sourcecode 1.67.0__py3-none-any.whl → 1.69.0__py3-none-any.whl

sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.67.0"
+__version__ = "1.69.0"

sourcecode/classifier.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import re
 from collections.abc import Iterable, Sequence
 from dataclasses import replace
 from typing import Any, Literal
@@ -104,6 +105,21 @@ class TypeClassifier:
         stack_names = {stack.stack for stack in stacks}
         framework_names = {framework.name for stack in stacks for framework in stack.frameworks}
 
+        # BUG #4 (JobRunr field test): a framework present only in a small optional
+        # integration/adapter submodule must NOT label the whole repo as that
+        # framework's app type. JobRunr is a framework-agnostic background-job
+        # LIBRARY whose `core` module holds ~85% of the code; Quarkus/Micronaut/Spring
+        # appear only in tiny per-framework adapter modules — yet presence-based
+        # classification returned project_type="api"+Quarkus. We weight by code
+        # locality: if the DOMINANT source module (the one with the most source files)
+        # contains no evidence of the app-defining framework, the framework is an
+        # optional adapter and the repo is a library. A monolithic Spring app is
+        # unaffected — its dominant module *does* use the framework. Drop such
+        # localized frameworks from the set that drives the app-type decision below.
+        _app_frameworks = framework_names & (_WEB_FRAMEWORKS | _API_FRAMEWORKS)
+        _localized = self._localized_adapter_frameworks(file_tree, stacks, _app_frameworks)
+        framework_names = framework_names - _localized
+
         if len(stack_names) >= 2 and self._is_fullstack(stacks):
             return "fullstack"
 
@@ -129,9 +145,16 @@ class TypeClassifier:
         if framework_names & _API_FRAMEWORKS:
             return "api"
 
+        # All app-defining frameworks were localized to optional adapter submodules
+        # (multi-module library with per-framework integrations) — report library,
+        # never "unknown", when there is clearly source code present.
+        if _localized and not (framework_names & (_WEB_FRAMEWORKS | _API_FRAMEWORKS)):
+            return "library"
+
+        # Strong CLI signals: a CLI framework or an explicit cli entry point.
         if framework_names & _CLI_FRAMEWORKS or any(
             entry.kind == "cli" for entry in entry_points
-        ) or any(path.startswith("bin/") for path in flat_paths):
+        ):
             return "cli"
 
         if stack_names:
@@ -141,8 +164,105 @@ class TypeClassifier:
             if single in {"cpp", "dotnet"} and any(entry.kind == "cli" for entry in entry_points):
                 return "cli"
 
+        # BUG #4 (JobRunr field test): a multi-module JVM repo with no app-defining
+        # web/API framework is a library/toolkit, not an "unknown" — never let the
+        # first command of an audit emit a vacuous classification for a clearly
+        # structured codebase (e.g. JobRunr: core + per-framework adapter modules).
+        # This is checked BEFORE the weak `bin/`-directory CLI heuristic so a build
+        # output / wrapper `bin/` dir does not mislabel a library as a CLI.
+        if stack_names & {"java", "kotlin", "scala"} and self._is_multi_module(file_tree):
+            return "library"
+
+        # Weak CLI heuristic: a top-level bin/ directory (only when nothing stronger).
+        if any(path.startswith("bin/") for path in flat_paths):
+            return "cli"
+
         return "unknown" if stacks else None
 
