Rank understanding the code second, and say why it is not an afterthought

.gitignore

@@ -1,3 +1,4 @@
 .claude
 *.out
-__pycache__/
+__pycache__/
+data-import/cache/

AGENTS.md

@@ -1,11 +1,27 @@
 # Rules
 
-- Go runs only through `docker compose run --rm <test|vet|fmt|build>`; the merge gate is `docker build .` plus CI's changelog check.
+- Go runs only through `docker compose run --rm <test|vet|fmt|build|cyclo>`; the merge gate is `docker build .` plus CI's changelog check.
 - Tests first, in their own commit; the implementation follows in the next. A re-pin of seeded output or of `testdata/shipped_shape.txt` is its own commit.
 - A change under `data/` or to the shape pin adds its `CHANGELOG.md` entry under `Unreleased` in the same PR, and so does a change to a flag, an exit code, an exported name, a fence, a builtin or the lowest Go; what is major is the README's Versioning table.
 - One-line commit messages: no ticket prefix, no repo name, no authorship trailers.
+- Merges are fast-forward only, which `tea pr merge` cannot spell — every style it
+  offers fails with "is it still open?", as does a merge whose required checks are
+  still pending, so read the checks before believing the style is the problem. Use
+  `tea api /repos/{owner}/{repo}/pulls/<n>/merge -f Do=fast-forward-only`.
+- Gitea queues Actions runs that `/repos/{owner}/{repo}/actions/tasks` does not
+  list, so an empty task list says nothing about whether CI ran; read
+  `/repos/{owner}/{repo}/commits/<sha>/status`.
+- README goal 2 is gated at 7.0 on the `comprehension-panel` skill, and below it
+  nothing else merges — no feature, no category, no data — bar a security fix and a
+  dependency bump. `todo.md` carries the round: the nine-seat findings run at depth 1,
+  a PR per item it names, then the run again, until the score passes. At or above 7.0
+  every pull request scores with the four-seat run and answers it in one run. No merge
+  lowers the last score.
 - Hard tabs. No comment by default; delete a restatement, a rationale, history, or a file preamble.
 - One spelling per result: reject the other at `New`, and let the error name the spelling to use.
 - A standing choice a reader would relitigate goes under Decisions in the README, not in a comment.
+- Prose naming a source states what that source states: read the register's own field
+  before paraphrasing it, and name the register you read before claiming none
+  publishes a spelling.
 - A README example is a `json` block that loads and renders as a category; `readme_test.go` runs every one.
-- Cyclomatic complexity is gated at 14: the table-shaped dispatches (`eachToken`, `calc.factor`, `walkPath`) sit at 13–14 and stay whole; anything else that reaches 14 is decomposed.
+- Cyclomatic complexity is gated at 14: the table-shaped dispatches (`linkParent`, `compileTemplate`, `renderEdges`) sit at it and stay whole; a function that would pass it is decomposed.

CHANGELOG.md

@@ -11,18 +11,82 @@ replacement, and each removed path, column or flag.
 - First release: the CLI, the library and the shipped data set.
 - Table categories: a category JSON naming a `rows` TSV beside it, with the options
   `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
+  `misc.territory[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.
 - `New` refuses a root choice of templates sharing one format and one set of string
   fields, naming the rows TSV to write instead.
-- `misc.country`, `misc.currency`, `misc.language`, `misc.httpstatus` and
+- `misc.territory`, `misc.currency`, `misc.language`, `misc.httpstatus` and
-  `misc.mimetype` are tables. `misc.country` is every ISO 3166 country that has a
+  `misc.mimetype` are tables. `misc.territory` is every ISO 3166-1 territory that has
-  capital, a currency and a TLD, with the columns `calling-code`, `capital`,
+  a capital, a currency and a TLD, with the columns `calling-code`, `capital`,
-  `currency`, `flag`, `languages`, `numeric` and `tld` added; `misc.currency` the
+  `country`, `currency`, `flag`, `languages`, `numeric` and `tld` added, `country`
+  holding the alpha-2 code of the sovereign state it belongs to and its own where it
+  is one; `misc.currency` the
   current ISO 4217 currencies with a minor unit, with `decimals` and `numeric`
-  added, and its symbols from CLDR. `DATA-LICENSES.md` lists each source.
+  added, and its symbols from CLDR; `misc.language` every ISO 639-2 entry carrying a
+  639-1 code, with a `code3` column holding its 639-2/T code; `misc.httpstatus` each
+  code the IANA registry lists with a plain reason phrase; and `misc.mimetype` each
+  type mime-db records as IANA-registered and gives a filename extension.
+  `DATA-LICENSES.md` lists each source.
+- `misc.timezone`, `misc.car` and `misc.useragent` are tables too. `misc.timezone`
+  is every zone tzdb `zone.tab` gives a shipped territory, with `offset` holding the
+  zone's standard UTC offset and `territory` linking to `misc.territory`, so
+  `misc.territory[SE].timezone` draws `Europe/Stockholm`; zones of a territory
+  `misc.territory` does not ship, Antarctica's among them, and the constant `UTC`
+  are gone; spell that one as the text `"UTC"`. A `weight` column carries the
+  population GeoNames records in each zone, so a draw favours the zones people live
+  in. `misc.useragent` is the top-user-agents desktop and mobile lists with `browser`,
+  `device` and `os` columns. `misc.car` keeps its makes and models in a `make` and a
+  `model` column.
+- `misc.httpmethod`, `misc.protocol` and `misc.port` are IANA's registries as tables.
+  `misc.httpmethod` is the eight methods RFC 9110 defines and PATCH, carrying
+  `safe` and `idempotent` as `true` or `false`; `misc.protocol` the keyword, its
+  `number` and its `name`, selectable by either; `misc.port` renders a TCP port number,
+  with the IANA `service` name beside it, keeping the first service the registry
+  describes for a port so a number selects one row.
+- `misc.tld` is the IANA root zone as a table: every delegated TLD keyed with its
+  leading dot, `.se` and `.xn--p1ai`, the register's `type` beside it, and a `unicode`
+  column holding the form the register displays, so `misc.tld[.рф]` selects the row
+  `.xn--p1ai` renders. A delegation the register marks "Not assigned" does not ship.
+- `misc.loglevel` is the eight syslog severities: the `keyword` a configuration writes,
+  `err` and `info`, keyed by the numerical `code` a PRI encodes and selectable by
+  either, with the `severity` RFC 5424 spells beside it.
+- `geo.SE` and `geo.US`: five linked tables per country, `region`, `municipality`,
+  `locality`, `postal-code` and `street`, weighted by population and address counts
+  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`.
+- `{date(from,to,'layout')}` and `{time('layout')}`: a second between two days, or
+  within one, in a single-quoted Go layout, drawn in UTC; `from` may equal `to`.
+  `sv_SE.date`, `en_US.date`, `sv_SE.time` and `en_US.time` render through them, so
+  `date.year`, `date.month`, `date.day`, `time.hour`, `time.minute`, `time.minute.t`,
+  `time.sec` and `time.ampm` are no longer paths — a part of a date is now its own
+  `{date(…,'2006')}`. `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`; `person.femalefirst` and `person.malefirst` are
+  no longer paths — draw `sex[f].first-name` and `sex[m].first-name` instead.
+  `en_US.title` links to `sex` as well, so `en_US.person.prefix` draws `Mr` or `Ms`
+  without contradicting the record's `sex`; `sv_SE.title` is an unsexed table of the
+  same shape.
+- `sv_SE.personnummer` and `sv_SE.samordningsnummer`, Skatteverket's test series
+  from a `sv_SE.birth-number` table under `sex`, in place of `sv_SE.ssn`, whose
+  `ssn.mmdd`, `ssn.mmdd.m` and `ssn.mmdd.d` go with it. `en_US.ssn` now draws the
+  ranges the SSA assigns and carries the columns `area`, `group` and `serial`, so
+  `--format csv en_US.ssn` writes a header where it used to fail; `en_US.itin` is new
+  and carries the same three. `person.prefix` is null where a person has no title,
+  where it used to be an empty string, so `--format sql` writes `NULL` and a `string`
+  struct field reading it becomes `*string`.
+- `ErrNoColumns` is exported, so a caller can tell the one record fence a path can
+  answer from the rest.
+- An error names a spelling that runs: a layout is named single-quoted and free of
+  its own quotes, a row of a table with no key is named as the path that selects it,
+  `sv_SE.sex[f].first-name[Kim]`, and a category with no columns names the record
+  that gives it one.

DATA-LICENSES.md

@@ -1,14 +1,31 @@
 # Data licenses
 
 Every shipped dataset, its source, its licence and the attribution it asks for. A
-`data-import/` script rebuilds each sourced table; a curated one is hand-written.
+`data-import/` script rebuilds each sourced table, run as the README's
+[Development](README.md#development) section says; a curated one is hand-written.
 
 | Table | Source | Licence | Attribution | Rebuild |
 |-------|--------|---------|-------------|---------|
-| `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` |
+| `geo/SE/locality.tsv`, `postal-code.tsv` | [GeoNames](https://www.geonames.org/) postal codes for SE; populations from SCB tätorter 2023 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); CC0 1.0 | "Postal codes from GeoNames, www.geonames.org" | `data-import/geo-se.py` |
+| `geo/SE/region.tsv`, `municipality.tsv` | [SCB](https://www.scb.se/) län and kommun codes 2026 and population 2024 | [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/) | none required | `data-import/geo-se.py` |
+| `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`, `sv_SE/birth-number.tsv`, `sv_SE/title.tsv`, `en_US/sex.tsv`, `en_US/title.tsv`, `misc/car.tsv` | curated; Skatteverket's test birth numbers are facts, and `car.tsv` waits for an international source (goal 12) | — | — | — |
 | `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) | — | — | — |
+| `misc/httpmethod.tsv` | [IANA HTTP Method Registry](https://www.iana.org/assignments/http-methods/) | [public domain](https://www.iana.org/help/licensing-terms) | none required | `data-import/httpmethod.py` |
-| `misc/language.tsv` | curated (ISO 639-1 codes are facts) | — | — | — |
+| `misc/httpstatus.tsv` | [IANA HTTP Status Code Registry](https://www.iana.org/assignments/http-status-codes/) | [public domain](https://www.iana.org/help/licensing-terms) | none required | `data-import/httpstatus.py` |
-| `misc/mimetype.tsv` | curated (IANA media types are facts) | — | — | — |
+| `misc/language.tsv` | [datasets/language-codes](https://github.com/datasets/language-codes), the [Library of Congress](https://www.loc.gov/standards/iso639-2/) ISO 639-2 register | [PDDL 1.0](https://opendatacommons.org/licenses/pddl/1-0/) | none required | `data-import/language.py` |
+| `misc/loglevel.tsv` | [RFC 5424](https://www.rfc-editor.org/rfc/rfc5424.txt) Table 2, the syslog message severities; keywords from the [POSIX](https://pubs.opengroup.org/onlinepubs/9799919799/basedefs/syslog.h.html) `<syslog.h>` severity macros | facts | none required | `data-import/loglevel.py` |
+| `misc/mimetype.tsv` | [mime-db](https://github.com/jshttp/mime-db), the IANA media type registry with filename extensions | [MIT](https://github.com/jshttp/mime-db/blob/master/LICENSE) | "Copyright (c) 2014 Jonathan Ong, Copyright (c) 2015-2022 Douglas Christopher Wilson" | `data-import/mimetype.py` |
+| `misc/port.tsv` | [IANA Service Name and Transport Protocol Port Number Registry](https://www.iana.org/assignments/service-names-port-numbers/) | [public domain](https://www.iana.org/help/licensing-terms) | none required | `data-import/port.py` |
+| `misc/protocol.tsv` | [IANA Protocol Numbers](https://www.iana.org/assignments/protocol-numbers/) | [public domain](https://www.iana.org/help/licensing-terms) | none required | `data-import/protocol.py` |
+| `misc/territory.tsv` | [datasets/country-codes](https://github.com/datasets/country-codes) | [PDDL 1.0](https://opendatacommons.org/licenses/pddl/1-0/) | none required | `data-import/territory.py` |
+| `misc/timezone.tsv` | [IANA tzdb](https://www.iana.org/time-zones) 2026d `zone.tab` and the standard offset of each zone; weights from [GeoNames](https://www.geonames.org/) `cities15000` populations | [public domain](https://data.iana.org/time-zones/tzdb/LICENSE); [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) | "Populations from GeoNames, www.geonames.org" | `data-import/timezone.py` |
+| `misc/tld.tsv` | [IANA Root Zone Database](https://www.iana.org/domains/root/db), checked against the root zone's [TLD list](https://data.iana.org/TLD/tlds-alpha-by-domain.txt) | [public domain](https://www.iana.org/help/licensing-terms) | none required | `data-import/tld.py` |
+| `misc/useragent.tsv` | [top-user-agents](https://github.com/microlinkhq/top-user-agents) desktop and mobile lists | [MIT](https://github.com/microlinkhq/top-user-agents/blob/master/LICENSE.md) | "Copyright © 2020 Kiko Beats" | `data-import/useragent.py` |
 
-Every other category is hand-written JSON under [`data/`](data), MIT like the code.
+Every other category is hand-written under [`data/`](data), MIT like the code.

README.md

@@ -17,10 +17,12 @@ fejkdata sv_SE.person.last                     # Eriksson
 fejkdata --seed 42 sv_SE.address               # the same address every run
 fejkdata -n 3 --separator ', ' sv_SE.word      # nät, barn, sol
 fejkdata --list                                # every path the data offers
-fejkdata 'misc.country[SE].capital'            # Stockholm — a table's row, selected by key or name
+fejkdata 'misc.territory[SE].capital'          # Stockholm — a table's row, selected by key or name
+fejkdata 'geo.SE.locality[Lund].street'        # Fjelievägen — a linked table, drawn inside the row
 fejkdata --data-path ./mydata sv_SE.word       # layer a directory over the shipped data
 fejkdata --no-shipped-data -d ./mydata --list  # only your data
 fejkdata 'name: {/sv_SE.person.last}'          # name: <a surname> — an inline template
+fejkdata "{date(1990-01-01,2010-12-31,'2006-01-02')}"  # 2003-11-27 — the argument in "…", the layout in '…'
 fejkdata '{"format":"name: {x}","x":["bosse","lina"]}'  # name: bosse or name: lina
 ```
 
@@ -31,11 +33,9 @@ a JSON object, array or string, or that carries a `{` token, is instead an
 **inline template**: a format string or a JSON value compiled and rendered on the
 spot. Its tokens reach the data by reference from the root —
 `{/sv_SE.person.last}`, so shipped and `--data-path` categories are alike
-available. An inline template sits in no folder, so the folder-relative `{.name}`
+available. A path never contains a brace or a quote, and a bracket only as a selector
-and `{..name}` are rejected naming the root spelling, and one reference alone —
+after a name, so the two spellings cannot collide; which spellings an inline template
-`{/sv_SE.person}` — is the path written as a template, rejected naming the path, as is
+rejects, and what each names instead, is under [Decisions](#decisions).
-a path written `/sv_SE.person`. A path never contains a brace or a quote, and a
-bracket only as a selector after a name, so the two cannot collide (see [Decisions](#decisions)).
 
 | Flag | |
 |------|--|
@@ -113,6 +113,12 @@ the template itself, which composes the format into one string rather than
 projecting columns — ask for more records with `--repeat`. A `repeat` on a column
 is fine.
 
+Columns are written in name order, whatever order the fields appear in. A category
+whose fields are the parts of one value — `sv_SE.price`, `sv_SE.version`, `misc.uuid` —
+projects those parts rather than the value, so for one column holding what `Fake`
+renders, write `{"format":"","price":"{/sv_SE.price}"}` as a fieldless category asks
+for.
+
 A column carrying a newline keeps it inside the quoted CSV field or the SQL string
 literal, so a row can span physical lines: read the stream with a CSV or SQL
 parser rather than splitting it on newlines.
@@ -140,6 +146,119 @@ a value two fields share in its own category and reference that. A field hold, t
 operand ties fields together within one column as always (see
 [Correlated fields](#correlated-fields) and [Decisions](#decisions)).
 
+## Data
+
+The shipped set under [`data/`](data) — one folder per locale (`en_US`, `sv_SE`)
+plus a locale-neutral `misc` folder — is embedded, so the CLI and the library
+work with no data on disk. A directory is a namespace: each JSON file is a
+category named after the file, each subdirectory a dot-path segment, so
+`mydata/sv_SE/person.json` is `sv_SE.person` and replaces the shipped one.
+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`, `first-name`,
+`ip`, `last-name`, `person`, `phone`, `price`, `sentence`, `sex`, `time`, `url`,
+`username`, `version` and `word`, formatted per locale; `sv_SE` adds
+`personnummer` and `samordningsnummer`, `en_US` adds `ssn` and `itin`. `misc`
+carries `car`, `coordinate`, `creditcard` (Luhn-valid), `currency` (ISO 4217),
+`datetime` (RFC 3339), `emoji`, `httpmethod`, `httpstatus`, `language` (ISO 639-1,
+with its 639-2/T code), `loglevel` (syslog severity), `mac`, `mimetype`, `objectid`,
+`port`, `protocol`, `territory` (ISO 3166-1), `timezone` (IANA), `tld` (IANA root
+zone), `useragent` and `uuid` (v4). Many carry sub-fields — `misc.currency.symbol`,
+`misc.territory.alpha2`, `misc.httpstatus.code` — which `--list` shows. `car`,
+`currency`, `httpmethod`, `httpstatus`, `language`, `loglevel`, `mimetype`, `port`,
+`protocol`, `territory`, `timezone`, `tld` and `useragent` are [tables](#table), so
+`misc.territory[SE].capital` and `misc.currency[Euro].symbol` select a row; `car` and
+`useragent` carry no key or name, so they are drawn from rather than selected in.
+
+`misc.httpmethod`, `misc.protocol` and `misc.port` are IANA's registries.
+`misc.httpmethod` is the eight methods RFC 9110 defines and PATCH; the register's
+other entries, WebDAV and DeltaV among them, do not ship. Its `safe` and
+`idempotent` are `true` or `false`, so a Go `bool` reads them, though `--format json`
+and `sql` write them as text, a table column carrying no datatype. `misc.protocol`
+carries a `number` and a `name`, the keyword itself where the register spells none out,
+and selects by either spelling.
+`misc.port` is the TCP assignments, rendering the number a port field holds with the
+IANA `service` beside it, and selecting by number alone. A draw spans the whole
+register, so pin `misc.port[443]` where a fixture needs a port a reader recognises;
+it stops at 49150, IANA assigning nothing above, so an ephemeral source port is
+`{int(49152,65535)}`.
+`misc.tld` is the root zone's delegated TLDs, keyed with the leading dot
+`misc.territory.tld` already carries, `.se`. Its `type` is the register's —
+`country-code`, `generic`, `generic-restricted`, `infrastructure` or `sponsored` — and
+its `unicode` the form the register displays, `.рф` for `.xn--p1ai` and the key itself
+for an ASCII one, which selects the row too, so `misc.tld[.рф]` renders `.xn--p1ai`. A
+draw spans the whole zone, `.arpa` and `.zuerich` alike, so pin `misc.tld[.com]` where
+a fixture needs one a reader recognises.
+`misc.loglevel` is the eight syslog severities, rendering the keyword a configuration
+writes, `err` and `info`, keyed by the numerical code a PRI encodes and selectable by
+either, so `misc.loglevel[3]` and `misc.loglevel[err]` are one row.
+`misc.loglevel.severity` is the name RFC 5424 spells, `Error` beside `err`; it
+selects nothing, the code and the keyword do.
+[`DATA-LICENSES.md`](DATA-LICENSES.md) names each table's source and licence.
+
+`misc.timezone` is every zone tzdb gives a shipped territory, from one apiece for most
+of them to dozens for the largest, weighted by the population GeoNames records in each,
+so `misc.territory[US].timezone` draws `America/New_York` far more often than
+`America/Nome`. It links to `misc.territory`, so `misc.territory[SE].timezone` is
+`Europe/Stockholm` and a drawn territory and zone agree. Its `offset` is the zone's
+*standard* offset, so do not pair it with a drawn `misc.datetime`: in a zone that
+observes DST it is the wrong one half the year, which is what storing a zone name
+avoids. A zone tzdb named recently — `Europe/Kyiv`, `America/Ciudad_Juarez` — is
+rejected outright by a consumer resolving it against older tzdata, so where the
+consumer validates the zone, pin one rather than draw it. There is no `UTC` row, tzdb
+giving that name no territory — spell it as the text `"UTC"`. `misc.useragent` carries
+`browser`, `device` and `os` beside the string, and `misc.car` a `make` and a `model`,
+until an international source replaces them.
+
+ISO 3166-1 codes territories, not sovereign states, so that is what the table is
+called: Greenland and Åland have codes of their own, and `misc.territory.country`
+names the state each belongs to — `DK` for Greenland, `FI` for Åland, and its own
+code for a sovereign one, or for one the register names no state for.
+
+`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, `sv_SE.birth-number`
+under `sex`, is Skatteverket's test series, 238 for a woman and 239 for a man, which no
+real person is ever given. `en_US.title` links to `sex` too, so a person's prefix
+never contradicts it.
+
+A person of a chosen sex is assembled from the tables — `sex[f].first-name` beside
+`last-name` — while a shipped `personnummer` agrees with the sex its own render
+*drew*, not with one a path selects. That test series is also small: a personnummer
+is one of about 70,000 values, a day in 1930–2025 against the two birth numbers, so a
+fixture past a few hundred rows repeats one and a `UNIQUE` column needs a category of
+your own. `sv_SE.date` and `en_US.date` are uniform over 1970-01-01 to 2029-12-31,
+`misc.datetime` over 2000-01-01 to 2029-12-31. What the two locales do not share:
+`en_US.address` carries a `region` column the Swedish one has no use for, and
+`sv_SE.title` has no `parent`, so it is selected as `sv_SE.title[dr]` rather than
+inside a sex.
+
+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.
+
+| Table | `geo.SE` | `geo.US` | Weight |
+|-------|----------|----------|--------|
+| `region` | län, by code or name | state, by USPS abbreviation or name; `code` is the FIPS code | population |
+| `municipality` | kommun, by code or name | county, by FIPS code or name | population |
+| `locality` | postort, by name | incorporated place of 25,000 people or more with a postal code of its own, by GEOID or name; Hawaii has none | tätort population, the kommun's where the postort names it, else 200; place population |
+| `postal-code` | postnummer with street delivery, by code | ZCTA, by code | one; address ranges |
+| `street` | gatunamn, the ten with most road segments per postort | street name, the ten with most address ranges per place | segments; address ranges |
+
+`geo.SE.region[Skåne län].municipality` draws a kommun in Skåne,
+`geo.SE.locality[Lund].street` a street in Lund, and
+`geo.US.region[IL].locality[Springfield]` settles which Springfield. A region row
+carries its `timezone`, the state's predominant zone, and a locality its `lat` and
+`lon`. What ports across countries is the five table names, the `name` column,
+selection by name, and the `address` record's columns `street`, `street-number`,
+`postal-code` and `locality`; every other column is the country's own, `code` on a
+Swedish region but `abbr` on a US one.
+
 ## Library
 
 ```sh
@@ -151,7 +270,7 @@ f, err := fejkdata.New(fejkdata.WithSeed(42))
 if err != nil {
 	log.Fatal(err)
 }
-v, err := f.Fake("sv_SE.address") // "Kungsvägen 68\n379 17 Stockholm"
+v, err := f.Fake("sv_SE.address") // "Järvedsvägen 43\n891 77 Järved"
 paths := f.List()                  // every path Fake accepts, sorted
 v, err = f.FakeTemplate("name: {/sv_SE.person.last}")      // compile + render in one call
 t, err := f.NewTemplate(`{"format":"name: {x}","x":["bosse","lina"]}`) // compile once
@@ -205,28 +324,6 @@ A `*Generator` is safe for concurrent use; a seeded sequence is reproducible onl
 when drawn from one goroutine. Changing how a value is composed shifts the seeded
 stream for that value and everything drawn after it.
 
-## Data
-
-The shipped set under [`data/`](data) — one folder per locale (`en_US`, `sv_SE`)
-plus a locale-neutral `misc` folder — is embedded, so the CLI and the library
-work with no data on disk. A directory is a namespace: each JSON file is a
-category named after the file, each subdirectory a dot-path segment, so
-`mydata/sv_SE/person.json` is `sv_SE.person` and replaces the shipped one.
-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`,
-`person`, `phone`, `price`, `sentence`, `ssn`, `time`, `url`, `username`,
-`version` and `word`, formatted per locale. `misc` carries `car`, `coordinate`,
-`country` (ISO 3166), `creditcard` (Luhn-valid), `currency` (ISO 4217), `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.
-
 ## Data format
 
 Every value is a **node**, nestable without limit:
@@ -378,12 +475,16 @@ numbers that skews the draw, and `parent` the table a column links to
 columns are the [record](#records)'s columns, so `--format csv` writes the rows and
 `--list` shows `country.alpha2`. A cell is a string node: `1{digits(2)} {digits(2)}`
 in a cell draws digits and `{/misc.uuid}` reads a reference, while `{name}` in a cell
-is refused, since a cell has no sibling. `New` proves the header, the options and every
+is refused, since a cell has no sibling. Each cell may select its own row of another
+table, `{/misc.currency[SEK].symbol}` on one row and `{/misc.currency[EUR].symbol}`
+on the next, since only one row renders. `New` proves the header, the options and every
 cell token, and refuses a TSV no category names, a key that is empty or repeats, a
 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.
 
@@ -393,11 +494,11 @@ inline template has no file beside it, so there it stays a choice.
 
 ### Row selection
 
-`[key]` or `[name]` after a table's name selects one row: `misc.country[SE]` and
+`[key]` or `[name]` after a table's name selects one row: `misc.territory[SE]` and
-`misc.country[Sweden]` name one row, and `misc.country[SE].capital` reads its column.
+`misc.territory[Sweden]` name one row, and `misc.territory[SE].capital` reads its column.
 A name naming several rows is an error listing their keys, unless a row selected
 before it settles which ([Linked tables](#linked-tables)). A selector is part of the path, so it works
-wherever a path does: `Fake`, `FakeRecord`, a `{/misc.country[SE].capital}` reference
+wherever a path does: `Fake`, `FakeRecord`, a `{/misc.territory[SE].capital}` reference
 and a struct tag. A dot inside the brackets belongs to the key or name, so
 `city[St. Louis]` selects it. A path starts with a name, and `[` still opens a JSON
 array at the start of a CLI argument, so `'[SE]'` alone names nothing.
@@ -442,9 +543,10 @@ table another path in the group selects a row of, `{/city.name}` beside
 `{/country[SE].name}`, which the first token rendered would otherwise decide. `New`
 also refuses a link cell that is no key of the parent, a parent row no child links
 to, a chain of parents that closes, a table named like a column of any table above
-it, and a cell or format of a table that references a table of its own family, since
+it, and a cell or format of a table that references a table of its own family, through
-a row rendered whole would draw the family apart from itself: read the family from a
+any template, a `repeat` or a `drawGroup` included, since a row rendered whole would
-template beside it, or add the value as a column.
+draw the family apart from itself: read the family from a template beside it, or add
+the value as a column.
 
 ### Options and fields
 
@@ -480,21 +582,34 @@ 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, and
+`from` may equal `to`, which is that one day. The instant is UTC, so a zone in the
+layout prints `UTC` or `Z`.
+The quotes delimit a layout outside a selector only, so `[O'Fallon]` in an
+argument stays a name. Rejected at `New`: a bound that is no calendar date, or not
+before the other; an unquoted layout, naming the single-quoted one; a layout naming no field, which is
+text, as is one day in a layout with no clock; for `date` a layout naming no date
+field, naming `time`; 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
 
@@ -548,9 +663,9 @@ 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
@@ -569,8 +684,8 @@ 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" } }
 ```
 
@@ -647,7 +762,7 @@ a minor only adds, and a major is the only release that changes what exists.
 | Surface | Major | Minor |
 |---------|-------|-------|
 | Shipped data | remove or rename a path; change a category's format; remove a value, or change a weight or a repeat; add a reference from one shipped category into another; change a table's key, name, weight or parent column, or remove a row | a path outside a record's columns, a locale, a value in a list, a row |
-| Records | remove, rename, retype or add a column; let a column be null | a record, as a new category |
+| Records (a table is one) | remove, rename, retype or add a column; let a column be null | a record, as a new category |
 | Data format | a fence: a spelling `New` rejects that it accepted; a template option, since it reserves a field name | a builtin |
 | CLI | remove or rename a flag, or change its default; change what an exit code means; change the framing a `--format` writes (header, quoting, statement shape), the `--list` layout, or what an error names | a flag, a format |
 | Library | change or remove an exported name; raise the lowest supported Go | an exported name, a `With…` option |
@@ -672,30 +787,71 @@ datatype and nullability, and each table's key, name, weight and parent columns;
 changes it or `data/` adds its `CHANGELOG.md` entry, which CI checks. A removed,
 renamed or retyped line is a major.
 
+## Audience
+
+App developers writing tests and fixtures, in Go and at a shell:
+
+- a **bulk fixture author**, thousands of rows into CSV or SQL
+- a **Go test author**, filling a struct with `FakeStruct`
+- a **hand fixture author**, one value at a shell
+- a **validator-facing author**, who needs a value a real checker accepts
+
+and a **contributor**, who reads [`todo.md`](todo.md), [`AGENTS.md`](AGENTS.md) and
+the Development section below, and who ships a register the four above then draw from.
+
 ## Goals
 
-1. **Valid by construction** — every value passes the check its real consumer
+1. **The best fake-data tool available, and used because it is** — a developer
+   choosing a seed-data library or CLI, in any language, should find this the one
+   worth switching to, and every goal below it is what that costs. Merit is only
+   half the goal: once the grammar, the data and the CLI are complete and stable,
+   it ships where those developers install from and is announced where they read.
+2. **Understanding the code is part of the product** — it is a compiler with static
+   fences behind a small API, it will grow, and the people who extend it will not be
+   the people who wrote it. So reading cost is judged alongside behaviour: reaching
+   the unit behind a symptom without asking a person, changing one piece without
+   holding the rest, names that tell the truth, and a file that stands with no second
+   document open beside it. A simulated reader panel scores those four, the score is a
+   ratchet no release lowers, and [`AGENTS.md`](AGENTS.md) says what each pull request
+   owes it.
+3. **Valid by construction** — every value passes the check its real consumer
    applies; facts that belong together come from one draw, within a value and
    across categories.
-2. **Text means what it says** — a format renders as written; only `{…}` varies,
+4. **Text means what it says** — a format renders as written; only `{…}` varies,
    random characters included (`{digits(3)}`). One spelling per result; the wrong
    one is a load error naming the right one.
-3. **Every mistake is a load error** — `New` rejects the data and `NewTemplate`
+5. **Every mistake is a load error** — `New` rejects the data and `NewTemplate`
    the inline template; on a loaded generator `Fake` fails only for an unknown
    path, `FakeStruct` only for a non-struct argument or a type its tags do not
    describe, with the same error every call, and `Template.Fake` cannot fail at all.
-4. **Zero to a value in one command** — `go install`, then `fejkdata sv_SE.person`:
+6. **Zero to a value in one command** — `go install`, then `fejkdata sv_SE.person`:
    no checkout, no flag. Flags are GNU-form (`--seed 42`, `-n 3`) in any position;
    the first custom template needs no escape and no option.
-5. **Data lives in JSON** — a builtin only for what data can't express.
+7. **Data lives in JSON** — a builtin only for what data can't express.
-6. **Reproducible** — seed in, same stream out; no builtin reads a clock.
+8. **Reproducible** — seed in, same stream out; no builtin reads a clock.
-7. **Zero dependencies** — standard library only.
+9. **Zero dependencies** — standard library only.
-8. **Docs index the grammar** — every syntax feature is a heading; every example
+10. **Docs index the grammar** — every syntax feature is a heading; every example
-   runs under test and shows its output; a rule is stated once.
+    runs under test and shows its output; a rule is stated once.
-9. **Fast enough to be free** — a value renders in about a microsecond and `New`
+11. **Fast enough to be free** — a value renders in about a microsecond and `New`
-   parses and validates the whole set once upfront, so generating fixtures stays
+    parses and validates the whole set once upfront, so generating fixtures stays
-   noise against a test's own runtime.
+    noise against a test's own runtime.
-
+12. **Data is sourced, or on its way there** — a shipped fact, a name, place,
+    code, id or classification, is read from a register or open dataset by a
+    [`data-import/`](data-import) script wherever one exists to read; where none
+    does yet a small hand-written set ships and [`todo.md`](todo.md) carries the
+    step that replaces it. Only non-factual copy stays authored. A sourced table
+    holds the rows its source holds: none is added by hand, and one is dropped
+    only by a rule the script states.
+13. **Breadth follows what most systems store** — a category is added in proportion
+    to how many real schemas hold it: names, addresses, phones, ids, money and
+    timestamps before anything domain-specific, and a catalogue serving one niche
+    waits behind everything serving many.
+14. **Realism is the default, inertness is selectable** — where a value could reach
+    something real, a domain anyone may register or an account a bank could issue,
+    the realistic breadth ships *and* so does the subset that provably reaches
+    nothing, each on its own path. A fixture that looks nothing like production
+    tests nothing; the caller who needs a value that can touch nothing asks for it
+    by name.
 ## Decisions
 
 - **Options and fields share one namespace.** `format`, `weight`, `repeat`,
@@ -703,8 +859,7 @@ 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
@@ -722,7 +877,9 @@ renamed or retyped line is a major.
   library's own advice reachable: the error for an object holding only a format
   names `"…"`, and that spelling has to work where it is printed. An argument or struct
   tag of one reference alone, `{/users}`, is refused naming the path `users`: both
-  render the same text, and only the path names a record. `IsTemplate` exports the
+  render the same text, and only the path names a record. A folder-relative `{.name}`
+  or `{..name}` is refused naming `{/name}`, since an inline template sits in no
+  folder. `IsTemplate` exports the
   rule, so the CLI, struct tags and any other caller read one.
 - **An inline template skips the cycle fence.** `New` proves the loaded tree
   acyclic, an inline node is a finite tree of its own, and nothing in the tree can
@@ -947,8 +1104,7 @@ renamed or retyped line is a major.
   A table is a category with a TSV beside its file, so only a root choice has the
   spelling the fence names; a nested choice of same-shaped templates and an inline
   one keep loading. Fields must all be strings because a cell is a string node: a
-  choice whose items carry a nested choice, as `misc.car` does, is not one table but
+  choice whose items carry a nested choice is not one table but two linked ones.
-  two linked ones, which a later conversion writes.
 - **A table is a record of string columns.** Its columns are the CSV header and the
   `INSERT` column list, fixed by the TSV header, so a table is a record by
   construction; every column is a string until a typed column option earns its place.
@@ -956,11 +1112,218 @@ renamed or retyped line is a major.
   against the parent's keys and a key's uniqueness is a data mistake, so both are
   load-time; the name index and the per-parent child lists serve only a draw or a
   selection, so they wait for the first one, keeping `New` linear in the bytes read.
+- **Two categories may name one TSV.** Each is a view of the file with its own
+  format and options, at the cost of holding the rows twice, which is what a
+  category over a register with two natural formats asks for; a TSV nothing names
+  stays a load error, since that one is a file forgotten rather than shared.
+- **The rows of a table are alternatives.** Only one row renders, so a cell in one
+  row and a cell in another never meet, and each may select its own row of another
+  table; the cells of one row, and whatever they reach, do meet, and so does the
+  format beside them. The rule the fence applies is that two reads meet unless
+  they sit in two rows of one table, or in a row outside a selected ancestor's. A
+  choice's items get no such treatment yet: two items selecting different rows
+  are still refused.
+- **A table never reaches its own family, by any route.** A `repeat` iteration and a
+  `drawGroup` each draw apart on purpose, but a row that lists three localities from
+  other regions is the output the family exists to prevent, so the own-family fence
+  walks through both rather than stopping where the draw fences do.
+- **Tables carrying token cells stay small.** The family fence compares the reads of
+  every pair of rows that can render together, so a table whose every row's cell
+  selects a row of another table loads in time quadratic in its rows: about a
+  second at four thousand rows. No shipped table carries such cells, and a register
+  is a column set rather than a set of references, so the fence is left as it is
+  until a real data set needs the indexed form.
+- **A path is walked once without drawing before it is walked for real.** A path
+  that fails below its first level then moves no seeded stream, at the cost of one
+  draw-free walk per call, which allocates nothing.
+- **A country's postal codes and streets are siblings under its locality.** No open
+  source pairs a Swedish street with its postnummer, and pairing the US through its
+  ZIPs would shape the two trees differently, so both draw inside the pinned
+  locality and an address agrees at that level. A street's own code is the exact
+  pairing to add when a source carries it.
+- **A locale's `address` reads its country's `geo` tree, so the shipped set loads
+  whole.** `data/sv_SE` alone no longer loads: a test loads `data` and prefixes
+  the locale, and `--no-shipped-data -d` takes the whole `data` folder or a set of
+  one's own.
+- **The default embed holds every Swedish postort the import can place and give a
+  street-delivery code and a street, and the US places of 25,000 or more.** Sweden
+  fits whole in 700 KB; every US place of 10,000 would pass a
+  megabyte and fetch 1,200 counties of TIGER files, so the threshold sits where the
+  two countries match in size, and `--min-population` and
+  `--streets-per-locality` on the import scripts build a fuller set. The two trees
+  add about 20 ms to `New`, which loads the shipped set in about 45 ms.
+- **A locale's `address` restates its country record's format.** A record cannot
+  read another whole and keep its columns, so `sv_SE.address` names the same four
+  columns as `geo.SE.address`, each a reference into it, and the format appears
+  twice; a column is spelled the same in both, `street-number`, so the two never
+  disagree on a name.
+- **A postort's kommun comes from its name, its tätort or its codes, never from
+  distance.** GeoNames leaves a fifth of Sweden's codes without a kommun and
+  carries stale spellings; the nearest code across a border named the wrong kommun
+  half the time it was tried, so a postort none of the three rules place is
+  dropped, as is one not cased like a place name.
+- **A highway designation is not a street, and a US postal code belongs to the place
+  holding most of its land inside places.** `I- 55 Bus` and `US Hwy 1` carry the
+  most address ranges in many places and would head every address, so the import
+  drops names spelled as a route. A ZCTA goes to the place its largest in-place part
+  lies in, census-designated places left out since they never ship, and ships only
+  when that place does, so a few dozen places whose every code lies mostly in a
+  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.
+- **`--list` stays a plain list of paths.** It is what a script reads, so every line
+  has to be a path that `Fake` takes; a marker for the tables a `[selector]` follows,
+  or a legend above them, would make the output something to parse before use.
+  `--help` names the selector spelling instead, and the Table section teaches it.
+- **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.
+- **A title is a table under `sex`.** A prefix drawn apart would put `Mr` on a record
+  whose `sex` column says `female`, which is the disagreement the record exists to
+  prevent; the tables this set already has are what a title needs, so `en_US.title`
+  links to `sex` as `first-name` does. Swedish has no everyday sexed honorific, so
+  `sv_SE.title` is a table as well but carries no `parent`. Its weight column is
+  `share`, not the `count` a name table carries, because the values are a curated
+  proportion rather than bearers anyone counted.
+- **A table owns the spelling of a selector on it.** A reference reaches a table by a
+  path that carries no selector — `sv_SE.person.first` reads `first-name` through
+  `sex` — so the walk that resolved a name cannot say where a reader would type one.
+  The table's own location can, which is why it keeps its path, and why an ambiguity
+  error names `sv_SE.sex[f].first-name[Kim]` rather than the table's own name.
+- **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.
+- **`misc` is what every locale shares.** A category whose facts differ by country
+  belongs in that country's locale, read from the register that country's own
+  records use; `misc` takes only sources that are international. NHTSA vPIC and
+  Mobility Sweden's registrations are national, so they build `en_US.car` and
+  `sv_SE.car`; `misc.car` waits for an international source rather than take one
+  of theirs.
+- **A register's canonical spelling loses to the one its domain writes.** Where a
+  source offers several spellings of one fact, the shipped one is what records in
+  that domain carry. `misc.timezone` reads `zone.tab` and not the `zone1970.tab`
+  that supersedes it, because the latter keeps one zone per set of countries that
+  have agreed since 1970: it spells Sweden `Europe/Berlin`, and no Swedish system
+  writes that. For the same reason `misc.language` takes the ISO 639-2 register's
+  first synonym over CLDR, which says "Chinese, Mandarin" for `zh`.
+- **`misc.territory` is the spine, and a `misc` table naming a territory links to
+  it.** Where every territory row has a child the column is a `parent`, and the
+  import drops the child rows whose territory the set does not ship — 17 of
+  `misc.timezone`'s, Antarctica's ten among them. Agreement across a record is
+  worth more than the last rows of a table. Where no such link can hold the fact
+  stays a column. Layer your own `misc.territory` over the shipped one and you
+  must layer `misc.timezone` too, or the link fails at load naming the row.
+- **A table whose register publishes no frequency draws evenly.** `misc.httpmethod`,
+  `misc.port`, `misc.httpstatus`, `misc.mimetype` and `misc.tld` weigh every row alike,
+  so GET is a ninth of the methods drawn. Goal 10 keeps an authored fact out of a
+  sourced table, and no register publishes how often a method, a port or a TLD is used,
+  so a weight here would be invented. Where one exists it is read, as `misc.timezone`
+  reads GeoNames populations and `sv_SE.first-name` SCB bearers.
+- **`misc.port` selects by number, and carries no `name`.** 29 of its services sit on
+  more than one port, `http-alt` on three, so `misc.port[http-alt]` could name no one
+  row. The number is what a port field holds anyway, and `misc.port[443].service`
+  reads the other way.
+- **`misc.car` is one flat table, not a make linked to its models.** A row is a make
+  and a model drawn together, so no render pairs a Volvo with a RAV4. Two linked
+  tables would reach the same pairs and add a selector nothing asks for; a make alone
+  is `misc.car.make`.
+- **`misc.territory` names its sovereign in a column, and there is no `misc.country`
+  table.** ISO 3166-1 codes territories, so `territory` is the honest name, and
+  `is_independent` in the register gives each one's state. A second table of the 195
+  sovereigns would hold a `DK` row beside the territory `DK` row, both carrying
+  Denmark's capital, currency, flag and TLD — two owners for one fact, drifting at
+  the next import. Splitting the columns to avoid that is worse: put `capital` on
+  the territory alone and a country row can no longer name Copenhagen. The column
+  cannot be a `parent`, since a table never reaches its own family; a test proves
+  every value names a row instead. A territory the register records no state for
+  stands alone, which is `EH` alone, and naming one for it would be a claim
+  fejkdata has no business making.
+- **`misc.loglevel` is a table keyed by the code, rendering POSIX's keyword.** A flat
+  list of names carries neither the code a PRI encodes nor a selector reaching it, and
+  goal 3 draws the two as one fact. The canonical spelling losing to the one its domain
+  writes, above, settles the rest: a configuration writes `info`, so RFC 5424's
+  `Informational` stays the `severity` column, and the code and the keyword hold the
+  two selector slots.
+- **`misc.tld` keys carry the leading dot, where other tables key on a bare code.**
+  The register spells a TLD `.se` and `misc.territory.tld` already ships it so, which a
+  bare key would make two spellings of one fact; `{/misc.tld}` also composes onto a
+  host with no separator. `misc.tld[se]` misses for it, which `todo.md` carries.
+- **`misc.tld` is a table of its own, and `misc.territory.tld` stays a column.** A
+  `parent` demands a child for every parent row, so linking them would drop every root
+  zone row naming no territory, which is most of them, and goal 12 holds a sourced
+  table whole. The loader refuses the link outright anyway: `tld` is a column of
+  `misc.territory`, and a table may not be named like a column of its ancestor.
+- **`misc.territory` carries a currency code, it does not link to `misc.currency`.**
+  A `parent` demands a child for every parent row, and ISO 4217 registers codes no
+  country's row can name: the funds codes (Mvdol, WIR Euro, US Dollar (Next day)),
+  and VED beside VES, both Venezuela's, of which a country row names one. Linking
+  would trade the register for the link, and `misc.territory.currency` already pairs a
+  country with its currency in one draw.
+- **An extension may name two media types.** `.xml`, `.rtf`, `.sub`, `.mpp` and `.ac`
+  each name two rows of `misc.mimetype`. Separating them would mean dropping a
+  registered type, or naming one by an extension that is not its own — `.mpt` is
+  Project's template, not its document. Selecting such a name is an error listing
+  both keys; select by type instead.
+- **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. They sit in a `birth-number` table under `sex`
+  rather than as a column of it: the render's shared draw of the family is what
+  makes the number and the name agree on sex, and `sex` stays one shape across
+  locales instead of collecting every sex-keyed id fact. A samordningsnummer's
+  day, the birthday plus 60, is drawn from 61 to 88, valid in every month, rather
+  than computed from the date drawn.
+- **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. The SSA's placeholder rows are top-1000 entries that name nobody, so
+  the import drops them by name rather than by a rank a regeneration would move.
 - **`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
   the one a reader can predict from the tables' parents.
 
+## Layout
+
+```
+fejkdata.go     Generator, New, options, the embedded data set, List
+node.go         the node model and JSON -> node compilation
+table.go        tables: the rows TSV, its options and links, row selection and draws
+path.go         the dotted-path walk with its selectors, and proving a path resolves
+render.go       Fake and the recursive renderer (choices, format strings, expansions)
+record.go       records: Record, the JSON/CSV/SQL serializers, and their entry points
+struct.go       structs: FakeStruct, fake tags, and a field's Go type as its column's datatype
+inline.go       inline templates: Template, NewTemplate, FakeTemplate, IsTemplate, and their compile and link
+template.go     the {token} grammar: scanning, tokens, operands, validation, compiling a format
+hold.go         the hold: one draw per expansion for paths and operands, and its fences
+draw.go         one reference draw per render and group: draw sets, the group option, and its fence
+family.go       a family of linked tables: the rows a render pins, and the fence over paths into one family
+reference.go    reference sigils, and binding references across the tree
+graph.go        the render graph: edges, cycles, the repeat bound, tree walks
+builtins.go     the {name()} function registry and its implementations
+layout.go       date and time layouts: the instants one is proved against, and the two samples
+checksum.go     the check characters a derivation appends, and the IBAN they sit inside
+transform.go    the builtins that rewrite an operand's value, and the ASCII folding
+calc.go         the {calc()} arithmetic evaluator: parser, eval, validation
+datatype.go     column datatypes: DataType, where datatype and null may sit, a column's datatype
+value.go        the value proof: what a typed column or calc operand holds, checked at load
+data.go         data loading: fs.FS folders/files -> namespace tree, multi-source merge
+cmd/fejkdata/   the fejkdata CLI
+data/           shipped data (JSON, and a TSV per table), embedded at build: locale folders, geo, misc
+data-import/    the scripts that rebuild each sourced table (see DATA-LICENSES.md)
+release-tooling/ the release CI publishes from the changelog heading
+testdata/       the pinned shipped shape (see Versioning)
+```
+
 ## Development
 
 Everything runs in Docker — **no local tooling beyond Docker is needed**.
@@ -983,6 +1346,15 @@ docker compose run --rm --user "$(id -u):$(id -g)" fmt   # gofmt -w .
 docker compose run --rm --user "$(id -u):$(id -g)" tidy  # go mod tidy
 ```
 
