feat(pdfengines): add embed feature

This commit is contained in:
Hubert Lenoir
2025-11-05 13:57:23 +01:00
committed by GitHub
parent f4d3fba306
commit a0ee800002
26 changed files with 479 additions and 17 deletions

View File

@@ -942,3 +942,19 @@ Feature: /forms/chromium/convert/html
| files | testdata/page-1-html/index.html | file |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/pdf"
@embed
Scenario: POST /forms/chromium/convert/html (Embeds)
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/chromium/convert/html" endpoint with the following form data and header(s):
| files | testdata/page-1-html/index.html | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| Gotenberg-Output-Filename | foo | header |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the response:
| foo.pdf |
And the "foo.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "foo.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -1075,3 +1075,20 @@ Feature: /forms/chromium/convert/markdown
| files | testdata/page-1-markdown/page_1.md | file |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/pdf"
@embed
Scenario: POST /forms/chromium/convert/markdown (Embeds)
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/chromium/convert/markdown" endpoint with the following form data and header(s):
| files | testdata/page-1-markdown/index.html | file |
| files | testdata/page-1-markdown/page_1.md | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| Gotenberg-Output-Filename | foo | header |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the response:
| foo.pdf |
And the "foo.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "foo.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -1039,3 +1039,20 @@ Feature: /forms/chromium/convert/url
| url | http://host.docker.internal:%d/html/testdata/page-1-html/index.html | field |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/pdf"
@embed
Scenario: POST /foo/forms/chromium/convert/url (Embeds)
Given I have a default Gotenberg container
And I have a static server
When I make a "POST" request to Gotenberg at the "/forms/chromium/convert/url" endpoint with the following form data and header(s):
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| url | http://host.docker.internal:%d/html/testdata/page-1-html/index.html | field |
| Gotenberg-Output-Filename | foo | header |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the webhook request:
| foo.pdf |
And the "foo.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "foo.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -652,3 +652,19 @@ Feature: /forms/libreoffice/convert
| files | testdata/page_1.docx | file |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/pdf"
@embed
Scenario: POST /forms/libreoffice/convert (Embeds)
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/libreoffice/convert" endpoint with the following form data and header(s):
| files | testdata/page_1.docx | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| Gotenberg-Output-Filename | foo | header |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the response:
| foo.pdf |
And the "foo.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "foo.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -0,0 +1,32 @@
@embed
Feature: /forms/pdfengines/embed
Scenario: POST /forms/pdfengines/embed
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/pdfengines/embed" endpoint with the following form data and header(s):
| files | testdata/page_1.pdf | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| embeds | testdata/page_2.pdf | file |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the response:
| page_1.pdf |
And the "page_1.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "page_1.pdf" PDF should have the "embed_2.xml" file embedded in it
And the "page_1.pdf" PDF should have the "page_2.pdf" file embedded in it
Scenario: POST /forms/pdfengines/embed with (Download From)
Given I have a default Gotenberg container
And I have a static server
When I make a "POST" request to Gotenberg at the "/forms/pdfengines/embed" endpoint with the following form data and header(s):
| files | testdata/page_1.pdf | file |
| downloadFrom | [{"url":"http://host.docker.internal:%d/static/testdata/embed_1.xml", "embedded": true},{"url":"http://host.docker.internal:%d/static/testdata/embed_2.xml", "embedded": false}] | field |
Then the response status code should be 200
And the response header "Content-Type" should be "application/pdf"
And there should be 1 PDF(s) in the response
And there should be the following file(s) in the response:
| page_1.pdf |
And the "page_1.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "page_1.pdf" PDF should NOT have the "embed_2.xml" file embedded in it

