@mailwoman/corpus 10.0.0 → 10.1.0

package/out/kr/adapters/localdata/permit-rows.d.ts

@@ -3,25 +3,29 @@
  * @license AGPL-3.0
  * @author Teffen Ellis, et al.
  *
- *   The Korean permit registry (지방행정인허가데이터) as a NOISY corpus source: reading the delivered CSVs, and turning
- *   an aligned string into a corpus row (#2204 §5).
+ * The Korean permit registry (지방행정인허가데이터) as an `observation` source. It reads the delivered
+ * CSVs and turns an aligned string into a corpus row.
  *
- *   The publisher delivers CP949, one file per business category, with both address systems typed by a clerk plus a
- *   planar coordinate in EPSG:5174 and both postcodes. Reading is separated from ALIGNING so the alignment rate per
- *   file can be measured before any row enters a corpus.
+ * The publisher delivers CP949, one file per business category, with both address systems typed by
+ * a clerk plus a planar coordinate in epsg:5174 and both postcodes. The adapter separates reading from
+ * aligning so the alignment rate per file can be measured before any row enters a corpus.
  */
 import { type PathBuilderLike } from "path-ts";
 import type { Aligned } from "#kr/adapters/localdata/align";
 /**
- * The source label every row of this adapter carries, and the name a config's `source_weights` addresses it by.
+ * The source label stored on every row from this adapter.
+ * Configs use this label as the `source_weights` key.
  */
 export declare const SOURCE = "localdata-kr";
 /**
- * Every permit in this registry is Korean; the publisher issues no others.
+ * Every permit in this registry is Korean.
+ * The publisher issues no others.
  */
 export declare const COUNTRY = "KR";
 /**
- * The 영업상태명 of a business still trading. A closed one's address records somewhere that was.
+ * The 영업상태명 of a business still trading.
+ *
+ * A closed one's address records somewhere that was.
  */
 export declare const OPEN_STATUS = "\uC601\uC5C5/\uC815\uC0C1";
 /**
@@ -43,7 +47,9 @@ export interface PermitRow {
 }
 export interface ReadPermitOptions {
     /**
-     * Keep only these 영업상태명 values. Empty admits every status.
+     * Keep only these 영업상태명 values.
+     *
+     * Empty admits every status.
      */
     statuses?: readonly string[];
 }
@@ -56,11 +62,12 @@ export declare function readPermitFile(path: PathBuilderLike, options?: ReadPerm
  */
 export declare function readPermitDirectory(directory: PathBuilderLike, options?: ReadPermitOptions): AsyncGenerator<PermitRow>;
 /**
- * One aligned string as a row in the CJK slice schema.
+ * One aligned string as a row in the CJK corpus schema.
  *
- * The token labels are derived from the spans rather than carried beside them: a token is `B-<tag>` when its FIRST
- * character falls inside a span, `O` otherwise. A span covering several tokens therefore labels only the token it
- * starts in, which is what the char-path trainer reads the spans for.
+ * The token labels are derived from the spans rather than stored beside them:
+ * a token is `B-<tag>` when its first character falls inside a span, `O` otherwise.
+ * A span covering several tokens labels only the token where it starts.
+ * The char-path trainer reads this label from each span.
  */
-export declare function alignedToSliceRow(aligned: Aligned): Record<string, unknown>;
+export declare function alignedToCJKRow(aligned: Aligned): Record<string, unknown>;
 //# sourceMappingURL=permit-rows.d.ts.map

package/out/kr/adapters/localdata/permit-rows.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"permit-rows.d.ts","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAGH,OAAO,EAA2B,KAAK,eAAe,EAAE,MAAM,SAAS,CAAA;AAIvE,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,8BAA8B,CAAA;AAE3D;;GAEG;AACH,eAAO,MAAM,MAAM,iBAAiB,CAAA;AAEpC;;GAEG;AACH,eAAO,MAAM,OAAO,OAAO,CAAA;AAE3B;;GAEG;AACH,eAAO,MAAM,WAAW,8BAAU,CAAA;AAOlC;;GAEG;AACH,MAAM,WAAW,SAAS;IACzB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,MAAM,CAAA;IACd,WAAW,EAAE,MAAM,CAAA;IACnB,UAAU,EAAE,MAAM,CAAA;IAClB,YAAY,EAAE,MAAM,CAAA;IACpB,WAAW,EAAE,MAAM,CAAA;IACnB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IAChB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;CAChB;AA2BD,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,QAAQ,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC5B;AAED;;GAEG;AACH,wBAAuB,cAAc,CACpC,IAAI,EAAE,eAAe,EACrB,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CA2B3B;AAED;;GAEG;AACH,wBAAuB,mBAAmB,CACzC,SAAS,EAAE,eAAe,EAC1B,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CAS3B;AAED;;;;;;GAMG;AACH,wBAAgB,iBAAiB,CAAC,OAAO,EAAE,OAAO,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAoC3E"}
+{"version":3,"file":"permit-rows.d.ts","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAGH,OAAO,EAAqB,KAAK,eAAe,EAAsB,MAAM,SAAS,CAAA;AAIrF,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,8BAA8B,CAAA;AAE3D;;;GAGG;AACH,eAAO,MAAM,MAAM,iBAAiB,CAAA;AAEpC;;;GAGG;AACH,eAAO,MAAM,OAAO,OAAO,CAAA;AAE3B;;;;GAIG;AACH,eAAO,MAAM,WAAW,8BAAU,CAAA;AASlC;;GAEG;AACH,MAAM,WAAW,SAAS;IACzB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,MAAM,CAAA;IACd,WAAW,EAAE,MAAM,CAAA;IACnB,UAAU,EAAE,MAAM,CAAA;IAClB,YAAY,EAAE,MAAM,CAAA;IACpB,WAAW,EAAE,MAAM,CAAA;IACnB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IAChB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;CAChB;AA2BD,MAAM,WAAW,iBAAiB;IACjC;;;;OAIG;IACH,QAAQ,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC5B;AAED;;GAEG;AACH,wBAAuB,cAAc,CACpC,IAAI,EAAE,eAAe,EACrB,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CA4B3B;AAED;;GAEG;AACH,wBAAuB,mBAAmB,CACzC,SAAS,EAAE,eAAe,EAC1B,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CAM3B;AAED;;;;;;;GAOG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,OAAO,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAoCzE"}

