Compare commits

...

11 Commits

Author SHA1 Message Date
d86a83d515 update description 2024-05-29 14:15:11 +02:00
8dd9bea8bb 1.0.9 2024-04-18 16:43:32 +02:00
1ddb442661 fix(core): update 2024-04-18 16:43:32 +02:00
871f152f2d update tsconfig 2024-04-14 18:05:46 +02:00
215273b44d update npmextra.json: githost 2024-04-01 21:37:04 +02:00
aa915b2a61 update npmextra.json: githost 2024-04-01 19:59:10 +02:00
7e169b4972 update npmextra.json: githost 2024-03-30 21:48:10 +01:00
f5d1becf03 switch to new org scheme 2023-07-11 01:20:29 +02:00
14618e7f8e switch to new org scheme 2023-07-10 10:17:06 +02:00
45ea0ff83f 1.0.8 2021-12-01 02:57:58 +01:00
ae65fcdcb5 fix(core): update 2021-12-01 02:57:57 +01:00
17 changed files with 5038 additions and 27353 deletions

View File

@ -0,0 +1,66 @@
name: Default (not tags)
on:
push:
tags-ignore:
- '**'
env:
IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci
NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git
NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
NPMCI_URL_CLOUDLY: ${{secrets.NPMCI_URL_CLOUDLY}}
jobs:
security:
runs-on: ubuntu-latest
continue-on-error: true
container:
image: ${{ env.IMAGE }}
steps:
- uses: actions/checkout@v3
- name: Install pnpm and npmci
run: |
pnpm install -g pnpm
pnpm install -g @shipzone/npmci
- name: Run npm prepare
run: npmci npm prepare
- name: Audit production dependencies
run: |
npmci command npm config set registry https://registry.npmjs.org
npmci command pnpm audit --audit-level=high --prod
continue-on-error: true
- name: Audit development dependencies
run: |
npmci command npm config set registry https://registry.npmjs.org
npmci command pnpm audit --audit-level=high --dev
continue-on-error: true
test:
if: ${{ always() }}
needs: security
runs-on: ubuntu-latest
container:
image: ${{ env.IMAGE }}
steps:
- uses: actions/checkout@v3
- name: Test stable
run: |
npmci node install stable
npmci npm install
npmci npm test
- name: Test build
run: |
npmci node install stable
npmci npm install
npmci npm build

View File

@ -0,0 +1,124 @@
name: Default (tags)
on:
push:
tags:
- '*'
env:
IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci
NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git
NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
NPMCI_URL_CLOUDLY: ${{secrets.NPMCI_URL_CLOUDLY}}
jobs:
security:
runs-on: ubuntu-latest
continue-on-error: true
container:
image: ${{ env.IMAGE }}
steps:
- uses: actions/checkout@v3
- name: Prepare
run: |
pnpm install -g pnpm
pnpm install -g @shipzone/npmci
npmci npm prepare
- name: Audit production dependencies
run: |
npmci command npm config set registry https://registry.npmjs.org
npmci command pnpm audit --audit-level=high --prod
continue-on-error: true
- name: Audit development dependencies
run: |
npmci command npm config set registry https://registry.npmjs.org
npmci command pnpm audit --audit-level=high --dev
continue-on-error: true
test:
if: ${{ always() }}
needs: security
runs-on: ubuntu-latest
container:
image: ${{ env.IMAGE }}
steps:
- uses: actions/checkout@v3
- name: Prepare
run: |
pnpm install -g pnpm
pnpm install -g @shipzone/npmci
npmci npm prepare
- name: Test stable
run: |
npmci node install stable
npmci npm install
npmci npm test
- name: Test build
run: |
npmci node install stable
npmci npm install
npmci npm build
release:
needs: test
if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
runs-on: ubuntu-latest
container:
image: ${{ env.IMAGE }}
steps:
- uses: actions/checkout@v3
- name: Prepare
run: |
pnpm install -g pnpm
pnpm install -g @shipzone/npmci
npmci npm prepare
- name: Release
run: |
npmci node install stable
npmci npm publish
metadata:
needs: test
if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
runs-on: ubuntu-latest
container:
image: ${{ env.IMAGE }}
continue-on-error: true
steps:
- uses: actions/checkout@v3
- name: Prepare
run: |
pnpm install -g pnpm
pnpm install -g @shipzone/npmci
npmci npm prepare
- name: Code quality
run: |
npmci command npm install -g typescript
npmci npm install
- name: Trigger
run: npmci trigger
- name: Build docs and upload artifacts
run: |
npmci node install stable
npmci npm install
pnpm install -g @git.zone/tsdoc
npmci command tsdoc
continue-on-error: true

