kakaotalk-chat-analyzer 0.4.1 → 0.4.2
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/README.md +2 -0
- package/dist/src/analysis.js +40 -6
- package/dist/src/analysis.js.map +1 -1
- package/dist/src/cli.js +2 -2
- package/dist/src/cli.js.map +1 -1
- package/dist/src/keyword-canonical.d.ts +1 -0
- package/dist/src/keyword-canonical.js +19 -0
- package/dist/src/keyword-canonical.js.map +1 -0
- package/dist/src/keyword-quality.js +0 -1
- package/dist/src/keyword-quality.js.map +1 -1
- package/dist/src/keyword-rank.js +1 -1
- package/dist/src/keyword-rank.js.map +1 -1
- package/dist/src/keyword-tokenize.d.ts +1 -1
- package/dist/src/keyword-tokenize.js +32 -11
- package/dist/src/keyword-tokenize.js.map +1 -1
- package/dist/src/kiwi-runtime.js +4 -3
- package/dist/src/kiwi-runtime.js.map +1 -1
- package/dist/src/report-progress.d.ts +7 -0
- package/dist/src/report-progress.js +24 -0
- package/dist/src/report-progress.js.map +1 -0
- package/dist/src/stream-parser.d.ts +2 -0
- package/dist/src/stream-parser.js +18 -0
- package/dist/src/stream-parser.js.map +1 -1
- package/dist/src/streaming-tfidf-keywords.js +4 -26
- package/dist/src/streaming-tfidf-keywords.js.map +1 -1
- package/dist/src/version.d.ts +2 -2
- package/dist/src/version.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -111,6 +111,7 @@ npm run bench:stream -- 100000
|
|
|
111
111
|
|
|
112
112
|
| 버전 | 요약 |
|
|
113
113
|
|------|------|
|
|
114
|
+
| **0.4.2** | 키워드 병합(공백+Kiwi)·브랜드 표기 통합·구 dedupe 제거, **진행률 % 기본 표시** |
|
|
114
115
|
| **0.4.1** | Kiwi CI 캐시, `keyword:diff` 스크립트, `KCA_NO_KIWI`, 잡음어·장문 절단 |
|
|
115
116
|
| **0.4.0** | **Kiwi** 형태소 + TF-IDF·PMI 키워드 (KR-WordRank 제거) |
|
|
116
117
|
| **0.3.3** | 하이라이트 문구, 키워드 꼬리 필터, 팩트 매트릭스 중복 정리 |
|
|
@@ -262,6 +263,7 @@ npm test
|
|
|
262
263
|
|
|
263
264
|
- **최초 실행** 시 GitHub에서 Kiwi 한국어 모델을 **무료**로 받아 `~/.cache/kakaotalk-chat-analyzer/kiwi-base/`에 둡니다.
|
|
264
265
|
- **`KCA_NO_KIWI=1`**: 형태소 없이 휴리스틱만(빠름, 품질↓).
|
|
266
|
+
- **진행률**: 기본으로 stderr에 `대화 분석 42% (…)` 표시. 끄려면 `--no-progress`.
|
|
265
267
|
- **키워드 비교**: `npm run keyword:diff -- ./KakaoTalk_Chat_....csv 30`
|
|
266
268
|
- LGPL 고지: [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md)
|
|
267
269
|
|
package/dist/src/analysis.js
CHANGED
|
@@ -1,9 +1,12 @@
|
|
|
1
|
+
import { stat } from "node:fs/promises";
|
|
1
2
|
import { ReportAggregator } from "./aggregator.js";
|
|
2
3
|
import { initKiwiRuntime } from "./kiwi-runtime.js";
|
|
3
4
|
export { maskPartialDisplayName, parseChatRoomNameFromExportPath, safeInputName } from "./analysis-labels.js";
|
|
4
5
|
import { runAnalyzeWorker, shouldUseAnalyzeWorker } from "./analyze-pool.js";
|
|
5
|
-
import {
|
|
6
|
+
import { logReportProgress, resetReportProgress } from "./report-progress.js";
|
|
7
|
+
import { estimateKakaoMessageCount, streamKakaoExport } from "./stream-parser.js";
|
|
6
8
|
const DEFAULT_TOP = 30;
|
|
9
|
+
const PROGRESS_COUNT_MIN_BYTES = 400_000;
|
|
7
10
|
/** Kiwi 등 리포트 엔진 준비(스트리밍 분석 전 1회 호출) */
|
|
8
11
|
export async function prepareReportEngine() {
|
|
9
12
|
await initKiwiRuntime();
|
|
@@ -27,16 +30,41 @@ export async function buildReportDataAsync(result, options) {
|
|
|
27
30
|
return buildReportData(result, options);
|
|
28
31
|
}
|
|
29
32
|
export async function buildReportFromExportSync(filePath, options) {
|
|
33
|
+
const showProgress = options?.progress !== false;
|
|
34
|
+
if (showProgress)
|
|
35
|
+
resetReportProgress();
|
|
36
|
+
if (showProgress)
|
|
37
|
+
logReportProgress({ phase: "형태소 엔진 준비", current: 0 });
|
|
30
38
|
await initKiwiRuntime();
|
|
39
|
+
if (showProgress)
|
|
40
|
+
logReportProgress({ phase: "형태소 엔진 준비", current: 1, total: 1 });
|
|
41
|
+
let estimated;
|
|
42
|
+
if (showProgress) {
|
|
43
|
+
try {
|
|
44
|
+
const { size } = await stat(filePath);
|
|
45
|
+
if (size >= PROGRESS_COUNT_MIN_BYTES) {
|
|
46
|
+
logReportProgress({ phase: "메시지 수 계산", current: 0 });
|
|
47
|
+
estimated = await estimateKakaoMessageCount(filePath);
|
|
48
|
+
logReportProgress({ phase: "메시지 수 계산", current: 1, total: 1 });
|
|
49
|
+
}
|
|
50
|
+
}
|
|
51
|
+
catch {
|
|
52
|
+
estimated = undefined;
|
|
53
|
+
}
|
|
54
|
+
}
|
|
31
55
|
const privacy = options?.privacy ?? "public-masked";
|
|
32
56
|
const top = options?.top ?? DEFAULT_TOP;
|
|
33
57
|
const agg = new ReportAggregator(filePath, privacy, top);
|
|
34
58
|
let meta = null;
|
|
35
|
-
const streamOpts =
|
|
59
|
+
const streamOpts = showProgress
|
|
36
60
|
? {
|
|
37
|
-
progressEvery:
|
|
61
|
+
progressEvery: estimated && estimated > 5_000 ? 500 : 250,
|
|
38
62
|
onProgress: (count) => {
|
|
39
|
-
|
|
63
|
+
logReportProgress({
|
|
64
|
+
phase: "대화 분석",
|
|
65
|
+
current: count,
|
|
66
|
+
total: estimated,
|
|
67
|
+
});
|
|
40
68
|
},
|
|
41
69
|
}
|
|
42
70
|
: undefined;
|
|
@@ -56,9 +84,15 @@ export async function buildReportFromExportSync(filePath, options) {
|
|
|
56
84
|
if (!meta) {
|
|
57
85
|
throw new Error(`No messages parsed from export: ${filePath}`);
|
|
58
86
|
}
|
|
87
|
+
if (showProgress) {
|
|
88
|
+
const total = estimated ?? meta.physicalLines;
|
|
89
|
+
logReportProgress({ phase: "대화 분석", current: total, total });
|
|
90
|
+
logReportProgress({ phase: "리포트 마무리", current: 0, total: 1 });
|
|
91
|
+
}
|
|
59
92
|
const report = agg.finalize(meta);
|
|
60
|
-
if (
|
|
61
|
-
|
|
93
|
+
if (showProgress) {
|
|
94
|
+
logReportProgress({ phase: "리포트 마무리", current: 1, total: 1 });
|
|
95
|
+
console.error(`[kca] 완료 ${report.summary.totalMessages.toLocaleString("ko-KR")}건`);
|
|
62
96
|
}
|
|
63
97
|
return report;
|
|
64
98
|
}
|
package/dist/src/analysis.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"analysis.js","sourceRoot":"","sources":["../../src/analysis.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AACnD,OAAO,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AACpD,OAAO,EAAE,sBAAsB,EAAE,+BAA+B,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AAC9G,OAAO,EAAE,gBAAgB,EAAE,sBAAsB,EAA2B,MAAM,mBAAmB,CAAC;
|
|
1
|
+
{"version":3,"file":"analysis.js","sourceRoot":"","sources":["../../src/analysis.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,OAAO,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AACnD,OAAO,EAAE,eAAe,EAAE,MAAM,mBAAmB,CAAC;AACpD,OAAO,EAAE,sBAAsB,EAAE,+BAA+B,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AAC9G,OAAO,EAAE,gBAAgB,EAAE,sBAAsB,EAA2B,MAAM,mBAAmB,CAAC;AACtG,OAAO,EAAE,iBAAiB,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAC;AAE9E,OAAO,EAAE,yBAAyB,EAAE,iBAAiB,EAAE,MAAM,oBAAoB,CAAC;AAGlF,MAAM,WAAW,GAAG,EAAE,CAAC;AACvB,MAAM,wBAAwB,GAAG,OAAO,CAAC;AAIzC,wCAAwC;AACxC,MAAM,CAAC,KAAK,UAAU,mBAAmB;IACvC,MAAM,eAAe,EAAE,CAAC;AAC1B,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,MAAmB,EAAE,OAA4B;IAC/E,MAAM,OAAO,GAAG,OAAO,EAAE,OAAO,IAAI,eAAe,CAAC;IACpD,MAAM,GAAG,GAAG,OAAO,EAAE,GAAG,IAAI,WAAW,CAAC;IACxC,MAAM,GAAG,GAAG,IAAI,gBAAgB,CAAC,MAAM,CAAC,QAAQ,EAAE,OAAO,EAAE,GAAG,CAAC,CAAC;IAChE,KAAK,MAAM,MAAM,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;QACpC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;IACtB,CAAC;IACD,OAAO,GAAG,CAAC,QAAQ,CAAC;QAClB,QAAQ,EAAE,MAAM,CAAC,QAAQ;QACzB,QAAQ,EAAE,MAAM,CAAC,QAAQ;QACzB,aAAa,EAAE,MAAM,CAAC,aAAa;QACnC,YAAY,EAAE,MAAM,CAAC,QAAQ,CAAC,MAAM;KACrC,CAAC,CAAC;AACL,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,oBAAoB,CACxC,MAAmB,EACnB,OAA4B;IAE5B,MAAM,mBAAmB,EAAE,CAAC;IAC5B,OAAO,eAAe,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAC1C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,yBAAyB,CAC7C,QAAgB,EAChB,OAA4B;IAE5B,MAAM,YAAY,GAAG,OAAO,EAAE,QAAQ,KAAK,KAAK,CAAC;IACjD,IAAI,YAAY;QAAE,mBAAmB,EAAE,CAAC;IAExC,IAAI,YAAY;QAAE,iBAAiB,CAAC,EAAE,KAAK,EAAE,WAAW,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC;IACxE,MAAM,eAAe,EAAE,CAAC;IACxB,IAAI,YAAY;QAAE,iBAAiB,CAAC,EAAE,KAAK,EAAE,WAAW,EAAE,OAAO,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;IAElF,IAAI,SAA6B,CAAC;IAClC,IAAI,YAAY,EAAE,CAAC;QACjB,IAAI,CAAC;YACH,MAAM,EAAE,IAAI,EAAE,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC;YACtC,IAAI,IAAI,IAAI,wBAAwB,EAAE,CAAC;gBACrC,iBAAiB,CAAC,EAAE,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC;gBACrD,SAAS,GAAG,MAAM,yBAAyB,CAAC,QAAQ,CAAC,CAAC;gBACtD,iBAAiB,CAAC,EAAE,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;YACjE,CAAC;QACH,CAAC;QAAC,MAAM,CAAC;YACP,SAAS,GAAG,SAAS,CAAC;QACxB,CAAC;IACH,CAAC;IAED,MAAM,OAAO,GAAG,OAAO,EAAE,OAAO,IAAI,eAAe,CAAC;IACpD,MAAM,GAAG,GAAG,OAAO,EAAE,GAAG,IAAI,WAAW,CAAC;IACxC,MAAM,GAAG,GAAG,IAAI,gBAAgB,CAAC,QAAQ,EAAE,OAAO,EAAE,GAAG,CAAC,CAAC;IACzD,IAAI,IAAI,GACN,IAAI,CAAC;IAEP,MAAM,UAAU,GAAmC,YAAY;QAC7D,CAAC,CAAC;YACE,aAAa,EAAE,SAAS,IAAI,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG;YACzD,UAAU,EAAE,CAAC,KAAK,EAAE,EAAE;gBACpB,iBAAiB,CAAC;oBAChB,KAAK,EAAE,OAAO;oBACd,OAAO,EAAE,KAAK;oBACd,KAAK,EAAE,SAAS;iBACjB,CAAC,CAAC;YACL,CAAC;SACF;QACH,CAAC,CAAC,SAAS,CAAC;IAEd,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,iBAAiB,CAAC,QAAQ,EAAE,UAAU,CAAC,EAAE,CAAC;QAClE,IAAI,KAAK,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;YAC5B,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;QAC5B,CAAC;aAAM,CAAC;YACN,IAAI,GAAG;gBACL,QAAQ,EAAE,KAAK,CAAC,IAAI,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,KAAK,CAAC,IAAI,CAAC,QAAQ;gBAC7B,aAAa,EAAE,KAAK,CAAC,IAAI,CAAC,aAAa;gBACvC,YAAY,EAAE,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM;aACzC,CAAC;QACJ,CAAC;IACH,CAAC;IAED,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,mCAAmC,QAAQ,EAAE,CAAC,CAAC;IACjE,CAAC;IAED,IAAI,YAAY,EAAE,CAAC;QACjB,MAAM,KAAK,GAAG,SAAS,IAAI,IAAI,CAAC,aAAa,CAAC;QAC9C,iBAAiB,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC,CAAC;QAC7D,iBAAiB,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;IAChE,CAAC;IAED,MAAM,MAAM,GAAG,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IAElC,IAAI,YAAY,EAAE,CAAC;QACjB,iBAAiB,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAC;QAC9D,OAAO,CAAC,KAAK,CAAC,YAAY,MAAM,CAAC,OAAO,CAAC,aAAa,CAAC,cAAc,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;IACrF,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,qBAAqB,CACzC,QAAgB,EAChB,OAA4B;IAE5B,IAAI,MAAM,sBAAsB,CAAC,QAAQ,EAAE,OAAO,CAAC,EAAE,CAAC;QACpD,OAAO,gBAAgB,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;IAC7C,CAAC;IACD,OAAO,yBAAyB,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;AACtD,CAAC"}
|
package/dist/src/cli.js
CHANGED
|
@@ -37,7 +37,7 @@ main
|
|
|
37
37
|
.option("-o, --out <dir>", "리포트 출력 폴더", DEFAULT_OUT)
|
|
38
38
|
.option("--profile", "파싱·집계·HTML 단계별 소요 시간을 출력합니다.", false)
|
|
39
39
|
.option("--no-worker", "3MB 이상 파일도 Worker 없이 메인 스레드에서 집계합니다.", false)
|
|
40
|
-
.option("--progress", "
|
|
40
|
+
.option("--no-progress", "분석·집계 진행률(%) 표시를 끕니다.", false)
|
|
41
41
|
.description("기본: 리포트 생성 후 BrewPage로 업로드(로컬만은 --local).")
