Merged in feature/postprocessing (pull request #114)

Feature/postprocessing

* tests

* passtest

* fixshorttests

* mosttests

* improvingbasedockerfile

* testspeeds

* testing

* host

* canparallel

* clean

* passfullsuite

* singlepagemax

* test

* findfeatures

* findstables

* tbls

* tablestoo

* tablestoo

* lateraltests

* tableloc

* cleanup

* inlinetable

* childids

* cleanup

* tests
This commit is contained in:
Michael McGuinness
2025-04-22 14:40:16 +00:00
parent edc50c7510
commit fee71e7740
404 changed files with 211048 additions and 2820 deletions
+43
View File
@@ -0,0 +1,43 @@
package documenttext
import (
"context"
"fmt"
"io"
"strings"
documenttypes "queryorchestration/internal/document/types"
)
func (s *Service) getDocumentText(ctx context.Context, doc documenttypes.File) (io.Reader, error) {
pagesNum, err := doc.GetPageCount(ctx)
if err != nil {
return nil, err
}
textPages := make([]string, pagesNum)
for i := range pagesNum {
text, err := s.getPageText(ctx, doc, i)
if err != nil {
return nil, err
}
textPages[i] = text
}
text, err := s.mergeDocument(textPages)
if err != nil {
return nil, err
}
return text, nil
}
func (s *Service) mergeDocument(pages []string) (io.Reader, error) {
var builder strings.Builder
for i, page := range pages {
builder.WriteString(fmt.Sprintf("Start of Page No. = %d\n\n", i+1))
builder.WriteString(page)
builder.WriteString("\n\n")
}
return strings.NewReader(builder.String()), nil
}