Compare commits

..

93 Commits

Author SHA1 Message Date
5bc84ffaa0 v4.1.2
Some checks failed
Default (tags) / security (push) Failing after 1s
Default (tags) / test (push) Failing after 1s
Default (tags) / release (push) Has been skipped
Default (tags) / metadata (push) Has been skipped
2026-03-01 18:32:03 +00:00
6435d0f042 fix(smartfs): replace smartfile with smartfs, update file reading to use SmartFs, remove GraphicsMagick/Ghostscript dependency checks, bump dev and runtime dependencies, update tests and docs, and adjust npmextra configuration 2026-03-01 18:32:03 +00:00
9fbd735088 4.1.1
Some checks failed
Default (tags) / security (push) Failing after 1s
Default (tags) / test (push) Failing after 1s
Default (tags) / release (push) Has been skipped
Default (tags) / metadata (push) Has been skipped
2025-08-02 17:31:27 +00:00
fe05713d57 update 2025-08-02 17:31:23 +00:00
be574df599 feat(image): add progressive JPEG generation support
Some checks failed
Default (tags) / security (push) Failing after 24s
Default (tags) / test (push) Failing after 12s
Default (tags) / release (push) Has been skipped
Default (tags) / metadata (push) Has been skipped
- Add convertPDFToJpegBytes method for progressive JPEG images
- Integrate @push.rocks/smartjimp for true progressive encoding
- Update readme with comprehensive documentation
- Update legal section to Task Venture Capital GmbH
2025-08-02 17:29:38 +00:00
6a4aeed3e1 BREAKING CHANGE(smartpdf): improve image generation quality and API consistency
- Renamed convertPDFToWebpPreviews to convertPDFToWebpBytes for consistency
- Added configurable scale options with DPI support
- Changed default scale to 3.0 (216 DPI) for better quality
- Added DPI helper methods and scale constants
2025-08-02 12:37:48 +00:00
a4c3415838 feat(smartpdf): add automatic port allocation and multi-instance support 2025-08-01 16:09:17 +00:00
f535eacd97 3.2.2 2025-02-25 18:22:06 +00:00
9908897aa2 fix(SmartPdf): Fix buffer handling for PDF conversion and text extraction 2025-02-25 18:22:06 +00:00
29d3cbb0b6 3.2.1 2025-02-25 18:06:45 +00:00
babc20649a fix(SmartPdf): Fix type for extractTextFromPdfBuffer function 2025-02-25 18:06:45 +00:00
1188643c4b 3.2.0 2025-02-25 18:03:27 +00:00
6b74301588 feat(smartpdf): Improve dependency versions and optimize PDF to PNG conversion. 2025-02-25 18:03:27 +00:00
168527573c 3.1.8 2024-11-30 20:43:05 +01:00
3d7bb37849 fix(core): Fix candidate handling in PDF generation 2024-11-30 20:43:05 +01:00
12a581ced9 3.1.7 2024-09-27 23:21:31 +02:00
857e1717a5 fix(dependencies): Update dependencies to latest versions 2024-09-27 23:21:30 +02:00
186bfb9d12 update description 2024-05-29 14:15:22 +02:00
c5bc354f65 3.1.6 2024-04-30 17:48:12 +02:00
c48bb0428f fix(core): update 2024-04-30 17:48:11 +02:00
46fbb615a0 3.1.5 2024-04-27 12:07:16 +02:00
3df4e103f9 fix(core): update 2024-04-27 12:07:16 +02:00
addff418c6 3.1.4 2024-04-26 13:39:58 +02:00
14d653e701 fix(core): update 2024-04-26 13:39:57 +02:00
040bac5256 3.1.3 2024-04-26 13:29:32 +02:00
bf44901a0a fix(core): update 2024-04-26 13:29:32 +02:00
b4d0f4e949 3.1.2 2024-04-26 13:28:07 +02:00
b2b47b1f6a fix(core): update 2024-04-26 13:28:07 +02:00
1b1398653b 3.1.1 2024-04-26 13:27:28 +02:00
1f61dcb115 fix(core): update 2024-04-26 13:27:27 +02:00
1476fc9174 3.1.0 2024-04-25 18:48:08 +02:00
d157a3acd9 feat(now supports pdf -> jpg): update 2024-04-25 18:48:08 +02:00
fe6be928a9 update tsconfig 2024-04-14 18:07:39 +02:00
8e537be454 update npmextra.json: githost 2024-04-01 21:37:16 +02:00
6947529e02 update npmextra.json: githost 2024-04-01 19:59:15 +02:00
b6d78929b9 update npmextra.json: githost 2024-03-30 21:48:15 +01:00
e997189a64 3.0.17 2024-03-19 17:52:28 +01:00
31940deb7a fix(core): update 2024-03-19 17:52:27 +01:00
922c6da234 3.0.16 2023-07-26 14:17:12 +02:00
aa8fb165eb fix(core): update 2023-07-26 14:17:11 +02:00
4cd4431565 switch to new org scheme 2023-07-11 01:24:04 +02:00
826183be8c switch to new org scheme 2023-07-10 10:17:20 +02:00
6d9b7ee0e4 3.0.15 2022-11-07 23:11:30 +01:00
3c66acb653 fix(core): update 2022-11-07 23:11:29 +01:00
aa0ad1dce5 3.0.14 2022-10-26 23:04:59 +02:00
65756457aa fix(core): update 2022-10-26 23:04:59 +02:00
67f21d2500 3.0.13 2022-10-26 22:58:26 +02:00
1cf095a5cc fix(core): update 2022-10-26 22:58:26 +02:00
ffeaec7fe9 3.0.12 2022-09-16 08:27:25 +02:00
a31e196e5b fix(core): update 2022-09-16 08:27:25 +02:00
57851d90a5 3.0.11 2022-09-15 20:52:22 +02:00
1e4b16b734 fix(core): update 2022-09-15 20:52:22 +02:00
876466b18d 3.0.10 2022-09-13 18:39:38 +02:00
82b1c187ee fix(core): update 2022-09-13 18:39:38 +02:00
4f93d258b8 3.0.9 2022-09-13 18:26:15 +02:00
60993fc005 fix(core): update 2022-09-13 18:26:14 +02:00
db4965c8f5 3.0.8 2022-09-05 01:02:05 +02:00
36a964d931 fix(core): update 2022-09-05 01:02:05 +02:00
6d90f4c9b4 3.0.7 2022-06-29 00:24:44 +02:00
839eafd73f fix(core): update 2022-06-29 00:24:43 +02:00
f4141bf201 3.0.6 2022-06-15 22:16:44 +02:00
5a46028053 fix(core): update 2022-06-15 22:16:44 +02:00
18d26647e1 3.0.5 2022-06-15 22:14:55 +02:00
0b5ec86780 fix(core): update 2022-06-15 22:14:55 +02:00
5e15729045 3.0.4 2022-06-12 19:26:49 +02:00
c98a5f1ac3 fix(core): update 2022-06-12 19:26:49 +02:00
7f02146a0e 3.0.3 2022-06-12 19:26:34 +02:00
5dab8c7351 fix(core): update 2022-06-12 19:26:34 +02:00
505e0e9a30 3.0.2 2022-03-25 01:14:12 +01:00
9e3510955a fix(core): update 2022-03-25 01:14:12 +01:00
c006d4fbc7 3.0.1 2022-03-24 23:32:28 +01:00
5e02c44647 fix(core): update 2022-03-24 23:32:27 +01:00
47f7cb18b5 3.0.0 2022-03-24 14:34:46 +01:00
3faf065c66 2.0.19 2022-03-24 14:32:50 +01:00
dfffd03790 fix(core): update 2022-03-24 14:32:49 +01:00
796aa905d2 2.0.18 2022-01-06 13:23:05 +01:00
253fb95143 fix(core): update 2022-01-06 13:23:04 +01:00
f3ea075b72 2.0.17 2022-01-06 13:10:12 +01:00
af725a7f78 fix(core): update 2022-01-06 13:10:12 +01:00
016e0db797 2.0.16 2022-01-05 23:55:38 +01:00
4cf8b2e1f8 fix(core): update 2022-01-05 23:55:37 +01:00
67b0aa9d47 2.0.15 2022-01-05 17:20:28 +01:00
567c6eafea fix(core): update 2022-01-05 17:20:28 +01:00
ff890fb2af 2.0.14 2022-01-05 16:32:48 +01:00
a512fd64b5 fix(core): update 2022-01-05 16:32:47 +01:00
377318a62a 2.0.13 2022-01-05 14:19:40 +01:00
671c871304 fix(core): update 2022-01-05 14:19:39 +01:00
e0cc6b5655 2.0.12 2022-01-05 14:17:43 +01:00
e74b44b49c fix(core): update 2022-01-05 14:17:43 +01:00
d6f0d88d4a 2.0.11 2021-10-14 16:04:58 +02:00
9674e5b8dc fix(core): update 2021-10-14 16:04:58 +02:00
ea4cf777a9 2.0.10 2021-10-14 10:59:45 +02:00
8a308fa9e3 fix(core): update 2021-10-14 10:59:45 +02:00
26 changed files with 13646 additions and 11462 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

