mcp-vector-search 0.5.1__py3-none-any.whl → 0.6.0__py3-none-any.whl

mcp_vector_search/parsers/utils.py

@@ -0,0 +1,265 @@
+"""Shared utilities for language parsers.
+
+This module contains common functionality used across multiple parsers
+to reduce code duplication and improve maintainability.
+"""
+
+from pathlib import Path
+from re import Pattern
+
+from ..config.constants import DEFAULT_CHUNK_SIZE
+from ..core.models import CodeChunk
+
+
+def split_into_lines(content: str) -> list[str]:
+    """Split content into lines, handling different line endings.
+
+    Args:
+        content: Text content to split
+
+    Returns:
+        List of lines with line endings preserved
+    """
+    # Handle different line endings and preserve them
+    return content.splitlines(keepends=True)
+
+
+def get_line_range(lines: list[str], start_line: int, end_line: int) -> str:
+    """Get content from a range of lines.
+
+    Args:
+        lines: List of lines
+        start_line: Starting line number (1-indexed)
+        end_line: Ending line number (1-indexed, inclusive)
+
+    Returns:
+        Joined content from the line range
+    """
+    # Convert to 0-indexed
+    start_idx = max(0, start_line - 1)
+    end_idx = min(len(lines), end_line)
+
+    return "".join(lines[start_idx:end_idx])
+
+
+def find_block_end(lines: list[str], start_line: int, indent_char: str = " ") -> int:
+    """Find the end of a code block based on indentation.
+
+    This is a simple heuristic that looks for the next line with equal or
+    lower indentation level than the starting line.
+
+    Args:
+        lines: List of lines
+        start_line: Starting line number (1-indexed)
+        indent_char: Character used for indentation (space or tab)
+
+    Returns:
+        End line number (1-indexed)
+    """
+    if start_line > len(lines):
+        return len(lines)
+
+    # Get indentation of starting line
+    start_idx = start_line - 1
+    start_indent = len(lines[start_idx]) - len(lines[start_idx].lstrip())
+
+    # Find next line with same or lower indentation
+    for i in range(start_idx + 1, len(lines)):
+        line = lines[i]
+        if line.strip():  # Skip empty lines
+            current_indent = len(line) - len(line.lstrip())
+            if current_indent <= start_indent:
+                return i  # Return 0-indexed position, will be used as end_line
+
+    return len(lines)
+
+
+def create_simple_chunks(
+    content: str, file_path: Path, chunk_size: int = DEFAULT_CHUNK_SIZE
+) -> list[CodeChunk]:
+    """Create simple line-based chunks from content.
+
+    This is a fallback chunking strategy when more sophisticated
+    parsing is not available.
+
+    Args:
+        content: File content
+        file_path: Path to source file
+        chunk_size: Number of lines per chunk
+
+    Returns:
+        List of code chunks
+    """
+    lines = split_into_lines(content)
+    chunks = []
+
+    for i in range(0, len(lines), chunk_size):
+        start_line = i + 1
+        end_line = min(i + chunk_size, len(lines))
+
+        chunk_content = get_line_range(lines, start_line, end_line)
+
+        if chunk_content.strip():
+            chunk = CodeChunk(
+                content=chunk_content,
+                start_line=start_line,
+                end_line=end_line,
+                file_path=str(file_path),
+                chunk_type="block",
+                metadata={"source": "simple_chunking"},
+            )
+            chunks.append(chunk)
+
+    return chunks
+
+
+def extract_docstring(lines: list[str], start_line: int) -> str | None:
+    """Extract docstring/comment block starting from a given line.
+
+    Supports Python docstrings (triple quotes), JavaDoc (/** */),
+    and hash-based comments (# or //).
+
+    Args:
+        lines: List of lines
+        start_line: Line number to start looking (1-indexed)
+
+    Returns:
+        Docstring content or None if not found
+    """
+    if start_line > len(lines):
+        return None
+
+    start_idx = start_line - 1
+
+    # Check for Python-style docstring
+    triple_double = '"""'
+    triple_single = "'''"
+    for quote in [triple_double, triple_single]:
+        if quote in lines[start_idx]:
+            # Multi-line docstring
+            docstring_lines = []
+            in_docstring = False
+
+            for line in lines[start_idx:]:
+                if quote in line:
+                    if in_docstring:
+                        # End of docstring
+                        docstring_lines.append(line[: line.index(quote) + 3])
+                        break
+                    else:
+                        # Start of docstring
+                        in_docstring = True
+                        docstring_lines.append(line)
+                        if line.count(quote) >= 2:
+                            # Single-line docstring
+                            break
+                elif in_docstring:
+                    docstring_lines.append(line)
+
+            if docstring_lines:
+                return "".join(docstring_lines).strip()
+
+    # Check for JavaDoc-style comment
+    if start_idx > 0 and "/**" in lines[start_idx - 1]:
+        comment_lines = []
+        for i in range(start_idx - 1, -1, -1):
+            comment_lines.insert(0, lines[i])
+            if "/**" in lines[i]:
+                break
+
+        for i in range(start_idx, len(lines)):
+            if "*/" in lines[i]:
+                comment_lines.append(lines[i])
+                break
+            comment_lines.append(lines[i])
+
+        return "".join(comment_lines).strip()
+
+    # Check for hash/slash comments on previous lines
+    comment_lines = []
+    for i in range(start_idx - 1, -1, -1):
+        line = lines[i].strip()
+        if line.startswith("#") or line.startswith("//"):
+            comment_lines.insert(0, lines[i])
+        elif line:
+            break
+
+    if comment_lines:
+        return "".join(comment_lines).strip()
+
+    return None
+
+
+def extract_imports_with_pattern(
+    content: str, pattern: Pattern[str], chunk_type: str = "import"
+) -> list[str]:
+    """Extract import/require/use statements using a regex pattern.
+
+    Args:
+        content: Source code content
+        pattern: Compiled regex pattern to match imports
+        chunk_type: Type of import (import, require, use, etc.)
+
+    Returns:
+        List of import statements
+    """
+    imports = []
+    for match in pattern.finditer(content):
+        import_line = match.group(0).strip()
+        imports.append(import_line)
+    return imports
+
+
+def find_code_blocks_with_patterns(
+    content: str, lines: list[str], patterns: dict[str, Pattern[str]], file_path: Path
+) -> list[CodeChunk]:
+    """Find code blocks (functions, classes, etc.) using regex patterns.
+
+    This is a generic fallback parser that can be configured with different
+    patterns for different languages.
+
+    Args:
+        content: Source code content
+        lines: Pre-split lines
+        patterns: Dictionary mapping block types to compiled regex patterns
+        file_path: Path to source file
+
+    Returns:
+        List of code chunks
+    """
+    chunks = []
+
+    for block_type, pattern in patterns.items():
+        for match in pattern.finditer(content):
+            # Extract the name from the first capturing group
+            name = match.group(1) if match.groups() else "unknown"
+
+            # Find line number
+            match_pos = match.start()
+            start_line = content[:match_pos].count("\n") + 1
+
+            # Find end of block using indentation
+            end_line = find_block_end(lines, start_line)
+
+            # Get block content
+            block_content = get_line_range(lines, start_line, end_line)
+
+            if block_content.strip():
+                # Extract docstring
+                docstring = extract_docstring(lines, start_line + 1)
+
+                chunk = CodeChunk(
+                    content=block_content,
+                    start_line=start_line,
+                    end_line=end_line,
+                    file_path=str(file_path),
+                    chunk_type=block_type,
+                    metadata={
+                        "name": name,
+                        "docstring": docstring,
+                        "source": "regex_fallback",
+                    },
+                )
+                chunks.append(chunk)
+
+    return chunks

