From a2ef45e13f57976f84887f7825afbd49dc0b6440 Mon Sep 17 00:00:00 2001
From: jayantp2003 <jayantparakh2003@gmail.com>
Date: Fri, 11 Oct 2024 17:08:04 +0530
Subject: [PATCH 1/2] Fix #859: Resolve issue with large zip breaking stream
 endpoint

---
 application/parser/file/rst_parser.py | 53 ++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/application/parser/file/rst_parser.py b/application/parser/file/rst_parser.py
index 633ec8445..eb9043b2e 100644
--- a/application/parser/file/rst_parser.py
+++ b/application/parser/file/rst_parser.py
@@ -91,6 +91,48 @@ def rst_to_tups(self, rst_text: str) -> List[Tuple[Optional[str], str]]:
             ]
         return rst_tups
 
+    def chunk_by_token_count(self, text: str, max_tokens: int = 100) -> List[str]:
+        """Chunk text by token count."""
+        # words = text.split()
+        # chunks = []
+        # current_chunk = []
+        # current_token_count = 0
+
+        # for word in words:
+        #     word_token_len = len(word.split())  # Token count
+        #     if current_token_count + word_token_len > max_tokens:
+        #         chunks.append(" ".join(current_chunk))
+        #         current_chunk = []
+        #         current_token_count = 0
+        #     current_chunk.append(word)
+        #     current_token_count += word_token_len
+
+        # if current_chunk:
+        #     chunks.append(" ".join(current_chunk))
+
+        # return chunks
+    
+
+        avg_token_length = 5
+    
+        # Calculate approximate chunk size in characters
+        chunk_size = max_tokens * avg_token_length
+        
+        # Split text into chunks
+        chunks = []
+        for i in range(0, len(text), chunk_size):
+            chunk = text[i:i+chunk_size]
+            
+            # Adjust chunk to end at a word boundary
+            if i + chunk_size < len(text):
+                last_space = chunk.rfind(' ')
+                if last_space != -1:
+                    chunk = chunk[:last_space]
+            
+            chunks.append(chunk.strip())
+        
+        return chunks
+    
     def remove_images(self, content: str) -> str:
         pattern = r"\.\. image:: (.*)"
         content = re.sub(pattern, "", content)
@@ -136,7 +178,7 @@ def _init_parser(self) -> Dict:
         return {}
 
     def parse_tups(
-            self, filepath: Path, errors: str = "ignore"
+            self, filepath: Path, errors: str = "ignore",max_tokens: Optional[int] = 1000
     ) -> List[Tuple[Optional[str], str]]:
         """Parse file into tuples."""
         with open(filepath, "r") as f:
@@ -156,6 +198,15 @@ def parse_tups(
             rst_tups = self.remove_whitespaces_excess(rst_tups)
         if self._remove_characters_excess:
             rst_tups = self.remove_characters_excess(rst_tups)
+
+        # Apply chunking if max_tokens is provided
+        if max_tokens is not None:
+            chunked_tups = []
+            for header, text in rst_tups:
+                chunks = self.chunk_by_token_count(text, max_tokens)
+                for idx, chunk in enumerate(chunks):
+                    chunked_tups.append((f"{header} - Chunk {idx + 1}", chunk))
+            return chunked_tups    
         return rst_tups
 
     def parse_file(

From 3db07f3a26c56d29e6d5a7d99c097206ac64cdce Mon Sep 17 00:00:00 2001
From: jayantp2003 <jayantparakh2003@gmail.com>
Date: Fri, 11 Oct 2024 17:10:12 +0530
Subject: [PATCH 2/2] Fix #859: Resolve issue with large zip breaking stream
 endpoint

---
 application/parser/file/rst_parser.py | 25 +------------------------
 1 file changed, 1 insertion(+), 24 deletions(-)

diff --git a/application/parser/file/rst_parser.py b/application/parser/file/rst_parser.py
index eb9043b2e..d39a0837f 100644
--- a/application/parser/file/rst_parser.py
+++ b/application/parser/file/rst_parser.py
@@ -93,37 +93,14 @@ def rst_to_tups(self, rst_text: str) -> List[Tuple[Optional[str], str]]:
 
     def chunk_by_token_count(self, text: str, max_tokens: int = 100) -> List[str]:
         """Chunk text by token count."""
-        # words = text.split()
-        # chunks = []
-        # current_chunk = []
-        # current_token_count = 0
-
-        # for word in words:
-        #     word_token_len = len(word.split())  # Token count
-        #     if current_token_count + word_token_len > max_tokens:
-        #         chunks.append(" ".join(current_chunk))
-        #         current_chunk = []
-        #         current_token_count = 0
-        #     current_chunk.append(word)
-        #     current_token_count += word_token_len
-
-        # if current_chunk:
-        #     chunks.append(" ".join(current_chunk))
-
-        # return chunks
     
-
         avg_token_length = 5
     
-        # Calculate approximate chunk size in characters
         chunk_size = max_tokens * avg_token_length
-        
-        # Split text into chunks
+
         chunks = []
         for i in range(0, len(text), chunk_size):
             chunk = text[i:i+chunk_size]
-            
-            # Adjust chunk to end at a word boundary
             if i + chunk_size < len(text):
                 last_space = chunk.rfind(' ')
                 if last_space != -1: