Files
go-toml/decode.go
T
Thomas Pelletier ea225df3ed v2: errors (#534)
```
name                              old time/op    new time/op    delta
UnmarshalDataset/config-32          86.7ms ± 2%    87.5ms ± 2%     ~     (p=0.113 n=9+10)
UnmarshalDataset/canada-32           129ms ± 4%     106ms ± 3%  -17.94%  (p=0.000 n=10+10)
UnmarshalDataset/citm_catalog-32    59.4ms ± 5%    58.7ms ± 5%     ~     (p=0.393 n=10+10)
UnmarshalDataset/twitter-32         27.0ms ± 7%    26.9ms ± 6%     ~     (p=0.720 n=10+9)
UnmarshalDataset/code-32             326ms ± 4%     322ms ± 7%     ~     (p=0.661 n=9+10)
UnmarshalDataset/example-32          510µs ±11%     526µs ± 7%     ~     (p=0.182 n=10+9)
UnmarshalSimple-32                  1.41µs ± 6%    1.41µs ± 4%     ~     (p=0.736 n=10+9)
ReferenceFile-32                    45.6µs ± 3%    43.9µs ±10%     ~     (p=0.089 n=10+10)

name                              old speed      new speed      delta
UnmarshalDataset/config-32        12.1MB/s ± 2%  12.0MB/s ± 2%     ~     (p=0.108 n=9+10)
UnmarshalDataset/canada-32        17.1MB/s ± 4%  20.9MB/s ± 3%  +21.86%  (p=0.000 n=10+10)
UnmarshalDataset/citm_catalog-32  9.41MB/s ± 5%  9.51MB/s ± 5%     ~     (p=0.362 n=10+10)
UnmarshalDataset/twitter-32       16.4MB/s ± 8%  16.5MB/s ± 6%     ~     (p=0.704 n=10+9)
UnmarshalDataset/code-32          8.24MB/s ± 4%  8.34MB/s ± 7%     ~     (p=0.675 n=9+10)
UnmarshalDataset/example-32       15.9MB/s ±11%  15.4MB/s ± 7%     ~     (p=0.182 n=10+9)
ReferenceFile-32                   115MB/s ± 4%   120MB/s ±10%     ~     (p=0.085 n=10+10)

name                              old alloc/op   new alloc/op   delta
UnmarshalDataset/config-32          16.9MB ± 0%    16.9MB ± 0%   -0.02%  (p=0.000 n=10+10)
UnmarshalDataset/canada-32          76.8MB ± 0%    74.3MB ± 0%   -3.31%  (p=0.000 n=10+10)
UnmarshalDataset/citm_catalog-32    37.3MB ± 0%    37.1MB ± 0%   -0.60%  (p=0.000 n=9+10)
UnmarshalDataset/twitter-32         15.6MB ± 0%    15.6MB ± 0%   -0.09%  (p=0.000 n=10+10)
UnmarshalDataset/code-32            60.2MB ± 0%    59.3MB ± 0%   -1.51%  (p=0.000 n=10+9)
UnmarshalDataset/example-32          238kB ± 0%     238kB ± 0%   -0.18%  (p=0.000 n=10+10)
ReferenceFile-32                    11.8kB ± 0%    11.8kB ± 0%     ~     (all equal)

name                              old allocs/op  new allocs/op  delta
UnmarshalDataset/config-32            653k ± 0%      645k ± 0%   -1.20%  (p=0.000 n=10+6)
UnmarshalDataset/canada-32           1.01M ± 0%     0.90M ± 0%  -11.04%  (p=0.000 n=9+10)
UnmarshalDataset/citm_catalog-32      384k ± 0%      370k ± 0%   -3.75%  (p=0.000 n=10+10)
UnmarshalDataset/twitter-32           160k ± 0%      157k ± 0%   -1.32%  (p=0.000 n=10+10)
UnmarshalDataset/code-32             2.97M ± 0%     2.91M ± 0%   -2.15%  (p=0.000 n=10+7)
UnmarshalDataset/example-32          3.69k ± 0%     3.63k ± 0%   -1.52%  (p=0.000 n=10+10)
ReferenceFile-32                       253 ± 0%       253 ± 0%     ~     (all equal)
```
2021-05-08 16:04:25 -04:00

360 lines
7.2 KiB
Go

package toml
import (
"math"
"strconv"
"time"
)
func parseInteger(b []byte) (int64, error) {
