trustgraph-ocr 0.23.21__tar.gz → 0.23.23__tar.gz

{trustgraph-ocr-0.23.21 → trustgraph-ocr-0.23.23}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: trustgraph-ocr
-Version: 0.23.21
+Version: 0.23.23
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Home-page: https://github.com/trustgraph-ai/trustgraph
-Download-URL: https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v0.23.21.tar.gz
+Download-URL: https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v0.23.23.tar.gz
 Author: trustgraph.ai
 Author-email: security@trustgraph.ai
 Classifier: Programming Language :: Python :: 3

{trustgraph-ocr-0.23.21 → trustgraph-ocr-0.23.23}/trustgraph/decoding/ocr/pdf_decoder.py

@@ -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__)
 

trustgraph-ocr-0.23.23/trustgraph/ocr_version.py

@@ -0,0 +1 @@
+__version__ = "0.23.23"

{trustgraph-ocr-0.23.21 → trustgraph-ocr-0.23.23}/trustgraph_ocr.egg-info/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: trustgraph-ocr
-Version: 0.23.21
+Version: 0.23.23
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Home-page: https://github.com/trustgraph-ai/trustgraph
-Download-URL: https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v0.23.21.tar.gz
+Download-URL: https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v0.23.23.tar.gz
 Author: trustgraph.ai
 Author-email: security@trustgraph.ai
 Classifier: Programming Language :: Python :: 3

trustgraph-ocr-0.23.21/trustgraph/ocr_version.py

@@ -1 +0,0 @@
-__version__ = "0.23.21"