ngrams in the kernel

gistfile1.txt

evan@fedora ~/code/index (master) $ ./bin/print_ngram_counts /var/codesearch/ | head -n 100
distinct ngrams:   385054
total ngram count: 365009415

1806890     0.495026%   0.495026%   \x20=\x20
1614139     0.442218%   0.937244%   \x09\x09\x09
1114430     0.305315%   1.242559%   \x20\x20\x20
1075092     0.294538%   1.537098%   str
1072463     0.293818%   1.830916%   \x20*/
1027687     0.281551%   2.112466%   \x20*\x20
975855      0.267351%   2.379817%   ine
971996      0.266293%   2.646110%   def
962478      0.263686%   2.909796%   tru
955115      0.261669%   3.171465%   ct\x20
944968      0.258889%   3.430353%   uct
937292      0.256786%   3.687139%   ruc
917263      0.251298%   3.938438%   int
886767      0.242944%   4.181381%   /*\x20
885251      0.242528%   4.423909%   fin
869707      0.238270%   4.662179%   ne\x20
846858      0.232010%   4.894189%   efi
836147      0.229075%   5.123265%   sta
821650      0.225104%   5.348368%   if\x20
791193      0.216760%   5.565128%   #de
743142      0.203595%   5.768723%   \x20th
738621      0.202357%   5.971080%   \x20in
733080      0.200839%   6.171919%   dev
710338      0.194608%   6.366527%   f\x20(
707736      0.193895%   6.560422%   tat
697027      0.190961%   6.751383%   ed\x20
683647      0.187296%   6.938679%   \x200x
683529      0.187263%   7.125942%   the
673070      0.184398%   7.310340%   \x09if
669964      0.183547%   7.493888%   ret
645034      0.176717%   7.670605%   nt\x20
624494      0.171090%   7.841694%   he\x20
603264      0.165274%   8.006968%   ati
588739      0.161294%   8.168262%   \x09re
584536      0.160143%   8.328405%   \x20re
578920      0.158604%   8.487009%   ter
569926      0.156140%   8.643149%   \x09/*
568610      0.155780%   8.798929%   tur
554073      0.151797%   8.950726%   \x09\x09\x20
537673      0.147304%   9.098029%   etu
519135      0.142225%   9.240255%   urn
518548      0.142064%   9.382319%   \x09\x20\x20
510508      0.139862%   9.522180%   0x0
508896      0.139420%   9.661600%   er\x20
501292      0.137337%   9.798937%   ion
488131      0.133731%   9.932668%   000
480757      0.131711%   10.064379%   con
479127      0.131264%   10.195643%   rn\x20
455725      0.124853%   10.320496%   ent
453012      0.124110%   10.444606%   ic\x20
449306      0.123094%   10.567700%   to\x20
436092      0.119474%   10.687174%   rea
435948      0.119435%   10.806609%   _re
434159      0.118945%   10.925554%   \x20st
431835      0.118308%   11.043862%   or\x20
426587      0.116870%   11.160732%   ate
423715      0.116083%   11.276815%   ing
421000      0.115339%   11.392155%   loc
417265      0.114316%   11.506471%   for
415753      0.113902%   11.620373%   tic
412234      0.112938%   11.733311%   \x20co
410174      0.112374%   11.845684%   )\x20{
408991      0.112049%   11.957734%   se\x20
406126      0.111265%   12.068998%   set
404792      0.110899%   12.179897%   (st
404364      0.110782%   12.290679%   tio
403833      0.110636%   12.401315%   ,\x200
399430      0.109430%   12.510746%   \x09st
398423      0.109154%   12.619900%   res
397451      0.108888%   12.728788%   dat
373947      0.102449%   12.831236%   \x20to
370524      0.101511%   12.932747%   and
368036      0.100829%   13.033576%   ng\x20
366716      0.100468%   13.134044%   reg
359986      0.098624%   13.232667%   _in
359933      0.098609%   13.331277%   \x09\x09r
358802      0.098299%   13.429576%   ata
358374      0.098182%   13.527758%   _de
356337      0.097624%   13.625382%   ode
350343      0.095982%   13.721364%   ice
349975      0.095881%   13.817245%   err
345772      0.094730%   13.911975%   de\x20
345758      0.094726%   14.006701%   \x090x
343975      0.094237%   14.100938%   is\x20
341045      0.093435%   14.194372%   \x09\x09i
333379      0.091334%   14.285707%   \x09\x20*
332172      0.091004%   14.376711%   x00
330696      0.090599%   14.467310%   ock
328185      0.089911%   14.557221%   on\x20
327783      0.089801%   14.647022%   =\x200
323074      0.088511%   14.735534%   ist
323023      0.088497%   14.824031%   \x20de
312151      0.085519%   14.909549%   lin
306949      0.084093%   14.993643%   ead
306673      0.084018%   15.077661%   ase
303740      0.083214%   15.160875%   ign
300509      0.082329%   15.243204%   0,\x20