mbuzz 0.1.0__tar.gz → 0.1.1__tar.gz

{mbuzz-0.1.0 → mbuzz-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mbuzz
-Version: 0.1.0
+Version: 0.1.1
 Summary: Multi-touch attribution SDK for Python
 Project-URL: Homepage, https://mbuzz.co
 Project-URL: Documentation, https://mbuzz.co/docs/getting-started

{mbuzz-0.1.0 → mbuzz-0.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "mbuzz"
-version = "0.1.0"
+version = "0.1.1"
 description = "Multi-touch attribution SDK for Python"
 readme = "README.md"
 license = "MIT"

{mbuzz-0.1.0 → mbuzz-0.1.1}/src/mbuzz/middleware/flask.py

@@ -8,6 +8,7 @@ from ..config import config
 from ..context import RequestContext, set_context, clear_context
 from ..cookies import VISITOR_COOKIE, SESSION_COOKIE, VISITOR_MAX_AGE, SESSION_MAX_AGE
 from ..utils.identifier import generate_id
+from ..utils.session_id import generate_deterministic, generate_from_fingerprint
 from ..client.session import create_session
 
 
@@ -55,8 +56,29 @@ def _get_or_create_visitor_id() -> str:
 
 
 def _get_or_create_session_id() -> str:
-    """Get session ID from cookie or generate new one."""
-    return request.cookies.get(SESSION_COOKIE) or generate_id()
+    """Get session ID from cookie or generate deterministic one."""
+    existing = request.cookies.get(SESSION_COOKIE)
+    if existing:
+        return existing
+
+    existing_visitor_id = request.cookies.get(VISITOR_COOKIE)
+    if existing_visitor_id:
+        return generate_deterministic(existing_visitor_id)
+    else:
+        return generate_from_fingerprint(_get_client_ip(), _get_user_agent())
+
+
+def _get_client_ip() -> str:
+    """Get client IP from request headers."""
+    forwarded = request.headers.get("X-Forwarded-For", "")
+    if forwarded:
+        return forwarded.split(",")[0].strip()
+    return request.remote_addr or "unknown"
+
+
+def _get_user_agent() -> str:
+    """Get user agent from request."""
+    return request.headers.get("User-Agent", "unknown")
 
 
 def _set_request_context(visitor_id: str, session_id: str) -> None:

mbuzz-0.1.1/src/mbuzz/utils/session_id.py

@@ -0,0 +1,39 @@
+"""Deterministic session ID generation."""
+
+import hashlib
+import secrets
+import time
+
+SESSION_TIMEOUT_SECONDS = 1800
+SESSION_ID_LENGTH = 64
+FINGERPRINT_LENGTH = 32
+
+
+def generate_deterministic(visitor_id: str, timestamp: int | None = None) -> str:
+    """Generate session ID for returning visitors."""
+    if timestamp is None:
+        timestamp = int(time.time())
+    time_bucket = timestamp // SESSION_TIMEOUT_SECONDS
+    raw = f"{visitor_id}_{time_bucket}"
+    return hashlib.sha256(raw.encode()).hexdigest()[:SESSION_ID_LENGTH]
+
+
+def generate_from_fingerprint(
+    client_ip: str,
+    user_agent: str,
+    timestamp: int | None = None
+) -> str:
+    """Generate session ID for new visitors using IP+UA fingerprint."""
+    if timestamp is None:
+        timestamp = int(time.time())
+    fingerprint = hashlib.sha256(
+        f"{client_ip}|{user_agent}".encode()
+    ).hexdigest()[:FINGERPRINT_LENGTH]
+    time_bucket = timestamp // SESSION_TIMEOUT_SECONDS
+    raw = f"{fingerprint}_{time_bucket}"
+    return hashlib.sha256(raw.encode()).hexdigest()[:SESSION_ID_LENGTH]
+
+
+def generate_random() -> str:
+    """Generate random session ID (fallback)."""
+    return secrets.token_hex(32)