+    def _is_multi_module(self, file_tree: dict[str, Any]) -> bool:
+        """True when the repo has >1 source module (distinct `*/src/...` roots)."""
+        _CODE_EXTS = (".java", ".kt", ".kts", ".scala", ".groovy")
+        modules = {
+            self._module_of(p)
+            for p in flatten_file_tree(file_tree)
+            if p.endswith(_CODE_EXTS)
+        }
+        modules.discard("")
+        return len(modules) >= 2
+
+    @staticmethod
+    def _module_of(path: str) -> str:
+        """Group a source path into its module root.
+
+        For Maven/Gradle layouts the module is everything before `/src/`
+        (e.g. `framework-support/jobrunr-quarkus/src/main/java/...` →
+        `framework-support/jobrunr-quarkus`). Otherwise the top-level directory.
+        """
+        norm = path.replace("\\", "/")
+        idx = norm.find("/src/")
+        if idx > 0:
+            return norm[:idx]
+        head, _, tail = norm.partition("/")
+        return head if tail else ""
+
+    _EVIDENCE_PATH_RE = re.compile(r"\(([^()]+)\)\s*$")
+
+    def _localized_adapter_frameworks(
+        self,
+        file_tree: dict[str, Any],
+        stacks: Sequence[StackDetection],
+        candidate_frameworks: set[str],
+    ) -> set[str]:
+        """Frameworks confined to a minority module while a framework-agnostic
+        module dominates the codebase (library + per-framework adapters).
+
+        Returns the subset of ``candidate_frameworks`` that should NOT drive the
+        project-type decision. A framework qualifies only when (a) the repo is
+        multi-module, (b) the framework's evidence files are all outside the
+        dominant source module, and (c) the framework has located evidence files
+        (a manifest-only/root detection applies repo-wide and never localizes).
+        """
+        if not candidate_frameworks:
+            return set()
+
+        _CODE_EXTS = (".java", ".kt", ".kts", ".scala", ".groovy")
+        module_file_counts: dict[str, int] = {}
+        for p in flatten_file_tree(file_tree):
+            if not p.endswith(_CODE_EXTS):
+                continue
+            mod = self._module_of(p)
+            module_file_counts[mod] = module_file_counts.get(mod, 0) + 1
+
+        # Need a genuine multi-module repo to reason about locality.
+        if len(module_file_counts) < 2:
+            return set()
+        dominant_module = max(module_file_counts, key=lambda m: module_file_counts[m])
+
+        # Collect evidence file paths per framework from detected_via.
+        evidence: dict[str, set[str]] = {}
+        for stack in stacks:
+            for fw in stack.frameworks:
+                if fw.name not in candidate_frameworks:
+                    continue
+                paths = evidence.setdefault(fw.name, set())
+                for ev in fw.detected_via:
+                    if ev.startswith("manifest:"):
+                        continue
+                    m = self._EVIDENCE_PATH_RE.search(ev)
+                    if m:
+                        paths.add(m.group(1).strip())
+
+        localized: set[str] = set()
+        for fw_name in candidate_frameworks:
+            files = evidence.get(fw_name) or set()
+            if not files:
+                # No locatable evidence (manifest-only) → applies repo-wide.
+                continue
+            modules = {self._module_of(f) for f in files}
+            if dominant_module not in modules:
+                localized.add(fw_name)
+        return localized
+
     def _is_fullstack(self, stacks: Sequence[StackDetection]) -> bool:
         has_web = False
         has_api = False

sourcecode/cli.py

@@ -5777,14 +5777,32 @@ def modernize_cmd(
         "statically_unreferenced": len(dead_zones),
         "framework_dispatched": len(framework_dispatched),
     }
+    # BUG #6 (v1.68.0): `member_count` counts ALL graph members in the subsystem —
+    # classes, methods AND fields — so it runs ~5x higher than the class count and
+    # is not comparable to the repo-level `total_classes` (which counts only
+    # class/interface nodes). Surface an unambiguous `class_count` alongside it,
+    # computed against the same class/interface node set as total_classes, so a
+    # reader does not have to reverse-engineer the unit. `member_count` is retained
+    # for backward compatibility but is now documented as the graph-member tally.
+    _class_fqns = {n["fqn"] for n in graph_nodes if n.get("type") in ("class", "interface")}
+
+    def _class_count(members: list) -> int:
+        return sum(1 for m in members if m in _class_fqns)
+
     _subsystem_summary = [
         {
             "label": s.get("label") or s.get("name") or "",
             "package_prefix": s.get("package_prefix") or s.get("pkg") or "",
+            "class_count": _class_count(s.get("members") or []),
             "member_count": len(s.get("members") or []),
         }
         for s in subsystems[:15]
     ]
+    _subsystem_summary_note = (
+        "class_count = class/interface declarations only (comparable to "
+        "summary.total_classes). member_count = all graph members in the subsystem "
+        "including methods and fields, so it is larger and not a class tally."
+    )
 
