@mailwoman/codex 7.2.0 → 7.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/address-system-conventions.ts +68 -0
- package/au/delivery-service.ts +179 -0
- package/au/index.ts +15 -0
- package/au/level-designator.ts +209 -0
- package/au/postcode.ts +51 -0
- package/au/state.ts +35 -0
- package/ca/index.ts +12 -0
- package/ca/postal-code.ts +121 -0
- package/ca/province.ts +99 -0
- package/ca/street-type.ts +167 -0
- package/country/codes.ts +534 -0
- package/country/country.ts +125 -0
- package/country/index.ts +15 -0
- package/country/names.ts +274 -0
- package/country/official-languages.ts +397 -0
- package/country/reference-data.ts +267 -0
- package/country/reference.ts +47 -0
- package/country/subdivision.ts +93 -0
- package/de/bundesland.ts +102 -0
- package/de/index.ts +12 -0
- package/de/postleitzahl.ts +91 -0
- package/de/street-type.ts +83 -0
- package/fr/cedex.ts +56 -0
- package/fr/code-postal.ts +105 -0
- package/fr/departement.ts +142 -0
- package/fr/index.ts +14 -0
- package/fr/region.ts +93 -0
- package/fr/voie.ts +98 -0
- package/gb/country.ts +74 -0
- package/gb/index.ts +14 -0
- package/gb/postcode-area.ts +107 -0
- package/gb/postcode.ts +109 -0
- package/gb/street-type.ts +90 -0
- package/index.ts +38 -0
- package/jp/address-unit.ts +87 -0
- package/jp/index.ts +13 -0
- package/jp/postal-code.ts +93 -0
- package/jp/prefecture.ts +173 -0
- package/level-semantics.ts +623 -0
- package/nz/delivery-service.ts +211 -0
- package/nz/index.ts +12 -0
- package/nz/postcode.ts +42 -0
- package/out/country/index.d.ts +1 -0
- package/out/country/index.d.ts.map +1 -1
- package/out/country/index.js +1 -0
- package/out/country/index.js.map +1 -1
- package/out/country/subdivision.d.ts +44 -0
- package/out/country/subdivision.d.ts.map +1 -0
- package/out/country/subdivision.js +76 -0
- package/out/country/subdivision.js.map +1 -0
- package/package.json +81 -37
- package/postcode-systems.ts +68 -0
- package/tools/build-country-surface-lexicon.ts +166 -0
- package/tools/export-country-surfaces.ts +46 -0
- package/tools/generate-country-reference.ts +153 -0
- package/tools/generate-official-languages.ts +188 -0
- package/tools/index.ts +12 -0
- package/us/floor-designator.ts +119 -0
- package/us/index.ts +19 -0
- package/us/military-address.ts +199 -0
- package/us/po-box.ts +82 -0
- package/us/state.ts +156 -0
- package/us/street-directional.ts +220 -0
- package/us/street-suffix.ts +345 -0
- package/us/unit-designator.ts +223 -0
- package/us/zipcode.ts +212 -0
|
@@ -0,0 +1,223 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* USPS Publication 28, Appendix C2 — Secondary Unit Designators.
|
|
7
|
+
*
|
|
8
|
+
* The sibling of {@link ./street-suffix.ts}: where that table standardizes the trailing street
|
|
9
|
+
* _type_ (AVENUE → AVE), this one standardizes the _secondary unit_ designator that introduces an
|
|
10
|
+
* apartment / suite / floor / room (APARTMENT → APT, SUITE → STE). For each canonical designator
|
|
11
|
+
* the value lists recognized variants in USPS order; the first is the approved USPS abbreviation
|
|
12
|
+
* (what the post office prints).
|
|
13
|
+
*
|
|
14
|
+
* Used by `@mailwoman/corpus`'s synthesis layer (the `unit-{expand,abbreviate}` augmentations) to
|
|
15
|
+
* vary the designator in a `unit` component while preserving the identifier — the data-generation
|
|
16
|
+
* counterpart to the runtime `UnitDesignatorClassifier` (which matches the broader libpostal
|
|
17
|
+
* `unit_types` lexicon). Designators are LEADING ("Apt 4B"), unlike street suffixes which trail.
