Compare commits

..

3 Commits

Author SHA1 Message Date
Julien Neuhart
083e0e307a chore(deps): update Go dependencies 2025-02-12 16:24:16 +01:00
Julien Neuhart
80f3f89a89 fix(pdfcpu): correct sorting for the output paths of the split method 2025-02-12 11:47:45 +01:00
Julien Neuhart
3dc8c18849 fix(fs): get file by ext sorted by mod time 2025-02-11 17:00:18 +01:00
12 changed files with 92 additions and 139 deletions

2
.env
View File

@@ -7,7 +7,7 @@ GOTENBERG_USER_UID=1001
NOTO_COLOR_EMOJI_VERSION=v2.047 # See https://github.com/googlefonts/noto-emoji/releases.
PDFTK_VERSION=v3.3.3 # See https://gitlab.com/pdftk-java/pdftk/-/releases - Binary package.
PDFCPU_VERSION=v0.8.1 # See https://github.com/pdfcpu/pdfcpu/releases.
GOLANGCI_LINT_VERSION=v1.63.4 # See https://github.com/golangci/golangci-lint/releases.
GOLANGCI_LINT_VERSION=v1.64.2 # See https://github.com/golangci/golangci-lint/releases.
GOTENBERG_VERSION=snapshot
DOCKERFILE=build/Dockerfile
DOCKERFILE_CLOUDRUN=build/Dockerfile.cloudrun

View File

@@ -32,7 +32,7 @@ jobs:
- name: Run linters
uses: golangci/golangci-lint-action@v6
with:
version: v1.63.4
version: v1.64.2
tests:
needs:

View File

@@ -37,12 +37,12 @@ linters:
- promlinter
#- sloglint
- staticcheck
- tenv
- testableexamples
- tparallel
- typecheck
- unconvert
- unused
- usetesting
- wastedassign
- whitespace

8
go.mod
View File

@@ -6,7 +6,7 @@ require (
github.com/alexliesenfeld/health v0.8.0
github.com/andybalholm/brotli v1.1.1 // indirect
github.com/barasher/go-exiftool v1.10.0
github.com/chromedp/cdproto v0.0.0-20250203011601-a3c71a042730
github.com/chromedp/cdproto v0.0.0-20250210231439-aea867ea8506
github.com/chromedp/chromedp v0.12.1
github.com/google/uuid v1.6.0
github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
@@ -24,8 +24,8 @@ require (
github.com/ulikunitz/xz v0.5.12 // indirect
go.uber.org/multierr v1.11.0
go.uber.org/zap v1.27.0
golang.org/x/crypto v0.32.0 // indirect
golang.org/x/net v0.34.0
golang.org/x/crypto v0.33.0 // indirect
golang.org/x/net v0.35.0
golang.org/x/sync v0.11.0
golang.org/x/sys v0.30.0 // indirect
golang.org/x/term v0.29.0
@@ -33,7 +33,7 @@ require (
)
require (
github.com/dlclark/regexp2 v1.11.4
github.com/dlclark/regexp2 v1.11.5
github.com/mholt/archives v0.1.0
github.com/shirou/gopsutil/v4 v4.25.1
)

