@dpuse/dpuse-tool-adaltas-csv-parser 1.0.118 → 1.0.120

package/dist/dpuse-tool-adaltas-csv-parser.es.js

@@ -2900,7 +2900,7 @@ var Tr = {
 	status: /* @__PURE__ */ Z(Cr),
 	statusId: /* @__PURE__ */ Z(Sr)
 };
-({ ...Tr }), J({ en: "Arrow" }), J({ en: "Avro" }), J({ en: "Delimited text (CSV, TAB, TSV…)" }), J({ en: "JSON" }), J({ en: "JSON Lines (JSONL)" }), J({ en: "Markdown (MD)" }), J({ en: "OpenDocument spreadsheet (ODS)" }), J({ en: "Parquet" }), J({ en: "SPSS (SAV)" }), J({ en: "SQLite" }), J({ en: "Excel (XLSX, XLSM)" }), J({ en: "XML" }), J({ en: "Newline" }), J({ en: "Carriage Return" }), J({ en: "Carriage Return/Newline" }), J({ en: "Colon" }), J({ en: "Comma" }), J({ en: "Exclamation Mark" }), J({ en: "Record Separator" }), J({ en: "Semicolon" }), J({ en: "Space" }), J({ en: "Tab" }), J({ en: "Underscore" }), J({ en: "Unit Separator" }), J({ en: "Vertical Bar" }), $([
+({ ...Tr }), J({ en: "Arrow" }), J({ en: "Avro" }), J({ en: "Delimited text (CSV, TSV…)" }), J({ en: "JSON" }), J({ en: "JSON Lines (JSONL)" }), J({ en: "Markdown (MD)" }), J({ en: "OpenDocument spreadsheet (ODS)" }), J({ en: "Parquet" }), J({ en: "SPSS (SAV)" }), J({ en: "SQLite" }), J({ en: "Excel (XLSX, XLSM)" }), J({ en: "XML" }), J({ en: "Newline" }), J({ en: "Carriage Return" }), J({ en: "Carriage Return/Newline" }), J({ en: "Colon" }), J({ en: "Comma" }), J({ en: "Exclamation Mark" }), J({ en: "Record Separator" }), J({ en: "Semicolon" }), J({ en: "Space" }), J({ en: "Tab" }), J({ en: "Underscore" }), J({ en: "Unit Separator" }), J({ en: "Vertical Bar" }), $([
 	"app",
 	"engine",
 	"connector",
@@ -2950,48 +2950,87 @@ var Er = {
 	"disabled",
 	"oAuth2",
 	"none"
-]), { ...Er }, $(["list"]), { ...Er };
-var Dr = 2048, Or = class extends Error {
-	data;
-	locator;
-	constructor(e, t, n, r) {
-		super(e, r), this.name = "DPUseError", this.data = n, this.locator = t;
-	}
-}, kr = class extends Or {
-	constructor(e, t, n, r) {
-		super(e, t, n, r), this.name = "FetchError";
-	}
-};
-async function Ar(e, t, n) {
-	let r = ` - ${e.statusText}`, i = `${t} Response status '${String(e.status)}${e.statusText ? r : ""}' received.`, a;
-	try {
-		a = await e.text();
-	} catch (e) {
-		a = `<body unavailable: ${Mr(e).message}>`;
-	}
-	return new kr(i, n, { body: Nr(a) });
-}
-function jr(e) {
+]), { ...Er };
+function Dr(e) {
 	try {
 		e();
 	} catch {}
 }
-function Mr(e) {
-	if (e instanceof Error) return e;
-	if (typeof e == "string") return Error(e);
-	if (typeof e == "number" || typeof e == "boolean" || typeof e == "bigint") return Error(String(e));
-	if (typeof e == "symbol") return Error(e.description ?? "Unknown error");
-	if (typeof e == "object") try {
-		return Error(JSON.stringify(e));
-	} catch {
-		return /* @__PURE__ */ Error("Unknown error");
+$([
+	"arrow",
+	"avro",
+	"dtv",
+	"json",
+	"jsonl",
+	"markdown",
+	"ods",
+	"parquet",
+	"sav",
+	"sqlite",
+	"xlsx",
+	"xml"
+]), { ...Er };
+async function Or(e, t, n) {
+	let r = kr(e), { issues: i, parsedRecords: a, valueDelimiterId: o } = await Ar(e, t.valueDelimiterIds, t.isComplete, n);
+	return {
+		issues: i,
+		parsedRecords: a,
+		recordDelimiterId: r,
+		valueDelimiterId: o
+	};
+}
+function kr(e) {
+	let t = (e.match(/\r\n/g) ?? []).length, n = (e.match(/(?<!\r)\n/g) ?? []).length, r = (e.match(/\r(?!\n)/g) ?? []).length;
+	return t >= n && t >= r ? "\r\n" : n >= t && n >= r ? "\n" : r >= t && r >= n ? "\r" : "\n";
+}
+async function Ar(e, t, n, r) {
+	let i, a, o, s = [], c, l = !1;
+	for (let u of t) {
+		let { issues: t, records: d } = await r(e, u, n);
+		if (t.length > 0) {
+			c = jr(c, {
+				delimiter: u,
+				issues: t,
+				records: d
+			});
+			continue;
+		}
+		if (l = !0, d.length === 0) continue;
+		let { averageValueCount: f, sumOfValueCountDiffs: p } = Mr(d);
+		(!o || p <= o) && (!a || f > a) && (i = u, a = f, o = p, s = d);
+	}
+	if (!l && c != null) {
+		let { delimiter: e, issues: t, records: n } = c;
+		return {
+			issues: t,
+			parsedRecords: n,
+			valueDelimiterId: Nr(n) ? e : void 0
+		};
 	}
-	return /* @__PURE__ */ Error("Unknown error");
+	return {
+		issues: [],
+		parsedRecords: s,
+		valueDelimiterId: i != null && Nr(s) ? i : void 0
+	};
+}
+function jr(e, t) {
+	return e == null || t.issues.length < e.issues.length ? t : e;
+}
+function Mr(e) {
+	let t = 0, n = 0, r;
+	for (let i of e) r != null && (n += Math.abs(i.length - r)), r = i.length, t += i.length;
+	return {
+		averageValueCount: t / e.length,
+		sumOfValueCountDiffs: n
+	};
 }
 function Nr(e) {
-	if (e != null && e !== "") return e.length > Dr ? `${e.slice(0, Dr)}... [truncated]` : e;
+	let t = /* @__PURE__ */ new Map();
+	for (let n of e) t.set(n.length, (t.get(n.length) ?? 0) + 1);
+	let [n = 0, r = 0] = [...t].toSorted((e, t) => t[1] - e[1])[0] ?? [];
+	return n > 1 && r * 2 > e.length;
 }
-$([
+$(["list"]), { ...Er }, $([
 	"list",
 	"render",
 	"setColorMode"
@@ -3002,8 +3041,8 @@ var Pr = {
 		groupId: null,
 		decoderId: "windows-1252"
 	},
-	Big5: {
-		id: "Big5",
+	big5: {
+		id: "big5",
 		groupId: "chineseTraditional",
 		decoderId: "big5"
 	},
@@ -3102,8 +3141,8 @@ var Pr = {
 		groupId: "greek",
 		decoderId: null
 	},
-	CP874: {
-		id: "CP874",
+	cp874: {
+		id: "cp874",
 		groupId: "thai",
 		decoderId: "windows-874"
 	},
@@ -3112,13 +3151,13 @@ var Pr = {
 		groupId: "greek",
 		decoderId: null
 	},
-	CP932: {
-		id: "CP932",
+	cp932: {
+		id: "cp932",
 		groupId: "japanese",
 		decoderId: "shift_jis"
 	},
-	CP949: {
-		id: "CP949",
+	cp949: {
+		id: "cp949",
 		groupId: "korean",
 		decoderId: "euc-kr"
 	},
@@ -3147,18 +3186,18 @@ var Pr = {
 		groupId: "vietnamese",
 		decoderId: "windows-1258"
 	},
-	"EUC-JP": {
-		id: "EUC-JP",
+	"euc-jp": {
+		id: "euc-jp",
 		groupId: "japanese",
 		decoderId: "euc-jp"
 	},
-	"EUC-KR": {
-		id: "EUC-KR",
+	"euc-kr": {
