feat(chromium): add generateTaggedPdf to form fields - closes #1210

This commit is contained in:
Julien Neuhart
2025-05-20 11:49:10 +02:00
parent 67ebe17fcb
commit ce155fb43e
6 changed files with 17 additions and 5 deletions

View File

@@ -220,6 +220,10 @@ type PdfOptions struct {
// GenerateDocumentOutline defines whether the document outline should be
// embedded into the PDF.
GenerateDocumentOutline bool
// GenerateTaggedPdf defines whether to generate tagged (accessible)
// PDF.
GenerateTaggedPdf bool
}
// DefaultPdfOptions returns the default values for PdfOptions.
@@ -241,6 +245,7 @@ func DefaultPdfOptions() PdfOptions {
FooterTemplate: "<html><head></head><body></body></html>",
PreferCssPageSize: false,
GenerateDocumentOutline: false,
GenerateTaggedPdf: false,
}
}

View File

@@ -207,6 +207,7 @@ func FormDataChromiumPdfOptions(ctx *api.Context) (*api.FormData, PdfOptions) {
headerTemplate, footerTemplate string
preferCssPageSize bool
generateDocumentOutline bool
generateTaggedPdf bool
)
form.
@@ -224,7 +225,8 @@ func FormDataChromiumPdfOptions(ctx *api.Context) (*api.FormData, PdfOptions) {
Content("header.html", &headerTemplate, defaultPdfOptions.HeaderTemplate).
Content("footer.html", &footerTemplate, defaultPdfOptions.FooterTemplate).
Bool("preferCssPageSize", &preferCssPageSize, defaultPdfOptions.PreferCssPageSize).
Bool("generateDocumentOutline", &generateDocumentOutline, defaultPdfOptions.GenerateDocumentOutline)
Bool("generateDocumentOutline", &generateDocumentOutline, defaultPdfOptions.GenerateDocumentOutline).
Bool("generateTaggedPdf", &generateTaggedPdf, defaultPdfOptions.GenerateTaggedPdf)
pdfOptions := PdfOptions{
Options: options,
@@ -243,6 +245,7 @@ func FormDataChromiumPdfOptions(ctx *api.Context) (*api.FormData, PdfOptions) {
FooterTemplate: footerTemplate,
PreferCssPageSize: preferCssPageSize,
GenerateDocumentOutline: generateDocumentOutline,
GenerateTaggedPdf: generateTaggedPdf,
}
return form, pdfOptions

View File

@@ -49,7 +49,8 @@ func printToPdfActionFunc(logger *zap.Logger, outputPath string, options PdfOpti
WithPageRanges(pageRanges).
WithPreferCSSPageSize(options.PreferCssPageSize).
WithGenerateDocumentOutline(options.GenerateDocumentOutline).
WithGenerateTaggedPDF(false)
// See https://github.com/gotenberg/gotenberg/issues/1210.
WithGenerateTaggedPDF(options.GenerateTaggedPdf)
hasCustomHeaderFooter := options.HeaderTemplate != DefaultPdfOptions().HeaderTemplate ||
options.FooterTemplate != DefaultPdfOptions().FooterTemplate

View File

@@ -393,6 +393,7 @@ Feature: /forms/chromium/convert/html
| marginRight | foo | field |
| preferCssPageSize | foo | field |
| generateDocumentOutline | foo | field |
| generateTaggedPdf | foo | field |
| printBackground | foo | field |
| omitBackground | foo | field |
| landscape | foo | field |
@@ -408,7 +409,7 @@ Feature: /forms/chromium/convert/html
Then the response header "Content-Type" should be "text/plain; charset=UTF-8"
Then the response body should match string:
"""
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form file 'index.html' is required
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateTaggedPdf' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form file 'index.html' is required
"""
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 |

View File

@@ -469,6 +469,7 @@ Feature: /forms/chromium/convert/markdown
| marginRight | foo | field |
| preferCssPageSize | foo | field |
| generateDocumentOutline | foo | field |
| generateTaggedPdf | foo | field |
| printBackground | foo | field |
| omitBackground | foo | field |
| landscape | foo | field |
@@ -484,7 +485,7 @@ Feature: /forms/chromium/convert/markdown
Then the response header "Content-Type" should be "text/plain; charset=UTF-8"
Then the response body should match string:
"""
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form file 'index.html' is required; no form file found for extensions: [.md]
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateTaggedPdf' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form file 'index.html' is required; no form file found for extensions: [.md]
"""
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 |

View File

@@ -451,6 +451,7 @@ Feature: /forms/chromium/convert/url
| marginRight | foo | field |
| preferCssPageSize | foo | field |
| generateDocumentOutline | foo | field |
| generateTaggedPdf | foo | field |
| printBackground | foo | field |
| omitBackground | foo | field |
| landscape | foo | field |
@@ -466,7 +467,7 @@ Feature: /forms/chromium/convert/url
Then the response header "Content-Type" should be "text/plain; charset=UTF-8"
Then the response body should match string:
"""
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'url' is required
Invalid form data: form field 'skipNetworkIdleEvent' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceHttpStatusCodes' is invalid (got 'foo', resulting to unmarshal failOnResourceHttpStatusCodes: invalid character 'o' in literal false (expecting 'a')); form field 'failOnResourceLoadingFailed' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'failOnConsoleExceptions' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'waitDelay' is invalid (got 'foo', resulting to time: invalid duration "foo"); form field 'emulatedMediaType' is invalid (got 'foo', resulting to wrong value, expected either 'screen', 'print' or empty); form field 'omitBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'landscape' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'printBackground' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'scale' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'singlePage' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'paperWidth' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'paperHeight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginTop' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginBottom' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginLeft' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'marginRight' is invalid (got 'foo', resulting to strconv.ParseFloat: parsing "foo": invalid syntax); form field 'preferCssPageSize' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateDocumentOutline' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'generateTaggedPdf' is invalid (got 'foo', resulting to strconv.ParseBool: parsing "foo": invalid syntax); form field 'url' is required
"""
Given 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):