package/out/kr/adapters/localdata/permit-rows.js

@@ -3,39 +3,45 @@
  * @license AGPL-3.0
  * @author Teffen Ellis, et al.
  *
- *   The Korean permit registry (지방행정인허가데이터) as a NOISY corpus source: reading the delivered CSVs, and turning
- *   an aligned string into a corpus row (#2204 §5).
+ * The Korean permit registry (지방행정인허가데이터) as an `observation` source. It reads the delivered
+ * CSVs and turns an aligned string into a corpus row.
  *
- *   The publisher delivers CP949, one file per business category, with both address systems typed by a clerk plus a
- *   planar coordinate in EPSG:5174 and both postcodes. Reading is separated from ALIGNING so the alignment rate per
- *   file can be measured before any row enters a corpus.
+ * The publisher delivers CP949, one file per business category, with both address systems typed by
+ * a clerk plus a planar coordinate in epsg:5174 and both postcodes. The adapter separates reading from
+ * aligning so the alignment rate per file can be measured before any row enters a corpus.
  */
 import { decodeByteStream, openReadStream } from "@mailwoman/core/fs/streams";
-import { basename, extname, join } from "path-ts";
+import { basename, extname, resolvePathBuilder } from "path-ts";
 import { CSVSpliterator } from "spliterator";
 import { Globerator } from "spliterator/node/fs";
 /**
- * The source label every row of this adapter carries, and the name a config's `source_weights` addresses it by.
+ * The source label stored on every row from this adapter.
+ * Configs use this label as the `source_weights` key.
  */
 export const SOURCE = "localdata-kr";
 /**
- * Every permit in this registry is Korean; the publisher issues no others.
+ * Every permit in this registry is Korean.
+ * The publisher issues no others.
  */
 export const COUNTRY = "KR";
 /**
- * The 영업상태명 of a business still trading. A closed one's address records somewhere that was.
+ * The 영업상태명 of a business still trading.
+ *
+ * A closed one's address records somewhere that was.
  */
 export const OPEN_STATUS = "영업/정상";
 /**
- * The publisher's encoding. `cp949` rather than `euc-kr` for the reason `decodeByteStream` states.
+ * The publisher's encoding.
+ *
+ * `cp949` rather than `euc-kr` for the reason `decodeByteStream` states.
  */
 const ENCODING = "cp949";
 /**
- * The first of these column spellings the row carries, trimmed, or the empty string.
+ * The first of these column spellings present in the row, trimmed, or the empty string.
  *
- * The publisher's older and newer exports name the same field differently — `도로명주소` against `도로명전체주소`, `좌표정보(X)`
- * against `좌표정보(x)` — and a directory holds both vintages, so each field names every spelling it has been delivered
- * under.
+ * The publisher's older and newer exports name the same field differently — `도로명주소`
+ * against `도로명전체주소`, `좌표정보(X)` against `좌표정보(x)` — and a directory holds both vintages,
+ * so each field names every spelling it has been delivered under.
  */
 function firstColumn(row, ...names) {
     for (const name of names) {
@@ -56,7 +62,8 @@ function toNumber(value) {
  */
 export async function* readPermitFile(path, options = {}) {
     const wanted = new Set(options.statuses ?? [OPEN_STATUS]);
-    const category = basename(String(path), extname(String(path)));
+    const file = path.toString();
+    const category = basename(file, extname(file));
     const bytes = openReadStream(path);
     for await (const row of CSVSpliterator.fromAsync(decodeByteStream(bytes, ENCODING))) {
         const status = firstColumn(row, "영업상태명");
@@ -83,22 +90,20 @@ export async function* readPermitFile(path, options = {}) {
  * Stream every permit of every CSV in a directory, in filename order.
  */
 export async function* readPermitDirectory(directory, options = {}) {
-    const files = await Globerator.from("*", { cwd: directory, withFileTypes: true, onlyFiles: false })
-        .filter((entry) => entry.isFile() && entry.name.endsWith(".csv"))
-        .map((entry) => entry.name)
-        .toSorted();
+    const files = await Globerator.files("csv", { cwd: directory, absolute: false, recursive: false }).toSorted();
     for (const name of files) {
-        yield* readPermitFile(join(directory, name), options);
+        yield* readPermitFile(resolvePathBuilder(directory, name), options);
     }
 }
 /**
- * One aligned string as a row in the CJK slice schema.
+ * One aligned string as a row in the CJK corpus schema.
  *
- * The token labels are derived from the spans rather than carried beside them: a token is `B-<tag>` when its FIRST
- * character falls inside a span, `O` otherwise. A span covering several tokens therefore labels only the token it
- * starts in, which is what the char-path trainer reads the spans for.
+ * The token labels are derived from the spans rather than stored beside them:
+ * a token is `B-<tag>` when its first character falls inside a span, `O` otherwise.
+ * A span covering several tokens labels only the token where it starts.
+ * The char-path trainer reads this label from each span.
  */
-export function alignedToSliceRow(aligned) {
+export function alignedToCJKRow(aligned) {
     const raw = aligned.raw;
     const tokens = [];
     const labels = [];

package/out/kr/adapters/localdata/permit-rows.js.map

@@ -1 +1 @@
-{"version":3,"file":"permit-rows.js","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAEH,OAAO,EAAE,gBAAgB,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAA;AAC7E,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAwB,MAAM,SAAS,CAAA;AACvE,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAA;AAIhD;;GAEG;AACH,MAAM,CAAC,MAAM,MAAM,GAAG,cAAc,CAAA;AAEpC;;GAEG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,IAAI,CAAA;AAE3B;;GAEG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,OAAO,CAAA;AAElC;;GAEG;AACH,MAAM,QAAQ,GAAG,OAAO,CAAA;AAoBxB;;;;;;GAMG;AACH,SAAS,WAAW,CAAC,GAAuC,EAAE,GAAG,KAAwB;IACxF,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,MAAM,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,CAAA;QAEvB,IAAI,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,IAAI;YAAE,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAA;IACvE,CAAC;IAED,OAAO,EAAE,CAAA;AACV,CAAC;AAED,SAAS,QAAQ,CAAC,KAAa;IAC9B,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE;QAAE,OAAO,IAAI,CAAA;IAE9B,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAA;IAE5B,OAAO,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAA;AAC/C,CAAC;AASD;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,cAAc,CACpC,IAAqB,EACrB,OAAO,GAAsB,EAAE;IAE/B,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,QAAQ,IAAI,CAAC,WAAW,CAAC,CAAC,CAAA;IACzD,MAAM,QAAQ,GAAG,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9D,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,CAAC,CAAA;IAElC,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,cAAc,CAAC,SAAS,CAAyB,gBAAgB,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC,EAAE,CAAC;QAC7G,MAAM,MAAM,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,CAAC,CAAA;QAExC,IAAI,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC;YAAE,SAAQ;QAEhD,MAAM,WAAW,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,EAAE,SAAS,CAAC,CAAA;QACxD,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,MAAM,EAAE,SAAS,CAAC,CAAA;QAEtD,IAAI,CAAC,WAAW,IAAI,CAAC,UAAU;YAAE,SAAQ;QAEzC,MAAM;YACL,QAAQ;YACR,IAAI,EAAE,WAAW,CAAC,GAAG,EAAE,MAAM,CAAC;YAC9B,MAAM;YACN,WAAW;YACX,UAAU;YACV,YAAY,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACzC,WAAW,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACxC,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;YACnD,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;SACnD,CAAA;IACF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,mBAAmB,CACzC,SAA0B,EAC1B,OAAO,GAAsB,EAAE;IAE/B,MAAM,KAAK,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,GAAG,EAAE,EAAE,GAAG,EAAE,SAAS,EAAE,aAAa,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC;SACjG,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,EAAE,IAAI,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;SAChE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC;SAC1B,QAAQ,EAAE,CAAA;IAEZ,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,KAAK,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,EAAE,OAAO,CAAC,CAAA;IACtD,CAAC;AACF,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,iBAAiB,CAAC,OAAgB;IACjD,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAA;IACvB,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,KAAK,IAAI,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC;QACvE,MAAM,KAAK,GAAG,GAAG,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;QAExC,MAAM,GAAG,KAAK,GAAG,KAAK,CAAC,MAAM,CAAA;QAE7B,IAAI,KAAK,GAAG,GAAG,CAAA;QAEf,KAAK,IAAI,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAChE,IAAI,OAAO,CAAC,UAAU,CAAC,IAAI,CAAE,IAAI,KAAK,IAAI,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAE,EAAE,CAAC;gBAC3E,KAAK,GAAG,KAAK,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAA;gBAErC,MAAK;YACN,CAAC;QACF,CAAC;QAED,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAClB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACnB,CAAC;IAED,OAAO;QACN,GAAG;QACH,MAAM;QACN,MAAM;QACN,WAAW,EAAE,CAAC,GAAG,OAAO,CAAC,UAAU,CAAC;QACpC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,OAAO,EAAE,OAAO;QAChB,MAAM,EAAE,MAAM;QACd,QAAQ,EAAE,OAAO,CAAC,QAAQ;KAC1B,CAAA;AACF,CAAC"}
+{"version":3,"file":"permit-rows.js","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAEH,OAAO,EAAE,gBAAgB,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAA;AAC7E,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAwB,kBAAkB,EAAE,MAAM,SAAS,CAAA;AACrF,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAA;AAIhD;;;GAGG;AACH,MAAM,CAAC,MAAM,MAAM,GAAG,cAAc,CAAA;AAEpC;;;GAGG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,IAAI,CAAA;AAE3B;;;;GAIG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,OAAO,CAAA;AAElC;;;;GAIG;AACH,MAAM,QAAQ,GAAG,OAAO,CAAA;AAoBxB;;;;;;GAMG;AACH,SAAS,WAAW,CAAC,GAAuC,EAAE,GAAG,KAAwB;IACxF,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,MAAM,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,CAAA;QAEvB,IAAI,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,IAAI;YAAE,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAA;IACvE,CAAC;IAED,OAAO,EAAE,CAAA;AACV,CAAC;AAED,SAAS,QAAQ,CAAC,KAAa;IAC9B,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE;QAAE,OAAO,IAAI,CAAA;IAE9B,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAA;IAE5B,OAAO,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAA;AAC/C,CAAC;AAWD;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,cAAc,CACpC,IAAqB,EACrB,OAAO,GAAsB,EAAE;IAE/B,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,QAAQ,IAAI,CAAC,WAAW,CAAC,CAAC,CAAA;IACzD,MAAM,IAAI,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAA;IAC5B,MAAM,QAAQ,GAAG,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC,CAAA;IAC9C,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,CAAC,CAAA;IAElC,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,cAAc,CAAC,SAAS,CAAyB,gBAAgB,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC,EAAE,CAAC;QAC7G,MAAM,MAAM,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,CAAC,CAAA;QAExC,IAAI,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC;YAAE,SAAQ;QAEhD,MAAM,WAAW,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,EAAE,SAAS,CAAC,CAAA;QACxD,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,MAAM,EAAE,SAAS,CAAC,CAAA;QAEtD,IAAI,CAAC,WAAW,IAAI,CAAC,UAAU;YAAE,SAAQ;QAEzC,MAAM;YACL,QAAQ;YACR,IAAI,EAAE,WAAW,CAAC,GAAG,EAAE,MAAM,CAAC;YAC9B,MAAM;YACN,WAAW;YACX,UAAU;YACV,YAAY,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACzC,WAAW,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACxC,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;YACnD,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;SACnD,CAAA;IACF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,mBAAmB,CACzC,SAA0B,EAC1B,OAAO,GAAsB,EAAE;IAE/B,MAAM,KAAK,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,SAAS,EAAE,QAAQ,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAE7G,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,KAAK,CAAC,CAAC,cAAc,CAAC,kBAAkB,CAAC,SAAS,EAAE,IAAI,CAAC,EAAE,OAAO,CAAC,CAAA;IACpE,CAAC;AACF,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,eAAe,CAAC,OAAgB;IAC/C,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAA;IACvB,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,KAAK,IAAI,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC;QACvE,MAAM,KAAK,GAAG,GAAG,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;QAExC,MAAM,GAAG,KAAK,GAAG,KAAK,CAAC,MAAM,CAAA;QAE7B,IAAI,KAAK,GAAG,GAAG,CAAA;QAEf,KAAK,IAAI,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAChE,IAAI,OAAO,CAAC,UAAU,CAAC,IAAI,CAAE,IAAI,KAAK,IAAI,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAE,EAAE,CAAC;gBAC3E,KAAK,GAAG,KAAK,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAA;gBAErC,MAAK;YACN,CAAC;QACF,CAAC;QAED,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAClB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACnB,CAAC;IAED,OAAO;QACN,GAAG;QACH,MAAM;QACN,MAAM;QACN,WAAW,EAAE,CAAC,GAAG,OAAO,CAAC,UAAU,CAAC;QACpC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,OAAO,EAAE,OAAO;QAChB,MAAM,EAAE,MAAM;QACd,QAAQ,EAAE,OAAO,CAAC,QAAQ;KAC1B,CAAA;AACF,CAAC"}

package/out/kr/tools/fetch/juso.d.ts

@@ -4,25 +4,28 @@
  * @author Teffen Ellis, et al.
  *
  *   Fetch the Korean road-name address register (도로명주소 주소DB) from the ministry's address-industry
- *   portal, business.juso.go.kr. This is the LABEL source for Korean addresses: about 6,000,000
+ *   portal, business.juso.go.kr. The ministry assigns the road names and building numbers it publishes, so
+ *   this source asserts `address` on `premise` rows: about 6,000,000
  *   road-name addresses and 8,000,000 lot-number (지번) records, split by the publisher into four
  *   pipe-delimited CP949 text files per region (도로명코드 / 주소 / 지번 / 부가정보), with the postcode in
  *   the supplementary file. No coordinates. The public-data portal labels it "이용허락범위 제한 없음"
- *   (no restriction on the scope of use), and it is a direct download with no application step — the
- *   distinction that matters against the ministry's entrance-coordinate products, which are provided
+ *   (no restriction on the scope of use). It is a direct download with no application step — the
+ *   distinction that matters against the ministry's entrance-coordinate products. Those products are provided
  *   only after a purpose-of-use review (`docs/superpowers/plans/counsel-dossier.md` §4).
  *
- *   The portal is a single-page app; the file behind it is reached in two calls. `selectAttrbDBDwldList`
+ *   The portal is a single-page app. the file behind it is reached in two calls. `selectAttrbDBDwldList`
  *   lists the monthly full files for one product (`rtlDtaDtlSn` 8 is the 주소DB, 2 the English
- *   road-name DB), and `/api/jst/download` streams one by the parameters the listing carried. The
- *   English DB rides along because it is the Latin-script half of the same register.
+ *   road-name DB), and `/api/jst/download` streams one by the parameters in the listing. The
+ *   English DB accompanies it as the Latin-script half of the same register.
  *
  *   Invoke via `mailwoman corpus fetch juso-kr --out-root <path>`.
  */
-import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index";
+import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
 export interface FetchJusoKROptions extends BaseFetchOptions {
     /**
-     * The month to fetch as `YYYYMM`. Defaults to the latest month the portal lists as present.
+     * The month to fetch as `yyyymm`.
+     *
+     * Defaults to the latest month the portal lists as present.
      */
     month?: string;
 }

package/out/kr/tools/fetch/juso.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"juso.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAMH,OAAO,KAAK,EACX,gBAAgB,EAChB,YAAY,EAGZ,MAAM,6BAA6B,CAAA;AAqCpC,MAAM,WAAW,kBAAmB,SAAQ,gBAAgB;IAC3D;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;CACd;AAsCD,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CA4DrH"}
+{"version":3,"file":"juso.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAMH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAqCrH,MAAM,WAAW,kBAAmB,SAAQ,gBAAgB;IAC3D;;;;OAIG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;CACd;AAsCD,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CA4DrH"}

