kordoc 2.8.0 → 2.9.0

package/dist/index.d.cts

@@ -164,6 +164,34 @@ interface ParseSuccess extends ParseResultBase {
     warnings?: ParseWarning[];
     /** 추출된 이미지 목록 — 마크다운에서 파일명으로 참조됨 */
     images?: ExtractedImage[];
+    /** 페이지별 텍스트 품질 신호 — PDF에서만 제공 */
+    pageQuality?: PageQuality[];
+    /** 문서 단위 품질 요약 — PDF에서만 제공 */
+    qualitySummary?: DocumentQualitySummary;
+}
+/** 페이지별 텍스트 품질 신호 (PDF 전용). 자세한 설명은 src/pdf/quality.ts */
+interface PageQuality {
+    page: number;
+    textChars: number;
+    hangulRatio: number;
+    controlCharRatio: number;
+    replacementCharRatio: number;
+    puaRatio: number;
+    needsOcr: boolean;
+    ocrReason?: "low_text" | "high_pua" | "high_control" | "high_replacement";
+}
+/** 문서 단위 품질 요약 (PDF 전용). */
+interface DocumentQualitySummary {
+    totalPages: number;
+    totalTextChars: number;
+    avgHangulRatio: number;
+    avgControlCharRatio: number;
+    avgReplacementCharRatio: number;
+    avgPuaRatio: number;
+    lowTextPageCount: number;
+    highPuaPageCount: number;
+    needsOcr: boolean;
+    ocrCandidatePages: number[];
 }
 /** 추출된 이미지 — ParseSuccess.images에 포함 */
 interface ExtractedImage {

package/dist/index.d.ts

@@ -164,6 +164,34 @@ interface ParseSuccess extends ParseResultBase {
     warnings?: ParseWarning[];
     /** 추출된 이미지 목록 — 마크다운에서 파일명으로 참조됨 */
     images?: ExtractedImage[];
+    /** 페이지별 텍스트 품질 신호 — PDF에서만 제공 */
+    pageQuality?: PageQuality[];
+    /** 문서 단위 품질 요약 — PDF에서만 제공 */
+    qualitySummary?: DocumentQualitySummary;
+}
+/** 페이지별 텍스트 품질 신호 (PDF 전용). 자세한 설명은 src/pdf/quality.ts */
+interface PageQuality {
+    page: number;
+    textChars: number;
+    hangulRatio: number;
+    controlCharRatio: number;
+    replacementCharRatio: number;
+    puaRatio: number;
+    needsOcr: boolean;
+    ocrReason?: "low_text" | "high_pua" | "high_control" | "high_replacement";
+}
+/** 문서 단위 품질 요약 (PDF 전용). */
+interface DocumentQualitySummary {
+    totalPages: number;
+    totalTextChars: number;
+    avgHangulRatio: number;
+    avgControlCharRatio: number;
+    avgReplacementCharRatio: number;
+    avgPuaRatio: number;
+    lowTextPageCount: number;
+    highPuaPageCount: number;
+    needsOcr: boolean;
+    ocrCandidatePages: number[];
 }
 /** 추출된 이미지 — ParseSuccess.images에 포함 */
 interface ExtractedImage {

package/dist/index.js

@@ -16,7 +16,7 @@ import {
   sanitizeHref,
   stripDtd,
   toArrayBuffer
-} from "./chunk-DLQY6FJH.js";
+} from "./chunk-RXZLTACX.js";
 import {
   parsePageRange
 } from "./chunk-SBVRCJFH.js";
@@ -19281,7 +19281,7 @@ async function parseHwp(buffer, options) {
 async function parsePdf(buffer, options) {
   let parsePdfDocument;
   try {
-    const mod = await import("./parser-ZQQM6J7T.js");
+    const mod = await import("./parser-OMPBVEFU.js");
     parsePdfDocument = mod.parsePdfDocument;
   } catch {
     return {
@@ -19292,8 +19292,8 @@ async function parsePdf(buffer, options) {
     };
   }
   try {
-    const { markdown, blocks, metadata, outline, warnings, isImageBased } = await parsePdfDocument(buffer, options);
-    return { success: true, fileType: "pdf", markdown, blocks, metadata, outline, warnings, isImageBased };
+    const { markdown, blocks, metadata, outline, warnings, isImageBased, pageQuality, qualitySummary } = await parsePdfDocument(buffer, options);
+    return { success: true, fileType: "pdf", markdown, blocks, metadata, outline, warnings, isImageBased, pageQuality, qualitySummary };
   } catch (err) {
     const isImageBased = err instanceof Error && "isImageBased" in err ? true : void 0;
     return { success: false, fileType: "pdf", error: err instanceof Error ? err.message : "PDF \uD30C\uC2F1 \uC2E4\uD328", code: classifyError(err), isImageBased };