feat: Migrate to CPR SDK

.github/workflows/code-quality.yml

@@ -18,22 +18,18 @@ jobs:
       # For repo checkout
       contents: read
     steps:
-      - uses: actions/checkout@v4
+      - name: Check out repository code
+        uses: actions/checkout@v4
 
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.9"
+          python-version: "3.10"
 
       - name: Install dependencies
         run: |
-          python -m pip install "poetry==1.7.0"
-          poetry config virtualenvs.create false
-          poetry install --no-cache
-          poetry install --only-root
-
-      - name: Export PYTHONPATH
-        run: echo "PYTHONPATH=$(pwd)" >> $GITHUB_ENV
+          python -m pip install poetry
+          poetry install
 
       - name: Trunk Check
         uses: trunk-io/trunk-action@v1

.github/workflows/test.yml

@@ -16,22 +16,15 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
-      - name: Install poetry
-        run: pipx install poetry==1.2.2
-
-      - name: Install python or load from cache with dependencies
+      - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.9"
-          cache: poetry
+          python-version: "3.10"
 
       - name: Install dependencies
         run: |
+          python -m pip install poetry
           poetry install
 
       - name: Run test suite
-        run: |
-          poetry run python -m pytest \
-          --nbmake \
-          --nbmake-find-import-errors \
-          --nbmake-timeout=20 -vvv
+        run: make test

Makefile

@@ -1,7 +1,7 @@
-.PHONY: test
+.PHONY: install test
 
 install:
 	poetry install
 
 test:
-	poetry run python -m pytest -vvv
+	poetry run pytest -vvv

pyproject.toml

@@ -8,7 +8,7 @@ packages = [{ include = "azure_pdf_parser", from = "src" }]
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 azure-ai-formrecognizer = "^3.2.1"
-cpr-data-access = { git = "https://github.com/climatepolicyradar/data-access.git", tag = "0.4.0" }
+cpr-sdk = "^1.1.6"
 requests = "^2.31.0"
 langdetect = "^1.0.9"
 pypdf = "^3.15.0"
@@ -22,7 +22,6 @@ pre-commit = "^2.17.0"
 python-dotenv = "^0.19.2"
 pytest = "^7.0.1"
 pytest-dotenv = "^0.5.2"
-nbmake = "^1.4.1"
 httpx = "^0.27.0"
 mock = "^5.1.0"
 

scripts/unece_sprint/check_parsed_docs.py

@@ -1,7 +1,7 @@
 """Check whether the UNECE documents can be loaded using the CPR SDK"""
 
 import boto3
-from cpr_data_access.parser_models import BaseParserOutput
+from cpr_sdk.parser_models import BaseParserOutput
 from rich.console import Console
 
 console = Console()

src/azure_pdf_parser/convert.py

@@ -7,7 +7,7 @@
     DocumentTable,
     Point,
 )
-from cpr_data_access.parser_models import (
+from cpr_sdk.parser_models import (
     CONTENT_TYPE_PDF,
     BlockType,
     ParserInput,

src/azure_pdf_parser/experimental_base.py

@@ -3,14 +3,14 @@
 from typing import List, Optional, Sequence, Union
 
 from azure.ai.formrecognizer import Point
-from cpr_data_access.parser_models import (
+from cpr_sdk.parser_models import (
     CONTENT_TYPE_HTML,
     CONTENT_TYPE_PDF,
     HTMLData,
     PDFData,
     TextBlock,
 )
-from cpr_data_access.pipeline_general_models import BackendDocument
+from cpr_sdk.pipeline_general_models import BackendDocument
 from langdetect import DetectorFactory, detect
 from pydantic import AnyHttpUrl, BaseModel, model_validator
 

src/azure_pdf_parser/run.py

@@ -7,7 +7,7 @@
 
 from azure.ai.formrecognizer import AnalyzeResult
 from azure.core.exceptions import HttpResponseError
-from cpr_data_access.parser_models import BackendDocument, ParserInput
+from cpr_sdk.parser_models import BackendDocument, ParserInput
 from dotenv import find_dotenv, load_dotenv
 from pydantic import AnyHttpUrl
 from tqdm.auto import tqdm
@@ -119,7 +119,7 @@ def run_parser(
 
     if not AZURE_PROCESSOR_KEY or not AZURE_PROCESSOR_ENDPOINT:
         raise ValueError(
-            """Missing Azure API credentials. Set AZURE_PROCESSOR_KEY and 
+            """Missing Azure API credentials. Set AZURE_PROCESSOR_KEY and
             AZURE_PROCESSOR_ENDPOINT environment variables."""
         )
 

tests/conftest.py

@@ -9,8 +9,8 @@
     DocumentTable,
     DocumentTableCell,
 )
-from cpr_data_access.parser_models import ParserInput
-from cpr_data_access.pipeline_general_models import BackendDocument
+from cpr_sdk.parser_models import ParserInput
+from cpr_sdk.pipeline_general_models import BackendDocument
 from pydantic import AnyHttpUrl
 
 from azure_pdf_parser import AzureApiWrapper, PDFPagesBatchExtracted

tests/test_azure_wrapper.py

@@ -2,7 +2,7 @@
 from unittest.mock import Mock, patch
 
 from azure.ai.formrecognizer import AnalyzeResult
-from cpr_data_access.parser_models import ParserInput, ParserOutput
+from cpr_sdk.parser_models import ParserInput, ParserOutput
 
 from azure_pdf_parser import (
     AzureApiWrapper,

tests/test_cli.py

@@ -3,7 +3,7 @@
 from unittest.mock import patch
 
 from click.testing import CliRunner
-from cpr_data_access.parser_models import ParserOutput
+from cpr_sdk.parser_models import ParserOutput
 
 from src.azure_pdf_parser import AzureApiWrapper
 

tests/test_convert.py

@@ -6,12 +6,7 @@
     DocumentTable,
     Point,
 )
-from cpr_data_access.parser_models import (
-    BlockType,
-    ParserInput,
-    ParserOutput,
-    PDFTextBlock,
-)
+from cpr_sdk.parser_models import BlockType, ParserInput, ParserOutput, PDFTextBlock
 
 from azure_pdf_parser.base import DIMENSION_CONVERSION_FACTOR
 from azure_pdf_parser.convert import (