     if (not _mod_is_pro) and _mod_large(str(root)):
         # Large monolith, free tier: structural discovery preview only — no dead
@@ -5801,6 +5819,7 @@ def modernize_cmd(
             ),
             "summary": _summary,
             "subsystem_summary": _subsystem_summary,
+            "subsystem_summary_note": _subsystem_summary_note,
             "hotspot_candidates": hotspots[:3],
             "high_coupling_nodes": [
                 {"fqn": n["fqn"], "in_degree": n.get("in_degree", 0), "role": n.get("role", "other")}
@@ -5833,9 +5852,11 @@ def modernize_cmd(
                 for n in framework_dispatched
             ],
             "subsystem_summary": _subsystem_summary,
+            "subsystem_summary_note": _subsystem_summary_note,
             "cross_module_tangles": [
                 {
                     "label": s.get("label") or s.get("name") or "",
+                    "class_count": _class_count(s.get("members") or []),
                     "member_count": len(s.get("members") or []),
                 }
                 for s in tangle_modules

sourcecode/detectors/java.py

@@ -90,6 +90,19 @@ _GRADLE_JAVA_VERSION_RE = re.compile(
 _GRADLE_JAVA_ENUM_RE = re.compile(
     r"""(?:sourceCompatibility|targetCompatibility)\s*=\s*JavaVersion\.VERSION_(\d+)"""
 )
+# BUG #4: a gradle line that genuinely declares a dependency or plugin. Matches a
+# quoted Maven coordinate (group:artifact, requires the colon), a plugins-block
+# `id '...'`, an `apply plugin:`, or a `classpath`/`platform(`/`enforcedPlatform(`
+# declaration. Deliberately does NOT match `it.name.contains('quarkus')`-style
+# subproject filters (a bare quoted name with no colon and no plugin/dep keyword).
+_GRADLE_DEP_LINE_RE = re.compile(
+    r"""['"][\w.\-]+:[\w.\-]+"""          # maven coordinate "group:artifact..."
+    r"""|\bclasspath\b"""
+    r"""|\b(?:enforced)?platform\s*\("""
+    r"""|\bapply\s+plugin\s*:"""
+    r"""|\bid\s*[('"]""",
+    re.IGNORECASE,
+)
 
 
 class JavaDetector(AbstractDetector):
@@ -279,7 +292,29 @@ class JavaDetector(AbstractDetector):
         original = "\n".join(read_text_lines(path))
         content = original.lower()
         sb_version = self._extract_gradle_sb_version(original)
-        return self._detect_jvm_frameworks(content, "build.gradle", sb_version=sb_version)
+        # BUG #4 (JobRunr field test): framework tokens must be matched only inside
+        # genuine dependency / plugin declarations, never anywhere in the file. A
+        # multi-module root build.gradle that EXCLUDES a subproject by name —
+        # `configure(subprojects.findAll { !it.name.contains('quarkus') })` — must
+        # not be read as "this project uses Quarkus". Restrict the scan to lines
+        # carrying a Maven coordinate / plugin id; the exclusion filter has neither.
+        dep_text = self._gradle_dependency_text(content)
+        return self._detect_jvm_frameworks(dep_text, "build.gradle", sb_version=sb_version)
+
+    @staticmethod
+    def _gradle_dependency_text(content: str) -> str:
+        """Keep only gradle lines that declare a dependency or plugin.
+
+        A real dependency carries a Maven coordinate (`group:artifact`...) and a
+        plugin carries an `id`/`plugin`/`classpath` token. Subproject-name filters
+        and arbitrary prose are dropped, so a framework substring there cannot
+        manufacture a phantom framework detection.
+        """
+        kept: list[str] = []
+        for line in content.splitlines():
+            if _GRADLE_DEP_LINE_RE.search(line):
+                kept.append(line)
+        return "\n".join(kept)
 