|
|
42
42
|
.action(async (csv, options) => {
|
|
43
43
|
const host = parseHostName(options.host);
|
|
@@ -51,7 +51,7 @@ main
|
|
|
51
51
|
top,
|
|
52
52
|
profile: options.profile,
|
|
53
53
|
worker: options.noWorker || options.profile ? false : undefined,
|
|
54
|
-
progress: options.
|
|
54
|
+
progress: !options.noProgress,
|
|
55
55
|
});
|
|
56
56
|
console.log(`리포트: ${htmlPath}`);
|
|
57
57
|
console.log(`크기: ${await formatFileSize(htmlPath)}`);
|
package/dist/src/cli.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"cli.js","sourceRoot":"","sources":["../../src/cli.ts"],"names":[],"mappings":";AACA,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,eAAe,EAAE,aAAa,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAC5F,OAAO,EAAE,sBAAsB,EAAE,MAAM,oBAAoB,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AACrE,OAAO,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAC;AAC/C,OAAO,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AAIvC,MAAM,iBAAiB,GAAG,mBAAmB,CAAC;AAC9C,MAAM,WAAW,GAAG,iBAAiB,CAAC;AACtC,MAAM,WAAW,GAAG,EAAE,CAAC;AAEvB,MAAM,OAAO,GAAG,IAAI,OAAO,EAAE,CAAC;AAE9B,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,WAAW,CAAC,4CAA4C,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;AAE/F,OAAO,CAAC,WAAW,CACjB,OAAO,EACP;;;;;;;;;;CAUD,CACA,CAAC;AAEF,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;AAE3E,IAAI;KACD,QAAQ,CAAC,OAAO,EAAE,oBAAoB,CAAC;KACvC,MAAM,CAAC,SAAS,EAAE,yBAAyB,EAAE,KAAK,CAAC;KACnD,MAAM,CAAC,WAAW,EAAE,uBAAuB,EAAE,KAAK,CAAC;KACnD,MAAM,CAAC,eAAe,EAAE,gCAAgC,EAAE,UAAU,CAAC;KACrE,MAAM,CAAC,cAAc,EAAE,eAAe,EAAE,IAAI,CAAC;KAC7C,MAAM,CAAC,kBAAkB,EAAE,YAAY,EAAE,iBAAiB,CAAC;KAC3D,MAAM,CAAC,kBAAkB,EAAE,kCAAkC,EAAE,eAAe,CAAC;KAC/E,MAAM,CAAC,eAAe,EAAE,aAAa,EAAE,MAAM,CAAC,WAAW,CAAC,CAAC;KAC3D,MAAM,CAAC,iBAAiB,EAAE,WAAW,EAAE,WAAW,CAAC;KACnD,MAAM,CAAC,WAAW,EAAE,8BAA8B,EAAE,KAAK,CAAC;KAC1D,MAAM,CAAC,aAAa,EAAE,sCAAsC,EAAE,KAAK,CAAC;KACpE,MAAM,CAAC,
|
|
1
|
+
{"version":3,"file":"cli.js","sourceRoot":"","sources":["../../src/cli.ts"],"names":[],"mappings":";AACA,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpC,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,eAAe,EAAE,aAAa,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAC5F,OAAO,EAAE,sBAAsB,EAAE,MAAM,oBAAoB,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AACrE,OAAO,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAC;AAC/C,OAAO,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AAIvC,MAAM,iBAAiB,GAAG,mBAAmB,CAAC;AAC9C,MAAM,WAAW,GAAG,iBAAiB,CAAC;AACtC,MAAM,WAAW,GAAG,EAAE,CAAC;AAEvB,MAAM,OAAO,GAAG,IAAI,OAAO,EAAE,CAAC;AAE9B,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,WAAW,CAAC,4CAA4C,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;AAE/F,OAAO,CAAC,WAAW,CACjB,OAAO,EACP;;;;;;;;;;CAUD,CACA,CAAC;AAEF,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;AAE3E,IAAI;KACD,QAAQ,CAAC,OAAO,EAAE,oBAAoB,CAAC;KACvC,MAAM,CAAC,SAAS,EAAE,yBAAyB,EAAE,KAAK,CAAC;KACnD,MAAM,CAAC,WAAW,EAAE,uBAAuB,EAAE,KAAK,CAAC;KACnD,MAAM,CAAC,eAAe,EAAE,gCAAgC,EAAE,UAAU,CAAC;KACrE,MAAM,CAAC,cAAc,EAAE,eAAe,EAAE,IAAI,CAAC;KAC7C,MAAM,CAAC,kBAAkB,EAAE,YAAY,EAAE,iBAAiB,CAAC;KAC3D,MAAM,CAAC,kBAAkB,EAAE,kCAAkC,EAAE,eAAe,CAAC;KAC/E,MAAM,CAAC,eAAe,EAAE,aAAa,EAAE,MAAM,CAAC,WAAW,CAAC,CAAC;KAC3D,MAAM,CAAC,iBAAiB,EAAE,WAAW,EAAE,WAAW,CAAC;KACnD,MAAM,CAAC,WAAW,EAAE,8BAA8B,EAAE,KAAK,CAAC;KAC1D,MAAM,CAAC,aAAa,EAAE,sCAAsC,EAAE,KAAK,CAAC;KACpE,MAAM,CAAC,eAAe,EAAE,uBAAuB,EAAE,KAAK,CAAC;KACvD,WAAW,CAAC,2CAA2C,CAAC;KACxD,MAAM,CAAC,KAAK,EAAE,GAAW,EAAE,OAAoB,EAAE,EAAE;IAClD,MAAM,IAAI,GAAG,aAAa,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACzC,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;IACtC,MAAM,SAAS,GAAG,iBAAiB,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;IAChD,MAAM,OAAO,GAAG,YAAY,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;IAC9C,MAAM,GAAG,GAAG,gBAAgB,CAAC,OAAO,CAAC,GAAG,EAAE,WAAW,CAAC,CAAC;IAEvD,MAAM,QAAQ,GAAG,MAAM,cAAc,CAAC,GAAG,EAAE;QACzC,MAAM,EAAE,OAAO,CAAC,GAAG;QACnB,OAAO;QACP,GAAG;QACH,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,MAAM,EAAE,OAAO,CAAC,QAAQ,IAAI,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS;QAC/D,QAAQ,EAAE,CAAC,OAAO,CAAC,UAAU;KAC9B,CAAC,CAAC;IACH,OAAO,CAAC,GAAG,CAAC,QAAQ,QAAQ,EAAE,CAAC,CAAC;IAChC,OAAO,CAAC,GAAG,CAAC,OAAO,MAAM,cAAc,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC;IAErD,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QAClB,OAAO,CAAC,GAAG,CAAC,wBAAwB,CAAC,CAAC;QACtC,OAAO;IACT,CAAC;IACD,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;QACnB,OAAO,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC;QACjC,OAAO;IACT,CAAC;IAED,IAAI,CAAC;QACH,MAAM,QAAQ,GAAG,cAAc,CAAC,IAAI,CAAC,CAAC;QACtC,MAAM,KAAK,GAAG,MAAM,aAAa,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC;QACnD,MAAM,IAAI,GAAG,MAAM,cAAc,CAAC,QAAQ,CAAC,CAAC;QAC5C,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,OAAO,CAAC;YACpC,IAAI;YACJ,OAAO;YACP,SAAS;YACT,KAAK,EAAE,aAAa;YACpB,UAAU,EAAE,KAAK,EAAE,UAAU;SAC9B,CAAC,CAAC;QAEH,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;YACtB,MAAM,cAAc,CAAC;gBACnB,QAAQ,EAAE,MAAM,CAAC,QAAQ;gBACzB,SAAS;gBACT,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,SAAS,EAAE,MAAM,CAAC,SAAS;gBAC3B,EAAE,EAAE,MAAM,CAAC,EAAE;gBACb,IAAI,EAAE,MAAM,CAAC,IAAI;gBACjB,SAAS,EAAE,MAAM,CAAC,SAAS;aAC5B,CAAC,CAAC;QACL,CAAC;QAED,kBAAkB,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;IACxC,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,CAAC,KAAK,CAAC,WAAW,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;QACnF,OAAO,CAAC,KAAK,CAAC,qBAAqB,QAAQ,EAAE,CAAC,CAAC;QAC/C,IAAI,IAAI,KAAK,UAAU,EAAE,CAAC;YACxB,OAAO,CAAC,KAAK,CAAC,iDAAiD,GAAG,2BAA2B,OAAO,EAAE,CAAC,CAAC;QAC1G,CAAC;QACD,OAAO,CAAC,QAAQ,GAAG,CAAC,CAAC;IACvB,CAAC;AACH,CAAC,CAAC,CAAC;AAEL,OAAO;KACJ,OAAO,CAAC,SAAS,CAAC;KAClB,QAAQ,CAAC,OAAO,EAAE,cAAc,CAAC;KACjC,WAAW,CAAC,gCAAgC,CAAC;KAC7C,MAAM,CAAC,KAAK,EAAE,GAAW,EAAE,EAAE;IAC5B,MAAM,OAAO,GAAG,MAAM,sBAAsB,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC;IAC3D,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IAC1B,IAAI,OAAO,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAChC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC;QACxB,KAAK,MAAM,OAAO,IAAI,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC;YACpD,OAAO,CAAC,GAAG,CAAC,KAAK,OAAO,CAAC,IAAI,MAAM,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;QACrD,CAAC;QACD,IAAI,OAAO,CAAC,QAAQ,CAAC,MAAM,GAAG,EAAE,EAAE,CAAC;YACjC,OAAO,CAAC,GAAG,CAAC,SAAS,OAAO,CAAC,QAAQ,CAAC,MAAM,GAAG,EAAE,GAAG,CAAC,CAAC;QACxD,CAAC;IACH,CAAC;AACH,CAAC,CAAC,CAAC;AAEL,MAAM,KAAK,GAAG,OAAO,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,WAAW,CAAC,sBAAsB,CAAC,CAAC;AAE3E,KAAK;KACF,OAAO,CAAC,OAAO,CAAC;KAChB,MAAM,CAAC,eAAe,EAAE,kCAAkC,EAAE,UAAU,CAAC;KACvE,MAAM,CAAC,kBAAkB,EAAE,QAAQ,EAAE,iBAAiB,CAAC;KACvD,WAAW,CAAC,sBAAsB,CAAC;KACnC,MAAM,CAAC,KAAK,EAAE,OAAqB,EAAE,EAAE;IACtC,MAAM,IAAI,GAAG,aAAa,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IACzC,MAAM,SAAS,GAAG,iBAAiB,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;IAChD,MAAM,OAAO,GAAG,MAAM,eAAe,CAAC,IAAI,EAAE,SAAS,CAAC,CAAC;IACvD,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,IAAI,IAAI,SAAS,aAAa,CAAC,CAAC,CAAC,GAAG,IAAI,IAAI,SAAS,iBAAiB,CAAC,CAAC;AACnG,CAAC,CAAC,CAAC;AAEL,OAAO,CAAC,aAAa,CAAC,EAAE,eAAe,EAAE,IAAI,EAAE,CAAC,CAAC;AAEjD,OAAO,CAAC,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,CAAC,KAAc,EAAE,EAAE;IACxD,OAAO,CAAC,KAAK,CAAC,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC;IACtE,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC;AAqBH,KAAK,UAAU,cAAc,CAC3B,GAAW,EACX,OAOC;IAED,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC;IAC7B,MAAM,GAAG,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,KAAa,EAAE,EAAU,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,SAAS,KAAK,KAAK,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,EAAE,GAAE,CAAC,CAAC;IAEjH,IAAI,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;IAC3B,MAAM,IAAI,GAAG,MAAM,qBAAqB,CAAC,OAAO,EAAE;QAChD,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,GAAG,EAAE,OAAO,CAAC,GAAG;QAChB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,QAAQ,EAAE,OAAO,CAAC,QAAQ;KAC3B,CAAC,CAAC;IACH,GAAG,CAAC,iBAAiB,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,CAAC;IAE/C,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;IACvB,MAAM,IAAI,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAC;IACpC,GAAG,CAAC,aAAa,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,CAAC;IAE3C,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;QACpB,OAAO,CAAC,KAAK,CAAC,mBAAmB,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,cAAc,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC;IACzF,CAAC;IAED,MAAM,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;IACvC,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IAE/C,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;IACvB,MAAM,KAAK,CAAC,MAAM,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACzC,MAAM,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC;IACxC,GAAG,CAAC,YAAY,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,CAAC;IAE1C,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,QAAgB;IAC5C,MAAM,EAAE,QAAQ,EAAE,GAAG,MAAM,MAAM,CAAC,kBAAkB,CAAC,CAAC;IACtD,OAAO,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;AACpC,CAAC;AAED,SAAS,YAAY,CAAC,KAAa;IACjC,IAAI,KAAK,KAAK,eAAe,IAAI,KAAK,KAAK,kBAAkB;QAAE,OAAO,KAAK,CAAC;IAC5E,MAAM,IAAI,KAAK,CAAC,2BAA2B,KAAK,oDAAoD,CAAC,CAAC;AACxG,CAAC;AAED,SAAS,QAAQ,CAAC,KAAa;IAC7B,MAAM,GAAG,GAAG,gBAAgB,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;IACxC,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,CAAC;AACxC,CAAC;AAED,SAAS,gBAAgB,CAAC,KAAa,EAAE,QAAgB;IACvD,MAAM,MAAM,GAAG,MAAM,CAAC,QAAQ,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;IAC1C,OAAO,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC;AACnE,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAa;IACtC,MAAM,UAAU,GAAG,KAAK,CAAC,WAAW,EAAE,CAAC,IAAI,EAAE,CAAC;IAC9C,IAAI,CAAC,mBAAmB,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAC1C,MAAM,IAAI,KAAK,CAAC,oCAAoC,CAAC,CAAC;IACxD,CAAC;IACD,OAAO,UAAU,CAAC;AACpB,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,QAAgB;IAC5C,MAAM,IAAI,GAAG,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC;IACzC,IAAI,IAAI,GAAG,IAAI;QAAE,OAAO,GAAG,IAAI,IAAI,CAAC;IACpC,IAAI,IAAI,GAAG,IAAI,GAAG,IAAI;QAAE,OAAO,GAAG,CAAC,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC;IACjE,OAAO,GAAG,CAAC,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC;AAClD,CAAC;AAED,SAAS,kBAAkB,CAAC,MAAqB,EAAE,SAAiB;IAClE,OAAO,CAAC,GAAG,CAAC,WAAW,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;IACtC,IAAI,MAAM,CAAC,SAAS;QAAE,OAAO,CAAC,GAAG,CAAC,OAAO,MAAM,CAAC,SAAS,EAAE,CAAC,CAAC;IAC7D,IAAI,MAAM,CAAC,SAAS;QAAE,OAAO,CAAC,GAAG,CAAC,cAAc,MAAM,CAAC,SAAS,EAAE,CAAC,CAAC;IACpE,IAAI,MAAM,CAAC,UAAU;QAAE,OAAO,CAAC,GAAG,CAAC,aAAa,SAAS,CAAC,MAAM,CAAC,UAAU,CAAC,KAAK,aAAa,EAAE,QAAQ,CAAC,CAAC;IAC1G,OAAO,CAAC,GAAG,CAAC,QAAQ,MAAM,CAAC,QAAQ,EAAE,CAAC,CAAC;IACvC,OAAO,CAAC,GAAG,CAAC,WAAW,SAAS,EAAE,CAAC,CAAC;AACtC,CAAC;AAED,SAAS,SAAS,CAAC,KAAa;IAC9B,IAAI,KAAK,CAAC,MAAM,IAAI,EAAE;QAAE,OAAO,UAAU,CAAC;IAC1C,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,MAAM,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AACrD,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export declare function canonicalKeywordToken(token: string): string;
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
/** 라틴 표기 → 채팅에서 흔한 한글 표기로 합침(분산 방지) */
|
|
2
|
+
const LATIN_TO_CANONICAL = {
|
|
3
|
+
claude: "클로드",
|
|
4
|
+
codex: "코덱스",
|
|
5
|
+
cursor: "커서",
|
|
6
|
+
chatgpt: "챗gpt",
|
|
7
|
+
gemini: "제미니",
|
|
8
|
+
openai: "오픈ai",
|
|
9
|
+
github: "깃허브",
|
|
10
|
+
npm: "npm",
|
|
11
|
+
};
|
|
12
|
+
export function canonicalKeywordToken(token) {
|
|
13
|
+
if (/^[A-Za-z][A-Za-z0-9+.-]*$/.test(token)) {
|
|
14
|
+
const key = token.toLowerCase();
|
|
15
|
+
return LATIN_TO_CANONICAL[key] ?? key;
|
|
16
|
+
}
|
|
17
|
+
return token;
|
|
18
|
+
}
|
|
19
|
+
//# sourceMappingURL=keyword-canonical.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"keyword-canonical.js","sourceRoot":"","sources":["../../src/keyword-canonical.ts"],"names":[],"mappings":"AAAA,uCAAuC;AACvC,MAAM,kBAAkB,GAA2B;IACjD,MAAM,EAAE,KAAK;IACb,KAAK,EAAE,KAAK;IACZ,MAAM,EAAE,IAAI;IACZ,OAAO,EAAE,MAAM;IACf,MAAM,EAAE,KAAK;IACb,MAAM,EAAE,MAAM;IACd,MAAM,EAAE,KAAK;IACb,GAAG,EAAE,KAAK;CACX,CAAC;AAEF,MAAM,UAAU,qBAAqB,CAAC,KAAa;IACjD,IAAI,2BAA2B,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QAC5C,MAAM,GAAG,GAAG,KAAK,CAAC,WAAW,EAAE,CAAC;QAChC,OAAO,kBAAkB,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC;IACxC,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"keyword-quality.js","sourceRoot":"","sources":["../../src/keyword-quality.ts"],"names":[],"mappings":"AAAA,6BAA6B;AAC7B,MAAM,WAAW,GAAG,IAAI,GAAG,CAAC;IAC1B,SAAS;IACT,OAAO;IACP,MAAM;IACN,MAAM;IACN,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,KAAK;IACL,MAAM;IACN,KAAK;IACL,KAAK;IACL,KAAK;CACN,CAAC,CAAC;AAEH,sBAAsB;AACtB,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC;IAC/B,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,
|
|
1
|
+
{"version":3,"file":"keyword-quality.js","sourceRoot":"","sources":["../../src/keyword-quality.ts"],"names":[],"mappings":"AAAA,6BAA6B;AAC7B,MAAM,WAAW,GAAG,IAAI,GAAG,CAAC;IAC1B,SAAS;IACT,OAAO;IACP,MAAM;IACN,MAAM;IACN,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,KAAK;IACL,MAAM;IACN,KAAK;IACL,KAAK;IACL,KAAK;CACN,CAAC,CAAC;AAEH,sBAAsB;AACtB,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC;IAC/B,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,KAAK;CACN,CAAC,CAAC;AAEH,MAAM,UAAU,cAAc,CAAC,KAAa;IAC1C,MAAM,CAAC,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;IACvB,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,IAAI,CAAC;IAC9B,IAAI,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IACrC,IAAI,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC;QAAE,OAAO,IAAI,CAAC;IAC1D,IAAI,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,IAAI,WAAW,CAAC,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;QAAE,OAAO,IAAI,CAAC;IAC1F,IAAI,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IAChC,IAAI,sBAAsB,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IAChD,IAAI,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IACvC,IAAI,gBAAgB,CAAC,GAAG,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IACzC,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IAC1E,OAAO,KAAK,CAAC;AACf,CAAC"}
|
package/dist/src/keyword-rank.js
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"keyword-rank.js","sourceRoot":"","sources":["../../src/keyword-rank.ts"],"names":[],"mappings":"AAcA,yBAAyB;AACzB,MAAM,UAAU,gBAAgB,CAAC,YAAoB;IACnD,IAAI,YAAY,GAAG,GAAG;QAAE,OAAO,CAAC,CAAC;IACjC,IAAI,YAAY,GAAG,KAAK;QAAE,OAAO,CAAC,CAAC;IACnC,IAAI,YAAY,GAAG,
|
|
1
|
+
{"version":3,"file":"keyword-rank.js","sourceRoot":"","sources":["../../src/keyword-rank.ts"],"names":[],"mappings":"AAcA,yBAAyB;AACzB,MAAM,UAAU,gBAAgB,CAAC,YAAoB;IACnD,IAAI,YAAY,GAAG,GAAG;QAAE,OAAO,CAAC,CAAC;IACjC,IAAI,YAAY,GAAG,KAAK;QAAE,OAAO,CAAC,CAAC;IACnC,IAAI,YAAY,GAAG,OAAO;QAAE,OAAO,CAAC,CAAC;IACrC,OAAO,CAAC,CAAC;AACX,CAAC"}
|
|
@@ -1,10 +1,13 @@
|
|
|
1
1
|
import { getKiwiRuntime, kiwiKeywordTokens } from "./kiwi-runtime.js";
|
|
2
|
+
import { canonicalKeywordToken } from "./keyword-canonical.js";
|
|
2
3
|
import { normalizeKoreanText } from "./korean-normalize.js";
|
|
3
4
|
const MAX_TOKEN_LEN = 32;
|
|
4
5
|
const HANGUL_GLUE_RE = /[가-힣]{6,}/;
|
|
6
|
+
const KIWI_MORPH_MAX_CHARS = 768;
|
|
5
7
|
const TRAILING_ENDING_RE = /(?:했(?:어|음|네|지)?|했|하는|하다|해서|이고|이었|었는|는데|지만|으로|에서|에게|부터|까지|처럼|보다|마다|라서|라고|습니다|세요|해요|함|임|음|네|지|아|어|야|요)$/u;
|
|
6
8
|
function normalizeToken(token) {
|
|
7
|
-
|
|
9
|
+
const t = /^[A-Za-z0-9_+-]+$/.test(token) ? token.toLowerCase() : token.trim();
|
|
10
|
+
return canonicalKeywordToken(t);
|
|
8
11
|
}
|
|
9
12
|
function spaceTokens(doc) {
|
|
10
13
|
const out = [];
|
|
@@ -25,10 +28,23 @@ function heuristicExtra(token) {
|
|
|
25
28
|
if (HANGUL_GLUE_RE.test(token)) {
|
|
26
29
|
const stem = token.replace(TRAILING_ENDING_RE, "");
|
|
27
30
|
if (stem.length >= 2 && stem.length < token.length)
|
|
28
|
-
extras.push(stem);
|
|
31
|
+
extras.push(canonicalKeywordToken(stem));
|
|
29
32
|
}
|
|
30
33
|
return extras;
|
|
31
34
|
}
|
|
35
|
+
function mergeTokens(...lists) {
|
|
36
|
+
const seen = new Set();
|
|
37
|
+
const out = [];
|
|
38
|
+
for (const list of lists) {
|
|
39
|
+
for (const t of list) {
|
|
40
|
+
if (!t || seen.has(t))
|
|
41
|
+
continue;
|
|
42
|
+
seen.add(t);
|
|
43
|
+
out.push(t);
|
|
44
|
+
}
|
|
45
|
+
}
|
|
46
|
+
return out;
|
|
47
|
+
}
|
|
32
48
|
/** 공백·접미사 휴리스틱만 (비교·KCA_NO_KIWI용) */
|
|
33
49
|
export function tokenizeHeuristicOnly(raw) {
|
|
34
50
|
const doc = normalizeKoreanText(raw, { keepEnglish: true, keepNumbers: true });
|
|
@@ -49,19 +65,24 @@ export function tokenizeHeuristicOnly(raw) {
|
|
|
49
65
|
}
|
|
50
66
|
return out;
|
|
51
67
|
}
|
|
52
|
-
|
|
68
|
+
function shouldRunKiwiMorph(doc) {
|
|
69
|
+
return /[가-힣]/.test(doc) && doc.length >= 3;
|
|
70
|
+
}
|
|
71
|
+
/** 본문 키워드: 공백 어절 + (한글 있으면) Kiwi 형태소 병합 */
|
|
53
72
|
export function tokenizeForKeywords(raw) {
|
|
73
|
+
const heur = tokenizeHeuristicOnly(raw);
|
|
54
74
|
if (process.env.KCA_NO_KIWI === "1")
|
|
55
|
-
return
|
|
75
|
+
return heur;
|
|
56
76
|
const doc = normalizeKoreanText(raw, { keepEnglish: true, keepNumbers: true });
|
|
57
77
|
if (!doc)
|
|
58
|
-
return
|
|
78
|
+
return heur;
|
|
59
79
|
const kiwi = getKiwiRuntime();
|
|
60
|
-
if (kiwi)
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
80
|
+
if (!kiwi || !shouldRunKiwiMorph(doc))
|
|
81
|
+
return heur;
