sqlseed 0.1.18__tar.gz → 0.1.19__tar.gz

{sqlseed-0.1.18 → sqlseed-0.1.19}/CHANGELOG.md

@@ -7,6 +7,24 @@ All notable changes to this project will be documented in this file.
 Format based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v0.1.19]
+
+### Added
+
+- Column mapper `_to_snake_case()` normalization: camelCase/PascalCase/Hungarian column names (`sOrderNo`, `sItemNo`, `userName`, `isActive`) now auto-resolve via snake-case fallback after direct matching
+- Sensitive identifier pattern rule: `user_no`, `card_no`, `card_number`, `identity_no` (and Hungarian variants `sUserNo`, `sCardNo`) map to masked string output instead of `foreign_key_or_integer`, preventing real values from leaking through FK resolution
+- `tests/test_mapper_camelcase.py` — 23 test cases covering camelCase mapping, sensitive field desensitization, and `_to_snake_case()` helper
+
+### Changed
+
+- `pyproject.toml`: moved `sqlite-utils` from required to optional dependency (matches `HAS_SQLITE_UTILS` fallback logic)
+- `pyproject.toml`: renamed `notebook` optional dep group to `tqdm` for clarity
+- `pyproject.toml`: restored `plugins/` to sdist exclude; added sdist exclude configs to plugin `pyproject.toml` files
+
+### Fixed
+
+- `test_fill_with_snapshot` now sets `SQLSEED_CACHE_DIR` to `tmp_path` via `monkeypatch.setenv`, fixing `PermissionError` when default cache directory is not writable
+
 ## [v0.1.17]
 
 ### Added

{sqlseed-0.1.18 → sqlseed-0.1.19}/CHANGELOG.zh-CN.md

@@ -7,6 +7,24 @@
 格式基于 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)，
 本项目遵循[语义化版本](https://semver.org/spec/v2.0.0.html)。
 
+## [v0.1.19]
+
+### 新增
+
+- 列映射器 `_to_snake_case()` 规范化：camelCase/PascalCase/Hungarian 列名（`sOrderNo`、`sItemNo`、`userName`、`isActive`）在直接匹配失败后自动通过 snake_case 回退解析
+- 敏感标识符模式规则：`user_no`、`card_no`、`card_number`、`identity_no`（及 Hungarian 变体 `sUserNo`、`sCardNo`）映射为脱敏字符串，防止真实值通过 FK 解析或 SharedPool 泄露
+- `tests/test_mapper_camelcase.py` — 23 个测试用例，覆盖 camelCase 映射、敏感字段脱敏和 `_to_snake_case()` 辅助函数
+
+### 变更
+
+- `pyproject.toml`：`sqlite-utils` 从必需依赖移至可选依赖（与 `HAS_SQLITE_UTILS` 回退逻辑一致）
+- `pyproject.toml`：可选依赖组 `notebook` 重命名为 `tqdm`
+- `pyproject.toml`：恢复 `plugins/` 到 sdist 排除列表；插件 `pyproject.toml` 新增 sdist 排除配置
+
+### 修复
+
+- `test_fill_with_snapshot` 通过 `monkeypatch.setenv` 将 `SQLSEED_CACHE_DIR` 设置为 `tmp_path`，修复默认缓存目录无写入权限时的 `PermissionError`
+
 ## [v0.1.17]
 
