Created
July 21, 2021 19:34
-
-
Save dgrahn/8fb4b3735754f17aa6fe63536c7829fd to your computer and use it in GitHub Desktop.
C/C++ Token Frequencies
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| token | freq | ||
|---|---|---|---|
| 0 | Identifier | 0.28975789809994656 | |
| 1 | , | 0.11085500513657347 | |
| 2 | IntegerLiteral | 0.07681658334963642 | |
| 3 | ( | 0.07371915527596774 | |
| 4 | ) | 0.07371346442857962 | |
| 5 | ; | 0.07120506446978692 | |
| 6 | = | 0.03211986303113621 | |
| 7 | -> | 0.029400075358314605 | |
| 8 | { | 0.02097414346886977 | |
| 9 | } | 0.020972327475899624 | |
| 10 | * | 0.017773761473940605 | |
| 11 | . | 0.016039581633917055 | |
| 12 | if | 0.012348802863512129 | |
| 13 | StringLiteral | 0.011417610919209918 | |
| 14 | & | 0.010554010968825212 | |
| 15 | [ | 0.008786112959013884 | |
| 16 | ] | 0.008785204270047805 | |
| 17 | struct | 0.008649981041622385 | |
| 18 | return | 0.007634802230846169 | |
| 19 | Directive | 0.007328694156260919 | |
| 20 | int | 0.006982866794537391 | |
| 21 | < | 0.0060099036264591454 | |
| 22 | - | 0.005206501627095519 | |
| 23 | static | 0.004545366388250609 | |
| 24 | : | 0.004410796631068959 | |
| 25 | == | 0.003943534491907844 | |
| 26 | void | 0.0037814462704533016 | |
| 27 | :: | 0.0034559100641442992 | |
| 28 | + | 0.0033367818639992723 | |
| 29 | > | 0.0029978779658566294 | |
| 30 | const | 0.002879925867759952 | |
| 31 | Not | 0.0027847130377939935 | |
| 32 | case | 0.00253097937922428 | |
| 33 | else | 0.0023321982049886426 | |
| 34 | FloatingLiteral | 0.0022200953400748897 | |
| 35 | unsigned | 0.0021729338056678525 | |
| 36 | ++ | 0.002104277468442321 | |
| 37 | break | 0.0019950357811655394 | |
| 38 | char | 0.001898146262325379 | |
| 39 | != | 0.001895911164461226 | |
| 40 | AndAnd | 0.001766705134334138 | |
| 41 | | | 0.0016638320794668284 | |
| 42 | BooleanLiteral | 0.001322241085718184 | |
| 43 | for | 0.001320744942031019 | |
| 44 | sizeof | 0.0012710460033290303 | |
| 45 | goto | 0.0012687614700151984 | |
| 46 | OrOr | 0.0011465693491827663 | |
| 47 | long | 0.0010043174385345383 | |
| 48 | CharacterLiteral | 0.0009884402724732364 | |
| 49 | += | 0.0008778460928471118 | |
| 50 | |= | 0.0007968639014632323 | |
| 51 | bool | 0.000640555972860234 | |
| 52 | ? | 0.0006262089974689497 | |
| 53 | / | 0.0005873789328862162 | |
| 54 | >= | 0.0005569013049138375 | |
| 55 | while | 0.0005059921017671452 | |
| 56 | ~ | 0.0005045036138422262 | |
| 57 | switch | 0.0004450728933059277 | |
| 58 | EOF | 0.0003992373830852928 | |
| 59 | <= | 0.00036605361627921497 | |
| 60 | &= | 0.0003408760071087381 | |
| 61 | default | 0.0003302084526067349 | |
| 62 | this | 0.00029528344230811984 | |
| 63 | -- | 0.0002926599395412768 | |
| 64 | float | 0.0002858186503732425 | |
| 65 | continue | 0.00027592009602970516 | |
| 66 | double | 0.00027365922248361854 | |
| 67 | enum | 0.00021285161887805719 | |