|
|
82
|
+
const slice = doc.length > KIWI_MORPH_MAX_CHARS ? doc.slice(0, KIWI_MORPH_MAX_CHARS) : doc;
|
|
83
|
+
const tailSlice = doc.length > KIWI_MORPH_MAX_CHARS ? doc.slice(KIWI_MORPH_MAX_CHARS) : "";
|
|
84
|
+
const fromKiwi = kiwiKeywordTokens(slice);
|
|
85
|
+
const fromTail = tailSlice ? spaceTokens(tailSlice) : [];
|
|
86
|
+
return mergeTokens(fromKiwi, heur, fromTail);
|
|
66
87
|
}
|
|
67
88
|
//# sourceMappingURL=keyword-tokenize.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"keyword-tokenize.js","sourceRoot":"","sources":["../../src/keyword-tokenize.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,cAAc,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AACtE,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAC;AAE5D,MAAM,aAAa,GAAG,EAAE,CAAC;AACzB,MAAM,cAAc,GAAG,WAAW,CAAC;AACnC,MAAM,kBAAkB,GACtB,yGAAyG,CAAC;AAE5G,SAAS,cAAc,CAAC,KAAa;IACnC,
|
|
1
|
+
{"version":3,"file":"keyword-tokenize.js","sourceRoot":"","sources":["../../src/keyword-tokenize.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,cAAc,EAAE,iBAAiB,EAAE,MAAM,mBAAmB,CAAC;AACtE,OAAO,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAC;AAC/D,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAC;AAE5D,MAAM,aAAa,GAAG,EAAE,CAAC;AACzB,MAAM,cAAc,GAAG,WAAW,CAAC;AACnC,MAAM,oBAAoB,GAAG,GAAG,CAAC;AACjC,MAAM,kBAAkB,GACtB,yGAAyG,CAAC;AAE5G,SAAS,cAAc,CAAC,KAAa;IACnC,MAAM,CAAC,GAAG,mBAAmB,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;IAC/E,OAAO,qBAAqB,CAAC,CAAC,CAAC,CAAC;AAClC,CAAC;AAED,SAAS,WAAW,CAAC,GAAW;IAC9B,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;QACnC,IAAI,CAAC,GAAG;YAAE,SAAS;QACnB,MAAM,CAAC,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC;QAC9B,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,aAAa;YAAE,SAAS;QACvD,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC;YAAE,SAAS;QACrC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACd,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,cAAc,CAAC,KAAa;IACnC,MAAM,MAAM,GAAa,EAAE,CAAC;IAC5B,IAAI,cAAc,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QAC/B,MAAM,IAAI,GAAG,KAAK,CAAC,OAAO,CAAC,kBAAkB,EAAE,EAAE,CAAC,CAAC;QACnD,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC,MAAM;YAAE,MAAM,CAAC,IAAI,CAAC,qBAAqB,CAAC,IAAI,CAAC,CAAC,CAAC;IAC/F,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,WAAW,CAAC,GAAG,KAAiB;IACvC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,KAAK,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC;YACrB,IAAI,CAAC,CAAC,IAAI,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;gBAAE,SAAS;YAChC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACZ,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,qCAAqC;AACrC,MAAM,UAAU,qBAAqB,CAAC,GAAW;IAC/C,MAAM,GAAG,GAAG,mBAAmB,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,IAAI,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,CAAC;IAC/E,IAAI,CAAC,GAAG;QAAE,OAAO,EAAE,CAAC;IACpB,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,MAAM,IAAI,GAAG,CAAC,CAAS,EAAE,EAAE;QACzB,IAAI,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;YAAE,OAAO;QACxB,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;QACZ,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACd,CAAC,CAAC;IACF,KAAK,MAAM,CAAC,IAAI,WAAW,CAAC,GAAG,CAAC,EAAE,CAAC;QACjC,IAAI,CAAC,CAAC,CAAC,CAAC;QACR,KAAK,MAAM,KAAK,IAAI,cAAc,CAAC,CAAC,CAAC;YAAE,IAAI,CAAC,KAAK,CAAC,CAAC;IACrD,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,kBAAkB,CAAC,GAAW;IACrC,OAAO,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,MAAM,IAAI,CAAC,CAAC;AAC9C,CAAC;AAED,2CAA2C;AAC3C,MAAM,UAAU,mBAAmB,CAAC,GAAW;IAC7C,MAAM,IAAI,GAAG,qBAAqB,CAAC,GAAG,CAAC,CAAC;IACxC,IAAI,OAAO,CAAC,GAAG,CAAC,WAAW,KAAK,GAAG;QAAE,OAAO,IAAI,CAAC;IAEjD,MAAM,GAAG,GAAG,mBAAmB,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,IAAI,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,CAAC;IAC/E,IAAI,CAAC,GAAG;QAAE,OAAO,IAAI,CAAC;IAEtB,MAAM,IAAI,GAAG,cAAc,EAAE,CAAC;IAC9B,IAAI,CAAC,IAAI,IAAI,CAAC,kBAAkB,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAC;IAEnD,MAAM,KAAK,GAAG,GAAG,CAAC,MAAM,GAAG,oBAAoB,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,oBAAoB,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC;IAC3F,MAAM,SAAS,GAAG,GAAG,CAAC,MAAM,GAAG,oBAAoB,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,oBAAoB,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAC3F,MAAM,QAAQ,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC;IAC1C,MAAM,QAAQ,GAAG,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IACzD,OAAO,WAAW,CAAC,QAAQ,EAAE,IAAI,EAAE,QAAQ,CAAC,CAAC;AAC/C,CAAC"}
|
package/dist/src/kiwi-runtime.js
CHANGED
|
@@ -5,6 +5,7 @@ import { fileURLToPath } from "node:url";
|
|
|
5
5
|
import { spawnSync } from "node:child_process";
|
|
6
6
|
import { pipeline } from "node:stream/promises";
|
|
7
7
|
import { KiwiBuilder, Match } from "kiwi-nlp";
|
|
8
|
+
import { canonicalKeywordToken } from "./keyword-canonical.js";
|
|
8
9
|
const KIWI_MODEL_TAG = "0.23.1";
|
|
9
10
|
const MODEL_URL = `https://github.com/bab2min/Kiwi/releases/download/v${KIWI_MODEL_TAG}/kiwi_model_v${KIWI_MODEL_TAG}_base.tgz`;
|
|
10
11
|
const MODEL_FILES = [
|
|
@@ -118,7 +119,7 @@ export function isKiwiReady() {
|
|
|
118
119
|
return readyKiwi !== null;
|
|
119
120
|
}
|
|
120
121
|
/** Kiwi가 켜져 있을 때만 호출 */
|
|
121
|
-
const KIWI_MAX_CHARS =
|
|
122
|
+
const KIWI_MAX_CHARS = 768;
|
|
122
123
|
export function kiwiKeywordTokens(text) {
|
|
123
124
|
const kiwi = readyKiwi;
|
|
124
125
|
if (!kiwi)
|
|
@@ -163,8 +164,8 @@ function normalizeKiwiForm(raw) {
|
|
|
163
164
|
if (w.length < 2)
|
|
164
165
|
return "";
|
|
165
166
|
if (/^[A-Za-z0-9_+-]+$/.test(w))
|
|
166
|
-
return w.toLowerCase();
|
|
167
|
-
return w;
|
|
167
|
+
return canonicalKeywordToken(w.toLowerCase());
|
|
168
|
+
return canonicalKeywordToken(w);
|
|
168
169
|
}
|
|
169
170
|
/** 캐시 디렉터리(테스트·진단용) */
|
|
170
171
|
export function kiwiCacheDir() {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"kiwi-runtime.js","sourceRoot":"","sources":["../../src/kiwi-runtime.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,YAAY,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAC;AACjF,OAAO,EAAE,OAAO,EAAE,MAAM,SAAS,CAAC;AAClC,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAC/C,OAAO,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAC;AAEhD,OAAO,EAAE,WAAW,EAAE,KAAK,EAAmB,MAAM,UAAU,CAAC;AAE/D,MAAM,cAAc,GAAG,QAAQ,CAAC;AAChC,MAAM,SAAS,GAAG,sDAAsD,cAAc,gBAAgB,cAAc,WAAW,CAAC;AAChI,MAAM,WAAW,GAAG;IAClB,mBAAmB;IACnB,UAAU;IACV,cAAc;IACd,cAAc;IACd,aAAa;IACb,YAAY;IACZ,aAAa;IACb,UAAU;IACV,WAAW;CACH,CAAC;AAEX,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,EAAE,EAAE,QAAQ,EAAE,yBAAyB,EAAE,WAAW,CAAC,CAAC;AACrF,MAAM,SAAS,GAAG,IAAI,CAAC,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC;AAE7D,IAAI,WAAW,GAAgC,IAAI,CAAC;AACpD,IAAI,SAAS,GAAgB,IAAI,CAAC;AAClC,IAAI,UAAU,GAAG,KAAK,CAAC;AAEvB,SAAS,eAAe;IACtB,OAAO,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,uBAAuB,CAAC,CAAC,CAAC,CAAC;AAC9E,CAAC;AAED,SAAS,QAAQ;IACf,OAAO,IAAI,CAAC,eAAe,EAAE,EAAE,MAAM,EAAE,gBAAgB,CAAC,CAAC;AAC3D,CAAC;AAED,SAAS,gBAAgB;IACvB,MAAM,KAAK,GAAe,EAAE,CAAC;IAC7B,KAAK,MAAM,IAAI,IAAI,WAAW,EAAE,CAAC;QAC/B,MAAM,CAAC,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAChC,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,CAAC,CAAC,CAAC;IAChC,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,cAAc;IACrB,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;QAAE,OAAO,KAAK,CAAC;IACzC,OAAO,WAAW,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;AAClE,CAAC;AAED,KAAK,UAAU,oBAAoB,CAAC,OAAe;IACjD,SAAS,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACjD,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,SAAS,CAAC,CAAC;IACnC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CAAC,+BAA+B,GAAG,CAAC,MAAM,MAAM,SAAS,EAAE,CAAC,CAAC;IAC9E,CAAC;IACD,MAAM,QAAQ,CAAC,GAAG,CAAC,IAAI,EAAE,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC;AACvD,CAAC;AAED,SAAS,mBAAmB,CAAC,OAAe;IAC1C,SAAS,CAAC,UAAU,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC3C,MAAM,GAAG,GAAG,SAAS,CAAC,KAAK,EAAE,CAAC,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,UAAU,CAAC,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC;IACxF,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACrB,MAAM,IAAI,KAAK,CAAC,GAAG,CAAC,MAAM,IAAI,cAAc,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;IAC5D,CAAC;IACD,IAAI,CAAC,cAAc,EAAE,EAAE,CAAC;QACtB,MAAM,IAAI,KAAK,CAAC,wDAAwD,CAAC,CAAC;IAC5E,CAAC;AACH,CAAC;AAED,KAAK,UAAU,iBAAiB;IAC9B,IAAI,cAAc,EAAE;QAAE,OAAO;IAC7B,MAAM,OAAO,GAAG,IAAI,CAAC,UAAU,EAAE,cAAc,cAAc,WAAW,CAAC,CAAC;IAC1E,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,EAAE,CAAC;QACzB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,yCAAyC,CAAC,CAAC;QAChE,MAAM,oBAAoB,CAAC,OAAO,CAAC,CAAC;IACtC,CAAC;IACD,IAAI,CAAC,cAAc,EAAE,EAAE,CAAC;QACtB