rescribe: support CCITTFaxDecode (tiff) encoded images in PDF reading

3 files changed, 57 insertions, 16 deletions

diff --git a/cmd/rescribe/main.go b/cmd/rescribe/main.go
index 74f6440..2c37dc5 100644
--- a/cmd/rescribe/main.go
+++ b/cmd/rescribe/main.go
@@ -28,6 +28,7 @@ import (
 	"strings"
 	"time"
 
+	"golang.org/x/image/tiff"
 	"rescribe.xyz/bookpipeline"
 	"rescribe.xyz/bookpipeline/internal/pipeline"
 	"rescribe.xyz/pdf"
@@ -424,7 +425,9 @@ func extractPdfImgs(ctx context.Context, path string) (string, error) {
 
 // rmIfNotImage attempts to decode a given file as an image. If it is
 // decode-able as PNG, then rename file extension from .jpg to .png,
-// if it fails to be read as PNG or JPEG it will be deleted.
+// if it is decode-able as TIFF then convert to PNG and rename file
+// extension appropriately, if it fails to be read as PNG, TIFF or
+// JPEG it will just be deleted.
 func rmIfNotImage(f string) error {
 	r, err := os.Open(f)
 	defer r.Close()
@@ -448,12 +451,39 @@ func rmIfNotImage(f string) error {
 		return fmt.Errorf("Failed to open image %s: %v\n", f, err)
 	}
 	_, err = jpeg.Decode(r)
+	if err == nil {
+		return nil
+	}
+
+	r, err = os.Open(f)
+	defer r.Close()
 	if err != nil {
+		return fmt.Errorf("Failed to open image %s: %v\n", f, err)
+	}
+	t, err := tiff.Decode(r)
+	if err == nil {
+		b := strings.TrimSuffix(f, ".jpg")
+		n, err := os.Create(b+".png")
+		defer n.Close()
+		if err != nil {
+			return fmt.Errorf("Failed to create file to store new png %s from tiff %s: %v\n", b+".png", f, err)
+		}
+		err = png.Encode(n, t)
+		if err != nil {
+			return fmt.Errorf("Failed to encode tiff as png for %s: %v\n", f, err)
+		}
 		r.Close()
 		err = os.Remove(f)
 		if err != nil {
-			return fmt.Errorf("Failed to remove invalid image %s: %v", f, err)
+			return fmt.Errorf("Failed to remove original tiff %s: %v\n", f, err)
 		}
+		return nil
+	}
+
+	r.Close()
+	err = os.Remove(f)
+	if err != nil {
+		return fmt.Errorf("Failed to remove invalid image %s: %v", f, err)
 	}
 
