Name the quoted spelling when an unquoted layout holding a comma splits into extra args

CHANGELOG.md

@@ -13,8 +13,9 @@ replacement, and each removed path, column or flag.
   `key`, `name`, `weight` and `parent`; a path selects a row by key or name,
   `misc.country[SE]`, and descends to a linked table by name; linked tables draw
   consistently within one render and draw group. `rows` is an option, so no
-  template may carry a field of that name. Refused at `New`: a `name` without a
+  template may carry a field of that name. A `name` without a `key` resolves
-  `key`, a name spelling another row's key, a table named like a column of any
+  inside the table's `parent`. Refused at `New`: a `name` without a `key` or a
+  `parent`, a name repeating inside one parent row, a name spelling another row's key, a table named like a column of any
   table above it, a table whose format or cell references its own family, and,
   within one render and draw group, a path drawing a table another path selects a
   row of, or two paths pinning different rows of one table.
@@ -31,4 +32,16 @@ replacement, and each removed path, column or flag.
   and built from SCB, GeoNames, Trafikverket NVDB and the US Census Bureau, and an
   `address` record over one consistent draw of them. `sv_SE.address` and
   `en_US.address` read those records, so `en_US.address.street` no longer carries
-  `name` and `suffix`, and a locale folder loads only beside `geo`.
+    `name` and `suffix`, and a locale folder loads only beside `geo`.
+- `{date(from,to,'layout')}` and `{time('layout')}`: a second between two days, or
+  within one, in a quoted Go layout. `sv_SE.date`, `en_US.date`, `sv_SE.time` and
+  `en_US.time` render through them, so `date.year`, `date.month`, `date.day` and
+  `time.hour` are no longer paths, and `misc.datetime` is an RFC 3339 instant.
+- `sex`, `first-name` and `last-name` tables in `sv_SE` and `en_US`, weighted by
+  bearers from SCB, the SSA and the Census Bureau; `first-name` links to `sex`, and a
+  name both sexes carry is a row under each. `person` reads them, so its columns are
+  `first`, `last`, `prefix` and `sex`, and `person.femalefirst` and
+  `person.malefirst` are no longer paths.
+- `sv_SE.personnummer` and `sv_SE.samordningsnummer`, Skatteverket's test series
+  over the sex the render drew, in place of `sv_SE.ssn`; `en_US.ssn` in the ranges
+  the SSA assigns, and `en_US.itin`.

DATA-LICENSES.md

@@ -11,6 +11,10 @@ Every shipped dataset, its source, its licence and the attribution it asks for.
 | `geo/SE/street.tsv` | [Trafikverket NVDB](https://www.trafikverket.se/) Gatunamn, through the open API | CC0 1.0 | none required | `data-import/geo-se.py` |
 | `geo/US/region.tsv`, `municipality.tsv`, `locality.tsv` | [Census Bureau](https://www.census.gov/) Gazetteer 2026 and population estimates 2025 | [public domain](https://www.usa.gov/government-works) | none required | `data-import/geo-us.py` |
 | `geo/US/postal-code.tsv`, `street.tsv` | Census Bureau ZCTA to place relationships 2020 and TIGER/Line 2025 address ranges and feature names | public domain | none required | `data-import/geo-us.py` |
+| `sv_SE/first-name.tsv`, `last-name.tsv` | [SCB](https://www.scb.se/) names with at least two bearers, 31 December 2022 | CC0 1.0 | "Källa: SCB" | `data-import/names-se.py` |
+| `en_US/first-name.tsv` | [SSA](https://www.ssa.gov/oact/babynames/) baby names, births 1930 to 2020, through [hackerb9/ssa-baby-names](https://github.com/hackerb9/ssa-baby-names) | public domain | none required | `data-import/names-us.py` |
+| `en_US/last-name.tsv` | Census Bureau surnames occurring 100 or more times, 2010 | public domain | none required | `data-import/names-us.py` |
+| `sv_SE/sex.tsv`, `en_US/sex.tsv` | curated (Skatteverket's test birth numbers are facts) | — | — | — |
 | `misc/country.tsv` | [datasets/country-codes](https://github.com/datasets/country-codes) | [PDDL 1.0](https://opendatacommons.org/licenses/pddl/1-0/) | none required | `data-import/country.py` |
 | `misc/currency.tsv` | [datasets/currency-codes](https://github.com/datasets/currency-codes); symbols from [Unicode CLDR](https://github.com/unicode-org/cldr) `en.xml` and `root.xml` | PDDL 1.0; [Unicode License v3](https://www.unicode.org/license.txt) | CLDR: "Copyright © 1991-2025 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries." | `data-import/currency.py` |
 | `misc/httpstatus.tsv` | curated (IANA HTTP status codes are facts) | — | — | — |

README.md

@@ -217,17 +217,27 @@ Sources merge in order; matching folders combine, any other clash is won by the
 last loaded. Names may not use `.`, `|`, `(`, `{`, `}`, `[`, `]`, `"` or `/`, nor be
 `-`, which a struct tag reserves; dot-prefixed entries are skipped, so a data directory can also be a checkout.
 
-Each locale carries `address`, `color`, `company`, `date`, `email`, `ip`,
+Each locale carries `address`, `color`, `company`, `date`, `email`, `first-name`,
-`person`, `phone`, `price`, `sentence`, `ssn`, `time`, `url`, `username`,
+`ip`, `last-name`, `person`, `phone`, `price`, `sentence`, `sex`, `time`, `url`,
-`version` and `word`, formatted per locale. `misc` carries `car`, `coordinate`,
+`username`, `version` and `word`, formatted per locale; `sv_SE` adds
-`country` (ISO 3166), `creditcard` (Luhn-valid), `currency` (ISO 4217), `emoji`,
+`personnummer` and `samordningsnummer`, `en_US` adds `ssn` and `itin`. `misc`
-`httpstatus`, `language` (ISO 639), `mac`, `mimetype`, `objectid`, `timezone`
+carries `car`, `coordinate`, `country` (ISO 3166), `creditcard` (Luhn-valid),
-(IANA), `useragent` and `uuid` (v4). Many carry sub-fields — `misc.currency.symbol`,
+`currency` (ISO 4217), `datetime` (RFC 3339), `emoji`, `httpstatus`, `language`
+(ISO 639), `mac`, `mimetype`, `objectid`, `timezone` (IANA), `useragent` and
+`uuid` (v4). Many carry sub-fields — `misc.currency.symbol`,
 `misc.country.alpha2`, `misc.httpstatus.code` — which `--list` shows. `country`,
 `currency`, `httpstatus`, `language` and `mimetype` are [tables](#table), so
 `misc.country[SE].capital` and `misc.currency[Euro].symbol` select a row;
 [`DATA-LICENSES.md`](DATA-LICENSES.md) names each table's source and licence.
 
+`sex`, `first-name` and `last-name` are tables weighted by bearers, from SCB, the
+SSA and the Census Bureau. `first-name` links to `sex`, so `sv_SE.sex[f].first-name`
+draws a woman's name, and a name both sexes carry is a row under each, so
+`en_US.sex[m].first-name[Taylor]` names the one a `first-name[Taylor]` alone cannot.
+`person` reads one draw of the three, so its `first` and `sex` columns agree, and so
+does a `personnummer` in the same render: its birth number is Skatteverket's test
+series, 238 for a woman and 239 for a man, which no real person is ever given.
+
 A `geo` folder holds one tree per country under its alpha-2 code: five
 [linked tables](#linked-tables) named alike, and an `address` record over one
 consistent draw of them, which the locale's `address` reads.
@@ -407,7 +417,9 @@ cell token, and refuses a TSV no category names, a key that is empty or repeats,
 weight that is not a positive number, and a key or name holding `[`, `]`, `{`, `}`,
 `"` or `|`, which a selector cannot spell; the rows are indexed on the first draw that
 selects one. A `name` needs a `key`, since a name naming several rows is reported by
-their keys, and a name spelling another row's key is refused, since the key would
+their keys, or a `parent`, inside whose row a name names one row, so `first-name[Kim]`
+is settled by the `sex` selected before it and a name repeating inside one parent row
+is refused; a name spelling another row's key is refused, since the key would
 select first and the name never. The table's options are its own — `rows`, `key`,
 `name`, `weight` and `parent` — so a column may be named `name`, as one usually is.
 
@@ -505,21 +517,30 @@ stays reproducible.
 | `{ulid()}` | sample | ULID, 26 Crockford base32 chars |
 | `{nanoid(n)}` | sample | URL-safe Nano ID, `n` chars |
 | `{iban(CC)}` | sample | length- and mod-97-valid IBAN for BE, DE, DK, ES, FI, NO or SE |
+| `{date(from,to,'layout')}` | sample | a second between two `YYYY-MM-DD` days, both included, in a quoted Go layout: `'2006-01-02'`, `'January 2, 2006'`, `'060102'`, `'2006-01-02T15:04:05Z'` |
+| `{time('layout')}` | sample | a second within a day: `'15:04'`, `'3:04 PM'` |
 | `{seq()}`, `{seq(name)}` | counter | next integer from 1 in this generator; `name` selects an independent counter |
 | `{calc(expr)}`, `{calc(expr,dp)}` | computation | an arithmetic expression over sibling fields ([Computation](#computation)) |
 | `{lowercase(x)}`, `{uppercase(x)}`, `{ascii(x)}` | transform | a field's value rewritten ([Transforms](#transforms)) |
 
 A derivation reads what is to its left, so place it after its payload; the
 buffer is per expansion, so a nested template keeps fixed parts out of the sum. A
-Swedish personnummer is a Luhn checksum over the nine digits before it:
+Swedish personnummer is a Luhn checksum over the nine digits before it, six of
+them a birthdate:
 
 ```json
-{ "format": "{century}{core}", "century": ["19", "20"],
+{ "format": "{date(1930-01-01,2010-12-31,'060102')}-{birth}{luhn()}", "birth": ["238", "239"] }
-  "core": { "format": "{digits(2)}{mmdd}-{digits(3)}{luhn()}", "mmdd": ["0115", "0704", "1218"] } }
 ```
 
-Renders e.g. `19811218-9876`. `{seq()}` spans `Fake` calls and `repeat`, resets
+Renders e.g. `811218-2389`. A layout is Go's: the reference time `Mon Jan 2
-with a new generator, and is the natural primary key for the SQL example above.
+15:04:05 MST 2006` spelled as the output should look, quoted, since a layout may
+carry the comma that separates arguments, with English names. Every second
+between the two days is reachable, so a layout with a clock draws the time too.
+Rejected at `New`: a bound that is no calendar date, or not before the other; an
+unquoted layout, naming the quoted one; a layout naming no field, which is text;
+and for `time` a layout naming a date field, naming `date`. `{seq()}` spans `Fake`
+calls and `repeat`, resets with a new generator, and is the natural primary key for
+the SQL example above.
 
