ref(relay): Optimize normalization regexes (#3921)

Optimizes memory footprint of regexes by:
- Avoiding (unicde aware) case insensitive matching
- Avoiding the use of unciode character sets like `\d` -> `[0-9]`, `\b`
-> `(?-u:\b)`, `\s` -> `(?-u:\s)`

relay-event-normalization/src/regexes.rs

@@ -9,51 +9,52 @@ pub static TRANSACTION_NAME_NORMALIZER_REGEX: Lazy<Regex> = Lazy::new(|| {
     Regex::new(
         r"(?x)
     (?P<uuid>[^/\\]*
-        \b[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\b
+        (?-u:\b)[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}(?-u:\b)
     [^/\\]*) |
     (?P<sha1>[^/\\]*
-        \b[0-9a-fA-F]{40}\b
+        (?-u:\b)[0-9a-fA-F]{40}(?-u:\b)
     [^/\\]*) |
     (?P<md5>[^/\\]*
-        \b[0-9a-fA-F]{32}\b
+        (?-u:\b)[0-9a-fA-F]{32}(?-u:\b)
     [^/\\]*) |
     (?P<date>[^/\\]*
         (?:
-            (?:\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|
-            (?:\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|
-            (?:\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))
+            (?:[0-9]{4}-[01][0-9]-[0-3][0-9]T[0-2][0-9]:[0-5][0-9]:[0-5][0-9]\.[0-9]+([+-][0-2][0-9]:[0-5][0-9]|Z))|
+            (?:[0-9]{4}-[01][0-9]-[0-3][0-9]T[0-2][0-9]:[0-5][0-9]:[0-5][0-9]([+-][0-2][0-9]:[0-5][0-9]|Z))|
+            (?:[0-9]{4}-[01][0-9]-[0-3][0-9]T[0-2][0-9]:[0-5][0-9]([+-][0-2][0-9]:[0-5][0-9]|Z))
         ) |
         (?:
-            \b(?:(Sun|Mon|Tue|Wed|Thu|Fri|Sat)\s+)?
-            (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s+
-            (?:[\d]{1,2})\s+
-            (?:[\d]{2}:[\d]{2}:[\d]{2})\s+
-            [\d]{4}
+            (?-u:\b)(?:(Sun|Mon|Tue|Wed|Thu|Fri|Sat)(?-u:\s)+)?
+            (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)(?-u:\s)+
+            (?:[0-9]{1,2})(?-u:\s)+
+            (?:[0-9]{2}:[0-9]{2}:[0-9]{2})(?-u:\s)+
+            [0-9]{4}
         ) |
         (?:
-            \b(?:(Sun|Mon|Tue|Wed|Thu|Fri|Sat),\s+)?
-            (?:0[1-9]|[1-2]?[\d]|3[01])\s+
-            (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s+
-            (?:19[\d]{2}|[2-9][\d]{3})\s+
-            (?:2[0-3]|[0-1][\d]):([0-5][\d])
-            (?::(60|[0-5][\d]))?\s+
-            (?:[-\+][\d]{2}[0-5][\d]|(?:UT|GMT|(?:E|C|M|P)(?:ST|DT)|[A-IK-Z]))
+            (?-u:\b)(?:(Sun|Mon|Tue|Wed|Thu|Fri|Sat),(?-u:\s)+)?
+            (?:0[1-9]|[1-2]?[0-9]|3[01])(?-u:\s)+
+            (?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)(?-u:\s)+
+            (?:19[0-9]{2}|[2-9][0-9]{3})(?-u:\s)+
+            (?:2[0-3]|[0-1][0-9]):([0-5][0-9])
+            (?::(60|[0-5][0-9]))?(?-u:\s)+
+            (?:[-\+][0-9]{2}[0-5][0-9]|(?:UT|GMT|(?:E|C|M|P)(?:ST|DT)|[A-IK-Z]))
         )
     [^/\\]*) |
     (?P<hex>[^/\\]*
-        \b0[xX][0-9a-fA-F]+\b
+        (?-u:\b)0[xX][0-9a-fA-F]+(?-u:\b)
     [^/\\]*) |
     (?:^|[/\\])
     (?P<int>
-        (:?[^%/\\]|%[0-9a-fA-F]{2})*\d{2,}
+        (:?[^%/\\]|%[0-9a-fA-F]{2})*[0-9]{2,}
     [^/\\]*)",
     )
     .unwrap()
 });
 
