Merge pull request #1 from TonicAI/f/ruff

Adding ruff

.github/workflows/ruff.yml

@@ -0,0 +1,10 @@
+name: Ruff
+on: [push]
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/ruff-action@v1
+        with:
+          args: "check --target-version py37"

docs/source/conf.py

@@ -36,10 +36,10 @@
     "sphinx.ext.autodoc",
     "sphinx.ext.napoleon",
     "sphinx.ext.autosummary",
-    'sphinx.ext.autosectionlabel',
-    'sphinxcontrib.googleanalytics'
+    "sphinx.ext.autosectionlabel",
+    "sphinxcontrib.googleanalytics",
 ]
-autosummary_generate = True  
+autosummary_generate = True
 source_suffix = [".rst"]
 
 # Napoleon settings
@@ -64,21 +64,21 @@
 html_show_sourcelink = False
 html_show_sphinx = False
 html_theme_options = {
-    'analytics_anonymize_ip': False,
-    'logo_only': True,
-    'prev_next_buttons_location': 'bottom',
-    'style_external_links': False,
-    'vcs_pageview_mode': '',
-    'style_nav_header_background': 'white',
-    'flyout_display': 'hidden',
-    'version_selector': False,
-    'language_selector': True,
+    "analytics_anonymize_ip": False,
+    "logo_only": True,
+    "prev_next_buttons_location": "bottom",
+    "style_external_links": False,
+    "vcs_pageview_mode": "",
+    "style_nav_header_background": "white",
+    "flyout_display": "hidden",
+    "version_selector": False,
+    "language_selector": True,
     # Toc options
-    'collapse_navigation': False,
-    'sticky_navigation': True,
-    'navigation_depth': 4,
-    'includehidden': True,
-    'titles_only': False,    
+    "collapse_navigation": False,
+    "sticky_navigation": True,
+    "navigation_depth": 4,
+    "includehidden": True,
+    "titles_only": False,
 }
 
 extensions += []
@@ -92,12 +92,12 @@
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ["_static"]
 html_css_files = ["custom.css"]
-#html_permalinks_icon = Icons.permalinks_icon
+# html_permalinks_icon = Icons.permalinks_icon
 
-# function signature 
-python_maximum_signature_line_length=20
-python_display_short_literal_types=True
+# function signature
+python_maximum_signature_line_length = 20
+python_display_short_literal_types = True
 
-#google analytics
-googleanalytics_id='G-F8WSWZQ7PC'
-googleanalytics_enabled=True
+# google analytics
+googleanalytics_id = "G-F8WSWZQ7PC"
+googleanalytics_enabled = True

pyproject.toml

@@ -19,7 +19,8 @@ more-itertools = "^8.6.0"
 tqdm = "^4.0.0"
 amplitude-analytics = "^1.1.4"
 
-[tool.poetry.dev-dependencies]
+[tool.poetry.group.dev.dependencies]
+ruff = "^0.7.3"
 pytest = "^5.2"
 
 [build-system]

tonic_textual/classes/SolarCsvConfig.py

@@ -1,5 +1,13 @@
 class SolarCsvConfig:
-    def __init__(self, num_columns, has_header=False, escape_char="\"", quote_char="\"", delimiter=",", null_char="\\N"):
+    def __init__(
+        self,
+        num_columns,
+        has_header=False,
+        escape_char='"',
+        quote_char='"',
+        delimiter=",",
+        null_char="\\N",
+    ):
         self.num_columns = num_columns
         self.has_header = has_header
         self.escape_char = escape_char
@@ -14,5 +22,5 @@ def to_dict(self):
             "escapeChar": self.escape_char,
             "quoteChar": self.quote_char,
             "delimiter": self.delimiter,
-            "nullChar": self.null_char
-        }
+            "nullChar": self.null_char,
+        }

tonic_textual/classes/azure_pipeline.py

@@ -3,6 +3,7 @@
 from tonic_textual.classes.httpclient import HttpClient
 from tonic_textual.classes.pipeline import Pipeline
 
+
 class AzurePipeline(Pipeline):
     """Class to represent and provide access to a Tonic Textual Azure blob storage pipeline.
 