|
|
18
|
+
*
|
|
19
|
+
* `US_UNIT_DESIGNATOR_REQUIRES_RANGE` (added for #1100, the secondary-address epic; retrieved from
|
|
20
|
+
* Appendix C2 2026-07-13) is Pub-28's own "Requires a Secondary Number" column: APT, BLDG, DEPT,
|
|
21
|
+
* FL, HNGR, KEY, LOT, PIER, RM, SLIP, SPC, STOP, STE, TRLR, and UNIT must be followed by an
|
|
22
|
+
* identifier ("Apt 4B", never bare "Apt"); BSMT, FRNT, LBBY, LOWR, OFC, PH, REAR, SIDE, and UPPR
|
|
23
|
+
* may stand alone. This formalizes, as provenance-tracked reference data, the split that
|
|
24
|
+
* `corpus/src/shard-recipes/unit.ts` previously hand-rolled (and only partially covered) as
|
|
25
|
+
* in-file `ID_DESIGNATORS`/`STANDALONE_DESIGNATORS` arrays for synthesis weighting. A SEPARATE,
|
|
26
|
+
* not-yet-built deliverable of #1100 is the per-locale *level-semantics* table (étage/RDC, EG/OG/UG,
|
|
27
|
+
* planta/piso/bajo, piano/terra, 階/F/B1, …) — this module stays US/Pub-28 only.
|
|
28
|
+
*
|
|
29
|
+
* Data is verbatim USPS Pub-28 C2.
|
|
30
|
+
* @see {@link https://pe.usps.com/text/pub28/28apc_003.htm USPS Secondary Unit Designators}
|
|
31
|
+
*/
|
|
32
|
+
|
|
33
|
+
/**
|
|
34
|
+
* Canonical USPS secondary unit designator → recognized variants. The first variant is the approved USPS abbreviation.
|
|
35
|
+
* Keys + values uppercase per the publication. The designators marked by USPS as "requires a secondary number" (APT,
|
|
36
|
+
* BLDG, FL, …) and the standalone ones (BSMT, LBBY, PH, …) are both included — synthesis treats them uniformly.
|
|
37
|
+
*/
|
|
38
|
+
export const US_UNIT_DESIGNATOR_VARIANTS = {
|
|
39
|
+
APARTMENT: ["APT", "APRT", "APMT"],
|
|
40
|
+
BASEMENT: ["BSMT"],
|
|
41
|
+
BUILDING: ["BLDG", "BLD"],
|
|
42
|
+
DEPARTMENT: ["DEPT"],
|
|
43
|
+
FLOOR: ["FL", "FLR"],
|
|
44
|
+
FRONT: ["FRNT"],
|
|
45
|
+
HANGAR: ["HNGR"],
|
|
46
|
+
KEY: ["KEY"],
|
|
47
|
+
LOBBY: ["LBBY"],
|
|
48
|
+
LOT: ["LOT"],
|
|
49
|
+
LOWER: ["LOWR"],
|
|
50
|
+
OFFICE: ["OFC"],
|
|
51
|
+
PENTHOUSE: ["PH"],
|
|
52
|
+
PIER: ["PIER"],
|
|
53
|
+
REAR: ["REAR"],
|
|
54
|
+
ROOM: ["RM"],
|
|
55
|
+
SIDE: ["SIDE"],
|
|
56
|
+
SLIP: ["SLIP"],
|
|
57
|
+
SPACE: ["SPC"],
|
|
58
|
+
STOP: ["STOP"],
|
|
59
|
+
SUITE: ["STE", "SUIT"],
|
|
60
|
+
TRAILER: ["TRLR"],
|
|
61
|
+
UNIT: ["UNIT"],
|
|
62
|
+
UPPER: ["UPPR"],
|
|
63
|
+
} as const satisfies Record<string, readonly string[]>
|
|
64
|
+
|
|
65
|
+
/** Canonical USPS secondary unit designator (full word, uppercase per the publication). */
|
|
66
|
+
export type USUnitDesignator = keyof typeof US_UNIT_DESIGNATOR_VARIANTS
|
|
67
|
+
|
|
68
|
+
/**
|
|
69
|
+
* Inverse lookup: every variant abbreviation OR full canonical word → its canonical key, built once at module load,
|
|
70
|
+
* lowercase-keyed for case-insensitive matching (`apt` → `"APARTMENT"`, `ste` → `"SUITE"`, `suite` → `"SUITE"`).
|
|
71
|
+
*/
|
|
72
|
+
export const US_UNIT_DESIGNATOR_LOOKUP: ReadonlyMap<string, USUnitDesignator> = (() => {
|
|
73
|
+
const out = new Map<string, USUnitDesignator>()
|
|
74
|
+
|
|
75
|
+
for (const canonical of Object.keys(US_UNIT_DESIGNATOR_VARIANTS) as USUnitDesignator[]) {
|
|
76
|
+
out.set(canonical.toLowerCase(), canonical)
|
|
77
|
+
|
|
78
|
+
for (const variant of US_UNIT_DESIGNATOR_VARIANTS[canonical]) {
|
|
79
|
+
// First canonical that claims a variant wins (matches the publication's ordering).
|
|
80
|
+
if (!out.has(variant.toLowerCase())) {
|
|
81
|
+
out.set(variant.toLowerCase(), canonical)
|
|
82
|
+
}
|
|
83
|
+
}
|
|
84
|
+
}
|
|
85
|
+
|
|
86
|
+
return out
|
|
87
|
+
})()
|
|
88
|
+
|
|
89
|
+
/** Approved USPS abbreviation per canonical (`APARTMENT → "APT"`, `SUITE → "STE"`). */
|
|
90
|
+
export const US_UNIT_DESIGNATOR_PREFERRED_ABBR: Readonly<Record<USUnitDesignator, string>> = Object.fromEntries(
|
|
91
|
+
(Object.keys(US_UNIT_DESIGNATOR_VARIANTS) as USUnitDesignator[]).map((k) => [k, US_UNIT_DESIGNATOR_VARIANTS[k][0]])
|
|
92
|
+
) as Readonly<Record<USUnitDesignator, string>>
|
|
93
|
+
|
|
94
|
+
/**
|
|
95
|
+
* Canonical designators Appendix C2 marks as "Requires a Secondary Number" — the designator must be followed by an
|
|
96
|
+
* identifier ("Apt 4B", "Rm 12"), never appearing bare. The remaining designators (BASEMENT, FRONT, LOBBY, LOWER,
|
|
97
|
+
* OFFICE, PENTHOUSE, REAR, SIDE, UPPER) may stand alone with no trailing identifier. Verbatim from USPS Pub-28 C2; see
|
|
98
|
+
* the module header for provenance (#1100).
|
|
99
|
+
*/
|
|
100
|
+
export const US_UNIT_DESIGNATOR_REQUIRES_RANGE: Readonly<Record<USUnitDesignator, boolean>> = {
|
|
101
|
+
APARTMENT: true,
|
|
102
|
+
BASEMENT: false,
|
|
103
|
+
BUILDING: true,
|
|
104
|
+
DEPARTMENT: true,
|
|
105
|
+
FLOOR: true,
|
|
106
|
+
FRONT: false,
|
|
107
|
+
HANGAR: true,
|
|
108
|
+
KEY: true,
|
|
109
|
+
LOBBY: false,
|
|
110
|
+
LOT: true,
|
|
111
|
+
LOWER: false,
|
|
112
|
+
OFFICE: false,
|
|
113
|
+
PENTHOUSE: false,
|
|
114
|
+
PIER: true,
|
|
115
|
+
REAR: false,
|
|
116
|
+
ROOM: true,
|
|
117
|
+
SIDE: false,
|
|
118
|
+
SLIP: true,
|
|
119
|
+
SPACE: true,
|
|
120
|
+
STOP: true,
|
|
121
|
+
SUITE: true,
|
|
122
|
+
TRAILER: true,
|
|
123
|
+
UNIT: true,
|
|
124
|
+
UPPER: false,
|
|
125
|
+
} as const satisfies Record<USUnitDesignator, boolean>
|
|
126
|
+
|
|
127
|
+
/**
|
|
128
|
+
* If the FIRST whitespace-separated word of `unit` is a known USPS designator variant, return the canonical key and the
|
|
129
|
+
* matched word. Returns null if the leading word isn't a known designator (e.g. a bare `"4B"` or `"#210"`).
|
|
130
|
+
* Leading-word-only — designators introduce the unit, unlike street suffixes which trail.
|
|
131
|
+
*/
|
|
132
|
+
export function matchLeadingDesignator(unit: string): { canonical: USUnitDesignator; matched: string } | null {
|
|
133
|
+
const trimmed = unit.trim()
|
|
134
|
+
|
|
135
|
+
if (!trimmed) return null
|
|
136
|
+
const first = trimmed.split(/\s+/)[0]!