@@ -1,137 +0,0 @@
# gitzone ci_default
image: registry.gitlab.com/hosttoday/ht-docker-node:npmci
cache:
paths:
- .npmci_cache/
key: '$CI_BUILD_STAGE'
stages:
- security
- test
- release
- metadata
# ====================
# security stage
# ====================
mirror:
stage: security
script:
- npmci git mirror
only:
- tags
tags:
- lossless
- docker
- notpriv
auditProductionDependencies:
image: registry.gitlab.com/hosttoday/ht-docker-node:npmci
stage: security
script:
- npmci npm prepare
- npmci command npm install --production --ignore-scripts
- npmci command npm config set registry https://registry.npmjs.org
- npmci command npm audit --audit-level=high --only=prod --production
tags:
- docker
auditDevDependencies:
image: registry.gitlab.com/hosttoday/ht-docker-node:npmci
stage: security
script:
- npmci npm prepare
- npmci command npm install --ignore-scripts
- npmci command npm config set registry https://registry.npmjs.org
- npmci command npm audit --audit-level=high --only=dev
tags:
- docker
allow_failure: true
# ====================
# test stage
# ====================
testStable:
stage: test
script:
- npmci npm prepare
- npmci node install stable
- npmci npm install
- npmci npm test
coverage: /\d+.?\d+?\%\s*coverage/
tags:
- docker
testBuild:
stage: test
script:
- npmci npm prepare
- npmci node install stable
- npmci npm install
- npmci command npm run build
coverage: /\d+.?\d+?\%\s*coverage/
tags:
- docker
release:
stage: release
script:
- npmci node install stable
- npmci npm publish
only:
- tags
tags:
- lossless
- docker
- notpriv
# ====================
# metadata stage
# ====================
codequality:
stage: metadata
allow_failure: true
only:
- tags
script:
- npmci command npm install -g tslint typescript
- npmci npm prepare
- npmci npm install
- npmci command "tslint -c tslint.json ./ts/**/*.ts"
tags:
- lossless
- docker
- priv
trigger:
stage: metadata
script:
- npmci trigger
only:
- tags
tags:
- lossless
- docker
- notpriv
pages:
stage: metadata
script:
- npmci node install lts
- npmci command npm install -g @gitzone/tsdoc
- npmci npm prepare
- npmci npm install
- npmci command tsdoc
tags:
- lossless
- docker
- notpriv
only:
- tags
artifacts:
expire_in: 1 week
paths:
- public
allow_failure: true

9
.snyk
View File

@@ -1,9 +0,0 @@
# Snyk (https://snyk.io) policy file, patches or ignores known vulnerabilities.
version: v1.13.5
# ignores vulnerabilities until expiry date; change duration by modifying expiry date
ignore:
SNYK-JS-LODASH-450202:
- '@pushrocks/smartnetwork > portscanner > async > lodash':
reason: None given
expires: '2019-09-13T09:39:26.276Z'
patch: {}

24
.vscode/launch.json vendored
View File

@@ -2,28 +2,10 @@
"version": "0.2.0",
"configurations": [
{
"name": "current file",
"type": "node",
"command": "npm test",
"name": "Run npm test",
"request": "launch",
"args": [
"${relativeFile}"
],
"runtimeArgs": ["-r", "@gitzone/tsrun"],
"cwd": "${workspaceRoot}",
"protocol": "inspector",
"internalConsoleOptions": "openOnSessionStart"
},
{
"name": "test.ts",
"type": "node",
"request": "launch",
"args": [
"test/test.ts"
],
"runtimeArgs": ["-r", "@gitzone/tsrun"],
"cwd": "${workspaceRoot}",
"protocol": "inspector",
"internalConsoleOptions": "openOnSessionStart"
"type": "node-terminal"
}
]
}

175
changelog.md Normal file
View File

@@ -0,0 +1,175 @@
# Changelog
## 2026-03-01 - 4.1.2 - fix(smartfs)
replace smartfile with smartfs, update file reading to use SmartFs, remove GraphicsMagick/Ghostscript dependency checks, bump dev and runtime dependencies, update tests and docs, and adjust npmextra configuration
- Replace usage/export of @push.rocks/smartfile with @push.rocks/smartfs and update readFileToPdfObject to use SmartFs + SmartFsProviderNode
- Remove execFile import and the GraphicsMagick/Ghostscript dependency-checking helpers from smartpdf (no more gm/gs checks)
- Bump devDependencies: @git.zone/tsbuild ^4.1.2, @git.zone/tsdoc ^1.12.0, @git.zone/tsrun ^2.0.1, @git.zone/tstest ^3.1.8, @types/node ^25.3.2
- Bump runtime dependencies: @push.rocks/smartfs ^1.3.1, @push.rocks/smartnetwork ^4.4.0, @tsclass/tsclass ^9.3.0, @types/express ^5.0.6, express ^5.2.1, pdf2json ^4.0.2
- Tests updated: switched example URLs to example.com, added a third PDF generation test that writes .nogit/3.pdf, and exported tap.start() as default
- npmextra.json reorganized to namespaced keys, added release.registries and accessLevel, and adjusted tsdoc/legal entries
- Documentation/readme refreshed: added issue reporting/security section, feature table, and various wording/formatting updates
## 2025-08-02 - 4.1.0 - feat(smartpdf)
Add progressive JPEG generation support
- Added new convertPDFToJpegBytes method for progressive JPEG generation
- Integrated @push.rocks/smartjimp for true progressive JPEG encoding
- Progressive JPEGs load in multiple passes, showing low-quality preview first
- Supports quality and scale options like other image generation methods
- Updated readme with comprehensive documentation and modern styling
- Updated legal section to reflect Task Venture Capital GmbH ownership
## 2025-08-02 - 4.0.0 - BREAKING CHANGE(smartpdf)
Improve image generation quality and API consistency
- BREAKING: Renamed `convertPDFToWebpPreviews` to `convertPDFToWebpBytes` for API consistency
- Added configurable scale options to `convertPDFToPngBytes` method
- Changed default scale from 1.0 to 3.0 for PNG generation (216 DPI)
- Changed default scale from 0.5 to 3.0 for WebP generation (216 DPI)
- Added DPI helper methods: `getScaleForDPI()` and scale constants (SCALE_SCREEN, SCALE_HIGH, SCALE_PRINT)
- Added maxWidth/maxHeight constraints for both PNG and WebP generation
- Improved test file organization with clear naming conventions
- Updated documentation with DPI/scale guidance and examples
## 2025-08-01 - 3.3.0 - feat(smartpdf)
Add automatic port allocation and multi-instance support
- Added ISmartPdfOptions interface with port configuration options
- Implemented automatic port allocation between 20000-30000 by default
- Added support for custom port ranges via portRangeStart/portRangeEnd options
- Added support for specific port assignment via port option
- Fixed resource cleanup when port allocation fails
- Multiple SmartPdf instances can now run simultaneously without port conflicts
- Updated readme with comprehensive documentation for all features
## 2025-02-25 - 3.2.2 - fix(SmartPdf)
Fix buffer handling for PDF conversion and text extraction
- Ensure Uint8Array is converted to Node Buffer for PDF conversion.
- Correct the PDF page viewport handling by using document dimensions.
- Fix extractTextFromPdfBuffer argument type from Uint8Array to Buffer.
## 2025-02-25 - 3.2.1 - fix(SmartPdf)
Fix type for extractTextFromPdfBuffer function
- Corrected the parameter type from Buffer to Uint8Array for extractTextFromPdfBuffer function.
## 2025-02-25 - 3.2.0 - feat(smartpdf)
Improve dependency versions and optimize PDF to PNG conversion.
- Update several dependencies to newer versions for better stability and performance.
- Refactor tests to enhance readability and add directory creation validations.
- Optimize PDF to PNG conversion by switching to a more efficient Puppeteer and PDF.js-based method.
- Add checks for presence of required dependencies (GraphicsMagick and Ghostscript).
- Fix media emulation issue by properly awaiting the emulateMediaType function.
## 2024-11-30 - 3.1.8 - fix(core)
Fix candidate handling in PDF generation
- Added error handling for missing PDF candidates in server requests.
- Updated devDependencies and dependencies to latest versions for better stability and new features.
- Patched header retrieval logic during PDF generation for security check.
## 2024-09-27 - 3.1.7 - fix(dependencies)
Update dependencies to latest versions
- Updated @git.zone/tsbuild to version ^2.1.84
- Updated @git.zone/tsdoc to version ^1.3.12
- Updated @git.zone/tsrun to version ^1.2.49
- Updated @push.rocks/tapbundle to version ^5.3.0
- Updated @types/node to version ^22.7.4
- Updated @push.rocks/smartfile to version ^11.0.21
- Updated @push.rocks/smartpromise to version ^4.0.4
- Updated @tsclass/tsclass to version ^4.1.2
- Updated express to version ^4.21.0
- Updated pdf2pic to version ^3.1.3
## 2024-05-29 - 3.1.6 - Core
Updated description
- Minor changes to documentation and internal text.
## 2024-04-25 to 2024-04-30 - 3.1.0 to 3.1.5 - Core
Fix updates in core functionality
- Fixes and updates in core function in versions 3.1.0 to 3.1.5.
## 2024-04-25 - 3.0.17 - Feature
Now supports PDF to JPG conversion
- Added support for converting PDF files to JPG format.
## 2024-03-19 to 2024-04-14 - 3.0.17 - Maintenance
Various updates to project configuration files
- Updated `tsconfig`.
- Updated `npmextra.json`.
## 2023-07-11 to 2024-03-19 - 3.0.15 to 3.0.16 - Organization
Switch to new organization scheme and core updates
- Switched to new organization scheme.
- Applied core updates and bug fixes.
## 2022-11-07 to 2023-07-10 - 3.0.13 to 3.0.14 - Core
Fixes and updates to core functionality
- Various minor bug fixes and updates to core components.
## 2022-09-13 to 2022-11-07 - 3.0.10 to 3.0.12 - Core
Ongoing core updates and maintenance
- Regular fixes and operational improvements in core functionalities.
## 2022-06-12 to 2022-09-13 - 3.0.7 to 3.0.9 - Core
Continued focus on high-priority bug fixes and core functionalities
- Regular fixes for critical bugs and enhancements.
## 2022-03-24 to 2022-06-29 - 3.0.3 to 3.0.6 - Core
Further optimization and maintenance releases
- Further improvements and refinements of issues in core functionalities.
## 2022-01-05 to 2022-03-25 - 3.0.0 to 3.0.2 - Major Version Release
Major release for version 3.0.x, including core fixes
- Increased version from 2.x to 3.0. New significant changes and fixes.
## 2022-01-05 to 2022-03-24 - 2.0.13 to 2.0.19 - Core
Routine core updates and bug fixes
- Regular bug fixes in core components.
## 2019-11-19 to 2022-01-06 - 2.0.0 to 2.0.11 - Core
Multiple core updates and a few performance improvements
- Some performance enhancements and multiple bug fixes.
## 2019-11-16 to 2019-11-19 - 1.0.27 to 1.0.29 - API
Breaking change in API
- Naming PDF results to better represent their content.
## 2019-05-29 to 2019-11-15 - 1.0.13 to 1.0.26 - Core
Core functional updates and some major restructuring
- Introduced multiple updates to the core, addressing bugs and improving stability.
## 2019-04-10 to 2019-05-28 - 1.0.4 to 1.0.12 - Core
Fixes and updates in the core
- Implementation of multiple essential fixes for core components.
## 2018-10-06 - 1.0.1 to 1.0.3 - Core and Typings
Initial implementation and core fixes
- Initial implementation of the project.
- Fixed compilation problems in typings.
## 2016-01-29 - unknown - Initial
Initial commit
- Initial commit for the project setup.

