mirror of
https://github.com/gnosygnu/xowa.git
synced 2026-03-02 03:49:30 +00:00
update
This commit is contained in:
@@ -441,8 +441,8 @@ app.bldr.cmds {
|
||||
|
||||
add ('simple.wikipedia.org' , 'wiki.mass_parse.exec') {
|
||||
cfg {
|
||||
num_wkrs = 8; load_all_templates = 'y'; cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2016-08-01 01:02:03';
|
||||
load_all_imglinks = 'y';
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_all_imglinks = 'y'; indexer_enabled = 'y';
|
||||
cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-04-01 00:00:00'
|
||||
|
||||
// uncomment the following 3 lines if using the build script as a "worker" helping a "server"
|
||||
// num_pages_in_pool = 32000;
|
||||
@@ -521,7 +521,8 @@ app.bldr.cmds {
|
||||
add ('www.wikidata.org' , 'wiki.page_props');
|
||||
add ('www.wikidata.org' , 'wiki.categorylinks');
|
||||
add ('www.wikidata.org' , 'wiki.redirect') {commit_interval = 1000; progress_interval = 100; cleanup_interval = 100;}
|
||||
// add ('www.wikidata.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
add ('www.wikidata.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
|
||||
add ('commons.wikimedia.org' , 'util.cleanup') {delete_all = 'y';}
|
||||
add ('commons.wikimedia.org' , 'util.download') {dump_type = 'pages-articles';}
|
||||
add ('commons.wikimedia.org' , 'util.download') {dump_type = 'image';}
|
||||
@@ -535,7 +536,8 @@ app.bldr.cmds {
|
||||
add ('commons.wikimedia.org' , 'file.page_regy') {build_commons = 'y'}
|
||||
add ('commons.wikimedia.org' , 'wiki.page_dump.make');
|
||||
add ('commons.wikimedia.org' , 'wiki.redirect') {commit_interval = 1000; progress_interval = 100; cleanup_interval = 100;}
|
||||
// add ('commons.wikimedia.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
add ('commons.wikimedia.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'pages-articles';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'pagelinks';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'categorylinks';}
|
||||
@@ -543,6 +545,7 @@ app.bldr.cmds {
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'image';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'imagelinks';}
|
||||
*/
|
||||
|
||||
/*
|
||||
// en.wikipedia.org
|
||||
add ('en.wikipedia.org' , 'text.init');
|
||||
@@ -568,28 +571,25 @@ app.bldr.cmds {
|
||||
}
|
||||
}
|
||||
}
|
||||
add ('en.wikipedia.org' , 'search.word__link_count')
|
||||
add ('en.wikipedia.org' , 'search.word__link_count');
|
||||
add ('en.wikipedia.org' , 'wiki.page_props');
|
||||
add ('en.wikipedia.org' , 'wiki.categorylinks');
|
||||
*/
|
||||
/*
|
||||
|
||||
add ('en.wikipedia.org' , 'file.page_regy') {build_commons = 'n'}
|
||||
// add ('en.wikipedia.org' , 'wiki.mass_parse.resume');
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.init') {cfg {ns_ids = '0|4|100|14|8';}}
|
||||
// add ('en.wikipedia.org' , 'wiki.mass_parse.resume');
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.exec') {cfg {
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_ifexists_ns = '*'; cleanup_interval = 25; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-01-01 01:02:03';}
|
||||
// num_wkrs = 1; load_all_templates = 'n'; load_all_imglnks = 'n'; cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2016-07-28 01:02:03';}
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_all_imglinks = 'y'; indexer_enabled = 'y';
|
||||
cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-04-01 00:00:00'
|
||||
}
|
||||
}
|
||||
*/
|
||||
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.make');
|
||||
*/
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'file.lnki_temp') {
|
||||
commit_interval = 10000; progress_interval = 50; cleanup_interval = 50; select_size = 25;
