feat: OCR, STT 기능 개선 및 버그 수정

.gitmodules

@@ -1,4 +1,4 @@
 [submodule "Team29_BE_Submodule"]
     path = Team29_BE_Submodule
     url = [email protected]:29ana-notai/Team29_BE_Submodule.git
-    branch = release/0.0.2
+    branch = release/0.0.3

build.gradle

@@ -5,7 +5,7 @@ plugins {
 }
 
 group = 'notai'
-version = '0.0.2'
+version = '0.0.3'
 
 java {
     toolchain {

src/main/java/notai/annotation/presentation/AnnotationController.java

@@ -76,6 +76,6 @@ public ResponseEntity<Void> deleteAnnotation(
     ) {
 
         annotationService.deleteAnnotation(documentId, annotationId);
-        return new ResponseEntity<>(HttpStatus.NO_CONTENT);
+        return new ResponseEntity<>(HttpStatus.OK);
     }
 }

src/main/java/notai/annotation/presentation/request/CreateAnnotationRequest.java

@@ -1,29 +1,29 @@
 package notai.annotation.presentation.request;
 
-import jakarta.validation.constraints.Max;
 import jakarta.validation.constraints.Positive;
 import jakarta.validation.constraints.PositiveOrZero;
 
 public record CreateAnnotationRequest(
 
-        @Positive(message = "페이지 번호는 양수여야 합니다.")
+        @PositiveOrZero(message = "페이지 번호는 0 이상이어야 합니다.")
         int pageNumber,
 
-//        @Max(value = ?, message = "x 좌표는 최대 ? 이하여야 합니다.")
+        // @Max(value = ?, message = "x 좌표는 최대 ? 이하여야 합니다.")
         @PositiveOrZero(message = "x 좌표는 0 이상이어야 합니다.")
         int x,
 
-//        @Max(value = ?, message = "x 좌표는 최대 ? 이하여야 합니다.")
+        // @Max(value = ?, message = "x 좌표는 최대 ? 이하여야 합니다.")
         @PositiveOrZero(message = "y 좌표는 0 이상이어야 합니다.")
         int y,
 
-//        @Max(value = ?, message = "width는 최대 ? 이하여야 합니다.")
+        // @Max(value = ?, message = "width는 최대 ? 이하여야 합니다.")
         @Positive(message = "width는 양수여야 합니다.")
         int width,
 
-//        @Max(value = ?, message = "height는 최대 ? 이하여야 합니다.")
+        // @Max(value = ?, message = "height는 최대 ? 이하여야 합니다.")
         @Positive(message = "height는 양수여야 합니다.")
         int height,
 
         String content
-) {}
+) {
+}

src/main/java/notai/client/ai/AiClient.java

@@ -2,17 +2,17 @@
 
 import notai.client.ai.request.LlmTaskRequest;
 import notai.client.ai.response.TaskResponse;
+import org.springframework.core.io.ByteArrayResource;
 import org.springframework.http.MediaType;
 import org.springframework.web.bind.annotation.RequestBody;
+import org.springframework.web.bind.annotation.RequestPart;
 import org.springframework.web.service.annotation.PostExchange;
 
-import java.io.InputStream;
-
 public interface AiClient {
 
     @PostExchange(url = "/api/ai/llm")
     TaskResponse submitLlmTask(@RequestBody LlmTaskRequest request);
 
     @PostExchange(url = "/api/ai/stt", contentType = MediaType.MULTIPART_FORM_DATA_VALUE)
-    TaskResponse submitSttTask(@RequestBody InputStream audioFileStream);
+    TaskResponse submitSttTask(@RequestPart("audio") ByteArrayResource audioFile);
 }

src/main/java/notai/client/ai/AiClientConfig.java

@@ -6,7 +6,10 @@
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Configuration;
 import org.springframework.http.HttpStatusCode;
+import org.springframework.http.converter.FormHttpMessageConverter;
+import org.springframework.http.converter.ResourceHttpMessageConverter;
 import org.springframework.web.client.RestClient;
+import org.springframework.web.client.RestTemplate;
 
 import static notai.client.HttpInterfaceUtil.createHttpInterface;
 import static notai.common.exception.ErrorMessages.AI_SERVER_ERROR;
@@ -20,15 +23,26 @@ public class AiClientConfig {
 