View File

View File

@@ -1,17 +1,40 @@
{
"npmci": {
"npmGlobalTools": [],
"npmAccessLevel": "public"
},
"gitzone": {
"@git.zone/cli": {
"projectType": "npm",
"module": {
"githost": "gitlab.com",
"gitscope": "pushrocks",
"githost": "code.foss.global",
"gitscope": "push.rocks",
"gitrepo": "smartpdf",
"shortDescription": "Create PDFs fast and smoothly",
"npmPackagename": "@pushrocks/smartpdf",
"license": "MIT"
"description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
"npmPackagename": "@push.rocks/smartpdf",
"license": "MIT",
"keywords": [
"PDF generation",
"HTML to PDF",
"website to PDF",
"PDF manipulation",
"puppeteer",
"express",
"node.js",
"typescript",
"automation",
"PDF merging",
"text extraction",
"PDF management"
]
},
"release": {
"registries": [
"https://verdaccio.lossless.digital",
"https://registry.npmjs.org"
],
"accessLevel": "public"
}
},
"@git.zone/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"
},
"@ship.zone/szci": {
"npmGlobalTools": []
}
}

11140
package-lock.json generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,33 +1,40 @@
{
"name": "@pushrocks/smartpdf",
"version": "2.0.9",
"name": "@push.rocks/smartpdf",
"version": "4.1.2",
"private": false,
"description": "create pdfs on the fly",
"description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
"main": "dist_ts/index.js",
"typings": "dist_ts/index.d.ts",
"type": "module",
"author": "Lossless GmbH",
"license": "MIT",
"scripts": {
"test": "(tstest test/ --web)",
"build": "(tsbuild --web)"
"test": "(tstest test/ --verbose --timeout 120)",
"build": "(tsbuild tsfolders --allowimplicitany)",
"buildDocs": "tsdoc"
},
"devDependencies": {
"@gitzone/tsbuild": "^2.1.25",
"@gitzone/tsrun": "^1.2.12",
"@gitzone/tstest": "^1.0.52",
"@pushrocks/tapbundle": "^3.2.14",
"@types/node": "^15.0.1",
"tslint": "^6.1.3",
"tslint-config-prettier": "^1.18.0"
"@git.zone/tsbuild": "^4.1.2",
"@git.zone/tsdoc": "^1.12.0",
"@git.zone/tsrun": "^2.0.1",
"@git.zone/tstest": "^3.1.8",
"@types/node": "^25.3.2"
},
"dependencies": {
"@pushrocks/smartfile": "^8.0.10",
"@pushrocks/smartnetwork": "^2.0.10",
"@pushrocks/smartpromise": "^3.1.5",
"@pushrocks/smartpuppeteer": "^1.0.21",
"@pushrocks/smartunique": "^3.0.3",
"@types/express": "^4.17.11",
"express": "^4.17.1"
"@push.rocks/smartbuffer": "^3.0.5",
"@push.rocks/smartdelay": "^3.0.5",
"@push.rocks/smartfs": "^1.3.1",
"@push.rocks/smartjimp": "^1.2.0",
"@push.rocks/smartnetwork": "^4.4.0",
"@push.rocks/smartpath": "^6.0.0",
"@push.rocks/smartpromise": "^4.2.3",
"@push.rocks/smartpuppeteer": "^2.0.5",
"@push.rocks/smartunique": "^3.0.9",
"@tsclass/tsclass": "^9.3.0",
"@types/express": "^5.0.6",
"express": "^5.2.1",
"pdf-lib": "^1.17.1",
"pdf2json": "^4.0.2"
},
"files": [
"ts/**/*",
@@ -43,5 +50,25 @@
],
"browserslist": [
"last 1 chrome versions"
]
],
"keywords": [
"PDF generation",
"HTML to PDF",
"website to PDF",
"PDF manipulation",
"puppeteer",
"express",
"node.js",
"typescript",
"automation",
"PDF merging",
"text extraction",
"PDF management"
],
"homepage": "https://code.foss.global/push.rocks/smartpdf",
"repository": {
"type": "git",
"url": "https://code.foss.global/push.rocks/smartpdf.git"
},
"packageManager": "pnpm@10.11.0+sha512.6540583f41cc5f628eb3d9773ecee802f4f9ef9923cc45b69890fb47991d4b092964694ec3a4f738a420c918a333062c8b925d312f42e4f0c263eb603551f977"
}

