cnhkmcp 2.2.0__py3-none-any.whl → 2.3.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- cnhkmcp/__init__.py +1 -1
- cnhkmcp/untracked/AI/321/206/320/261/320/234/321/211/320/255/320/262/321/206/320/237/320/242/321/204/342/225/227/342/225/242/README.md +1 -1
- cnhkmcp/untracked/AI/321/206/320/261/320/234/321/211/320/255/320/262/321/206/320/237/320/242/321/204/342/225/227/342/225/242/config.json +2 -2
- cnhkmcp/untracked/AI/321/206/320/261/320/234/321/211/320/255/320/262/321/206/320/237/320/242/321/204/342/225/227/342/225/242/main.py +1 -1
- cnhkmcp/untracked/AI/321/206/320/261/320/234/321/211/320/255/320/262/321/206/320/237/320/242/321/204/342/225/227/342/225/242/vector_db/chroma.sqlite3 +0 -0
- cnhkmcp/untracked/APP/Tranformer/Transformer.py +2 -2
- cnhkmcp/untracked/APP/Tranformer/transformer_config.json +1 -1
- cnhkmcp/untracked/APP/blueprints/feature_engineering.py +2 -2
- cnhkmcp/untracked/APP/blueprints/inspiration_house.py +4 -4
- cnhkmcp/untracked/APP/blueprints/paper_analysis.py +3 -3
- cnhkmcp/untracked/APP/give_me_idea/BRAIN_Alpha_Template_Expert_SystemPrompt.md +34 -73
- cnhkmcp/untracked/APP/give_me_idea/alpha_data_specific_template_master.py +2 -2
- cnhkmcp/untracked/APP/give_me_idea/what_is_Alpha_template.md +366 -1
- cnhkmcp/untracked/APP/simulator/wqb20260130130030.log +210 -0
- cnhkmcp/untracked/APP/simulator/wqb20260130131757.log +104 -0
- cnhkmcp/untracked/APP/simulator/wqb20260130172245.log +70 -0
- cnhkmcp/untracked/APP/static/inspiration.js +350 -14
- cnhkmcp/untracked/APP/templates/index.html +18 -3
- cnhkmcp/untracked/APP/templates/transformer_web.html +1 -1
- cnhkmcp/untracked/APP/trailSomeAlphas/README.md +38 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/ace.log +66 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/enhance_template.py +588 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/requirements.txt +3 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/run_pipeline.py +1051 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/run_pipeline_step_by_step.ipynb +5258 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/OUTPUT_TEMPLATE.md +325 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/SKILL.md +503 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/examples.md +244 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/output_report/ASI_delay1_analyst11_ideas.md +285 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/output_report/GLB_delay1_fundamental72_ideas.md +362 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-data-feature-engineering/reference.md +399 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/SKILL.md +40 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/config.json +6 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709385783386000.json +388 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709386274840400.json +131 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709386838244700.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709387369198500.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709387908905800.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709388486243600.json +240 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709389024058600.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709389549608700.json +41 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709390068714000.json +110 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709390591996900.json +36 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709391129137100.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709391691643500.json +41 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709392192099200.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709392703423500.json +46 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769709393213729400.json +246 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710186683932500.json +388 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710187165414300.json +131 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710187665211700.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710188149193400.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710188667627400.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710189220822000.json +240 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710189726189500.json +1926 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710190248066100.json +41 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710190768298700.json +110 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710191282588100.json +36 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710191838960900.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710192396688000.json +41 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710192941922400.json +31 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710193473524600.json +46 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710194001961200.json +246 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710420975888800.json +46 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710421647590100.json +196 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710422131378500.json +5 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710422644184400.json +196 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710423702350600.json +196 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_1_idea_1769710424244661800.json +5 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/analyst11_ASI_delay1.csv +211 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/analyst11_ASI_delay1/final_expressions.json +7062 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/final_expressions.json +138 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759441444909600.json +38 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759441920092000.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759442418767100.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759442902507600.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759443377036200.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759443845377000.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759444313546700.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759444784598600.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759445274311200.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759445747421700.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759446222137800.json +22 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759446686222600.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759447154698500.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759447629677000.