+A `--user` command answering `permission denied` on `/cache` has met root-owned
+files in the `gocache` volume: Docker creates the volume root-owned, and every
+command here that omits `--user` writes into it as root. Hand it back, and again
+whenever it recurs:
+
+```sh
+docker compose run --rm --user root --entrypoint chown test -R "$(id -u):$(id -g)" /cache
+```
+
 Every pull request runs `docker build .` against both the latest and the lowest
 supported Go, and must pass before it can be merged — unless it changes none of
 the files the build and its tests read, nor the workflow itself, in which case
@@ -1005,11 +1377,33 @@ REPIN=1 docker compose run --rm --user "$(id -u):$(id -g)" test
 
 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):
+[`DATA-LICENSES.md`](DATA-LICENSES.md). Downloads are cached under
+`data-import/cache/`, which is ignored by version control and grows past a
+gigabyte, so pass `--cache DIR` to reuse a copy you already have and delete it to
+fetch afresh; `geo-us.py` fetches two
+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`, 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)" -e TRAFIKVERKET_API_KEY data-import data-import/geo-se.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)" data-import data-import/httpmethod.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/httpstatus.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/language.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/loglevel.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/mimetype.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
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/port.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/protocol.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/territory.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/timezone.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/tld.py
+docker compose run --rm --user "$(id -u):$(id -g)" data-import data-import/useragent.py
 ```
 
 To release, head `CHANGELOG.md` with the version's section in place of `Unreleased`
@@ -1017,35 +1411,6 @@ and merge: once `main` passes the gate, CI tags that commit `vX.Y.Z` and publish
 the Gitea release with the section as its body. A top heading of `[Unreleased]`
 publishes nothing.
 
-## Layout
-
-```
-fejkdata.go     Generator, New, options, the embedded data set, List
-node.go         the node model and JSON -> node compilation
-table.go        tables: the rows TSV, its options and links, row selection and draws
-path.go         the dotted-path walk with its selectors, and proving a path resolves
-render.go       Fake and the recursive renderer (choices, format strings, expansions)
-record.go       records: Record, the JSON/CSV/SQL serializers, and their entry points
-struct.go       structs: FakeStruct, fake tags, and a field's Go type as its column's datatype
-inline.go       inline templates: Template, NewTemplate, FakeTemplate, IsTemplate, and their compile and link
-template.go     the {token} grammar: scanning, tokens, operands, validation, compiling a format
-hold.go         the hold: one draw per expansion for paths and operands, and its fences
-draw.go         one reference draw per render and group: draw sets, the group option, and its fence
-family.go       a family of linked tables: the rows a render pins, and the fence over paths into one family
-reference.go    reference sigils, and binding references across the tree
-graph.go        the render graph: edges, cycles, the repeat bound, tree walks
-builtins.go     the {name()} function registry and its implementations
-calc.go         the {calc()} arithmetic evaluator: parser, eval, validation
-datatype.go     column datatypes: DataType, where datatype and null may sit, a column's datatype
-value.go        the value proof: what a typed column or calc operand holds, checked at load
-data.go         data loading: fs.FS folders/files -> namespace tree, multi-source merge
-cmd/fejkdata/   the fejkdata CLI
-data/           shipped data (JSON, and a TSV per table), embedded at build: locale folders + a misc folder
-data-import/    the scripts that rebuild each sourced table (see DATA-LICENSES.md)
-release-tooling/ the release CI publishes from the changelog heading
-testdata/       the pinned shipped shape (see Versioning)
-```
-
 ## License
 
 MIT — see [LICENSE](LICENSE). Forked from [github.com/Timewave-AB/fakes](https://github.com/Timewave-AB/fakes).

bench_test.go

@@ -26,12 +26,12 @@ func benchPath(b *testing.B, dir, path string) {
 	}
 }
 
-func BenchmarkPerson(b *testing.B)     { benchPath(b, "data/sv_SE", "person") }
+func BenchmarkPerson(b *testing.B)       { benchPath(b, "data", "sv_SE.person") }
-func BenchmarkAddress(b *testing.B)    { benchPath(b, "data/sv_SE", "address") }
+func BenchmarkAddress(b *testing.B)      { benchPath(b, "data", "sv_SE.address") }
-func BenchmarkWord(b *testing.B)       { benchPath(b, "data/sv_SE", "word") }
+func BenchmarkWord(b *testing.B)         { benchPath(b, "data", "sv_SE.word") }
-func BenchmarkCreditcard(b *testing.B) { benchPath(b, "data/misc", "creditcard") }
+func BenchmarkCreditcard(b *testing.B)   { benchPath(b, "data", "misc.creditcard") }
-func BenchmarkSSN(b *testing.B)        { benchPath(b, "data/sv_SE", "ssn") }
+func BenchmarkPersonnummer(b *testing.B) { benchPath(b, "data", "sv_SE.personnummer") }
-func BenchmarkUUIDv7(b *testing.B)     { benchPath(b, "data/misc", "uuid") }
+func BenchmarkUUIDv7(b *testing.B)       { benchPath(b, "data", "misc.uuid") }
 
 func tmpData(b *testing.B, name, body string) string {
 	b.Helper()

builtins.go

@@ -7,7 +7,6 @@ import (
 	"math"
 	"strconv"
 	"strings"
-	"unicode"
 )
 
 // maxLen caps sample output lengths (hex, nanoid, base64, digits, upper, lower)
@@ -60,6 +59,8 @@ 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},
@@ -88,13 +89,11 @@ func derive(f func(emitted string) string) func([]string) callFn {
 		return func(_ *session, emitted string, _ []string) string { return f(emitted) }
 	}
 }
-
 func sample(f func(rng) string) func([]string) callFn {
 	return func([]string) callFn {
 		return func(s *session, _ string, _ []string) string { return f(s) }
 	}
 }
-
 func chars(alphabet string) func([]string) callFn {
 	return func(a []string) callFn {
 		n := atoi(a[0])
@@ -113,96 +112,6 @@ func formatFloat(v float64, dp int) string {
 	return s
 }
 
-// transforms are the builtins that rewrite one operand's value; they nest, so
-// {lowercase(ascii(x))} folds then lowers.
-var transforms = map[string]func(string) string{
-	"ascii":     asciiFold,
-	"lowercase": strings.ToLower,
-	"uppercase": strings.ToUpper,
-}
-
-// unwrapTransform peels nested transform calls off an operand arg, returning the
-// field it finally names and the transforms to apply, innermost last.
-func unwrapTransform(arg string) (leaf string, chain []func(string) string, err error) {
-	for {
-		name, args, isCall := funcCall(arg)
-		if !isCall {
-			return arg, chain, nil
-		}
-		fn, isTransform := transforms[name]
-		if !isTransform {
-			return "", nil, fmt.Errorf("%s(%s) is not a transform, so it cannot be an operand", name, strings.Join(args, ","))
-		}
-		if len(args) != 1 {
-			return "", nil, fmt.Errorf("%s takes 1 arg, got %d", name, len(args))
-		}
-		chain = append(chain, fn)
-		arg = args[0]
-	}
-}
-
-func transformArg(fields map[string]node, a []string) error {
-	leaf, _, err := unwrapTransform(a[0])
-	if err != nil {
-		return err
-	}
-	if isRef(leaf) {
-		_, _, err := refShape(leaf)
-		return err
-	}
-	return checkArm(leaf, fields, false)
-}
-
-func transformOperand(a []string) []string {
-	leaf, _, err := unwrapTransform(a[0])
-	if err != nil {
-		return nil
-	}
-	return []string{leaf}
-}
-
-func transformPrep(outer func(string) string) func([]string) callFn {
-	return func(a []string) callFn {
-		_, chain, err := unwrapTransform(a[0])
-		if err != nil {
-			panic(fmt.Sprintf("fejkdata: transform arg %q reached prep unvalidated: %v", a[0], err))
-		}
-		return func(_ *session, _ string, operands []string) string {
-			v := operands[0]
-			for i := len(chain) - 1; i >= 0; i-- {
-				v = chain[i](v)
-			}
-			return outer(v)
-		}
-	}
-}
-
-// asciiFolds maps the Latin letters with diacritics or ligatures to ASCII.
-var asciiFolds = map[rune]string{
-	'À': "A", 'Á': "A", 'Â': "A", 'Ã': "A", 'Ä': "A", 'Å': "A", 'Æ': "AE", 'Ç': "C",
-	'È': "E", 'É': "E", 'Ê': "E", 'Ë': "E", 'Ì': "I", 'Í': "I", 'Î': "I", 'Ï': "I",
-	'Ð': "D", 'Ñ': "N", 'Ò': "O", 'Ó': "O", 'Ô': "O", 'Õ': "O", 'Ö': "O", 'Ø': "O",
-	'Ù': "U", 'Ú': "U", 'Û': "U", 'Ü': "U", 'Ý': "Y", 'Þ': "Th", 'ß': "ss", 'Œ': "OE",
-	'à': "a", 'á': "a", 'â': "a", 'ã': "a", 'ä': "a", 'å': "a", 'æ': "ae", 'ç': "c",
-	'è': "e", 'é': "e", 'ê': "e", 'ë': "e", 'ì': "i", 'í': "i", 'î': "i", 'ï': "i",
-	'ð': "d", 'ñ': "n", 'ò': "o", 'ó': "o", 'ô': "o", 'õ': "o", 'ö': "o", 'ø': "o",
-	'ù': "u", 'ú': "u", 'û': "u", 'ü': "u", 'ý': "y", 'þ': "th", 'ÿ': "y", 'œ': "oe",
-}
-
-// asciiFold rewrites s to ASCII: folded Latin letters stay, any other non-ASCII
-// rune is dropped.
-func asciiFold(s string) string {
-	var b strings.Builder
-	for _, r := range s {
-		if r <= unicode.MaxASCII {
-			b.WriteRune(r)
-		} else {
-			b.WriteString(asciiFolds[r])
-		}
-	}
-	return b.String()
-}
-
 // atoi parses an arg a builtin's check already validated. It panics rather than
 // returning zero, so a check that stops covering its own args is a stack trace and
 // not a silently wrong length, range or decimal count.
@@ -222,7 +131,6 @@ func atof(s string) float64 {
 	}
 	return f
 }
-
 func randBytes(r rng, n int) []byte {
 	b := make([]byte, n)
 	for i := range b {
@@ -230,7 +138,6 @@ func randBytes(r rng, n int) []byte {
 	}
 	return b
 }
-
 func randChars(r rng, n int, alphabet string) string {
 	b := make([]byte, n)
 	for i := range b {
@@ -253,7 +160,6 @@ func plainInt(s string) (int, error) {
 	}
 	return n, nil
 }
-
 func posIntArg(_ map[string]node, a []string) error {
 	n, err := plainInt(a[0])
 	if errors.Is(err, strconv.ErrRange) {
@@ -270,7 +176,6 @@ func posIntArg(_ map[string]node, a []string) error {
 	}
 	return nil
 }
-
 func intRangeArgs(_ map[string]node, a []string) error {
 	lo, err := plainInt(a[0])
 	if err != nil {
@@ -291,7 +196,6 @@ func intRangeArgs(_ map[string]node, a []string) error {
 	}
 	return nil
 }
-
 func floatArgs(_ map[string]node, a []string) error {
 	lo, e1 := strconv.ParseFloat(a[0], 64)
 	hi, e2 := strconv.ParseFloat(a[1], 64)
@@ -319,10 +223,9 @@ func floatArgs(_ map[string]node, a []string) error {
 	}
 	return nil
 }
-
 func seqArg(_ map[string]node, a []string) error {
 	if len(a) > 1 {
-		return fmt.Errorf("seq takes at most one name, got %d args", len(a))
+		return fmt.Errorf("seq takes at most one name, got %d", len(a))
 	}
 	if len(a) == 1 && a[0] == "" {
 		return fmt.Errorf("seq name must not be empty")
@@ -373,96 +276,3 @@ func ulid(r rng) string {
 	}
 	return string(out)
 }
-
-// luhnCheck returns the Luhn check digit (0-9) over the digits of s; non-digit
-// runes are skipped. Doubling runs from the rightmost digit, so the result is
-// correct whatever the payload length.
-func luhnCheck(s string) int {
-	sum, double := 0, true
-	for i := len(s) - 1; i >= 0; i-- {
-		c := s[i]
-		if c < '0' || c > '9' {
-			continue
-		}
-		d := int(c - '0')
-		if double {
-			if d *= 2; d > 9 {
-				d -= 9
-			}
-		}
-		double = !double
-		sum += d
-	}
-	return (10 - sum%10) % 10
-}
-
-// mod11Check returns the weighted mod-11 check character over the digits of s
-// (weights 2..7 cycling from the right). A would-be value of 10 emits 'X', as in
-// ISBN-10 / ISO 7064; non-digits are skipped.
-func mod11Check(s string) string {
-	sum, w := 0, 2
-	for i := len(s) - 1; i >= 0; i-- {
-		c := s[i]
-		if c < '0' || c > '9' {
-			continue
-		}
-		sum += int(c-'0') * w
-		if w++; w > 7 {
-			w = 2
-		}
-	}
-	if chk := (11 - sum%11) % 11; chk != 10 {
-		return string(rune('0' + chk))
-	}
-	return "X"
-}
-
-// eanCheck returns the EAN-13 / UPC-A / ISBN-13 / GTIN check digit over the
-// digits of s: weights 3 and 1 alternating from the rightmost digit, mod 10.
-func eanCheck(s string) string {
-	sum, w := 0, 3
-	for i := len(s) - 1; i >= 0; i-- {
-		c := s[i]
-		if c < '0' || c > '9' {
-			continue
-		}
-		sum += int(c-'0') * w
-		w = 4 - w // 3 <-> 1
-	}
-	return string(rune('0' + (10-sum%10)%10))
-}
-
-// ibanLen maps a supported country code to the full IBAN length. The check digits
-// sit between the country code and the BBAN, so — unlike luhn/ean — iban can't be
-// a left-to-right derivation; it generates the whole value instead.
-var ibanLen = map[string]int{"BE": 16, "DE": 22, "DK": 18, "ES": 24, "FI": 18, "NO": 15, "SE": 24}
-
-func ibanArg(_ map[string]node, a []string) error {
-	if _, ok := ibanLen[a[0]]; !ok {
-		return fmt.Errorf("iban(%q): unsupported country code", a[0])
-	}
-	return nil
-}
-
-// iban generates a structurally valid IBAN for cc: a numeric BBAN of the right
-// length, then mod-97 check digits. Real bank/branch structure isn't modelled —
-// the result passes length and checksum validation, which is what fake data needs.
-func iban(r rng, cc string) string {
-	bban := make([]byte, ibanLen[cc]-4)
-	for i := range bban {
-		bban[i] = byte('0' + r.IntN(10))
-	}
-	rem := 0
-	feed := func(d int) { rem = (rem*10 + d) % 97 }
-	for _, c := range bban {
-		feed(int(c - '0'))
-	}
-	for i := 0; i < len(cc); i++ { // letters A-Z -> 10..35, fed as two digits
-		v := int(cc[i]-'A') + 10
-		feed(v / 10)
-		feed(v % 10)
-	}
-	feed(0)
-	feed(0)
-	return fmt.Sprintf("%s%02d%s", cc, 98-rem, bban)
-}

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 +236,135 @@ 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')}"`:        "is after",
+		`"{date(1990-01-01,1990-01-01,'2006-01-02')}"`:        "write it as text",
+		`"{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,\"January 2, 2006\")}"`: "quoted: '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 arguments",
+		`"{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",
+		`"{date(1990-01-01,1990-12-31,'15:04')}"`:             "time('15:04')",
+	} {
+		_, 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)
+		}
+	}
+}
+
+// TestBuiltinLayoutErrorsNameARunnableSpelling pins the two layout errors a user
+// can follow: a double-quoted layout is named single-quoted, without its own
+// quotes carried into the suggestion, whether it split on a comma or not.
+func TestBuiltinLayoutErrorsNameARunnableSpelling(t *testing.T) {
+	_, err := compile(parse(t, `"{date(1990-01-01,1990-12-31,\"2006-01-02\")}"`))
+	if err == nil || !strings.Contains(err.Error(), "write '2006-01-02'") {
+		t.Fatalf("a double-quoted layout = %v, want it named single-quoted", err)
+	}
+	if strings.Contains(err.Error(), `'"`) {
+		t.Errorf("%v names a layout that renders its own quotes", err)
+	}
+	if !strings.Contains(err.Error(), "is double-quoted") {
+		t.Errorf("%v does not say which quotes were wrong", err)
+	}
+	_, err = compile(parse(t, `"{time(15:04)}"`))
+	if err == nil || !strings.Contains(err.Error(), "write '15:04'") {
+		t.Fatalf("a bare layout = %v, want it named quoted", err)
+	}
+	// The comma hint belongs to a layout that split, not to a call given extra args.
+	_, err = compile(parse(t, `"{time(0,12,'15:04')}"`))
+	if err == nil || !strings.Contains(err.Error(), "takes 1 argument, got 3") {
+		t.Fatalf("time with three args = %v, want the count named in the singular", err)
+	}
+	if strings.Contains(err.Error(), "holding a comma") {
+		t.Errorf("%v offers the comma hint though the layout is already quoted", err)
+	}
+}
+
+// TestBuiltinDateSpansOneDay pins that from == to is a day: with a clock layout it
+// draws every second of it, and without one it could only emit one value.
+func TestBuiltinDateSpansOneDay(t *testing.T) {
+	f := engine(1)
+	seen := map[string]bool{}
+	for i := 0; i < 500; i++ {
+		got := mustRender(t, f, `"{date(2026-01-01,2026-01-01,'2006-01-02 15:04:05')}"`)
+		if !strings.HasPrefix(got, "2026-01-01 ") {
+			t.Fatalf("date over one day = %q, out of range", got)
+		}
+		seen[got] = true
+	}
+	if len(seen) < 400 {
+		t.Fatalf("date over one day drew %d distinct seconds in 500, want the whole day", len(seen))
+	}
+	_, err := compile(parse(t, `"{date(2026-01-01,2026-01-01,'2006-01-02')}"`))
+	if err == nil || !strings.Contains(err.Error(), "write it as text") {
+		t.Fatalf("one day in a date-only layout = %v, want it named a constant", err)
+	}
+}

checksum.go

@@ -0,0 +1,96 @@
+package fejkdata
+
+import "fmt"
+
+// luhnCheck returns the Luhn check digit (0-9) over the digits of s; non-digit
+// runes are skipped. Doubling runs from the rightmost digit, so the result is
+// correct whatever the payload length.
+func luhnCheck(s string) int {
+	sum, double := 0, true
+	for i := len(s) - 1; i >= 0; i-- {
+		c := s[i]
+		if c < '0' || c > '9' {
+			continue
+		}
+		d := int(c - '0')
+		if double {
+			if d *= 2; d > 9 {
+				d -= 9
+			}
+		}
+		double = !double
+		sum += d
+	}
+	return (10 - sum%10) % 10
+}
+
+// mod11Check returns the weighted mod-11 check character over the digits of s
+// (weights 2..7 cycling from the right). A would-be value of 10 emits 'X', as in
+// ISBN-10 / ISO 7064; non-digits are skipped.
+func mod11Check(s string) string {
+	sum, w := 0, 2
+	for i := len(s) - 1; i >= 0; i-- {
+		c := s[i]
+		if c < '0' || c > '9' {
+			continue
+		}
+		sum += int(c-'0') * w
+		if w++; w > 7 {
+			w = 2
+		}
+	}
+	if chk := (11 - sum%11) % 11; chk != 10 {
+		return string(rune('0' + chk))
+	}
+	return "X"
+}
+
+// eanCheck returns the EAN-13 / UPC-A / ISBN-13 / GTIN check digit over the
+// digits of s: weights 3 and 1 alternating from the rightmost digit, mod 10.
+func eanCheck(s string) string {
+	sum, w := 0, 3
+	for i := len(s) - 1; i >= 0; i-- {
+		c := s[i]
+		if c < '0' || c > '9' {
+			continue
+		}
+		sum += int(c-'0') * w
+		w = 4 - w // 3 <-> 1
+	}
+	return string(rune('0' + (10-sum%10)%10))
+}
+
+// ibanLen maps a supported country code to the full IBAN length. The check digits
+// sit between the country code and the BBAN, so — unlike luhn/ean — iban can't be
+// a left-to-right derivation; it generates the whole value instead.
+var ibanLen = map[string]int{"BE": 16, "DE": 22, "DK": 18, "ES": 24, "FI": 18, "NO": 15, "SE": 24}
+
+func ibanArg(_ map[string]node, a []string) error {
+	if _, ok := ibanLen[a[0]]; !ok {
+		return fmt.Errorf("iban(%q): unsupported country code", a[0])
+	}
+	return nil
+}
+
+// iban generates a structurally valid IBAN for cc: a numeric BBAN of the right
+// length, then mod-97 check digits. Real bank/branch structure isn't modelled —
+// the result passes length and checksum validation, which is what fake data needs.
+func iban(r rng, cc string) string {
+	bban := make([]byte, ibanLen[cc]-4)
+	for i := range bban {
+		bban[i] = byte('0' + r.IntN(10))
+	}
+	rem := 0
+	feed := func(d int) { rem = (rem*10 + d) % 97 }
+	for _, c := range bban {
+		feed(int(c - '0'))
+	}
+	for i := 0; i < len(cc); i++ { // letters A-Z -> 10..35, fed as two digits
+		v := int(cc[i]-'A') + 10
+		feed(v / 10)
+		feed(v % 10)
+	}
+	feed(0)
+	feed(0)
+	return fmt.Sprintf("%s%02d%s", cc, 98-rem, bban)
+}

cmd/fejkdata/main.go

@@ -24,10 +24,13 @@ import (
 const usage = `Usage: fejkdata [flags] <path|template>
 
   <path>                 a category, or a dotted path into one (person, person.last);
-                         a table's row by key or name: 'misc.country[SE]', 'misc.country[Sweden].tld'
+                         a table's row by key or name: 'misc.territory[SE]', 'misc.territory[Sweden].tld'
   <template>             a format string or JSON value to render inline, e.g.
                          'name: {/sv_SE.person.last}' or '{"format":"{x}","x":["bosse","lina"]}'
 
+A layout inside a template is single-quoted, so quote the whole argument with " to
+keep it: "{date(1990-01-01,2010-12-31,'2006-01-02')}".
+
 An argument containing a { token, or a JSON object, array or string, is a
 template; any other argument is a path (a path never contains a brace or a quote,
 and a bracket only as a [selector] after a table's name). Templates reach the
@@ -279,7 +282,7 @@ func (in invocation) check() (argKind, error) {
 		return argPath, nil
 	}
 	if len(in.paths) != 1 {
-		return argPath, fmt.Errorf("expected one path or template, got %d", len(in.paths))
+		return argPath, fmt.Errorf("expected one path or template, got %d%s", len(in.paths), templateSplit(in.paths))
 	}
 	return classify(in.paths[0])
 }
@@ -475,11 +478,25 @@ func run(args []string, stdout, stderr io.Writer) int {
 			return misuse(stderr, te.error)
 		}
 		fmt.Fprintln(stderr, err)
+		if errors.Is(err, fejkdata.ErrNoColumns) {
+			fmt.Fprintln(stderr, "wrap that JSON in single quotes, which keep a shell from expanding its braces")
+		}
 		return 1
 	}
 	return 0
 }
 
+// templateSplit names the cure for a template a shell split on its spaces, which is
+// what several arguments carrying a token mean.
+func templateSplit(paths []string) string {
+	for _, p := range paths {
+		if strings.Contains(p, "{") {
+			return `; a template's spaces split the argument, so wrap the whole argument in "…", or in '…' where it carries double quotes`
+		}
+	}
+	return ""
+}
+
 func misuse(stderr io.Writer, err error) int {
 	// A library error already names the program, so the prefix is not doubled.
 	fmt.Fprintf(stderr, "fejkdata: %s\ntry 'fejkdata --help'\n", strings.TrimPrefix(err.Error(), "fejkdata: "))

cmd/fejkdata/main_test.go

@@ -14,6 +14,7 @@ import (
 const (
 	svSE = "../../data/sv_SE"
 	enUS = "../../data/en_US"
+	misc = "../../data/misc"
 )
 
 func runOut(args ...string) (int, string, string) {
@@ -222,6 +223,14 @@ func TestRunMisuse(t *testing.T) {
 			t.Errorf("run(%v) stdout = %q, want nothing", args, out)
 		}
 	}
+	// A template a shell split names both quotings, since which one cures it turns
+	// on whether the argument carries a double-quoted JSON.
+	_, _, errb := runOut("{date(1990-01-01,2010-12-31,", "January", "2,", "2006)}")
+	for _, want := range []string{`wrap the whole argument in "…"`, `or in '…'`} {
+		if !strings.Contains(errb, want) {
+			t.Errorf("a split template stderr = %q, want it to name %s", errb, want)
+		}
+	}
 }
 
 func TestRunMultipleDataPaths(t *testing.T) {
@@ -343,8 +352,8 @@ func TestRunSelectsATableRow(t *testing.T) {
 	if code, _, errb := runOut("--no-shipped-data", "-d", dir, "[Skåne län]"); code != 2 || !strings.Contains(errb, "JSON") {
 		t.Fatalf("[Skåne län] = %d, stderr=%q, want misuse: a leading bracket that is no JSON names nothing", code, errb)
 	}
-	if code, out, _ := runOut("--seed", "1", "--format", "csv", "misc.country[SE]"); code != 0 || !strings.HasPrefix(out, "alpha2,") || !strings.Contains(out, "\nSE,SWE,") {
+	if code, out, _ := runOut("--seed", "1", "--format", "csv", "misc.territory[SE]"); code != 0 || !strings.HasPrefix(out, "alpha2,") || !strings.Contains(out, "\nSE,SWE,") {
-		t.Fatalf("--format csv misc.country[SE] = %d, %q", code, out)
+		t.Fatalf("--format csv misc.territory[SE] = %d, %q", code, out)
 	}
 }
 
@@ -405,14 +414,14 @@ func TestRunTemplateMisuse(t *testing.T) {
 }
 
 func TestRunNoShippedData(t *testing.T) {
-	code, list, errb := runOut("--no-shipped-data", "-d", svSE, "--list")
+	code, list, errb := runOut("--no-shipped-data", "-d", misc, "--list")
 	if code != 0 {
 		t.Fatalf("run = %d, stderr=%q", code, errb)
 	}
-	if strings.Contains(list, "en_US") || !strings.Contains(list, "person\n") {
+	if strings.Contains(list, "sv_SE") || !strings.Contains(list, "uuid\n") {
 		t.Errorf("--no-shipped-data --list = %q, want only the given dir", list)
 	}
-	code, out, _ := runOut("--no-shipped-data", "-d", svSE, "-s", "3", "person")
+	code, out, _ := runOut("--no-shipped-data", "-d", misc, "-s", "3", "uuid")
 	if code != 0 || strings.TrimSpace(out) == "" {
 		t.Errorf("run = %d, out=%q", code, out)
 	}
@@ -612,3 +621,21 @@ func TestRunNumbersFollowTheShell(t *testing.T) {
 		t.Errorf("run(--seed 007 --repeat +3) = %d, %q, stderr %q; want the same as --seed 7 --repeat 3 %q", code, got, errb, want)
 	}
 }
+
+// TestRunRecordOfAFieldlessPath pins the way out of asking a category of one value
+// for columns: the record to write, and the quoting a shell needs to take it. The
+// argument is well-formed and only the data cannot serve it, so the code is 1.
+func TestRunRecordOfAFieldlessPath(t *testing.T) {
+	code, out, errb := runOut("--format", "csv", "sv_SE.personnummer")
+	if code != 1 {
+		t.Fatalf("run(--format csv sv_SE.personnummer) = %d, want 1", code)
+	}
+	for _, want := range []string{`{"format":"","personnummer":"{/sv_SE.personnummer}"}`, "single quotes"} {
+		if !strings.Contains(errb, want) {
+			t.Errorf("stderr = %q, want it to name %s", errb, want)
+		}
+	}
+	if out != "" {
+		t.Errorf("stdout = %q, want nothing", out)
+	}
+}

data-import/currency.py

@@ -1,35 +1,29 @@
 #!/usr/bin/env python3
 """Rebuild data/misc/currency.tsv from datasets/currency-codes (PDDL) and CLDR's symbols (Unicode).
 
-    data-import/currency.py [--source URL_OR_FILE] [--symbols URL_OR_FILE ...] [--out FILE]
+    data-import/currency.py [--source URL_OR_FILE] [--symbols URL_OR_FILE ...] [--cache DIR] [--out FILE]
 
 The symbols come from the first locale file that has one, narrow symbols before wide.
 """
 import argparse
 import csv
 import io
-import re
-import sys
-import urllib.request
 import xml.etree.ElementTree as ET
 from pathlib import Path
 
+import source
+import tsv
+
 SOURCE = "https://raw.githubusercontent.com/datasets/currency-codes/main/data/codes-all.csv"
 SYMBOLS = [
     "https://raw.githubusercontent.com/unicode-org/cldr/main/common/main/en.xml",
     "https://raw.githubusercontent.com/unicode-org/cldr/main/common/main/root.xml",
 ]
 OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "currency.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["code", "decimals", "name", "numeric", "symbol"]
 
 
-def read(source):
-    if re.match(r"^https?://", source):
-        with urllib.request.urlopen(source, timeout=60) as r:
-            return r.read().decode("utf-8")
-    return Path(source).read_text(encoding="utf-8")
-
-
 def symbols(xml_texts):
     """CLDR's symbol per code: the first locale's narrow symbol, else the first locale's wide one."""
     narrow, wide = {}, {}
@@ -58,24 +52,16 @@ def rows(text, symbol):
         }
 
 
-def write(out, table):
-    lines = ["\t".join(COLUMNS)]
-    for row in sorted(table, key=lambda r: r["code"]):
-        cells = [row[c] for c in COLUMNS]
-        assert all(cells) and not any("\t" in c or "\n" in c for c in cells), row
-        lines.append("\t".join(cells))
-    Path(out).write_text("\n".join(lines) + "\n", encoding="utf-8")
-    return len(lines) - 1
-
-
 def main():
     p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
     p.add_argument("--source", default=SOURCE)
     p.add_argument("--symbols", nargs="+", default=SYMBOLS)
     p.add_argument("--out", default=str(OUT))
     a = p.parse_args()
-    n = write(a.out, rows(read(a.source), symbols(read(s) for s in a.symbols)))
+    symbol = symbols(source.fetch(s, a.cache, Path(s).name).decode("utf-8") for s in a.symbols)
-    print(f"{a.out}: {n} rows", file=sys.stderr)
+    table = rows(source.fetch(a.source, a.cache, "codes-all.csv").decode("utf-8"), symbol)
+    tsv.write(a.out, COLUMNS, sorted(table, key=lambda r: r["code"]))
 
 
 if __name__ == "__main__":

data-import/geo-se.py

@@ -0,0 +1,234 @@
+#!/usr/bin/env python3
+"""Rebuild data/geo/SE/*.tsv from SCB (CC0), GeoNames (CC BY 4.0) and Trafikverket NVDB (CC0).
+
+    TRAFIKVERKET_API_KEY=… data-import/geo-se.py [--key-file FILE] [--cache DIR] [--streets-per-locality N] [--out DIR]
+"""
+import argparse
+import collections
+import csv
+import io
+import json
+import math
+import os
+import re
+import sys
+import urllib.request
+import zipfile
+from pathlib import Path
+
+import source
+import tsv
+import xlsx
+
+CODES = "https://www.scb.se/contentassets/7a89e48960f741e08918e489ea36354a/kommunlankod-2026.xlsx"
+POPULATION = "https://api.scb.se/OV0104/v1/doris/sv/ssd/START/BE/BE0101/BE0101A/BefolkningNy"
+POPULATION_QUERY = {
+    "query": [
+        {"code": "Region", "selection": {"filter": "all", "values": ["*"]}},
+        {"code": "ContentsCode", "selection": {"filter": "item", "values": ["BE0101N1"]}},
+        {"code": "Tid", "selection": {"filter": "top", "values": ["1"]}},
+    ],
+    "response": {"format": "json"},
+}
+TATORTER = "https://geodata.scb.se/geoserver/stat/wfs?service=WFS&version=2.0.0&request=GetFeature&typeNames=stat:Tatorter_2023&outputFormat=csv&propertyName=tatort,kommun,bef"
+POSTAL_CODES = "https://download.geonames.org/export/zip/SE.zip"
+NVDB = "https://api.trafikinfo.trafikverket.se/v2/data.json"
+NVDB_PAGE = 50000
+OUT = Path(__file__).resolve().parent.parent / "data" / "geo" / "SE"
+CACHE = Path(__file__).resolve().parent / "cache"
+TIMEZONE = "Europe/Stockholm"
