@@ -2348,7 +2348,7 @@ bool Addresses::updateAddresses ( ) {
2348
2348
// scan m_siteTitleBuf for either p1 or p2
2349
2349
char *d = m_siteTitleBuf;
2350
2350
char *dend = m_siteTitleBuf + m_siteTitleBufSize;
2351
- // loop over the \0 delimeted list of titles
2351
+ // loop over the \0 delimited list of titles
2352
2352
for ( ; d < dend ; d += gbstrlen(d) + 1 ) {
2353
2353
// skip "the"
2354
2354
if ( strncasecmp(d,"the ",4) == 0 ) d += 4;
@@ -2898,7 +2898,7 @@ bool Addresses::updateAddresses ( ) {
2898
2898
// here to 888 or 999 or whatever
2899
2899
// . but we need this in case there is ambiguity as to
2900
2900
// which lat/lon pair is the real deal when there are
2901
- // mutiple ones in the same vicinity...
2901
+ // multiple ones in the same vicinity...
2902
2902
// . so we have to nuke the address somehow if its lat/lon
2903
2903
// only
2904
2904
if ( *ptr != dval && fabs(*ptr - dval) > .010 ) {
@@ -4570,7 +4570,7 @@ bool Addresses::set2 ( ) {
4570
4570
//if ( wids[i] == h_at ) { atPreceeds = true; continue; }
4571
4571
// count the number of numbers
4572
4572
int32_t nums = 0;
4573
- // are we delimeted on the left end?
4573
+ // are we delimited on the left end?
4574
4574
//bool leftEnd = false;
4575
4575
// keep an accumulative hash of all the wids in the phrase
4576
4576
bool firstWasDir = false; // 1st word is a direction?
@@ -4609,10 +4609,10 @@ bool Addresses::set2 ( ) {
4609
4609
//if ( i-1 >= 0 && tids[i-1] ) leftEnd = true;
4610
4610
//if ( i-2 >= 0 && tids[i-2] ) leftEnd = true;
4611
4611
// if we are cap'd and word before us is not let that be a
4612
- // delimeter as well
4612
+ // delimiter as well
4613
4613
//if (i-2>= 0 && isCap && wids[i-2] &&!ww->isCapitalized(i-2))
4614
4614
// leftEnd = true;
4615
- // need a delimeter on the left
4615
+ // need a delimiter on the left
4616
4616
//if ( ! leftEnd ) { atPreceeds = false; continue; }
4617
4617
// save it
4618
4618
int32_t ns_stack = m_sm.getNumPtrs();//m_ns;
@@ -4645,7 +4645,7 @@ bool Addresses::set2 ( ) {
4645
4645
// skip if non-breaking tag
4646
4646
if ( ! isBreakingTagId(tids[j]) )
4647
4647
continue;
4648
- // . allow br tags since microsofot front page
4648
+ // . allow br tags since microsoft front page
4649
4649
// . no! this is causing the zip code from
4650
4650
// a previous address to be used as the
4651
4651
// street address for the name of a business
@@ -5569,7 +5569,7 @@ bool Addresses::set2 ( ) {
5569
5569
// assume not an indicator tag
5570
5570
inCityIndicator = false;
5571
5571
inStateIndicator = false;
5572
- // mus tbe xml
5572
+ // must be xml
5573
5573
if ( m_tids[i] != TAG_XMLTAG ) continue;
5574
5574
// it can inidcate things
5575
5575
char *tagName = m_wptrs[i]+1;
@@ -5743,7 +5743,7 @@ bool Addresses::set2 ( ) {
5743
5743
5744
5744
//
5745
5745
// make a list of occupation names for avoid false positive
5746
- // identifcation of a place because it is after the word "at" but
5746
+ // identification of a place because it is after the word "at" but
5747
5747
// really it is something like "john, an engineer at HP, ..." referring
5748
5748
// to where that person works. fixes
5749
5749
// www.aliconferences.com/conf/social_media_govt1209/pre.htm which has
@@ -5928,7 +5928,7 @@ bool Addresses::set2 ( ) {
5928
5928
"integrator",
5929
5929
"machinist",
5930
5930
"monkey", // grease monkey code monkey
5931
- "liason ",
5931
+ "liaison ",
5932
5932
"fabricator",
5933
5933
"wholesaler",
5934
5934
"baker",
@@ -6264,7 +6264,7 @@ bool Addresses::set2 ( ) {
6264
6264
lastWasBreak = 1;
6265
6265
continue;
6266
6266
}
6267
- // does it have some kind of delimeter before it?