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759448102331200.json +10 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_1_idea_1769759448573382000.json +14 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/data/fundamental72_GLB_delay1/fundamental72_GLB_delay1.csv +330 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/ace.log +3 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/ace_lib.py +1514 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/fetch_dataset.py +119 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/helpful_functions.py +180 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/implement_idea.py +236 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/merge_expression_list.py +90 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/brain-feature-implementation/scripts/parsetab.py +60 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/template_final_enhance/op/321/206/320/220/342/225/227/321/207/342/225/227/320/243.md +434 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/template_final_enhance/sample_prompt.md +62 -0
- cnhkmcp/untracked/APP/trailSomeAlphas/skills/template_final_enhance//321/205/320/235/320/245/321/205/320/253/320/260/321/205/320/275/320/240/321/206/320/220/320/255/321/210/320/220/320/223/321/211/320/220/342/225/227/321/210/342/225/233/320/241/321/211/320/243/342/225/233.md +354 -0
- cnhkmcp/untracked/APP/usage.md +2 -2
- cnhkmcp/untracked/APP//321/210/342/224/220/320/240/321/210/320/261/320/234/321/206/320/231/320/243/321/205/342/225/235/320/220/321/206/320/230/320/241.py +400 -9
- cnhkmcp/untracked/back_up/platform_functions.py +2 -2
- cnhkmcp/untracked/mcp/321/206/320/246/320/227/321/204/342/225/227/342/225/242/321/210/320/276/342/225/221/321/205/320/255/320/253/321/207/320/231/320/2302_/321/205/320/266/320/222/321/206/320/256/320/254/321/205/320/236/320/257/321/207/320/231/320/230/321/205/320/240/320/277/321/205/320/232/320/270/321/204/342/225/225/320/235/321/204/342/225/221/320/226/321/206/342/225/241/320/237/321/210/320/267/320/230/321/205/320/251/320/270/321/205/342/226/221/342/226/222/321/210/320/277/320/245/321/210/342/224/220/320/251/321/204/342/225/225/320/272/platform_functions.py +2 -2
- cnhkmcp/untracked/platform_functions.py +2 -2
- cnhkmcp/untracked/skills/alpha-expression-verifier/scripts/validator.py +889 -0
- cnhkmcp/untracked/skills/brain-feature-implementation/scripts/implement_idea.py +4 -3
- cnhkmcp/untracked/skills/brain-improve-alpha-performance/arXiv_API_Tool_Manual.md +490 -0
- cnhkmcp/untracked/skills/brain-improve-alpha-performance/reference.md +1 -1
- cnhkmcp/untracked/skills/brain-improve-alpha-performance/scripts/arxiv_api.py +229 -0
- cnhkmcp/untracked//321/211/320/225/320/235/321/207/342/225/234/320/276/321/205/320/231/320/235/321/210/342/224/220/320/240/321/210/320/261/320/234/321/206/320/230/320/241_/321/205/320/276/320/231/321/210/320/263/320/225/321/205/342/224/220/320/225/321/210/320/266/320/221/321/204/342/225/233/320/255/321/210/342/225/241/320/246/321/205/320/234/320/225.py +35 -11
- cnhkmcp/vector_db/_manifest.json +1 -0
- cnhkmcp/vector_db/_meta.json +1 -0
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/METADATA +1 -1
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/RECORD +121 -33
- /cnhkmcp/untracked/{skills/expression_verifier → APP/trailSomeAlphas/skills/brain-feature-implementation}/scripts/validator.py +0 -0
- /cnhkmcp/untracked/skills/{expression_verifier → alpha-expression-verifier}/SKILL.md +0 -0
- /cnhkmcp/untracked/skills/{expression_verifier → alpha-expression-verifier}/scripts/verify_expr.py +0 -0
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/WHEEL +0 -0
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/entry_points.txt +0 -0
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/licenses/LICENSE +0 -0
- {cnhkmcp-2.2.0.dist-info → cnhkmcp-2.3.1.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,889 @@
|
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
# -*- coding: utf-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
表达式验证器 - 使用抽象语法树验证字符串表达式格式是否正确
|
|
5
|
+
|
|
6
|
+
本模块实现了一个能够检测字符串表达式格式是否正确的系统,基于PLY(Python Lex-Yacc)
|
|
7
|
+
构建词法分析器和语法分析器,识别表达式中的操作符、函数和字段,并验证其格式正确性。
|
|
8
|
+
"""
|
|
9
|
+
|
|
10
|
+
import re
|
|
11
|
+
import sys
|
|
12
|
+
import json
|
|
13
|
+
import os
|
|
14
|
+
from typing import List, Dict, Any, Optional, Tuple
|
|
15
|
+
|
|
16
|
+
# 尝试导入PLY库,如果不存在则提供安装提示
|
|
17
|
+
try:
|
|
18
|
+
import ply.lex as lex
|
|
19
|
+
import ply.yacc as yacc
|
|
20
|
+
except ImportError:
|
|
21
|
+
print("错误: 需要安装PLY库。请运行 'pip install ply' 来安装。")
|
|
22
|
+
sys.exit(1)
|
|
23
|
+
|
|
24
|
+
# 1. 定义支持的操作符和函数
|
|
25
|
+
supported_functions = {
|
|
26
|
+
# Group 类别函数
|
|
27
|
+
'group_min': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
28
|
+
'group_mean': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression']},
|
|
29
|
+
'group_median': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
30
|
+
'group_max': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
31
|
+
'group_rank': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
32
|
+
'group_vector_proj': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'category']},
|
|
33
|
+
'group_normalize': {'min_args': 2, 'max_args': 5, 'arg_types': ['expression', 'category', 'expression', 'expression', 'expression']},
|
|
34
|
+
'group_extra': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'category']},
|
|
35
|
+
'group_backfill': {'min_args': 3, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'expression'], 'param_names': ['x', 'cat', 'days', 'std']},
|
|
36
|
+
'group_scale': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
37
|
+
'group_count': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
38
|
+
'group_zscore': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
39
|
+
'group_std_dev': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
40
|
+
'group_sum': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
41
|
+
'group_neutralize': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'category']},
|
|
42
|
+
'group_multi_regression': {'min_args': 4, 'max_args': 9, 'arg_types': ['expression'] * 9},
|
|
43
|
+
'group_cartesian_product': {'min_args': 2, 'max_args': 2, 'arg_types': ['category', 'category']},
|
|
44
|
+
'combo_a': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression']},
|
|
45
|
+
|
|
46
|
+
# Transformational 类别函数
|
|
47
|
+
'right_tail': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
48
|
+
'bucket': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # 第二个参数可以是string类型的range参数
|
|
49
|
+
'tail': {'min_args': 1, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'expression']},
|
|
50
|
+
'left_tail': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
51
|
+
'trade_when': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression']},