package/out/kr/tools/fetch/juso.js

@@ -4,25 +4,26 @@
  * @author Teffen Ellis, et al.
  *
  *   Fetch the Korean road-name address register (도로명주소 주소DB) from the ministry's address-industry
- *   portal, business.juso.go.kr. This is the LABEL source for Korean addresses: about 6,000,000
+ *   portal, business.juso.go.kr. The ministry assigns the road names and building numbers it publishes, so
+ *   this source asserts `address` on `premise` rows: about 6,000,000
  *   road-name addresses and 8,000,000 lot-number (지번) records, split by the publisher into four
  *   pipe-delimited CP949 text files per region (도로명코드 / 주소 / 지번 / 부가정보), with the postcode in
  *   the supplementary file. No coordinates. The public-data portal labels it "이용허락범위 제한 없음"
- *   (no restriction on the scope of use), and it is a direct download with no application step — the
- *   distinction that matters against the ministry's entrance-coordinate products, which are provided
+ *   (no restriction on the scope of use). It is a direct download with no application step — the
+ *   distinction that matters against the ministry's entrance-coordinate products. Those products are provided
  *   only after a purpose-of-use review (`docs/superpowers/plans/counsel-dossier.md` §4).
  *
- *   The portal is a single-page app; the file behind it is reached in two calls. `selectAttrbDBDwldList`
+ *   The portal is a single-page app. the file behind it is reached in two calls. `selectAttrbDBDwldList`
  *   lists the monthly full files for one product (`rtlDtaDtlSn` 8 is the 주소DB, 2 the English
- *   road-name DB), and `/api/jst/download` streams one by the parameters the listing carried. The
- *   English DB rides along because it is the Latin-script half of the same register.
+ *   road-name DB), and `/api/jst/download` streams one by the parameters in the listing. The
+ *   English DB accompanies it as the Latin-script half of the same register.
  *
  *   Invoke via `mailwoman corpus fetch juso-kr --out-root <path>`.
  */
 import { makeDirectories } from "@mailwoman/core/fs/writers";
 import { sha256File } from "@mailwoman/core/hash";
-import { join } from "path-ts";
-import { resumableDownload, writeManifest } from "#tools/fetch/download/index";
+import { stringifyJSON } from "@mailwoman/core/json";
+import { resumableDownload, writeManifest } from "#tools/fetch/download";
 const SLUG = "juso-kr";
 const PORTAL = "https://business.juso.go.kr";
 const LIST_URL = `${PORTAL}/api/jst/selectAttrbDBDwldList`;
@@ -48,7 +49,7 @@ async function listMonthlyFiles(sn, year, month) {
     const res = await fetch(LIST_URL, {
         method: "POST",
         headers: { ...BROWSER_HEADERS, accept: "application/json", "content-type": "application/json;charset=UTF-8" },
-        body: JSON.stringify({ rtlDtaDtlSn: sn, year, month, expand: "Y" }),
+        body: stringifyJSON({ rtlDtaDtlSn: sn, year, month, expand: "Y" }),
     });
     if (!res.ok)
         throw new Error(`juso-kr: listing product ${sn} answered HTTP ${res.status}`);
@@ -69,7 +70,7 @@ function downloadURL(file, regYmd) {
     return `${DOWNLOAD_URL}?${query.toString()}`;
 }
 export async function fetchJusoKR(options, report) {
-    const destDir = join(options.outRoot, SLUG);
+    const destDir = options.outRoot(SLUG);
     await makeDirectories(destDir);
     const now = new Date();
     const files = [];
@@ -83,12 +84,12 @@ export async function fetchJusoKR(options, report) {
             continue;
         }
         const url = downloadURL(file, String(now.getFullYear()));
-        const dest = join(destDir, file.tmprFileNm);
+        const dest = destDir(file.tmprFileNm);
         report?.(`=== ${SLUG} / ${product.name} ${file.crtrYm} → ${file.tmprFileNm}`);
         let bytes;
         try {
-            // The portal drops a connection every few megabytes and answers Range with 206, so the transfer resumes
-            // from what landed rather than starting the 181 MB over.
+            // The portal drops a connection every few megabytes and answers Range with 206,
+            // so the transfer resumes from what landed rather than starting the 181 MB over.
             bytes = await resumableDownload({ url, dest, headers: BROWSER_HEADERS, report });
         }
         catch (error) {
@@ -114,7 +115,7 @@ export async function fetchJusoKR(options, report) {
         downloaded_at: new Date().toISOString(),
         files,
     };
-    await writeManifest(join(destDir, "MANIFEST.json"), manifest);
+    await writeManifest(destDir("MANIFEST.json"), manifest);
     return { fetched: files.length, skipped: 0, failed: failedCodes.length, failedCodes };
 }
 //# sourceMappingURL=juso.js.map