View File

@@ -368,3 +368,16 @@ Feature: /forms/pdfengines/merge
| files | testdata/page_2.pdf | file |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/pdf"
@embed
Scenario: POST /foo/forms/pdfengines/merge (Embeds)
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/pdfengines/merge" endpoint with the following form data and header(s):
| files | testdata/page_1.pdf | file |
| files | testdata/page_2.pdf | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| Gotenberg-Output-Filename | foo | header |
Then the response status code should be 200
And the "foo.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "foo.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -650,3 +650,23 @@ Feature: /forms/pdfengines/split
| splitSpan | 2 | field |
Then the response status code should be 200
Then the response header "Content-Type" should be "application/zip"
@embed
Scenario: POST /foo/forms/pdfengines/split (Embeds)
Given I have a default Gotenberg container
When I make a "POST" request to Gotenberg at the "/forms/pdfengines/split" endpoint with the following form data and header(s):
| files | testdata/pages_3.pdf | file |
| embeds | testdata/embed_1.xml | file |
| embeds | testdata/embed_2.xml | file |
| splitMode | intervals | field |
| splitSpan | 2 | field |
Then the response status code should be 200
And the response header "Content-Type" should be "application/zip"
And there should be 2 PDF(s) in the response
And there should be the following file(s) in the response:
| pages_3_0.pdf |
| pages_3_1.pdf |
And the "pages_3_0.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "pages_3_0.pdf" PDF should have the "embed_2.xml" file embedded in it
And the "pages_3_1.pdf" PDF should have the "embed_1.xml" file embedded in it
And the "pages_3_1.pdf" PDF should have the "embed_2.xml" file embedded in it

View File

@@ -735,6 +735,41 @@ func (s *scenario) thePdfShouldBeSetToLandscapeOrientation(ctx context.Context,
return nil
}
func (s *scenario) thePdfShouldHaveTheFollowingEmbedsInIt(ctx context.Context, name, should string, embed string) error {
path, err := s.getPath(name)
if err != nil {
return fmt.Errorf("get path %q: %w", name, err)
}
invert := should == "should NOT"
cmd := []string{
"verapdf",
"--off",
"--loglevel",
"0",
"--extract",
"embeddedFile",
name,
}
output, err := execCommandInIntegrationToolsContainer(ctx, cmd, path)
if err != nil {
return fmt.Errorf("exec %q: %w", cmd, err)
}
found := strings.Contains(output, fmt.Sprintf("<fileName>%s</fileName>", embed))
if invert && found {
return fmt.Errorf("embed %q found", embed)
}
if !invert && !found {
return fmt.Errorf("embed %q not found", embed)
}
return nil
}
func (s *scenario) thePdfShouldHaveTheFollowingContentAtPage(ctx context.Context, name, kind string, page int, expected *godog.DocString) error {
var path string
if !strings.HasPrefix(name, "*_") {
@@ -927,6 +962,7 @@ func InitializeScenario(ctx *godog.ScenarioContext) {
ctx.Then(`^the "([^"]*)" PDF should have (\d+) page\(s\)$`, s.thePdfShouldHavePages)
ctx.Then(`^the "([^"]*)" PDF (should|should NOT) be set to landscape orientation$`, s.thePdfShouldBeSetToLandscapeOrientation)
ctx.Then(`^the "([^"]*)" PDF (should|should NOT) have the following content at page (\d+):$`, s.thePdfShouldHaveTheFollowingContentAtPage)
ctx.Then(`^the "([^"]*)" PDF (should|should NOT) have the "([^"]*)" file embedded in it$`, s.thePdfShouldHaveTheFollowingEmbedsInIt)
ctx.After(func(ctx context.Context, sc *godog.Scenario, err error) (context.Context, error) {
if s.gotenbergContainer != nil {
errTerminate := s.gotenbergContainer.Terminate(ctx, testcontainers.StopTimeout(0))
@@ -950,3 +986,14 @@ func InitializeScenario(ctx *godog.ScenarioContext) {
return ctx, nil
})
}
func (s *scenario) getPath(name string) (string, error) {
path := fmt.Sprintf("%s/%s/%s", s.workdir, s.resp.Header().Get("Gotenberg-Trace"), name)
_, err := os.Stat(path)
if os.IsNotExist(err) {
return "", fmt.Errorf("PDF %q does not exist", path)
}
return path, nil
}

5
test/integration/testdata/embed_1.xml vendored Normal file
View File

@@ -0,0 +1,5 @@
<xml>
<test>test 1.1</test>
<test>test 1.2</test>
<test>test 1.3</test>
</xml>

5
test/integration/testdata/embed_2.xml vendored Normal file
View File

@@ -0,0 +1,5 @@
<xml>
<test>test 2.1</test>
<test>test 2.2</test>
<test>test 2.3</test>
</xml>