init

.github/workflows/publish.yml

@@ -0,0 +1,66 @@
+name: Build plugin
+
+on:
+  push:
+    # Sequence of patterns matched against refs/tags
+    tags:
+      - "*" # Push events to matching any tag format, i.e. 1.0, 20.15.10
+
+env:
+  PLUGIN_NAME: logseq-ocr
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Use Node.js
+        uses: actions/setup-node@v1
+        with:
+          node-version: "16.x" # You might need to adjust this value to your own version
+      - name: Build
+        id: build
+        run: |
+          npm install -g yarn
+          yarn
+          yarn build
+          mkdir ${{ env.PLUGIN_NAME }}
+          cp README.md package.json ${{ env.PLUGIN_NAME }}
+          mv dist ${{ env.PLUGIN_NAME }}
+          zip -r ${{ env.PLUGIN_NAME }}.zip ${{ env.PLUGIN_NAME }}
+          ls
+          echo "::set-output name=tag_name::$(git tag --sort version:refname | tail -n 1)"
+
+      - name: Create Release
+        uses: ncipollo/release-action@v1
+        id: create_release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VERSION: ${{ github.ref }}
+        with:
+          allowUpdates: true
+          draft: false
+          prerelease: false
+
+      - name: Upload zip file
+        id: upload_zip
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: ./${{ env.PLUGIN_NAME }}.zip
+          asset_name: ${{ env.PLUGIN_NAME }}-${{ steps.build.outputs.tag_name }}.zip
+          asset_content_type: application/zip
+
+      - name: Upload package.json
+        id: upload_metadata
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: ./package.json
+          asset_name: package.json
+          asset_content_type: application/json

.gitignore

@@ -0,0 +1,130 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-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
+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/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# 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 variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# 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
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# 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
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 xxchan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,17 @@
+# logseq-ocr
+
+Read image from clipboard and OCR it!
+
+> **Note**
+>
+> OCR language can be configured in the plugin settings
+
+https://user-images.githubusercontent.com/37948597/235365289-fce2a5a3-a81d-444a-8b8f-91a879c00fde.mov
+
+Credit: inspired by [@laixintao](https://github.com/laixintao) https://www.kawabangga.com/posts/4876
+
+Hint: Other ways to do similar things:
+- From the command line: `pngpaste - | tesseract stdin stdout`
+- [Raycast script command](https://github.com/raycast/script-commands/blob/master/commands/conversions/clipboard-ocr.sh)
+
+This plugin can be slightly more convenient when pasting into Logseq.

index.html

@@ -0,0 +1,14 @@
+<!doctype html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport"
+        content="width=device-width, user-scalable=no, initial-scale=1.0, maximum-scale=1.0, minimum-scale=1.0">
+  <meta http-equiv="X-UA-Compatible" content="ie=edge">
+  <title>OCR LSPlugin :)</title>
+</head>
+<body>
+<div id="app"></div>
+<script src="./index.js" type="module"></script>
+</body>
+</html>

index.js

@@ -0,0 +1,65 @@
+import { createWorker } from 'tesseract.js';
+import "@logseq/libs"
+
+
+async function pocr(worker) {
+    try {
+        // necessary to have the window focused in order to access the clipboard
+        window.focus();
+
+        const clipboardItem = await navigator.clipboard.read()
+        if (!clipboardItem) {
+            console.error('No clipboard item found')
+            return
+        }
+        console.log('Clipboard item: ', clipboardItem)
+        const data = await clipboardItem[0].getType('image/png').catch(err => {
+            throw new Error('Clipboard item is not an image')
+        })
+        console.log('Clipboard data: ', data)
+
+        const ocrResult = await worker.recognize(
+            data,
+            {},
+            { text: true }
+        )
+        console.log('OCR result: ', ocrResult)
+        return ocrResult.data.text
+    } catch (err) {
+        logseq.UI.showMsg('Failed to read image from clipboard: ' + err, 'error')
+    }
+}
+
+const SETTINGS_SCHEMA = [
+    {
+        key: 'lang',
+        type: 'string',
+        title: 'lang',
+        default: 'eng',
+        description: 'The language for OCR. e.g., `chi_sim+eng` means Simplified Chinese & English. Please check [HERE](https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016) for supported languages'
+    }
+]
+
+async function main() {
+    logseq.useSettingsSchema(SETTINGS_SCHEMA);
+    const lang = logseq.settings.lang || 'eng'
+
+    const worker = await createWorker();
+    await worker.loadLanguage(lang);
+    await worker.initialize(lang);
+    await worker.setParameters({
+        preserve_interword_spaces: "1",
+    });
+
+    logseq.Editor.registerSlashCommand(
+        'OCR image from clipboard',
+        async () => {
+            const text = await pocr(worker, lang)
+            await logseq.Editor.insertAtEditingCursor(text)
+        },
+    )
+}
+
+
+// bootstrap
+logseq.ready(main).catch(console.error)

package.json

@@ -0,0 +1,21 @@
+{
+  "name": "logseq-ocr",
+  "version": "0.0.1",
+  "author": "xxchan",
+  "license": "MIT",
+  "dependencies": {
+    "@logseq/libs": "^0.0.14",
+    "tesseract.js": "^4.0.3"
+  },
+  "logseq": {
+    "main": "dist/index.html",
+    "id": "logseq-ocr"
+  },
+  "scripts": {
+    "dev": "parcel watch --public-url . index.html",
+    "build": "parcel build --public-url . --no-source-maps index.html"
+  },
+  "devDependencies": {
+    "parcel": "^2.8.3"
+  }
+}