+		id: "euc-kr",
 		groupId: "korean",
 		decoderId: "euc-kr"
 	},
-	GB18030: {
-		id: "GB18030",
+	gb18030: {
+		id: "gb18030",
 		groupId: "chineseSimplified",
 		decoderId: "gb18030"
 	},
@@ -3167,68 +3206,68 @@ var Pr = {
 		groupId: "western",
 		decoderId: null
 	},
-	"HZ-GB-2312": {
-		id: "HZ-GB-2312",
+	"hz-gb-2312": {
+		id: "hz-gb-2312",
 		groupId: "chineseSimplified",
 		decoderId: null
 	},
-	IBM855: {
-		id: "IBM855",
+	ibm855: {
+		id: "ibm855",
 		groupId: "cyrillic",
 		decoderId: null
 	},
-	IBM866: {
-		id: "IBM866",
+	ibm866: {
+		id: "ibm866",
 		groupId: "cyrillic",
 		decoderId: "ibm866"
 	},
-	"ISO-2022-JP": {
-		id: "ISO-2022-JP",
+	"iso-2022-jp": {
+		id: "iso-2022-jp",
 		groupId: "japanese",
 		decoderId: "iso-2022-jp"
 	},
-	"ISO-2022-KR": {
-		id: "ISO-2022-KR",
+	"iso-2022-kr": {
+		id: "iso-2022-kr",
 		groupId: "korean",
 		decoderId: null
 	},
-	"ISO-8859-1": {
-		id: "ISO-8859-1",
+	"iso-8859-1": {
+		id: "iso-8859-1",
 		groupId: "western",
 		decoderId: "windows-1252"
 	},
-	"ISO-8859-2": {
-		id: "ISO-8859-2",
+	"iso-8859-2": {
+		id: "iso-8859-2",
 		groupId: "centralEuropean",
 		decoderId: "iso-8859-2"
 	},
-	"ISO-8859-5": {
-		id: "ISO-8859-5",
+	"iso-8859-5": {
+		id: "iso-8859-5",
 		groupId: "cyrillic",
 		decoderId: "iso-8859-5"
 	},
-	"ISO-8859-6": {
-		id: "ISO-8859-6",
+	"iso-8859-6": {
+		id: "iso-8859-6",
 		groupId: "arabic",
 		decoderId: "iso-8859-6"
 	},
-	"ISO-8859-7": {
-		id: "ISO-8859-7",
+	"iso-8859-7": {
+		id: "iso-8859-7",
 		groupId: "greek",
 		decoderId: "iso-8859-7"
 	},
-	"ISO-8859-8": {
-		id: "ISO-8859-8",
+	"iso-8859-8": {
+		id: "iso-8859-8",
 		groupId: "hebrew",
 		decoderId: "iso-8859-8-i"
 	},
-	"ISO-8859-9": {
-		id: "ISO-8859-9",
+	"iso-8859-9": {
+		id: "iso-8859-9",
 		groupId: "turkish",
 		decoderId: "windows-1254"
 	},
-	"ISO-8859-13": {
-		id: "ISO-8859-13",
+	"iso-8859-13": {
+		id: "iso-8859-13",
 		groupId: "baltic",
 		decoderId: "iso-8859-13"
 	},
@@ -3272,13 +3311,13 @@ var Pr = {
 		groupId: "romanian",
 		decoderId: "iso-8859-16"
 	},
-	Johab: {
-		id: "Johab",
+	johab: {
+		id: "johab",
 		groupId: "korean",
 		decoderId: null
 	},
-	"KOI8-R": {
-		id: "KOI8-R",
+	"koi8-r": {
+		id: "koi8-r",
 		groupId: "cyrillic",
 		decoderId: "koi8-r"
 	},
@@ -3292,38 +3331,38 @@ var Pr = {
 		groupId: "cyrillic",
 		decoderId: "koi8-u"
 	},
-	KZ1048: {
-		id: "KZ1048",
+	kz1048: {
+		id: "kz1048",
 		groupId: "cyrillic",
 		decoderId: null
 	},
-	MacCyrillic: {
-		id: "MacCyrillic",
+	maccyrillic: {
+		id: "maccyrillic",
 		groupId: "cyrillic",
 		decoderId: "x-mac-cyrillic"
 	},
-	MacGreek: {
-		id: "MacGreek",
+	macgreek: {
+		id: "macgreek",
 		groupId: "greek",
 		decoderId: null
 	},
-	MacIceland: {
-		id: "MacIceland",
+	maciceland: {
+		id: "maciceland",
 		groupId: "nordic",
 		decoderId: null
 	},
-	MacLatin2: {
-		id: "MacLatin2",
+	maclatin2: {
+		id: "maclatin2",