 ### Computation
 
@@ -573,9 +594,9 @@ without naming `sv_SE`:
 
 Renders e.g. `Hej, Pat Smith!`. A reference path into a category is held like a
 [correlated](#correlated-fields) path, but for the whole render — one `Fake`, or one
-record — rather than one format: `{.person.femalefirst} {.person.last}` name one
+record — rather than one format: `{.person.first} {.person.last}` name one
 person, as do the same two references in sibling fields or a nested template, and
-`{lowercase(.person.femalefirst)}` reads that same draw. Each `repeat` iteration is
+`{lowercase(.person.first)}` reads that same draw. Each `repeat` iteration is
 a render of its own, in no group, so it draws anew, and a [draw group](#draw-group) holds a
 draw apart. A bare reference names no field and makes its own picks each time —
 `{/misc.uuid} {/misc.uuid}` is two draws — while the reference paths inside what it
@@ -594,8 +615,8 @@ its groups by name; the unnamed group spans them all.
 
 ```json
 { "format": "{payer} pays {payee}; signed {signature}",
-  "payer": { "format": "{/sv_SE.person.femalefirst} {/sv_SE.person.last}", "drawGroup": "payer" },
+    "payer": { "format": "{/sv_SE.person.first} {/sv_SE.person.last}", "drawGroup": "payer" },
-  "payee": "{/sv_SE.person.femalefirst} {/sv_SE.person.last}",
+  "payee": "{/sv_SE.person.first} {/sv_SE.person.last}",
   "signature": { "format": "{/sv_SE.person.last}", "drawGroup": "payer" } }
 ```
 
@@ -728,8 +749,7 @@ renamed or retyped line is a major.
   key, or prefixing options, would tax every template to guard against a
   misspelt option.
 - **`{a|b}` stays beside nested choices.** `[[…], […]]` picks the same way, but
-  its arms are anonymous; `{femalefirst|malefirst}` keeps `person.femalefirst`
+  its arms are anonymous; `{female|male}` keeps `person.female` addressable.
-  addressable.
 - **Flags follow getopt_long.** `--name value` and `--name=value` both work; a
   short flag's value attaches or follows (`-s42`, `-s 42`) and short flags bundle
   (`-hn 3`), as every shell user expects. A single-dash long flag is rejected
@@ -1040,6 +1060,30 @@ renamed or retyped line is a major.
   bigger neighbour ship no address; counting the land outside every place too would
   drop a quarter of the places, whose codes straddle unincorporated land, for a
   postal city the USPS mostly names the same way.
+- **A layout is always quoted.** A layout may carry the comma that separates
+  arguments, `'January 2, 2006'`, and one spelling for every layout beats a rule
+  about which ones need the quotes, so the bare spelling is refused naming the
+  quoted one. The layout is Go's reference time because the library renders with
+  it and a Go caller already knows it; its names are English, and a locale's own
+  month and weekday names are data.
+- **No builtin reads the clock, so a date is bounded by days, never by an age.**
+  An `age(min,max)` would make a seeded fixture change with the day it runs on,
+  which is what a seed exists to prevent; a birthdate for someone 20 to 60 is
+  `date(1966-01-01,2006-12-31,…)`, re-pinned as any fixture is.
+- **A name column without a key resolves inside its parent.** A given name both
+  sexes carry is a row under each, so `name` cannot be the key; the parent's row
+  tells the two apart, `sex[f].first-name[Kim]`, the ambiguity error spells each
+  row inside its parent, and a name repeating inside one parent row is refused at
+  load, since nothing could then select it.
+- **The Swedish ids draw Skatteverket's test series.** A Luhn-valid personnummer
+  over a random birth number may be a living person's; 238 and 239 after any date
+  are blocked from assignment, so the shipped `personnummer` and
+  `samordningsnummer` use those, read from the `sex` table's `birth-number`
+  column so the number and the name agree on sex.
+- **The US given names come from a mirror of the SSA file.** ssa.gov refuses a
+  client outside the US, so `names-us.py` reads a GitHub copy that ends at 2020,
+  which a count over the births since 1930 barely feels; `--names` takes the
+  official zip.
 - **`List` advertises direct descents only.** `region.municipality.locality` is
   listed, and `region.locality` resolves too but is not: the set of every descent
   through a chain of five tables is every subsequence of it, and the direct chain is
@@ -1091,15 +1135,19 @@ A shipped table built from a source is rebuilt by its script under
 [`data-import/`](data-import), one command per dataset, fetching the source named in
 [`DATA-LICENSES.md`](DATA-LICENSES.md). Downloads are cached under
 `data-import/cache/`, so delete it to fetch afresh; `geo-us.py` fetches two
-TIGER/Line files per county it ships, a few hundred megabytes, and `geo-se.py` needs
+TIGER/Line files per county it ships, a few hundred megabytes, `geo-se.py` needs
 a Trafikverket API key, free at [data.trafikverket.se](https://data.trafikverket.se/),
-in `TRAFIKVERKET_API_KEY` or a `--key-file`:
+in `TRAFIKVERKET_API_KEY` or a `--key-file`, and the Census host behind `geo-us.py`
+and `names-us.py` rejects a client for a while after a burst, so `--surnames` takes
+a copy of the surname file:
 
 ```sh
 docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/country.py
 docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/currency.py
 docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/geo-us.py
 docker compose run --rm --user "$(id -u):$(id -g)" -e TRAFIKVERKET_API_KEY data-import data-import/geo-se.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/names-se.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/names-us.py
 ```
 
 To release, head `CHANGELOG.md` with the version's section in place of `Unreleased`

bench_test.go

@@ -30,7 +30,7 @@ func BenchmarkPerson(b *testing.B)     { benchPath(b, "data", "sv_SE.person") }
 func BenchmarkAddress(b *testing.B)    { benchPath(b, "data", "sv_SE.address") }
 func BenchmarkWord(b *testing.B)       { benchPath(b, "data", "sv_SE.word") }
 func BenchmarkCreditcard(b *testing.B) { benchPath(b, "data", "misc.creditcard") }
-func BenchmarkSSN(b *testing.B)        { benchPath(b, "data", "sv_SE.ssn") }
+func BenchmarkSSN(b *testing.B)        { benchPath(b, "data", "sv_SE.personnummer") }
 func BenchmarkUUIDv7(b *testing.B)     { benchPath(b, "data", "misc.uuid") }
 
 func tmpData(b *testing.B, name, body string) string {

builtins.go

@@ -7,6 +7,7 @@ import (
 	"math"
 	"strconv"
 	"strings"
+	"time"
 	"unicode"
 )
 
