Discussion:Serveur d'exploration sur la grippe en Allemagne

Faits épidémiques

Sur PubMed Central

Simple filtrage

HfdCat $EXPLOR_AREA/FixData/Pmc/Corpus/repository.hfd               \
   | grep Saar | SxmlFindText -s Saar -a 30 -b 30 | grep body       \
   | StrDictSelect -t FixInput/HfdPmcRepo2HfdPubMed.dict -sr

Avec GeoNames

curl http://download.geonames.org/export/zip/DE.zip -o DE.zip
unzip DE.zip
mv DE.txt Import/geoNamesPosCodesDE.txt
cat Import/geoNamesPosCodesDE.txt | SxmlSelect -p @3 > FixInput/geoNamesDE.dict
HfdCat $EXPLOR_AREA/FixData/Pmc/Corpus/repository.hfd         \
   |   SxmlFindText -D FixInput/geoNamesDE.dict -a 20 -b 20 | grep body       \
   | StrDictSelect -t FixInput/HfdPmcRepo2HfdPubMed.dict -sr

Avec Wikipédia

cat <<... >Import/extractCities.lex
%START EXT
%START ET1
%%
"==A=="      BEGIN EXT;
<EXT>^"*"[ ]*"[["/[A-Za-z]+"]]"   BEGIN ET1;
<ET1>"]]"      {putchar ('\n');   BEGIN EXT;}
<ET1>.         ECHO;
.   ;
\n  ;
%%
main()
{
    yylex();
}
...

lex Import/extractCities.lex

gcc lex.yy.c -ll -o FixBin/extractCities

WicriGetPage -l wicri-germany.en -p "List of cities and towns in Germany"   \
  | ./FixBin/extractCities > FixInput/citiesGermany.dict

HfdCat $EXPLOR_AREA/FixData/Pmc/Corpus/repository.hfd         \
   |   SxmlFindText -D FixInput/citiesGermany.dict -a 20 -b 20 | grep body       \
   | StrDictSelect -t FixInput/HfdPmcRepo2HfdPubMed.dict -sr