#first commit

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+indent_style = space
+indent_size = 2
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+end_of_line = lf

.eslintignore

@@ -0,0 +1,4 @@
+/*.js
+node_modules
+dist
+@types

.eslintrc.json

@@ -0,0 +1,67 @@
+{
+  "env": {
+    "es2020": true,
+    "node": true,
+    "jest": true
+  },
+  "extends": [
+    "airbnb-base",
+    "plugin:@typescript-eslint/recommended",
+    "prettier/@typescript-eslint",
+    "plugin:prettier/recommended"
+  ],
+  "parser": "@typescript-eslint/parser",
+  "parserOptions": {
+    "ecmaVersion": 2020,
+    "sourceType": "module"
+  },
+  "plugins": [
+    "@typescript-eslint",
+    "prettier"
+  ],
+  "rules": {
+    "prettier/prettier": "error",
+    "no-param-reassign": "off",
+    "no-plusplus": "off",
+    "no-await-in-loop": "off",
+    "no-useless-constructor": "off",
+    "no-underscore-dangle": "off",
+    "camelcase": "off",
+    "no-console": "off",
+    "class-methods-use-this": "off",
+
+    "@typescript-eslint/no-unused-vars": [
+      "error",
+      {
+        "argsIgnorePattern": "^_"
+      }
+    ],
+    "@typescript-eslint/naming-convention": [
+      "error",
+      {
+        "selector": "interface",
+        "format": [
+          "PascalCase"
+        ],
+        "custom": {
+          "regex": "^I[A-Z]",
+          "match": true
+        }
+      }
+    ],
+    "import/extensions": [
+      "error",
+      "ignorePackages",
+      {
+        "ts": "never"
+      }
+    ],
+    "no-shadow": "off",
+    "@typescript-eslint/no-shadow": ["error"]
+  },
+  "settings": {
+    "import/resolver": {
+      "typescript": {}
+    }
+  }
+}

.gitignore

@@ -1,109 +1,5 @@
-# ---> Node
-# Logs
-logs
+node_modules
+dist
 *.log
-npm-debug.log*
-yarn-debug.log*
-yarn-error.log*
-lerna-debug.log*
-
-# Diagnostic reports (https://nodejs.org/api/report.html)
-report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
-
-# Runtime data
-pids
-*.pid
-*.seed
-*.pid.lock
-
-# Directory for instrumented libs generated by jscoverage/JSCover
-lib-cov
-
-# Coverage directory used by tools like istanbul
+*.logs
 coverage
-*.lcov
-
-# nyc test coverage
-.nyc_output
-
-# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
-.grunt
-
-# Bower dependency directory (https://bower.io/)
-bower_components
-
-# node-waf configuration
-.lock-wscript
-
-# Compiled binary addons (https://nodejs.org/api/addons.html)
-build/Release
-
-# Dependency directories
-node_modules/
-jspm_packages/
-
-# TypeScript v1 declaration files
-typings/
-
-# TypeScript cache
-*.tsbuildinfo
-
-# Optional npm cache directory
-.npm
-
-# Optional eslint cache
-.eslintcache
-
-# Microbundle cache
-.rpt2_cache/
-.rts2_cache_cjs/
-.rts2_cache_es/
-.rts2_cache_umd/
-
-# Optional REPL history
-.node_repl_history
-
-# Output of 'npm pack'
-*.tgz
-
-# Yarn Integrity file
-.yarn-integrity
-
-# dotenv environment variables file
-.env
-.env.test
-
-# parcel-bundler cache (https://parceljs.org/)
-.cache
-
-# Next.js build output
-.next
-
-# Nuxt.js build / generate output
-.nuxt
-dist
-
-# Gatsby files
-.cache/
-# Comment in the public line in if your project uses Gatsby and not Next.js
-# https://nextjs.org/blog/next-9-1#public-directory-support
-# public
-
-# vuepress build output
-.vuepress/dist
-
-# Serverless directories
-.serverless/
-
-# FuseBox cache
-.fusebox/
-
-# DynamoDB Local files
-.dynamodb/
-
-# TernJS port file
-.tern-port
-
-# Stores VSCode versions used for testing VSCode extensions
-.vscode-test
-

Dockerfile.development

@@ -0,0 +1,11 @@
+FROM node:14.15.1
+
+
+WORKDIR /app
+RUN apt-get update
+RUN apt-get install build-essential libpoppler-cpp-dev pkg-config python-dev -y
+RUN apt install poppler-utils -y
+
+
+EXPOSE 3333
+CMD yarn && yarn dev:server