+ONE_POSITION = {"Stockholm", "Göteborg", "Malmö"}
+UNMATCHED_POPULATION = 200
+
+
+def scb_codes(cache):
+    regions, municipalities = {}, {}
+    for cells in xlsx.rows(source.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()
+    return regions, municipalities
+
+
+def scb_population(cache):
+    body = json.dumps(POPULATION_QUERY).encode()
+    data = source.fetch(POPULATION, cache, "befolkning.json", data=body, headers={"Content-Type": "application/json"})
+    return {row["key"][0]: row["values"][0] for row in json.loads(data.decode("utf-8-sig"))["data"]}
+
+
+def scb_tatorter(cache):
+    text = source.fetch(TATORTER, cache, "tatorter.csv").decode("utf-8")
+    by_name = collections.defaultdict(list)
+    for r in csv.DictReader(io.StringIO(text)):
+        by_name[r["tatort"]].append((r["kommun"], int(r["bef"])))
+    return by_name
+
+
+def geonames(cache):
+    z = zipfile.ZipFile(io.BytesIO(source.fetch(POSTAL_CODES, cache, "SE.zip", magic=b"PK")))
+    rows = []
+    for line in z.read("SE.txt").decode("utf-8").splitlines():
+        f = line.split("\t")
+        lat, lon = (float(f[9]), float(f[10])) if f[9] and f[10] else (None, None)
+        rows.append({"code": f[1], "locality": f[2], "municipality": f[6], "lat": lat, "lon": lon})
+    return rows
+
+
+def nvdb_segments(cache, key):
+    path = cache / "nvdb-gatunamn.tsv"
+    if not path.exists():
+        with open(path.with_suffix(".part"), "w", encoding="utf-8") as out:
+            change = "0"
+            while True:
+                query = (
+                    f'<REQUEST><LOGIN authenticationkey="{key}"/>'
+                    f'<QUERY objecttype="Gatunamn" namespace="vägdata.nvdb_dk_o" schemaversion="1.0" limit="{NVDB_PAGE}" changeid="{change}">'
+                    "<FILTER><EQ name=\"Deleted\" value=\"false\"/></FILTER>"
+                    "<INCLUDE>Namn</INCLUDE><INCLUDE>Geometry.WKT-WGS84-3D</INCLUDE></QUERY></REQUEST>"
+                )
+                req = urllib.request.Request(NVDB, data=query.encode(), headers={"Content-Type": "text/xml"})
+                with urllib.request.urlopen(req, timeout=600) as r:
+                    result = json.load(r)["RESPONSE"]["RESULT"][0]
+                rows = result.get("Gatunamn", [])
+                for row in rows:
+                    m = re.match(r"LINESTRING Z \(([-\d.]+) ([-\d.]+) ", row.get("Geometry", {}).get("WKT-WGS84-3D", ""))
+                    name = " ".join(row.get("Namn", "").split())
+                    if m and name:
+                        out.write(f"{name}\t{m.group(1)}\t{m.group(2)}\n")
+                change = result["INFO"]["LASTCHANGEID"]
+                if len(rows) < NVDB_PAGE:
+                    break
+        path.with_suffix(".part").rename(path)
+    for line in path.read_text(encoding="utf-8").splitlines():
+        name, lon, lat = line.split("\t")
+        yield name, float(lat), float(lon)
+
+
+class Nearest:
+    """Nearest point by an equirectangular distance, over a degree grid."""
+
+    def __init__(self, points, cell=0.05):
+        self.cell = cell
+        self.grid = collections.defaultdict(list)
+        for lat, lon, value in points:
+            self.grid[(int(lat // cell), int(lon // cell))].append((lat, lon, value))
+
+    def find(self, lat, lon):
+        ci, cj = int(lat // self.cell), int(lon // self.cell)
+        best, best_d = None, math.inf
+        ring = 0
+        while ring < 400:
+            for i in range(ci - ring, ci + ring + 1):
+                for j in range(cj - ring, cj + ring + 1):
+                    if max(abs(i - ci), abs(j - cj)) != ring:
+                        continue
+                    for plat, plon, value in self.grid.get((i, j), ()):
+                        d = (plat - lat) ** 2 + ((plon - lon) * math.cos(math.radians(lat))) ** 2
+                        if d < best_d:
+                            best, best_d = value, d
+            if best is not None and math.sqrt(best_d) < ring * self.cell * math.cos(math.radians(lat)):
+                return best
+            ring += 1
+        return best
+
+
+def street_delivery(name, codes):
+    """The codes delivered to a street: the digit after the postort's own prefix says box, company or reply."""
+    if name in ONE_POSITION:
+        return [c for c in codes if c[1] != "0"]
+    largest = collections.Counter(c[:3] for c in codes).most_common(1)[0][1]
+    length = 3 if largest * 2 >= len(codes) else 2
+    return [c for c in codes if c[length] not in "018"]
+
+
+def municipality_of(name, rows, tatorter, municipalities):
+    named = [code for code, n in municipalities.items() if n == name]
+    if named:
+        return named[0], "kommun"
+    voted = collections.Counter(r["municipality"] for r in rows if r["municipality"] in municipalities)
+    matches = tatorter.get(name, [])
+    if matches:
+        in_vote = [m for m in matches if voted and m[0] == voted.most_common(1)[0][0]]
+        return max(in_vote or matches, key=lambda m: m[1])[0], "tatort"
+    if voted:
+        return voted.most_common(1)[0][0], "codes"
+    return None, "unplaced"
+
+
+def population_of(name, municipality, tatorter, municipalities, population):
+    matches = [m for m in tatorter.get(name, []) if m[0] == municipality]
+    if matches:
+        return str(max(m[1] for m in matches))
+    return population[municipality] if municipalities[municipality] == name else str(UNMATCHED_POPULATION)
+
+
+def well_cased(name):
+    return all(part[:1].isupper() and (len(part) == 1 or not part.isupper()) for part in re.split(r"[ -]", name))
+
+
+def localities(codes, tatorter, municipalities, population):
+    """Each postort with its municipality, weight, centroid and street-delivery codes."""
+    by_locality = collections.defaultdict(list)
+    for r in codes:
+        by_locality[r["locality"]].append(r)
+    out, how = {}, collections.Counter()
+    for name, rows in by_locality.items():
+        municipality, method = municipality_of(name, rows, tatorter, municipalities)
+        how[method] += 1
+        kept = street_delivery(name, [r["code"].replace(" ", "") for r in rows])
+        with_point = [r for r in rows if r["lat"] is not None]
+        if municipality is None or not kept or not with_point or not well_cased(name):
+            continue
+        lat = sum(r["lat"] for r in with_point) / len(with_point)
+        lon = sum(r["lon"] for r in with_point) / len(with_point)
+        out[name] = {"name": name, "municipality": municipality, "population": population_of(name, municipality, tatorter, municipalities, population), "lat": f"{lat:.4f}", "lon": f"{lon:.4f}", "codes": kept}
+    print(f"municipality by {dict(how)}; {len(by_locality) - len(out)} postorter dropped", file=sys.stderr)
+    return out
+
+
+def streets(segments, codes, localities, per_locality):
+    """The names with most segments per locality, each segment at its nearest code centroid."""
+    nearest = Nearest((r["lat"], r["lon"], r["locality"]) for r in codes if r["lat"] is not None and r["locality"] in localities)
+    count = collections.Counter()
+    for name, lat, lon in segments:
+        if name[0].isalpha():
+            count[(nearest.find(lat, lon), name)] += 1
+    of = collections.defaultdict(list)
+    for (locality, name), n in count.items():
+        of[locality].append((n, name))
+    return {locality: [{"name": name, "locality": locality, "segments": n} for n, name in sorted(named, key=lambda s: (-s[0], s[1]))[:per_locality]] for locality, named in of.items()}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--key-file", help="file holding the Trafikverket API key; TRAFIKVERKET_API_KEY otherwise")
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--streets-per-locality", type=int, default=10)
+    a = p.parse_args()
+    key = Path(a.key_file).read_text().strip() if a.key_file else os.environ.get("TRAFIKVERKET_API_KEY")
+    if not key:
+        sys.exit("set TRAFIKVERKET_API_KEY or pass --key-file")
+    cache, out = Path(a.cache), Path(a.out)
+    cache.mkdir(parents=True, exist_ok=True)
+    out.mkdir(parents=True, exist_ok=True)
+
+    regions, municipalities = scb_codes(cache)
+    population = scb_population(cache)
+    codes = geonames(cache)
+    places = localities(codes, scb_tatorter(cache), municipalities, population)
+    named = streets(nvdb_segments(cache, key), codes, places, a.streets_per_locality)
+    places = {name: l for name, l in places.items() if name in named}
+    empty = sorted(m for m in municipalities if not any(l["municipality"] == m for l in places.values()))
+    if empty:
+        sys.exit(f"municipalities without a locality: {empty}")
+
+    tsv.write(out / "region.tsv", ["code", "name", "population", "timezone"], [{"code": c, "name": n, "population": population[c], "timezone": TIMEZONE} for c, n in sorted(regions.items())])
+    tsv.write(out / "municipality.tsv", ["code", "name", "region", "population"], [{"code": c, "name": n, "region": c[:2], "population": population[c]} for c, n in sorted(municipalities.items())])
+    tsv.write(out / "locality.tsv", ["name", "municipality", "population", "lat", "lon"], [l for _, l in sorted(places.items())])
+    tsv.write(out / "postal-code.tsv", ["code", "locality"], sorted(({"code": f"{c[:3]} {c[3:]}", "locality": l["name"]} for l in places.values() for c in l["codes"]), key=lambda r: r["code"]))
+    tsv.write(out / "street.tsv", ["name", "locality", "segments"], [s for locality in sorted(named) for s in named[locality]])
+
+
+if __name__ == "__main__":
+    main()

data-import/geo-us.py

@@ -0,0 +1,202 @@
+#!/usr/bin/env python3
+"""Rebuild data/geo/US/*.tsv from the Census Bureau's Gazetteer, population estimates, ZCTA relationships and TIGER/Line files (public domain).
+
+    data-import/geo-us.py [--cache DIR] [--min-population N] [--streets-per-locality N] [--out DIR]
+"""
+import argparse
+import collections
+import concurrent.futures
+import csv
+import io
+import re
+import struct
+import sys
+import zipfile
+from pathlib import Path
+
+import source
+import tsv
+
+GAZETTEER = "https://www2.census.gov/geo/docs/maps-data/data/gazetteer/2026_Gazetteer/2026_Gaz_{}_national.zip"
+POPULATION = "https://www2.census.gov/programs-surveys/popest/datasets/2020-2025/{}"
+STATES = POPULATION.format("state/totals/NST-EST2025-ALLDATA.csv")
+COUNTIES = POPULATION.format("counties/totals/co-est2025-alldata.csv")
+PLACES = POPULATION.format("cities/totals/sub-est2025.csv")
+ZCTA_PLACE = "https://www2.census.gov/geo/docs/maps-data/data/rel2020/zcta520/tab20_zcta520_place20_natl.txt"
+TIGER = "https://www2.census.gov/geo/tiger/TIGER2025/{0}/tl_2025_{1}_{2}.zip"
+OUT = Path(__file__).resolve().parent.parent / "data" / "geo" / "US"
+CACHE = Path(__file__).resolve().parent / "cache"
+ESTIMATE = "POPESTIMATE2025"
+CDP = "57"
+HIGHWAY = re.compile(r"\b(I- |Hwy |Highway |Loop |Rte |Route |Rd )\d")
+SUFFIX = re.compile(r" (city and borough|city|town|village|borough|municipality|comunidad|zona urbana|metropolitan government|metro government|consolidated government|unified government|urban county|corporation|plantation)( \(balance\))?$")
+# Places whose Census name is a merged government's; the postal city is what an address carries.
+NAMES = {"1303440": "Athens", "1304204": "Augusta", "1349008": "Macon", "2148006": "Louisville", "3011397": "Butte", "4732742": "Hartsville", "4752006": "Nashville"}
+TIMEZONES = {
+    "AK": "America/Anchorage", "AL": "America/Chicago", "AR": "America/Chicago", "AZ": "America/Phoenix",
+    "CA": "America/Los_Angeles", "CO": "America/Denver", "CT": "America/New_York", "DC": "America/New_York",
+    "DE": "America/New_York", "FL": "America/New_York", "GA": "America/New_York", "HI": "Pacific/Honolulu",
+    "IA": "America/Chicago", "ID": "America/Boise", "IL": "America/Chicago", "IN": "America/Indiana/Indianapolis",
+    "KS": "America/Chicago", "KY": "America/New_York", "LA": "America/Chicago", "MA": "America/New_York",
+    "MD": "America/New_York", "ME": "America/New_York", "MI": "America/Detroit", "MN": "America/Chicago",
+    "MO": "America/Chicago", "MS": "America/Chicago", "MT": "America/Denver", "NC": "America/New_York",
+    "ND": "America/Chicago", "NE": "America/Chicago", "NH": "America/New_York", "NJ": "America/New_York",
+    "NM": "America/Denver", "NV": "America/Los_Angeles", "NY": "America/New_York", "OH": "America/New_York",
+    "OK": "America/Chicago", "OR": "America/Los_Angeles", "PA": "America/New_York", "PR": "America/Puerto_Rico",
+    "RI": "America/New_York", "SC": "America/New_York", "SD": "America/Chicago", "TN": "America/Chicago",
+    "TX": "America/Chicago", "UT": "America/Denver", "VA": "America/New_York", "VT": "America/New_York",
+    "WA": "America/Los_Angeles", "WI": "America/Chicago", "WV": "America/New_York", "WY": "America/Denver",
+}
+
+
+def text(data):
+    try:
+        return data.decode("utf-8-sig")
+    except UnicodeDecodeError:
+        return data.decode("latin-1")
+
+
+def gazetteer(cache, kind):
+    z = zipfile.ZipFile(io.BytesIO(source.fetch(GAZETTEER.format(kind), cache, f"gaz_{kind}.zip", magic=b"PK")))
+    rows = text(z.read(z.namelist()[0])).splitlines()
+    header = [h.strip() for h in rows[0].split("|")]
+    return [dict(zip(header, (c.strip() for c in row.split("|")))) for row in rows[1:]]
+
+
+def csv_rows(cache, url, name):
+    return list(csv.DictReader(io.StringIO(text(source.fetch(url, cache, name)))))
+
+
+def dbf_rows(data, wanted):
+    """The records of a dBASE file, the wanted fields only."""
+    count, header_len, record_len = struct.unpack("<xxxxIHH", data[:12])
+    fields, pos = [], 32
+    while data[pos] != 0x0D:
+        name = data[pos:pos + 11].split(b"\0")[0].decode()
+        fields.append((name, data[pos + 16]))
+        pos += 32
+    pos = header_len
+    for _ in range(count):
+        record = data[pos:pos + record_len]
+        pos += record_len
+        if record[:1] == b"*":
+            continue
+        row, at = {}, 1
+        for name, length in fields:
+            if name in wanted:
+                row[name] = record[at:at + length].decode("utf-8", "replace").strip()
+            at += length
+        yield row
+
+
+def tiger_zip(cache, kind, county):
+    return source.fetch(TIGER.format(kind.upper(), county, kind), cache, f"tl_{county}_{kind}.zip", magic=b"PK")
+
+
+def tiger(cache, kind, county, wanted):
+    z = zipfile.ZipFile(io.BytesIO(tiger_zip(cache, kind, county)))
+    return dbf_rows(z.read(f"tl_2025_{county}_{kind}.dbf"), wanted)
+
+
+def place_name(geoid, name):
+    if geoid in NAMES:
+        return NAMES[geoid]
+    stripped = SUFFIX.sub("", name)
+    if stripped == name:
+        print(f"{geoid}: no suffix stripped from {name!r}", file=sys.stderr)
+    return stripped
+
+
+def localities(cache, min_population, counties):
+    """Each shipped place with its county, population and centroid."""
+    place_population, county_part = {}, collections.defaultdict(list)
+    for r in csv_rows(cache, PLACES, "sub-est2025.csv"):
+        if r["SUMLEV"] == "162":
+            place_population[r["STATE"] + r["PLACE"]] = int(r[ESTIMATE])
+        elif r["SUMLEV"] == "157":
+            county_part[r["STATE"] + r["PLACE"]].append((int(r[ESTIMATE]), r["STATE"] + r["COUNTY"]))
+    out = {}
+    for r in gazetteer(cache, "place"):
+        geoid, population = r["GEOID"], place_population.get(r["GEOID"], 0)
+        if r["FUNCSTAT"] not in ("A", "F", "N") or r["LSAD"] == CDP or population < min_population or not county_part.get(geoid):
+            continue
+        county = max(county_part[geoid])[1]
+        if county not in counties:
+            print(f"{geoid} {r['NAME']}: county {county} unknown, dropped", file=sys.stderr)
+            continue
+        out[geoid] = {"code": geoid, "name": place_name(geoid, r["NAME"]), "municipality": county, "population": population, "lat": r["INTPTLAT"], "lon": r["INTPTLONG"]}
+    return out
+
+
+def postal_codes(cache, localities):
+    """Each ZCTA whose largest part inside an incorporated place lies in a shipped place."""
+    parts = {}
+    for r in csv.DictReader(io.StringIO(text(source.fetch(ZCTA_PLACE, cache, "zcta-place.txt"))), delimiter="|"):
+        if r["GEOID_ZCTA5_20"] and r["GEOID_PLACE_20"] and not r["NAMELSAD_PLACE_20"].endswith(" CDP"):
+            parts.setdefault(r["GEOID_ZCTA5_20"], []).append((int(r["AREALAND_PART"]), r["GEOID_PLACE_20"]))
+    largest = {zcta: max(p)[1] for zcta, p in parts.items()}
+    return {zcta: place for zcta, place in largest.items() if place in localities}
+
+
+def streets(cache, counties, locality_of_zcta, per_locality):
+    """The names with most TIGER address ranges per place, and the address ranges per ZCTA."""
+    with concurrent.futures.ThreadPoolExecutor(3) as pool:
+        list(pool.map(lambda c: (tiger_zip(cache, "addr", c), tiger_zip(cache, "featnames", c)), counties))
+    addresses, count = collections.Counter(), collections.Counter()
+    for county in counties:
+        zips = collections.defaultdict(set)
+        for r in tiger(cache, "addr", county, {"TLID", "ZIP"}):
+            if r["ZIP"] in locality_of_zcta:
+                zips[r["TLID"]].add(r["ZIP"])
+                addresses[r["ZIP"]] += 1
+        for r in tiger(cache, "featnames", county, {"TLID", "FULLNAME", "PAFLAG"}):
+            if r["PAFLAG"] == "P" and r["FULLNAME"] and not HIGHWAY.search(r["FULLNAME"]):
+                for z in zips.get(r["TLID"], ()):
+                    count[(locality_of_zcta[z], r["FULLNAME"])] += 1
+    of = collections.defaultdict(list)
+    for (locality, name), n in count.items():
+        of[locality].append((n, name))
+    named = {locality: [{"name": name, "locality": locality, "addresses": n} for n, name in sorted(ranked, key=lambda s: (-s[0], s[1]))[:per_locality]] for locality, ranked in of.items()}
+    return named, addresses
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--min-population", type=int, default=25000)
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--streets-per-locality", type=int, default=10)
+    a = p.parse_args()
+    cache, out = Path(a.cache), Path(a.out)
+    cache.mkdir(parents=True, exist_ok=True)
+    out.mkdir(parents=True, exist_ok=True)
+
+    state_population = {r["STATE"]: r[ESTIMATE] for r in csv_rows(cache, STATES, "nst-est2025.csv") if r["SUMLEV"] == "040"}
+    regions = {r["USPS"]: {"abbr": r["USPS"], "code": r["GEOID"], "name": r["NAME"], "population": state_population[r["GEOID"]], "timezone": TIMEZONES[r["USPS"]]} for r in gazetteer(cache, "state")}
+    county_population = {r["STATE"] + r["COUNTY"]: r[ESTIMATE] for r in csv_rows(cache, COUNTIES, "co-est2025.csv") if r["SUMLEV"] == "050"}
+    counties, unestimated = {}, collections.Counter()
+    for r in gazetteer(cache, "counties"):
+        if r["GEOID"] not in county_population:
+            unestimated[r["USPS"]] += 1
+            continue
+        counties[r["GEOID"]] = {"code": r["GEOID"], "name": r["NAME"], "region": r["USPS"], "population": county_population[r["GEOID"]]}
+    print(f"counties without a population estimate, dropped: {dict(unestimated)}", file=sys.stderr)
+
+    places = localities(cache, a.min_population, counties)
+    locality_of_zcta = postal_codes(cache, places)
+    named, addresses = streets(cache, sorted({l["municipality"] for l in places.values()}), locality_of_zcta, a.streets_per_locality)
+    for geoid in [l for l in places if l not in named]:
+        print(f"{geoid} {places[geoid]['name']}: no streets, dropped", file=sys.stderr)
+        del places[geoid]
+    kept_counties = {l["municipality"] for l in places.values()}
+    kept_regions = {counties[c]["region"] for c in kept_counties}
+
+    tsv.write(out / "region.tsv", ["abbr", "code", "name", "population", "timezone"], [r for _, r in sorted(regions.items()) if r["abbr"] in kept_regions])
+    tsv.write(out / "municipality.tsv", ["code", "name", "region", "population"], [c for _, c in sorted(counties.items()) if c["code"] in kept_counties])
+    tsv.write(out / "locality.tsv", ["code", "name", "municipality", "population", "lat", "lon"], [l for _, l in sorted(places.items())])
+    tsv.write(out / "postal-code.tsv", ["code", "locality", "addresses"], [{"code": z, "locality": l, "addresses": addresses[z]} for z, l in sorted(locality_of_zcta.items()) if addresses[z] and l in places])
+    tsv.write(out / "street.tsv", ["name", "locality", "addresses"], [s for locality in sorted(named) for s in named[locality]])
+
+
+if __name__ == "__main__":
+    main()

data-import/httpmethod.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/httpmethod.tsv from the IANA HTTP Method Registry.
+
+    data-import/httpmethod.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+A method ships when the register cites RFC 9110 section 9.3 or RFC 5789 for it, which
+is the eight HTTP defines and PATCH; the register's other entries do not. The
+register's `yes` and `no` ship as `true` and `false`, which a consumer's boolean reads.
+"""
+import argparse
+import csv
+import io
+import re
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.iana.org/assignments/http-methods/methods.csv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "httpmethod.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["idempotent", "method", "safe"]
+CORE = re.compile(r"\[RFC9110, Section 9\.3\.|\[RFC5789, Section 2\]")
+BOOLEAN = {"yes": "true", "no": "false"}
+SELECTOR = '[]{}"|'  # mirrors inSelector in table.go
+EXPECTED = 9
+
+
+def rows(text):
+    for r in csv.DictReader(io.StringIO(text)):
+        method = (r["Method Name"] or "").strip()
+        if not CORE.search(r["Reference"] or ""):
+            continue
+        if set(method) & set(SELECTOR):
+            sys.exit(f"{method}: a method holding one of {SELECTOR} is one a selector cannot spell")
+        answers = {}
+        for column in ("Safe", "Idempotent"):
+            answer = (r[column] or "").strip()
+            if answer not in BOOLEAN:
+                sys.exit(f"{method}: {column} {answer!r} is neither yes nor no")
+            answers[column] = BOOLEAN[answer]
+        yield {"idempotent": answers["Idempotent"], "method": method, "safe": answers["Safe"]}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = sorted(rows(source.fetch(a.source, a.cache, "http-methods.csv").decode("utf-8")), key=lambda r: r["method"])
+    if len(table) != EXPECTED:
+        sys.exit(f"{len(table)} methods cite RFC 9110 section 9.3 or RFC 5789, not {EXPECTED}; the register's Reference column has moved")
+    tsv.write(a.out, COLUMNS, table)
+
+
+if __name__ == "__main__":
+    main()

data-import/httpstatus.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/httpstatus.tsv from the IANA HTTP Status Code Registry.
+
+    data-import/httpstatus.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+What ships is the codes in use: a range, an unassigned code and a qualified reason are all skipped.
+"""
+import argparse
+import csv
+import io
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.iana.org/assignments/http-status-codes/http-status-codes-1.csv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "httpstatus.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["code", "reason"]
+
+
+def rows(text):
+    for r in csv.DictReader(io.StringIO(text)):
+        code, reason = r["Value"].strip(), r["Description"].strip()
+        if code.isdigit() and reason and "(" not in reason and reason != "Unassigned":
+            yield {"code": code, "reason": reason}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = rows(source.fetch(a.source, a.cache, "http-status-codes-1.csv").decode("utf-8"))
+    tsv.write(a.out, COLUMNS, sorted(table, key=lambda r: int(r["code"])))
+
+
+if __name__ == "__main__":
+    main()

data-import/language.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/language.tsv from datasets/language-codes (PDDL), the LoC ISO 639-2 register.
+
+    data-import/language.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+Only the 639-2 entries carrying a 639-1 code ship, since the alpha-2 code is the key.
+"""
+import argparse
+import csv
+import io
+import re
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://raw.githubusercontent.com/datasets/language-codes/main/data/language-codes-full.csv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "language.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["code", "code3", "name"]
+
+
+def name(english):
+    """The register lists every synonym; the first, without its qualifier, is the one a selector spells."""
+    return re.sub(r"\s*\([^)]*\)", "", english.split(";")[0]).strip()
+
+
+def rows(text):
+    for r in csv.DictReader(io.StringIO(text)):
+        if r["alpha2"]:
+            yield {"code": r["alpha2"], "code3": r["alpha3-t"] or r["alpha3-b"], "name": name(r["English"])}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = rows(source.fetch(a.source, a.cache, "language-codes-full.csv").decode("utf-8"))
+    tsv.write(a.out, COLUMNS, sorted(table, key=lambda r: r["code"]))
+
+
+if __name__ == "__main__":
+    main()

data-import/loglevel.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/loglevel.tsv from RFC 5424 and POSIX <syslog.h>.
+
+    data-import/loglevel.py [--source URL_OR_FILE] [--posix URL_OR_FILE] [--cache DIR] [--out FILE]
+
+Every severity in Table 2 ships, paired to POSIX's keywords by the order each source
+lists them, which holds only because a keyword prefixes the severity RFC 5424 numbers
+alike.
+"""
+import argparse
+import html
+import re
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.rfc-editor.org/rfc/rfc5424.txt"
+POSIX = "https://pubs.opengroup.org/onlinepubs/9799919799/basedefs/syslog.h.html"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "loglevel.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["code", "keyword", "severity"]
+TABLE = re.compile(r"Table 1\.\s+Syslog Message Facilities(.*?)Table 2\.\s+Syslog Message Severities", re.S)
+ROW = re.compile(r"^ +(\d) +([A-Z][a-z]+): ", re.M)
+SECTION = re.compile(r"severity level portion of the.*?macros:(.*?)The following shall be declared as functions", re.S)
+MACRO = re.compile(r"\bLOG_([A-Z]+)\b")
+EXPECTED = 8
+
+
+def severities(text):
+    table = TABLE.search(text)
+    if not table:
+        sys.exit("the RFC holds no text between the facility and the severity caption; its tables have moved")
+    return ROW.findall(table.group(1))
+
+
+def keywords(page):
+    section = SECTION.search(html.unescape(re.sub(r"<[^>]+>", "", page)))
+    if not section:
+        sys.exit("POSIX spells no severity list between its own caption and the function declarations; the page has moved")
+    return [m.lower() for m in MACRO.findall(section.group(1))]
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--posix", default=POSIX)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = sorted(severities(source.fetch(a.source, a.cache, "rfc5424.txt").decode("utf-8")))
+    codes = [code for code, _ in table]
+    if codes != [str(i) for i in range(EXPECTED)]:
+        sys.exit(f"the severity table numbers {codes}, not 0 through {EXPECTED - 1}")
+    words = keywords(source.fetch(a.posix, a.cache, "posix-syslog.h.html").decode("utf-8"))
+    if len(words) != EXPECTED:
+        sys.exit(f"POSIX lists {len(words)} severity macros, not {EXPECTED}: {words}")
+    rows = []
+    for (code, severity), keyword in zip(table, words):
+        if not severity.lower().startswith(keyword):
+            sys.exit(f"severity {code} is {severity} in the RFC and {keyword} in POSIX, which is no prefix of it")
+        rows.append({"code": code, "keyword": keyword, "severity": severity})
+    tsv.write(a.out, COLUMNS, rows)
+
+
+if __name__ == "__main__":
+    main()

data-import/mimetype.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/mimetype.tsv from mime-db (MIT), the IANA media type registry with extensions.
+
+    data-import/mimetype.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+Only types mime-db records as IANA-registered, with a filename extension, ship.
+"""
+import argparse
+import json
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://raw.githubusercontent.com/jshttp/mime-db/master/db.json"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "mimetype.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["ext", "type"]
+FIXUPS = {"application/mp4": "mp4s", "audio/mpeg": "mp3", "audio/ogg": "ogg", "video/quicktime": "mov"}
+
+
+def rows(db):
+    for mimetype, entry in db.items():
+        if entry.get("source") == "iana" and entry.get("extensions"):
+            yield {"ext": "." + FIXUPS.get(mimetype, entry["extensions"][0]), "type": mimetype}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = rows(json.loads(source.fetch(a.source, a.cache, "mime-db.json").decode("utf-8")))
+    tsv.write(a.out, COLUMNS, sorted(table, key=lambda r: r["type"]))
+
+
+if __name__ == "__main__":
+    main()

data-import/names-se.py