@@ -60,6 +61,8 @@ var builtins = map[string]builtin{
 		cc := a[0]
 		return func(s *session, _ string, _ []string) string { return iban(s, cc) }
 	}},
+	"date":      {arity: -1, check: dateArgs, prep: datePrep},
+	"time":      {arity: -1, check: timeArg, prep: timePrep},
 	"calc":      {arity: -1, check: checkCalc, prep: calcPrep, operands: calcOperands},
 	"lowercase": {arity: 1, check: transformArg, prep: transformPrep(strings.ToLower), operands: transformOperand},
 	"uppercase": {arity: 1, check: transformArg, prep: transformPrep(strings.ToUpper), operands: transformOperand},
@@ -466,3 +469,106 @@ func iban(r rng, cc string) string {
 	feed(0)
 	return fmt.Sprintf("%s%02d%s", cc, 98-rem, bban)
 }
+
+const dayLayout = "2006-01-02"
+
+// The two instants a layout is proved against: alike in nothing, so a layout that
+// formats them alike names no field, and one that tells their days apart at the same
+// clock names a date field.
+var (
+	layoutProbe  = time.Date(2001, 2, 3, 4, 5, 6, 0, time.UTC)
+	layoutProbe2 = time.Date(2010, 11, 12, 13, 14, 15, 0, time.UTC)
+	layoutDay    = time.Date(2010, 11, 12, 4, 5, 6, 0, time.UTC)
+)
+
+// layoutArg is the Go layout a quoted arg holds; unquoted, it is refused naming the
+// quoted spelling, since a layout may carry the comma that splits args.
+func layoutArg(a string) (string, error) {
+	if len(a) < 2 || a[0] != '\'' || a[len(a)-1] != '\'' {
+		return "", fmt.Errorf("layout %s is not quoted; write '%s'", a, strings.Trim(a, "'"))
+	}
+	layout := a[1 : len(a)-1]
+	if layoutProbe.Format(layout) == layoutProbe2.Format(layout) {
+		return "", fmt.Errorf("layout '%s' names no field, so it is the constant %q; write it as text", layout, layout)
+	}
+	return layout, nil
+}
+
+// layoutOf is layoutArg for an arg a check already validated.
+func layoutOf(a string) string {
+	layout, err := layoutArg(a)
+	if err != nil {
+		panic(fmt.Sprintf("fejkdata: builtin arg %q reached prep unvalidated: %v", a, err))
+	}
+	return layout
+}
+
+// layoutArity checks a call that ends in a layout takes n args; an unquoted layout
+// carrying a comma splits into more, so the error names its quoted spelling.
+func layoutArity(name string, n int, a []string) error {
+	if len(a) == n {
+		return nil
+	}
+	hint := ""
+	if len(a) > n {
+		hint = fmt.Sprintf("; a layout holding a comma is quoted: '%s'", strings.Join(a[n-1:], ", "))
+	}
+	return fmt.Errorf("%s takes %d args, got %d%s", name, n, len(a), hint)
+}
+
+func dateArgs(_ map[string]node, a []string) error {
+	if err := layoutArity("date", 3, a); err != nil {
+		return err
+	}
+	from, err := time.Parse(dayLayout, a[0])
+	if err != nil {
+		return fmt.Errorf("date(from,to,layout): from %q is not a YYYY-MM-DD date", a[0])
+	}
+	to, err := time.Parse(dayLayout, a[1])
+	if err != nil {
+		return fmt.Errorf("date(from,to,layout): to %q is not a YYYY-MM-DD date", a[1])
+	}
+	if !from.Before(to) {
+		return fmt.Errorf("date(from,to,layout): from %s is not before to %s", a[0], a[1])
+	}
+	_, err = layoutArg(a[2])
+	return err
+}
+
+func timeArg(_ map[string]node, a []string) error {
+	if err := layoutArity("time", 1, a); err != nil {
+		return err
+	}
+	layout, err := layoutArg(a[0])
+	if err != nil {
+		return err
+	}
+	if layoutProbe.Format(layout) != layoutDay.Format(layout) {
+		return fmt.Errorf("time(layout): '%s' names a date field; write date(from,to,layout)", layout)
+	}
+	return nil
+}
+
+// datePrep draws a second in [from 00:00:00, to 23:59:59] UTC; the span is counted
+// in seconds, since a Duration overflows past 292 years.
+func datePrep(a []string) callFn {
+	from, err := time.Parse(dayLayout, a[0])
+	if err != nil {
+		panic(fmt.Sprintf("fejkdata: builtin arg %q reached prep unvalidated: %v", a[0], err))
+	}
+	to, err := time.Parse(dayLayout, a[1])
+	if err != nil {
+		panic(fmt.Sprintf("fejkdata: builtin arg %q reached prep unvalidated: %v", a[1], err))
+	}
+	layout, start, span := layoutOf(a[2]), from.Unix(), int(to.Unix()-from.Unix())+86400
+	return func(s *session, _ string, _ []string) string {
+		return time.Unix(start+int64(s.IntN(span)), 0).UTC().Format(layout)
+	}
+}
+
+func timePrep(a []string) callFn {
+	layout := layoutOf(a[0])
+	return func(s *session, _ string, _ []string) string {
+		return time.Unix(int64(s.IntN(86400)), 0).UTC().Format(layout)
+	}
+}

builtins_test.go

@@ -4,7 +4,9 @@ import (
 	"encoding/base64"
 	"regexp"
 	"strconv"
+	"strings"
 	"testing"
+	"time"
 )
 
 func TestBuiltinIDGenerators(t *testing.T) {
@@ -41,6 +43,7 @@ func TestBuiltinSamplesReproducible(t *testing.T) {
 		`"{uuid()}"`, `"{ulid()}"`,
 		`"{nanoid(12)}"`, `"{int(1,1000000)}"`,
 		`"{float(0,1,6)}"`, `"{base64(12)}"`, `"{iban(SE)}"`,
+		`"{date(2000-01-01,2020-12-31,'2006-01-02 15:04:05')}"`, `"{time('15:04:05')}"`,
 	} {
 		if a, b := mustRender(t, engine(7), tmpl), mustRender(t, engine(7), tmpl); a != b {
 			t.Fatalf("%s not reproducible: %q != %q", tmpl, a, b)
@@ -233,3 +236,84 @@ func TestClassBuiltinArgs(t *testing.T) {
 		}
 	}
 }
+
+// TestBuiltinDateAndTime pins the two clock-free samples: date draws a second in
+// [from 00:00:00, to 23:59:59], both days reachable, and renders it in the quoted Go
+// layout, commas and English names included; time draws a second within one day.
+func TestBuiltinDateAndTime(t *testing.T) {
+	f := engine(1)
+	seen := map[string]bool{}
+	for i := 0; i < 500; i++ {
+		got := mustRender(t, f, `"{date(1990-01-01,1990-12-31,'2006-01-02')}"`)
+		if d, err := time.Parse("2006-01-02", got); err != nil || d.Year() != 1990 {
+			t.Fatalf("date = %q, want a 1990 calendar date (err %v)", got, err)
+		}
+		seen[got] = true
+	}
+	if len(seen) < 200 {
+		t.Fatalf("date drew %d distinct days of 365 in 500, want a uniform spread", len(seen))
+	}
+	lo, hi := false, false
+	for i := 0; i < 200; i++ {
+		got := mustRender(t, f, `"{date(2020-02-28,2020-02-29,'2006-01-02')}"`)
+		if got != "2020-02-28" && got != "2020-02-29" {
+			t.Fatalf("date(2020-02-28,2020-02-29) = %q, out of range", got)
+		}
+		lo, hi = lo || got == "2020-02-28", hi || got == "2020-02-29"
+	}
+	if !lo || !hi {
+		t.Fatalf("date never hit a bound: lo=%v hi=%v (bounds must be inclusive)", lo, hi)
+	}
+	if got := mustRender(t, f, `"{date(2020-07-04,2020-07-05,'January 2, 2006')}"`); got != "July 4, 2020" && got != "July 5, 2020" {
+		t.Fatalf("date with a comma in its layout = %q", got)
+	}
+	rfc := regexp.MustCompile(`^2021-\d\d-\d\dT\d\d:\d\d:\d\dZ$`)
+	clock := regexp.MustCompile(`^([01]\d|2[0-3]):[0-5]\d$`)
+	ampm := regexp.MustCompile(`^(1[0-2]|[1-9]):[0-5]\d (AM|PM)$`)
+	seconds := map[string]bool{}
+	for i := 0; i < 300; i++ {
+		got := mustRender(t, f, `"{date(2021-01-01,2021-12-31,'2006-01-02T15:04:05Z07:00')}"`)
+		if !rfc.MatchString(got) {
+			t.Fatalf("date in an RFC 3339 layout = %q, want %s", got, rfc)
+		}
+		seconds[got[17:19]] = true
+		if got := mustRender(t, f, `"{time('15:04')}"`); !clock.MatchString(got) {
+			t.Fatalf("time('15:04') = %q, want %s", got, clock)
+		}
+		if got := mustRender(t, f, `"{time('3:04 PM')}"`); !ampm.MatchString(got) {
+			t.Fatalf("time('3:04 PM') = %q, want %s", got, ampm)
+		}
+		got = mustRender(t, f, `"{date(1950-01-01,2000-12-31,'060102')}-238{luhn()}"`)
+		if d := digitsOnly(got); len(d) != 10 || !luhnValid(d) {
+			t.Fatalf("a personnummer over date() = %q, want ten Luhn-valid digits", got)
+		}
+	}
+	if len(seconds) < 30 {
+		t.Fatalf("date drew %d distinct seconds in 300, want the whole day, not midnight", len(seconds))
+	}
+}
+
+// TestBuiltinDateArgs pins the New-time checks: bounds are calendar dates in order,
+// the layout is quoted, names a field, and for time names no date field.
+func TestBuiltinDateArgs(t *testing.T) {
+	for tmpl, want := range map[string]string{
+		`"{date(1990-13-01,1990-12-31,'2006-01-02')}"`:     "1990-13-01",
+		`"{date(1990-12-31,1990-01-01,'2006-01-02')}"`:     "before",
+		`"{date(1990-01-01,1990-01-01,'2006-01-02')}"`:     "before",
+		`"{date(1990-01-01,1990-12-31,2006-01-02)}"`:       "'2006-01-02'",
+		`"{date(1990-01-01,1990-12-31,'January 2, 2006)}"`: "'",
+		`"{date(1990-01-01,1990-12-31,'x')}"`:              "text",
+		`"{date(1990-01-01,1990-12-31,'')}"`:               "text",
+		`"{date(1990-01-01,1990-12-31)}"`:                  "3 args",
+		`"{date(1990-01-01,1990-12-31,January 2, 2006)}"`:  "'January 2, 2006'",
+		`"{time(3:04 PM, Mon)}"`:                           "'3:04 PM, Mon'",
+		`"{time(15:04)}"`:                                  "'15:04'",
+		`"{time('2006-01-02 15:04')}"`:                     "date(",
+		`"{time('x')}"`:                                    "text",
+	} {
+		_, err := compile(parse(t, tmpl))
+		if err == nil || !strings.Contains(err.Error(), want) {
+			t.Errorf("compile(%s) = %v, want an error mentioning %q", tmpl, err, want)
+		}
+	}
+}

data-import/geo-se.py

@@ -13,7 +13,6 @@ import os
 import re
 import sys
 import urllib.request
-import xml.etree.ElementTree as ET
 import zipfile
 from pathlib import Path
 