if len(b) > 2 && b[0] == '0' {
switch b[1] {
case 'x':
return parseIntHex(b)
case 'b':
return parseIntBin(b)
case 'o':
return parseIntOct(b)
default:
return 0, newDecodeError(b[1:2], "invalid base: '%c'", b[1])
}
}
return parseIntDec(b)
}
func parseLocalDate(b []byte) (LocalDate, error) {
// full-date = date-fullyear "-" date-month "-" date-mday
// date-fullyear = 4DIGIT
// date-month = 2DIGIT ; 01-12
// date-mday = 2DIGIT ; 01-28, 01-29, 01-30, 01-31 based on month/year
var date LocalDate
if len(b) != 10 || b[4] != '-' || b[7] != '-' {
return date, newDecodeError(b, "dates are expected to have the format YYYY-MM-DD")
}
var err error
date.Year, err = parseDecimalDigits(b[0:4])
if err != nil {
return date, err
}
v, err := parseDecimalDigits(b[5:7])
if err != nil {
return date, err
}
date.Month = time.Month(v)
date.Day, err = parseDecimalDigits(b[8:10])
if err != nil {
return date, err
}
return date, nil
}
func parseDecimalDigits(b []byte) (int, error) {
v := 0
for i, c := range b {
if !isDigit(c) {
return 0, newDecodeError(b[i:i+1], "should be a digit (0-9)")
}
v *= 10
v += int(c - '0')
}
return v, nil
}
func parseDateTime(b []byte) (time.Time, error) {
// offset-date-time = full-date time-delim full-time
// full-time = partial-time time-offset
// time-offset = "Z" / time-numoffset
// time-numoffset = ( "+" / "-" ) time-hour ":" time-minute
originalBytes := b
dt, b, err := parseLocalDateTime(b)
if err != nil {
return time.Time{}, err
}
var zone *time.Location
if len(b) == 0 {
return time.Time{}, newDecodeError(originalBytes, "date-time is missing timezone")
}
if b[0] == 'Z' {
b = b[1:]
zone = time.UTC
} else {
const dateTimeByteLen = 6
if len(b) != dateTimeByteLen {
return time.Time{}, newDecodeError(b, "invalid date-time timezone")
}
direction := 1
switch b[0] {
case '+':
case '-':
direction = -1
default:
return time.Time{}, newDecodeError(b[0:1], "invalid timezone offset character")
}
hours := digitsToInt(b[1:3])
minutes := digitsToInt(b[4:6])
seconds := direction * (hours*3600 + minutes*60)
zone = time.FixedZone("", seconds)
}
if len(b) > 0 {
return time.Time{}, newDecodeError(b, "extra bytes at the end of the timezone")
}
t := time.Date(
dt.Date.Year,
dt.Date.Month,
dt.Date.Day,
dt.Time.Hour,
dt.Time.Minute,
dt.Time.Second,
dt.Time.Nanosecond,
zone)
return t, nil
}
func parseLocalDateTime(b []byte) (LocalDateTime, []byte, error) {
var dt LocalDateTime
const localDateTimeByteMinLen = 11
if len(b) < localDateTimeByteMinLen {
return dt, nil, newDecodeError(b, "local datetimes are expected to have the format YYYY-MM-DDTHH:MM:SS[.NNNNNNNNN]")
}
date, err := parseLocalDate(b[:10])
if err != nil {
return dt, nil, err
}
dt.Date = date
sep := b[10]
if sep != 'T' && sep != ' ' {
return dt, nil, newDecodeError(b[10:11], "datetime separator is expected to be T or a space")
}
t, rest, err := parseLocalTime(b[11:])
if err != nil {
return dt, nil, err
}
dt.Time = t
return dt, rest, nil
}
// parseLocalTime is a bit different because it also returns the remaining
// []byte that is didn't need. This is to allow parseDateTime to parse those
// remaining bytes as a timezone.
