Files
Stirling-PDF/Taskfile.yml
T
EthanHealy01 4487f23ff7 feat(pdf-to-markdown): add pymupdf-convert CLI for faster PDF→Markdown conversion
Introduces a new  directory containing a small standalone
CLI tool () that converts PDFs to Markdown using PyMuPDF
and pymupdf4llm. When installed, it replaces the slower pdftohtml-based
converter with a significantly faster path.
The tool is invoked as an OS subprocess, following the same pattern already
used for LibreOffice and Tesseract. A new  service handles
discovery (PATH probe, cached 30 s), temp file I/O, and process execution via
the existing  infrastructure. Auto-detected at startup via
 — no configuration flag required. Falls back
transparently to the bundled pdftohtml converter if not found.
 is baked into the Docker base image via the existing
Python venv build stage and symlinked onto PATH, so all Docker users get
the faster path automatically with no manual steps.
AGPL notice:  is licensed under AGPL-3.0-or-later because
it depends on PyMuPDF (AGPL-3.0 / Artifex commercial). It is a SEPARATE
program from the rest of Stirling PDF and shares no source code with the
MIT-licensed core or the proprietary engine. The subprocess boundary
ensures the AGPL copyleft attaches to this tool alone and does not extend
to Stirling PDF. The LICENSE file and pymupdf-worker/LICENSE document this
separation explicitly. Do not replace the subprocess invocation with an
in-process import of PyMuPDF.
2026-06-01 19:42:49 +01:00

182 lines
4.9 KiB
YAML

version: '3'
output: prefixed
vars:
FIND_FREE_PORT_PS: powershell -NoProfile -File scripts/find-free-port.ps1
FIND_FREE_PORT_SH: bash scripts/find-free-port.sh
includes:
backend:
taskfile: .taskfiles/backend.yml
dir: .
frontend:
taskfile: .taskfiles/frontend.yml
dir: frontend
engine:
taskfile: .taskfiles/engine.yml
dir: engine
docker:
taskfile: .taskfiles/docker.yml
dir: .
desktop:
taskfile: .taskfiles/desktop.yml
dir: frontend
e2e:
taskfile: .taskfiles/e2e.yml
dir: .
pymupdf:
taskfile: .taskfiles/pymupdf.yml
dir: pymupdf-worker
tasks:
# ============================================================
# Setup & Prerequisites
# ============================================================
install:
desc: "Install all project dependencies"
cmds:
- task: frontend:install
- task: engine:install
# ============================================================
# Development
# ============================================================
dev:
desc: "Start backend + frontend concurrently on free ports"
vars:
PORTS:
sh: '{{if eq OS "windows"}}{{.FIND_FREE_PORT_PS}} 8080 5173{{else}}{{.FIND_FREE_PORT_SH}} 8080 5173{{end}}'
BACKEND_PORT: '{{index (splitList "\n" .PORTS) 0}}'
FRONTEND_PORT: '{{index (splitList "\n" .PORTS) 1}}'
deps:
- task: backend:dev
vars:
PORT: '{{.BACKEND_PORT}}'
- task: frontend:dev
vars:
PORT: '{{.FRONTEND_PORT}}'
BACKEND_URL: 'http://localhost:{{.BACKEND_PORT}}'
OPEN: "true"
dev:saas:
desc: "Start SaaS backend + frontend concurrently on free ports"
vars:
PORTS:
sh: '{{if eq OS "windows"}}{{.FIND_FREE_PORT_PS}} 8080 5173{{else}}{{.FIND_FREE_PORT_SH}} 8080 5173{{end}}'
BACKEND_PORT: '{{index (splitList "\n" .PORTS) 0}}'
FRONTEND_PORT: '{{index (splitList "\n" .PORTS) 1}}'
deps:
- task: backend:dev:saas
vars:
PORT: '{{.BACKEND_PORT}}'
- task: frontend:dev:saas
vars:
PORT: '{{.FRONTEND_PORT}}'
BACKEND_URL: 'http://localhost:{{.BACKEND_PORT}}'
OPEN: "true"
dev:all:
desc: "Start backend + frontend + engine concurrently on free ports"
vars:
PORTS:
sh: '{{if eq OS "windows"}}{{.FIND_FREE_PORT_PS}} 8080 5173 5001{{else}}{{.FIND_FREE_PORT_SH}} 8080 5173 5001{{end}}'
BACKEND_PORT: '{{index (splitList "\n" .PORTS) 0}}'
FRONTEND_PORT: '{{index (splitList "\n" .PORTS) 1}}'
ENGINE_PORT: '{{index (splitList "\n" .PORTS) 2}}'
deps:
- task: engine:dev
vars:
PORT: '{{.ENGINE_PORT}}'
- task: backend:dev
vars:
PORT: '{{.BACKEND_PORT}}'
AIENGINE_URL: 'http://localhost:{{.ENGINE_PORT}}'
- task: frontend:dev
vars:
PORT: '{{.FRONTEND_PORT}}'
BACKEND_URL: 'http://localhost:{{.BACKEND_PORT}}'
OPEN: "true"
# ============================================================
# Build
# ============================================================
build:
desc: "Build all components"
cmds:
- task: backend:build
- task: frontend:build
# ============================================================
# Test
# ============================================================
test:
desc: "Run ALL tests (backend + frontend + engine)"
cmds:
- task: backend:test
- task: frontend:test
- task: engine:test
# ============================================================
# Lint & Format
# ============================================================
lint:
desc: "Run all linters"
cmds:
- task: frontend:lint
- task: engine:lint
fix:
desc: "Auto-fix all components"
cmds:
- task: backend:fix
- task: frontend:fix
- task: engine:fix
format:
desc: "Auto-fix formatting across all components"
cmds:
- task: backend:format
- task: frontend:format
- task: engine:format
format:check:
desc: "Check formatting across all components"
cmds:
- task: backend:format:check
- task: frontend:format:check
- task: engine:format:check
# ============================================================
# Quality Gate
# ============================================================
check:
desc: "Quick quality gate for local development"
cmds:
- task: backend:check
- task: frontend:check
- task: engine:check
check:all:
desc: "Full CI quality gate"
cmds:
- task: backend:check
- task: frontend:check:all
- task: engine:check
# ============================================================
# Clean
# ============================================================
clean:
desc: "Clean all build artifacts"
cmds:
- task: backend:clean
- task: engine:clean