fix missing pkl file bug and use md_file in to_page

output_tmp/expected_output/61a-sp24-mt2_sol_2_pages/61a-sp24-mt2_sol_2_pages.md

@@ -0,0 +1,11 @@
+1. (7.0 points) What Would Python Display? Assume the following code has been executed. The Link class appears on the midterm 2 study guide (page 2, left side). def shake(it): if it is not Link.empty and it.rest is not Link.empty: if it.first + 1 < it.rest.first: it.rest = Link(it.rest.first-1, it.rest) shake(it) else: shake(it.rest) it = Link(2, Link(5, Link(7))) off = Link(1, it.rest) shake(it) def cruel(summer): while summer is not Link.empty: yield summer.first summer = summer.rest if summer is not Link.empty: summer = summer.rest summer = Link(1, Link(2, Link(3, Link(4)))) Write the output printed for each expression below or _Error_ if an error occurs. 1. (2.0 pt) print(it) <2 5 7> <2 4 5 7> <2 4 5 6 7> <2 3 4 5 7> <2 4 3 5 7> <2 3 4 5 6 7> <2 4 3 5 6 7> (2.0 pt) print(off) <1 5 6 7> (2.0 pt) print([x*x for x in cruel(summer)]) [1, 9]
+
+**(d) (1.0 pt)** What is the order of growth of the time it takes to evaluate shake(Link(1, Link(n))) in terms of n?
+
+exponential
+
+quadratic
+
+linear
+
+constant

rag/file_conversion_router/api.py

@@ -16,3 +16,5 @@ def convert_directory(input_dir: Union[str, Path], output_dir: Union[str, Path])
     """
     process_folder(input_dir, output_dir)
 
+if __name__ == "__main__": 
+    convert_directory("output_tmp\\input", "output_tmp\expected_output")

rag/file_conversion_router/conversion/md_converter.py

@@ -27,19 +27,19 @@ def _to_markdown(self, input_path: Path, output_path: Path) -> Path:
     def _to_page(self, input_path: Path, output_path: Path) -> Page:
         """Perform Markdown to Page conversion."""
         try:
-            md_file_path = self._to_markdown(input_path, output_path)
+            md_file = self._to_markdown(input_path, output_path,)
         except Exception as e:
             self._logger.error(f"An error occurred during markdown conversion: {str(e)}")
             raise
 
         output_path.parent.mkdir(parents=True, exist_ok=True)
 
-        filetype = md_file_path.suffix.lstrip('.')
-        with open(md_file_path, "r") as input_file:
+        filetype = md_file.suffix.lstrip('.')
+        with open(md_file, "r") as input_file:
             text = input_file.read()
 
-        metadata_path = md_file_path.with_name(f"{md_file_path.stem}_metadata.yaml")
+
+        metadata_path = input_path.with_name(f"{input_path.stem}_metadata.yaml")
         metadata_content = self._read_metadata(metadata_path)
         url = metadata_content.get("URL")
-        return Page(pagename=md_file_path.stem, content={'text': text}, filetype=filetype, page_url=url)
-
+        return Page(pagename = input_path.stem, content={'text': text}, filetype=filetype, page_url=url)

rag/file_conversion_router/conversion/pdf_converter.py

@@ -182,21 +182,19 @@ def _to_markdown(self, input_path: Path, output_path: Path) -> Path:
     def _to_page(self, input_path: Path, output_path: Path) -> Page:
         """Perform Markdown to Page conversion."""
         try:
-            md_file_path = self._to_markdown(input_path, output_path,)
+            md_file = self._to_markdown(input_path, output_path,)
         except Exception as e:
             self._logger.error(f"An error occurred during markdown conversion: {str(e)}")
             raise
 
         output_path.parent.mkdir(parents=True, exist_ok=True)
 
-        filetype = md_file_path.suffix.lstrip('.')
-        with open(md_file_path, "r") as input_file:
-            text = md_file_path.read()
+        filetype = md_file.suffix.lstrip('.')
+        with open(md_file, "r") as input_file:
+            text = input_file.read()
 