@@ -38,24 +37,9 @@ CACHE = Path(__file__).resolve().parent / "cache"
 TIMEZONE = "Europe/Stockholm"
 ONE_POSITION = {"Stockholm", "Göteborg", "Malmö"}
 UNMATCHED_POPULATION = 200
-XLSX_NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
-
-
-def xlsx_rows(data):
-    z = zipfile.ZipFile(io.BytesIO(data))
-    strings = ["".join(t.text or "" for t in si.iter("{%s}t" % XLSX_NS["m"])) for si in ET.fromstring(z.read("xl/sharedStrings.xml")).findall("m:si", XLSX_NS)]
-    sheet = ET.fromstring(z.read("xl/worksheets/sheet1.xml"))
-    for row in sheet.findall(".//m:row", XLSX_NS):
-        cells = []
-        for c in row.findall("m:c", XLSX_NS):
-            v = c.find("m:v", XLSX_NS)
-            cells.append("" if v is None else strings[int(v.text)] if c.get("t") == "s" else v.text)
-        yield cells
-
-
 def scb_codes(cache):
     regions, municipalities = {}, {}
-    for cells in xlsx_rows(tsv.fetch(CODES, cache, "kommunlankod.xlsx", magic=b"PK")):
+    for cells in tsv.xlsx_rows(tsv.fetch(CODES, cache, "kommunlankod.xlsx", magic=b"PK")):
         if len(cells) < 2 or not re.fullmatch(r"\d{2}|\d{4}", cells[0]):
             continue
         (regions if len(cells[0]) == 2 else municipalities)[cells[0]] = cells[1].strip()

data-import/names-se.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""Rebuild data/sv_SE/first-name.tsv and last-name.tsv from SCB's whole-population name counts (CC0, "Källa: SCB").
+
+    data-import/names-se.py [--source URL_OR_FILE] [--first N] [--last N] [--cache DIR] [--out DIR]
+
+A tilltalsnamn goes under each sex that carries it, so a name both sexes carry has two rows.
+"""
+import argparse
+import re
+from pathlib import Path
+
+import tsv
+
+SOURCE = "https://www.scb.se/contentassets/9fe7dbb460994c72b835163dbc491ef9/namn-med-minst-tva-barare-31-december-2022.xlsx"
+OUT = Path(__file__).resolve().parent.parent / "data" / "sv_SE"
+CACHE = Path(__file__).resolve().parent / "cache"
+SHEETS = {"f": "Tilltalsnamn kvinnor", "m": "Tilltalsnamn män"}
+SURNAMES = "Efternamn"
+NAME = re.compile(r"^[^\W\d_]{2,}([ '-][^\W\d_]{2,})*$")
+PARTICLES = {"af", "av", "de", "den", "der", "di", "du", "la", "le", "van", "von"}
+
+
+def cased(name):
+    """SCB's uppercase name as it is written: each part capitalised, a particle before another part lowercased."""
+    parts = name.lower().split(" ")
+    return " ".join(w if w in PARTICLES and len(parts) > 1 else w.title() for w in parts)
+
+
+def counted(rows, top):
+    """The top names of a sheet by bearers, initials and single letters dropped."""
+    names = [(cells[0], int(cells[1])) for cells in rows if len(cells) >= 2 and cells[1].isdigit() and NAME.match(cells[0])]
+    return sorted(names, key=lambda n: (-n[1], n[0]))[:top]
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--first", type=int, default=2000, help="names per sex")
+    p.add_argument("--last", type=int, default=5000)
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--source", default=SOURCE)
+    a = p.parse_args()
+    data = tsv.fetch(a.source, a.cache, "scb-namn-2022.xlsx", magic=b"PK")
+    first = [{"name": cased(n), "sex": sex, "count": c} for sex, sheet in SHEETS.items() for n, c in counted(tsv.xlsx_rows(data, sheet), a.first)]
+    last = [{"name": cased(n), "count": c} for n, c in counted(tsv.xlsx_rows(data, SURNAMES), a.last)]
+    out = Path(a.out)
+    tsv.write(out / "first-name.tsv", ["name", "sex", "count"], sorted(first, key=lambda r: (r["name"], r["sex"])))
+    tsv.write(out / "last-name.tsv", ["name", "count"], sorted(last, key=lambda r: r["name"]))
+
+
+if __name__ == "__main__":
+    main()

data-import/names-us.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+"""Rebuild data/en_US/first-name.tsv and last-name.tsv from SSA baby names and the Census 2010 surnames (public domain).
+
+    data-import/names-us.py [--names URL_OR_FILE] [--surnames URL_OR_FILE] [--from-year YEAR] [--first N] [--last N] [--cache DIR] [--out DIR]
+
+A given name is counted over the births of --from-year and later, under each sex it was given to, so a
+name both sexes carry has two rows. --names takes SSA's names.zip or a merged name,sex,count,year file;
+--surnames takes the Census names.zip or its Names_2010Census.csv.
+"""
+import argparse
+import collections
+import csv
+import io
+import re
+import zipfile
+from pathlib import Path
+
+import tsv
+
+NAMES = "https://raw.githubusercontent.com/hackerb9/ssa-baby-names/master/alldata.txt"
+SURNAMES = "https://www2.census.gov/topics/genealogy/2010surnames/names.zip"
+OUT = Path(__file__).resolve().parent.parent / "data" / "en_US"
+CACHE = Path(__file__).resolve().parent / "cache"
+MC = re.compile(r"^Mc([a-z])")
+
+
+def csv_rows(data, member):
+    """The rows of a CSV, or of every member of a zip named like member, name,sex,count[,year]."""
+    if data.startswith(b"PK"):
+        z = zipfile.ZipFile(io.BytesIO(data))
+        for n in sorted(z.namelist()):
+            if re.fullmatch(member, n):
+                year = re.sub(r"\D", "", n)
+                for r in csv.reader(io.StringIO(z.read(n).decode("utf-8-sig"))):
+                    yield r + [year] if year else r
+        return
+    yield from csv.reader(io.StringIO(data.decode("utf-8-sig")))
+
+
+def given(data, from_year):
+    counts = collections.Counter()
+    for r in csv_rows(data, r"yob\d{4}\.txt"):
+        if len(r) >= 4 and r[3].isdigit() and int(r[3]) >= from_year:
+            counts[(r[0], r[1].lower())] += int(r[2])
+    return counts
+
+
+def surname(name):
+    """A Census uppercase surname as it is written: capitalised, and Mc before a capital."""
+    return MC.sub(lambda m: "Mc" + m.group(1).upper(), name.title())
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--first", type=int, default=2000, help="names per sex")
+    p.add_argument("--from-year", type=int, default=1930)
+    p.add_argument("--last", type=int, default=5000)
+    p.add_argument("--names", default=NAMES)
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--surnames", default=SURNAMES)
+    a = p.parse_args()
+    counts = given(tsv.fetch(a.names, a.cache, "ssa-names.txt"), a.from_year)
+    first = []
+    for sex in ("f", "m"):
+        top = sorted(((n, c) for (n, s), c in counts.items() if s == sex), key=lambda n: (-n[1], n[0]))[:a.first]
+        first += [{"name": n, "sex": sex, "count": c} for n, c in top]
+    rows = csv_rows(tsv.fetch(a.surnames, a.cache, "census-surnames-2010.zip"), r"Names_2010Census\.csv")
+    last = [{"name": surname(r[0]), "count": int(r[2])} for r in rows if len(r) >= 3 and r[2].isdigit() and r[0].isalpha()]
+    last = sorted(last, key=lambda r: (-r["count"], r["name"]))[:a.last]
+    out = Path(a.out)
+    tsv.write(out / "first-name.tsv", ["name", "sex", "count"], sorted(first, key=lambda r: (r["name"], r["sex"])))
+    tsv.write(out / "last-name.tsv", ["name", "count"], sorted(last, key=lambda r: r["name"]))
+
+
+if __name__ == "__main__":
+    main()

data-import/tsv.py

@@ -1,10 +1,15 @@
 """A source fetched once into the cache, and a table written as the loader admits it."""
+import io
 import re
 import sys
 import time
 import urllib.request
+import xml.etree.ElementTree as ET
+import zipfile
 from pathlib import Path
 
+XLSX_NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main", "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships"}
+
 
 def fetch(source, cache, name, magic=b"", data=None, headers=None):
     """The bytes of a URL, downloaded into cache/name once, or of a local file."""
@@ -28,6 +33,21 @@ def fetch(source, cache, name, magic=b"", data=None, headers=None):
     sys.exit(f"{source}: no valid download in 5 attempts")
 
 
+def xlsx_rows(data, sheet=None):
+    """The rows of an xlsx sheet named sheet, the first sheet by default, each a list of cell texts."""
+    z = zipfile.ZipFile(io.BytesIO(data))
+    strings = ["".join(t.text or "" for t in si.iter("{%s}t" % XLSX_NS["m"])) for si in ET.fromstring(z.read("xl/sharedStrings.xml")).findall("m:si", XLSX_NS)]
+    rels = {r.get("Id"): r.get("Target") for r in ET.fromstring(z.read("xl/_rels/workbook.xml.rels"))}
+    sheets = {s.get("name"): rels[s.get("{%s}id" % XLSX_NS["r"])] for s in ET.fromstring(z.read("xl/workbook.xml")).iter("{%s}sheet" % XLSX_NS["m"])}
+    target = sheets[sheet] if sheet else next(iter(sheets.values()))
+    for row in ET.fromstring(z.read("xl/" + target)).findall(".//m:row", XLSX_NS):
+        cells = []
+        for c in row.findall("m:c", XLSX_NS):
+            v = c.find("m:v", XLSX_NS)
+            cells.append("" if v is None else strings[int(v.text)] if c.get("t") == "s" else v.text)
+        yield cells
+
+
 def write(path, columns, rows):
     """Write the rows as a TSV; every cell must be non-empty and free of tabs, newlines and braces."""
     lines = ["\t".join(columns)]

data/en_US/date.json

@@ -1,13 +1 @@
-{
+"{date(1970-01-01,2029-12-31,'01/02/2006')}"
-  "format": "{month}/{day}/{year}",
-  "month": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"],
-  "day": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28"],
-  "year": [
-    "197{digits(1)}",
-    "198{digits(1)}",
-    { "format": "199{digits(1)}", "weight": 2 },
-    { "format": "200{digits(1)}", "weight": 3 },
-    { "format": "201{digits(1)}", "weight": 3 },
-    { "format": "202{digits(1)}", "weight": 2 }
-  ]
-}

data/en_US/first-name.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "first-name.tsv", "name": "name", "parent": "sex", "weight": "count" }

data/en_US/itin.json

@@ -0,0 +1,15 @@
+{
+  "format": "9{digits(2)}-{group}-{serial}",
+  "group": [
+    { "format": "{int(50,65)}", "weight": 16 },
+    { "format": "{int(70,88)}", "weight": 19 },
+    { "format": "{int(90,92)}", "weight": 3 },
+    { "format": "{int(94,99)}", "weight": 6 }
+  ],
+  "serial": [
+    { "format": "000{int(1,9)}", "weight": 9 },
+    { "format": "00{int(10,99)}", "weight": 90 },
+    { "format": "0{int(100,999)}", "weight": 900 },
+    { "format": "{int(1000,9999)}", "weight": 9000 }
+  ]
+}

