gopdfocr

package main

import (
    "fmt"
    sp "github.com/scipipe/scipipe"
    comp "github.com/scipipe/scipipe/components"
    "io/ioutil"
    //  "path/filepath"
    "os"
    "strings"
)

func main() {

    path := "data/*/attachments/*.pdf"

    wf := sp.NewWorkflow("pdf2ocr", 20)

    globpdf := comp.NewFileGlobber(wf, "findpdf", path)

    ximages := wf.NewProc("pdfimages", "pdfimages -tiff -p \"{i:in}\" \"{i:in}\" ; ls \"{i:in}\"*.tif > {o:out} ") // {o:out}
    ximages.In("in").From(globpdf.Out())

    ocr := wf.NewProc("tesseract", "# Just create the ports: {i:tiffiles} {o:out}")
    ocr.CustomExecute = func(t *sp.Task) {
        tiffiles, err := ioutil.ReadFile(t.InPath("tiffiles"))
        sp.Check(err)

        tifFiles := strings.Split(string(tiffiles), "\n")
        for _, tifFile := range tifFiles {
            //fmt.Println(filepath.Abs(tifFile))
            fmt.Println(os.Getwd())
            //sp.ExecCmd(fmt.Sprintf("tesseract %s %s.ocr -psm 1 -l eng && ls %s*.txt >> %s", tifFile, tifFile, tifFile, t.OutIP("out").TempPath()))
            //sp.ExecCmd(fmt.Sprintf("/usr/bin/tesseract \"%s\" \"%s.ocr\" --psm 1 --oem 1 -l eng ", tifFile, tifFile))
            sp.ExecCmd(fmt.Sprintf("ls %s  ", tifFile))
        }
    }
    ocr.In("tiffiles").From(ximages.Out("out"))
    //  ocr.SetOut("out", "{i:tiffiles}.tesseract.out")

    wf.Run()
}
~