mcp_vector_search/utils/gitignore.py

@@ -123,7 +123,7 @@ class GitignoreParser:
             with open(gitignore_path, encoding="utf-8", errors="ignore") as f:
                 lines = f.readlines()
 
-            for line_num, line in enumerate(lines, 1):
+            for _line_num, line in enumerate(lines, 1):
                 line = line.strip()
 
                 # Skip empty lines and comments

{mcp_vector_search-0.5.1.dist-info → mcp_vector_search-0.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-vector-search
-Version: 0.5.1
+Version: 0.6.0
 Summary: CLI-first semantic code search with MCP integration
 Project-URL: Homepage, https://github.com/bobmatnyc/mcp-vector-search
 Project-URL: Documentation, https://mcp-vector-search.readthedocs.io
@@ -44,6 +44,7 @@ Requires-Dist: click-didyoumean>=0.3.0
 Requires-Dist: httpx>=0.25.0
 Requires-Dist: loguru>=0.7.0
 Requires-Dist: mcp>=1.12.4
+Requires-Dist: packaging>=23.0
 Requires-Dist: pydantic-settings>=2.1.0
 Requires-Dist: pydantic>=2.5.0
 Requires-Dist: rich>=13.0.0
@@ -62,7 +63,7 @@ Description-Content-Type: text/markdown
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-> ⚠️ **Alpha Release (v0.0.3)**: This is an early-stage project under active development. Expect breaking changes and rough edges. Feedback and contributions are welcome!
+> ⚠️ **Alpha Release (v0.6.0)**: This is an early-stage project under active development. Expect breaking changes and rough edges. Feedback and contributions are welcome!
 
 A modern, fast, and intelligent code search tool that understands your codebase through semantic analysis and AST parsing. Built with Python, powered by ChromaDB, and designed for developer productivity.
 
@@ -73,6 +74,7 @@ A modern, fast, and intelligent code search tool that understands your codebase
 - **AST-Aware Parsing**: Understands code structure (functions, classes, methods)
 - **Multi-Language Support**: 8 languages - Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby, HTML, and Markdown/Text (with extensible architecture)
 - **Real-time Indexing**: File watching with automatic index updates
+- **Automatic Version Tracking**: Smart reindexing on tool upgrades
 - **Local-First**: Complete privacy with on-device processing
 - **Zero Configuration**: Auto-detects project structure and languages
 