package/out/kr/tools/fetch/juso.js.map

@@ -1 +1 @@
-{"version":3,"file":"juso.js","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAQ9B,OAAO,EAAE,iBAAiB,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAA;AAE9E,MAAM,IAAI,GAAG,SAAS,CAAA;AACtB,MAAM,MAAM,GAAG,6BAA6B,CAAA;AAC5C,MAAM,QAAQ,GAAG,GAAG,MAAM,gCAAgC,CAAA;AAC1D,MAAM,YAAY,GAAG,GAAG,MAAM,mBAAmB,CAAA;AACjD,MAAM,OAAO,GAAG,GAAG,MAAM,iCAAiC,CAAA;AAE1D;;GAEG;AACH,MAAM,QAAQ,GAAG;IAChB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,MAAM,EAAE;IACzB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,UAAU,EAAE;CACpB,CAAA;AAEV,MAAM,OAAO,GACZ,iFAAiF,CAAA;AAElF,MAAM,WAAW,GAAG,iEAAiE,CAAA;AAwBrF,MAAM,eAAe,GAAG;IACvB,YAAY,EAAE,wDAAwD;IACtE,OAAO,EAAE,OAAO;CAChB,CAAA;AAED;;GAEG;AACH,KAAK,UAAU,gBAAgB,CAAC,EAAU,EAAE,IAAY,EAAE,KAAa;IACtE,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,QAAQ,EAAE;QACjC,MAAM,EAAE,MAAM;QACd,OAAO,EAAE,EAAE,GAAG,eAAe,EAAE,MAAM,EAAE,kBAAkB,EAAE,cAAc,EAAE,gCAAgC,EAAE;QAC7G,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC;KACnE,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,EAAE,kBAAkB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAC1F,MAAM,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,CAAiB,CAAA;IAE/C,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,gBAAgB,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,GAAG,CAAC,CAAA;AACrF,CAAC;AAED,SAAS,WAAW,CAAC,IAAgB,EAAE,MAAc;IACpD,MAAM,KAAK,GAAG,IAAI,eAAe,CAAC;QACjC,OAAO,EAAE,IAAI,CAAC,UAAU;QACxB,QAAQ,EAAE,IAAI,CAAC,UAAU;QACzB,KAAK,EAAE,IAAI,CAAC,MAAM;QAClB,QAAQ,EAAE,IAAI,CAAC,MAAM;QACrB,YAAY,EAAE,IAAI,CAAC,UAAU;QAC7B,SAAS,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC7B,MAAM,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC1B,MAAM;KACN,CAAC,CAAA;IAEF,OAAO,GAAG,YAAY,IAAI,KAAK,CAAC,QAAQ,EAAE,EAAE,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,OAA2B,EAAE,MAA+B;IAC7F,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAE9B,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAA;IACtB,MAAM,KAAK,GAAqB,EAAE,CAAA;IAClC,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,MAAM,GAAG,MAAM,gBAAgB,CAAC,OAAO,CAAC,EAAE,EAAE,GAAG,CAAC,WAAW,EAAE,EAAE,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAA;QACxF,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;QAEnG,IAAI,CAAC,IAAI,EAAE,CAAC;YACX,MAAM,EAAE,CAAC,OAAO,OAAO,CAAC,IAAI,wBAAwB,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;YACnG,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,WAAW,CAAC,IAAI,EAAE,MAAM,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAA;QACxD,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,IAAI,CAAC,UAAU,CAAC,CAAA;QAC3C,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,MAAM,IAAI,CAAC,UAAU,EAAE,CAAC,CAAA;QAC7E,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,wGAAwG;YACxG,yDAAyD;YACzD,KAAK,GAAG,MAAM,iBAAiB,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,OAAO,EAAE,eAAe,EAAE,MAAM,EAAE,CAAC,CAAA;QACjF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAElC,KAAK,CAAC,IAAI,CAAC;YACV,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ,EAAE,IAAI,CAAC,UAAU;YACzB,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAC,CAAA;QAEF,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;IACtE,CAAC;IAED,MAAM,QAAQ,GAA6B;QAC1C,MAAM,EAAE,IAAI;QACZ,UAAU,EAAE,OAAO;QACnB,OAAO,EAAE,OAAO;QAChB,WAAW,EAAE,WAAW;QACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,KAAK;KACL,CAAA;IAED,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;IAE7D,OAAO,EAAE,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACtF,CAAC"}
+{"version":3,"file":"juso.js","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAGpD,OAAO,EAAE,iBAAiB,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAExE,MAAM,IAAI,GAAG,SAAS,CAAA;AACtB,MAAM,MAAM,GAAG,6BAA6B,CAAA;AAC5C,MAAM,QAAQ,GAAG,GAAG,MAAM,gCAAgC,CAAA;AAC1D,MAAM,YAAY,GAAG,GAAG,MAAM,mBAAmB,CAAA;AACjD,MAAM,OAAO,GAAG,GAAG,MAAM,iCAAiC,CAAA;AAE1D;;GAEG;AACH,MAAM,QAAQ,GAAG;IAChB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,MAAM,EAAE;IACzB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,UAAU,EAAE;CACpB,CAAA;AAEV,MAAM,OAAO,GACZ,iFAAiF,CAAA;AAElF,MAAM,WAAW,GAAG,iEAAiE,CAAA;AA0BrF,MAAM,eAAe,GAAG;IACvB,YAAY,EAAE,wDAAwD;IACtE,OAAO,EAAE,OAAO;CAChB,CAAA;AAED;;GAEG;AACH,KAAK,UAAU,gBAAgB,CAAC,EAAU,EAAE,IAAY,EAAE,KAAa;IACtE,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,QAAQ,EAAE;QACjC,MAAM,EAAE,MAAM;QACd,OAAO,EAAE,EAAE,GAAG,eAAe,EAAE,MAAM,EAAE,kBAAkB,EAAE,cAAc,EAAE,gCAAgC,EAAE;QAC7G,IAAI,EAAE,aAAa,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC;KAClE,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,EAAE,kBAAkB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAC1F,MAAM,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,CAAiB,CAAA;IAE/C,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,gBAAgB,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,GAAG,CAAC,CAAA;AACrF,CAAC;AAED,SAAS,WAAW,CAAC,IAAgB,EAAE,MAAc;IACpD,MAAM,KAAK,GAAG,IAAI,eAAe,CAAC;QACjC,OAAO,EAAE,IAAI,CAAC,UAAU;QACxB,QAAQ,EAAE,IAAI,CAAC,UAAU;QACzB,KAAK,EAAE,IAAI,CAAC,MAAM;QAClB,QAAQ,EAAE,IAAI,CAAC,MAAM;QACrB,YAAY,EAAE,IAAI,CAAC,UAAU;QAC7B,SAAS,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC7B,MAAM,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC1B,MAAM;KACN,CAAC,CAAA;IAEF,OAAO,GAAG,YAAY,IAAI,KAAK,CAAC,QAAQ,EAAE,EAAE,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,OAA2B,EAAE,MAA+B;IAC7F,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IACrC,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAE9B,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAA;IACtB,MAAM,KAAK,GAAqB,EAAE,CAAA;IAClC,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,MAAM,GAAG,MAAM,gBAAgB,CAAC,OAAO,CAAC,EAAE,EAAE,GAAG,CAAC,WAAW,EAAE,EAAE,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAA;QACxF,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;QAEnG,IAAI,CAAC,IAAI,EAAE,CAAC;YACX,MAAM,EAAE,CAAC,OAAO,OAAO,CAAC,IAAI,wBAAwB,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;YACnG,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,WAAW,CAAC,IAAI,EAAE,MAAM,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAA;QACxD,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;QACrC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,MAAM,IAAI,CAAC,UAAU,EAAE,CAAC,CAAA;QAC7E,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,gFAAgF;YAChF,iFAAiF;YACjF,KAAK,GAAG,MAAM,iBAAiB,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,OAAO,EAAE,eAAe,EAAE,MAAM,EAAE,CAAC,CAAA;QACjF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAElC,KAAK,CAAC,IAAI,CAAC;YACV,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ,EAAE,IAAI,CAAC,UAAU;YACzB,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAC,CAAA;QAEF,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;IACtE,CAAC;IAED,MAAM,QAAQ,GAA6B;QAC1C,MAAM,EAAE,IAAI;QACZ,UAAU,EAAE,OAAO;QACnB,OAAO,EAAE,OAAO;QAChB,WAAW,EAAE,WAAW;QACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,KAAK;KACL,CAAA;IAED,MAAM,aAAa,CAAC,OAAO,CAAC,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;IAEvD,OAAO,EAAE,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACtF,CAAC"}

package/out/kr/tools/fetch/localdata.d.ts

@@ -4,25 +4,32 @@
  * @author Teffen Ellis, et al.
  *
  *   Fetch Korea's local-government permit registry (지방행정인허가데이터): one CSV per permit category,
- *   every business a local authority has licensed, about 195 categories. Each row carries BOTH address
+ *   every business a local authority has licensed, about 195 categories. Each row includes both address
  *   forms of the same premises — `소재지전체주소` (the lot-number form, 지번) and `도로명전체주소` (the
- *   road-name form) — plus both postcodes and a planar coordinate (`좌표정보(x/y)`, EPSG:5174). That
- *   pairing is the cheapest dual-format signal Korean addresses offer, and the coordinate is the
- *   board's coordinate half, which is why this is the NOISY source for Korean and not a side dish.
+ *   road-name form) — plus both postcodes and a planar coordinate (`좌표정보(x/y)`, epsg:5174). That
+ *   The two formats together provide the cheapest dual-format signal in Korean addresses.
+ *   The coordinate supplies the board's coordinate half. That role gives this source its weight.
+ *
+ *   What it asserts differs by field. The local authority grants the permit, so the permit identifier is an
+ *   `identity` assertion. The address is an `observation`: a clerk typed it, in both address systems, with
+ *   no validation. The registry attests only that it received the string. Both sit on `premise` rows —
+ *   the address of the licensed premises. One verdict over the source would discard the permit identity.
  *
  *   The public-data portal labels the category files "이용허락범위 제한 없음" and links them to
- *   `file.localdata.go.kr`, which serves them behind a session: the category page sets the XSRF cookie,
+ *   `file.localdata.go.kr`, which serves them behind a session: the category page sets the xsrf cookie,
  *   `/file/validate/download-count` is the portal's own rate check (429 when it wants a pause), and
- *   `/file/download/<slug>/info` streams the CSV. The files are CP949 as delivered; the adapter
- *   decodes. The restaurant category alone is about 700 MB.
+ *   `/file/download/<slug>/info` streams the CSV. The files are CP949 as delivered. the adapter
+ *   decodes. The restaurant category by itself is about 700 MB.
  *
  *   Invoke via `mailwoman corpus fetch localdata-kr --out-root <path>`, optionally with
  *   `--categories general_restaurants,rest_cafes`.
  */
-import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index";
+import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
 export interface FetchLocaldataKROptions extends BaseFetchOptions {
     /**
-     * Category slugs to fetch (the path segment of `/file/<slug>/info`). Defaults to every category the portal lists.
+     * Category slugs to fetch (the path segment of `/file/<slug>/info`).
+     *
+     * Defaults to every category the portal lists.
      */
     categories?: string[];
 }

