├── LICENSE ├── README.md ├── aan_1.sqlite ├── example.py ├── m_schema.py ├── requirements.txt ├── schema_engine.py ├── schema_representation.png └── utils.py /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # M-Schema: a semi-structure representation of database schema 2 | ## Introduction 3 | MSchema is a semi-structured schema representation of database structure, which could be used in various scenarios such as Text-to-SQL. 4 | This repository contains the code for connecting to the database and constructing M-Schema. 5 | We support a variety of relational databases, such as MySQL, PostgreSQL, Oracle, etc. 6 | 7 |

8 | image 9 |

10 | 11 | ## Requirements 12 | + python >= 3.9 13 | 14 | You can install the required packages with the following command: 15 | ```shell 16 | pip install -r requirements.txt 17 | ``` 18 | 19 | ## Quick Start 20 | You can just connect to the database using [```sqlalchemy```](https://www.sqlalchemy.org/) and construct M-Schema representation. 21 | 22 | 1. Create a database connection. 23 | 24 | Take PostgreSQL as an example: 25 | ```python 26 | from sqlalchemy import create_engine 27 | db_engine = create_engine(f"postgresql+psycopg2://{db_user_name}:{db_pwd}@{db_host}:{port}/{db_name}") 28 | ``` 29 | 30 | Connect to MySQL: 31 | ```python 32 | db_engine = create_engine(f"mysql+pymysql://{db_user_name}:{db_pwd}@{db_host}:{port}/{db_name}") 33 | ``` 34 | 35 | Connect to SQLite: 36 | ```python 37 | import os 38 | db_path = "" 39 | abs_path = os.path.abspath(db_path) 40 | db_engine = create_engine(f'sqlite:///{abs_path}') 41 | ``` 42 | 43 | 2. Construct M-Schema representation. 44 | ```python 45 | from schema_engine import SchemaEngine 46 | 47 | schema_engine = SchemaEngine(engine=db_engine, db_name=db_name) 48 | mschema = schema_engine.mschema 49 | mschema_str = mschema.to_mschema() 50 | print(mschema_str) 51 | mschema.save(f'./{db_name}.json') 52 | ``` 53 | 54 | 3. Use for Text-to-SQL. 55 | ```python 56 | dialect = db_engine.dialect.name 57 | question = '' 58 | evidence = '' 59 | prompt = """You are now a {dialect} data analyst, and you are given a database schema as follows: 60 | 61 | 【Schema】 62 | {db_schema} 63 | 64 | 【Question】 65 | {question} 66 | 67 | 【Evidence】 68 | {evidence} 69 | 70 | Please read and understand the database schema carefully, and generate an executable SQL based on the user's question and evidence. The generated SQL is protected by ```sql and ```. 71 | """.format(dialect=dialect, question=question, db_schema=mschema_str, evidence=evidence) 72 | 73 | # Replace the function call_llm() with your own function or method to interact with a LLM API. 74 | # response = call_llm(prompt) 75 | ``` 76 | 77 | 78 | ## Citation 79 | If you find our work helpful, feel free to give us a cite. 80 | ```bibtex 81 | @article{xiyansql, 82 | title={A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL}, 83 | author={Yingqi Gao and Yifu Liu and Xiaoxia Li and Xiaorong Shi and Yin Zhu and Yiming Wang and Shiqi Li and Wei Li and Yuntao Hong and Zhiling Luo and Jinyang Gao and Liyu Mou and Yu Li}, 84 | year={2024}, 85 | journal={arXiv preprint arXiv:2411.08599}, 86 | url={https://arxiv.org/abs/2411.08599}, 87 | primaryClass={cs.AI} 88 | } 89 | ``` 90 | -------------------------------------------------------------------------------- /aan_1.sqlite: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/XGenerationLab/M-Schema/e8e49054d17cafa4255ac96b80cd3ca6ecc4ab31/aan_1.sqlite -------------------------------------------------------------------------------- /example.py: -------------------------------------------------------------------------------- 1 | import os 2 | from schema_engine import SchemaEngine 3 | from sqlalchemy import create_engine 4 | 5 | # 1.connect to the database engine 6 | db_name= 'aan_1' 7 | db_path = f'./{db_name}.sqlite' 8 | abs_path = os.path.abspath(db_path) 9 | assert os.path.exists(abs_path) 10 | db_engine = create_engine(f'sqlite:///{abs_path}') 11 | 12 | # 2.Construct