11892
pnpm-lock.yaml generated Normal file

File diff suppressed because it is too large Load Diff

2
pnpm-workspace.yaml Normal file
View File

@@ -0,0 +1,2 @@
onlyBuiltDependencies:
- sharp

1
readme.hints.md Normal file
View File

@@ -0,0 +1 @@

442
readme.md
View File

@@ -1,41 +1,423 @@
# @pushrocks/smartpdf
Create PDFs fast and smoothly
# @push.rocks/smartpdf 📄✨
## Availabililty and Links
* [npmjs.org (npm package)](https://www.npmjs.com/package/@pushrocks/smartpdf)
* [gitlab.com (source)](https://gitlab.com/pushrocks/smartpdf)
* [github.com (source mirror)](https://github.com/pushrocks/smartpdf)
* [docs (typedoc)](https://pushrocks.gitlab.io/smartpdf/)
> **Transform HTML, websites, and PDFs into beautiful documents and images with just a few lines of code.**
## Status for master
[![npm version](https://img.shields.io/npm/v/@push.rocks/smartpdf.svg?style=flat-square)](https://www.npmjs.com/package/@push.rocks/smartpdf)
[![TypeScript](https://img.shields.io/badge/TypeScript-5.x-blue.svg?style=flat-square)](https://www.typescriptlang.org/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](./license)
Status Category | Status Badge
-- | --
GitLab Pipelines | [![pipeline status](https://gitlab.com/pushrocks/smartpdf/badges/master/pipeline.svg)](https://lossless.cloud)
GitLab Pipline Test Coverage | [![coverage report](https://gitlab.com/pushrocks/smartpdf/badges/master/coverage.svg)](https://lossless.cloud)
npm | [![npm downloads per month](https://badgen.net/npm/dy/@pushrocks/smartpdf)](https://lossless.cloud)
Snyk | [![Known Vulnerabilities](https://badgen.net/snyk/pushrocks/smartpdf)](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/smartpdf)](https://lossless.cloud)
PackagePhobia (package size on registry) | [![PackagePhobia](https://badgen.net/packagephobia/publish/@pushrocks/smartpdf)](https://lossless.cloud)
BundlePhobia (total size when bundled) | [![BundlePhobia](https://badgen.net/bundlephobia/minzip/@pushrocks/smartpdf)](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)
## Issue Reporting and Security
## Usage
For reporting bugs, issues, or security vulnerabilities, please visit [community.foss.global/](https://community.foss.global/). This is the central community hub for all issue reporting. Developers who sign and comply with our contribution agreement and go through identification can also get a [code.foss.global/](https://code.foss.global/) account to submit Pull Requests directly.
## Contribution
## 🚀 Why SmartPDF?
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). :)
SmartPDF is your Swiss Army knife for PDF operations in Node.js. Whether you're generating invoices from HTML, snapshotting web pages, merging documents, or converting PDF pages to images — SmartPDF handles it all through a clean, async-first TypeScript API backed by headless Chromium.
## Contribution
### ✨ Features at a Glance
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). :)
| Feature | Description |
|---------|-------------|
| 📝 **HTML → PDF** | Render any HTML string (with full CSS) into an A4-sized PDF |
| 🌐 **Website → PDF** | Capture a live URL as a PDF — either A4 or full-page scroll |
| 🔀 **PDF Merging** | Combine multiple PDF buffers into a single document |
| 🖼️ **PDF → Images** | Convert PDF pages to **PNG**, **WebP**, or progressive **JPEG** |
| 📑 **Text Extraction** | Pull raw text content from any PDF buffer |
| 🔌 **Smart Port Management** | Automatic port allocation so multiple instances never collide |
| 🎛️ **DPI Control** | Built-in scale constants for screen, high-quality, and print resolutions |
| 🌐 **BYO Browser** | Optionally pass your own Puppeteer `Browser` instance |
For further information read the linked docs at the top of this readme.
## 📦 Installation
> MIT licensed | **©** [Lossless GmbH](https://lossless.gmbh)
| By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy)
```bash
pnpm add @push.rocks/smartpdf
```
[![repo-footer](https://lossless.gitlab.io/publicrelations/repofooter.svg)](https://maintainedby.lossless.com)
> **Prerequisites:** SmartPDF uses headless Chromium via Puppeteer under the hood. On most systems this is handled automatically. If you run into browser-launch issues (CI, Docker, etc.), make sure the required system libraries are installed — see the [Puppeteer troubleshooting guide](https://pptr.dev/troubleshooting).
## 🎯 Quick Start
```typescript
import { SmartPdf } from '@push.rocks/smartpdf';
import * as fs from 'fs';
// 1. Create and start
const smartPdf = await SmartPdf.create();
await smartPdf.start();
// 2. Generate a PDF from HTML
const pdf = await smartPdf.getA4PdfResultForHtmlString(`
<h1>Hello, PDF World! 🌍</h1>
<p>Generated with SmartPDF.</p>
`);
// 3. Write to disk
fs.writeFileSync('my-first.pdf', pdf.buffer);
// 4. Clean up
await smartPdf.stop();
```
Every method returns an `IPdf` object:
```typescript
interface IPdf {
id: string | null; // Unique identifier
name: string; // Filename
buffer: Buffer; // Raw PDF bytes
metadata?: {
textExtraction?: string; // Extracted text (when available)
};
}
```
## 📚 How It Works
SmartPDF spins up a lightweight Express server bound to `localhost` and a headless Chromium browser. When you call a generation method:
1. Your HTML is registered internally and served at `http://localhost:{port}/{id}`
2. Puppeteer navigates to that URL, waits for the page to fully render, and captures a PDF
3. A header-based security check ensures only the correct content is captured
4. The server and browser are torn down when you call `stop()`
This architecture means you get **pixel-perfect CSS rendering**, **web font support**, and **full JavaScript execution** — the same rendering engine that powers Chrome.
## 🏗️ Instance Management
```typescript
const smartPdf = await SmartPdf.create();
await smartPdf.start();
// ... your operations ...
await smartPdf.stop();
```
For production use, wrap in try/finally:
```typescript
const smartPdf = await SmartPdf.create();
try {
await smartPdf.start();
// ... generate PDFs ...
} finally {
await smartPdf.stop();
}
```
### 🔌 Smart Port Allocation
Run multiple instances without conflicts:
```typescript
// Each instance auto-selects a free port (default range: 2000030000)
const instance1 = new SmartPdf();
const instance2 = new SmartPdf();
await instance1.start(); // e.g. port 20000
await instance2.start(); // e.g. port 20001
console.log(instance1.serverPort); // 20000
console.log(instance2.serverPort); // 20001
// Custom range
const custom = new SmartPdf({ portRangeStart: 4000, portRangeEnd: 5000 });
// Or pin a specific port
const pinned = new SmartPdf({ port: 3000 });
```
If a specific port is already in use, `start()` throws an error immediately instead of silently failing.
### 🌐 Bring Your Own Browser
Pass an existing Puppeteer `Browser` instance — SmartPDF won't close it when you call `stop()`:
```typescript
import puppeteer from 'puppeteer';
const browser = await puppeteer.launch({
headless: 'new',
args: ['--no-sandbox'],
});
const smartPdf = await SmartPdf.create();
await smartPdf.start(browser); // uses your browser
await smartPdf.stop(); // server stops, browser stays open
await browser.close(); // you manage browser lifecycle
```
## 🎨 PDF Generation
### 📝 HTML → A4 PDF
Renders at a 794×1122 viewport (A4 at 96 DPI) with full CSS support:
```typescript
const pdf = await smartPdf.getA4PdfResultForHtmlString(`
<style>
body { font-family: 'Helvetica', sans-serif; margin: 40px; }
.header {
background: linear-gradient(135deg, #667eea, #764ba2);
color: white; padding: 30px; border-radius: 10px; text-align: center;
}
table { width: 100%; border-collapse: collapse; margin-top: 20px; }
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
th { background: #f5f5f5; }
</style>
<div class="header">
<h1>Invoice #2024-001</h1>
</div>
<table>
<tr><th>Item</th><th>Qty</th><th>Price</th></tr>
<tr><td>Widget Pro</td><td>5</td><td>$49.99</td></tr>
<tr><td>Gizmo Ultra</td><td>2</td><td>$129.99</td></tr>
</table>
`);
fs.writeFileSync('invoice.pdf', pdf.buffer);
```
### 🌐 Website → PDF
Two methods depending on your needs:
```typescript
// Standard capture — uses the document's own dimensions
const pdf = await smartPdf.getPdfResultForWebsite('https://example.com');
// Full-page capture — scrolls to bottom, captures everything as a single page
const fullPdf = await smartPdf.getFullWebsiteAsSinglePdf('https://example.com');
```
`getPdfResultForWebsite` uses a 1980×1200 viewport and respects the page's own width/height. `getFullWebsiteAsSinglePdf` uses a 1920px-wide viewport and measures the full scroll height, producing a single tall page.
### 🔀 Merge Multiple PDFs
Combine any number of PDF buffers into one document using `pdf-lib`:
```typescript
const invoice = await smartPdf.readFileToPdfObject('./invoice.pdf');
const terms = await smartPdf.readFileToPdfObject('./terms.pdf');
const appendix = await smartPdf.getA4PdfResultForHtmlString('<h1>Appendix</h1>...');
const merged = await smartPdf.mergePdfs([
invoice.buffer,
terms.buffer,
appendix.buffer,
]);
fs.writeFileSync('complete-package.pdf', merged);
```
### 📑 Read a PDF from Disk
```typescript
const pdfObject = await smartPdf.readFileToPdfObject('./document.pdf');
console.log(pdfObject.name); // "document.pdf"
console.log(pdfObject.buffer); // <Buffer ...>
```
### 📖 Extract Text
Pull raw text from any PDF buffer:
```typescript
const text = await smartPdf.extractTextFromPdfBuffer(pdf.buffer);
console.log(text);
```
> Uses [pdf2json](https://github.com/modesty/pdf2json) under the hood. Works best with text-based PDFs; scanned documents may return limited results.
## 🖼️ PDF → Image Conversion
Convert PDF pages to raster images using Puppeteer + PDF.js. Each page becomes a separate image buffer.
### PNG — Lossless Quality
```typescript
const pngPages = await smartPdf.convertPDFToPngBytes(pdf.buffer, {
scale: SmartPdf.SCALE_HIGH, // 3.0 = ~216 DPI (default)
});
pngPages.forEach((png, i) => {
fs.writeFileSync(`page-${i + 1}.png`, Buffer.from(png));
});
```
### WebP — Modern & Efficient
2560% smaller than PNG at similar visual quality:
```typescript
const webpPages = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
scale: 2.0, // ~144 DPI
quality: 90, // 0100 (default: 85)
});
```
### JPEG — Progressive Loading
Generates true progressive JPEGs (multi-pass rendering) via sharp:
```typescript
const jpegPages = await smartPdf.convertPDFToJpegBytes(pdf.buffer, {
scale: SmartPdf.SCALE_HIGH,
quality: 85, // 0100 (default: 85)
maxWidth: 1920, // optional dimension constraints
maxHeight: 1080,
});
```
### 📏 DPI & Scale Reference
All image methods accept a `scale` parameter. PDF.js renders at 72 DPI by default, so `scale` is a multiplier:
| Constant | Value | DPI | Use Case |
|----------|-------|-----|----------|
| `SmartPdf.SCALE_SCREEN` | 2.0 | ~144 | Web display, thumbnails |
| `SmartPdf.SCALE_HIGH` | 3.0 | ~216 | General purpose (default) |
| `SmartPdf.SCALE_PRINT` | 6.0 | ~432 | Print-quality output |
Or calculate a custom scale:
```typescript
const scale = SmartPdf.getScaleForDPI(300); // → 4.167
```
### 🖼️ Dimension Constraints
All image methods support `maxWidth` and `maxHeight` to cap output size while preserving aspect ratio:
```typescript
// High-res render, but capped at 800×1000 px
const constrained = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
scale: SmartPdf.SCALE_HIGH,
quality: 90,
maxWidth: 800,
maxHeight: 1000,
});
```
### 📊 Format Comparison
| Format | Typical Size vs PNG | Lossy? | Transparency | Progressive | Best For |
|--------|-------------------|--------|--------------|-------------|----------|
| **PNG** | baseline | No | ✅ | — | Screenshots, diagrams, text-heavy docs |
| **WebP** | 4075% | Yes | ✅ | — | Modern web apps, thumbnails |
| **JPEG** | 5070% | Yes | ❌ | ✅ | Photos, complex graphics, email |
## ⚡ Parallel Processing
Process multiple URLs concurrently with separate instances:
```typescript
const urls = [
'https://example.com/page1',
'https://example.com/page2',
'https://example.com/page3',
];
// Spin up parallel instances
const instances = await Promise.all(
urls.map(() => SmartPdf.create())
);
await Promise.all(instances.map(i => i.start()));
// Generate in parallel
const pdfs = await Promise.all(
urls.map((url, i) => instances[i].getFullWebsiteAsSinglePdf(url))
);
// Merge all results
const merged = await instances[0].mergePdfs(pdfs.map(p => p.buffer));
fs.writeFileSync('all-pages.pdf', merged);
// Clean up
await Promise.all(instances.map(i => i.stop()));
```
## 📝 Full API Reference
### `SmartPdf` Class
#### Static Properties
| Property | Type | Value | Description |
|----------|------|-------|-------------|
| `SCALE_SCREEN` | `number` | `2.0` | ~144 DPI scale factor |
| `SCALE_HIGH` | `number` | `3.0` | ~216 DPI scale factor (default) |
| `SCALE_PRINT` | `number` | `6.0` | ~432 DPI scale factor |
#### Static Methods
| Method | Returns | Description |
|--------|---------|-------------|
| `create(options?)` | `Promise<SmartPdf>` | Factory method to create an instance |
| `getScaleForDPI(dpi)` | `number` | Converts a DPI value to a scale factor (`dpi / 72`) |
#### Instance Properties
| Property | Type | Description |
|----------|------|-------------|
| `serverPort` | `number` | The port the internal Express server is listening on |
#### Instance Methods
| Method | Returns | Description |
|--------|---------|-------------|
| `start(browser?)` | `Promise<void>` | Starts internal server + browser. Optionally accepts an existing Puppeteer `Browser`. |
| `stop()` | `Promise<void>` | Shuts down server and browser (unless external browser was provided). |
| `getA4PdfResultForHtmlString(html)` | `Promise<IPdf>` | Renders HTML at 794×1122 viewport → A4 PDF |
| `getPdfResultForWebsite(url)` | `Promise<IPdf>` | Captures website at 1980×1200 viewport → PDF |
| `getFullWebsiteAsSinglePdf(url)` | `Promise<IPdf>` | Captures full scrollable page at 1920px wide → single-page PDF |
| `mergePdfs(buffers)` | `Promise<Uint8Array>` | Merges an array of PDF `Uint8Array` buffers |
| `readFileToPdfObject(path)` | `Promise<IPdf>` | Reads a PDF file from disk into an `IPdf` object |
| `extractTextFromPdfBuffer(buffer)` | `Promise<string>` | Extracts raw text from a PDF buffer |
| `convertPDFToPngBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a PNG buffer |
| `convertPDFToWebpBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a WebP buffer |
| `convertPDFToJpegBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a progressive JPEG buffer |
#### Image Conversion Options
```typescript
{
scale?: number; // DPI multiplier (default: 3.0)
quality?: number; // 0100, WebP/JPEG only (default: 85)
maxWidth?: number; // Max output width in pixels
maxHeight?: number; // Max output height in pixels
}
```
### `ISmartPdfOptions` Interface
```typescript
{
port?: number; // Use a specific port
portRangeStart?: number; // Auto-allocation range start (default: 20000)
portRangeEnd?: number; // Auto-allocation range end (default: 30000)
}
```
## License and Legal Information
This repository contains open-source code licensed under the MIT License. A copy of the license can be found in the [LICENSE](./LICENSE) file.
**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 or third parties, 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 or the guidelines of the respective third-party owners, and any usage must be approved in writing. Third-party trademarks used herein are the property of their respective owners and used only in a descriptive manner, e.g. for an implementation of an API or similar.
### Company Information
Task Venture Capital GmbH
Registered at District Court Bremen HRB 35230 HB, Germany
For any legal inquiries or 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.

97
test/test.port.ts Normal file
View File

@@ -0,0 +1,97 @@
import { expect, tap } from '@git.zone/tstest/tapbundle';
import * as smartpdf from '../ts/index.js';
tap.test('should create multiple SmartPdf instances with automatic port allocation', async () => {
const instance1 = new smartpdf.SmartPdf();
const instance2 = new smartpdf.SmartPdf();
const instance3 = new smartpdf.SmartPdf();
// Start all instances
await instance1.start();
await instance2.start();
await instance3.start();
// Verify all instances have different ports
expect(instance1.serverPort).toBeGreaterThanOrEqual(20000);
expect(instance1.serverPort).toBeLessThanOrEqual(30000);
expect(instance2.serverPort).toBeGreaterThanOrEqual(20000);
expect(instance2.serverPort).toBeLessThanOrEqual(30000);
expect(instance3.serverPort).toBeGreaterThanOrEqual(20000);
expect(instance3.serverPort).toBeLessThanOrEqual(30000);
// Ensure all ports are different
expect(instance1.serverPort).not.toEqual(instance2.serverPort);
expect(instance1.serverPort).not.toEqual(instance3.serverPort);
expect(instance2.serverPort).not.toEqual(instance3.serverPort);
console.log(`Instance 1 port: ${instance1.serverPort}`);
console.log(`Instance 2 port: ${instance2.serverPort}`);
console.log(`Instance 3 port: ${instance3.serverPort}`);
// Test that all instances work correctly
const pdf1 = await instance1.getA4PdfResultForHtmlString('<h1>Instance 1</h1>');
const pdf2 = await instance2.getA4PdfResultForHtmlString('<h1>Instance 2</h1>');
const pdf3 = await instance3.getA4PdfResultForHtmlString('<h1>Instance 3</h1>');
expect(pdf1.buffer).toBeInstanceOf(Buffer);
expect(pdf2.buffer).toBeInstanceOf(Buffer);
expect(pdf3.buffer).toBeInstanceOf(Buffer);
// Clean up
await instance1.stop();
await instance2.stop();
await instance3.stop();
});
tap.test('should create SmartPdf instance with custom port range', async () => {
const customInstance = new smartpdf.SmartPdf({
portRangeStart: 25000,
portRangeEnd: 26000
});
await customInstance.start();
expect(customInstance.serverPort).toBeGreaterThanOrEqual(25000);
expect(customInstance.serverPort).toBeLessThanOrEqual(26000);
console.log(`Custom range instance port: ${customInstance.serverPort}`);
await customInstance.stop();
});
tap.test('should create SmartPdf instance with specific port', async () => {
const specificPortInstance = new smartpdf.SmartPdf({
port: 28888
});
await specificPortInstance.start();
expect(specificPortInstance.serverPort).toEqual(28888);
console.log(`Specific port instance: ${specificPortInstance.serverPort}`);
await specificPortInstance.stop();
});
tap.test('should throw error when specific port is already in use', async () => {
const instance1 = new smartpdf.SmartPdf({ port: 29999 });
await instance1.start();
const instance2 = new smartpdf.SmartPdf({ port: 29999 });
let errorThrown = false;
try {
await instance2.start();
} catch (error) {
errorThrown = true;
expect(error.message).toInclude('already in use');
}
expect(errorThrown).toBeTrue();
await instance1.stop();
});
export default tap.start();