|
|
137
|
+
const canonical = US_UNIT_DESIGNATOR_LOOKUP.get(first.toLowerCase())
|
|
138
|
+
|
|
139
|
+
if (!canonical) return null
|
|
140
|
+
|
|
141
|
+
return { canonical, matched: first }
|
|
142
|
+
}
|
|
143
|
+
|
|
144
|
+
/** Result of {@link matchLeadingDesignatorWithRange}: the leading designator plus its optional secondary range. */
|
|
145
|
+
export interface UnitDesignatorRangeMatch {
|
|
146
|
+
/** The matched canonical designator, i.e. "APARTMENT", "SUITE". */
|
|
147
|
+
canonical: USUnitDesignator
|
|
148
|
+
/** The designator's own matched surface form, i.e. "Apt". */
|
|
149
|
+
matched: string
|
|
150
|
+
/**
|
|
151
|
+
* The secondary range/identifier token immediately following the designator, i.e. "4B" in "Apt 4B". Undefined when
|
|
152
|
+
* the designator appears standalone (e.g. bare "Basement"). This module does not validate the range's own shape —
|
|
153
|
+
* numeric, letter, or alphanumeric ranges are all USPS-valid.
|
|
154
|
+
*/
|
|
155
|
+
range: string | undefined
|
|
156
|
+
/**
|
|
157
|
+
* Whether USPS Pub-28 Appendix C2 marks this designator as requiring a secondary range (see
|
|
158
|
+
* {@link US_UNIT_DESIGNATOR_REQUIRES_RANGE}). Informational only — not enforced by this matcher.
|
|
159
|
+
*/
|
|
160
|
+
requiresRange: boolean
|
|
161
|
+
}
|
|
162
|
+
|
|
163
|
+
/**
|
|
164
|
+
* Like {@link matchLeadingDesignator}, but also captures the secondary range/identifier token immediately following the
|
|
165
|
+
* designator, if present ("Apt 4B" → designator "APARTMENT", range "4B"; "Basement" → range `undefined`). Mirrors
|
|
166
|
+
* `street-suffix`/`street-directional`'s designator+adjacent-token matchers.
|
|
167
|
+
*/
|
|
168
|
+
export function matchLeadingDesignatorWithRange(unit: string): UnitDesignatorRangeMatch | null {
|
|
169
|
+
const trimmed = unit.trim()
|
|
170
|
+
|
|
171
|
+
if (!trimmed) return null
|
|
172
|
+
const parts = trimmed.split(/\s+/)
|
|
173
|
+
const first = parts[0]!
|
|
174
|
+
const canonical = US_UNIT_DESIGNATOR_LOOKUP.get(first.toLowerCase())
|
|
175
|
+
|
|
176
|
+
if (!canonical) return null
|
|
177
|
+
|
|
178
|
+
return {
|
|
179
|
+
canonical,
|
|
180
|
+
matched: first,
|
|
181
|
+
range: parts[1],
|
|
182
|
+
requiresRange: US_UNIT_DESIGNATOR_REQUIRES_RANGE[canonical],
|
|
183
|
+
}
|
|
184
|
+
}
|
|
185
|
+
|
|
186
|
+
/** Result of a successful USPS secondary-unit designator lookup. */
|
|
187
|
+
export interface UnitDesignatorMatch<D extends USUnitDesignator = USUnitDesignator> {
|
|
188
|
+
/** The matched canonical designator, i.e. "APARTMENT", "SUITE". */
|
|
189
|
+
designator: D
|
|
190
|
+
/** The approved USPS abbreviation, i.e. "APT", "STE". */
|
|
191
|
+
abbreviation: (typeof US_UNIT_DESIGNATOR_VARIANTS)[D][0]
|
|
192
|
+
}
|
|
193
|
+
|
|
194
|
+
/**
|
|
195
|
+
* Look up a USPS secondary unit designator (by canonical word, abbreviation, or any variant) and its approved
|
|
196
|
+
* abbreviation.
