HarpJS to Hugo Blog Migrator

harp2hugo.go

/*
This tool takes a blog built on Harp.js (http://harpjs.com/) with the Baseline
theme (https://github.com/rosshj/baseline) and converts it into something
usable by Hugo (https://gohugo.io/). It will not work out of the box for you,
as it has some customisations to deal with mixed trailing/non-trailing slashes
and mixed use of directories for posts. This is what happens when you go from
Posterous to WordPress to Harp to Hugo! I also changed the format of _data.json
to put all the posts in an array to make it easier to parse before running
this tool. But it should be very easy to modify everything to suit your needs.
Just run it in the directory with all the Markdown source.

The MIT License (MIT)

Copyright (c) 2015 Conor O'Neill ([email protected])

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.
*/

package main

import (
	"encoding/json"
	"fmt"
	"io/ioutil"
	"os"
	"path/filepath"
	"strings"
	"time"
)

type Feed struct {
	Layout bool
}

type Sitemap struct {
	Layout bool
}

type CNAME struct {
	Layout bool
}

type Entry struct {
	ID          int
	Author      string
	Date        int64
	Ptype       string
	Description string
	Slug        string
	Status      string
	Title       string
	FBImage     string `json:"FBImage,omitempty"`
}

type Config struct {
	Feed    Feed
	Sitemap Sitemap
	CNAME   CNAME
	Entrys  []Entry
}

var conf Config

func visit(path string, f os.FileInfo, err error) error {
	var slug string
	if strings.HasSuffix(path, ".md") {
		if strings.HasSuffix(path, "index.md") {
			slug = filepath.Base(filepath.Dir(path))
			//fmt.Printf("index.md Visited: %s\n", slug)
		} else {
			slug = filepath.Base(path)[:len(filepath.Base(path))-3]
			//fmt.Printf("Non index.md Visited: %s\n", slug)
		}
	} else {
		// fmt.Printf("Non Markdown Visited: %s\n", path)
	}
	if len(slug) > 0 {
		for _, post := range conf.Entrys {
			if post.Slug == slug {
				outtext := "+++\n"
				tm := time.Unix(post.Date/1000, 0)
				outtext += "date = \"" + tm.Format(time.RFC3339) + "\"\n"
				outtext += "draft = false\n"
				outtext += "title = \"" + post.Title + "\"\n"
				outtext += "description = \"" + post.Description + "\"\n"
				outtext += "slug = \"" + post.Slug + "\"\n"
				outtext += "+++\n\n"
				readfile, err := ioutil.ReadFile(path)
				if err == nil {
					outtext += string(readfile)
					err := ioutil.WriteFile(path, []byte(outtext), 0644)
					if err != nil {
						panic(err)
					}
					fmt.Printf("Updated: %s\n", path)
				}
			}
		}
	}
	return nil
}

func main() {
	content, err := ioutil.ReadFile("_data.json")
	if err != nil {
		fmt.Print("Error:", err)
	}
	err = json.Unmarshal(content, &conf)
	if err != nil {
		fmt.Print("Error:", err)
	}

	err = filepath.Walk(".", visit)
}