package/out/kr/tools/fetch/localdata.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"localdata.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/localdata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AASH,OAAO,KAAK,EACX,gBAAgB,EAChB,YAAY,EAGZ,MAAM,6BAA6B,CAAA;AAiBpC,MAAM,WAAW,uBAAwB,SAAQ,gBAAgB;IAChE;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,EAAE,CAAA;CACrB;AAsDD,wBAAsB,gBAAgB,CACrC,OAAO,EAAE,uBAAuB,EAChC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA4FvB"}
+{"version":3,"file":"localdata.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/localdata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAWrH,MAAM,WAAW,uBAAwB,SAAQ,gBAAgB;IAChE;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,EAAE,CAAA;CACrB;AAyDD,wBAAsB,gBAAgB,CACrC,OAAO,EAAE,uBAAuB,EAChC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA6FvB"}

package/out/kr/tools/fetch/localdata.js

@@ -4,17 +4,22 @@
  * @author Teffen Ellis, et al.
  *
  *   Fetch Korea's local-government permit registry (지방행정인허가데이터): one CSV per permit category,
- *   every business a local authority has licensed, about 195 categories. Each row carries BOTH address
+ *   every business a local authority has licensed, about 195 categories. Each row includes both address
  *   forms of the same premises — `소재지전체주소` (the lot-number form, 지번) and `도로명전체주소` (the
- *   road-name form) — plus both postcodes and a planar coordinate (`좌표정보(x/y)`, EPSG:5174). That
- *   pairing is the cheapest dual-format signal Korean addresses offer, and the coordinate is the
- *   board's coordinate half, which is why this is the NOISY source for Korean and not a side dish.
+ *   road-name form) — plus both postcodes and a planar coordinate (`좌표정보(x/y)`, epsg:5174). That
+ *   The two formats together provide the cheapest dual-format signal in Korean addresses.
+ *   The coordinate supplies the board's coordinate half. That role gives this source its weight.
+ *
+ *   What it asserts differs by field. The local authority grants the permit, so the permit identifier is an
+ *   `identity` assertion. The address is an `observation`: a clerk typed it, in both address systems, with
+ *   no validation. The registry attests only that it received the string. Both sit on `premise` rows —
+ *   the address of the licensed premises. One verdict over the source would discard the permit identity.
  *
  *   The public-data portal labels the category files "이용허락범위 제한 없음" and links them to
- *   `file.localdata.go.kr`, which serves them behind a session: the category page sets the XSRF cookie,
+ *   `file.localdata.go.kr`, which serves them behind a session: the category page sets the xsrf cookie,
  *   `/file/validate/download-count` is the portal's own rate check (429 when it wants a pause), and
- *   `/file/download/<slug>/info` streams the CSV. The files are CP949 as delivered; the adapter
- *   decodes. The restaurant category alone is about 700 MB.
+ *   `/file/download/<slug>/info` streams the CSV. The files are CP949 as delivered. the adapter
+ *   decodes. The restaurant category by itself is about 700 MB.
  *
  *   Invoke via `mailwoman corpus fetch localdata-kr --out-root <path>`, optionally with
  *   `--categories general_restaurants,rest_cafes`.
@@ -24,8 +29,7 @@ import { pathExists } from "@mailwoman/core/fs/readers";
 import { makeDirectories } from "@mailwoman/core/fs/writers";
 import { sha256File } from "@mailwoman/core/hash";
 import { sleep } from "@mailwoman/core/utils/sleep";
-import { join } from "path-ts";
-import { cookieHeader, loadCollectionFiles, streamBodyToFile, withRetries, writeManifest, } from "#tools/fetch/download/index";
+import { cookieHeader, loadCollectionFiles, streamBodyToFile, withRetries, writeManifest } from "#tools/fetch/download";
 const SLUG = "localdata-kr";
 const PORTAL = "https://file.localdata.go.kr";
 const INDEX_URL = `${PORTAL}/file/general_restaurants/info`;
@@ -35,7 +39,8 @@ const HTTP_TOO_MANY_REQUESTS = 429;
 const RATE_PAUSE_MS = 30_000;
 const USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) mailwoman-corpus-fetch";
 /**
- * Open a session on the portal: the category page answers the XSRF cookie and the navigation that names every category.
+ * Open a session on the portal: the category page answers the xsrf cookie
+ * and the navigation that names every category.
  */
 async function openSession() {
     const res = await fetch(INDEX_URL, {
@@ -57,7 +62,9 @@ async function openSession() {
     return { cookie, xsrf, categories };
 }
 /**
- * The portal's own rate check; a 429 carries the pause it asks for in prose, so the caller sleeps and retries.
+ * The portal's own rate check.
+ *
+ * A 429 response states the requested pause in prose, so the caller sleeps and retries.
  */
 async function validateDownloadCount(session) {
     const headers = { "user-agent": USER_AGENT, cookie: session.cookie, referer: INDEX_URL };
@@ -68,15 +75,16 @@ async function validateDownloadCount(session) {
     return res.status !== HTTP_TOO_MANY_REQUESTS;
 }
 export async function fetchLocaldataKR(options, report) {
-    const destDir = join(options.outRoot, SLUG);
+    const destDir = options.outRoot(SLUG);
     await makeDirectories(destDir);
-    const manifestPath = join(destDir, "MANIFEST.json");
+    const manifestPath = destDir("MANIFEST.json");
     const session = await openSession();
     const wanted = options.categories?.length
         ? session.categories.filter((category) => options.categories.includes(category.slug))
         : session.categories;
     report?.(`=== ${SLUG}: ${wanted.length} of ${session.categories.length} categories`);
-    // A previous run's entries survive, keyed by file name, so a re-run after an interruption fetches only what is missing.
+    // A previous run's entries survive, keyed by file name, so a re-run
+    // after an interruption fetches only what is missing.
     const previous = await loadCollectionFiles(manifestPath);
     const files = new Map();
     let fetched = 0;
@@ -84,7 +92,7 @@ export async function fetchLocaldataKR(options, report) {
     const failedCodes = [];
     for (const category of wanted) {
         const filename = `${category.slug}.csv`;
-        const dest = join(destDir, filename);
+        const dest = destDir(filename);
         const url = `${PORTAL}/file/download/${category.slug}/info`;
         const before = previous.get(filename);
         if (before && (await pathExists(dest))) {

