allaun/BioSight
1
0
Fork 0
mirror of https://github.com/allaunthefox/BioSight.git synced 2026-08-19 00:40:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(dna): optimize char classification and fix Unicode math symbol misclassification

Browse source 
- Pre-defined and unified character sets (OPERATOR_CHARS, BRACKET_CHARS, PUNCT_CHARS, WHITESPACE_CHARS).
- Defined precise sets for SYMMETRY_CHARS, PERIODICITY_CHARS, CONTINUITY_CHARS, and META_MATH_CHARS.
- Re-ordered specific checks to precede c.isalpha() so Unicode/Greek math letters are not misclassified as standard lower/upper alpha.

Build: 3307 jobs, 0 errors (lake build)
This commit is contained in:
allaun 2026-06-27 22:53:16 -05:00
parent 295130c078
commit 09b9f690e0
1 changed files with 24 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
python/phi/charclass.py
View file

@ -35,7 +35,14 @@ CHAR_CLASSES = {
OPERATOR_CHARS = set("+-*/^%=<>!&|~") OPERATOR_CHARS = set("+-*/^%=<>!&|~")
BRACKET_CHARS = set("()[]{}") BRACKET_CHARS = set("()[]{}")
PUNCT_CHARS = set(".,;:'\"@#$\\") PUNCT_CHARS = set(".,;:'\"@#$\\_")
WHITESPACE_CHARS = set(" \t\n\r")
# Unicode mathematical sets (placed at the top to prevent misclassification as standard alpha)
SYMMETRY_CHARS = set("≈≡∼")
PERIODICITY_CHARS = set("πθλ∞")
CONTINUITY_CHARS = set("→Δ∇∫")
META_MATH_CHARS = set("√∑∏∂")
def classify_char(c: str) -> int: def classify_char(c: str) -> int:
@ -84,31 +91,30 @@ def classify_char(c: str) -> int:
>>> classify_char("©") >>> classify_char("©")
7 7
""" """
# Check Unicode math classes first so Greek/math symbols are not misclassified as standard alpha
if c in PERIODICITY_CHARS:
return 9
if c in CONTINUITY_CHARS:
return 10
if c in SYMMETRY_CHARS:
return 8
if c in META_MATH_CHARS:
return 11
# Check standard ASCII classes
if c.isdigit(): if c.isdigit():
return 0 return 0
if c.isalpha(): if c.isalpha():
return 1 if c.islower() else 2 return 1 if c.islower() else 2
# Operator chars if c in OPERATOR_CHARS:
if c in "+-*/^%=<>!&|~":
return 3 return 3
# Bracket chars if c in BRACKET_CHARS:
if c in "()[]{}":
return 4 return 4
# Punctuation if c in PUNCT_CHARS:
if c in ".,;:'\"@#$\\":
return 5 return 5
# Whitespace if c in WHITESPACE_CHARS:
if c in (" ", "\t", "\n", "\r"):
return 6 return 6
# Other (General)
if c in "$\\pi\\theta\\lambda\\infty$": # Periodicity
return 9
if c in "$\\rightarrow\\Delta\\nabla\\int$": # Continuity
return 10
if c in "=$\\approx\\equiv\\sim$": # Symmetry
return 8
if c in "$\\sqrt{}\\sum\\prod\\partial$": # Meta-math
return 11
return 7 return 7