M-Schema 13 | schema_engine = SchemaEngine(engine=db_engine, db_name=db_name) 14 | mschema = schema_engine.mschema 15 | mschema_str = mschema.to_mschema() 16 | print(mschema_str) 17 | mschema.save(f'./{db_name}.json') 18 | 19 | # 3.Use for Text-to-SQL 20 | dialect = db_engine.dialect.name 21 | question = '' 22 | evidence = '' 23 | prompt = """You are now a {dialect} data analyst, and you are given a database schema as follows: 24 | 25 | 【Schema】 26 | {db_schema} 27 | 28 | 【Question】 29 | {question} 30 | 31 | 【Evidence】 32 | {evidence} 33 | 34 | Please read and understand the database schema carefully, and generate an executable SQL based on the user's question and evidence. The generated SQL is protected by ```sql and ```. 35 | """.format(dialect=dialect, question=question, db_schema=mschema_str, evidence=evidence) 36 | 37 | # Replace the function call_llm() with your own function or method to interact with a LLM API. 38 | # response = call_llm(prompt) 39 | -------------------------------------------------------------------------------- /m_schema.py: -------------------------------------------------------------------------------- 1 | from utils import examples_to_str, read_json, write_json 2 | from typing import Any, Dict, Iterable, List, Optional, Tuple, Union 3 | 4 | 5 | class MSchema: 6 | def __init__(self, db_id: str = 'Anonymous', schema: Optional[str] = None): 7 | self.db_id = db_id 8 | self.schema = schema 9 | self.tables = {} 10 | self.foreign_keys = [] 11 | 12 | def add_table(self, name, fields={}, comment=None): 13 | self.tables[name] = {"fields": fields.copy(), 'examples': [], 'comment': comment} 14 | 15 | def add_field(self, table_name: str, field_name: str, field_type: str = "", 16 | primary_key: bool = False, nullable: bool = True, default: Any = None, 17 | autoincrement: bool = False, comment: str = "", examples: list = [], **kwargs): 18 | self.tables[table_name]["fields"][field_name] = { 19 | "type": field_type, 20 | "primary_key": primary_key, 21 | "nullable": nullable, 22 | "default": default if default is None else f'{default}', 23 | "autoincrement": autoincrement, 24 | "comment": comment, 25 | "examples": examples.copy(), 26 | **kwargs} 27 | 28 | def add_foreign_key(self, table_name, field_name, ref_schema, ref_table_name, ref_field_name): 29 | self.foreign_keys.append([table_name, field_name, ref_schema, ref_table_name, ref_field_name]) 30 | 31 | def get_field_type(self, field_type, simple_mode=True)->str: 32 | if not simple_mode: 33 | return field_type 34 | else: 35 | return field_type.split("(")[0] 36 | 37 | def has_table(self, table_name: str) -> bool: 38 | if table_name in self.tables.keys(): 39 | return True 40 | else: 41 | return False 42 | 43 | def has_column(self, table_name: str, field_name: str) -> bool: 44 | if self.has_table(table_name): 45 | if field_name in self.tables[table_name]["fields"].keys(): 46 | return True 47 | else: 48 | return False 49 | else: 50 | return False 51 | 52 | def get_field_info(self, table_name: str, field_name: str) -> Dict: 53 | try: 54 | return self.tables[table_name]['fields'][field_name] 55 | except: 56 | return {} 57 | 58 | def single_table_mschema(self, table_name: str, selected_columns: List = None, 59 | example_num=3, show_type_detail=False) -> str: 60 | table_info = self.tables.get(table_name, {}) 61 | output = [] 62 | table_comment = table_info.get('comment', '') 63 | if table_comment is not None and table_comment != 'None' and len(table_comment) > 0: 64 | if self.schema is not None and len(self.schema) > 0: 65 | output.append(f"# Table: {self.schema}.{table_name}, {table_comment}") 66 | else: 67 | output.append(f"# Table: {table_name}, {table_comment}") 68 | else: 69 | if self.schema is not None and len(self.schema) > 0: 70 | output.append(f"# Table: {self.schema}.