     def _extract_gradle_sb_version(self, content: str) -> str | None:
         m = _GRADLE_SB_PLUGIN_RE.search(content)

sourcecode/explain.py

@@ -223,7 +223,89 @@ def _build_purpose(
         if role_anns:
             desc = f"{role_anns[0]} bean"
 
-    return desc or "No stereotype detected — may be a plain class or utility."
+    if desc:
+        return desc
+
+    # BUG #4 (JobRunr field test): with no recognized framework annotation, the old
+    # fallback returned "No stereotype detected — may be a plain class or utility",
+    # which is actively misleading for a central domain class. Libraries and clean/
+    # hexagonal architectures model rich roles WITHOUT DI annotations. Infer a
+    # low-confidence structural role from signals the tool already computes:
+    # in-degree (coupling), lifecycle methods, and naming convention.
+    structural = _structural_purpose(class_fqn, raw_nodes, cir)
+    if structural:
+        return structural
+    return "No stereotype detected — may be a plain class or utility."
+
+
+# Lifecycle method names that signal an orchestrator/component managing state.
+_LIFECYCLE_METHODS = frozenset({
+    "start", "stop", "init", "initialize", "shutdown", "close",
+    "pause", "resume", "run", "destroy", "open", "restart",
+})
+
+# Class-name suffix → inferred role (no annotation required).
+_NAME_ROLE_SUFFIXES: tuple[tuple[str, str], ...] = (
+    ("Server", "server/orchestrator"),
+    ("Manager", "manager/coordinator"),
+    ("Controller", "controller"),
+    ("Service", "service"),
+    ("Repository", "repository/data access"),
+    ("Factory", "factory"),
+    ("Builder", "builder"),
+    ("Handler", "handler"),
+    ("Listener", "listener"),
+    ("Provider", "provider"),
+    ("Registry", "registry"),
+    ("Scheduler", "scheduler"),
+    ("Dispatcher", "dispatcher"),
+    ("Processor", "processor"),
+    ("Filter", "filter"),
+    ("Interceptor", "interceptor"),
+)
+
+
+def _structural_purpose(
+    class_fqn: str,
+    raw_nodes: list[dict],
+    cir: "CanonicalRepositoryIR",
+) -> str:
+    """Infer a low-confidence stereotype from structural signals (no annotations)."""
+    try:
+        in_degree = len(_build_callers(class_fqn, cir))
+    except Exception:
+        in_degree = 0
+
+    try:
+        method_names = {m.split("(")[0].lower() for m in _build_public_methods(class_fqn, raw_nodes)}
+    except Exception:
+        method_names = set()
+    lifecycle = sorted(method_names & _LIFECYCLE_METHODS)
+
+    simple = _simple(class_fqn)
+    role = ""
+    for suffix, label in _NAME_ROLE_SUFFIXES:
+        if simple.endswith(suffix):
+            role = label
+            break
+    if not role and lifecycle:
+        role = "orchestrator/lifecycle component"
+
+    # Require at least one real signal — otherwise stay honestly silent.
+    if not role and in_degree < 3:
+        return ""
+
+    head = f"Likely {role} (no DI annotations found)" if role else \
+        "Likely a structurally significant class (no DI annotations found)"
+    signals: list[str] = []
+    if in_degree >= 3:
+        signals.append(f"high in-degree ({in_degree})")
+    elif in_degree:
+        signals.append(f"in-degree {in_degree}")
+    if lifecycle:
+        signals.append(f"lifecycle methods detected ({'/'.join(lifecycle)})")
+    suffix = f" — {', '.join(signals)}" if signals else ""
+    return f"{head}{suffix} — inferred from structure, not annotations (low confidence)."
 