package/out/kr/tools/fetch/localdata.js.map

@@ -1 +1 @@
-{"version":3,"file":"localdata.js","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/localdata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAQ9B,OAAO,EACN,YAAY,EACZ,mBAAmB,EACnB,gBAAgB,EAChB,WAAW,EACX,aAAa,GACb,MAAM,6BAA6B,CAAA;AAEpC,MAAM,IAAI,GAAG,cAAc,CAAA;AAC3B,MAAM,MAAM,GAAG,8BAA8B,CAAA;AAC7C,MAAM,SAAS,GAAG,GAAG,MAAM,gCAAgC,CAAA;AAC3D,MAAM,OAAO,GAAG,4EAA4E,CAAA;AAC5F,MAAM,WAAW,GAAG,yDAAyD,CAAA;AAC7E,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAClC,MAAM,aAAa,GAAG,MAAM,CAAA;AAoB5B,MAAM,UAAU,GAAG,wDAAwD,CAAA;AAE3E;;GAEG;AACH,KAAK,UAAU,WAAW;IACzB,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,SAAS,EAAE;QAClC,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,WAAW,EAAE,OAAO,EAAE,yBAAyB,EAAE;KAC9F,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,iDAAiD,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAC3F,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,MAAM,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;IAChC,MAAM,IAAI,GAAG,oBAAoB,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IACnD,MAAM,UAAU,GAAe,EAAE,CAAA;IACjC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,KAAK,MAAM,CAAC,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,kEAAkE,CAAC,EAAE,CAAC;QAChH,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAQ;QAC9C,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACd,UAAU,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA;IAC7C,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,EAAE,CAAA;AACpC,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,qBAAqB,CAAC,OAAgB;IACpD,MAAM,OAAO,GAA2B,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,CAAA;IAEhH,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC;QAClB,OAAO,CAAC,cAAc,CAAC,GAAG,OAAO,CAAC,IAAI,CAAA;IACvC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,MAAM,+BAA+B,EAAE,EAAE,OAAO,EAAE,CAAC,CAAA;IAE9E,OAAO,GAAG,CAAC,MAAM,KAAK,sBAAsB,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACrC,OAAgC,EAChC,MAA+B;IAE/B,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAC9B,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,OAAO,GAAG,MAAM,WAAW,EAAE,CAAA;IAEnC,MAAM,MAAM,GAAG,OAAO,CAAC,UAAU,EAAE,MAAM;QACxC,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,OAAO,CAAC,UAAW,CAAC,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QACtF,CAAC,CAAC,OAAO,CAAC,UAAU,CAAA;IAErB,MAAM,EAAE,CAAC,OAAO,IAAI,KAAK,MAAM,CAAC,MAAM,OAAO,OAAO,CAAC,UAAU,CAAC,MAAM,aAAa,CAAC,CAAA;IAEpF,wHAAwH;IACxH,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,YAAY,CAAC,CAAA;IACxD,MAAM,KAAK,GAAG,IAAI,GAAG,EAA0B,CAAA;IAC/C,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,QAAQ,IAAI,MAAM,EAAE,CAAC;QAC/B,MAAM,QAAQ,GAAG,GAAG,QAAQ,CAAC,IAAI,MAAM,CAAA;QACvC,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QACpC,MAAM,GAAG,GAAG,GAAG,MAAM,kBAAkB,QAAQ,CAAC,IAAI,OAAO,CAAA;QAC3D,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QAErC,IAAI,MAAM,IAAI,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;YAE3B,OAAO,EAAE,CAAA;YAET,SAAQ;QACT,CAAC;QAED,MAAM,EAAE,CAAC,OAAO,QAAQ,CAAC,IAAI,KAAK,QAAQ,CAAC,IAAI,GAAG,CAAC,CAAA;QAEnD,OAAO,CAAC,CAAC,MAAM,qBAAqB,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;YAChD,MAAM,EAAE,CAAC,wCAAwC,aAAa,GAAG,IAAI,GAAG,CAAC,CAAA;YACzE,MAAM,KAAK,CAAC,aAAa,CAAC,CAAA;QAC3B,CAAC;QAED,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,KAAK,GAAG,MAAM,WAAW,CACxB,KAAK,IAAI,EAAE;gBACV,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;oBAC5B,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE;oBAChG,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC;iBACtC,CAAC,CAAA;gBAEF,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,CAAC,UAAU,CAAC,EAAE,CAAC;oBAC9E,MAAM,IAAI,KAAK,CAAC,QAAQ,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,QAAQ,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAA;gBACpG,CAAC;gBAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YACnC,CAAC,EACD,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,CAAC,IAAI,EAAE,CAChC,CAAA;QACF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,OAAO,KAAK,0CAA0C,CAAC,CAAA;YAChE,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAClC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,CAAC,CAAA;QAE/G,OAAO,EAAE,CAAA;QACT,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,MAAM,QAAQ,GAA6B;YAC1C,MAAM,EAAE,IAAI;YACZ,UAAU,EAAE,SAAS;YACrB,OAAO,EAAE,OAAO;YAChB,WAAW,EAAE,WAAW;YACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,KAAK,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;SAC1B,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACrE,CAAC"}
+{"version":3,"file":"localdata.js","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/localdata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AAGnD,OAAO,EAAE,YAAY,EAAE,mBAAmB,EAAE,gBAAgB,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAEvH,MAAM,IAAI,GAAG,cAAc,CAAA;AAC3B,MAAM,MAAM,GAAG,8BAA8B,CAAA;AAC7C,MAAM,SAAS,GAAG,GAAG,MAAM,gCAAgC,CAAA;AAC3D,MAAM,OAAO,GAAG,4EAA4E,CAAA;AAC5F,MAAM,WAAW,GAAG,yDAAyD,CAAA;AAC7E,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAClC,MAAM,aAAa,GAAG,MAAM,CAAA;AAsB5B,MAAM,UAAU,GAAG,wDAAwD,CAAA;AAE3E;;;GAGG;AACH,KAAK,UAAU,WAAW;IACzB,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,SAAS,EAAE;QAClC,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,WAAW,EAAE,OAAO,EAAE,yBAAyB,EAAE;KAC9F,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,iDAAiD,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAC3F,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,MAAM,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;IAChC,MAAM,IAAI,GAAG,oBAAoB,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IACnD,MAAM,UAAU,GAAe,EAAE,CAAA;IACjC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,KAAK,MAAM,CAAC,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,kEAAkE,CAAC,EAAE,CAAC;QAChH,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAQ;QAC9C,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACd,UAAU,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA;IAC7C,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,UAAU,EAAE,CAAA;AACpC,CAAC;AAED;;;;GAIG;AACH,KAAK,UAAU,qBAAqB,CAAC,OAAgB;IACpD,MAAM,OAAO,GAA2B,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,CAAA;IAEhH,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC;QAClB,OAAO,CAAC,cAAc,CAAC,GAAG,OAAO,CAAC,IAAI,CAAA;IACvC,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,MAAM,+BAA+B,EAAE,EAAE,OAAO,EAAE,CAAC,CAAA;IAE9E,OAAO,GAAG,CAAC,MAAM,KAAK,sBAAsB,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACrC,OAAgC,EAChC,MAA+B;IAE/B,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IACrC,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAC9B,MAAM,YAAY,GAAG,OAAO,CAAC,eAAe,CAAC,CAAA;IAE7C,MAAM,OAAO,GAAG,MAAM,WAAW,EAAE,CAAA;IAEnC,MAAM,MAAM,GAAG,OAAO,CAAC,UAAU,EAAE,MAAM;QACxC,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,OAAO,CAAC,UAAW,CAAC,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QACtF,CAAC,CAAC,OAAO,CAAC,UAAU,CAAA;IAErB,MAAM,EAAE,CAAC,OAAO,IAAI,KAAK,MAAM,CAAC,MAAM,OAAO,OAAO,CAAC,UAAU,CAAC,MAAM,aAAa,CAAC,CAAA;IAEpF,oEAAoE;IACpE,sDAAsD;IACtD,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,YAAY,CAAC,CAAA;IACxD,MAAM,KAAK,GAAG,IAAI,GAAG,EAA0B,CAAA;IAC/C,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,QAAQ,IAAI,MAAM,EAAE,CAAC;QAC/B,MAAM,QAAQ,GAAG,GAAG,QAAQ,CAAC,IAAI,MAAM,CAAA;QACvC,MAAM,IAAI,GAAG,OAAO,CAAC,QAAQ,CAAC,CAAA;QAC9B,MAAM,GAAG,GAAG,GAAG,MAAM,kBAAkB,QAAQ,CAAC,IAAI,OAAO,CAAA;QAC3D,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QAErC,IAAI,MAAM,IAAI,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;YAE3B,OAAO,EAAE,CAAA;YAET,SAAQ;QACT,CAAC;QAED,MAAM,EAAE,CAAC,OAAO,QAAQ,CAAC,IAAI,KAAK,QAAQ,CAAC,IAAI,GAAG,CAAC,CAAA;QAEnD,OAAO,CAAC,CAAC,MAAM,qBAAqB,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;YAChD,MAAM,EAAE,CAAC,wCAAwC,aAAa,GAAG,IAAI,GAAG,CAAC,CAAA;YACzE,MAAM,KAAK,CAAC,aAAa,CAAC,CAAA;QAC3B,CAAC;QAED,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,KAAK,GAAG,MAAM,WAAW,CACxB,KAAK,IAAI,EAAE;gBACV,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;oBAC5B,OAAO,EAAE,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE;oBAChG,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC;iBACtC,CAAC,CAAA;gBAEF,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,CAAC,UAAU,CAAC,EAAE,CAAC;oBAC9E,MAAM,IAAI,KAAK,CAAC,QAAQ,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,QAAQ,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAA;gBACpG,CAAC;gBAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YACnC,CAAC,EACD,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,CAAC,IAAI,EAAE,CAChC,CAAA;QACF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,OAAO,KAAK,0CAA0C,CAAC,CAAA;YAChE,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAClC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,CAAC,CAAA;QAE/G,OAAO,EAAE,CAAA;QACT,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,MAAM,QAAQ,GAA6B;YAC1C,MAAM,EAAE,IAAI;YACZ,UAAU,EAAE,SAAS;YACrB,OAAO,EAAE,OAAO;YAChB,WAAW,EAAE,WAAW;YACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,KAAK,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;SAC1B,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACrE,CAAC"}