|
||||
ns_ids = '0|4|14|100|12|8|6|10|828|108|118|446|710|2300|2302|2600';
|
||||
hdump_bldr {enabled = 'y'; hzip_enabled = 'y'; hzip_diff = 'y';}
|
||||
}
|
||||
*/
|
||||
/*
|
||||
// SELECT * FROM image ORDER BY img_timestamp DESC LIMIT 20; // 20170306194400
|
||||
// SELECT * FROM page WHERE page_namespace = 6 ORDER BY page_touched DESC LIMIT 20; // 20170302024207
|
||||
// SELECT * FROM xowa_cfg WHERE cfg_key = 'props.modified_latest';
|
||||
add ('commons.wikimedia.org' , 'file.page_regy') {build_commons = 'y'}
|
||||
add ('en.wikipedia.org' , 'file.page_regy') {build_commons = 'n';}
|
||||
add ('en.wikipedia.org' , 'file.lnki_regy');
|
||||
@@ -597,9 +597,15 @@ app.bldr.cmds {
|
||||
add ('en.wikipedia.org' , 'file.orig_regy');
|
||||
add ('en.wikipedia.org' , 'file.xfer_temp.thumb');
|
||||
|
||||
// SELECT * FROM orig_regy WHERE lnki_ttl = 'BSicon_CONTr.svg';
|
||||
// SELECT * FROM page_regy WHERE src_ttl = 'BSicon_CONTr.svg';
|
||||
// SELECT Count(*) FROM xfer_regy WHERE xfer_status = 0;
|
||||
// SELECT * FROM xfer_regy WHERE xfer_status = 0 AND lnki_page_id = 372692; --en.w:Featured_picture_candidates
|
||||
|
||||
add ('en.wikipedia.org' , 'file.xfer_regy');
|
||||
add ('en.wikipedia.org' , 'file.xfer_regy_update');
|
||||
*/
|
||||
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'file.fsdb_make') {
|
||||
commit_interval = 1000; progress_interval = 200; select_interval = 10000;
|
||||
@@ -630,7 +636,10 @@ app.bldr.run;
|
||||
2016-10-12: explicitly set web_access_enabled to y
|
||||
</li>
|
||||
<li>
|
||||
2017-02-02: updated script for multi-threaded version and new options
|
||||
2017-02-02: added multi-threaded version and new options
|
||||
</li>
|
||||
<li>
|
||||
2017-05-12: added full-text search
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
|
||||
@@ -441,8 +441,8 @@ app.bldr.cmds {
|
||||
|
||||
add ('simple.wikipedia.org' , 'wiki.mass_parse.exec') {
|
||||
cfg {
|
||||
num_wkrs = 8; load_all_templates = 'y'; cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2016-08-01 01:02:03';
|
||||
load_all_imglinks = 'y';
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_all_imglinks = 'y'; indexer_enabled = 'y';
|
||||
cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-04-01 00:00:00'
|
||||
|
||||
// uncomment the following 3 lines if using the build script as a "worker" helping a "server"
|
||||
// num_pages_in_pool = 32000;
|
||||
@@ -521,7 +521,8 @@ app.bldr.cmds {
|
||||
add ('www.wikidata.org' , 'wiki.page_props');
|
||||
add ('www.wikidata.org' , 'wiki.categorylinks');
|
||||
add ('www.wikidata.org' , 'wiki.redirect') {commit_interval = 1000; progress_interval = 100; cleanup_interval = 100;}
|
||||
// add ('www.wikidata.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
add ('www.wikidata.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
|
||||
add ('commons.wikimedia.org' , 'util.cleanup') {delete_all = 'y';}
|
||||
add ('commons.wikimedia.org' , 'util.download') {dump_type = 'pages-articles';}
|
||||
add ('commons.wikimedia.org' , 'util.download') {dump_type = 'image';}
|
||||
@@ -535,7 +536,8 @@ app.bldr.cmds {
|
||||
add ('commons.wikimedia.org' , 'file.page_regy') {build_commons = 'y'}
|
||||
add ('commons.wikimedia.org' , 'wiki.page_dump.make');
|
||||
add ('commons.wikimedia.org' , 'wiki.redirect') {commit_interval = 1000; progress_interval = 100; cleanup_interval = 100;}
|
||||
// add ('commons.wikimedia.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
add ('commons.wikimedia.org' , 'util.cleanup') {delete_tmp = 'y'; delete_by_match('*.xml|*.sql|*.bz2|*.gz');}
|
||||
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'pages-articles';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'pagelinks';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'categorylinks';}
