@helloxiaohu/plugin-mineru6 0.0.2

package/dist/lib/mineru-toolset.strategy.js

@@ -0,0 +1,236 @@
+import { __decorate, __metadata, __param } from "tslib";
+import { Injectable, forwardRef, Inject } from '@nestjs/common';
+import { ConfigService } from '@nestjs/config';
+import { ToolsetStrategy, } from '@xpert-ai/plugin-sdk';
+import { MinerUResultParserService } from './result-parser.service.js';
+import { MinerUToolset } from './mineru.toolset.js';
+import { MinerU, icon } from './types.js';
+import { buildMinerUTool } from './mineru.tool.js';
+/**
+ * ToolsetStrategy for MinerU PDF parser tool
+ * Registers MinerU as a toolset that can be used in agent workflows
+ */
+let MinerUToolsetStrategy = class MinerUToolsetStrategy {
+    constructor(configService, resultParser) {
+        this.configService = configService;
+        this.resultParser = resultParser;
+        /**
+         * Metadata for MinerU toolset
+         */
+        this.meta = {
+            author: 'Xpert AI',
+            tags: ['pdf', 'markdown', 'parser', 'ocr', 'mineru', 'document', 'extraction'],
+            name: MinerU,
+            label: {
+                en_US: 'MinerU PDF Parser',
+                zh_Hans: 'MinerU PDF 解析器',
+            },
+            description: {
+                en_US: 'Convert PDF files to markdown format using MinerU. Supports OCR, formula recognition, and table extraction.',
+                zh_Hans: '使用 MinerU 将 PDF 文件转换为 Markdown 格式。支持 OCR、公式识别和表格提取。',
+            },
+            icon: {
+                svg: icon,
+                color: '#14b8a6',
+            },
+            configSchema: {
+                type: 'object',
+                properties: {
+                    /**
+                     * NOTE:
+                     * We intentionally keep MinerU as a "self-contained" toolset that stores its own API credentials,
+                     * instead of relying on the platform IntegrationPermission flow.
+                     *
+                     * Reason: during the built-in toolset authorization step, the platform may send `credentials = null`,
+                     * and backend may access `credentials.integration`, causing a 500 (`Cannot read properties of null (reading 'integration')`).
+                     * Defining API fields directly ensures the authorization UI renders fields and always submits an object.
+                     */
+                    apiUrl: {
+                        type: 'string',
+                        title: {
+                            en_US: 'Base URL',
+                            zh_Hans: 'Base URL',
+                        },
+                        description: {
+                            en_US: 'MinerU API base url. Official: https://mineru.net/api/v4',
+                            zh_Hans: 'MinerU 服务地址。官方： https://mineru.net/api/v4',
+                        },
+                        default: 'https://mineru.net/api/v4',
+                    },
+                    apiKey: {
+                        type: 'string',
+                        title: {
+                            en_US: 'API Key',
+                            zh_Hans: 'API Key',
+                        },
+                        description: {
+                            en_US: 'The API Key of the MinerU server (required for official API)',
+                            zh_Hans: 'MinerU 服务令牌（官方 API 必填）',
+                        },
+                        'x-ui': {
+                            component: 'secretInput',
+                            label: 'API Key',
+                            placeholder: 'MinerU API Key',
+                            revealable: true,
+                            maskSymbol: '*',
+                            persist: true,
+                        },
+                    },
+                    serverType: {
+                        type: 'string',
+                        title: {
+                            en_US: 'Server Type',
+                            zh_Hans: '服务类型',
+                        },
+                        description: {
+                            en_US: 'Select MinerU service type: official API or self-hosted',
+                            zh_Hans: '选择 MinerU 服务类型：官方 API 或自部署',
+                        },
+                        enum: ['official', 'self-hosted'],
+                        default: 'official',
+                    },
+                    // Default parsing settings (optional, can be overridden when calling the tool)
+                    isOcr: {
+                        type: 'boolean',
+                        title: {
+                            en_US: 'Enable OCR',