README.md

@@ -1,2 +1,41 @@
-# pdf-extract-Via_Software
 
+
+<h1 align="center">Extract data from PDF</h1>
+
+# Usando o template
+## Criando um projeto novo
+1. Acesse a pagina do gitea: https://gitea.tron.com.br/Tron_Informatica/pdf-extract-template
+2. Localize o botão "Usar este modelo" <br>
+![Pagina do gitea - Projeto](https://gitea.tron.com.br/Tron_Informatica/pdf-extract-template/raw/branch/master/resources/gitea-template.png) <br>
+3. Preencha os campos e crie o repositorio. Marque a opção "Conteúdo Git (Branch padrão)" e lembre de trocar o proprietario para 'Tron_informatica' <br>
+![Pagina do gitea - Novo repositorio](https://gitea.tron.com.br/Tron_Informatica/pdf-extract-template/raw/branch/master/resources/gitea-novo-repo.png) <br>
+4. clone o novo repositório criado
+
+## Usando o template
+1. Troque o nome do projeto nos arquivos: docker-composer.yaml e package.json <br>
+![Arquivos para renomear](https://gitea.tron.com.br/Tron_Informatica/pdf-extract-template/raw/branch/master/resources/renomear-projeto.png) <br>
+2. Crie seus controllers, services e rotas, dexei alguns arquivos como teste <br>
+![Arquivos para renomear](https://gitea.tron.com.br/Tron_Informatica/pdf-extract-template/raw/branch/master/resources/arquivos-exemplos.png) <br>
+
+## Scripts
+### Rodando projeto
+```console
+:~$ yarn docker:server
+```
+
+### Exibindo o bash do container
+Obs: o projeto precisa está em execução
+```console
+:~$ yarn docker:bash
+```
+
+### Rodando teste unitários
+```console
+:~$ yarn docker:test
+```
+
+### Instalando dependência
+```console
+:~$ yarn docker:bash
+root@947961d6b834:/app# yarn add <dependência>
+```

babel.config.js

@@ -0,0 +1,19 @@
+module.exports = {
+  presets: [
+    ['@babel/preset-env', { targets: { node: 'current' } }],
+    '@babel/preset-typescript',
+    ['const-enum', { "transform": "constObject" }]
+  ],
+  plugins: [
+    ['module-resolver', {
+      alias: {
+        '@modules': './src/modules',
+        '@config': './src/config',
+        '@shared': './src/shared'
+      }
+    }],
+    'babel-plugin-transform-typescript-metadata',
+    ['@babel/plugin-proposal-decorators', { 'legacy': true }],
+    ['@babel/plugin-proposal-class-properties', { 'loose': true }]
+  ],
+}

docker-compose.yaml

@@ -0,0 +1,17 @@
+version: "3"
+services:
+  node:
+    build:
+      context: ./
+      dockerfile: Dockerfile.development
+    container_name: nome-do-projeto
+    tty: true
+    volumes:
+    - ./:/app
+    ports:
+      - "3333:3333"
+    networks:
+      - nome-do-projeto
+networks:
+  nome-do-projeto:
+    driver: bridge