View File

@ -125,7 +125,7 @@ pages:
stage: metadata
script:
- npmci node install lts
- npmci command npm install -g @gitzone/tsdoc
- npmci command npm install -g @git.zone/tsdoc
- npmci npm prepare
- npmci npm install
- npmci command tsdoc

View File

@ -2,17 +2,31 @@
"gitzone": {
"projectType": "npm",
"module": {
"githost": "gitlab.com",
"gitscope": "pushrocks",
"githost": "code.foss.global",
"gitscope": "push.rocks",
"gitrepo": "smartocr",
"shortDescription": "an ocr module using ocrmypdf",
"npmPackagename": "@pushrocks/smartocr",
"npmPackagename": "@push.rocks/smartocr",
"license": "MIT",
"projectDomain": "push.rocks"
"projectDomain": "push.rocks",
"description": "A module that performs optical character recognition (OCR) using ocrmypdf.",
"keywords": [
"OCR",
"optical character recognition",
"ocrmypdf",
"text extraction",
"PDF processing",
"machine learning",
"document analysis",
"text recognition"
]
}
},
"npmci": {
"npmGlobalTools": [],
"npmAccessLevel": "public"
},
"tsdoc": {
"legal": "\n## License and Legal Information\n\nThis repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. \n\n**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.\n\n### Trademarks\n\nThis project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.\n\n### Company Information\n\nTask Venture Capital GmbH \nRegistered at District court Bremen HRB 35230 HB, Germany\n\nFor any legal inquiries or if you require further information, please contact us via email at hello@task.vc.\n\nBy using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.\n"
}
}

27270
package-lock.json generated

File diff suppressed because it is too large Load Diff

View File

@ -1,30 +1,31 @@
{
"name": "@pushrocks/smartocr",
"version": "1.0.7",
"name": "@push.rocks/smartocr",
"version": "1.0.9",
"private": false,
"description": "an ocr module using ocrmypdf",
"description": "A module that performs optical character recognition (OCR) using ocrmypdf.",
"main": "dist_ts/index.js",
"typings": "dist_ts/index.d.ts",
"author": "Lossless GmbH",
"license": "MIT",
"scripts": {
"test": "(tstest test/ --web)",
"build": "(tsbuild --web)"
"build": "(tsbuild --web)",
"buildDocs": "tsdoc"
},
"devDependencies": {
"@gitzone/tsbuild": "^2.1.25",
"@gitzone/tsbundle": "^1.0.78",
"@gitzone/tstest": "^1.0.44",
"@pushrocks/tapbundle": "^3.2.9",
"@types/node": "^16.11.11",
"tslint": "^6.1.3",
"tslint-config-prettier": "^1.15.0"
"@git.zone/tsbuild": "^2.1.66",
"@git.zone/tsbundle": "^2.0.8",
"@git.zone/tsrun": "^1.2.46",
"@git.zone/tstest": "^1.0.77",
"@push.rocks/tapbundle": "^5.0.8",
"@types/node": "^20.12.7"
},
"dependencies": {
"@pushrocks/smartfile": "^9.0.1",
"@pushrocks/smartpromise": "^3.1.6",
"@pushrocks/smartshell": "^2.0.30",
"@pushrocks/smartunique": "^3.0.3"
"@push.rocks/smartfile": "^11.0.14",
"@push.rocks/smartpath": "^5.0.14",
"@push.rocks/smartpromise": "^4.0.2",
"@push.rocks/smartshell": "^3.0.3",
"@push.rocks/smartunique": "^3.0.3"
},
"browserslist": [
"last 1 chrome versions"
@ -40,5 +41,24 @@
"cli.js",
"npmextra.json",
"readme.md"
]
}
],
"keywords": [
"OCR",
"optical character recognition",
"ocrmypdf",
"text extraction",
"PDF processing",
"machine learning",
"document analysis",
"text recognition"
],
"repository": {
"type": "git",
"url": "https://code.foss.global/push.rocks/smartocr.git"
},
"bugs": {
"url": "https://code.foss.global/push.rocks/smartocr/issues"
},
"homepage": "https://code.foss.global/push.rocks/smartocr",
"type": "module"
}

