更新新增三个模块

This commit is contained in:
super
2026-03-22 11:20:09 +08:00
parent c80e1889ef
commit 497d65d41d
96 changed files with 5393 additions and 588 deletions
@@ -46,7 +46,8 @@ public class SplitRunController {
- splitMode=rows_per_file 时按固定条数切分;
- splitMode=parts 时按总条数尽量均分;
- 输出文件命名遵循 原文件名_split_序号.xlsx;
- 返回结果中 rowCount 表示该结果文件包含的数据行数。
- 本次拆分任务产生的所有 xlsx 会统一打成一个 zip 上传;
- 返回结果中 rowCount 表示该压缩包包含的数据总行数,entries 表示压缩包内文件摘要。
""")
@ApiResponses({
@io.swagger.v3.oas.annotations.responses.ApiResponse(responseCode = "200", description = "执行成功,返回拆分结果统计", content = @Content(schema = @Schema(implementation = SplitRunVo.class))),
@@ -30,4 +30,7 @@ public class SplitRunRequest {
@Schema(description = "按份数拆分时的份数")
private Integer parts;
@Schema(description = "文件夹上传场景下的总压缩包名称(不含扩展名)")
private String archiveName;
}
@@ -14,4 +14,7 @@ public class SplitSourceFileDto {
@Schema(description = "原始文件名")
private String originalFilename;
@Schema(description = "相对上传目录路径")
private String relativePath;
}
@@ -0,0 +1,15 @@
package com.nanri.aiimage.modules.split.model.vo;
import io.swagger.v3.oas.annotations.media.Schema;
import lombok.Data;
@Data
@Schema(description = "拆分压缩包内文件项")
public class SplitArchiveEntryVo {
@Schema(description = "文件名")
private String filename;
@Schema(description = "该文件包含的数据行数")
private Integer rowCount;
}
@@ -3,6 +3,8 @@ package com.nanri.aiimage.modules.split.model.vo;
import io.swagger.v3.oas.annotations.media.Schema;
import lombok.Data;
import java.util.List;
@Data
@Schema(description = "数据拆分结果项")
public class SplitResultItemVo {
@@ -22,9 +24,15 @@ public class SplitResultItemVo {
@Schema(description = "错误信息")
private String error;
@Schema(description = "结果行数")
@Schema(description = "结果总行数")
private Integer rowCount;
@Schema(description = "下载地址")
private String downloadUrl;
@Schema(description = "压缩包内文件数量")
private Integer entryCount;
@Schema(description = "压缩包内文件列表")
private List<SplitArchiveEntryVo> entries;
}
@@ -3,13 +3,15 @@ package com.nanri.aiimage.modules.split.service;
import cn.hutool.core.io.FileUtil;
import cn.hutool.core.util.IdUtil;
import cn.hutool.json.JSONUtil;
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
import com.nanri.aiimage.common.exception.BusinessException;
import com.nanri.aiimage.config.StorageProperties;
import com.nanri.aiimage.modules.file.service.oss.OssStorageService;
import com.nanri.aiimage.modules.split.model.dto.SplitRunRequest;
import com.nanri.aiimage.modules.split.model.dto.SplitSourceFileDto;
import com.nanri.aiimage.modules.split.model.vo.SplitArchiveEntryVo;
import com.nanri.aiimage.modules.split.model.vo.SplitResultItemVo;
import com.nanri.aiimage.modules.split.model.vo.SplitRunVo;
import com.nanri.aiimage.modules.file.service.oss.OssStorageService;
import com.nanri.aiimage.modules.task.mapper.FileResultMapper;
import com.nanri.aiimage.modules.task.mapper.FileTaskMapper;
import com.nanri.aiimage.modules.task.model.entity.FileResultEntity;
@@ -20,6 +22,7 @@ import org.apache.poi.ss.usermodel.DataFormatter;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.usermodel.WorkbookFactory;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.springframework.core.io.FileSystemResource;
import org.springframework.core.io.Resource;
@@ -28,18 +31,28 @@ import org.springframework.stereotype.Service;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.nio.file.Files;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
import java.util.zip.ZipEntry;