{mcp_vector_search-0.5.1.dist-info → mcp_vector_search-0.6.0.dist-info}/RECORD

@@ -1,60 +1,62 @@
-mcp_vector_search/__init__.py,sha256=wWzwwtd5LyUT8xL6wgwEixYc6hnUgUWgjsUwYPE6ub8,299
+mcp_vector_search/__init__.py,sha256=WdjRcgYzYCEwrp2yc382O83RTxum5rX2oE_-xoPhV_8,299
 mcp_vector_search/py.typed,sha256=lCKeV9Qcn9sGtbRsgg-LJO2ZwWRuknnnlmomq3bJFH0,43
 mcp_vector_search/cli/__init__.py,sha256=TNB7CaOASz8u3yHWLbNmo8-GtHF0qwUjVKWAuNphKgo,40
-mcp_vector_search/cli/didyoumean.py,sha256=dzHtzGaCRtKGum1KqyPBNP4_7d2JNsxgcT4kD7rIfp4,15941
+mcp_vector_search/cli/didyoumean.py,sha256=F_ss-EX4F9RgnMsEhdTwLpyNCah9SqnBZc2tBtzASck,15918
 mcp_vector_search/cli/export.py,sha256=iluxuRT2KELdKlQeDAlVkteiel4GGrng153UAw9H0as,10804
-mcp_vector_search/cli/history.py,sha256=osQVNiTIdGSRZQiJEjC_AYMmHxaqv7RSKSeuO325Ip0,9115
+mcp_vector_search/cli/history.py,sha256=6wRrSfxpUe9hJXuaEeVxOVkFlcpqkIiGfwzDgd5N6c8,9323
 mcp_vector_search/cli/interactive.py,sha256=T7P4dAdvbglznzQYgiePv5YNyOx9FeE57Y3OKYnnbYE,12744
-mcp_vector_search/cli/main.py,sha256=b9au8AD_VETgSFeLSpcLYDOdRVVUL6aQms8D_wn84T8,16702
+mcp_vector_search/cli/main.py,sha256=VsW2U-E-_9jB6UfA4vTE0K-d657WZyLyIM2hvXgre9c,17057
 mcp_vector_search/cli/output.py,sha256=7ShIk_UKzhDzRGxI6JluPu0gGkbmKOevqgIAKR4oCa0,12560
-mcp_vector_search/cli/suggestions.py,sha256=i3KF8AaMa86aT5n64xwdw8R_ZiS-UehnF97fM0YzWAU,13184
+mcp_vector_search/cli/suggestions.py,sha256=h-UaxoLcHmFbhZSm0WG7nKJXAIRIqhv7aGsXijp7vA8,13273
 mcp_vector_search/cli/commands/__init__.py,sha256=vQls-YKZ54YEwmf7g1dL0T2SS9D4pdQljXzsUChG_V4,42
 mcp_vector_search/cli/commands/auto_index.py,sha256=imVVbxWRlA128NPdK9BetNNl3ELrsdq-hqcsLqyAmoM,12712
 mcp_vector_search/cli/commands/config.py,sha256=EHLqToCXrZs3gjIAg7pV8Bq8yVslUXWC4AnTcZQgSPQ,11337
 mcp_vector_search/cli/commands/index.py,sha256=soupoLR3EBsSzjqvzxurT9I6A8ZYM9asWVmJY3bDqMI,15394
-mcp_vector_search/cli/commands/init.py,sha256=orIJo71nETcLZCU6olWNVSz_jNWFhwDYu-1lHEqhkfA,25522
-mcp_vector_search/cli/commands/install.py,sha256=3Eiih--rizmpLNGyeDJlA93n8tSzUUJGm8GwMloVwy0,24617
+mcp_vector_search/cli/commands/init.py,sha256=1kK2YmWnMCnAmWjI3Om3d_NE89APisL-vvUFfKcyp2I,26408
+mcp_vector_search/cli/commands/install.py,sha256=phk7Eb7UOU5IsRfJyaDPdOfdUWli9gyA4cHjhgXcNEI,24609
 mcp_vector_search/cli/commands/mcp.py,sha256=FKZNxYrDc7HfPTFBUEypCv-8atsrHEdbtU6Yfg9QUMA,18569
-mcp_vector_search/cli/commands/reset.py,sha256=3gagCRnW7FRrUzJDgD49WfB7IK2TkQgMFnHRIZSr0zE,13733
-mcp_vector_search/cli/commands/search.py,sha256=PA3jOmWQCdkW-D6vCxodgWf8wpX2S3ZO4j_1OWjlY7E,19143
-mcp_vector_search/cli/commands/status.py,sha256=Aj2KZjnI7DtVUXTNfTcZuAnjK3Zhlt9TC4HWSViQMj8,17595
+mcp_vector_search/cli/commands/reset.py,sha256=bsIT6zjDf6gsvIkVaRaUClYzlTyNe--8t0NWkBY0ldU,13724
