Encoding='utf 8' correction & resolve .gitignore & merge main

.gitignore

@@ -173,3 +173,4 @@ Caddyfile
 
 # ignore default output directory
 tmp/*
+digest.txt

src/gitingest/__init__.py

@@ -1,4 +1,4 @@
-from gitingest.clone import clone_repo
+from gitingest.clone import clone_repo, CloneConfig
 from gitingest.ingest import ingest
 from gitingest.ingest_from_query import ingest_from_query
 from gitingest.parse_query import parse_query

src/gitingest/cli.py

@@ -1,8 +1,16 @@
+import os
+import pathlib
 import click
+import sys
 
-from gitingest.ingest import ingest
 from gitingest.ingest_from_query import MAX_FILE_SIZE
+from .encoding import setup_encoding
 
+# Setup encoding first
+setup_encoding()
+
+# Define constants
+DEFAULT_IGNORE_PATTERNS = []
 
 @click.command()
 @click.argument("source", type=str, required=True)
@@ -19,14 +27,41 @@ def main(
 ) -> None:
     """Analyze a directory and create a text dump of its contents."""
     try:
-        # Combine default and custom ignore patterns
+        from gitingest.ingest import ingest
+
+        # Convert paths to absolute with proper encoding
+        source = str(pathlib.Path(source).resolve())
+
+        # Handle patterns
         exclude_patterns = list(exclude_pattern)
         include_patterns = list(set(include_pattern))
-
+
+        # Set default output name
         if not output:
             output = "digest.txt"
-        summary, _, _ = ingest(source, max_size, include_patterns, exclude_patterns, output=output)
-
+        output = str(pathlib.Path(output).resolve())
+
+        # Call ingest with encoding awareness
+        summary, tree, content = ingest(
+            source, 
+            max_size, 
+            include_patterns, 
+            exclude_patterns, 
+            output=output
+        )
+
+        # Write output with explicit encoding
+        with open(output, 'w', encoding='utf-8', errors='replace') as f:
+            if isinstance(summary, bytes):
+                summary = summary.decode('utf-8', errors='replace')
+            if isinstance(tree, bytes):
+                tree = tree.decode('utf-8', errors='replace')
+            if isinstance(content, bytes):
+                content = content.decode('utf-8', errors='replace')
+
+            f.write(f"{summary}\n\n{tree}\n\n{content}")
+
+        # Print messages with encoding handling
         click.echo(f"Analysis complete! Output written to: {output}")
         click.echo("\nSummary:")
         click.echo(summary)

src/gitingest/encoding.py

@@ -0,0 +1,17 @@
+import sys
+import io
+import codecs
+
+def setup_encoding():
+    if sys.stdout.encoding != 'utf-8':
+        sys.stdout = io.TextIOWrapper(
+            sys.stdout.buffer, 
+            encoding='utf-8', 
+            errors='replace'
+        )
+    if sys.stderr.encoding != 'utf-8':
+        sys.stderr = io.TextIOWrapper(
+            sys.stderr.buffer, 
+            encoding='utf-8', 
+            errors='replace'
+        )

src/gitingest/ingest.py

@@ -2,20 +2,41 @@
 import inspect
 import shutil
 from pathlib import Path
+import io
+import sys
+from typing import Union
 
-from gitingest.clone import CloneConfig, clone_repo
-from gitingest.ingest_from_query import ingest_from_query
+# Import other modules from the package
 from gitingest.parse_query import parse_query
+from gitingest.clone import clone_repo, CloneConfig
+from gitingest.ingest_from_query import ingest_from_query
 
+def setup_encoding():
+    if sys.stdout.encoding != 'utf-8':
+        sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
+    if sys.stderr.encoding != 'utf-8':
+        sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8', errors='replace')
 
-def ingest(
-    source: str,
-    max_file_size: int = 10 * 1024 * 1024,  # 10 MB
-    include_patterns: list[str] | str | None = None,
-    exclude_patterns: list[str] | str | None = None,
-    output: str | None = None,
-) -> tuple[str, str, str]:
-
+def ingest(source: str, max_file_size: int = 10 * 1024 * 1024, 
+          include_patterns: Union[list[str], str] = None, 
+          exclude_patterns: Union[list[str], str] = None, 
+          output: str = None) -> tuple[str, str, str]:
+    """
+    Analyze and create a text dump of source contents.
+
+    Args:
+        source: Path to source directory or git URL
+        max_file_size: Maximum file size to process in bytes
+        include_patterns: Patterns to include in analysis
+        exclude_patterns: Patterns to exclude from analysis
+        output: Output file path
+
+    Returns:
+        Tuple of (summary, tree, content)
+    """
+    setup_encoding()
+    query = None
+
     try:
         query = parse_query(
             source=source,
@@ -43,14 +64,31 @@ def ingest(
         summary, tree, content = ingest_from_query(query)
 
         if output:
-            with open(f"{output}", "w") as f:
-                f.write(tree + "\n" + content)
+            # Write with explicit UTF-8 encoding
+            with open(output, "w", encoding='utf-8', errors='replace') as f:
+                # Ensure all content is properly encoded
+                tree = tree.encode('utf-8', errors='replace').decode('utf-8') if isinstance(tree, str) else tree
+                content = content.encode('utf-8', errors='replace').decode('utf-8') if isinstance(content, str) else content
+                f.write(f"{tree}\n{content}")
 
         return summary, tree, content
-
+
+    except UnicodeEncodeError as e:
+        # Handle encoding errors specifically
+        error_msg = f"Encoding error while processing {source}: {str(e)}"
+        raise RuntimeError(error_msg)
+
+    except Exception as e:
+        # Handle other errors
+        error_msg = f"Error while processing {source}: {str(e)}"
+        raise RuntimeError(error_msg)
+
     finally:
         # Clean up the temporary directory if it was created
-        if query["url"]:
+        if query and query.get('url'):
             # Get parent directory two levels up from local_path (../tmp)
-            cleanup_path = str(Path(query["local_path"]).parents[1])
-            shutil.rmtree(cleanup_path, ignore_errors=True)
+            cleanup_path = str(Path(query['local_path']).parents[1])
+            try:
+                shutil.rmtree(cleanup_path, ignore_errors=True)
+            except Exception as e:
+                print(f"Warning: Could not clean up temporary directory: {str(e)}", file=sys.stderr)