4671
pnpm-lock.yaml generated Normal file

File diff suppressed because it is too large Load Diff

1
readme.hints.md Normal file
View File

@ -0,0 +1 @@

105
readme.md
View File

@ -1,39 +1,90 @@
# @pushrocks/smartocr
# @push.rocks/smartocr
an ocr module using ocrmypdf
## Availabililty and Links
* [npmjs.org (npm package)](https://www.npmjs.com/package/@pushrocks/smartocr)
* [gitlab.com (source)](https://gitlab.com/pushrocks/smartocr)
* [github.com (source mirror)](https://github.com/pushrocks/smartocr)
* [docs (typedoc)](https://pushrocks.gitlab.io/smartocr/)
## Install
To install `@push.rocks/smartocr`, use the following command with npm:
## Status for master
```bash
npm install @push.rocks/smartocr --save
```
Status Category | Status Badge
-- | --
GitLab Pipelines | [![pipeline status](https://gitlab.com/pushrocks/smartocr/badges/master/pipeline.svg)](https://lossless.cloud)
GitLab Pipline Test Coverage | [![coverage report](https://gitlab.com/pushrocks/smartocr/badges/master/coverage.svg)](https://lossless.cloud)
npm | [![npm downloads per month](https://badgen.net/npm/dy/@pushrocks/smartocr)](https://lossless.cloud)
Snyk | [![Known Vulnerabilities](https://badgen.net/snyk/pushrocks/smartocr)](https://lossless.cloud)
TypeScript Support | [![TypeScript](https://badgen.net/badge/TypeScript/>=%203.x/blue?icon=typescript)](https://lossless.cloud)
node Support | [![node](https://img.shields.io/badge/node->=%2010.x.x-blue.svg)](https://nodejs.org/dist/latest-v10.x/docs/api/)
Code Style | [![Code Style](https://badgen.net/badge/style/prettier/purple)](https://lossless.cloud)
PackagePhobia (total standalone install weight) | [![PackagePhobia](https://badgen.net/packagephobia/install/@pushrocks/smartocr)](https://lossless.cloud)
PackagePhobia (package size on registry) | [![PackagePhobia](https://badgen.net/packagephobia/publish/@pushrocks/smartocr)](https://lossless.cloud)
BundlePhobia (total size when bundled) | [![BundlePhobia](https://badgen.net/bundlephobia/minzip/@pushrocks/smartocr)](https://lossless.cloud)
Platform support | [![Supports Windows 10](https://badgen.net/badge/supports%20Windows%2010/yes/green?icon=windows)](https://lossless.cloud) [![Supports Mac OS X](https://badgen.net/badge/supports%20Mac%20OS%20X/yes/green?icon=apple)](https://lossless.cloud)
This module depends on a few external utilities like `ocrmypdf`, so make sure you have these installed and available in your system's PATH. Consult the `ocrmypdf` documentation for installation instructions suitable for your operating system.
## Usage
Use TypeScript for best in class intellisense
This module provides a TypeScript interface for OCR processing of PDF documents using `ocrmypdf`, encapsulated in the `SmartOcr` class. Here's how to leverage it in your TypeScript project.
## Contribution
### Preparing Your Project
We are always happy for code contributions. If you are not the code contributing type that is ok. Still, maintaining Open Source repositories takes considerable time and thought. If you like the quality of what we do and our modules are useful to you we would appreciate a little monthly contribution: You can [contribute one time](https://lossless.link/contribute-onetime) or [contribute monthly](https://lossless.link/contribute). :)
First, ensure your TypeScript configuration is set up to handle ESModule syntax. You will also need to have Node.js and the external `ocrmypdf` tool installed on your system.
For further information read the linked docs at the top of this readme.
### Basic Setup
> MIT licensed | **©** [Lossless GmbH](https://lossless.gmbh)
| By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy)
```typescript
import { SmartOcr } from '@push.rocks/smartocr';
[![repo-footer](https://lossless.gitlab.io/publicrelations/repofooter.svg)](https://maintainedby.lossless.com)