mbuzz-0.1.1/tests/test_session_id.py

@@ -0,0 +1,146 @@
+"""Tests for deterministic session ID generation."""
+
+import pytest
+from mbuzz.utils.session_id import (
+    generate_deterministic,
+    generate_from_fingerprint,
+    generate_random,
+)
+
+
+class TestGenerateDeterministic:
+    sample_visitor_id = "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2"
+    sample_timestamp = 1735500000
+
+    def test_returns_64_char_hex_string(self):
+        result = generate_deterministic(self.sample_visitor_id, self.sample_timestamp)
+        assert len(result) == 64
+        assert all(c in "0123456789abcdef" for c in result)
+
+    def test_is_consistent(self):
+        result1 = generate_deterministic(self.sample_visitor_id, self.sample_timestamp)
+        result2 = generate_deterministic(self.sample_visitor_id, self.sample_timestamp)
+        assert result1 == result2
+
+    def test_same_within_time_bucket(self):
+        # bucket = timestamp / 1800
+        # 1735500000 / 1800 = 964166
+        # 1735500599 / 1800 = 964166 (last second of bucket)
+        timestamp1 = 1735500000
+        timestamp2 = 1735500001
+        timestamp3 = 1735500599
+
+        result1 = generate_deterministic(self.sample_visitor_id, timestamp1)
+        result2 = generate_deterministic(self.sample_visitor_id, timestamp2)
+        result3 = generate_deterministic(self.sample_visitor_id, timestamp3)
+
+        assert result1 == result2
+        assert result1 == result3
+
+    def test_different_across_time_buckets(self):
+        timestamp1 = 1735500000
+        timestamp2 = 1735501800  # Next bucket
+
+        result1 = generate_deterministic(self.sample_visitor_id, timestamp1)
+        result2 = generate_deterministic(self.sample_visitor_id, timestamp2)
+
+        assert result1 != result2
+
+    def test_different_for_different_visitors(self):
+        result1 = generate_deterministic("visitor_a", self.sample_timestamp)
+        result2 = generate_deterministic("visitor_b", self.sample_timestamp)
+
+        assert result1 != result2
+
+
+class TestGenerateFromFingerprint:
+    sample_ip = "203.0.113.42"
+    sample_user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
+    sample_timestamp = 1735500000
+
+    def test_returns_64_char_hex_string(self):
+        result = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, self.sample_timestamp
+        )
+        assert len(result) == 64
+        assert all(c in "0123456789abcdef" for c in result)
+
+    def test_is_consistent(self):
+        result1 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, self.sample_timestamp
+        )
+        result2 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, self.sample_timestamp
+        )
+        assert result1 == result2
+
+    def test_same_within_time_bucket(self):
+        timestamp1 = 1735500000
+        timestamp2 = 1735500001
+
+        result1 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, timestamp1
+        )
+        result2 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, timestamp2
+        )
+
+        assert result1 == result2
+
+    def test_different_across_time_buckets(self):
+        timestamp1 = 1735500000
+        timestamp2 = 1735501800
+
+        result1 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, timestamp1
+        )
+        result2 = generate_from_fingerprint(
+            self.sample_ip, self.sample_user_agent, timestamp2
+        )
+
+        assert result1 != result2
+
+    def test_different_for_different_ips(self):
+        result1 = generate_from_fingerprint(
+            "192.168.1.1", self.sample_user_agent, self.sample_timestamp
+        )
+        result2 = generate_from_fingerprint(
+            "192.168.1.2", self.sample_user_agent, self.sample_timestamp
+        )
+
+        assert result1 != result2
+
+    def test_different_for_different_user_agents(self):
+        result1 = generate_from_fingerprint(
+            self.sample_ip, "Mozilla/5.0 Chrome", self.sample_timestamp
+        )
+        result2 = generate_from_fingerprint(
+            self.sample_ip, "Mozilla/5.0 Safari", self.sample_timestamp
+        )
+
+        assert result1 != result2
+
+
+class TestGenerateRandom:
+    def test_returns_64_char_hex_string(self):
+        result = generate_random()
+        assert len(result) == 64
+        assert all(c in "0123456789abcdef" for c in result)
+
+    def test_returns_unique_ids(self):
+        result1 = generate_random()
+        result2 = generate_random()
+        assert result1 != result2
+
+
+class TestCrossMethod:
+    def test_deterministic_and_fingerprint_produce_different_ids(self):
+        visitor_id = "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2"
+        ip = "203.0.113.42"
+        user_agent = "Mozilla/5.0"
+        timestamp = 1735500000
+
+        deterministic = generate_deterministic(visitor_id, timestamp)
+        fingerprint = generate_from_fingerprint(ip, user_agent, timestamp)
+
+        assert deterministic != fingerprint