gh-137627: Make csv.Sniffer.sniff() delimiter detection 1.6x faster

Lib/csv.py

@@ -84,6 +84,8 @@ class excel:
 __version__ = "1.0"
 
 
+_ASCII_CHARS = frozenset(map(chr, range(127))) # 7-bit ASCII
+
 class Dialect:
     """Describe a CSV dialect.
 
@@ -364,28 +366,33 @@ def _guess_delimiter(self, data, delimiters):
         try and evaluate the smallest portion of the data possible, evaluating
         additional chunks as necessary.
         """
+        from collections import Counter, defaultdict
 
         data = list(filter(None, data.split('\n')))
 
-        ascii = [chr(c) for c in range(127)] # 7-bit ASCII
-
         # build frequency tables
         chunkLength = min(10, len(data))
         iteration = 0
-        charFrequency = {}
+        # {char -> {count_per_line -> num_lines_with_that_count}}
+        charFrequency = defaultdict(Counter)
         modes = {}
         delims = {}
         start, end = 0, chunkLength
         while start < len(data):
             iteration += 1
-            for line in data[start:end]:
-                for char in ascii:
-                    metaFrequency = charFrequency.get(char, {})
-                    # must count even if frequency is 0
-                    freq = line.count(char)
-                    # value is the mode
-                    metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
-                    charFrequency[char] = metaFrequency
+            chunk = data[start:end]
+            candidate_chars = set().union(*chunk)
+            candidate_chars &= _ASCII_CHARS
+            for line in chunk:
+                for char in candidate_chars:
+                    count = line.count(char)
+                    charFrequency[char][count] += 1
+
+            # must count even if frequency is 0
+            missing_chars = _ASCII_CHARS - candidate_chars
+            chunk_len = len(chunk)
+            for char in missing_chars:
+                charFrequency[char][0] += chunk_len
 
             for char in charFrequency.keys():
                 items = list(charFrequency[char].items())

Misc/NEWS.d/next/Library/2025-08-11-04-52-18.gh-issue-137627.Ku5Yi2.rst

@@ -0,0 +1 @@
+:meth:`csv.Sniffer.sniff` 2x faster