Solr at ${curl_url} failed:
124
+ logMessage $rs
125
+ logExit failed 2
126
+ fi
127
+
128
+ logExit ended 0
@@ -0,0 +1,129 @@
1
+ #!/bin/bash
2
+ #
3
+ # Licensed to the Apache Software Foundation (ASF) under one or more
4
+ # contributor license agreements. See the NOTICE file distributed with
5
+ # this work for additional information regarding copyright ownership.
6
+ # The ASF licenses this file to You under the Apache License, Version 2.0
7
+ # (the "License"); you may not use this file except in compliance with
8
+ # the License. You may obtain a copy of the License at
9
+ #
10
+ # http://www.apache.org/licenses/LICENSE-2.0
11
+ #
12
+ # Unless required by applicable law or agreed to in writing, software
13
+ # distributed under the License is distributed on an "AS IS" BASIS,
14
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ # See the License for the specific language governing permissions and
16
+ # limitations under the License.
17
+ #
18
+ # Shell script to force a optimized commit of all changes since last commit
19
+ # for a Solr server
20
+
21
+ orig_dir=$(pwd)
22
+ cd ${0%/*}/..
23
+ solr_root=$(pwd)
24
+ cd ${orig_dir}
25
+ curl_url=""
26
+
27
+ unset solr_hostname solr_port webapp_name user verbose debug solr_url
28
+ . ${solr_root}/bin/scripts-util
29
+
30
+ # set up variables
31
+ prog=${0##*/}
32
+ log=${solr_root}/logs/${prog}.log
33
+
34
+ # define usage string
35
+ USAGE="\
36
+ usage: $prog [-h hostname] [-p port] [-u username] [-U url] [-v] [-V]
37
+ -h specify Solr hostname (defaults to localhost)
38
+ -p specify Solr port number
39
+ -w specify name of Solr webapp (defaults to solr)
40
+ -u specify user to sudo to before running script
41
+ -U specify full update url (overrides -h,-p,-w parameters)
42
+ -v increase verbosity
43
+ -V output debugging info
44
+ "
45
+
46
+ # parse args
47
+ originalargs="$@"
48
+ while getopts h:p:w:u:U:vV OPTION
49
+ do
50
+ case $OPTION in
51
+ h)
52
+ solr_hostname="$OPTARG"
53
+ ;;
54
+ p)
55
+ solr_port="$OPTARG"
56
+ ;;
57
+ w)
58
+ webapp_name="$OPTARG"
59
+ ;;
60
+ u)
61
+ user="$OPTARG"
62
+ ;;
63
+ U)
64
+ solr_url="$OPTARG"
65
+ ;;
66
+ v)
67
+ verbose="v"
68
+ ;;
69
+ V)
70
+ debug="V"
71
+ ;;
72
+ *)
73
+ echo "$USAGE"
74
+ exit 1
75
+ esac
76
+ done
77
+
78
+ [[ -n $debug ]] && set -x
79
+
80
+ if [[ -n ${solr_url} ]]
81
+ then
82
+ curl_url=${solr_url}
83
+ else
84
+ if [[ -z ${solr_port} ]]
85
+ then
86
+ echo "Solr port number missing in $confFile or command line."
87
+ echo "$USAGE"
88
+ exit 1
89
+ fi
90
+
91
+ # use default hostname if not specified
92
+ if [[ -z ${solr_hostname} ]]
93
+ then
94
+ solr_hostname=localhost
95
+ fi
96
+
97
+ # use default webapp name if not specified
98
+ if [[ -z ${webapp_name} ]]
99
+ then
100
+ webapp_name=solr
101
+ fi
102
+ curl_url=http://${solr_hostname}:${solr_port}/${webapp_name}/update
103
+ fi
104
+
105
+ fixUser "$@"
106
+
107
+ start=`date +"%s"`
108
+
109
+ logMessage started by $oldwhoami
110
+ logMessage command: $0 $@
111
+
112
+ rs=`curl ${curl_url} -s -H 'Content-type:text/xml; charset=utf-8' -d "<optimize/>"`
113
+ if [[ $? != 0 ]]
114
+ then
115
+ logMessage failed to connect to Solr server at ${curl_url}
116
+ logMessage optimize failed
117
+ logExit failed 1
118
+ fi
119
+
120
+ # check status of optimize request
121
+ rc=`echo $rs|cut -f2 -d'"'`
122
+ if [[ $? != 0 ]]
123
+ then
124
+ logMessage optimize request to Solr at ${curl_url} failed:
125
+ logMessage $rs
126
+ logExit failed 2
127
+ fi
128
+
129
+ logExit ended 0