import java.util.zip.ZipOutputStream;
@Service
@RequiredArgsConstructor
public class SplitRunService {
private static final String MODULE_TYPE = "SPLIT";
private static final String ZIP_CONTENT_TYPE = "application/zip";
private static final String SPLIT_MODE_ROWS_PER_FILE = "rows_per_file";
private static final String SPLIT_MODE_PARTS = "parts";
private static final String HEADER_SUFFIX_MARKER = "idASIN\u56fd\u5bb6\u72b6\u6001\u4ef7\u683c\u53d8\u4f53\u6570\u91cf";
private static final String HEADER_STOP_COLUMN = "\u7f29\u7565\u56fe\u5730\u57408";
private static final DateTimeFormatter ZIP_NAME_DATE_FORMATTER = DateTimeFormatter.ofPattern("yyyyMMdd");
private final FileTaskMapper fileTaskMapper;
private final FileResultMapper fileResultMapper;
private final StorageProperties storageProperties;
@@ -49,8 +62,8 @@ public class SplitRunService {
validateRequest(request);
FileTaskEntity task = new FileTaskEntity();
task.setTaskNo("SPLIT-" + IdUtil.getSnowflakeNextIdStr());
task.setModuleType("SPLIT");
task.setTaskNo(MODULE_TYPE + "-" + IdUtil.getSnowflakeNextIdStr());
task.setModuleType(MODULE_TYPE);
task.setTaskMode("IMMEDIATE");
task.setStatus("SUCCESS");
task.setSourceFileCount(request.getFiles().size());
@@ -61,56 +74,42 @@ public class SplitRunService {
task.setFinishedAt(LocalDateTime.now());
fileTaskMapper.insert(task);
boolean folderMode = request.getArchiveName() != null && !request.getArchiveName().isBlank();
List<SplitResultItemVo> items = new ArrayList<>();
int successCount = 0;
int failedCount = 0;
List<TaskSplitChunkResult> allChunkResults = new ArrayList<>();
List<String> successSourceNames = new ArrayList<>();
for (SplitSourceFileDto sourceFile : request.getFiles()) {
try {
File inputFile = findLocalSourceFile(sourceFile.getFileKey());
if (inputFile == null || !inputFile.exists()) {
throw new BusinessException("上传文件不存在,请重新上传");
throw new BusinessException("Uploaded source file does not exist, please upload again.");
}
String inputName = sourceFile.getOriginalFilename() == null ? inputFile.getName() : sourceFile.getOriginalFilename();
String inputName = sourceFile.getOriginalFilename() == null
? inputFile.getName()
: sourceFile.getOriginalFilename();
List<SplitChunkResult> chunkResults = splitExcelByLegacyRules(inputFile, inputName, request);
for (SplitChunkResult chunkResult : chunkResults) {
SplitResultItemVo item = new SplitResultItemVo();
item.setSourceFilename(inputName);
item.setOutputFilename(chunkResult.outputFile().getName());
item.setSuccess(true);
item.setRowCount(chunkResult.rowCount());
String ossObjectKey = ossStorageService.uploadResultFile(chunkResult.outputFile(), "SPLIT");
String downloadUrl = ossStorageService.generateDownloadUrl(ossObjectKey);
FileResultEntity resultEntity = new FileResultEntity();
resultEntity.setTaskId(task.getId());
resultEntity.setModuleType("SPLIT");
resultEntity.setSourceFilename(inputName);
resultEntity.setResultFilename(chunkResult.outputFile().getName());
resultEntity.setResultFileUrl(downloadUrl);
resultEntity.setResultFileSize(chunkResult.outputFile().length());
resultEntity.setResultContentType("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet");
resultEntity.setRowCount(chunkResult.rowCount());
resultEntity.setSuccess(1);
resultEntity.setCreatedAt(LocalDateTime.now());
fileResultMapper.insert(resultEntity);
item.setDownloadUrl(downloadUrl);
item.setResultId(resultEntity.getId());
items.add(item);
allChunkResults.add(new TaskSplitChunkResult(sourceFile.getRelativePath(), inputName, chunkResult.outputFile(), chunkResult.rowCount()));
}
successSourceNames.add(inputName);
successCount++;
} catch (Exception ex) {
SplitResultItemVo item = new SplitResultItemVo();
item.setSourceFilename(sourceFile.getOriginalFilename());
item.setSuccess(false);
item.setError(ex.getMessage());
item.setEntries(new ArrayList<>());
item.setEntryCount(0);
items.add(item);
failedCount++;
FileResultEntity resultEntity = new FileResultEntity();
resultEntity.setTaskId(task.getId());
resultEntity.setModuleType("SPLIT");
resultEntity.setModuleType(MODULE_TYPE);
resultEntity.setSourceFilename(sourceFile.getOriginalFilename());
resultEntity.setSuccess(0);
resultEntity.setErrorMessage(ex.getMessage());
@@ -119,6 +118,38 @@ public class SplitRunService {
}
}
if (!allChunkResults.isEmpty()) {
File zipFile = packageTaskSplitResultsAsZip(request.getArchiveName(), successSourceNames, allChunkResults);
String ossObjectKey = ossStorageService.uploadResultFile(zipFile, MODULE_TYPE);
String downloadUrl = ossStorageService.generateDownloadUrl(ossObjectKey);
SplitResultItemVo item = new SplitResultItemVo();
item.setSourceFilename(folderMode && request.getArchiveName() != null && !request.getArchiveName().isBlank()
? request.getArchiveName()
: successSourceNames.size() == 1 ? successSourceNames.get(0) : "Current split task");
item.setOutputFilename(zipFile.getName());
item.setSuccess(true);
item.setRowCount(allChunkResults.stream().mapToInt(TaskSplitChunkResult::rowCount).sum());
item.setDownloadUrl(downloadUrl);
item.setEntryCount(allChunkResults.size());
item.setEntries(allChunkResults.stream().map(this::toArchiveEntry).toList());
FileResultEntity resultEntity = new FileResultEntity();
resultEntity.setTaskId(task.getId());
resultEntity.setModuleType(MODULE_TYPE);
resultEntity.setSourceFilename(item.getSourceFilename());
resultEntity.setResultFilename(zipFile.getName());
resultEntity.setResultFileUrl(downloadUrl);
resultEntity.setResultFileSize(zipFile.length());
resultEntity.setResultContentType(ZIP_CONTENT_TYPE);
resultEntity.setRowCount(item.getRowCount());
resultEntity.setSuccess(1);
resultEntity.setCreatedAt(LocalDateTime.now());
fileResultMapper.insert(resultEntity);
item.setResultId(resultEntity.getId());
items.add(0, item);
}
task.setSuccessFileCount(successCount);
task.setFailedFileCount(failedCount);
task.setResultJson(JSONUtil.toJsonStr(items));
@@ -135,19 +166,21 @@ public class SplitRunService {
public List<SplitResultItemVo> listHistory() {
return fileResultMapper.selectList(new LambdaQueryWrapper<FileResultEntity>()
.eq(FileResultEntity::getModuleType, "SPLIT")
.eq(FileResultEntity::getSuccess, 1)
.eq(FileResultEntity::getModuleType, MODULE_TYPE)
.orderByDesc(FileResultEntity::getCreatedAt)
.last("limit 100"))
.stream()
.map(entity -> {
SplitResultItemVo vo = new SplitResultItemVo();
vo.setResultId(entity.getId());
vo.setSourceFilename(entity.getCreatedAt() == null ? "" : entity.getCreatedAt().toLocalDate().toString().replace("-", ""));
vo.setSourceFilename(entity.getSourceFilename());
vo.setOutputFilename(entity.getResultFilename());
vo.setDownloadUrl(entity.getResultFileUrl());
vo.setDownloadUrl(entity.getSuccess() != null && entity.getSuccess() == 1 ? entity.getResultFileUrl() : null);
vo.setRowCount(entity.getRowCount());
vo.setSuccess(true);
vo.setSuccess(entity.getSuccess() != null && entity.getSuccess() == 1);
vo.setError(entity.getErrorMessage());