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC;QACjD,mBAAmB,CAAC,OAAO,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,KAAK,UAAU,SAAS;IACtB,MAAM,OAAO,GAAG,MAAM,WAAW,CAAC,MAAM,CAAC,QAAQ,EAAE,CAAC,CAAC;IACrD,OAAO,OAAO,CAAC,KAAK,CAAC;QACnB,UAAU,EAAE,gBAAgB,EAAE;QAC9B,SAAS,EAAE,MAAM;QACjB,kBAAkB,EAAE,IAAI;QACxB,eAAe,EAAE,IAAI;QACrB,YAAY,EAAE,IAAI;QAClB,aAAa,EAAE,IAAI;KACpB,CAAC,CAAC;AACL,CAAC;AAED,sCAAsC;AACtC,MAAM,CAAC,KAAK,UAAU,eAAe;IACnC,IAAI,OAAO,CAAC,GAAG,CAAC,WAAW,KAAK,GAAG,EAAE,CAAC;QACpC,UAAU,GAAG,IAAI,CAAC;QAClB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,IAAI,SAAS;QAAE,OAAO,SAAS,CAAC;IAChC,IAAI,UAAU;QAAE,OAAO,IAAI,CAAC;IAC5B,IAAI,CAAC,WAAW,EAAE,CAAC;QACjB,WAAW,GAAG,CAAC,KAAK,IAAI,EAAE;YACxB,IAAI,CAAC;gBACH,MAAM,iBAAiB,EAAE,CAAC;gBAC1B,SAAS,GAAG,MAAM,SAAS,EAAE,CAAC;gBAC9B,OAAO,SAAS,CAAC;YACnB,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,UAAU,GAAG,IAAI,CAAC;gBAClB,MAAM,GAAG,GAAG,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC7D,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,uCAAuC,GAAG,IAAI,CAAC,CAAC;gBACrE,OAAO,IAAI,CAAC;YACd,CAAC;QACH,CAAC,CAAC,EAAE,CAAC;IACP,CAAC;IACD,OAAO,WAAW,CAAC;AACrB,CAAC;AAED,MAAM,UAAU,cAAc;IAC5B,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,WAAW;IACzB,OAAO,SAAS,KAAK,IAAI,CAAC;AAC5B,CAAC;AAED,wBAAwB;AACxB,MAAM,cAAc,GAAG,GAAG,CAAC;AAE3B,MAAM,UAAU,iBAAiB,CAAC,IAAY;IAC5C,MAAM,IAAI,GAAG,SAAS,CAAC;IACvB,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IAErB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,GAAG,cAAc,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,cAAc,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;IAClF,MAAM,MAAM,GAAG,IAAI,CAAC,QAAQ,CAC1B,KAAK,EACL,KAAK,CAAC,cAAc;QAClB,KAAK,CAAC,GAAG;QACT,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,MAAM;QACZ,KAAK,CAAC,aAAa,EACrB,SAAS,EACT,SAAS,EACT,OAAO,CACR,CAAC;IAEF,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;QACvB,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,GAAG,CAAC;YAAE,SAAS;QACnC,MAAM,IAAI,GAAG,iBAAiB,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC;QACtC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAS;QACtC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QACf,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACjB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,GAAW;IAC/B,IAAI,GAAG,KAAK,IAAI,IAAI,GAAG,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC;IAC9C,IAAI,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC;QAAE,OAAO,IAAI,CAAC;IACtC,IAAI,GAAG,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC;IAC9B,IAAI,GAAG,KAAK,OAAO,IAAI,GAAG,KAAK,SAAS;QAAE,OAAO,IAAI,CAAC;IACtD,IAAI,GAAG,KAAK,WAAW;QAAE,OAAO,IAAI,CAAC;IACrC,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,iBAAiB,CAAC,GAAW;IACpC,IAAI,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAC;IACnB,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,CAAC,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IACtC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAC;IAC5B,IAAI,mBAAmB,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,CAAC,CAAC,WAAW,EAAE,CAAC;
|
|
1
|
+
{"version":3,"file":"kiwi-runtime.js","sourceRoot":"","sources":["../../src/kiwi-runtime.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,YAAY,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAC;AACjF,OAAO,EAAE,OAAO,EAAE,MAAM,SAAS,CAAC;AAClC,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAC/C,OAAO,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAC;AAEhD,OAAO,EAAE,WAAW,EAAE,KAAK,EAAmB,MAAM,UAAU,CAAC;AAC/D,OAAO,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAC;AAE/D,MAAM,cAAc,GAAG,QAAQ,CAAC;AAChC,MAAM,SAAS,GAAG,sDAAsD,cAAc,gBAAgB,cAAc,WAAW,CAAC;AAChI,MAAM,WAAW,GAAG;IAClB,mBAAmB;IACnB,UAAU;IACV,cAAc;IACd,cAAc;IACd,aAAa;IACb,YAAY;IACZ,aAAa;IACb,UAAU;IACV,WAAW;CACH,CAAC;AAEX,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,EAAE,EAAE,QAAQ,EAAE,yBAAyB,EAAE,WAAW,CAAC,CAAC;AACrF,MAAM,SAAS,GAAG,IAAI,CAAC,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC;AAE7D,IAAI,WAAW,GAAgC,IAAI,CAAC;AACpD,IAAI,SAAS,GAAgB,IAAI,CAAC;AAClC,IAAI,UAAU,GAAG,KAAK,CAAC;AAEvB,SAAS,eAAe;IACtB,OAAO,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,uBAAuB,CAAC,CAAC,CAAC,CAAC;AAC9E,CAAC;AAED,SAAS,QAAQ;IACf,OAAO,IAAI,CAAC,eAAe,EAAE,EAAE,MAAM,EAAE,gBAAgB,CAAC,CAAC;AAC3D,CAAC;AAED,SAAS,gBAAgB;IACvB,MAAM,KAAK,GAAe,EAAE,CAAC;IAC7B,KAAK,MAAM,IAAI,IAAI,WAAW,EAAE,CAAC;QAC/B,MAAM,CAAC,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;QAChC,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,CAAC,CAAC,CAAC;IAChC,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,cAAc;IACrB,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;QAAE,OAAO,KAAK,CAAC;IACzC,OAAO,WAAW,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;AAClE,CAAC;AAED,KAAK,UAAU,oBAAoB,CAAC,OAAe;IACjD,SAAS,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACjD,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,SAAS,CAAC,CAAC;IACnC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CAAC,+BAA+B,GAAG,CAAC,MAAM,MAAM,SAAS,EAAE,CAAC,CAAC;IAC9E,CAAC;IACD,MAAM,QAAQ,CAAC,GAAG,CAAC,IAAI,EAAE,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC;AACvD,CAAC;AAED,SAAS,mBAAmB,CAAC,OAAe;IAC1C,SAAS,CAAC,UAAU,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IAC3C,MAAM,GAAG,GAAG,SAAS,CAAC,KAAK,EAAE,CAAC,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,UAAU,CAAC,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC;IACxF,IAAI,GAAG,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACrB,MAAM,IAAI,KAAK,CAAC,GAAG,CAAC,MAAM,IAAI,cAAc,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;IAC5D,CAAC;IACD,IAAI,CAAC,cAAc,EAAE,EAAE,CAAC;QACtB,MAAM,IAAI,KAAK,CAAC,wDAAwD,CAAC,CAAC;IAC5E,CAAC;AACH,CAAC;AAED,KAAK,UAAU,iBAAiB;IAC9B,IAAI,cAAc,EAAE;QAAE,OAAO;IAC7B,MAAM,OAAO,GAAG,IAAI,CAAC,UAAU,EAAE,cAAc,cAAc,WAAW,CAAC,CAAC;IAC1E,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,EAAE,CAAC;QACzB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,yCAAyC,CAAC,CAAC;QAChE,MAAM,oBAAoB,CAAC,OAAO,CAAC,CAAC;IACtC,CAAC;IACD,IAAI,CAAC,cAAc,EAAE,EAAE,CAAC;QACtB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC;QACjD,mBAAmB,CAAC,OAAO,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED,KAAK,UAAU,SAAS;IACtB,MAAM,OAAO,GAAG,MAAM,WAAW,CAAC,MAAM,CAAC,QAAQ,EAAE,CAAC,CAAC;IACrD,OAAO,OAAO,CAAC,KAAK,CAAC;QACnB,UAAU,EAAE,gBAAgB,EAAE;QAC9B,SAAS,EAAE,MAAM;QACjB,kBAAkB,EAAE,IAAI;QACxB,eAAe,EAAE,IAAI;QACrB,YAAY,EAAE,IAAI;QAClB,aAAa,EAAE,IAAI;KACpB,CAAC,CAAC;AACL,CAAC;AAED,sCAAsC;AACtC,MAAM,CAAC,KAAK,UAAU,eAAe;IACnC,IAAI,OAAO,CAAC,GAAG,CAAC,WAAW,KAAK,GAAG,EAAE,CAAC;QACpC,UAAU,GAAG,IAAI,CAAC;QAClB,OAAO,IAAI,CAAC;IACd,CAAC;IACD,IAAI,SAAS;QAAE,OAAO,SAAS,CAAC;IAChC,IAAI,UAAU;QAAE,OAAO,IAAI,CAAC;IAC5B,IAAI,CAAC,WAAW,EAAE,CAAC;QACjB,WAAW,GAAG,CAAC,KAAK,IAAI,EAAE;YACxB,IAAI,CAAC;gBACH,MAAM,iBAAiB,EAAE,CAAC;gBAC1B,SAAS,GAAG,MAAM,SAAS,EAAE,CAAC;gBAC9B,OAAO,SAAS,CAAC;YACnB,CAAC;YAAC,OAAO,GAAG,EAAE,CAAC;gBACb,UAAU,GAAG,IAAI,CAAC;gBAClB,MAAM,GAAG,GAAG,GAAG,YAAY,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;gBAC7D,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,uCAAuC,GAAG,IAAI,CAAC,CAAC;gBACrE,OAAO,IAAI,CAAC;YACd,CAAC;QACH,CAAC,CAAC,EAAE,CAAC;IACP,CAAC;IACD,OAAO,WAAW,CAAC;AACrB,CAAC;AAED,MAAM,UAAU,cAAc;IAC5B,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,WAAW;IACzB,OAAO,SAAS,KAAK,IAAI,CAAC;AAC5B,CAAC;AAED,wBAAwB;AACxB,MAAM,cAAc,GAAG,GAAG,CAAC;AAE3B,MAAM,UAAU,iBAAiB,CAAC,IAAY;IAC5C,MAAM,IAAI,GAAG,SAAS,CAAC;IACvB,IAAI,CAAC,IAAI;QAAE,OAAO,EAAE,CAAC;IAErB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,GAAG,cAAc,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,cAAc,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;IAClF,MAAM,MAAM,GAAG,IAAI,CAAC,QAAQ,CAC1B,KAAK,EACL,KAAK,CAAC,cAAc;QAClB,KAAK,CAAC,GAAG;QACT,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,OAAO;QACb,KAAK,CAAC,MAAM;QACZ,KAAK,CAAC,aAAa,EACrB,SAAS,EACT,SAAS,EACT,OAAO,CACR,CAAC;IAEF,MAAM,GAAG,GAAa,EAAE,CAAC;IACzB,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;QACvB,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,GAAG,CAAC;YAAE,SAAS;QACnC,MAAM,IAAI,GAAG,iBAAiB,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC;QACtC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAS;QACtC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QACf,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACjB,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED,SAAS,YAAY,CAAC,GAAW;IAC/B,IAAI,GAAG,KAAK,IAAI,IAAI,GAAG,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC;IAC9C,IAAI,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC;QAAE,OAAO,IAAI,CAAC;IACtC,IAAI,GAAG,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC;IAC9B,IAAI,GAAG,KAAK,OAAO,IAAI,GAAG,KAAK,SAAS;QAAE,OAAO,IAAI,CAAC;IACtD,IAAI,GAAG,KAAK,WAAW;QAAE,OAAO,IAAI,CAAC;IACrC,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,iBAAiB,CAAC,GAAW;IACpC,IAAI,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAC;IACnB,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,CAAC,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IACtC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAC;IAC5B,IAAI,mBAAmB,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,qBAAqB,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC;IAC/E,OAAO,qBAAqB,CAAC,CAAC,CAAC,CAAC;AAClC,CAAC;AAED,uBAAuB;AACvB,MAAM,UAAU,YAAY;IAC1B,OAAO,UAAU,CAAC;AACpB,CAAC;AAED,MAAM,UAAU,wBAAwB;IACtC,SAAS,GAAG,IAAI,CAAC;IACjB,WAAW,GAAG,IAAI,CAAC;IACnB,UAAU,GAAG,KAAK,CAAC;AACrB,CAAC"}
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
let lastPrintedPct = -1;
|
|
2
|
+
let lastPhase = "";
|
|
3
|
+
export function logReportProgress(update) {
|
|
4
|
+
const { phase, current, total } = update;
|
|
5
|
+
if (total !== undefined && total > 0) {
|
|
6
|
+
const pct = Math.min(99, Math.round((current / total) * 100));
|
|
7
|
+
if (phase === lastPhase && pct === lastPrintedPct && current < total)
|
|
8
|
+
return;
|
|
9
|
+
lastPhase = phase;
|
|
10
|
+
lastPrintedPct = pct;
|
|
11
|
+
process.stderr.write(`[kca] ${phase} ${pct}% (${current.toLocaleString("ko-KR")}/${total.toLocaleString("ko-KR")}건)\n`);
|
|
12
|
+
if (current >= total)
|
|
13
|
+
lastPrintedPct = -1;
|
|
14
|
+
return;
|
|
15
|
+
}
|
|
16
|
+
lastPhase = phase;
|
|
17
|
+
lastPrintedPct = -1;
|
|
18
|
+
process.stderr.write(`[kca] ${phase}… ${current.toLocaleString("ko-KR")}\n`);
|
|
19
|
+
}
|
|
20
|
+
export function resetReportProgress() {
|
|
21
|
+
lastPrintedPct = -1;
|
|
22
|
+
lastPhase = "";
|
|
23
|
+
}
|
|
24
|
+
//# sourceMappingURL=report-progress.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"report-progress.js","sourceRoot":"","sources":["../../src/report-progress.ts"],"names":[],"mappings":"AAMA,IAAI,cAAc,GAAG,CAAC,CAAC,CAAC;AACxB,IAAI,SAAS,GAAG,EAAE,CAAC;AAEnB,MAAM,UAAU,iBAAiB,CAAC,MAA4B;IAC5D,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,GAAG,MAAM,CAAC;IACzC,IAAI,KAAK,KAAK,SAAS,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;QACrC,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,OAAO,GAAG,KAAK,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC;QAC9D,IAAI,KAAK,KAAK,SAAS,IAAI,GAAG,KAAK,cAAc,IAAI,OAAO,GAAG,KAAK;YAAE,OAAO;QAC7E,SAAS,GAAG,KAAK,CAAC;QAClB,cAAc,GAAG,GAAG,CAAC;QACrB,OAAO,CAAC,MAAM,CAAC,KAAK,CAClB,SAAS,KAAK,IAAI,GAAG,MAAM,OAAO,CAAC,cAAc,CAAC,OAAO,CAAC,IAAI,KAAK,CAAC,cAAc,CAAC,OAAO,CAAC,MAAM,CAClG,CAAC;QACF,IAAI,OAAO,IAAI,KAAK;YAAE,cAAc,GAAG,CAAC,CAAC,CAAC;QAC1C,OAAO;IACT,CAAC;IACD,SAAS,GAAG,KAAK,CAAC;IAClB,cAAc,GAAG,CAAC,CAAC,CAAC;IACpB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,SAAS,KAAK,KAAK,OAAO,CAAC,cAAc,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;AAC/E,CAAC;AAED,MAAM,UAAU,mBAAmB;IACjC,cAAc,GAAG,CAAC,CAAC,CAAC;IACpB,SAAS,GAAG,EAAE,CAAC;AACjB,CAAC"}
|
|
@@ -15,6 +15,8 @@ export type StreamParseEvent = {
|
|
|
15
15
|
record: ChatRecord;
|
|
16
16
|
};
|
|
17
17
|
export declare function streamKakaoExport(filePath: string, options?: StreamParseOptions): AsyncGenerator<StreamParseEvent>;
|
|
18
|
+
/** DATE 줄만 세어 메시지 건수 추정(진행률 %용, CSV 2회 읽기) */
|
|
19
|
+
export declare function estimateKakaoMessageCount(filePath: string): Promise<number>;
|
|
18
20
|
export declare function describeStreamedExport(filePath: string): Promise<{
|
|
19
21
|
text: string;
|
|
20
22
|
warnings: ParseWarning[];
|
|
@@ -82,6 +82,24 @@ export async function* streamKakaoExport(filePath, options) {
|
|
|
82
82
|
},
|
|
83
83
|
};
|
|
84
84
|
}
|
|
85
|
+
/** DATE 줄만 세어 메시지 건수 추정(진행률 %용, CSV 2회 읽기) */
|
|
86
|
+
export async function estimateKakaoMessageCount(filePath) {
|
|
87
|
+
const sample = await readFileSample(filePath, SAMPLE_BYTES);
|
|
88
|
+
const { encoding, skipBytes } = detectEncodingFromBytes(sample);
|
|
89
|
+
const input = openDecodedStream(filePath, encoding, skipBytes, READ_HIGH_WATER_MARK);
|
|
90
|
+
const rl = createInterface({ input, crlfDelay: Infinity });
|
|
91
|
+
let lineNumber = 0;
|
|
92
|
+
let count = 0;
|
|
93
|
+
for await (const rawLine of rl) {
|
|
94
|
+
lineNumber += 1;
|
|
95
|
+
const line = rawLine.replace(/\r$/, "");
|
|
96
|
+
if (lineNumber === 1)
|
|
97
|
+
continue;
|
|
98
|
+
if (DATE_LINE_RE.test(line))
|
|
99
|
+
count += 1;
|
|
100
|
+
}
|
|
101
|
+
return count;
|
|
102
|
+
}
|
|
85
103
|
export async function describeStreamedExport(filePath) {
|
|
86
104
|
let messages = 0;
|
|
87
105
|
let multiline = 0;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"stream-parser.js","sourceRoot":"","sources":["../../src/stream-parser.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AACrC,OAAO,EAAE,eAAe,EAAE,MAAM,eAAe,CAAC;AAChD,OAAO,EAAE,uBAAuB,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AAC3E,OAAO,EAAE,YAAY,EAAE,eAAe,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AAIlF,MAAM,YAAY,GAAG,GAAG,GAAG,IAAI,CAAC;AAChC,MAAM,oBAAoB,GAAG,IAAI,GAAG,IAAI,CAAC;AAsBzC,SAAS,YAAY,CAAC,OAAsB;IAC1C,OAAO;QACL,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,OAAO,EAAE,OAAO,CAAC,KAAK,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC;KACnF,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,iBAAiB,CACtC,QAAgB,EAChB,OAA4B;IAE5B,MAAM,MAAM,GAAG,MAAM,cAAc,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAC;IAC5D,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,GAAG,uBAAuB,CAAC,MAAM,CAAC,CAAC;IAEhE,MAAM,QAAQ,GAAmB,EAAE,CAAC;IACpC,MAAM,KAAK,GAAG,iBAAiB,CAAC,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,oBAAoB,CAAC,CAAC;IACrF,MAAM,EAAE,GAAG,eAAe,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,CAAC,CAAC;IAE3D,IAAI,UAAU,GAAG,CAAC,CAAC;IACnB,IAAI,MAAM,GAAa,EAAE,CAAC;IAC1B,IAAI,OAAO,GAAyB,IAAI,CAAC;IACzC,IAAI,aAAa,GAAG,CAAC,CAAC;IACtB,IAAI,WAAW,GAAG,CAAC,CAAC;IACpB,MAAM,aAAa,GAAG,OAAO,EAAE,aAAa,IAAI,MAAM,CAAC;IAEvD,IAAI,KAAK,EAAE,MAAM,OAAO,IAAI,EAAE,EAAE,CAAC;QAC/B,UAAU,IAAI,CAAC,CAAC;QAChB,aAAa,IAAI,CAAC,CAAC;QACnB,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;QAExC,IAAI,UAAU,KAAK,CAAC,EAAE,CAAC;YACrB,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC;gBACjB,MAAM,IAAI,KAAK,CAAC,2BAA2B,QAAQ,EAAE,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,GAAG,eAAe,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;YACzC,SAAS;QACX,CAAC;QAED,IAAI,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAC5B,IAAI,OAAO,EAAE,CAAC;gBACZ,WAAW,IAAI,CAAC,CAAC;gBACjB,IAAI,OAAO,EAAE,UAAU,IAAI,WAAW,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;oBAC7D,OAAO,CAAC,UAAU,CAAC,WAAW,CAAC,CAAC;gBAClC,CAAC;gBACD,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,YAAY,CAAC,OAAO,CAAC,EAAE,CAAC;gBACxD,OAAO,GAAG,IAAI,CAAC;YACjB,CAAC;YACD,MAAM,OAAO,GAAG,gBAAgB,CAAC,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC;YAC7D,OAAO,GAAG;gBACR,IAAI,EAAE,OAAO,CAAC,IAAI;gBAClB,OAAO,EAAE,OAAO,CAAC,OAAO;gBACxB,IAAI,EAAE,OAAO,CAAC,IAAI;gBAClB,MAAM,EAAE,OAAO,CAAC,MAAM;gBACtB,KAAK,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC;aACzB,CAAC;YACF,SAAS;QACX,CAAC;QAED,IAAI,CAAC,OAAO,EAAE,CAAC;YACb,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC3B,QAAQ,CAAC,IAAI,CAAC;oBACZ,IAAI,EAAE,UAAU;oBAChB,IAAI,EAAE,6BAA6B;oBACnC,OAAO,EAAE,2DAA2D;iBACrE,CAAC,CAAC;YACL,CAAC;YACD,SAAS;QACX,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC3B,CAAC;IAED,IAAI,OAAO,EAAE,CAAC;QACZ,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,YAAY,CAAC,OAAO,CAAC,EAAE,CAAC;IAC1D,CAAC;IAED,MAAM;QACJ,IAAI,EAAE,MAAM;QACZ,IAAI,EAAE;YACJ,QAAQ;YACR,QAAQ;YACR,aAAa;YACb,QAAQ;YACR,MAAM;SACP;KACF,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,sBAAsB,CAAC,QAAgB;IAI3D,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,MAAM,YAAY,GAAG,IAAI,GAAG,EAAU,CAAC;IACvC,IAAI,KAAK,GAAkB,IAAI,CAAC;IAChC,IAAI,IAAI,GAAkB,IAAI,CAAC;IAC/B,IAAI,IAAI,GAA2B,IAAI,CAAC;IAExC,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,iBAAiB,CAAC,QAAQ,CAAC,EAAE,CAAC;QACtD,IAAI,KAAK,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YAC1B,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC;YAClB,SAAS;QACX,CAAC;QACD,QAAQ,IAAI,CAAC,CAAC;QACd,IAAI,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC;YAAE,SAAS,IAAI,CAAC,CAAC;QACxD,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;QACtC,IAAI,CAAC,KAAK;YAAE,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC;QACzC,IAAI,GAAG,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC;IAC9B,CAAC;IAED,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,+BAA+B,QAAQ,EAAE,CAAC,CAAC;IAC7D,CAAC;IAED,MAAM,IAAI,GAAG;QACX,SAAS,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE;QAClC,aAAa,IAAI,CAAC,QAAQ,EAAE;QAC5B,WAAW,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE;QAClC,mBAAmB,IAAI,CAAC,aAAa,EAAE;QACvC,aAAa,QAAQ,EAAE;QACvB,iBAAiB,YAAY,CAAC,IAAI,EAAE;QACpC,UAAU,KAAK,IAAI,QAAQ,OAAO,IAAI,IAAI,QAAQ,EAAE;QACpD,uBAAuB,SAAS,EAAE;QAClC,aAAa,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE;KACpC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAEb,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,CAAC,QAAQ,EAAE,CAAC;AAC3C,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,QAAgB,EAAE,QAAgB;IAC9D,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACzC,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;QACnC,MAAM,EAAE,SAAS,EAAE,GAAG,MAAM,MAAM,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,CAAC,CAAC;QAC7D,OAAO,GAAG,CAAC,QAAQ,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC;IACpC,CAAC;YAAS,CAAC;QACT,MAAM,MAAM,CAAC,KAAK,EAAE,CAAC;IACvB,CAAC;AACH,CAAC"}