|
|
52
|
+
'generate_stats': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
53
|
+
|
|
54
|
+
# Cross Sectional 类别函数
|
|
55
|
+
'winsorize': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['x', 'std']},
|
|
56
|
+
'rank': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
57
|
+
'regression_proj': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
58
|
+
'vector_neut': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
59
|
+
'regression_neut': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
60
|
+
'multi_regression': {'min_args': 2, 'max_args': 100, 'arg_types': ['expression'] * 100}, # 支持多个自变量
|
|
61
|
+
|
|
62
|
+
# Time Series 类别函数
|
|
63
|
+
'ts_std_dev': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
64
|
+
'ts_mean': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
65
|
+
'ts_delay': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
66
|
+
'ts_corr': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
67
|
+
'ts_zscore': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
68
|
+
'ts_returns': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number'], 'param_names': ['x', 'd', 'mode']},
|
|
69
|
+
'ts_product': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
70
|
+
'ts_backfill': {'min_args': 2, 'max_args': 4, 'arg_types': ['expression', 'number', 'number', 'string']},
|
|
71
|
+
'days_from_last_change': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
72
|
+
'last_diff_value': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
73
|
+
'ts_scale': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number']},
|
|
74
|
+
'ts_entropy': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number'], 'param_names': ['x', 'd', 'buckets']},
|
|
75
|
+
'ts_step': {'min_args': 1, 'max_args': 1, 'arg_types': ['number']},
|
|
76
|
+
'ts_sum': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
77
|
+
'ts_co_kurtosis': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
78
|
+
'inst_tvr': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
79
|
+
'ts_decay_exp_window': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number'], 'param_names': ['x', 'd', 'factor']},
|
|
80
|
+
'ts_av_diff': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
81
|
+
'ts_kurtosis': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
82
|
+
'ts_min_max_diff': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number']},
|
|
83
|
+
'ts_arg_max': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
84
|
+
'ts_max': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
85
|
+
'ts_min_max_cps': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number']},
|
|
86
|
+
'ts_rank': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number']},
|
|
87
|
+
'ts_ir': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
88
|
+
'ts_theilsen': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
89
|
+
'hump_decay': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
90
|
+
'ts_weighted_decay': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
91
|
+
'ts_quantile': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'string']},
|
|
92
|
+
'ts_min': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
93
|
+
'ts_count_nans': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
94
|
+
'ts_covariance': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
95
|
+
'ts_co_skewness': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
96
|
+
'ts_min_diff': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
97
|
+
'ts_decay_linear': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'boolean']},
|
|
98
|
+
'jump_decay': {'min_args': 2, 'max_args': 5, 'arg_types': ['expression', 'number', 'expression', 'number', 'number'], 'param_names': ['x', 'd', 'stddev', 'sensitivity', 'force']},
|
|
99
|
+
'ts_moment': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'number', 'number'], 'param_names': ['x', 'd', 'k']},
|
|
100
|
+
'ts_arg_min': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
101
|
+
'ts_regression': {'min_args': 3, 'max_args': 5, 'arg_types': ['expression', 'expression', 'number', 'number', 'number'], 'param_names': ['y', 'x', 'd', 'lag', 'rettype']},
|
|
102
|
+
'ts_skewness': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
103
|
+
'ts_max_diff': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
104
|
+
'kth_element': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'number', 'number']},
|
|
105
|
+
'hump': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'number'], 'param_names': ['x', 'hump']},
|
|
106
|
+
'ts_median': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
107
|
+
'ts_delta': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
108
|
+
'ts_poly_regression': {'min_args': 3, 'max_args': 4, 'arg_types': ['expression', 'expression', 'number', 'number']},
|
|
109
|
+
'ts_target_tvr_decay': {'min_args': 1, 'max_args': 4, 'arg_types': ['expression', 'number', 'number', 'number'], 'param_names': ['x', 'lambda_min', 'lambda_max', 'target_tvr']},
|
|
110
|
+
'ts_target_tvr_delta_limit': {'min_args': 2, 'max_args': 5, 'arg_types': ['expression', 'expression', 'number', 'number', 'number']},
|
|
111
|
+
'ts_target_tvr_hump': {'min_args': 1, 'max_args': 4, 'arg_types': ['expression', 'number', 'number', 'number']},
|
|
112
|
+
'ts_delta_limit': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number']},
|
|
113
|
+
|
|
114
|
+
# Special 类别函数
|
|
115
|
+
'inst_pnl': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
116
|
+
'self_corr': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
117
|
+
'in': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # 注意:这是关键字
|
|
118
|
+
'universe_size': {'min_args': 0, 'max_args': 0, 'arg_types': []},
|
|
119
|
+
|
|
120
|
+
# Missing functions from operators.py
|
|
121
|
+
'quantile': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'driver', 'sigma']}, # quantile(x, driver = gaussian, sigma = 1.0)
|
|
122
|
+
'normalize': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'boolean', 'number']}, # normalize(x, useStd = false, limit = 0.0)
|
|
123
|
+
'zscore': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']}, # zscore(x)
|
|
124
|
+
|
|
125
|
+
# Logical 类别函数
|
|
126
|
+
'or': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # 注意:这是关键字
|
|
127
|
+
'and': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # 注意:这是关键字
|
|
128
|
+
'not': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']}, # 注意:这是关键字
|
|
129
|
+
'is_nan': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
130
|
+
'is_not_nan': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
131
|
+
'less': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
132
|
+
'equal': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
133
|
+