@@ -0,0 +1,54 @@
+#!/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 source
+import tsv
+import xlsx
+
+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", "da", "de", "del", "den", "der", "di", "dos", "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 = source.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(xlsx.rows(data, sheet), a.first)]
+    last = [{"name": cased(n), "count": c} for n, c in counted(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 +1,79 @@
+#!/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 source
+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])")
+PLACEHOLDERS = {"Baby", "Female", "Infant", "Male", "Notnamed", "Unknown", "Unnamed"}
+
+
+def csv_or_zip_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_or_zip_rows(data, r"yob\d{4}\.txt"):
+        if len(r) >= 4 and r[3].isdigit() and int(r[3]) >= from_year and r[0] not in PLACEHOLDERS:
+            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(source.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_or_zip_rows(source.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/port.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/port.tsv from the IANA Service Name and Transport Protocol Port Number Registry.
+
+    data-import/port.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+A row needs a service name and a numeric TCP port. A port the registry lists more than
+once keeps the first service it describes, or the first of them where it describes none,
+so a number selects one row.
+"""
+import argparse
+import csv
+import io
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.csv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "port.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["number", "service"]
+FLOOR = 4000
+
+
+def rows(text):
+    best, described = {}, set()
+    for r in csv.DictReader(io.StringIO(text)):
+        service, number = (r["Service Name"] or "").strip(), (r["Port Number"] or "").strip()
+        transport, description = (r["Transport Protocol"] or "").strip(), (r["Description"] or "").strip()
+        if transport != "tcp" or not service or not number.isdigit():
+            continue
+        if not 1 <= int(number) <= 65535:
+            sys.exit(f"{service}: port {number} is outside 1-65535")
+        if number not in best or (description and number not in described):
+            best[number] = {"number": number, "service": service}
+        if description:
+            described.add(number)
+    return sorted(best.values(), key=lambda r: int(r["number"]))
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = rows(source.fetch(a.source, a.cache, "service-names-port-numbers.csv").decode("utf-8"))
+    if len(table) < FLOOR:
+        sys.exit(f"only {len(table)} ports named a TCP service; the registry's columns have moved")
+    tsv.write(a.out, COLUMNS, table)
+
+
+if __name__ == "__main__":
+    main()

data-import/protocol.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/protocol.tsv from the IANA Protocol Numbers registry.
+
+    data-import/protocol.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
+
+A row needs a number and a keyword, which drops the seven numbers assigned to a class of
+protocols rather than to one; a keyword the registry reserves or marks deprecated goes
+too. Where the registry names no protocol beside the keyword, the keyword is the name.
+"""
+import argparse
+import csv
+import io
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.iana.org/assignments/protocol-numbers/protocol-numbers-1.csv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "protocol.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["keyword", "name", "number"]
+SKIP = ("Reserved", "deprecated")
+SELECTOR = '[]{}"|'  # mirrors inSelector in table.go
+
+
+def rows(text):
+    for r in csv.DictReader(io.StringIO(text)):
+        number, keyword = (r["Decimal"] or "").strip(), (r["Keyword"] or "").strip()
+        if not number.isdigit() or not keyword or any(s in keyword for s in SKIP):
+            continue
+        if not 0 <= int(number) <= 255:
+            sys.exit(f"{keyword}: protocol number {number} is outside 0-255")
+        yield {"keyword": keyword, "name": " ".join((r["Protocol"] or "").split()) or keyword, "number": number}
+
+
+def refuse_an_unselectable_row(table):
+    """What the loader refuses at New, and a name that names two rows rather than one."""
+    keywords, names = {}, {}
+    for r in table:
+        for column in ("keyword", "name"):
+            if set(r[column]) & set(SELECTOR):
+                sys.exit(f"{r['keyword']}: {column} {r[column]!r} holds one of {SELECTOR}, which a selector cannot spell")
+        if r["keyword"] in keywords:
+            sys.exit(f"{r['keyword']}: repeats the keyword of protocol {keywords[r['keyword']]}")
+        keywords[r["keyword"]] = r["number"]
+    for r in table:
+        if r["name"] != r["keyword"] and r["name"] in keywords:
+            sys.exit(f"{r['keyword']}: name {r['name']!r} is another protocol's keyword")
+        if r["name"] in names:
+            sys.exit(f"{r['keyword']}: name {r['name']!r} repeats {names[r['name']]}'s, so it selects neither")
+        names[r["name"]] = r["keyword"]
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = sorted(rows(source.fetch(a.source, a.cache, "protocol-numbers-1.csv").decode("utf-8")), key=lambda r: int(r["number"]))
+    refuse_an_unselectable_row(table)
+    tsv.write(a.out, COLUMNS, table)
+
+
+if __name__ == "__main__":
+    main()

data-import/source.py

@@ -0,0 +1,29 @@
+"""A source fetched once into the cache."""
+import re
+import sys
+import time
+import urllib.request
+from pathlib import Path
+
+
+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."""
+    if not re.match(r"^https?://", source):
+        return Path(source).read_bytes()
+    path = Path(cache) / name
+    if path.exists():
+        return path.read_bytes()
+    for attempt in range(1, 6):
+        req = urllib.request.Request(source, data=data, headers={"User-Agent": "fejkdata data-import", **(headers or {})})
+        try:
+            with urllib.request.urlopen(req, timeout=600) as r:
+                body = r.read()
+        except OSError:
+            body = b""
+        if body and body.startswith(magic) and b"Request Rejected" not in body[:512]:
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_bytes(body)
+            return body
+        if attempt < 5:
+            time.sleep(10 * attempt)
+    sys.exit(f"{source}: no valid download in 5 attempts")

data-import/territory.py

@@ -1,30 +1,28 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/country.tsv from datasets/country-codes (PDDL).
+"""Rebuild data/misc/territory.tsv from datasets/country-codes (PDDL).
 
-    data-import/country.py [--source URL_OR_FILE] [--out FILE]
+    data-import/territory.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
 """
 import argparse
 import csv
 import io
 import re
 import sys
-import urllib.request
 from pathlib import Path
 
+import source
+import tsv
+
 SOURCE = "https://raw.githubusercontent.com/datasets/country-codes/main/data/country-codes.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "country.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "territory.tsv"
-COLUMNS = ["alpha2", "alpha3", "calling-code", "capital", "currency", "flag", "languages", "name", "numeric", "tld"]
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["alpha2", "alpha3", "calling-code", "capital", "country", "currency", "flag", "languages", "name", "numeric", "tld"]
+SOVEREIGN = re.compile(r"^(?:Part of|Territor(?:y|ies) of|Crown dependency of|Commonwealth of|Associated with) ([A-Z]{2})$")
+STANDALONE = {"In contention", "International"}
 # Gaps in the source, keyed by alpha2.
 FIXUPS = {"TR": {"currency": "TRY"}}
 
 
-def read(source):
-    if re.match(r"^https?://", source):
-        with urllib.request.urlopen(source, timeout=60) as r:
-            return r.read().decode("utf-8")
-    return Path(source).read_text(encoding="utf-8")
-
-
 def flag(alpha2):
     return "".join(chr(0x1F1E6 + ord(c) - ord("A")) for c in alpha2)
 
@@ -38,6 +36,16 @@ def languages(field):
     return ",".join(p for p in field.split(",") if p)
 
 
+def country(alpha2, independent):
+    """The sovereign state the register records; a territory it records none for stands alone."""
+    m = SOVEREIGN.match(independent)
+    if m:
+        return m.group(1)
+    if independent == "Yes" or independent in STANDALONE:
+        return alpha2
+    sys.exit(f"{alpha2}: is_independent {independent!r} names no sovereign this script can read")
+
+
 def rows(text):
     for r in csv.DictReader(io.StringIO(text)):
         alpha2 = r["ISO3166-1-Alpha-2"]
@@ -46,6 +54,7 @@ def rows(text):
             "alpha3": r["ISO3166-1-Alpha-3"],
             "calling-code": calling_code(r["Dial"]),
             "capital": r["Capital"],
+            "country": country(alpha2, r["is_independent"]),
             "currency": r["ISO4217-currency_alphabetic_code"].split(",")[0],
             "flag": flag(alpha2),
             "languages": languages(r["Languages"]),
@@ -58,23 +67,18 @@ def rows(text):
             yield row
 
 
-def write(out, table):
-    lines = ["\t".join(COLUMNS)]
-    for row in sorted(table, key=lambda r: r["alpha2"]):
-        cells = [row[c] for c in COLUMNS]
-        assert not any("\t" in c or "\n" in c for c in cells), row
-        lines.append("\t".join(cells))
-    Path(out).write_text("\n".join(lines) + "\n", encoding="utf-8")
-    return len(lines) - 1
-
-
 def main():
     p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
     p.add_argument("--source", default=SOURCE)
     p.add_argument("--out", default=str(OUT))
     a = p.parse_args()
-    n = write(a.out, rows(read(a.source)))
+    table = sorted(rows(source.fetch(a.source, a.cache, "country-codes.csv").decode("utf-8")), key=lambda r: r["alpha2"])
-    print(f"{a.out}: {n} rows", file=sys.stderr)
+    shipped = {r["alpha2"] for r in table}
+    for r in table:
+        if r["country"] not in shipped:
+            sys.exit(f"{r['alpha2']}: country {r['country']} is no shipped territory; a sovereign the set drops leaves its territories unreadable")
+    tsv.write(a.out, COLUMNS, table)
 
 
 if __name__ == "__main__":

data-import/timezone.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/timezone.tsv from the IANA tzdb tarball (public domain) and GeoNames (CC BY 4.0).
+
+    data-import/timezone.py [--source URL_OR_FILE] [--cities URL_OR_FILE] [--cache DIR] [--out FILE] [--territories FILE]
+
+The offset is the zone's standard offset, the first field of its Zone rule's last
+continuation line, with a Link resolved to its target. The weight is the population
+GeoNames records in the zone's cities of 15,000 or more, never below that threshold,
+so a drawn zone is one people live in.
+"""
+import argparse
+import csv
+import io
+import re
+import sys
+import tarfile
+import zipfile
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://data.iana.org/time-zones/tzdata-latest.tar.gz"
+CITIES = "https://download.geonames.org/export/dump/cities15000.zip"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "timezone.tsv"
+TERRITORIES = Path(__file__).resolve().parent.parent / "data" / "misc" / "territory.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["offset", "territory", "weight", "zone"]
+REGIONS = ["africa", "antarctica", "asia", "australasia", "backward", "etcetera", "europe", "northamerica", "southamerica"]
+# GeoNames' own cutoff, so a zone it records no city in weighs less than one would.
+FLOOR = 15000
+
+
+def member(tar, name):
+    try:
+        f = tar.extractfile(name)
+    except KeyError:
+        f = None
+    if f is None:
+        sys.exit(f"{name}: the tarball no longer holds it as a file; the tzdb layout has moved")
+    return f.read().decode("utf-8")
+
+
+def offsets(tar):
+    """Every zone's standard offset, and every link's target."""
+    std, links = {}, {}
+    for name in REGIONS:
+        zone = None
+        for raw in member(tar, name).splitlines():
+            line = raw.split("#")[0].rstrip()
+            if not line.strip():
+                continue
+            if line.startswith("Zone"):
+                f = line.split()
+                zone, std[f[1]] = f[1], f[2]
+            elif line.startswith("Link"):
+                f = line.split()
+                links[f[2]], zone = f[1], None
+            elif line[0] in " \t" and zone:
+                std[zone] = line.split()[0]
+            else:
+                zone = None
+    return std, links
+
+
+def resolve(zone, std, links):
+    for _ in range(10):
+        if zone in std:
+            return std[zone]
+        if zone not in links:
+            return None
+        zone = links[zone]
+    return None
+
+
+def utc_offset(raw):
+    """±HH:MM from a tzdb STDOFF field, which writes the minutes and seconds only when it has them."""
+    m = re.match(r"^(-)?(\d{1,2})(?::(\d{2})(?::(\d{2}))?)?$", raw)
+    if not m or (m.group(4) or "00") != "00":
+        return None
+    return f"{'-' if m.group(1) else '+'}{int(m.group(2)):02d}:{m.group(3) or '00'}"
+
+
+def population(body):
+    """The population GeoNames records per timezone, summed over its cities."""
+    with zipfile.ZipFile(io.BytesIO(body)) as z:
+        text = z.read("cities15000.txt").decode("utf-8")
+    per = {}
+    for city in csv.reader(io.StringIO(text), delimiter="\t", quoting=csv.QUOTE_NONE):
+        if len(city) > 17 and city[17] and city[14].isdigit():
+            per[city[17]] = per.get(city[17], 0) + int(city[14])
+    return per
+
+
+def rows(tar, territories, pop):
+    std, links = offsets(tar)
+    for line in member(tar, "zone.tab").splitlines():
+        if line.startswith("#") or not line.strip():
+            continue
+        fields = line.split("\t")
+        if len(fields) < 3:
+            sys.exit(f"zone.tab: {line!r} has {len(fields)} fields; a row names a territory, a location and a zone")
+        territory, zone = fields[0], fields[2]
+        if territory not in territories:
+            continue
+        raw = resolve(zone, std, links)
+        if raw is None:
+            sys.exit(f"{zone}: the tarball gives it no Zone rule and no Link to one")
+        offset = utc_offset(raw)
+        if offset is None:
+            sys.exit(f"{zone}: standard offset {raw!r} is not a ±HH:MM the table can spell")
+        yield {"offset": offset, "territory": territory, "weight": max(pop.get(zone, 0), FLOOR), "zone": zone}
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--cities", default=CITIES)
+    p.add_argument("--territories", default=str(TERRITORIES))
+    a = p.parse_args()
+    shipped = {r["alpha2"] for r in csv.DictReader(io.StringIO(Path(a.territories).read_text(encoding="utf-8")), delimiter="\t")}
+    pop = population(source.fetch(a.cities, a.cache, "cities15000.zip", magic=b"PK"))
+    body = source.fetch(a.source, a.cache, "tzdata-latest.tar.gz", magic=b"\x1f\x8b")
+    with tarfile.open(fileobj=io.BytesIO(body)) as tar:
+        table = sorted(rows(tar, shipped, pop), key=lambda r: r["zone"])
+        print(f"tzdb {tar.extractfile('version').read().decode('utf-8').strip()}", file=sys.stderr)
+    linked = {r["territory"] for r in table}
+    if missing := shipped - linked:
+        sys.exit(f"no zone for {sorted(missing)}; a parent row without a child is a load error")
+    if (floored := sum(1 for r in table if r["weight"] == FLOOR)) > len(table) // 2:
+        sys.exit(f"{floored} of {len(table)} zones fell to the floor; GeoNames' population or timezone column has moved")
+    tsv.write(a.out, COLUMNS, table)
+
+
+if __name__ == "__main__":
+    main()

data-import/tld.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/tld.tsv from the IANA Root Zone Database.
+
+    data-import/tld.py [--source URL_OR_FILE] [--zone URL_OR_FILE] [--cache DIR] [--out FILE]
+
+A TLD ships when the database names a manager for it; one it marks "Not assigned" is a
+delegation the root zone no longer holds, and the zone file is fetched to prove the two
+agree. The key is the A-label the root zone holds; `unicode` is the form the database
+displays, less the bidi marks it wraps a right-to-left label in, and proved to punycode
+back to the key.
+"""
+import argparse
+import html
+import re
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://www.iana.org/domains/root/db"
+ZONE = "https://data.iana.org/TLD/tlds-alpha-by-domain.txt"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "tld.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["tld", "type", "unicode"]
+TYPES = ("country-code", "generic", "generic-restricted", "infrastructure", "sponsored")
+BIDI = {0x200E: None, 0x200F: None}
+ROW = re.compile(r'<a href="/domains/root/db/([^"]+)\.html">([^<]+)</a>.*?</td>\s*<td>([^<]*)</td>\s*<td>(.*?)</td>', re.S)
+
+
+def rows(page):
+    for a_label, shown, kind, manager in ROW.findall(page):
+        if "Not assigned" in manager:
+            continue
+        kind = kind.strip()
+        if kind not in TYPES:
+            sys.exit(f"{a_label}: the database types it {kind!r}, which is none of {TYPES}")
+        yield {"tld": "." + a_label, "type": kind, "unicode": html.unescape(shown).strip().translate(BIDI)}
+
+
+def prove_each_unicode_form_is_its_key(table):
+    """The displayed form is the key's own spelling, which punycode encodes back to."""
+    for r in table:
+        label = r["unicode"][1:]
+        encoded = label if label.isascii() else "xn--" + label.encode("punycode").decode("ascii")
+        if "." + encoded != r["tld"]:
+            sys.exit(f"{r['tld']}: the database displays {r['unicode']!r}, which is no spelling of it")
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--zone", default=ZONE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    table = sorted(rows(source.fetch(a.source, a.cache, "root-db.html").decode("utf-8")), key=lambda r: r["tld"])
+    prove_each_unicode_form_is_its_key(table)
+    listing = source.fetch(a.zone, a.cache, "tlds-alpha-by-domain.txt").decode("utf-8")
+    delegated = {"." + line.strip().lower() for line in listing.splitlines() if line.strip() and not line.startswith("#")}
+    shipped = {r["tld"] for r in table}
+    if len(table) != len(delegated) or shipped != delegated:
+        sys.exit(f"the database assigns {len(table)} rows where the root zone holds {len(delegated)} TLDs: {sorted(shipped ^ delegated)[:10]}")
+    tsv.write(a.out, COLUMNS, table)
+
+
+if __name__ == "__main__":
+    main()

data-import/tsv.py

@@ -0,0 +1,18 @@
+"""A table written as the loader admits it."""
+import re
+import sys
+from pathlib import Path
+
+
+def write(path, columns, rows):
+    """Write the rows as a TSV; the table needs two rows, and every cell must be non-empty and free of tabs, newlines and braces."""
+    lines = ["\t".join(columns)]
+    for row in rows:
+        cells = [str(row[c]) for c in columns]
+        if not all(cells) or any(re.search(r"[\t\n{}]", c) for c in cells):
+            raise ValueError(f"{path}: a cell is empty or holds a tab, newline or brace: {row}")
+        lines.append("\t".join(cells))
+    if len(lines) < 3:
+        raise ValueError(f"{path}: has {len(lines) - 1} rows below its header; a table is at least two rows")
+    Path(path).write_text("\n".join(lines) + "\n", encoding="utf-8")
+    print(f"{path}: {len(lines) - 1} rows", file=sys.stderr)

data-import/useragent.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+"""Rebuild data/misc/useragent.tsv from microlinkhq/top-user-agents (MIT).
+
+    data-import/useragent.py [--source URL] [--cache DIR] [--out FILE]
+
+The desktop and mobile lists partition the whole, so `device` is read rather than
+parsed. A row ships when the string names a browser and an operating system both.
+"""
+import argparse
+import json
+import re
+import sys
+from pathlib import Path
+
+import source
+import tsv
+
+SOURCE = "https://raw.githubusercontent.com/microlinkhq/top-user-agents/master/src"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "useragent.tsv"
+CACHE = Path(__file__).resolve().parent / "cache"
+COLUMNS = ["browser", "device", "os", "ua"]
+# First match wins: a Chromium fork this list does not name ships as Chrome.
+BROWSERS = [("Edge", r"Edg(A|iOS)?/"), ("Opera", r"OPR/"), ("Samsung Internet", r"SamsungBrowser/"),
+            ("Chrome", r"(Chrome|CriOS)/"), ("Firefox", r"(Firefox|FxiOS)/"), ("Safari", r"Version/[\d.]+ .*Safari")]
+SYSTEMS = [("iOS", r"iPhone|iPad|CPU OS "), ("Android", r"Android"), ("ChromeOS", r"CrOS"),
+           ("Windows", r"Windows NT"), ("macOS", r"Macintosh|Mac OS X"), ("Linux", r"X11.*Linux|Ubuntu")]
+
+
+def named(table, ua):
+    for name, pattern in table:
+        if re.search(pattern, ua):
+            return name
+    return ""
+
+
+def rows(desktop, mobile):
+    seen, kept = set(), []
+    for device, uas in (("desktop", desktop), ("mobile", mobile)):
+        for ua in uas:
+            browser, os = named(BROWSERS, ua), named(SYSTEMS, ua)
+            if not browser or not os:
+                print(f"dropped, naming no {'browser' if not browser else 'operating system'}: {ua}", file=sys.stderr)
+                continue
+            if ua in seen:
+                sys.exit(f"{ua}: listed twice, which would draw it twice as often")
+            seen.add(ua)
+            kept.append({"browser": browser, "device": device, "os": os, "ua": ua})
+    if len(kept) < 0.8 * (len(desktop) + len(mobile)):
+        sys.exit(f"only {len(kept)} of {len(desktop) + len(mobile)} strings named both; the tokens have moved")
+    return kept
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--source", default=SOURCE)
+    p.add_argument("--out", default=str(OUT))
+    a = p.parse_args()
+    lists = [json.loads(source.fetch(f"{a.source}/{n}.json", a.cache, f"top-user-agents-{n}.json")) for n in ("desktop", "mobile")]
+    tsv.write(a.out, COLUMNS, sorted(rows(*lists), key=lambda r: (r["browser"], r["os"], r["ua"])))
+
+
+if __name__ == "__main__":
+    main()

data-import/xlsx.py

@@ -0,0 +1,21 @@
+"""The rows of an xlsx sheet."""
+import io
+import xml.etree.ElementTree as ET
+import zipfile
+
+NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main", "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships"}
+
+
+def 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" % NS["m"])) for si in ET.fromstring(z.read("xl/sharedStrings.xml")).findall("m:si", 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" % NS["r"])] for s in ET.fromstring(z.read("xl/workbook.xml")).iter("{%s}sheet" % NS["m"])}
+    target = sheets[sheet] if sheet else next(iter(sheets.values()))
+    for row in ET.fromstring(z.read("xl/" + target)).findall(".//m:row", NS):
+        cells = []
+        for c in row.findall("m:c", NS):
+            v = c.find("m:v", NS)
+            cells.append("" if v is None else strings[int(v.text)] if c.get("t") == "s" else v.text)
+        yield cells

data.go

@@ -43,7 +43,7 @@ func loadData(sources []dataSource) (map[string]node, error) {
 			}
 			info, err := os.Stat(src.path)
 			if err != nil {
-				return nil, err
+				return nil, fmt.Errorf("data path %s: %w", src.path, err)
 			}
 			if !info.IsDir() {
 				return nil, fmt.Errorf("%s is not a directory", src.path)
@@ -62,6 +62,7 @@ func loadData(sources []dataSource) (map[string]node, error) {
 	if len(root) == 0 {
 		return nil, fmt.Errorf("no .json data found")
 	}
+	setTablePaths(root)
 	if err := linkTables(root); err != nil {
 		return nil, err
 	}

data/en_US/address.json

@@ -1,17 +1,8 @@
 {
   "format": "{street-number} {street}\n{locality}, {region} {postal-code}",
-  "street": {
+  "street": "{/geo.US.address.street}",
-    "format": "{name} {suffix}",
+  "street-number": "{/geo.US.address.street-number}",
-    "name": ["Adams", "Ashby", "Aspen", "Bay", "Birch", "Bridge", "Cedar", "Chestnut", "Church", "Clark", "Cypress", "Dogwood", "Elm", "Forest", "Franklin", "Garden", "Grove", "Hawthorn", "Hickory", "Highland", "Jackson", "Jefferson", "Juniper", "Lake", "Laurel", "Liberty", "Lincoln", "Madison", "Magnolia", "Maple", "Market", "Meadow", "Mill", "Oak", "Park", "Pine", "Poplar", "Prospect", "Ridge", "River", "Spruce", "Sunset", "Sycamore", "Union", "Walnut", "Washington", "Willow", "Wilson"],
+  "locality": "{/geo.US.address.locality}",
-    "suffix": ["Avenue", "Boulevard", "Circle", "Court", "Drive", "Lane", "Place", "Road", "Street", "Terrace", "Trail", "Way"]
+  "region": "{/geo.US.address.region}",
-  },
+  "postal-code": "{/geo.US.address.postal-code}"
-  "street-number": [
-    "{int(10,99)}",
-    { "format": "{int(100,999)}", "weight": 2 },
-    { "format": "{int(1000,9999)}", "weight": 0.5 },
-    { "format": "{int(10,99)}{int(100,999)}", "weight": 0.3 }
-  ],
-  "locality": ["Albany", "Atlanta", "Austin", "Baltimore", "Boston", "Charlotte", "Chicago", "Cincinnati", "Cleveland", "Columbus", "Dallas", "Denver", "Detroit", "El Paso", "Fort Worth", "Fresno", "Houston", "Indianapolis", "Jacksonville", "Kansas City", "Las Vegas", "Long Beach", "Los Angeles", "Memphis", "Mesa", "Miami", "Milwaukee", "Minneapolis", "Nashville", "New Orleans", "Oakland", "Oklahoma City", "Omaha", "Orlando", "Philadelphia", "Phoenix", "Pittsburgh", "Portland", "Raleigh", "Sacramento", "San Antonio", "San Diego", "San Jose", "Seattle", "St. Louis", "Tampa", "Tucson", "Tulsa"],
-  "region": ["AL", "AZ", "CA", "CO", "CT", "FL", "GA", "IL", "IN", "KY", "LA", "MA", "MD", "MI", "MN", "MO", "NC", "NJ", "NV", "NY", "OH", "OK", "OR", "PA", "TN", "TX", "VA", "WA", "WI"],
-  "postal-code": ["{int(10000,99999)}", { "format": "{int(10000,99999)}-{digits(4)}", "weight": 0.3 }]
 }

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 +1,16 @@
+{
+  "format": "{area}-{group}-{serial}",
+  "area": "9{digits(2)}",
+  "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": [null, { "format": "{.title.name} ", "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/en_US/title.json

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

data/en_US/title.tsv

@@ -0,0 +1,11 @@
+name	sex	share
+Dr	f	6
+Dr	m	6
+Miss	f	4
+Mr	m	60
+Mrs	f	22
+Ms	f	30
+Mx	f	1
+Mx	m	1
+Prof	f	3
+Prof	m	3

data/geo/SE/address.json

@@ -0,0 +1,14 @@
+{
+  "format": "{street} {street-number}\n{postal-code} {locality}",
+  "street": "{.street.name}",
+  "street-number": [
+    "{int(1,9)}",
+    "{int(10,99)}",
+    { "format": "{int(100,999)}", "weight": 0.2 },
+    { "format": "{int(1,9)}{upper(1)}", "weight": 0.2 },
+    { "format": "{int(10,99)}{upper(1)}", "weight": 0.1 },
+    { "format": "{int(100,999)}{upper(1)}", "weight": 0.05 }
+  ],
+  "postal-code": "{.postal-code.code}",
+  "locality": "{.locality.name}"
+}

data/geo/SE/locality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "locality.tsv", "key": "name", "parent": "municipality", "weight": "population" }

data/geo/SE/municipality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "municipality.tsv", "key": "code", "name": "name", "parent": "region", "weight": "population" }

data/geo/SE/municipality.tsv

@@ -0,0 +1,291 @@
+code	name	region	population
+0114	Upplands Väsby	01	50323
+0115	Vallentuna	01	35119
+0117	Österåker	01	49787
+0120	Värmdö	01	46635
+0123	Järfälla	01	88950
+0125	Ekerö	01	28910
+0126	Huddinge	01	114304
+0127	Botkyrka	01	95905
+0128	Salem	01	17507
+0136	Haninge	01	100895
+0138	Tyresö	01	49179
+0139	Upplands-Bro	01	32868
+0140	Nykvarn	01	12342
+0160	Täby	01	77744
+0162	Danderyd	01	32425
+0163	Sollentuna	01	77624
+0180	Stockholm	01	995574
+0181	Södertälje	01	102911
+0182	Nacka	01	112112
+0183	Sundbyberg	01	56274
+0184	Solna	01	85789
+0186	Lidingö	01	48377
+0187	Vaxholm	01	11822
+0188	Norrtälje	01	66585
+0191	Sigtuna	01	52767
+0192	Nynäshamn	01	30579
+0305	Håbo	03	22973
+0319	Älvkarleby	03	9552
+0330	Knivsta	03	21193
+0331	Heby	03	14345
+0360	Tierp	03	21104
+0380	Uppsala	03	248016
+0381	Enköping	03	48591
+0382	Östhammar	03	22138
+0428	Vingåker	04	8750
+0461	Gnesta	04	11458
+0480	Nyköping	04	58344
+0481	Oxelösund	04	12031
+0482	Flen	04	15362
+0483	Katrineholm	04	34154
+0484	Eskilstuna	04	107203
+0486	Strängnäs	04	39313
+0488	Trosa	04	14927
+0509	Ödeshög	05	5237
+0512	Ydre	05	3626
+0513	Kinda	05	9957
+0560	Boxholm	05	5517
+0561	Åtvidaberg	05	11467
+0562	Finspång	05	21623
+0563	Valdemarsvik	05	7525
+0580	Linköping	05	168035
+0581	Norrköping	05	144980
+0582	Söderköping	05	14789
+0583	Motala	05	43505
+0584	Vadstena	05	7490
+0586	Mjölby	05	28695
+0604	Aneby	06	6797
+0617	Gnosjö	06	9131
+0642	Mullsjö	06	7594
+0643	Habo	06	13456
+0662	Gislaved	06	28936
+0665	Vaggeryd	06	14825
+0680	Jönköping	06	147654
+0682	Nässjö	06	31587
+0683	Värnamo	06	34542
+0684	Sävsjö	06	11563
+0685	Vetlanda	06	27528
+0686	Eksjö	06	17792
+0687	Tranås	06	18604
+0760	Uppvidinge	07	9061
+0761	Lessebo	07	8289
+0763	Tingsryd	07	11966
+0764	Alvesta	07	19830
+0765	Älmhult	07	17653
+0767	Markaryd	07	9938
+0780	Växjö	07	98334
+0781	Ljungby	07	28280
+0821	Högsby	08	5321
+0834	Torsås	08	6984
+0840	Mörbylånga	08	16224
+0860	Hultsfred	08	13673
+0861	Mönsterås	08	13069
+0862	Emmaboda	08	9006
+0880	Kalmar	08	72704
+0881	Nybro	08	19951
+0882	Oskarshamn	08	26923
+0883	Västervik	08	36447
+0884	Vimmerby	08	15384
+0885	Borgholm	08	10666
+0980	Gotland	09	60971
+1060	Olofström	10	13000
+1080	Karlskrona	10	66301
+1081	Ronneby	10	28741
+1082	Karlshamn	10	31751
+1083	Sölvesborg	10	17430
+1214	Svalöv	12	14543
+1230	Staffanstorp	12	27303
+1231	Burlöv	12	20101
+1233	Vellinge	12	37816
+1256	Östra Göinge	12	13978
+1257	Örkelljunga	12	10277
+1260	Bjuv	12	15985
+1261	Kävlinge	12	32477
+1262	Lomma	12	24715
+1263	Svedala	12	23581
+1264	Skurup	12	17099
+1265	Sjöbo	12	19337
+1266	Hörby	12	15562
+1267	Höör	12	17518
+1270	Tomelilla	12	13639
+1272	Bromölla	12	12470
+1273	Osby	12	12947
+1275	Perstorp	12	7235
+1276	Klippan	12	17714
+1277	Åstorp	12	16449
+1278	Båstad	12	16026
+1280	Malmö	12	365644
+1281	Lund	12	131590
+1282	Landskrona	12	47309
+1283	Helsingborg	12	152091
+1284	Höganäs	12	28430
+1285	Eslöv	12	34922
+1286	Ystad	12	32106
+1287	Trelleborg	12	47269
+1290	Kristianstad	12	86379
+1291	Simrishamn	12	18890
+1292	Ängelholm	12	45110
+1293	Hässleholm	12	52114
+1315	Hylte	13	10196
+1380	Halmstad	13	106084
+1381	Laholm	13	26595
+1382	Falkenberg	13	47337
+1383	Varberg	13	69070
+1384	Kungsbacka	13	85792
+1401	Härryda	14	40003
+1402	Partille	14	41060
+1407	Öckerö	14	12771
+1415	Stenungsund	14	27851
+1419	Tjörn	14	16092
+1421	Orust	14	15352
+1427	Sotenäs	14	9104
+1430	Munkedal	14	10354
+1435	Tanum	14	12773
+1438	Dals-Ed	14	4606
+1439	Färgelanda	14	6376
+1440	Ale	14	32576
+1441	Lerum	14	43570
+1442	Vårgårda	14	12474
+1443	Bollebygd	14	9802
+1444	Grästorp	14	5555
+1445	Essunga	14	5560
+1446	Karlsborg	14	7023
+1447	Gullspång	14	5031
+1452	Tranemo	14	11839
+1460	Bengtsfors	14	9076
+1461	Mellerud	14	9052
+1462	Lilla Edet	14	14442
+1463	Mark	14	35155
+1465	Svenljunga	14	10747
+1466	Herrljunga	14	9497
+1470	Vara	14	16088
+1471	Götene	14	13286
+1472	Tibro	14	11338
+1473	Töreboda	14	9043
+1480	Göteborg	14	608993
+1481	Mölndal	14	71420
+1482	Kungälv	14	50313
+1484	Lysekil	14	13907
+1485	Uddevalla	14	57010
+1486	Strömstad	14	13482
+1487	Vänersborg	14	40041
+1488	Trollhättan	14	59003
+1489	Alingsås	14	42722
+1490	Borås	14	114872
+1491	Ulricehamn	14	24985
+1492	Åmål	14	11906
+1493	Mariestad	14	24583
+1494	Lidköping	14	40425
+1495	Skara	14	18707
+1496	Skövde	14	57995
+1497	Hjo	14	9350
+1498	Tidaholm	14	12805
+1499	Falköping	14	32806
+1715	Kil	17	12061
+1730	Eda	17	8412
+1737	Torsby	17	11321
+1760	Storfors	17	3788
+1761	Hammarö	17	16992
+1762	Munkfors	17	3625
+1763	Forshaga	17	11520
+1764	Grums	17	9004
+1765	Årjäng	17	9825
+1766	Sunne	17	13356
+1780	Karlstad	17	98084
+1781	Kristinehamn	17	23756
+1782	Filipstad	17	9776
+1783	Hagfors	17	11418
+1784	Arvika	17	25547
+1785	Säffle	17	14899
+1814	Lekeberg	18	8606
+1860	Laxå	18	5423
+1861	Hallsberg	18	16120
+1862	Degerfors	18	9278
+1863	Hällefors	18	6321
+1864	Ljusnarsberg	18	4369
+1880	Örebro	18	160140
+1881	Kumla	18	22681
+1882	Askersund	18	11477
+1883	Karlskoga	18	30180
+1884	Nora	18	10639
+1885	Lindesberg	18	23141
+1904	Skinnskatteberg	19	4256
+1907	Surahammar	19	9845
+1960	Kungsör	19	8694
+1961	Hallstahammar	19	16653
+1962	Norberg	19	5452
+1980	Västerås	19	160634
+1981	Sala	19	22843
+1982	Fagersta	19	13072
+1983	Köping	19	25729
+1984	Arboga	19	13980
+2021	Vansbro	20	6752
+2023	Malung-Sälen	20	10254
+2026	Gagnef	20	10384
+2029	Leksand	20	16137
+2031	Rättvik	20	10998
+2034	Orsa	20	6851
+2039	Älvdalen	20	6882
+2061	Smedjebacken	20	10823
+2062	Mora	20	20540
+2080	Falun	20	59945
+2081	Borlänge	20	51425
+2082	Säter	20	11223
+2083	Hedemora	20	15281
+2084	Avesta	20	22417
+2085	Ludvika	20	26634
+2101	Ockelbo	21	5715
+2104	Hofors	21	9281
+2121	Ovanåker	21	11341
+2132	Nordanstig	21	9262
+2161	Ljusdal	21	18445
+2180	Gävle	21	103838
+2181	Sandviken	21	38360
+2182	Söderhamn	21	24545
+2183	Bollnäs	21	26243
+2184	Hudiksvall	21	37528
+2260	Ånge	22	9044
+2262	Timrå	22	17521
+2280	Härnösand	22	24515
+2281	Sundsvall	22	99048
+2282	Kramfors	22	17491
+2283	Sollefteå	22	18396
+2284	Örnsköldsvik	22	55443
+2303	Ragunda	23	5146
+2305	Bräcke	23	6035
+2309	Krokom	23	15680
+2313	Strömsund	23	11023
+2321	Åre	23	12693
+2326	Berg	23	7108
+2361	Härjedalen	23	10175
+2380	Östersund	23	64979
+2401	Nordmaling	24	6942
+2403	Bjurholm	24	2359
+2404	Vindeln	24	5417
+2409	Robertsfors	24	6690
+2417	Norsjö	24	3968
+2418	Malå	24	2962
+2421	Storuman	24	5577
+2422	Sorsele	24	2357
+2425	Dorotea	24	2294
+2460	Vännäs	24	9132
+2462	Vilhelmina	24	6229
+2463	Åsele	24	2694
+2480	Umeå	24	134249
+2481	Lycksele	24	12118
+2482	Skellefteå	24	78150
+2505	Arvidsjaur	25	6089
+2506	Arjeplog	25	2599
+2510	Jokkmokk	25	4701
+2513	Överkalix	25	3201
+2514	Kalix	25	15391
+2518	Övertorneå	25	4057
+2521	Pajala	25	5857
+2523	Gällivare	25	17233
+2560	Älvsbyn	25	7774
+2580	Luleå	25	79645
+2581	Piteå	25	42447
+2582	Boden	25	28049
+2583	Haparanda	25	9151
+2584	Kiruna	25	22426

data/geo/SE/postal-code.json

@@ -0,0 +1 @@
+{ "format": "{code}", "rows": "postal-code.tsv", "key": "code", "parent": "locality" }

data/geo/SE/region.json

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

data/geo/SE/region.tsv

@@ -0,0 +1,22 @@
+code	name	population	timezone
+01	Stockholms län	2473307	Europe/Stockholm
+03	Uppsala län	407912	Europe/Stockholm
+04	Södermanlands län	301542	Europe/Stockholm
+05	Östergötlands län	472446	Europe/Stockholm
+06	Jönköpings län	370009	Europe/Stockholm
+07	Kronobergs län	203351	Europe/Stockholm
+08	Kalmar län	246352	Europe/Stockholm
+09	Gotlands län	60971	Europe/Stockholm
+10	Blekinge län	157223	Europe/Stockholm
+12	Skåne län	1428626	Europe/Stockholm
+13	Hallands län	345074	Europe/Stockholm
+14	Västra Götalands län	1772821	Europe/Stockholm
+17	Värmlands län	283384	Europe/Stockholm
+18	Örebro län	308375	Europe/Stockholm
+19	Västmanlands län	281158	Europe/Stockholm
+20	Dalarnas län	286546	Europe/Stockholm
+21	Gävleborgs län	284558	Europe/Stockholm
+22	Västernorrlands län	241458	Europe/Stockholm
+23	Jämtlands län	132839	Europe/Stockholm
+24	Västerbottens län	281138	Europe/Stockholm
+25	Norrbottens län	248620	Europe/Stockholm

data/geo/SE/street.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "street.tsv", "parent": "locality", "weight": "segments" }

data/geo/US/address.json

@@ -0,0 +1,13 @@
+{
+  "format": "{street-number} {street}\n{locality}, {region} {postal-code}",
+  "street": "{.street.name}",
+  "street-number": [
+    "{int(10,99)}",
+    { "format": "{int(100,999)}", "weight": 2 },
+    { "format": "{int(1000,9999)}", "weight": 0.5 },
+    { "format": "{int(10,99)}{int(100,999)}", "weight": 0.3 }
+  ],
+  "locality": "{.locality.name}",
+  "region": "{.region.abbr}",
+  "postal-code": "{.postal-code.code}"
+}

data/geo/US/locality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "locality.tsv", "key": "code", "name": "name", "parent": "municipality", "weight": "population" }

data/geo/US/municipality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "municipality.tsv", "key": "code", "name": "name", "parent": "region", "weight": "population" }

data/geo/US/municipality.tsv

@@ -0,0 +1,666 @@
+code	name	region	population
+01001	Autauga County	AL	61920
+01003	Baldwin County	AL	267761
+01031	Coffee County	AL	56953
+01055	Etowah County	AL	103886
+01069	Houston County	AL	110318
+01073	Jefferson County	AL	665742
+01077	Lauderdale County	AL	97135
+01081	Lee County	AL	189881
+01083	Limestone County	AL	122928
+01089	Madison County	AL	433516
+01097	Mobile County	AL	411658
+01101	Montgomery County	AL	225891
+01103	Morgan County	AL	126483
+01113	Russell County	AL	58898
+01117	Shelby County	AL	238552
+01125	Tuscaloosa County	AL	241368
+02020	Anchorage Municipality	AK	287155
+02090	Fairbanks North Star Borough	AK	93972
+02110	Juneau City and Borough	AK	31609
+04003	Cochise County	AZ	126332
+04005	Coconino County	AZ	144368
+04013	Maricopa County	AZ	4689558
+04015	Mohave County	AZ	228102
+04019	Pima County	AZ	1074685
+04021	Pinal County	AZ	539380
+04025	Yavapai County	AZ	252552
+04027	Yuma County	AZ	224449
+05007	Benton County	AR	332554
+05031	Craighead County	AR	116957
+05045	Faulkner County	AR	133979
+05051	Garland County	AR	99695
+05055	Greene County	AR	47411
+05069	Jefferson County	AR	62987
+05085	Lonoke County	AR	76664
+05091	Miller County	AR	42357
+05115	Pope County	AR	64976
+05119	Pulaski County	AR	404611
+05125	Saline County	AR	133288
+05131	Sebastian County	AR	130641
+05143	Washington County	AR	271213
+06001	Alameda County	CA	1636630
+06007	Butte County	CA	209211
+06013	Contra Costa County	CA	1170070
+06019	Fresno County	CA	1035456
+06023	Humboldt County	CA	131647
+06025	Imperial County	CA	181411
+06029	Kern County	CA	927068
+06031	Kings County	CA	154327
+06037	Los Angeles County	CA	9694934
+06039	Madera County	CA	167927
+06041	Marin County	CA	253694
+06047	Merced County	CA	297260
+06053	Monterey County	CA	433729
+06055	Napa County	CA	132949
+06059	Orange County	CA	3149507
+06061	Placer County	CA	442081
+06065	Riverside County	CA	2544916
+06067	Sacramento County	CA	1618460
+06069	San Benito County	CA	70082
+06071	San Bernardino County	CA	2224091
+06073	San Diego County	CA	3282248
+06075	San Francisco County	CA	826079
+06077	San Joaquin County	CA	823815
+06079	San Luis Obispo County	CA	282367
+06081	San Mateo County	CA	743568
+06083	Santa Barbara County	CA	442065
+06085	Santa Clara County	CA	1914391
+06087	Santa Cruz County	CA	258852
+06089	Shasta County	CA	181648
+06095	Solano County	CA	455376
+06097	Sonoma County	CA	486444
+06099	Stanislaus County	CA	557719
+06101	Sutter County	CA	98787
+06107	Tulare County	CA	485146
+06111	Ventura County	CA	830851
+06113	Yolo County	CA	224410
+08001	Adams County	CO	554668
+08005	Arapahoe County	CO	673820
+08013	Boulder County	CO	328560
+08014	Broomfield County	CO	79174
+08031	Denver County	CO	740613
+08035	Douglas County	CO	399396
+08041	El Paso County	CO	757040
+08059	Jefferson County	CO	580451
+08069	Larimer County	CO	377292
+08077	Mesa County	CO	162845
+08101	Pueblo County	CO	169277
+08123	Weld County	CO	378426
+09110	Capitol Planning Region	CT	994115
+09120	Greater Bridgeport Planning Region	CT	337697
+09130	Lower Connecticut River Valley Planning Region	CT	177311
+09140	Naugatuck Valley Planning Region	CT	463349
+09160	Northwest Hills Planning Region	CT	114690
+09170	South Central Connecticut Planning Region	CT	578741
+09180	Southeastern Connecticut Planning Region	CT	284015
+09190	Western Connecticut Planning Region	CT	640482
+10001	Kent County	DE	194786
+10003	New Castle County	DE	588026
+11001	District of Columbia	DC	693645
+12001	Alachua County	FL	290028
+12005	Bay County	FL	204479
+12009	Brevard County	FL	663982
+12011	Broward County	FL	2013317
+12031	Duval County	FL	1062963
+12033	Escambia County	FL	333834
+12035	Flagler County	FL	140360
+12057	Hillsborough County	FL	1574115
+12061	Indian River County	FL	172799
+12069	Lake County	FL	456068
+12071	Lee County	FL	875607
+12073	Leon County	FL	299048
+12081	Manatee County	FL	468200
+12083	Marion County	FL	442660
+12086	Miami-Dade County	FL	2802029
+12091	Okaloosa County	FL	221810
+12095	Orange County	FL	1528002
+12097	Osceola County	FL	481718
+12099	Palm Beach County	FL	1575726
+12103	Pinellas County	FL	948563
+12105	Polk County	FL	874790
+12111	St. Lucie County	FL	402449
+12115	Sarasota County	FL	479958
+12117	Seminole County	FL	491884
+12127	Volusia County	FL	606573
+13015	Bartow County	GA	120800
+13021	Bibb County	GA	157556
+13031	Bulloch County	GA	86949
+13045	Carroll County	GA	131036
+13051	Chatham County	GA	311855
+13057	Cherokee County	GA	299273
+13059	Clarke County	GA	129921
+13067	Cobb County	GA	793345
+13077	Coweta County	GA	160240
+13089	DeKalb County	GA	774394
+13095	Dougherty County	GA	82616
+13097	Douglas County	GA	154293
+13113	Fayette County	GA	125156
+13115	Floyd County	GA	101378
+13121	Fulton County	GA	1098791
+13135	Gwinnett County	GA	1018099
+13139	Hall County	GA	226568
+13151	Henry County	GA	264922
+13153	Houston County	GA	178214
+13179	Liberty County	GA	70313
+13185	Lowndes County	GA	122867
+13215	Muscogee County	GA	202171
+13245	Richmond County	GA	206559
+13285	Troup County	GA	72844
+13313	Whitfield County	GA	106212
+16001	Ada County	ID	546141
+16005	Bannock County	ID	91591
+16019	Bonneville County	ID	135771
+16027	Canyon County	ID	275123
+16055	Kootenai County	ID	191864
+16057	Latah County	ID	41842
+16065	Madison County	ID	55172
+16069	Nez Perce County	ID	42905
+16083	Twin Falls County	ID	97539
+17001	Adams County	IL	64267
+17007	Boone County	IL	53568
+17019	Champaign County	IL	209972
+17031	Cook County	IL	5194625
+17037	DeKalb County	IL	101835
+17043	DuPage County	IL	934298
+17089	Kane County	IL	525757
+17093	Kendall County	IL	145470
+17095	Knox County	IL	47767
+17097	Lake County	IL	719339
+17111	McHenry County	IL	317751
+17113	McLean County	IL	171419
+17115	Macon County	IL	99300
+17119	Madison County	IL	263110
+17143	Peoria County	IL	178553
+17161	Rock Island County	IL	141869
+17163	St. Clair County	IL	250708
+17167	Sangamon County	IL	194170
+17179	Tazewell County	IL	130049
+17183	Vermilion County	IL	71259
+17197	Will County	IL	712253
+17201	Winnebago County	IL	283674
+18003	Allen County	IN	402329
+18005	Bartholomew County	IN	85729
+18011	Boone County	IN	80689
+18019	Clark County	IN	130451
+18035	Delaware County	IN	113106
+18039	Elkhart County	IN	208774
+18043	Floyd County	IN	82153
+18053	Grant County	IN	66524
+18057	Hamilton County	IN	387036
+18059	Hancock County	IN	90969
+18063	Hendricks County	IN	193510
+18067	Howard County	IN	83904
+18081	Johnson County	IN	174262
+18089	Lake County	IN	504612
+18091	LaPorte County	IN	111294
+18095	Madison County	IN	135088
+18097	Marion County	IN	992196
+18105	Monroe County	IN	143345
+18127	Porter County	IN	176049
+18141	St. Joseph County	IN	272861
+18157	Tippecanoe County	IN	190456
+18163	Vanderburgh County	IN	181995
+18167	Vigo County	IN	106512
+18177	Wayne County	IN	66169
+19013	Black Hawk County	IA	131532
+19033	Cerro Gordo County	IA	42372
+19049	Dallas County	IA	118457
+19061	Dubuque County	IA	99381
+19103	Johnson County	IA	160044
+19113	Linn County	IA	232028
+19127	Marshall County	IA	39890
+19153	Polk County	IA	516546
+19155	Pottawattamie County	IA	92996
+19163	Scott County	IA	175259
+19169	Story County	IA	101291
+19179	Wapello County	IA	35210
+19193	Woodbury County	IA	106649
+20045	Douglas County	KS	120920
+20055	Finney County	KS	37505
+20057	Ford County	KS	33993
+20091	Johnson County	KS	636906
+20103	Leavenworth County	KS	84590
+20155	Reno County	KS	61539
+20161	Riley County	KS	72598
+20169	Saline County	KS	53377
+20173	Sedgwick County	KS	538433
+20177	Shawnee County	KS	178607
+20209	Wyandotte County	KS	170597
+21015	Boone County	KY	145316
+21047	Christian County	KY	70115
+21059	Daviess County	KY	104898
+21067	Fayette County	KY	329751
+21073	Franklin County	KY	52649
+21093	Hardin County	KY	113482
+21101	Henderson County	KY	44255
+21111	Jefferson County	KY	795222
+21113	Jessamine County	KY	57147
+21117	Kenton County	KY	175779
+21145	McCracken County	KY	67553
+21151	Madison County	KY	101696
+21209	Scott County	KY	62262
+21227	Warren County	KY	149375
+22015	Bossier Parish	LA	131867
+22017	Caddo Parish	LA	224226
+22019	Calcasieu Parish	LA	208466
+22033	East Baton Rouge Parish	LA	456180
+22045	Iberia Parish	LA	66846
+22051	Jefferson Parish	LA	431398
+22071	Orleans Parish	LA	362154
+22073	Ouachita Parish	LA	158542
+22079	Rapides Parish	LA	125877
+22103	St. Tammany Parish	LA	279108
+22109	Terrebonne Parish	LA	104163
+23001	Androscoggin County	ME	116487
+23005	Cumberland County	ME	317222
+23019	Penobscot County	ME	157967
+24003	Anne Arundel County	MD	603380
+24021	Frederick County	MD	302883
+24031	Montgomery County	MD	1074582
+24033	Prince George's County	MD	970374
+24043	Washington County	MD	157731
+24045	Wicomico County	MD	106899
+24510	Baltimore city	MD	569997
+25001	Barnstable County	MA	233539
+25003	Berkshire County	MA	128224
+25005	Bristol County	MA	593640
+25009	Essex County	MA	826653
+25013	Hampden County	MA	464338
+25015	Hampshire County	MA	164065
+25017	Middlesex County	MA	1669979
+25021	Norfolk County	MA	739749
+25023	Plymouth County	MA	546829
+25025	Suffolk County	MA	791891
+25027	Worcester County	MA	888502
+26017	Bay County	MI	102123
+26025	Calhoun County	MI	133408
+26049	Genesee County	MI	401093
+26065	Ingham County	MI	289709
+26075	Jackson County	MI	159552
+26077	Kalamazoo County	MI	263795
+26081	Kent County	MI	675232
+26099	Macomb County	MI	886221
+26111	Midland County	MI	83754
+26121	Muskegon County	MI	177901
+26125	Oakland County	MI	1288337
+26139	Ottawa County	MI	308459
+26145	Saginaw County	MI	187688
+26147	St. Clair County	MI	160486
+26161	Washtenaw County	MI	370214
+26163	Wayne County	MI	1769038
+27003	Anoka County	MN	381605
+27013	Blue Earth County	MN	70634
+27019	Carver County	MN	114379
+27027	Clay County	MN	67734
+27037	Dakota County	MN	457710
+27053	Hennepin County	MN	1284784
+27099	Mower County	MN	40971
+27109	Olmsted County	MN	166731
+27123	Ramsey County	MN	541623
+27131	Rice County	MN	69939
+27137	St. Louis County	MN	200518
+27139	Scott County	MN	159017
+27141	Sherburne County	MN	104194
+27145	Stearns County	MN	164110
+27147	Steele County	MN	37464
+27163	Washington County	MN	286895
+27169	Winona County	MN	50523
+28033	DeSoto County	MS	197918
+28035	Forrest County	MS	79034
+28047	Harrison County	MS	217136
+28049	Hinds County	MS	211888
+28071	Lafayette County	MS	59597
+28075	Lauderdale County	MS	70317
+28081	Lee County	MS	83731
+28089	Madison County	MS	116298
+28105	Oktibbeha County	MS	51896
+28121	Rankin County	MS	162181
+28151	Washington County	MS	40446
+29019	Boone County	MO	191746
+29021	Buchanan County	MO	83540
+29031	Cape Girardeau County	MO	83999
+29037	Cass County	MO	115859
+29043	Christian County	MO	96725
+29047	Clay County	MO	265032
+29051	Cole County	MO	77908
+29077	Greene County	MO	309286
+29095	Jackson County	MO	732994
+29097	Jasper County	MO	127428
+29183	St. Charles County	MO	426499
+29189	St. Louis County	MO	990911
+29510	St. Louis city	MO	278144
+30013	Cascade County	MT	85029
+30029	Flathead County	MT	115429
+30031	Gallatin County	MT	128740
+30049	Lewis and Clark County	MT	75331
+30063	Missoula County	MT	123513
+30093	Silver Bow County	MT	36118
+30111	Yellowstone County	MT	172692
+31001	Adams County	NE	31071
+31019	Buffalo County	NE	51172
+31053	Dodge County	NE	38057
+31055	Douglas County	NE	606460
+31079	Hall County	NE	63633
+31109	Lancaster County	NE	334049
+31119	Madison County	NE	36106
+31141	Platte County	NE	35649
+31153	Sarpy County	NE	208303
+32003	Clark County	NV	2407226
+32019	Lyon County	NV	65088
+32031	Washoe County	NV	509386
+32510	Carson City	NV	58571
+33011	Hillsborough County	NH	433415
+33013	Merrimack County	NH	158078
+33017	Strafford County	NH	135043
+34001	Atlantic County	NJ	278657
+34003	Bergen County	NJ	977026
+34007	Camden County	NJ	535799
+34011	Cumberland County	NJ	157148
+34013	Essex County	NJ	896379
+34017	Hudson County	NJ	735033
+34021	Mercer County	NJ	399289
+34023	Middlesex County	NJ	883335
+34025	Monmouth County	NJ	651035
+34031	Passaic County	NJ	531624
+34039	Union County	NJ	601863
+35001	Bernalillo County	NM	667601
+35005	Chaves County	NM	63364
+35009	Curry County	NM	46655
+35013	Doña Ana County	NM	229091
+35015	Eddy County	NM	62509
+35025	Lea County	NM	74749
+35035	Otero County	NM	70368
+35043	Sandoval County	NM	159565
+35045	San Juan County	NM	120340
+35049	Santa Fe County	NM	156907
+36001	Albany County	NY	321225
+36007	Broome County	NY	195736
+36011	Cayuga County	NY	74365
+36013	Chautauqua County	NY	124126
+36015	Chemung County	NY	80415
+36027	Dutchess County	NY	300708
+36029	Erie County	NY	946741
+36047	Kings County	NY	2653963
+36055	Monroe County	NY	750506
+36059	Nassau County	NY	1398939
+36063	Niagara County	NY	208912
+36065	Oneida County	NY	226392
+36067	Onondaga County	NY	466584
+36071	Orange County	NY	417669
+36083	Rensselaer County	NY	160510
+36091	Saratoga County	NY	241343
+36093	Schenectady County	NY	162581
+36103	Suffolk County	NY	1546090
+36109	Tompkins County	NY	104047
+36119	Westchester County	NY	1015743
+37001	Alamance County	NC	186177
+37019	Brunswick County	NC	174702
+37021	Buncombe County	NC	277417
+37025	Cabarrus County	NC	249725
+37035	Catawba County	NC	170172
+37049	Craven County	NC	105025
+37051	Cumberland County	NC	338473
+37057	Davidson County	NC	180182
+37063	Durham County	NC	347240
+37067	Forsyth County	NC	401718
+37071	Gaston County	NC	246558
+37081	Guilford County	NC	562234
+37097	Iredell County	NC	211798
+37101	Johnston County	NC	256448
+37105	Lee County	NC	70258
+37119	Mecklenburg County	NC	1233383
+37127	Nash County	NC	99365
+37129	New Hanover County	NC	245959
+37133	Onslow County	NC	217175
+37135	Orange County	NC	152498
+37147	Pitt County	NC	182936
+37151	Randolph County	NC	149516
+37159	Rowan County	NC	155096
+37179	Union County	NC	267674
+37183	Wake County	NC	1257235
+37191	Wayne County	NC	122278
+37195	Wilson County	NC	81150
+38015	Burleigh County	ND	103251
+38017	Cass County	ND	201794
+38035	Grand Forks County	ND	74501
+38059	Morton County	ND	34601
+38089	Stark County	ND	34013
+38101	Ward County	ND	68233
+38105	Williams County	ND	41767
+39003	Allen County	OH	100881
+39009	Athens County	OH	63197
+39017	Butler County	OH	400128
+39023	Clark County	OH	135340
+39035	Cuyahoga County	OH	1232925
+39041	Delaware County	OH	242032
+39045	Fairfield County	OH	169752
+39049	Franklin County	OH	1361536
+39057	Greene County	OH	174322
+39061	Hamilton County	OH	838418
+39063	Hancock County	OH	75034
+39085	Lake County	OH	232217
+39089	Licking County	OH	185564
+39093	Lorain County	OH	323219
+39095	Lucas County	OH	423347
+39099	Mahoning County	OH	224706
+39101	Marion County	OH	65115
+39103	Medina County	OH	185025
+39109	Miami County	OH	112634
+39113	Montgomery County	OH	539598
+39119	Muskingum County	OH	87014
+39133	Portage County	OH	163404
+39139	Richland County	OH	124893
+39151	Stark County	OH	373771
+39153	Summit County	OH	538376
+39155	Trumbull County	OH	198972
+39159	Union County	OH	73446
+39165	Warren County	OH	257181
+39169	Wayne County	OH	116758
+39173	Wood County	OH	134176
+40027	Cleveland County	OK	303973
+40031	Comanche County	OK	122158
+40047	Garfield County	OK	61779
+40101	Muskogee County	OK	66708
+40109	Oklahoma County	OK	822125
+40119	Payne County	OK	83889
+40125	Pottawatomie County	OK	75102
+40143	Tulsa County	OK	698782
+40147	Washington County	OK	54037
+41003	Benton County	OR	97728
+41005	Clackamas County	OR	426280
+41017	Deschutes County	OR	213072
+41029	Jackson County	OR	221795
+41033	Josephine County	OR	87867
+41039	Lane County	OR	381584
+41043	Linn County	OR	132843
+41047	Marion County	OR	355777
+41051	Multnomah County	OR	795391
+41067	Washington County	OR	611708
+41071	Yamhill County	OR	110024
+42003	Allegheny County	PA	1225035
+42011	Berks County	PA	440072
+42013	Blair County	PA	119541
+42027	Centre County	PA	157393
+42043	Dauphin County	PA	293351
+42045	Delaware County	PA	580937
+42049	Erie County	PA	265832
+42069	Lackawanna County	PA	216502
+42071	Lancaster County	PA	563159
+42075	Lebanon County	PA	146380
+42077	Lehigh County	PA	384383
+42079	Luzerne County	PA	332126
+42081	Lycoming County	PA	112587
+42091	Montgomery County	PA	877643
+42095	Northampton County	PA	324411
+42101	Philadelphia County	PA	1574281
+42133	York County	PA	473197
+44003	Kent County	RI	173495
+44007	Providence County	RI	678179
+45003	Aiken County	SC	181515
+45007	Anderson County	SC	219930
+45013	Beaufort County	SC	204433
+45015	Berkeley County	SC	274666
+45019	Charleston County	SC	436200
+45035	Dorchester County	SC	178397
+45041	Florence County	SC	138504
+45045	Greenville County	SC	583125
+45051	Horry County	SC	427551
+45063	Lexington County	SC	317588
+45077	Pickens County	SC	139198
+45079	Richland County	SC	434956
+45083	Spartanburg County	SC	380857
+45085	Sumter County	SC	105067
+45091	York County	SC	306887
+46011	Brookings County	SD	37635
+46013	Brown County	SD	37561
+46099	Minnehaha County	SD	212691
+46103	Pennington County	SD	116792
+47001	Anderson County	TN	82066
+47003	Bedford County	TN	55273
+47009	Blount County	TN	143820
+47011	Bradley County	TN	115465
+47037	Davidson County	TN	745904
+47063	Hamblen County	TN	68843
+47065	Hamilton County	TN	390833
+47093	Knox County	TN	511453
+47113	Madison County	TN	100790
+47119	Maury County	TN	118131
+47125	Montgomery County	TN	249935
+47141	Putnam County	TN	86612
+47149	Rutherford County	TN	386352
+47157	Shelby County	TN	910226
+47163	Sullivan County	TN	163759
+47165	Sumner County	TN	215538
+47179	Washington County	TN	141199
+47187	Williamson County	TN	272061
+47189	Wilson County	TN	175033
+48005	Angelina County	TX	88154
+48027	Bell County	TX	402248
+48029	Bexar County	TX	2160088
+48037	Bowie County	TX	92696
+48039	Brazoria County	TX	419080
+48041	Brazos County	TX	249088
+48061	Cameron County	TX	433946
+48085	Collin County	TX	1297179
+48091	Comal County	TX	209166
+48099	Coryell County	TX	85592
+48113	Dallas County	TX	2661397
+48121	Denton County	TX	1069346
+48135	Ector County	TX	173801
+48139	Ellis County	TX	240867
+48141	El Paso County	TX	877858
+48157	Fort Bend County	TX	975191
+48167	Galveston County	TX	372207
+48181	Grayson County	TX	153613
+48183	Gregg County	TX	126095
+48187	Guadalupe County	TX	201111
+48201	Harris County	TX	5045026
+48209	Hays County	TX	304390
+48215	Hidalgo County	TX	921549
+48231	Hunt County	TX	123336
+48245	Jefferson County	TX	254321
+48251	Johnson County	TX	218048
+48257	Kaufman County	TX	209235
+48265	Kerr County	TX	54037
+48277	Lamar County	TX	51503
+48303	Lubbock County	TX	328906
+48309	McLennan County	TX	272020
+48323	Maverick County	TX	58823
+48329	Midland County	TX	187855
+48339	Montgomery County	TX	781194
+48347	Nacogdoches County	TX	66035
+48349	Navarro County	TX	57181
+48355	Nueces County	TX	352992
+48367	Parker County	TX	184767
+48381	Randall County	TX	152351
+48397	Rockwall County	TX	140738
+48423	Smith County	TX	252549
+48439	Tarrant County	TX	2248466
+48441	Taylor County	TX	150077
+48451	Tom Green County	TX	120602
+48453	Travis County	TX	1389670
+48465	Val Verde County	TX	47835
+48469	Victoria County	TX	92656
+48471	Walker County	TX	83842
+48479	Webb County	TX	281224
+48485	Wichita County	TX	129555
+48491	Williamson County	TX	752827
+49005	Cache County	UT	145000
+49011	Davis County	UT	381227
+49021	Iron County	UT	67141
+49035	Salt Lake County	UT	1220916
+49045	Tooele County	UT	87461
+49049	Utah County	UT	759859
+49053	Washington County	UT	213670
+49057	Weber County	UT	278174
+50007	Chittenden County	VT	169115
+51059	Fairfax County	VA	1167873
+51107	Loudoun County	VA	449749
+51121	Montgomery County	VA	98434
+51510	Alexandria city	VA	160662
+51540	Charlottesville city	VA	44388
+51550	Chesapeake city	VA	255332
+51590	Danville city	VA	41647
+51600	Fairfax city	VA	26772
+51630	Fredericksburg city	VA	30393
+51650	Hampton city	VA	137315
+51660	Harrisonburg city	VA	50839
+51680	Lynchburg city	VA	81347
+51683	Manassas city	VA	44332
+51700	Newport News city	VA	183230
+51710	Norfolk city	VA	231013
+51730	Petersburg city	VA	33734
+51740	Portsmouth city	VA	96777
+51760	Richmond city	VA	237257
+51770	Roanoke city	VA	99111
+51775	Salem city	VA	25816
+51790	Staunton city	VA	26801
+51800	Suffolk city	VA	104699
+51810	Virginia Beach city	VA	453737
+51840	Winchester city	VA	28272
+53005	Benton County	WA	221722
+53007	Chelan County	WA	81941
+53011	Clark County	WA	532119
+53015	Cowlitz County	WA	114885
+53021	Franklin County	WA	102612
+53025	Grant County	WA	105727
+53033	King County	WA	2344939
+53035	Kitsap County	WA	283374
+53053	Pierce County	WA	946288
+53057	Skagit County	WA	132975
+53061	Snohomish County	WA	870656
+53063	Spokane County	WA	558344
+53067	Thurston County	WA	304261
+53071	Walla Walla County	WA	62361
+53073	Whatcom County	WA	236392
+53075	Whitman County	WA	48512
+53077	Yakima County	WA	259185
+54011	Cabell County	WV	91183
+54039	Kanawha County	WV	172381
+54061	Monongalia County	WV	107991
+54069	Ohio County	WV	40496
+54107	Wood County	WV	82385
+55009	Brown County	WI	275803
+55025	Dane County	WI	590375
+55031	Douglas County	WI	43990
+55035	Eau Claire County	WI	109033
+55039	Fond du Lac County	WI	104669
+55059	Kenosha County	WI	168448
+55063	La Crosse County	WI	121339
+55071	Manitowoc County	WI	81710
+55073	Marathon County	WI	139432
+55079	Milwaukee County	WI	924216
+55087	Outagamie County	WI	195894
+55089	Ozaukee County	WI	94346
+55097	Portage County	WI	71943
+55101	Racine County	WI	198919
+55105	Rock County	WI	166472
+55117	Sheboygan County	WI	118047
+55131	Washington County	WI	139238
+55133	Waukesha County	WI	417210
+55139	Winnebago County	WI	174218
+56001	Albany County	WY	38558
+56005	Campbell County	WY	48145
+56021	Laramie County	WY	102938
+56025	Natrona County	WY	80526

data/geo/US/postal-code.json

@@ -0,0 +1 @@
+{ "format": "{code}", "rows": "postal-code.tsv", "key": "code", "parent": "locality", "weight": "addresses" }

data/geo/US/region.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "region.tsv", "key": "abbr", "name": "name", "weight": "population" }

data/geo/US/region.tsv

@@ -0,0 +1,51 @@