async function runOcrOnPdf(pdfFilePath: string): Promise<Buffer> {
// Initialize the SmartOcr instance
const smartOcrInstance = await SmartOcr.createAndInit();
// Load your PDF file into a Buffer, this can be from a file or even a remote source
const pdfBuffer = await fs.promises.readFile(pdfFilePath);
// Process the PDF Buffer through SmartOcr
const processedBuffer = await smartOcrInstance.processPdfBuffer(pdfBuffer);
return processedBuffer;
}
// Replace './path/to/your/document.pdf' with the actual path to the PDF document you want to OCR
const ocredPdfBuffer = await runOcrOnPdf('./path/to/your/document.pdf');
// You can now save this buffer to a file, or use it as needed in your application
await fs.promises.writeFile('./path/to/output/document_ocr.pdf', ocredPdfBuffer);
```
In the example above, we import the `SmartOcr` class and use it to process a PDF by passing a `Buffer` of the PDF file to the `processPdfBuffer` method. The method returns a `Buffer` of the processed PDF which includes a text layer added by OCR.
### Advanced Usage
The `SmartOcr` class maintains an internal `smartshell` instance to interface with the `ocrmypdf` command. This setup is abstracted away, ensuring you don't need to manage or understand the underlying shell commands to use OCR functionality in your application.
### Handling OCR Result
The result of the `processPdfBuffer` is a `Buffer` that contains the OCR-processed PDF. This buffer can be directly written to a file system or further manipulated in memory, depending on your application's needs.
### Error Handling
It's important to handle errors that may arise from reading files or the OCR process. The OCR process depends on the external `ocrmypdf` utility, so errors can occur if the utility encounters unsupported PDF structures or if there are issues with the installation of `ocrmypdf`.
```typescript
try {
const ocredPdfBuffer = await runOcrOnPdf('./path/to/your/document.pdf');
await fs.promises.writeFile('./path/to/output/document_ocr.pdf', ocredPdfBuffer);
} catch (error) {
console.error('Failed to OCR the document:', error);
}
```
### Conclusion
The `@push.rocks/smartocr` library simplifies adding OCR capabilities to your TypeScript applications by abstracting away the complexity of interfacing with `ocrmypdf`. With minimal setup, you can start processing PDF documents to add searchable text layers, making this library a valuable tool for any project that requires OCR functionality.
## License and Legal Information
This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository.
**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
### Trademarks
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
### Company Information
Task Venture Capital GmbH
Registered at District court Bremen HRB 35230 HB, Germany
For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.

View File

@ -1,18 +1,19 @@
import { expect, tap } from '@pushrocks/tapbundle';
import * as smartocr from '../ts/index';
import { expect, tap } from '@push.rocks/tapbundle';
import * as smartocr from '../ts/index.js';
let testOcrInstance: smartocr.SmartOcr;
tap.test('should create a valid instance of Smartocr', async () => {
testOcrInstance = await smartocr.SmartOcr.createAndInit();
expect(testOcrInstance).to.be.instanceOf(smartocr.SmartOcr);
expect(testOcrInstance).toBeInstanceOf(smartocr.SmartOcr);
});
tap.test('should ocr a pdfBuffer', async () => {
const smartfile = await import('@pushrocks/smartfile');
const pdfBuffer = (await smartfile.Smartfile.fromFilePath('./test/demo_without_textlayer.pdf'))
const smartfile = await import('@push.rocks/smartfile');
const pdfBuffer = (await smartfile.SmartFile.fromFilePath('./test/demo_without_textlayer.pdf'))
.contentBuffer;
testOcrInstance.processPdfBuffer(pdfBuffer);
const resultBuffer = await testOcrInstance.processPdfBuffer(pdfBuffer);
console.log(resultBuffer);
});
tap.start();