6267
+ // does it have some kind of delimiter before it?
6268
6268
else if ( is_lower_utf8(wptrs[i])){lastWasBreak = 0; continue;}
6269
6269
// each candidate needs somekind of "break" before them
6270
6270
if ( ! lastWasBreak ) continue;
@@ -6742,7 +6742,7 @@ bool Addresses::set2 ( ) {
6742
6742
// topologically speaking. we need to telescope it out and
6743
6743
// tether it to the first street we hit. including afterats and
6744
6744
// fake street names? it might be tethered to a place venue name
6745
- // that we never recognize. and intead we tether it to a brother
6745
+ // that we never recognize. and instead we tether it to a brother
6746
6746
// brother city/state when we shouldn't.
6747
6747
//Place *latlon [MAX_LATLONS];
6748
6748
//Place *pctry [10]; int32_t ny = 0;
@@ -6795,7 +6795,7 @@ bool Addresses::set2 ( ) {
6795
6795
// . "bn" = baseNum
6796
6796
// . TODO: make sure state we select is not in a street!
6797
6797
int32_t bn = 0;
6798
- // alway have a NULL
6798
+ // always have a NULL
6799
6799
padm1 [ bn++ ] = NULL;
6800
6800
// then
6801
6801
for ( int32_t i = 0 ; i < m_npSaved ; i++ ) {
@@ -6806,7 +6806,7 @@ bool Addresses::set2 ( ) {
6806
6806
// . allow state to come from anywhere in the document
6807
6807
// . TODO: later add meta description to get christinesaari.com
6808
6808
if ( p->m_type != PT_STATE ) continue;
6809
- // skip if interesects a street, like "ohio street"
6809
+ // skip if intersects a street, like "ohio street"
6810
6810
if ( p->m_a >= 0 && bits && (bits[p->m_a] & D_IS_IN_STREET) )
6811
6811
continue;
6812
6812
// make the key for deduping
@@ -6956,7 +6956,7 @@ bool Addresses::set2 ( ) {
6956
6956
//pp->m_crid = 0;
6957
6957
pp->m_bits = 0;
6958
6958
pp->m_flags2 = 0;
6959
- // thats a suite
6959
+ // that's a suite
6960
6960
psuite[nu++] = pp;
6961
6961
// now just use this
6962
6962
setHashes(pp,m_words,m_niceness);
@@ -7084,7 +7084,7 @@ bool Addresses::set2 ( ) {
7084
7084
//pp->m_crid = 0;
7085
7085
pp->m_bits = 0;
7086
7086
pp->m_flags2 = 0;
7087
- // thats a suite
7087
+ // that's a suite
7088
7088
psuite[nu++] = pp;
7089
7089
// now just use this
7090
7090
setHashes(pp,m_words,m_niceness);
@@ -7298,7 +7298,7 @@ bool Addresses::set2 ( ) {
7298
7298
// that we have no place name!
7299
7299
// . fixes http://obits.abqjournal.com/obits/2004/04/13
7300
7300
if ( i >= 0 && i < nw && bits && ( bits[i] & D_IS_IN_DATE ) &&
7301
- // incase place name ends in midnight or noon
7301
+ // in case place name ends in midnight or noon
7302
7302
wids[i] != h_daily &&
7303
7303
wids[i] != h_noon &&
7304
7304
wids[i] != h_midnight )
@@ -7522,7 +7522,7 @@ bool Addresses::set2 ( ) {
7522
7522
if ( isLower && //_lower_utf8(wptrs[i]) &&
7523
7523
// must not be an allowable lowercase word
7524
7524
! s_lc.isInTable(&wids[i])
7525
- // for smoe reason 's' is not a query
7525
+ // for some reason 's' is not a query
7526
7526
// stop word, and we had a bar named
7527
7527
// "Slim's" that we needed to get
7528
7528
// ... this is in s_lc table now
@@ -7711,7 +7711,7 @@ bool Addresses::set2 ( ) {
7711
7711
if ( ampCount > 0 ) break;
7712
7712
continue;
7713
7713
}
7714
- // . this is a good delimeter for place names
7714
+ // . this is a good delimiter for place names
7715
7715
// usually, but of course if someone has
7716
7716
// "Gigablast, \nInc." then this will hurt!
7717
7717
// . i was only allow inc. or llc. to follow
@@ -8057,7 +8057,7 @@ bool Addresses::set2 ( ) {
8057
8057
// "map" or "reviews" which may be in lower case
8058
8058
if ( (street->m_bits & PLF_HAS_UPPER) && hadLower ) {
8059
8059
//lasti = -1;
8060
- // EXPERIEMENT :
8060
+ // EXPERIMENT :
8061
8061
// skip back to a tag like we do for
8062
8062
// "Write a Review" skipping logic below
8063
8063
//i = lasti - 1;
@@ -8070,7 +8070,7 @@ bool Addresses::set2 ( ) {
8070
8070
// . add the place name if we found something
8071
8071
// . if we broke out of the loop because of the alnumCount then
8072
8072
// that is NOT good because we want something that has a
8073
- // delimeter on the left!
8073
+ // delimiter on the left!
8074
8074
if ( lasti >= 0 && lasti<=righti && alphaCount > 0 &&
8075
8075
// this is restricted above!
8076
8076
//alnumCount <10 &&
@@ -8159,7 +8159,7 @@ bool Addresses::set2 ( ) {
8159
8159
isCityState3 (prev1->m_hash,prev2->m_hash)==1) {
8160
8160
// wipe out previous name
8161
8161
nn = savednn;
8162
- // wipe out prevous place
8162
+ // wipe out previous place
8163
8163
//m_np = savednp;
8164
8164
m_pm.setNumPtrs ( savednp );
8165
8165
// reset this too!
@@ -8209,7 +8209,7 @@ bool Addresses::set2 ( ) {
8209
8209
// xor it in
8210
8210
h ^= *hw; // wids[k];
8211
8211
}
8212
- // only consumate it if not the single word "the"
8212
+ // only consummate it if not the single word "the"
8213
8213
if ( h ) {
8214
8214
// set it
8215
8215
pp->m_hash = h;
@@ -10270,7 +10270,7 @@ void Addresses::print ( SafeBuf *pbuf , int64_t uh64 ) {
10270
10270
}
10271
10271
10272
10272
// . looks up each word/phrase in our table of known places
10273
- // . table incudes cities, countries, states (adm1), counties, zipcodes
10273
+ // . table includes cities, countries, states (adm1), counties, zipcodes
10274
10274
/*
10275
10275
int32_t Addresses::addProperPlaces ( int32_t a ,
10276
10276
int32_t b ,
@@ -10808,7 +10808,7 @@ bool Addresses::addAddress ( Place *name1 ,
10808
10808
// unless in parens!
10809
10809
if ( c ) continue;
10810
10810
// crap... Msg13.cpp when it sets the dates does not
10811
- // filter out html entites for speed, so watch
10811
+ // filter out html entities for speed, so watch
10812
10812
// out for crap after an ampersand or &#. this
10813
10813
// was causing some americantowns.com urls to
10814
10814
// not get their address inlined!
@@ -10987,7 +10987,7 @@ bool Addresses::addAddress ( Place *name1 ,
10987
10987
// and then if all else is equal, having a zip is better than just
10988
10988
// a city because it is more specific
10989
10989
if ( zip ) score += 1000;
10990
- // having a valid adm1 is good (might not have one explicity if city
10990
+ // having a valid adm1 is good (might not have one explicitly if city
10991
10991
// is unique to a particular state)
10992
10992
if ( adm1 ) score += 100;
10993
10993
// prefer city over no city
@@ -12370,7 +12370,7 @@ int32_t Address::serialize ( char *buf , int32_t bufSize , char *origUrl ,
12370
12370
// sanity check. these should be filtered out
12371
12371
//if ( m_score <= 0.0 ) { char *xx=NULL;*xx=0; }
12372
12372
12373
- // also truncate at semicolon in urls since that is our delimeter
12373
+ // also truncate at semicolon in urls since that is our delimiter
12374
12374
char *o = origUrl;
12375
12375
for ( ; o && *o && *o !=';' ; o++ );
12376
12376
// truncate this if we should
@@ -12386,7 +12386,7 @@ int32_t Address::serialize ( char *buf , int32_t bufSize , char *origUrl ,
12386
12386
// how much buffer space do we need?
