mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-17 16:38:54 +00:00
* 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>
148 lines
3.6 KiB
Go
148 lines
3.6 KiB
Go
package mlrval
|
|
|
|
import (
|
|
"github.com/johnkerl/miller/v6/pkg/lib"
|
|
)
|
|
|
|
// It's essential that we use mv.Type() not mv.mvtype since types are
|
|
// JIT-computed on first access for most data-file values. See type.go for more
|
|
// information.
|
|
|
|
func (mv *Mlrval) IsLegit() bool {
|
|
t := mv.Type()
|
|
return MT_INT <= t && t < MT_ERROR
|
|
}
|
|
|
|
// TODO: comment no JIT-infer here -- absent is non-inferrable and we needn't take the expense of JIT.
|
|
func (mv *Mlrval) IsErrorOrAbsent() bool {
|
|
t := mv.mvtype
|
|
return t == MT_ERROR || t == MT_ABSENT
|
|
}
|
|
|
|
func (mv *Mlrval) IsError() bool {
|
|
return mv.Type() == MT_ERROR
|
|
}
|
|
|
|
func (mv *Mlrval) GetError() (bool, error) {
|
|
if mv.Type() == MT_ERROR {
|
|
return true, mv.err
|
|
}
|
|
return false, nil
|
|
}
|
|
|
|
// TODO: comment no JIT-infer here -- absent is non-inferrable and we needn't take the expense of JIT.
|
|
func (mv *Mlrval) IsAbsent() bool {
|
|
return mv.mvtype == MT_ABSENT
|
|
}
|
|
|
|
// TODO: comment no JIT-infer here -- NULL is non-inferrable and we needn't take the expense of JIT.
|
|
// This is a literal in JSON files, or else explicitly set to NULL.
|
|
func (mv *Mlrval) IsNull() bool {
|
|
return mv.mvtype == MT_NULL
|
|
}
|
|
|
|
func (mv *Mlrval) IsVoid() bool {
|
|
if mv.mvtype == MT_VOID {
|
|
return true
|
|
}
|
|
if mv.mvtype == MT_PENDING && mv.printrep == "" {
|
|
lib.InternalCodingErrorIf(!mv.printrepValid)
|
|
return true
|
|
}
|
|
return false
|
|
}
|
|
|
|
func (mv *Mlrval) IsErrorOrVoid() bool {
|
|
return mv.IsError() || mv.IsVoid()
|
|
}
|
|
|
|
// * Error is non-empty
|
|
// * Absent is non-empty (shouldn't have been assigned in the first place; error should be surfaced)
|
|
// * Void is empty
|
|
// * Empty string is empty
|
|
// * Int/float/bool/array/map are all non-empty
|
|
func (mv *Mlrval) IsEmptyString() bool {
|
|
if mv.mvtype == MT_VOID {
|
|
return true
|
|
}
|
|
if mv.mvtype == MT_STRING && mv.printrep == "" {
|
|
return true
|
|
}
|
|
if mv.mvtype == MT_PENDING && mv.printrep == "" {
|
|
lib.InternalCodingErrorIf(!mv.printrepValid)
|
|
return true
|
|
}
|
|
return false
|
|
}
|
|
|
|
func (mv *Mlrval) IsString() bool {
|
|
return mv.Type() == MT_STRING
|
|
}
|
|
|
|
func (mv *Mlrval) IsStringOrVoid() bool {
|
|
t := mv.Type()
|
|
return t == MT_STRING || t == MT_VOID
|
|
}
|
|
|
|
func (mv *Mlrval) IsStringOrInt() bool {
|
|
t := mv.Type()
|
|
return t == MT_STRING || t == MT_VOID || t == MT_INT
|
|
}
|
|
|
|
func (mv *Mlrval) IsBytes() bool {
|
|
// Bytes are never from deferred type, so no JIT-infer is needed.
|
|
return mv.mvtype == MT_BYTES
|
|
}
|
|
|
|
func (mv *Mlrval) IsInt() bool {
|
|
return mv.Type() == MT_INT
|
|
}
|
|
|
|
func (mv *Mlrval) IsFloat() bool {
|
|
return mv.Type() == MT_FLOAT
|
|
}
|
|
|
|
func (mv *Mlrval) IsNumeric() bool {
|
|
t := mv.Type()
|
|
return t == MT_INT || t == MT_FLOAT
|
|
}
|
|
|
|
func (mv *Mlrval) IsIntZero() bool {
|
|
return mv.Type() == MT_INT && mv.intf.(int64) == 0
|
|
}
|
|
|
|
func (mv *Mlrval) IsBool() bool {
|
|
return mv.Type() == MT_BOOL
|
|
}
|
|
|
|
func (mv *Mlrval) IsTrue() bool {
|
|
return mv.Type() == MT_BOOL && mv.intf.(bool)
|
|
}
|
|
func (mv *Mlrval) IsFalse() bool {
|
|
return mv.Type() == MT_BOOL && !mv.intf.(bool)
|
|
}
|
|
|
|
func (mv *Mlrval) IsArray() bool {
|
|
// TODO: comment non-deferrable type -- don't force a (potentially
|
|
// expensive in bulk) JIT-infer of other types
|
|
// return mv.Type() == MT_ARRAY
|
|
return mv.mvtype == MT_ARRAY
|
|
}
|
|
func (mv *Mlrval) IsMap() bool {
|
|
// TODO: comment non-deferrable type -- don't force a (potentially
|
|
// expensive in bulk) JIT-infer of other types
|
|
// return mv.Type() == MT_ARRAY
|
|
return mv.mvtype == MT_MAP
|
|
}
|
|
func (mv *Mlrval) IsArrayOrMap() bool {
|
|
// TODO: comment why not
|
|
// In flatten we don't want to type-infer things that don't need to be jitted.
|
|
// Arrays & maps are never from deferred type.
|
|
// t := mv.Type()
|
|
t := mv.mvtype
|
|
return t == MT_ARRAY || t == MT_MAP
|
|
}
|
|
|
|
func (mv *Mlrval) IsFunction() bool {
|
|
return mv.mvtype == MT_FUNC
|
|
}
|