diff options
| author | J08nY | 2023-07-26 20:33:32 +0200 |
|---|---|---|
| committer | J08nY | 2023-08-24 11:05:53 +0200 |
| commit | 9303ea15d1e240e61837fcd4860509cc378299a7 (patch) | |
| tree | e686c60c48f4df2d1970a71fab460632aaf36b65 /src | |
| parent | 544e6c24fb241992e163d5ceda7cc6c5152c4c30 (diff) | |
| download | sec-certs-9303ea15d1e240e61837fcd4860509cc378299a7.tar.gz sec-certs-9303ea15d1e240e61837fcd4860509cc378299a7.tar.zst sec-certs-9303ea15d1e240e61837fcd4860509cc378299a7.zip | |
Do not rerun pdf to text conversion, it is pointless.
Either it works the first time or not, this just
wastes time.
Diffstat (limited to 'src')
| -rw-r--r-- | src/sec_certs/dataset/dataset.py | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/src/sec_certs/dataset/dataset.py b/src/sec_certs/dataset/dataset.py index b544294e..e836f492 100644 --- a/src/sec_certs/dataset/dataset.py +++ b/src/sec_certs/dataset/dataset.py @@ -297,8 +297,6 @@ class Dataset(Generic[CertSubType, AuxiliaryDatasetsSubType], ComplexSerializabl logger.info("Converting all PDFs to txt") self._convert_all_pdfs_body(fresh) - if fresh: - self._convert_all_pdfs_body(False) self.state.pdfs_converted = True |