breaking: replace bytes with byte, upd parser, etc

This commit is contained in:
ge 2025-01-13 19:32:42 +03:00
parent 2f51ad63d7
commit 9206200515
5 changed files with 66 additions and 133 deletions

View File

@ -15,8 +15,8 @@ serve: clean doc
build:
v -path "$$(realpath $$PWD/../)|@vlib|@vmodules" \
-prod -skip-unused -parallel-cc -cflags -static -cflags -s -d no_segfault_handler \
cmd/dataunit.v -o dataunit
-prod -parallel-cc -cflags -static -cflags -s -d no_segfault_handler \
cmd/dataunit -o dataunit
clean:
rm -r $(DOC_DIR) || true

View File

@ -12,13 +12,16 @@ Example:
import dataunits
fn main() {
// convert via convert fn
kilobytes := dataunits.convert(500, dataunits.mbit, dataunits.kb)
println(kilobytes) // 62500.0
// convert via DataSize method (the arguments order matters)
mebibytes := (dataunits.gib * 15).mib()
println(mebibytes) // 15360.0
bytes := dataunits.DataSize(2000 * dataunits.gib).bytes()
// convert via DataSize method with explicit type cast
bytes := dataunits.DataSize(2000 * dataunits.gib).byte()
println(bytes) // 2.147483648e+12 == 2147483648000
}
```

View File

@ -1,88 +0,0 @@
// This is free and unencumbered software released into the public domain.
// Anyone is free to copy, modify, publish, use, compile, sell, or
// distribute this software, either in source code form or as a compiled
// binary, for any purpose, commercial or non-commercial, and by any
// means.
// In jurisdictions that recognize copyright laws, the author or authors
// of this software dedicate any and all copyright interest in the
// software to the public domain. We make this dedication for the benefit
// of the public at large and to the detriment of our heirs and
// successors. We intend this dedication to be an overt act of
// relinquishment in perpetuity of all present and future rights to this
// software under copyright law.
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
// IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
// OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
// ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
// OTHER DEALINGS IN THE SOFTWARE.
// For more information, please refer to <https://unlicense.org/>
/*
dataunit - a simple CLI tool for data units convertion.
*/
module main
import os
import flag
import dataunits
@[name: 'dataunit']
struct FlagConfig {
help bool
from string @[short: f]
to string @[short: t]
mut:
value f64 @[ignore]
}
fn main() {
mut flags, no_matches := flag.to_struct[FlagConfig](os.args, skip: 1, style: .v) or {
eprintln('cmdline parsing error, see -help for info')
exit(2)
}
if no_matches.len > 1 {
eprintln('unrecognized arguments: ${no_matches[1..]}')
exit(2)
} else if no_matches.len == 1 {
flags.value = no_matches[0].f64()
}
if flags.help {
println('convert the value between data size units.')
println('usage: dataunit -f <unit> -t <unit> <value>')
println('options:')
println(' -help print this help message and exit')
println(' -f, -from source data unit')
println(' -t, -to destination data unit')
exit(0)
}
if flags.from == '' || flags.to == '' {
eprintln('no -from or -to flag set, see -help for info')
exit(2)
}
if flags.value == 0 {
eprintln('no value passed, see -help for info')
exit(2)
}
src := dataunits.from_string(flags.from, ci: true) or {
eprintln('invalid source unit: ${err}')
exit(1)
}
dst := dataunits.from_string(flags.to, ci: true) or {
eprintln('invalid destination unit: ${err}')
exit(1)
}
result := '${dataunits.convert(flags.value, src, dst):.20f}'
splitted := result.split('.')
if splitted[1].contains_only('0') {
println(splitted[0])
} else {
println(result.trim_right('0'))
}
}

