TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-21 09:58:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use ocrmypdf tool to create pdf/a during conversion

Browse Source 
- Use another external tool to convert pdf to pdf which also adds the
  extracted text as another layer into the pdf

- Although not used, the external conversion routine will now check
  for an existing text file that is named as the pdf file with extension
  `.txt`. If present it is included in the conversion result and will be
  used as the extracted text.

- text extraction for pdf files happens now on the converted file,
  because it may already contain the text from the conversion step and
  thus avoids running OCR twice.

- All errors during conversion are not fatal; processing continues
  without a converted file.
This commit is contained in:
Eike Kettner
2020-07-18 12:48:41 +02:00
parent 99210365ce
commit 3d49ceaab5
16 changed files with 316 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
nix/module-joex.nix
View File

@ -131,6 +131,23 @@ let
};
working-dir = "/tmp/docspell-convert";
};
ocrmypdf = {
enabled = true;
command = {
program = "${pkgs.ocrmypdf}/bin/ocrmypdf";
args = [
"-l" "{{lang}}"
"--skip-text"
"--deskew"
"-j" "1"
"{{infile}}"
"{{outfile}}"
];
timeout = "5 minutes";
};
working-dir = "/tmp/docspell-convert";
};
};
files = {
chunk-size = 524288;
@ -860,6 +877,66 @@ in {
process.
'';
};
ocrmypdf = mkOption {
type = types.submodule({
options = {
enabled = mkOption {
type = types.bool;
default = defaults.convert.ocrmypdf.enabled;
description = "Whether to use ocrmypdf to convert pdf to pdf/a.";
};
working-dir = mkOption {
type = types.str;
default = defaults.convert.ocrmypdf.working-dir;
description = "Directory where the conversion processes can put their temp files";
};
command = mkOption {
type = types.submodule({
options = {
program = mkOption {
type = types.str;
default = defaults.convert.ocrmypdf.command.program;
description = "The path to the executable.";
};
args = mkOption {
type = types.listOf types.str;
default = defaults.convert.ocrmypdf.command.args;
description = "The arguments to the program";
};
timeout = mkOption {
type = types.str;
default = defaults.convert.ocrmypdf.command.timeout;
description = "The timeout when executing the command";
};
};
});
default = defaults.convert.ocrmypdf.command;
description = "The system command";
};
};
});
default = defaults.convert.orcmypdf;
description = ''
The tool ocrmypdf can be used to convert pdf files to pdf files
in order to add extracted text as a separate layer. This makes
image-only pdfs searchable and you can select and copy/paste the
text. It also converts pdfs into pdf/a type pdfs, which are best
suited for archiving. So it makes sense to use this even for
text-only pdfs.
It is recommended to install ocrympdf, but it also is optional.
If it is enabled but fails, the error is not fatal and the
processing will continue using the original pdf for extracting
text. You can also disable it to remove the errors from the
processing logs.
The `--skip-text` option is necessary to not fail on "text" pdfs
(where ocr is not necessary). In this case, the pdf will be
converted to PDF/A.
'';
};
};
});
default = defaults.convert;