52699e4 · sphinx · git.iko.soy

git.iko.soy/sphinx

on master help sign in

resetting from ngram experiment, trying to get more data in

52699e4Hunter Miller4 years ago

desk/app/seek.hoon+23−81

compare with master

unifiedsplit

@@ -98,22 +98,31 @@

98 |= [=mark =vase]

99 |^ ^+ cor

100 ?+ mark ~|(bad-poke/mark !!)

101− %directory-listing

101+ %declare

102− =+ !<(=listing:s vase)

102+ =+ !<(=declare:s vase)

103− (publish listing)

103+ di-abet:(publish declare di-core)

104+ %declarations

105+ =+ !<(declared=(list declare:s) vase)

106+ =. di-core (roll declared publish)

107+ cor

104 ==

108 ==

105 ++ publish

109 ++ publish

106− |= =listing:s

110+ |= [=declare:s core=_di-core]

107− ^+ cor

111+ ^+ di-core

108 ::

112 ::

109− ?> =(src.bowl source.listing)

110 ?> from-self

113 ?> from-self

114+ =/ listing

115+ :* post=q.declare

111− ?> =(hash.listing (digest post.listing))

116+ hash=(digest q.declare)

117+ reach=p.declare

118+ source=our.bowl

119+ time=now.bowl

120+ ==

112 ?: (~(has by directory) hash.listing)

121 ?: (~(has by directory) hash.listing)

113 ~& 'Listing already exists.'

122 ~& 'Listing already exists.'

114 cor

123 cor

115 =. published (~(put by directory) hash.listing listing)

124 =. published (~(put by directory) hash.listing listing)

116− di-abet:(di-publish:(di-abed:di-core hash.listing) listing)

125+ (di-publish:(di-abed:core hash.listing) listing)

117 --

126 --

118::

127::

119++ watch

128++ watch

@@ -165,16 +174,7 @@

165 =/ limit (slav %ud i.t.t.t.t.path)

174 =/ limit (slav %ud i.t.t.t.t.path)

166 :: expects encoded @t values)

175 :: expects encoded @t values)

167 =/ term `@t`(slav %t i.t.t.path)

176 =/ term `@t`(slav %t i.t.t.path)

168− =/ term-counts (get-term-counts term)

169− ~& term-counts

170− =/ terms (get-terms term-counts)

171− ~& terms

172− =/ all=(list listing:s)

173− %- zing

174− %+ turn

175− terms

176− |= [=key:s v=@ud]

177− (get-listings (get-hashes key))

177+ =/ all (get-listings (get-hashes term))

178 =/ listings (swag [start limit] all)

179 :* listings

180 start

@@ -183,69 +183,15 @@

183 (lent all)

184 ==

185 ==

186−::

187−++ get-terms

188− |= tally=(map @t @ud)

189− ^- (list [@t @ud])

190− =/ sorted

191− %+ sort

192− ~(tap by tally)

193− |= [[k=@t v=@ud] [l=@t w=@ud]]

194− (lth v w)

195− =/ median-index (div (lent sorted) 2)

196− =/ q1 (median (scag +(median-index) sorted))

197− =/ q3 (median (slag median-index sorted))

198− =/ iqr (sub q3 q1)

199− %+ skim

200− sorted

201− |= [k=@t v=@ud]

202− (gth:rs (sun:rs v) (mul:rs (sun:rs q3) .1.5))

203−++ median

204− |= terms=(list [k=@t v=@ud])

205− ^- @ud

206− =/ length (lent terms)

207− =/ middle (div length 2)

208− ?. =((mod length 2) 0) (tail (snag middle terms))

209− %+ div

210− %+ add

211− (tail (snag middle terms))

212− (tail (snag +(middle) terms))

213− 2

214−++ get-term-counts

215− |= term=@t

216− ^- (map @t @ud)

217− =/ parts (split:sift term)

218− =/ ngrams=(list @t)

219− %- zing

220− %+ turn

221− parts

222− |= part=@t

223− (iching part)

224− %+ roll

225− ngrams

226− |= [ngram=@t tally=(map @t @ud)]

227− ^- (map @t @ud)

228− =/ words=(set @t) (~(gut by trigrams) ngram *(set @t))

229− %-

230− %- ~(uno by tally)

231− %- malt

232− %+ turn

233− ~(tap in words)

234− |= word=@t

235− [word 1]

236− |= [k=@t v=@ud w=@ud]

237− (add v w)

238++ get-hashes

186++ get-hashes

239 |= =key:s

187 |= =key:s

240− ^- (list hash:s)

241 %+ turn

188 %+ turn

242 %+ sort (~(gut by lookup) key *(list entry:s))

189 %+ sort (~(gut by lookup) key *(list entry:s))

243 |= [a=entry:s b=entry:s]

190 |= [a=entry:s b=entry:s]

