feat: add SVN (Subversion) working copy support

.serena/.gitignore

@@ -0,0 +1,2 @@
+/cache
+/project.local.yml

.serena/project.yml

@@ -0,0 +1,154 @@
+# the name by which the project can be referenced within Serena
+project_name: "code-review-graph"
+
+
+# list of languages for which language servers are started; choose from:
+#   al                  bash                clojure             cpp                 csharp
+#   csharp_omnisharp    dart                elixir              elm                 erlang
+#   fortran             fsharp              go                  groovy              haskell
+#   haxe                java                julia               kotlin              lua
+#   markdown
+#   matlab              nix                 pascal              perl                php
+#   php_phpactor        powershell          python              python_jedi         r
+#   rego                ruby                ruby_solargraph     rust                scala
+#   swift               terraform           toml                typescript          typescript_vts
+#   vue                 yaml                zig
+#   (This list may be outdated. For the current list, see values of Language enum here:
+#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
+#   For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+#   - For Free Pascal/Lazarus, use pascal
+# Special requirements:
+#   Some languages require additional setup/installations.
+#   See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers
+# When using multiple languages, the first language server that supports a given file will be used for that file.
+# The first language is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+languages:
+- python
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# line ending convention to use when writing source files.
+# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default)
+# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings.
+line_ending:
+
+# The language backend to use for this project.
+# If not set, the global setting from serena_config.yml is used.
+# Valid values: LSP, JetBrains
+# Note: the backend is fixed at startup. If a project with a different backend
+# is activated post-init, an error will be returned.
+language_backend:
+
+# whether to use project's .gitignore files to ignore files
+ignore_all_files_in_gitignore: true
+
+# advanced configuration option allowing to configure language server-specific options.
+# Maps the language key to the options.
+# Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available.
+# No documentation on options means no options are available.
+ls_specific_settings: {}
+
+# list of additional paths to ignore in this project.
+# Same syntax as gitignore, so you can use * and **.
+# Note: global ignored_paths from serena_config.yml are also applied additively.
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude.
+# This extends the existing exclusions (e.g. from the global configuration)
+#
+# Below is the complete list of tools for convenience.
+# To make sure you have the latest list of tools, and to view their descriptions, 
+# execute `uv run scripts/print_tool_overview.py`.
+#
+#  * `activate_project`: Activates a project based on the project name or path.
+#  * `check_onboarding_performed`: Checks whether project onboarding was already performed.
+#  * `create_text_file`: Creates/overwrites a file in the project directory.
+#  * `delete_memory`: Delete a memory file. Should only happen if a user asks for it explicitly,
+#       for example by saying that the information retrieved from a memory file is no longer correct
+#       or no longer relevant for the project.
+#  * `edit_memory`: Replaces content matching a regular expression in a memory.
+#  * `execute_shell_command`: Executes a shell command.
+#  * `find_file`: Finds files in the given relative paths
+#  * `find_referencing_symbols`: Finds symbols that reference the given symbol using the language server backend
+#  * `find_symbol`: Performs a global (or local) search using the language server backend.
+#  * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
+#  * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
+#  * `initial_instructions`: Provides instructions Serena usage (i.e. the 'Serena Instructions Manual')
+#       for clients that do not read the initial instructions when the MCP server is connected.
+#  * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
+#  * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
+#  * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
+#  * `list_memories`: List available memories. Any memory can be read using the `read_memory` tool.
+#  * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
+#  * `read_file`: Reads a file within the project directory.
+#  * `read_memory`: Read the content of a memory file. This tool should only be used if the information
+#       is relevant to the current task. You can infer whether the information
+#       is relevant from the memory file name.
+#       You should not read the same memory file multiple times in the same conversation.
+#  * `rename_memory`: Renames or moves a memory. Moving between project and global scope is supported
+#       (e.g., renaming "global/foo" to "bar" moves it from global to project scope).
+#  * `rename_symbol`: Renames a symbol throughout the codebase using language server refactoring capabilities.
+#       For JB, we use a separate tool.
+#  * `replace_content`: Replaces content in a file (optionally using regular expressions).
+#  * `replace_symbol_body`: Replaces the full definition of a symbol using the language server backend.
+#  * `safe_delete_symbol`:
+#  * `search_for_pattern`: Performs a search for a pattern in the project.
+#  * `write_memory`: Write some information (utf-8-encoded) about this project that can be useful for future tasks to a memory in md format.
+#       The memory name should be meaningful.
+excluded_tools: []
+
+# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default).
+# This extends the existing inclusions (e.g. from the global configuration).
+included_optional_tools: []
+
+# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools.
+# This cannot be combined with non-empty excluded_tools or included_optional_tools.
+fixed_tools: []
+
+# list of mode names to that are always to be included in the set of active modes
+# The full set of modes to be activated is base_modes + default_modes.
+# If the setting is undefined, the base_modes from the global configuration (serena_config.yml) apply.
+# Otherwise, this setting overrides the global configuration.
+# Set this to [] to disable base modes for this project.
+# Set this to a list of mode names to always include the respective modes for this project.
+base_modes:
+
+# list of mode names that are to be activated by default.
+# The full set of modes to be activated is base_modes + default_modes.
+# If the setting is undefined, the default_modes from the global configuration (serena_config.yml) apply.
+# Otherwise, this overrides the setting from the global configuration (serena_config.yml).
+# This setting can, in turn, be overridden by CLI parameters (--mode).
+default_modes:
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+# time budget (seconds) per tool call for the retrieval of additional symbol information
+# such as docstrings or parameter information.
+# This overrides the corresponding setting in the global configuration; see the documentation there.
+# If null or missing, use the setting from the global configuration.
+symbol_info_budget:
+
+# list of regex patterns which, when matched, mark a memory entry as read‑only.
+# Extends the list from the global configuration, merging the two lists.
+read_only_memory_patterns: []
+
+# list of regex patterns for memories to completely ignore.
+# Matching memories will not appear in list_memories or activate_project output
+# and cannot be accessed via read_memory or write_memory.
+# To access ignored memory files, use the read_file tool on the raw file path.
+# Extends the list from the global configuration, merging the two lists.
+# Example: ["_archive/.*", "_episodes/.*"]
+ignored_memory_patterns: []