|
||||
@@ -543,6 +545,7 @@ app.bldr.cmds {
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'image';}
|
||||
add ('en.wikipedia.org' , 'util.download') {dump_type = 'imagelinks';}
|
||||
*/
|
||||
|
||||
/*
|
||||
// en.wikipedia.org
|
||||
add ('en.wikipedia.org' , 'text.init');
|
||||
@@ -568,28 +571,25 @@ app.bldr.cmds {
|
||||
}
|
||||
}
|
||||
}
|
||||
add ('en.wikipedia.org' , 'search.word__link_count')
|
||||
add ('en.wikipedia.org' , 'search.word__link_count');
|
||||
add ('en.wikipedia.org' , 'wiki.page_props');
|
||||
add ('en.wikipedia.org' , 'wiki.categorylinks');
|
||||
*/
|
||||
/*
|
||||
|
||||
add ('en.wikipedia.org' , 'file.page_regy') {build_commons = 'n'}
|
||||
// add ('en.wikipedia.org' , 'wiki.mass_parse.resume');
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.init') {cfg {ns_ids = '0|4|100|14|8';}}
|
||||
// add ('en.wikipedia.org' , 'wiki.mass_parse.resume');
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.exec') {cfg {
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_ifexists_ns = '*'; cleanup_interval = 25; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-01-01 01:02:03';}
|
||||
// num_wkrs = 1; load_all_templates = 'n'; load_all_imglnks = 'n'; cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2016-07-28 01:02:03';}
|
||||
num_wkrs = 8; load_all_templates = 'y'; load_all_imglinks = 'y'; indexer_enabled = 'y';
|
||||
cleanup_interval = 50; hzip_enabled = 'y'; hdiff_enabled ='y'; manual_now = '2017-04-01 00:00:00'
|
||||
}
|
||||
}
|
||||
*/
|
||||
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'wiki.mass_parse.make');
|
||||
*/
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'file.lnki_temp') {
|
||||
commit_interval = 10000; progress_interval = 50; cleanup_interval = 50; select_size = 25;
|
||||
ns_ids = '0|4|14|100|12|8|6|10|828|108|118|446|710|2300|2302|2600';
|
||||
hdump_bldr {enabled = 'y'; hzip_enabled = 'y'; hzip_diff = 'y';}
|
||||
}
|
||||
*/
|
||||
/*
|
||||
// SELECT * FROM image ORDER BY img_timestamp DESC LIMIT 20; // 20170306194400
|
||||
// SELECT * FROM page WHERE page_namespace = 6 ORDER BY page_touched DESC LIMIT 20; // 20170302024207
|
||||
// SELECT * FROM xowa_cfg WHERE cfg_key = 'props.modified_latest';
|
||||
add ('commons.wikimedia.org' , 'file.page_regy') {build_commons = 'y'}
|
||||
add ('en.wikipedia.org' , 'file.page_regy') {build_commons = 'n';}
|
||||
add ('en.wikipedia.org' , 'file.lnki_regy');
|
||||
@@ -597,9 +597,15 @@ app.bldr.cmds {
|
||||
add ('en.wikipedia.org' , 'file.orig_regy');
|
||||
add ('en.wikipedia.org' , 'file.xfer_temp.thumb');
|
||||
|
||||
// SELECT * FROM orig_regy WHERE lnki_ttl = 'BSicon_CONTr.svg';
|
||||
// SELECT * FROM page_regy WHERE src_ttl = 'BSicon_CONTr.svg';
|
||||
// SELECT Count(*) FROM xfer_regy WHERE xfer_status = 0;
|
||||
// SELECT * FROM xfer_regy WHERE xfer_status = 0 AND lnki_page_id = 372692; --en.w:Featured_picture_candidates
|
||||
|
||||
add ('en.wikipedia.org' , 'file.xfer_regy');
|
||||
add ('en.wikipedia.org' , 'file.xfer_regy_update');
|
||||
*/
|
||||
|
||||
/*
|
||||
add ('en.wikipedia.org' , 'file.fsdb_make') {
|
||||
commit_interval = 1000; progress_interval = 200; select_interval = 10000;
|
||||
@@ -630,7 +636,10 @@ app.bldr.run;
|
||||
2016-10-12: explicitly set web_access_enabled to y
|
||||
</li>
|
||||
<li>
|
||||
2017-02-02: updated script for multi-threaded version and new options
|
||||
2017-02-02: added multi-threaded version and new options
|
||||
</li>
|
||||
<li>
|
||||
2017-05-12: added full-text search
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
|
||||
Reference in New Issue
Block a user