     @Bean
     public AiClient aiClient() {
-        RestClient restClient =
-                RestClient.builder().baseUrl(aiServerUrl).requestInterceptor((request, body, execution) -> {
-                    request.getHeaders().setContentLength(body.length); // Content-Length 설정 안하면 411 에러 발생
-                    return execution.execute(request, body);
-                }).defaultStatusHandler(HttpStatusCode::isError, (request, response) -> {
-                    String responseBody = new String(response.getBody().readAllBytes());
-                    log.error("Response Status: {}", response.getStatusCode());
-                    throw new ExternalApiException(AI_SERVER_ERROR, response.getStatusCode().value());
-                }).build();
+        RestClient restClient = RestClient.builder()
+            .baseUrl(aiServerUrl)
+            .messageConverters(converters -> {
+                converters.addAll(new RestTemplate().getMessageConverters());
+                converters.add(new FormHttpMessageConverter());
+            })
+            .requestInterceptor((request, body, execution) -> {
+                request.getHeaders().setContentLength(body.length); // Content-Length 설정 안하면 411 에러 발생
+                return execution.execute(request, body);
+            })
+            .defaultStatusHandler(HttpStatusCode::isError, (request, response) -> {
+                String responseBody = new String(response.getBody().readAllBytes());
+                log.error("AI 서버에서 오류가 발생했습니다. - Status: {}, Body: {}",
+                    response.getStatusCode(), 
+                    responseBody
+                );
+                throw new ExternalApiException(AI_SERVER_ERROR, response.getStatusCode().value());
+            })
+            .build();
+
         return createHttpInterface(restClient, AiClient.class);
     }
 }

src/main/java/notai/common/config/AuthConfig.java

@@ -17,8 +17,12 @@ public class AuthConfig implements WebMvcConfigurer {
 
     @Override
     public void addInterceptors(InterceptorRegistry registry) {
-        registry.addInterceptor(authInterceptor).addPathPatterns("/api/**").excludePathPatterns(
-                "/api/members/oauth/login/**").excludePathPatterns("/api/members/token/refresh");
+        registry.addInterceptor(authInterceptor)
+                .addPathPatterns("/api/**")
+                .excludePathPatterns("/api/members/oauth/login/**")
+                .excludePathPatterns("/api/members/token/refresh")
+                .excludePathPatterns("/api/ai/stt/callback")
+                .excludePathPatterns("/api/ai/llm/callback");
     }
 
     @Override

src/main/java/notai/common/config/SwaggerConfig.java

@@ -38,6 +38,6 @@ public OpenAPI openAPI() {
     }
 
     private Info apiInfo() {
-        return new Info().title("notai API").description("notai API 문서입니다.").version("0.0.2");
+        return new Info().title("notai API").description("notai API 문서입니다.").version("0.0.3");
     }
 }

src/main/java/notai/common/domain/vo/FilePath.java

@@ -14,19 +14,14 @@
 @NoArgsConstructor(access = PROTECTED)
 public class FilePath {
 
-    @Column(length = 50)
+    @Column(length = 255)
     private String filePath;
 
     private FilePath(String filePath) {
         this.filePath = filePath;
     }
 
     public static FilePath from(String filePath) {
-        // 추후 확장자 추가
-        if (!filePath.matches(
-                "[a-zA-Z0-9ㄱ-ㅎㅏ-ㅣ가-힣()\\[\\]+\\-&/_\\s]+(/[a-zA-Z0-9ㄱ-ㅎㅏ-ㅣ가-힣()\\[\\]+\\-&/_\\s]+)*/?[a-zA-Z0-9ㄱ-ㅎㅏ-ㅣ가-힣()\\[\\]+\\-&/_\\s]+\\.mp3")) {
-            throw new BadRequestException(INVALID_FILE_TYPE);
-        }
         return new FilePath(filePath);
     }
 }

src/main/java/notai/common/exception/type/BadRequestException.java

@@ -9,4 +9,7 @@ public class BadRequestException extends ApplicationException {
     public BadRequestException(ErrorMessages message) {
         super(message, 400);
     }
+    public BadRequestException(String message) {
+        super(message, 400);
+    }
 }

src/main/java/notai/document/presentation/DocumentController.java

@@ -1,5 +1,7 @@
 package notai.document.presentation;
 
