feat: XLSX - CSV (#48)

* build(gomod): add tealeg/xlsx as dep

* feat(documents): add a csv struct that converts csv to xlsx files

* test(document): add test function to test csv-xlsx

* feat(xlsx): add a xlsx struct able to convert xlsx files to csv ones

* test(documents): add a test function to make sure xlsx - csv works as expected

* feat(documents): add changes to integrate the new kind of documents

* refactor(csv): remove the outdir

* feat(main): add the text kind of document to the main file

* docs(readme): add the csv and xlsx kind of documents to the conversion matrix

* build(gomod): resolve conflicts on go module

README.md

@@ -95,10 +95,12 @@ A modal will pop up with a preview of the converted image.
 
 ## Documents X Documents
 
-|      | DOCX | PDF |
-| ---- | ---- | --- |
-| PDF  | ✅   |     |
-| DOCX |      | ✅  |
+|      | DOCX | PDF | XLSX | CSV |
+| ---- | ---- | --- | ---- | --- |
+| PDF  | ✅   |     |      |     |
+| DOCX |      | ✅  |      |     |
+| CSV  |      |     |  ✅  |     |
+| XLSX |      |     |      | ✅  |
 
 ## License
 The MIT License (MIT). See [LICENSE](LICENSE) file for more details.

go.mod

@@ -9,17 +9,25 @@ require (
 	github.com/go-chi/chi/v5 v5.0.10
 	github.com/signintech/gopdf v0.20.0
 	github.com/stretchr/testify v1.8.4
+	github.com/tealeg/xlsx/v3 v3.3.6
 	golang.org/x/image v0.14.0
 	golang.org/x/text v0.14.0
 )
 
