Forks/privacore-open-source-search-engine
1
0
Fork 0
forked from Mirrors/privacore-open-source-search-engine
Code Pull Requests Activity

Merge branch 'master' into sqlite

Browse Source
This commit is contained in:
Ivan Skytte Jørgensen
2017-10-26 13:43:33 +02:00
parent 3956eac447 9ec9342312
commit c5d07d92f0
37 changed files with 2243 additions and 1224 deletions

825
AdultCheck.cpp

@ -1,825 +0,0 @@
#include "AdultCheck.h"
#include "matches2.h"
#include "Log.h"
#include "Conf.h"
#include "Speller.h" //g_speller for word split uses
#include "Xml.h"
#include <stddef.h>
// . an "id" of 2 means very indicative of a dirty doc
// . an "id" of 1 means it must be joined with another dirty word to indicate
// . taken mostly from Url.cpp
// . see matches2.h for Needle class definition
static const Needle s_dirtyWords [] = {
{"upskirt" ,2,0},
{"downblouse",2,0},
{"shemale" ,1,0},
{"spank" ,1,0},
{"dildo" ,2,0},
{"bdsm" ,2,0},
{"voyeur" ,2,0},
{"fisting" ,2,0},
{"vibrator" ,2,0},
{"ejaculat" ,2,0},
{"rgasm" ,2,0},
{"orgy" ,2,0},
{"orgies" ,2,0},
{"stripper" ,1,0},
{"softcore" ,2,0},
{"whore" ,2,0},
// gary slutkin on ted.com. make this just 1 point.
{"slut" ,1,0},
{"smut" ,2,0},
{"tits" ,2,0},
{"lesbian" ,2,0},
{"swinger" ,2,0},
{"fetish" ,2,0},
{"nude" ,1,0},
{"centerfold",2,0},
{"incest" ,2,0},
{"pedophil" ,2,0},
{"pedofil" ,2,0},
{"horny" ,2,0}, // horny toad
{"pussy" ,2,0}, // pussy willow pussy cat
{"pussies" ,2,0},
{"penis" ,2,0},
{"vagina" ,2,0},
{"phuck" ,2,0},
{"blowjob" ,2,0},
{"blow job" ,2,0},
{"gangbang" ,2,0},
{"xxx" ,1,0}, // yahoo.com has class="fz-xxxl"
{"porn" ,2,0},
{"felch" ,2,0},
{"cunt" ,2,0},
{"bestial" ,2,0},
{"beastial" ,2,0},
{"kink" ,2,0},
// . "sex" is often substring in tagids.
// . too many false positives, make "1" not "2"
{"sex" ,1,0},
{"anal" ,2,0},
{"cum" ,2,0}, // often used for cumulative
{"clit" ,2,0},
{"fuck" ,2,0},
{"boob" ,1,0},
{"wank" ,2,0},
{"fick" ,2,0},
{"eroti" ,2,0},
{"gay" ,1,0}, // make 1 pt. 'marvin gay'
// new stuff not in Url.cpp
{"thong" ,1,0},
{"masturbat" ,2,0},
{"bitch" ,1,0},
{"hell" ,1,0},
{"damn" ,1,0},
{"rimjob" ,2,0},
{"cunnilingu",2,0},
{"felatio" ,2,0},
{"fellatio" ,2,0},
{"dick" ,1,0},
{"cock" ,1,0},
{"rape" ,2,0},
{"raping" ,2,0},
{"bukake" ,2,0},
{"shit" ,2,0},
{"naked" ,1,0},
{"nympho" ,2,0},
{"hardcore" ,1,0}, // hardcore gamer, count as 1
{"sodom" ,2,0},
{"titties" ,2,0}, // re-do
{"twat" ,2,0},
{"bastard" ,1,0},
{"erotik" ,2,0},
// EXCEPTIONS
// smut
{"transmut" ,-2,0},
{"bismuth" ,-2,0},
// sex
{"middlesex" ,-1,0},
{"sussex" ,-1,0},
{"essex" ,-1,0},
{"deusex" ,-1,0},
{"sexchange" ,-1,0},
{"sexpress" ,-1,0},
{"sexpert" ,-1,0},
// EXCEPTIONS
// sex
{"middlesex" ,-1,0},
{"sussex" ,-1,0},
{"essex" ,-1,0},
{"deusex" ,-1,0},
{"sexchange" ,-1,0},
{"sexpress" ,-1,0},
{"sexpert" ,-1,0},
{"sexcel" ,-1,0},
{"sexist" ,-1,0},
{"sexile" ,-1,0},
{"sexperi" ,-1,0},
{"sexual" ,-1,0},
{"sexpose" ,-1,0},
{"sexclu" ,-1,0},
{"sexo" ,-1,0},
{"sexism" ,-1,0},
{"sexpan" ,-1,0}, // buttonsexpanion
{"same-sex" ,-1,0},
{"opposite sex",-1,0},
// anal
{"analog" ,-2,0},
{"analy" ,-2,0},
{"canal" ,-2,0},
{"kanal" ,-2,0},
{"banal" ,-2,0},
{"ianalbert" ,-2,0}, // ian albert
// cum
{"circum" ,-2,0},
{"cum laude" ,-2,0},
{"succum" ,-2,0},
{"cumber" ,-2,0},
{"docum" ,-2,0},
{"cumul" ,-2,0},
{"acumen" ,-2,0},
{"incum" ,-2,0},
{"capsicum" ,-2,0},
{"modicum" ,-2,0},
{"locum" ,-2,0},
{"scum" ,-2,0},
{"accum" ,-2,0},
{"cumbre" ,-2,0},
{"swank" ,-2,0},
{"fickle" ,-2,0},
{"traffick" ,-2,0},
{"scleroti" ,-2,0},
{"gaylor" ,-2,0},
{"gaynor" ,-2,0},
{"gayner" ,-2,0},
{"gayton" ,-2,0},
{"dipthong" ,-1,0},
// hell
{"hellen" ,-1,0},
{"hellman" ,-1,0},
{"shell" ,-1,0},
{"mitchell" ,-1,0},
{"chelle" ,-1,0}, // me/michelle
{"hello" ,-1,0},
{"moschella" ,-1,0},
{"othello" ,-1,0},
{"schelling" ,-1,0},
{"seychelles" ,-1,0},
{"wheller" ,-1,0},
{"winchell" ,-1,0},
// dick
{"dicker" ,-1,0},
{"dickins" ,-1,0},
{"dickies" ,-1,0},
{"dickran" ,-1,0},
// cock
{"babcock" ,-1,0},
{"cocked" ,-1,0},
{"cocking" ,-1,0},
{"cockpit" ,-1,0},
{"cockroach" ,-1,0},
{"cocktail" ,-1,0},
{"cocky" ,-1,0},
{"hancock" ,-1,0},
{"hitchcock" ,-1,0},
{"peacock" ,-1,0},
{"shuttlecock",-1,0},
{"stopcock" ,-1,0},
{"weathercock",-1,0},
{"woodcock" ,-1,0},
{"cockburn" ,-1,0},
// kink
{"kinko" ,-2,0},
{"ukink" ,-2,0}, // ink shop in uk
// naked
{"snaked" ,-1,0},
// rape
{"drape" ,-2,0},
{"grape" ,-2,0},
{"scrape" ,-2,0},
{"therape" ,-2,0},
{"trapez" ,-2,0},
{"parapet" ,-2,0},
{"scraping" ,-2,0},
{"draping" ,-2,0},
// twat
{"twatch" ,-2,0}, // courtwatch -- cspan.org
// clit
{"heraclitus" ,-2,0},
// boob
{"booboo" ,-1,0},
// shit
{"shitak" ,-2,0},
// scunthorpe (north lincolnshire)
{"scunthorpe" ,-2,0}
};
static const int32_t numDirty = sizeof(s_dirtyWords) / sizeof(s_dirtyWords[0]);
#if 0
////
//// New stuff from sex.com adult word list
////
////
//// make it a 2nd part because of performance limits on matches2.cpp algo
////
static const Needle s_dirtyWordsPart2 [] = {
{"amateurfoto" ,2,0},
{"amateurhardcore" ,2,0},
{"amateurindex",2,0},
{"amateurnaked",2,0},
{"amatuerhardcore" ,2,0},
{"ampland" ,2,0},
//{"animehentai" ,2,0}, dup
{"anitablonde" ,2,0},
{"asiacarrera" ,2,0},
{"asshole" ,2,0},
{"asslick" ,2,0},
{"asspic" ,2,0},
{"assworship" ,2,0},
//{"badgirl" ,2,0}, not necessarily bad
{"bareceleb" ,2,0},
{"barenaked" ,2,0},
{"beaverboy" ,2,0},
{"beavershot" ,2,0}, // was beavershots
//{"bigball" ,2,0}, // not necessarily bad
{"bigbreast" ,2,0},
//{"bigbutt" ,2,0}, // not necessarily bad
{"bigcock" ,2,0},
{"bigdick" ,2,0},
{"biggestdick" ,2,0},
{"biggesttit" ,2,0},
{"bighairyball",2,0},
{"bighooter" ,2,0},
{"bignipple" ,2,0},
{"bigtit" ,2,0},
{"blackbooty" ,2,0},
{"blackbutt" ,2,0},
{"blackcock" ,2,0},
{"blackdick" ,2,0},
{"blackhardcore" ,2,0},
{"blackonblonde" ,2,0},
{"blacksonblonde" ,2,0},
{"blacktit" ,2,0},
{"blacktwat" ,2,0},
{"boner" ,1,0}, // softcore, someone's lastname?
{"bordello" ,2,0},
{"braless" ,2,0},
{"brothel" ,2,0},
{"bukake" ,2,0},
{"bukkake" ,2,0},
{"bustyblonde" ,2,0},
{"bustyceleb" ,2,0},
{"butthole" ,2,0},
{"buttman" ,2,0},
{"buttpic" ,2,0},
{"buttplug" ,2,0},
{"buttthumbnails" ,2,0},
{"callgirl" ,2,0},
{"celebritiesnaked" ,2,0},
{"celebritybush" ,2,0},
{"celebritybutt" ,2,0},
{"chaseylain" ,2,0},
{"chickswithdick" ,2,0},
{"christycanyon" ,2,0},
{"cicciolina" ,2,0},
//{"cunilingus" ,2,0},
{"cunniling" ,2,0}, // abbreviate
{"cyberlust" ,2,0},
{"danniashe" ,2,0},
{"dicksuck" ,2,0},
{"dirtymind" ,2,0},
{"dirtypicture",2,0},
{"doggiestyle" ,2,0},
{"doggystyle" ,2,0},
{"domatrix" ,2,0},
{"dominatrix" ,2,0},
//{"dyke",2,0}, // dick van dyke!
{"ejaculation" ,2,0},
{"erosvillage" ,2,0},
{"facesit" ,2,0},
{"fatass" ,2,0},
{"feetfetish" ,2,0},
{"felatio" ,2,0},
{"fellatio" ,2,0},
{"femdom" ,2,0},
{"fetishwear" ,2,0},
{"fettegirl" ,2,0},
{"fingerbang" ,2,0},
{"fingering" ,1,0}, // fingering the keyboard? use 1
{"flesh4free" ,2,0},
{"footfetish" ,2,0},
{"footjob" ,2,0},
{"footlicking" ,2,0},
{"footworship" ,2,0},
{"fornication" ,2,0},
{"freeass" ,2,0},
{"freebigtit" ,2,0},
{"freedick" ,2,0},
{"freehardcore",2,0},
//{"freehentai" ,2,0}, dup
{"freehooter" ,2,0},
{"freelargehooter" ,2,0},
{"freenakedpic",2,0},
{"freenakedwomen" ,2,0},
{"freetit" ,2,0},
{"freevoyeur" ,2,0},
{"gratishardcoregalerie" ,2,0},
{"hardcorecelebs" ,2,0},
{"hardcorefree",2,0},
{"hardcorehooter" ,2,0},
{"hardcorejunkie" ,2,0},
{"hardcorejunky" ,2,0},
{"hardcoremovie" ,2,0},
{"hardcorepic" ,2,0},
{"hardcorepix" ,2,0},
{"hardcoresample" ,2,0},
{"hardcorestories" ,2,0},
{"hardcorethumb" ,2,0},
{"hardcorevideo" ,2,0},
{"harddick" ,2,0},
{"hardnipple" ,2,0},
{"hardon" ,2,0},
{"hentai" ,2,0},
{"interacialhardcore" ,2,0},
{"intercourseposition" ,2,0},
{"interracialhardcore" ,2,0},
{"ittybittytitty" ,2,0},
{"jackoff" ,2,0},
{"jennajameson",2,0},
{"jennicam" ,2,0},
{"jerkoff" ,2,0},
{"jism",2,0},
{"jiz" ,2,0},
{"justhardcore",2,0},
{"karasamateurs" ,2,0},
{"kascha" ,2,0},
{"kaylakleevage" ,2,0},
{"kobetai" ,2,0},
{"lapdance" ,2,0},
{"largedick" ,2,0},
{"largehooter" ,2,0},
{"largestbreast" ,2,0},
{"largetit" ,2,0},
{"lesben" ,2,0},
{"lesbo" ,2,0},
{"lickadick" ,2,0},
{"lindalovelace" ,2,0},
{"longdick" ,2,0},
{"lovedoll" ,2,0},
{"makinglove" ,2,0},
{"mangax" ,2,0},
{"manpic" ,2,0},
{"marilynchambers" ,2,0},
{"massivecock" ,2,0},
{"masterbating",2,0},
{"mensdick" ,2,0},
{"milf",2,0},
{"minka" ,2,0},
{"monstercock" ,2,0},
{"monsterdick" ,2,0},
{"muffdiving" ,2,0},
{"nacktfoto" ,2,0},
{"nakedblackwomen" ,2,0},
{"nakedceleb" ,2,0},
{"nakedcelebrity" ,2,0},
{"nakedcheerleader" ,2,0},
{"nakedchick" ,2,0},
{"nakedgirl" ,2,0},
{"nakedguy" ,2,0},
{"nakedladies" ,2,0},
{"nakedlady" ,2,0},
{"nakedman" ,2,0},
{"nakedmen" ,2,0},
{"nakedness" ,2,0},
{"nakedphoto" ,2,0},
{"nakedpic" ,2,0},
{"nakedstar" ,2,0},
{"nakedwife" ,2,0},
{"nakedwoman" ,2,0},
{"nakedwomen" ,2,0},
{"nastychat" ,2,0},
{"nastythumb" ,2,0},
{"naughtylink" ,2,0},
{"naughtylinx" ,2,0},
{"naughtylynx" ,2,0},
{"naughtynurse",2,0},
{"niceass" ,2,0},
{"nikkinova" ,2,0},
{"nikkityler" ,2,0},
{"nylonfetish" ,2,0},
{"nympho" ,2,0},
{"openleg" ,2,0},
{"oral4free" ,2,0},
{"pantyhosefetish" ,2,0},
{"peepcam" ,2,0},
{"persiankitty",2,0},
{"perverted" ,2,0},
{"pimpserver" ,2,0},
{"pissing" ,2,0},
{"poontang" ,2,0},
{"privatex" ,2,0},
{"prono" ,2,0},
{"publicnudity",2,0},
{"puffynipple" ,2,0},
{"racqueldarrian" ,2,0},
//{"rape",2,0}, // dup!
{"rawlink" ,2,0},
{"realhardcore",2,0},
{"rubberfetish",2,0},
{"seka",2,0},
{"sheboy" ,2,0},
{"showcam" ,2,0},
{"showercam" ,2,0},
{"smallbreast" ,2,0},
{"smalldick" ,2,0},
{"spycamadult" ,2,0},
{"strapon" ,2,0},
{"stripclub" ,2,0},
{"stripshow" ,2,0},
{"striptease" ,2,0},
{"strokeit" ,2,0},
{"strokeme" ,2,0},
{"suckdick" ,2,0},
{"sylviasaint" ,2,0},
{"teenhardcore",2,0},
{"teenie" ,2,0},
{"teenpic" ,2,0},
{"teensuck" ,2,0},
{"tgp" ,2,0},
{"threesome" ,2,0},
{"thumblord" ,2,0},
{"thumbzilla" ,2,0},
{"tiffanytowers" ,2,0},
{"tinytitties" ,2,0},
//{"tities" ,2,0}, // entities
{"titman" ,2,0},
{"titsandass" ,2,0},
{"titties" ,2,0},
{"titts" ,2,0},
{"titty" ,2,0},
{"tokyotopless",2,0},
{"tommysbookmark" ,2,0},
{"toplesswomen",2,0},
{"trannies" ,2,0},
{"twinks" ,2,0},
{"ultradonkey" ,2,0},
{"ultrahardcore" ,2,0},
{"uncutcock" ,2,0},
{"vividtv" ,2,0},
{"wendywhoppers" ,2,0},
{"wetdick" ,2,0},
{"wetpanties" ,2,0},
{"wifesharing" ,2,0},
{"wifeswapping",2,0},
{"xrated" ,2,0}
};
static const int32_t numDirty2 = sizeof(s_dirtyWordsPart2) / sizeof(s_dirtyWordsPart2[0]);
static bool initDirtyWordsPart2 = initializeNeedle(s_dirtyWordsPart2, numDirty2);
#endif
int32_t getAdultPoints ( char *s, int32_t slen, const char *url ) {
NeedleMatch dirtyWordsMatches[numDirty];
// . use the matches function to get all the matches
// . then check each match to see if it is actually a legit word
// . actually match the dirty words, then match the clean words
// then we can subtract counts.
getMatches2(s_dirtyWords, dirtyWordsMatches, numDirty, s, slen, NULL, NULL);
int32_t points = 0;