vo.setEntryCount(0);
vo.setEntries(new ArrayList<>());
return vo;
})
.toList();
@@ -155,55 +188,45 @@ public class SplitRunService {
public void deleteHistory(Long resultId) {
FileResultEntity entity = fileResultMapper.selectById(resultId);
if (entity == null || !"SPLIT".equals(entity.getModuleType())) {
throw new BusinessException("记录不存在");
if (entity == null || !MODULE_TYPE.equals(entity.getModuleType())) {
throw new BusinessException("Split result record does not exist.");
}
fileResultMapper.deleteById(resultId);
}
public Resource getResultFile(Long resultId) {
FileResultEntity entity = fileResultMapper.selectById(resultId);
if (entity == null || entity.getResultFileUrl() == null || !"SPLIT".equals(entity.getModuleType())) {
throw new BusinessException("结果文件不存在");
if (entity == null || entity.getResultFileUrl() == null || !MODULE_TYPE.equals(entity.getModuleType())) {
throw new BusinessException("Split result file does not exist.");
}
File file = new File(entity.getResultFileUrl());
if (!file.exists()) {
throw new BusinessException("结果文件不存在");
throw new BusinessException("Split result file does not exist.");
}
return new FileSystemResource(file);
}
private List<SplitChunkResult> splitExcelByLegacyRules(File inputFile, String originalFilename, SplitRunRequest request) throws Exception {
private List<SplitChunkResult> splitExcelByLegacyRules(
File inputFile,
String originalFilename,
SplitRunRequest request
) throws Exception {
DataFormatter formatter = new DataFormatter();
try (FileInputStream fis = new FileInputStream(inputFile); Workbook workbook = org.apache.poi.ss.usermodel.WorkbookFactory.create(fis)) {
try (FileInputStream fis = new FileInputStream(inputFile);
Workbook workbook = WorkbookFactory.create(fis)) {
Sheet sheet = workbook.getSheetAt(0);
Row headerRow = sheet.getRow(0);
if (headerRow == null) {
throw new BusinessException("Excel 表头为空");
throw new BusinessException("Excel header row is empty.");
}
Map<String, Integer> headerMap = new HashMap<>();
for (int i = 0; i < headerRow.getLastCellNum(); i++) {
Cell cell = headerRow.getCell(i);
String value = normalizeCellText(cell == null ? null : formatter.formatCellValue(cell));
if (value.isBlank()) {
continue;
}
value = value.split("idASIN国家状态价格变体数量", 2)[0].trim().isEmpty()
? value
: value.split("idASIN国家状态价格变体数量", 2)[0].trim();
if (headerMap.containsKey(value)) {
continue;
}
headerMap.put(value, i);
if ("缩略图地址8".equals(value)) {
break;
}
}
List<String> missing = request.getSelectedColumns().stream().filter(column -> !headerMap.containsKey(column)).toList();
Map<String, Integer> headerMap = buildHeaderMap(headerRow, formatter);
List<String> missing = request.getSelectedColumns().stream()
.filter(column -> !headerMap.containsKey(column))
.toList();
if (!missing.isEmpty()) {
throw new BusinessException("缺少列:" + String.join("、", missing));
throw new BusinessException("Missing required columns: " + String.join(", ", missing));
}
List<List<String>> rowsData = new ArrayList<>();
@@ -215,39 +238,23 @@ public class SplitRunService {
List<String> projected = new ArrayList<>();
for (String column : request.getSelectedColumns()) {
Integer sourceIndex = headerMap.get(column);
String value = sourceIndex == null ? "" : normalizeCellText(formatter.formatCellValue(row.getCell(sourceIndex)));
String value = sourceIndex == null
? ""
: normalizeCellText(formatter.formatCellValue(row.getCell(sourceIndex)));
projected.add(value);
}
rowsData.add(projected);
}