data/en_US/last-name.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "last-name.tsv", "key": "name", "weight": "count" }

data/en_US/person.json

@@ -1,7 +1,7 @@
 {
-  "format": "{prefix}{femalefirst|malefirst} {last}",
+  "format": "{prefix}{first} {last}",
-  "femalefirst": ["Abigail", "Addison", "Amelia", "Aria", "Aubrey", "Audrey", "Aurora", "Ava", "Bella", "Brooklyn", "Camila", "Caroline", "Charlotte", "Chloe", "Claire", "Eleanor", "Elizabeth", "Ella", "Ellie", "Emily", "Emma", "Evelyn", "Gianna", "Grace", "Hannah", "Harper", "Hazel", "Isabella", "Layla", "Leah", "Lillian", "Lily", "Lucy", "Luna", "Madison", "Maya", "Mia", "Mila", "Naomi", "Natalie", "Nora", "Olivia", "Paisley", "Penelope", "Riley", "Savannah", "Scarlett", "Sofia", "Sophia", "Stella", "Victoria", "Violet", "Zoe"],
+  "first": "{.first-name.name}",
-  "malefirst": ["Aiden", "Alexander", "Andrew", "Anthony", "Asher", "Benjamin", "Caleb", "Carter", "Charles", "Christopher", "Daniel", "David", "Dylan", "Elijah", "Ethan", "Ezra", "Gabriel", "Grayson", "Henry", "Isaac", "Jack", "Jackson", "Jacob", "James", "Jayden", "John", "Joseph", "Joshua", "Julian", "Levi", "Liam", "Lincoln", "Logan", "Lucas", "Luke", "Mason", "Mateo", "Matthew", "Michael", "Nathan", "Noah", "Oliver", "Owen", "Samuel", "Sebastian", "Theodore", "Thomas", "William", "Wyatt"],
+  "last": "{.last-name.name}",
-  "last": ["Adams", "Allen", "Anderson", "Bailey", "Baker", "Bell", "Bennett", "Brooks", "Brown", "Campbell", "Carter", "Clark", "Collins", "Cook", "Cooper", "Cox", "Davis", "Edwards", "Evans", "Flores", "Foster", "Garcia", "Gonzalez", "Gray", "Green", "Hall", "Harris", "Hayes", "Hernandez", "Hill", "Howard", "Hughes", "Jackson", "James", "Jenkins", "Johnson", "Jones", "Kelly", "King", "Lee", "Lewis", "Long", "Lopez", "Martin", "Martinez", "Miller", "Mitchell", "Moore", "Morgan", "Morris", "Murphy", "Nelson", "Parker", "Perez", "Perry", "Peterson", "Phillips", "Powell", "Price", "Ramirez", "Reed", "Richardson", "Rivera", "Roberts", "Robinson", "Rodriguez", "Rogers", "Ross", "Russell", "Sanchez", "Sanders", "Scott", "Smith", "Stewart", "Sullivan", "Taylor", "Thomas", "Thompson", "Torres", "Turner", "Walker", "Ward", "Watson", "White", "Williams", "Wilson", "Wood", "Wright", "Young"],
+  "prefix": ["", { "format": "{title} ", "title": ["Dr", "Miss", "Mr", "Mrs", "Ms", "Mx", "Prof"], "weight": 0.1 }],
-  "prefix": ["", { "format": "{title} ", "title": ["Dr", "Miss", "Mr", "Mrs", "Ms", "Mx", "Prof"], "weight": 0.1 }]
+  "sex": "{.sex.name}"
 }

data/en_US/sex.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "sex.tsv", "key": "code", "name": "name" }

data/en_US/sex.tsv

@@ -0,0 +1,3 @@
+code	name
+f	female
+m	male

data/en_US/ssn.json

@@ -1 +1,19 @@
-"{int(100,999)}-{digits(2)}-{digits(4)}"
+{
+  "format": "{area}-{group}-{serial}",
+  "area": [
+    { "format": "00{int(1,9)}", "weight": 9 },
+    { "format": "0{int(10,99)}", "weight": 90 },
+    { "format": "{int(100,665)}", "weight": 566 },
+    { "format": "{int(667,899)}", "weight": 233 }
+  ],
+  "group": [
+    { "format": "0{int(1,9)}", "weight": 9 },
+    { "format": "{int(10,99)}", "weight": 90 }
+  ],
+  "serial": [
+    { "format": "000{int(1,9)}", "weight": 9 },
+    { "format": "00{int(10,99)}", "weight": 90 },
+    { "format": "0{int(100,999)}", "weight": 900 },
+    { "format": "{int(1000,9999)}", "weight": 9000 }
+  ]
+}

data/en_US/time.json

@@ -1,6 +1 @@
-{
+"{time('3:04 PM')}"
-  "format": "{hour}:{minute} {ampm}",
-  "hour": ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12"],
-  "minute": { "format": "{t}{digits(1)}", "t": ["0", "1", "2", "3", "4", "5"] },
-  "ampm": ["AM", "PM"]
-}

data/misc/datetime.json

@@ -0,0 +1 @@
+"{date(2000-01-01,2029-12-31,'2006-01-02T15:04:05Z')}"

data/sv_SE/date.json

@@ -1,13 +1 @@
-{
+"{date(1970-01-01,2029-12-31,'2006-01-02')}"
-  "format": "{year}-{month}-{day}",
-  "month": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"],
-  "day": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28"],
-  "year": [
-    "197{digits(1)}",
-    "198{digits(1)}",
-    { "format": "199{digits(1)}", "weight": 2 },
-    { "format": "200{digits(1)}", "weight": 3 },
-    { "format": "201{digits(1)}", "weight": 3 },
-    { "format": "202{digits(1)}", "weight": 2 }
-  ]
-}

data/sv_SE/first-name.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "first-name.tsv", "name": "name", "parent": "sex", "weight": "count" }

data/sv_SE/last-name.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "last-name.tsv", "key": "name", "weight": "count" }

data/sv_SE/person.json

@@ -1,32 +1,7 @@
 {
-  "format": "{prefix}{femalefirst|malefirst} {last}",
+  "format": "{prefix}{first} {last}",
-  "femalefirst": ["Agnes", "Alice", "Alicia", "Alma", "Amanda", "Anna", "Astrid", "Cornelia", "Ebba", "Elin", "Ella", "Ellen", "Elsa", "Emilia", "Emma", "Ester", "Eva", "Frida", "Hanna", "Hedda", "Ida", "Ingrid", "Isabelle", "Julia", "Karin", "Klara", "Kristina", "Lena", "Linnéa", "Lova", "Maja", "Maria", "Moa", "Molly", "Märta", "Nellie", "Nora", "Olivia", "Saga", "Sara", "Selma", "Signe", "Siri", "Sofia", "Stina", "Tilde", "Tuva", "Wilma", "Ylva", "Åsa"],
+  "first": "{.first-name.name}",
-  "malefirst": ["Adam", "Albin", "Alexander", "Alfred", "Anders", "Anton", "Arvid", "Axel", "Bengt", "Bo", "Carl", "David", "Edvin", "Elias", "Emil", "Erik", "Filip", "Folke", "Fredrik", "Gustav", "Göran", "Hampus", "Hans", "Henrik", "Hugo", "Isak", "Johan", "Jonas", "Karl", "Kjell", "Lars", "Leo", "Linus", "Love", "Magnus", "Mats", "Mattias", "Mikael", "Nils", "Olle", "Oskar", "Otto", "Patrik", "Per", "Pontus", "Rasmus", "Samuel", "Sixten", "Stefan", "Sten", "Sven", "Theodor", "Tobias", "Viktor", "William", "Åke"],
+  "last": "{.last-name.name}",
-  "last": [
+  "prefix": ["", { "format": "{string} ", "string": ["dr", "prof"], "weight": 0.05 }],
-    {
+  "sex": "{.sex.name}"
-      "format": "{first}sson",
-      "weight": 5,
-      "first": ["Ander", "Arvid", "Bengt", "Daniel", "David", "Erik", "Fredrik", "Gustaf", "Henrik", "Håkan", "Isak", "Jakob", "Johan", "Jon", "Jön", "Karl", "Lar", "Magnu", "Matt", "Mikael", "Mårten", "Nil", "Ol", "Per", "Petter", "Samuel", "Sven"]
-    },
-    {
-      "format": "{first}{last}",
-      "weight": 3.6,
-      "first": ["Ahl", "Berg", "Blom", "Ceder", "Dahl", "Ek", "Eng", "Falk", "Fors", "Gran", "Hag", "Hed", "Holm", "Lind", "Lund", "Mal", "Ny", "Rosen", "Sand", "Sjö", "Skog", "Söder", "Sten", "Strand", "Sund", "Wik", "Öst"],
-      "last": ["berg", "blad", "crona", "dahl", "ed", "fors", "gren", "holm", "in", "kvist", "löf", "lund", "man", "mark", "qvist", "roth", "stedt", "sten", "strand", "ström", "vall"]
-    },
-    {
-      "format": "{first}{last}",
-      "weight": 0.267,
-      "first": ["Hell", "Wall"],
-      "last": ["berg", "blad", "crona", "dahl", "ed", "fors", "gren", "holm", "in", "kvist", "man", "mark", "qvist", "roth", "stedt", "sten", "strand", "ström", "vall"]
-    },
-    {
-      "format": "{first}{last}",
-      "weight": 0.133,
-      "first": "Norr",
-      "last": ["berg", "blad", "crona", "dahl", "ed", "fors", "gren", "holm", "in", "kvist", "löf", "lund", "man", "mark", "qvist", "stedt", "sten", "strand", "ström", "vall"]
-    },
-    ["Berg", "Blom", "Eismar", "Falk", "Holm", "Lind", "Norberg", "Strand", "Ström", "von Flemming", "Åberg", "Öberg"]
-  ],
-  "prefix": ["", { "format": "{string} ", "string": ["dr", "prof"], "weight": 0.05 }]
 }