+                            zh_Hans: '启用 OCR',
+                        },
+                        description: {
+                            en_US: 'Enable OCR for image-based PDFs (default: true)',
+                            zh_Hans: '为基于图像的 PDF 启用 OCR（默认：true）',
+                        },
+                        default: true,
+                    },
+                    enableFormula: {
+                        type: 'boolean',
+                        title: {
+                            en_US: 'Enable Formula Recognition',
+                            zh_Hans: '启用公式识别',
+                        },
+                        description: {
+                            en_US: 'Enable formula recognition (default: true)',
+                            zh_Hans: '启用公式识别（默认：true）',
+                        },
+                        default: true,
+                    },
+                    enableTable: {
+                        type: 'boolean',
+                        title: {
+                            en_US: 'Enable Table Recognition',
+                            zh_Hans: '启用表格识别',
+                        },
+                        description: {
+                            en_US: 'Enable table recognition (default: true)',
+                            zh_Hans: '启用表格识别（默认：true）',
+                        },
+                        default: true,
+                    },
+                    language: {
+                        type: 'string',
+                        title: {
+                            en_US: 'Document Language',
+                            zh_Hans: '文档语言',
+                        },
+                        description: {
+                            en_US: 'Document language: "en" for English, "ch" for Chinese (default: "ch")',
+                            zh_Hans: '文档语言："en" 表示英语，"ch" 表示中文（默认："ch"）',
+                        },
+                        enum: ['en', 'ch'],
+                        default: 'ch',
+                    },
+                    modelVersion: {
+                        type: 'string',
+                        title: {
+                            en_US: 'Model Version',
+                            zh_Hans: '模型版本',
+                        },
+                        description: {
+                            en_US: 'Model version: "pipeline" or "vlm" (default: "pipeline")',
+                            zh_Hans: '模型版本："pipeline" 或 "vlm"（默认："pipeline"）',
+                        },
+                        enum: ['pipeline', 'vlm'],
+                        default: 'pipeline',
+                    },
+                },
+                required: ['serverType'], // apiKey required only for official, validated in validateConfig
+            },
+        };
+        /**
+         * Permissions required by MinerU toolset
+         */
+        this.permissions = [
+            {
+                type: 'filesystem',
+                operations: ['read', 'write', 'list'],
+                scope: [],
+            },
+        ];
+    }
+    /**
+     * Validate toolset configuration
+     */
+    validateConfig(config) {
+        if (!config) {
+            return Promise.resolve();
+        }
+        const serverType = config.serverType ?? 'official';
+        if (serverType === 'official' && !config.apiKey) {
+            throw new Error('MinerU apiKey is required for official serverType');
+        }
+        return Promise.resolve();
+    }
+    /**
+     * Create MinerU toolset instance
+     * Note: config may be null/undefined during authorization phase
+     */
+    async create(config) {
+        // Inject dependencies into config
+        // If config is null/undefined, create empty config
+        const baseConfig = config || {};
+        const configWithDependencies = {
+            ...baseConfig,
+            configService: this.configService,
+            resultParser: this.resultParser,
+        };
+        return new MinerUToolset(configWithDependencies);
+    }
+    /**
+     * Create tools for MinerU toolset
+     * Tools are created dynamically in MinerUToolset.initTools()
+     * based on the toolset credentials/configuration
+     */
+    createTools() {
+        /**
+         * IMPORTANT:
+         * The console UI requires builtin providers to expose at least one tool so users can
+         * enable it (otherwise it fails the "Enable at least one tool" validation).
+         *
+         * The returned tools here are used for listing/preview & toggling in UI. Actual execution
+         * will use the toolset instance created by `create()` -> `MinerUToolset.initTools()`,
+         * which wires credentials (apiUrl/apiKey/serverType) correctly.
