TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow to always use OCR extracted text

Browse Source 
Fixes: #1628
This commit is contained in:
eikek
2022-07-07 17:58:03 +02:00
parent d0d8a8fbe7
commit d413b16b03
2 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
modules/extract/src/main/scala/docspell/extract/PdfExtract.scala
View File

@ -48,15 +48,21 @@ object PdfExtract {
// maybe better: inspect the pdf and decide whether ocr or not
for {
pdfboxRes <-
logger.debug("Trying to strip text from pdf using pdfbox.") *>
PdfboxExtract.getTextAndMetaData[F](in)
if (stripMinLen > 0)
logger.debug("Trying to strip text from pdf using pdfbox.") *>
PdfboxExtract.getTextAndMetaData[F](in)
else
logger
.debug(s"Not stripping text from pdf, min-length=$stripMinLen")
.as(Right(Text("") -> None))
res <- pdfboxRes.fold(
ex =>
logger.info(
s"Stripping text from PDF resulted in an error: ${ex.getMessage}. Trying with OCR. "
) >> runOcr.map(txt => Result(txt, None)).attempt,
pair =>
if (pair._1.length >= stripMinLen) Result(pair).pure[F].attempt
if (pair._1.length >= stripMinLen && stripMinLen > 0)
Result(pair).pure[F].attempt
else
logger
.info(