package/out/lu/adapters/bd-adresses/adapter.d.ts

@@ -0,0 +1,109 @@
+/**
+ * @copyright Sister Software
+ * @license AGPL-3.0
+ * @author Teffen Ellis, et al.
+ *
+ * `bd-adresses`: the Administration du cadastre et de la topographie's BD-Adresses CSV adapter,
+ * covering Luxembourg.
+ *
+ * Input is the semicolon-separated `addresses.csv` the ACT publishes for the whole country through
+ * `data.public.lu`, beside a GeoJSON and a shapefile carrying the same records. The adapter reads
+ * `rue` as the street, `numero` as the house number, and `code_postal` with `localite` as the
+ * postcode and its postal locality.
+ *
+ * The publisher describes BD-Adresses as `un sous-ensemble des adresses figurant dans le registre
+ * national des localités et des rues`, enriched with coordinates. The row count is therefore the
+ * published subset rather than Luxembourg's address count.
+ *
+ * `data.public.lu` states `cc-zero` for the dataset, and the address-source register elects
+ * `CC0-1.0` for `lu-property-building-1` on that statement, so the adapter records that license on
+ * every row.
+ *
+ * Luxembourg writes the house number before the street, which `STREET_ORDERS` records as
+ * `number-first`, and `COMMA_JOINED_STREET_COUNTRIES` does not list it. `formatAddressRow` therefore
+ * renders `20 Kaesfurterstrooss, L-9755 Hupperdange`.
+ *
+ * ## The file carries one street name, in no single language
+ *
+ * Luxembourg is trilingual, and the CSV declares one street column.
+ * There is no `rue_fr`, `rue_de` or `rue_lb` to choose between, so the adapter emits `rue` as the
+ * publisher wrote it.
+ *
+ * What that column holds is mixed.
+ * Measured over the 179,622 rows of the 2026-09-28 edition with a generic-word probe rather than a
+ * language classifier: 133,449 values open with a French street generic such as `Rue`, `Avenue` or
+ * `Montée`, 18,629 close with a Luxembourgish one such as `-strooss`, `-wee` or `-gaass`, and the
+ * remaining 27,544 match neither probe and include plainly Luxembourgish forms such as
+ * `Am Stengber`, `An Hiesel` and `Um Reebou`.
+ * No column marks a row's language, so `locale` reads `und-LU`.
+ * `und` is BCP-47's undetermined language subtag, and the repository already stores it in
+ * `#recipes/bare/country` and `#tools/postcode-triples`.
+ * Labeling every row `fr-LU` or `lb-LU` would assert a language for a name the publisher did not
+ * tag.
+ *
+ * ## The number comes from `numero`, and never from the street line
+ *
+ * `rue` and `numero` are separate columns and the publisher never composes them, so neither
+ * `splitStreetLine` nor `composeHouseNumber` applies here: there is no line to split and no second
+ * column to join.
+ * Splitting the street would also be wrong in both directions.
+ * 175 `rue` values end in a digit, among them `Route Nationale 1`, `Rue du 9 août 2019` and
+ * `Cité des Sacrifiés 1940-1945`.
+ * `numero` already carries its own suffix as one token: 162,273 rows hold bare digits, 17,087 a
+ * trailing letter such as `12A`, 239 a hyphenated range such as `22-26`, eight the word `BIS` or
+ * `bis`, and 15 are empty.
+ *
+ * `id_geoportail` is the publisher's own composition of the same two values.
+ * It ends in `_<id_caclr_rue>_<numero>` on 179,607 of the 179,607 numbered rows, so the number this
+ * adapter emits agrees with the publisher's where the publisher states one.
+ * The file publishes no preformatted address line, so a rendered single line has no publisher-side
+ * counterpart to be asserted against.
+ *
+ * ## Reading the file needs a quote-aware parser
+ *
+ * 22 rows RFC 4180-quote `rue` and double its interior quotes:
+ * `"Cité ""Pënscherbierg""";3;Wilwerwiltz;…`.
+ * Those rows carry no semicolon inside the quotes, so a naive split on `;` still yields 13 fields
+ * and passes a field-count check while handing the street to the corpus as
+ * `"Cité ""Pënscherbierg"""`.
+ * `CSVSpliterator` unescapes it to `Cité "Pënscherbierg"`.
+ * The same edition carries 0 fields with an embedded newline and 0 carriage returns in the whole
+ * file.
+ *
+ * The file opens with a UTF-8 byte-order mark, the three bytes `EF BB BF`, which the reader strips.
+ * The first record's own first key therefore reads `rue` rather than the mark followed by `rue`.
+ * That mark is why the portal's byte count exceeds by three what a reader that discards it reports.
+ *
+ * The adapter streams with `CSVSpliterator.fromAsync`.
+ * It honors `opts.limit`, `opts.signal` and `opts.country`.
+ */
+import { type CorpusAdapter } from "#types";
+/**
+ * Registry id for this adapter.
+ *
+ * Stamped into every row it emits, so a corpus record can be traced back to the dataset it came from.
+ */
+export declare const BD_ADRESSES_ADAPTER_ID = "bd-adresses";
+/**
+ * The license the address-source register elects for this publication.
+ */
+export declare const BD_ADRESSES_DEFAULT_LICENSE = "CC0-1.0";
+/**
+ * Every jurisdiction this adapter emits, checked against a caller's `--country`.
+ *
+ * BD-Adresses is one national file and Luxembourg has no dependency, so this is a single entry
+ * where `ban`, `matrikkelen` and `ryhti` each carry more than one.
+ */
+export declare const BD_ADRESSES_COUNTRIES: readonly string[];
+/**
+ * The columns `rows` indexes by name, in the order the published header declares them.
+ *
+ * A caller that downloads the file checks its header against this list.
+ */
+export declare const BD_ADRESSES_REQUIRED_COLUMNS: readonly string[];
+export declare function createBDAdressesAdapter(): CorpusAdapter;
+/**
+ * The configured adapter instance registered with the corpus builder.
+ */
+export declare const bdAdressesAdapter: CorpusAdapter;
+//# sourceMappingURL=adapter.d.ts.map