'greater': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
134
|
+
'is_finite': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
135
|
+
'if_else': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression']},
|
|
136
|
+
'not_equal': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
137
|
+
'less_equal': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
138
|
+
'greater_equal': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
139
|
+
|
|
140
|
+
# Vector 类别函数
|
|
141
|
+
'vec_kurtosis': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
142
|
+
'vec_min': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
143
|
+
'vec_count': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
144
|
+
'vec_sum': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
145
|
+
'vec_skewness': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
146
|
+
'vec_max': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
147
|
+
'vec_avg': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
148
|
+
'vec_range': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
149
|
+
'vec_choose': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number'], 'param_names': ['x', 'nth']},
|
|
150
|
+
'vec_powersum': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'number'], 'param_names': ['x', 'constant']},
|
|
151
|
+
'vec_stddev': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
152
|
+
'vec_percentage': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'number'], 'param_names': ['x', 'percentage']},
|
|
153
|
+
'vec_ir': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
154
|
+
'vec_norm': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
155
|
+
'ts_percentage': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'number', 'number'], 'param_names': ['x', 'd', 'percentage']},
|
|
156
|
+
'signed_power': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
157
|
+
'ts_product': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number']},
|
|
158
|
+
|
|
159
|
+
# Additional functions from test cases
|
|
160
|
+
'rank_by_side': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'number', 'number'], 'param_names': ['x', 'rate', 'scale']},
|
|
161
|
+
'log_diff': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
162
|
+
'nan_mask': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']},
|
|
163
|
+
'ts_partial_corr': {'min_args': 4, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'number']},
|
|
164
|
+
'ts_triple_corr': {'min_args': 4, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'number']},
|
|
165
|
+
'clamp': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'lower', 'upper']},
|
|
166
|
+
'keep': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number'], 'param_names': ['x', 'condition', 'period']},
|
|
167
|
+
'replace': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'target', 'dest']},
|
|
168
|
+
'filter': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'h', 't']},
|
|
169
|
+
'one_side': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'string'], 'param_names': ['x', 'side']},
|
|
170
|
+
'scale_down': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'number'], 'param_names': ['x', 'constant']},
|
|
171
|
+
|
|
172
|
+
# Arithmetic 类别函数
|
|
173
|
+
'add': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'boolean']}, # add(x, y, filter=false)
|
|
174
|
+
'multiply': {'min_args': 2, 'max_args': 100, 'arg_types': ['expression'] * 99 + ['boolean'], 'param_names': ['x', 'y', 'filter']}, # multiply(x, y, ..., filter=false)
|
|
175
|
+
'sign': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
176
|
+
'subtract': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'boolean']}, # subtract(x, y, filter=false)
|
|
177
|
+
'pasteurize': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
178
|
+
'log': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
179
|
+
'purify': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
180
|
+
'arc_tan': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
181
|
+
'max': {'min_args': 2, 'max_args': 100, 'arg_types': ['expression'] * 100}, # max(x, y, ...)
|
|
182
|
+
'to_nan': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'boolean']}, # to_nan(x, value=0, reverse=false)
|
|
183
|
+
'abs': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
184
|
+
'sigmoid': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
185
|
+
'divide': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # divide(x, y)
|
|
186
|
+
'min': {'min_args': 2, 'max_args': 100, 'arg_types': ['expression'] * 100}, # min(x, y, ...)
|
|
187
|
+
'tanh': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
188
|
+
'nan_out': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'lower', 'upper']}, # nan_out(x, lower=0, upper=0)
|
|
189
|
+
'signed_power': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # signed_power(x, y)
|
|
190
|
+
'inverse': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
191
|
+
'round': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
192
|
+
'sqrt': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
193
|
+
's_log_1p': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
194
|
+
'reverse': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']}, # -x
|
|
195
|
+
'power': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression']}, # power(x, y)
|
|
196
|
+
'densify': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
197
|
+
'floor': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression']},
|
|
198
|
+
# Appended missing operators
|
|
199
|
+
'arc_cos': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['x']},
|
|
200
|
+
'arc_sin': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['x']},
|
|
201
|
+
'ceiling': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['x']},
|
|
202
|
+
'exp': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['x']},
|
|
203
|
+
'fraction': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['x']},
|
|
204
|
+
'round_down': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['x', 'f']},
|
|
205
|
+
'is_not_finite': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
206
|
+
'negate': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
207
|
+
'ts_rank_gmean_amean_diff': {'min_args': 5, 'max_args': 5, 'arg_types': ['expression', 'expression', 'expression', 'expression', 'number'], 'param_names': ['input1', 'input2', 'input3', '...', 'd']},
|
|
208
|
+
'ts_vector_neut': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number'], 'param_names': ['x', 'y', 'd']},
|
|
209
|
+
'ts_vector_proj': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'number'], 'param_names': ['x', 'y', 'd']},
|
|
210
|
+
'scale': {'min_args': 1, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'expression'], 'param_names': ['x', 'scale', 'longscale', 'shortscale']},
