mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-26 00:46:22 +02:00
Port Tesseract OCR code to new API
This commit is contained in:
parent
1e861dc984
commit
848d93922b
1 changed files with 25 additions and 26 deletions
|
|
@ -10,39 +10,42 @@ import pytesseract
|
|||
from pdf2image import convert_from_bytes
|
||||
|
||||
from ... schema import Document, TextDocument, Metadata
|
||||
from ... schema import document_ingest_queue, text_ingest_queue
|
||||
from ... log_level import LogLevel
|
||||
from ... base import ConsumerProducer
|
||||
from ... base import FlowProcessor, ConsumerSpec, ProducerSpec
|
||||
|
||||
module = "ocr"
|
||||
default_ident = "pdf-decoder"
|
||||
|
||||
default_input_queue = document_ingest_queue
|
||||
default_output_queue = text_ingest_queue
|
||||
default_subscriber = module
|
||||
|
||||
class Processor(ConsumerProducer):
|
||||
class Processor(FlowProcessor):
|
||||
|
||||
def __init__(self, **params):
|
||||
|
||||
input_queue = params.get("input_queue", default_input_queue)
|
||||
output_queue = params.get("output_queue", default_output_queue)
|
||||
subscriber = params.get("subscriber", default_subscriber)
|
||||
id = params.get("id", default_ident)
|
||||
|
||||
super(Processor, self).__init__(
|
||||
**params | {
|
||||
"input_queue": input_queue,
|
||||
"output_queue": output_queue,
|
||||
"subscriber": subscriber,
|
||||
"input_schema": Document,
|
||||
"output_schema": TextDocument,
|
||||
"id": id,
|
||||
}
|
||||
)
|
||||
|
||||
self.register_specification(
|
||||
ConsumerSpec(
|
||||
name = "input",
|
||||
schema = Document,
|
||||
handler = self.on_message,
|
||||
)
|
||||
)
|
||||
|
||||
self.register_specification(
|
||||
ProducerSpec(
|
||||
name = "output",
|
||||
schema = TextDocument,
|
||||
)
|
||||
)
|
||||
|
||||
print("PDF OCR inited")
|
||||
|
||||
async def handle(self, msg):
|
||||
async def on_message(self, msg, consumer, flow):
|
||||
|
||||
print("PDF message received")
|
||||
print("PDF message received", flush=True)
|
||||
|
||||
v = msg.value()
|
||||
|
||||
|
|
@ -65,19 +68,15 @@ class Processor(ConsumerProducer):
|
|||
text=text.encode("utf-8"),
|
||||
)
|
||||
|
||||
await self.send(r)
|
||||
await flow("output").send(r)
|
||||
|
||||
print("Done.", flush=True)
|
||||
|
||||
@staticmethod
|
||||
def add_args(parser):
|
||||
|
||||
ConsumerProducer.add_args(
|
||||
parser, default_input_queue, default_subscriber,
|
||||
default_output_queue,
|
||||
)
|
||||
FlowProcessor.add_args(parser)
|
||||
|
||||
def run():
|
||||
|
||||
Processor.launch(module, __doc__)
|
||||
Processor.launch(default_ident, __doc__)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue