| 1 | package Bin::Data::1D ; | ||
| 2 | our $VERSION = '0.130' ; | ||
| 3 | our $DATE = '2021-05-29T00:15+0900' ; | ||
| 4 | |||
| 5 | =encoding utf8 | ||
| 6 | |||
| 7 | =head1 NAME | ||
| 8 | |||
| 9 | Bin::Data::1D | ||
| 10 | |||
| 11 | =head1 SYNOPSIS | ||
| 12 | |||
| 13 | This module "Bin::Li" provides scripts for specific functions that deals "line-recorded data". | ||
| 14 | |||
| 15 | =head1 DESCRIPTION | ||
| 16 | |||
| 17 | The included commands are as follows. | ||
| 18 | |||
| 19 | =over 4 | ||
| 20 | |||
| 21 | =item * | ||
| 22 | 1. B<expskip> ; Only shows 1st, 10th, 100th, 1000th lines and so on. | ||
| 23 | |||
| 24 | =item * | ||
| 25 | 2. B<freq> ; Counts the frequencies of each different value that appears as one line. | ||
| 26 | |||
| 27 | =item * | ||
| 28 | 3. B<sampler> ; Randomly selected lines will be extracted. | ||
| 29 | |||
| 30 | =item * | ||
| 31 | 4. B<cat-n> ; Alternative function of "cat -n". i.e. the space will become the tab character, not the sequence of the space characters. | ||
| 32 | |||
| 33 | =item * | ||
| 34 | 5. B<chars2code> ; Each line is interpreted as the stream of binary codes. Hexagonal ASCII codes or Unicode will be shown. | ||
| 35 | |||
| 36 | =item * | ||
| 37 | 6. B<summing> ; Accumulative sum will be shown while reading each line. | ||
| 38 | |||
| 39 | =item * | ||
| 40 | 7. B<gzpaste> ; Unix `paste` funciton for multiple gzipped files. | ||
| 41 | |||
| 42 | |||
| 43 | =item * | ||
| 44 | 8. B<linedigest> ; print each "digest" (hash value) of all the lines. | ||
| 45 | |||
| 46 | =item * | ||
| 47 | 9. B<idmaker> ; put the same id (number) on each "different" line values. | ||
| 48 | |||
| 49 | =item * | ||
| 50 | 10. B<uniq-c> ; Alternative of "uniq -c". | ||
| 51 | |||
| 52 | =item * | ||
| 53 | 11. B<wc-l> ; Alternative of "wc -l". | ||
| 54 | |||
| 55 | =item * | ||
| 56 | 12. B<headomit> ; a utility especially for multiple files so that the common first line values will be treated (omitted or reserved). | ||
| 57 | |||
| 58 | =item * | ||
| 59 | 13. B<lminusl> ; Given 2 files A and B, each file regarded to be a set of line values {a} or {b} for the two, {a∈A}\{b∈B} will be shown. | ||
| 60 | |||
| 61 | =item * | ||
| 62 | 14. B<alluniq> ; gives the infomation whether every line of a file contains all different or how the "multitudes" distributes. useful. | ||
| 63 | |||
| 64 | =item * | ||
| 65 | 15. B<digitdemog> ; shows the character distributions for each digits from the left (not the right) of all the lines. | ||
| 66 | |||
| 67 | =item * | ||
| 68 | 16. B<entrolines> ; calculates the "entropy" how each line values are different. | ||
| 69 | |||
| 70 | =item * | ||
| 71 | 17. B<venn> ; outputs the table that represents the concept of the Venn diagram for given multiple files. | ||
| 72 | |||
| 73 | =back | ||
| 74 | |||
| 75 | =head1 SEE ALSO | ||
| 76 | |||
| 77 | =cut | ||
| 78 | |||
| 79 | 1 ; |