Privacy Policy Cookie Policy Terms and Conditions Wikipedia:Orphaned Articles/How to update - Wikipedia, the free encyclopedia

Wikipedia:Orphaned Articles/How to update

From Wikipedia, the free encyclopedia

Apart from "manual" updating of the Wikipedia:Orphaned Articles list, the automatic routine described on this page can be used.

#Use at your own risk, no warranty implied or given
#Please debug/improve the query.

DROP TABLE IF EXISTS temp_deorphan;

#  Define as the links table, droping some keys
CREATE TABLE `temp_deorphan` (
  `l_from` int(8) unsigned NOT NULL default '0',
  `l_to` int(8) unsigned NOT NULL default '0',
  KEY `l_from` (`l_from`),
  KEY `l_to` (`l_to`)
) TYPE=MyISAM; 

# This is slow .. links has over 6 mio entries
# 
INSERT INTO temp_deorphan SELECT l_from, l_to
FROM links
LIMIT 10000000;

# Remove links that don't de-orphan pages
# This version does two in one 
#    1.1 millon rows
DELETE 
 FROM temp_deorphan 
USING temp_deorphan, cur
WHERE l_from = cur_id
      AND (cur_namespace <>0    #links from namespaces other than the article namespace.
      OR cur_is_redirect=1);          #links from redirects 

#find cur_id of disambig marker (Template:Disambig)
DROP TABLE IF EXISTS temp_disambigid;

CREATE TABLE temp_disambigid
SELECT cur_id AS d_id
    FROM cur
WHERE (cur_title = 'Disambig')
      AND cur_namespace=10;   #     10 = Template namespace

#links from disambiguation pages are not included
#i.e. a page linked only from a disambiguation page is an orphan
# approx. 100000 rows
DELETE 
 FROM temp_deorphan 
USING temp_disambigid AS id, links AS l, temp_deorphan AS d 
WHERE l.l_to = id.d_id
AND l.l_from=d.l_from;

#This avoids that disambiguation pages show up as orphans
INSERT INTO temp_deorphan
 SELECT DISTINCT 999999, l_from
    FROM links, temp_disambigid
WHERE d_id = l_to
LIMIT 20000;

#Adds a temporary table with the orphans
#12000 rows
DROP TABLE IF EXISTS temp_orphans;
CREATE TABLE temp_orphans 
SELECT cur_id 
FROM cur 
LEFT JOIN temp_deorphan ON cur_id=l_to
WHERE l_to IS NULL 
        AND cur_namespace=0 
        AND cur_is_redirect=0
LIMIT 20000;


#Output from list (filtering some  600 rambot orphans)
SELECT CONCAT('#[[', REPLACE (cur_title, '_', ' '), ']]') AS orphanslist
INTO OUTFILE 'wp:\wp_orphanend_articles.txt'  #set this to path you need
FROM cur, temp_orphans
WHERE temp_orphans.cur_id = cur.cur_id
AND NOT (cur_title LIKE '%(CDP)%'
        OR cur_title LIKE '%(town)%' 
        OR cur_title LIKE '%(city)%' 
        OR cur_title LIKE '%(village)%' 
        OR cur_title LIKE '%Township%')
ORDER BY Lower(cur_title)
LIMIT 20000;

Note: these queries are slow.

THIS WEB:

aa - ab - af - ak - als - am - an - ang - ar - arc - as - ast - av - ay - az - ba - bar - bat_smg - be - bg - bh - bi - bm - bn - bo - bpy - br - bs - bug - bxr - ca - cbk_zam - cdo - ce - ceb - ch - cho - chr - chy - closed_zh_tw - co - cr - cs - csb - cu - cv - cy - da - de - diq - dv - dz - ee - el - eml - en - eo - es - et - eu - fa - ff - fi - fiu_vro - fj - fo - fr - frp - fur - fy - ga - gd - gl - glk - gn - got - gu - gv - ha - haw - he - hi - ho - hr - hsb - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - ilo - io - is - it - iu - ja - jbo - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ksh - ku - kv - kw - ky - la - lad - lb - lbe - lg - li - lij - lmo - ln - lo - lt - lv - map_bms - mg - mh - mi - mk - ml - mn - mo - mr - ms - mt - mus - my - mzn - na - nah - nap - nds - nds_nl - ne - new - ng - nl - nn - no - nov - nrm - nv - ny - oc - om - or - os - pa - pag - pam - pap - pdc - pi - pih - pl - pms - ps - pt - qu - rm - rmy - rn - ro - roa_rup - roa_tara - ru - ru_sib - rw - sa - sc - scn - sco - sd - se - searchcom - sg - sh - si - simple - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - test - tet - tg - th - ti - tk - tl - tlh - tn - to - tokipona - tpi - tr - ts - tt - tum - tw - ty - udm - ug - uk - ur - uz - ve - vec - vi - vls - vo - wa - war - wo - wuu - xal - xh - yi - yo - za - zea - zh - zh_classical - zh_min_nan - zh_yue - zu

