Convert MS Office documents to PDF

converter.go

package main

import (
	"io"
	"io/ioutil"
	"log"
	"net/http"
	"os"
	"os/exec"
	"time"

	"github.com/creasty/defaults"
)

var httpClient = &http.Client{
	Transport: &http.Transport{
		MaxIdleConnsPerHost: 20,
	},
	Timeout: time.Second * 30,
}

type Converter struct {
	SrcURL      string
	TimeoutSec  time.Duration `default:"600"`
}

func (c *Converter) download() (*os.File, error) {
	res, err := httpClient.Get(c.SrcURL)
	if err != nil {
		return nil, err
	}
	defer res.Body.Close()

	fp, err := ioutil.TempFile("", "foo")
	if err != nil {
		return nil, err
	}
	defer fp.Close()

	if _, err := io.Copy(fp, res.Body); err != nil {
		return fp, err
	}

	return fp, err
}

func (c *Converter) convert(downloaded *os.File) (*os.File, error) {
	cmd := exec.Command(
		"libreoffice",
		"--headless",
		"--nodefault",
		"--nofirststartwizard",
		"--nolockcheck",
		"--nologo",
		"--norestore",
		"--invisible",
		"--convert-to",
		"pdf",
		"--outdir",
		os.TempDir(),
		downloaded.Name(),
	)
	if err := cmd.Start(); err != nil {
		return nil, err
	}

	done := make(chan error, 1)
	go func() {
		done <- cmd.Wait()
	}()

	select {
	case <-time.After(c.TimeoutSec * time.Second):
		if err := cmd.Process.Kill(); err != nil {
			log.Printf("Conversion time limit exceeded. url = %s\n", c.SrcURL)
			return nil, err
		}
	case err := <-done:
		if err != nil {
			return nil, err
		}
	}

	fp, err := os.Open(downloaded.Name() + ".pdf")
	if err != nil {
		return nil, err
	}
	return fp, nil
}

func (c *Converter) Perform(callback func(fp *os.File) error) error {
	if err := defaults.Set(c); err != nil {
		return err
	}

	downloaded, err := c.download()
	if err != nil {
		return err
	}
	defer os.Remove(downloaded.Name())

	converted, err := c.convert(downloaded)
	if err != nil {
		return err
	}
	defer os.Remove(converted.Name())

	return callback(converted)
}

Dockerfile

FROM ubuntu:16.04

RUN set -ex \
    && apt-get update \
    && apt-get install -y locales \
    && locale-gen en_US.UTF-8 \
    && update-locale LANG=en_US.UTF-8 \
    && apt-get clean \
    && rm -rf /var/cache/apt/archives/* /var/lib/apt/lists/*
ENV LC_ALL C
ENV LC_ALL en_US.UTF-8

ENV DEBIAN_FRONTEND noninteractive

RUN set -ex \
    && apt-get update \
    && apt-get install -y --no-install-recommends \
      curl \
      software-properties-common \
    && apt-get clean \
    && rm -rf /var/cache/apt/archives/* /var/lib/apt/lists/*

# LibreOffice
# Based on xcgd/libreoffice
# @see https://hub.docker.com/r/xcgd/libreoffice/~/dockerfile/
RUN set -ex \
    && apt-get update \
    && apt-get install -y --no-install-recommends \
      libreoffice-writer \
      libreoffice-calc \
      libreoffice-impress \
      ure \
      libreoffice-java-common \
      libreoffice-core \
      libreoffice-common \
      fonts-opensymbol \
      hyphen-fr \
      hyphen-de \
      hyphen-en-us \
      hyphen-it \
      hyphen-ru \
      fonts-dejavu \
      fonts-dejavu-core \
      fonts-dejavu-extra \
      fonts-dustin \
      fonts-f500 \
      fonts-fanwood \
      fonts-freefont-ttf \
      fonts-liberation \
      fonts-lmodern \
      fonts-lyx \
      fonts-sil-gentium \
      fonts-texgyre \
      fonts-tlwg-purisa \
      fonts-ipafont \
    && apt-get clean \
    && rm -rf /var/cache/apt/archives/* /var/lib/apt/lists/*

RUN mkdir /app
COPY ./bin  /app/bin

EXPOSE 80
CMD ["/app/bin/server"]