// each needle has an associated score
for ( int32_t i = 0 ; i < numDirty ; i++ ) {
// skip if no match
if ( dirtyWordsMatches[i].m_count <= 0 ) continue;
// . the "id", is positive for dirty words, - for clean
// . uses +2/-2 for really dirty words
// . uses +1/-1 for borderline dirty words
points += s_dirtyWords[i].m_id;
logDebug(g_conf.m_logDebugDirty, "dirty: %s %" PRId32" %s", s_dirtyWords[i].m_string, (int32_t) s_dirtyWords[i].m_id, url);
}
////
//
// repeat for part2
//
// we have to do two separate parts otherwise the algo in
// matches2.cpp gets really slow. it was not meant to match
// so many needles in one haystack.
//
///
#if 0
// . disable this for now. most of these are phrases and they
// will not be detected.
// . TODO: hash the dirty words and phrases and just lookup
// words in that table like we do for isStopWord(), but use
// isDirtyWord(). Then replace the code is Speller.cpp
// with isDirtyUrl() which will split the string into words
// and call isDirtyWord() on each one. also use bi and tri grams
// in the hash table.
getMatches2 ( s_dirtyWordsPart2 ,
numDirty2 ,
s ,
slen ,
NULL , // linkPos
NULL , // needleNum
false , // stopAtFirstMatch?
NULL , // hadPreMatch ptr
true ); // saveQuickTables?
// each needle has an associated score
for ( int32_t i = 0 ; i < numDirty2 ; i++ ) {
// skip if no match
if ( s_dirtyWordsPart2[i].m_count <= 0 ) continue;
// . the "id", is positive for dirty words, - for clean
// . uses +2/-2 for really dirty words
// . uses +1/-1 for borderline dirty words
points += s_dirtyWordsPart2[i].m_id;
// log debug
if ( ! g_conf.m_logDebugDirty ) continue;
// show it in the log
log("dirty: %s %" PRId32" %s"
,s_dirtyWordsPart2[i].m_string
,(int32_t)s_dirtyWordsPart2[i].m_id
,url
);
}
#endif
return points;
}
/// @todo ALC this is not a good way to check if it's adult or not
// . these are going to be adult, in any language
// . this seems only to be used by Speller.cpp when splitting up words
// in the url domain.
// . s/slen is a full word that is found in our "dictionary" so using
// phrases like biglittlestuff probably should not go here.
bool isAdult(const char *s, int32_t slen, const char **loc) {
const char *a = NULL;
const char **p = loc ? loc : &a;
// check for naughty words
if ( ( *p = strnstr ( s, "upskirt", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "downblouse", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "adult", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "shemale", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "spank", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "dildo", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "shaved", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "bdsm", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "voyeur", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "shemale", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "fisting", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "escorts", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "vibrator", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "rgasm", slen ) ) ) return true; // 0rgasm
if ( ( *p = strnstr ( s, "orgy", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "orgies", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "orgasm", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "masturbat", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "stripper", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "lolita", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "softcore", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "whore", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "slut", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "smut", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "tits", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "lesbian", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "swinger", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "housewife", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "housewive", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "nude", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "bondage", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "centerfold", slen) ) ) return true;
if ( ( *p = strnstr ( s, "incest", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "pedophil", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "pedofil", slen ) ) ) return true;
// hornyear.com
if ( ( *p = strnstr ( s, "horny", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "pussy", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "pussies", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "penis", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "vagina", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "phuck", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "blowjob", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "gangbang", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "xxx", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "porn", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "felch", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "cunt", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "bestial", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "tranny", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "beastial", slen ) ) ) return true;
if ( ( *p = strnstr ( s, "crotch", slen ) ) ) return true;
// these below may have legit meanings
if ( ( *p = strnstr ( s, "kink", slen ) ) ) {
if ( strnstr ( s, "kinko", slen ) ) return false;// the store
return true;
}
if ( ( *p = strnstr ( s, "sex", slen ) ) ) {
// sexton, sextant, sextuplet, sextet
if ( strnstr ( s, "sext", slen ) ) return false;
if ( strnstr ( s, "middlesex", slen ) ) return false;
if ( strnstr ( s, "sussex", slen ) ) return false;
if ( strnstr ( s, "essex", slen ) ) return false;
if ( strnstr ( s, "deusex", slen ) )
return false; // video game
if ( strnstr ( s, "sexchange", slen ) )
return false; // businessexh
if ( strnstr ( s, "sexpress", slen ) )
return false; // *express
if ( strnstr ( s, "sexpert", slen ) )
return false; // *expert
if ( strnstr ( s, "sexcel", slen ) )
return false; // *excellence
if ( strnstr ( s, "sexist", slen ) )
return false; // existence
if ( strnstr ( s, "sexile", slen ) )
return false; // existence
if ( strnstr ( s, "harassm", slen ) )
return false; // harassment
if ( strnstr ( s, "sexperi", slen ) )
return false; // experience
if ( strnstr ( s, "transex", slen ) )
return false; // transexual
if ( strnstr ( s, "sexual", slen ) )
return false; // abuse,health
if ( strnstr ( s, "sexpo", slen ) )
return false; // expo,expose
if ( strnstr ( s, "exoti", slen ) )
return false; // exotic(que)
if ( strnstr ( s, "sexclu", slen ) )
return false; // exclusive/de
return true;
}
// www.losAnaLos.de
// sanalcafe.net
if ( ( *p = strnstr ( s, "anal", slen ) ) ) {
if ( strnstr ( s, "analog", slen ) )
return false; // analogy
if ( strnstr ( s, "analy", slen ) )
return false; // analysis
if ( strnstr ( s, "canal", slen ) )
return false;
if ( strnstr ( s, "kanal", slen ) )
return false; // german
if ( strnstr ( s, "banal", slen ) )
return false;
return true;
}
if ( ( *p = strnstr ( s, "cum", slen ) ) ) {
if ( strnstr ( s, "circum", slen ) )
return false; // circumvent
if ( strnstr ( s, "magn", slen ) )
return false; // magna cum
if ( strnstr ( s, "succu", slen ) )
return false; // succumb
if ( strnstr ( s, "cumber", slen ) )
return false; // encumber
if ( strnstr ( s, "docum", slen ) )
return false; // document
if ( strnstr ( s, "cumul", slen ) )
return false; // accumulate
if ( strnstr ( s, "acumen", slen ) )
return false; // acumen
if ( strnstr ( s, "cucum", slen ) )
return false; // cucumber
if ( strnstr ( s, "incum", slen ) )
return false; // incumbent
if ( strnstr ( s, "capsicum", slen ) ) return false;
if ( strnstr ( s, "modicum", slen ) ) return false;
if ( strnstr ( s, "locum", slen ) )
return false; // slocum
if ( strnstr ( s, "scum", slen ) ) return false;
if ( strnstr ( s, "accu", slen ) )
return false; // compounds!
// arcum.de
// cummingscove.com
// cumchristo.org
return true;
}
if ( ( *p = strnstr ( s, "clit", slen ) ) &&
! strnstr ( s, "heraclitus", slen ) )
return true;
// fuckedcompany.com is ok
if ( ( *p = strnstr ( s, "fuck", slen ) ) &&
! strnstr ( s, "fuckedcomp", slen ) )
return true;
if ( ( *p = strnstr ( s, "boob", slen ) ) &&
! strnstr ( s, "booboo", slen ) )
return true;
if ( ( *p = strnstr ( s, "wank", slen ) )&&
! strnstr ( s, "swank", slen ) )
return true;
// fick is german for fuck (fornication under consent of the king)
if ( ( *p = strnstr ( s, "fick", slen ) )&&
! strnstr ( s, "fickle", slen ) &&
! strnstr ( s, "traffick", slen ) )return true;
// sclerotic
// buerotipp.de
if ( ( *p = strnstr ( s, "eroti", slen ) ) &&
! strnstr ( s, "sclero", slen ) )
return true;
// albaberlin.com
// babelfish.altavista.com
if ( ( *p = strnstr ( s, "babe", slen ) ) &&
! strnstr ( s, "toyland", slen ) &&
! strnstr ( s, "babel", slen ) )
return true;
// what is gaya.dk?
if ( ( *p = strnstr ( s, "gay", slen ) ) &&
! strnstr ( s, "gaylord", slen ) )
return true;
// url appears to be ok
return false;
}
bool isAdultUrl(const char *s, int32_t slen) {
if(!isAdult(s,slen))
return false;
// check for naughty words. Split words to deep check if we're surely
// adult. Required because montanalinux.org is showing up as porn
// because it has 'anal' in the hostname.
// send each phrase seperately to be tested.
// hotjobs.yahoo.com
const char *a = s;
const char *p = s;
bool foundCleanSequence = false;
char splitWords[1024];
char *splitp = splitWords;
while(p < s + slen) {
while(p < s + slen && *p != '.' && *p != '-')
p++;
bool isPorn = false;
// TODO: do not include "ult" in the dictionary, it is
// always splitting "adult" as "ad ult". i'd say do not
// allow it to split a dirty word into two words like that.
if(g_speller.canSplitWords(a, p - a, &isPorn, splitp, langEnglish)) {
if(isPorn) {
log(LOG_DEBUG,"build: identified %s as porn after splitting words as %s",
s, splitp);
return true;
}
foundCleanSequence = true;
// keep searching for some porn sequence
}
p++;
a = p;
splitp += strlen(splitp);
}
// if we found a clean sequence, its not porn
if(foundCleanSequence) {
log(LOG_INFO,"build: did not identify url %s as porn after splitting words as %s",
s, splitWords);
return false;
}
// we tried to get some seq of words but failed. Still report
// this as porn, since isAdult() was true
logf(LOG_DEBUG,"build: failed to find sequence of words to prove %s was not porn.", s );
return true;
}
bool isAdultTLD(const char *tld, size_t tld_len) {
if(tld) {
if((tld_len==5 && memcmp(tld,"adult",5)==0) ||
(tld_len==4 && memcmp(tld,"porn",4)==0) ||
(tld_len==3 && memcmp(tld,"sex",3)==0) ||
(tld_len==4 && memcmp(tld,"sexy",4)==0) ||
(tld_len==3 && memcmp(tld,"xxx",3)==0))
return true;
}
return false;
}

