55e81ca4bb
I've broken out the OCR-specific code from the consumers and dumped it
all into its own app, `paperless_tesseract`. This new app should serve
as a sample of how to create one's own consumer for different file
types.
Documentation for how to do this isn't ready yet, but for the impatient:
* Create a new app
* containing a `parsers.py` for your parser modelled after
`paperless_tesseract.parsers.RasterisedDocumentParser`
* containing a `signals.py` with a handler moddelled after
`paperless_tesseract.signals.ConsumerDeclaration`
* connect the signal handler to
`documents.signals.document_consumer_declaration` in
`your_app.apps`
* Install the app into Paperless by declaring
`PAPERLESS_INSTALLED_APPS=your_app`. Additional apps should be
separated with commas.
* Restart the consumer
46 lines
1.1 KiB
Python
46 lines
1.1 KiB
Python
import logging
|
|
import shutil
|
|
import tempfile
|
|
|
|
from django.conf import settings
|
|
|
|
|
|
class ParseError(Exception):
|
|
pass
|
|
|
|
|
|
class DocumentParser(object):
|
|
"""
|
|
Subclass this to make your own parser. Have a look at
|
|
`paperless_tesseract.parsers` for inspiration.
|
|
"""
|
|
|
|
SCRATCH = settings.SCRATCH_DIR
|
|
|
|
def __init__(self, path):
|
|
self.document_path = path
|
|
self.tempdir = tempfile.mkdtemp(prefix="paperless", dir=self.SCRATCH)
|
|
self.logger = logging.getLogger(__name__)
|
|
self.logging_group = None
|
|
|
|
def get_thumbnail(self):
|
|
"""
|
|
Returns the path to a file we can use as a thumbnail for this document.
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
def get_text(self):
|
|
"""
|
|
Returns the text from the document and only the text.
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
def log(self, level, message):
|
|
getattr(self.logger, level)(message, extra={
|
|
"group": self.logging_group
|
|
})
|
|
|
|
def cleanup(self):
|
|
self.log("debug", "Deleting directory {}".format(self.tempdir))
|
|
shutil.rmtree(self.tempdir)
|