|
|
1
|
+
{"version":3,"file":"stream-parser.js","sourceRoot":"","sources":["../../src/stream-parser.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AACrC,OAAO,EAAE,eAAe,EAAE,MAAM,eAAe,CAAC;AAChD,OAAO,EAAE,uBAAuB,EAAE,iBAAiB,EAAE,MAAM,eAAe,CAAC;AAC3E,OAAO,EAAE,YAAY,EAAE,eAAe,EAAE,gBAAgB,EAAE,MAAM,iBAAiB,CAAC;AAIlF,MAAM,YAAY,GAAG,GAAG,GAAG,IAAI,CAAC;AAChC,MAAM,oBAAoB,GAAG,IAAI,GAAG,IAAI,CAAC;AAsBzC,SAAS,YAAY,CAAC,OAAsB;IAC1C,OAAO;QACL,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,OAAO,EAAE,OAAO,CAAC,KAAK,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC;KACnF,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,iBAAiB,CACtC,QAAgB,EAChB,OAA4B;IAE5B,MAAM,MAAM,GAAG,MAAM,cAAc,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAC;IAC5D,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,GAAG,uBAAuB,CAAC,MAAM,CAAC,CAAC;IAEhE,MAAM,QAAQ,GAAmB,EAAE,CAAC;IACpC,MAAM,KAAK,GAAG,iBAAiB,CAAC,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,oBAAoB,CAAC,CAAC;IACrF,MAAM,EAAE,GAAG,eAAe,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,CAAC,CAAC;IAE3D,IAAI,UAAU,GAAG,CAAC,CAAC;IACnB,IAAI,MAAM,GAAa,EAAE,CAAC;IAC1B,IAAI,OAAO,GAAyB,IAAI,CAAC;IACzC,IAAI,aAAa,GAAG,CAAC,CAAC;IACtB,IAAI,WAAW,GAAG,CAAC,CAAC;IACpB,MAAM,aAAa,GAAG,OAAO,EAAE,aAAa,IAAI,MAAM,CAAC;IAEvD,IAAI,KAAK,EAAE,MAAM,OAAO,IAAI,EAAE,EAAE,CAAC;QAC/B,UAAU,IAAI,CAAC,CAAC;QAChB,aAAa,IAAI,CAAC,CAAC;QACnB,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;QAExC,IAAI,UAAU,KAAK,CAAC,EAAE,CAAC;YACrB,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC;gBACjB,MAAM,IAAI,KAAK,CAAC,2BAA2B,QAAQ,EAAE,CAAC,CAAC;YACzD,CAAC;YACD,MAAM,GAAG,eAAe,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;YACzC,SAAS;QACX,CAAC;QAED,IAAI,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAC5B,IAAI,OAAO,EAAE,CAAC;gBACZ,WAAW,IAAI,CAAC,CAAC;gBACjB,IAAI,OAAO,EAAE,UAAU,IAAI,WAAW,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;oBAC7D,OAAO,CAAC,UAAU,CAAC,WAAW,CAAC,CAAC;gBAClC,CAAC;gBACD,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,YAAY,CAAC,OAAO,CAAC,EAAE,CAAC;gBACxD,OAAO,GAAG,IAAI,CAAC;YACjB,CAAC;YACD,MAAM,OAAO,GAAG,gBAAgB,CAAC,IAAI,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC;YAC7D,OAAO,GAAG;gBACR,IAAI,EAAE,OAAO,CAAC,IAAI;gBAClB,OAAO,EAAE,OAAO,CAAC,OAAO;gBACxB,IAAI,EAAE,OAAO,CAAC,IAAI;gBAClB,MAAM,EAAE,OAAO,CAAC,MAAM;gBACtB,KAAK,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC;aACzB,CAAC;YACF,SAAS;QACX,CAAC;QAED,IAAI,CAAC,OAAO,EAAE,CAAC;YACb,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC3B,QAAQ,CAAC,IAAI,CAAC;oBACZ,IAAI,EAAE,UAAU;oBAChB,IAAI,EAAE,6BAA6B;oBACnC,OAAO,EAAE,2DAA2D;iBACrE,CAAC,CAAC;YACL,CAAC;YACD,SAAS;QACX,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC3B,CAAC;IAED,IAAI,OAAO,EAAE,CAAC;QACZ,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,YAAY,CAAC,OAAO,CAAC,EAAE,CAAC;IAC1D,CAAC;IAED,MAAM;QACJ,IAAI,EAAE,MAAM;QACZ,IAAI,EAAE;YACJ,QAAQ;YACR,QAAQ;YACR,aAAa;YACb,QAAQ;YACR,MAAM;SACP;KACF,CAAC;AACJ,CAAC;AAED,8CAA8C;AAC9C,MAAM,CAAC,KAAK,UAAU,yBAAyB,CAAC,QAAgB;IAC9D,MAAM,MAAM,GAAG,MAAM,cAAc,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAC;IAC5D,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,GAAG,uBAAuB,CAAC,MAAM,CAAC,CAAC;IAChE,MAAM,KAAK,GAAG,iBAAiB,CAAC,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,oBAAoB,CAAC,CAAC;IACrF,MAAM,EAAE,GAAG,eAAe,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,QAAQ,EAAE,CAAC,CAAC;IAC3D,IAAI,UAAU,GAAG,CAAC,CAAC;IACnB,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,KAAK,EAAE,MAAM,OAAO,IAAI,EAAE,EAAE,CAAC;QAC/B,UAAU,IAAI,CAAC,CAAC;QAChB,MAAM,IAAI,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;QACxC,IAAI,UAAU,KAAK,CAAC;YAAE,SAAS;QAC/B,IAAI,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC;YAAE,KAAK,IAAI,CAAC,CAAC;IAC1C,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,sBAAsB,CAAC,QAAgB;IAI3D,IAAI,QAAQ,GAAG,CAAC,CAAC;IACjB,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,MAAM,YAAY,GAAG,IAAI,GAAG,EAAU,CAAC;IACvC,IAAI,KAAK,GAAkB,IAAI,CAAC;IAChC,IAAI,IAAI,GAAkB,IAAI,CAAC;IAC/B,IAAI,IAAI,GAA2B,IAAI,CAAC;IAExC,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,iBAAiB,CAAC,QAAQ,CAAC,EAAE,CAAC;QACtD,IAAI,KAAK,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YAC1B,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC;YAClB,SAAS;QACX,CAAC;QACD,QAAQ,IAAI,CAAC,CAAC;QACd,IAAI,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC;YAAE,SAAS,IAAI,CAAC,CAAC;QACxD,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;QACtC,IAAI,CAAC,KAAK;YAAE,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC;QACzC,IAAI,GAAG,KAAK,CAAC,MAAM,CAAC,OAAO,CAAC;IAC9B,CAAC;IAED,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,+BAA+B,QAAQ,EAAE,CAAC,CAAC;IAC7D,CAAC;IAED,MAAM,IAAI,GAAG;QACX,SAAS,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE;QAClC,aAAa,IAAI,CAAC,QAAQ,EAAE;QAC5B,WAAW,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE;QAClC,mBAAmB,IAAI,CAAC,aAAa,EAAE;QACvC,aAAa,QAAQ,EAAE;QACvB,iBAAiB,YAAY,CAAC,IAAI,EAAE;QACpC,UAAU,KAAK,IAAI,QAAQ,OAAO,IAAI,IAAI,QAAQ,EAAE;QACpD,uBAAuB,SAAS,EAAE;QAClC,aAAa,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE;KACpC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAEb,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,CAAC,QAAQ,EAAE,CAAC;AAC3C,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,QAAgB,EAAE,QAAgB;IAC9D,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACzC,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;QACnC,MAAM,EAAE,SAAS,EAAE,GAAG,MAAM,MAAM,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,CAAC,CAAC;QAC7D,OAAO,GAAG,CAAC,QAAQ,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC;IACpC,CAAC;YAAS,CAAC;QACT,MAAM,MAAM,CAAC,KAAK,EAAE,CAAC;IACvB,CAAC;AACH,CAAC"}
|
|
@@ -56,29 +56,6 @@ function passesFilters(label, df, minDf, stop) {
|
|
|
56
56
|
}
|
|
57
57
|
return true;
|
|
58
58
|
}
|
|
59
|
-
function demoteSubsumedByPhrases(items) {
|
|
60
|
-
const phrases = items.filter((i) => i.label.includes(" "));
|
|
61
|
-
if (phrases.length === 0)
|
|
62
|
-
return items;
|
|
63
|
-
const parts = new Set();
|
|
64
|
-
for (const p of phrases) {
|
|
65
|
-
for (const w of p.label.split(" "))
|
|
66
|
-
parts.add(w);
|
|
67
|
-
}
|
|
68
|
-
const phraseScore = new Map(phrases.map((p) => [p.label, p.score]));
|
|
69
|
-
return items.filter((item) => {
|
|
70
|
-
if (item.label.includes(" ") || !parts.has(item.label))
|
|
71
|
-
return true;
|
|
72
|
-
for (const ph of phrases) {
|
|
73
|
-
if (!ph.label.split(" ").includes(item.label))
|
|
74
|
-
continue;
|
|
75
|
-
const ps = phraseScore.get(ph.label) ?? 0;
|
|
76
|
-
if (ps >= item.score * 0.82)
|
|
77
|
-
return false;
|
|
78
|
-
}
|
|
79
|
-
return true;
|
|
80
|
-
});
|
|
81
|
-
}
|
|
82
59
|
/** 메시지 스트림 → TF-IDF 어절·2-gram 키워드 */
|
|
83
60
|
export class StreamingTfidfKeywords {
|
|
84
61
|
tokenize;
|
|
@@ -141,11 +118,12 @@ export class StreamingTfidfKeywords {
|
|
|
141
118
|
const base = tfidfScore(tf, df, N) * BIGRAM_SCORE_BOOST * pmiMultiplier(label, df, N, this.docFreq);
|
|
142
119
|
items.push({ label, score: base, messageHits: df });
|
|
143
120
|
}
|
|
144
|
-
|
|
121
|
+
return items
|
|
122
|
+
.sort((a, b) => b.score - a.score ||
|
|
145
123
|
b.messageHits - a.messageHits ||
|
|
146
124
|
b.label.length - a.label.length ||
|
|
147
|
-
a.label.localeCompare(b.label))
|
|
148
|
-
|
|
125
|
+
a.label.localeCompare(b.label))
|
|
126
|
+
.slice(0, limit);
|
|
149
127
|
}
|
|
150
128
|
prunePair(dfMap, tfMap, keep) {
|
|
151
129
|
const kept = [...dfMap.entries()]