View File

@ -37,8 +37,8 @@ pub fn (d DataSize) nibble() f64 {
return f64(d / nibble)
}
pub fn (d DataSize) bytes() f64 {
return f64(d / bytes)
pub fn (d DataSize) byte() f64 {
return f64(d / byte)
}
pub fn (d DataSize) kb() f64 {
@ -171,9 +171,9 @@ pub fn (d DataSize) yibit() f64 {
pub const bit = DataSize(1)
pub const nibble = bit * 4
pub const bytes = bit * 8
pub const byte = bit * 8
pub const kb = bytes * 1000
pub const kb = byte * 1000
pub const mb = kb * 1000
pub const gb = mb * 1000
pub const tb = gb * 1000
@ -182,7 +182,7 @@ pub const eb = pb * 1000
pub const zb = eb * 1000
pub const yb = zb * 1000
pub const kib = bytes * 1024
pub const kib = byte * 1024
pub const mib = kib * 1024
pub const gib = mib * 1024
pub const tib = gib * 1024
@ -212,7 +212,7 @@ pub const yibit = zibit * 1024
const units = {
'bit': bit
'nibble': nibble
'bytes': bytes
'byte': byte
'kB': kb
'MB': mb
'GB': gb
@ -282,22 +282,22 @@ pub fn convert(value f64, from DataSize, to DataSize) f64 {
// from_string parses input and returns the actual DataSize.
// Note: Case insensitivity makes unit abbreviations such as `Mb` (megabit) and `MB` (megabyte)
// ambiguous. Use `bit` suffix for bit units. The `b` suffix will be accepted as byte unit.
// ambiguous. Use `bit` suffix for values in bits. The `b` suffix will be accepted as byte unit.
// Example:
// ```
// assert dataunits.from_string('GiB')! == dataunits.gib
// assert dataunits.from_string('M')! == dataunits.mib
// assert dataunits.from_string('M', bits: true, metric: true)! == dataunits.mbit
// assert dataunits.from_string('ZeTtAbYtEs', ci: true)! == dataunits.zb
// assert dataunits.from_string('M')! == dataunits.mb
// assert dataunits.from_string('M', in_bits: true)! == dataunits.mbit
// assert dataunits.from_string('ZeTtAbYtEs', case_insensitive: true)! == dataunits.zb
// ```
pub fn from_string(input string, params ParseParams) !DataSize {
if !input.is_pure_ascii() {
return error('${input} non-ASCII characters is not allowed in data size unit')
}
unit := parse_unit_str(input, params)
if params.ci {
if params.case_insensitive {
for key, value in units {
if key.to_lower_ascii() == unit {
if key.to_lower_ascii() == unit.to_lower_ascii() {
return value
}
}
@ -309,45 +309,52 @@ fn parse_unit_str(input string, params ParseParams) string {
mut unit := ''
match true {
input.to_lower_ascii() in ['byte', 'bytes'] {
return 'bytes'
return 'byte'
}
input.to_lower_ascii() in ['bit', 'bits'] {
return 'bit'
}
input.len == 1 {
if params.metric {
unit = input
} else {
if params.binary_size {
unit = input.to_upper_ascii() + 'i'
} else {
unit = input
}
if params.bits {
if params.in_bits {
unit += 'bit'
} else {
unit += 'B'
}
return unit
}
input.len == 2 && input[1] == u8(`b`) && params.ci == false {
if input[0] != u8(`k`) {
return input[..1] + 'bit'
input.len == 2 && input[1] == u8(`i`) {
if params.in_bits {
return input + 'bit'
}
return input[..1].to_upper_ascii() + 'bit'
return input + 'B'
}
input.len == 3 && input.ends_with('ib') && params.case_insensitive == false {
// Mib -> Mibit
return input[..2] + 'bit'
}
input.len == 2 && input[1] == u8(`b`) && params.case_insensitive == false {
// Mb -> Mbit
return input[..1] + 'bit'
}
else {
unit = input
}
}
if params.ci {
if params.case_insensitive {
unit = unit.to_lower_ascii()
}
if unit.len == 5 && unit.ends_with('ibit') {
// prevent Gibit --> Git transform
return unit
}
unit = unit.replace_each(maps.flat_map[string, string, string](prefixes, |k, v| [
k,
v,
]))
// transform full names to short ones: megabits --> mbit, etc.
prefixes_array := maps.flat_map[string, string, string](prefixes, |k, v| [k, v])