 ### 新增

{sqlseed-0.1.18 → sqlseed-0.1.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlseed
-Version: 0.1.18
+Version: 0.1.19
 Summary: Declarative SQLite test data generation toolkit
 Project-URL: Homepage, https://github.com/sunbos/sqlseed
 Project-URL: Documentation, https://github.com/sunbos/sqlseed#readme
@@ -28,12 +28,12 @@ Requires-Dist: pyyaml>=6.0
 Requires-Dist: rich>=13.0
 Requires-Dist: rstr>=3.2
 Requires-Dist: simpleeval>=1.0
-Requires-Dist: sqlite-utils>=3.36
 Requires-Dist: structlog>=24.0
 Requires-Dist: typing-extensions>=4.4
 Provides-Extra: all
 Requires-Dist: faker>=30.0; extra == 'all'
 Requires-Dist: mimesis>=18.0; extra == 'all'
+Requires-Dist: sqlite-utils>=3.36; extra == 'all'
 Requires-Dist: tqdm>=4.66; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: mypy>=1.10; extra == 'dev'
@@ -43,6 +43,7 @@ Requires-Dist: pytest-benchmark>=4.0; extra == 'dev'
 Requires-Dist: pytest-cov>=5.0; extra == 'dev'
 Requires-Dist: pytest>=8.0; extra == 'dev'
 Requires-Dist: ruff>=0.5; extra == 'dev'
+Requires-Dist: sqlite-utils>=3.36; extra == 'dev'
 Requires-Dist: tqdm>=4.66; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: mkdocs-material>=9.0; extra == 'docs'
@@ -51,8 +52,10 @@ Provides-Extra: faker
 Requires-Dist: faker>=30.0; extra == 'faker'
 Provides-Extra: mimesis
 Requires-Dist: mimesis>=18.0; extra == 'mimesis'
-Provides-Extra: notebook
-Requires-Dist: tqdm>=4.66; extra == 'notebook'
+Provides-Extra: sqlite-utils
+Requires-Dist: sqlite-utils>=3.36; extra == 'sqlite-utils'
+Provides-Extra: tqdm
+Requires-Dist: tqdm>=4.66; extra == 'tqdm'
 Description-Content-Type: text/markdown
 
 <div align="center">

{sqlseed-0.1.18 → sqlseed-0.1.19}/pyproject.toml

@@ -27,7 +27,6 @@ classifiers = [
 ]
 
 dependencies = [
-    "sqlite-utils>=3.36",
     "pydantic>=2.0",
     "pluggy>=1.3",
     "structlog>=24.0",
@@ -46,11 +45,13 @@ Repository = "https://github.com/sunbos/sqlseed"
 Issues = "https://github.com/sunbos/sqlseed/issues"
 
 [project.optional-dependencies]
+sqlite-utils = ["sqlite-utils>=3.36"]
 faker = ["faker>=30.0"]
 mimesis = ["mimesis>=18.0"]
-notebook = ["tqdm>=4.66"]
-all = ["faker>=30.0", "mimesis>=18.0", "tqdm>=4.66"]
+tqdm = ["tqdm>=4.66"]
+all = ["sqlite-utils>=3.36", "faker>=30.0", "mimesis>=18.0", "tqdm>=4.66"]
 dev = [
+    "sqlite-utils>=3.36",
     "pytest>=8.0",
     "pytest-cov>=5.0",
     "pytest-asyncio>=0.24",
@@ -83,6 +84,7 @@ packages = ["src/sqlseed"]
 exclude = [
     "docs/",
     "tests/",
+    "plugins/",
     ".github/",
     ".trae/",
     ".gemini/",

{sqlseed-0.1.18 → sqlseed-0.1.19}/src/sqlseed/core/mapper.py

@@ -130,6 +130,11 @@ class ColumnMapper:
     PATTERN_MATCH_RULES: ClassVar[list[tuple[str, str, dict[str, Any]]]] = [
         (r"^id$", "autoincrement", {}),
         (r".*_id$", "foreign_key_or_integer", {}),
+        (
+            r".*(?:user|card|identity)(?:_no|_number|_nbr)$",
+            "string",
+            {"min_length": 8, "max_length": 20, "charset": "alphanumeric"},
+        ),
         (r".*_no$|.*_nbr$", "foreign_key_or_integer", {}),
         (r".*_ids$", "json", {}),
         (r".*_at$", "datetime", {}),
@@ -255,6 +260,12 @@ class ColumnMapper:
             return GeneratorSpec(generator_name="skip")
         return None
 
+    _CAMELCASE_RE: ClassVar[re.Pattern[str]] = re.compile(r"(?<=[a-z0-9])(?=[A-Z])|(?<=[A-Z])(?=[A-Z][a-z])")
+
+    @classmethod
+    def _to_snake_case(cls, name: str) -> str:
+        return cls._CAMELCASE_RE.sub("_", name).lower()
+
     def map_column(
         self,
         column_info: ColumnInfo,
@@ -287,6 +298,15 @@ class ColumnMapper:
         if pattern_match:
             return pattern_match
 