jest.config.js

@@ -0,0 +1,193 @@
+// For a detailed explanation regarding each configuration property, visit:
+// https://jestjs.io/docs/en/configuration.html
+
+module.exports = {
+   // All imported modules in your tests should be mocked automatically
+   // automock: false,
+
+   // Stop running tests after `n` failures
+   // bail: 0,
+
+   // The directory where Jest should store its cached dependency information
+   // cacheDirectory: "C:\\Users\\danil\\AppData\\Local\\Temp\\jest",
+
+   // Automatically clear mock calls and instances between every test
+   clearMocks: true,
+
+   // Indicates whether the coverage information should be collected while executing the test
+   collectCoverage: true,
+
+   // An array of glob patterns indicating a set of files for which coverage information should be collected
+   collectCoverageFrom: [
+    '<rootDir>/src/services/**/*.ts',
+   ],
+
+   // The directory where Jest should output its coverage files
+   coverageDirectory: 'coverage',
+
+   // An array of regexp pattern strings used to skip coverage collection
+   // coveragePathIgnorePatterns: [
+   //   "\\\\node_modules\\\\"
+   // ],
+
+   // Indicates which provider should be used to instrument code for coverage
+   // coverageProvider: "babel",
+
+   // A list of reporter names that Jest uses when writing coverage reports
+   coverageReporters: [
+      "text-summary",
+      "lcov",
+   ],
+
+   // An object that configures minimum threshold enforcement for coverage results
+   // coverageThreshold: undefined,
+
+   // A path to a custom dependency extractor
+   // dependencyExtractor: undefined,
+
+   // Make calling deprecated APIs throw helpful error messages
+   // errorOnDeprecated: false,
+
+   // Force coverage collection from ignored files using an array of glob patterns
+   // forceCoverageMatch: [],
+
+   // A path to a module which exports an async function that is triggered once before all test suites
+   // globalSetup: undefined,
+
+   // A path to a module which exports an async function that is triggered once after all test suites
+   // globalTeardown: undefined,
+
+   // A set of global variables that need to be available in all test environments
+   // globals: {},
+
+   // The maximum amount of workers used to run your tests. Can be specified as % or a number. E.g. maxWorkers: 10% will use 10% of your CPU amount + 1 as the maximum worker number. maxWorkers: 2 will use a maximum of 2 workers.
+   // maxWorkers: "50%",
+
+   // An array of directory names to be searched recursively up from the requiring module's location
+   // moduleDirectories: [
+   //   "node_modules"
+   // ],
+
+   // An array of file extensions your modules use
+   // moduleFileExtensions: [
+   //   "js",
+   //   "json",
+   //   "jsx",
+   //   "ts",
+   //   "tsx",
+   //   "node"
+   // ],
+
+   // A map from regular expressions to module names or to arrays of module names that allow to stub out resources with a single module
+   //moduleNameMapper: pathsToModuleNameMapper(compilerOptions.paths, {prefix: '<rootDir>/src/'}),
+
+   // An array of regexp pattern strings, matched against all module paths before considered 'visible' to the module loader
+   // modulePathIgnorePatterns: [],
+
+   // Activates notifications for test results
+   // notify: false,
+
+   // An enum that specifies notification mode. Requires { notify: true }
+   // notifyMode: "failure-change",
+
+   // A preset that is used as a base for Jest's configuration
+   preset: 'ts-jest',
+
+   // Run tests from one or more projects
+   // projects: undefined,
+
+   // Use this configuration option to add custom reporters to Jest
+   // reporters: undefined,
+
+   // Automatically reset mock state between every test
+   // resetMocks: false,
+
+   // Reset the module registry before running each individual test
+   // resetModules: false,
+
+   // A path to a custom resolver
+   // resolver: undefined,
+
+   // Automatically restore mock state between every test
+   // restoreMocks: false,
+
+   // The root directory that Jest should scan for tests and modules within
+   // rootDir: './src',
+
+   // A list of paths to directories that Jest should use to search for files in
+   // roots: [
+   //   "<rootDir>"
+   // ],
+
+   // Allows you to use a custom runner instead of Jest's default test runner
+   // runner: "jest-runner",
+
+   // The paths to modules that run some code to configure or set up the testing environment before each test
+   // setupFiles: [],
+
+   // A list of paths to modules that run some code to configure or set up the testing framework before each test
+   setupFilesAfterEnv: [
+      "./jest.setup.ts"
+   ],
+
+   // The number of seconds after which a test is considered as slow and reported as such in the results.
+   // slowTestThreshold: 5,
+
+   // A list of paths to snapshot serializer modules Jest should use for snapshot testing
+   // snapshotSerializers: [],
+
+   // The test environment that will be used for testing
+   testEnvironment: "node",
+
+   // Options that will be passed to the testEnvironment
+   // testEnvironmentOptions: {},
+
+   // Adds a location field to test results
+   // testLocationInResults: false,
+
+   // The glob patterns Jest uses to detect test files
+   testMatch: [
+     "**/*.spec.ts",
+   ],
+
+   // An array of regexp pattern strings that are matched against all test paths, matched tests are skipped
+   // testPathIgnorePatterns: [
+   //   "\\\\node_modules\\\\"
+   // ],
+
+   // The regexp pattern or array of patterns that Jest uses to detect test files
+   // testRegex: [],
+
+   // This option allows the use of a custom results processor
+   // testResultsProcessor: undefined,
+
+   // This option allows use of a custom test runner
+   // testRunner: "jasmine2",
+
+   // This option sets the URL for the jsdom environment. It is reflected in properties such as location.href
+   // testURL: "http://localhost",
+
+   // Setting this value to "fake" allows the use of fake timers for functions such as "setTimeout"
+   // timers: "real",
+
+   // A map from regular expressions to paths to transformers
+   // transform: undefined,
+
+   // An array of regexp pattern strings that are matched against all source file paths, matched files will skip transformation
+   // transformIgnorePatterns: [
+   //   "\\\\node_modules\\\\",
+   //   "\\.pnp\\.[^\\\\]+$"
+   // ],
+
+   // An array of regexp pattern strings that are matched against all modules before the module loader will automatically return a mock for them
+   // unmockedModulePathPatterns: undefined,
+
+   // Indicates whether each individual test should be reported during the run
+   // verbose: undefined,
+
+   // An array of regexp patterns that are matched against all source file paths before re-running tests in watch mode
+   // watchPathIgnorePatterns: [],
+
+   // Whether to use watchman for file crawling
+   // watchman: true,
+ };

jest.setup.ts

@@ -0,0 +1,2 @@
+import 'reflect-metadata';
+import './src/containers';

ormconfig.json

@@ -0,0 +1,13 @@
+{
+  "type": "mongodb",
+  "host": "mongo",
+  "port": 27017,
+  "username": "",
+  "password": "",
+  "database": "db-extract-pdf",
+  "synchronize": false,
+  "logging": false,
+  "entities": [
+     "src/modules/**/typeorm/entities/*.ts"
+  ]
+}