16
go.sum
View File

@@ -38,8 +38,8 @@ github.com/bodgit/windows v1.0.1/go.mod h1:a6JLwrB4KrTR5hBpp8FI9/9W9jJfeQ2h4XDXU
github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/chromedp/cdproto v0.0.0-20250203011601-a3c71a042730 h1:IEa+Va47x06CJQaLKFoce5iPTRRR5uI/GbeZbxdnYdc=
github.com/chromedp/cdproto v0.0.0-20250203011601-a3c71a042730/go.mod h1:RTGuBeCeabAJGi3OZf71a6cGa7oYBfBP75VJZFLv6SU=
github.com/chromedp/cdproto v0.0.0-20250210231439-aea867ea8506 h1:OfjMcN8R6eUWZfKyJaTnlyiZh1BGgmEKmRkCZuDtGRw=
github.com/chromedp/cdproto v0.0.0-20250210231439-aea867ea8506/go.mod h1:RTGuBeCeabAJGi3OZf71a6cGa7oYBfBP75VJZFLv6SU=
github.com/chromedp/chromedp v0.12.1 h1:kBMblXk7xH5/6j3K9uk8d7/c+fzXWiUsCsPte0VMwOA=
github.com/chromedp/chromedp v0.12.1/go.mod h1:F6+wdq9LKFDMoyxhq46ZLz4VLXrsrCAR3sFqJz4Nqc0=
github.com/chromedp/sysutil v1.1.0 h1:PUFNv5EcprjqXZD9nJb9b/c9ibAbxiYo4exNWZyipwM=
@@ -51,8 +51,8 @@ github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDk
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/dlclark/regexp2 v1.11.4 h1:rPYF9/LECdNymJufQKmri9gV604RvvABwgOA8un7yAo=
github.com/dlclark/regexp2 v1.11.4/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
github.com/dsnet/compress v0.0.2-0.20230904184137-39efe44ab707 h1:2tV76y6Q9BB+NEBasnqvs7e49aEBFI8ejC89PSnWH+4=
github.com/dsnet/compress v0.0.2-0.20230904184137-39efe44ab707/go.mod h1:qssHWj60/X5sZFNxpG4HBPDHVqxNm4DfnCKgrbZOT+s=
github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdfkVLjJ8T6VcRQv3SXugXy999NBtR9aFY=
@@ -232,8 +232,8 @@ golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8U
golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.32.0 h1:euUpcYgM8WcP71gNpTqQCn6rC2t6ULUPiOzfWaXVVfc=
golang.org/x/crypto v0.32.0/go.mod h1:ZnnJkOaASj8g0AjIduWNlq2NRxL0PlBrbKVyZ6V/Ugc=
golang.org/x/crypto v0.33.0 h1:IOBPskki6Lysi0lo9qQvbxiQ+FvsCC/YWOecCHAixus=
golang.org/x/crypto v0.33.0/go.mod h1:bVdXmD7IV/4GdElGPozy6U7lWdRXA4qyRVGJV57uQ5M=
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=
@@ -276,8 +276,8 @@ golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLL
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.34.0 h1:Mb7Mrk043xzHgnRM88suvJFwzVrRfHEHJEl5/71CKw0=
golang.org/x/net v0.34.0/go.mod h1:di0qlW3YNM5oh6GqDGQr92MyTozJPmybPK4Ev/Gm31k=
golang.org/x/net v0.35.0 h1:T5GQRQb2y08kTAByq9L4/bz8cipCdA8FbRTXewonqY8=
golang.org/x/net v0.35.0/go.mod h1:EglIi67kWsHKlRzzVMUD93VMSWGFOMSZgxFjparz1Qk=
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=

View File

@@ -3,8 +3,6 @@ package gotenberg
import (
"fmt"
"os"
"path/filepath"
"strings"
"github.com/google/uuid"
)
@@ -86,25 +84,6 @@ func (fs *FileSystem) MkdirAll() (string, error) {
return path, nil
}
// WalkDir walks through the root level of a directory and returns a list of
// files paths that match the specified file extension.
func WalkDir(dir, ext string) ([]string, error) {
var files []string
err := filepath.Walk(dir, func(path string, info os.FileInfo, pathErr error) error {
if pathErr != nil {
return pathErr
}
if info.IsDir() {
return nil
}
if strings.EqualFold(filepath.Ext(info.Name()), ext) {
files = append(files, path)
}
return nil
})
return files, err
}
// Interface guards.
var (
_ MkdirAll = (*OsMkdirAll)(nil)

View File

@@ -6,7 +6,6 @@ import (
"io"
"os"
"path/filepath"
"reflect"
"strings"
"testing"
@@ -145,78 +144,3 @@ func TestFileSystem_MkdirAll(t *testing.T) {
})
}
}
func TestWalkDir(t *testing.T) {
for _, tc := range []struct {
scenario string
dir string
ext string
expectError bool
expectFiles []string
}{
{
scenario: "directory does not exist",
dir: uuid.NewString(),
ext: ".pdf",
expectError: true,
},
{
scenario: "find PDF files",
dir: func() string {
path := fmt.Sprintf("%s/a_directory", os.TempDir())
err := os.MkdirAll(path, 0o755)
if err != nil {
t.Fatalf(fmt.Sprintf("expected no error but got: %v", err))
}
err = os.WriteFile(fmt.Sprintf("%s/a_foo_file.pdf", path), []byte{1}, 0o755)
if err != nil {
t.Fatalf("expected no error but got: %v", err)
}
err = os.WriteFile(fmt.Sprintf("%s/a_bar_file.PDF", path), []byte{1}, 0o755)
if err != nil {
t.Fatalf("expected no error but got: %v", err)
}
err = os.WriteFile(fmt.Sprintf("%s/a_baz_file.txt", path), []byte{1}, 0o755)
if err != nil {
t.Fatalf("expected no error but got: %v", err)
}
return path
}(),
ext: ".pdf",
expectError: false,
expectFiles: []string{"/tmp/a_directory/a_bar_file.PDF", "/tmp/a_directory/a_foo_file.pdf"},
},
} {
t.Run(tc.scenario, func(t *testing.T) {
defer func() {
err := os.RemoveAll(tc.dir)
if err != nil {
t.Fatalf("expected no error while cleaning up but got: %v", err)
}
}()
files, err := WalkDir(tc.dir, tc.ext)
if !tc.expectError && err != nil {
t.Fatalf("expected no error but got: %v", err)
}
if tc.expectError && err == nil {
t.Fatal("expected error but got none")
}
if tc.expectError && err != nil {
return
}
if !reflect.DeepEqual(files, tc.expectFiles) {
t.Errorf("expected files %+v, but got %+v", tc.expectFiles, files)
}
})
}
}

View File

@@ -7,7 +7,8 @@ import (
)
// AlphanumericSort implements sort.Interface and helps to sort strings
// alphanumerically.
// alphanumerically by either a numeric prefix or, if missing, a numeric
// suffix.
//
// See: https://github.com/gotenberg/gotenberg/issues/805.
type AlphanumericSort []string
@@ -21,20 +22,20 @@ func (s AlphanumericSort) Swap(i, j int) {
}
func (s AlphanumericSort) Less(i, j int) bool {
numI, restI := extractPrefix(s[i])
numJ, restJ := extractPrefix(s[j])
numI, restI := extractNumber(s[i])
numJ, restJ := extractNumber(s[j])
// Compares numerical prefixes if they exist.
// If both strings contain a number, compare them numerically.
if numI != -1 && numJ != -1 {
if numI != numJ {
return numI < numJ
}
// If numbers are equal, falls back to string comparison of the rest.
// If the numbers are equal, compare the "rest" strings.
return restI < restJ
}
// If one has a numerical prefix and the other doesn't, the one with the
// number comes first.
// If one contains a number and the other doesn't, the one with the number
// comes first.
if numI != -1 {
return true
}
@@ -42,28 +43,52 @@ func (s AlphanumericSort) Less(i, j int) bool {
return false
}
// If neither has a numerical prefix, compare as strings
// Neither has a number; fall back to lexicographical order.
return s[i] < s[j]
}
// extractPrefix attempts to extract a numerical prefix and the rest of the filename
func extractPrefix(filename string) (int, string) {
matches := numPrefixRegexp.FindStringSubmatch(filename)
if len(matches) > 2 {
prefix, err := strconv.Atoi(matches[1])
if err == nil {
return prefix, matches[2]
// extractNumber attempts to extract a numeric portion from the filename.
// It first checks for a numeric prefix (digits at the beginning).
// If none is found, it next attempts to match a number immediately before the
// extension (for filenames such as "sample1_1.pdf").
// If that fails, it then attempts a trailing numeric pattern.
// If no number is found, it returns -1 and the original string.
func extractNumber(str string) (int, string) {
// Check for a numeric prefix.
if matches := prefixRegexp.FindStringSubmatch(str); len(matches) > 2 {
if num, err := strconv.Atoi(matches[1]); err == nil {
return num, matches[2]
}
}
// Returns -1 if no numerical prefix is found, indicating to just compare
// as strings.
return -1, filename
// Check for a number immediately before an extension.
if matches := extensionSuffixRegexp.FindStringSubmatch(str); len(matches) > 3 {
if num, err := strconv.Atoi(matches[2]); err == nil {
// Remove the numeric block but keep the extension.
return num, matches[1] + matches[3]
}
}
// Check for a trailing number (with no extension following).
if matches := suffixRegexp.FindStringSubmatch(str); len(matches) > 2 {
if num, err := strconv.Atoi(matches[2]); err == nil {
return num, matches[1]
}
}
// No numeric portion found.
return -1, str
}
var numPrefixRegexp = regexp.MustCompile(`^(\d+)(.*)$`)
// Regular expressions used by extractNumber.
var (
// Matches a numeric prefix: one or more digits at the start.
prefixRegexp = regexp.MustCompile(`^(\d+)(.*)$`)
// Matches a numeric block immediately before a file extension.
extensionSuffixRegexp = regexp.MustCompile(`^(.*?)(\d+)(\.[^.]+)$`)
// Matches a trailing numeric sequence when there is no extension.
suffixRegexp = regexp.MustCompile(`^(.*?)(\d+)$`)
)
// Interface guard.
var (
_ sort.Interface = (*AlphanumericSort)(nil)
)
var _ sort.Interface = (*AlphanumericSort)(nil)

