Initial attempt at git module

pyproject.toml

@@ -8,6 +8,7 @@ authors = [
 ]
 requires-python = ">=3.13"
 dependencies = [
+    "gitpython>=3.1.44",
     "rich>=14.0.0",
 ]
 

src/reviewllama/cli.py

@@ -3,8 +3,11 @@ import sys
 from pathlib import Path
 from typing import List, Optional
 
+from reviewllama.git_diff import analyze_git_repository
+
 from .configs import OllamaConfig, ReviewConfig, create_config_from_vars
-from .logger import log_paths, log_review_start
+from .logger import (log_git_analysis_result, log_git_analysis_start,
+                     log_paths, log_review_start)
 
 
 def normalize_server_url(url: str) -> str:
@@ -62,6 +65,13 @@ Examples:
         help="Maximum number of retry attempts (default: %(default)s)",
     )
 
+    parser.add_argument(
+        "--base-branch",
+        dest="base_branch",
+        default="master",
+        help="Base branch to compare against (default: %(default)s)",
+    )
+
     return parser
 
 
@@ -81,6 +91,7 @@ def transform_namespace_to_config(namespace: argparse.Namespace) -> ReviewConfig
         server_url=normalize_server_url(namespace.server_url),
         timeout=namespace.timeout,
         max_retries=namespace.max_retries,
+        base_branch=namespace.base_branch,
     )
 
 
@@ -97,6 +108,11 @@ def cli() -> None:
         # TODO: Pass config to review engine
         log_review_start(config)
         log_paths(config.paths)
+        
+        for path in Paths:
+            analysis = analyze_git_repository(path, config.base_branch)
+            log_git_analysis_start(path, config.base_branch)
+            log_git_analysis_result(analysis)
     except SystemExit:
         # argparse calls sys.exit on error, let it propagate
         raise

src/reviewllama/configs.py

@@ -2,6 +2,8 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import List
 
+from .cli import normalize_server_url
+
 
 @dataclass(frozen=True)
 class OllamaConfig:
@@ -19,6 +21,7 @@ class ReviewConfig:
 
     paths: List[Path]
     ollama: OllamaConfig
+    base_branch: str
 
 
 def create_ollama_config(
@@ -34,14 +37,19 @@ def create_ollama_config(
 
 
 def create_review_config(
-    paths: List[Path], ollama_config: OllamaConfig
+    paths: List[Path], ollama_config: OllamaConfig, base_branch: str
 ) -> ReviewConfig:
     """Create complete ReviewConfig from validated components."""
-    return ReviewConfig(paths=paths, ollama=ollama_config)
+    return ReviewConfig(paths=paths, ollama=ollama_config, base_branch=base_branch)
 
 
 def create_config_from_vars(
-    paths: List[Path], model: str, server_url: str, timeout: int, max_retries: int
+    paths: List[Path],
+    model: str,
+    server_url: str,
+    timeout: int,
+    max_retries: int,
+    base_branch: str,
 ):
     ollama_config = OllamaConfig(
         model=model,
@@ -50,4 +58,4 @@ def create_config_from_vars(
         max_retries=max_retries,
     )
 
-    return create_review_config(paths, ollama_config)
+    return create_review_config(paths, ollama_config, base_branch)

