From c30056a700d7e54ebd4d6ad370e08070dc6b3ccc Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Fri, 3 May 2024 21:34:18 +0300
Subject: [PATCH] lint : fix

---
 scripts/gen-unicode-data.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/scripts/gen-unicode-data.py b/scripts/gen-unicode-data.py
index ee6de3f08..d49cbf2a0 100644
--- a/scripts/gen-unicode-data.py
+++ b/scripts/gen-unicode-data.py
@@ -1,5 +1,5 @@
 import regex
-import struct
+
 
 def cpt_to_utf8_str(cpt):
     if cpt <= 0xFF:
@@ -11,13 +11,15 @@ def cpt_to_utf8_str(cpt):
     else:
         return bytes([cpt & 0xFF, (cpt >> 8) & 0xFF, (cpt >> 16) & 0xFF, cpt >> 24])
 
+
 def is_match(codepoint, regex_expr):
     try:
         res = regex.match(regex_expr, cpt_to_utf8_str(codepoint).decode('utf-32'))
         return res is not None
-    except:
+    except Exception:
         return False
 
+
 def get_matches(regex_expr):
     unicode_ranges = []
     current_range = None
@@ -37,6 +39,7 @@ def get_matches(regex_expr):
 
     return unicode_ranges
 
+
 def print_cat(cat, ranges):
     print("const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_{} = {{".format(cat))
     cnt = 0
@@ -53,6 +56,7 @@ def print_cat(cat, ranges):
     print("};")
     print("")
 
+
 print_cat("number",      get_matches(r'\p{N}'))
 print_cat("letter",      get_matches(r'\p{L}'))
 print_cat("whitespace",  get_matches(r'\p{Z}'))
@@ -60,4 +64,3 @@ print_cat("accent_mark", get_matches(r'\p{M}'))
 print_cat("punctuation", get_matches(r'\p{P}'))
 print_cat("symbol",      get_matches(r'\p{S}'))
 print_cat("control",     get_matches(r'\p{C}'))
-