+        snake_name = self._to_snake_case(column_info.name)
+        if snake_name != column_name:
+            snake_exact = self._match_exact(snake_name)
+            if snake_exact:
+                return snake_exact
+            snake_pattern = self._match_pattern(snake_name)
+            if snake_pattern:
+                return snake_pattern
+
         fallback_spec = self._map_from_default_or_nullable(column_info, column_type, enrich, force_type_infer)
         if fallback_spec:
             return fallback_spec

sqlseed-0.1.18/plugins/mcp-server-sqlseed/README.md

@@ -1,77 +0,0 @@
-# mcp-server-sqlseed
-
-**[English](README.md)** | [中文](README.zh-CN.md)
-
-[Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for [sqlseed](https://github.com/sunbos/sqlseed) — enabling AI assistants to inspect schemas, generate configs, and fill SQLite databases.
-
-## Installation
-
-```bash
-# Basic
-pip install mcp-server-sqlseed
-
-# With AI support (includes sqlseed-ai)
-pip install mcp-server-sqlseed[ai]
-```
-
-## Configuration
-
-### Claude Desktop
-
-Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or equivalent:
-
-```json
-{
-  "mcpServers": {
-    "sqlseed": {
-      "command": "mcp-server-sqlseed"
-    }
-  }
-}
-```
-
-### Cursor / Other MCP Clients
-
-Use command: `mcp-server-sqlseed`
-
-## MCP Tools
-
-| Tool | Description |
-|:-----|:------------|
-| `sqlseed_inspect_schema` | Inspect database schema: columns, foreign keys, indexes, sample data, schema_hash. Accepts optional `table_name` (all tables if omitted). |
-| `sqlseed_generate_yaml` | AI-driven YAML config generation with self-correction. Requires `sqlseed-ai` plugin and API key. Supports `api_key`/`base_url`/`model` parameter overrides. |
-| `sqlseed_execute_fill` | Execute data generation. Accepts optional `yaml_config` string, `count`, and `enrich` flag. Max YAML config size: 256KB. |
-
-### MCP Resource
-
-| Resource | Description |
-|:---------|:------------|
-| `sqlseed://schema/{db_path}/{table_name}` | Read-only JSON schema for a specific table |
-
-## Example Usage
-
-After configuring your MCP client, you can prompt:
-
-> "Inspect the schema of `app.db`, generate a YAML config for the `users` table, then fill 1000 rows."
-
-The AI assistant will call:
-1. `sqlseed_inspect_schema` → get table structure
-2. `sqlseed_generate_yaml` → generate YAML config (if sqlseed-ai is installed)
-3. `sqlseed_execute_fill` → fill data
-
-## AI Integration
-
-When `sqlseed-ai` is installed and an API key is configured (`SQLSEED_AI_API_KEY` or `OPENAI_API_KEY`), the `sqlseed_generate_yaml` tool uses LLM-driven analysis with self-correction. Without the AI plugin, the tool returns a fallback message.
-
-## Requirements
-
-- Python >= 3.10
-- `sqlseed >= 0.1.0`
-- `mcp >= 1.0`
-
-Optional:
-- `sqlseed-ai` (for `sqlseed_generate_yaml` tool)
-
-## License
-
-AGPL-3.0-or-later