 		groupId: "centralEuropean",
 		decoderId: null
 	},
-	MacRoman: {
-		id: "MacRoman",
+	macroman: {
+		id: "macroman",
 		groupId: "western",
 		decoderId: "macintosh"
 	},
-	MacTurkish: {
-		id: "MacTurkish",
+	macturkish: {
+		id: "macturkish",
 		groupId: "turkish",
 		decoderId: null
 	},
@@ -3332,13 +3371,13 @@ var Pr = {
 		groupId: "cyrillic",
 		decoderId: null
 	},
-	SHIFT_JIS: {
-		id: "SHIFT_JIS",
+	shift_jis: {
+		id: "shift_jis",
 		groupId: "japanese",
 		decoderId: "shift_jis"
 	},
-	"TIS-620": {
-		id: "TIS-620",
+	"tis-620": {
+		id: "tis-620",
 		groupId: "thai",
 		decoderId: "windows-874"
 	},
@@ -3352,13 +3391,13 @@ var Pr = {
 		groupId: null,
 		decoderId: "utf-8"
 	},
-	"UTF-8-SIG": {
-		id: "UTF-8-SIG",
+	"utf-8-sig": {
+		id: "utf-8-sig",
 		groupId: null,
 		decoderId: "utf-8"
 	},
-	"UTF-16": {
-		id: "UTF-16",
+	"utf-16": {
+		id: "utf-16",
 		groupId: "unicode16",
 		decoderId: null
 	},
@@ -3372,8 +3411,8 @@ var Pr = {
 		groupId: "unicode16",
 		decoderId: "utf-16le"
 	},
-	"UTF-32": {
-		id: "UTF-32",
+	"utf-32": {
+		id: "utf-32",
 		groupId: "unicode32",
 		decoderId: null
 	},
@@ -3387,43 +3426,43 @@ var Pr = {
 		groupId: "unicode32",
 		decoderId: null
 	},
-	"Windows-1250": {
-		id: "Windows-1250",
+	"windows-1250": {
+		id: "windows-1250",
 		groupId: "centralEuropean",
 		decoderId: "windows-1250"
 	},
-	"Windows-1251": {
-		id: "Windows-1251",
+	"windows-1251": {
+		id: "windows-1251",
 		groupId: "cyrillic",
 		decoderId: "windows-1251"
 	},
-	"Windows-1252": {
-		id: "Windows-1252",
+	"windows-1252": {
+		id: "windows-1252",
 		groupId: "western",
 		decoderId: "windows-1252"
 	},
-	"Windows-1253": {
-		id: "Windows-1253",
+	"windows-1253": {
+		id: "windows-1253",
 		groupId: "greek",
 		decoderId: "windows-1253"
 	},
-	"Windows-1254": {
-		id: "Windows-1254",
+	"windows-1254": {
+		id: "windows-1254",
 		groupId: "turkish",
 		decoderId: "windows-1254"
 	},
-	"Windows-1255": {
-		id: "Windows-1255",
+	"windows-1255": {
+		id: "windows-1255",
 		groupId: "hebrew",
 		decoderId: "windows-1255"
 	},
-	"Windows-1256": {
-		id: "Windows-1256",
+	"windows-1256": {
+		id: "windows-1256",
 		groupId: "arabic",
 		decoderId: "windows-1256"
 	},
-	"Windows-1257": {
-		id: "Windows-1257",
+	"windows-1257": {
+		id: "windows-1257",
 		groupId: "baltic",
 		decoderId: "windows-1257"
 	}
@@ -3465,71 +3504,70 @@ var Lr = {
 	to_line: -1,
 	trim: !1
 }, Rr = 4, zr = 50, Br = 1e4, Vr = class {
-	async parseStream(e, t, n, r, i) {
-		return new Promise((a, o) => {
-			let s, c, l, u = !1, d = !1, f = () => {
-				if (d) return;
-				d = !0;
-				let e = s;
-				s = void 0, l = void 0, e != null && (jr(() => e.removeAllListeners()), jr(() => e.end())), jr(() => void c?.cancel()), c = void 0;
+	async parseStream(e, t, n) {
+		return new Promise((r, i) => {
+			let a, o, s, c = !1, l = !1, u = () => {
+				if (l) return;
+				l = !0;
+				let e = a;
