mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-21 10:29:02 +00:00
12c96298b9
* Add MT_BYTES mlrval type: foundation and disposition tables First step toward a first-class bytes type in the DSL (#1231). Adds MT_BYTES (payload []byte, rendered as lowercase hex in all output formats, JSON-encoded as a hex string), extends every disposition matrix/vector with the new row/column -- real cells for comparison, sorting, and dot-concat of bytes with bytes; type-error stubs elsewhere -- and adds sweep tests asserting no table has nil cells, since Go zero-fills short array literals when MT_DIM grows. Bytes values are not yet constructible from the DSL; b"..." literals and constructor/codec functions follow in subsequent commits. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Add b"..." bytes-literal syntax to the DSL Adds a bytes_literal token to the grammar (regenerating the PGPG lexer and parser) and a BytesLiteralNode in the CST which evaluates to an MT_BYTES mlrval. Escape handling reuses UnbackslashStringLiteral, which is already byte-oriented: b"\xff" is the single byte 0xff. Unlike string literals, bytes literals never participate in regex-capture replacement. A bare identifier b is unaffected. Part of #1231. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Add bytes DSL functions: conversions, codecs, and bytes-aware built-ins - bytes(x) converts strings to bytes; string(b) reinterprets raw bytes as UTF-8 text (the reverse) - base64_decode now always returns bytes (superseding the interim string-or-hex behavior); base64_encode accepts string or bytes - New hex_encode/hex_decode functions - is_bytes and asserting_bytes predicates - md5/sha1/sha256/sha512 accept bytes, hashing the raw payload - strlen of bytes is the byte count; substr/substr0/substr1 on bytes slice by byte position and return bytes The Cyrillic-LDAP scenario from #1231 now works without exec workarounds: string(base64_decode($x)) recovers the text, and binary payloads survive undamaged as bytes. Closes #1231. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Add bytes-type docs and regression cases Documents the bytes type on the data-types page, regenerates the function-reference/man-page material, and adds regression coverage: literal escape forms, operators (concat/compare/slice/sort and type errors), conversions and codec round-trips, and CSV-to-JSON output rendering of bytes fields. Part of #1231. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Reposition MT_BYTES to sort adjacent to MT_STRING in the type enum MT_BYTES was appended after MT_ABSENT for index stability; move it right after MT_STRING instead, since that's where it conceptually belongs and where it already sorts in the cmp disposition matrices. Mechanically re-derive all ~40 disposition tables in pkg/bifs and pkg/mlrval accordingly. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * fix windows CI * fix merge --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
55 lines
1.4 KiB
Go
55 lines
1.4 KiB
Go
package bifs
|
|
|
|
import (
|
|
"crypto/md5"
|
|
"crypto/sha1"
|
|
"crypto/sha256"
|
|
"crypto/sha512"
|
|
"fmt"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/mlrval"
|
|
)
|
|
|
|
// hashableBytes returns the raw payload to hash: for strings, their UTF-8
|
|
// bytes; for bytes values, the bytes themselves.
|
|
func hashableBytes(funcname string, input1 *mlrval.Mlrval) ([]byte, *mlrval.Mlrval) {
|
|
if input1.IsBytes() {
|
|
return input1.AcquireBytesValue(), nil
|
|
}
|
|
if !input1.IsStringOrVoid() {
|
|
return nil, mlrval.FromNotStringError(funcname, input1)
|
|
}
|
|
return []byte(input1.AcquireStringValue()), nil
|
|
}
|
|
|
|
func BIF_md5(input1 *mlrval.Mlrval) *mlrval.Mlrval {
|
|
payload, errval := hashableBytes("md5", input1)
|
|
if errval != nil {
|
|
return errval
|
|
}
|
|
return mlrval.FromString(fmt.Sprintf("%x", md5.Sum(payload)))
|
|
}
|
|
|
|
func BIF_sha1(input1 *mlrval.Mlrval) *mlrval.Mlrval {
|
|
payload, errval := hashableBytes("sha1", input1)
|
|
if errval != nil {
|
|
return errval
|
|
}
|
|
return mlrval.FromString(fmt.Sprintf("%x", sha1.Sum(payload)))
|
|
}
|
|
|
|
func BIF_sha256(input1 *mlrval.Mlrval) *mlrval.Mlrval {
|
|
payload, errval := hashableBytes("sha256", input1)
|
|
if errval != nil {
|
|
return errval
|
|
}
|
|
return mlrval.FromString(fmt.Sprintf("%x", sha256.Sum256(payload)))
|
|
}
|
|
|
|
func BIF_sha512(input1 *mlrval.Mlrval) *mlrval.Mlrval {
|
|
payload, errval := hashableBytes("sha512", input1)
|
|
if errval != nil {
|
|
return errval
|
|
}
|
|
return mlrval.FromString(fmt.Sprintf("%x", sha512.Sum512(payload)))
|
|
}
|