|
|
197
|
+
*/
|
|
198
|
+
export function lookupUnitDesignator<D extends USUnitDesignator>(designator: D): UnitDesignatorMatch<D>
|
|
199
|
+
export function lookupUnitDesignator(input: string | null | undefined): UnitDesignatorMatch | null
|
|
200
|
+
export function lookupUnitDesignator(input: string | null | undefined): UnitDesignatorMatch | null {
|
|
201
|
+
if (!input || typeof input !== "string") return null
|
|
202
|
+
const designator = US_UNIT_DESIGNATOR_LOOKUP.get(input.trim().toLowerCase())
|
|
203
|
+
|
|
204
|
+
if (!designator) return null
|
|
205
|
+
|
|
206
|
+
return { designator, abbreviation: US_UNIT_DESIGNATOR_VARIANTS[designator][0] }
|
|
207
|
+
}
|
|
208
|
+
|
|
209
|
+
/**
|
|
210
|
+
* True when a token is any USPS secondary unit designator or abbreviation (case-insensitive) — `"Apt"`, `"STE"`,
|
|
211
|
+
* `"floor"`.
|
|
212
|
+
*/
|
|
213
|
+
export function isUnitDesignatorToken(input: unknown): boolean {
|
|
214
|
+
return typeof input === "string" && US_UNIT_DESIGNATOR_LOOKUP.has(input.trim().toLowerCase())
|
|
215
|
+
}
|
|
216
|
+
|
|
217
|
+
/**
|
|
218
|
+
* Alias of {@link isUnitDesignatorToken} under Pub-28's own term ("secondary unit designator"). Added for #1100 so
|
|
219
|
+
* secondary-address call sites can spell the predicate after the publication's vocabulary.
|
|
220
|
+
*/
|
|
221
|
+
export function isSecondaryUnitDesignatorToken(input: unknown): boolean {
|
|
222
|
+
return isUnitDesignatorToken(input)
|
|
223
|
+
}
|
package/us/zipcode.ts
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* US ZIP (Zone Improvement Plan) codes: branded string types, the shape patterns, the first-digit →
|
|
7
|
+
* state geographic prior, and a state-plus-ZIP plucker.
|
|
8
|
+
*/
|
|
9
|
+
|
|
10
|
+
import type { Tagged } from "type-fest"
|
|
11
|
+
|
|
12
|
+
import { isUSStateAbbreviation, type USStateAbbreviation } from "./state.ts"
|
|
13
|
+
|
|
14
|
+
/**
|
|
15
|
+
* USPS-recognized ZIP code digits.
|
|
16
|
+
*
|
|
17
|
+
* @internal
|
|
18
|
+
*/
|
|
19
|
+
export type ZipCodeDigit = 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9
|
|
20
|
+
|
|
21
|
+
/**
|
|
22
|
+
* A ZIP (Zone Improvement Plan) Code is a five-digit code assigned by the USPS to a section of a street, a collection
|
|
23
|
+
* of streets, an establishment, structure, or group of post office boxes, for the delivery of mail.
|
|
24
|
+
*
|
|
25
|
+
* - The first 3 digits of the ZIP code represent a specific central mail processing facility, which can be used to
|
|
26
|
+
* identify the locality and region of the address, i.e. the city and state.
|
|
27
|
+
* - The last 2 digits of the ZIP code represent a specific post office or delivery area.
|
|
28
|
+
*
|
|
29
|
+
* ```txt
|
|
30
|
+
* 90210
|
|
31
|
+
* / |⎿__(Post Office)
|
|
32
|
+
* / \
|
|
33
|
+
* (State) \
|
|
34
|
+
* \
|
|
35
|
+
* (City)
|
|
36
|
+
* ```
|
|
37
|
+
*
|
|
38
|
+
* Note that ZIP codes are not areas, but rather a group of deliverable addresses, which can and do change over time.
|
|
39
|
+
*
|
|
40
|
+
* @category Delivery
|
|
41
|
+
* @category Postal
|
|
42
|
+
* @title ZIP Code
|
|
43
|
+
* @pattern ^\d{5}$
|
|
44
|
+
* @see {@linkcode ZipCodePlusFour} for the extended ZIP code format.
|
|
45
|
+
*/
|
|
46
|
+
export type ZipCode = Tagged<string, "ZipCode">
|
|
47
|
+
|
|
48
|
+
/**
|
|
49
|
+
* The extended ZIP code format includes the five-digit ZIP code followed by a hyphen and four additional digits. This
|
|
50
|
+
* extended format is used to provide more precise location information.
|
|
51
|
+
*
|
|
52
|
+
* - The first 3 digits of the ZIP code represent a specific central mail processing facility,
|
|
53
|
+
* - The last 2 digits of the ZIP code represent a specific post office or delivery area.
