Minor changes for cost codes, package updates. Added pyproject.toml file

app.py

@@ -719,7 +719,7 @@ with app:
             print("Downloading cost codes from S3")
             app.load(download_file_from_s3, inputs=[s3_default_bucket, s3_default_cost_codes_file, default_cost_codes_output_folder_location]).\
             success(load_in_default_cost_codes, inputs = [default_cost_codes_output_folder_location, default_cost_code_textbox], outputs=[cost_code_dataframe, cost_code_dataframe_base, cost_code_choice_drop])
-            print("Successfully loaded cost codesc from S3")
+            print("Successfully loaded cost codes from S3")
         elif os.path.exists(COST_CODES_PATH):
             print("Loading cost codes from default cost codes path location:", COST_CODES_PATH)
             app.load(load_in_default_cost_codes, inputs = [default_cost_codes_output_folder_location, default_cost_code_textbox], outputs=[cost_code_dataframe, cost_code_dataframe_base, cost_code_choice_drop])

pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "doc_redaction" # Your application's name
+version = "0.6.0" # Your application's current version
+description = "Redact PDF/image-based documents, or CSV/XLSX files using a Gradio-based GUI interface" # A short description
+readme = "README.md" # Path to your project's README file
+requires-python = ">=3.10" # The minimum Python version required
+
+dependencies = [
+    "pdfminer.six==20240706",
+    "pdf2image==1.17.0",
+    "pymupdf==1.25.3",
+    "opencv-python==4.10.0.84",
+    "presidio_analyzer==2.2.358",
+    "presidio_anonymizer==2.2.358",
+    "presidio-image-redactor==0.0.56",
+    "pikepdf==9.5.2",
+    "pandas==2.2.3",
+    "scikit-learn==1.6.1",
+    "spacy==3.8.4",
+    # Direct URL dependency for spacy model
+    "en_core_web_lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.8.0/en_core_web_lg-3.8.0.tar.gz",
+    "gradio==5.27.1",
+    "boto3==1.38.4",
+    "pyarrow==19.0.1",
+    "openpyxl==3.1.5",
+    "Faker==36.1.1",
+    "python-levenshtein==0.26.1",
+    "spaczz==0.6.1",
+    # Direct URL dependency for gradio_image_annotator wheel
+    "gradio_image_annotation @ https://github.com/seanpedrick-case/gradio_image_annotator/releases/download/v0.3.2/gradio_image_annotation-0.3.2-py3-none-any.whl",
+    "rapidfuzz==3.12.1",
+    "python-dotenv==1.0.1",
+    "numpy==1.26.4",
+    "awslambdaric==3.0.1"
+]
+
+[project.urls]
+Homepage = "https://seanpedrick-case.github.io/doc_redaction/README.html"
+repository = "https://github.com/seanpedrick-case/doc_redaction"
+
+[project.optional-dependencies]
+dev = ["pytest"]
+
+# Optional: You can add configuration for tools used in your project under the [tool] section
+# For example, configuration for a linter like Ruff:
+[tool.ruff]
+line-length = 88
+select = ["E", "F", "I"]
+
+# Optional: Configuration for a formatter like Black:
+[tool.black]
+line-length = 88
+target-version = ['py310']

requirements.txt

@@ -10,8 +10,8 @@ pandas==2.2.3
 scikit-learn==1.6.1
 spacy==3.8.4
 en_core_web_lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.8.0/en_core_web_lg-3.8.0.tar.gz
-gradio==5.25.2
-boto3==1.37.29
+gradio==5.27.1
+boto3==1.38.4
 pyarrow==19.0.1
 openpyxl==3.1.5
 Faker==36.1.1

tools/config.py

@@ -255,10 +255,11 @@ DEFAULT_COST_CODE = get_or_create_env_var('DEFAULT_COST_CODE', '')
 
 COST_CODES_PATH = get_or_create_env_var('COST_CODES_PATH', '') # 'config/COST_CENTRES.csv' # file should be a csv file with a single table in it that has two columns with a header. First column should contain cost codes, second column should contain a name or description for the cost code
 
-S3_COST_CODES_PATH = get_or_create_env_var('S3_COST_CODES_PATH', '') # COST_CENTRES.csv # This is a path within the DOCUMENT_REDACTION_BUCKET
-
+S3_COST_CODES_PATH = get_or_create_env_var('S3_COST_CODES_PATH', '') # COST_CENTRES.csv # This is a path within the DOCUMENT_REDACTION_BUCKET  
+    
+# A default path in case s3 cost code location is provided but no local cost code location given
 if COST_CODES_PATH: OUTPUT_COST_CODES_PATH = COST_CODES_PATH
-else: OUTPUT_COST_CODES_PATH = ''
+else: OUTPUT_COST_CODES_PATH = 'config/cost_codes.csv'
 
 ENFORCE_COST_CODES = get_or_create_env_var('ENFORCE_COST_CODES', 'False') # If you have cost codes listed, is it compulsory to choose one before redacting?