|
|
211
|
+
'generalized_rank': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['open', 'm']},
|
|
212
|
+
'rank_gmean_amean_diff': {'min_args': 4, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'expression'], 'param_names': ['input1', 'input2', 'input3', '...']},
|
|
213
|
+
'truncate': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['x', 'maxPercent']},
|
|
214
|
+
'vector_proj': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['x', 'y']},
|
|
215
|
+
'vec_filter': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['vec', 'value']},
|
|
216
|
+
'group_coalesce': {'min_args': 4, 'max_args': 4, 'arg_types': ['expression', 'expression', 'expression', 'expression'], 'param_names': ['original_group', 'group2', 'group3', '…']},
|
|
217
|
+
'group_percentage': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'category', 'expression'], 'param_names': ['x', 'group', 'percentage']},
|
|
218
|
+
'group_vector_neut': {'min_args': 3, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['x', 'y', 'g']},
|
|
219
|
+
'convert': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['x', 'mode']},
|
|
220
|
+
'reduce_avg': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['input', 'threshold']},
|
|
221
|
+
'reduce_choose': {'min_args': 2, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['input', 'nth', 'ignoreNan']},
|
|
222
|
+
'reduce_count': {'min_args': 2, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['input', 'threshold']},
|
|
223
|
+
'reduce_ir': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
224
|
+
'reduce_kurtosis': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
225
|
+
'reduce_max': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
226
|
+
'reduce_min': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
227
|
+
'reduce_norm': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
228
|
+
'reduce_percentage': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['input', 'percentage']},
|
|
229
|
+
'reduce_powersum': {'min_args': 1, 'max_args': 3, 'arg_types': ['expression', 'expression', 'expression'], 'param_names': ['input', 'constant', 'precise']},
|
|
230
|
+
'reduce_range': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
231
|
+
'reduce_skewness': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
232
|
+
'reduce_stddev': {'min_args': 1, 'max_args': 2, 'arg_types': ['expression', 'expression'], 'param_names': ['input', 'threshold']},
|
|
233
|
+
'reduce_sum': {'min_args': 1, 'max_args': 1, 'arg_types': ['expression'], 'param_names': ['input']},
|
|
234
|
+
}
|
|
235
|
+
|
|
236
|
+
# 2. 定义group类型字段
|
|
237
|
+
group_fields = {
|
|
238
|
+
'sector', 'subindustry', 'industry', 'exchange', 'country', 'market'
|
|
239
|
+
}
|
|
240
|
+
|
|
241
|
+
# 3. 有效类别集合
|
|
242
|
+
valid_categories = group_fields
|
|
243
|
+
|
|
244
|
+
# 4. 字段命名模式 - 只校验字段是不是数字字母下划线组成
|
|
245
|
+
field_patterns = [
|
|
246
|
+
re.compile(r'^[a-zA-Z0-9_]+$'), # 只允许数字、字母和下划线组成的字段名
|
|
247
|
+
]
|
|
248
|
+
|
|
249
|
+
# 4. 抽象语法树节点类型
|
|
250
|
+
class ASTNode:
|
|
251
|
+
"""抽象语法树节点基类"""
|
|
252
|
+
def __init__(self, node_type: str, children: Optional[List['ASTNode']] = None,
|
|
253
|
+
value: Optional[Any] = None, line: Optional[int] = None):
|
|
254
|
+
self.node_type = node_type # 'function', 'operator', 'field', 'number', 'expression'
|
|
255
|
+
self.children = children or []
|
|
256
|
+
self.value = value
|
|
257
|
+
self.line = line
|
|
258
|
+
|
|
259
|
+
def __str__(self) -> str:
|
|
260
|
+
return f"ASTNode({self.node_type}, {self.value}, line={self.line})"
|
|
261
|
+
|
|
262
|
+
def __repr__(self) -> str:
|
|
263
|
+
return self.__str__()
|
|
264
|
+
|
|
265
|
+
class ExpressionValidator:
|
|
266
|
+
"""表达式验证器类"""
|
|
267
|
+
|
|
268
|
+
def __init__(self):
|
|
269
|
+
"""初始化词法分析器和语法分析器"""
|
|
270
|
+
# 构建词法分析器
|
|
271
|
+
self.lexer = lex.lex(module=self, debug=False)
|
|
272
|
+
# 构建语法分析器
|
|
273
|
+
self.parser = yacc.yacc(module=self, debug=False)
|
|
274
|
+
# 错误信息存储
|
|
275
|
+
self.errors = []
|
|
276
|
+
|
|
277
|
+
# 词法分析器规则
|
|
278
|
+
tokens = ('FUNCTION', 'FIELD', 'NUMBER', 'LPAREN', 'RPAREN',
|
|
279
|
+
'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'COMMA', 'CATEGORY',
|
|
280
|
+
'EQUAL', 'ASSIGN', 'IDENTIFIER', 'STRING', 'GREATER', 'LESS', 'GREATEREQUAL', 'LESSEQUAL', 'NOTEQUAL', 'BOOLEAN')
|
|
281
|
+
|
|
282
|
+
# 忽略空白字符
|
|
283
|
+
t_ignore = ' \t\n'
|
|
284
|
+
|
|
285
|
+
# 操作符 - 注意顺序很重要,长的操作符要放在前面
|
|
286
|
+
t_PLUS = r'\+'
|
|
287
|
+
t_MINUS = r'-'
|
|
288
|
+
t_TIMES = r'\*'
|
|
289
|
+
t_DIVIDE = r'/'
|
|
290
|
+
t_LPAREN = r'\('
|
|
291
|
+
t_RPAREN = r'\)'
|
|
292
|
+
t_COMMA = r','
|
|
293
|
+
t_EQUAL = r'=='
|
|
294
|
+
t_NOTEQUAL = r'!='
|
|
295
|
+
t_GREATEREQUAL = r'>='
|
|
296
|
+
t_LESSEQUAL = r'<='
|
|
297
|
+
t_GREATER = r'>'
|
|
298
|
+
t_LESS = r'<'
|
|
299
|
+
t_ASSIGN = r'='
|
|
300
|
+
|
|
301
|
+
# 数字(整数和浮点数)
|
|
302
|
+
def t_NUMBER(self, t):
|
|
303
|
+
r'\d+\.?\d*'
|
|
304
|
+
if '.' in t.value:
|
|
305
|
+
t.value = float(t.value)
|
|
306
|
+
else:
|
|
307
|
+
t.value = int(t.value)
|
|
308
|
+
return t
|
|
309
|
+
|
|
310
|
+
# 字符串 - 需要放在所有其他标识符规则之前
|
|
311
|
+
def t_STRING(self, t):
|
|
312
|
+
r"'[^']*'|\"[^\"]*\""
|
|
313
|
+
# 去除引号
|
|
314
|
+
t.value = t.value[1:-1]
|
|
315
|
+
return t
|
|
316
|
+
|
|
317
|
+
# 函数和字段名
|
|
318
|
+
def t_IDENTIFIER(self, t):
|
|
319
|
+
r'[a-zA-Z_][a-zA-Z0-9_]*'
|
|
320
|
+
# 检查是否为布尔值
|
|
321
|
+
if t.value.lower() in {'true', 'false'}:
|
|
322
|
+
t.type = 'BOOLEAN'
|
|
323
|
+
t.value = t.value.lower() # 转换为小写以保持一致性
|
|
324
|
+
else:
|
|
325
|
+
# 查看当前token后面的字符,判断是否为参数名(后面跟着'=')
|
|
326
|
+
lexpos = t.lexpos
|
|
327
|
+
next_chars = ''
|
|
328
|
+
if lexpos + len(t.value) < len(t.lexer.lexdata):
|
|
329
|
+
# 查看当前token后面的字符,跳过空格
|
|
330
|
+
next_pos = lexpos + len(t.value)
|
|
331
|
+
while next_pos < len(t.lexer.lexdata) and t.lexer.lexdata[next_pos].isspace():
|
|
332
|
+
next_pos += 1
|
|
333
|
+
if next_pos < len(t.lexer.lexdata):
|
|
334
|
+
next_chars = t.lexer.lexdata[next_pos:next_pos+1]
|
|
335
|
+
|
|
336
|
+
# 如果后面跟着'=',则为参数名
|
|
337
|
+
if next_chars == '=':
|
|
338
|
+
t.type = 'IDENTIFIER'
|
|
339
|
+
# 如果后面跟着'(',则为函数名
|
|
340
|
+
elif next_chars == '(':
|
|
341
|
+
t.type = 'FUNCTION'
|
|
342
|
+
t.value = t.value.lower() # 转换为小写以保持一致性
|
|
343
|
+
# 检查是否为参数名(支持更多参数名)
|
|
344
|
+
elif t.value in {'std', 'k', 'lambda_min', 'lambda_max', 'target_tvr', 'range', 'buckets', 'lag', 'rettype', 'mode', 'nth', 'constant', 'percentage', 'driver', 'sigma', 'rate', 'scale', 'filter', 'lower', 'upper', 'target', 'dest', 'event', 'sensitivity', 'force', 'h', 't', 'period', 'stddev', 'factor', 'k', 'useStd', 'limit', 'gaussian', 'uniform', 'cauchy'}:
|
|
345
|
+