data/sv_SE/personnummer.json

@@ -0,0 +1 @@
+"{date(1930-01-01,2025-12-31,'060102')}-{.sex.birth-number}{luhn()}"

data/sv_SE/samordningsnummer.json

@@ -0,0 +1 @@
+"{date(1930-01-01,2025-12-31,'0601')}{int(61,88)}-{.sex.birth-number}{luhn()}"

data/sv_SE/sex.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "sex.tsv", "key": "code", "name": "name" }

data/sv_SE/sex.tsv

@@ -0,0 +1,3 @@
+code	name	birth-number
+f	kvinna	238
+m	man	239

data/sv_SE/ssn.json

@@ -1,22 +0,0 @@
-{
-  "format": "{digits(2)}{mmdd}-{digits(3)}{luhn()}",
-  "mmdd": [
-    {
-      "format": "{m}{d}",
-      "weight": 7,
-      "m": ["01", "03", "05", "07", "08", "10", "12"],
-      "d": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28", "29", "30", "31"]
-    },
-    {
-      "format": "{m}{d}",
-      "weight": 4,
-      "m": ["04", "06", "09", "11"],
-      "d": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28", "29", "30"]
-    },
-    {
-      "format": "{m}{d}",
-      "m": "02",
-      "d": ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25", "26", "27", "28"]
-    }
-  ]
-}

data/sv_SE/time.json

@@ -1,17 +1 @@
-{
+"{time('15:04')}"
-  "format": "{hour}:{minute}{sec}",
-  "hour": [
-    { "format": "0{digits(1)}", "weight": 4 },
-    { "format": "1{digits(1)}", "weight": 4 },
-    { "format": "2{t}", "t": ["0", "1", "2", "3"], "weight": 2 }
-  ],
-  "minute": { "format": "{t}{digits(1)}", "t": ["0", "1", "2", "3", "4", "5"] },
-  "sec": [
-    "",
-    {
-      "format": ":{s}",
-      "s": { "format": "{t}{digits(1)}", "t": ["0", "1", "2", "3", "4", "5"] },
-      "weight": 0.4
-    }
-  ]
-}

data_test.go

@@ -10,7 +10,7 @@ import (
 
 // TestShippedDataCategories asserts every shipped locale emits only well-formed
 // values for each data category. en and sv patterns differ where the format is
-// locale-specific (date, time, ssn, company, price, ...); the rest are shared.
+// locale-specific (date, time, company, price, ...); the rest are shared.
 func TestShippedDataCategories(t *testing.T) {
 	letters := regexp.MustCompile(`^[\pL'-]+$`)
 	semver := regexp.MustCompile(`^v?\d+\.\d+\.\d+(-(alpha|beta|rc)\.\d+)?$`)
@@ -33,10 +33,7 @@ func TestShippedDataCategories(t *testing.T) {
 			regexp.MustCompile(`^\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$`)},
 		{"time",
 			regexp.MustCompile(`^([1-9]|1[0-2]):[0-5]\d (AM|PM)$`),
-			regexp.MustCompile(`^([01]\d|2[0-3]):[0-5]\d(:[0-5]\d)?$`)},
+			regexp.MustCompile(`^([01]\d|2[0-3]):[0-5]\d$`)},
-		{"ssn",
-			regexp.MustCompile(`^[1-9]\d{2}-\d{2}-\d{4}$`),
-			regexp.MustCompile(`^\d{2}(0[1-9]|1[0-2])(0[1-9]|[12]\d|3[01])-\d{4}$`)},
 		{"version", semver, semver},
 		{"email", email, email},
 		{"ip", ip, ip},
@@ -72,7 +69,11 @@ func TestShippedMiscCategories(t *testing.T) {
 	v4 := regexp.MustCompile(`^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$`)
 	mac := regexp.MustCompile(`^([0-9a-f]{2}:){5}[0-9a-f]{2}$`)
 	objectid := regexp.MustCompile(`^[0-9a-f]{24}$`)
+	datetime := regexp.MustCompile(`^\d{4}-\d\d-\d\dT\d\d:\d\d:\d\dZ$`)
 	for i := 0; i < 200; i++ {
+		if v := fake(t, f, "datetime"); !datetime.MatchString(v) {
+			t.Fatalf("misc datetime %q is not an RFC 3339 UTC instant", v)
+		}
 		if v := fake(t, f, "objectid"); !objectid.MatchString(v) {
 			t.Fatalf("misc objectid %q is not 24 hex chars", v)
 		}
@@ -147,30 +148,121 @@ func TestSwedishPersonNamesHaveNoTripleLetter(t *testing.T) {
 	}
 }
 
-// TestSwedishPersonnummer checks the two rules the shape regex can't: the date
+// TestSwedishPersonnummer checks what the shape regex can't: the date is a real
-// is a real calendar date (so month-length variants never emit e.g. Apr 31 or
+// calendar date, the birth number is Skatteverket's test series (238 female, 239
-// Feb 30) and the trailing digit is a valid Luhn checksum over the other nine.
+// male), the trailing digit is a Luhn checksum over the other nine, and a
+// samordningsnummer is the same with 60 added to the day.
 func TestSwedishPersonnummer(t *testing.T) {
 	sv := newGenerator(t, "data", WithSeed(1))
-	sawLongMonthEnd := false
+	re := regexp.MustCompile(`^\d{6}-23[89]\d$`)
+	sawLongMonthEnd, birth := false, map[string]bool{}
 	for i := 0; i < 2000; i++ {
-		v := fake(t, sv, "sv_SE.ssn")
+		v := fake(t, sv, "sv_SE.personnummer")
 		d := digitsOnly(v)
-		if len(d) != 10 {
+		if !re.MatchString(v) {
-			t.Fatalf("ssn %q has %d digits, want 10", v, len(d))
+			t.Fatalf("personnummer %q, want YYMMDD-238C or YYMMDD-239C", v)
 		}
-		if _, err := time.Parse("060102", d[:6]); err != nil { // 2-digit year, real-date check
+		if _, err := time.Parse("060102", d[:6]); err != nil {
-			t.Fatalf("ssn %q is not a valid calendar date: %v", v, err)
+			t.Fatalf("personnummer %q is not a valid calendar date: %v", v, err)
 		}
 		if !luhnValid(d) {
-			t.Fatalf("ssn %q fails the Luhn check", v)
+			t.Fatalf("personnummer %q fails the Luhn check", v)
 		}
-		if d[4:6] == "31" {
+		sawLongMonthEnd = sawLongMonthEnd || d[4:6] == "31"
-			sawLongMonthEnd = true
+		birth[d[6:9]] = true
+		s := fake(t, sv, "sv_SE.samordningsnummer")
+		sd := digitsOnly(s)
+		day, err := strconv.Atoi(sd[4:6])
+		if !re.MatchString(s) || err != nil || day < 61 || day > 88 || !luhnValid(sd) {
+			t.Fatalf("samordningsnummer %q, want YYMM(61-88)-23[89]C, Luhn-valid", s)
+		}
+		if _, err := time.Parse("0601", sd[:4]); err != nil {
+			t.Fatalf("samordningsnummer %q is not a valid year and month: %v", s, err)
 		}
 	}
 	if !sawLongMonthEnd {
-		t.Fatal("never generated a 31st — 31-day months are not reaching their last day")
+		t.Fatal("never generated a 31st")
+	}
+	if !birth["238"] || !birth["239"] {
+		t.Fatalf("birth numbers drawn %v, want both 238 and 239", birth)
+	}
+	for i := 0; i < 200; i++ {
+		got := fakeTemplate(t, sv, `{/sv_SE.person.sex} {/sv_SE.personnummer}`)
+		if f, m := strings.HasPrefix(got, "kvinna ") && got[14:17] == "238", strings.HasPrefix(got, "man ") && got[11:14] == "239"; !f && !m {
+			t.Fatalf("%q: a person and a personnummer in one render disagree on sex", got)
+		}
+	}
+}
+
+// TestShippedUSTaxIds pins the SSA and IRS ranges: an SSN's area is 001-899 but
+// 666, its group 01-99 and its serial 0001-9999; an ITIN is 9XX-GG-XXXX with GG
+// in 50-65, 70-88, 90-92 or 94-99.
+func TestShippedUSTaxIds(t *testing.T) {
+	f := newGenerator(t, "data", WithSeed(5))
+	ssn := regexp.MustCompile(`^(\d{3})-(\d{2})-(\d{4})$`)
+	itin := regexp.MustCompile(`^9\d{2}-(5\d|6[0-5]|7\d|8[0-8]|9[0-24-9])-\d{4}$`)
+	for i := 0; i < 2000; i++ {
+		v := fake(t, f, "en_US.ssn")
+		m := ssn.FindStringSubmatch(v)
+		if m == nil {
+			t.Fatalf("ssn %q, want AAA-GG-SSSS", v)
+		}
+		area, _ := strconv.Atoi(m[1])
+		group, _ := strconv.Atoi(m[2])
+		serial, _ := strconv.Atoi(m[3])
+		if area < 1 || area > 899 || area == 666 || group < 1 || serial < 1 {
+			t.Fatalf("ssn %q is in a range the SSA never assigns", v)
+		}
+		if v := fake(t, f, "en_US.itin"); !itin.MatchString(v) {
+			t.Fatalf("itin %q, want %s", v, itin)
+		}
+	}
+}
+
+// TestShippedPersonNames pins the name tables: a sex pins its first names, a name
+// both sexes carry appears under both, and the record's sex agrees with its name.
+func TestShippedPersonNames(t *testing.T) {
+	f := newGenerator(t, "data", WithSeed(9))
+	for path, want := range map[string]string{
+		"sv_SE.sex[f]":                        "kvinna",
+		"sv_SE.sex[man].code":                 "m",
+		"en_US.sex[f]":                        "female",
+		"sv_SE.sex[f].first-name[Anna]":       "Anna",
+		"sv_SE.sex[m].first-name[Erik].sex":   "m",
+		"en_US.sex[m].first-name[James]":      "James",
+		"en_US.sex[f].first-name[Taylor].sex": "f",
+		"en_US.sex[m].first-name[Taylor].sex": "m",
+		"sv_SE.last-name[Andersson]":          "Andersson",
+		"sv_SE.last-name[Andersson].count":    "",
+		"en_US.last-name[Smith]":              "Smith",
+	} {
+		got := fake(t, f, path)
+		if want == "" && !regexp.MustCompile(`^[1-9]\d*$`).MatchString(got) {
+			t.Errorf("Fake(%q) = %q, want a count", path, got)
+		} else if want != "" && got != want {
+			t.Errorf("Fake(%q) = %q, want %q", path, got, want)
+		}
+	}
+	if _, err := f.Fake("en_US.first-name[Taylor]"); err == nil || !strings.Contains(err.Error(), "sex[f].first-name[Taylor]") {
+		t.Fatalf("Fake(en_US.first-name[Taylor]) = %v, want both sexes' rows listed", err)
+	}
+	for _, locale := range []string{"sv_SE", "en_US"} {
+		seen := map[string]bool{}
+		for i := 0; i < 2000; i++ {
+			seen[fake(t, f, locale+".sex[f].first-name")] = true
+			first, sex := fake(t, f, locale+".person.first"), fake(t, f, locale+".person.sex")
+			if first == "" || sex == "" {
+				t.Fatalf("%s.person lacks a first name or a sex", locale)
+			}
+		}
+		if len(seen) < 300 || !seen["Anna"] && locale == "sv_SE" || !seen["Mary"] && locale == "en_US" {
+			t.Fatalf("%s female first names: %d distinct in 2000, want a weighted register", locale, len(seen))
+		}
+		got := fakeTemplate(t, f, `{/`+locale+`.sex.code}|{/`+locale+`.person.first}`)
+		code, first, _ := strings.Cut(got, "|")
+		if v := fake(t, f, locale+".sex["+code+"].first-name["+first+"]"); v != first {
+			t.Fatalf("%s: %q drawn as a %s name is not one", locale, first, code)
+		}
 	}
 }
 