src/reviewllama/git_diff.py

@@ -0,0 +1,164 @@
+"""
+Git analysis module for ReviewLlama using functional programming style.
+"""
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import List, Optional, Tuple
+
+from git import Repo
+from git.diff import Diff
+from git.exc import GitCommandError, InvalidGitRepositoryError
+from git.objects import Commit
+from rich.console import Console
+
+
+@dataclass(frozen=True)
+class GitDiff:
+    """Represents a git diff with metadata."""
+    file_path: str
+    old_content: str
+    new_content: str
+    diff_text: str
+    change_type: str  # 'added', 'modified', 'deleted'
+
+
+@dataclass(frozen=True)
+class GitAnalysis:
+    """Complete git analysis result."""
+    repository_path: Path
+    current_branch: str
+    base_branch: str
+    diffs: List[GitDiff]
+    total_files_changed: int
+
+
+def find_git_repository(path: Path) -> Repo:
+    """Find and return git repository from given path."""
+    try:
+        return Repo(path, search_parent_directories=True)
+    except InvalidGitRepositoryError:
+        raise ValueError(f"No git repository found at or above {path}")
+
+
+def get_current_branch_name(repo: Repo) -> str:
+    """Get the name of the current branch."""
+    try:
+        return repo.active_branch.name
+    except TypeError:
+        # Detached HEAD state
+        return repo.head.commit.hexsha[:8]
+
+
+def branch_exists(repo: Repo, branch_name: str) -> bool:
+    """Check if a branch exists in the repository."""
+    try:
+        repo.commit(branch_name)
+        return True
+    except:
+        return False
+
+
+def get_base_branch(repo: Repo, requested_base: str) -> str:
+    """Determine the base branch to compare against."""
+    # Try requested base first
+    if branch_exists(repo, requested_base):
+        return requested_base
+    
+    # Fall back to common master branch names
+    common_masters = ['master', 'main', 'develop']
+    for branch in common_masters:
+        if branch_exists(repo, branch):
+            return branch
+    
+    raise ValueError(f"Base branch '{requested_base}' not found and no common master branch exists")
+
+
+def get_diff_between_branches(repo: Repo, base_branch: str, current_branch: str):
+    """Get diff between two branches."""
+    try:
+        base_commit = repo.commit(base_branch)
+        current_commit = repo.commit(current_branch)
+        return base_commit.diff(current_commit)
+    except GitCommandError as e:
+        raise ValueError(f"Failed to get diff between {base_branch} and {current_branch}: {e}")
+
+
+def determine_change_type(diff_item: Diff) -> str:
+    """Determine the type of change from a diff item."""
+    if diff_item.new_file:
+        return 'added'
+    elif diff_item.deleted_file:
+        return 'deleted'
+    else:
+        return 'modified'
+
+
+def extract_file_content(diff_item: Diff, is_old: bool = True) -> str:
+    """Extract file content from diff item."""
+    try:
+        blob = diff_item.a_blob if is_old else diff_item.b_blob
+        if blob is None:
+            return ""
+        return blob.data_stream.read().decode('utf-8', errors='ignore')
+    except (UnicodeDecodeError, AttributeError):
+        return ""
+
+
+def create_git_diff(diff_item: Diff) -> GitDiff:
+    """Create GitDiff from git.Diff object."""
+    file_path = diff_item.a_path or diff_item.b_path or "unknown"
+    old_content = extract_file_content(diff_item, is_old=True)
+    new_content = extract_file_content(diff_item, is_old=False)
+    diff_text = str(diff_item)
+    change_type = determine_change_type(diff_item)
+    
+    return GitDiff(
+        file_path=file_path,
+        old_content=old_content,
+        new_content=new_content,
+        diff_text=diff_text,
+        change_type=change_type
+    )
+
+
+def process_diff_items(diff_index) -> List[GitDiff]:
+    """Process all diff items into GitDiff objects."""
+    return [create_git_diff(item) for item in diff_index]
+
+
+def filter_reviewable_diffs(diffs: List[GitDiff]) -> List[GitDiff]:
+    """Filter diffs to only include reviewable files."""
+
+    # TODO: Update this to a more complete list of programming language extensions
+    reviewable_extensions = {
+        '.py', '.js', '.ts', '.java', '.cpp', '.c', '.h', '.hpp',
+        '.go', '.rs', '.rb', '.php', '.cs', '.swift', '.kt',
+        '.scala', '.clj', '.sh', '.sql', '.yml', '.yaml', '.json'
+    }
+    
+    def is_reviewable(diff: GitDiff) -> bool:
+        path = Path(diff.file_path)
+        return path.suffix.lower() in reviewable_extensions
+    
+    return [diff for diff in diffs if is_reviewable(diff)]
+
+
+def analyze_git_repository(path: Path, base_branch: str) -> GitAnalysis:
+    """Analyze git repository and extract diffs for review."""
+    repo = find_git_repository(path)
+    current_branch = get_current_branch_name(repo)
+    resolved_base_branch = get_base_branch(repo, base_branch)
+    
+    diff_index = get_diff_between_branches(repo, resolved_base_branch, current_branch)
+    all_diffs = process_diff_items(diff_index)
+    reviewable_diffs = filter_reviewable_diffs(all_diffs)
+    
+    return GitAnalysis(
+        repository_path=path,
+        current_branch=current_branch,
+        base_branch=resolved_base_branch,
+        diffs=reviewable_diffs,
+        total_files_changed=len(reviewable_diffs)
+    )
+