code_review_graph/changes.py

@@ -1,6 +1,6 @@
 """Change impact analysis for code review.
 
-Maps git diffs to affected functions, flows, communities, and test coverage
+Maps git/svn diffs to affected functions, flows, communities, and test coverage
 gaps. Produces risk-scored, priority-ordered review guidance.
 """
 
@@ -10,6 +10,7 @@
 import os
 import re
 import subprocess
+from pathlib import Path
 from typing import Any
 
 from .constants import SECURITY_KEYWORDS as _SECURITY_KEYWORDS
@@ -21,10 +22,11 @@
 _GIT_TIMEOUT = int(os.environ.get("CRG_GIT_TIMEOUT", "30"))  # seconds, configurable
 
 _SAFE_GIT_REF = re.compile(r"^[A-Za-z0-9_.~^/@{}\-]+$")
+_SAFE_SVN_REV = re.compile(r"^r?\d+(:r?\d+|:HEAD|:BASE|:COMMITTED)?$", re.IGNORECASE)
 
 
 # ---------------------------------------------------------------------------
-# 1. parse_git_diff_ranges
+# 1. parse_git_diff_ranges / parse_svn_diff_ranges
 # ---------------------------------------------------------------------------
 
 
@@ -65,6 +67,70 @@ def parse_git_diff_ranges(
     return _parse_unified_diff(result.stdout)
 