15
AdultCheck.h

@ -1,15 +0,0 @@
#ifndef ADULT_CHECK_H_
#define ADULT_CHECK_H_
#include <inttypes.h>
#include <stddef.h>
int32_t getAdultPoints ( char *s, int32_t slen, const char *url );
bool isAdult(const char *s, int32_t slen, const char **loc = nullptr);
bool isAdultUrl(const char *s, int32_t slen);
bool isAdultTLD(const char *tld, size_t tld_len);
#endif

3
Conf.cpp

@ -236,6 +236,7 @@ Conf::Conf ( ) {
m_logTraceDnsCache = false;
m_logTraceFile = false;
m_logTraceHttpMime = false;
m_logTraceLanguageResultOverride = false;
m_logTraceMem = false;
m_logTraceMsg0 = false;
m_logTraceMsg4 = false;
@ -254,7 +255,6 @@ Conf::Conf ( ) {
m_logTraceRdbTree = false;
m_logTraceRepairs = false;
m_logTraceRobots = false;
m_logTraceRobotsBlocked = false;
m_logTraceRobotsCheckList = false;
m_logTraceSpider = false;
m_logTraceSpiderUrlCache = false;
@ -266,6 +266,7 @@ Conf::Conf ( ) {
m_logTracePhrases= false;
m_logTraceUrlMatchList = false;
m_logTraceUrlMatchHostList = false;
m_logTraceUrlResultOverride = false;
m_logTraceWordSpam=false;
m_logTraceUrlClassification = false;
m_logTimingAddurl = false;

3
Conf.h

@ -386,6 +386,7 @@ class Conf {
bool m_logTraceDnsCache;
bool m_logTraceFile;
bool m_logTraceHttpMime;
bool m_logTraceLanguageResultOverride;
bool m_logTraceMem;
bool m_logTraceMsg0;
bool m_logTraceMsg4;
@ -405,7 +406,6 @@ class Conf {
bool m_logTraceRepairs;
bool m_logTraceRobots;
bool m_logTraceRobotsBlocked;
bool m_logTraceRobotsCheckList;
bool m_logTraceSpider;
bool m_logTraceSpiderUrlCache;
@ -417,6 +417,7 @@ class Conf {
bool m_logTracePhrases;
bool m_logTraceUrlMatchList;
bool m_logTraceUrlMatchHostList;
bool m_logTraceUrlResultOverride;
bool m_logTraceWordSpam;
bool m_logTraceUrlClassification;
bool m_logTraceTopTree;

467
FxAdultCheck.cpp Normal file

@ -0,0 +1,467 @@
//
// Copyright (C) 2017 Privacore ApS - https://www.privacore.com
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//
// License TL;DR: If you change this file, you must publish your changes.
//
#include "FxAdultCheck.h"
#include "Log.h"
#include "Conf.h"
#include "Mem.h"
#include "termid_mask.h"
#include "Phrases.h"
#include "Words.h"
#include "XmlDoc.h"
#include <stddef.h>
#include <fstream>
#include <sys/stat.h>
AdultCheck::AdultCheck(XmlDoc *xd, bool debug) {
m_docAdultScore = 0;
m_numUniqueDirtyWords = 0;
m_numUniqueDirtyPhrases = 0;
m_numWordsChecked = 0;
m_emptyDocumentBody = false;
m_result = false;
m_resultValid = false;
if( xd ) {
m_url = xd->getFirstUrl();
if( m_url == (Url *)-1 ) {
log(LOG_WARN, "XmlDoc::getFirstUrl() failed in AdultCheck::AdultCheck");
m_url = NULL;
}
m_xml = xd->getXml();
if( m_xml == (Xml *)-1 ) {
log(LOG_WARN, "XmlDoc::getXml() failed in AdultCheck::AdultCheck");
m_xml = NULL;
}
m_words = xd->getWords();
if( m_words == (Words *)-1 ) {
log(LOG_WARN, "XmlDoc::getWords() failed in AdultCheck::AdultCheck");
m_words = NULL;
}
m_phrases = xd->getPhrases();
if( m_phrases == (Phrases *)-1 ) {
log(LOG_WARN, "XmlDoc::getPhrases() failed in AdultCheck::AdultCheck");
m_phrases = NULL;
}
}
else {
m_url = NULL;
m_xml = NULL;
m_words = NULL;
m_phrases = NULL;
}
m_debbufSize = 0;
m_debbufUsed = 0;
m_debbuf = NULL;
if( debug ) {
m_debbufSize = 2000;
m_debbuf = (char *)mmalloc(m_debbufSize, "adultcheck");
if( !m_debbuf ) {
m_debbufSize = 0;
}
}
}
AdultCheck::~AdultCheck() {
if( m_debbuf ) {
mfree(m_debbuf, m_debbufSize, "adultcheck");
}
}
int32_t AdultCheck::getScore() {
if( m_resultValid ) {
return m_docAdultScore;
}
return -1;
}
int32_t AdultCheck::getNumUniqueDirtyWords() {
if( m_resultValid ) {
return m_numUniqueDirtyWords;
}
return -1;
}
int32_t AdultCheck::getNumUniqueDirtyPhrases() {
if( m_resultValid ) {
return m_numUniqueDirtyPhrases;
}
return -1;
}
int32_t AdultCheck::getNumWordsChecked() {
if( m_resultValid ) {
return m_numWordsChecked;
}
return -1;
}
bool AdultCheck::hasEmptyDocumentBody() {
if( m_resultValid ) {
return m_emptyDocumentBody;
}
return false;
}
const char *AdultCheck::getReason() {
return m_reason.c_str();
}
const char *AdultCheck::getDebugInfo() {
if( m_debbuf ) {
return m_debbuf;
}
return "";
}
bool AdultCheck::hasAdultRatingTag() {
if( !m_xml ) {
return false;
}
int32_t mtlen;
// https://webmasters.googleblog.com/2012/04/1000-words-about-images.html
// http://www.safelabeling.org/how.htm
// http://www.rtalabel.org/index.php?content=howto
char *mtag = m_xml->getMetaContentPointer( "rating", 6, "name", &mtlen );
if( !mtag || mtlen <= 0 ) {
// http://www.billdietrich.me/Computers.html#ContentRating
// https://en.wikipedia.org/wiki/User:ArneBab/Voluntary_Content_Rating
mtag = m_xml->getMetaContentPointer( "voluntary content rating", 24, "name", &mtlen );
}
switch( mtlen ) {
case 5:
if( strncasecmp(mtag, "adult", mtlen) == 0 ) {
return true;
}
break;
case 6:
if( strncasecmp(mtag, "mature", mtlen) == 0 ) {
return true;
}
break;
case 7:
// non-standard, seen in the wild
if( strncasecmp(mtag, "adulto", mtlen) == 0 ) {
return true;
}
break;
case 10:
// non-standard, seen in the wild
if( strncasecmp(mtag, "restricted", mtlen) == 0 ) {
return true;
}
break;
case 27:
if( strncasecmp(mtag, "RTA-5042-1996-1400-1577-RTA", mtlen) == 0 ) {
return true;
}
break;
}
if( mtlen > 0 ) {
// non-standard, seen in the wild
if( strncasestr(mtag, "porn", mtlen) ||
strncasestr(mtag, "porno", mtlen) ||
strncasestr(mtag, "adult", mtlen) ||
strncasestr(mtag, "fuck", mtlen) ||
strncasestr(mtag, "sex", mtlen) ||
strncasestr(mtag, "xxx", mtlen) ) {
return true;
}
}
// YouTube
mtag = m_xml->getMetaContentPointer( "isFamilyFriendly", 16, "itemprop", &mtlen );
switch( mtlen ) {
case 5:
if( strncasecmp(mtag, "false", mtlen) == 0 ) {
return true;
}
break;
}
return false;
}
bool AdultCheck::hasAdultAds() {
if( !m_xml ) {
return false;
}
int32_t mtlen;
//
// Adult ad networks verification tags
//
char *mtag = m_xml->getMetaContentPointer( "ero_verify", 10, "name", &mtlen );
if( mtag && mtlen > 0 ) {
return true;
}
mtag = m_xml->getMetaContentPointer( "juicyads-site-verification", 26, "name", &mtlen );
if( mtag && mtlen > 0 ) {
return true;
}
mtag = m_xml->getMetaContentPointer( "trafficjunky-site-verification", 30, "name", &mtlen );
if( mtag && mtlen > 0 ) {
return true;
}
mtag = m_xml->getMetaContentPointer( "adamo-site-verification", 23, "name", &mtlen );
if( mtag && mtlen > 0 ) {
return true;
}
return false;
}
bool AdultCheck::isDocAdult() {
// Hash table used to hold unique termIds to make sure we only count each unique word once
HashTableX uniqueTermIds;
if( m_resultValid ) {
return m_result;
}
//
// Check for adult TLDs
//
if( m_url && m_url->isAdult() ) {
m_reason = "adultTLD";
m_docAdultScore += 1000;
}
//
// Check for adult content meta tags
//
if( !m_docAdultScore ) {
if( hasAdultRatingTag() ) {
m_reason = "adultRatingTag";
m_docAdultScore += 1000;
}
if( !m_docAdultScore &&
hasAdultAds() ) {
m_reason = "adultAds";
m_docAdultScore += 1000;
}
}
//
// If not blocked by the cheaper checks, do the hard work and check document content
//
if( !m_docAdultScore ) {
//
// Score words and phrases from the document body text
//
if( m_words ) {
if (!uniqueTermIds.set(sizeof(int64_t), 0, m_words->getNumWords()+5000, NULL, 0, false, "uniquetermids", false, 0)) {
log(LOG_ERROR,"Could not initialize uniqueTermIds hash table");
}
if( !m_words->getNumWords() ) {
// No words in document body
m_emptyDocumentBody = true;
}
else {
g_adultCheckList.getDirtyScore(m_words, m_phrases, &uniqueTermIds, &m_docAdultScore, &m_numUniqueDirtyWords, &m_numUniqueDirtyPhrases, m_debbuf, m_debbufUsed, m_debbufSize);
m_numWordsChecked += m_words->getNumWords();
}
}
else {
// No words in document body
m_emptyDocumentBody = true;
}
//
// Score words and phrases from the document meta tags
//
if( m_xml ) {
Words metaw;
Bits metab;
Phrases metap;
int32_t mtlen;
char *mtag = m_xml->getMetaContentPointer( "keywords", 8, "name", &mtlen );
if( mtlen > 0 ) {
metaw.set(mtag, mtlen, true);
}
mtag = m_xml->getMetaContentPointer( "description", 11, "name", &mtlen );
if( mtlen > 0 ) {
//log(LOG_ERROR, "SETTING DESCRIPTION WORDS");
metaw.addWords(mtag, mtlen, true);
}
if( metaw.getNumWords() ) {
if( !metab.set(&metaw) ) {
log(LOG_ERROR,"COULD NOT SET BITS FOR META WORDS");
}
if( !metap.set(&metaw, &metab) ) {
log(LOG_ERROR,"COULD NOT SET PHRASES FOR META WORDS");
}
g_adultCheckList.getDirtyScore(&metaw, &metap, &uniqueTermIds, &m_docAdultScore, &m_numUniqueDirtyWords, &m_numUniqueDirtyPhrases, m_debbuf, m_debbufUsed, m_debbufSize);
m_numWordsChecked += metaw.getNumWords();
}
}
//
// Score words and phrases from URL
//
if( m_url ) {
Words urlw;
Bits urlb;
Phrases urlp;
urlw.set(m_url->getUrl(), m_url->getUrlLen(), true);
if( !urlb.set(&urlw) ) {
log(LOG_ERROR,"COULD NOT SET BITS FOR URL WORDS");
}
if( !urlp.set(&urlw, &urlb) ) {
log(LOG_ERROR,"COULD NOT SET PHRASES FOR URL WORDS");
}
g_adultCheckList.getDirtyScore(&urlw, &urlp, &uniqueTermIds, &m_docAdultScore, &m_numUniqueDirtyWords, &m_numUniqueDirtyPhrases, m_debbuf, m_debbufUsed, m_debbufSize);
m_numWordsChecked += urlw.getNumWords();
}
if( m_docAdultScore > 0 ) {
m_reason = "adultTerms";
}
//
// Additional check for adult content compliance statement
//
// "18 U.S.C. 2257 Record-Keeping Requirements Compliance Statement"
// "18 USC. 2257 Record-Keeping Requirements Compliance Statement"
int64_t hs18 = hash64Lower_utf8_nospaces("18", 2);
int64_t hsu = hash64Lower_utf8_nospaces("u", 1);
int64_t hss = hash64Lower_utf8_nospaces("s", 1);
int64_t hsc = hash64Lower_utf8_nospaces("c", 1);
int64_t hsusc = hash64Lower_utf8_nospaces("usc", 3);
int64_t hs2257 = hash64Lower_utf8_nospaces("2257", 4);
int64_t hsrecord = hash64Lower_utf8_nospaces("record", 6);
int64_t hskeeping = hash64Lower_utf8_nospaces("keeping", 7);
int64_t hsrequirements = hash64Lower_utf8_nospaces("requirements", 12);
int64_t hscompliance = hash64Lower_utf8_nospaces("compliance", 10);
if( uniqueTermIds.getSlot(&hs18) >= 0 &&
uniqueTermIds.getSlot(&hs2257) >= 0 &&
uniqueTermIds.getSlot(&hsrecord) >= 0 &&
uniqueTermIds.getSlot(&hskeeping) >= 0 &&
uniqueTermIds.getSlot(&hsrequirements) >= 0 &&
uniqueTermIds.getSlot(&hscompliance) >= 0 &&
( (uniqueTermIds.getSlot(&hsu) >= 0 &&
uniqueTermIds.getSlot(&hss) >= 0 &&
uniqueTermIds.getSlot(&hsc) >= 0) ||
uniqueTermIds.getSlot(&hsusc) >= 0
)) {
m_reason = "USC2257Disclaimer";
m_docAdultScore+=1000;
//log(LOG_ERROR,"@@@ USC 2257 compliance statement FOUND in %s: score=%" PRId32 "", url->getUrl(), m_docAdultScore);
}
//TODO:
//18 U.S.C. 2257
//Title 18 U.S.C. 2257 Compliance Statement
//Compliance with 18 U.S.C. &sect; 2257
//<meta http-equiv="PICS-Label" content='(pics-1.1 "http://www.icra.org/ratingsv02.html" comment "ICRAonline EN v2.0" l gen true for "" r (nb 1 nc 1 nd 1 ne 1 nh 1 ni 1 vz 1 la 1 oz 1 cz 1) "http://www.rsac.org/ratingsv01.html" l gen true for "" r (n 3 s 3 v 0 l 4))' />
//Beskyt dine b<>rn mod erotiske sites med
//Protect your children against Adult Content with
//Eltern k<>nnen ihre Kinder vor ungeeigneten Inhalten sch<63>tzen mit
//Prot<6F>gez vos enfants contre le Contenu pour adultes au moyen de
//Skydda dina barn mot inneh<65>ll som endast <20>r avsett f<>r vuxna med hj<68>lp av
//Beskytt barna dine mot voksent innhold med
//Proteggete i vostri figli dal contenuto erotico di questo sito con
//Los padres, protegen a sus menores del Contenido Adulto con
//Os Pais devem usar um dos seguintes programas para salvaguardar os filhos do conte<74>do er<65>tico
//Bescherm minderjarigen tegen expliciete beelden op internet met software als Netnanny, Cyberpatrol of Cybersitter.
}
bool adult = false;
if( ( m_docAdultScore >= 30 || m_numUniqueDirtyWords > 7) ||
( m_docAdultScore >= 30 || m_numUniqueDirtyPhrases >= 3) ) {
adult = true;
}
m_result = adult;
m_resultValid = true;
return m_result;
}
// Check for adult TLDs
// https://tld-list.com/tld-categories/adult
bool isAdultTLD(const char *tld, size_t tld_len) {
switch(tld_len) {
case 3:
if( strncasecmp(tld, "cam", tld_len) == 0 ||
strncasecmp(tld, "sex", tld_len) == 0 ||
strncasecmp(tld, "xxx", tld_len) == 0 ) {
return true;
}
break;
case 4:
if( strncasecmp(tld, "porn", tld_len) == 0 ||
strncasecmp(tld, "sexy", tld_len) == 0 ||
strncasecmp(tld, "tube", tld_len) == 0 ) {
return true;
}
break;
case 5:
if( strncasecmp(tld, "adult", tld_len) == 0 ) {
return true;
}
break;
case 6:
if( strncasecmp(tld, "webcam", tld_len) == 0 ) {
return true;
}
break;
default:
break;
}
return false;
}