t.type = 'IDENTIFIER'
|
|
346
|
+
# 检查是否为函数名(不区分大小写)
|
|
347
|
+
elif t.value.lower() in supported_functions:
|
|
348
|
+
t.type = 'FUNCTION'
|
|
349
|
+
t.value = t.value.lower() # 转换为小写以保持一致性
|
|
350
|
+
# 检查是否为有效类别
|
|
351
|
+
elif t.value in valid_categories:
|
|
352
|
+
t.type = 'CATEGORY'
|
|
353
|
+
# 检查是否为字段名
|
|
354
|
+
elif self._is_valid_field(t.value):
|
|
355
|
+
t.type = 'FIELD'
|
|
356
|
+
else:
|
|
357
|
+
# 其他标识符,保留为IDENTIFIER类型
|
|
358
|
+
t.type = 'IDENTIFIER'
|
|
359
|
+
return t
|
|
360
|
+
|
|
361
|
+
# 行号跟踪
|
|
362
|
+
def t_newline(self, t):
|
|
363
|
+
r'\n+'
|
|
364
|
+
t.lexer.lineno += len(t.value)
|
|
365
|
+
|
|
366
|
+
# 错误处理
|
|
367
|
+
def t_error(self, t):
|
|
368
|
+
if t:
|
|
369
|
+
# 检查是否为非法字符
|
|
370
|
+
if not re.match(r'[a-zA-Z0-9_\+\-\*/\(\)\,\s=<>!]', t.value[0]):
|
|
371
|
+
# 这是一个非法字符
|
|
372
|
+
self.errors.append(f"非法字符 '{t.value[0]}' (行 {t.lexer.lineno})")
|
|
373
|
+
else:
|
|
374
|
+
# 这是一个非法标记
|
|
375
|
+
self.errors.append(f"非法标记 '{t.value}' (行 {t.lexer.lineno})")
|
|
376
|
+
# 跳过这个字符,继续处理
|
|
377
|
+
t.lexer.skip(1)
|
|
378
|
+
else:
|
|
379
|
+
self.errors.append("词法分析器到达文件末尾")
|
|
380
|
+
|
|
381
|
+
# 语法分析器规则
|
|
382
|
+
def p_expression(self, p):
|
|
383
|
+
"""expression : comparison
|
|
384
|
+
| expression EQUAL comparison
|
|
385
|
+
| expression NOTEQUAL comparison
|
|
386
|
+
| expression GREATER comparison
|
|
387
|
+
| expression LESS comparison
|
|
388
|
+
| expression GREATEREQUAL comparison
|
|
389
|
+
| expression LESSEQUAL comparison"""
|
|
390
|
+
if len(p) == 2:
|
|
391
|
+
p[0] = p[1]
|
|
392
|
+
else:
|
|
393
|
+
p[0] = ASTNode('binop', [p[1], p[3]], {'op': p[2]})
|
|
394
|
+
|
|
395
|
+
def p_comparison(self, p):
|
|
396
|
+
"""comparison : term
|
|
397
|
+
| comparison PLUS term
|
|
398
|
+
| comparison MINUS term"""
|
|
399
|
+
if len(p) == 2:
|
|
400
|
+
p[0] = p[1]
|
|
401
|
+
else:
|
|
402
|
+
p[0] = ASTNode('binop', [p[1], p[3]], {'op': p[2]})
|
|
403
|
+
|
|
404
|
+
def p_term(self, p):
|
|
405
|
+
"""term : factor
|
|
406
|
+
| term TIMES factor
|
|
407
|
+
| term DIVIDE factor"""
|
|
408
|
+
if len(p) == 2:
|
|
409
|
+
p[0] = p[1]
|
|
410
|
+
else:
|
|
411
|
+
p[0] = ASTNode('binop', [p[1], p[3]], {'op': p[2]})
|
|
412
|
+
|
|
413
|
+
def p_factor(self, p):
|
|
414
|
+
"""factor : NUMBER
|
|
415
|
+
| STRING
|
|
416
|
+
| FIELD
|
|
417
|
+
| CATEGORY
|
|
418
|
+
| IDENTIFIER
|
|
419
|
+
| BOOLEAN
|
|
420
|
+
| MINUS factor
|
|
421
|
+
| LPAREN expression RPAREN
|
|
422
|
+
| function_call"""
|
|
423
|
+
if len(p) == 2:
|
|
424
|
+
# 数字、字符串、字段、类别或标识符
|
|
425
|
+
if p.slice[1].type == 'NUMBER':
|
|
426
|
+
p[0] = ASTNode('number', value=p[1])
|
|
427
|
+
elif p.slice[1].type == 'STRING':
|
|
428
|
+
p[0] = ASTNode('string', value=p[1])
|
|
429
|
+
elif p.slice[1].type == 'FIELD':
|
|
430
|
+
p[0] = ASTNode('field', value=p[1])
|
|
431
|
+
elif p.slice[1].type == 'CATEGORY':
|
|
432
|
+
p[0] = ASTNode('category', value=p[1])
|
|
433
|
+
elif p.slice[1].type == 'BOOLEAN':
|
|
434
|
+
p[0] = ASTNode('boolean', value=p[1])
|
|
435
|
+
elif p.slice[1].type == 'IDENTIFIER':
|
|
436
|
+
p[0] = ASTNode('identifier', value=p[1])
|
|
437
|
+
else:
|
|
438
|
+
p[0] = p[1]
|
|
439
|
+
elif len(p) == 3:
|
|
440
|
+
# 一元负号
|
|
441
|
+
p[0] = ASTNode('unop', [p[2]], {'op': p[1]})
|
|
442
|
+
elif len(p) == 4:
|
|
443
|
+
# 括号表达式
|
|
444
|
+
p[0] = p[2]
|
|
445
|
+
else:
|
|
446
|
+
# 函数调用
|
|
447
|
+
p[0] = p[1]
|
|
448
|
+
|
|
449
|
+
def p_function_call(self, p):
|
|
450
|
+
'''function_call : FUNCTION LPAREN args RPAREN'''
|
|
451
|
+
p[0] = ASTNode('function', p[3], p[1])
|
|
452
|
+
|
|
453
|
+
def p_args(self, p):
|
|
454
|
+
'''args : arg_list
|
|
455
|
+
| empty'''
|
|
456
|
+
if len(p) == 2 and p[1] is not None:
|
|
457
|
+
p[0] = p[1]
|
|
458
|
+
else:
|
|
459
|
+
p[0] = []
|
|
460
|
+
|
|
461
|
+
def p_arg_list(self, p):
|
|
462
|
+
'''arg_list : arg
|
|
463
|
+
| arg_list COMMA arg'''
|
|
464
|
+
if len(p) == 2:
|
|
465
|
+
p[0] = [p[1]]
|
|
466
|
+
else:
|
|
467
|
+
p[0] = p[1] + [p[3]]
|
|
468
|
+
|
|
469
|
+
def p_arg(self, p):
|
|
470
|
+
'''arg : expression
|
|
471
|
+
| IDENTIFIER ASSIGN expression'''
|
|
472
|
+
if len(p) == 2:
|
|
473
|
+
p[0] = {'type': 'positional', 'value': p[1]}
|
|
474
|
+
else:
|
|
475
|
+
p[0] = {'type': 'named', 'name': p[1], 'value': p[3]}
|
|
476
|
+
|
|
477
|
+
def p_empty(self, p):
|
|
478
|
+
'''empty :'''
|
|
479
|
+
p[0] = None
|
|
480
|
+
|
|
481
|
+
# 语法错误处理
|
|
482
|
+
def p_error(self, p):
|
|
483
|
+
if p:
|
|
484
|
+
self.errors.append(f"语法错误在位置 {p.lexpos}: 非法标记 '{p.value}'")
|
|
485
|
+
else:
|
|
486
|
+
self.errors.append("语法错误: 表达式不完整")
|
|
487
|
+
|
|
488
|
+
def _is_valid_field(self, field_name: str) -> bool:
|
|
489
|
+
"""检查字段名是否符合模式"""
|
|
490
|
+
for pattern in field_patterns:
|
|
491
|
+
if pattern.match(field_name):
|
|
492
|
+
return True
|
|
493
|
+
return False
|
|
494
|
+
|
|
495
|
+
def validate_function(self, node: ASTNode, is_in_group_arg: bool = False) -> List[str]:
|
|
496
|
+
"""验证函数调用的参数数量和类型"""
|
|
497
|
+
function_name = node.value
|
|
498
|
+
args = node.children
|
|
499
|
+
function_info = supported_functions.get(function_name)
|
|
500
|
+
|
|
501
|
+
if not function_info:
|
|
502
|
+
return [f"未知函数: {function_name}"]
|
|
503
|
+
|
|
504
|
+
errors = []
|
|
505
|
+
|
|
506
|
+
# 检查参数数量
|
|
507
|
+
if len(args) < function_info['min_args']:
|
|
508
|
+
errors.append(f"函数 {function_name} 需要至少 {function_info['min_args']} 个参数,但只提供了 {len(args)}")
|
|
509
|
+
elif len(args) > function_info['max_args']:
|
|
510
|
+
errors.append(f"函数 {function_name} 最多接受 {function_info['max_args']} 个参数,但提供了 {len(args)}")
|
|
511
|
+
|
|
512
|
+
# 处理参数验证
|
|
513
|
+
# 跟踪已使用的位置参数索引
|
|
514
|
+
positional_index = 0
|
|
515
|
+
|
|
516
|
+
# 对于所有函数,支持命名参数
|
|
517
|
+
for arg in args:
|
|
518
|
+
if isinstance(arg, dict):
|
|
519
|
+
if arg['type'] == 'named':
|
|
520
|
+
# 命名参数
|
|
521
|
+
if 'param_names' in function_info and arg['name'] in function_info['param_names']:
|
|
522
|
+
# 查找参数在param_names中的索引
|
|
523
|
+
param_index = function_info['param_names'].index(arg['name'])
|
|
524
|
+
if param_index < len(function_info['arg_types']):
|
|
525
|
+
expected_type = function_info['arg_types'][param_index]
|
|
526
|
+
arg_errors = self._validate_arg_type(arg['value'], expected_type, param_index, function_name, is_in_group_arg)
|
|
527
|
+
errors.extend(arg_errors)
|
|
528
|
+
# 对于winsorize函数,支持std和clip参数
|
|
529
|
+
elif function_name == 'winsorize' and arg['name'] in ['std', 'clip']:
|
|
530
|
+
arg_errors = self._validate_arg_type(arg['value'], 'number', 0, function_name, is_in_group_arg)
|
|
531
|
+
errors.extend(arg_errors)
|
|
532
|
+
# 对于bucket函数,支持'range'和'buckets'参数
|
|
533
|
+
elif function_name == 'bucket' and arg['name'] in ['range', 'buckets']:
|
|
534
|
+
# range和buckets参数应该是string类型
|
|
535
|
+
arg_errors = self._validate_arg_type(arg['value'], 'string', 1, function_name, is_in_group_arg)
|
|
536
|
+
errors.extend(arg_errors)
|
|
537
|
+
else:
|
|
538
|
+
errors.append(f"函数 {function_name} 不存在参数 '{arg['name']}'")
|
|
539
|
+
elif arg['type'] == 'positional':
|
|
540
|
+
# 位置参数(字典形式)
|
|
541
|
+
# 对于winsorize函数,第二个参数必须是命名参数
|
|
542
|
+
if function_name == 'winsorize' and positional_index == 1:
|
|
543
|
+
errors.append(f"函数 {function_name} 的第二个参数必须使用命名参数 'std='")
|
|
544
|
+
# 对于ts_moment函数,第三个参数必须是命名参数
|
|
545
|
+
elif function_name == 'ts_moment' and positional_index == 2:
|
|
546
|
+
errors.append(f"函数 {function_name} 的第三个参数必须使用命名参数 'k='")
|
|
547
|
+
else:
|
|
548
|
+
# 验证位置参数的类型
|
|
549
|
+
if positional_index < len(function_info['arg_types']):
|
|
550
|
+
expected_type = function_info['arg_types'][positional_index]
|
|
551
|
+
arg_errors = self._validate_arg_type(arg['value'], expected_type, positional_index, function_name, is_in_group_arg)
|
|
552
|
+
errors.extend(arg_errors)
|
|
553
|
+
positional_index += 1
|
|
554
|
+
else:
|
|
555
|
+
# 其他字典类型参数
|
|
556
|
+
errors.append(f"参数 {positional_index+1} 格式错误")
|
|
557
|
+
positional_index += 1
|
|
558
|
+
else:
|
|
559
|
+
# 位置参数(直接ASTNode形式)
|
|
560
|
+
# 对于winsorize函数,第二个参数必须是命名参数
|
|
561
|
+
if function_name == 'winsorize' and positional_index == 1:
|
|
562
|
+
errors.append(f"函数 {function_name} 的第二个参数必须使用命名参数 'std='")
|
|
563
|
+
# 对于ts_moment函数,第三个参数必须是命名参数
|
|
564
|
+
elif function_name == 'ts_moment' and positional_index == 2:
|
|
565
|
+
errors.append(f"函数 {function_name} 的第三个参数必须使用命名参数 'k='")
|
|
566
|
+
else:
|
|
567
|
+
# 验证位置参数的类型
|
|
568
|
+
if positional_index < len(function_info['arg_types']):
|
|
569
|
+
expected_type = function_info['arg_types'][positional_index]
|
|
570
|
+
arg_errors = self._validate_arg_type(arg, expected_type, positional_index, function_name, is_in_group_arg)
|
|
571
|
+
errors.extend(arg_errors)
|
|
572
|
+
positional_index += 1
|
|
573
|
+
|
|
574
|
+
return errors
|
|
575
|
+
|
|
576
|
+
def _validate_arg_type(self, arg: ASTNode, expected_type: str, arg_index: int, function_name: str, is_in_group_arg: bool = False) -> List[str]:
|
|
577
|
+
"""验证参数类型是否符合预期"""
|
|
578
|
+
errors = []
|
|
579
|
+
|
|
580
|
+
# 首先检查是否是group类型字段,如果是则只能用于Group类型函数
|
|
581
|
+
# 但是如果当前函数是group_xxx或在group函数的参数链中,则允许使用
|
|
582
|
+
if arg.node_type == 'category' and arg.value in group_fields:
|
|
583
|
+
if not (function_name.startswith('group_') or is_in_group_arg):
|
|
584
|
+
errors.append(f"Group类型字段 '{arg.value}' 只能用于Group类型函数的参数中")
|
|
585
|
+
|
|
586
|
+
# 然后验证参数类型是否符合预期
|
|
587
|
+
if expected_type == 'expression':
|
|
588
|
+
# 表达式可以是任何有效的AST节点
|
|
589
|
+
pass
|
|
590
|
+
elif expected_type == 'number':
|
|
591
|
+
if arg.node_type != 'number':
|
|
592
|
+
errors.append(f"参数 {arg_index+1} 应该是一个数字,但得到 {arg.node_type}")
|
|
593
|
+
elif expected_type == 'boolean':
|
|
594
|
+
# 布尔值可以是数字(0/1)
|
|
595
|
+
if arg.node_type != 'number':
|
|
596
|
+
errors.append(f"参数 {arg_index+1} 应该是一个布尔值(0/1),但得到 {arg.node_type}")
|
|
597
|
+
elif expected_type == 'field':
|
|
598
|
+
if arg.node_type != 'field' and arg.node_type != 'category':
|
|
599
|
+
# 允许field或category作为字段参数
|
|
600
|
+
errors.append(f"参数 {arg_index+1} 应该是一个字段,但得到 {arg.node_type}")
|
|
601
|
+
elif arg.node_type == 'field' and not self._is_valid_field(arg.value):
|
|
602
|
+
errors.append(f"无效的字段名: {arg.value}")
|
|
603
|
+
elif expected_type == 'category':
|
|
604
|
+
if not function_name.startswith('group_'):
|
|
605
|
+
# 非group函数的category参数必须是category类型且在valid_categories中
|
|
606
|
+
if arg.node_type != 'category':
|
|
607
|
+
errors.append(f"参数 {arg_index+1} 应该是一个类别,但得到 {arg.node_type}")
|
|
608
|
+
elif arg.value not in valid_categories:
|
|
609
|
+
errors.append(f"无效的类别: {arg.value}")
|
|
610
|
+
# group函数的category参数可以是任何类型(field、category等),不进行类型校验
|
|
611
|
+
|
|
612
|
+
return errors
|
|
613
|
+
|
|
614
|
+
def validate_ast(self, ast: Optional[ASTNode], is_in_group_arg: bool = False) -> List[str]:
|
|
615
|
+
"""递归验证抽象语法树"""
|
|
616
|
+
if not ast:
|
|
617
|
+
return ["无法解析表达式"]
|
|
618
|
+
|
|
619
|
+
errors = []
|
|
620
|
+
|
|
621
|
+
# 根据节点类型进行验证
|
|
622
|
+
if ast.node_type == 'function':
|
|
623
|
+
# 检查当前函数是否是group函数
|
|
624
|
+
is_group_function = ast.value.startswith('group_')
|
|
625
|
+
# 确定当前是否在group函数的参数链中
|
|
626
|
+
current_in_group_arg = is_in_group_arg or is_group_function
|
|
627
|
+
# 验证函数
|
|
628
|
+
function_errors = self.validate_function(ast, current_in_group_arg)
|
|
629
|
+
errors.extend(function_errors)
|
|
630
|
+
|
|
631
|
+
# 递归验证子节点时使用current_in_group_arg
|
|
632
|
+
for child in ast.children:
|
|
633
|
+
if isinstance(child, dict):
|
|
634
|
+
# 命名参数,验证其值
|
|
635
|
+
if 'value' in child and hasattr(child['value'], 'node_type'):
|
|
636
|
+
child_errors = self.validate_ast(child['value'], current_in_group_arg)
|
|
637
|
+
errors.extend(child_errors)
|
|
638
|
+
elif hasattr(child, 'node_type'):
|
|
639
|
+
child_errors = self.validate_ast(child, current_in_group_arg)
|
|
640
|
+
errors.extend(child_errors)
|
|
641
|
+
elif ast.node_type in ['unop', 'binop']:
|
|
642
|
+
# 对操作符的子节点进行验证
|
|
643
|
+
for child in ast.children:
|
|
644
|
+
if hasattr(child, 'node_type'):
|
|
645
|
+
child_errors = self.validate_ast(child, is_in_group_arg)
|
|
646
|
+
errors.extend(child_errors)
|
|
647
|
+
elif ast.node_type == 'field':
|
|
648
|
+
# 验证字段名
|
|
649
|
+
if not self._is_valid_field(ast.value):
|
|
650
|
+
errors.append(f"无效的字段名: {ast.value}")
|
|
651
|
+
else:
|
|
652
|
+
# 递归验证子节点
|
|
653
|
+
for child in ast.children:
|
|
654
|
+
if isinstance(child, dict):
|
|
655
|
+
# 命名参数,验证其值
|
|
656
|
+
if 'value' in child and hasattr(child['value'], 'node_type'):
|
|
657
|
+
child_errors = self.validate_ast(child['value'], is_in_group_arg)
|
|
658
|
+
errors.extend(child_errors)
|
|
659
|
+
elif hasattr(child, 'node_type'):
|
|
660
|
+
child_errors = self.validate_ast(child, is_in_group_arg)
|
|
661
|
+
errors.extend(child_errors)
|
|
662
|
+
|
|
663
|
+
return errors
|
|
664
|
+
|
|
665
|
+
def _process_semicolon_expression(self, expression: str) -> Tuple[bool, str]:
|
|
666
|
+
"""处理带有分号的表达式,将其转换为不带分号的简化形式
|
|
667
|
+
|
|
668
|
+
Args:
|
|
669
|
+
expression: 要处理的表达式字符串
|
|
670
|
+
|
|
671
|
+
Returns:
|
|
672
|
+
Tuple[bool, str]: (是否成功, 转换后的表达式或错误信息)
|
|
673
|
+
"""
|
|
674
|
+
# 检查表达式是否以分号结尾
|
|
675
|
+
if expression.strip().endswith(';'):
|
|
676
|
+
return False, "表达式不能以分号结尾"
|
|
677
|
+
|
|
678
|
+
# 分割表达式为语句列表
|
|
679
|
+
statements = [stmt.strip() for stmt in expression.split(';') if stmt.strip()]
|
|
680
|
+
if not statements:
|
|
681
|
+
return False, "表达式不能为空"
|
|
682
|
+
|
|
683
|
+
