b516b2985d
- bex/reduce.py: Faithful implementation of Reduce with support-weighted SOA edit distance, adjunction, iterative merging, and Minimize - experiments/context_eval.py: Multi-codebase support (RAGSAK + Flask), Reduce experiments with thresholds 0.05-0.4 - tests/test_reduce.py: 24 tests covering all Reduce components - Flask cloned to external_refs/flask for cross-validation Results: - RAGSAK: 12.0% coverage (First 3 symbols) - Flask: 10.7% coverage (First 3 symbols) - Reduce has minimal impact (1-2 merges per codebase at ε=0.3) - Coverage ceiling appears to be ~10-12% for prefix-based grouping
29 lines
980 B
Python
29 lines
980 B
Python
"""
|
|
bex — Paper-faithful implementation of BEX inference algorithms.
|
|
|
|
Papers:
|
|
- Bex et al. 2010 (TODS): Inference of Concise Regular Expressions and DTDs
|
|
- Bex et al. 2010 (arXiv 1004.2372): Learning Deterministic Regular Expressions
|
|
|
|
Algorithms implemented:
|
|
TODS 2010: 2T-INF, REWRITE, RWR, RWR², RWR₀, CRX
|
|
arXiv 2010: iKoa, Disambiguate, rwr², iDRegEx
|
|
"""
|
|
|
|
from .soa import SOA
|
|
from .twotinf import build_soa
|
|
from .rwr0 import rwr0
|
|
from .crx import CRX
|
|
from .ikoa import ikoa
|
|
from .rwrsq import rwr_sq
|
|
from .idregex import idregex
|
|
from .kore import kOREInference, validate_k_ore
|
|
from .koa import KOA, build_complete_koa
|
|
from .expr import concat, disj, star, optional, alphabet, strip_k
|
|
from .marking import mark_koa
|
|
from .tokenizer import YAMLTokenizer
|
|
from .ensemble import infer_ensemble
|
|
from .template import generate_template
|
|
from .reduce import reduce_contexts, soa_distance, build_soa_with_support, minimize_contexts, reduce_and_infer
|
|
|
|
__version__ = "0.2.0"
|