Replace dict-based query with ParsedQuery dataclass (#133)

- Introduce ParsedQuery dataclass to store query parameters and metadata
- Update ingestion and parser modules to use ParsedQuery instead of dict[str, Any]
- Convert ignore_patterns and include_patterns to sets
- Clean references to max size and pattern handling
- Update tests to reflect new dataclass usage

Author: filipchristiansen

src/config.py

@@ -2,6 +2,11 @@
 
 from pathlib import Path
 
+MAX_FILE_SIZE = 10 * 1024 * 1024  # 10 MB
+MAX_DIRECTORY_DEPTH = 20  # Maximum depth of directory traversal
+MAX_FILES = 10_000  # Maximum number of files to process
+MAX_TOTAL_SIZE_BYTES = 500 * 1024 * 1024  # 500 MB
+
 MAX_DISPLAY_SIZE: int = 300_000
 TMP_BASE_PATH = Path("/tmp/gitingest")
 DELETE_REPO_AFTER: int = 60 * 60  # In seconds

src/gitingest/cli.py

@@ -4,7 +4,7 @@
 
 import click
 
-from gitingest.query_ingestion import MAX_FILE_SIZE
+from config import MAX_FILE_SIZE
 from gitingest.repository_ingest import ingest
 
 
@@ -49,8 +49,8 @@ async def main(
     """
     try:
         # Combine default and custom ignore patterns
-        exclude_patterns = list(exclude_pattern)
-        include_patterns = list(set(include_pattern))
+        exclude_patterns = set(exclude_pattern)
+        include_patterns = set(include_pattern)
 
         if not output:
             output = "digest.txt"
@@ -61,7 +61,7 @@ async def main(
         click.echo(summary)
 
     except Exception as e:
-        click.echo(f"Error: {str(e)}", err=True)
+        click.echo(f"Error: {e}", err=True)
         raise click.Abort()
 
 

src/gitingest/ignore_patterns.py

@@ -1,6 +1,6 @@
 """ Default ignore patterns for Gitingest. """
 
-DEFAULT_IGNORE_PATTERNS: list[str] = [
+DEFAULT_IGNORE_PATTERNS: set[str] = {
     # Python
     "*.pyc",
     "*.pyo",
@@ -29,18 +29,17 @@
     "*.war",
     "*.ear",
     "*.nar",
-    "target/",
     ".gradle/",
     "build/",
     ".settings/",
-    ".project",
     ".classpath",
     "gradle-app.setting",
     "*.gradle",
+    # IDEs and editors / Java
+    ".project",
     # C/C++
     "*.o",
     "*.obj",
-    "*.so",
     "*.dll",
     "*.dylib",
     "*.exe",
@@ -68,21 +67,22 @@
     ".ruby-gemset",
     ".rvmrc",
     # Rust
-    "target/",
     "Cargo.lock",
     "**/*.rs.bk",
+    # Java / Rust
+    "target/",
     # Go
-    "bin/",
     "pkg/",
     # .NET/C#
-    "bin/",
     "obj/",
     "*.suo",
     "*.user",
     "*.userosscache",
     "*.sln.docstates",
     "packages/",
     "*.nupkg",
+    # Go / .NET / C#
+    "bin/",
     # Version control
     ".git",
     ".svn",
@@ -112,12 +112,9 @@
     ".idea",
     ".vscode",
     ".vs",
-    "*.swp",
     "*.swo",
     "*.swn",
     ".settings",
-    ".project",
-    ".classpath",
     "*.sublime-*",
     # Temporary and cache files
     "*.log",
@@ -140,9 +137,6 @@
     "*.egg",
     "*.whl",
     "*.so",
-    "*.dylib",
-    "*.dll",
-    "*.class",
     # Documentation
     "site-packages",
     ".docusaurus",
@@ -159,4 +153,4 @@
     "*.tfstate*",
     ## Dependencies in various languages
     "vendor/",
-]
+}