View File

@@ -1,44 +1,295 @@
import { expect, tap } from '@pushrocks/tapbundle';
import * as smartpdf from '../ts/index';
import { expect, tap } from '@git.zone/tstest/tapbundle';
import * as smartpdf from '../ts/index.js';
import * as fs from 'fs';
import * as path from 'path';
let testSmartPdf: smartpdf.SmartPdf;
tap.test('should create a valid instance of smartpdf', async () => {
/**
* Ensures that a directory exists.
* @param dirPath - The directory path to ensure.
*/
function ensureDir(dirPath: string): void {
if (!fs.existsSync(dirPath)) {
fs.mkdirSync(dirPath, { recursive: true });
}
}
// Clean test results directory at start
const testResultsDir = path.join('.nogit', 'testresults');
if (fs.existsSync(testResultsDir)) {
fs.rmSync(testResultsDir, { recursive: true, force: true });
}
ensureDir(testResultsDir);
tap.test('should create a valid instance of SmartPdf', async () => {
testSmartPdf = new smartpdf.SmartPdf();
expect(testSmartPdf).to.be.instanceof(smartpdf.SmartPdf);
expect(testSmartPdf).toBeInstanceOf(smartpdf.SmartPdf);
});
tap.test('should start the instance', async () => {
tap.test('should start the SmartPdf instance', async () => {
await testSmartPdf.start();
});
tap.test('should create a pdf from html string', async () => {
await testSmartPdf.getPdfResultForHtmlString('hi');
tap.test('should create PDFs from HTML string', async () => {
const pdf1 = await testSmartPdf.getA4PdfResultForHtmlString('hi');
const pdf2 = await testSmartPdf.getA4PdfResultForHtmlString('hello');
expect(pdf1.buffer).toBeInstanceOf(Buffer);
expect(pdf2.buffer).toBeInstanceOf(Buffer);
});
tap.test('should create a pdf from website as A4', async () => {
await testSmartPdf.getPdfResultForWebsite('https://www.wikipedia.org');
tap.test('should create PDFs from websites', async () => {
const pdfA4 = await testSmartPdf.getPdfResultForWebsite('https://example.com');
const pdfSingle = await testSmartPdf.getFullWebsiteAsSinglePdf('https://example.com');
expect(pdfA4.buffer).toBeInstanceOf(Buffer);
expect(pdfSingle.buffer).toBeInstanceOf(Buffer);
});
tap.test('should create a pdf from website as single page PDF', async () => {
await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
tap.test('should create valid PDF results and write them to disk', async () => {
const writePdfToDisk = async (urlArg: string, fileName: string) => {
const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf(urlArg);
expect(pdfResult.buffer).toBeInstanceOf(Buffer);
ensureDir('.nogit');
fs.writeFileSync(path.join('.nogit', fileName), pdfResult.buffer as Buffer);
};
await writePdfToDisk('https://lossless.com/', '1.pdf');
await writePdfToDisk('https://layer.io', '2.pdf');
});
tap.test('should create a valid PDFResult', async () => {
const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf(
'https://maintainedby.lossless.com'
);
expect(pdfResult.buffer).to.be.instanceOf(Buffer);
const fs = await import('fs');
tap.test('should merge PDFs into a combined PDF', async () => {
const pdf1 = await testSmartPdf.readFileToPdfObject('.nogit/1.pdf');
const pdf2 = await testSmartPdf.readFileToPdfObject('.nogit/2.pdf');
const mergedBuffer = await testSmartPdf.mergePdfs([pdf1.buffer, pdf2.buffer]);
ensureDir('.nogit');
fs.writeFileSync(path.join('.nogit', 'combined.pdf'), mergedBuffer);
});
if (!fs.existsSync('.nogit/')) {
fs.mkdirSync('.nogit/');
tap.test('should create PNG images from combined PDF using Puppeteer conversion', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
const images = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
expect(images.length).toBeGreaterThan(0);
console.log('Puppeteer-based conversion image sizes:', images.map(img => img.length));
});
tap.test('should store PNG results from both conversion functions in .nogit/testresults', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
// Convert using Puppeteer-based function and store images
const imagesPuppeteer = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
imagesPuppeteer.forEach((img, index) => {
const filePath = path.join(testResultsDir, `png_combined_page${index + 1}.png`);
fs.writeFileSync(filePath, Buffer.from(img));
});
});
tap.test('should create a third PDF for image conversion tests', async () => {
const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
expect(pdfResult.buffer).toBeInstanceOf(Buffer);
ensureDir('.nogit');
fs.writeFileSync(path.join('.nogit', '3.pdf'), pdfResult.buffer as Buffer);
});
tap.test('should create WebP preview images from PDF', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
const webpPreviews = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer);
expect(webpPreviews.length).toBeGreaterThan(0);
console.log('WebP preview sizes:', webpPreviews.map(img => img.length));
// Also create PNG previews for comparison
const pngPreviews = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
console.log('PNG preview sizes:', pngPreviews.map(img => img.length));
// Save the first page as both WebP and PNG preview
fs.writeFileSync(path.join(testResultsDir, 'webp_default_page1.webp'), Buffer.from(webpPreviews[0]));
fs.writeFileSync(path.join(testResultsDir, 'png_default_page1.png'), Buffer.from(pngPreviews[0]));
});
tap.test('should create WebP previews with custom scale and quality', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Create smaller previews with lower quality for thumbnails
const thumbnails = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
scale: 0.5, // Create readable thumbnails at ~36 DPI
quality: 70
});
expect(thumbnails.length).toBeGreaterThan(0);
console.log('Thumbnail sizes:', thumbnails.map(img => img.length));
// Save thumbnails
thumbnails.forEach((thumb, index) => {
fs.writeFileSync(path.join(testResultsDir, `webp_thumbnail_page${index + 1}.webp`), Buffer.from(thumb));
});
});
tap.test('should create WebP previews with max dimensions', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Create previews with maximum dimensions (will use high scale but constrain to max size)
const constrainedPreviews = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
scale: smartpdf.SmartPdf.SCALE_HIGH, // Start with high quality
quality: 90,
maxWidth: 800,
maxHeight: 1000
});
expect(constrainedPreviews.length).toBeGreaterThan(0);
console.log('Constrained preview sizes:', constrainedPreviews.map(img => img.length));
// Save constrained preview
fs.writeFileSync(path.join(testResultsDir, 'webp_constrained_page1.webp'), Buffer.from(constrainedPreviews[0]));
});
tap.test('should verify WebP files are smaller than PNG', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Generate both PNG and WebP versions at the same scale for fair comparison
const comparisonScale = smartpdf.SmartPdf.SCALE_HIGH; // Both use 3.0 scale
const pngImages = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer, {
scale: comparisonScale
});
const webpImages = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
scale: comparisonScale,
quality: 85
});
expect(pngImages.length).toEqual(webpImages.length);
// Compare sizes
let totalPngSize = 0;
let totalWebpSize = 0;
pngImages.forEach((png, index) => {
const pngSize = png.length;
const webpSize = webpImages[index].length;
totalPngSize += pngSize;
totalWebpSize += webpSize;
const reduction = ((pngSize - webpSize) / pngSize * 100).toFixed(1);
console.log(`Page ${index + 1}: PNG=${pngSize} bytes, WebP=${webpSize} bytes, Reduction=${reduction}%`);
// Save comparison files
fs.writeFileSync(path.join(testResultsDir, `comparison_png_page${index + 1}.png`), Buffer.from(png));
fs.writeFileSync(path.join(testResultsDir, `comparison_webp_page${index + 1}.webp`), Buffer.from(webpImages[index]));
});
const totalReduction = ((totalPngSize - totalWebpSize) / totalPngSize * 100).toFixed(1);
console.log(`Total size reduction: ${totalReduction}% (PNG: ${totalPngSize} bytes, WebP: ${totalWebpSize} bytes)`);
// WebP should be smaller
expect(totalWebpSize).toBeLessThan(totalPngSize);
});
tap.test('should create JPEG images from PDF', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer);
expect(jpegImages.length).toBeGreaterThan(0);
console.log('JPEG image sizes:', jpegImages.map(img => img.length));
// Save the first page as JPEG
fs.writeFileSync(path.join(testResultsDir, 'jpeg_default_page1.jpg'), Buffer.from(jpegImages[0]));
});
tap.test('should create JPEG images with different quality levels', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Test different quality levels
const qualityLevels = [50, 70, 85, 95];
for (const quality of qualityLevels) {
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
scale: smartpdf.SmartPdf.SCALE_HIGH,
quality: quality
});
console.log(`JPEG quality ${quality}: ${jpegImages[0].length} bytes`);
// Save first page at each quality level
fs.writeFileSync(
path.join(testResultsDir, `jpeg_quality_${quality}_page1.jpg`),
Buffer.from(jpegImages[0])
);
}
fs.writeFileSync('.nogit/sample.pdf', pdfResult.buffer);
});
tap.test('should be able to close properly', async () => {
tap.test('should create JPEG images with max dimensions', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Create constrained JPEG images
const constrainedJpegs = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
scale: smartpdf.SmartPdf.SCALE_HIGH,
quality: 85,
maxWidth: 1200,
maxHeight: 1200
});
expect(constrainedJpegs.length).toBeGreaterThan(0);
console.log('Constrained JPEG sizes:', constrainedJpegs.map(img => img.length));
// Save constrained JPEG
fs.writeFileSync(path.join(testResultsDir, 'jpeg_constrained_page1.jpg'), Buffer.from(constrainedJpegs[0]));
});
tap.test('should compare file sizes between PNG, WebP, and JPEG', async () => {
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
// Generate all three formats at the same scale
const comparisonScale = smartpdf.SmartPdf.SCALE_HIGH; // 3.0 scale
const pngImages = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer, {
scale: comparisonScale
});
const webpImages = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
scale: comparisonScale,
quality: 85
});
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
scale: comparisonScale,
quality: 85
});
expect(pngImages.length).toEqual(webpImages.length);
expect(pngImages.length).toEqual(jpegImages.length);
// Compare sizes
let totalPngSize = 0;
let totalWebpSize = 0;
let totalJpegSize = 0;
pngImages.forEach((png, index) => {
const pngSize = png.length;
const webpSize = webpImages[index].length;
const jpegSize = jpegImages[index].length;
totalPngSize += pngSize;
totalWebpSize += webpSize;
totalJpegSize += jpegSize;
const webpReduction = ((pngSize - webpSize) / pngSize * 100).toFixed(1);
const jpegReduction = ((pngSize - jpegSize) / pngSize * 100).toFixed(1);
console.log(`Page ${index + 1}:`);
console.log(` PNG: ${pngSize} bytes`);
console.log(` WebP: ${webpSize} bytes (${webpReduction}% smaller than PNG)`);
console.log(` JPEG: ${jpegSize} bytes (${jpegReduction}% smaller than PNG)`);
});
const totalWebpReduction = ((totalPngSize - totalWebpSize) / totalPngSize * 100).toFixed(1);
const totalJpegReduction = ((totalPngSize - totalJpegSize) / totalPngSize * 100).toFixed(1);
console.log('\nTotal size comparison:');
console.log(`PNG: ${totalPngSize} bytes`);
console.log(`WebP: ${totalWebpSize} bytes (${totalWebpReduction}% reduction)`);
console.log(`JPEG: ${totalJpegSize} bytes (${totalJpegReduction}% reduction)`);
// JPEG and WebP should both be smaller than PNG
expect(totalJpegSize).toBeLessThan(totalPngSize);
expect(totalWebpSize).toBeLessThan(totalPngSize);
});
tap.test('should close the SmartPdf instance properly', async () => {
await testSmartPdf.stop();
});
tap.start();
export default tap.start();

8
ts/00_commitinfo_data.ts Normal file
View File

@@ -0,0 +1,8 @@
/**
* autocreated commitinfo by @push.rocks/commitinfo
*/
export const commitinfo = {
name: '@push.rocks/smartpdf',
version: '4.1.2',
description: 'A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.'
}

View File

@@ -6,4 +6,10 @@ declare global {
}
// normal
export * from './smartpdf.classes.smartpdf';
export * from './smartpdf.classes.smartpdf.js';
// additional types
import type * as tsclassTypes from '@tsclass/tsclass';
type IPdf = tsclassTypes.business.IPdf;
export type { IPdf };

View File

@@ -1 +0,0 @@
export * from './interface.pdfresult';

View File

@@ -1,5 +0,0 @@
export interface IPdfResult {
name: string;
id: string;
buffer: Buffer;
}

View File

@@ -1,8 +1,15 @@
import * as plugins from './smartpdf.plugins';
/*
* pdf candidate is a construct used internally for mapping html
* to pdf buffers delivered by puppeteer
*/
import * as plugins from './smartpdf.plugins.js';
export class PdfCandidate {
pdfId = plugins.smartunique.shortId();
doneDeferred = plugins.smartpromise.defer();
public htmlString: string;
public pdfId = plugins.smartunique.shortId();
public doneDeferred = plugins.smartpromise.defer();
constructor(public htmlString) {}
constructor(htmlStringArg: string) {
this.htmlString = htmlStringArg;
}
}