{table_name}") 71 | else: 72 | output.append(f"# Table: {table_name}") 73 | 74 | field_lines = [] 75 | # 处理表中的每一个字段 76 | for field_name, field_info in table_info['fields'].items(): 77 | if selected_columns is not None and field_name.lower() not in selected_columns: 78 | continue 79 | 80 | raw_type = self.get_field_type(field_info['type'], not show_type_detail) 81 | field_line = f"({field_name}:{raw_type.upper()}" 82 | if field_info['comment'] != '': 83 | field_line += f", {field_info['comment'].strip()}" 84 | else: 85 | pass 86 | 87 | ## 打上主键标识 88 | is_primary_key = field_info.get('primary_key', False) 89 | if is_primary_key: 90 | field_line += f", Primary Key" 91 | 92 | # 如果有示例，添加上 93 | if len(field_info.get('examples', [])) > 0 and example_num > 0: 94 | examples = field_info['examples'] 95 | examples = [s for s in examples if s is not None] 96 | examples = examples_to_str(examples) 97 | if len(examples) > example_num: 98 | examples = examples[:example_num] 99 | 100 | if raw_type in ['DATE', 'TIME', 'DATETIME', 'TIMESTAMP']: 101 | examples = [examples[0]] 102 | elif len(examples) > 0 and max([len(s) for s in examples]) > 20: 103 | if max([len(s) for s in examples]) > 50: 104 | examples = [] 105 | else: 106 | examples = [examples[0]] 107 | else: 108 | pass 109 | if len(examples) > 0: 110 | example_str = ', '.join([str(example) for example in examples]) 111 | field_line += f", Examples: [{example_str}]" 112 | else: 113 | pass 114 | else: 115 | field_line += "" 116 | field_line += ")" 117 | 118 | field_lines.append(field_line) 119 | output.append('[') 120 | output.append(',\n'.join(field_lines)) 121 | output.append(']') 122 | 123 | return '\n'.join(output) 124 | 125 | def to_mschema(self, selected_tables: List = None, selected_columns: List = None, 126 | example_num=3, show_type_detail=False) -> str: 127 | """ 128 | convert to a MSchema string. 129 | selected_tables: 默认为None，表示选择所有的表 130 | selected_columns: 默认为None，表示所有列全选，格式['table_name.column_name'] 131 | """ 132 | output = [] 133 | 134 | output.append(f"【DB_ID】 {self.db_id}") 135 | output.append(f"【Schema】") 136 | 137 | if selected_tables is not None: 138 | selected_tables = [s.lower() for s in selected_tables] 139 | if selected_columns is not None: 140 | selected_columns = [s.lower() for s in selected_columns] 141 | selected_tables = [s.split('.')[0].lower() for s in selected_columns] 142 | 143 | # 依次处理每一个表 144 | for table_name, table_info in self.tables.items(): 145 | if selected_tables is None or table_name.lower() in selected_tables: 146 | cur_table_type = table_info.get('type', 'table') 147 | column_names = list(table_info['fields'].keys()) 148 | if selected_columns is not None: 149 | cur_selected_columns = [c.lower() for c in column_names if f"{table_name}.{c}".lower() in selected_columns] 150 | else: 151 | cur_selected_columns = selected_columns 152 | output.append(self.single_table_mschema(table_name, cur_selected_columns, example_num, show_type_detail)) 153 | 154 | # 添加外键信息，选择table_type为view时不展示外键 155 | if self.foreign_keys: 156 | output.append("【Foreign keys】") 157 | for fk in self.foreign_keys: 158 | ref_schema = fk[2] 159 | table1, column1, _, table2, column2 = fk 160 | if selected_tables is None or \ 161 | (table1.lower() in selected_tables and table2.lower() in selected_tables): 162 | if ref_schema == self.schema: 163 | output.append(f"{fk[0]}.{fk[1]}={fk[3]}.{fk[4]}") 164 | 165 | return '\n'.join(output) 166 | 167 | def dump(self): 168 | schema_dict = { 169 | "db_id": self.db_id, 170 | "schema": self.schema, 171 | "tables": self.tables, 172 | "foreign_keys": self.foreign_keys 173 | } 174 | return schema_dict 175 | 176 | def save(self, file_path: str): 177 | schema_dict = self.dump() 178 | write_json(file_path, schema_dict) 179 | 180 | def load(self, file_path: str): 181 | data = read_json(file_path) 182 | self.db_id = data.get("db_id", "Anonymous") 183 | self.schema = data.get("schema", None) 184 | self.tables = data.get("tables", {}) 185 | self.foreign_keys = data.get("foreign_keys", []) 186 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | llama-index 2 | numpy 3 | sqlalchemy 4 | -------------------------------------------------------------------------------- /schema_engine.py: -------------------------------------------------------------------------------- 1 | import json, os 2 | from typing import Any, Dict, Iterable, List, Optional, Tuple, Union 3 | from sqlalchemy import create_engine, MetaData, Table, Column, String, Integer, select, text 4 | from sqlalchemy.engine import Engine 5 | from llama_index.core import SQLDatabase 6 | from utils import read_json, write_json, save_raw_text, examples_to_str 7 | from m_schema import MSchema 8 | 9 | 10 | class SchemaEngine(SQLDatabase): 11 | def __init__(self, engine: Engine, schema: Optional[str] = None, metadata: Optional[MetaData] = None, 12 | ignore_tables: Optional[List[str]] = None, include_tables: Optional[List[str]] = None, 13 | sample_rows_in_table_info: int = 3, indexes_in_table_info: bool = False, 14 | custom_table_info: Optional[dict] = None, view_support: bool = False, max_string_length: int = 300, 15 | mschema: Optional[MSchema] = None, db_name: Optional[str] = ''): 16 | super().__init__(engine, schema, metadata, ignore_tables, include_tables, sample_rows_in_table_info, 17 | indexes_in_table_info, custom_table_info, view_support, max_string_length) 18 | 19 | self._db_name = db_name 20 | # Dictionary to store table names and their corresponding schema 21 | self._tables_schemas: Dict[str, str] = {} 22 | 23 | # If a schema is specified, filter by that schema and store that value for every table. 24 | if schema: 25 | self._usable_tables = [ 26 | table_name for table_name in self._usable_tables 27 | if self._inspector.has_table(table_name, schema) 28 | ] 29 | for table_name in self._usable_tables: 30 | self._tables_schemas[table_name] = schema 31 | else: 32 | all_tables = [] 33 | # Iterate through all available schemas 34 | for s in self.get_schema_names(): 35 | tables = self._inspector.get_table_names(schema=s) 36 | all_tables.extend(tables) 37 | for table in tables: 38 | self._tables_schemas[table] = s 39 | self._usable_tables = all_tables 40 | 41 | self._dialect = engine.dialect.name 42 | if mschema is not None: 43 | self._mschema = mschema 44 | else: 45 | self._mschema = MSchema(db_id=db_name, schema=schema) 46 | self.init_mschema() 47 | 48 | @property 49 | def mschema(self) -> MSchema: 50 | """Return M-Schema""" 51 | return self._mschema 52 | 53 | def get_pk_constraint(self, table_name: str) -> Dict: 54 | return self._inspector.get_pk_constraint(table_name, self._tables_schemas[table_name] )['constrained_columns'] 55 | 56 | def get_table_comment(self, table_name: str): 57 | try: 58 | return self._inspector.get_table_comment(table_name, self._tables_schemas[table_name])['text'] 59 | except: # sqlite does not support comments 60 | return '' 61 | 62 | def default_schema_name(self) -> Optional[str]: 63 | return self._inspector.default_schema_name 64 | 65 | def get_schema_names(self) -> List[str]: 66 | return self._inspector.get_schema_names() 67 | 68 | def get_foreign_keys(self, table_name: str): 69 | return self._inspector.get_foreign_keys(table_name, self._tables_schemas[table_name]) 70 | 71 | def get_unique_constraints(self, table_name: str): 72 | return self._inspector.get_unique_constraints(table_name, self._tables_schemas[table_name]) 73 | 74 | def fectch_distinct_values(self, table_name: str, column_name: str, max_num: int = 5): 75 | table = Table(table_name, self.metadata_obj, autoload_with=self._engine, schema=self._tables_schemas[table_name]) 76 | # Construct SELECT DISTINCT query 77 | query = select(table.c[column_name]).distinct().limit(max_num) 78 | values = [] 79 | with self._engine.connect() as connection: 80 | result = connection.execute(query) 81 | distinct_values = result.fetchall() 82 | for value in distinct_values: 83 | if value[0] is not None and value[0] != '': 84 | values.append(value[0]) 85 | return values 86 | 87 | def init_mschema(self): 88 | for table_name in self._usable_tables: 89 | table_comment = self.get_table_comment(table_name) 90 | table_comment = '' if table_comment is