8
ts/00_commitinfo_data.ts Normal file
View File

@ -0,0 +1,8 @@
/**
* autocreated commitinfo by @pushrocks/commitinfo
*/
export const commitinfo = {
name: '@push.rocks/smartocr',
version: '1.0.9',
description: 'A module that performs optical character recognition (OCR) using ocrmypdf.'
}

View File

@ -1 +1 @@
export * from './smartocr.classes.smartocr';
export * from './smartocr.classes.smartocr.js';

View File

@ -1,5 +1,5 @@
import * as plugins from './smartocr.plugins';
import * as paths from './smartocr.paths';
import * as plugins from './smartocr.plugins.js';
import * as paths from './smartocr.paths.js';
export class SmartOcr {
// STATIC
@ -18,10 +18,10 @@ export class SmartOcr {
const uniqueString = plugins.smartunique.uni('doc_');
const originalPath = plugins.path.join(paths.noGitDir, `${uniqueString}.pdf`);
const processedPath = plugins.path.join(paths.noGitDir, `${uniqueString}_processed.pdf`);
const originalSmartfile = await plugins.smartfile.Smartfile.fromBuffer(originalPath, pdfBufferArg);
const originalSmartfile = await plugins.smartfile.SmartFile.fromBuffer(originalPath, pdfBufferArg);
await originalSmartfile.write();
await this.smartshellInstance.exec(`ocrmypdf --rotate-pages ${originalPath} ${processedPath}`);
const processedSmartfile = await plugins.smartfile.Smartfile.fromFilePath(processedPath);
const processedSmartfile = await plugins.smartfile.SmartFile.fromFilePath(processedPath);
await originalSmartfile.delete();
await processedSmartfile.delete();
return processedSmartfile.contentBuffer;

View File

@ -1,4 +1,4 @@
import * as plugins from './smartocr.plugins';
import * as plugins from './smartocr.plugins.js';
export const packageDir = plugins.path.join(__dirname, '../');
export const packageDir = plugins.path.join(plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url), '../');
export const noGitDir = plugins.path.join(packageDir, './.nogit');

View File

@ -6,14 +6,16 @@ export {
}
// @pushrocks scope
import * as smartfile from '@pushrocks/smartfile';
import * as smartshell from '@pushrocks/smartshell';
import * as smartunique from '@pushrocks/smartunique';
import * as smartpromise from '@pushrocks/smartpromise';
import * as smartfile from '@push.rocks/smartfile';
import * as smartshell from '@push.rocks/smartshell';
import * as smartunique from '@push.rocks/smartunique';
import * as smartpath from '@push.rocks/smartpath';
import * as smartpromise from '@push.rocks/smartpromise';
export {
smartfile,
smartshell,
smartunique,
smartpath,
smartpromise
}

14
tsconfig.json Normal file
View File

@ -0,0 +1,14 @@
{
"compilerOptions": {
"experimentalDecorators": true,
"useDefineForClassFields": false,
"target": "ES2022",
"module": "NodeNext",
"moduleResolution": "NodeNext",
"esModuleInterop": true,
"verbatimModuleSyntax": true
},
"exclude": [
"dist_*/**/*.d.ts"
]
}

View File

@ -1,17 +0,0 @@
{
"extends": ["tslint:latest", "tslint-config-prettier"],
"rules": {
"semicolon": [true, "always"],
"no-console": false,
"ordered-imports": false,
"object-literal-sort-keys": false,
"member-ordering": {
"options":{
"order": [
"static-method"
]
}
}
},
"defaultSeverity": "warning"
}