Static Wikipedia 2008 (no images)

aa - ab - af - ak - als - am - an - ang - ar - arc - as - ast - av - ay - az - ba - bar - bat_smg - bcl - be - be_x_old - bg - bh - bi - bm - bn - bo - bpy - br - bs - bug - bxr - ca - cbk_zam - cdo - ce - ceb - ch - cho - chr - chy - co - cr - crh - cs - csb - cu - cv - cy - da - de - diq - dsb - dv - dz - ee - el - eml - en - eo - es - et - eu - ext - fa - ff - fi - fiu_vro - fj - fo - fr - frp - fur - fy - ga - gan - gd - gl - glk - gn - got - gu - gv - ha - hak - haw - he - hi - hif - ho - hr - hsb - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - ilo - io - is - it - iu - ja - jbo - jv - ka - kaa - kab - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ksh - ku - kv - kw - ky - la - lad - lb - lbe - lg - li - lij - lmo - ln - lo - lt - lv - map_bms - mdf - mg - mh - mi - mk - ml - mn - mo - mr - mt - mus - my - myv - mzn - na - nah - nap - nds - nds_nl - ne - new - ng - nl - nn - no - nov - nrm - nv - ny - oc - om - or - os - pa - pag - pam - pap - pdc - pi - pih - pl - pms - ps - pt - qu - quality - rm - rmy - rn - ro - roa_rup - roa_tara - ru - rw - sa - sah - sc - scn - sco - sd - se - sg - sh - si - simple - sk - sl - sm - sn - so - sr - srn - ss - st - stq - su - sv - sw - szl - ta - te - tet - tg - th - ti - tk - tl - tlh - tn - to - tpi - tr - ts - tt - tum - tw - ty - udm - ug - uk - ur - uz - ve - vec - vi - vls - vo - wa - war - wo - wuu - xal - xh - yi - yo - za - zea - zh - zh_classical - zh_min_nan - zh_yue - zu -

Static Wikipedia 2007:

aa - ab - af - ak - als - am - an - ang - ar - arc - as - ast - av - ay - az - ba - bar - bat_smg - be - bg - bh - bi - bm - bn - bo - bpy - br - bs - bug - bxr - ca - cbk_zam - cdo - ce - ceb - ch - cho - chr - chy - closed_zh_tw - co - cr - cs - csb - cu - cv - cy - da - de - diq - dv - dz - ee - el - eml - en - eo - es - et - eu - fa - ff - fi - fiu_vro - fj - fo - fr - frp - fur - fy - ga - gd - gl - glk - gn - got - gu - gv - ha - haw - he - hi - ho - hr - hsb - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - ilo - io - is - it - iu - ja - jbo - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ksh - ku - kv - kw - ky - la - lad - lb - lbe - lg - li - lij - lmo - ln - lo - lt - lv - map_bms - mg - mh - mi - mk - ml - mn - mo - mr - ms - mt - mus - my - mzn - na - nah - nap - nds - nds_nl - ne - new - ng - nl - nn - no - nov - nrm - nv - ny - oc - om - or - os - pa - pag - pam - pap - pdc - pi - pih - pl - pms - ps - pt - qu - rm - rmy - rn - ro - roa_rup - roa_tara - ru - ru_sib - rw - sa - sc - scn - sco - sd - se - searchcom - sg - sh - si - simple - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - test - tet - tg - th - ti - tk - tl - tlh - tn - to - tokipona - tpi - tr - ts - tt - tum - tw - ty - udm - ug - uk - ur - uz - ve - vec - vi - vls - vo - wa - war - wo - wuu - xal - xh - yi - yo - za - zea - zh - zh_classical - zh_min_nan - zh_yue - zu

Static Wikipedia 2006:

aa - ab - af - ak - als - am - an - ang - ar - arc - as - ast - av - ay - az - ba - bar - bat_smg - be - bg - bh - bi - bm - bn - bo - bpy - br - bs - bug - bxr - ca - cbk_zam - cdo - ce - ceb - ch - cho - chr - chy - closed_zh_tw - co - cr - cs - csb - cu - cv - cy - da - de - diq - dv - dz - ee - el - eml - en - eo - es - et - eu - fa - ff - fi - fiu_vro - fj - fo - fr - frp - fur - fy - ga - gd - gl - glk - gn - got - gu - gv - ha - haw - he - hi - ho - hr - hsb - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - ilo - io - is - it - iu - ja - jbo - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ksh - ku - kv - kw - ky - la - lad - lb - lbe - lg - li - lij - lmo - ln - lo - lt - lv - map_bms - mg - mh - mi - mk - ml - mn - mo - mr - ms - mt - mus - my - mzn - na - nah - nap - nds - nds_nl - ne - new - ng - nl - nn - no - nov - nrm - nv - ny - oc - om - or - os - pa - pag - pam - pap - pdc - pi - pih - pl - pms - ps - pt - qu - rm - rmy - rn - ro - roa_rup - roa_tara - ru - ru_sib - rw - sa - sc - scn - sco - sd - se - searchcom - sg - sh - si - simple - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - test - tet - tg - th - ti - tk - tl - tlh - tn - to - tokipona - tpi - tr - ts - tt - tum - tw - ty - udm - ug - uk - ur - uz - ve - vec - vi - vls - vo - wa - war - wo - wuu - xal - xh - yi - yo - za - zea - zh - zh_classical - zh_min_nan - zh_yue - zu