+abbr	code	name	population	timezone
+AK	02	Alaska	737270	America/Anchorage
+AL	01	Alabama	5193088	America/Chicago
+AR	05	Arkansas	3114791	America/Chicago
+AZ	04	Arizona	7623818	America/Phoenix
+CA	06	California	39355309	America/Los_Angeles
+CO	08	Colorado	6012561	America/Denver
+CT	09	Connecticut	3688496	America/New_York
+DC	11	District of Columbia	693645	America/New_York
+DE	10	Delaware	1059952	America/New_York
+FL	12	Florida	23462518	America/New_York
+GA	13	Georgia	11302748	America/New_York
+IA	19	Iowa	3238387	America/Chicago
+ID	16	Idaho	2029733	America/Boise
+IL	17	Illinois	12719141	America/Chicago
+IN	18	Indiana	6973333	America/Indiana/Indianapolis
+KS	20	Kansas	2977220	America/Chicago
+KY	21	Kentucky	4606864	America/New_York
+LA	22	Louisiana	4618189	America/Chicago
+MA	25	Massachusetts	7154084	America/New_York
+MD	24	Maryland	6265347	America/New_York
+ME	23	Maine	1414874	America/New_York
+MI	26	Michigan	10127884	America/Detroit
+MN	27	Minnesota	5830405	America/Chicago
+MO	29	Missouri	6270541	America/Chicago
+MS	28	Mississippi	2954160	America/Chicago
+MT	30	Montana	1144694	America/Denver
+NC	37	North Carolina	11197968	America/New_York
+ND	38	North Dakota	799358	America/Chicago
+NE	31	Nebraska	2018006	America/Chicago
+NH	33	New Hampshire	1415342	America/New_York
+NJ	34	New Jersey	9548215	America/New_York
+NM	35	New Mexico	2125498	America/Denver
+NV	32	Nevada	3282188	America/Los_Angeles
+NY	36	New York	20002427	America/New_York
+OH	39	Ohio	11900510	America/New_York
+OK	40	Oklahoma	4123288	America/Chicago
+OR	41	Oregon	4273586	America/Los_Angeles
+PA	42	Pennsylvania	13059432	America/New_York
+RI	44	Rhode Island	1114521	America/New_York
+SC	45	South Carolina	5570274	America/New_York
+SD	46	South Dakota	935094	America/Chicago
+TN	47	Tennessee	7315076	America/Chicago
+TX	48	Texas	31709821	America/Chicago
+UT	49	Utah	3538904	America/Denver
+VA	51	Virginia	8880107	America/New_York
+VT	50	Vermont	644663	America/New_York
+WA	53	Washington	8001020	America/Los_Angeles
+WI	55	Wisconsin	5972787	America/Chicago
+WV	54	West Virginia	1766147	America/New_York
+WY	56	Wyoming	588753	America/Denver

data/geo/US/street.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "street.tsv", "parent": "locality", "weight": "addresses" }

data/misc/car.json

@@ -1,10 +1 @@
-[
+{ "format": "{make} {model}", "rows": "car.tsv" }
-  { "format": "{maker} {model}", "maker": "BMW", "model": ["3 Series", "5 Series", "X3", "X5"] },
-  { "format": "{maker} {model}", "maker": "Ford", "model": ["Fiesta", "Focus", "Mustang", "Explorer"] },
-  { "format": "{maker} {model}", "maker": "Honda", "model": ["Civic", "Accord", "CR-V", "Jazz"] },
-  { "format": "{maker} {model}", "maker": "Mercedes-Benz", "model": ["A-Class", "C-Class", "E-Class", "GLC"] },
-  { "format": "{maker} {model}", "maker": "Tesla", "model": ["Model 3", "Model S", "Model X", "Model Y"] },
-  { "format": "{maker} {model}", "maker": "Toyota", "model": ["Corolla", "Camry", "RAV4", "Yaris"] },
-  { "format": "{maker} {model}", "maker": "Volkswagen", "model": ["Golf", "Passat", "Polo", "Tiguan"] },
-  { "format": "{maker} {model}", "maker": "Volvo", "model": ["XC40", "XC60", "XC90", "V60"] }
-]

data/misc/car.tsv

@@ -0,0 +1,33 @@
+make	model
+BMW	3 Series
+BMW	5 Series
+BMW	X3
+BMW	X5
+Ford	Explorer
+Ford	Fiesta
+Ford	Focus
+Ford	Mustang
+Honda	Accord
+Honda	CR-V
+Honda	Civic
+Honda	Jazz
+Mercedes-Benz	A-Class
+Mercedes-Benz	C-Class
+Mercedes-Benz	E-Class
+Mercedes-Benz	GLC
+Tesla	Model 3
+Tesla	Model S
+Tesla	Model X
+Tesla	Model Y
+Toyota	Camry
+Toyota	Corolla
+Toyota	RAV4
+Toyota	Yaris
+Volkswagen	Golf
+Volkswagen	Passat
+Volkswagen	Polo
+Volkswagen	Tiguan
+Volvo	V60
+Volvo	XC40
+Volvo	XC60
+Volvo	XC90

data/misc/country.json

@@ -1 +0,0 @@
-{ "format": "{name}", "rows": "country.tsv", "key": "alpha2", "name": "name" }

data/misc/country.tsv

@@ -1,242 +0,0 @@
-alpha2	alpha3	calling-code	capital	currency	flag	languages	name	numeric	tld
-AD	AND	376	Andorra la Vella	EUR	🇦🇩	ca	Andorra	020	.ad
-AE	ARE	971	Abu Dhabi	AED	🇦🇪	ar-AE,fa,en,hi,ur	United Arab Emirates	784	.ae
-AF	AFG	93	Kabul	AFN	🇦🇫	fa-AF,ps,uz-AF,tk	Afghanistan	004	.af
-AG	ATG	1-268	St. John's	XCD	🇦🇬	en-AG	Antigua & Barbuda	028	.ag
-AI	AIA	1-264	The Valley	XCD	🇦🇮	en-AI	Anguilla	660	.ai
-AL	ALB	355	Tirana	ALL	🇦🇱	sq,el	Albania	008	.al
-AM	ARM	374	Yerevan	AMD	🇦🇲	hy	Armenia	051	.am
-AO	AGO	244	Luanda	AOA	🇦🇴	pt-AO	Angola	024	.ao
-AR	ARG	54	Buenos Aires	ARS	🇦🇷	es-AR,en,it,de,fr,gn	Argentina	032	.ar
-AS	ASM	1-684	Pago Pago	USD	🇦🇸	en-AS,sm,to	American Samoa	016	.as
-AT	AUT	43	Vienna	EUR	🇦🇹	de-AT,hr,hu,sl	Austria	040	.at
-AU	AUS	61	Canberra	AUD	🇦🇺	en-AU	Australia	036	.au
-AW	ABW	297	Oranjestad	AWG	🇦🇼	nl-AW,pap,es,en	Aruba	533	.aw
-AX	ALA	358	Mariehamn	EUR	🇦🇽	sv-AX	Åland Islands	248	.ax
-AZ	AZE	994	Baku	AZN	🇦🇿	az,ru,hy	Azerbaijan	031	.az
-BA	BIH	387	Sarajevo	BAM	🇧🇦	bs,hr-BA,sr-BA	Bosnia	070	.ba
-BB	BRB	1-246	Bridgetown	BBD	🇧🇧	en-BB	Barbados	052	.bb
-BD	BGD	880	Dhaka	BDT	🇧🇩	bn-BD,en	Bangladesh	050	.bd
-BE	BEL	32	Brussels	EUR	🇧🇪	nl-BE,fr-BE,de-BE	Belgium	056	.be
-BF	BFA	226	Ouagadougou	XOF	🇧🇫	fr-BF,mos	Burkina Faso	854	.bf
-BG	BGR	359	Sofia	EUR	🇧🇬	bg,tr-BG,rom	Bulgaria	100	.bg
-BH	BHR	973	Manama	BHD	🇧🇭	ar-BH,en,fa,ur	Bahrain	048	.bh
-BI	BDI	257	Gitega	BIF	🇧🇮	fr-BI,rn	Burundi	108	.bi
-BJ	BEN	229	Porto-Novo	XOF	🇧🇯	fr-BJ	Benin	204	.bj
-BL	BLM	590	Gustavia	EUR	🇧🇱	fr	St. Barthélemy	652	.gp
-BM	BMU	1-441	Hamilton	BMD	🇧🇲	en-BM,pt	Bermuda	060	.bm
-BN	BRN	673	Bandar Seri Begawan	BND	🇧🇳	ms-BN,en-BN	Brunei	096	.bn
-BO	BOL	591	Sucre	BOB	🇧🇴	es-BO,qu,ay	Bolivia	068	.bo
-BR	BRA	55	Brasilia	BRL	🇧🇷	pt-BR,es,en,fr	Brazil	076	.br
-BS	BHS	1-242	Nassau	BSD	🇧🇸	en-BS	Bahamas	044	.bs
-BT	BTN	975	Thimphu	INR	🇧🇹	dz	Bhutan	064	.bt
-BW	BWA	267	Gaborone	BWP	🇧🇼	en-BW,tn-BW	Botswana	072	.bw
-BY	BLR	375	Minsk	BYN	🇧🇾	be,ru	Belarus	112	.by
-BZ	BLZ	501	Belmopan	BZD	🇧🇿	en-BZ,es	Belize	084	.bz
-CA	CAN	1	Ottawa	CAD	🇨🇦	en-CA,fr-CA,iu	Canada	124	.ca
-CC	CCK	61	West Island	AUD	🇨🇨	ms-CC,en	Cocos Islands	166	.cc
-CD	COD	243	Kinshasa	CDF	🇨🇩	fr-CD,ln,ktu,kg,sw,lua	Congo - Kinshasa	180	.cd
-CF	CAF	236	Bangui	XAF	🇨🇫	fr-CF,sg,ln,kg	Central African Republic	140	.cf
-CG	COG	242	Brazzaville	XAF	🇨🇬	fr-CG,kg,ln-CG	Congo - Brazzaville	178	.cg
-CH	CHE	41	Bern	CHF	🇨🇭	de-CH,fr-CH,it-CH,rm	Switzerland	756	.ch
-CI	CIV	225	Yamoussoukro	XOF	🇨🇮	fr-CI	Côte d’Ivoire	384	.ci
-CK	COK	682	Avarua	NZD	🇨🇰	en-CK,mi	Cook Islands	184	.ck
-CL	CHL	56	Santiago	CLP	🇨🇱	es-CL	Chile	152	.cl
-CM	CMR	237	Yaounde	XAF	🇨🇲	en-CM,fr-CM	Cameroon	120	.cm
-CN	CHN	86	Beijing	CNY	🇨🇳	zh-CN,yue,wuu,dta,ug,za	China	156	.cn
-CO	COL	57	Bogota	COP	🇨🇴	es-CO	Colombia	170	.co
-CR	CRI	506	San Jose	CRC	🇨🇷	es-CR,en	Costa Rica	188	.cr
-CU	CUB	53	Havana	CUP	🇨🇺	es-CU,pap	Cuba	192	.cu
-CV	CPV	238	Praia	CVE	🇨🇻	pt-CV	Cape Verde	132	.cv
-CW	CUW	599	 Willemstad	XCG	🇨🇼	nl,pap	Curaçao	531	.cw
-CX	CXR	61	Flying Fish Cove	AUD	🇨🇽	en,zh,ms-CX	Christmas Island	162	.cx
-CY	CYP	357	Nicosia	EUR	🇨🇾	el-CY,tr-CY,en	Cyprus	196	.cy
-CZ	CZE	420	Prague	CZK	🇨🇿	cs,sk	Czechia	203	.cz
-DE	DEU	49	Berlin	EUR	🇩🇪	de	Germany	276	.de
-DJ	DJI	253	Djibouti	DJF	🇩🇯	fr-DJ,ar,so-DJ,aa	Djibouti	262	.dj
-DK	DNK	45	Copenhagen	DKK	🇩🇰	da-DK,en,fo,de-DK	Denmark	208	.dk
-DM	DMA	1-767	Roseau	XCD	🇩🇲	en-DM	Dominica	212	.dm
-DO	DOM	1-809	Santo Domingo	DOP	🇩🇴	es-DO	Dominican Republic	214	.do
-DZ	DZA	213	Algiers	DZD	🇩🇿	ar-DZ	Algeria	012	.dz
-EC	ECU	593	Quito	USD	🇪🇨	es-EC	Ecuador	218	.ec
-EE	EST	372	Tallinn	EUR	🇪🇪	et,ru	Estonia	233	.ee
-EG	EGY	20	Cairo	EGP	🇪🇬	ar-EG,en,fr	Egypt	818	.eg
-EH	ESH	212	El-Aaiun	MAD	🇪🇭	ar,mey	Western Sahara	732	.eh
-ER	ERI	291	Asmara	ERN	🇪🇷	aa-ER,ar,tig,kun,ti-ER	Eritrea	232	.er
-ES	ESP	34	Madrid	EUR	🇪🇸	es-ES,ca,gl,eu,oc	Spain	724	.es
-ET	ETH	251	Addis Ababa	ETB	🇪🇹	am,en-ET,om-ET,ti-ET,so-ET,sid	Ethiopia	231	.et
-FI	FIN	358	Helsinki	EUR	🇫🇮	fi-FI,sv-FI,smn	Finland	246	.fi
-FJ	FJI	679	Suva	FJD	🇫🇯	en-FJ,fj	Fiji	242	.fj
-FK	FLK	500	Stanley	FKP	🇫🇰	en-FK	Falkland Islands	238	.fk
-FM	FSM	691	Palikir	USD	🇫🇲	en-FM,chk,pon,yap,kos,uli,woe,nkr,kpg	Micronesia	583	.fm
-FO	FRO	298	Torshavn	DKK	🇫🇴	fo,da-FO	Faroe Islands	234	.fo
-FR	FRA	33	Paris	EUR	🇫🇷	fr-FR,frp,br,co,ca,eu,oc	France	250	.fr
-GA	GAB	241	Libreville	XAF	🇬🇦	fr-GA	Gabon	266	.ga
-GB	GBR	44	London	GBP	🇬🇧	en-GB,cy-GB,gd	UK	826	.uk
-GD	GRD	1-473	St. George's	XCD	🇬🇩	en-GD	Grenada	308	.gd
-GE	GEO	995	Tbilisi	GEL	🇬🇪	ka,ru,hy,az	Georgia	268	.ge
-GF	GUF	594	Cayenne	EUR	🇬🇫	fr-GF	French Guiana	254	.gf
-GG	GGY	44	St Peter Port	GBP	🇬🇬	en,nrf	Guernsey	831	.gg
-GH	GHA	233	Accra	GHS	🇬🇭	en-GH,ak,ee,tw	Ghana	288	.gh
-GI	GIB	350	Gibraltar	GIP	🇬🇮	en-GI,es,it,pt	Gibraltar	292	.gi
-GL	GRL	299	Nuuk	DKK	🇬🇱	kl,da-GL,en	Greenland	304	.gl
-GM	GMB	220	Banjul	GMD	🇬🇲	en-GM,mnk,wof,wo,ff	Gambia	270	.gm
-GN	GIN	224	Conakry	GNF	🇬🇳	fr-GN	Guinea	324	.gn
-GP	GLP	590	Basse-Terre	EUR	🇬🇵	fr-GP	Guadeloupe	312	.gp
-GQ	GNQ	240	Ciudad de la Paz	XAF	🇬🇶	es-GQ,fr,pt	Equatorial Guinea	226	.gq
-GR	GRC	30	Athens	EUR	🇬🇷	el-GR,en,fr	Greece	300	.gr
-GT	GTM	502	Guatemala City	GTQ	🇬🇹	es-GT	Guatemala	320	.gt
-GU	GUM	1-671	Hagatna	USD	🇬🇺	en-GU,ch-GU	Guam	316	.gu
-GW	GNB	245	Bissau	XOF	🇬🇼	pt-GW,pov	Guinea-Bissau	624	.gw
-GY	GUY	592	Georgetown	GYD	🇬🇾	en-GY	Guyana	328	.gy
-HK	HKG	852	Hong Kong	HKD	🇭🇰	zh-HK,yue,zh,en	Hong Kong	344	.hk
-HN	HND	504	Tegucigalpa	HNL	🇭🇳	es-HN,cab,miq	Honduras	340	.hn
-HR	HRV	385	Zagreb	EUR	🇭🇷	hr-HR,sr	Croatia	191	.hr
-HT	HTI	509	Port-au-Prince	HTG	🇭🇹	ht,fr-HT	Haiti	332	.ht
-HU	HUN	36	Budapest	HUF	🇭🇺	hu-HU	Hungary	348	.hu
-ID	IDN	62	Jakarta	IDR	🇮🇩	id,en,nl,jv	Indonesia	360	.id
-IE	IRL	353	Dublin	EUR	🇮🇪	en-IE,ga-IE	Ireland	372	.ie
-IL	ISR	972	Jerusalem	ILS	🇮🇱	he,ar-IL,en-IL	Israel	376	.il
-IM	IMN	44	Douglas	GBP	🇮🇲	en,gv	Isle of Man	833	.im
-IN	IND	91	New Delhi	INR	🇮🇳	en-IN,hi,bn,te,mr,ta,ur,gu,kn,ml,or,pa,as,bh,sat,ks,ne,sd,kok,doi,mni,sit,sa,fr,lus,inc	India	356	.in
-IO	IOT	246	Diego Garcia	USD	🇮🇴	en-IO	British Indian Ocean Territory	086	.io
-IQ	IRQ	964	Baghdad	IQD	🇮🇶	ar-IQ,ku,hy	Iraq	368	.iq
-IR	IRN	98	Tehran	IRR	🇮🇷	fa-IR,ku	Iran	364	.ir
-IS	ISL	354	Reykjavik	ISK	🇮🇸	is,en,de,da,sv,no	Iceland	352	.is
-IT	ITA	39	Rome	EUR	🇮🇹	it-IT,de-IT,fr-IT,sc,ca,co,sl	Italy	380	.it
-JE	JEY	44	Saint Helier	GBP	🇯🇪	en,fr,nrf	Jersey	832	.je
-JM	JAM	1-876	Kingston	JMD	🇯🇲	en-JM	Jamaica	388	.jm
-JO	JOR	962	Amman	JOD	🇯🇴	ar-JO,en	Jordan	400	.jo
-JP	JPN	81	Tokyo	JPY	🇯🇵	ja	Japan	392	.jp
-KE	KEN	254	Nairobi	KES	🇰🇪	en-KE,sw-KE	Kenya	404	.ke
-KG	KGZ	996	Bishkek	KGS	🇰🇬	ky,uz,ru	Kyrgyzstan	417	.kg
-KH	KHM	855	Phnom Penh	KHR	🇰🇭	km,fr,en	Cambodia	116	.kh
-KI	KIR	686	Tarawa	AUD	🇰🇮	en-KI,gil	Kiribati	296	.ki
-KM	COM	269	Moroni	KMF	🇰🇲	ar,fr-KM	Comoros	174	.km
-KN	KNA	1-869	Basseterre	XCD	🇰🇳	en-KN	St. Kitts & Nevis	659	.kn
-KP	PRK	850	Pyongyang	KPW	🇰🇵	ko-KP	North Korea	408	.kp
-KR	KOR	82	Seoul	KRW	🇰🇷	ko-KR,en	South Korea	410	.kr
-KW	KWT	965	Kuwait City	KWD	🇰🇼	ar-KW,en	Kuwait	414	.kw
-KY	CYM	1-345	George Town	KYD	🇰🇾	en-KY	Cayman Islands	136	.ky
-KZ	KAZ	7	Nur-Sultan	KZT	🇰🇿	kk,ru	Kazakhstan	398	.kz
-LA	LAO	856	Vientiane	LAK	🇱🇦	lo,fr,en	Laos	418	.la
-LB	LBN	961	Beirut	LBP	🇱🇧	ar-LB,fr-LB,en,hy	Lebanon	422	.lb
-LC	LCA	1-758	Castries	XCD	🇱🇨	en-LC	St. Lucia	662	.lc
-LI	LIE	423	Vaduz	CHF	🇱🇮	de-LI	Liechtenstein	438	.li
-LK	LKA	94	Colombo	LKR	🇱🇰	si,ta,en	Sri Lanka	144	.lk
-LR	LBR	231	Monrovia	LRD	🇱🇷	en-LR	Liberia	430	.lr
-LS	LSO	266	Maseru	LSL	🇱🇸	en-LS,st,zu,xh	Lesotho	426	.ls
-LT	LTU	370	Vilnius	EUR	🇱🇹	lt,ru,pl	Lithuania	440	.lt
-LU	LUX	352	Luxembourg	EUR	🇱🇺	lb,de-LU,fr-LU	Luxembourg	442	.lu
-LV	LVA	371	Riga	EUR	🇱🇻	lv,ru,lt	Latvia	428	.lv
-LY	LBY	218	Tripoli	LYD	🇱🇾	ar-LY,it,en	Libya	434	.ly
-MA	MAR	212	Rabat	MAD	🇲🇦	ar-MA,ber,fr	Morocco	504	.ma
-MC	MCO	377	Monaco	EUR	🇲🇨	fr-MC,en,it	Monaco	492	.mc
-MD	MDA	373	Chisinau	MDL	🇲🇩	ro,ru,gag,tr	Moldova	498	.md
-ME	MNE	382	Podgorica	EUR	🇲🇪	sr,hu,bs,sq,hr,rom	Montenegro	499	.me
-MF	MAF	590	Marigot	EUR	🇲🇫	fr	St. Martin	663	.gp
-MG	MDG	261	Antananarivo	MGA	🇲🇬	fr-MG,mg	Madagascar	450	.mg
-MH	MHL	692	Majuro	USD	🇲🇭	mh,en-MH	Marshall Islands	584	.mh
-MK	MKD	389	Skopje	MKD	🇲🇰	mk,sq,tr,rmm,sr	North Macedonia	807	.mk
-ML	MLI	223	Bamako	XOF	🇲🇱	fr-ML,bm	Mali	466	.ml
-MM	MMR	95	Nay Pyi Taw	MMK	🇲🇲	my	Myanmar	104	.mm
-MN	MNG	976	Ulaanbaatar	MNT	🇲🇳	mn,ru	Mongolia	496	.mn
-MO	MAC	853	Macao	MOP	🇲🇴	zh,zh-MO,pt	Macao	446	.mo
-MP	MNP	1-670	Saipan	USD	🇲🇵	fil,tl,zh,ch-MP,en-MP	Northern Mariana Islands	580	.mp
-MQ	MTQ	596	Fort-de-France	EUR	🇲🇶	fr-MQ	Martinique	474	.mq
-MR	MRT	222	Nouakchott	MRU	🇲🇷	ar-MR,fuc,snk,fr,mey,wo	Mauritania	478	.mr
-MS	MSR	1-664	Plymouth	XCD	🇲🇸	en-MS	Montserrat	500	.ms
-MT	MLT	356	Valletta	EUR	🇲🇹	mt,en-MT	Malta	470	.mt
-MU	MUS	230	Port Louis	MUR	🇲🇺	en-MU,bho,fr	Mauritius	480	.mu
-MV	MDV	960	Male	MVR	🇲🇻	dv,en	Maldives	462	.mv
-MW	MWI	265	Lilongwe	MWK	🇲🇼	ny,yao,tum,swk	Malawi	454	.mw
-MX	MEX	52	Mexico City	MXN	🇲🇽	es-MX	Mexico	484	.mx
-MY	MYS	60	Kuala Lumpur	MYR	🇲🇾	ms-MY,en,zh,ta,te,ml,pa,th	Malaysia	458	.my
-MZ	MOZ	258	Maputo	MZN	🇲🇿	pt-MZ,vmw	Mozambique	508	.mz
-NA	NAM	264	Windhoek	NAD	🇳🇦	en-NA,af,de,hz,naq	Namibia	516	.na
-NC	NCL	687	Noumea	XPF	🇳🇨	fr-NC	New Caledonia	540	.nc
-NE	NER	227	Niamey	XOF	🇳🇪	fr-NE,ha,kr,dje	Niger	562	.ne
-NF	NFK	672	Kingston	AUD	🇳🇫	en-NF	Norfolk Island	574	.nf
-NG	NGA	234	Abuja	NGN	🇳🇬	en-NG,ha,yo,ig,ff	Nigeria	566	.ng
-NI	NIC	505	Managua	NIO	🇳🇮	es-NI,en	Nicaragua	558	.ni
-NL	NLD	31	Amsterdam	EUR	🇳🇱	nl-NL,fy-NL	Netherlands	528	.nl
-NO	NOR	47	Oslo	NOK	🇳🇴	no,nb,nn,se,fi	Norway	578	.no
-NP	NPL	977	Kathmandu	NPR	🇳🇵	ne,en	Nepal	524	.np
-NR	NRU	674	Yaren	AUD	🇳🇷	na,en-NR	Nauru	520	.nr
-NU	NIU	683	Alofi	NZD	🇳🇺	niu,en-NU	Niue	570	.nu
-NZ	NZL	64	Wellington	NZD	🇳🇿	en-NZ,mi	New Zealand	554	.nz
-OM	OMN	968	Muscat	OMR	🇴🇲	ar-OM,en,bal,ur	Oman	512	.om
-PA	PAN	507	Panama City	PAB	🇵🇦	es-PA,en	Panama	591	.pa
-PE	PER	51	Lima	PEN	🇵🇪	es-PE,qu,ay	Peru	604	.pe
-PF	PYF	689	Papeete	XPF	🇵🇫	fr-PF,ty	French Polynesia	258	.pf
-PG	PNG	675	Port Moresby	PGK	🇵🇬	en-PG,ho,meu,tpi	Papua New Guinea	598	.pg
-PH	PHL	63	Manila	PHP	🇵🇭	tl,en-PH,fil,ceb,ilo,hil,war,pam,bik,bcl,pag,mrw,tsg,mdh,cbk,krj,sgd,msb,akl,ibg,yka,mta,abx	Philippines	608	.ph
-PK	PAK	92	Islamabad	PKR	🇵🇰	ur-PK,en-PK,pa,sd,ps,brh	Pakistan	586	.pk
-PL	POL	48	Warsaw	PLN	🇵🇱	pl	Poland	616	.pl
-PM	SPM	508	Saint-Pierre	EUR	🇵🇲	fr-PM	St. Pierre & Miquelon	666	.pm
-PN	PCN	870	Adamstown	NZD	🇵🇳	en-PN	Pitcairn	612	.pn
-PR	PRI	1	San Juan	USD	🇵🇷	en-PR,es-PR	Puerto Rico	630	.pr
-PT	PRT	351	Lisbon	EUR	🇵🇹	pt-PT,mwl	Portugal	620	.pt
-PW	PLW	680	Melekeok	USD	🇵🇼	pau,sov,en-PW,tox,ja,fil,zh	Palau	585	.pw
-PY	PRY	595	Asuncion	PYG	🇵🇾	es-PY,gn	Paraguay	600	.py
-QA	QAT	974	Doha	QAR	🇶🇦	ar-QA,es	Qatar	634	.qa
-RE	REU	262	Saint-Denis	EUR	🇷🇪	fr-RE	Réunion	638	.re
-RO	ROU	40	Bucharest	RON	🇷🇴	ro,hu,rom	Romania	642	.ro
-RS	SRB	381	Belgrade	RSD	🇷🇸	sr,hu,bs,rom	Serbia	688	.rs
-RU	RUS	7	Moscow	RUB	🇷🇺	ru,tt,xal,cau,ady,kv,ce,tyv,cv,udm,tut,mns,bua,myv,mdf,chm,ba,inh,kbd,krc,av,sah,nog	Russia	643	.ru
-RW	RWA	250	Kigali	RWF	🇷🇼	rw,en-RW,fr-RW,sw	Rwanda	646	.rw
-SA	SAU	966	Riyadh	SAR	🇸🇦	ar-SA	Saudi Arabia	682	.sa
-SB	SLB	677	Honiara	SBD	🇸🇧	en-SB,tpi	Solomon Islands	090	.sb
-SC	SYC	248	Victoria	SCR	🇸🇨	en-SC,fr-SC	Seychelles	690	.sc
-SD	SDN	249	Khartoum	SDG	🇸🇩	ar-SD,en,fia	Sudan	729	.sd
-SE	SWE	46	Stockholm	SEK	🇸🇪	sv-SE,se,sma,fi-SE	Sweden	752	.se
-SG	SGP	65	Singapore	SGD	🇸🇬	cmn,en-SG,ms-SG,ta-SG,zh-SG	Singapore	702	.sg
-SH	SHN	290	Jamestown	SHP	🇸🇭	en-SH	St. Helena	654	.sh
-SI	SVN	386	Ljubljana	EUR	🇸🇮	sl,sh	Slovenia	705	.si
-SJ	SJM	47	Longyearbyen	NOK	🇸🇯	no,ru	Svalbard & Jan Mayen	744	.sj
-SK	SVK	421	Bratislava	EUR	🇸🇰	sk,hu	Slovakia	703	.sk
-SL	SLE	232	Freetown	SLE	🇸🇱	en-SL,men,tem	Sierra Leone	694	.sl
-SM	SMR	378	San Marino	EUR	🇸🇲	it-SM	San Marino	674	.sm
-SN	SEN	221	Dakar	XOF	🇸🇳	fr-SN,wo,fuc,mnk	Senegal	686	.sn
-SO	SOM	252	Mogadishu	SOS	🇸🇴	so-SO,ar-SO,it,en-SO	Somalia	706	.so
-SR	SUR	597	Paramaribo	SRD	🇸🇷	nl-SR,en,srn,hns,jv	Suriname	740	.sr
-SS	SSD	211	Juba	SSP	🇸🇸	en	South Sudan	728	.ss
-ST	STP	239	Sao Tome	STN	🇸🇹	pt-ST	São Tomé & Príncipe	678	.st
-SV	SLV	503	San Salvador	SVC	🇸🇻	es-SV	El Salvador	222	.sv
-SX	SXM	1-721	Philipsburg	XCG	🇸🇽	nl,en	Sint Maarten	534	.sx
-SY	SYR	963	Damascus	SYP	🇸🇾	ar-SY,ku,hy,arc,fr,en	Syria	760	.sy
-SZ	SWZ	268	Mbabane	SZL	🇸🇿	en-SZ,ss-SZ	Eswatini	748	.sz
-TC	TCA	1-649	Cockburn Town	USD	🇹🇨	en-TC	Turks & Caicos Islands	796	.tc
-TD	TCD	235	N'Djamena	XAF	🇹🇩	fr-TD,ar-TD,sre	Chad	148	.td
-TF	ATF	262	Port-aux-Francais	EUR	🇹🇫	fr	French Southern Territories	260	.tf
-TG	TGO	228	Lome	XOF	🇹🇬	fr-TG,ee,hna,kbp,dag,ha	Togo	768	.tg
-TH	THA	66	Bangkok	THB	🇹🇭	th,en	Thailand	764	.th
-TJ	TJK	992	Dushanbe	TJS	🇹🇯	tg,ru	Tajikistan	762	.tj
-TL	TLS	670	Dili	USD	🇹🇱	tet,pt-TL,id,en	Timor-Leste	626	.tl
-TM	TKM	993	Ashgabat	TMT	🇹🇲	tk,ru,uz	Turkmenistan	795	.tm
-TN	TUN	216	Tunis	TND	🇹🇳	ar-TN,fr	Tunisia	788	.tn
-TO	TON	676	Nuku'alofa	TOP	🇹🇴	to,en-TO	Tonga	776	.to
-TR	TUR	90	Ankara	TRY	🇹🇷	tr-TR,ku,diq,az,av	Türkiye	792	.tr
-TT	TTO	1-868	Port of Spain	TTD	🇹🇹	en-TT,hns,fr,es,zh	Trinidad & Tobago	780	.tt
-TV	TUV	688	Funafuti	AUD	🇹🇻	tvl,en,sm,gil	Tuvalu	798	.tv
-TW	TWN	886	Taipei	TWD	🇹🇼	zh-TW,zh,nan,hak	Taiwan	158	.tw
-TZ	TZA	255	Dodoma	TZS	🇹🇿	sw-TZ,en,ar	Tanzania	834	.tz
-UA	UKR	380	Kyiv	UAH	🇺🇦	uk,ru-UA,rom,pl,hu	Ukraine	804	.ua
-UG	UGA	256	Kampala	UGX	🇺🇬	en-UG,lg,sw,ar	Uganda	800	.ug
-US	USA	1	Washington	USD	🇺🇸	en-US,es-US,haw,fr	US	840	.us
-UY	URY	598	Montevideo	UYU	🇺🇾	es-UY	Uruguay	858	.uy
-UZ	UZB	998	Tashkent	UZS	🇺🇿	uz,ru,tg	Uzbekistan	860	.uz
-VA	VAT	39	Vatican City	EUR	🇻🇦	la,it,fr	Vatican City	336	.va
-VC	VCT	1-784	Kingstown	XCD	🇻🇨	en-VC,fr	St. Vincent & Grenadines	670	.vc
-VE	VEN	58	Caracas	VES	🇻🇪	es-VE	Venezuela	862	.ve
-VG	VGB	1-284	Road Town	USD	🇻🇬	en-VG	British Virgin Islands	092	.vg
-VI	VIR	1-340	Charlotte Amalie	USD	🇻🇮	en-VI	U.S. Virgin Islands	850	.vi
-VN	VNM	84	Hanoi	VND	🇻🇳	vi,en,fr,zh,km	Vietnam	704	.vn
-VU	VUT	678	Port Vila	VUV	🇻🇺	bi,en-VU,fr-VU	Vanuatu	548	.vu
-WF	WLF	681	Mata Utu	XPF	🇼🇫	wls,fud,fr-WF	Wallis & Futuna	876	.wf
-WS	WSM	685	Apia	WST	🇼🇸	sm,en-WS	Samoa	882	.ws
-YE	YEM	967	Sanaa	YER	🇾🇪	ar-YE	Yemen	887	.ye
-YT	MYT	262	Mamoudzou	EUR	🇾🇹	fr-YT	Mayotte	175	.yt
-ZA	ZAF	27	Pretoria	ZAR	🇿🇦	zu,xh,af,nso,en-ZA,tn,st,ts,ss,ve,nr	South Africa	710	.za
-ZM	ZMB	260	Lusaka	ZMW	🇿🇲	en-ZM,bem,loz,lun,lue,ny,toi	Zambia	894	.zm
-ZW	ZWE	263	Harare	ZWG	🇿🇼	en-ZW,sn,nr,nd	Zimbabwe	716	.zw

data/misc/datetime.json

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

data/misc/httpmethod.json

@@ -0,0 +1 @@
+{ "format": "{method}", "rows": "httpmethod.tsv", "key": "method" }

data/misc/httpmethod.tsv

@@ -0,0 +1,10 @@
+idempotent	method	safe
+false	CONNECT	false
+true	DELETE	false
+true	GET	true
+true	HEAD	true
+true	OPTIONS	true
+false	PATCH	false
+false	POST	false
+true	PUT	false
+true	TRACE	true

data/misc/httpstatus.tsv

@@ -1,17 +1,61 @@
 code	reason
+100	Continue
+101	Switching Protocols
+102	Processing
+103	Early Hints
 200	OK
 201	Created
+202	Accepted
+203	Non-Authoritative Information
 204	No Content
+205	Reset Content
+206	Partial Content
+207	Multi-Status
+208	Already Reported
+226	IM Used
+300	Multiple Choices
 301	Moved Permanently
 302	Found
+303	See Other
 304	Not Modified
+305	Use Proxy
+307	Temporary Redirect
+308	Permanent Redirect
 400	Bad Request
 401	Unauthorized
+402	Payment Required
 403	Forbidden
 404	Not Found
+405	Method Not Allowed
+406	Not Acceptable
+407	Proxy Authentication Required
+408	Request Timeout
 409	Conflict
-422	Unprocessable Entity
+410	Gone
+411	Length Required
+412	Precondition Failed
+413	Content Too Large
+414	URI Too Long
+415	Unsupported Media Type
+416	Range Not Satisfiable
+417	Expectation Failed
+421	Misdirected Request
+422	Unprocessable Content
+423	Locked
+424	Failed Dependency
+425	Too Early
+426	Upgrade Required
+428	Precondition Required
 429	Too Many Requests
+431	Request Header Fields Too Large
+451	Unavailable For Legal Reasons
 500	Internal Server Error
+501	Not Implemented
 502	Bad Gateway
 503	Service Unavailable
+504	Gateway Timeout
+505	HTTP Version Not Supported
+506	Variant Also Negotiates
+507	Insufficient Storage
+508	Loop Detected
+511	Network Authentication Required

data/misc/language.tsv

@@ -1,17 +1,184 @@
-code	name
+code	code3	name
-ar	Arabic
+aa	aar	Afar
-zh	Chinese
+ab	abk	Abkhazian
-da	Danish
+ae	ave	Avestan
-nl	Dutch
+af	afr	Afrikaans
-en	English
+ak	aka	Akan
-fi	Finnish
+am	amh	Amharic
-fr	French
+an	arg	Aragonese
-de	German
+ar	ara	Arabic
-it	Italian
+as	asm	Assamese
-ja	Japanese
+av	ava	Avaric
-no	Norwegian
+ay	aym	Aymara
-pl	Polish
+az	aze	Azerbaijani
-pt	Portuguese
+ba	bak	Bashkir
-ru	Russian
+be	bel	Belarusian
-es	Spanish
+bg	bul	Bulgarian
-sv	Swedish
+bi	bis	Bislama
+bm	bam	Bambara
+bn	ben	Bengali
+bo	bod	Tibetan
+br	bre	Breton
+bs	bos	Bosnian
+ca	cat	Catalan
+ce	che	Chechen
+ch	cha	Chamorro
+co	cos	Corsican
+cr	cre	Cree
+cs	ces	Czech
+cu	chu	Church Slavic
+cv	chv	Chuvash
+cy	cym	Welsh
+da	dan	Danish
+de	deu	German
+dv	div	Divehi
+dz	dzo	Dzongkha
+ee	ewe	Ewe
+el	ell	Modern Greek
+en	eng	English
+eo	epo	Esperanto
+es	spa	Spanish
+et	est	Estonian
+eu	eus	Basque
+fa	fas	Persian
+ff	ful	Fulah
+fi	fin	Finnish
+fj	fij	Fijian
+fo	fao	Faroese
+fr	fra	French
+fy	fry	Western Frisian
+ga	gle	Irish
+gd	gla	Gaelic
+gl	glg	Galician
+gn	grn	Guarani
+gu	guj	Gujarati
+gv	glv	Manx
+ha	hau	Hausa
+he	heb	Hebrew
+hi	hin	Hindi
+ho	hmo	Hiri Motu
+hr	hrv	Croatian
+ht	hat	Haitian
+hu	hun	Hungarian
+hy	hye	Armenian
+hz	her	Herero
+ia	ina	Interlingua
+id	ind	Indonesian
+ie	ile	Interlingue
+ig	ibo	Igbo
+ii	iii	Sichuan Yi
+ik	ipk	Inupiaq
+io	ido	Ido
+is	isl	Icelandic
+it	ita	Italian
+iu	iku	Inuktitut
+ja	jpn	Japanese
+jv	jav	Javanese
+ka	kat	Georgian
+kg	kon	Kongo
+ki	kik	Kikuyu
+kj	kua	Kuanyama
+kk	kaz	Kazakh
+kl	kal	Kalaallisut
+km	khm	Central Khmer
+kn	kan	Kannada
+ko	kor	Korean
+kr	kau	Kanuri
+ks	kas	Kashmiri
+ku	kur	Kurdish
+kv	kom	Komi
+kw	cor	Cornish
+ky	kir	Kirghiz
+la	lat	Latin
+lb	ltz	Luxembourgish
+lg	lug	Ganda
+li	lim	Limburgan
+ln	lin	Lingala
+lo	lao	Lao
+lt	lit	Lithuanian
+lu	lub	Luba-Katanga
+lv	lav	Latvian
+mg	mlg	Malagasy
+mh	mah	Marshallese
+mi	mri	Maori
+mk	mkd	Macedonian
+ml	mal	Malayalam
+mn	mon	Mongolian
+mr	mar	Marathi
+ms	msa	Malay
+mt	mlt	Maltese
+my	mya	Burmese
+na	nau	Nauru
+nb	nob	Norwegian Bokmål
+nd	nde	North Ndebele
+ne	nep	Nepali
+ng	ndo	Ndonga
+nl	nld	Dutch
+nn	nno	Norwegian Nynorsk
+no	nor	Norwegian
+nr	nbl	South Ndebele
+nv	nav	Navajo
+ny	nya	Chichewa
+oc	oci	Occitan
+oj	oji	Ojibwa
+om	orm	Oromo
+or	ori	Oriya
+os	oss	Ossetian
+pa	pan	Panjabi
+pi	pli	Pali
+pl	pol	Polish
+ps	pus	Pushto
+pt	por	Portuguese
+qu	que	Quechua
+rm	roh	Romansh
+rn	run	Rundi
+ro	ron	Romanian
+ru	rus	Russian
+rw	kin	Kinyarwanda
+sa	san	Sanskrit
+sc	srd	Sardinian
+sd	snd	Sindhi
+se	sme	Northern Sami
+sg	sag	Sango
+si	sin	Sinhala
+sk	slk	Slovak
+sl	slv	Slovenian
+sm	smo	Samoan
+sn	sna	Shona
+so	som	Somali
+sq	sqi	Albanian
+sr	srp	Serbian
+ss	ssw	Swati
+st	sot	Sotho, Southern
+su	sun	Sundanese
+sv	swe	Swedish
+sw	swa	Swahili
+ta	tam	Tamil
+te	tel	Telugu
+tg	tgk	Tajik
+th	tha	Thai
+ti	tir	Tigrinya
+tk	tuk	Turkmen
+tl	tgl	Tagalog
+tn	tsn	Tswana
+to	ton	Tonga
+tr	tur	Turkish
+ts	tso	Tsonga
+tt	tat	Tatar
+tw	twi	Twi
+ty	tah	Tahitian
+ug	uig	Uighur
+uk	ukr	Ukrainian
+ur	urd	Urdu
+uz	uzb	Uzbek
+ve	ven	Venda
+vi	vie	Vietnamese
+vo	vol	Volapük
+wa	wln	Walloon
+wo	wol	Wolof
+xh	xho	Xhosa
+yi	yid	Yiddish
+yo	yor	Yoruba
+za	zha	Zhuang
+zh	zho	Chinese
+zu	zul	Zulu

data/misc/loglevel.json

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

data/misc/loglevel.tsv

@@ -0,0 +1,9 @@
+code	keyword	severity
+0	emerg	Emergency
+1	alert	Alert
+2	crit	Critical
+3	err	Error
+4	warning	Warning
+5	notice	Notice
+6	info	Informational
+7	debug	Debug

data/misc/mimetype.tsv

@@ -1,16 +1,702 @@
 ext	type
+.ez	application/andrew-inset
+.atom	application/atom+xml
+.atomcat	application/atomcat+xml
+.atomdeleted	application/atomdeleted+xml
+.atomsvc	application/atomsvc+xml
+.dwd	application/atsc-dwd+xml
+.held	application/atsc-held+xml
+.rsat	application/atsc-rsat+xml
+.aml	application/automationml-aml+xml
+.amlx	application/automationml-amlx+zip
+.xcs	application/calendar+xml
+.ccxml	application/ccxml+xml
+.cdfx	application/cdfx+xml
+.cdmia	application/cdmi-capability
+.cdmic	application/cdmi-container
+.cdmid	application/cdmi-domain
+.cdmio	application/cdmi-object
+.cdmiq	application/cdmi-queue
+.cpl	application/cpl+xml
+.cwl	application/cwl
+.mpd	application/dash+xml
+.mpp	application/dash-patch+xml
+.davmount	application/davmount+xml
+.dcm	application/dicom
+.dssc	application/dssc+der
+.xdssc	application/dssc+xml
+.emma	application/emma+xml
+.emotionml	application/emotionml+xml
+.epub	application/epub+zip
+.exi	application/exi
+.exp	application/express
+.fdf	application/fdf
+.fdt	application/fdt+xml
+.pfr	application/font-tdpfr
+.geojson	application/geo+json
+.gml	application/gml+xml
 .gz	application/gzip
+.stk	application/hyperstudio
+.ink	application/inkml+xml
+.ipfix	application/ipfix
+.its	application/its+xml
+.jar	application/java-archive
 .json	application/json
+.kbl	application/kbl+xml
+.jsonld	application/ld+json
+.lgr	application/lgr+xml
+.lostxml	application/lost+xml
+.hqx	application/mac-binhex40
+.mads	application/mads+xml
+.webmanifest	application/manifest+json
+.mrc	application/marc
+.mrcx	application/marcxml+xml
+.ma	application/mathematica
+.mathml	application/mathml+xml
+.mbox	application/mbox
+.mpf	application/media-policy-dataset+xml
+.mscml	application/mediaservercontrol+xml
+.meta4	application/metalink4+xml
+.mets	application/mets+xml
+.maei	application/mmt-aei+xml
+.musd	application/mmt-usd+xml
+.mods	application/mods+xml
+.m21	application/mp21
+.mp4s	application/mp4
+.doc	application/msword
+.mxf	application/mxf
+.nq	application/n-quads
+.nt	application/n-triples
+.cjs	application/node
+.bin	application/octet-stream
+.oda	application/oda
+.opf	application/oebps-package+xml
+.ogx	application/ogg
+.oxps	application/oxps
+.relo	application/p2p-overlay+xml
+.xer	application/patch-ops-error+xml
 .pdf	application/pdf
+.pgp	application/pgp-encrypted
+.asc	application/pgp-keys
+.sig	application/pgp-signature
+.p10	application/pkcs10
+.p7m	application/pkcs7-mime
+.p7s	application/pkcs7-signature
+.p8	application/pkcs8
+.ac	application/pkix-attr-cert
+.cer	application/pkix-cert
+.crl	application/pkix-crl
+.pkipath	application/pkix-pkipath
+.pki	application/pkixcmp
+.pls	application/pls+xml
+.ai	application/postscript
+.provx	application/provenance+xml
+.cww	application/prs.cww
+.xsf	application/prs.xsf+xml
+.pskcxml	application/pskc+xml
+.rdf	application/rdf+xml
+.rif	application/reginfo+xml
+.rnc	application/relax-ng-compact-syntax
+.rl	application/resource-lists+xml
+.rld	application/resource-lists-diff+xml
+.rs	application/rls-services+xml
+.rapd	application/route-apd+xml
+.sls	application/route-s-tsid+xml
+.rusd	application/route-usd+xml
+.gbr	application/rpki-ghostbusters
+.mft	application/rpki-manifest
+.roa	application/rpki-roa
+.rtf	application/rtf
+.sbml	application/sbml+xml
+.scq	application/scvp-cv-request
+.scs	application/scvp-cv-response
+.spq	application/scvp-vp-request
+.spp	application/scvp-vp-response
+.sdp	application/sdp
+.senmlx	application/senml+xml
+.sensmlx	application/sensml+xml
+.setpay	application/set-payment-initiation
+.setreg	application/set-registration-initiation
+.shf	application/shf+xml
+.siv	application/sieve
+.smi	application/smil+xml
+.rq	application/sparql-query
+.srx	application/sparql-results+xml
+.sql	application/sql
+.gram	application/srgs
+.grxml	application/srgs+xml
+.sru	application/sru+xml
+.ssml	application/ssml+xml
+.swidtag	application/swid+xml
+.tei	application/tei+xml
+.tfi	application/thraud+xml
+.tsd	application/timestamped-data
+.toml	application/toml
+.trig	application/trig
+.ttml	application/ttml+xml
+.rsheet	application/urc-ressheet+xml
+.td	application/urc-targetdesc+xml
+.vec	application/vec+xml
+.1km	application/vnd.1000minds.decision-model+xml
+.plb	application/vnd.3gpp.pic-bw-large
+.psb	application/vnd.3gpp.pic-bw-small
+.pvb	application/vnd.3gpp.pic-bw-var
+.tcap	application/vnd.3gpp2.tcap
+.pwn	application/vnd.3m.post-it-notes
+.aso	application/vnd.accpac.simply.aso
+.imp	application/vnd.accpac.simply.imp
+.acu	application/vnd.acucobol
+.atc	application/vnd.acucorp
+.fcdt	application/vnd.adobe.formscentral.fcdt
+.fxp	application/vnd.adobe.fxp
+.xdp	application/vnd.adobe.xdp+xml
+.age	application/vnd.age
+.ahead	application/vnd.ahead.space
+.azf	application/vnd.airzip.filesecure.azf
+.azs	application/vnd.airzip.filesecure.azs
+.acc	application/vnd.americandynamics.acc
+.ami	application/vnd.amiga.ami
+.cii	application/vnd.anser-web-certificate-issue-initiation
+.atx	application/vnd.antix.game-component
+.parquet	application/vnd.apache.parquet
+.mpkg	application/vnd.apple.installer+xml
+.key	application/vnd.apple.keynote
+.m3u8	application/vnd.apple.mpegurl
+.numbers	application/vnd.apple.numbers
+.pages	application/vnd.apple.pages
+.swi	application/vnd.aristanetworks.swi
+.iota	application/vnd.astraea-software.iota
+.aep	application/vnd.audiograph
+.bmml	application/vnd.balsamiq.bmml+xml
+.mpm	application/vnd.blueice.multipass
+.bmi	application/vnd.bmi
+.rep	application/vnd.businessobjects
+.cdxml	application/vnd.chemdraw+xml
+.mmd	application/vnd.chipnuts.karaoke-mmd
+.cdy	application/vnd.cinderella
+.csl	application/vnd.citationstyles.style+xml
+.cla	application/vnd.claymore
+.rp9	application/vnd.cloanto.rp9