fejkdata_test.go

@@ -81,3 +81,14 @@ func TestDifferentSeedsDiffer(t *testing.T) {
 	}
 	t.Fatal("seeds 1 and 2 produced identical sequences")
 }
+
+// fakeTemplate renders an inline template against a loaded generator, so its
+// references resolve.
+func fakeTemplate(t *testing.T, f *Generator, s string) string {
+	t.Helper()
+	got, err := f.FakeTemplate(s)
+	if err != nil {
+		t.Fatalf("FakeTemplate(%s) = %v", s, err)
+	}
+	return got
+}

table.go

@@ -222,8 +222,8 @@ func (t *table) bindOptions(o tableOptionValues) error {
 		}
 		*opt.into = i
 	}
-	if t.name >= 0 && t.key < 0 {
+	if t.name >= 0 && t.key < 0 && t.parent < 0 {
-		return fmt.Errorf("name selects a row as a key does, and lists the rows it matches by their keys, so it needs a key column; add key")
+		return fmt.Errorf("name selects a row as a key does, and lists the rows it matches by their keys, so it needs a key column, or a parent inside which each name is one row; add key")
 	}
 	if err := t.indexKeys(); err != nil {
 		return err
@@ -231,9 +231,18 @@ func (t *table) bindOptions(o tableOptionValues) error {
 	return t.sumWeights()
 }
 
-// indexKeys proves every key names one row, and keeps the index a link is proved by.
+// indexKeys proves every key names one row, and keeps the index a link is proved by;
+// without a key, a name names one row inside its parent.
 func (t *table) indexKeys() error {
 	if t.key < 0 {
+		inside := make(map[string]int, t.rows())
+		for r := 0; r < t.rows() && t.name >= 0; r++ {
+			k := t.cell(r, t.parent) + "\t" + t.cell(r, t.name)
+			if first, dup := inside[k]; dup {
+				return fmt.Errorf("%s line %d: name %q repeats line %d inside %s %q; a name selects one row inside its parent", t.file, r+2, t.cell(r, t.name), first+2, t.columns[t.parent], t.cell(r, t.parent))
+			}
+			inside[k] = r
+		}
 		return nil
 	}
 	t.byKey = make(map[string]int, t.rows())
@@ -488,8 +497,8 @@ func (t *table) under(r int, a *table, pr int) bool {
 // find is the row a selector names: by key first, then by name, where a name
 // naming several rows resolves inside the ancestors pinned in d.
 func (t *table) find(sel string, d *draws) (int, error) {
-	if t.key < 0 {
+	if t.key < 0 && t.name < 0 {
-		return 0, fmt.Errorf("%s has no key column to select a row by", t.category)
+		return 0, fmt.Errorf("%s has no key or name column to select a row by", t.category)
 	}
 	if r, ok := t.byKey[sel]; ok {
 		return r, nil
@@ -506,7 +515,14 @@ func (t *table) find(sel string, d *draws) (int, error) {
 	}
 	keys := make([]string, len(rows))
 	for i, r := range rows {
-		keys[i] = t.cell(r, t.key)
+		if t.key < 0 {
+			keys[i] = t.selectorSpelling(r)
+		} else {
+			keys[i] = t.cell(r, t.key)
+		}
+	}
+	if t.key < 0 {
+		return 0, fmt.Errorf("%q names %d rows of %s; select it inside its %s, one of %v", sel, len(rows), t.category, t.parentT.category, keys)
 	}
 	inside := ""
 	if t.parentT != nil {
@@ -515,7 +531,14 @@ func (t *table) find(sel string, d *draws) (int, error) {
 	return 0, fmt.Errorf("%q names %d rows of %s; select one by key, one of %v%s", sel, len(rows), t.category, keys, inside)
 }
 
-// selectorSpelling is how a path writes a selected row, for messages.
+// selectorSpelling is how a path writes a selected row, for messages: by key, or
+// by name inside its parent's row.
 func (t *table) selectorSpelling(r int) string {
-	return t.category + "[" + t.cell(r, t.key) + "]"
+	switch {
+	case t.key >= 0:
+		return t.category + "[" + t.cell(r, t.key) + "]"
+	case t.name >= 0:
+		return t.parentT.selectorSpelling(t.parentRow(r)) + "." + t.category + "[" + t.cell(r, t.name) + "]"
+	}
+	return fmt.Sprintf("%s line %d", t.file, r+2)
 }

table_test.go

@@ -440,6 +440,7 @@ func TestTableFences(t *testing.T) {
 		"a bracket in a key":                             {map[string]string{"t.json": `{"format":"{a}","rows":"t.tsv","key":"a"}`, "t.tsv": "a\nx[1]\ny\n"}, `"["`},
 		"a brace in a name":                              {map[string]string{"t.json": `{"format":"{a}","rows":"t.tsv","key":"a","name":"n"}`, "t.tsv": "a\tn\nx\tx{1}\ny\ty\n"}, `"{"`},
 		"name without a key":                             {map[string]string{"t.json": `{"format":"{a}","rows":"t.tsv","name":"a"}`, "t.tsv": "a\nx\nx\n"}, "key"},
+		"a name repeating inside one parent row":         {with(siblings(), map[string]string{"street.json": `{"format":"{name}","rows":"street.tsv","name":"name","parent":"locality"}`, "street.tsv": "name\tlocality\nAvenyn\tL1\nAvenyn\tL1\nStorgatan\tL2\nStorgatan\tL3\nStorgatan\tL4\nStorgatan\tL5\nStorgatan\tL6\nStorgatan\tL7\nStorgatan\tL8\n"}), `"Avenyn"`},
 		"a name that is another row's key":               {map[string]string{"t.json": `{"format":"{a}","rows":"t.tsv","key":"a","name":"n"}`, "t.tsv": "a\tn\nx\ty\ny\tz\n"}, `"y"`},
 		"a cell reading its family":                      {with(geo(), map[string]string{"locality.tsv": "code\tname\tmunicipality\tnote\nL1\tStockholm\t0180\t{/municipality.code}\nL2\tSolna\t0184\t-\nL3\tMalmö\t1280\t-\nL4\tLund\t1281\t-\nL5\tGöteborg\t1480\t-\n"}), "family"},
 		"a format reading its family":                    {with(geo(), map[string]string{"locality.json": `{"format":"{name} {/region.name}","rows":"locality.tsv","key":"code","name":"name","parent":"municipality"}`}), "family"},
@@ -709,3 +710,37 @@ func TestShippedTables(t *testing.T) {
 		t.Fatalf("country draws %d distinct rows in 5000, want the full register", len(count))
 	}
 }
+
+// TestNamedTableWithoutAKeyResolvesInsideItsParent pins a table whose rows are
+// told apart only by their parent: a name selects a row inside the parent pinned
+// before it, an ambiguous one is listed by its parent's spelling, and a name
+// repeating inside one parent row is a load error (see TestTableFences).
+func TestNamedTableWithoutAKeyResolvesInsideItsParent(t *testing.T) {
+	files := siblings()
+	files["street.json"] = `{"format":"{name}","rows":"street.tsv","name":"name","parent":"locality","weight":"segments"}`
+	f := newGenerator(t, writeFiles(t, files), WithSeed(1))
+	for path, want := range map[string]string{
+		"street[Avenyn]":                                                   "Avenyn",
+		"street[Avenyn].locality":                                          "L5",
+		"locality[L7].street[Sandbyvägen]":                                 "Sandbyvägen",
+		"locality[L7].street[Sandbyvägen].segments":                        "2",
+		"municipality[0184].locality[Sandby].street[Sandbyvägen]":          "Sandbyvägen",
+		"municipality[0184].locality[Sandby].street[Sandbyvägen].locality": "L8",
+	} {
+		if got := fake(t, f, path); got != want {
+			t.Errorf("Fake(%q) = %q, want %q", path, got, want)
+		}
+	}
+	for path, want := range map[string]string{
+		"street[Sandbyvägen]":         "locality[L7].street[Sandbyvägen]",
+		"locality[L1].street[Avenyn]": "not inside",
+		"street[Kungsgatan]":          `"Kungsgatan"`,
+	} {
+		if _, err := f.Fake(path); err == nil || !strings.Contains(err.Error(), want) {
+			t.Errorf("Fake(%q) = %v, want an error mentioning %s", path, err, want)
+		}
+	}
+	if got := fakeTemplate(t, f, `{/locality[L8].name}: {/locality[L8].street[Sandbyvägen].name}`); got != "Sandby: Sandbyvägen" {
+		t.Fatalf("a name selected inside a pinned parent = %q", got)
+	}
+}

template.go

@@ -88,17 +88,28 @@ func funcCall(body string) (name string, args []string, ok bool) {
 	return body[:lp], splitArgs(body[lp+1 : len(body)-1]), true
 }
 
