mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-17 16:38:54 +00:00
* Tier-2 structured verb options: OptionSpec, initial migration (#2098) PR 3 of the AI-friendly roadmap (plans/plan-2098-llm.md). Infrastructure: - Add OptionSpec{Flag,Arg,Type,Desc,Repeatable,Values} to pkg/transformers/aaa_record_transformer.go alongside TransformerSetup. Type is one of: bool, string, int, float, csv-list, regex, filename, format, enum. For type=="enum", Values lists the valid choices. - Add Options []OptionSpec to TransformerSetup (nil = not yet migrated). - Emit Options in VerbInfoForJSON (omitempty so unmigrated verbs stay backward-compatible; agents check key presence for Tier-2 availability). UsageText is always present as the Tier-1 prose fallback. - Add VerbOptionsNilCheck() in aaa_verb_options_check.go: progress report of migrated vs. unmigrated verbs, analogous to FLAG_TABLE.NilCheck(). - Wire verb-options-nil-check into mlr help (internal/docgen section). Initial migration (5/70 verbs): - nothing: empty Options (no verb-specific options, explicitly migrated) - cat: -n (bool), -N (string), -g (csv-list), --filename, --filenum (bool) - head: -g (csv-list), -n (int) - tail: -g (csv-list), -n (int) - tee: -a, -p (bool) Tests: - 5 new unit tests in aaa_transformer_json_test.go covering migrated/ unmigrated paths, field population, JSON round-trip, and key-presence. - Regression test case 0003: mlr help verb-options-nil-check golden output. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> * Migrate all 70 verbs to structured OptionSpec; bump catalog schema to v2 Completes the Tier-2 migration started in the previous commit. Every verb in TRANSFORMER_LOOKUP_TABLE now has a non-nil Options field. - Workflow-migrated all 65 remaining verbs. Each Setup var now carries Options: []OptionSpec{...} with Flag/Arg/Type/Desc fields. Verbs with no verb-specific options (altkv, check, group-like, nothing, etc.) use an empty slice to signal "migrated but no options." - Drop `omitempty` from VerbInfoForJSON.Options: empty slices were silently dropped, making migrated-no-option verbs indistinguishable from unmigrated ones in JSON. Without omitempty: null=unmigrated, []=migrated-no-options, [...]= migrated-with-options. Bump catalogSchemaVersion 1→2 for this shape change. - Replace the two "unmigrated-verb" unit tests (which used stats1 as an example) with TestAllVerbsFullyMigrated (asserts every verb has non-nil Options) and TestAllVerbsHaveOptionsKeyInJSON (asserts every migrated verb emits the "options" key in JSON). - Regenerate test/cases/cli-help/0003/expout: now reads "Verb options migration: 70/70 migrated." Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> * remove a transitional helper * git rms * Render verb usage Options blocks from structured OptionSpec Each verb's usage message and its Tier-2 OptionSpec list previously duplicated the option text. New WriteVerbOptions (aaa_verb_usage.go) renders the "Options:" block from the specs: aligned flag column, descriptions word-wrapped at 80, uniform trailing -h|--help line. - OptionSpec gains Aliases (JSON "aliases") so long-form spellings like join's --lk|--left-keep-field-names survive in both outputs - All 70 verbs migrated; options literals hoisted to package-level vars (usage funcs can't reference their Setup var without a Go init cycle) - Hand-written per-option details the specs had condensed away are merged into Desc, enriching the JSON catalog - Non-option prose (examples, cross-references, dynamic accumulator listings) kept verbatim - Regenerated the six usage-embedding regression expectations and the two affected doc pages Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Fix pre-existing usage-text bugs surfaced by the OptionSpec migration - gap: usage said "One of -f or -g is required" but the parser takes -n or -g - seqgen: drop description line copy-pasted from cat ("Passes input records directly to output...") which contradicted "Discards the input record stream" - utf8-to-latin1: description read inverted ("from Latin-1 to UTF-8") - sec2gmtdate: usage said "../c/mlr" instead of "mlr" - top: document the accepted-but-undocumented --max flag - stats2: add linreg-pca to the -a enum values, matching the runtime accumulator table Regression expectations and docs regenerated accordingly. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Fix check usage sentence order; stats1 usage blank line to usage stream - check: the description's second and third lines were swapped, reading "Consumes records without printing any output, / Useful for doing a well-formatted check on input data. / with the exception that warnings are printed to stderr." - stats1: a bare fmt.Println() in the usage func wrote its blank line to process stdout instead of the usage output stream Regression expectation and docs regenerated. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
178 lines
4.5 KiB
Go
178 lines
4.5 KiB
Go
package transformers
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"regexp"
|
|
"strings"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/cli"
|
|
"github.com/johnkerl/miller/v6/pkg/types"
|
|
)
|
|
|
|
const verbNameGrep = "grep"
|
|
|
|
var grepOptions = []OptionSpec{
|
|
{Flag: "-i", Type: "bool", Desc: "Use case-insensitive search."},
|
|
{Flag: "-v", Type: "bool", Desc: "Invert: pass through records which do not match the regex."},
|
|
{Flag: "-a", Type: "bool", Desc: "Only grep for values, not keys and values."},
|
|
}
|
|
|
|
var GrepSetup = TransformerSetup{
|
|
Verb: verbNameGrep,
|
|
UsageFunc: transformerGrepUsage,
|
|
ParseCLIFunc: transformerGrepParseCLI,
|
|
IgnoresInput: false,
|
|
Options: grepOptions,
|
|
}
|
|
|
|
func transformerGrepUsage(
|
|
o *os.File,
|
|
) {
|
|
fmt.Fprintf(o, "Usage: %s %s [options] {regular expression}\n", "mlr", verbNameGrep)
|
|
fmt.Fprintf(o, "Passes through records which match the regular expression.\n")
|
|
|
|
WriteVerbOptions(o, grepOptions)
|
|
|
|
fmt.Fprintf(o, `Note that "%s filter" is more powerful, but requires you to know field names.