package.json

@@ -0,0 +1,72 @@
+{
+  "name": "nome-do-projeto",
+  "version": "1.0.0",
+  "description": "Extraçao de dados de arquivos PDF",
+  "main": "server.js",
+  "author": "Daniel Souza <daniel.souza@tron.com.br>",
+  "license": "MIT",
+  "private": true,
+  "scripts": {
+    "build": "rm -rf ./dist && babel src --extensions \".js,.ts\" --out-dir dist --copy-files",
+    "start": "NODE_ENV=production node ./src/http/server.ts",
+    "dev:server": "cross-env NODE_ENV=development ts-node-dev -r tsconfig-paths/register --inspect --respawn --transpile-only --ignore-watch node_modules ./src/http/server.ts",
+    "docker:run": "docker-compose -f ./docker-compose.yaml down && docker-compose -f ./docker-compose.yaml up --build -d",
+    "docker:logs": "docker logs -f nome-do-projeto",
+    "docker:server": "yarn docker:run && yarn docker:logs",
+    "docker:bash": "docker exec -it nome-do-projeto bash",
+    "docker:test": "docker-compose -f ./docker-compose.yaml up --build -d && docker exec -it nome-do-projeto yarn test",
+    "test": "jest"
+  },
+  "dependencies": {
+    "@types/mongodb": "^3.6.0",
+    "axios": "^0.20.0",
+    "cors": "^2.8.5",
+    "date-fns": "^2.16.1",
+    "dotenv": "^8.2.0",
+    "express": "^4.17.1",
+    "express-async-errors": "^3.1.1",
+    "mongodb": "^3.6.3",
+    "multer": "^1.4.2",
+    "pdf-parse": "^1.1.1",
+    "reflect-metadata": "^0.1.13",
+    "tsyringe": "^4.3.0",
+    "typeorm": "^0.2.29",
+    "uuid": "^8.3.1",
+    "yup": "^0.31.1"
+  },
+  "devDependencies": {
+    "@babel/cli": "^7.12.1",
+    "@babel/core": "^7.12.3",
+    "@babel/node": "^7.12.1",
+    "@babel/plugin-proposal-class-properties": "^7.12.1",
+    "@babel/plugin-proposal-decorators": "^7.12.1",
+    "@babel/plugin-transform-typescript": "^7.12.1",
+    "@babel/preset-env": "^7.12.1",
+    "@babel/preset-typescript": "^7.12.1",
+    "@types/cors": "^2.8.7",
+    "@types/express": "^4.17.8",
+    "@types/jest": "^26.0.19",
+    "@types/multer": "^1.4.4",
+    "@types/pdf-parse": "^1.1.0",
+    "@types/pdfjs-dist": "^2.1.7",
+    "@types/uuid": "^8.3.0",
+    "@types/yup": "^0.29.9",
+    "@typescript-eslint/eslint-plugin": "^4.4.0",
+    "@typescript-eslint/parser": "^4.4.0",
+    "babel-plugin-module-resolver": "^4.0.0",
+    "babel-plugin-transform-typescript-metadata": "^0.3.1",
+    "babel-preset-const-enum": "^1.0.0",
+    "cross-env": "^7.0.2",
+    "eslint": "6.8.0",
+    "eslint-config-airbnb-base": "^14.2.0",
+    "eslint-config-prettier": "^6.11.0",
+    "eslint-import-resolver-typescript": "^2.2.1",
+    "eslint-plugin-import": "^2.21.2",
+    "eslint-plugin-prettier": "^3.1.4",
+    "jest": "^26.6.3",
+    "prettier": "^2.1.0",
+    "ts-jest": "^26.4.4",
+    "ts-node-dev": "^1.0.0-pre.63",
+    "typescript": "^4.0.3"
+  }
+}

prettier.config.js

@@ -0,0 +1,6 @@
+module.exports = {
+  singleQuote: true,
+  trailingComma: 'all',
+  arrowParens: 'avoid',
+  printWidth: 100,
+}

