fix: correct snake_case conversion for consecutive uppercase letters in Python (#3587)

`mangleIdentifier()` in `src/languages/python.ts` incorrectly converted
camelCase identifiers with consecutive uppercase letters. For example,
`enforceSSL` became `enforce_sSL` instead of `enforce_ssl`.

The root cause was a single regex (`/[^A-Z][A-Z]/g`) that only handled
simple camelCase boundaries. It couldn't detect where an uppercase
acronym ends and the next word begins.

Replaced with a two-step regex approach:
- `([a-z0-9])([A-Z])` — lowercase/digit to uppercase boundary
- `([A-Z]+)([A-Z][a-z])` — end of uppercase run before a new word

| Input | Before | After |
|-------|--------|-------|
| `enforceSSL` | `enforce_sSL` | `enforce_ssl` |
| `myVPCId` | `my_vPCId` | `my_vpc_id` |
| `getHTTPSUrl` | `get_hTTPSUrl` | `get_https_url` |
| `parseJSON` | `parse_jSON` | `parse_json` |

Added 12 test cases covering acronyms, digit boundaries, single
uppercase letters, simple camelCase regression guards, leading
underscores, already-snake_case passthrough, and multiple acronyms.

---

By submitting this pull request, I confirm that my contribution is made
under the terms of the [Apache 2.0 license].

[Apache 2.0 license]: https://www.apache.org/licenses/LICENSE-2.0

Author: alvazjor

src/languages/python.ts

@@ -842,8 +842,13 @@ function mangleIdentifier(originalIdentifier: string) {
     // Probably a class, leave as-is
     return originalIdentifier;
   }
-  // Turn into snake-case
-  const cased = originalIdentifier.replace(/[^A-Z][A-Z]/g, (m) => `${m[0].slice(0, 1)}_${m.slice(1).toLowerCase()}`);
+  // Turn into snake_case by inserting '_' at two kinds of boundary, then lowercasing:
+  // 1. lowercase/digit → uppercase: e.g. myVPCId → my_VPCId, getHTTPSUrl → get_HTTPSUrl
+  // 2. end of uppercase run → new word: e.g. my_VPCId → my_VPC_Id, get_HTTPSUrl → get_HTTPS_Url
+  const cased = originalIdentifier
+    .replace(/([a-z0-9])([A-Z])/g, '$1_$2')
+    .replace(/([A-Z]+)([A-Z][a-z])/g, '$1_$2')
+    .toLowerCase();
   return IDENTIFIER_KEYWORDS.includes(cased) ? `${cased}_` : cased;
 }
 

test/translations/identifiers/consecutive_uppercase.py

@@ -0,0 +1,24 @@
+# enforce_ssl: bool
+# my_vpc_id: str
+# parse_json: str
+# to_json: str
+# ec2_instance_id: str
+# x509_certificate: str
+# get_x: bool
+# some_method: str
+# arn_value: str
+# _private_field: str
+# already_snake: str
+# from_https_to_json: str
+print(enforce_ssl)
+print(my_vpc_id)
+print(parse_json)
+print(to_json)
+print(ec2_instance_id)
+print(x509_certificate)
+print(get_x)
+print(some_method)
+print(arn_value)
+print(_private_field)
+print(already_snake)
+print(from_https_to_json)

test/translations/identifiers/consecutive_uppercase.ts

@@ -0,0 +1,24 @@
+declare const enforceSSL: boolean;
+declare const myVPCId: string;
+declare const parseJSON: string;
+declare const toJSON: string;
+declare const ec2InstanceId: string;
+declare const x509Certificate: string;
+declare const getX: boolean;
+declare const someMethod: string;
+declare const arnValue: string;
+declare const _privateField: string;
+declare const already_snake: string;
+declare const fromHTTPSToJSON: string;
+console.log(enforceSSL);
+console.log(myVPCId);
+console.log(parseJSON);
+console.log(toJSON);
+console.log(ec2InstanceId);
+console.log(x509Certificate);
+console.log(getX);
+console.log(someMethod);
+console.log(arnValue);
+console.log(_privateField);
+console.log(already_snake);
+console.log(fromHTTPSToJSON);