244 (gte rank.a rank.b)

191 (gte rank.a rank.b)

245 |=(=entry:s hash.entry)

192 |=(=entry:s hash.entry)

246++ get-listings

193++ get-listings

247− |= l=(list hash:s)

194+ |= l=(list hash)

248− ^- (list listing:s)

249 %+ turn l

195 %+ turn l

250 |=(=hash:s (~(got by directory) hash))

196 |=(=hash:s (~(got by directory) hash))

251++ from-self =(our src):bowl

197++ from-self =(our src):bowl

@@ -264,22 +210,18 @@

264 =/ entries=lookup:s

210 =/ entries=lookup:s

265 %- malt

211 %- malt

266 %- zing

212 %- zing

267− :~ %+ turn

268− (sift:sift title.post.l)

269− |= word=@t

270− [word ~[[hash rank=0]]]

213+ :~ ~[[title.post.l ~[[hash rank=0]]]]

271− ~[[type.post.l ~[[hash rank=1]]]]

272 %+ turn

214 %+ turn

273 tags.post.l

215 tags.post.l

274 |= tag=@t

216 |= tag=@t

275− [tag ~[[hash rank=2]]]

217+ [tag ~[[hash rank=1]]]

276 %+ turn

218 %+ turn

277 (sift:sift description.post.l)

219 (sift:sift description.post.l)

278 |= word=@t

220 |= word=@t

279− [word ~[[hash rank=3]]]

221+ [word ~[[hash rank=2]]]

222+ ~[[type.post.l ~[[hash rank=3]]]]

280 ==

223 ==

281 =/ keys ~(tap in ~(key by entries))

224 =/ keys ~(tap in ~(key by entries))

282− ~& keys

283 =. trail (~(put by trail) hash keys)

225 =. trail (~(put by trail) hash keys)

284 =. lookup

226 =. lookup

285 %- ~(uni by entries)

227 %- ~(uni by entries)

desk/gen/publish-all.hoonnew file+29

@@ -0,0 +1,29 @@

1+/- s=seek

2+/+ *seek

3+:- %say

4+|= $: [now=@da eny=@uv =beak]

5+ [ ~]

6+ ==

7+:- %declarations

8+^- (list declare:s)

9+:* :- %friends

10+ ['networked subject' %group 'web+urbitgraph://group/~matwet/networked-subject' 'https://subject.network | networked subject' 'https://urbits3.ams3.digitaloceanspaces.com/sitful-hatred/2022.7.07..17.15.52-ns.png' ~['hosting' 'networking' 'urbit' 'ops']]

11+ :- %friends

12+ ['Hooniverse' %group 'web+urbitgraph://group/~hiddev-dannut/new-hooniverse' 'Community based Hoon learning for all levels. For discussion of Hoon specific to Uqbar, join ~hiddev-dannut/uhoon' 'https://i.imgur.com/ghThlz7.png' ~['hoon' 'dev' 'urbit' 'programming' 'education']]

13+ :- %friends

14+ ['Hollow Mars Theory' %group 'web+urbitgraph://group/~rabsef-bicrym/hollow-mars-theory' 'Definitely NOT a Conspiracy Chat' '' ~['conspiracies' 'ufos' 'steel beams']]

15+ :- %friends

16+ ['celestial systems' %group 'web+urbitgraph://group/~nocsyx-lassul/celestial-systems' 'A place for pilots who are building hosting providers' '' ~['hosting' 'ops' 'urbit']]

17+ :- %friends

18+ ['Structure' %group 'web+urbitgraph://group/~fabled-faster/structure' 'Urbit Structural Design and Engineering Group. Always Thinking About Mechanics.' 'https://fabled-faster.nyc3.digitaloceanspaces.com/fabled-faster/2022.1.27..17.59.43-image.png' ~['design' 'ux' 'hci' 'urbit']]

19+ :- %friends

20+ ['The Marketplace' %group 'web+urbitgraph://group/~tirrel/the-marketplace' 'Welcome to The Marketplace, featuring The Pit, Urbit\'s first open-outcry market!' 'https://snipboard.io/U0IYyi.jpg' ~['urbit' 'market' 'sell' 'buy']]

21+ :- %friends

22+ ['The Forge' %group 'web+urbitgraph://group/~middev/the-forge' 'pale fire computing' 'https://nyc3.digitaloceanspaces.com/archiv/littel-wolfur/2021.5.06..21.01.58-the%20forge.png' ~['dev' 'programming' 'hoon' 'urbit']]

23+ :- %friends

24+ ['UFORIA' %group 'web+urbitgraph://group/~tiplec-lacnyx/ufora' 'UFO Research, Investigations, and Analysis' 'https://tiplec-lacnyx.nyc3.digitaloceanspaces.com/tiplec-lacnyx/2021.12.27..06.09.47-change1.jpg' ~['UFO' 'conspiracies' 'research']]