int totalRows = rowsData.size();
if (totalRows == 0) {
throw new BusinessException("没有可拆分的数据行");
}
List<List<List<String>>> chunks = new ArrayList<>();
if ("rows_per_file".equals(request.getSplitMode())) {
int chunkSize = request.getRowsPerFile();
for (int i = 0; i < totalRows; i += chunkSize) {
chunks.add(rowsData.subList(i, Math.min(i + chunkSize, totalRows)));
}
} else {
int actualParts = Math.min(request.getParts(), totalRows);
int base = totalRows / actualParts;
int remainder = totalRows % actualParts;
int start = 0;
for (int i = 0; i < actualParts; i++) {
int size = base + (i < remainder ? 1 : 0);
int end = start + size;
chunks.add(rowsData.subList(start, end));
start = end;
}
if (rowsData.isEmpty()) {
throw new BusinessException("No data rows available for splitting.");
}
List<List<List<String>>> chunks = buildChunks(rowsData, request);
File outputDir = FileUtil.mkdir(FileUtil.file(storageProperties.getLocalTempDir(), "split-result"));
String sourceStem = FileUtil.mainName(originalFilename);
List<SplitChunkResult> results = new ArrayList<>();
for (int i = 0; i < chunks.size(); i++) {
File outputFile = buildNamedOutputFile(outputDir, sourceStem + "_split_" + (i + 1) + ".xlsx");
try (XSSFWorkbook outputWorkbook = new XSSFWorkbook()) {
@@ -269,19 +276,63 @@ public class SplitRunService {
}
results.add(new SplitChunkResult(outputFile, chunks.get(i).size()));
}
return results;
}
}
private Map<String, Integer> buildHeaderMap(Row headerRow, DataFormatter formatter) {
Map<String, Integer> headerMap = new HashMap<>();
for (int i = 0; i < headerRow.getLastCellNum(); i++) {
Cell cell = headerRow.getCell(i);
String value = normalizeHeaderName(cell == null ? null : formatter.formatCellValue(cell));
if (value.isBlank() || headerMap.containsKey(value)) {
continue;
}
headerMap.put(value, i);
if (HEADER_STOP_COLUMN.equals(value)) {
break;
}
}
return headerMap;
}
private List<List<List<String>>> buildChunks(List<List<String>> rowsData, SplitRunRequest request) {
int totalRows = rowsData.size();
List<List<List<String>>> chunks = new ArrayList<>();
if (SPLIT_MODE_ROWS_PER_FILE.equals(request.getSplitMode())) {
int chunkSize = request.getRowsPerFile();
for (int i = 0; i < totalRows; i += chunkSize) {
chunks.add(rowsData.subList(i, Math.min(i + chunkSize, totalRows)));
}
return chunks;
}
int actualParts = Math.min(request.getParts(), totalRows);
int base = totalRows / actualParts;
int remainder = totalRows % actualParts;
int start = 0;
for (int i = 0; i < actualParts; i++) {
int size = base + (i < remainder ? 1 : 0);
int end = start + size;
chunks.add(rowsData.subList(start, end));
start = end;
}
return chunks;
}
private void validateRequest(SplitRunRequest request) {
if (!List.of("rows_per_file", "parts").contains(request.getSplitMode())) {
throw new BusinessException("拆分模式不合法");
if (!List.of(SPLIT_MODE_ROWS_PER_FILE, SPLIT_MODE_PARTS).contains(request.getSplitMode())) {
throw new BusinessException("Invalid split mode.");
}
if ("rows_per_file".equals(request.getSplitMode()) && (request.getRowsPerFile() == null || request.getRowsPerFile() <= 0)) {
throw new BusinessException("每份条数不合法");
if (SPLIT_MODE_ROWS_PER_FILE.equals(request.getSplitMode())
&& (request.getRowsPerFile() == null || request.getRowsPerFile() <= 0)) {
throw new BusinessException("Invalid rowsPerFile value.");
}
if ("parts".equals(request.getSplitMode()) && (request.getParts() == null || request.getParts() <= 0)) {
throw new BusinessException("拆分份数不合法");