+import io.swagger.v3.oas.annotations.Parameter;
+import io.swagger.v3.oas.annotations.media.Content;
 import lombok.RequiredArgsConstructor;
 import notai.auth.Auth;
 import notai.document.application.DocumentQueryService;
@@ -12,6 +14,7 @@
 import notai.document.presentation.response.DocumentFindResponse;
 import notai.document.presentation.response.DocumentSaveResponse;
 import notai.document.presentation.response.DocumentUpdateResponse;
+import org.springframework.http.MediaType;
 import org.springframework.http.ResponseEntity;
 import org.springframework.web.bind.annotation.*;
 import org.springframework.web.multipart.MultipartFile;
@@ -30,10 +33,11 @@ public class DocumentController {
     private static final Long ROOT_FOLDER_ID = -1L;
     private static final String FOLDER_URL_FORMAT = "/api/folders/%s/documents/%s";
 
-    @PostMapping
+    @PostMapping(consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
     public ResponseEntity<DocumentSaveResponse> saveDocument(
             @Auth Long memberId,
             @PathVariable Long folderId,
+            @Parameter(content = @Content(mediaType = MediaType.APPLICATION_PDF_VALUE))
             @RequestPart MultipartFile pdfFile,
             @RequestPart DocumentSaveRequest documentSaveRequest
     ) {

src/main/java/notai/llm/application/LlmTaskService.java

@@ -73,13 +73,16 @@ private void submitPageTask(Integer pageNumber, Map<Integer, List<Annotation>> a
         if (foundSummary.isEmpty() && foundProblem.isEmpty()) {
             Summary summary = new Summary(foundDocument, pageNumber);
             Problem problem = new Problem(foundDocument, pageNumber);
+            summaryRepository.save(summary);
+            problemRepository.save(problem);
 
             LlmTask taskRecord = new LlmTask(taskId, summary, problem);
             llmTaskRepository.save(taskRecord);
         }
         if (foundSummary.isPresent() && foundProblem.isPresent()) {
             LlmTask foundTaskRecord = llmTaskRepository.getBySummaryAndProblem(foundSummary.get(), foundProblem.get());
             llmTaskRepository.delete(foundTaskRecord);
+            llmTaskRepository.flush();
 
             LlmTask taskRecord = new LlmTask(taskId, foundSummary.get(), foundProblem.get());
             llmTaskRepository.save(taskRecord);

src/main/java/notai/llm/domain/LlmTask.java

@@ -25,12 +25,12 @@ public class LlmTask extends RootEntity<UUID> {
     private UUID id;
 
     @NotNull
-    @OneToOne(fetch = FetchType.LAZY, cascade = CascadeType.PERSIST)
+    @OneToOne(fetch = FetchType.LAZY)
     @JoinColumn(name = "summary_id")
     private Summary summary;
 
     @NotNull
-    @OneToOne(fetch = FetchType.LAZY, cascade = CascadeType.PERSIST)
+    @OneToOne(fetch = FetchType.LAZY)
     @JoinColumn(name = "problem_id")
     private Problem problem;
 

src/main/java/notai/llm/presentation/request/LlmTaskSubmitRequest.java

@@ -1,7 +1,7 @@
 package notai.llm.presentation.request;
 
 import jakarta.validation.constraints.NotNull;
-import jakarta.validation.constraints.Positive;
+import jakarta.validation.constraints.PositiveOrZero;
 import notai.llm.application.command.LlmTaskSubmitCommand;
 
 import java.util.List;
@@ -10,7 +10,7 @@ public record LlmTaskSubmitRequest(
 
         @NotNull(message = "문서 ID는 필수 입력 값입니다.") Long documentId,
 
-        List<@Positive(message = "페이지 번호는 양수여야 합니다.") Integer> pages
+        List<@PositiveOrZero(message = "페이지 번호는 음수일 수 없습니다.") Integer> pages
 ) {
     public LlmTaskSubmitCommand toCommand() {
         return new LlmTaskSubmitCommand(documentId, pages);

src/main/java/notai/ocr/domain/OCR.java

@@ -28,7 +28,7 @@ public class OCR extends RootEntity<Long> {
     private Integer pageNumber;
 
     @NotNull
-    @Column(name = "content", columnDefinition = "TEXT")
+    @Column(name = "content", columnDefinition = "LONGTEXT")
     private String content;
 
     public OCR(Document document, Integer pageNumber, String content) {

src/main/java/notai/pageRecording/domain/PageRecording.java

@@ -31,7 +31,6 @@ public class PageRecording {
     @NotNull
     private Double startTime;
 