View File

@@ -17,6 +17,16 @@ func TestAlphanumericSort(t *testing.T) {
values: []string{"10qux.pdf", "2_baz.txt", "2_aza.txt", "1bar.pdf", "Afoo.txt", "Bbar.docx", "25zeta.txt", "3.pdf", "4_foo.pdf"},
expectedSort: []string{"1bar.pdf", "2_aza.txt", "2_baz.txt", "3.pdf", "4_foo.pdf", "10qux.pdf", "25zeta.txt", "Afoo.txt", "Bbar.docx"},
},
{
scenario: "numeric suffixes with extensions",
values: []string{"sample1_10.pdf", "sample1_11.pdf", "sample1_4.pdf", "sample1_3.pdf", "sample1_1.pdf", "sample1_2.pdf"},
expectedSort: []string{"sample1_1.pdf", "sample1_2.pdf", "sample1_3.pdf", "sample1_4.pdf", "sample1_10.pdf", "sample1_11.pdf"},
},
{
scenario: "numeric suffixes",
values: []string{"sample1_10", "sample1_11", "sample1_4", "sample1_3", "sample1_1", "sample1_2"},
expectedSort: []string{"sample1_1", "sample1_2", "sample1_3", "sample1_4", "sample1_10", "sample1_11"},
},
{
scenario: "hrtime (PHP library)",
values: []string{"245654773395259", "245654773395039", "245654773395149", "245654773394919", "245654773394369"},

View File

@@ -7,6 +7,7 @@ import (
"os"
"os/exec"
"path/filepath"
"sort"
"strings"
"syscall"
@@ -128,11 +129,25 @@ func (engine *PdfCpu) Split(ctx context.Context, logger *zap.Logger, mode gotenb
return nil, fmt.Errorf("split PDFs with pdfcpu: %w", err)
}
outputPaths, err := gotenberg.WalkDir(outputDirPath, ".pdf")
var outputPaths []string
err = filepath.Walk(outputDirPath, func(path string, info os.FileInfo, pathErr error) error {
if pathErr != nil {
return pathErr
}
if info.IsDir() {
return nil
}
if strings.EqualFold(filepath.Ext(info.Name()), ".pdf") {
outputPaths = append(outputPaths, path)
}
return nil
})
if err != nil {
return nil, fmt.Errorf("walk directory to find resulting PDFs from split with pdfcpu: %w", err)
}
sort.Sort(gotenberg.AlphanumericSort(outputPaths))
return outputPaths, nil
}

View File

@@ -230,15 +230,15 @@ func TestPdfCpu_Split(t *testing.T) {
scenario: "success (intervals)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals, Span: "1"},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
inputPath: "/tests/test/testdata/pdfengines/sample4.pdf",
expectError: false,
expectOutputPathsCount: 3,
expectOutputPathsCount: 20,
},
{
scenario: "success (pages)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1"},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
inputPath: "/tests/test/testdata/pdfengines/sample4.pdf",
expectError: false,
expectOutputPathsCount: 1,
},
@@ -246,7 +246,7 @@ func TestPdfCpu_Split(t *testing.T) {
scenario: "success (pages & unify)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
inputPath: "/tests/test/testdata/pdfengines/sample4.pdf",
expectError: false,
expectOutputPathsCount: 1,
},

BIN
test/testdata/pdfengines/sample4.pdf vendored Normal file

Binary file not shown.