create pull request

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

graphify/extract.py

@@ -2075,7 +2075,7 @@ def extract_svelte(path: Path) -> dict:
         # static imports are silently dropped (#713). Regex over each script
         # body recovers them.
         script_re = _re.compile(
-            r"<script\b[^>]*>([\s\S]*?)</script\s*>", _re.IGNORECASE
+            r"<script\b[^>]*>([\s\S]*?)</script(?:\s+[^>]*)?>", _re.IGNORECASE
         )
         static_import_re = _re.compile(
             r"""import\s+(?:[^'"`;]+?\s+from\s+)?['"]([^'"]+)['"]"""
@@ -2133,7 +2133,7 @@ def extract_astro(path: Path) -> dict:
             r"\A\s*---\s*\r?\n([\s\S]*?)\r?\n---\s*(?:\r?\n|\Z)"
         )
         script_re = _re.compile(
-            r"<script\b[^>]*>([\s\S]*?)</script\s*>", _re.IGNORECASE
+            r"<script\b[^>]*>([\s\S]*?)</script\b[^>]*>", _re.IGNORECASE
         )
         static_import_re = _re.compile(
             r"""import\s+(?:[^'"`;]+?\s+from\s+)?['"]([^'"]+)['"]"""

graphify/extractors/dart.py

@@ -16,10 +16,10 @@ def extract_dart(path: Path) -> dict:
 
     # Remove inline and multi-line comments while leaving string literals untouched to prevent stripping URLs/paths inside strings
     comment_string_pattern = re.compile(
-        r'"""(?:\\.|[\s\S])*?"""'
-        r"|'''(?:\\.|[\s\S])*?'''"
-        r'|"(?:\\.|[^"\\])*"'
-        r"|'(?:\\.|[^'\\])*'"
+        r'r?"""(?:\\.|[\s\S])*?"""'  # Add r? to match raw triple-quoted strings
+        r"|r?'''(?:\\.|[\s\S])*?'''"  # Add r? here too
+        r'|r?"(?:\\.|[^"\\])*"'        # Add r? for regular double-quoted
+        r"|r?'(?:\\.|[^'\\])*'"        # Add r? for regular single-quoted
         r"|/\*[\s\S]*?\*/"
         r"|//[^\n]*"
     )

graphify/extractors/resolution.py

@@ -860,7 +860,7 @@ def _resolve_lua_import_target(raw_module: str, str_path: str) -> str:
     return _make_id(raw_module)
 
 _VUE_SCRIPT_RE = re.compile(
-    r"""(<script\b(?:"[^"]*"|'[^']*'|[^>"'])*>)([\s\S]*?)(</script\s*>)""",
+    r"""(<script\b(?:"[^"]*"|'[^']*'|[^>"'])*>)([\s\S]*?)(</script\b[^>]*>)""",
     re.IGNORECASE,
 )
 

graphify/ingest.py

@@ -64,16 +64,18 @@ def _safe_filename(url: str, suffix: str) -> str:
 
 def _detect_url_type(url: str) -> str:
     """Classify the URL for targeted extraction."""
-    lower = url.lower()
-    if "twitter.com" in lower or "x.com" in lower:
+    parsed = urllib.parse.urlparse(url)
+    host = (parsed.hostname or "").lower()
+
+    if host in {"twitter.com", "x.com"} or host.endswith(".twitter.com") or host.endswith(".x.com"):
         return "tweet"
-    if "arxiv.org" in lower:
+    if host == "arxiv.org" or host.endswith(".arxiv.org"):
         return "arxiv"
-    if "github.com" in lower:
+    if host == "github.com" or host.endswith(".github.com"):
         return "github"
-    if "youtube.com" in lower or "youtu.be" in lower:
+    if host == "youtube.com" or host.endswith(".youtube.com") or host == "youtu.be" or host.endswith(".youtu.be"):
         return "youtube"
-    parsed = urllib.parse.urlparse(url)
+
     path = parsed.path.lower()
     if path.endswith(".pdf"):
         return "pdf"

worked/httpx/raw/auth.py

@@ -82,13 +82,21 @@ def _build_credentials(self, request: Request, challenge: dict) -> str:
         """Compute the Authorization header value for a digest challenge."""
         self._nonce_count += 1
         nc = f"{self._nonce_count:08x}"
-        cnonce = hashlib.md5(str(time.time()).encode()).hexdigest()[:8]
         realm = challenge.get("realm", "")
         nonce = challenge.get("nonce", "")
+        algorithm = challenge.get("algorithm", "SHA-256").upper()
 
-        ha1 = hashlib.md5(f"{self.username}:{realm}:{self.password}".encode()).hexdigest()
-        ha2 = hashlib.md5(f"{request.method}:{request.url.path}".encode()).hexdigest()
-        response_hash = hashlib.md5(f"{ha1}:{nonce}:{nc}:{cnonce}:auth:{ha2}".encode()).hexdigest()
+        def _hash_hex(value: str) -> str:
+            data = value.encode()
+            if algorithm in ("SHA-256", "SHA-256-SESS"):
+                return hashlib.sha256(data).hexdigest()
+            raise ValueError(f"Unsupported or weak digest algorithm: {algorithm}")
+
+        cnonce = _hash_hex(str(time.time()))[:8]
+
+        ha1 = _hash_hex(f"{self.username}:{realm}:{self.password}")
+        ha2 = _hash_hex(f"{request.method}:{request.url.path}")
+        response_hash = _hash_hex(f"{ha1}:{nonce}:{nc}:{cnonce}:auth:{ha2}")
 
         return (
             f'Digest username="{self.username}", realm="{realm}", '