None else table_comment.strip() 91 | table_with_schema = self._tables_schemas[table_name] + '.' + table_name 92 | self._mschema.add_table(table_with_schema, fields={}, comment=table_comment) 93 | pks = self.get_pk_constraint(table_name) 94 | 95 | fks = self.get_foreign_keys(table_name) 96 | for fk in fks: 97 | referred_schema = fk['referred_schema'] 98 | for c, r in zip(fk['constrained_columns'], fk['referred_columns']): 99 | self._mschema.add_foreign_key(table_with_schema, c, referred_schema, fk['referred_table'], r) 100 | 101 | fields = self._inspector.get_columns(table_name, schema=self._tables_schemas[table_name]) 102 | for field in fields: 103 | field_type = f"{field['type']!s}" 104 | field_name = field['name'] 105 | primary_key = field_name in pks 106 | field_comment = field.get("comment", None) 107 | field_comment = "" if field_comment is None else field_comment.strip() 108 | autoincrement = field.get('autoincrement', False) 109 | default = field.get('default', None) 110 | if default is not None: 111 | default = f'{default}' 112 | 113 | try: 114 | examples = self.fectch_distinct_values(table_name, field_name, 5) 115 | except: 116 | examples = [] 117 | examples = examples_to_str(examples) 118 | 119 | self._mschema.add_field( 120 | table_with_schema, field_name, field_type=field_type, primary_key=primary_key, 121 | nullable=field['nullable'], default=default, autoincrement=autoincrement, 122 | comment=field_comment, examples=examples 123 | ) 124 | -------------------------------------------------------------------------------- /schema_representation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/XGenerationLab/M-Schema/e8e49054d17cafa4255ac96b80cd3ca6ecc4ab31/schema_representation.png -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- 1 | import datetime 2 | import decimal 3 | import re 4 | import json 5 | 6 | 7 | def write_json(path, data): 8 | with open(path, 'w', encoding='utf-8') as f: 9 | json.dump(data, f, ensure_ascii=False, indent=2) 10 | 11 | 12 | def read_json(path): 13 | with open(path, 'r', encoding='utf-8') as f: 14 | data = json.load(f) 15 | return data 16 | 17 | 18 | def read_text(filename)->str: 19 | data = [] 20 | with open(filename, 'r', encoding='utf-8') as file: 21 | for line in file.readlines(): 22 | line = line.strip() 23 | data.append(line) 24 | return data 25 | 26 | 27 | def save_raw_text(filename, content): 28 | with open(filename, 'w', encoding='utf-8') as file: 29 | file.write(content) 30 | 31 | 32 | def read_map_file(path): 33 | data = {} 34 | with open(path, 'r', encoding='utf-8') as f: 35 | for line in f.readlines(): 36 | line = line.strip().split('\t') 37 | data[line[0]] = line[1].split('、') 38 | data[line[0]].append(line[0]) 39 | return data 40 | 41 | 42 | def save_json(target_file,js,indent=4): 43 | with open(target_file, 'w', encoding='utf-8') as f: 44 | json.dump(js, f, ensure_ascii=False, indent=indent) 45 | 46 | def is_email(string): 47 | pattern = r'^[\w\.-]+@[\w\.-]+\.\w+$' 48 | match = re.match(pattern, string) 49 | if match: 50 | return True 51 | else: 52 | return False 53 | 54 | 55 | def examples_to_str(examples: list) -> list[str]: 56 | """ 57 | from examples to a list of str 58 | """ 59 | values = examples 60 | for i in range(len(values)): 61 | if isinstance(values[i], datetime.date): 62 | values = [values[i]] 63 | break 64 | elif isinstance(values[i], datetime.datetime): 65 | values = [values[i]] 66 | break 67 | elif isinstance(values[i], decimal.Decimal): 68 | values[i] = str(float(values[i])) 69 | elif is_email(str(values[i])): 70 | values = [] 71 | break 72 | elif 'http://' in str(values[i]) or 'https://' in str(values[i]): 73 | values = [] 74 | break 75 | elif values[i] is not None and not isinstance(values[i], str): 76 | pass 77 | elif values[i] is not None and '.com' in values[i]: 78 | pass 79 | 80 | return [str(v) for v in values if v is not None and len(str(v)) > 0] 81 | 82 | --------------------------------------------------------------------------------