| 68 | new | 0.00020547138713060672 | |
| 69 | -= | 0.00020360668966295733 | |
| 70 | inline | 0.0001989171698112128 | |
| 71 | % | 0.00019744514754579771 | |
| 72 | auto | 0.00019552155072137154 | |
| 73 | MultiLineMacro | 0.0001612895600262687 | |
| 74 | PointerLiteral | 0.0001251066195069563 | |
| 75 | short | 0.000124903414802518 | |
| 76 | extern | 0.00011851700871386241 | |
| 77 | UserDefinedLiteral | 0.00011629075921813445 | |
| 78 | typedef | 0.00010647857264465849 | |
| 79 | namespace | 9.858140382535317e-05 | |
| 80 | class | 9.815264266841171e-05 | |
| 81 | ^ | 8.51566592509554e-05 | |
| 82 | do | 8.462298722142718e-05 | |
| 83 | static_cast | 8.070516050984315e-05 | |
| 84 | template | 7.647194717065874e-05 | |
| 85 | union | 7.576861729437307e-05 | |
| 86 | volatile | 7.188418355580161e-05 | |
| 87 | using | 6.643181893232157e-05 | |
| 88 | private | 5.974022107533789e-05 | |
| 89 | public | 5.677063168957646e-05 | |
| 90 | typename | 4.849909994355986e-05 | |
| 91 | delete | 4.797254507993871e-05 | |
| 92 | *= | 4.781323597712179e-05 | |
| 93 | >>= | 3.9646538161357816e-05 | |
| 94 | register | 3.886607359510646e-05 | |
| 95 | ... | 3.6170514332350325e-05 | |
| 96 | virtual | 3.269310554132849e-05 | |
| 97 | ^= | 3.225314927477107e-05 | |
| 98 | operator | 3.223945353929586e-05 | |
| 99 | throw | 3.1813654662218426e-05 | |
| 100 | asm | 2.9072391652988855e-05 | |
| 101 | <<= | 2.820059653612476e-05 | |
| 102 | /= | 2.6522715055743893e-05 | |
| 103 | wchar_t | 2.564314876313263e-05 | |
| 104 | override | 2.525155075357614e-05 | |
| 105 | reinterpret_cast | 2.5131405298831575e-05 | |
| 106 | try | 1.741370447388534e-05 | |
| 107 | catch | 1.600658306730923e-05 | |
| 108 | static_assert | 1.5125054745177641e-05 | |
| 109 | signed | 1.3128978242000654e-05 | |
| 110 | noexcept | 1.2640509833774034e-05 | |
| 111 | constexpr | 1.1923330337344905e-05 | |
| 112 | dynamic_cast | 9.529269610878605e-06 | |
| 113 | final | 7.148750735219252e-06 | |
| 114 | const_cast | 5.982535776805313e-06 | |
| 115 | decltype | 5.7780230526868046e-06 | |
| 116 | %= | 5.5216127241973635e-06 | |
| 117 | protected | 4.7412635714472045e-06 | |
| 118 | explicit | 2.6733229281924574e-06 | |
| 119 | friend | 2.44818965852701e-06 | |
| 120 | export | 2.0843678315915803e-06 | |
| 121 | typeid | 2.066824979409857e-06 | |
| 122 | mutable | 1.2851293358124168e-06 | |
| 123 | ->* | 1.2548909984991834e-06 | |
| 124 | char16_t | 1.2363094248067004e-06 | |
| 125 | char32_t | 8.326314687917419e-07 | |
| 126 | alignof | 6.199628572554138e-07 | |
| 127 | .* | 3.985612907952893e-07 | |
| 128 | alignas | 3.5347308299489553e-07 | |
| 129 | thread_local | 2.8872610882419364e-07 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This data contains the frequency of usage for C/C++ tokens.
freqis the # of type / # of tokens. This data was drawn from over 10M C/C++ files from the top ~36,500 GitHub repositories.