 /// Captures initial all-caps words as redis command, the rest as arguments.
-pub static REDIS_COMMAND_REGEX: Lazy<Regex> =
-    Lazy::new(|| Regex::new(r"\s*(?P<command>[A-Z]+(\s+[A-Z]+)*\b)(?P<args>.+)?").unwrap());
+pub static REDIS_COMMAND_REGEX: Lazy<Regex> = Lazy::new(|| {
+    Regex::new(r"(?-u:\s)*(?P<command>[A-Z]+((?-u:\s)+[A-Z]+)*(?-u:\b))(?P<args>.+)?").unwrap()
+});
 
 /// Regex with multiple capture groups for resource tokens we should scrub.
 ///
@@ -65,44 +66,44 @@ pub static REDIS_COMMAND_REGEX: Lazy<Regex> =
 /// <https://github.com/getsentry/sentry/blob/de5949a9a313d7ef0bf0685f84fe6e981ac38558/src/sentry/utils/performance_issues/base.py#L292-L306>
 pub static RESOURCE_NORMALIZER_REGEX: Lazy<Regex> = Lazy::new(|| {
     Regex::new(
-        r"(?xi)
+        r"(?x)
         # UUIDs.
-        (?P<uuid>[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}) |
+        (?P<uuid>[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}) |
         # Version strings.
         (?P<version>(v[0-9]+(?:\.[0-9]+)*)) |
         # Hexadecimal strings with more than 5 digits.
-        (?P<hex>[a-f0-9]{5}[a-f0-9]+) |
+        (?P<hex>[a-fA-F0-9]{5}[a-fA-F0-9]+) |
         # Integer IDs with more than one digit.
-        (?P<int>\d\d+)
+        (?P<int>[0-9][0-9]+)
         ",
     )
     .unwrap()
 });
 
 pub static DB_SQL_TRANSACTION_CORE_DATA_REGEX: Lazy<Regex> =
-    Lazy::new(|| Regex::new(r"(?P<int>\d+)").unwrap());
+    Lazy::new(|| Regex::new(r"(?P<int>[0-9]+)").unwrap());
 
 pub static DB_SUPABASE_REGEX: Lazy<Regex> = Lazy::new(|| {
     Regex::new(
-        r"(?xi)
+        r"(?x)
         # UUIDs.
-        (?P<uuid>[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}) |
+        (?P<uuid>[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}) |
         # Hexadecimal strings with more than 5 digits.
-        (?P<hex>[a-f0-9]{5}[a-f0-9]+) |
+        (?P<hex>[a-fA-F0-9]{5}[a-fA-F0-9]+) |
         # Integer IDs with more than one digit.
-        (?P<int>\d\d+)
+        (?P<int>[0-9][0-9]+)
         ",
     )
     .unwrap()
 });
 
 pub static FUNCTION_NORMALIZER_REGEX: Lazy<Regex> = Lazy::new(|| {
     Regex::new(
-        r"(?xi)
+        r"(?x)
         # UUIDs.
-        (?P<uuid>[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}) |
+        (?P<uuid>[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}) |
         # Hexadecimal strings with more than 5 digits.
-        (?P<hex>[a-f0-9]{5}[a-f0-9]+)
+        (?P<hex>[a-fA-F0-9]{5}[a-fA-F0-9]+)
         ",
     )
     .unwrap()