src/__tests__/resources/recibo-pagamento-data.json

@@ -0,0 +1,224 @@
+[
+  {
+      "company": {
+          "name": "INSTITUTO DE EDUCACAO VOOS OLYMPIO LTDA",
+          "code": "00261",
+          "cnpj": "31001804000139",
+          "refEndDate": "2020-10-31",
+          "refStartDate": "2020-10-01",
+          "address": "COND SOLAR DE BRASILIA QD 02 BL B, 207 LOTES 3 E 4"
+      },
+      "employee": {
+          "code": "000001",
+          "name": "RAPHAEL VOOS LENZI",
+          "salary": 3000,
+          "role": "SUPERVISOR PEDAGOGICO",
+          "admissionDate": "01/09/2018",
+          "baseINSS": 3000,
+          "aliquotINSS": 9.3873,
+          "baseFGTS": 3000,
+          "valueFGTS": 240,
+          "baseIRRF": 2718.38,
+          "events": [
+              {
+                  "code": "001",
+                  "description": "Salário Base",
+                  "discount": 0,
+                  "eventReference": "",
+                  "earnings": 3000
+              },
+              {
+                  "code": "615",
+                  "description": "TAXA ASSISTENCIAL 2%",
+                  "discount": 60,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "903",
+                  "description": "INSS Folha",
+                  "discount": 281.62,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "914",
+                  "description": "IRRF Folha",
+                  "discount": 61.08,
+                  "eventReference": "",
+                  "earnings": 0
+              }
+          ]
+      }
+  },
+  {
+      "company": {
+          "name": "INSTITUTO DE EDUCACAO VOOS OLYMPIO LTDA",
+          "code": "00261",
+          "cnpj": "31001804000139",
+          "refEndDate": "2020-10-31",
+          "refStartDate": "2020-10-01",
+          "address": "COND SOLAR DE BRASILIA QD 02 BL B, 207 LOTES 3 E 4"
+      },
+      "employee": {
+          "code": "000005",
+          "name": "MARIA BÁRBARA SEIXO DE BRITTO DE MELO",
+          "salary": 1536.9,
+          "role": "ASSISTENTE ADMINISTRATIVO",
+          "admissionDate": "02/01/2019",
+          "baseINSS": 640.37,
+          "aliquotINSS": 7.5,
+          "baseFGTS": 640.37,
+          "valueFGTS": 51.22,
+          "baseIRRF": 592.35,
+          "events": [
+              {
+                  "code": "001",
+                  "description": "Salário Base",
+                  "discount": 0,
+                  "eventReference": "",
+                  "earnings": 640.37
+              },
+              {
+                  "code": "637",
+                  "description": "PLANO DE SAÚDE",
+                  "discount": 202.51,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "604",
+                  "description": "Vale Transporte 6%",
+                  "discount": 38.42,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "615",
+                  "description": "TAXA ASSISTENCIAL 2%",
+                  "discount": 30.72,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "903",
+                  "description": "INSS Folha",
+                  "discount": 48.02,
+                  "eventReference": "",
+                  "earnings": 0
+              }
+          ]
+      }
+  },
+  {
+      "company": {
+          "name": "INSTITUTO DE EDUCACAO VOOS OLYMPIO LTDA",
+          "code": "00261",
+          "cnpj": "31001804000139",
+          "refEndDate": "2020-10-31",
+          "refStartDate": "2020-10-01",
+          "address": "COND SOLAR DE BRASILIA QD 02 BL B, 207 LOTES 3 E 4"
+      },
+      "employee": {
+          "code": "000011",
+          "name": "VALDIRA PEREIRA",
+          "salary": 1229.52,
+          "role": "AUXILIAR DE SERVIÇOS GERAIS",
+          "admissionDate": "16/10/2019",
+          "baseINSS": 512.29,
+          "aliquotINSS": 7.5,
+          "baseFGTS": 512.29,
+          "valueFGTS": 40.98,
+          "baseIRRF": 284.28,
+          "events": [
+              {
+                  "code": "001",
+                  "description": "Salário Base",
+                  "discount": 0,
+                  "eventReference": "",
+                  "earnings": 512.29
+              },
+              {
+                  "code": "599",
+                  "description": "Salário Família",
+                  "discount": 0,
+                  "eventReference": "001,00",
+                  "earnings": 48.62
+              },
+              {
+                  "code": "604",
+                  "description": "Vale Transporte 6%",
+                  "discount": 30.73,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "615",
+                  "description": "TAXA ASSISTENCIAL 2%",
+                  "discount": 24.6,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "903",
+                  "description": "INSS Folha",
+                  "discount": 38.42,
+                  "eventReference": "",
+                  "earnings": 0
+              }
+          ]
+      }
+  },
+  {
+      "company": {
+          "name": "INSTITUTO DE EDUCACAO VOOS OLYMPIO LTDA",
+          "code": "00261",
+          "cnpj": "31001804000139",
+          "refEndDate": "2020-10-31",
+          "refStartDate": "2020-10-01",
+          "address": "COND SOLAR DE BRASILIA QD 02 BL B, 207 LOTES 3 E 4"
+      },
+      "employee": {
+          "code": "000012",
+          "name": "BRUNO LINS VOOS",
+          "salary": 1536.9,
+          "role": "CONSULTOR DE VENDAS",
+          "admissionDate": "13/01/2020",
+          "baseINSS": 640.37,
+          "aliquotINSS": 7.5,
+          "baseFGTS": 640.37,
+          "valueFGTS": 51.22,
+          "baseIRRF": 592.35,
+          "events": [
+              {
+                  "code": "001",
+                  "description": "Salário Base",
+                  "discount": 0,
+                  "eventReference": "",
+                  "earnings": 640.37
+              },
+              {
+                  "code": "604",
+                  "description": "Vale Transporte 6%",
+                  "discount": 38.42,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "615",
+                  "description": "TAXA ASSISTENCIAL 2%",
+                  "discount": 30.72,
+                  "eventReference": "",
+                  "earnings": 0
+              },
+              {
+                  "code": "903",
+                  "description": "INSS Folha",
+                  "discount": 48.02,
+                  "eventReference": "",
+                  "earnings": 0
+              }
+          ]
+      }
+  }
+]