 
+def parse_svn_diff_ranges(
+    repo_root: str,
+    rev_range: str | None = None,
+) -> dict[str, list[tuple[int, int]]]:
+    """Run ``svn diff`` and extract changed line ranges per file.
+
+    Args:
+        repo_root: Absolute path to the SVN working copy root.
+        rev_range: Optional SVN revision range in ``rXXX:HEAD`` format.
+            When *None*, diffs the working copy against BASE (local changes).
+
+    Returns:
+        Mapping of file paths to lists of ``(start_line, end_line)`` tuples.
+        Returns an empty dict on error.
+    """
+    cmd = ["svn", "diff", "--non-interactive"]
+    if rev_range:
+        if not _SAFE_SVN_REV.match(rev_range):
+            logger.warning("Invalid SVN revision range rejected: %s", rev_range)
+            return {}
+        cmd.extend(["-r", rev_range])
+    try:
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            encoding="utf-8",
+            errors="replace",
+            cwd=repo_root,
+            timeout=_GIT_TIMEOUT,
+        )
+        if result.returncode != 0:
+            logger.warning("svn diff failed (rc=%d): %s", result.returncode, result.stderr[:200])
+            return {}
+    except (OSError, subprocess.SubprocessError) as exc:
+        logger.warning("svn diff error: %s", exc)
+        return {}
+
+    return _parse_unified_diff(result.stdout)
+
+
+def parse_diff_ranges(
+    repo_root: str,
+    base: str = "HEAD~1",
+) -> dict[str, list[tuple[int, int]]]:
+    """Auto-detect VCS and return changed line ranges per file.
+
+    Dispatches to :func:`parse_git_diff_ranges` for Git repositories and
+    :func:`parse_svn_diff_ranges` for SVN working copies.
+
+    Args:
+        repo_root: Absolute path to the repository/working-copy root.
+        base: For Git: the ref to diff against (default ``HEAD~1``).
+              For SVN: an optional revision range (e.g. ``"r100:HEAD"``);
+              when *base* is not a valid SVN revision, working-copy changes
+              (``svn diff``) are used instead.
+    """
+    root_path = Path(repo_root)
+    if (root_path / ".svn").exists():
+        rev_range = base if _SAFE_SVN_REV.match(base) else None
+        return parse_svn_diff_ranges(repo_root, rev_range)
+    return parse_git_diff_ranges(repo_root, base)
+
+
 def _parse_unified_diff(diff_text: str) -> dict[str, list[tuple[int, int]]]:
     """Parse unified diff output into file -> line-range mappings.
 
@@ -215,17 +281,18 @@ def analyze_changes(
         store: The graph store.
         changed_files: List of changed file paths.
         changed_ranges: Optional pre-parsed diff ranges. If not provided and
-            ``repo_root`` is given, they are computed via git.
-        repo_root: Repository root (for git diff).
-        base: Git ref to diff against.
+            ``repo_root`` is given, they are computed via the detected VCS
+            (Git or SVN).
+        repo_root: Repository root (for git/svn diff).
+        base: Git ref or SVN revision range to diff against.
 
     Returns:
         Dict with ``summary``, ``risk_score``, ``changed_functions``,
         ``affected_flows``, ``test_gaps``, and ``review_priorities``.
     """
     # Compute changed ranges if not provided.
     if changed_ranges is None and repo_root is not None:
-        changed_ranges = parse_git_diff_ranges(repo_root, base)
+        changed_ranges = parse_diff_ranges(repo_root, base)
 
     # Map changes to nodes.
     if changed_ranges:

code_review_graph/cli.py

@@ -640,14 +640,23 @@ def main() -> None:
                 print(f"Built on branch: {stored_branch}")
             if stored_sha:
                 print(f"Built at commit: {stored_sha[:12]}")
-            from .incremental import _git_branch_info
-            current_branch, current_sha = _git_branch_info(repo_root)
-            if stored_branch and current_branch and stored_branch != current_branch:
-                print(
-                    f"WARNING: Graph was built on '{stored_branch}' "
-                    f"but you are now on '{current_branch}'. "
-                    f"Run 'code-review-graph build' to rebuild."
-                )
+            from .incremental import _git_branch_info, detect_vcs
+            vcs = detect_vcs(repo_root)
+            if vcs == "git":
+                current_branch, current_sha = _git_branch_info(repo_root)
+                if stored_branch and current_branch and stored_branch != current_branch:
+                    print(
+                        f"WARNING: Graph was built on '{stored_branch}' "
+                        f"but you are now on '{current_branch}'. "
+                        f"Run 'code-review-graph build' to rebuild."
+                    )
+            elif vcs == "svn":
+                stored_rev = store.get_metadata("svn_revision")
+                stored_svn_branch = store.get_metadata("svn_branch")
+                if stored_svn_branch:
+                    print(f"SVN branch: {stored_svn_branch}")
+                if stored_rev:
+                    print(f"SVN revision at build: {stored_rev}")
 
         elif args.command == "watch":
             watch(repo_root, store)