if (SPLIT_MODE_PARTS.equals(request.getSplitMode())
&& (request.getParts() == null || request.getParts() <= 0)) {
throw new BusinessException("Invalid parts value.");
}
}
@@ -290,8 +341,11 @@ public class SplitRunService {
if (!baseDir.exists()) {
return null;
}
List<File> matchedFiles = FileUtil.loopFiles(baseDir, pathname -> pathname.isFile() && pathname.getName().startsWith(fileKey));
return matchedFiles.isEmpty() ? null : matchedFiles.getFirst();
List<File> matchedFiles = FileUtil.loopFiles(
baseDir,
pathname -> pathname.isFile() && pathname.getName().startsWith(fileKey)
);
return matchedFiles.isEmpty() ? null : matchedFiles.get(0);
}
private File buildNamedOutputFile(File outputDir, String filename) {
@@ -299,6 +353,7 @@ public class SplitRunService {
if (!candidate.exists()) {
return candidate;
}
String mainName = FileUtil.mainName(filename);
String extName = FileUtil.extName(filename);
int index = 2;
@@ -314,6 +369,61 @@ public class SplitRunService {
}
}
private File packageTaskSplitResultsAsZip(String archiveName, List<String> successSourceNames, List<TaskSplitChunkResult> chunkResults) {
File outputDir = FileUtil.mkdir(FileUtil.file(storageProperties.getLocalTempDir(), "split-result"));
String zipFilename = archiveName != null && !archiveName.isBlank()
? archiveName + ".zip"
: successSourceNames.size() == 1
? FileUtil.mainName(successSourceNames.getFirst()) + ".zip"
: LocalDateTime.now().format(ZIP_NAME_DATE_FORMATTER) + ".zip";
File zipFile = buildNamedOutputFile(outputDir, zipFilename);
try (ZipOutputStream zos = new ZipOutputStream(new FileOutputStream(zipFile))) {
for (TaskSplitChunkResult chunkResult : chunkResults) {
String zipEntryName = buildFolderZipEntry(chunkResult.relativePath(), chunkResult.sourceFilename(), chunkResult.outputFile().getName(), true);
ZipEntry entry = new ZipEntry(zipEntryName);
zos.putNextEntry(entry);
Files.copy(chunkResult.outputFile().toPath(), zos);
zos.closeEntry();
}
} catch (Exception ex) {
throw new BusinessException("拆分结果打包失败:" + ex.getMessage());
}
return zipFile;
}
private String buildFolderZipEntry(String relativePath, String inputName, String outputFilename, boolean includeSourceStemFolder) {
String normalizedRelativePath = relativePath == null ? "" : relativePath.replace('\\', '/');
String relativeDir = normalizedRelativePath.contains("/")
? normalizedRelativePath.substring(0, normalizedRelativePath.lastIndexOf('/'))
: "";
List<String> parts = new ArrayList<>();
if (!relativeDir.isBlank()) {
parts.add(relativeDir);
}
if (includeSourceStemFolder) {
parts.add(FileUtil.mainName(inputName));
}
parts.add(outputFilename);
return String.join("/", parts);
}
private SplitArchiveEntryVo toArchiveEntry(TaskSplitChunkResult chunkResult) {
SplitArchiveEntryVo vo = new SplitArchiveEntryVo();
vo.setFilename(chunkResult.outputFile().getName());
vo.setRowCount(chunkResult.rowCount());
return vo;
}
private String normalizeHeaderName(String value) {
String normalized = normalizeCellText(value);
if (normalized.isBlank()) {
return normalized;
}
String prefix = normalized.split(HEADER_SUFFIX_MARKER, 2)[0].trim();
return prefix.isEmpty() ? normalized : prefix;
}
private String normalizeCellText(String value) {
if (value == null) {
return "";
@@ -330,4 +440,7 @@ public class SplitRunService {
private record SplitChunkResult(File outputFile, int rowCount) {
}
private record TaskSplitChunkResult(String relativePath, String sourceFilename, File outputFile, int rowCount) {
}
}