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"streaming-tfidf-keywords.js","sourceRoot":"","sources":["../../src/streaming-tfidf-keywords.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EACL,gBAAgB,GAGjB,MAAM,mBAAmB,CAAC;AAE3B,MAAM,gBAAgB,GAAG,MAAM,CAAC;AAChC,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,gBAAgB,GAAG,MAAM,CAAC;AAChC,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,kBAAkB,GAAG,IAAI,CAAC;AAEhC,OAAO,EAAE,gBAAgB,EAAoD,CAAC;AAE9E,SAAS,aAAa,CAAC,CAAS,EAAE,CAAS;IACzC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,KAAK,CAAC;IAC/C,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,GAAG,EAAE;QAAE,OAAO,KAAK,CAAC;IAC3C,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,KAAK,CAAC;IACrD,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,UAAU,CAAC,EAAU,EAAE,EAAU,EAAE,cAAsB;IAChE,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,cAAc,GAAG,CAAC,CAAC,GAAG,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC;AACtE,CAAC;AAED,SAAS,aAAa,CAAC,KAAa,EAAE,EAAU,EAAE,CAAS,EAAE,OAA4B;IACvF,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IACnC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAC/B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,CAAC,CAAC;IACjC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,KAAK,CAAC;IACrB,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC;IACjC,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC;IACjC,IAAI,GAAG,GAAG,CAAC,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IAC3C,MAAM,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC;IACnB,MAAM,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;IACnB,MAAM,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;IACnB,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,GAAG,CAAC,EAAE,GAAG,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC;IAC/C,IAAI,GAAG,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IACtB,OAAO,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,aAAa,CACpB,KAAa,EACb,EAAU,EACV,KAAa,EACb,IAAqC;IAErC,IAAI,EAAE,GAAG,KAAK;QAAE,OAAO,KAAK,CAAC;IAC7B,IAAI,IAAI,EAAE,GAAG,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACnC,IAAI,cAAc,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACxC,IAAI,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QACxB,KAAK,MAAM,IAAI,IAAI,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;YACpC,IAAI,IAAI,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,cAAc,CAAC,IAAI,CAAC;gBAAE,OAAO,KAAK,CAAC;QAC5D,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;
|
|
1
|
+
{"version":3,"file":"streaming-tfidf-keywords.js","sourceRoot":"","sources":["../../src/streaming-tfidf-keywords.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EACL,gBAAgB,GAGjB,MAAM,mBAAmB,CAAC;AAE3B,MAAM,gBAAgB,GAAG,MAAM,CAAC;AAChC,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,gBAAgB,GAAG,MAAM,CAAC;AAChC,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,kBAAkB,GAAG,IAAI,CAAC;AAEhC,OAAO,EAAE,gBAAgB,EAAoD,CAAC;AAE9E,SAAS,aAAa,CAAC,CAAS,EAAE,CAAS;IACzC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,KAAK,CAAC;IAC/C,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,GAAG,EAAE;QAAE,OAAO,KAAK,CAAC;IAC3C,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC;QAAE,OAAO,KAAK,CAAC;IACrD,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,UAAU,CAAC,EAAU,EAAE,EAAU,EAAE,cAAsB;IAChE,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,cAAc,GAAG,CAAC,CAAC,GAAG,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC;AACtE,CAAC;AAED,SAAS,aAAa,CAAC,KAAa,EAAE,EAAU,EAAE,CAAS,EAAE,OAA4B;IACvF,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IACnC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAC/B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,CAAC,CAAC;IACjC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,KAAK,CAAC;IACrB,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC;IACjC,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC;IACjC,IAAI,GAAG,GAAG,CAAC,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IAC3C,MAAM,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC;IACnB,MAAM,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;IACnB,MAAM,EAAE,GAAG,GAAG,GAAG,CAAC,CAAC;IACnB,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,GAAG,CAAC,EAAE,GAAG,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC;IAC/C,IAAI,GAAG,GAAG,CAAC;QAAE,OAAO,CAAC,CAAC;IACtB,OAAO,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,aAAa,CACpB,KAAa,EACb,EAAU,EACV,KAAa,EACb,IAAqC;IAErC,IAAI,EAAE,GAAG,KAAK;QAAE,OAAO,KAAK,CAAC;IAC7B,IAAI,IAAI,EAAE,GAAG,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACnC,IAAI,cAAc,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACxC,IAAI,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QACxB,KAAK,MAAM,IAAI,IAAI,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;YACpC,IAAI,IAAI,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,cAAc,CAAC,IAAI,CAAC;gBAAE,OAAO,KAAK,CAAC;QAC5D,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAID,qCAAqC;AACrC,MAAM,OAAO,sBAAsB;IAChB,QAAQ,CAAoB;IACrC,SAAS,GAAG,CAAC,CAAC;IACL,QAAQ,GAAG,IAAI,GAAG,EAAkB,CAAC;IACrC,OAAO,GAAG,IAAI,GAAG,EAAkB,CAAC;IACpC,QAAQ,GAAG,IAAI,GAAG,EAAkB,CAAC;IACrC,QAAQ,GAAG,IAAI,GAAG,EAAkB,CAAC;IAEtD,YAAY,WAA8B,mBAAmB;QAC3D,IAAI,CAAC,QAAQ,GAAG,QAAQ,CAAC;IAC3B,CAAC;IAED,WAAW,CAAC,GAAW;QACrB,MAAM,MAAM,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC;QAClC,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO;QAChC,IAAI,CAAC,SAAS,IAAI,CAAC,CAAC;QAEpB,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;QAC/B,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;YACtD,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;gBACjB,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;gBACpD,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACd,CAAC;QACH,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,GAAG,EAAU,CAAC;QACjC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,CAAE,CAAC;YACrB,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,CAAC;YACzB,IAAI,CAAC,aAAa,CAAC,CAAC,EAAE,CAAC,CAAC;gBAAE,SAAS;YACnC,MAAM,EAAE,GAAG,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;YACvB,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;YACxD,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;gBACpB,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;gBACxD,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;YACjB,CAAC;QACH,CAAC;QAED,IAAI,IAAI,CAAC,OAAO,CAAC,IAAI,GAAG,gBAAgB;YAAE,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,OAAO,EAAE,IAAI,CAAC,QAAQ,EAAE,gBAAgB,CAAC,CAAC;QACxG,IAAI,IAAI,CAAC,QAAQ,CAAC,IAAI,GAAG,eAAe;YAAE,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,QAAQ,EAAE,IAAI,CAAC,QAAQ,EAAE,eAAe,CAAC,CAAC;IAC1G,CAAC;IAED,mBAAmB,CAAC,UAAiC,EAAE;QACrD,MAAM,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC;QACtC,MAAM,KAAK,GAAG,OAAO,CAAC,UAAU,IAAI,gBAAgB,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACrE,MAAM,WAAW,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,GAAG,CAAC,CAAC,CAAC;QAC3C,MAAM,IAAI,GAAG,OAAO,CAAC,SAAS,CAAC;QAC/B,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,IAAI,GAAG,CAAC;QACnC,MAAM,KAAK,GAAsB,EAAE,CAAC;QAEpC,KAAK,MAAM,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YACvC,IAAI,CAAC,aAAa,CAAC,KAAK,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC;gBAAE,SAAS;YACrD,MAAM,EAAE,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YACzC,KAAK,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,UAAU,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAC,CAAC;QACvE,CAAC;QAED,KAAK,MAAM,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;YACxC,IAAI,CAAC,aAAa,CAAC,KAAK,EAAE,EAAE,EAAE,WAAW,EAAE,IAAI,CAAC;gBAAE,SAAS;YAC3D,MAAM,EAAE,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YACzC,MAAM,IAAI,GAAG,UAAU,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,GAAG,kBAAkB,GAAG,aAAa,CAAC,KAAK,EAAE,EAAE,EAAE,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;YACpG,KAAK,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,WAAW,EAAE,EAAE,EAAE,CAAC,CAAC;QACtD,CAAC;QAED,OAAO,KAAK;aACT,IAAI,CACH,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACP,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK;YACjB,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,WAAW;YAC7B,CAAC,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,KAAK,CAAC,MAAM;YAC/B,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CACjC;aACA,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;IACrB,CAAC;IAEO,SAAS,CAAC,KAA0B,EAAE,KAA0B,EAAE,IAAY;QACpF,MAAM,IAAI,GAAG,CAAC,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC;aAC9B,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;aACxD,KAAK,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC;QAClB,MAAM,OAAO,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QAC9C,KAAK,CAAC,KAAK,EAAE,CAAC;QACd,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,IAAI;YAAE,KAAK,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;QAC3C,KAAK,MAAM,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;YAClC,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC;gBAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC;QACvC,CAAC;IACH,CAAC;CACF"}
|
package/dist/src/version.d.ts
CHANGED
|
@@ -1,2 +1,2 @@
|
|
|
1
|
-
export declare const VERSION = "0.4.
|
|
2
|
-
export declare const USER_AGENT = "kakaotalk-chat-analyzer/0.4.
|
|
1
|
+
export declare const VERSION = "0.4.2";
|
|
2
|
+
export declare const USER_AGENT = "kakaotalk-chat-analyzer/0.4.2";
|
package/dist/src/version.js
CHANGED
package/package.json
CHANGED