//nolint:cyclop,funlen
func parseLocalTime(b []byte) (LocalTime, []byte, error) {
var (
nspow = [10]int{0, 1e8, 1e7, 1e6, 1e5, 1e4, 1e3, 1e2, 1e1, 1e0}
t LocalTime
)
const localTimeByteLen = 8
if len(b) < localTimeByteLen {
return t, nil, newDecodeError(b, "times are expected to have the format HH:MM:SS[.NNNNNN]")
}
var err error
t.Hour, err = parseDecimalDigits(b[0:2])
if err != nil {
return t, nil, err
}
if b[2] != ':' {
return t, nil, newDecodeError(b[2:3], "expecting colon between hours and minutes")
}
t.Minute, err = parseDecimalDigits(b[3:5])
if err != nil {
return t, nil, err
}
if b[5] != ':' {
return t, nil, newDecodeError(b[5:6], "expecting colon between minutes and seconds")
}
t.Second, err = parseDecimalDigits(b[6:8])
if err != nil {
return t, nil, err
}
if len(b) >= 9 && b[8] == '.' {
frac := 0
digits := 0
for i, c := range b[9:] {
if !isDigit(c) {
if i == 0 {
return t, nil, newDecodeError(b[i:i+1], "need at least one digit after fraction point")
}
break
}
//nolint:gomnd
if i >= 9 {
return t, nil, newDecodeError(b[i:i+1], "maximum precision for date time is nanosecond")
}
frac *= 10
frac += int(c - '0')
digits++
}
t.Nanosecond = frac * nspow[digits]
return t, b[9+digits:], nil
}
return t, b[8:], nil
}
//nolint:cyclop
func parseFloat(b []byte) (float64, error) {
//nolint:godox
// TODO: inefficient
if len(b) == 4 && (b[0] == '+' || b[0] == '-') && b[1] == 'n' && b[2] == 'a' && b[3] == 'n' {
return math.NaN(), nil
}
cleaned, err := checkAndRemoveUnderscores(b)
if err != nil {
return 0, err
}
if cleaned[0] == '.' {
return 0, newDecodeError(b, "float cannot start with a dot")
}
if cleaned[len(cleaned)-1] == '.' {
return 0, newDecodeError(b, "float cannot end with a dot")
}
f, err := strconv.ParseFloat(string(cleaned), 64)
if err != nil {
return 0, newDecodeError(b, "coudn't parse float: %w", err)
}
return f, nil
}
func parseIntHex(b []byte) (int64, error) {
cleaned, err := checkAndRemoveUnderscores(b[2:])
if err != nil {
return 0, err
}
i, err := strconv.ParseInt(string(cleaned), 16, 64)
if err != nil {
return 0, newDecodeError(b, "couldn't parse hexadecimal number: %w", err)
}
return i, nil
}
func parseIntOct(b []byte) (int64, error) {
cleaned, err := checkAndRemoveUnderscores(b[2:])
if err != nil {
return 0, err
}
i, err := strconv.ParseInt(string(cleaned), 8, 64)
if err != nil {
return 0, newDecodeError(b, "couldn't parse octal number: %w", err)
}
return i, nil
}
func parseIntBin(b []byte) (int64, error) {
cleaned, err := checkAndRemoveUnderscores(b[2:])
if err != nil {
return 0, err
}
i, err := strconv.ParseInt(string(cleaned), 2, 64)
if err != nil {
return 0, newDecodeError(b, "couldn't parse binary number: %w", err)
}
return i, nil
}
func parseIntDec(b []byte) (int64, error) {
cleaned, err := checkAndRemoveUnderscores(b)
if err != nil {
return 0, err
}
i, err := strconv.ParseInt(string(cleaned), 10, 64)
if err != nil {
return 0, newDecodeError(b, "couldn't parse decimal number: %w", err)
}
return i, nil
}
func checkAndRemoveUnderscores(b []byte) ([]byte, error) {
if len(b) == 0 {
return b, nil
}
if b[0] == '_' {
return nil, newDecodeError(b[0:1], "number cannot start with underscore")
}
if b[len(b)-1] == '_' {
return nil, newDecodeError(b[len(b)-1:], "number cannot end with underscore")
}
// fast path
i := 0
for ; i < len(b); i++ {
if b[i] == '_' {
break
}
}
if i == len(b) {
return b, nil
}
before := false
cleaned := make([]byte, i, len(b))
copy(cleaned, b)
for i++; i < len(b); i++ {
c := b[i]
if c == '_' {
if !before {
return nil, newDecodeError(b[i-1:i+1], "number must have at least one digit between underscores")
}
before = false
} else {
before = true
cleaned = append(cleaned, c)
}
}
return cleaned, nil
}