View File

@@ -1,25 +1,56 @@
import * as plugins from './smartpdf.plugins';
import * as paths from './smartpdf.paths';
import * as plugins from './smartpdf.plugins.js';
import * as paths from './smartpdf.paths.js';
import { Server } from 'http';
import { PdfCandidate } from './smartpdf.classes.pdfcandidate';
import { PdfCandidate } from './smartpdf.classes.pdfcandidate.js';
import { type IPdf } from '@tsclass/tsclass/dist_ts/business/pdf.js';
declare const document: any;
declare const document;
import * as interfaces from './interfaces';
export interface ISmartPdfOptions {
port?: number;
portRangeStart?: number;
portRangeEnd?: number;
}
export class SmartPdf {
// STATIC SCALE CONSTANTS
public static readonly SCALE_SCREEN = 2.0; // ~144 DPI - Good for screen display
public static readonly SCALE_HIGH = 3.0; // ~216 DPI - High quality (default)
public static readonly SCALE_PRINT = 6.0; // ~432 DPI - Print quality
/**
* Calculate scale factor for desired DPI
* PDF.js default is 72 DPI, so scale = desiredDPI / 72
*/
public static getScaleForDPI(dpi: number): number {
return dpi / 72;
}
// STATIC
public static async create(optionsArg?: ISmartPdfOptions) {
const smartpdfInstance = new SmartPdf(optionsArg);
return smartpdfInstance;
}
// INSTANCE
htmlServerInstance: Server;
serverPort: number;
headlessBrowser: plugins.smartpuppeteer.puppeteer.Browser;
externalBrowserBool: boolean = false;
private _readyDeferred: plugins.smartpromise.Deferred<void>;
private _candidates: { [key: string]: PdfCandidate } = {};
private _options: ISmartPdfOptions;
constructor() {
constructor(optionsArg?: ISmartPdfOptions) {
this._readyDeferred = new plugins.smartpromise.Deferred();
this._options = {
portRangeStart: 20000,
portRangeEnd: 30000,
...optionsArg
};
}
async start(headlessBrowserArg?) {
async start(headlessBrowserArg?: plugins.smartpuppeteer.puppeteer.Browser) {
const done = plugins.smartpromise.defer();
// lets set the external browser in case one is provided
this.headlessBrowser = headlessBrowserArg;
// setup puppeteer
@@ -27,23 +58,60 @@ export class SmartPdf {
this.externalBrowserBool = true;
} else {
this.headlessBrowser = await plugins.smartpuppeteer.getEnvAwareBrowserInstance({
forceNoSandbox: true,
forceNoSandbox: false,
});
}
// setup server
// Find an available port BEFORE creating server
const smartnetworkInstance = new plugins.smartnetwork.SmartNetwork();
if (this._options.port) {
// If a specific port is requested, check if it's available
const isPortAvailable = await smartnetworkInstance.isLocalPortUnused(this._options.port);
if (isPortAvailable) {
this.serverPort = this._options.port;
} else {
// Clean up browser if we created one
if (!this.externalBrowserBool && this.headlessBrowser) {
await this.headlessBrowser.close();
}
throw new Error(`Requested port ${this._options.port} is already in use`);
}
} else {
// Find a free port in the specified range
this.serverPort = await smartnetworkInstance.findFreePort(
this._options.portRangeStart,
this._options.portRangeEnd
);
if (!this.serverPort) {
// Clean up browser if we created one
if (!this.externalBrowserBool && this.headlessBrowser) {
await this.headlessBrowser.close();
}
throw new Error(`No free ports available in range ${this._options.portRangeStart}-${this._options.portRangeEnd}`);
}
}
// Now setup server after we know we have a valid port
const app = plugins.express();
app.get('/:pdfId', (req, res) => {
res.setHeader('PDF-ID', this._candidates[req.params.pdfId].pdfId);
res.send(this._candidates[req.params.pdfId].htmlString);
const wantedCandidate = this._candidates[req.params.pdfId];
if (!wantedCandidate) {
console.log(`${req.url} not attached to a candidate`);
return;
}
res.setHeader('pdf-id', wantedCandidate.pdfId);
res.send(wantedCandidate.htmlString);
});
this.htmlServerInstance = plugins.http.createServer(app);
const smartnetworkInstance = new plugins.smartnetwork.SmartNetwork();
const portAvailable = smartnetworkInstance.isLocalPortUnused(3210);
this.htmlServerInstance.listen(3210, 'localhost');
this.htmlServerInstance.listen(this.serverPort, 'localhost');
this.htmlServerInstance.on('listening', () => {
console.log(`SmartPdf server listening on port ${this.serverPort}`);
this._readyDeferred.resolve();
done.resolve();
});
await done.promise;
}
// stop
@@ -61,14 +129,18 @@ export class SmartPdf {
}
/**
* returns a pdf for a given html string;
* Returns a PDF for a given HTML string.
*/
async getPdfResultForHtmlString(htmlStringArg: string): Promise<interfaces.IPdfResult> {
async getA4PdfResultForHtmlString(htmlStringArg: string): Promise<plugins.tsclass.business.IPdf> {
await this._readyDeferred.promise;
const pdfCandidate = new PdfCandidate(htmlStringArg);
this._candidates[pdfCandidate.pdfId] = pdfCandidate;
const page = await this.headlessBrowser.newPage();
const response = await page.goto(`http://localhost:3210/${pdfCandidate.pdfId}`, {
await page.setViewport({
width: 794,
height: 1122,
});
const response = await page.goto(`http://localhost:${this.serverPort}/${pdfCandidate.pdfId}`, {
waitUntil: 'networkidle2',
});
const headers = response.headers();
@@ -80,11 +152,13 @@ export class SmartPdf {
}
const pdfBuffer = await page.pdf({
format: 'A4',
width: 794,
height: 1122,
printBackground: true,
displayHeaderFooter: false,
preferCSSPageSize: true,
});
// Convert Uint8Array to Node Buffer
const nodePdfBuffer = Buffer.from(pdfBuffer);
await page.close();
delete this._candidates[pdfCandidate.pdfId];
pdfCandidate.doneDeferred.resolve();
@@ -92,12 +166,19 @@ export class SmartPdf {
return {
id: pdfCandidate.pdfId,
name: `${pdfCandidate.pdfId}.js`,
buffer: pdfBuffer,
metadata: {
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
},
buffer: nodePdfBuffer,
};
}
async getPdfResultForWebsite(websiteUrl: string): Promise<interfaces.IPdfResult> {
async getPdfResultForWebsite(websiteUrl: string): Promise<plugins.tsclass.business.IPdf> {
const page = await this.headlessBrowser.newPage();
await page.setViewport({
width: 1980,
height: 1200,
});
await page.emulateMediaType('screen');
const response = await page.goto(websiteUrl, { waitUntil: 'networkidle2' });
const pdfId = plugins.smartunique.shortId();
@@ -108,45 +189,376 @@ export class SmartPdf {
};
});
const pdfBuffer = await page.pdf({
format: 'A4',
height: documentWidth,
height: documentHeight,
width: documentWidth,
printBackground: true,
displayHeaderFooter: false,
preferCSSPageSize: true,
});
// Convert Uint8Array to Node Buffer
const nodePdfBuffer = Buffer.from(pdfBuffer);
await page.close();
return {
id: pdfId,
name: `${pdfId}.js`,
buffer: pdfBuffer,
metadata: {
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
},
buffer: nodePdfBuffer,
};
}
async getFullWebsiteAsSinglePdf(websiteUrl: string) {
async getFullWebsiteAsSinglePdf(websiteUrl: string): Promise<plugins.tsclass.business.IPdf> {
const page = await this.headlessBrowser.newPage();
page.emulateMediaType('screen');
await page.setViewport({
width: 1920,
height: 1200,
});
await page.emulateMediaType('screen');
const response = await page.goto(websiteUrl, { waitUntil: 'networkidle2' });
const pdfId = plugins.smartunique.shortId();
// Use both document.body and document.documentElement to ensure we have a valid height and width.
const { documentHeight, documentWidth } = await page.evaluate(() => {
return {
documentHeight: document.height,
documentWidth: document.width,
documentHeight: Math.max(
document.body.scrollHeight,
document.documentElement.scrollHeight
) || 1200,
documentWidth: Math.max(
document.body.clientWidth,
document.documentElement.clientWidth
) || 1920,
};
});
// Update viewport height to the full document height.
await page.setViewport({
width: 1920,
height: documentHeight,
});
const pdfBuffer = await page.pdf({
format: 'A4',
height: documentWidth,
width: documentWidth,
height: documentHeight,
width: 1920,
printBackground: true,
displayHeaderFooter: false,
preferCSSPageSize: true,
scale: 1,
pageRanges: '1',
});
// Convert Uint8Array to Node Buffer
const nodePdfBuffer = Buffer.from(pdfBuffer);
await page.close();
return {
id: pdfId,
name: `${pdfId}.js`,
buffer: pdfBuffer,
metadata: {
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
},
buffer: nodePdfBuffer,
};
}
public async mergePdfs(inputPdfBuffers: Uint8Array[]): Promise<Uint8Array> {
const mergedPdf = await plugins.pdfLib.PDFDocument.create();
for (const pdfBytes of inputPdfBuffers) {
const pdfDoc = await plugins.pdfLib.PDFDocument.load(pdfBytes);
const pages = await mergedPdf.copyPages(pdfDoc, pdfDoc.getPageIndices());
pages.forEach((page) => mergedPdf.addPage(page));
}
const mergedPdfBytes = await mergedPdf.save();
return mergedPdfBytes;
}
public async readFileToPdfObject(pathArg: string): Promise<plugins.tsclass.business.IPdf> {
const absolutePath = plugins.smartpath.transform.makeAbsolute(pathArg);
const parsedPath = plugins.path.parse(absolutePath);
const smartfsInstance = new plugins.smartfs.SmartFs(new plugins.smartfs.SmartFsProviderNode());
const fileContent = await smartfsInstance.file(absolutePath).read();
const buffer = Buffer.from(fileContent);
return {
name: parsedPath.base,
buffer,
id: null,
metadata: null,
};
}
public async extractTextFromPdfBuffer(pdfBufferArg: Buffer): Promise<string> {
const deferred = plugins.smartpromise.defer<string>();
const pdfParser: any = new plugins.pdf2json();
pdfParser.on('pdfParser_dataReady', (pdfData: any) => {
let finalText = '';
for (const page of pdfData.Pages) {
for (const text of page.Texts) {
for (const letter of text.R) {
finalText = finalText + letter.T;
}
}
}
deferred.resolve(finalText);
});
pdfParser.parseBuffer(pdfBufferArg);
return deferred.promise;
}
/**
* Converts a PDF to PNG bytes for each page using Puppeteer and PDF.js.
* This method creates a temporary HTML page that loads PDF.js from a CDN,
* renders each PDF page to a canvas, and then screenshots each canvas element.
*/
public async convertPDFToPngBytes(
pdfBytes: Uint8Array,
options: {
scale?: number; // Scale factor for output size (default: 3.0 for 216 DPI)
maxWidth?: number; // Maximum width in pixels (optional)
maxHeight?: number; // Maximum height in pixels (optional)
} = {}
): Promise<Uint8Array[]> {
// Set default scale for higher quality output (3.0 = ~216 DPI)
const scale = options.scale || 3.0;
// Create a new page using the headless browser.
const page = await this.headlessBrowser.newPage();
// Prepare PDF data as a base64 string.
const base64Pdf: string = Buffer.from(pdfBytes).toString('base64');
// HTML template that loads PDF.js and renders the PDF.
const htmlTemplate: string = `
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>PDF to PNG Converter</title>
<style>
body { margin: 0; }
canvas { display: block; margin: 10px auto; }
</style>
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.min.js"></script>
</head>
<body>
<script>
(async function() {
pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.worker.min.js';
const pdfData = "__PDF_DATA__";
const raw = atob(pdfData);
const pdfArray = new Uint8Array([...raw].map(c => c.charCodeAt(0)));
const loadingTask = pdfjsLib.getDocument({data: pdfArray});
const pdf = await loadingTask.promise;
const numPages = pdf.numPages;
for (let pageNum = 1; pageNum <= numPages; pageNum++) {
const page = await pdf.getPage(pageNum);
// Apply scale factor to viewport
const viewport = page.getViewport({ scale: ${scale} });
// Apply max width/height constraints if specified
let finalScale = ${scale};
${options.maxWidth ? `
if (viewport.width > ${options.maxWidth}) {
finalScale = ${options.maxWidth} / (viewport.width / ${scale});
}` : ''}
${options.maxHeight ? `
if (viewport.height > ${options.maxHeight}) {
const heightScale = ${options.maxHeight} / (viewport.height / ${scale});
finalScale = Math.min(finalScale, heightScale);
}` : ''}
// Get final viewport with adjusted scale
const finalViewport = page.getViewport({ scale: finalScale });
const canvas = document.createElement('canvas');
const context = canvas.getContext('2d');
canvas.width = finalViewport.width;
canvas.height = finalViewport.height;
canvas.setAttribute('data-page', pageNum);
await page.render({ canvasContext: context, viewport: finalViewport }).promise;
document.body.appendChild(canvas);
}
window.renderComplete = true;
})();
</script>
</body>
</html>
`;
// Replace the placeholder with the actual base64 PDF data.
const htmlContent: string = htmlTemplate.replace("__PDF_DATA__", base64Pdf);
// Set the page content.
await page.setContent(htmlContent, { waitUntil: 'networkidle0' });
// Wait until the PDF.js rendering is complete.
await page.waitForFunction(() => (window as any).renderComplete === true, { timeout: 30000 });
// Query all canvas elements (each representing a rendered PDF page).
const canvasElements = await page.$$('canvas');
const pngBuffers: Uint8Array[] = [];
for (const canvasElement of canvasElements) {
// Screenshot the canvas element. The screenshot will be a PNG buffer.
const screenshotBuffer = (await canvasElement.screenshot({ encoding: 'binary' })) as Buffer;
pngBuffers.push(new Uint8Array(screenshotBuffer));
}
await page.close();
return pngBuffers;
}
/**
* Converts a PDF to WebP bytes for each page.
* This method creates web-optimized images using WebP format.
* WebP provides 25-35% better compression than JPEG/PNG while maintaining quality.
*/
public async convertPDFToWebpBytes(
pdfBytes: Uint8Array,
options: {
scale?: number; // Scale factor for preview size (default: 3.0 for 216 DPI)
quality?: number; // WebP quality 0-100 (default: 85)
maxWidth?: number; // Maximum width in pixels (optional)
maxHeight?: number; // Maximum height in pixels (optional)
} = {}
): Promise<Uint8Array[]> {
// Set default options for higher quality output (3.0 = ~216 DPI)
const scale = options.scale || 3.0;
const quality = options.quality || 85;
// Create a new page using the headless browser
const page = await this.headlessBrowser.newPage();
// Prepare PDF data as a base64 string
const base64Pdf: string = Buffer.from(pdfBytes).toString('base64');
// HTML template that loads PDF.js and renders the PDF with scaling
const htmlTemplate: string = `
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>PDF to WebP Preview Converter</title>
<style>
body { margin: 0; }
canvas { display: block; margin: 10px auto; }
</style>
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.min.js"></script>
</head>
<body>
<script>
(async function() {
pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.worker.min.js';
const pdfData = "__PDF_DATA__";
const raw = atob(pdfData);
const pdfArray = new Uint8Array([...raw].map(c => c.charCodeAt(0)));
const loadingTask = pdfjsLib.getDocument({data: pdfArray});
const pdf = await loadingTask.promise;
const numPages = pdf.numPages;
for (let pageNum = 1; pageNum <= numPages; pageNum++) {
const page = await pdf.getPage(pageNum);
// Apply scale factor to viewport
const viewport = page.getViewport({ scale: ${scale} });
// Apply max width/height constraints if specified
let finalScale = ${scale};
${options.maxWidth ? `
if (viewport.width > ${options.maxWidth}) {
finalScale = ${options.maxWidth} / (viewport.width / ${scale});
}` : ''}
${options.maxHeight ? `
if (viewport.height > ${options.maxHeight}) {
const heightScale = ${options.maxHeight} / (viewport.height / ${scale});
finalScale = Math.min(finalScale, heightScale);
}` : ''}
// Get final viewport with adjusted scale
const finalViewport = page.getViewport({ scale: finalScale });
const canvas = document.createElement('canvas');
const context = canvas.getContext('2d');
canvas.width = finalViewport.width;
canvas.height = finalViewport.height;
canvas.setAttribute('data-page', pageNum);
await page.render({ canvasContext: context, viewport: finalViewport }).promise;
document.body.appendChild(canvas);
}
window.renderComplete = true;
})();
</script>
</body>
</html>
`;
// Replace the placeholder with the actual base64 PDF data
const htmlContent: string = htmlTemplate.replace("__PDF_DATA__", base64Pdf);
// Set the page content
await page.setContent(htmlContent, { waitUntil: 'networkidle0' });
// Wait until the PDF.js rendering is complete
await page.waitForFunction(() => (window as any).renderComplete === true, { timeout: 30000 });
// Query all canvas elements (each representing a rendered PDF page)
const canvasElements = await page.$$('canvas');
const webpBuffers: Uint8Array[] = [];
for (const canvasElement of canvasElements) {
// Screenshot the canvas element as WebP
const screenshotBuffer = (await canvasElement.screenshot({
type: 'webp',
quality: quality,
encoding: 'binary'
})) as Buffer;
webpBuffers.push(new Uint8Array(screenshotBuffer));
}
await page.close();
return webpBuffers;
}
/**
* Converts a PDF to progressive JPEG bytes for each page.
* This method creates progressive JPEG images that load in multiple passes,
* showing a low-quality preview first, then progressively improving.
* Uses SmartJimp for true progressive JPEG encoding.
*/
public async convertPDFToJpegBytes(
pdfBytes: Uint8Array,
options: {
scale?: number; // Scale factor for output size (default: 3.0 for 216 DPI)
quality?: number; // JPEG quality 0-100 (default: 85)
maxWidth?: number; // Maximum width in pixels (optional)
maxHeight?: number; // Maximum height in pixels (optional)
} = {}
): Promise<Uint8Array[]> {
// First, convert PDF to PNG using our existing method
const pngBuffers = await this.convertPDFToPngBytes(pdfBytes, {
scale: options.scale,
maxWidth: options.maxWidth,
maxHeight: options.maxHeight
});
// Initialize SmartJimp in sharp mode for progressive JPEG support
const smartJimpInstance = new plugins.smartjimp.SmartJimp({ mode: 'sharp' });
// Convert each PNG to progressive JPEG
const jpegBuffers: Uint8Array[] = [];
const quality = options.quality || 85;
for (const pngBuffer of pngBuffers) {
// Convert PNG buffer to progressive JPEG
const jpegBuffer = await smartJimpInstance.computeAssetVariation(
Buffer.from(pngBuffer),
{
format: 'jpeg',
progressive: true,
// SmartJimp uses a different quality scale, need to check if adjustment is needed
// For now, pass through the quality value
quality
}
);
jpegBuffers.push(new Uint8Array(jpegBuffer));
}
return jpegBuffers;
}
}