12387
12387
int32_t need = getStoredSize( olen + extra , includeHash );
12388
12388
12389
- // silenty ignore overflow errors
12389
+ // silently ignore overflow errors
12390
12390
if ( need > bufSize ) return -1;
12391
12391
12392
12392
PlaceDesc *pd = NULL;
@@ -12932,7 +12932,7 @@ void Address::printEssentials ( SafeBuf *pbuf , bool forEvents ,
12932
12932
uh64);
12933
12933
//char *p = pbuf->getBuf();
12934
12934
//
12935
- // map utf8 characters into &#xxxx entites because
12935
+ // map utf8 characters into &#xxxx entities because
12936
12936
// the senddiv() function maps all utuf8 chars to
12937
12937
// crap like "%u2019" for the apostrophe for instance
12938
12938
//
@@ -13785,7 +13785,7 @@ bool initPlaceDescTable ( ) {
13785
13785
//loadedIndicators = true;
13786
13786
13787
13787
// keep these separate so we do not have to recompute any time we
13788
- // add or substract to/from this list
13788
+ // add or subtract to/from this list
13789
13789
addIndicator ( "airport" , IND_NAME , 1.0 );
13790
13790
addIndicator ( "airstrip" , IND_NAME , 1.0 );
13791
13791
addIndicator ( "area" , IND_NAME , 1.0 );
@@ -14682,7 +14682,7 @@ pd=(PlaceDesc *)g_cities.getValueFromSlot(pd->getSlot());
14682
14682
// . go through the places in allCountries.txt
14683
14683
// . format described in /gb/geo/geonames/readme.txt
14684
14684
char buf[10000];
14685
- // for debuging
14685
+ // for debugging
14686
14686
char *dbuf = buf;
14687
14687
14688
14688
//char topBuf[1000000];
@@ -14753,7 +14753,7 @@ pd=(PlaceDesc *)g_cities.getValueFromSlot(pd->getSlot());
14753
14753
//if ( strncmp(buf,"3856157\t", 8) ==0 )
14754
14754
// log("gotit");
14755
14755
14756
- // parse out the tab delimeted things from the line
14756
+ // parse out the tab delimited things from the line
14757
14757
for ( ; *p ; p++ ) {
14758
14758
// skip if no tab
14759
14759
if ( *p != '\t' ) continue;
@@ -15255,7 +15255,7 @@ pd=(PlaceDesc *)g_cities.getValueFromSlot(pd->getSlot());
15255
15255
char *a1name = NULL;
15256
15256
char *a2name = NULL;
15257
15257
//char *zipEnd = NULL;
15258
- // parse out the tab delimeted things from the line
15258
+ // parse out the tab delimited things from the line
15259
15259
for ( ; *p ; p++ ) {
15260
15260
// a temp var
15261
15261
char *s = p;
@@ -15987,7 +15987,7 @@ key128_t Address::makePlacedbKey (int64_t docId,bool useName1,bool useName2){
15987
15987
uint64_t cid64 = (uint64_t)getCityId32 ( cityHash , adm1Str );
15988
15988
// incorporate that into "h"
15989
15989
h = hash64 ( cid64 , h );
15990
- // store that in most signficant int64_t
15990
+ // store that in most significant int64_t
15991
15991
k.n1 = h;
15992
15992
15993
15993
// street hash
@@ -19713,7 +19713,7 @@ void PlaceMem::setNumPtrs ( int32_t newNumPtrs ) {
19713
19713
break;
19714
19714
}
19715
19715
}
19716
- // this is wierd
19716
+ // this is weird
19717
19717
if ( m_cursorPoolNum < 0 ) { char *xx=NULL;*xx=0; }
19718
19718
// reset final
19719
19719
m_numPlacePtrs = newNumPtrs;
@@ -19781,7 +19781,7 @@ bool loadPlaces ( ) {
19781
19781
g_nameTable.set ( 8 , // 64 bit key hash
19782
19782
4 , // placedec ptr
19783
19783
0 , // no initial slots
19784
- NULL , // no intiial buf
19784
+ NULL , // no initial buf
19785
19785
0 , // zero initial buf size
19786
19786
true , // allow dups?
19787
19787
0 , // niceness
0 commit comments