Modification des paramètres d'indexation pour prendre en compte l'UTF-8

This commit is contained in:
Michael RICOIS 2012-04-26 08:32:53 +00:00
parent b043b4b9d2
commit 95e62ac7d3
3 changed files with 29 additions and 13 deletions

View File

@ -1,3 +1,4 @@
source act
{
type = mysql
@ -5,12 +6,12 @@ source act
sql_user = sphinx
sql_pass = indexer
sql_db = jo
sql_query_pre =
sql_query_pre = SET NAMES utf8
sql_query = \
SELECT id, Siren1, RaisonSociale, Siren2, actif, dateLien, IF(dateUpdate>dateInsert,dateUpdate,dateInsert) as dateMaj, \
source, Pmin*1 AS PminNum, MajMin, PpPm, IF(Pays='','FRA',Pays) AS Pays \
FROM liens \
WHERE ActionPart=1 AND Siren1>1000 AND Siren1 IN (SELECT DISTINCT SIREN FROM etablissements_old);
WHERE ActionPart=1 AND Siren1>1000 AND Siren1 IN (SELECT DISTINCT SIREN FROM etablissements);
sql_attr_uint = actif
sql_attr_uint = source
sql_attr_uint = PminNum
@ -25,8 +26,15 @@ index act
path = /dbs/sphinx/act
docinfo = extern
morphology = none
charset_type = sbcs
charset_type = utf-8
charset_table = 0..9, A..Z->a..z, a..z, \
U+23, U+25, U+26, U+2B, U+3D, U+40, \
U+C0..U+DE->U+E0..U+FE, U+DF, U+E0..U+FF
U+23, U+25, U+26, U+2B, U+3D, U+40, \
U+C0->a, U+C1->a, U+C2->a, U+C3->a, U+C4->a, U+C5->a, U+C6->a, U+C7->c, \
U+C8->e, U+C8->e, U+C9->e, U+CA->e, U+CB->e, U+CC->i, U+CD->i, U+CE->i, \
U+CF->i, U+D0->d, U+D1->n, U+D2->o, U+D3->o, U+D4->o, U+D5->o, U+D6->o, \
U+D8->o, U+D9->u, U+DA->u, U+DB->u, U+DC->u, U+DD->y, U+E0->a, U+E1->a, \
U+E2->a, U+E3->a, U+E4->a, U+E5->a, U+E7->c, U+E8->e, U+E9->e, U+EA->e, \
U+EB->e, U+EC->i, U+ED->i, U+EE->i, U+EF->i, U+F1->n, U+F2->o, U+F3->o, \
U+F4->o, U+F5->o, U+F6->o, U+F8->o, U+F9->u, U+FA->u,U+FB->u, U+FC->u, \
U+FD->y, U+FF->y, U+0152->U+0153, U+0153
}

View File

@ -1,3 +1,4 @@
source dir
{
type = mysql
@ -5,7 +6,7 @@ source dir
sql_user = sphinx
sql_pass = indexer
sql_db = jo
sql_query_pre =
sql_query_pre = SET NAMES utf8
sql_query = \
SELECT id, siren, adr_dep, typeDir, dirSiren, civilite, CONCAT(nom,' ',naissance_nom, ' ', dirRS) AS nom, prenom, \
YEAR(naissance_date) AS naiss_annee, \
@ -30,8 +31,15 @@ index dir
path = /dbs/sphinx/dir
docinfo = extern
morphology = none
charset_type = sbcs
charset_type = utf8
charset_table = 0..9, A..Z->a..z, a..z, \
U+23, U+25, U+26, U+2B, U+3D, U+40, \
U+C0..U+DE->U+E0..U+FE, U+DF, U+E0..U+FF
U+23, U+25, U+26, U+2B, U+3D, U+40, \
U+C0->a, U+C1->a, U+C2->a, U+C3->a, U+C4->a, U+C5->a, U+C6->a, U+C7->c, \
U+C8->e, U+C8->e, U+C9->e, U+CA->e, U+CB->e, U+CC->i, U+CD->i, U+CE->i, \
U+CF->i, U+D0->d, U+D1->n, U+D2->o, U+D3->o, U+D4->o, U+D5->o, U+D6->o, \
U+D8->o, U+D9->u, U+DA->u, U+DB->u, U+DC->u, U+DD->y, U+E0->a, U+E1->a, \
U+E2->a, U+E3->a, U+E4->a, U+E5->a, U+E7->c, U+E8->e, U+E9->e, U+EA->e, \
U+EB->e, U+EC->i, U+ED->i, U+EE->i, U+EF->i, U+F1->n, U+F2->o, U+F3->o, \
U+F4->o, U+F5->o, U+F6->o, U+F8->o, U+F9->u, U+FA->u,U+FB->u, U+FC->u, \
U+FD->y, U+FF->y, U+0152->U+0153, U+0153
}

View File

@ -2,8 +2,8 @@ source histo
{
type = mysql
sql_host = 192.168.78.230
sql_user = sphinx_histo
sql_pass = sphinx
sql_user = sphinx
sql_pass = indexer
sql_db = histobodacc
sql_port = 3306 # optional, default is 3306
sql_query = SELECT id, nomFichier, annee1, dateBod, texte FROM bodacc_ocr;
@ -14,10 +14,10 @@ source histo
index histo
{
source = histo
path = /home/sphinx/histo
path = /dbs/sphinx/histo
docinfo = extern
morphology = none
min_word_len = 1
min_word_len = 2
charset_type = sbcs
html_strip = 1
}