sqlseed-0.1.18/plugins/mcp-server-sqlseed/README.zh-CN.md

@@ -1,77 +0,0 @@
-# mcp-server-sqlseed
-
-[English](README.md) | **[中文](README.zh-CN.md)**
-
-[Model Context Protocol (MCP)](https://modelcontextprotocol.io/) 服务器，用于 [sqlseed](https://github.com/sunbos/sqlseed) — 让 AI 助手直接检查 Schema、生成配置和填充 SQLite 数据库。
-
-## 安装
-
-```bash
-# 基础安装
-pip install mcp-server-sqlseed
-
-# 含 AI 支持（包含 sqlseed-ai）
-pip install mcp-server-sqlseed[ai]
-```
-
-## 配置
-
-### Claude Desktop
-
-添加到 `~/Library/Application Support/Claude/claude_desktop_config.json`（macOS）：
-
-```json
-{
-  "mcpServers": {
-    "sqlseed": {
-      "command": "mcp-server-sqlseed"
-    }
-  }
-}
-```
-
-### Cursor / 其他 MCP 客户端
-
-使用命令：`mcp-server-sqlseed`
-
-## MCP Tools
-
-| Tool | 说明 |
-|:-----|:-----|
-| `sqlseed_inspect_schema` | 检查数据库 Schema：列、外键、索引、样本数据、schema_hash。可选 `table_name`（省略则返回所有表）。 |
-| `sqlseed_generate_yaml` | AI 驱动的 YAML 配置生成，含自纠正。需要 `sqlseed-ai` 插件和 API Key。支持 `api_key`/`base_url`/`model` 参数覆盖。 |
-| `sqlseed_execute_fill` | 执行数据生成。可选 `yaml_config` 字符串、`count` 和 `enrich` 标志。YAML 配置最大 256KB。 |
-
-### MCP Resource
-
-| Resource | 说明 |
-|:---------|:-----|
-| `sqlseed://schema/{db_path}/{table_name}` | 指定表的只读 JSON Schema |
-
-## 使用示例
-
-配置 MCP 客户端后，可以这样提示：
-
-> "检查 `app.db` 的 Schema，为 `users` 表生成 YAML 配置，然后填充 1000 行数据。"
-
-AI 助手会依次调用：
-1. `sqlseed_inspect_schema` → 获取表结构
-2. `sqlseed_generate_yaml` → 生成 YAML 配置（需安装 sqlseed-ai）
-3. `sqlseed_execute_fill` → 填充数据
-
-## AI 集成
-
-当安装了 `sqlseed-ai` 并配置了 API Key（`SQLSEED_AI_API_KEY` 或 `OPENAI_API_KEY`）时，`sqlseed_generate_yaml` 工具使用 LLM 驱动的分析和自纠正。未安装 AI 插件时，该工具返回回退消息。
-
-## 依赖
-
-- Python >= 3.10
-- `sqlseed >= 0.1.0`
-- `mcp >= 1.0`
-
-可选：
-- `sqlseed-ai`（用于 `sqlseed_generate_yaml` 工具）
-
-## 许可证
-
-AGPL-3.0-or-later

sqlseed-0.1.18/plugins/mcp-server-sqlseed/pyproject.toml

@@ -1,47 +0,0 @@
-[build-system]
-requires = ["hatchling", "hatch-vcs"]
-build-backend = "hatchling.build"
-
-[project]
-name = "mcp-server-sqlseed"
-dynamic = ["version"]
-requires-python = ">=3.10"
-description = "MCP server for sqlseed - AI-powered SQLite test data generation"
-readme = "README.md"
-license = "AGPL-3.0-or-later"
-authors = [
-    {name = "SunBo", email = "1443584939@qq.com"},
-]
-classifiers = [
-    "Development Status :: 3 - Alpha",
-    "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
-]
-dependencies = [
-    "sqlseed>=0.1.0,<2",
-    "mcp>=1.0,<2",
-]
-
-[project.urls]
-Homepage = "https://github.com/sunbos/sqlseed"
-Repository = "https://github.com/sunbos/sqlseed/tree/main/plugins/mcp-server-sqlseed"
-
-[project.optional-dependencies]
-ai = ["sqlseed-ai"]
-
-[project.scripts]
-mcp-server-sqlseed = "mcp_server_sqlseed:main"
-
-[tool.hatch.version]
-source = "vcs"
-fallback-version = "0.0.0"
-
-[tool.hatch.version.raw-options]
-root = "../.."
-
-[tool.hatch.build.targets.wheel]
-packages = ["src/mcp_server_sqlseed"]

sqlseed-0.1.18/plugins/mcp-server-sqlseed/src/mcp_server_sqlseed/__init__.py

@@ -1,7 +0,0 @@
-from __future__ import annotations
-
-from mcp_server_sqlseed.server import mcp
-
-
-def main() -> None:
-    mcp.run()

sqlseed-0.1.18/plugins/mcp-server-sqlseed/src/mcp_server_sqlseed/__main__.py

@@ -1,6 +0,0 @@
-from __future__ import annotations
-
-from mcp_server_sqlseed import main
-
-if __name__ == "__main__":
-    main()

sqlseed-0.1.18/plugins/mcp-server-sqlseed/src/mcp_server_sqlseed/config.py

@@ -1,9 +0,0 @@
-from __future__ import annotations
-
-from pydantic import BaseModel
-
-
-class MCPServerConfig(BaseModel):
-    db_path: str | None = None
-    host: str = "localhost"
-    port: int = 8000

sqlseed-0.1.18/plugins/mcp-server-sqlseed/src/mcp_server_sqlseed/server.py

@@ -1,190 +0,0 @@
-from __future__ import annotations
-
-import hashlib
-import json
-from pathlib import Path
-from typing import Any
-
-import yaml
-from mcp.server.fastmcp import FastMCP
-
-from sqlseed.config.models import GeneratorConfig
-from sqlseed.core.orchestrator import DataOrchestrator
-
-try:
-    from sqlseed_ai.analyzer import SchemaAnalyzer
-    from sqlseed_ai.config import AIConfig
-    from sqlseed_ai.refiner import AiConfigRefiner, AISuggestionFailedError
-
-    _AI_AVAILABLE = True
-except ImportError:
-    _AI_AVAILABLE = False
-
-mcp = FastMCP("sqlseed")
-
-_MAX_YAML_CONFIG_SIZE = 256 * 1024
-
-
-def _validate_db_path(db_path: str) -> str:
-    resolved = Path(db_path).resolve()
-    valid_exts = (".db", ".sqlite", ".sqlite3")
-    if not str(resolved).endswith(valid_exts):
-        raise ValueError(f"Invalid database path: {db_path}. Must be a .db, .sqlite, or .sqlite3 file.")
-    if not resolved.exists():
-        raise ValueError(f"Database file not found: {db_path}")
-    return str(resolved)
-
-
-def _validate_table_name(table_name: str, allowed_tables: list[str]) -> str:
-    if table_name not in allowed_tables:
-        raise ValueError(f"Table '{table_name}' does not exist in the database. Available: {allowed_tables}")
-    return table_name
-
-
-def _serialize_schema_context(ctx: dict[str, Any]) -> dict[str, Any]:
-    return {
-        "table_name": ctx["table_name"],
-        "columns": [
-            {
-                "name": c.name,
-                "type": c.type,
-                "nullable": c.nullable,
-                "default": c.default,
-                "is_primary_key": c.is_primary_key,
-                "is_autoincrement": c.is_autoincrement,
-            }
-            for c in ctx["columns"]
-        ],
-        "foreign_keys": [
-            {"column": fk.column, "ref_table": fk.ref_table, "ref_column": fk.ref_column} for fk in ctx["foreign_keys"]
-        ],
-        "indexes": ctx["indexes"],
-        "sample_data": ctx["sample_data"],
-        "all_table_names": ctx["all_table_names"],
-    }
-
-
-def _compute_schema_hash(schema_ctx: dict[str, Any]) -> str:
-    hash_input = json.dumps(
-        {
-            "columns": [{"name": c.name, "type": c.type, "nullable": c.nullable} for c in schema_ctx["columns"]],
-            "foreign_keys": [{"column": fk.column, "ref_table": fk.ref_table} for fk in schema_ctx["foreign_keys"]],
-        },
-        sort_keys=True,
-    )
-    return hashlib.sha256(hash_input.encode()).hexdigest()[:16]
-
-
-@mcp.resource("sqlseed://schema/{db_path}/{table_name}")
-def get_schema_resource(db_path: str, table_name: str) -> str:
-    db_path = _validate_db_path(db_path)
-    with DataOrchestrator(db_path) as orch:
-        _validate_table_name(table_name, orch.get_table_names())
-        ctx = orch.get_schema_context(table_name)
-        serializable_ctx = _serialize_schema_context(ctx)
-        return json.dumps(serializable_ctx, ensure_ascii=False, indent=2)
-
-
-@mcp.tool()
-def sqlseed_inspect_schema(db_path: str, table_name: str | None = None) -> dict[str, Any]:
-    """Inspect database schema. Returns column info, foreign keys, indexes,
