From 3948e592a7e2e7bdd133f7863b3d6ac925165873 Mon Sep 17 00:00:00 2001
From: Haitham-AbdelKarim <haithammoabdelkarim@gmail.com>
Date: Tue, 12 Mar 2024 16:07:42 +0200
Subject: [PATCH] Refactor markdown removal functions to accept markdown as
 input string

---
 project_explainer_ui/ui.py                   |  2 +-
 project_processor/gh_processor/file_utils.py | 66 +++-----------------
 2 files changed, 10 insertions(+), 58 deletions(-)

diff --git a/project_explainer_ui/ui.py b/project_explainer_ui/ui.py
index a836666..03bfd95 100644
--- a/project_explainer_ui/ui.py
+++ b/project_explainer_ui/ui.py
@@ -5,7 +5,7 @@ def summarize(summarization_type, github_project_url, github_project_branch="mai
     gptExplainer = Explainer(huggingface_model_id)
     if summarization_type == "brief":
         return gptExplainer.brief(github_url=github_project_url, branch=github_project_branch)["summary"]
-    return gptExplainer.outline(github_url=github_project_url, branch=github_project_branch)["summary"]
+    return gptExplainer.outline(github_url=github_project_url, branch=github_project_branch)
 
 demo = gr.Interface(
     fn=summarize,
diff --git a/project_processor/gh_processor/file_utils.py b/project_processor/gh_processor/file_utils.py
index 77480c4..27c2710 100644
--- a/project_processor/gh_processor/file_utils.py
+++ b/project_processor/gh_processor/file_utils.py
@@ -398,120 +398,72 @@ def get_elements_from_markdown_file(file_path: str, elements: List[str]) -> Dict
     return result
 
 
-def remove_images_from_markdown(file_path: str) -> str:
+def remove_images_from_markdown(markdown_content: str) -> str:
     """
     Removes image tags from a Markdown file and returns the updated content without images.
 
     Args:
-        file_path: The path to the Markdown file.
+        markdown_content: The Markdown content that will be processed.
 
     Returns:
         The Markdown content without images.
 
-    Raises:
-        ValueError: If the provided file is not a Markdown file or if the file does not exist.
     """
-
-    if not file_path.lower().endswith('.md'):
-        raise ValueError(
-            "Invalid file. Only Markdown files (.md) are supported.")
-
-    if not os.path.isfile(file_path):
-        raise ValueError("File not found.")
-
-    with open(file_path, 'r') as f:
-        markdown_content = f.read()
-
+    
     markdown_content_without_images = re.sub(
         '!\[.*?\]\(.*?\)', '', markdown_content)
 
     return markdown_content_without_images
 
 
-def remove_links_from_markdown(file_path: str) -> str:
+def remove_links_from_markdown(markdown_content: str) -> str:
     """
     Removes link tags from a Markdown file and returns the updated content.
 
     Args:
-        file_path: The path to the Markdown file.
+        markdown_content: The Markdown content that will be processed.
 
     Returns:
         The Markdown content without links.
 
-    Raises:
-        ValueError: If the provided file is not a Markdown file or if the file does not exist.
     """
 
-    if not file_path.lower().endswith('.md'):
-        raise ValueError(
-            "Invalid file. Only Markdown files (.md) are supported.")
-
-    if not os.path.isfile(file_path):
-        raise ValueError("File not found.")
-
-    with open(file_path, 'r') as f:
-        markdown_content = f.read()
-
     markdown_content_without_links = re.sub(
         '\[.*?\]\(.*?\)', '', markdown_content)
 
     return markdown_content_without_links
 
 
-def remove_code_blocks_from_markdown(file_path: str) -> str:
+def remove_code_blocks_from_markdown(markdown_content: str) -> str:
     """
     Removes code blocks from a Markdown file and returns the updated content.
 
     Args:
-        file_path: The path to the Markdown file.
+        markdown_content: The Markdown content that will be processed.
 
     Returns:
         The Markdown content without code blocks.
 
-    Raises:
-        ValueError: If the provided file is not a Markdown file or if the file does not exist.
     """
 
-    if not file_path.lower().endswith('.md'):
-        raise ValueError(
-            "Invalid file. Only Markdown files (.md) are supported.")
-
-    if not os.path.isfile(file_path):
-        raise ValueError("File not found.")
-
-    with open(file_path, 'r') as f:
-        markdown_content = f.read()
-
     markdown_content_without_code_blocks = re.sub(
         '```[\s\S]*?```', '', markdown_content)
 
     return markdown_content_without_code_blocks
 
 
-def remove_tables_from_markdown(file_path: str) -> str:
+def remove_tables_from_markdown(markdown_content: str) -> str:
     """
     Removes tables from a Markdown file and returns the updated content.
 
     Args:
-        file_path: The path to the Markdown file.
+        markdown_content: The Markdown content that will be processed.
 
     Returns:
         The Markdown content without tables.
 
-    Raises:
-        ValueError: If the provided file is not a Markdown file or if the file does not exist.
     """
 
-    if not file_path.lower().endswith('.md'):
-        raise ValueError(
-            "Invalid file. Only Markdown files (.md) are supported.")
-
-    if not os.path.isfile(file_path):
-        raise ValueError("File not found.")
-
-    with open(file_path, 'r') as f:
-        markdown_content = f.read()
-
     markdown_content_without_tables = re.sub(
         r'\n\|.*\|\n\|.*\|\n(\|.*\|)+', '', markdown_content)