+				a = void 0, s = void 0, e != null && (Dr(() => e.removeAllListeners()), Dr(() => e.end())), Dr(() => void o?.cancel()), o = void 0;
+			}, d = (e) => {
+				c || (c = !0, u(), i(e instanceof Error ? e : Error(String(e))));
 			};
-			r.signal.addEventListener("abort", f, { once: !0 });
-			let p = (e) => {
-				u || (u = !0, f(), r.signal.aborted || r.abort(e), o(e instanceof Error ? e : Error(String(e))));
-			};
-			(async () => {
-				s = ar({
+			t.abortSignal.addEventListener("abort", () => {
+				d(t.abortSignal.reason);
+			}, { once: !0 }), (async () => {
+				t.abortSignal.throwIfAborted(), a = ar({
 					...Lr,
-					...t,
 					cast: (e, t) => ({
 						value: e,
-						wasValueQuoted: t.quoting
-					})
-				}), l = Hr({
-					chunk: i,
-					chunkSize: e.chunkSize ?? Br
-				}), s.on("readable", () => {
+						valueWasQuoted: t.quoting
+					}),
+					delimiter: t.valueDelimiterId,
+					relax_column_count: !0
+				}), s = Hr({
+					chunk: n,
+					chunkSize: t.chunkSize ?? Br
+				}), a.on("readable", () => {
 					try {
-						if (s == null || l == null) return;
+						if (a == null || s == null) return;
 						let e;
-						for (; (e = s.read()) != null;) {
-							if (u) return;
-							r.signal.throwIfAborted(), l.push(e);
+						for (; (e = a.read()) != null;) {
+							if (c) return;
+							t.abortSignal.throwIfAborted(), s.push(e);
 						}
 					} catch (e) {
-						p(e);
+						d(e);
 					}
-				}), s.on("error", (e) => {
-					p(e);
-				}), s.on("end", () => {
-					u || (l?.flush(), a(Ur(s)));
-				});
-				let o = await fetch(encodeURI(n), { signal: r.signal });
-				if (!o.ok || o.body == null) throw await Ar(o, `Failed to fetch '${n}' file.`, "dpuse-connector-file-store-emulator|Connector|retrieve");
-				c = o.body.getReader();
-				let d = new TextDecoder(Ir(e.encodingId)), f = await c.read();
+				}), a.on("error", (e) => {
+					d(e);
+				}), a.on("end", () => {
+					c || (s?.flush(), r(Ur(a)));
+				}), o = e.getReader();
+				let i = new TextDecoder(Ir(t.encodingId)), l = 0, u = !1, f = await o.read();
 				for (; !f.done;) {
-					if (u) return;
-					r.signal.throwIfAborted();
-					let e = d.decode(f.value, { stream: !0 });
-					e.length > 0 && s.write(e), f = await c.read();
+					if (c) return;
+					t.abortSignal.throwIfAborted(), l += f.value.length;
+					let e = i.decode(f.value, { stream: !0 });
+					e.length > 0 && (a.write(e), u = !0), f = await o.read();
 				}
-				if (u) return;
-				let m = d.decode();
-				m.length > 0 && s.write(m), s.end();
+				if (c) return;
+				let p = i.decode();
+				p.length > 0 && (a.write(p), u = !0), u ? a.end() : (a.removeAllListeners(), a = void 0, r({
+					byteCount: l,
+					commentLineCount: 0,
+					emptyLineCount: 0,
+					lineCount: 0,
+					nonUniformRecordCount: 0,
+					recordCount: 0
+				}));
 			})().catch((e) => {
-				p(e);
+				d(e);
 			});
 		});
