Discuție Proiect:Cod Wikipedia/WinBatch/Wget download

Căutare în articolele downloadate, modificare pentru a număra satele din comune: - vezi Discuție Proiect:Localitățile din România/Listă de comune#Lista simplă

set PATTERN="componenta *= *"
grep -i %PATTERN% index*.* > 000-grep-result.txt

cat 000-grep-result.txt | sed -e "s/_/ /g" | sed -e "s/\&action=edit//" | sed -e "s/index.php@title=//" ^
 | sed -e "s/\]\]/_1_/" ^
 | sed -e "s/\]\]/_2_/" ^
 | sed -e "s/\]\]/_3_/" ^
 | sed -e "s/\]\]/_4_/" ^
 | sed -e "s/\]\]/_5_/" ^
 | sed -e "s/\]\]/_6_/" ^
 | sed -e "s/\]\]/_7_/" ^
 | sed -e "s/\]\]/_8_/" ^
 | sed -e "s/\]\]/_9_/" ^
 | sed -e "s/\]\]/_a_/" ^
 | sed -e "s/\]\]/_b_/" ^
 | sed -e "s/\]\]/_c_/" ^
 | sed -e "s/\]\]/_d_/" ^
 | sed -e "s/\]\]/_e_/" ^
 | sed -e "s/\]\]/_f_/" ^
 | sed -e "s/\]\]/_g_/" ^
 | sed -e "s/\]\]/_h_/" ^
 | sed -e "s/\]\]/_i_/" ^
 | sed -e "s/\]\]/_j_/" ^
 | sed -e "s/\]\]/_k_/" ^
 | sed -e "s/\]\]/_l_/" ^
 | sed -e "s/\]\]/_m_/" ^
 | sed -e "s/\]\]/_n_/" ^
 | sed -e "s/\]\]/_o_/" ^
 | sed -e "s/\]\]/_p_/" ^
 | sed -e "s/\]\]/_q_/" ^
 | sed -e "s/\]\]/_r_/" ^
 | sed -e "s/\]\]/_s_/" ^
 | sed -e "s/\]\]/_t_/" ^
 | sed -e "s/\]\]/_u_/" ^
 | sed -e "s/\]\]/_v_/" ^
 | sed -e "s/\]\]/_w_/" ^
 | sed -e "s/\]\]/_x_/" ^
 | sed -e "s/\]\]/_y_/" ^
 | sed -e "s/\]\]/_z_/" ^
 | sort | uniq | grep -v "000-pattern" > 000-grep-result-clean1.txt
cat 000-grep-result-clean1.txt | sed -e "s/:.*_\(.\)_/:_\1_/" | sed -e "s/\x7c *componenta *= *//"> 000-grep-result-clean2.txt 

cat 000-grep-result-clean2.txt ^
 | sed -e "s/_a_/10/" ^
 | sed -e "s/_b_/11/" ^
 | sed -e "s/_c_/12/" ^
 | sed -e "s/_d_/13/" ^
 | sed -e "s/_e_/14/" ^
 | sed -e "s/_f_/15/" ^
 | sed -e "s/_g_/16/" ^
 | sed -e "s/_h_/17/" ^
 | sed -e "s/_i_/18/" ^
 | sed -e "s/_j_/19/" ^
 | sed -e "s/_k_/20/" ^
 | sed -e "s/_l_/21/" ^
 | sed -e "s/_m_/22/" ^
 | sed -e "s/_n_/23/" ^
 | sed -e "s/_o_/24/" ^
 | sed -e "s/_p_/25/" ^
 | sed -e "s/_q_/26/" ^
 | sed -e "s/_r_/27/" ^
 | sed -e "s/_s_/28/" ^
 | sed -e "s/_t_/29/" ^
 | sed -e "s/_u_/30/" ^
 | sed -e "s/_v_/31/" ^
 | sed -e "s/_w_/32/" ^
 | sed -e "s/_x_/33/" ^
 | sed -e "s/_y_/34/" ^
 | sed -e "s/_z_/35/" ^
 | sed -e "s/_\(.\)_/\1/" ^
 > 000-grep-result-clean3.txt

echo1 -ne \xEF\xBB\xBF > 000-grep-result-in.txt
cat 000-grep-result-clean3.txt >> 000-grep-result-in.txt

cat 000-grep-result-in.txt ^
 | sed -e "s/\xc3\x25AE/\xc3\xAE/g" ^
 | sed -e "s/\xc3\x258E/\xc3\x8E/g" ^
 | sed -e "s/\xc3\x25A2/\xc3\xA2/g" ^
 | sed -e "s/\xc3\x2582/\xc3\x82/g" ^
 | sed -e "s/\xc4\x2583/\xc4\x83/g" ^
 | sed -e "s/\xc4\x2582/\xc4\x82/g" ^
 | sed -e "s/\xc8\x2599/\xc8\x99/g" ^
 | sed -e "s/\xc8\x2598/\xc8\x98/g" ^
 | sed -e "s/\xc8\x259B/\xc8\x9B/g" ^
 | sed -e "s/\xc8\x259A/\xc8\x9A/g" ^
 | sed -e "s/\xc5\x259F/\xc5\x9f/g" ^
 | sed -e "s/\xc5\x259E/\xc5\x9e/g" ^
 | sed -e "s/\xc5\x25A3/\xc5\xa3/g" ^
 | sed -e "s/\xc5\x25A2/\xc5\xa2/g" ^
 > 000-grep-result-clean-diacritics.txt

sort1 -t ":" -n -k2 000-grep-result-clean-diacritics.txt > 000-grep-result-sorted.txt

Înlocuire - sedilă cu virgulă

Vrem să înlocuim peste tot ș și ț cu sedilă cu ș și ț cu virgulă. De exemplu vrem să schimbăm Căpăţâneşti în Căpățânești

cat in.txt ^
 | sed -e "s/\xc5\x9f/\xc8\x99/g" ^
 | sed -e "s/\xc5\x9e/\xc8\x98/g" ^
 | sed -e "s/\xc5\xa3/\xc8\x9b/g" ^
 | sed -e "s/\xc5\xa2/\xc8\x9a/g" > out.txt
paste -d " - " in.txt out.txt > out2.txt