+mcp_vector_search/cli/commands/search.py,sha256=JFEkXQjevx2XZJhHTH8xy7G7XVcH5nGazJfacKSyEA4,20650
+mcp_vector_search/cli/commands/status.py,sha256=7ro6M3aifV0cuCqqxJ278P9g-fbhzvjoOABUoitMrPo,18929
 mcp_vector_search/cli/commands/watch.py,sha256=2pyWRoo4fIppFnyQ4sW4IBLHmpb_IwnTjRnzHkVBPcQ,8927
 mcp_vector_search/config/__init__.py,sha256=r_qAQkU5gc0EQ2pv8EQARACe4klhrR_WRJqCb9lfGc0,54
-mcp_vector_search/config/defaults.py,sha256=62wM6NGwjLQW8mu0Wp9eIykii2-3dbxuqzszB7spkVw,4945
-mcp_vector_search/config/settings.py,sha256=v1bc2K2yTwDzQKiy_BQhTWCP7FinSWX99vQGTWJRD2I,4159
+mcp_vector_search/config/constants.py,sha256=afXR6SvLLd8QYY4MG4s1vq-hCJiQsE5PhnE-XG9lvb4,1092
+mcp_vector_search/config/defaults.py,sha256=CYeUOd5cTvyKDZpimgYEku28jeKo5w013dHiXxXP5kY,5128
+mcp_vector_search/config/settings.py,sha256=m8o8j-tvWcuzrnNL6YWbi2fFbcB3lZY1kMNinJJUFCM,4328
 mcp_vector_search/core/__init__.py,sha256=bWKtKmmaFs7gG5XPCbrx77UYIVeO1FF8wIJxpj1dLNw,48
 mcp_vector_search/core/auto_indexer.py,sha256=0S4lZXaUgqEytMSA2FxQsh5hN7V1mbSLYVzEf_dslYQ,10307
 mcp_vector_search/core/connection_pool.py,sha256=Yo-gUQQbHawtuvh6OcJiAlbbvWQGQBd31QZOvs498fg,11224
-mcp_vector_search/core/database.py,sha256=wh55w42V5FbMX1rgo4zxLNb0t6fzq6UJx8NOBjAqfxs,35533
+mcp_vector_search/core/database.py,sha256=4CDqtmxtg1EsajZP36Xwc43jD_84szVfq5SFLpJh3eg,35515
 mcp_vector_search/core/embeddings.py,sha256=wSMUNxZcuGPMxxQ1AbKqA1a3-0c6AiOqmuuI7OqTyaQ,10578
 mcp_vector_search/core/exceptions.py,sha256=3bCjT8wmrLz_0e_Tayr90049zNTKYFWZa19kl0saKz8,1597
-mcp_vector_search/core/factory.py,sha256=GnsCBcRndBaUBWSXwtt8QKInAo-rGGBTSOKznUFETwA,10016
+mcp_vector_search/core/factory.py,sha256=tM6Ft-V9buF7nn9xbRMU1ngji-BJOKt6BhtfQhFLmF4,10384
 mcp_vector_search/core/git_hooks.py,sha256=xOfPpzgKoNTwM-vbhAihUucgudBQk45bCAVR5zJOFlQ,10878
-mcp_vector_search/core/indexer.py,sha256=_hY_9llmJdc2j5ct0eugSyMWUGLP1WEh7kzsEnCbroc,15758
+mcp_vector_search/core/indexer.py,sha256=MlsMDcGvl1ww6wAtCeTVU5AkaBM-z2LP4HGXErKoDHM,18331
 mcp_vector_search/core/models.py,sha256=fnZxvUkd9Afxmdwtw2BJX7uik6rQTwuWBTTqTeqDi0A,6697
 mcp_vector_search/core/project.py,sha256=RNeLBZZw6SO5mXqCwYfhStTGuVgeMq1US5UftG0SBYk,10069
 mcp_vector_search/core/scheduler.py,sha256=PBSlu-ieDYCXOMGYY7QKv9UReFEDPHNmwnUv_xb4vxg,11761
-mcp_vector_search/core/search.py,sha256=ZnrKIEqjLNVnh3_lfsVE0p97EWlNDZxYcc5SHhJUlRE,29787
+mcp_vector_search/core/search.py,sha256=9OC8-KwWdbw4y4QPQ-VXfz0encVHTJWYLtah3_chqG8,33682
 mcp_vector_search/core/watcher.py,sha256=-DFRCnuUfcqcTrkZPQqfJSvxKAxnpt-axgEj1V-B0O4,10862
 mcp_vector_search/mcp/__init__.py,sha256=gfKR0QV7Jqvj5y0LMBe9gSghd5_rPsvm_rml0ryQtoY,158
 mcp_vector_search/mcp/__main__.py,sha256=KgwB59HM5pRLe2Aj-fvDFcTp95lyT0wfmS3ENcx9gPc,571