70
FxAdultCheck.h Normal file

@ -0,0 +1,70 @@
//
// Copyright (C) 2017 Privacore ApS - https://www.privacore.com
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//
// License TL;DR: If you change this file, you must publish your changes.
//
#ifndef FXADULTCHECK_H_
#define FXADULTCHECK_H_
#include <inttypes.h>
#include <stddef.h>
#include <string>
#include "FxAdultCheckList.h"
class AdultCheck {
public:
AdultCheck(XmlDoc *xd, bool debug=false);
~AdultCheck();
bool init();
bool isDocAdult();
int32_t getScore();
int32_t getNumUniqueDirtyWords();
int32_t getNumUniqueDirtyPhrases();
int32_t getNumWordsChecked();
bool hasEmptyDocumentBody();
const char *getReason();
const char *getDebugInfo();
private:
bool hasAdultRatingTag();
bool hasAdultAds();
Url *m_url;
Xml *m_xml;
Words *m_words;
Phrases *m_phrases;
char *m_debbuf;
int m_debbufUsed;
int m_debbufSize;
std::string m_reason;
int32_t m_docAdultScore;
int32_t m_numUniqueDirtyWords;
int32_t m_numUniqueDirtyPhrases;
int32_t m_numWordsChecked;
bool m_emptyDocumentBody;
bool m_resultValid;
bool m_result;
};
bool isAdultTLD(const char *tld, size_t tld_len);
#endif

264
FxAdultCheckList.cpp Normal file

@ -0,0 +1,264 @@
//
// Copyright (C) 2017 Privacore ApS - https://www.privacore.com
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//
// License TL;DR: If you change this file, you must publish your changes.
//
#include "FxAdultCheckList.h"
#include "Log.h"
#include "termid_mask.h"
#include "Phrases.h"
#include "Words.h"
#include <stddef.h>
#include <fstream>
#include <sys/stat.h>
AdultCheckList g_adultCheckList;
AdultCheckList::AdultCheckList() : m_initialized(false) {}
AdultCheckList::~AdultCheckList(){}
bool AdultCheckList::init() {
if( m_initialized ) {
return true;
}
log(LOG_INFO, "Initializing AdultCheckList");
if( load() ) {
m_initialized = true;
}
return m_initialized;
}
bool AdultCheckList::load() {
//
// Initialize dirty single words
//
int32_t need4 = 10000 * 4 + 5000;
if (!m_dirtyTerms.set(sizeof(int64_t), 4, need4, NULL, 0, false, "dirty", false, 0)) {
log(LOG_ERROR,"Could not initialize dirty word hashtable");
return false;
}
if( !loadScoredTermList(&m_dirtyTerms, "adultwords.txt") ) {
log(LOG_ERROR,"Could not load dirty word file");
}
//
// Initialize dirty phrases (bigrams) - use same hash table as words
//
if( !loadScoredTermList(&m_dirtyTerms, "adultphrases.txt") ) {
log(LOG_ERROR,"Could not load dirty phrase file");
}
return true;
}
bool AdultCheckList::loadScoredTermList(HashTableX *ht, const char *filename) {
log(LOG_INFO, "Loading %s", filename);
struct stat st;
if (stat(filename, &st) != 0) {
// probably not found
log(LOG_INFO, "loadScoredTermlist: Unable to stat %s", filename);
return false;
}
std::ifstream file(filename);
std::string line;
while (std::getline(file, line)) {
// ignore comments & empty lines
if (line.length() == 0 || line[0] == '#') {
continue;
}
auto firstColEnd = line.find_first_of("|");
size_t secondCol = line.find_first_not_of("|", firstColEnd);
if( firstColEnd == std::string::npos || secondCol == std::string::npos) {
// invalid format
log(LOG_ERROR,"Invalid line read: %.*s", (int)line.length(), line.data());
continue;
}
size_t secondColEnd = line.find_first_of("|", secondCol);
size_t thirdCol = line.find_first_not_of("|", secondColEnd);
if (thirdCol == std::string::npos) {
// invalid format
log(LOG_ERROR,"Invalid line read: %.*s", (int)line.length(), line.data());
continue;
}
std::string lang = std::string(line, 0, firstColEnd);
std::string col2(line, secondCol, secondColEnd - secondCol);
std::string col3 = std::string(line, thirdCol);
int32_t dwscore = atoi(col3.data());
if( dwscore < 1 || col2.length() < 1 || col3.length() < 1 ) {
log(LOG_ERROR,"Invalid line read: %.*s", (int)line.length(), line.data());
continue;
}
//log(LOG_ERROR,"read: %s [%" PRId32 "] [%s]", col2.c_str(), dwscore, lang.c_str());
int64_t dwid = hash64Lower_utf8_nospaces(col2.data(), col2.length());
if( !ht->addKey(&dwid, &dwscore) ) {
log(LOG_ERROR,"COULD NOT ADD [%.*s] TO DIRTY WORD LIST", (int)col2.length(), col2.data());
return false;
}
}
log(LOG_INFO, "Loaded %s", filename);
return true;
}
bool AdultCheckList::getDirtyScore(Words *w, Phrases *p, HashTableX *uniqueTermIds, int32_t *docAdultScore, int32_t *numUniqueDirtyWords, int32_t *numUniqueDirtyPhrases, char *debbuf, int32_t &debbuf_used, int32_t debbuf_size) {
if( !w || !uniqueTermIds || !docAdultScore || !numUniqueDirtyWords || !numUniqueDirtyPhrases ) {
return false;
}
if( debbuf ) {
debbuf[debbuf_used] = '\0';
}
int rc;
bool debug=false;
const uint64_t *wids = reinterpret_cast<const uint64_t*>(w->getWordIds());
int32_t nw = w->getNumWords();
// log(LOG_ERROR,"=== numWords=%" PRId32 ", debbuf=%p, debbuf_size=%" PRId32 " ===", nw, debbuf, debbuf_size);
for(int32_t i=0; i < nw; i++) {
if( !wids[i] ) {
continue;
}
char *s = w->getWord(i);
if( !s ) {
continue;
}
int32_t slen = w->getWordLen(i);
int64_t termId = hash64Lower_utf8_nospaces( s , slen );
// only process if we haven't seen it before
if ( uniqueTermIds->getSlot( &termId ) >= 0 ) {
if(debug) log(LOG_ERROR,"ALREADY SEEN WORD %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ")", i, slen, s, (uint64_t)termId, (uint64_t)(termId & TERMID_MASK));
}
else {
// add to hash table. return NULL and set g_errno on error
if ( !uniqueTermIds->addKey(&termId)) {
log(LOG_ERROR,"Could not add termId to uniqueTermIds hash table");
}
int32_t *sc = (int32_t*)m_dirtyTerms.getValue64(termId);
if( sc ) {
if(debug) log(LOG_ERROR,"DIRTY WORD %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ") score %" PRId32 ". debbuf_used=%" PRId32 ", debbuf_size=%" PRId32 "", i, slen, s, (uint64_t)termId, (uint64_t)(termId & TERMID_MASK), *sc, debbuf_used, debbuf_size);
(*docAdultScore) += *sc;
(*numUniqueDirtyWords)++;
if( debbuf ) {
// 2=", ", 2="w:"
if( debbuf_used+slen+2+2+1 < debbuf_size ) {
if(debbuf_used ) {
rc = snprintf(&debbuf[debbuf_used], debbuf_size - debbuf_used, ", ");
if( rc > 0 ) {
debbuf_used += rc;
}
}
rc = snprintf(&debbuf[debbuf_used], debbuf_size - debbuf_used, "w:%.*s", slen, s);
if( rc > 0 ) {
debbuf_used += rc;
}
}
}
}
else {
if(debug) log(LOG_ERROR,"WORD %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ")", i, slen, s, (uint64_t)termId, (uint64_t)(termId & TERMID_MASK));
}
}
const uint64_t *pids = reinterpret_cast<const uint64_t*>(p->getPhraseIds2());
if( !pids[i] ) {
// No phrases
continue;
}
int32_t plen;
char pbuf[256];
p->getPhrase(i, pbuf, sizeof(pbuf), &plen);
if( plen ) {
int64_t phraseId = hash64Lower_utf8_nospaces( pbuf , plen );
if ( uniqueTermIds->getSlot ( &phraseId ) >= 0 ) {
if(debug) log(LOG_ERROR,"ALREADY SEEN PHRASE %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ")", i, plen, pbuf, (uint64_t)phraseId, (uint64_t)(phraseId & TERMID_MASK));
continue;
}
// add to hash table. return NULL and set g_errno on error
if ( !uniqueTermIds->addKey(&phraseId)) {
log(LOG_ERROR,"Could not add phraseId to uniqueTermIds hash table");
}
int32_t *sc = (int32_t*)m_dirtyTerms.getValue64(phraseId);
if( sc ) {
if(debug) log(LOG_ERROR,"DIRTY PHRASE %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ") score %" PRId32 ". debbuf_used=%" PRId32 ", debbuf_size=%" PRId32 "", i, plen, pbuf, (uint64_t)phraseId, (uint64_t)(phraseId & TERMID_MASK), *sc, debbuf_used, debbuf_size);
(*docAdultScore) += *sc;
(*numUniqueDirtyPhrases)++;
if( debbuf ) {
// 2=", ", 2="p:"
if( debbuf_used+plen+2+2+1 < debbuf_size ) {
if(debbuf_used) {
rc = snprintf(&debbuf[debbuf_used], debbuf_size-debbuf_used, ", ");
if( rc > 0 ) {
debbuf_used += rc;
}
}
rc = snprintf(&debbuf[debbuf_used], debbuf_size-debbuf_used, "p:%.*s", plen, pbuf);
if( rc > 0 ) {
debbuf_used += rc;
}
}
}
}
else {
if(debug) log(LOG_ERROR,"PHRASE %" PRId32 ": %.*s -> %" PRIu64 " (%" PRId64 ")", i, plen, pbuf, (uint64_t)phraseId, (uint64_t)(phraseId & TERMID_MASK));
}
}
}
if( debbuf ) {
debbuf[debbuf_used] = '\0';
}
return true;
}