+.c4g	application/vnd.clonk.c4group
+.c11amc	application/vnd.cluetrust.cartomobile-config
+.c11amz	application/vnd.cluetrust.cartomobile-config-pkg
+.csp	application/vnd.commonspace
+.cdbcmsg	application/vnd.contact.cmsg
+.cmc	application/vnd.cosmocaller
+.clkx	application/vnd.crick.clicker
+.clkk	application/vnd.crick.clicker.keyboard
+.clkp	application/vnd.crick.clicker.palette
+.clkt	application/vnd.crick.clicker.template
+.clkw	application/vnd.crick.clicker.wordbank
+.wbs	application/vnd.criticaltools.wbs+xml
+.pml	application/vnd.ctc-posml
+.ppd	application/vnd.cups-ppd
+.dart	application/vnd.dart
+.rdz	application/vnd.data-vision.rdz
+.dbf	application/vnd.dbf
+.dcmp	application/vnd.dcmp+xml
+.uvf	application/vnd.dece.data
+.uvt	application/vnd.dece.ttml+xml
+.uvx	application/vnd.dece.unspecified
+.uvz	application/vnd.dece.zip
+.fe_launch	application/vnd.denovo.fcselayout-link
+.dna	application/vnd.dna
+.dpg	application/vnd.dpgraph
+.dfac	application/vnd.dreamfactory
+.ait	application/vnd.dvb.ait
+.svc	application/vnd.dvb.service
+.geo	application/vnd.dynageo
+.mag	application/vnd.ecowin.chart
+.nml	application/vnd.enliven
+.esf	application/vnd.epson.esf
+.msf	application/vnd.epson.msf
+.qam	application/vnd.epson.quickanime
+.slt	application/vnd.epson.salt
+.ssf	application/vnd.epson.ssf
+.es3	application/vnd.eszigno3+xml
+.ez2	application/vnd.ezpix-album
+.ez3	application/vnd.ezpix-package
+.mseed	application/vnd.fdsn.mseed
+.seed	application/vnd.fdsn.seed
+.gph	application/vnd.flographit
+.ftc	application/vnd.fluxtime.clip
+.fm	application/vnd.framemaker
+.fsc	application/vnd.fsc.weblaunch
+.oas	application/vnd.fujitsu.oasys
+.oa2	application/vnd.fujitsu.oasys2
+.oa3	application/vnd.fujitsu.oasys3
+.fg5	application/vnd.fujitsu.oasysgp
+.bh2	application/vnd.fujitsu.oasysprs
+.ddd	application/vnd.fujixerox.ddd
+.xdw	application/vnd.fujixerox.docuworks
+.xbd	application/vnd.fujixerox.docuworks.binder
+.fzs	application/vnd.fuzzysheet
+.txd	application/vnd.genomatix.tuxedo
+.ggb	application/vnd.geogebra.file
+.ggs	application/vnd.geogebra.slides
+.ggt	application/vnd.geogebra.tool
+.gex	application/vnd.geometry-explorer
+.gxt	application/vnd.geonext
+.g2w	application/vnd.geoplan
+.g3w	application/vnd.geospace
+.gmx	application/vnd.gmx
+.kml	application/vnd.google-earth.kml+xml
+.kmz	application/vnd.google-earth.kmz
+.xdcf	application/vnd.gov.sk.xmldatacontainer+xml
+.gqf	application/vnd.grafeq
+.gac	application/vnd.groove-account
+.ghf	application/vnd.groove-help
+.gim	application/vnd.groove-identity-message
+.grv	application/vnd.groove-injector
+.gtm	application/vnd.groove-tool-message
+.tpl	application/vnd.groove-tool-template
+.vcg	application/vnd.groove-vcard
+.hal	application/vnd.hal+xml
+.zmm	application/vnd.handheld-entertainment+xml
+.hbci	application/vnd.hbci
+.les	application/vnd.hhe.lesson-player
+.hpgl	application/vnd.hp-hpgl
+.hpid	application/vnd.hp-hpid
+.hps	application/vnd.hp-hps
+.jlt	application/vnd.hp-jlyt
+.pcl	application/vnd.hp-pcl
+.pclxl	application/vnd.hp-pclxl
+.sfd-hdstx	application/vnd.hydrostatix.sof-data
+.mpy	application/vnd.ibm.minipay
+.irm	application/vnd.ibm.rights-management
+.sc	application/vnd.ibm.secure-container
+.icc	application/vnd.iccprofile
+.igl	application/vnd.igloader
+.ivp	application/vnd.immervision-ivp
+.ivu	application/vnd.immervision-ivu
+.igm	application/vnd.insors.igm
+.xpw	application/vnd.intercon.formnet
+.i2g	application/vnd.intergeo
+.qbo	application/vnd.intu.qbo
+.qfx	application/vnd.intu.qfx
+.rcprofile	application/vnd.ipunplugged.rcprofile
+.irp	application/vnd.irepository.package+xml
+.xpr	application/vnd.is-xpr
+.fcs	application/vnd.isac.fcs
+.jam	application/vnd.jam
+.rms	application/vnd.jcp.javame.midlet-rms
+.jisp	application/vnd.jisp
+.joda	application/vnd.joost.joda-archive
+.ktz	application/vnd.kahootz
+.karbon	application/vnd.kde.karbon
+.chrt	application/vnd.kde.kchart
+.kfo	application/vnd.kde.kformula
+.flw	application/vnd.kde.kivio
+.kon	application/vnd.kde.kontour
+.kpr	application/vnd.kde.kpresenter
+.ksp	application/vnd.kde.kspread
+.kwd	application/vnd.kde.kword
+.htke	application/vnd.kenameaapp
+.kia	application/vnd.kidspiration
+.kne	application/vnd.kinar
+.skp	application/vnd.koan
+.sse	application/vnd.kodak-descriptor
+.lasxml	application/vnd.las.las+xml
+.lbd	application/vnd.llamagraphics.life-balance.desktop
+.lbe	application/vnd.llamagraphics.life-balance.exchange+xml
+.123	application/vnd.lotus-1-2-3
+.apr	application/vnd.lotus-approach
+.pre	application/vnd.lotus-freelance
+.nsf	application/vnd.lotus-notes
+.org	application/vnd.lotus-organizer
+.scm	application/vnd.lotus-screencam
+.lwp	application/vnd.lotus-wordpro
+.portpkg	application/vnd.macports.portpkg
+.mvt	application/vnd.mapbox-vector-tile
+.mcd	application/vnd.mcd
+.mc1	application/vnd.medcalcdata
+.cdkey	application/vnd.mediastation.cdkey
+.mwf	application/vnd.mfer
+.mfm	application/vnd.mfmp
+.flo	application/vnd.micrografx.flo
+.igx	application/vnd.micrografx.igx
+.mif	application/vnd.mif
+.daf	application/vnd.mobius.daf
+.dis	application/vnd.mobius.dis
+.mbk	application/vnd.mobius.mbk
+.mqy	application/vnd.mobius.mqy
+.msl	application/vnd.mobius.msl
+.plc	application/vnd.mobius.plc
+.txf	application/vnd.mobius.txf
+.mpn	application/vnd.mophun.application
+.mpc	application/vnd.mophun.certificate
+.xul	application/vnd.mozilla.xul+xml
+.cil	application/vnd.ms-artgalry
+.cab	application/vnd.ms-cab-compressed
+.xls	application/vnd.ms-excel
+.xlam	application/vnd.ms-excel.addin.macroenabled.12
+.xlsb	application/vnd.ms-excel.sheet.binary.macroenabled.12
+.xlsm	application/vnd.ms-excel.sheet.macroenabled.12
+.xltm	application/vnd.ms-excel.template.macroenabled.12
+.eot	application/vnd.ms-fontobject
+.chm	application/vnd.ms-htmlhelp
+.ims	application/vnd.ms-ims
+.lrm	application/vnd.ms-lrm
+.thmx	application/vnd.ms-officetheme
+.ppt	application/vnd.ms-powerpoint
+.ppam	application/vnd.ms-powerpoint.addin.macroenabled.12
+.pptm	application/vnd.ms-powerpoint.presentation.macroenabled.12
+.sldm	application/vnd.ms-powerpoint.slide.macroenabled.12
+.ppsm	application/vnd.ms-powerpoint.slideshow.macroenabled.12
+.potm	application/vnd.ms-powerpoint.template.macroenabled.12
+.mpp	application/vnd.ms-project
+.docm	application/vnd.ms-word.document.macroenabled.12
+.dotm	application/vnd.ms-word.template.macroenabled.12
+.wps	application/vnd.ms-works
+.wpl	application/vnd.ms-wpl
+.xps	application/vnd.ms-xpsdocument
+.mseq	application/vnd.mseq
+.mus	application/vnd.musician
+.msty	application/vnd.muvee.style
+.taglet	application/vnd.mynfc
+.bdo	application/vnd.nato.bindingdataobject+xml
+.nlu	application/vnd.neurolanguage.nlu
+.ntf	application/vnd.nitf
+.nnd	application/vnd.noblenet-directory
+.nns	application/vnd.noblenet-sealer
+.nnw	application/vnd.noblenet-web
+.ac	application/vnd.nokia.n-gage.ac+xml
+.ngdat	application/vnd.nokia.n-gage.data
+.rpst	application/vnd.nokia.radio-preset
+.rpss	application/vnd.nokia.radio-presets
+.edm	application/vnd.novadigm.edm
+.edx	application/vnd.novadigm.edx
+.ext	application/vnd.novadigm.ext
+.odc	application/vnd.oasis.opendocument.chart
+.otc	application/vnd.oasis.opendocument.chart-template
+.odf	application/vnd.oasis.opendocument.formula
+.odft	application/vnd.oasis.opendocument.formula-template
+.odg	application/vnd.oasis.opendocument.graphics
+.otg	application/vnd.oasis.opendocument.graphics-template
+.odi	application/vnd.oasis.opendocument.image
+.oti	application/vnd.oasis.opendocument.image-template
+.odp	application/vnd.oasis.opendocument.presentation
+.otp	application/vnd.oasis.opendocument.presentation-template
+.ods	application/vnd.oasis.opendocument.spreadsheet
+.ots	application/vnd.oasis.opendocument.spreadsheet-template
+.odt	application/vnd.oasis.opendocument.text
+.odm	application/vnd.oasis.opendocument.text-master
+.ott	application/vnd.oasis.opendocument.text-template
+.oth	application/vnd.oasis.opendocument.text-web
+.xo	application/vnd.olpc-sugar
+.dd2	application/vnd.oma.dd2+xml
+.obgx	application/vnd.openblox.game+xml
+.osm	application/vnd.openstreetmap.data+xml
+.pptx	application/vnd.openxmlformats-officedocument.presentationml.presentation
+.sldx	application/vnd.openxmlformats-officedocument.presentationml.slide
+.ppsx	application/vnd.openxmlformats-officedocument.presentationml.slideshow
+.potx	application/vnd.openxmlformats-officedocument.presentationml.template
+.xlsx	application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
+.xltx	application/vnd.openxmlformats-officedocument.spreadsheetml.template
+.docx	application/vnd.openxmlformats-officedocument.wordprocessingml.document
+.dotx	application/vnd.openxmlformats-officedocument.wordprocessingml.template
+.mgp	application/vnd.osgeo.mapguide.package
+.dp	application/vnd.osgi.dp
+.esa	application/vnd.osgi.subsystem
+.pdb	application/vnd.palm
+.paw	application/vnd.pawaafile
+.str	application/vnd.pg.format
+.ei6	application/vnd.pg.osasli
+.efif	application/vnd.picsel
+.wg	application/vnd.pmi.widget
+.plf	application/vnd.pocketlearn
+.pbd	application/vnd.powerbuilder6
+.systemverify	application/vnd.pp.systemverify+xml
+.box	application/vnd.previewsystems.box
+.mgz	application/vnd.proteus.magazine
+.qps	application/vnd.publishare-delta-tree
+.ptid	application/vnd.pvi.ptid1
+.xhtm	application/vnd.pwg-xhtml-print+xml
+.qxd	application/vnd.quark.quarkxpress
+.rar	application/vnd.rar
+.bed	application/vnd.realvnc.bed
+.mxl	application/vnd.recordare.musicxml
+.musicxml	application/vnd.recordare.musicxml+xml
+.cryptonote	application/vnd.rig.cryptonote
+.link66	application/vnd.route66.link66+xml
+.st	application/vnd.sailingtracker.track
+.see	application/vnd.seemail
+.sema	application/vnd.sema
+.semd	application/vnd.semd
+.semf	application/vnd.semf
+.ifm	application/vnd.shana.informed.formdata
+.itp	application/vnd.shana.informed.formtemplate
+.iif	application/vnd.shana.informed.interchange
+.ipk	application/vnd.shana.informed.package
+.twd	application/vnd.simtech-mindmapper
+.mmf	application/vnd.smaf
+.teacher	application/vnd.smart.teacher
+.fo	application/vnd.software602.filler.form+xml
+.sdkm	application/vnd.solent.sdkm+xml
+.dxp	application/vnd.spotfire.dxp
+.sfs	application/vnd.spotfire.sfs
+.sqlite	application/vnd.sqlite3
+.smzip	application/vnd.stepmania.package
+.sm	application/vnd.stepmania.stepchart
+.wadl	application/vnd.sun.wadl+xml
+.sus	application/vnd.sus-calendar
+.svd	application/vnd.svd
+.xsm	application/vnd.syncml+xml
+.bdm	application/vnd.syncml.dm+wbxml
+.xdm	application/vnd.syncml.dm+xml
+.ddf	application/vnd.syncml.dmddf+xml
+.tao	application/vnd.tao.intent-module-archive
+.pcap	application/vnd.tcpdump.pcap
+.tmo	application/vnd.tmobile-livetv
+.tpt	application/vnd.trid.tpt
+.mxs	application/vnd.triscape.mxs
+.tra	application/vnd.trueapp
+.ufd	application/vnd.ufdl
+.utz	application/vnd.uiq.theme
+.umj	application/vnd.umajin
+.unityweb	application/vnd.unity
+.uoml	application/vnd.uoml+xml
+.vcx	application/vnd.vcx
+.vsd	application/vnd.visio
+.vis	application/vnd.visionary
+.vsf	application/vnd.vsf
+.wbxml	application/vnd.wap.wbxml
+.wmlc	application/vnd.wap.wmlc
+.wmlsc	application/vnd.wap.wmlscriptc
+.wtb	application/vnd.webturbo
+.nbp	application/vnd.wolfram.player
+.wpd	application/vnd.wordperfect
+.wqd	application/vnd.wqd
+.stf	application/vnd.wt.stf
+.xar	application/vnd.xara
+.xfdl	application/vnd.xfdl
+.hvd	application/vnd.yamaha.hv-dic
+.hvs	application/vnd.yamaha.hv-script
+.hvp	application/vnd.yamaha.hv-voice
+.osf	application/vnd.yamaha.openscoreformat
+.osfpvg	application/vnd.yamaha.openscoreformat.osfpvg+xml
+.saf	application/vnd.yamaha.smaf-audio
+.spf	application/vnd.yamaha.smaf-phrase
+.cmp	application/vnd.yellowriver-custom-menu
+.zir	application/vnd.zul
+.zaz	application/vnd.zzazz.deck+xml
+.vxml	application/voicexml+xml
+.wasm	application/wasm
+.wif	application/watcherinfo+xml
+.wgt	application/widget
+.wsdl	application/wsdl+xml
+.wspolicy	application/wspolicy+xml
+.der	application/x-x509-ca-cert
+.xav	application/xcap-att+xml
+.xca	application/xcap-caps+xml
+.xdf	application/xcap-diff+xml
+.xel	application/xcap-el+xml
+.xns	application/xcap-ns+xml
+.xenc	application/xenc+xml
+.xfdf	application/xfdf
+.xhtml	application/xhtml+xml
+.xlf	application/xliff+xml
 .xml	application/xml
+.dtd	application/xml-dtd
+.xop	application/xop+xml
+.xsl	application/xslt+xml
+.mxml	application/xv+xml
+.yang	application/yang
+.yin	application/yin+xml
 .zip	application/zip
+.3gpp	audio/3gpp
+.adts	audio/aac
+.amr	audio/amr
+.au	audio/basic
+.mka	audio/matroska
+.mxmf	audio/mobile-xmf
+.m4a	audio/mp4
 .mp3	audio/mpeg
+.ogg	audio/ogg
+.uva	audio/vnd.dece.audio
+.eol	audio/vnd.digital-winds
+.dra	audio/vnd.dra
+.dts	audio/vnd.dts
+.dtshd	audio/vnd.dts.hd
+.lvp	audio/vnd.lucent.voice
+.pya	audio/vnd.ms-playready.media.pya
+.ecelp4800	audio/vnd.nuera.ecelp4800
+.ecelp7470	audio/vnd.nuera.ecelp7470
+.ecelp9600	audio/vnd.nuera.ecelp9600
+.rip	audio/vnd.rip
+.ttc	font/collection
+.otf	font/otf
+.ttf	font/ttf
+.woff	font/woff
+.woff2	font/woff2
+.exr	image/aces
+.apng	image/apng
+.avci	image/avci
+.avcs	image/avcs
+.avif	image/avif
+.bmp	image/bmp
+.cgm	image/cgm
+.drle	image/dicom-rle
+.dpx	image/dpx
+.emf	image/emf
+.fits	image/fits
+.g3	image/g3fax
 .gif	image/gif
+.heic	image/heic
+.heics	image/heic-sequence
+.heif	image/heif
+.heifs	image/heif-sequence
+.hej2	image/hej2k
+.ief	image/ief
+.jaii	image/jaii
+.jais	image/jais
+.jls	image/jls
+.jp2	image/jp2
 .jpg	image/jpeg
+.jph	image/jph
+.jhc	image/jphc
+.jpm	image/jpm
+.jpx	image/jpx
+.jxl	image/jxl
+.jxr	image/jxr
+.jxra	image/jxra
+.jxrs	image/jxrs
+.jxs	image/jxs
+.jxsc	image/jxsc
+.jxsi	image/jxsi
+.jxss	image/jxss
+.ktx	image/ktx
+.ktx2	image/ktx2
 .png	image/png
+.btif	image/prs.btif
+.pti	image/prs.pti
 .svg	image/svg+xml
+.t38	image/t38
+.tif	image/tiff
+.tfx	image/tiff-fx
+.psd	image/vnd.adobe.photoshop
+.azv	image/vnd.airzip.accelerator.azv
+.facti	image/vnd.blockfact.facti
+.uvi	image/vnd.dece.graphic
+.djvu	image/vnd.djvu
+.sub	image/vnd.dvb.subtitle
+.dwg	image/vnd.dwg
+.dxf	image/vnd.dxf
+.fbs	image/vnd.fastbidsheet
+.fpx	image/vnd.fpx
+.fst	image/vnd.fst
+.mmr	image/vnd.fujixerox.edmics-mmr
+.rlc	image/vnd.fujixerox.edmics-rlc
+.ico	image/vnd.microsoft.icon
+.mdi	image/vnd.ms-modi
+.npx	image/vnd.net-fpx
+.b16	image/vnd.pco.b16
+.tap	image/vnd.tencent.tap
+.vtf	image/vnd.valve.source.texture
+.wbmp	image/vnd.wap.wbmp
+.xif	image/vnd.xiff
+.pcx	image/vnd.zbrush.pcx
 .webp	image/webp
+.wmf	image/wmf
+.disposition-notification	message/disposition-notification
+.u8msg	message/global
+.u8dsn	message/global-delivery-status
+.u8mdn	message/global-disposition-notification
+.u8hdr	message/global-headers
+.eml	message/rfc822
+.wsc	message/vnd.wfa.wsc
+.3mf	model/3mf
+.gltf	model/gltf+json
+.glb	model/gltf-binary
+.igs	model/iges
+.jt	model/jt
+.msh	model/mesh
+.mtl	model/mtl
+.obj	model/obj
+.prc	model/prc
+.step	model/step
+.stpx	model/step+xml
+.stpz	model/step+zip
+.stpxz	model/step-xml+zip
+.stl	model/stl
+.u3d	model/u3d
+.bary	model/vnd.bary
+.cld	model/vnd.cld
+.dae	model/vnd.collada+xml
+.dwf	model/vnd.dwf
+.gdl	model/vnd.gdl
+.gtw	model/vnd.gtw
+.mts	model/vnd.mts
+.ogex	model/vnd.opengex
+.x_b	model/vnd.parasolid.transmit.binary
+.x_t	model/vnd.parasolid.transmit.text
+.pyo	model/vnd.pytha.pyox
+.vds	model/vnd.sap.vds
+.usda	model/vnd.usda
+.usdz	model/vnd.usdz+zip
+.bsp	model/vnd.valve.source.compiled-map
+.vtu	model/vnd.vtu
+.wrl	model/vrml
+.x3db	model/x3d+fastinfoset
+.x3d	model/x3d+xml
+.x3dv	model/x3d-vrml
+.appcache	text/cache-manifest
+.ics	text/calendar
+.css	text/css
 .csv	text/csv
 .html	text/html
+.js	text/javascript
+.md	text/markdown
+.n3	text/n3
 .txt	text/plain
+.dsc	text/prs.lines.tag
+.rtx	text/richtext
+.rtf	text/rtf
+.sgml	text/sgml
+.shex	text/shex
+.spdx	text/spdx
+.tsv	text/tab-separated-values
+.t	text/troff
+.ttl	text/turtle
+.uri	text/uri-list
+.vcard	text/vcard
+.curl	text/vnd.curl
+.sub	text/vnd.dvb.subtitle
+.ged	text/vnd.familysearch.gedcom
+.fly	text/vnd.fly
+.flx	text/vnd.fmi.flexstor
+.gv	text/vnd.graphviz
+.3dml	text/vnd.in3d.3dml
+.spot	text/vnd.in3d.spot
+.jad	text/vnd.sun.j2me.app-descriptor
+.wml	text/vnd.wap.wml
+.wmls	text/vnd.wap.wmlscript
+.vtt	text/vtt
+.wgsl	text/wgsl
+.xml	text/xml
+.3gp	video/3gpp
+.3g2	video/3gpp2
+.h261	video/h261
+.h263	video/h263
+.h264	video/h264
+.m4s	video/iso.segment
+.jpgv	video/jpeg
+.mkv	video/matroska
+.mk3d	video/matroska-3d
+.mj2	video/mj2
+.ts	video/mp2t
 .mp4	video/mp4
+.mpeg	video/mpeg
+.ogv	video/ogg
+.mov	video/quicktime
+.uvh	video/vnd.dece.hd
+.uvm	video/vnd.dece.mobile
+.uvp	video/vnd.dece.pd
+.uvs	video/vnd.dece.sd
+.uvv	video/vnd.dece.video
+.dvb	video/vnd.dvb.file
+.fvt	video/vnd.fvt
+.mxu	video/vnd.mpegurl
+.pyv	video/vnd.ms-playready.media.pyv
+.uvu	video/vnd.uvvu.mp4
+.viv	video/vnd.vivo

data/misc/port.json

@@ -0,0 +1 @@
+{ "format": "{number}", "rows": "port.tsv", "key": "number" }

data/misc/protocol.json

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

data/misc/protocol.tsv

@@ -0,0 +1,140 @@
+keyword	name	number
+HOPOPT	IPv6 Hop-by-Hop Option	0
+ICMP	Internet Control Message	1
+IGMP	Internet Group Management	2
+GGP	Gateway-to-Gateway	3
+IPv4	IPv4 encapsulation	4
+ST	Stream	5
+TCP	Transmission Control	6
+CBT	CBT	7
+EGP	Exterior Gateway Protocol	8
+IGP	any private interior gateway (used by Cisco for their IGRP)	9
+BBN-RCC-MON	BBN RCC Monitoring	10
+NVP-II	Network Voice Protocol	11
+PUP	PUP	12
+EMCON	EMCON	14
+XNET	Cross Net Debugger	15
+CHAOS	Chaos	16
+UDP	User Datagram	17
+MUX	Multiplexing	18
+DCN-MEAS	DCN Measurement Subsystems	19
+HMP	Host Monitoring	20
+PRM	Packet Radio Measurement	21
+XNS-IDP	XEROX NS IDP	22
+TRUNK-1	Trunk-1	23
+TRUNK-2	Trunk-2	24
+LEAF-1	Leaf-1	25
+LEAF-2	Leaf-2	26
+RDP	Reliable Data Protocol	27
+IRTP	Internet Reliable Transaction	28
+ISO-TP4	ISO Transport Protocol Class 4	29
+NETBLT	Bulk Data Transfer Protocol	30
+MFE-NSP	MFE Network Services Protocol	31
+MERIT-INP	MERIT Internodal Protocol	32
+DCCP	Datagram Congestion Control Protocol	33
+3PC	Third Party Connect Protocol	34
+IDPR	Inter-Domain Policy Routing Protocol	35
+XTP	XTP	36
+DDP	Datagram Delivery Protocol	37
+IDPR-CMTP	IDPR Control Message Transport Proto	38
+TP++	TP++ Transport Protocol	39
+IL	IL Transport Protocol	40
+IPv6	IPv6 encapsulation	41
+SDRP	Source Demand Routing Protocol	42
+IPv6-Route	Routing Header for IPv6	43
+IPv6-Frag	Fragment Header for IPv6	44
+IDRP	Inter-Domain Routing Protocol	45
+RSVP	Reservation Protocol	46
+GRE	Generic Routing Encapsulation	47
+DSR	Dynamic Source Routing Protocol	48
+BNA	BNA	49
+ESP	Encap Security Payload	50
+AH	Authentication Header	51
+I-NLSP	Integrated Net Layer Security TUBA	52
+NARP	NBMA Address Resolution Protocol	54
+Min-IPv4	Minimal IPv4 Encapsulation	55
+TLSP	Transport Layer Security Protocol using Kryptonet key management	56
+SKIP	SKIP	57
+IPv6-ICMP	ICMP for IPv6	58
+IPv6-NoNxt	No Next Header for IPv6	59
+IPv6-Opts	Destination Options for IPv6	60
+CFTP	CFTP	62
+SAT-EXPAK	SATNET and Backroom EXPAK	64
+KRYPTOLAN	Kryptolan	65
+RVD	MIT Remote Virtual Disk Protocol	66
+IPPC	Internet Pluribus Packet Core	67
+SAT-MON	SATNET Monitoring	69
+VISA	VISA Protocol	70
+IPCV	Internet Packet Core Utility	71
+CPNX	Computer Protocol Network Executive	72
+CPHB	Computer Protocol Heart Beat	73
+WSN	Wang Span Network	74
+PVP	Packet Video Protocol	75
+BR-SAT-MON	Backroom SATNET Monitoring	76
+SUN-ND	SUN ND PROTOCOL-Temporary	77
+WB-MON	WIDEBAND Monitoring	78
+WB-EXPAK	WIDEBAND EXPAK	79
+ISO-IP	ISO Internet Protocol	80
+VMTP	VMTP	81
+SECURE-VMTP	SECURE-VMTP	82
+VINES	VINES	83
+IPTM	Internet Protocol Traffic Manager	84
+NSFNET-IGP	NSFNET-IGP	85
+DGP	Dissimilar Gateway Protocol	86
+TCF	TCF	87
+EIGRP	EIGRP	88
+OSPFIGP	OSPFIGP	89
+Sprite-RPC	Sprite RPC Protocol	90
+LARP	Locus Address Resolution Protocol	91
+MTP	Multicast Transport Protocol	92
+AX.25	AX.25 Frames	93
+IPIP	IP-within-IP Encapsulation Protocol	94
+SCC-SP	Semaphore Communications Sec. Pro.	96
+ETHERIP	Ethernet-within-IP Encapsulation	97
+ENCAP	Encapsulation Header	98
+GMTP	GMTP	100
+IFMP	Ipsilon Flow Management Protocol	101
+PNNI	PNNI over IP	102
+PIM	Protocol Independent Multicast	103
+ARIS	ARIS	104
+SCPS	SCPS	105
+QNX	QNX	106
+A/N	Active Networks	107
+IPComp	IP Payload Compression Protocol	108
+SNP	Sitara Networks Protocol	109
+Compaq-Peer	Compaq Peer Protocol	110
+IPX-in-IP	IPX in IP	111
+VRRP	Virtual Router Redundancy Protocol	112
+PGM	PGM Reliable Transport Protocol	113
+L2TP	Layer Two Tunneling Protocol	115
+DDX	D-II Data Exchange (DDX)	116
+IATP	Interactive Agent Transfer Protocol	117
+STP	Schedule Transfer Protocol	118
+SRP	SpectraLink Radio Protocol	119
+UTI	UTI	120
+SMP	Simple Message Protocol	121
+PTP	Performance Transparency Protocol	123
+ISIS over IPv4	ISIS over IPv4	124
+FIRE	FIRE	125
+CRTP	Combat Radio Transport Protocol	126
+CRUDP	Combat Radio User Datagram	127
+SSCOPMCE	SSCOPMCE	128
+IPLT	IPLT	129
+SPS	Secure Packet Shield	130
+PIPE	Private IP Encapsulation within IP	131
+SCTP	Stream Control Transmission Protocol	132
+FC	Fibre Channel	133
+RSVP-E2E-IGNORE	RSVP-E2E-IGNORE	134
+Mobility Header	Mobility Header	135
+UDPLite	UDPLite	136
+MPLS-in-IP	MPLS-in-IP	137
+manet	MANET Protocols	138
+HIP	Host Identity Protocol	139
+Shim6	Shim6 Protocol	140
+WESP	Wrapped Encapsulating Security Payload	141
+ROHC	Robust Header Compression	142
+Ethernet	Ethernet	143
+AGGFRAG	AGGFRAG encapsulation payload for ESP	144
+NSH	Network Service Header	145
+Homa	Homa	146
+BIT-EMU	Bit-stream Emulation	147

data/misc/territory.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "territory.tsv", "key": "alpha2", "name": "name" }

data/misc/territory.tsv

@@ -0,0 +1,242 @@
+alpha2	alpha3	calling-code	capital	country	currency	flag	languages	name	numeric	tld
+AD	AND	376	Andorra la Vella	AD	EUR	🇦🇩	ca	Andorra	020	.ad
+AE	ARE	971	Abu Dhabi	AE	AED	🇦🇪	ar-AE,fa,en,hi,ur	United Arab Emirates	784	.ae
+AF	AFG	93	Kabul	AF	AFN	🇦🇫	fa-AF,ps,uz-AF,tk	Afghanistan	004	.af
+AG	ATG	1-268	St. John's	AG	XCD	🇦🇬	en-AG	Antigua & Barbuda	028	.ag
+AI	AIA	1-264	The Valley	GB	XCD	🇦🇮	en-AI	Anguilla	660	.ai
+AL	ALB	355	Tirana	AL	ALL	🇦🇱	sq,el	Albania	008	.al
+AM	ARM	374	Yerevan	AM	AMD	🇦🇲	hy	Armenia	051	.am
+AO	AGO	244	Luanda	AO	AOA	🇦🇴	pt-AO	Angola	024	.ao
+AR	ARG	54	Buenos Aires	AR	ARS	🇦🇷	es-AR,en,it,de,fr,gn	Argentina	032	.ar
+AS	ASM	1-684	Pago Pago	US	USD	🇦🇸	en-AS,sm,to	American Samoa	016	.as
+AT	AUT	43	Vienna	AT	EUR	🇦🇹	de-AT,hr,hu,sl	Austria	040	.at
+AU	AUS	61	Canberra	AU	AUD	🇦🇺	en-AU	Australia	036	.au
+AW	ABW	297	Oranjestad	NL	AWG	🇦🇼	nl-AW,pap,es,en	Aruba	533	.aw
+AX	ALA	358	Mariehamn	FI	EUR	🇦🇽	sv-AX	Åland Islands	248	.ax
+AZ	AZE	994	Baku	AZ	AZN	🇦🇿	az,ru,hy	Azerbaijan	031	.az
+BA	BIH	387	Sarajevo	BA	BAM	🇧🇦	bs,hr-BA,sr-BA	Bosnia	070	.ba
+BB	BRB	1-246	Bridgetown	BB	BBD	🇧🇧	en-BB	Barbados	052	.bb
+BD	BGD	880	Dhaka	BD	BDT	🇧🇩	bn-BD,en	Bangladesh	050	.bd
+BE	BEL	32	Brussels	BE	EUR	🇧🇪	nl-BE,fr-BE,de-BE	Belgium	056	.be
+BF	BFA	226	Ouagadougou	BF	XOF	🇧🇫	fr-BF,mos	Burkina Faso	854	.bf
+BG	BGR	359	Sofia	BG	EUR	🇧🇬	bg,tr-BG,rom	Bulgaria	100	.bg
+BH	BHR	973	Manama	BH	BHD	🇧🇭	ar-BH,en,fa,ur	Bahrain	048	.bh
+BI	BDI	257	Gitega	BI	BIF	🇧🇮	fr-BI,rn	Burundi	108	.bi
+BJ	BEN	229	Porto-Novo	BJ	XOF	🇧🇯	fr-BJ	Benin	204	.bj
+BL	BLM	590	Gustavia	FR	EUR	🇧🇱	fr	St. Barthélemy	652	.gp
+BM	BMU	1-441	Hamilton	GB	BMD	🇧🇲	en-BM,pt	Bermuda	060	.bm
+BN	BRN	673	Bandar Seri Begawan	BN	BND	🇧🇳	ms-BN,en-BN	Brunei	096	.bn
+BO	BOL	591	Sucre	BO	BOB	🇧🇴	es-BO,qu,ay	Bolivia	068	.bo
+BR	BRA	55	Brasilia	BR	BRL	🇧🇷	pt-BR,es,en,fr	Brazil	076	.br
+BS	BHS	1-242	Nassau	BS	BSD	🇧🇸	en-BS	Bahamas	044	.bs
+BT	BTN	975	Thimphu	BT	INR	🇧🇹	dz	Bhutan	064	.bt
+BW	BWA	267	Gaborone	BW	BWP	🇧🇼	en-BW,tn-BW	Botswana	072	.bw
+BY	BLR	375	Minsk	BY	BYN	🇧🇾	be,ru	Belarus	112	.by
+BZ	BLZ	501	Belmopan	BZ	BZD	🇧🇿	en-BZ,es	Belize	084	.bz
+CA	CAN	1	Ottawa	CA	CAD	🇨🇦	en-CA,fr-CA,iu	Canada	124	.ca
+CC	CCK	61	West Island	AU	AUD	🇨🇨	ms-CC,en	Cocos Islands	166	.cc
+CD	COD	243	Kinshasa	CD	CDF	🇨🇩	fr-CD,ln,ktu,kg,sw,lua	Congo - Kinshasa	180	.cd
+CF	CAF	236	Bangui	CF	XAF	🇨🇫	fr-CF,sg,ln,kg	Central African Republic	140	.cf
+CG	COG	242	Brazzaville	CG	XAF	🇨🇬	fr-CG,kg,ln-CG	Congo - Brazzaville	178	.cg
+CH	CHE	41	Bern	CH	CHF	🇨🇭	de-CH,fr-CH,it-CH,rm	Switzerland	756	.ch
+CI	CIV	225	Yamoussoukro	CI	XOF	🇨🇮	fr-CI	Côte d’Ivoire	384	.ci
+CK	COK	682	Avarua	NZ	NZD	🇨🇰	en-CK,mi	Cook Islands	184	.ck
+CL	CHL	56	Santiago	CL	CLP	🇨🇱	es-CL	Chile	152	.cl
+CM	CMR	237	Yaounde	CM	XAF	🇨🇲	en-CM,fr-CM	Cameroon	120	.cm
+CN	CHN	86	Beijing	CN	CNY	🇨🇳	zh-CN,yue,wuu,dta,ug,za	China	156	.cn
+CO	COL	57	Bogota	CO	COP	🇨🇴	es-CO	Colombia	170	.co
+CR	CRI	506	San Jose	CR	CRC	🇨🇷	es-CR,en	Costa Rica	188	.cr
+CU	CUB	53	Havana	CU	CUP	🇨🇺	es-CU,pap	Cuba	192	.cu
+CV	CPV	238	Praia	CV	CVE	🇨🇻	pt-CV	Cape Verde	132	.cv
+CW	CUW	599	 Willemstad	NL	XCG	🇨🇼	nl,pap	Curaçao	531	.cw
+CX	CXR	61	Flying Fish Cove	AU	AUD	🇨🇽	en,zh,ms-CX	Christmas Island	162	.cx
+CY	CYP	357	Nicosia	CY	EUR	🇨🇾	el-CY,tr-CY,en	Cyprus	196	.cy
+CZ	CZE	420	Prague	CZ	CZK	🇨🇿	cs,sk	Czechia	203	.cz
+DE	DEU	49	Berlin	DE	EUR	🇩🇪	de	Germany	276	.de
+DJ	DJI	253	Djibouti	DJ	DJF	🇩🇯	fr-DJ,ar,so-DJ,aa	Djibouti	262	.dj
+DK	DNK	45	Copenhagen	DK	DKK	🇩🇰	da-DK,en,fo,de-DK	Denmark	208	.dk
+DM	DMA	1-767	Roseau	DM	XCD	🇩🇲	en-DM	Dominica	212	.dm
+DO	DOM	1-809	Santo Domingo	DO	DOP	🇩🇴	es-DO	Dominican Republic	214	.do
+DZ	DZA	213	Algiers	DZ	DZD	🇩🇿	ar-DZ	Algeria	012	.dz
+EC	ECU	593	Quito	EC	USD	🇪🇨	es-EC	Ecuador	218	.ec
+EE	EST	372	Tallinn	EE	EUR	🇪🇪	et,ru	Estonia	233	.ee
+EG	EGY	20	Cairo	EG	EGP	🇪🇬	ar-EG,en,fr	Egypt	818	.eg
+EH	ESH	212	El-Aaiun	EH	MAD	🇪🇭	ar,mey	Western Sahara	732	.eh
+ER	ERI	291	Asmara	ER	ERN	🇪🇷	aa-ER,ar,tig,kun,ti-ER	Eritrea	232	.er
+ES	ESP	34	Madrid	ES	EUR	🇪🇸	es-ES,ca,gl,eu,oc	Spain	724	.es
+ET	ETH	251	Addis Ababa	ET	ETB	🇪🇹	am,en-ET,om-ET,ti-ET,so-ET,sid	Ethiopia	231	.et
+FI	FIN	358	Helsinki	FI	EUR	🇫🇮	fi-FI,sv-FI,smn	Finland	246	.fi
+FJ	FJI	679	Suva	FJ	FJD	🇫🇯	en-FJ,fj	Fiji	242	.fj
+FK	FLK	500	Stanley	GB	FKP	🇫🇰	en-FK	Falkland Islands	238	.fk
+FM	FSM	691	Palikir	FM	USD	🇫🇲	en-FM,chk,pon,yap,kos,uli,woe,nkr,kpg	Micronesia	583	.fm
+FO	FRO	298	Torshavn	DK	DKK	🇫🇴	fo,da-FO	Faroe Islands	234	.fo
+FR	FRA	33	Paris	FR	EUR	🇫🇷	fr-FR,frp,br,co,ca,eu,oc	France	250	.fr
+GA	GAB	241	Libreville	GA	XAF	🇬🇦	fr-GA	Gabon	266	.ga
+GB	GBR	44	London	GB	GBP	🇬🇧	en-GB,cy-GB,gd	UK	826	.uk
+GD	GRD	1-473	St. George's	GD	XCD	🇬🇩	en-GD	Grenada	308	.gd
+GE	GEO	995	Tbilisi	GE	GEL	🇬🇪	ka,ru,hy,az	Georgia	268	.ge
+GF	GUF	594	Cayenne	FR	EUR	🇬🇫	fr-GF	French Guiana	254	.gf
+GG	GGY	44	St Peter Port	GB	GBP	🇬🇬	en,nrf	Guernsey	831	.gg
+GH	GHA	233	Accra	GH	GHS	🇬🇭	en-GH,ak,ee,tw	Ghana	288	.gh
+GI	GIB	350	Gibraltar	GB	GIP	🇬🇮	en-GI,es,it,pt	Gibraltar	292	.gi
+GL	GRL	299	Nuuk	DK	DKK	🇬🇱	kl,da-GL,en	Greenland	304	.gl
+GM	GMB	220	Banjul	GM	GMD	🇬🇲	en-GM,mnk,wof,wo,ff	Gambia	270	.gm
+GN	GIN	224	Conakry	GN	GNF	🇬🇳	fr-GN	Guinea	324	.gn
+GP	GLP	590	Basse-Terre	FR	EUR	🇬🇵	fr-GP	Guadeloupe	312	.gp
+GQ	GNQ	240	Ciudad de la Paz	GQ	XAF	🇬🇶	es-GQ,fr,pt	Equatorial Guinea	226	.gq
+GR	GRC	30	Athens	GR	EUR	🇬🇷	el-GR,en,fr	Greece	300	.gr
+GT	GTM	502	Guatemala City	GT	GTQ	🇬🇹	es-GT	Guatemala	320	.gt
+GU	GUM	1-671	Hagatna	US	USD	🇬🇺	en-GU,ch-GU	Guam	316	.gu
+GW	GNB	245	Bissau	GW	XOF	🇬🇼	pt-GW,pov	Guinea-Bissau	624	.gw
+GY	GUY	592	Georgetown	GY	GYD	🇬🇾	en-GY	Guyana	328	.gy
+HK	HKG	852	Hong Kong	CN	HKD	🇭🇰	zh-HK,yue,zh,en	Hong Kong	344	.hk
+HN	HND	504	Tegucigalpa	HN	HNL	🇭🇳	es-HN,cab,miq	Honduras	340	.hn
+HR	HRV	385	Zagreb	HR	EUR	🇭🇷	hr-HR,sr	Croatia	191	.hr
+HT	HTI	509	Port-au-Prince	HT	HTG	🇭🇹	ht,fr-HT	Haiti	332	.ht
+HU	HUN	36	Budapest	HU	HUF	🇭🇺	hu-HU	Hungary	348	.hu
+ID	IDN	62	Jakarta	ID	IDR	🇮🇩	id,en,nl,jv	Indonesia	360	.id
+IE	IRL	353	Dublin	IE	EUR	🇮🇪	en-IE,ga-IE	Ireland	372	.ie
+IL	ISR	972	Jerusalem	IL	ILS	🇮🇱	he,ar-IL,en-IL	Israel	376	.il
+IM	IMN	44	Douglas	GB	GBP	🇮🇲	en,gv	Isle of Man	833	.im
+IN	IND	91	New Delhi	IN	INR	🇮🇳	en-IN,hi,bn,te,mr,ta,ur,gu,kn,ml,or,pa,as,bh,sat,ks,ne,sd,kok,doi,mni,sit,sa,fr,lus,inc	India	356	.in
+IO	IOT	246	Diego Garcia	GB	USD	🇮🇴	en-IO	British Indian Ocean Territory	086	.io
+IQ	IRQ	964	Baghdad	IQ	IQD	🇮🇶	ar-IQ,ku,hy	Iraq	368	.iq
+IR	IRN	98	Tehran	IR	IRR	🇮🇷	fa-IR,ku	Iran	364	.ir
+IS	ISL	354	Reykjavik	IS	ISK	🇮🇸	is,en,de,da,sv,no	Iceland	352	.is
+IT	ITA	39	Rome	IT	EUR	🇮🇹	it-IT,de-IT,fr-IT,sc,ca,co,sl	Italy	380	.it
+JE	JEY	44	Saint Helier	GB	GBP	🇯🇪	en,fr,nrf	Jersey	832	.je
+JM	JAM	1-876	Kingston	JM	JMD	🇯🇲	en-JM	Jamaica	388	.jm
+JO	JOR	962	Amman	JO	JOD	🇯🇴	ar-JO,en	Jordan	400	.jo
+JP	JPN	81	Tokyo	JP	JPY	🇯🇵	ja	Japan	392	.jp
+KE	KEN	254	Nairobi	KE	KES	🇰🇪	en-KE,sw-KE	Kenya	404	.ke
+KG	KGZ	996	Bishkek	KG	KGS	🇰🇬	ky,uz,ru	Kyrgyzstan	417	.kg
+KH	KHM	855	Phnom Penh	KH	KHR	🇰🇭	km,fr,en	Cambodia	116	.kh
+KI	KIR	686	Tarawa	KI	AUD	🇰🇮	en-KI,gil	Kiribati	296	.ki
+KM	COM	269	Moroni	KM	KMF	🇰🇲	ar,fr-KM	Comoros	174	.km
+KN	KNA	1-869	Basseterre	KN	XCD	🇰🇳	en-KN	St. Kitts & Nevis	659	.kn
+KP	PRK	850	Pyongyang	KP	KPW	🇰🇵	ko-KP	North Korea	408	.kp
+KR	KOR	82	Seoul	KR	KRW	🇰🇷	ko-KR,en	South Korea	410	.kr
+KW	KWT	965	Kuwait City	KW	KWD	🇰🇼	ar-KW,en	Kuwait	414	.kw
+KY	CYM	1-345	George Town	GB	KYD	🇰🇾	en-KY	Cayman Islands	136	.ky
+KZ	KAZ	7	Nur-Sultan	KZ	KZT	🇰🇿	kk,ru	Kazakhstan	398	.kz