src/reviewllama/logger.py

@@ -6,6 +6,7 @@ from rich.console import Console
 from rich.text import Text
 
 from .configs import ReviewConfig
+from .git_diff import GitAnalysis
 
 
 def create_console() -> Console:
@@ -42,3 +43,39 @@ def log_error(error: str) -> None:
     """Log error message with colored output."""
     console = create_error_console()
     console.print(f"Error: {error}")
+
+
+def log_git_analysis_start(path: Path, base_branch: str) -> None:
+    """Log the start of git analysis."""
+    console = create_console
+    console.print(f"[dim]Analyzing git repository at:[/dim] [yellow]{path}[/yellow]")
+    console.print(f"[dim]Base branch:[/dim] [cyan]{base_branch}[/cyan]")
+
+
+def log_git_analysis_result(analysis: GitAnalysis) -> None:
+    """Log the results of git analysis."""
+    console = create_console()
+    console.print(
+        f"[dim]Current branch:[/dim] [green]{analysis.current_branch}[/green]"
+    )
+    console.print(f"[dim]Comparing against:[/dim] [cyan]{analysis.base_branch}[/cyan]")
+    console.print(
+        f"[dim]Files changed:[/dim] [yellow]{analysis.total_files_changed}[/yellow]"
+    )
+
+    if analysis.diffs:
+        console.print("\n[bold]Changed files:[/bold]")
+        for diff in analysis.diffs:
+            change_color = {
+                "added": "green",
+                "modified": "yellow",
+                "deleted": "red",
+            }.get(diff.change_type, "white")
+
+            console.print(
+                f"  [{change_color}]{diff.change_type.upper():>8}[/{change_color}] {diff.file_path}"
+            )
+    else:
+        console.print("[dim]No reviewable files changed.[/dim]")
+
+    console.print()

uv.lock

@@ -2,6 +2,30 @@ version = 1
 revision = 1
 requires-python = ">=3.13"
 
+[[package]]
+name = "gitdb"
+version = "4.0.12"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "smmap" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/72/94/63b0fc47eb32792c7ba1fe1b694daec9a63620db1e313033d18140c2320a/gitdb-4.0.12.tar.gz", hash = "sha256:5ef71f855d191a3326fcfbc0d5da835f26b13fbcba60c32c21091c349ffdb571", size = 394684 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/61/5c78b91c3143ed5c14207f463aecfc8f9dbb5092fb2869baf37c273b2705/gitdb-4.0.12-py3-none-any.whl", hash = "sha256:67073e15955400952c6565cc3e707c554a4eea2e428946f7a4c162fab9bd9bcf", size = 62794 },
+]
+
+[[package]]
+name = "gitpython"
+version = "3.1.44"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "gitdb" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c0/89/37df0b71473153574a5cdef8f242de422a0f5d26d7a9e231e6f169b4ad14/gitpython-3.1.44.tar.gz", hash = "sha256:c87e30b26253bf5418b01b0660f818967f3c503193838337fe5e573331249269", size = 214196 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1d/9a/4114a9057db2f1462d5c8f8390ab7383925fe1ac012eaa42402ad65c2963/GitPython-3.1.44-py3-none-any.whl", hash = "sha256:9e0e10cda9bed1ee64bc9a6de50e7e38a9c9943241cd7f585f6df3ed28011110", size = 207599 },
+]
+
 [[package]]
 name = "markdown-it-py"
 version = "3.0.0"
@@ -37,11 +61,15 @@ name = "reviewllama"
 version = "0.1.0"
 source = { editable = "." }
 dependencies = [
+    { name = "gitpython" },
     { name = "rich" },
 ]
 
 [package.metadata]
-requires-dist = [{ name = "rich", specifier = ">=14.0.0" }]
+requires-dist = [
+    { name = "gitpython", specifier = ">=3.1.44" },
+    { name = "rich", specifier = ">=14.0.0" },
+]
 
 [[package]]
 name = "rich"
@@ -55,3 +83,12 @@ sdist = { url = "https://files.pythonhosted.org/packages/a1/53/830aa4c3066a8ab0a
 wheels = [
     { url = "https://files.pythonhosted.org/packages/0d/9b/63f4c7ebc259242c89b3acafdb37b41d1185c07ff0011164674e9076b491/rich-14.0.0-py3-none-any.whl", hash = "sha256:1c9491e1951aac09caffd42f448ee3d04e58923ffe14993f6e83068dc395d7e0", size = 243229 },
 ]
+
+[[package]]
+name = "smmap"
+version = "5.0.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/44/cd/a040c4b3119bbe532e5b0732286f805445375489fceaec1f48306068ee3b/smmap-5.0.2.tar.gz", hash = "sha256:26ea65a03958fa0c8a1c7e8c7a58fdc77221b8910f6be2131affade476898ad5", size = 22329 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/be/d09147ad1ec7934636ad912901c5fd7667e1c858e19d355237db0d0cd5e4/smmap-5.0.2-py3-none-any.whl", hash = "sha256:b30115f0def7d7531d22a0fb6502488d879e75b260a9db4d0819cfb25403af5e", size = 24303 },
+]