53
FxAdultCheckList.h Normal file

@ -0,0 +1,53 @@
//
// Copyright (C) 2017 Privacore ApS - https://www.privacore.com
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//
// License TL;DR: If you change this file, you must publish your changes.
//
#ifndef FXADULTCHECKLIST_H_
#define FXADULTCHECKLIST_H_
#include <inttypes.h>
#include <stddef.h>
#include <string>
#include "HashTableX.h"
class Phrases;
class Words;
class Xml;
class XmlDoc;
class Url;
class AdultCheckList {
public:
AdultCheckList();
~AdultCheckList();
bool init();
bool getDirtyScore(Words *w, Phrases *p, HashTableX *uniqueTermIds, int32_t *docAdultScore, int32_t *numUniqueDirtyWords, int32_t *numUniqueDirtyPhrases, char *debbuf, int32_t &debbuf_used, int32_t debbuf_size);
protected:
bool load();
private:
bool loadScoredTermList(HashTableX *ht, const char *filename);
HashTableX m_dirtyTerms;
bool m_initialized;
};
extern AdultCheckList g_adultCheckList;
#endif

642
LICENSE

@ -1,3 +1,15 @@
IMPORTANT NOTICE: THIS IS A MIXED LICENSE PROJECT.
The original Gigablast project is covered by an Apache License with additional
restrictions. All files not marked otherwise, are covered by this license.
Files developed entirely by Privacore ApS is covered by the GNU Affero General
Public License. Bascially this means that you have to publish changes you make
to these files, even if you only run the code on a server.
===============================================================================
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
@ -199,4 +211,632 @@ license that then you can arrange a licensing agreement with Matt Wells.
Likewise, the Event datamining logic is in Events.cpp and must be separately licensed
as well.
The companies ElasticSearch BV, LucidWorks and their subsidiaries or affiliates are excluded from this license.
The companies ElasticSearch BV, LucidWorks and their subsidiaries or affiliates are
excluded from this license.
===============================================================================
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS

128
LanguageResultOverride.cpp Normal file

@ -0,0 +1,128 @@
//
// Created by alc on 10/25/17.
//
#include "LanguageResultOverride.h"
#include "ResultOverride.h"
#include "Url.h"
#include "Log.h"
#include "Conf.h"
#include "GbUtil.h"
#include <sys/stat.h>
#include <fstream>
LanguageResultOverride::LanguageResultOverride(const char *filename)
: m_filename(filename)
, m_languageResultOverrideMap(new languageresultoverridemap_t)
, m_lastModifiedTime(0) {
}
LanguageResultOverride::LanguageResultOverride(languageresultoverridemap_ptr_t languageResultOverrideMap)
: m_filename(nullptr)
, m_languageResultOverrideMap(languageResultOverrideMap)
, m_lastModifiedTime(0) {
}
bool LanguageResultOverride::load() {
// sanity check to make sure we don't call load with a null filename
if (m_filename == nullptr) {
gbshutdownLogicError();
}
logTrace(g_conf.m_logTraceLanguageResultOverride, "Loading %s", m_filename);
struct stat st;
if (stat(m_filename, &st) != 0) {
// probably not found
log(LOG_INFO, "RobotsBlockedResultOverride::load: Unable to stat %s", m_filename);
return false;
}
if (m_lastModifiedTime != 0 && m_lastModifiedTime == st.st_mtime) {
// not modified. assume successful
logTrace(g_conf.m_logTraceLanguageResultOverride, "Not modified");
return true;
}
languageresultoverridemap_ptr_t tmpLanguageResultOverride(new languageresultoverridemap_t);
std::ifstream file(m_filename);
std::string line;
while (std::getline(file, line)) {
// ignore comments & empty lines
if (line.length() == 0 || line[0] == '#') {
continue;
}
std::vector<std::string> tokens = split(line, '|');
if (tokens.size() != 3) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
tmpLanguageResultOverride->emplace(tokens[0], ResultOverride(tokens[1], tokens[2]));
logTrace(g_conf.m_logTraceLanguageResultOverride, "Adding criteria '%s' to list", line.c_str());
}
swapLanguageResultOverride(tmpLanguageResultOverride);
m_lastModifiedTime = st.st_mtime;
logTrace(g_conf.m_logTraceLanguageResultOverride, "Loaded %s", m_filename);
return true;
}
std::string LanguageResultOverride::getTitle(const std::string &lang, const Url &url) const {
logTrace(g_conf.m_logTraceLanguageResultOverride, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto resultOverrideMap = getLanguageResultOverrideMap();
auto it = resultOverrideMap->find(lang);
if (it != resultOverrideMap->end()) {
logTrace(g_conf.m_logTraceLanguageResultOverride, "found lang=%s", lang.c_str());
return it->second.getTitle(url);
}
// default to english
if (lang.compare("en") != 0) {
auto it = resultOverrideMap->find("en");
if (it != resultOverrideMap->end()) {
logTrace(g_conf.m_logTraceLanguageResultOverride, "found default lang=en");
return it->second.getTitle(url);
}
}
// empty means no override
return "";
}
std::string LanguageResultOverride::getSummary(const std::string &lang, const Url &url) const {
logTrace(g_conf.m_logTraceLanguageResultOverride, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto resultOverrideMap = getLanguageResultOverrideMap();
auto it = resultOverrideMap->find(lang);
if (it != resultOverrideMap->end()) {
logTrace(g_conf.m_logTraceLanguageResultOverride, "found lang=%s", lang.c_str());
return it->second.getSummary(url);
}
// default to english
if (lang.compare("en") != 0) {
auto it = resultOverrideMap->find("en");
if (it != resultOverrideMap->end()) {
logTrace(g_conf.m_logTraceLanguageResultOverride, "found default lang=en");
return it->second.getSummary(url);
}
}
// empty means no override
return "";
}
void LanguageResultOverride::swapLanguageResultOverride(languageresultoverridemapconst_ptr_t languageResultOverrideMap) {
std::atomic_store(&m_languageResultOverrideMap, languageResultOverrideMap);
}
languageresultoverridemapconst_ptr_t LanguageResultOverride::getLanguageResultOverrideMap() const {
return m_languageResultOverrideMap;
}

37
LanguageResultOverride.h Normal file

@ -0,0 +1,37 @@
#ifndef LANGUAGERESULTOVERRIDE_H
#define LANGUAGERESULTOVERRIDE_H
#include <string>
#include <map>
#include <memory>
#include <vector>
struct ResultOverride;
typedef std::map<std::string, ResultOverride> languageresultoverridemap_t;
typedef std::shared_ptr<languageresultoverridemap_t> languageresultoverridemap_ptr_t;
typedef std::shared_ptr<const languageresultoverridemap_t> languageresultoverridemapconst_ptr_t;
class Url;
class LanguageResultOverride {
public:
explicit LanguageResultOverride(const char *filename);
explicit LanguageResultOverride(languageresultoverridemap_ptr_t languageResultOverrideMap);
std::string getTitle(const std::string &lang, const Url &url) const;
std::string getSummary(const std::string &lang, const Url &url) const;
protected:
bool load();
void swapLanguageResultOverride(languageresultoverridemapconst_ptr_t resultOverrideMap);
languageresultoverridemapconst_ptr_t getLanguageResultOverrideMap() const;
const char *m_filename;
languageresultoverridemapconst_ptr_t m_languageResultOverrideMap;
time_t m_lastModifiedTime;
};
#endif //LANGUAGERESULTOVERRIDE_H

7
Makefile

@ -11,12 +11,13 @@ export BASE_DIR
unexport CONFIG_CPPFLAGS
OBJS_O0 = \
Abbreviations.o AdultCheck.o \
Abbreviations.o \
BigFile.o \
Clusterdb.o Collectiondb.o Conf.o CountryCode.o \
DailyMerge.o Dir.o Dns.o Domains.o \
Errno.o Entities.o \
File.o \
FxAdultCheckList.o FxAdultCheck.o\
GbMutex.o \
HashTable.o HighFrequencyTermShortcuts.o PageTemperatureRegistry.o Docid2Siteflags.o HttpMime.o HttpRequest.o HttpServer.o Hostdb.o \
iana_charset.o Images.o ip.o \
@ -62,7 +63,7 @@ OBJS_O2 = \
OBJS_O3 = \
DocDelete.o DnsBlockList.o \
IPAddressChecks.o \
Linkdb.o \
LanguageResultOverride.o Linkdb.o \
Msg40.o \
Msg25.o \
RdbBuckets.o RdbIndex.o RdbIndexQuery.o RdbList.o RdbMap.o ResultOverride.o RobotsBlockedResultOverride.o RobotsCheckList.o \
@ -70,7 +71,7 @@ OBJS_O3 = \
ScoringWeights.o \
TopTree.o \
UrlMatch.o UrlMatchList.o UrlMatchHostList.o UrlBlockCheck.o UrlComponent.o UrlParser.o UdpStatistic.o \
UrlRealtimeClassification.o \
UrlRealtimeClassification.o UrlResultOverride.o \
WantedChecker.o \
MergeSpaceCoordinator.o \
GbMoveFile.o GbMoveFile2.o GbCopyFile.o GbMakePath.o \

1
Msg20.cpp

@ -744,6 +744,7 @@ int64_t Msg20Request::makeCacheKey() const
hash_buffer.pushLong(m_getLinkInfo);
hash_buffer.pushLong(m_onlyNeedGoodInlinks);
hash_buffer.pushLong(m_getLinkText);
hash_buffer.pushLong(m_prefferedResultLangId);
hash_buffer.safeMemcpy(ptr_qbuf,size_qbuf);
hash_buffer.safeMemcpy(ptr_ubuf,size_ubuf);
hash_buffer.safeMemcpy(ptr_linkee,size_linkee);

1
Msg20.h

@ -51,6 +51,7 @@ class Msg20Request {
// language the query is in (ptr_qbuf)
uint8_t m_langId;
uint8_t m_prefferedResultLangId;
// we now use the numeric collection # and not the ptr_coll
collnum_t m_collnum;

1
Msg25.cpp

@ -1272,6 +1272,7 @@ bool Msg25::sendRequests() {
// buzz sets the query to see if inlinker has the query terms
// so we can set <absScore2>
r->m_langId = langUnknown; // no synonyms i guess
r->m_prefferedResultLangId = langUnknown;
r->ptr_qbuf = m_qbuf;
r->size_qbuf = m_qbufSize;

6
Msg40.cpp

@ -11,7 +11,7 @@
#include "HttpServer.h"
#include "PageResults.h"
#include "HashTable.h"
#include "AdultCheck.h"
//#include "AdultCheck.h"
#include "Process.h"
#include "UrlRealtimeClassification.h"
#include "UdpServer.h"
@ -263,6 +263,8 @@ bool Msg40::prepareToGetDocIds ( ) {
// . if query has dirty words and family filter is on, set
// number of results to 0, and set the m_queryClen flag to true
// . m_qbuf1 should be the advanced/composite query
#if 0
//@@@ TODO
if ( m_si->m_familyFilter &&
getAdultPoints ( m_si->m_sbuf1.getBufStart() ,
m_si->m_sbuf1.length() ,
@ -271,6 +273,7 @@ bool Msg40::prepareToGetDocIds ( ) {
m_msg3a.reset();
return true;
}
#endif
return getDocIds( false );
}
@ -976,6 +979,7 @@ bool Msg40::launchMsg20s(bool recalled) {
req.ptr_qbuf = const_cast<char*>(q->getQuery());
req.size_qbuf = q->getQueryLen()+1;
req.m_langId = m_si->m_queryLangId;
req.m_prefferedResultLangId = getLangIdFromAbbr(m_si->getPreferredResultLanguage().c_str());
req.m_highlightQueryTerms = m_si->m_doQueryHighlighting;

18
PageResults.cpp

@ -1871,18 +1871,6 @@ static bool printInlinkText ( SafeBuf *sb , Msg20Reply *mr , SearchInput *si ,
return true;
}
static std::string getPreferredResultLanguage(const SearchInput *si) {
if (si->m_fx_qlang && strlen(si->m_fx_qlang) == 2) {
return si->m_fx_qlang;
}
if (si->m_fx_blang && strlen(si->m_fx_blang) >= 2) {
return std::string(si->m_fx_blang, 2);
}
return "en";
}
// use this for xml as well as html
bool printResult(State0 *st, int32_t ix , int32_t *numPrintedSoFar) {
SafeBuf *sb = &st->m_sb;
@ -2243,10 +2231,10 @@ bool printResult(State0 *st, int32_t ix , int32_t *numPrintedSoFar) {
strLen = 0;
}
std::string preferredResultLang = getPreferredResultLanguage(si);
std::string preferredResultLang = si->getPreferredResultLanguage();
std::string overriddenTitle;
// override title
if (mr->m_indexCode == EDOCDISALLOWEDROOT) {
if (strLen == 0 && mr->m_indexCode == EDOCDISALLOWEDROOT) {
overriddenTitle = g_robotsBlockedResultOverride.getTitle(preferredResultLang, uu);
str = overriddenTitle.c_str();
strLen = overriddenTitle.length();
@ -2405,7 +2393,7 @@ bool printResult(State0 *st, int32_t ix , int32_t *numPrintedSoFar) {
// override summary
std::string overriddenSummary;
if (mr->m_indexCode == EDOCDISALLOWEDROOT) {
if (strLen == 0 && mr->m_indexCode == EDOCDISALLOWEDROOT) {
overriddenSummary = g_robotsBlockedResultOverride.getSummary(preferredResultLang, uu);
str = overriddenSummary.c_str();
strLen = overriddenSummary.length();

22
Parms.cpp

@ -5402,7 +5402,7 @@ void Parms::init ( ) {
m->m_group = false;
m++;
m->m_title = "stable-summary cache max age";
m->m_title = "unstable-summary cache max age";
m->m_desc = "How long to cache unstable summaries.";
m->m_cgi = "unstablesumcacheage";
m->m_xml = "UnstableSummaryCacheAge";
@ -8673,6 +8673,13 @@ void Parms::init ( ) {
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for LanguageResultOverride";
m->m_cgi = "ltrc_langro";
simple_m_set(Conf,m_logTraceLanguageResultOverride);
m->m_def = "0";
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for Mem";
m->m_cgi = "ltrc_mem";
simple_m_set(Conf,m_logTraceMem);
@ -8800,13 +8807,6 @@ void Parms::init ( ) {
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for RobotsBlockedMsg";
m->m_cgi = "ltrc_robotsb";
simple_m_set(Conf,m_logTraceRobotsBlocked);
m->m_def = "0";
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for RobotsCheckList";
m->m_cgi = "ltrc_robotscl";
simple_m_set(Conf,m_logTraceRobotsCheckList);
@ -8886,6 +8886,12 @@ void Parms::init ( ) {
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for UrlResultOverride";
m->m_cgi = "ltrc_urlro";
simple_m_set(Conf,m_logTraceUrlResultOverride);
m->m_def = "0";
m->m_page = PAGE_LOG;
m++;
m->m_title = "log trace info for Word Spam detection";
m->m_cgi = "ltrc_wordspam";

97
RobotsBlockedResultOverride.cpp

@ -1,22 +1,16 @@
#include "RobotsBlockedResultOverride.h"
#include "ResultOverride.h"
#include "Loop.h"
#include "Url.h"
#include "Log.h"
#include "Conf.h"
#include "Url.h"
#include "GbUtil.h"
#include <sys/stat.h>
#include <fstream>
RobotsBlockedResultOverride g_robotsBlockedResultOverride;
static const char *s_resultoverride_filename = "robotsblockedresultoverride.txt";
RobotsBlockedResultOverride::RobotsBlockedResultOverride()
: m_filename(s_resultoverride_filename)
, m_resultOverrideMap(new resultoverridemap_t)
, m_lastModifiedTime(0) {
: LanguageResultOverride(s_resultoverride_filename) {
}
bool RobotsBlockedResultOverride::init() {
@ -35,80 +29,21 @@ void RobotsBlockedResultOverride::reload(int /*fd*/, void *state) {
robotsBlockedResultOverride->load();
}
bool RobotsBlockedResultOverride::load() {
g_conf.m_logTraceRobotsBlocked = true;
logTrace(g_conf.m_logTraceRobotsBlocked, "Loading %s", m_filename);
struct stat st;
if (stat(m_filename, &st) != 0) {
// probably not found
log(LOG_INFO, "RobotsBlockedResultOverride::load: Unable to stat %s", m_filename);
return false;
std::string RobotsBlockedResultOverride::getTitle(const std::string &lang, const Url &url) const {
std::string title = LanguageResultOverride::getTitle(lang, url);
if (title.empty()) {
// default title when nothing is configured
title = std::string(url.getHost(), url.getHostLen());
}
if (m_lastModifiedTime != 0 && m_lastModifiedTime == st.st_mtime) {
// not modified. assume successful
logTrace(g_conf.m_logTraceRobotsBlocked, "Not modified");
return true;
return title;
}
std::string RobotsBlockedResultOverride::getSummary(const std::string &lang, const Url &url) const {
std::string summary = LanguageResultOverride::getSummary(lang, url);
if (summary.empty()) {
// default description when nothing is configured
summary = "No description available";
}
resultoverridemap_ptr_t tmpResultOverride(new resultoverridemap_t);
std::ifstream file(m_filename);
std::string line;
while (std::getline(file, line)) {
// ignore comments & empty lines
if (line.length() == 0 || line[0] == '#') {
continue;
}
std::vector<std::string> tokens = split(line, '|');
if (tokens.size() != 3) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
tmpResultOverride->emplace(tokens[0], ResultOverride(tokens[1], tokens[2]));
logTrace(g_conf.m_logTraceRobotsBlocked, "Adding criteria '%s' to list", line.c_str());
}
swapResultOverride(tmpResultOverride);
m_lastModifiedTime = st.st_mtime;
logTrace(g_conf.m_logTraceRobotsBlocked, "Loaded %s", m_filename);
return true;
}
std::string RobotsBlockedResultOverride::getTitle(const std::string &lang, const Url &url) {
logTrace(g_conf.m_logTraceRobotsBlocked, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto resultOverrideMap = getResultOverrideMap();
auto it = resultOverrideMap->find(lang);
if (it != resultOverrideMap->end()) {
return it->second.getTitle(url);
}
// return as default
return std::string(url.getHost(), url.getHostLen());
}
std::string RobotsBlockedResultOverride::getSummary(const std::string &lang, const Url &url) {
logTrace(g_conf.m_logTraceRobotsBlocked, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto resultOverrideMap = getResultOverrideMap();
auto it = resultOverrideMap->find(lang);
if (it != resultOverrideMap->end()) {
return it->second.getSummary(url);
}
// return as default
return "No description available";
}
void RobotsBlockedResultOverride::swapResultOverride(resultoverridemapconst_ptr_t resultOverrideMap) {
std::atomic_store(&m_resultOverrideMap, resultOverrideMap);
}
resultoverridemapconst_ptr_t RobotsBlockedResultOverride::getResultOverrideMap() {
return m_resultOverrideMap;
}
return summary;
}

29
RobotsBlockedResultOverride.h

@ -1,19 +1,10 @@
#ifndef ROBOTSBLOCKEDRESULTOVERRIDE_H
#define ROBOTSBLOCKEDRESULTOVERRIDE_H
#include <string>
#include <map>
#include <memory>
#include "LanguageResultOverride.h"
struct ResultOverride;
typedef std::map<std::string, ResultOverride> resultoverridemap_t;
typedef std::shared_ptr<resultoverridemap_t> resultoverridemap_ptr_t;
typedef std::shared_ptr<const resultoverridemap_t> resultoverridemapconst_ptr_t;
class Url;
class RobotsBlockedResultOverride {
class RobotsBlockedResultOverride : public LanguageResultOverride {
public:
RobotsBlockedResultOverride();
@ -21,20 +12,8 @@ public:
static void reload(int /*fd*/, void *state);
std::string getTitle(const std::string &lang, const Url &url);
std::string getSummary(const std::string &lang, const Url &url);
protected:
bool load();
const char *m_filename;
private:
void swapResultOverride(resultoverridemapconst_ptr_t resultOverrideMap);
resultoverridemapconst_ptr_t getResultOverrideMap();
resultoverridemapconst_ptr_t m_resultOverrideMap;
time_t m_lastModifiedTime;
std::string getTitle(const std::string &lang, const Url &url) const;
std::string getSummary(const std::string &lang, const Url &url) const;
};
extern RobotsBlockedResultOverride g_robotsBlockedResultOverride;

12
SearchInput.cpp

@ -751,3 +751,15 @@ bool SearchInput::setQueryBuffers ( HttpRequest *hr ) {
return true;
}
std::string SearchInput::getPreferredResultLanguage() {
if (m_fx_qlang && strlen(m_fx_qlang) == 2) {
return m_fx_qlang;
}
if (m_fx_blang && strlen(m_fx_blang) >= 2) {
return std::string(m_fx_blang, 2);
}
return "en";
}

3
SearchInput.h

@ -16,6 +16,7 @@
#include "Query.h" // MAX_QUERY_LEN
#include "HttpRequest.h"
#include <string>
class CollectionRec;
@ -35,6 +36,8 @@ public:
void copy ( class SearchInput *si ) ;
std::string getPreferredResultLanguage();
///////////
//
// BEGIN COMPUTED THINGS

233
Speller.cpp

@ -1,7 +1,6 @@
#include "Speller.h"
#include "Query.h"
#include "StopWords.h"
#include "AdultCheck.h"
#include "Hostdb.h"
#include "Process.h"
#include "Conf.h"
@ -531,238 +530,6 @@ int32_t Speller::getPhrasePopularity( const char *str, uint64_t h, unsigned char
return max;
}
// splits words and checks if they form a porn word or not. montanalinux.org
// is showing up as porn because it has 'anal' in the hostname. So try to
// find a combination of words such that they are NOT porn.
// try this only after isAdult() succeeds.
// Always tries to find longer words first. so 'montanalinux' is split as
// 'montana' and 'linux' and not as 'mont', 'analinux'
// if it finds a seq of words leading upto a porn word, then it returns true
// eg. shall split montanalinux into 'mont', 'anal', and return true without
// checking if 'inux' is a word. Need to do this because isAdult() cannot
// define where an adult word has ended.
// TODO: chatswingers.com NOT identified as porn because it is split as
// 'chats' and 'wingers'.
bool Speller::canSplitWords(const char *s, int32_t slen, bool *isPorn, char *splitWords, unsigned char langId) {
*isPorn = false;
const char *index[1024];
if ( slen == 0 )
return true;
*splitWords = '\0';
// this is the current word we're on
int32_t curr = 0;
index[curr++] = s;
index[curr] = s + slen;
while ( curr > 0 ){
const char *nextWord = NULL;
while (findNext( index[curr - 1], index[curr], &nextWord, isPorn, langId )){
// next word in chain
index[curr++] = nextWord;
index[curr] = s + slen;
// found a porn word OR
// finished making a sequence of words
if ( *isPorn || nextWord == s + slen ){
char *p = splitWords;
for ( int32_t k = 1; k < curr; k++ ){
gbmemcpy (p, index[k - 1],
index[k] - index[k - 1]);
p += index[k] - index[k - 1];
*p = ' ';
p++;
}
*p = '\0';
return true;
}
}
// did not find any word. reduce the current position
while ( --curr > 0 ){
if ( curr > 0 && index[curr] > index[curr-1] ){
index[curr]--;
break;
}
}
}
return false;
}
bool Speller::findNext(const char *s, const char *send, const char **nextWord, bool *isPorn, unsigned char langId) {
const char *loc = NULL;
int32_t slen = send - s;
// check if there is an adult word in there
// NOTE: The word 'adult' gives a lot of false positives, so even
// though it is in the isAdult() list, skip it.
// s/slen constitues an individual word.
if ( isAdult ( s, slen, &loc ) && strncmp ( s, "adult", 5 ) != 0 ){
// if this string starts with the adult word, don't check
// further
if ( loc == s ){
*isPorn = true;
*nextWord = send;
return true;
}
}
for(const char *a = send; a > s; a--) {
// a hack, if the word is only one letter long, check if it
// is 'a' or 'i'. If not then continue
if ( a - s == 1 && *s != 'a' && *s != 'i')
continue;
// another hack, the end word of the string cannot be 2 letters
// or less. freesex was being split as 'frees ex'
if ( a == send && a - s <= 2 )
continue;
// do not allow "ult" to be a word because it always will
// split "adult" into "ad+ult"
if ( a - s == 3 && s[0]=='u' && s[1]=='l' && s[2]=='t' )
continue;
// adultsiteratings = "ad ul ts it era tings"
if ( a - s == 2 && s[0]=='u' && s[1]=='l' )
continue;
// lashaxxxnothing = "lash ax xx nothing"
if ( a - s == 2 && s[0]=='u' && s[1]=='l' )
continue;
// livesexasian = "lives ex asian"
if ( a - s == 2 && s[0]=='e' && s[1]=='x' )
continue;
// fuckedtits = "fu ck edt its"
if ( a - s == 2 && s[0]=='c' && s[1]=='k' )
continue;
// blogsexe = "blogs exe" ... many others
// any 3 letter fucking word starting with "ex"
if ( a - s == 3 && s[0]=='e' && s[1]=='x' )
continue;
// shemales = "*s hem ales"
if ( a - s == 4 && s[0]=='a' &&s[1]=='l'&&s[2]=='e'&&s[3]=='s')
continue;
// grooverotica = "groove rot ica"
if ( a - s == 3 && s[0]=='i' && s[1]=='c' && s[2]=='a' )
continue;
// dinerotik = dinero tik
if ( a - s == 3 && s[0]=='t' && s[1]=='i' && s[2]=='k' )
continue;
// nudeslutpics = "nud esl ut pics"
if ( a - s == 3 && s[0]=='n' && s[1]=='u' && s[2]=='d' )
continue;
// seepornos = "seep or nos"
if ( a - s == 3 && s[0]=='n' && s[1]=='o' && s[2]=='s' )
continue;
// bookslut = "books lut"
if ( a - s == 3 && s[0]=='l' && s[1]=='u' && s[2]=='t' )
continue;
// lesexegratuit = "lese xe gratuit"
if ( a - s == 2 && s[0]=='x' && s[1]=='e' )
continue;
// mooiemensensexdating = "mens ense xd a ting"
if ( a - s == 2 && s[0]=='x' && s[1]=='d' )
continue;
// mpornlinks = mpo rn links
if ( a - s == 2 && s[0]=='r' && s[1]=='n' )
continue;
// ukpornbases = ukp or nba bes
if ( a - s == 2 && s[0]=='o' && s[1]=='r' )
continue;
// slut
if ( a - s == 2 && s[0]=='l' && s[1]=='u' )
continue;
// independentstockholmescorts = "tock holme sco rts"
if ( a - s == 3 && s[0]=='s' && s[1]=='c' && s[2]=='o' )
continue;
// relatosexcitantes = relat ose xci tan tes
if ( a - s == 3 && s[0]=='x' && s[1]=='c' && s[2]=='i' )
continue;
// babe = * bes
if ( a - s == 3 && s[0]=='b' && s[1]=='e' && s[2]=='s' )
continue;
// xpornreviews "xp orn reviews "
if ( a - s == 3 && s[0]=='o' && s[1]=='r' && s[2]=='n' )
continue;
// shemal fix
if ( a - s == 3 && s[0]=='h' && s[1]=='e' && s[2]=='m' )
continue;
// adultswim = adults wim
if ( a - s == 3 && s[0]=='w' && s[1]=='i' && s[2]=='m' )
continue;
// bdsm
if ( a - s == 3 && s[0]=='d' && s[1]=='s' && s[2]=='m' )
continue;
// anal
if ( a - s == 3 && s[0]=='n' && s[1]=='a' && s[2]=='l' )
continue;
// vibrator = bra
if ( a - s == 3 && s[0]=='b' && s[1]=='r' && s[2]=='a' )
continue;
// sitiospornox = sitio spor nox
if ( a - s == 4 && s[0]=='s' && s[1]=='p' && s[2]=='o' &&
s[3] == 'r' )
continue;
// orn*
if ( a - s == 4 && s[0]=='o' && s[1]=='r' && s[2]=='n' )
continue;
// hotescorts = hote scor
if ( a - s == 4 && s[0]=='s' && s[1]=='c' && s[2]=='o' &&
s[3] == 'r' )
continue;
// uniformsluts = uniformts lutz
if ( a - s == 4 && s[0]=='l' && s[1]=='u' && s[2]=='t' &&
s[3] == 'z' )
continue;
// free porn login = freep ornl
if ( a - s == 5 && s[0]=='f' && s[1]=='r' && s[2]=='e' &&
s[3] == 'e' && s[4] == 'p' )
continue;
// shemal fix
if ( a - s == 5 && s[0]=='h' && s[1]=='e' && s[2]=='m' &&
s[3] == 'a' && s[4] == 'l' )
continue;
// inbondage = inbond age
if ( a - s == 6 &&
s[0]=='i' && s[1]=='n' && s[2]=='b' &&
s[3]=='o' && s[4]=='n' && s[5]=='d' )
continue;
// swingers = wingers
if ( a - s == 7 &&
s[0]=='w' && s[1]=='i' && s[2]=='n' &&
s[3]=='g' && s[4]=='e' && s[5]=='r' &&
s[6]=='s' )
continue;
// free sex contents = freese xc ont ents
if ( a - s == 2 && s[0]=='x' && s[1]=='c' )
continue;
// mosexstore = mose xs tore
if ( a - s == 2 && s[0]=='x' && s[1]=='s' )
continue;
// phonesexfootsies
if ( a - s == 8 &&
s[0]=='p' && s[1]=='h' && s[2]=='o' &&
s[3]=='n' && s[4]=='e' && s[5]=='s' &&
s[6]=='e' && s[7]=='x' )
continue;
// cybersex
if ( a - s == 8 &&
s[0]=='c' && s[1]=='y' && s[2]=='b' &&
s[3]=='e' && s[4]=='r' && s[5]=='s' &&
s[6]=='e' && s[7]=='x' )
continue;
// hotescorts
// check if the word has popularity. if it is in the
// unifiedDict, then it is considered to be a word
uint64_t h = hash64d(s, a-s);//a - s, encodeType);
int32_t pop = getPhrasePopularity( s, h, langId );
// continue if did not find it
if ( pop <= 0 )
continue;
// this is our next word
*nextWord = a;
return true;
}
return false;
}
// This isn't really much use except for the spider
// language detection to keep from making 32 sequential

