trustgraph-ocr 1.2.0__tar.gz → 1.2.4__tar.gz

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/PKG-INFO

@@ -1,15 +1,18 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: trustgraph-ocr
-Version: 1.2.0
+Version: 1.2.4
 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/v1.2.0.tar.gz
-Author: trustgraph.ai
-Author-email: security@trustgraph.ai
+Author-email: "trustgraph.ai" <security@trustgraph.ai>
+Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph
 Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+Requires-Dist: trustgraph-base<1.3,>=1.2
+Requires-Dist: pulsar-client
+Requires-Dist: prometheus-client
+Requires-Dist: boto3
+Requires-Dist: pdf2image
+Requires-Dist: pytesseract
 
 See https://trustgraph.ai/

trustgraph_ocr-1.2.4/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "trustgraph-ocr"
+dynamic = ["version"]
+authors = [{name = "trustgraph.ai", email = "security@trustgraph.ai"}]
+description = "TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline."
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+    "trustgraph-base>=1.2,<1.3",
+    "pulsar-client",
+    "prometheus-client",
+    "boto3",
+    "pdf2image",
+    "pytesseract",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+Homepage = "https://github.com/trustgraph-ai/trustgraph"
+
+[project.scripts]
+pdf-ocr = "trustgraph.decoding.ocr:run"
+
+[tool.setuptools.packages.find]
+include = ["trustgraph*"]
+
+[tool.setuptools.dynamic]
+version = {attr = "trustgraph.ocr_version.__version__"}

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/trustgraph/decoding/ocr/pdf_decoder.py

@@ -6,12 +6,16 @@ PDF document as text as separate output objects.
 
 import tempfile
 import base64
+import logging
 import pytesseract
 from pdf2image import convert_from_bytes
 
 from ... schema import Document, TextDocument, Metadata
 from ... base import FlowProcessor, ConsumerSpec, ProducerSpec
 
+# Module logger
+logger = logging.getLogger(__name__)
+
 default_ident = "pdf-decoder"
 
 class Processor(FlowProcessor):
@@ -41,15 +45,15 @@ class Processor(FlowProcessor):
             )
         )
 
-        print("PDF OCR inited")
+        logger.info("PDF OCR processor initialized")
 
     async def on_message(self, msg, consumer, flow):
 
-        print("PDF message received", flush=True)
+        logger.info("PDF message received")
 
         v = msg.value()
 
-        print(f"Decoding {v.metadata.id}...", flush=True)
+        logger.info(f"Decoding {v.metadata.id}...")
 
         blob = base64.b64decode(v.data)
 
@@ -60,7 +64,7 @@ class Processor(FlowProcessor):
             try:
                 text = pytesseract.image_to_string(page, lang='eng')
             except Exception as e:
-                print(f"Page did not OCR: {e}")
+                logger.warning(f"Page did not OCR: {e}")
                 continue
 
             r = TextDocument(
@@ -70,7 +74,7 @@ class Processor(FlowProcessor):
 
             await flow("output").send(r)
 
-        print("Done.", flush=True)
+        logger.info("PDF decoding complete")
 
     @staticmethod
     def add_args(parser):

trustgraph_ocr-1.2.4/trustgraph/ocr_version.py

@@ -0,0 +1 @@
+__version__ = "1.2.4"

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/trustgraph_ocr.egg-info/PKG-INFO

@@ -1,15 +1,18 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: trustgraph-ocr
-Version: 1.2.0
+Version: 1.2.4
 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/v1.2.0.tar.gz
-Author: trustgraph.ai
-Author-email: security@trustgraph.ai
+Author-email: "trustgraph.ai" <security@trustgraph.ai>
+Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph
 Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+Requires-Dist: trustgraph-base<1.3,>=1.2
+Requires-Dist: pulsar-client
+Requires-Dist: prometheus-client
+Requires-Dist: boto3
+Requires-Dist: pdf2image
+Requires-Dist: pytesseract
 
 See https://trustgraph.ai/

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/trustgraph_ocr.egg-info/SOURCES.txt

@@ -1,6 +1,5 @@
 README.md
-setup.py
-scripts/pdf-ocr
+pyproject.toml
 trustgraph/ocr_version.py
 trustgraph/decoding/ocr/__init__.py
 trustgraph/decoding/ocr/__main__.py
@@ -8,5 +7,6 @@ trustgraph/decoding/ocr/pdf_decoder.py
 trustgraph_ocr.egg-info/PKG-INFO
 trustgraph_ocr.egg-info/SOURCES.txt
 trustgraph_ocr.egg-info/dependency_links.txt
+trustgraph_ocr.egg-info/entry_points.txt
 trustgraph_ocr.egg-info/requires.txt
 trustgraph_ocr.egg-info/top_level.txt

trustgraph_ocr-1.2.4/trustgraph_ocr.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdf-ocr = trustgraph.decoding.ocr:run

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/trustgraph_ocr.egg-info/top_level.txt

@@ -1,2 +1 @@
-scripts
 trustgraph

trustgraph-ocr-1.2.0/scripts/pdf-ocr

@@ -1,6 +0,0 @@
-#!/usr/bin/env python3
-
-from trustgraph.decoding.ocr import run
-
-run()
-

trustgraph-ocr-1.2.0/setup.py

@@ -1,47 +0,0 @@
-import setuptools
-import os
-import importlib
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-# Load a version number module
-spec = importlib.util.spec_from_file_location(
-    'version', 'trustgraph/ocr_version.py'
-)
-version_module = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(version_module)
-
-version = version_module.__version__
-
-setuptools.setup(
-    name="trustgraph-ocr",
-    version=version,
-    author="trustgraph.ai",
-    author_email="security@trustgraph.ai",
-    description="TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/trustgraph-ai/trustgraph",
-    packages=setuptools.find_namespace_packages(
-        where='./',
-    ),
-    classifiers=[ 
-        "Programming Language :: Python :: 3",
-        "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
-        "Operating System :: OS Independent",
-    ],
-    python_requires='>=3.8',
-    download_url = "https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v" + version + ".tar.gz",
-    install_requires=[
-        "trustgraph-base>=1.2,<1.3",
-        "pulsar-client",
-        "prometheus-client",
-        "boto3",
-        "pdf2image",
-        "pytesseract",
-    ],
-    scripts=[
-        "scripts/pdf-ocr",
-    ]
-)

trustgraph-ocr-1.2.0/trustgraph/ocr_version.py

@@ -1 +0,0 @@
-__version__ = "1.2.0"

{trustgraph-ocr-1.2.0 → trustgraph_ocr-1.2.4}/trustgraph_ocr.egg-info/requires.txt

@@ -1,6 +1,6 @@
+trustgraph-base<1.3,>=1.2
+pulsar-client
+prometheus-client
 boto3
 pdf2image
-prometheus-client
-pulsar-client
 pytesseract
-trustgraph-base<1.3,>=1.2