src/__tests__/services/mapaFolha/ExtractDataPDFMapaFolhaService.spec.ts

@@ -0,0 +1,107 @@
+import { container } from 'tsyringe';
+import path from 'path';
+import { promises as fs } from 'fs';
+import { Readable } from 'stream';
+import AppError from '../../../erros/AppError';
+import ExtractDataPDFMapaFolhaService from '../../../services/mapaFolha/ExtractDataPDFMapaFolhaService';
+import reciboPagamentoData from '../../resources/recibo-pagamento-data.json';
+
+describe('Mapa Folha - ExtractDataPDFMapaFolhaService', () => {
+  afterEach(() => {
+    jest.restoreAllMocks();
+  });
+
+  it('Deve ser capaz de extrair os dados do PDF do mapa da folha ', async () => {
+    const extractDataPDFMapaFolha = container.resolve(ExtractDataPDFMapaFolhaService);
+
+    const filePath = path.resolve(__dirname, '..', '..', 'resources', 'recibo-pagamento.pdf');
+
+    const file = await fs.readFile(filePath);
+    const { size } = await fs.stat(filePath);
+    const readableStream = new Readable();
+
+    const fileMulter: Express.Multer.File = {
+      fieldname: 'pdf',
+      originalname: 'report-mapa-folha.pdf',
+      encoding: 'utf-8',
+      mimetype: 'application/pdf',
+      size,
+      stream: readableStream,
+      destination: filePath,
+      filename: 'report-mapa-folha.pdf',
+      path: filePath,
+      buffer: file,
+    };
+
+    const data = await extractDataPDFMapaFolha.execute({
+      files: [fileMulter],
+    });
+
+    expect(data).toEqual(expect.arrayContaining(reciboPagamentoData));
+  });
+
+  it('Deve gerar uma exceção caso não seja passado o arquivo ', async () => {
+    const params = {} as { files: Express.Multer.File[] };
+
+    const extractDataPDFMapaFolha = container.resolve(ExtractDataPDFMapaFolhaService);
+
+    await expect(extractDataPDFMapaFolha.execute(params)).rejects.toBeInstanceOf(AppError);
+  });
+
+  it('Deve gerar uma exceção caso o arquivo não seja um PDF 1', async () => {
+    const extractDataPDFMapaFolha = container.resolve(ExtractDataPDFMapaFolhaService);
+
+    const filePath = path.resolve(__dirname, '..', '..', 'resources', 'recibo-pagamento-data.json');
+
+    const file = await fs.readFile(filePath);
+    const { size } = await fs.stat(filePath);
+    const readableStream = new Readable();
+
+    const fileMulter: Express.Multer.File = {
+      fieldname: 'pdf',
+      originalname: 'recibo-pagamento-data.json',
+      encoding: 'utf-8',
+      mimetype: 'application/json',
+      size,
+      stream: readableStream,
+      destination: filePath,
+      filename: 'recibo-pagamento-data.json',
+      path: filePath,
+      buffer: file,
+    };
+
+    await expect(extractDataPDFMapaFolha.execute({ files: [fileMulter] })).rejects.toBeInstanceOf(
+      AppError,
+    );
+  });
+
+  it('Não deve gerar uma exceção caso receba um PDF diferente do experado ', async () => {
+    const extractDataPDFMapaFolha = container.resolve(ExtractDataPDFMapaFolhaService);
+
+    const filePath = path.resolve(__dirname, '..', '..', 'resources', 'empty-pdf.pdf');
+
+    const file = await fs.readFile(filePath);
+    const { size } = await fs.stat(filePath);
+
+    const readableStream = new Readable();
+
+    const fileMulter: Express.Multer.File = {
+      fieldname: 'pdf',
+      originalname: 'empty-pdf.pdf',
+      encoding: 'utf-8',
+      mimetype: 'application/pdf',
+      size,
+      stream: readableStream,
+      destination: filePath,
+      filename: 'empty-pdf.pdf',
+      path: filePath,
+      buffer: file,
+    };
+
+    const data = await extractDataPDFMapaFolha.execute({
+      files: [fileMulter],
+    });
+
+    expect(data).toEqual([]);
+  });
+});

src/config/upload.ts

@@ -0,0 +1,22 @@
+import multer from 'multer';
+import crypto from 'crypto';
+import os from 'os';
+
+const tmpFolder = os.tmpdir();
+
+export default {
+  tempdir: {
+    directory: tmpFolder,
+
+    storage: multer.diskStorage({
+      destination: tmpFolder,
+      filename(request, file, callback) {
+        const fileHash = crypto.randomBytes(10).toString('hex');
+        const originalname = file.originalname.replace(/[^0-9-a-zA-Z.]/g, '-');
+        const filename = `${fileHash}-${originalname}`;
+
+        return callback(null, filename);
+      },
+    }),
+  },
+};

src/containers/index.ts

@@ -0,0 +1,5 @@
+import { container } from 'tsyringe';
+import IPdfToTextProvider from './providers/pdfToText/IPdfToTextProvider';
+import LinuxPdfToText from './providers/pdfToText/implementations/LinuxPdfToText';
+
+container.registerSingleton<IPdfToTextProvider>('PdfToTextProvider', LinuxPdfToText);

src/containers/providers/pdfToText/IPdfToTextProvider.ts

@@ -0,0 +1,5 @@
+import IOptionsPdfParseDTO from './dto/IOptionsPdfParseDTO';
+
+export default interface IPdfToTextProvider {
+  extract(filePath: string, options?: IOptionsPdfParseDTO): Promise<string>;
+}

src/containers/providers/pdfToText/dto/IOptionsPdfParseDTO.ts

@@ -0,0 +1,3 @@
+export default interface IOptionsPdfParseDTO {
+  pageNumber?: number;
+}

src/containers/providers/pdfToText/implementations/LinuxPdfToText.ts

@@ -0,0 +1,32 @@
+import fs from 'fs';
+import { v4 } from 'uuid';
+import os from 'os';
+import { exec } from 'child_process';
+import path from 'path';
+
+import IPdfToTextProvider from '../IPdfToTextProvider';
+import IOptionsPdfParseDTO from '../dto/IOptionsPdfParseDTO';
+
+export default class LinuxPdfToText implements IPdfToTextProvider {
+  public async extract(filePath: string, options: IOptionsPdfParseDTO = {}): Promise<string> {
+    const tempTextFile = path.resolve(os.tmpdir(), v4());
+    const { pageNumber } = options;
+
+    const pageNumberOption = pageNumber !== undefined ? `-f ${pageNumber} -l ${pageNumber}` : '';
+
+    const command = `pdftotext -layout  ${pageNumberOption} ${filePath} ${tempTextFile}`;
+
+    return new Promise((resolve, reject) => {
+      exec(command, async err => {
+        if (err) {
+          return reject(err);
+        }
+
+        const contentFile = await fs.promises.readFile(tempTextFile);
+
+        await fs.promises.unlink(tempTextFile);
+        return resolve(contentFile.toString());
+      });
+    });
+  }
+}

src/containers/providers/pdfToText/implementations/PdfParseProvider.ts

@@ -0,0 +1,13 @@
+import pdfParse from 'pdf-parse';
+import fs from 'fs';
+import IPdfToTextProvider from '../IPdfToTextProvider';
+
+export default class PdfParseProvider implements IPdfToTextProvider {
+  public async extract(filePath: string): Promise<string> {
+    const dataBuffer = fs.readFileSync(filePath);
+
+    const data = await pdfParse(dataBuffer);
+
+    return data.text;
+  }
+}

src/erros/AppError.ts

@@ -0,0 +1,10 @@
+export default class AppError {
+  public readonly message: string;
+
+  public readonly statusCode: number;
+
+  public constructor(message: string, statusCode = 400) {
+    this.message = message;
+    this.statusCode = statusCode;
+  }
+}

src/http/controllers/ExempleController.ts

@@ -0,0 +1,15 @@
+import { Request, Response } from 'express';
+import { container } from 'tsyringe';
+import ExempleService from '../../services/exemple/ExempleService';
+
+export default class ExempleController {
+  public async exemple(request: Request, response: Response): Promise<Response> {
+    const files = Array.isArray(request.files) ? request.files : request.files.pdf;
+
+    const exemple = container.resolve(ExempleService);
+
+    const responseData = await exemple.execute({ files });
+
+    return response.json(responseData);
+  }
+}

src/http/middlewares/error.ts

@@ -0,0 +1,23 @@
+import { Response, Request, NextFunction } from 'express';
+import AppError from '../../erros/AppError';
+
+export default function error(
+  err: Error,
+  _request: Request,
+  response: Response,
+  _next: NextFunction,
+): Response {
+  if (err instanceof AppError) {
+    return response.status(err.statusCode).json({
+      status: 'error',
+      message: err.message,
+    });
+  }
+
+  console.error(err);
+
+  return response.status(500).json({
+    status: 'error',
+    message: 'Internal server error',
+  });
+}

src/http/routes/exemple.routes.ts

@@ -0,0 +1,12 @@
+import { Router } from 'express';
+import multer from 'multer';
+import uploadConfig from '../../config/upload';
+import ExempleController from '../controllers/ExempleController';
+
+const exempleRoutes = Router();
+const exempleController = new ExempleController();
+const upload = multer(uploadConfig.tempdir);
+
+exempleRoutes.post('/exemple', upload.array('pdf'), exempleController.exemple);
+
+export default exempleRoutes;

src/http/routes/index.ts

@@ -0,0 +1,8 @@
+import { Router } from 'express';
+import exempleRoutes from './exemple.routes';
+
+const routes = Router();
+
+routes.use('/exemple', exempleRoutes);
+
+export default routes;

src/http/server.ts

@@ -0,0 +1,22 @@
+import 'reflect-metadata';
+import 'express-async-errors';
+import 'dotenv/config';
+import '../containers';
+
+import express from 'express';
+import cors from 'cors';
+import net from 'net';
+import error from './middlewares/error';
+import routes from './routes';
+
+const app = express();
+app.use(cors());
+app.use(express.json({ limit: '50MB' }));
+app.use(routes);
+app.use(error);
+
+const listener = app.listen(3333, () => {
+  const { port } = listener.address() as net.AddressInfo;
+
+  console.log(`Server started on port ${port}`);
+});

src/services/exemple/ExempleService.ts

@@ -0,0 +1,58 @@
+import { inject, injectable } from 'tsyringe';
+import AppError from '../../erros/AppError';
+import IPdfToTextProvider from '../../containers/providers/pdfToText/IPdfToTextProvider';
+import regexMapaFolha from '../../utils/regex/regexMapaFolha';
+import * as format from '../../utils/format';
+
+interface IRequest {
+  files: Express.Multer.File[];
+}
+
+interface ICompanyContent {
+  name: string;
+  code: string;
+  cnpj: string;
+  refEndDate: string;
+  refStartDate: string;
+  address: string;
+  contentEmployee: string;
+}
+
+type IResponse = Array<{
+  fileName: string;
+  content: string;
+}>;
+
+@injectable()
+export default class ExempleService {
+  constructor(
+    @inject('PdfToTextProvider')
+    private pdfToTextProvider: IPdfToTextProvider,
+  ) {}
+
+  public async execute({ files }: IRequest): Promise<IResponse> {
+    if (!files) {
+      throw new AppError('File is required');
+    }
+
+    files.forEach(file => {
+      if (file.mimetype !== 'application/pdf') {
+        throw new AppError('Only PDF is accepted');
+      }
+    });
+
+    const response: IResponse = [];
+
+    for (let indexFile = 0; indexFile < files.length; indexFile++) {
+      const file = files[indexFile];
+      const contentFile = await this.pdfToTextProvider.extract(file.path);
+
+      response.push({
+        fileName: file.filename,
+        content: contentFile,
+      });
+    }
+
+    return response;
+  }
+}