# 存储变量赋值
|
|
684
|
+
variables = {}
|
|
685
|
+
|
|
686
|
+
# 处理每个赋值语句(除了最后一个)
|
|
687
|
+
for i, stmt in enumerate(statements[:-1]):
|
|
688
|
+
# 检查是否包含赋值符号
|
|
689
|
+
if '=' not in stmt:
|
|
690
|
+
return False, f"第{i+1}个语句必须是赋值语句(使用=符号)"
|
|
691
|
+
|
|
692
|
+
# 检查是否是比较操作符(==, !=, <=, >=)
|
|
693
|
+
if any(op in stmt for op in ['==', '!=', '<=', '>=']):
|
|
694
|
+
# 如果包含比较操作符,需要确认是否有赋值符号
|
|
695
|
+
# 使用临时替换法:将比较操作符替换为临时标记,再检查是否还有=
|
|
696
|
+
temp_stmt = stmt
|
|
697
|
+
for op in ['==', '!=', '<=', '>=']:
|
|
698
|
+
temp_stmt = temp_stmt.replace(op, '---')
|
|
699
|
+
|
|
700
|
+
if '=' not in temp_stmt:
|
|
701
|
+
return False, f"第{i+1}个语句必须是赋值语句,不能只是比较表达式"
|
|
702
|
+
|
|
703
|
+
# 找到第一个=符号(不是比较操作符的一部分)
|
|
704
|
+
# 先将比较操作符替换为临时标记,再找=
|
|
705
|
+
temp_stmt = stmt
|
|
706
|
+
for op in ['==', '!=', '<=', '>=']:
|
|
707
|
+
temp_stmt = temp_stmt.replace(op, '---')
|
|
708
|
+
|
|
709
|
+
if '=' not in temp_stmt:
|
|
710
|
+
return False, f"第{i+1}个语句必须是赋值语句(使用=符号)"
|
|
711
|
+
|
|
712
|
+
# 找到实际的=位置
|
|
713
|
+
equals_pos = temp_stmt.index('=')
|
|
714
|
+
|
|
715
|
+
# 在原始语句中找到对应位置
|
|
716
|
+
real_equals_pos = 0
|
|
717
|
+
temp_count = 0
|
|
718
|
+
for char in stmt:
|
|
719
|
+
if temp_count == equals_pos:
|
|
720
|
+
break
|
|
721
|
+
if char in '!<>':
|
|
722
|
+
# 检查是否是比较操作符的一部分
|
|
723
|
+
if real_equals_pos + 1 < len(stmt) and stmt[real_equals_pos + 1] == '=':
|
|
724
|
+
# 是比较操作符,跳过两个字符
|
|
725
|
+
real_equals_pos += 2
|
|
726
|
+
temp_count += 3 # 因为替换成了三个字符的---
|
|
727
|
+
else:
|
|
728
|
+
real_equals_pos += 1
|
|
729
|
+
temp_count += 1
|
|
730
|
+
else:
|
|
731
|
+
real_equals_pos += 1
|
|
732
|
+
temp_count += 1
|
|
733
|
+
|
|
734
|
+
# 分割变量名和值
|
|
735
|
+
var_name = stmt[:real_equals_pos].strip()
|
|
736
|
+
var_value = stmt[real_equals_pos + 1:].strip()
|
|
737
|
+
|
|
738
|
+
# 检查变量名是否有效
|
|
739
|
+
if not re.match(r'^[a-zA-Z_][a-zA-Z0-9_]*$', var_name):
|
|
740
|
+
return False, f"第{i+1}个语句的变量名'{var_name}'无效,只能包含字母、数字和下划线,且不能以数字开头"
|
|
741
|
+
|
|
742
|
+
var_name_lower = var_name.lower() # 变量名不区分大小写
|
|
743
|
+
|
|
744
|
+
# 检查变量名是否在后续表达式中使用
|
|
745
|
+
# 这里不需要,因为后面的表达式会检查
|
|
746
|
+
|
|
747
|
+
# 检查变量值中使用的变量是否已经定义
|
|
748
|
+
# 简单检查:提取所有可能的变量名
|
|
749
|
+
used_vars = re.findall(r'\b[a-zA-Z_][a-zA-Z0-9_]*\b', var_value)
|
|
750
|
+
for used_var in used_vars:
|
|
751
|
+
used_var_lower = used_var.lower()
|
|
752
|
+
if used_var_lower not in variables:
|
|
753
|
+
# 检查是否是函数名
|
|
754
|
+
if used_var not in supported_functions:
|
|
755
|
+
# 对于单个字母或简单单词,不自动视为字段名,要求先定义
|
|
756
|
+
if len(used_var) <= 2:
|
|
757
|
+
return False, f"第{i+1}个语句中使用的变量'{used_var}'未在之前定义"
|
|
758
|
+
# 对于较长的字段名,仍然允许作为字段名
|
|
759
|
+
elif not self._is_valid_field(used_var):
|
|
760
|
+
return False, f"第{i+1}个语句中使用的变量'{used_var}'未在之前定义"
|
|
761
|
+
|
|
762
|
+
# 将之前定义的变量替换到当前值中
|
|
763
|
+
for existing_var, existing_val in variables.items():
|
|
764
|
+
# 使用单词边界匹配,避免替换到其他单词的一部分
|
|
765
|
+
var_value = re.sub(rf'\b{existing_var}\b', existing_val, var_value)
|
|
766
|
+
|
|
767
|
+
# 存储变量
|
|
768
|
+
variables[var_name_lower] = var_value
|
|
769
|
+
|
|
770
|
+
# 处理最后一个语句(实际的表达式)
|
|
771
|
+
final_stmt = statements[-1]
|
|
772
|
+
|
|
773
|
+
# 检查最后一个语句是否是赋值语句
|
|
774
|
+
if '=' in final_stmt:
|
|
775
|
+
# 替换比较操作符为临时标记,然后检查是否还有单独的=
|
|
776
|
+
temp_stmt = final_stmt
|
|
777
|
+
for op in ['==', '!=', '<=', '>=']:
|
|
778
|
+
temp_stmt = temp_stmt.replace(op, '---')
|
|
779
|
+
|
|
780
|
+
if '=' in temp_stmt:
|
|
781
|
+
return False, "最后一个语句不能是赋值语句"
|
|
782
|
+
|
|
783
|
+
# 检查最后一个语句中使用的变量是否已经定义
|
|
784
|
+
used_vars = re.findall(r'\b[a-zA-Z_][a-zA-Z0-9_]*\b', final_stmt)
|
|
785
|
+
for used_var in used_vars:
|
|
786
|
+
used_var_lower = used_var.lower()
|
|
787
|
+
if used_var_lower not in variables:
|
|
788
|
+
# 检查是否是函数名
|
|
789
|
+
if used_var not in supported_functions:
|
|
790
|
+
# 在分号表达式中,所有非函数名的标识符都必须是变量,必须在之前定义
|
|
791
|
+
return False, f"最后一个语句中使用的变量'{used_var}'未在之前定义"
|
|
792
|
+
|
|
793
|
+
# 将变量替换到最后一个表达式中
|
|
794
|
+
final_expr = final_stmt
|
|
795
|
+
for var_name, var_value in variables.items():
|
|
796
|
+
final_expr = re.sub(rf'\b{var_name}\b', var_value, final_expr)
|
|
797
|
+
|
|
798
|
+
return True, final_expr
|
|
799
|
+
|
|
800
|
+
def check_expression(self, expression: str) -> Dict[str, Any]:
|
|
801
|
+
"""
|
|
802
|
+
检查表达式格式是否正确
|
|
803
|
+
|
|
804
|
+
Args:
|
|
805
|
+
expression: 要验证的表达式字符串
|
|
806
|
+
|
|
807
|
+
Returns:
|
|
808
|
+
包含验证结果的字典
|
|
809
|
+
"""
|
|
810
|
+
# 重置错误列表
|
|
811
|
+
self.errors = []
|
|
812
|
+
|
|
813
|
+
try:
|
|
814
|
+
expression = expression.strip()
|
|
815
|
+
if not expression:
|
|
816
|
+
return {
|
|
817
|
+
'valid': False,
|
|
818
|
+
'errors': ['表达式不能为空'],
|
|
819
|
+
'tokens': [],
|
|
820
|
+
'ast': None
|
|
821
|
+
}
|
|
822
|
+
|
|
823
|
+
# 处理带有分号的表达式
|
|
824
|
+
if ';' in expression:
|
|
825
|
+
success, result = self._process_semicolon_expression(expression)
|
|
826
|
+
if not success:
|
|
827
|
+
return {
|
|
828
|
+
'valid': False,
|
|
829
|
+
'errors': [result],
|
|
830
|
+
'tokens': [],
|
|
831
|
+
'ast': None
|
|
832
|
+
}
|
|
833
|
+
expression = result
|
|
834
|
+
|
|
835
|
+
# 重置词法分析器的行号
|
|
836
|
+
self.lexer.lineno = 1
|
|
837
|
+
|
|
838
|
+
# 词法分析(用于调试)
|
|
839
|
+
self.lexer.input(expression)
|
|
840
|
+
tokens = []
|
|
841
|
+
# 调试:打印识别的标记
|
|
842
|
+
# print(f"\n调试 - 表达式: {expression}")
|
|
843
|
+
# print("识别的标记:")
|
|
844
|
+
for token in self.lexer:
|
|
845
|
+
# print(f" - 类型: {token.type}, 值: '{token.value}', 位置: {token.lexpos}")
|
|
846
|
+
tokens.append(token)
|
|
847
|
+
|
|
848
|
+
# 重新设置词法分析器的输入,以便语法分析器使用
|
|
849
|
+
self.lexer.input(expression)
|
|
850
|
+
self.lexer.lineno = 1
|
|
851
|
+
|
|
852
|
+
# 语法分析
|
|
853
|
+
ast = self.parser.parse(expression, lexer=self.lexer)
|
|
854
|
+
|
|
855
|
+
# 验证AST
|
|
856
|
+
validation_errors = self.validate_ast(ast)
|
|
857
|
+
|
|
858
|
+
# 合并所有错误
|
|
859
|
+
all_errors = self.errors + validation_errors
|
|
860
|
+
|
|
861
|
+
# 检查括号是否匹配
|
|
862
|
+
bracket_count = 0
|
|
863
|
+
for char in expression:
|
|
864
|
+
if char == '(':
|
|
865
|
+
bracket_count += 1
|
|
866
|
+
elif char == ')':
|
|
867
|
+
bracket_count -= 1
|
|
868
|
+
if bracket_count < 0:
|
|
869
|
+
all_errors.append("括号不匹配: 右括号过多")
|
|
870
|
+
break
|
|
871
|
+
if bracket_count > 0:
|
|
872
|
+
all_errors.append("括号不匹配: 左括号过多")
|
|
873
|
+
|
|
874
|
+
return {
|
|
875
|
+
'valid': len(all_errors) == 0,
|
|
876
|
+
'errors': all_errors,
|
|
877
|
+
'tokens': tokens,
|
|
878
|
+
'ast': ast
|
|
879
|
+
}
|
|
880
|
+
except Exception as e:
|
|
881
|
+
return {
|
|
882
|
+
'valid': False,
|
|
883
|
+
'errors': [f"解析错误: {str(e)}"],
|
|
884
|
+
'tokens': [],
|
|
885
|
+
'ast': None
|
|
886
|
+
}
|
|
887
|
+
|
|
888
|
+
|
|
889
|
+
|