+LA	LAO	856	Vientiane	LA	LAK	🇱🇦	lo,fr,en	Laos	418	.la
+LB	LBN	961	Beirut	LB	LBP	🇱🇧	ar-LB,fr-LB,en,hy	Lebanon	422	.lb
+LC	LCA	1-758	Castries	LC	XCD	🇱🇨	en-LC	St. Lucia	662	.lc
+LI	LIE	423	Vaduz	LI	CHF	🇱🇮	de-LI	Liechtenstein	438	.li
+LK	LKA	94	Colombo	LK	LKR	🇱🇰	si,ta,en	Sri Lanka	144	.lk
+LR	LBR	231	Monrovia	LR	LRD	🇱🇷	en-LR	Liberia	430	.lr
+LS	LSO	266	Maseru	LS	LSL	🇱🇸	en-LS,st,zu,xh	Lesotho	426	.ls
+LT	LTU	370	Vilnius	LT	EUR	🇱🇹	lt,ru,pl	Lithuania	440	.lt
+LU	LUX	352	Luxembourg	LU	EUR	🇱🇺	lb,de-LU,fr-LU	Luxembourg	442	.lu
+LV	LVA	371	Riga	LV	EUR	🇱🇻	lv,ru,lt	Latvia	428	.lv
+LY	LBY	218	Tripoli	LY	LYD	🇱🇾	ar-LY,it,en	Libya	434	.ly
+MA	MAR	212	Rabat	MA	MAD	🇲🇦	ar-MA,ber,fr	Morocco	504	.ma
+MC	MCO	377	Monaco	MC	EUR	🇲🇨	fr-MC,en,it	Monaco	492	.mc
+MD	MDA	373	Chisinau	MD	MDL	🇲🇩	ro,ru,gag,tr	Moldova	498	.md
+ME	MNE	382	Podgorica	ME	EUR	🇲🇪	sr,hu,bs,sq,hr,rom	Montenegro	499	.me
+MF	MAF	590	Marigot	FR	EUR	🇲🇫	fr	St. Martin	663	.gp
+MG	MDG	261	Antananarivo	MG	MGA	🇲🇬	fr-MG,mg	Madagascar	450	.mg
+MH	MHL	692	Majuro	MH	USD	🇲🇭	mh,en-MH	Marshall Islands	584	.mh
+MK	MKD	389	Skopje	MK	MKD	🇲🇰	mk,sq,tr,rmm,sr	North Macedonia	807	.mk
+ML	MLI	223	Bamako	ML	XOF	🇲🇱	fr-ML,bm	Mali	466	.ml
+MM	MMR	95	Nay Pyi Taw	MM	MMK	🇲🇲	my	Myanmar	104	.mm
+MN	MNG	976	Ulaanbaatar	MN	MNT	🇲🇳	mn,ru	Mongolia	496	.mn
+MO	MAC	853	Macao	CN	MOP	🇲🇴	zh,zh-MO,pt	Macao	446	.mo
+MP	MNP	1-670	Saipan	US	USD	🇲🇵	fil,tl,zh,ch-MP,en-MP	Northern Mariana Islands	580	.mp
+MQ	MTQ	596	Fort-de-France	FR	EUR	🇲🇶	fr-MQ	Martinique	474	.mq
+MR	MRT	222	Nouakchott	MR	MRU	🇲🇷	ar-MR,fuc,snk,fr,mey,wo	Mauritania	478	.mr
+MS	MSR	1-664	Plymouth	GB	XCD	🇲🇸	en-MS	Montserrat	500	.ms
+MT	MLT	356	Valletta	MT	EUR	🇲🇹	mt,en-MT	Malta	470	.mt
+MU	MUS	230	Port Louis	MU	MUR	🇲🇺	en-MU,bho,fr	Mauritius	480	.mu
+MV	MDV	960	Male	MV	MVR	🇲🇻	dv,en	Maldives	462	.mv
+MW	MWI	265	Lilongwe	MW	MWK	🇲🇼	ny,yao,tum,swk	Malawi	454	.mw
+MX	MEX	52	Mexico City	MX	MXN	🇲🇽	es-MX	Mexico	484	.mx
+MY	MYS	60	Kuala Lumpur	MY	MYR	🇲🇾	ms-MY,en,zh,ta,te,ml,pa,th	Malaysia	458	.my
+MZ	MOZ	258	Maputo	MZ	MZN	🇲🇿	pt-MZ,vmw	Mozambique	508	.mz
+NA	NAM	264	Windhoek	NA	NAD	🇳🇦	en-NA,af,de,hz,naq	Namibia	516	.na
+NC	NCL	687	Noumea	FR	XPF	🇳🇨	fr-NC	New Caledonia	540	.nc
+NE	NER	227	Niamey	NE	XOF	🇳🇪	fr-NE,ha,kr,dje	Niger	562	.ne
+NF	NFK	672	Kingston	AU	AUD	🇳🇫	en-NF	Norfolk Island	574	.nf
+NG	NGA	234	Abuja	NG	NGN	🇳🇬	en-NG,ha,yo,ig,ff	Nigeria	566	.ng
+NI	NIC	505	Managua	NI	NIO	🇳🇮	es-NI,en	Nicaragua	558	.ni
+NL	NLD	31	Amsterdam	NL	EUR	🇳🇱	nl-NL,fy-NL	Netherlands	528	.nl
+NO	NOR	47	Oslo	NO	NOK	🇳🇴	no,nb,nn,se,fi	Norway	578	.no
+NP	NPL	977	Kathmandu	NP	NPR	🇳🇵	ne,en	Nepal	524	.np
+NR	NRU	674	Yaren	NR	AUD	🇳🇷	na,en-NR	Nauru	520	.nr
+NU	NIU	683	Alofi	NZ	NZD	🇳🇺	niu,en-NU	Niue	570	.nu
+NZ	NZL	64	Wellington	NZ	NZD	🇳🇿	en-NZ,mi	New Zealand	554	.nz
+OM	OMN	968	Muscat	OM	OMR	🇴🇲	ar-OM,en,bal,ur	Oman	512	.om
+PA	PAN	507	Panama City	PA	PAB	🇵🇦	es-PA,en	Panama	591	.pa
+PE	PER	51	Lima	PE	PEN	🇵🇪	es-PE,qu,ay	Peru	604	.pe
+PF	PYF	689	Papeete	FR	XPF	🇵🇫	fr-PF,ty	French Polynesia	258	.pf
+PG	PNG	675	Port Moresby	PG	PGK	🇵🇬	en-PG,ho,meu,tpi	Papua New Guinea	598	.pg
+PH	PHL	63	Manila	PH	PHP	🇵🇭	tl,en-PH,fil,ceb,ilo,hil,war,pam,bik,bcl,pag,mrw,tsg,mdh,cbk,krj,sgd,msb,akl,ibg,yka,mta,abx	Philippines	608	.ph
+PK	PAK	92	Islamabad	PK	PKR	🇵🇰	ur-PK,en-PK,pa,sd,ps,brh	Pakistan	586	.pk
+PL	POL	48	Warsaw	PL	PLN	🇵🇱	pl	Poland	616	.pl
+PM	SPM	508	Saint-Pierre	FR	EUR	🇵🇲	fr-PM	St. Pierre & Miquelon	666	.pm
+PN	PCN	870	Adamstown	GB	NZD	🇵🇳	en-PN	Pitcairn	612	.pn
+PR	PRI	1	San Juan	US	USD	🇵🇷	en-PR,es-PR	Puerto Rico	630	.pr
+PT	PRT	351	Lisbon	PT	EUR	🇵🇹	pt-PT,mwl	Portugal	620	.pt
+PW	PLW	680	Melekeok	PW	USD	🇵🇼	pau,sov,en-PW,tox,ja,fil,zh	Palau	585	.pw
+PY	PRY	595	Asuncion	PY	PYG	🇵🇾	es-PY,gn	Paraguay	600	.py
+QA	QAT	974	Doha	QA	QAR	🇶🇦	ar-QA,es	Qatar	634	.qa
+RE	REU	262	Saint-Denis	FR	EUR	🇷🇪	fr-RE	Réunion	638	.re
+RO	ROU	40	Bucharest	RO	RON	🇷🇴	ro,hu,rom	Romania	642	.ro
+RS	SRB	381	Belgrade	RS	RSD	🇷🇸	sr,hu,bs,rom	Serbia	688	.rs
+RU	RUS	7	Moscow	RU	RUB	🇷🇺	ru,tt,xal,cau,ady,kv,ce,tyv,cv,udm,tut,mns,bua,myv,mdf,chm,ba,inh,kbd,krc,av,sah,nog	Russia	643	.ru
+RW	RWA	250	Kigali	RW	RWF	🇷🇼	rw,en-RW,fr-RW,sw	Rwanda	646	.rw
+SA	SAU	966	Riyadh	SA	SAR	🇸🇦	ar-SA	Saudi Arabia	682	.sa
+SB	SLB	677	Honiara	SB	SBD	🇸🇧	en-SB,tpi	Solomon Islands	090	.sb
+SC	SYC	248	Victoria	SC	SCR	🇸🇨	en-SC,fr-SC	Seychelles	690	.sc
+SD	SDN	249	Khartoum	SD	SDG	🇸🇩	ar-SD,en,fia	Sudan	729	.sd
+SE	SWE	46	Stockholm	SE	SEK	🇸🇪	sv-SE,se,sma,fi-SE	Sweden	752	.se
+SG	SGP	65	Singapore	SG	SGD	🇸🇬	cmn,en-SG,ms-SG,ta-SG,zh-SG	Singapore	702	.sg
+SH	SHN	290	Jamestown	GB	SHP	🇸🇭	en-SH	St. Helena	654	.sh
+SI	SVN	386	Ljubljana	SI	EUR	🇸🇮	sl,sh	Slovenia	705	.si
+SJ	SJM	47	Longyearbyen	NO	NOK	🇸🇯	no,ru	Svalbard & Jan Mayen	744	.sj
+SK	SVK	421	Bratislava	SK	EUR	🇸🇰	sk,hu	Slovakia	703	.sk
+SL	SLE	232	Freetown	SL	SLE	🇸🇱	en-SL,men,tem	Sierra Leone	694	.sl
+SM	SMR	378	San Marino	SM	EUR	🇸🇲	it-SM	San Marino	674	.sm
+SN	SEN	221	Dakar	SN	XOF	🇸🇳	fr-SN,wo,fuc,mnk	Senegal	686	.sn
+SO	SOM	252	Mogadishu	SO	SOS	🇸🇴	so-SO,ar-SO,it,en-SO	Somalia	706	.so
+SR	SUR	597	Paramaribo	SR	SRD	🇸🇷	nl-SR,en,srn,hns,jv	Suriname	740	.sr
+SS	SSD	211	Juba	SS	SSP	🇸🇸	en	South Sudan	728	.ss
+ST	STP	239	Sao Tome	ST	STN	🇸🇹	pt-ST	São Tomé & Príncipe	678	.st
+SV	SLV	503	San Salvador	SV	SVC	🇸🇻	es-SV	El Salvador	222	.sv
+SX	SXM	1-721	Philipsburg	NL	XCG	🇸🇽	nl,en	Sint Maarten	534	.sx
+SY	SYR	963	Damascus	SY	SYP	🇸🇾	ar-SY,ku,hy,arc,fr,en	Syria	760	.sy
+SZ	SWZ	268	Mbabane	SZ	SZL	🇸🇿	en-SZ,ss-SZ	Eswatini	748	.sz
+TC	TCA	1-649	Cockburn Town	GB	USD	🇹🇨	en-TC	Turks & Caicos Islands	796	.tc
+TD	TCD	235	N'Djamena	TD	XAF	🇹🇩	fr-TD,ar-TD,sre	Chad	148	.td
+TF	ATF	262	Port-aux-Francais	FR	EUR	🇹🇫	fr	French Southern Territories	260	.tf
+TG	TGO	228	Lome	TG	XOF	🇹🇬	fr-TG,ee,hna,kbp,dag,ha	Togo	768	.tg
+TH	THA	66	Bangkok	TH	THB	🇹🇭	th,en	Thailand	764	.th
+TJ	TJK	992	Dushanbe	TJ	TJS	🇹🇯	tg,ru	Tajikistan	762	.tj
+TL	TLS	670	Dili	TL	USD	🇹🇱	tet,pt-TL,id,en	Timor-Leste	626	.tl
+TM	TKM	993	Ashgabat	TM	TMT	🇹🇲	tk,ru,uz	Turkmenistan	795	.tm
+TN	TUN	216	Tunis	TN	TND	🇹🇳	ar-TN,fr	Tunisia	788	.tn
+TO	TON	676	Nuku'alofa	TO	TOP	🇹🇴	to,en-TO	Tonga	776	.to
+TR	TUR	90	Ankara	TR	TRY	🇹🇷	tr-TR,ku,diq,az,av	Türkiye	792	.tr
+TT	TTO	1-868	Port of Spain	TT	TTD	🇹🇹	en-TT,hns,fr,es,zh	Trinidad & Tobago	780	.tt
+TV	TUV	688	Funafuti	TV	AUD	🇹🇻	tvl,en,sm,gil	Tuvalu	798	.tv
+TW	TWN	886	Taipei	TW	TWD	🇹🇼	zh-TW,zh,nan,hak	Taiwan	158	.tw
+TZ	TZA	255	Dodoma	TZ	TZS	🇹🇿	sw-TZ,en,ar	Tanzania	834	.tz
+UA	UKR	380	Kyiv	UA	UAH	🇺🇦	uk,ru-UA,rom,pl,hu	Ukraine	804	.ua
+UG	UGA	256	Kampala	UG	UGX	🇺🇬	en-UG,lg,sw,ar	Uganda	800	.ug
+US	USA	1	Washington	US	USD	🇺🇸	en-US,es-US,haw,fr	US	840	.us
+UY	URY	598	Montevideo	UY	UYU	🇺🇾	es-UY	Uruguay	858	.uy
+UZ	UZB	998	Tashkent	UZ	UZS	🇺🇿	uz,ru,tg	Uzbekistan	860	.uz
+VA	VAT	39	Vatican City	VA	EUR	🇻🇦	la,it,fr	Vatican City	336	.va
+VC	VCT	1-784	Kingstown	VC	XCD	🇻🇨	en-VC,fr	St. Vincent & Grenadines	670	.vc
+VE	VEN	58	Caracas	VE	VES	🇻🇪	es-VE	Venezuela	862	.ve
+VG	VGB	1-284	Road Town	GB	USD	🇻🇬	en-VG	British Virgin Islands	092	.vg
+VI	VIR	1-340	Charlotte Amalie	US	USD	🇻🇮	en-VI	U.S. Virgin Islands	850	.vi
+VN	VNM	84	Hanoi	VN	VND	🇻🇳	vi,en,fr,zh,km	Vietnam	704	.vn
+VU	VUT	678	Port Vila	VU	VUV	🇻🇺	bi,en-VU,fr-VU	Vanuatu	548	.vu
+WF	WLF	681	Mata Utu	FR	XPF	🇼🇫	wls,fud,fr-WF	Wallis & Futuna	876	.wf
+WS	WSM	685	Apia	WS	WST	🇼🇸	sm,en-WS	Samoa	882	.ws
+YE	YEM	967	Sanaa	YE	YER	🇾🇪	ar-YE	Yemen	887	.ye
+YT	MYT	262	Mamoudzou	FR	EUR	🇾🇹	fr-YT	Mayotte	175	.yt
+ZA	ZAF	27	Pretoria	ZA	ZAR	🇿🇦	zu,xh,af,nso,en-ZA,tn,st,ts,ss,ve,nr	South Africa	710	.za
+ZM	ZMB	260	Lusaka	ZM	ZMW	🇿🇲	en-ZM,bem,loz,lun,lue,ny,toi	Zambia	894	.zm
+ZW	ZWE	263	Harare	ZW	ZWG	🇿🇼	en-ZW,sn,nr,nd	Zimbabwe	716	.zw

data/misc/timezone.json

@@ -1 +1 @@
-["UTC", "Africa/Cairo", "Africa/Johannesburg", "America/Chicago", "America/Denver", "America/Los_Angeles", "America/Mexico_City", "America/New_York", "America/Sao_Paulo", "America/Toronto", "Asia/Dubai", "Asia/Hong_Kong", "Asia/Kolkata", "Asia/Shanghai", "Asia/Singapore", "Asia/Tokyo", "Australia/Sydney", "Europe/Amsterdam", "Europe/Berlin", "Europe/London", "Europe/Madrid", "Europe/Moscow", "Europe/Oslo", "Europe/Paris", "Europe/Stockholm", "Europe/Warsaw", "Pacific/Auckland"]
+{ "format": "{zone}", "rows": "timezone.tsv", "key": "zone", "parent": "territory", "weight": "weight" }

data/misc/timezone.tsv

@@ -0,0 +1,402 @@
+offset	territory	weight	zone
++00:00	CI	17496811	Africa/Abidjan
++00:00	GH	11277813	Africa/Accra
++03:00	ET	18690487	Africa/Addis_Ababa
++01:00	DZ	20111539	Africa/Algiers
++03:00	ER	798575	Africa/Asmara
++00:00	ML	7673493	Africa/Bamako
++01:00	CF	2582076	Africa/Bangui
++00:00	GM	1305981	Africa/Banjul
++00:00	GW	904776	Africa/Bissau
++02:00	MW	3030905	Africa/Blantyre
++01:00	CG	3748808	Africa/Brazzaville
++02:00	BI	1251675	Africa/Bujumbura
++02:00	EG	47242427	Africa/Cairo
++00:00	MA	22808531	Africa/Casablanca
++01:00	ES	85985	Africa/Ceuta
++00:00	GN	6679241	Africa/Conakry
++00:00	SN	10055356	Africa/Dakar
++03:00	TZ	21350525	Africa/Dar_es_Salaam
++03:00	DJ	1316108	Africa/Djibouti
++01:00	CM	8330801	Africa/Douala
++00:00	EH	374107	Africa/El_Aaiun
++00:00	SL	1752243	Africa/Freetown
++02:00	BW	1262880	Africa/Gaborone
++02:00	ZW	4508424	Africa/Harare
++02:00	ZA	47939803	Africa/Johannesburg
++02:00	SS	1679674	Africa/Juba
++03:00	UG	9664318	Africa/Kampala
++02:00	SD	11781926	Africa/Khartoum
++02:00	RW	2910190	Africa/Kigali
++01:00	CD	20651243	Africa/Kinshasa
++01:00	NG	75725576	Africa/Lagos
++01:00	GA	1731692	Africa/Libreville
++00:00	TG	3089219	Africa/Lome
++01:00	AO	23567341	Africa/Luanda
++02:00	CD	16660579	Africa/Lubumbashi
++02:00	ZM	8422414	Africa/Lusaka
++01:00	GQ	355840	Africa/Malabo
++02:00	MZ	8598836	Africa/Maputo
++02:00	LS	739682	Africa/Maseru
++02:00	SZ	191312	Africa/Mbabane
++03:00	SO	6165052	Africa/Mogadishu
++00:00	LR	2127307	Africa/Monrovia
++03:00	KE	16920989	Africa/Nairobi
++01:00	TD	3363418	Africa/Ndjamena
++01:00	NE	3689982	Africa/Niamey
++00:00	MR	2157288	Africa/Nouakchott
++00:00	BF	6125427	Africa/Ouagadougou
++01:00	BJ	4001576	Africa/Porto-Novo
++00:00	ST	53300	Africa/Sao_Tome
++02:00	LY	6105792	Africa/Tripoli
++01:00	TN	7314557	Africa/Tunis
++02:00	NA	983097	Africa/Windhoek
+-10:00	US	15000	America/Adak
+-09:00	US	366200	America/Anchorage
+-04:00	AI	15000	America/Anguilla
+-04:00	AG	51737	America/Antigua
+-03:00	BR	858988	America/Araguaina
+-03:00	AR	11817784	America/Argentina/Buenos_Aires
+-03:00	AR	580969	America/Argentina/Catamarca
+-03:00	AR	8998034	America/Argentina/Cordoba
+-03:00	AR	413866	America/Argentina/Jujuy
+-03:00	AR	237745	America/Argentina/La_Rioja
+-03:00	AR	695484	America/Argentina/Mendoza
+-03:00	AR	241619	America/Argentina/Rio_Gallegos
+-03:00	AR	2120781	America/Argentina/Salta
+-03:00	AR	518624	America/Argentina/San_Juan
+-03:00	AR	266728	America/Argentina/San_Luis
+-03:00	AR	788916	America/Argentina/Tucuman
+-03:00	AR	109506	America/Argentina/Ushuaia
+-04:00	AW	90927	America/Aruba
+-03:00	PY	3653883	America/Asuncion
+-05:00	CA	15000	America/Atikokan
+-03:00	BR	13131907	America/Bahia
+-06:00	MX	36253	America/Bahia_Banderas
+-04:00	BB	98511	America/Barbados
+-03:00	BR	7977349	America/Belem
+-06:00	BZ	132559	America/Belize
+-04:00	CA	15000	America/Blanc-Sablon
+-04:00	BR	550434	America/Boa_Vista
+-05:00	CO	37243567	America/Bogota
+-07:00	US	748802	America/Boise
+-07:00	CA	15000	America/Cambridge_Bay
+-04:00	BR	2429053	America/Campo_Grande
+-05:00	MX	1328961	America/Cancun
+-04:00	VE	28324666	America/Caracas
+-03:00	GF	155245	America/Cayenne
+-05:00	KY	44705	America/Cayman
+-06:00	US	55510713	America/Chicago
+-06:00	MX	1533843	America/Chihuahua
+-07:00	MX	1512450	America/Ciudad_Juarez
+-06:00	CR	1458629	America/Costa_Rica
+-03:00	CL	62723	America/Coyhaique
+-07:00	CA	15000	America/Creston
+-04:00	BR	2960376	America/Cuiaba
+-04:00	CW	145838	America/Curacao
++00:00	GL	15000	America/Danmarkshavn
+-07:00	CA	15000	America/Dawson
+-07:00	CA	21465	America/Dawson_Creek
+-07:00	US	9069711	America/Denver
+-05:00	US	4344725	America/Detroit
+-04:00	DM	16571	America/Dominica
+-06:00	CA	3518059	America/Edmonton
+-05:00	BR	142900	America/Eirunepe
+-06:00	SV	2571611	America/El_Salvador
+-07:00	CA	15000	America/Fort_Nelson
+-03:00	BR	21824546	America/Fortaleza
+-04:00	CA	122883	America/Glace_Bay
+-04:00	CA	15000	America/Goose_Bay
+-05:00	TC	27489	America/Grand_Turk
+-04:00	GD	15000	America/Grenada
+-04:00	GP	250260	America/Guadeloupe
+-06:00	GT	7302205	America/Guatemala
+-05:00	EC	11564603	America/Guayaquil
+-04:00	GY	314746	America/Guyana
+-04:00	CA	843888	America/Halifax
+-05:00	CU	11972822	America/Havana
+-07:00	MX	2215048	America/Hermosillo
+-05:00	US	2672398	America/Indiana/Indianapolis
+-06:00	US	15000	America/Indiana/Knox
+-05:00	US	15000	America/Indiana/Marengo
+-05:00	US	15000	America/Indiana/Petersburg
+-06:00	US	15000	America/Indiana/Tell_City
+-05:00	US	15000	America/Indiana/Vevay
+-05:00	US	15451	America/Indiana/Vincennes
+-05:00	US	15000	America/Indiana/Winamac
+-06:00	CA	15000	America/Inuvik
+-05:00	CA	15000	America/Iqaluit
+-05:00	JM	2069735	America/Jamaica
+-09:00	US	31555	America/Juneau
+-05:00	US	909379	America/Kentucky/Louisville
+-05:00	US	15000	America/Kentucky/Monticello
+-04:00	BO	6958595	America/La_Paz
+-05:00	PE	21406340	America/Lima
+-08:00	US	46301242	America/Los_Angeles
+-04:00	SX	15000	America/Lower_Princes
+-03:00	BR	4805317	America/Maceio
+-06:00	NI	2621115	America/Managua
+-04:00	BR	3918958	America/Manaus
+-04:00	MF	15000	America/Marigot
+-04:00	MQ	243860	America/Martinique
+-06:00	MX	1899165	America/Matamoros
+-07:00	MX	2951216	America/Mazatlan
+-06:00	US	15000	America/Menominee
+-06:00	MX	4154924	America/Merida
+-09:00	US	15000	America/Metlakatla
+-06:00	MX	61603325	America/Mexico_City
+-03:00	PM	15000	America/Miquelon
+-04:00	CA	381536	America/Moncton
+-06:00	MX	9714766	America/Monterrey
+-03:00	UY	2457462	America/Montevideo
+-04:00	MS	15000	America/Montserrat
+-05:00	BS	319054	America/Nassau
+-05:00	US	88988896	America/New_York
+-09:00	US	15000	America/Nome
+-02:00	BR	15000	America/Noronha
+-06:00	US	15000	America/North_Dakota/Beulah
+-06:00	US	15000	America/North_Dakota/Center
+-06:00	US	21382	America/North_Dakota/New_Salem
+-02:00	GL	15000	America/Nuuk
+-06:00	MX	50784	America/Ojinaga
+-05:00	PA	1692726	America/Panama
+-03:00	SR	454064	America/Paramaribo
+-07:00	US	6541994	America/Phoenix
+-05:00	HT	5328623	America/Port-au-Prince
+-04:00	TT	456832	America/Port_of_Spain
+-04:00	BR	1551818	America/Porto_Velho
+-04:00	PR	1605968	America/Puerto_Rico
+-03:00	CL	135935	America/Punta_Arenas
+-06:00	CA	15000	America/Rankin_Inlet
+-03:00	BR	8832691	America/Recife
+-06:00	CA	982810	America/Regina
+-06:00	CA	15000	America/Resolute
+-05:00	BR	794527	America/Rio_Branco
+-03:00	BR	1403419	America/Santarem
+-04:00	CL	15912038	America/Santiago
+-04:00	DO	7521391	America/Santo_Domingo
+-03:00	BR	129186469	America/Sao_Paulo
+-02:00	GL	15000	America/Scoresbysund
+-09:00	US	15000	America/Sitka
+-04:00	BL	15000	America/St_Barthelemy
+-03:30	CA	202443	America/St_Johns
+-04:00	KN	15000	America/St_Kitts
+-04:00	LC	45210	America/St_Lucia
+-04:00	VI	70601	America/St_Thomas
+-04:00	VC	48723	America/St_Vincent
+-06:00	CA	16604	America/Swift_Current
+-06:00	HN	4808928	America/Tegucigalpa
+-04:00	GL	15000	America/Thule
+-08:00	MX	3797218	America/Tijuana
+-05:00	CA	24763654	America/Toronto
+-04:00	VG	15000	America/Tortola
+-07:00	CA	6340886	America/Vancouver
+-07:00	CA	28201	America/Whitehorse
+-06:00	CA	922566	America/Winnipeg
+-09:00	US	15000	America/Yakutat
++10:00	AU	15000	Antarctica/Macquarie
++01:00	SJ	15000	Arctic/Longyearbyen
++03:00	YE	6904010	Asia/Aden
++05:00	KZ	9055499	Asia/Almaty
++03:00	JO	4950859	Asia/Amman
++12:00	RU	15604	Asia/Anadyr
++05:00	KZ	282409	Asia/Aqtau
++05:00	KZ	598827	Asia/Aqtobe
++05:00	TM	2706037	Asia/Ashgabat
++05:00	KZ	388248	Asia/Atyrau
++03:00	IQ	29681856	Asia/Baghdad
++03:00	BH	815447	Asia/Bahrain
++04:00	AZ	5491302	Asia/Baku
++07:00	TH	49896297	Asia/Bangkok
++07:00	RU	1413356	Asia/Barnaul
++02:00	LB	4467748	Asia/Beirut
++06:00	KG	2233412	Asia/Bishkek
++08:00	BN	230416	Asia/Brunei
++09:00	RU	486311	Asia/Chita
++05:30	LK	4297175	Asia/Colombo
++03:00	SY	10939175	Asia/Damascus
++06:00	BD	35955225	Asia/Dhaka
++09:00	TL	311685	Asia/Dili
++04:00	AE	12931222	Asia/Dubai
++05:00	TJ	2578933	Asia/Dushanbe
++02:00	CY	109959	Asia/Famagusta
++07:00	VN	42129036	Asia/Ho_Chi_Minh
++08:00	HK	24678261	Asia/Hong_Kong
++07:00	MN	122174	Asia/Hovd
++08:00	RU	2231790	Asia/Irkutsk
++07:00	ID	68794489	Asia/Jakarta
++09:00	ID	2512221	Asia/Jayapura
++02:00	IL	7901151	Asia/Jerusalem
++04:30	AF	8764027	Asia/Kabul
++12:00	RU	247112	Asia/Kamchatka
++05:00	PK	88744953	Asia/Karachi
++05:45	NP	5913313	Asia/Kathmandu
++09:00	RU	15000	Asia/Khandyga
++05:30	IN	365373326	Asia/Kolkata
++07:00	RU	2615869	Asia/Krasnoyarsk
++08:00	MY	33322164	Asia/Kuala_Lumpur
++08:00	MY	4013140	Asia/Kuching
++03:00	KW	1662180	Asia/Kuwait
++08:00	MO	1236695	Asia/Macau
++11:00	RU	92782	Asia/Magadan
++08:00	ID	12458359	Asia/Makassar
++08:00	PH	64227523	Asia/Manila
++04:00	OM	3290021	Asia/Muscat
++02:00	CY	679420	Asia/Nicosia
++07:00	RU	2355475	Asia/Novokuznetsk
++07:00	RU	2119272	Asia/Novosibirsk
++06:00	RU	1243165	Asia/Omsk
++05:00	KZ	364799	Asia/Oral
++07:00	KH	4111780	Asia/Phnom_Penh
++07:00	ID	1819584	Asia/Pontianak
++09:00	KP	12876883	Asia/Pyongyang
++03:00	QA	1566088	Asia/Qatar
++05:00	KZ	529104	Asia/Qostanay
++05:00	KZ	511391	Asia/Qyzylorda
++03:00	SA	23913997	Asia/Riyadh
++11:00	RU	326982	Asia/Sakhalin
++05:00	UZ	3864475	Asia/Samarkand
++09:00	KR	47400555	Asia/Seoul
++08:00	CN	861293141	Asia/Shanghai
++08:00	SG	11621053	Asia/Singapore
++11:00	RU	15000	Asia/Srednekolymsk
++08:00	TW	26394699	Asia/Taipei
++05:00	UZ	7452125	Asia/Tashkent
++04:00	GE	1827911	Asia/Tbilisi
++03:30	IR	50648371	Asia/Tehran
++06:00	BT	170210	Asia/Thimphu
++09:00	JP	141330654	Asia/Tokyo
++07:00	RU	783576	Asia/Tomsk
++08:00	MN	1438738	Asia/Ulaanbaatar
++06:00	CN	12667986	Asia/Urumqi
++10:00	RU	15000	Asia/Ust-Nera
++07:00	LA	1561716	Asia/Vientiane
++10:00	RU	2534711	Asia/Vladivostok
++09:00	RU	902983	Asia/Yakutsk
++06:30	MM	18836338	Asia/Yangon
++05:00	RU	15407217	Asia/Yekaterinburg
++04:00	AM	2880620	Asia/Yerevan
+-01:00	PT	20056	Atlantic/Azores
+-04:00	BM	15000	Atlantic/Bermuda
++00:00	ES	2054431	Atlantic/Canary
+-01:00	CV	252678	Atlantic/Cape_Verde
++00:00	FO	15000	Atlantic/Faroe
++00:00	PT	213794	Atlantic/Madeira
++00:00	IS	245356	Atlantic/Reykjavik
++00:00	SH	15000	Atlantic/St_Helena
+-03:00	FK	15000	Atlantic/Stanley
++09:30	AU	1706678	Australia/Adelaide
++10:00	AU	5807246	Australia/Brisbane
++09:30	AU	17456	Australia/Broken_Hill
++09:30	AU	199509	Australia/Darwin
++08:45	AU	15000	Australia/Eucla
++10:00	AU	392450	Australia/Hobart
++10:00	AU	15000	Australia/Lindeman
++10:30	AU	15000	Australia/Lord_Howe
++10:00	AU	9304158	Australia/Melbourne
++08:00	AU	3086441	Australia/Perth
++10:00	AU	9352313	Australia/Sydney
++01:00	NL	13892513	Europe/Amsterdam
++01:00	AD	36283	Europe/Andorra
++04:00	RU	644812	Europe/Astrakhan
++02:00	GR	6286690	Europe/Athens
++01:00	RS	5756549	Europe/Belgrade
++01:00	DE	62740682	Europe/Berlin
++01:00	SK	2548401	Europe/Bratislava
++01:00	BE	9038306	Europe/Brussels
++02:00	RO	11070040	Europe/Bucharest
++01:00	HU	9366333	Europe/Budapest
++01:00	DE	15000	Europe/Busingen
++02:00	MD	1460347	Europe/Chisinau
++01:00	DK	3885672	Europe/Copenhagen
++01:00	IE	2720758	Europe/Dublin
++01:00	GI	26544	Europe/Gibraltar
++00:00	GG	16488	Europe/Guernsey
++02:00	FI	5265184	Europe/Helsinki
++00:00	IM	26218	Europe/Isle_of_Man
++03:00	TR	77554557	Europe/Istanbul
++00:00	JE	28000	Europe/Jersey
++02:00	RU	664545	Europe/Kaliningrad
++03:00	RU	782604	Europe/Kirov
++02:00	UA	35633582	Europe/Kyiv
++00:00	PT	6372176	Europe/Lisbon
++01:00	SI	552127	Europe/Ljubljana
++00:00	GB	57817786	Europe/London
++01:00	LU	131322	Europe/Luxembourg
++01:00	ES	42918247	Europe/Madrid
++01:00	MT	141714	Europe/Malta
++02:00	AX	15000	Europe/Mariehamn
++03:00	BY	6105410	Europe/Minsk
++01:00	MC	48977	Europe/Monaco
++03:00	RU	69342062	Europe/Moscow
++01:00	NO	3296711	Europe/Oslo
++01:00	FR	33093827	Europe/Paris
++01:00	ME	398494	Europe/Podgorica
++01:00	CZ	5924565	Europe/Prague
++02:00	LV	1206422	Europe/Riga
++01:00	IT	34033666	Europe/Rome
++04:00	RU	3546813	Europe/Samara
++01:00	SM	15000	Europe/San_Marino
++01:00	BA	1905798	Europe/Sarajevo
++04:00	RU	1705529	Europe/Saratov
++03:00	UA	1620906	Europe/Simferopol
++01:00	MK	1754303	Europe/Skopje
++02:00	BG	4111057	Europe/Sofia
++01:00	SE	7149541	Europe/Stockholm
++02:00	EE	1106943	Europe/Tallinn
++01:00	AL	1629643	Europe/Tirane
++04:00	RU	814189	Europe/Ulyanovsk
++01:00	LI	15000	Europe/Vaduz
++01:00	VA	15000	Europe/Vatican
++01:00	AT	5274040	Europe/Vienna
++02:00	LT	2103133	Europe/Vilnius
++03:00	RU	1837053	Europe/Volgograd
++01:00	PL	22720110	Europe/Warsaw
++01:00	HR	1650334	Europe/Zagreb
++01:00	CH	3461664	Europe/Zurich
++03:00	MG	6115943	Indian/Antananarivo
++06:00	IO	15000	Indian/Chagos
++07:00	CX	15000	Indian/Christmas
++06:30	CC	15000	Indian/Cocos
++03:00	KM	118353	Indian/Comoro
++05:00	TF	15000	Indian/Kerguelen
++04:00	SC	22881	Indian/Mahe
++05:00	MV	103693	Indian/Maldives
++04:00	MU	701493	Indian/Mauritius
++03:00	YT	138967	Indian/Mayotte
++04:00	RE	804329	Indian/Reunion
++13:00	WS	40407	Pacific/Apia
++12:00	NZ	5203989	Pacific/Auckland
++11:00	PG	40266	Pacific/Bougainville
++12:45	NZ	15000	Pacific/Chatham
++10:00	FM	15000	Pacific/Chuuk
+-06:00	CL	15000	Pacific/Easter
++11:00	VU	35901	Pacific/Efate
++12:00	FJ	334403	Pacific/Fiji
++12:00	TV	15000	Pacific/Funafuti
+-06:00	EC	15000	Pacific/Galapagos
+-09:00	PF	15000	Pacific/Gambier
++11:00	SB	194707	Pacific/Guadalcanal
++10:00	GU	121094	Pacific/Guam
+-10:00	US	1569453	Pacific/Honolulu
++13:00	KI	15000	Pacific/Kanton
++14:00	KI	15000	Pacific/Kiritimati
++11:00	FM	15000	Pacific/Kosrae
++12:00	MH	15000	Pacific/Kwajalein
++12:00	MH	45701	Pacific/Majuro
+-09:30	PF	15000	Pacific/Marquesas
++12:00	NR	15000	Pacific/Nauru
+-11:00	NU	15000	Pacific/Niue
++11:00	NF	15000	Pacific/Norfolk
++11:00	NC	137086	Pacific/Noumea
+-11:00	AS	15000	Pacific/Pago_Pago
++09:00	PW	15000	Pacific/Palau
+-08:00	PN	15000	Pacific/Pitcairn
++11:00	FM	15000	Pacific/Pohnpei
++10:00	PG	588589	Pacific/Port_Moresby
+-10:00	CK	15000	Pacific/Rarotonga
++10:00	MP	48220	Pacific/Saipan
+-10:00	PF	81958	Pacific/Tahiti
++12:00	KI	40311	Pacific/Tarawa
++13:00	TO	22400	Pacific/Tongatapu
++12:00	WF	15000	Pacific/Wallis

data/misc/tld.json

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

data/misc/useragent.json

@@ -1 +1 @@
-["Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:124.0) Gecko/20100101 Firefox/124.0", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:123.0) Gecko/20100101 Firefox/123.0", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4 Safari/605.1.15", "Mozilla/5.0 (iPhone; CPU iPhone OS 17_4 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4 Mobile/15E148 Safari/604.1", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0"]
+{ "format": "{ua}", "rows": "useragent.tsv" }

data/misc/useragent.tsv

@@ -0,0 +1,97 @@
+browser	device	os	ua
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/153.0.0.0 Mobile Safari/537.36
+Chrome	mobile	Android	Mozilla/5.0 (Linux; Android 12; Pixel 6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36
+Chrome	desktop	ChromeOS	Mozilla/5.0 (X11; CrOS x86_64 14541.0.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36
+Chrome	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/153.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.5938.132 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 YaBrowser/26.8.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.7922.34 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36
+Chrome	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/153.0.0.0 Safari/537.36
+Chrome	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 26_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/152.0.7977.64 Mobile/15E148 Safari/604.1
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36
+Chrome	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/153.0.0.0 Safari/537.36
+Edge	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36 Edg/151.0.0.0
+Edge	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36 Edg/152.0.0.0
+Edge	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/153.0.0.0 Safari/537.36 Edg/153.0.0.0
+Edge	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/152.0.0.0 Safari/537.36 Edg/152.0.0.0
+Firefox	desktop	Linux	Mozilla/5.0 (X11; Linux x86_64; rv:155.0) Gecko/20100101 Firefox/155.0
+Firefox	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:126.0) Gecko/20100101 Firefox/126.0
+Firefox	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:154.0) Gecko/20100101 Firefox/154.0
+Firefox	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:155.0) Gecko/20100101 Firefox/155.0
+Firefox	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:154.0) Gecko/20100101 Firefox/154.0
+Firefox	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:155.0) Gecko/20100101 Firefox/155.0
+Opera	desktop	Windows	Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/151.0.0.0 Safari/537.36 OPR/135.0.0.0
+Opera	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36 OPR/134.0.0.0
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.5 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.7.5 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.2 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.3 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.5 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.5.2 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.6 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.6.1 Mobile/15E148 Safari/604.1
+Safari	mobile	iOS	Mozilla/5.0 (iPhone; CPU iPhone OS 18_7 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/27.0 Mobile/15E148 Safari/604.1
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.6 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.2 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.5 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.5.2 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.6 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.6.1 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/26.6.2 Safari/605.1.15
+Safari	desktop	macOS	Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/27.0 Safari/605.1.15
+Samsung Internet	mobile	Android	Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/30.0 Chrome/143.0.0.0 Mobile Safari/537.36

data/sv_SE/address.json

@@ -1,21 +1,7 @@
 {
   "format": "{street} {street-number}\n{postal-code} {locality}",
-  "street": [
+  "street": "{/geo.SE.address.street}",
-    {
+  "street-number": "{/geo.SE.address.street-number}",
-      "format": "{first}{last}",
+  "postal-code": "{/geo.SE.address.postal-code}",
-      "first": ["Ängs", "Bergs", "Björk", "Drottning", "Eke", "Furu", "Hamn", "Köpmans", "Kungs", "Linné", "Norra", "Nybro", "Oden", "Öster", "Park", "Skogs", "Skol", "Slotts", "Söder", "Stations", "Stor", "Strand", "Trädgårds", "Vasa", "Väster"],
+  "locality": "{/geo.SE.address.locality}"
-      "last": ["gatan", "vägen", "stigen", "gränd", "backen", "torget", "allén"]
-    },
-    ["Avenyn", "Birger Jarlsgatan", "Promenaden", "Staby", "Sveavägen", "Vintjärn"]
-  ],
-  "street-number": [
-    "{int(1,9)}",
-    "{int(10,99)}",
-    { "format": "{int(100,999)}", "weight": 0.2 },
-    { "format": "{int(1,9)}{upper(1)}", "weight": 0.2 },
-    { "format": "{int(10,99)}{upper(1)}", "weight": 0.1 },
-    { "format": "{int(100,999)}{upper(1)}", "weight": 0.05 }
-  ],
-  "postal-code": "{int(100,999)} {int(10,99)}",
-  "locality": ["Alingsås", "Alvesta", "Ängelholm", "Arboga", "Arvika", "Avesta", "Boden", "Bollnäs", "Borås", "Borlänge", "Enköping", "Eskilstuna", "Eslöv", "Fagersta", "Falkenberg", "Falköping", "Falun", "Finspång", "Gällivare", "Gävle", "Göteborg", "Halmstad", "Haparanda", "Härnösand", "Hässleholm", "Helsingborg", "Huddinge", "Hudiksvall", "Jönköping", "Kalmar", "Karlshamn", "Karlskoga", "Karlskrona", "Karlstad", "Katrineholm", "Kiruna", "Köping", "Kramfors", "Kristianstad", "Kristinehamn", "Landskrona", "Lidingö", "Lidköping", "Lindesberg", "Linköping", "Ljungby", "Ludvika", "Luleå", "Lund", "Lycksele", "Malmö", "Mariestad", "Mjölby", "Mölndal", "Mora", "Motala", "Nacka", "Nässjö", "Norrköping", "Norrtälje", "Nyköping", "Nynäshamn", "Örebro", "Örnsköldsvik", "Oskarshamn", "Östersund", "Piteå", "Rabbalshede", "Ronneby", "Säffle", "Sandviken", "Sävsjö", "Sigtuna", "Skara", "Skellefteå", "Skövde", "Söderhamn", "Södertälje", "Sollentuna", "Solna", "Sölvesborg", "Stockholm", "Strängnäs", "Sundbyberg", "Sundsvall", "Täby", "Tierp", "Tranås", "Trelleborg", "Trollhättan", "Uddevalla", "Ulricehamn", "Umeå", "Upplands Väsby", "Uppsala", "Vänersborg", "Varberg", "Värnamo", "Västerås", "Västervik", "Växjö", "Vetlanda", "Vimmerby", "Visby", "Ystad"]
 }

data/sv_SE/birth-number.json

@@ -0,0 +1 @@
+{ "format": "{number}", "rows": "birth-number.tsv", "parent": "sex" }

data/sv_SE/birth-number.tsv

@@ -0,0 +1,3 @@
+sex	number
+f	238
+m	239

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": [null, { "format": "{.title.name} ", "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 }]
 }