src/utils/date/dates.ts

@@ -0,0 +1,16 @@
+const dates = [
+  { description: 'janeiro', value: 1 },
+  { description: 'fevereiro', value: 2 },
+  { description: 'março', value: 3 },
+  { description: 'abril', value: 4 },
+  { description: 'maio', value: 5 },
+  { description: 'junho', value: 6 },
+  { description: 'julho', value: 7 },
+  { description: 'agosto', value: 8 },
+  { description: 'setembro', value: 9 },
+  { description: 'outubro', value: 10 },
+  { description: 'novembro', value: 11 },
+  { description: 'dezembro', value: 12 },
+];
+
+export default dates;

src/utils/format/index.ts

@@ -0,0 +1,33 @@
+import dates from '../date/dates';
+
+export const registryRemoveMask = (cnpj: string): string => cnpj?.replace(/\D/gm, '') || '';
+
+export const competenceDescriptionToDate = (competenceDescription: string): string => {
+  const [monthDescription, year] = competenceDescription.split('de');
+
+  const month = dates.find(date => {
+    const dateDescriptionNormalized = date.description.toLocaleLowerCase('en-US').trim();
+    const monthDescriptionNormalized = monthDescription.toLocaleLowerCase('en-US').trim();
+
+    return dateDescriptionNormalized === monthDescriptionNormalized;
+  })?.value;
+
+  const monthFormatted = `00${month}`.slice(-2);
+
+  return `${monthFormatted}/${year.trim()}`;
+};
+
+export const brazilianDateToEnglish = (brazilianDate: string): string => {
+  const date = brazilianDate || '';
+  const [day, month, year] = date.split('/');
+
+  return day && month && year ? `${year}-${month}-${day}` : '';
+};
+
+export const brazilianMoneyToNumber = (money: string): number => {
+  const value = money?.replace(/\./gm, '').replace(/,/, '.');
+
+  return value ? Number(value) : 0;
+};
+
+export default {};

src/utils/regex/regexMapaFolha.ts

@@ -0,0 +1,39 @@
+const regexMapaFolha = {
+  companyName: (): RegExp => /Empresa\s*:\s*(?<companyName>.*?)\s*\(\s*(\d{1,})\s*\)\s*Página/gm,
+
+  companyCode: (): RegExp => /Empresa\s*:\s*.*?\s*\(\s*(?<companyCode>\d{1,})\s*\)\s*Página/gm,
+
+  companyAddress: (): RegExp => /End\.\s*:\s*(?<companyAddress>.*?)CNPJ\/CEI/gm,
+
+  /**
+   * Em caso de endereços grande pode quebrar o CNPJ por isso estou pegando qualquer ocorrencia de 14 caracteres numericos entre "CNPJ/CEI" e "Ref"
+   * até o momento não teve caso de partir o cnpj no meio
+   */
+  companyCNPJ: (): RegExp => /CNPJ\/CEI:((.|\n)*?)(?<companyCNPJ>\d{14})((.|\n)*?)Ref\.:/gm,
+
+  reportReference: (): RegExp =>
+    /Ref\.:\s*(?<refStartDate>\d{2}\/\d{2}\/\d{4})\s*a\s*(?<refEndDate>\d{2}\/\d{2}\/\d{4})/gm,
+
+  contentEmployePage: (): RegExp =>
+    /Ref\.:\s*\d{2}\/\d{2}\/\d{4}\s*a\s*\d{2}\/\d{2}\/\d{4}(.*?)\n{1,}(?<contentEmployePage>(.|\n)*)/gm,
+
+  employeeInfo: (): RegExp =>
+    /^(?<employeeCode>\d{1,})\s*(?<employeeName>.*?)(?<employeeSalary>(\.?\d{1,}){1,},\d{2})\s*Função\s*:(?<employeeRole>(.|\n)*?)(?<employeeContentRest>Livro(.|\n)*?Base INSS:.*$)/gm,
+
+  employeeAdmissionDate: (): RegExp =>
+    /Admissão\s*:\s*(?<employeeAdmissionDate>\d{2}\/\d{2}\/\d{4})/gm,
+
+  employeeEvents: (): RegExp => /Admissão\s*:(.*?)\n(?<events>(.|\n)*?)(.*)\n\s*\*{5,}/gm,
+
+  eventReference: (): RegExp => /.*?\s{2,}(?<eventReference>.*?)\s{2,}.*/g,
+
+  eventInfo: (): RegExp => /^(?<eventCode>\d{1,})\s*(?<eventDescription>(.*?))\s{2}/g,
+
+  inss: (): RegExp => /Base\sINSS:(?<baseINSS>.*?)\(Aliq\.:(?<aliquotINSS>(.*?))%\)/gm,
+
+  fgts: (): RegExp => /Base\sFGTS:(?<baseFGTS>.*?)\(Valor:(?<valueFGTS>(.*?))\)/gm,
+
+  baseIRRF: (): RegExp => /Base\sIRRF\sFolha:\s(?<baseIRRF>.{1,15})/gm,
+};
+
+export default regexMapaFolha;

tsconfig.json

@@ -0,0 +1,16 @@
+{
+  "compilerOptions": {
+    "target": "es5",
+    "module": "commonjs",
+    "outDir": "./dist",
+    "strict": true,
+    "strictPropertyInitialization": false,
+    "resolveJsonModule": true,
+    "esModuleInterop": true,
+    "experimentalDecorators": true,
+    "emitDecoratorMetadata": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "allowJs": true
+  }
+}