8
Summary.cpp

@ -94,6 +94,14 @@ bool Summary::verifySummary(const char *titleBuf, int32_t titleBufLen) {
return false;
}
void Summary::setSummary(const std::string &summary) {
m_summaryLen = summary.copy(m_summary, MAX_SUMMARY_LEN);
m_summary[m_summaryLen] = '\0';
m_summaryExcerptLen[0] = m_summaryLen;
m_numExcerpts = 1;
m_displayLen = m_summaryLen;
}
// let's try to get a nicer summary by using what the website set as description
// Use the following in priority order (highest first)
// - itemprop = "description"

3
Summary.h

@ -21,6 +21,7 @@
#define GB_SUMMARY_H
#include "gb-include.h"
#include <string>
#define MAX_SUMMARY_LEN (1024*20)
#define MAX_SUMMARY_EXCERPTS 1024
@ -39,6 +40,8 @@ public:
Summary();
~Summary();
void setSummary(const std::string &summary);
bool setSummary(const Xml *xml, const Words *words, const Sections *sections, Pos *pos, const Query *q,
int32_t maxSummaryLen, int32_t numDisplayLines, int32_t maxNumLines, int32_t maxNumCharsPerLine,
const Url *f, const Matches *matches, const char *titleBuf, int32_t titleBufLen);

5
Title.cpp

@ -61,6 +61,11 @@ void Title::reset() {
m_titleTagEnd = -1;
}
void Title::setTitle(const std::string &title) {
m_titleLen = title.copy(m_title, MAX_TITLE_LEN);
m_title[m_titleLen] = '\0';
}
bool Title::setTitleFromTags( Xml *xml, int32_t maxTitleLen, uint8_t contentType ) {
/// @todo cater for CT_DOC (when antiword is replaced)
// only allow html & pdf documents for now

3
Title.h

@ -4,6 +4,7 @@
#define GB_TITLE_H
#include <stdint.h>
#include <string>
#define MAX_TITLE_LEN 2048
@ -22,6 +23,8 @@ public:
void reset();
void setTitle(const std::string &title);
bool setTitle( Xml *xml, Words *words, int32_t maxTitleLen, Query *query, LinkInfo *linkInfo, Url *firstUrl,
const char *filteredRootTitleBuf, int32_t filteredRootTitleBufSize, uint8_t contentType,
uint8_t langId );

5
TitleRecVersion.h

@ -19,6 +19,9 @@
// strip ascii tab & newline from url
// store m_indexCode in TitleRec
#define TITLEREC_CURRENT_VERSION 125
//#define TITLEREC_CURRENT_VERSION 125
// new adult detection
#define TITLEREC_CURRENT_VERSION 126
#endif // GB_TITLERECVERSION_H

11
Url.cpp

@ -2,7 +2,7 @@
#include "UrlParser.h"
#include "Domains.h"
#include "HashTable.h"
#include "AdultCheck.h"
#include "FxAdultCheck.h"
#include "ip.h" // atoip ( s,len)
#include "Punycode.h"
#include "Unicode.h"
@ -1670,8 +1670,13 @@ bool Url::isHostWWW ( ) const {
// . if you add a word here, add it to PageResults.cpp:isQueryDirty()
bool Url::isAdult() const {
//certain TLDs are clearly adult-oriented
if(isAdultTLD(m_tld,m_tldLen))
if( isAdultTLD(m_tld, m_tldLen))
return true;
#if 0
//@@@
if(m_hlen<=0)
return false; // Invalid URL (no hostname)
if(m_tldLen<=0)
@ -1716,10 +1721,10 @@ bool Url::isAdult() const {
// point to next
p = pend + 1;
}
#endif
return false;
}
// . remove any session id
// . i'm sick of these tihngs causing dup problems
// . types:

135
UrlResultOverride.cpp Normal file

@ -0,0 +1,135 @@
#include "UrlResultOverride.h"
#include "LanguageResultOverride.h"
#include "ResultOverride.h"
#include "Loop.h"
#include "Log.h"
#include "Conf.h"
#include "Url.h"
#include "GbUtil.h"
#include <sys/stat.h>
#include <fstream>
UrlResultOverride g_urlResultOverride;
static const char *s_resultoverride_filename = "urlresultoverride.txt";
UrlResultOverride::UrlResultOverride()
: m_filename(s_resultoverride_filename)
, m_urlResultOverrideMap(new urlresultoverridemap_t)
, m_lastModifiedTime(0) {
}
bool UrlResultOverride::init() {
if (!g_loop.registerSleepCallback(60000, this, &reload, "UrlResultOverride::reload", 0)) {
log(LOG_WARN, "UrlResultOverride::init: Failed to register callback.");
return false;
}
load();
return true;
}
void UrlResultOverride::reload(int /*fd*/, void *state) {
UrlResultOverride *urlResultOverride = static_cast<UrlResultOverride*>(state);
urlResultOverride->load();
}
bool UrlResultOverride::load() {
logTrace(g_conf.m_logTraceUrlResultOverride, "Loading %s", m_filename);
struct stat st;
if (stat(m_filename, &st) != 0) {
// probably not found
log(LOG_INFO, "UrlResultOverride::load: Unable to stat %s", m_filename);
return false;
}
if (m_lastModifiedTime != 0 && m_lastModifiedTime == st.st_mtime) {
// not modified. assume successful
logTrace(g_conf.m_logTraceUrlResultOverride, "Not modified");
return true;
}
urlresultoverridemap_ptr_t tmpUrlResultOverride(new urlresultoverridemap_t);
languageresultoverridemap_ptr_t tmpLanguageResultOverride(new languageresultoverridemap_t);
std::string prevUrl;
std::ifstream file(m_filename);
std::string line;
while (std::getline(file, line)) {
// ignore comments & empty lines
if (line.length() == 0 || line[0] == '#') {
continue;
}
std::vector<std::string> tokens = split(line, '|');
if (tokens.size() != 4) {
logError("Invalid line found. Ignoring line='%s'", line.c_str());
continue;
}
std::string currentUrl(tokens[0]);
if (!prevUrl.empty() && prevUrl.compare(currentUrl) != 0) {
logTrace(g_conf.m_logTraceUrlResultOverride, "Adding url '%s' to url map", prevUrl.c_str());
tmpLanguageResultOverride = std::make_shared<languageresultoverridemap_t>();
tmpUrlResultOverride->emplace(prevUrl, LanguageResultOverride(tmpLanguageResultOverride));
}
tmpLanguageResultOverride->emplace(tokens[1], ResultOverride(tokens[2], tokens[3]));
logTrace(g_conf.m_logTraceUrlResultOverride, "Adding criteria '%s' to language map", line.c_str());
prevUrl = currentUrl;
}
// add last item
tmpUrlResultOverride->emplace(prevUrl, LanguageResultOverride(tmpLanguageResultOverride));
swapUrlResultOverride(tmpUrlResultOverride);
m_lastModifiedTime = st.st_mtime;
logTrace(g_conf.m_logTraceUrlResultOverride, "Loaded %s", m_filename);
return true;
}
std::string UrlResultOverride::getTitle(const std::string &lang, const Url &url) {
logTrace(g_conf.m_logTraceUrlResultOverride, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto urlResultOverrideMap = getUrlResultOverrideMap();
auto it = urlResultOverrideMap->find(url.getUrl());
if (it != urlResultOverrideMap->end()) {
logTrace(g_conf.m_logTraceUrlResultOverride, "found url=%s", url.getUrl());
return it->second.getTitle(lang, url);
}
logTrace(g_conf.m_logTraceUrlResultOverride, "lang=%s url=%s no override", lang.c_str(), url.getUrl());
// empty means no override
return "";
}
std::string UrlResultOverride::getSummary(const std::string &lang, const Url &url) {
logTrace(g_conf.m_logTraceUrlResultOverride, "lang=%s url=%s", lang.c_str(), url.getUrl());
auto urlResultOverrideMap = getUrlResultOverrideMap();
auto it = urlResultOverrideMap->find(url.getUrl());
if (it != urlResultOverrideMap->end()) {
logTrace(g_conf.m_logTraceUrlResultOverride, "found url=%s", url.getUrl());
return it->second.getSummary(lang, url);
}
logTrace(g_conf.m_logTraceUrlResultOverride, "lang=%s url=%s no override", lang.c_str(), url.getUrl());
// empty means no override
return "";
}
void UrlResultOverride::swapUrlResultOverride(urlresultoverridemapconst_ptr_t resultOverrideMap) {
std::atomic_store(&m_urlResultOverrideMap, resultOverrideMap);
}
urlresultoverridemapconst_ptr_t UrlResultOverride::getUrlResultOverrideMap() {
return m_urlResultOverrideMap;
}

44
UrlResultOverride.h Normal file

@ -0,0 +1,44 @@
#ifndef URLRESULTOVERRIDE_H
#define URLRESULTOVERRIDE_H
#include <string>
#include <map>
#include <memory>
class LanguageResultOverride;
typedef std::map<std::string, LanguageResultOverride> urlresultoverridemap_t;
typedef std::shared_ptr<urlresultoverridemap_t> urlresultoverridemap_ptr_t;
typedef std::shared_ptr<const urlresultoverridemap_t> urlresultoverridemapconst_ptr_t;
class Url;
class UrlResultOverride {
public:
UrlResultOverride();
bool init();
static void reload(int /*fd*/, void *state);
std::string getTitle(const std::string &lang, const Url &url);
std::string getSummary(const std::string &lang, const Url &url);
protected:
bool load();
const char *m_filename;
private:
void swapUrlResultOverride(urlresultoverridemapconst_ptr_t resultOverrideMap);
urlresultoverridemapconst_ptr_t getUrlResultOverrideMap();
urlresultoverridemapconst_ptr_t m_urlResultOverrideMap;
time_t m_lastModifiedTime;
};
extern UrlResultOverride g_urlResultOverride;
#endif //URLRESULTOVERRIDE_H

2
Words.h

@ -49,7 +49,7 @@ class Words {
// . use range (node1,node2] and if node2 is -1 that means the last one
bool set( Xml *xml, bool computeIds, int32_t node1 = 0, int32_t node2 = -1 );
inline bool addWords( char *s, int32_t nodeLen, bool computeIds );
bool addWords( char *s, int32_t nodeLen, bool computeIds );
// get the spam modified score of the ith word (baseScore is the
// score if the word is not spammed)