|
|
54
|
+
* - The four additional digits represent a specific delivery route within the ZIP code area.
|
|
55
|
+
*
|
|
56
|
+
* ```txt
|
|
57
|
+
* 90210-1234
|
|
58
|
+
* \_/\ /\__/
|
|
59
|
+
* / | \
|
|
60
|
+
* (State, City)_ / | \_ (Delivery Route)
|
|
61
|
+
* |
|
|
62
|
+
* (Post Office)
|
|
63
|
+
* ```
|
|
64
|
+
*
|
|
65
|
+
* Note that ZIP codes are not areas, but rather a group of deliverable addresses, which can and do change over time.
|
|
66
|
+
*
|
|
67
|
+
* @category Delivery
|
|
68
|
+
* @category Postal
|
|
69
|
+
* @type string
|
|
70
|
+
* @title ZIP Code+4
|
|
71
|
+
* @pattern ^\d{5}-\d{4}$
|
|
72
|
+
* @see {@linkcode ZipCode} for the standard ZIP code format.
|
|
73
|
+
*/
|
|
74
|
+
export type ZipCodePlusFour = Tagged<string, "ZipCodePlusFour">
|
|
75
|
+
|
|
76
|
+
/**
|
|
77
|
+
* Type utility to extract the state abbreviation from a ZIP code.
|
|
78
|
+
*
|
|
79
|
+
* @internal
|
|
80
|
+
*/
|
|
81
|
+
export type ExtractStateFromZipCode<Zip extends ZipCode | ZipCodePlusFour> =
|
|
82
|
+
Zip extends `${infer StateCode}${infer _Rest}` ? StateCode : never
|
|
83
|
+
|
|
84
|
+
/**
|
|
85
|
+
* Record of US state abbreviations to their corresponding ZIP code prefix (the leading digit). A cheap geographic
|
|
86
|
+
* prior: a 5-digit code's first digit narrows it to a band of states, which the parser can weigh against the
|
|
87
|
+
* surrounding city/state tokens.
|
|
88
|
+
*
|
|
89
|
+
* @internal
|
|
90
|
+
* @see {@linkcode ZipCodePrefixAbbreviationMap} for the reverse mapping.
|
|
91
|
+
*/
|
|
92
|
+
export const StateAbbreviationZipCodePrefixRecord = {
|
|
93
|
+
AL: 3,
|
|
94
|
+
AK: 9,
|
|
95
|
+
AZ: 8,
|
|
96
|
+
AR: 7,
|
|
97
|
+
CA: 9,
|
|
98
|
+
CO: 8,
|
|
99
|
+
CT: 0,
|
|
100
|
+
DE: 1,
|
|
101
|
+
DC: 2,
|
|
102
|
+
FL: 3,
|
|
103
|
+
GA: 3,
|
|
104
|
+
HI: 9,
|
|
105
|
+
ID: 8,
|
|
106
|
+
IL: 6,
|
|
107
|
+
IN: 4,
|
|
108
|
+
IA: 5,
|
|
109
|
+
KS: 6,
|
|
110
|
+
KY: 4,
|
|
111
|
+
LA: 7,
|
|
112
|
+
ME: 0,
|
|
113
|
+
MD: 2,
|
|
114
|
+
MA: 0,
|
|
115
|
+
MI: 4,
|
|
116
|
+
MN: 5,
|
|
117
|
+
MS: 3,
|
|
118
|
+
MO: 6,
|
|
119
|
+
MT: 5,
|
|
120
|
+
NE: 6,
|
|
121
|
+
NV: 8,
|
|
122
|
+
NH: 0,
|
|
123
|
+
NJ: 0,
|
|
124
|
+
NM: 8,
|
|
125
|
+
NY: 1,
|
|
126
|
+
NC: 2,
|
|
127
|
+
ND: 5,
|
|
128
|
+
OH: 4,
|
|
129
|
+
OK: 7,
|
|
130
|
+
OR: 9,
|
|
131
|
+
PA: 1,
|
|
132
|
+
RI: 0,
|
|
133
|
+
SC: 2,
|
|
134
|
+
SD: 5,
|
|
135
|
+
TN: 3,
|
|
136
|
+
TX: 7,
|
|
137
|
+
UT: 8,
|
|
138
|
+
VT: 0,
|
|
139
|
+
VA: 2,
|
|
140
|
+
WA: 9,
|
|
141
|
+
WV: 2,
|
|
142
|
+
WI: 5,
|
|
143
|
+
WY: 8,
|
|
144
|
+
PR: 0,
|
|
145
|
+
GU: 9,
|
|
146
|
+
VI: 0,
|
|
147
|
+
MP: 9,
|
|
148
|
+
AS: 9,
|
|
149
|
+
} as const satisfies Record<USStateAbbreviation, ZipCodeDigit>
|
|
150
|
+
|
|
151
|
+
/**
|
|
152
|
+
* Map of ZIP code prefixes to their corresponding US state abbreviations.
