chore: run make tidy on api files (#253)

These were excluded from linting when they were autogenerated. We need
to tidy these files, otherwise we'll get blocked by our internal deploy
pipeline.

Note that this should replace the current 0.0.47 candidate.

Makefile

@@ -102,7 +102,7 @@ check: check-src check-tests check-version
 ## check-src:                   runs linters (source only, no tests)
 .PHONY: check-src
 check-src:
-	black --line-length 100 ${PACKAGE_NAME} --check --exclude ${PACKAGE_NAME}/api
+	black --line-length 100 ${PACKAGE_NAME} --check
 	flake8 ${PACKAGE_NAME}
 	mypy ${PACKAGE_NAME} --ignore-missing-imports --install-types --non-interactive --implicit-optional
 
@@ -114,7 +114,7 @@ check-tests:
 ## tidy:                        run black
 .PHONY: tidy
 tidy:
-	black --line-length 100 ${PACKAGE_NAME} --exclude ${PACKAGE_NAME}/api
+	black --line-length 100 ${PACKAGE_NAME}
 	black --line-length 100 test_${PIPELINE_PACKAGE} scripts/smoketest.py
 
 ## check-scripts:               run shellcheck

prepline_general/api/app.py

@@ -29,10 +29,7 @@
 async def http_error_handler(request: Request, e: HTTPException):
     logger.error(e.detail)
 
-    return JSONResponse(
-        status_code=e.status_code,
-        content={"detail": e.detail}
-    )
+    return JSONResponse(status_code=e.status_code, content={"detail": e.detail})
 
 
 # Note(austin) - Convert any other errors to HTTPException
@@ -48,10 +45,7 @@ async def error_handler(request: Request, e: Exception):
 
     logger.error(trace)
 
-    error = HTTPException(
-        status_code=500,
-        detail=str(e)
-    )
+    error = HTTPException(status_code=500, detail=str(e))
 
     return await http_error_handler(request, error)
 
@@ -85,6 +79,7 @@ def filter(self, record: logging.LogRecord) -> bool:
 logging.getLogger("uvicorn.access").addFilter(HealthCheckFilter())
 logging.getLogger("uvicorn.access").addFilter(MetricsCheckFilter())
 
+
 @app.get("/healthcheck", status_code=status.HTTP_200_OK, include_in_schema=False)
 def healthcheck(request: Request):
     return {"healthcheck": "HEALTHCHECK STATUS: EVERYTHING OK!"}

prepline_general/api/general.py

@@ -277,13 +277,11 @@ def pipeline_api(
             # This will raise if the file is encrypted
             pdf.metadata
         except pypdf.errors.EmptyFileError:
-            raise HTTPException(
-                status_code=400, detail=f"File does not appear to be a valid PDF"
-            )
+            raise HTTPException(status_code=400, detail="File does not appear to be a valid PDF")
         except pypdf.errors.FileNotDecryptedError:
             raise HTTPException(
                 status_code=400,
-                detail=f"File is encrypted. Please decrypt it with password.",
+                detail="File is encrypted. Please decrypt it with password.",
             )
 
     strategy = (m_strategy[0] if len(m_strategy) else "auto").lower()
@@ -332,19 +330,30 @@ def pipeline_api(
         m_skip_infer_table_types[0] if len(m_skip_infer_table_types) else ["pdf", "jpg", "png"]
     )
 
-    chunking_strategy = (m_chunking_strategy[0].lower() if len(m_chunking_strategy) else None)
+    chunking_strategy = m_chunking_strategy[0].lower() if len(m_chunking_strategy) else None
     chunk_strategies = ["by_title"]
     if chunking_strategy and (chunking_strategy not in chunk_strategies):
         raise HTTPException(
-            status_code=400, detail=f"Invalid chunking strategy: {chunking_strategy}. Must be one of {chunk_strategies}"
+            status_code=400,
+            detail=f"Invalid chunking strategy: {chunking_strategy}. Must be one of {chunk_strategies}",
         )
-
-    multipage_sections_str = (m_multipage_sections[0] if len(m_multipage_sections) else "false").lower()
+
+    multipage_sections_str = (
+        m_multipage_sections[0] if len(m_multipage_sections) else "false"
+    ).lower()
     multipage_sections = multipage_sections_str == "true"
 
-    combine_under_n_chars = (int(m_combine_under_n_chars[0]) if m_combine_under_n_chars and m_combine_under_n_chars[0].isdigit() else 500)
+    combine_under_n_chars = (
+        int(m_combine_under_n_chars[0])
+        if m_combine_under_n_chars and m_combine_under_n_chars[0].isdigit()
+        else 500
+    )
 
-    new_after_n_chars = (int(m_new_after_n_chars[0]) if m_new_after_n_chars and m_new_after_n_chars[0].isdigit() else 1500)
+    new_after_n_chars = (
+        int(m_new_after_n_chars[0])
+        if m_new_after_n_chars and m_new_after_n_chars[0].isdigit()
+        else 1500
+    )
 
     try:
         logger.debug(
@@ -477,9 +486,7 @@ def get_validated_mimetype(file):
         if content_type not in allowed_mimetypes:
             raise HTTPException(
                 status_code=400,
-                detail=(
-                    f"File type {content_type} is not supported."
-                ),
+                detail=(f"File type {content_type} is not supported."),
             )
 
     return content_type