diff --git a/db/ignore_patterns/moinmoinwiki.json b/db/ignore_patterns/moinmoinwiki.json new file mode 100644 index 00000000..c653145d --- /dev/null +++ b/db/ignore_patterns/moinmoinwiki.json @@ -0,0 +1,77 @@ +{ + "name": "moinmoinwiki", + "patterns": [ + "^https?://{primary_netloc}/.*\\?action=login$", + "^https?://{primary_netloc}/.*\\?action=refresh$", + "^https?://{primary_netloc}/.*\\?action=SpellCheck$", + "^https?://{primary_netloc}/.*\\?action=CopyPage$", + "^https?://{primary_netloc}/.*\\?action=PackagePages$", + "^https?://{primary_netloc}/.*\\?action=SyncPages$", + "^https?://{primary_netloc}/.*\\?action=Load$", + "^https?://{primary_netloc}/.*\\?action=info&hitcounts=1$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)0&rev2=\\1[023456789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)1&rev2=\\1[13456789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)2&rev2=\\1[02456789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)3&rev2=\\1[01356789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)4&rev2=\\1[01246789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)5&rev2=\\1[01235789]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)6&rev2=\\1[01234689]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)7&rev2=\\1[01234579]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)8&rev2=\\1[01234568]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9][0-9]|[1-9]|)9&rev2=\\1[012345679]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=[0-9]&rev2=[23456789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])0[0-9]&rev2=\\1[23456789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])1[0-9]&rev2=\\1[3456789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])2[0-9]&rev2=\\1[0456789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])3[0-9]&rev2=\\1[0156789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])4[0-9]&rev2=\\1[0126789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])5[0-9]&rev2=\\1[0123789][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])6[0-9]&rev2=\\1[0123489][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])7[0-9]&rev2=\\1[0123459][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])8[0-9]&rev2=\\1[0123456][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])9[0-9]&rev2=\\1[01234567][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=10&rev2=[0-8]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])10&rev2=\\1(?:0[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)20&rev2=\\1(?:1[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)30&rev2=\\1(?:2[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)40&rev2=\\1(?:3[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)50&rev2=\\1(?:4[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)60&rev2=\\1(?:5[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)70&rev2=\\1(?:6[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)80&rev2=\\1(?:7[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)90&rev2=\\1(?:8[0-8])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=1[1-9]&rev2=[0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])1[1-9]&rev2=\\1(?:0[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)2[1-9]&rev2=\\1(?:1[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)3[1-9]&rev2=\\1(?:2[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)4[1-9]&rev2=\\1(?:3[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)5[1-9]&rev2=\\1(?:4[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)6[1-9]&rev2=\\1(?:5[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)7[1-9]&rev2=\\1(?:6[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)8[1-9]&rev2=\\1(?:7[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)9[1-9]&rev2=\\1(?:8[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=[0-8]&rev2=1[0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9])[0-8]&rev2=\\1(?:1[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)1[0-8]&rev2=\\1(?:2[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)2[0-8]&rev2=\\1(?:3[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)3[0-8]&rev2=\\1(?:4[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)4[0-8]&rev2=\\1(?:5[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)5[0-8]&rev2=\\1(?:6[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)6[0-8]&rev2=\\1(?:7[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)7[0-8]&rev2=\\1(?:8[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)8[0-8]&rev2=\\1(?:9[0-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=9&rev2=1[1-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)09&rev2=\\1(?:1[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)19&rev2=\\1(?:2[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)29&rev2=\\1(?:3[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)39&rev2=\\1(?:4[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)49&rev2=\\1(?:5[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)59&rev2=\\1(?:6[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)69&rev2=\\1(?:7[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)79&rev2=\\1(?:8[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=([1-9]|)89&rev2=\\1(?:9[1-9])$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=[0-8]?[0-9]&rev2=[1-9][0-9][0-9]$", + "^https?://{primary_netloc}/[^?]+\\?action=diff&rev1=9[0-8]&rev2=[1-9][0-9][0-9]$" + ], + "type": "ignore_patterns" +}