@@ -17,11 +18,11 @@ class AzurePipeline(Pipeline):
     client: HttpClient
         The HTTP client to use.
     """
-        
+
     def __init__(self, name: str, id: str, client: HttpClient):
         super().__init__(name, id, client)
-    
-    def set_output_location(self, container: str, prefix: Optional[str]=None):
+
+    def set_output_location(self, container: str, prefix: Optional[str] = None):
         """Sets the location in Azure blob storage where the pipeline stores processed files.
 
         Parameters
@@ -35,7 +36,9 @@ def set_output_location(self, container: str, prefix: Optional[str]=None):
         container = self.__prepare_container_name(container)
         prefix = prefix or ""
         output_location = container + "/" + prefix
-        self.client.http_patch(f'/api/parsejobconfig/{self.id}', data={'outputPath': output_location})
+        self.client.http_patch(
+            f"/api/parsejobconfig/{self.id}", data={"outputPath": output_location}
+        )
 
     def add_prefixes(self, container: str, prefixes: List[str]):
         """Add prefixes to your pipeline. Textual processes all of the files under the prefix that are of supported file types.
@@ -47,10 +50,16 @@ def add_prefixes(self, container: str, prefixes: List[str]):
         prefix: List[str]
             The list of prefixes to include
         """
-        
+
         container = self.__prepare_container_name(container)
-        path_prefixes = [container + "/" + prefix for prefix in prefixes if prefix is not None and len(prefix)>0]
-        self.client.http_patch(f'/api/parsejobconfig/{self.id}', data={'pathPrefixes': path_prefixes})
+        path_prefixes = [
+            container + "/" + prefix
+            for prefix in prefixes
+            if prefix is not None and len(prefix) > 0
+        ]
+        self.client.http_patch(
+            f"/api/parsejobconfig/{self.id}", data={"pathPrefixes": path_prefixes}
+        )
 
     def add_files(self, container: str, file_paths: List[str]) -> str:
         """Add files to your pipeline
@@ -62,18 +71,24 @@ def add_files(self, container: str, file_paths: List[str]) -> str:
         prefix: List[str]
             The list of files to include
         """
-                
+
         container = self.__prepare_container_name(container)
 
-        selected_files = [container + "/" + path for path in file_paths if path is not None and len(path)>0]
-        self.client.http_patch(f'/api/parsejobconfig/{self.id}', data={'selectedFiles': selected_files})
+        selected_files = [
+            container + "/" + path
+            for path in file_paths
+            if path is not None and len(path) > 0
+        ]
+        self.client.http_patch(
+            f"/api/parsejobconfig/{self.id}", data={"selectedFiles": selected_files}
+        )
 
-    def __prepare_container_name(self,container: str) -> str:
+    def __prepare_container_name(self, container: str) -> str:
         if container.startswith("adfs://"):
             return container[7:]
         elif container.startswith("wasbs://"):
             return container[8:]
         elif container.startswith("azure://"):
             return container[8:]
         else:
-            return container
+            return container

tonic_textual/classes/common_api_responses/label_custom_list.py

@@ -11,10 +11,9 @@ class LabelCustomList:
         The list of regexes to use when overriding entities.
 
     """
+
     def __init__(self, regexes: Optional[List[str]] = None):
         self.regexes = regexes if regexes is not None else []
 
     def to_dict(self):
-        return {
-            "regexes": self.regexes
-        }
+        return {"regexes": self.regexes}

tonic_textual/classes/common_api_responses/replacement.py

@@ -78,7 +78,11 @@ def __init__(
             score=score,
             language=language,
             **({} if new_text is None else {"new_text": new_text}),
-            **({} if example_redaction is None else {"example_redaction": example_redaction}),
+            **(
+                {}
+                if example_redaction is None
+                else {"example_redaction": example_redaction}
+            ),
             **({} if json_path is None else {"json_path": json_path}),
             **({} if xml_path is None else {"xml_path": xml_path}),
         )

tonic_textual/classes/common_api_responses/single_detection_result.py

@@ -1,6 +1,7 @@
 import json
 from typing import Optional, Dict
 
+
 class SingleDetectionResult(dict):
     """A span of text that has been detected as a named entity.
 
@@ -20,6 +21,7 @@ class SingleDetectionResult(dict):
         The JSON path of the entity in the original JSON document. This is only
         present if the input text was a JSON document.
     """
+
     def __init__(
         self,
         start: int,