unit = unit.replace_each(prefixes_array)
unit = unit.replace_each(['bytes', 'B', 'byte', 'B']).replace_once('bits', 'bit')
return unit
}
@ -355,9 +362,12 @@ fn parse_unit_str(input string, params ParseParams) string {
@[params]
pub struct ParseParams {
pub:
ci bool // if true parse string in case insensitive mode
bits bool // if true interpret single letter abbreviations as bit, otherwise as byte
metric bool // if ture apply single letter as metric prefix (power of ten), otherwise as binary
// if true parse string in case insensitive mode
case_insensitive bool
// if true accept input such 'M', 'Gi' as bits, otherwise as bytes
in_bits bool
// if true accept single letter prefix as binary (power of two), otherwise as metric prefix
binary_size bool
}
// to_string returns a string representation of data size unit in short form

View File

@ -1,31 +1,39 @@
import dataunits
fn test_convert() {
assert (dataunits.nibble * 4).bytes() == 2
assert (dataunits.nibble * 4).byte() == 2
assert (dataunits.bit * 8).bit() == 8
assert (dataunits.bit * 8).bytes() == 1
assert (dataunits.bit * 8).byte() == 1
assert (dataunits.gib * 10).mib() == 10240
assert (dataunits.gib * 5000).bytes() == i64(5368709120000)
assert (dataunits.gib * 5000).byte() == i64(5368709120000)
assert (dataunits.mbit * 500).kb() == 62500
assert dataunits.convert(500, dataunits.mbit, dataunits.kb) == 62500
assert dataunits.DataSize(4000 * dataunits.gib).bytes() == f64(4294967296000)
assert dataunits.DataSize(4000 * dataunits.gib).byte() == f64(4294967296000)
}
fn test_from_string() {
assert dataunits.from_string('GiB')! == dataunits.gib
assert dataunits.from_string('M')! == dataunits.mib
assert dataunits.from_string('m', ci: true)! == dataunits.mib
assert dataunits.from_string('M', bits: true, metric: true)! == dataunits.mbit
assert dataunits.from_string('ZeTtAbYtEs', ci: true)! == dataunits.zb
assert dataunits.from_string('bytes')! == dataunits.bytes
assert dataunits.from_string('byte')! == dataunits.bytes
assert dataunits.from_string('M')! == dataunits.mb
assert dataunits.from_string('m', case_insensitive: true)! == dataunits.mb
assert dataunits.from_string('M', binary_size: true)! == dataunits.mib
assert dataunits.from_string('M', in_bits: true)! == dataunits.mbit
assert dataunits.from_string('ZeTtAbYtEs', case_insensitive: true)! == dataunits.zb
assert dataunits.from_string('bytes')! == dataunits.byte
assert dataunits.from_string('byte')! == dataunits.byte
assert dataunits.from_string('megabytes')! == dataunits.mb
assert dataunits.from_string('megabyte')! == dataunits.mb
assert dataunits.from_string('exbibit')! == dataunits.eibit
assert dataunits.from_string('Mb')! == dataunits.mbit
assert dataunits.from_string('MB')! == dataunits.mb
assert dataunits.from_string('Mb', ci: true)! == dataunits.mb
assert dataunits.from_string('Mb', case_insensitive: true)! == dataunits.mb
assert dataunits.from_string('Gibit')! == dataunits.gibit
assert dataunits.from_string('gibit', ci: true)! == dataunits.gibit
assert dataunits.from_string('Gib', ci: true)! == dataunits.gib
assert dataunits.from_string('gibit', case_insensitive: true)! == dataunits.gibit
assert dataunits.from_string('gIBiT', case_insensitive: true)! == dataunits.gibit
assert dataunits.from_string('Gib', case_insensitive: true)! == dataunits.gib
assert dataunits.from_string('Gib')! == dataunits.gibit
assert dataunits.from_string('k')! == dataunits.kb
assert dataunits.from_string('kB')! == dataunits.kb
assert dataunits.from_string('kb')! == dataunits.kbit
assert dataunits.from_string('Ki')! == dataunits.kib
assert dataunits.from_string('Gi')! == dataunits.gib
}