 	return nil
diff --git a/go.mod b/go.mod
index 2ac72fa..eecbbbb 100644
--- a/go.mod
+++ b/go.mod
@@ -7,8 +7,8 @@ require (
 	github.com/aws/aws-sdk-go v1.40.6
 	github.com/nickjwhite/gofpdf v1.12.7-0.20210817123627-3cbaeb9797ef
 	github.com/wcharczuk/go-chart/v2 v2.1.0
-	golang.org/x/image v0.0.0-20220601225756-64ec528b34cd
-	rescribe.xyz/pdf v0.1.3
-	rescribe.xyz/preproc v0.4.2
+	golang.org/x/image v0.1.0
+	rescribe.xyz/pdf v0.1.4
+	rescribe.xyz/preproc v0.4.3
 	rescribe.xyz/utils v0.1.3
 )
diff --git a/go.sum b/go.sum
index 1f5c2af..a69aa7a 100644
--- a/go.sum
+++ b/go.sum
@@ -297,8 +297,9 @@ github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9de
 github.com/yuin/goldmark v1.1.32/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
-github.com/yuin/goldmark v1.4.0 h1:OtISOGfH6sOWa1/qXqqAiOIAO6Z5J3AEAE18WAq6BiQ=
 github.com/yuin/goldmark v1.4.0/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
+github.com/yuin/goldmark v1.4.13 h1:fVcFKWvrslecOb/tg+Cc05dkeYx540o0FuFt3nUVDoE=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.etcd.io/etcd/api/v3 v3.5.0/go.mod h1:cbVKeC6lCfl7j/8jBhAK6aIYO9XOjdptoxU/nLQcPvs=
 go.etcd.io/etcd/client/pkg/v3 v3.5.0/go.mod h1:IJHfcCEKxYu1Os13ZdwCwIUTUVGYTSAM3YSwc9/Ac1g=
 go.etcd.io/etcd/client/v2 v2.305.0/go.mod h1:h9puh54ZTgAKtEbut2oe9P4L/oqKCVB6xsXlzd7alYQ=
@@ -320,6 +321,7 @@ golang.org/x/crypto v0.0.0-20190820162420-60c769a6c586/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -335,8 +337,9 @@ golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMx
 golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/image v0.0.0-20190910094157-69e4b8554b2a/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/image v0.0.0-20200927104501-e162460cd6b5/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
-golang.org/x/image v0.0.0-20220601225756-64ec528b34cd h1:9NbNcTg//wfC5JskFW4Z3sqwVnjmJKHxLAol1bW2qgw=
 golang.org/x/image v0.0.0-20220601225756-64ec528b34cd/go.mod h1:doUCurBvlfPMKfmIpRIywoHmhN3VyhnoFDbvIEWF4hY=
+golang.org/x/image v0.1.0 h1:r8Oj8ZA2Xy12/b5KZYj3tuv7NG/fBz3TwQVvpJ9l8Rk=
+golang.org/x/image v0.1.0/go.mod h1:iyPr49SD/G/TBxYVB/9RRtGUT5eNbo2u4NamWeQcD5c=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
 golang.org/x/lint v0.0.0-20190301231843-5614ed5bae6f/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
@@ -362,6 +365,7 @@ golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181023162649-9b4f9f5ad519/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -399,8 +403,9 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20210316092652-d523dce5a7f4/go.mod h1:RBQZq4jEuRlivfhVLdyRGr576XBO4/greRjx4P4O3yc=
 golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20210614182718-04defd469f4e/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.0.0-20210805182204-aaa1db679c0d h1:20cMwl2fHAzkJMEA+8J4JgqBQcQGzbisXo31MIeenXI=
 golang.org/x/net v0.0.0-20210805182204-aaa1db679c0d/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b h1:PxfKdU9lEEDYjdIzOtC4qFWgkU2rGHdKlKowJSMN9h0=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -424,6 +429,7 @@ golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180823144017-11551d06cbcc/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181026203630-95b1ffbd15a5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -471,9 +477,12 @@ golang.org/x/sys v0.0.0-20210510120138-977fb7262007/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210809222454-d867a43fc93e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220412211240-33da011f77ad h1:ntjMns5wyP/fN65tdBD4g8J5w8n015+iIIs9rtjXkY0=
 golang.org/x/sys v0.0.0-20220412211240-33da011f77ad/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f h1:v4INt8xihDGvnrfjMDVXGxw9wrfxYyCjk0KbXjhR55s=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -482,8 +491,9 @@ golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.4.0 h1:BrVqGRd7+k1DiOgtnFvAkoQEWQvBc25ouMJM6429SFg=
+golang.org/x/text v0.4.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -540,6 +550,7 @@ golang.org/x/tools v0.1.0/go.mod h1:xkSsbof2nBLbhDlRMhhhyNLN/zl3eTqcnHD5viDpcZ0=
 golang.org/x/tools v0.1.2/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.5/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.8-0.20211022200916-316ba0b74098/go.mod h1:LGqMHiF4EqQNHR1JncWGqT5BVaXmza+X+BDGol+dOxo=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -670,12 +681,12 @@ honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWh
 honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
 honnef.co/go/tools v0.0.1-2020.1.3/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
 honnef.co/go/tools v0.0.1-2020.1.4/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
-rescribe.xyz/integral v0.6.0 h1:CLF3sQ6th/OuG+/rp/lLR+AGOT4R7tG3IiUjSLKsriw=
-rescribe.xyz/integral v0.6.0/go.mod h1:gKJq4UaVn17RsMsUasEMcJDkTkwqeb6AzPIJtwcUipg=
-rescribe.xyz/pdf v0.1.3 h1:Fl4HHQPfkIUJs8WIkpjCm8yGu6Wd1TIDLZgXhVy8Pdk=
-rescribe.xyz/pdf v0.1.3/go.mod h1:fIia5YlYagNbBARPP2JXDoXXR5zd14Us5RkaKXUz7Nw=
-rescribe.xyz/preproc v0.4.2 h1:aX6rOf6ha3UNcHM0oHuY1MQi7ZwYj+46OxhTcptAI4E=
-rescribe.xyz/preproc v0.4.2/go.mod h1:LJe+rQ9cAxn/29cVK5l6X1hH1ZWRAI1Bs73yDGjvT4A=
+rescribe.xyz/integral v0.6.1 h1:0+4lajevAWO33sxnS33+URUbSalAh2Diti7ZWV/DbqU=
+rescribe.xyz/integral v0.6.1/go.mod h1:gKJq4UaVn17RsMsUasEMcJDkTkwqeb6AzPIJtwcUipg=
+rescribe.xyz/pdf v0.1.4 h1:VyKbgkjenSYaTq65RjYQyrem3KcBlOAmMIlErz2mxTQ=
+rescribe.xyz/pdf v0.1.4/go.mod h1:fIia5YlYagNbBARPP2JXDoXXR5zd14Us5RkaKXUz7Nw=
+rescribe.xyz/preproc v0.4.3 h1:DySrMD7uqJyd1dAw9eYbaTCHPMPFTE3cVcy05BmkLN4=
+rescribe.xyz/preproc v0.4.3/go.mod h1:wY+4/ZMEtMb2ifew57+0ClfMNH01ctiiiyGeh0zcfUY=
 rescribe.xyz/utils v0.1.3 h1:2rlHbUjAGXy/xgtmUb6Y7Kbpxl3qkwtWzkFUQ/cOaIA=
 rescribe.xyz/utils v0.1.3/go.mod h1:4L2vClYUFklsXggN0CUyP/alcgzLNRT0dMpMfEiVbX8=
 rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=