-    @NotNull
     private Double endTime;
 
     public PageRecording(Recording recording, Integer pageNumber, Double startTime, Double endTime) {

src/main/java/notai/recording/application/RecordingService.java

@@ -60,7 +60,7 @@ public RecordingSaveResult saveRecording(RecordingSaveCommand command) {
             return RecordingSaveResult.of(savedRecording.getId(), foundDocument.getId(), savedRecording.getCreatedAt());
 
         } catch (IllegalArgumentException e) {
-            throw new BadRequestException(INVALID_AUDIO_ENCODING);
+            throw new BadRequestException(INVALID_AUDIO_ENCODING + " : " + e.getMessage());
         } catch (IOException e) {
             throw new InternalServerErrorException(FILE_SAVE_ERROR); // TODO: 재시도 로직 추가?
         }

src/main/java/notai/stt/application/SttService.java

@@ -33,6 +33,7 @@ public void updateSttResult(UpdateSttResultCommand command) {
         SttTask sttTask = sttTaskRepository.getById(command.taskId());
         Stt stt = sttTask.getStt();
         Recording recording = stt.getRecording();
+
         List<PageRecording> pageRecordings = pageRecordingRepository.findAllByRecordingIdOrderByStartTime(recording.getId());
 
         SttPageMatchedDto matchedResult = stt.matchWordsWithPages(command.words(), pageRecordings);

src/main/java/notai/stt/application/SttTaskService.java

@@ -15,12 +15,13 @@
 import notai.stt.domain.SttRepository;
 import notai.sttTask.domain.SttTask;
 import notai.sttTask.domain.SttTaskRepository;
+import org.springframework.core.io.ByteArrayResource;
 import org.springframework.stereotype.Service;
 import org.springframework.transaction.annotation.Transactional;
 
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.IOException;
+import java.nio.file.Files;
 
 @Service
 @Transactional
@@ -35,8 +36,17 @@ public void submitSttTask(SttRequestCommand command) {
         Recording recording = recordingRepository.getById(command.recordingId());
         File audioFile = validateAudioFile(command.audioFilePath());
 
-        try (FileInputStream fileInputStream = new FileInputStream(audioFile)) {
-            TaskResponse response = aiClient.submitSttTask(fileInputStream);
+        try {
+            byte[] audioBytes = Files.readAllBytes(audioFile.toPath());
+
+            ByteArrayResource resource = new ByteArrayResource(audioBytes) {
+                @Override
+                public String getFilename() {
+                    return audioFile.getName();
+                }
+            };
+
+            TaskResponse response = aiClient.submitSttTask(resource);
             createAndSaveSttTask(recording, response);
         } catch (IOException e) {
             throw new FileProcessException(FILE_READ_ERROR);

src/main/java/notai/stt/domain/Stt.java

@@ -92,7 +92,7 @@ public SttPageMatchedDto matchWordsWithPages(
         for (PageRecording page : pageRecordings) {
             List<SttPageMatchedDto.PageMatchedWord> pageWords = new ArrayList<>();
             double pageStart = page.getStartTime();
-            double pageEnd = page.getEndTime();
+            Double pageEnd = page.getEndTime();
 
             // 현재 페이지의 시간 범위에 속하는 단어들을 찾아 매칭
             while (wordIndex < words.size()) {
@@ -104,18 +104,17 @@ public SttPageMatchedDto matchWordsWithPages(
                     continue;
                 }
 
-                // 마지막 페이지가 아닐 경우, 페이지 종료 시간을 벗어난 단어가 나오면 다음 페이지로
-                if (page != lastPage && word.start() - TIME_THRESHOLD >= pageEnd) {
+                // 마지막 페이지이거나 endTime이 null이면 시작 시간만 체크
+                if ((page == lastPage || pageEnd == null) || word.start() - TIME_THRESHOLD < pageEnd) {
+                    pageWords.add(new SttPageMatchedDto.PageMatchedWord(
+                            word.word(),
+                            (int) word.start(),
+                            (int) word.end()
+                    ));
+                    wordIndex++;
+                } else {
                     break;
                 }
-
-                // 현재 페이지에 단어 매칭하여 추가
-                pageWords.add(new SttPageMatchedDto.PageMatchedWord(
-                        word.word(),
-                        (int) word.start(),
-                        (int) word.end()
-                ));
-                wordIndex++;
             }
 
             // 매칭된 단어가 있는 경우만 맵에 추가