Support PDF as input type

If the input file is a PDF, the requested page is converted into a PNG
with fitz and then passed onto to tesseract for text extraction.

cmd/super-zaje/super-zaje.go

@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"errors"
+	"fmt"
 	"io"
 	"log"
 	"net/http"
@@ -11,13 +12,18 @@ import (
 	"regexp"
 	"strings"
 
+	"github.com/gen2brain/go-fitz"
 	"github.com/jessp01/zaje"
 	"github.com/otiai10/gosseract/v2"
 	"github.com/urfave/cli"
 )
 
 func main() {
 
+	var isPdf bool
+
+	var pdfPage int
+
 	app := cli.NewApp()
 	zaje.PopulateAppMetadata(app)
 
@@ -28,6 +34,20 @@ func main() {
 	},
 	)
 
+	app.Flags = append(app.Flags, cli.BoolFlag{
+		Name:        "pdf",
+		Usage:       "Pass if input is a PDF file.\n",
+		Destination: &isPdf,
+	},
+	)
+
+	app.Flags = append(app.Flags, cli.IntFlag{
+		Name:        "pdf-page-number, pn",
+		Usage:       "When working on a PDF, set the page to process (first page is 0, not 1).\n",
+		Destination: &pdfPage,
+	},
+	)
+
 	app.Action = func(c *cli.Context) error {
 		log.SetFlags(log.LstdFlags | log.Lshortfile)
 		fi, err := os.Stdin.Stat()
@@ -42,6 +62,31 @@ func main() {
 				return errors.New("no input file provided. " + app.Name + " needs a file or data from STDIN")
 			}
 			filename = c.Args().Get(0)
+			if isPdf {
+				imgFileName := filepath.Join(os.TempDir(), fmt.Sprintf("%s_p%d.png", filepath.Base(filename), pdfPage))
+				imageFilePtr, err := os.Create(imgFileName)
+				if err != nil {
+					log.Fatal(err)
+				}
+				doc, err := fitz.New(filename)
+				if err != nil {
+					log.Fatal(err)
+				}
+
+				img, err := doc.ImagePNG(pdfPage, 300.00)
+				if err != nil {
+					log.Fatal(err)
+				}
+
+				err = os.WriteFile(imgFileName, img, 0644)
+				if err != nil {
+					log.Fatal(err)
+				}
+
+				imageFilePtr.Close()
+				doc.Close()
+				filename = imgFileName
+			}
 			data, err := zaje.ReadDataFromFile(filename)
 			if err != nil {
 				log.Fatal(err)

go.mod

@@ -1,16 +1,21 @@
 module github.com/jessp01/zaje
 
-go 1.19
+go 1.22
+
+toolchain go1.22.2
 
 require (
 	github.com/fatih/color v1.15.0
+	github.com/gen2brain/go-fitz v1.24.14
 	github.com/jessp01/gohighlight v0.21.1-17
 	github.com/otiai10/gosseract/v2 v2.4.0
 	github.com/urfave/cli v1.22.14
 )
 
 require (
 	github.com/cpuguy83/go-md2man/v2 v2.0.2 // indirect
+	github.com/ebitengine/purego v0.8.0 // indirect
+	github.com/jupiterrider/ffi v0.2.0 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.17 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect

go.sum

@@ -4,10 +4,16 @@ github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46t
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/ebitengine/purego v0.8.0 h1:JbqvnEzRvPpxhCJzJJ2y0RbiZ8nyjccVUrSM3q+GvvE=
+github.com/ebitengine/purego v0.8.0/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
 github.com/fatih/color v1.15.0 h1:kOqh6YHBtK8aywxGerMG2Eq3H6Qgoqeo13Bk2Mv/nBs=
 github.com/fatih/color v1.15.0/go.mod h1:0h5ZqXfHYED7Bhv2ZJamyIOUej9KtShiJESRwBDUSsw=
+github.com/gen2brain/go-fitz v1.24.14 h1:09weRkjVtLYNGo7l0J7DyOwBExbwi8SJ9h8YPhw9WEo=
+github.com/gen2brain/go-fitz v1.24.14/go.mod h1:0KaZeQgASc20Yp5R/pFzyy7SmP01XcoHKNF842U2/S4=
 github.com/jessp01/gohighlight v0.21.1-17 h1:/1tJS01Q9ss/ueOeZbVjSsDKdFPXjuOMbQYna0tsp5g=
 github.com/jessp01/gohighlight v0.21.1-17/go.mod h1:52r0Yxd1+T9f7uLenaO2/34K3gPOejxCxXwdNc/2Z8Y=
+github.com/jupiterrider/ffi v0.2.0 h1:tMM70PexgYNmV+WyaYhJgCvQAvtTCs3wXeILPutihnA=
+github.com/jupiterrider/ffi v0.2.0/go.mod h1:yqYqX5DdEccAsHeMn+6owkoI2llBLySVAF8dwCDZPVs=
 github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
 github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=