-    sample data, and schema_hash for specified table or all tables."""
-    db_path = _validate_db_path(db_path)
-    with DataOrchestrator(db_path) as orch:
-        if table_name:
-            _validate_table_name(table_name, orch.get_table_names())
-        tables = [table_name] if table_name else orch.get_table_names()
-        result: dict[str, Any] = {}
-        for tbl in tables:
-            ctx = orch.get_schema_context(tbl)
-            result[tbl] = _serialize_schema_context(ctx)
-            result[tbl]["schema_hash"] = _compute_schema_hash(ctx)
-        return result
-
-
-@mcp.tool()
-def sqlseed_generate_yaml(
-    db_path: str,
-    table_name: str,
-    max_retries: int = 3,
-    api_key: str | None = None,
-    base_url: str | None = None,
-    model: str | None = None,
-) -> str:
-    """Generate YAML config for a table using AI analysis with self-correction.
-    Returns YAML string for human review. Requires sqlseed-ai plugin and API key."""
-    if not _AI_AVAILABLE:
-        return "# No AI suggestions available. Ensure sqlseed-ai plugin is installed and API key is configured."
-
-    db_path = _validate_db_path(db_path)
-    with DataOrchestrator(db_path) as orch:
-        _validate_table_name(table_name, orch.get_table_names())
-
-    ai_config = AIConfig.from_env().apply_overrides(api_key=api_key, base_url=base_url, model=model)
-
-    ai_config.resolve_model()
-
-    analyzer = SchemaAnalyzer(config=ai_config)
-    refiner = AiConfigRefiner(analyzer, db_path)
-
-    try:
-        result = refiner.generate_and_refine(
-            table_name=table_name,
-            max_retries=max_retries,
-        )
-    except AISuggestionFailedError as e:
-        return f"# AI suggestion failed: {e}"
-    except (ValueError, RuntimeError, OSError) as e:
-        return f"# Error: {e}"
-
-    if result:
-        output = {"db_path": db_path, "provider": "mimesis", "locale": "en_US", "tables": [result]}
-        return str(yaml.dump(output, allow_unicode=True, sort_keys=False, default_flow_style=False))
-    return "# No AI suggestions available. Ensure sqlseed-ai plugin is installed and API key is configured."
-
-
-@mcp.tool()
-def sqlseed_execute_fill(
-    db_path: str,
-    table_name: str,
-    count: int = 1000,
-    yaml_config: str | None = None,
-    enrich: bool = False,
-) -> dict[str, Any]:
-    """Execute data generation for a table. Optionally provide YAML config string for column rules."""
-    db_path = _validate_db_path(db_path)
-
-    if yaml_config is not None and len(yaml_config) > _MAX_YAML_CONFIG_SIZE:
-        raise ValueError(f"yaml_config exceeds maximum allowed size of {_MAX_YAML_CONFIG_SIZE} bytes")
-
-    with DataOrchestrator(db_path) as orch:
-        _validate_table_name(table_name, orch.get_table_names())
-        column_configs = None
-        clear_before = False
-        seed = None
-
-        if yaml_config:
-            data = yaml.safe_load(yaml_config)
-            config = GeneratorConfig(**data)
-            for t in config.tables:
-                if t.name == table_name:
-                    column_configs = t.columns
-                    clear_before = t.clear_before
-                    seed = t.seed
-                    break
-
-        result = orch.fill_table(
-            table_name=table_name,
-            count=count,
-            column_configs=column_configs,
-            clear_before=clear_before,
-            seed=seed,
-            enrich=enrich,
-        )
-
-        return {
-            "table_name": result.table_name,
-            "count": result.count,
-            "elapsed": result.elapsed,
-            "errors": result.errors,
-        }