 require (
 	github.com/davecgh/go-spew v1.1.1 // indirect
-	github.com/kr/pretty v0.1.0 // indirect
+	github.com/frankban/quicktest v1.14.6 // indirect
+	github.com/google/btree v1.0.0 // indirect
+	github.com/google/go-cmp v0.5.9 // indirect
+	github.com/kr/pretty v0.3.1 // indirect
+	github.com/kr/text v0.2.0 // indirect
+	github.com/peterbourgon/diskv/v3 v3.0.1 // indirect
 	github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/rogpeppe/fastuuid v1.2.0 // indirect
+	github.com/rogpeppe/go-internal v1.9.0 // indirect
+	github.com/shabbyrobe/xmlwriter v0.0.0-20200208144257-9fca06d00ffa // indirect
 	golang.org/x/net v0.18.0 // indirect
-	gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -1,37 +1,60 @@
 github.com/chai2010/webp v1.1.1 h1:jTRmEccAJ4MGrhFOrPMpNGIJ/eybIgwKpcACsrTEapk=
 github.com/chai2010/webp v1.1.1/go.mod h1:0XVwvZWdjjdxpUEIf7b9g9VkHFnInUSYujwqTLEuldU=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 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/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=
+github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
 github.com/gen2brain/go-fitz v1.23.7 h1:HPhzEVzmOINvCKqQgB/DwMzYh4ArIgy3tMwq1eJTcbg=
 github.com/gen2brain/go-fitz v1.23.7/go.mod h1:HU04vc+RisUh/kvEd2pB0LAxmK1oyXdN4ftyshUr9rQ=
 github.com/go-chi/chi/v5 v5.0.10 h1:rLz5avzKpjqxrYwXNfmjkrYYXOyLJd37pz53UFHC6vk=
 github.com/go-chi/chi/v5 v5.0.10/go.mod h1:DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
-github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
-github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
-github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
+github.com/google/btree v1.0.0 h1:0udJVsspx3VBr5FwtLhQQtuAsVc79tTq0ocGIPAU6qo=
+github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
+github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
+github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e h1:fD57ERR4JtEqsWbfPhv4DMiApHyliiK5xCTNVSPiaAs=
+github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
+github.com/peterbourgon/diskv/v3 v3.0.1 h1:x06SQA46+PKIUftmEujdwSEpIx8kR+M9eLYsUxeYveU=
+github.com/peterbourgon/diskv/v3 v3.0.1/go.mod h1:kJ5Ny7vLdARGU3WUuy6uzO6T0nb/2gWcT1JiBvRmb5o=
 github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311 h1:zyWXQ6vu27ETMpYsEMAsisQ+GqJ4e1TPvSNfdOPF0no=
 github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311/go.mod h1:vBmVV0Do6hSBHC8uKUQ71JGW+ZGQq74llk/7bXwjDoI=
+github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pkg/profile v1.5.0 h1:042Buzk+NhDI+DeSAA62RwJL8VAuZUMQZUjCsRz1Mug=
+github.com/pkg/profile v1.5.0/go.mod h1:qBsxPvzyUincmltOk6iyRVxHYg4adc0OFOv72ZdLa18=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/rogpeppe/fastuuid v1.2.0 h1:Ppwyp6VYCF1nvBTXL3trRso7mXMlRrw9ooo375wvi2s=
+github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
+github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
+github.com/shabbyrobe/xmlwriter v0.0.0-20200208144257-9fca06d00ffa h1:2cO3RojjYl3hVTbEvJVqrMaFmORhL6O06qdW42toftk=
+github.com/shabbyrobe/xmlwriter v0.0.0-20200208144257-9fca06d00ffa/go.mod h1:Yjr3bdWaVWyME1kha7X0jsz3k2DgXNa1Pj3XGyUAbx8=
 github.com/signintech/gopdf v0.20.0 h1:a1rArIMmQCAFzjjCqXPgxynTPkytMccPuGZlUU8Jorw=
 github.com/signintech/gopdf v0.20.0/go.mod h1:wrLtZoWaRNrS4hphED0oflFoa6IWkOu6M3nJjm4VbO4=
 github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/tealeg/xlsx/v3 v3.3.6 h1:b0SPORnNa8BDbFEujljp2IpTDVse3D+Ad5IaMz7KUL8=
+github.com/tealeg/xlsx/v3 v3.3.6/go.mod h1:KV4FTFtvGy0TBlOivJLZu/YNZk6e0Qtk7eOSglWksuA=
 golang.org/x/image v0.14.0 h1:tNgSxAFe3jC4uYqvZdTr84SZoM1KfwdC9SKIFrLjFn4=
 golang.org/x/image v0.14.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.18.0 h1:mIYleuAkSbHh0tCv7RvjL3F6ZVbLjq4+R7zbOn3Kokg=
 golang.org/x/net v0.18.0/go.mod h1:/czyP5RqHAH4odGYxBJ1qz0+CE5WZ+2j1YgoEo8F2jQ=
+golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY=
-gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b h1:QRR6H1YWRnHb4Y/HeNFCTJLFVxaq6wH4YuVdsUOr75U=
+gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -183,7 +183,8 @@ func handleUploadFile(w http.ResponseWriter, r *http.Request) error {
 		return WithHTTPStatus(err, http.StatusInternalServerError)
 	}
 
-	if fileType == "application" {
+	switch fileType {
+	case "application", "text":
 		targetFileSubType = "zip"
 	}
 

pkg/files/document_factory.go

@@ -24,6 +24,10 @@ func (d *DocumentFactory) NewFile(f string) (File, error) {
 		return documents.NewPdf(d.filename), nil
 	case documents.DOCX, documents.DOCXMIMEType:
 		return documents.NewDocx(d.filename), nil
+	case documents.XLSX, documents.XLSXMIMEType:
+		return documents.NewXlsx(d.filename), nil
+	case documents.CSV:
+		return documents.NewCsv(d.filename), nil
 	default:
 		return nil, fmt.Errorf("type file file  %s not recognized", f)
 	}