25+ :- %friends

26+ ['Urbit Community' %group 'web+urbitgraph://group/~bitbet-bolbel/urbit-community' 'World hub, help desk, meet and greet, etc.' 'https://fabled-faster.nyc3.digitaloceanspaces.com/fabled-faster/2021.4.02..21.52.41-UC.png' ~['general' 'urbit' 'community' 'help']]

27+ :- %friends

28+ ['Urbytes' %group 'web+urbitgraph://group/~nartes-fasrum/urbytes' 'We feed and water Mars.' '' ~['cooking' 'food' 'beverages' 'peanut butter eggs']]

29+==

desk/gen/publish.hoon+4−4

@@ -2,8 +2,8 @@

2/+ *seek

3:- %say

4|= $: [now=@da eny=@uv =beak]

5− [[=post:s source=@p ~] ~]

5+ [[=post:s ~] ~]

6 ==

7−:- %directory-listing

7+:- %declare

8−^- listing:s

8+^- declare:s

9−[post (digest post) %friends source now]

9+[%friends post]

desk/lib/seek-json.hoon+18−1

@@ -34,6 +34,23 @@

34++ dejs

35 =, dejs:format

36 |%

37−

37+ ++ declarations (ar declare)

38+ ++ declare

39+ ^- $-(json declare:s)

40+ %- ot

41+ :~ reach/(su (perk [%friends %public %private ~]))

42+ post/post

43+ ==

44+ ++ post

45+ ^- $-(json post:s)

46+ %- ot

47+ :~ title/so

48+ type/type

49+ link/so

50+ description/so

51+ tags/(ar so)

52+ image/so

53+ ==

54+ ++ type (su (perk [%app %group %content %other ~]))

38 --

55 --

39--

56--

desk/lib/sift.hoon+20−5

@@ -6,16 +6,31 @@

6 (split corpus)

7 |= word=@t

8 (~(has in words) word)

9+++ norm

10+ |= corpus=@t

11+ (crip (cass (trimall (crip (expunge corpus)))))

9++ split

12++ split

10 |= corpus=@t

13 |= corpus=@t

11 ^- (list @t)

14 ^- (list @t)

12− =/ lines (crip (trimall corpus))

15+ ~& (norm corpus)

13− %+ rash lines

16+ %+ rash (norm corpus)

14− (more ace (cook crip (plus ;~(pose aln hep))))

17+ (more ace (cook crip (plus allowed)))

18+++ allowed ;~(pose aln hep ace)

19+++ banned ;~(less allowed prn)

20+++ expunge

21+ |= corpus=@t

22+ ^- (list @t)

23+ %- zing

24+ %+ rash corpus

25+ %- star

26+ ;~ pose

27+ ;~(sfix allowed (plus banned))

28+ (plus allowed)

29+ ==

15++ trimall

30++ trimall

16− |= value=@t

31+ |= corpus=@t

17 |^ ^- tape

32 |^ ^- tape

18− %+ rash value

33+ %+ rash corpus

19 %+ ifix [(star ws) (star ws)]

34 %+ ifix [(star ws) (star ws)]

20 %- star

35 %- star

21 ;~ less

36 ;~ less

desk/mar/declarations.hoonnew file+14

@@ -0,0 +1,14 @@

1+/- s=seek

2+/+ j=seek-json

3+|_ d=(list declare:s)

4+++ grad %noun

5+++ grow

6+ |%

7+ ++ noun d

8+ --

9+++ grab

10+ |%

11+ ++ noun (list declare:s)

12+ ++ json declarations:dejs:j

13+ --

14+--

desk/mar/declare.hoonnew file+14

@@ -0,0 +1,14 @@

1+/- s=seek

2+/+ j=seek-json

3+|_ =declare:s

4+++ grad %noun

5+++ grow

6+ |%

7+ ++ noun declare

8+ --

9+++ grab

10+ |%

11+ ++ noun declare:s

12+ ++ json declare:dejs:j

13+ --

14+--

desk/sur/seek.hoon+4−2

@@ -28,14 +28,16 @@

28 image=@t

29 ==

30::

31++$ reach ?(%private %friends %public)

32+::

33++$ declare (pair reach post)

34+::

31:: a listing includes the content of the post as well as information

35:: a listing includes the content of the post as well as information

32:: that would affect the hash so are left out, namely time, source and

36:: that would affect the hash so are left out, namely time, source and

33:: hash. each post has a source and time so that they can be updated

37:: hash. each post has a source and time so that they can be updated

34:: via the source requesting to replace the listing and hash.

38:: via the source requesting to replace the listing and hash.

35::

39::

36::

40::

37−+$ reach ?(%private %friends %public)

38−::

39+$ listing

41+$ listing

40 $: =post

42 $: =post

41 =hash

43 =hash