-// splitArgs parses a function arg list: comma-separated outside a selector,
+// splitArgs parses a function arg list: comma-separated outside a selector or a
-// trimmed; empty -> none.
+// quoted layout, trimmed; empty -> none.
 func splitArgs(s string) []string {
 	if strings.TrimSpace(s) == "" {
 		return nil
 	}
-	args := splitOutside(s, ',')
+	var args []string
-	for i := range args {
+	depth, quoted, start := 0, false, 0
-		args[i] = strings.TrimSpace(args[i])
+	for i := 0; i < len(s); i++ {
+		switch c := s[i]; {
+		case c == '\'':
+			quoted = !quoted
+		case quoted:
+		case c == '[':
+			depth++
+		case c == ']' && depth > 0:
+			depth--
+		case c == ',' && depth == 0:
+			args, start = append(args, strings.TrimSpace(s[start:i])), i+1
+		}
 	}
-	return args
+	return append(args, strings.TrimSpace(s[start:]))
 }
 
 // checkFunc validates a function token at compile time: well-formed, naming a

testdata/shipped_shape.txt

@@ -8,20 +8,27 @@ en_US.color
 en_US.company	format "{base} {suffix}"
 en_US.company.base	string
 en_US.company.suffix	string
-en_US.date	format "{month}/{day}/{year}"
+en_US.date	format "{date(1970-01-01,2029-12-31,'01/02/2006')}"
-en_US.date.day	string
-en_US.date.month	string
-en_US.date.year	string
 en_US.email	format "{local}@{domain}"
 en_US.email.domain	string
 en_US.email.local	string
 en_US.email.local.n
+en_US.first-name	format "{name}"	name name	weight count	parent sex
+en_US.first-name.count	string
+en_US.first-name.name	string
+en_US.first-name.sex	string
 en_US.ip
-en_US.person	format "{prefix}{femalefirst|malefirst} {last}"
+en_US.itin	format "9{digits(2)}-{group}-{serial}"
-en_US.person.femalefirst	string
+en_US.itin.group	string
+en_US.itin.serial	string
+en_US.last-name	format "{name}"	key name	weight count
+en_US.last-name.count	string
+en_US.last-name.name	string
+en_US.person	format "{prefix}{first} {last}"	reads en_US.first-name en_US.last-name en_US.sex
+en_US.person.first	string
 en_US.person.last	string
-en_US.person.malefirst	string
 en_US.person.prefix	string
+en_US.person.sex	string
 en_US.phone
 en_US.phone.area
 en_US.phone.exch
@@ -34,12 +41,18 @@ en_US.sentence.adj
 en_US.sentence.noun
 en_US.sentence.prep
 en_US.sentence.verb
-en_US.ssn	format "{int(100,999)}-{digits(2)}-{digits(4)}"
+en_US.sex	format "{name}"	key code	name name
-en_US.time	format "{hour}:{minute} {ampm}"
+en_US.sex.code	string
-en_US.time.ampm	string
+en_US.sex.first-name
-en_US.time.hour	string
+en_US.sex.first-name.count
-en_US.time.minute	string
+en_US.sex.first-name.name
-en_US.time.minute.t
+en_US.sex.first-name.sex
+en_US.sex.name	string
+en_US.ssn	format "{area}-{group}-{serial}"
+en_US.ssn.area	string
+en_US.ssn.group	string
+en_US.ssn.serial	string
+en_US.time	format "{time('3:04 PM')}"
 en_US.url	format "https://{host}{path}"
 en_US.url.host	string
 en_US.url.path	string
@@ -216,6 +229,7 @@ misc.currency.decimals	string
 misc.currency.name	string
 misc.currency.numeric	string
 misc.currency.symbol	string
+misc.datetime	format "{date(2000-01-01,2029-12-31,'2006-01-02T15:04:05Z')}"
 misc.emoji
 misc.httpstatus	format "{code} {reason}"	key code	name reason
 misc.httpstatus.code	string
@@ -241,20 +255,25 @@ sv_SE.color
 sv_SE.company	format "{base} {suffix}"
 sv_SE.company.base	string
 sv_SE.company.suffix	string
-sv_SE.date	format "{year}-{month}-{day}"
+sv_SE.date	format "{date(1970-01-01,2029-12-31,'2006-01-02')}"
-sv_SE.date.day	string
-sv_SE.date.month	string
-sv_SE.date.year	string
 sv_SE.email	format "{local}@{domain}"
 sv_SE.email.domain	string
 sv_SE.email.local	string
 sv_SE.email.local.n
+sv_SE.first-name	format "{name}"	name name	weight count	parent sex
+sv_SE.first-name.count	string
+sv_SE.first-name.name	string
+sv_SE.first-name.sex	string
 sv_SE.ip
-sv_SE.person	format "{prefix}{femalefirst|malefirst} {last}"
+sv_SE.last-name	format "{name}"	key name	weight count
-sv_SE.person.femalefirst	string
+sv_SE.last-name.count	string
+sv_SE.last-name.name	string
+sv_SE.person	format "{prefix}{first} {last}"	reads sv_SE.first-name sv_SE.last-name sv_SE.sex
+sv_SE.person.first	string
 sv_SE.person.last	string
-sv_SE.person.malefirst	string
 sv_SE.person.prefix	string
+sv_SE.person.sex	string
+sv_SE.personnummer	format "{date(1930-01-01,2025-12-31,'060102')}-{.sex.birth-number}{luhn()}"	reads sv_SE.sex
 sv_SE.phone
 sv_SE.phone.a
 sv_SE.phone.b
@@ -263,20 +282,21 @@ sv_SE.phone.prefix
 sv_SE.price	format "{amt}{ore} kr"
 sv_SE.price.amt	string
 sv_SE.price.ore	string
+sv_SE.samordningsnummer	format "{date(1930-01-01,2025-12-31,'0601')}{int(61,88)}-{.sex.birth-number}{luhn()}"	reads sv_SE.sex
 sv_SE.sentence
 sv_SE.sentence.adj
 sv_SE.sentence.noun
 sv_SE.sentence.prep
 sv_SE.sentence.verb
-sv_SE.ssn	format "{digits(2)}{mmdd}-{digits(3)}{luhn()}"
+sv_SE.sex	format "{name}"	key code	name name
-sv_SE.ssn.mmdd	string
+sv_SE.sex.birth-number	string
-sv_SE.ssn.mmdd.d
+sv_SE.sex.code	string
-sv_SE.ssn.mmdd.m
+sv_SE.sex.first-name
-sv_SE.time	format "{hour}:{minute}{sec}"
+sv_SE.sex.first-name.count
-sv_SE.time.hour	string
+sv_SE.sex.first-name.name
-sv_SE.time.minute	string
+sv_SE.sex.first-name.sex
-sv_SE.time.minute.t
+sv_SE.sex.name	string
-sv_SE.time.sec	string
+sv_SE.time	format "{time('15:04')}"
 sv_SE.url	format "https://{host}{path}"
 sv_SE.url.host	string
 sv_SE.url.path	string

todo.md

@@ -42,7 +42,7 @@ value is composed; TSV says which values exist.
   and a `data-import/` directory of Python scripts that rebuild each TSV from its
   source, so a refresh is one command per dataset.
 - Make every shipped category a record with its building blocks as columns
-  (`sv_SE.person` → `femalefirst`, `malefirst`; `misc.uuid` → `variant`).
+  (`sv_SE.person` → `first`, `last`, `sex`, done in step 3; `misc.uuid` → `variant`).
 - Share the handle lists between `email.local` and `username` only if that is a
   clean win — a reference between shipped categories is a major once tagged.
 
@@ -75,9 +75,8 @@ countries; the README maps each to the native term.
 
 #### Builtins the data cannot express
 
-- `{date(from,to,layout)}`: a date in `[from, to]` in a Go layout, and `{age(min,max)}`
+- `{date(from,to,'layout')}` and `{time('layout')}` shipped in step 3; `age()` is
-  as the birthdate spelling; `{time(layout)}`. Personnummer, SSN, birthdate, card
+  rejected, README Decisions. Add a `unix` layout once something needs it.
-  expiry, unix time and ISO datetime all build on it.
 - Derivations: `{isin()}` (Luhn over letters expanded to digits), `{cusip()}`,
   `{aba()}` (3-7-1 weights), `{vin()}` (position 9 over the whole; a sample taking
   the WMI, since the check sits mid-string).
@@ -165,7 +164,9 @@ address, phone, national id, company and date names each.
 1. Table node, key and name selection, parent links, consistent draws, the
    choice-of-rows fence, `DATA-LICENSES.md`, `data-import/` — done.
 2. `geo/SE` and `geo/US`, and `address` in both locales on top of them — done.
-3. Weighted person names and valid ids in both locales; `date()`.
+3. Weighted person names and valid ids in both locales; `date()` — done. Middle
+   names wait for a draw group that shares its family's pins, so a second name
+   is drawn under the same sex.
 4. `misc` conversions and the new `misc` tables.
 5. The remaining locale categories: company, phone, finance, vehicle, words.
 6. Records with building-block columns across the shipped set; shape re-pin.