45
XmlDoc.cpp

@ -27,7 +27,7 @@
#include "Wiktionary.h"
#include "Parms.h"
#include "Domains.h"
#include "AdultCheck.h"
#include "FxAdultCheck.h"
#include "Doledb.h"
#include "IPAddressChecks.h"
#include "PageRoot.h"
@ -48,6 +48,7 @@
#include "DnsBlockList.h"
#include "GbDns.h"
#include "RobotsCheckList.h"
#include "UrlResultOverride.h"
#ifdef _VALGRIND_
@ -1157,6 +1158,12 @@ bool XmlDoc::set2 ( char *titleRec ,
m_indexCode = 0;
}
// adult detection code replaced. Invalidate old document versions.
if( m_version < 126 ) {
m_isAdultValid = false;
}
m_indexCodeValid = true;
m_redirError = 0;
m_redirErrorValid = true;
@ -2172,6 +2179,7 @@ int32_t *XmlDoc::getIndexCode ( ) {
if ( cr->m_doUrlSpamCheck && ! m_check2 ) {
m_check2 = true;
if ( m_firstUrl.isAdult() ) {
m_indexCode = EDOCURLSPAM;
m_indexCodeValid = true;
@ -3137,6 +3145,11 @@ SafeBuf *XmlDoc::getTitleRecBuf ( ) {
// . check content for adult words
char *XmlDoc::getIsAdult ( ) {
// adult detection code replaced. Invalidate old document versions.
if( m_version < 126 ) {
m_isAdultValid = false;
}
if ( m_isAdultValid ) return &m_isAdult2;
// call that
@ -3150,9 +3163,8 @@ char *XmlDoc::getIsAdult ( ) {
// time it
int64_t start = gettimeofdayInMilliseconds();
// score that up
int32_t total = getAdultPoints ( ptr_utf8Content, size_utf8Content - 1 , m_firstUrl.getUrl() );
AdultCheck achk(this);
m_isAdult = achk.isDocAdult();
// debug msg
int64_t took = gettimeofdayInMilliseconds() - start;
@ -3161,9 +3173,6 @@ char *XmlDoc::getIsAdult ( ) {
"build: Took %" PRId64" ms to check doc of %" PRId32" bytes for "
"dirty words.",took,size_utf8Content-1);
m_isAdult = false;
// adult?
if ( total >= 2 ) m_isAdult = true;
// set shadow member
m_isAdult2 = (bool)m_isAdult;
// validate
@ -3171,7 +3180,7 @@ char *XmlDoc::getIsAdult ( ) {
// note it
if ( m_isAdult2 && g_conf.m_logDebugDirty )
log("dirty: %s points = %" PRId32,m_firstUrl.getUrl(),total);
log("dirty: %s score = %" PRId32,m_firstUrl.getUrl(), achk.getScore());
// no dirty words found
return &m_isAdult2;
@ -16124,6 +16133,16 @@ Title *XmlDoc::getTitle() {
return &m_title;
}
// look for override
if (m_req && m_req->m_prefferedResultLangId != langUnknown) {
std::string title = g_urlResultOverride.getTitle(getLanguageAbbr(m_req->m_prefferedResultLangId), m_firstUrl);
if (!title.empty()) {
m_titleValid = true;
m_title.setTitle(title);
return &m_title;
}
}
uint8_t *contentTypePtr = getContentType();
if ( ! contentTypePtr || contentTypePtr == (void *)-1 ) {
return (Title *)contentTypePtr;
@ -16197,6 +16216,16 @@ Summary *XmlDoc::getSummary () {
return &m_summary;
}
// look for override
if (m_req && m_req->m_prefferedResultLangId != langUnknown) {
std::string summary = g_urlResultOverride.getSummary(getLanguageAbbr(m_req->m_prefferedResultLangId), m_firstUrl);
if (!summary.empty()) {
m_summaryValid = true;
m_summary.setSummary(summary);
return &m_summary;
}
}
// time cpu set time
m_cpuSummaryStartTime = gettimeofdayInMilliseconds();

41
adultphrases.txt.example Normal file

@ -0,0 +1,41 @@
#
# Format:
#
# language | phrase | score
#
# Language is currently unused. Even though a word must have a language specified, it may
# be used in other languages as well.
#
# Score based on "would you want your 10 year old daughter to see and read this content?".
#
# scores
# 1 as single term, the word can be considered OK in some situations (like "rape" in "rape conviction rate")
# 5 likely adult content
# 10 very likely adult content
# 20 almost certainly adult content
# 99 certainly adult content
# 666 likely illegal content
#
# 5 matches or a score over 30 should be a clear adult content indicator. Phrase matches will use other,
# higher scores.
#
# CAREFUL: "as seating" and "ass eating" results in the same term id...
#
#
en|pussy gallery|99
en|pussy galleries|99
en|cumshot compilation|99
en|teen porn|99
en|sadomaso online|99
en|bbw cams|99
en|bbw porn|99
en|bbw strippers|99
en|bbw videos|99
en|biggest cocks|20
en|biggest cock|20
en|biggest dicks|20
en|biggest dick|20
en|biggest tits|20
#
# .. etc. Filling this in is left as an exercise for the reader.
#

39
adultwords.txt.example Normal file

@ -0,0 +1,39 @@
#
# language | word | score
#
# Language is currently unused. Even though a word must have a language specified, it may
# be used in other languages as well.
#
# Score based on "would you want your 10 year old daughter to see and read this content?".
#
# scores
# 1 as single term, the word can be considered OK in some situations (like "rape" in "rape conviction rate")
# 5 likely adult content
# 10 very likely adult content
# 20 almost certainly adult content
#
# 5 matches or a score over 30 should be a clear adult content indicator. Phrase matches will use higher scores.
#
en|redtube|10
en|porntube|20
en|twats|5
en|pantyhose|1
en|3some|5
en|4some|5
en|analdildo|20
en|anal|1
en|assfucking|20
en|assfuck|20
en|bangbros|20
en|banging|5
en|bbw|20
en|bdsm|2
en|blowjobs|20
en|blowjobx|20
en|blowjob|20
en|bondage|5
en|boners|1
en|boner|1
#
# .. etc. Filling this in is left as an exercise for the reader.
#

188
main.cpp

@ -91,6 +91,9 @@
#include "SpiderdbHostDelete.h"
#include "ConvertSpiderdb.h"
#include "RobotsBlockedResultOverride.h"
#include "UrlResultOverride.h"
#include "FxAdultCheck.h"
#include <sys/stat.h> //umask()
#include <fcntl.h>
#include <sys/mman.h>
@ -123,6 +126,8 @@ static void dumpLinkdb(const char *coll, int32_t sfn, int32_t numFiles, bool inc
static void dumpUnwantedTitledbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree);
static void dumpWantedTitledbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree);
static void dumpAdultTitledbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree);
//static void dumpUnwantedSpiderdbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree);
//
//static int32_t verifySpiderdb(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree, int32_t firstIp);
@ -1340,8 +1345,10 @@ int main2 ( int argc , char *argv[] ) {
dumpUnwantedTitledbRecs(coll, startFileNum, numFiles, includeTree);
} else if (strcmp(argv[cmdarg+1], "wt") == 0) {
dumpWantedTitledbRecs(coll, startFileNum, numFiles, includeTree);
// } else if (strcmp(argv[cmdarg+1], "us") == 0) {
// dumpUnwantedSpiderdbRecs(coll, startFileNum, numFiles, includeTree);
} else if (strcmp(argv[cmdarg+1], "at") == 0) {
dumpAdultTitledbRecs(coll, startFileNum, numFiles, includeTree);
// } else if (strcmp(argv[cmdarg+1], "us") == 0) {
// dumpUnwantedSpiderdbRecs(coll, startFileNum, numFiles, includeTree);
} else {
goto printHelp;
}
@ -1635,6 +1642,10 @@ int main2 ( int argc , char *argv[] ) {
g_robotsCheckList.init();
g_robotsBlockedResultOverride.init();
g_urlResultOverride.init();
// Initialize adult detection
g_adultCheckList.init();
// initialize generate global index thread
if (!RdbBase::initializeGlobalIndexThread()) {
@ -3883,6 +3894,179 @@ static void dumpWantedTitledbRecs(const char *coll, int32_t startFileNum, int32_
}
static void dumpAdultTitledbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree) {
if(startFileNum!=0 && numFiles<0) {
//this may apply to all files, but I haven't checked into hash-based ones yet
fprintf(stderr,"If <startFileNum> is specified then <numFiles> must be too\n");
return;
}
if (!ucInit(g_hostdb.m_dir)) {
log("Unicode initialization failed!");
return;
}
// init our table for doing zobrist hashing
if ( ! hashinit() ) {
log("db: Failed to init hashtable." );
return;
}
g_titledb.init ();
g_titledb.getRdb()->addRdbBase1(coll);
key96_t startKey ;
key96_t endKey ;
key96_t lastKey ;
startKey.setMin();
endKey.setMax();
lastKey.setMin();
startKey = Titledb::makeFirstKey(0);
Msg5 msg5;
RdbList list;
// make this
XmlDoc *xd;
try {
xd = new (XmlDoc);
}
catch(std::bad_alloc&) {
fprintf(stdout,"could not alloc for xmldoc\n");
exit(-1);
}
const CollectionRec *cr = g_collectiondb.getRec(coll);
if(cr==NULL) {
fprintf(stderr,"Unknown collection '%s'\n", coll);
return;
}
// initialize shlib & blacklist
if (!WantedChecker::initialize()) {
fprintf(stderr, "Unable to initialize WantedChecker");
return;
}
g_urlBlackList.init();
g_urlWhiteList.init();
g_adultCheckList.init();
for(;;) {
// use msg5 to get the list, should ALWAYS block since no threads
if ( ! msg5.getList ( RDB_TITLEDB ,
cr->m_collnum ,
&list ,
&startKey ,
&endKey ,
commandLineDumpdbRecSize,
includeTree ,
startFileNum ,
numFiles ,
NULL , // state
NULL , // callback
0 , // niceness
false , // err correction?
-1 , // maxRetries
false)) // isRealMerge
{
log(LOG_LOGIC,"db: getList did not block.");
return;
}
// all done if empty
if ( list.isEmpty() ) {
return;
}
// loop over entries in list
for(list.resetListPtr(); !list.isExhausted(); list.skipCurrentRecord()) {
key96_t k = list.getCurrentKey();
char *rec = list.getCurrentRec();
int32_t recSize = list.getCurrentRecSize();
int64_t docId = Titledb::getDocIdFromKey(&k);
if ( k <= lastKey ) {
log("key out of order. lastKey.n1=%" PRIx32" n0=%" PRIx64" currKey.n1=%" PRIx32" n0=%" PRIx64" ",
lastKey.n1, lastKey.n0, k.n1, k.n0);
}
lastKey = k;
if ( (k.n0 & 0x01) == 0) {
// delete key
continue;
}
// free the mem
xd->reset();
// uncompress the title rec
if ( ! xd->set2 ( rec , recSize , coll ,NULL , 0 ) ) {
//set2() may have logged something but not the docid
log(LOG_WARN, "dbdump: XmlDoc::set2() failed for docid %" PRId64, docId);
continue;
}
// extract the url
Url *url = xd->getFirstUrl();
if( url == (void *)-1 ) {
log(LOG_WARN, "dbdump: XmlDoc::getFirstUrl() failed for docid %" PRId64, docId);
continue;
}
const char *reason = NULL;
// Don't dump unwanted URLs
if( ! isUrlUnwanted(*url, &reason)) {
Url **redirUrlPtr = xd->getRedirUrl();
if (redirUrlPtr && *redirUrlPtr) {
Url *redirUrl = *redirUrlPtr;
if (isUrlUnwanted(*redirUrl, &reason)) {
continue;
}
}
// Get adult flag including generating debug info.
// Could just call xd->getIsAdult() to get the simple indicator
// without debug information.
AdultCheck achk(xd, true);
bool newblocked = achk.isDocAdult();
// Sanity check.
bool gbadult = false;
char *adultbit = xd->getIsAdult();
if( adultbit ) {
if( *adultbit != newblocked ) {
// Mismatch - should never happen
log(LOG_ERROR, "Adult check mismatch! docid=%" PRId64 ", url=%s, gbadult=%s, score=%" PRId32 ", newblock=%s",
docId, url->getUrl(), gbadult?"true":"false", achk.getScore(), newblocked?"true":"false");
gbshutdownLogicError();
}
}
if( newblocked ) {
time_t idxtim = (time_t)xd->getIndexedTime();
struct tm tm_buf;
tm *tm1 = gmtime_r(&idxtim,&tm_buf);
char idxtim_s[64];
strftime(idxtim_s,64,"%Y%m%d-%H%M%S",tm1);
fprintf(stdout, "%" PRId64 "\t%s\t%s\t%s\tscore=%" PRId32 "\tunique dw=%" PRId32 "\tunique dp=%" PRId32 "\twords=%" PRId32 "\t%s\t%s\n",
docId, url->getUrl(), idxtim_s, achk.getReason(),
achk.getScore(), achk.getNumUniqueDirtyWords(), achk.getNumUniqueDirtyPhrases(),
achk.getNumWordsChecked(), achk.hasEmptyDocumentBody()?"EMPTYDOC":"HASCONTENT", achk.getDebugInfo());
}
}
}
startKey = *(key96_t *)list.getLastKey();
startKey++;
// watch out for wrap around
if ( startKey < *(key96_t *)list.getLastKey() ) {
return;
}
}
}
#if 0
static void dumpUnwantedSpiderdbRecs(const char *coll, int32_t startFileNum, int32_t numFiles, bool includeTree) {

1
urlresultoverride.txt.example Normal file

@ -0,0 +1 @@
http://www.example.com/|en|Example Domain|This domain is established to be used for illustrative examples in documents. You may use this domain in examples without prior coordination or asking for permission.