 	}
-	async parseText(e, t, n = !1) {
-		let r = Wr(e), { issues: i, parsedRecords: a, valueDelimiterId: o } = await Gr(e, t, n);
-		return {
-			issues: i,
-			parsedRecords: a,
-			recordDelimiterId: r,
-			valueDelimiterId: o
-		};
+	async parseText(e, t) {
+		return await Or(e, t, Wr);
 	}
 };
 function Hr(e) {
@@ -3561,52 +3599,15 @@ function Ur(e) {
 		recordCount: e?.info.records ?? -1
 	};
 }
-function Wr(e) {
-	let t = (e.match(/\r\n/g) ?? []).length, n = (e.match(/(?<!\r)\n/g) ?? []).length, r = (e.match(/\r(?!\n)/g) ?? []).length;
-	return t >= n && t >= r ? "\r\n" : n >= t && n >= r ? "\n" : r >= t && r >= n ? "\r" : "\n";
-}
-async function Gr(e, t, n) {
-	let r, i, a, o = [], s, c = !1;
-	for (let l of t) {
-		let { issues: t, records: u } = await qr(e, l, n);
-		if (t.length > 0) {
-			s = Kr(s, {
-				delimiter: l,
-				issues: t,
-				records: u
-			});
-			continue;
-		}
-		if (c = !0, u.length === 0) continue;
-		let { averageValueCount: d, sumOfValueCountDiffs: f } = Yr(u);
-		(!a || f <= a) && (!i || d > i) && (r = l, i = d, a = f, o = u);
-	}
-	if (!c && s != null) {
-		let { delimiter: e, issues: t, records: n } = s;
-		return {
-			issues: t,
-			parsedRecords: n,
-			valueDelimiterId: Xr(n) ? e : void 0
-		};
-	}
-	return {
-		issues: [],
-		parsedRecords: o,
-		valueDelimiterId: r != null && Xr(o) ? r : void 0
-	};
-}
-function Kr(e, t) {
-	return e == null || t.issues.length < e.issues.length ? t : e;
-}
-function qr(e, t, n) {
+function Wr(e, t, n) {
 	return new Promise((r) => {
 		let i = [], a = [], o = 0, s = (e) => {
-			e == null || !n && e.code === "CSV_QUOTE_NOT_CLOSED" || (i.push(Jr(e, o + 1)), e.lines != null && (o = e.lines));
+			e == null || !n && e.code === "CSV_QUOTE_NOT_CLOSED" || (i.push(Gr(e, o + 1)), e.lines != null && (o = e.lines));
 		}, c = ar({
 			...Lr,
 			cast: (e, t) => ({
 				value: e,
-				wasValueQuoted: t.quoting
+				valueWasQuoted: t.quoting
 			}),
 			delimiter: t,
 			info: !0,
@@ -3631,7 +3632,7 @@ function qr(e, t, n) {
 		}), c.write(e), c.end();
 	});
 }
-function Jr(e, t) {
+function Gr(e, t) {
 	let n = e.lines, r = e.code === "CSV_INVALID_CLOSING_QUOTE" ? /got "(.*?)" at line/u.exec(e.message)?.[1] : void 0, i = typeof e.field == "string" ? e.field : r;
 	return {
 		endLineNumber: n != null && n > t ? n : void 0,
@@ -3644,18 +3645,4 @@ function Jr(e, t) {
 		value: i != null && i.length > zr ? `${i.slice(0, zr)}…` : i
 	};
 }
-function Yr(e) {
-	let t = 0, n = 0, r;
-	for (let i of e) r != null && (n += Math.abs(i.length - r)), r = i.length, t += i.length;
-	return {
-		averageValueCount: t / e.length,
-		sumOfValueCountDiffs: n
-	};
-}
-function Xr(e) {
-	let t = /* @__PURE__ */ new Map();
-	for (let n of e) t.set(n.length, (t.get(n.length) ?? 0) + 1);
-	let [n = 0, r = 0] = [...t].toSorted((e, t) => t[1] - e[1])[0] ?? [];
-	return n > 1 && r * 2 > e.length;
-}
 export { Vr as Tool };