|
|
153
|
+
*/
|
|
154
|
+
const ZipCodePrefixAbbreviationMap = new Map<ZipCodeDigit, USStateAbbreviation[]>()
|
|
155
|
+
|
|
156
|
+
for (const [state, prefix] of Object.entries(StateAbbreviationZipCodePrefixRecord) as [
|
|
157
|
+
USStateAbbreviation,
|
|
158
|
+
ZipCodeDigit,
|
|
159
|
+
][]) {
|
|
160
|
+
const states = ZipCodePrefixAbbreviationMap.get(prefix) ?? []
|
|
161
|
+
ZipCodePrefixAbbreviationMap.set(prefix, [...states, state])
|
|
162
|
+
}
|
|
163
|
+
|
|
164
|
+
export { ZipCodePrefixAbbreviationMap }
|
|
165
|
+
|
|
166
|
+
/**
|
|
167
|
+
* Regex patterns for ZIP codes.
|
|
168
|
+
*/
|
|
169
|
+
export const ZipCodePatterns = {
|
|
170
|
+
/**
|
|
171
|
+
* 5-digit, or 9-digit ZIP code or ZIP+4 code.
|
|
172
|
+
*/
|
|
173
|
+
Standard: /^\d{5}(?:[-\s]\d{4})?$/,
|
|
174
|
+
|
|
175
|
+
/**
|
|
176
|
+
* Two-letter state abbreviation followed by a 5-digit ZIP code or ZIP+4 code.
|
|
177
|
+
*/
|
|
178
|
+
StateAbbreviationWithZipCode: /^(?:([A-Za-z]{2})[ ,]*)?([0-9]{5}(?:[-\s][0-9]{4})?)$/,
|
|
179
|
+
} as const
|
|
180
|
+
|
|
181
|
+
/**
|
|
182
|
+
* Type-predicate to determine if a value is a valid ZIP code.
|
|
183
|
+
*/
|
|
184
|
+
export function isZipCode(input: unknown): input is ZipCode | ZipCodePlusFour {
|
|
185
|
+
return typeof input === "string" && ZipCodePatterns.Standard.test(input)
|
|
186
|
+
}
|
|
187
|
+
|
|
188
|
+
export interface PluckedStateZIPCodeResult {
|
|
189
|
+
stateAbbreviation: USStateAbbreviation | null
|
|
190
|
+
zipCode: ZipCode | ZipCodePlusFour
|
|
191
|
+
}
|
|
192
|
+
|
|
193
|
+
/**
|
|
194
|
+
* Given an address string like `"NY"`, `"CA 94016"`, attempts to match the state abbreviation and postal code, if
|
|
195
|
+
* applicable.
|
|
196
|
+
*
|
|
197
|
+
* @see {@linkcode isUSStateAbbreviation} to validate the state abbreviation.
|
|
198
|
+
*/
|
|
199
|
+
export function pluckStateZIPCode(input: unknown): PluckedStateZIPCodeResult | null {
|
|
200
|
+
if (!input || typeof input !== "string") return null
|
|
201
|
+
|
|
202
|
+
const [, stateAbbreviation, zipCode = null] = input.match(ZipCodePatterns.StateAbbreviationWithZipCode) || []
|
|
203
|
+
|
|
204
|
+
if (!zipCode) return null
|
|
205
|
+
|
|
206
|
+
const normalizedState = stateAbbreviation?.toUpperCase()
|
|
207
|
+
|
|
208
|
+
return {
|
|
209
|
+
stateAbbreviation: isUSStateAbbreviation(normalizedState) ? normalizedState : null,
|
|
210
|
+
zipCode: zipCode as ZipCode | ZipCodePlusFour,
|
|
211
|
+
}
|
|
212
|
+
}
|