+         */
+        return [
+            buildMinerUTool(this.configService, this.resultParser, 
+            // No credentials at listing time
+            undefined, undefined, 
+            // Defaults used if user doesn't pass tool-call parameters
+            {
+                isOcr: true,
+                enableFormula: true,
+                enableTable: true,
+                language: 'ch',
+                modelVersion: 'pipeline',
+            }),
+        ];
+    }
+};
+MinerUToolsetStrategy = __decorate([
+    Injectable(),
+    ToolsetStrategy(MinerU),
+    __param(0, Inject(forwardRef(() => ConfigService))),
+    __param(1, Inject(MinerUResultParserService)),
+    __metadata("design:paramtypes", [ConfigService,
+        MinerUResultParserService])
+], MinerUToolsetStrategy);
+export { MinerUToolsetStrategy };

package/dist/lib/mineru.client.d.ts

@@ -0,0 +1,120 @@
+import { IIntegration } from '@metad/contracts';
+import { ConfigService } from '@nestjs/config';
+import { XpFileSystem } from '@xpert-ai/plugin-sdk';
+import { AxiosResponse } from 'axios';
+import { MinerUIntegrationOptions, MineruSelfHostedTaskResult, MinerUServerType } from './types.js';
+interface CreateTaskOptions {
+    url?: string;
+    filePath?: string;
+    fileName?: string;
+    isOcr?: boolean;
+    enableFormula?: boolean;
+    enableTable?: boolean;
+    language?: string;
+    modelVersion?: string;
+    dataId?: string;
+    pageRanges?: string;
+    extraFormats?: string[];
+    callbackUrl?: string;
+    seed?: string;
+    /** Optional parse method used by self-hosted MinerU deployments */
+    parseMethod?: string;
+    /** Optional backend identifier used by self-hosted MinerU deployments */
+    backend?: string;
+    /** Optional mineru backend server url (used when backend is VLM client) */
+    serverUrl?: string;
+    /** Whether to request intermediate JSON payloads from self-hosted MinerU */
+    returnMiddleJson?: boolean;
+}
+interface CreateBatchTaskFile {
+    url: string;
+    isOcr?: boolean;
+    dataId?: string;
+    pageRanges?: string;
+}
+interface CreateBatchTaskOptions {
+    files: CreateBatchTaskFile[];
+    enableFormula?: boolean;
+    enableTable?: boolean;
+    language?: string;
+    modelVersion?: string;
+    extraFormats?: string[];
+    callbackUrl?: string;
+    seed?: string;
+}
+interface TaskResultOptions {
+    enableFormula?: boolean;
+    enableTable?: boolean;
+    language?: string;
+}
+export declare class MinerUClient {
+    private readonly configService;
+    private readonly permissions?;
+    private readonly logger;
+    private readonly baseUrl;
+    private readonly token?;
+    readonly serverType: MinerUServerType;
+    private readonly localTasks;
+    get fileSystem(): XpFileSystem | undefined;
+    constructor(configService: ConfigService, permissions?: {
+        fileSystem?: XpFileSystem;
+        integration?: Partial<IIntegration<MinerUIntegrationOptions>>;
+    });
+    /**
+     * Create a MinerU extraction task. For self-hosted deployments the file will be uploaded immediately
+     * and the parsed result cached locally, while official deployments follow the async task lifecycle.
+     */
+    createTask(options: CreateTaskOptions): Promise<{
+        taskId: string;
+    }>;
+    /**
+     * Create a batch MinerU extraction task. Only supported for official MinerU deployments.
+     */
+    createBatchTask(options: CreateBatchTaskOptions): Promise<{
+        batchId: string;
+        fileUrls?: string[];
+    }>;
+    getSelfHostedTask(taskId: string): MineruSelfHostedTaskResult | undefined;
+    /**
+     * Query offical task status or results.
+     */
+    getTaskResult(taskId: string, options?: TaskResultOptions): Promise<{
+        full_zip_url?: string;
+        full_url?: string;
+        content?: string;
+        status?: string;
+    }>;
+    /**
+     * Query batch task results. Only supported for official MinerU deployments.
+     */
+    getBatchResult(batchId: string): Promise<any>;
+    /**
+     * Wait for a task to complete and return the result when available.