 
-        metadata_path = md_file_path.with_name(f"{md_file_path.stem}_metadata.yaml")
+        metadata_path = input_path.with_name(f"{input_path.stem}_metadata.yaml")
         metadata_content = self._read_metadata(metadata_path)
         url = metadata_content.get("URL")
-        print("PDF",url)
-        return Page(pagename = md_file_path.stem, content={'text': text}, filetype=filetype, page_url = url)
-
+        return Page(pagename=input_path.stem, content={'text': text}, filetype=filetype, page_url=url)

rag/file_conversion_router/conversion/rst_converter.py

@@ -29,21 +29,22 @@ def _to_markdown(self, input_path: Path, output_path: Path) -> Path:
     def _to_page(self, input_path: Path, output_path: Path) -> Page:
         """Perform Markdown to Page conversion."""
         try:
-            md_file_path = self._to_markdown(input_path, output_path)
+            md_file = self._to_markdown(input_path, output_path,)
         except Exception as e:
             self._logger.error(f"An error occurred during markdown conversion: {str(e)}")
             raise
 
         output_path.parent.mkdir(parents=True, exist_ok=True)
 
-        filetype = md_file_path.suffix.lstrip('.')
-        with open(md_file_path, "r") as input_file:
+        filetype = md_file.suffix.lstrip('.')
+        with open(md_file, "r") as input_file:
             text = input_file.read()
 
-        metadata_path = md_file_path.with_name(f"{md_file_path.stem}_metadata.yaml")
+
+        metadata_path = input_path.with_name(f"{input_path.stem}_metadata.yaml")
         metadata_content = self._read_metadata(metadata_path)
         url = metadata_content.get("URL")
-        return Page(pagename=md_file_path.stem, content={'text': text}, filetype=filetype, page_url=url)
+        return Page(pagename = input_path.stem, content={'text': text}, filetype=filetype, page_url=url)
 
 
 # converter = RstConverter()

rag/file_conversion_router/conversion/video_converter.py

@@ -170,19 +170,19 @@ def _to_markdown(self, input_path, output_path):
     def _to_page(self, input_path: Path, output_path: Path) -> Page:
         """Perform Markdown to Page conversion."""
         try:
-            md_file_path = self._to_markdown(input_path, output_path)
+            md_file = self._to_markdown(input_path, output_path,)
         except Exception as e:
             self._logger.error(f"An error occurred during markdown conversion: {str(e)}")
             raise
 
         output_path.parent.mkdir(parents=True, exist_ok=True)
 
-        filetype = md_file_path.suffix.lstrip('.')
-        with open(md_file_path, "r") as input_file:
+        filetype = md_file.suffix.lstrip('.')
+        with open(md_file, "r") as input_file:
             text = input_file.read()
 
-        metadata_path = md_file_path.with_name(f"{md_file_path.stem}_metadata.yaml")
+
+        metadata_path = input_path.with_name(f"{input_path.stem}_metadata.yaml")
         metadata_content = self._read_metadata(metadata_path)
         url = metadata_content.get("URL")
-        return Page(pagename=md_file_path.stem, content={'text': text}, filetype=filetype, page_url=url)
-
+        return Page(pagename = input_path.stem, content={'text': text}, filetype=filetype, page_url=url)

rag/file_conversion_router/services/directory_service.py

@@ -58,7 +58,7 @@ def process_folder(input_dir: Union[str, Path], output_dir: Union[str, Path]) ->
         if input_file_path.suffix in valid_extensions and input_file_path.is_file():
             # Construct the output subdirectory and file path
             output_subdir = output_dir / input_file_path.relative_to(input_dir).parent
-            output_subdir.mkdir(parents=True, exist_ok=True)
+            # output_subdir.mkdir(parents=True, exist_ok=True)
             output_file_path = output_subdir / input_file_path.stem
 
             # Instantiate a new converter object for each file based on the file extension