pkg/files/documents/csv.go

@@ -0,0 +1,160 @@
+package documents
+
+import (
+	"archive/zip"
+	"bytes"
+	"encoding/csv"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"slices"
+	"strings"
+
+	"github.com/tealeg/xlsx/v3"
+)
+
+// Csv struct implements the File and Document interface from the file package.
+type Csv struct {
+	filename            string
+	compatibleFormats   map[string][]string
+	compatibleMIMETypes map[string][]string
+}
+
+// NewCsv returns a pointer to Csv.
+func NewCsv(filename string) *Csv {
+	c := Csv{
+		filename: filename,
+		compatibleFormats: map[string][]string{
+			"Document": {
+				XLSX,
+			},
+		},
+		compatibleMIMETypes: map[string][]string{
+			"Document": {
+				XLSX,
+			},
+		},
+	}
+
+	return &c
+}
+
+// SupportedFormats returns a map witht the compatible formats that CSv is
+// compatible to be converted to.
+func (c *Csv) SupportedFormats() map[string][]string {
+	return c.compatibleFormats
+}
+
+// SupportedMIMETypes returns a map witht the compatible MIME types that Docx is
+// compatible to be converted to.
+func (c *Csv) SupportedMIMETypes() map[string][]string {
+	return c.compatibleMIMETypes
+}
+
+func (c *Csv) ConvertTo(fileType, subType string, file io.Reader) (io.Reader, error) {
+	compatibleFormats, ok := c.SupportedFormats()[fileType]
+	if !ok {
+		return nil, fmt.Errorf("file type not supported: %s", fileType)
+	}
+
+	if !slices.Contains(compatibleFormats, subType) {
+		return nil, fmt.Errorf("sub-type not supported: %s", subType)
+	}
+
+	switch strings.ToLower(fileType) {
+	case documentType:
+		switch subType {
+		case XLSX:
+			xlsxFilename := fmt.Sprintf(
+				"%s.xlsx",
+				strings.TrimSuffix(c.filename, filepath.Ext(c.filename)),
+			)
+
+			xlsxPath := filepath.Join("/tmp", xlsxFilename)
+
+			// Parses the file name of the Zip file.
+			zipFileName := filepath.Join("/tmp", fmt.Sprintf(
+				"%s.zip",
+				strings.TrimSuffix(c.filename, filepath.Ext(c.filename)),
+			))
+
+			reader := csv.NewReader(file)
+			xlsxFile := xlsx.NewFile()
+			sheet, err := xlsxFile.AddSheet(strings.TrimSuffix(c.filename, filepath.Ext(c.filename)))
+			if err != nil {
+				return nil, fmt.Errorf("error creating a xlsx sheet %w", err)
+			}
+
+			for {
+				fields, err := reader.Read()
+				if err == io.EOF {
+					break
+				}
+
+				row := sheet.AddRow()
+				for _, field := range fields {
+					cell := row.AddCell()
+					cell.Value = field
+				}
+			}
+
+			xlsxFile.Save(xlsxPath)
+
+			tmpCsvFile, err := os.Open(xlsxPath)
+			if err != nil {
+				return nil, fmt.Errorf(
+					"error at opening the pdf file: %w",
+					err,
+				)
+			}
+			defer tmpCsvFile.Close()
+
+			// Creates the zip file that will be returned.
+			archive, err := os.Create(zipFileName)
+			if err != nil {
+				return nil, fmt.Errorf(
+					"error at creating the zip file to store the pdf file: %w",
+					err,
+				)
+			}
+
+			// Creates a Zip Writer to add files later on.
+			zipWriter := zip.NewWriter(archive)
+
+			w1, err := zipWriter.Create(xlsxFilename)
+			if err != nil {
+				return nil, fmt.Errorf(
+					"eror at creating a zip file: %w",
+					err,
+				)
+			}
+
+			if _, err := io.Copy(w1, tmpCsvFile); err != nil {
+				return nil, fmt.Errorf(
+					"error at writing the pdf file content to the zip writer: %w",
+					err,
+				)
+			}
+
+			// Closes both zip writer and the zip file after its done with the writing.
+			zipWriter.Close()
+			archive.Close()
+
+			// Reads the zip file as an slice of bytes.
+			zipFile, err := os.ReadFile(zipFileName)
+			if err != nil {
+				return nil, fmt.Errorf("error reading zip file: %v", err)
+			}
+
+			return bytes.NewReader(zipFile), nil
+		}
+	}
+
+	return nil, errors.New("not implemented")
+}
+
+func (c *Csv) DocumentType() string {
+	return CSV
+}

pkg/files/documents/documents.go

@@ -4,10 +4,14 @@ const (
 	DOCX         = "docx"
 	DOCXMIMEType = "vnd.openxmlformats-officedocument.wordprocessingml.document"
 	PDF          = "pdf"
+	CSV          = "csv"
+	XLSX         = "xlsx"
+	XLSXMIMEType = "vnd.openxmlformats-officedocument.spreadsheetml.sheet"
 
 	imageMimeType = "image/"
 	imageType     = "image"
 
 	documentMimeType = "application/"
+	tesxtMimeType    = "text/"
 	documentType     = "document"
 )