+     */
+    waitForTask(taskId: string, timeoutMs?: number, intervalMs?: number): Promise<any>;
+    private ensureOfficial;
+    private resolveServerType;
+    private resolveCredentials;
+    private readIntegrationOptions;
+    private normalizeBaseUrl;
+    private buildApiUrl;
+    private getOfficialHeaders;
+    private getSelfHostedHeaders;
+    private createOfficialTask;
+    private createSelfHostedTask;
+    private invokeSelfHostedParse;
+    private invokeSelfHostedParseV1;
+    private isSelfHostedApiV1;
+    private normalizeSelfHostedResponse;
+    private normalizeSelfHostedFileResult;
+    private normalizeImageMap;
+    private parseJsonSafe;
+    private buildLanguageList;
+    private booleanToString;
+    private downloadFile;
+    private extractFileName;
+    getSelfHostedOpenApiSpec(): Promise<AxiosResponse<any, any>>;
+    validateOfficialApiToken(): Promise<void>;
+}
+export {};
+//# sourceMappingURL=mineru.client.d.ts.map

package/dist/lib/mineru.client.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"mineru.client.d.ts","sourceRoot":"","sources":["../../src/lib/mineru.client.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,kBAAkB,CAAC;AAEhD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAC/C,OAAO,EAAmB,YAAY,EAAE,MAAM,sBAAsB,CAAC;AACrE,OAAc,EAAE,aAAa,EAAE,MAAM,OAAO,CAAC;AAK7C,OAAO,EAIL,wBAAwB,EAExB,0BAA0B,EAC1B,gBAAgB,EACjB,MAAM,YAAY,CAAC;AAIpB,UAAU,iBAAiB;IACzB,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,KAAK,CAAC,EAAE,OAAO,CAAC;IAChB,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,mEAAmE;IACnE,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,yEAAyE;IACzE,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,2EAA2E;IAC3E,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,4EAA4E;IAC5E,gBAAgB,CAAC,EAAE,OAAO,CAAC;CAC5B;AAED,UAAU,mBAAmB;IAC3B,GAAG,EAAE,MAAM,CAAC;IACZ,KAAK,CAAC,EAAE,OAAO,CAAC;IAChB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,UAAU,sBAAsB;IAC9B,KAAK,EAAE,mBAAmB,EAAE,CAAC;IAC7B,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,UAAU,iBAAiB;IACzB,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AASD,qBAAa,YAAY;IAWrB,OAAO,CAAC,QAAQ,CAAC,aAAa;IAC9B,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC;IAX/B,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAiC;IACxD,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAS;IAChC,SAAgB,UAAU,EAAE,gBAAgB,CAAC;IAC7C,OAAO,CAAC,QAAQ,CAAC,UAAU,CAAiD;IAE5E,IAAI,UAAU,IAAI,YAAY,GAAG,SAAS,CAEzC;gBAEkB,aAAa,EAAE,aAAa,EAC5B,WAAW,CAAC,EAAE;QACvB,UAAU,CAAC,EAAE,YAAY,CAAC;QAC1B,WAAW,CAAC,EAAE,OAAO,CAAC,YAAY,CAAC,wBAAwB,CAAC,CAAC,CAAC;KACjE;IAkBP;;;OAGG;IACG,UAAU,CAAC,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC;QAAE,MAAM,EAAE,MAAM,CAAA;KAAE,CAAC;IAYzE;;OAEG;IACG,eAAe,CAAC,OAAO,EAAE,sBAAsB,GAAG,OAAO,CAAC;QAAE,OAAO,EAAE,MAAM,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAA;KAAE,CAAC;IAmCzG,iBAAiB,CAAC,MAAM,EAAE,MAAM,GAAG,0BAA0B,GAAG,SAAS;IAOzE;;OAEG;IACG,aAAa,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,iBAAiB,GAAG,OAAO,CAAC;QACxE,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,QAAQ,CAAC,EAAE,MAAM,CAAC;QAClB,OAAO,CAAC,EAAE,MAAM,CAAC;QACjB,MAAM,CAAC,EAAE,MAAM,CAAC;KACjB,CAAC;IAoBF;;OAEG;IACG,cAAc,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC;IAiBnD;;OAEG;IACG,WAAW,CAAC,MAAM,EAAE,MAAM,EAAE,SAAS,SAAgB,EAAE,UAAU,SAAO,GAAG,OAAO,CAAC,GAAG,CAAC;IAsB7F,OAAO,CAAC,cAAc;IAMtB,OAAO,CAAC,iBAAiB;IAczB,OAAO,CAAC,kBAAkB;IAyB1B,OAAO,CAAC,sBAAsB;IAI9B,OAAO,CAAC,gBAAgB;IAIxB,OAAO,CAAC,WAAW;IAQnB,OAAO,CAAC,kBAAkB;IAO1B,OAAO,CAAC,oBAAoB;YAYd,kBAAkB;YA4BlB,oBAAoB;YASpB,qBAAqB;YA0DrB,uBAAuB;IA+CrC,OAAO,CAAC,iBAAiB;IAgBzB,OAAO,CAAC,2BAA2B;IAenC,OAAO,CAAC,6BAA6B;IAcrC,OAAO,CAAC,iBAAiB;IAQzB,OAAO,CAAC,aAAa;IAcrB,OAAO,CAAC,iBAAiB;IAQzB,OAAO,CAAC,eAAe;YAIT,YAAY;IAkB1B,OAAO,CAAC,eAAe;IA0BvB,wBAAwB,IAAI,OAAO,CAAC,aAAa,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;IAKtD,wBAAwB;CAU/B"}