 mcp_vector_search/mcp/server.py,sha256=YmHyvJqg_CjxEN356ShFrTPLgDKzaLXyrt8tNHVryEY,28322
 mcp_vector_search/parsers/__init__.py,sha256=jr0Yqz1xMok4lnG7_aXnkZThGuefrlAj8PWVbfeT3QQ,228
-mcp_vector_search/parsers/base.py,sha256=-zBY9T0modfegowaNyf5_upkS3ImR4TgrRwoSLuAiDw,5421
-mcp_vector_search/parsers/dart.py,sha256=Cs10Tw3XvvA_nJpUilKgrj8E2Sq6F3urODEFH_ZPS3M,21840
+mcp_vector_search/parsers/base.py,sha256=kOurwRR4xlyIje9rHLlEVa-OCl1LK8ih_fAFWHFg78g,5395
+mcp_vector_search/parsers/dart.py,sha256=li2JP0vwpSsZnMNq0PweZCD_o-y1jUwubHlSA8nm8KQ,21816
 mcp_vector_search/parsers/html.py,sha256=nzEVDV4oCBp3wpL8vp6WWx5eqiB39agu9E048JkuRJQ,13010
 mcp_vector_search/parsers/javascript.py,sha256=P7fT_tXCzUuXATTkTx_DyD4EuG0_KjIDlay09MhkKTE,9824
 mcp_vector_search/parsers/php.py,sha256=1QjnE8SAQF86VQ7pNfn1Pmpg5Dni4M7KCLU7212DkXM,24774
 mcp_vector_search/parsers/python.py,sha256=IB4gQ6DD6Oqvws5p3LQtHTJOtmH6f9FWmO9fQRfGQx4,15688
 mcp_vector_search/parsers/registry.py,sha256=L00EUp58ff_xatgQW-cBvE0AVBQi7cGtvr6zWV_NYbc,6457
 mcp_vector_search/parsers/ruby.py,sha256=xNn_z8txAWL7E1ULcFMiqn5idFhf5GQn8N3x1yE-c2k,23818
-mcp_vector_search/parsers/text.py,sha256=qKD-P76-lVjY16FH9ZffKihWaphoBV2R8laWXOwoNug,6024
+mcp_vector_search/parsers/text.py,sha256=jvMdFspbmrrOR1GSGzf2gvBDCXz1cPN_xemoDK4fUvM,6084
+mcp_vector_search/parsers/utils.py,sha256=10vT-GJSeDUoGSIslz8zq4RyavFiMtizCmcnn9cbQqE,8103
 mcp_vector_search/utils/__init__.py,sha256=Eq6lY-oPMfCt-GpPUbg9QbmTHuQVmTaVDBMU2183KVw,887
-mcp_vector_search/utils/gitignore.py,sha256=lc8_GK2L8dzlqPRZNB3XfQvVCbnLtz_l0eQN_13z8Xo,7684
+mcp_vector_search/utils/gitignore.py,sha256=bzie3V5gOGIN7j3FNVLLCx8O_hfZJDUqqAy5T3lT3Ek,7685
 mcp_vector_search/utils/timing.py,sha256=THC7mfbTYnUpnnDcblgQacYMzbEkfFoIShx6plmhCgg,11285
 mcp_vector_search/utils/version.py,sha256=d7fS-CLemxb8UzZ9j18zH0Y0Ud097ljKKYYOPulnGPE,1138
-mcp_vector_search-0.5.1.dist-info/METADATA,sha256=6QMMzeEpShXc8-jF74xNpBEuNGbexHDpNZ5AqxsPY88,19021
-mcp_vector_search-0.5.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-mcp_vector_search-0.5.1.dist-info/entry_points.txt,sha256=y3Ygtc_JiBchNEIL-tPABo7EbzBExGAxwGdkkeP5D2I,86
-mcp_vector_search-0.5.1.dist-info/licenses/LICENSE,sha256=FqZUgGJH_tZKZLQsMCpXaLawRyLmyFKRVfMwYyEcyTs,1072
-mcp_vector_search-0.5.1.dist-info/RECORD,,
+mcp_vector_search-0.6.0.dist-info/METADATA,sha256=do--B4P_ROSsUmBn1n9xsO8ANdVOXkSYAcqY2YF_c7w,19120
+mcp_vector_search-0.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+mcp_vector_search-0.6.0.dist-info/entry_points.txt,sha256=y3Ygtc_JiBchNEIL-tPABo7EbzBExGAxwGdkkeP5D2I,86
+mcp_vector_search-0.6.0.dist-info/licenses/LICENSE,sha256=FqZUgGJH_tZKZLQsMCpXaLawRyLmyFKRVfMwYyEcyTs,1072
+mcp_vector_search-0.6.0.dist-info/RECORD,,