View File

@@ -1,3 +1,6 @@
import * as plugins from './smartpdf.plugins';
import * as plugins from './smartpdf.plugins.js';
export const packageDir = plugins.path.join(__dirname, '../');
export const packageDir = plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../'
);

View File

@@ -5,15 +5,36 @@ import * as path from 'path';
export { http, path };
// @pushrocks
import * as smartfile from '@pushrocks/smartfile';
import * as smartpromise from '@pushrocks/smartpromise';
import * as smartpuppeteer from '@pushrocks/smartpuppeteer';
import * as smartnetwork from '@pushrocks/smartnetwork';
import * as smartunique from '@pushrocks/smartunique';
import * as smartbuffer from '@push.rocks/smartbuffer';
import * as smartfs from '@push.rocks/smartfs';
import * as smartdelay from '@push.rocks/smartdelay';
import * as smartpromise from '@push.rocks/smartpromise';
import * as smartpath from '@push.rocks/smartpath';
import * as smartpuppeteer from '@push.rocks/smartpuppeteer';
import * as smartnetwork from '@push.rocks/smartnetwork';
import * as smartunique from '@push.rocks/smartunique';
import * as smartjimp from '@push.rocks/smartjimp';
export { smartfile, smartpromise, smartpuppeteer, smartunique, smartnetwork };
export {
smartbuffer,
smartfs,
smartdelay,
smartpromise,
smartpath,
smartpuppeteer,
smartunique,
smartnetwork,
smartjimp,
};
// tsclass scope
import * as tsclass from '@tsclass/tsclass';
export { tsclass };
// thirdparty
import express from 'express';
import pdf2json from 'pdf2json';
import pdfLib from 'pdf-lib';
export { express };
export { express, pdf2json, pdfLib, };

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"
}