|
|
By contrast, "%s grep" allows you to regex-match the entire record. It does this
|
|
by formatting each record in memory as DKVP (or NIDX, if -a is supplied), using
|
|
OFS "," and OPS "=", and matching the resulting line against the regex specified
|
|
here. In particular, the regex is not applied to the input stream: if you have
|
|
CSV with header line "x,y,z" and data line "1,2,3" then the regex will be
|
|
matched, not against either of these lines, but against the DKVP line
|
|
"x=1,y=2,z=3". Furthermore, not all the options to system grep are supported,
|
|
and this command is intended to be merely a keystroke-saver. To get all the
|
|
features of system grep, you can do
|
|
"%s --odkvp ... | grep ... | %s --idkvp ..."
|
|
`, "mlr", "mlr", "mlr", "mlr")
|
|
}
|
|
|
|
func transformerGrepParseCLI(
|
|
pargi *int,
|
|
argc int,
|
|
args []string,
|
|
_ *cli.TOptions,
|
|
doConstruct bool, // false for first pass of CLI-parse, true for second pass
|
|
) (RecordTransformer, error) {
|
|
|
|
// Skip the verb name from the current spot in the mlr command line
|
|
argi := *pargi
|
|
verb := args[argi]
|
|
argi++
|
|
|
|
ignoreCase := false
|
|
invert := false
|
|
valuesOnly := false
|
|
|
|
for argi < argc /* variable increment: 1 or 2 depending on flag */ {
|
|
opt := args[argi]
|
|
if !strings.HasPrefix(opt, "-") {
|
|
break // No more flag options to process
|
|
}
|
|
if args[argi] == "--" {
|
|
break // All transformers must do this so main-flags can follow verb-flags
|
|
}
|
|
argi++
|
|
|
|
switch opt {
|
|
case "-h", "--help":
|
|
transformerGrepUsage(os.Stdout)
|
|
return nil, cli.ErrHelpRequested
|
|
|
|
case "-i":
|
|
ignoreCase = true
|
|
|
|
case "-v":
|
|
invert = true
|
|
|
|
case "-a":
|
|
valuesOnly = true
|
|
|
|
default:
|
|
return nil, cli.VerbErrorf(verb, "option \"%s\" not recognized", opt)
|
|
}
|
|
}
|
|
|
|
// Get the regex from the command line
|
|
if argi >= argc {
|
|
return nil, cli.VerbErrorf(verb, "pattern required")
|
|
}
|
|
pattern := args[argi]
|
|
argi++
|
|
|
|
if ignoreCase {
|
|
pattern = "(?i)" + pattern
|
|
}
|
|
|
|
// TODO: maybe CompilePOSIX
|
|
regexp, err := regexp.Compile(pattern)
|
|
if err != nil {
|
|
return nil, cli.VerbErrorf(verb, "invalid regex \"%s\": %w", pattern, err)
|
|
}
|
|
|
|
*pargi = argi
|
|
if !doConstruct { // All transformers must do this for main command-line parsing
|
|
return nil, nil
|
|
}
|
|
|
|
transformer, err := NewTransformerGrep(
|
|
regexp,
|
|
invert,
|
|
valuesOnly,
|
|
)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return transformer, nil
|
|
}
|
|
|
|
type TransformerGrep struct {
|
|
regexp *regexp.Regexp
|
|
invert bool
|
|
valuesOnly bool
|
|
}
|
|
|
|
func NewTransformerGrep(
|
|
regexp *regexp.Regexp,
|
|
invert bool,
|
|
valuesOnly bool,
|
|
) (*TransformerGrep, error) {
|
|
tr := &TransformerGrep{
|
|
regexp: regexp,
|
|
invert: invert,
|
|
valuesOnly: valuesOnly,
|
|
}
|
|
return tr, nil
|
|
}
|
|
|
|
func (tr *TransformerGrep) Transform(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext, // list of *types.RecordAndContext
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) {
|
|
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
if !inrecAndContext.EndOfStream {
|
|
inrec := inrecAndContext.Record
|
|
var inrecAsString string
|
|
if tr.valuesOnly {
|
|
inrecAsString = inrec.ToNIDXString()
|
|
} else {
|
|
inrecAsString = inrec.ToDKVPString()
|
|
}
|
|
matches := tr.regexp.MatchString(inrecAsString)
|
|
if tr.invert {
|
|
if !matches {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
} else {
|
|
if matches {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
}
|
|
} else {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
}
|