 
 def _build_public_methods(class_fqn: str, raw_nodes: list[dict]) -> list[str]:

sourcecode/integration_detector.py

@@ -7,8 +7,14 @@ deterministic source-text matching (same approach as the JNDI datasource scan in
 
 Covered clients:
 
-  * HTTP   — ``RestTemplate``, ``WebClient``, ``@FeignClient`` (declarative)
-  * LDAP   — ``LdapTemplate``
+  * HTTP   — ``RestTemplate``, ``WebClient``, ``@FeignClient`` (declarative),
+             JDK/Apache/OkHttp clients
+  * LDAP   — ``LdapTemplate``, JNDI ``InitialLdapContext``/``LdapContext``
+  * DNS    — JNDI ``DirContext`` configured with ``DnsContextFactory`` (BUG #2:
+             ``DirContext`` is protocol-agnostic and is classified by its
+             ``INITIAL_CONTEXT_FACTORY``, not assumed to be LDAP)
+  * SMTP   — JavaMail / Jakarta Mail (BUG #1: gated on a mail import so the bare
+             word "Transport" in a log string is not a false positive)
   * JMS    — ``JmsTemplate``, ActiveMQ connection factories
 
 Each hit is reported with a ``file:line`` evidence anchor and, when a literal URL
@@ -28,6 +34,24 @@ _URL_RE = re.compile(r'"((?:https?|ldaps?|tcp|amqp|jms|nio)://[^"]*)"')
 # First string literal on a line (fallback target, e.g. WebClient.create("x")).
 _STR_RE = re.compile(r'"([^"]+)"')
 
+# BUG #1 (v1.68.0): a JavaMail/Jakarta-Mail import is required before an SMTP token
+# (Transport, MimeMessage) is trusted. The bare word "Transport" is also a common
+# English noun that appears in log strings ( logger.warn("Transport initialization
+# failure") in non-mail code), so a mail-import gate plus a string-literal skip
+# stops those false positives.
+_MAIL_IMPORT_RE = re.compile(
+    r"^\s*import\s+(?:(?:javax|jakarta)\.mail|org\.springframework\.mail)\b",
+    re.MULTILINE,
+)
+
+# BUG #2 (v1.68.0): javax.naming.directory.{DirContext,InitialDirContext} is NOT
+# LDAP-specific — the actual protocol is decided by the value bound to
+# Context.INITIAL_CONTEXT_FACTORY. com.sun.jndi.dns.DnsContextFactory means DNS
+# (SRV/A record lookups), com.sun.jndi.ldap.LdapCtxFactory means LDAP. Classify by
+# the factory class present in the file instead of defaulting to LDAP.
+_DNS_FACTORY_RE = re.compile(r"jndi\.dns|DnsContextFactory", re.IGNORECASE)
+_LDAP_FACTORY_RE = re.compile(r"jndi\.ldap|LdapCtxFactory", re.IGNORECASE)
+
 # Declarative HTTP client. Attrs may span multiple lines, so matched on full text.
 _FEIGN_RE = re.compile(r"@FeignClient\s*\(([^)]*)\)", re.DOTALL)
 _ATTR_URL_RE = re.compile(r'url\s*=\s*"([^"]*)"')
@@ -82,6 +106,39 @@ def _extract_target(line: str) -> Optional[str]:
     return None
 
 
+def _in_string_literal(line: str, idx: int) -> bool:
+    """True if char offset ``idx`` falls inside a double-quoted string on ``line``.
+
+    BUG #1 (v1.68.0): a Java type token never legitimately appears inside a string
+    literal, so a match there (e.g. the word "Transport" in a log message) is noise,
+    not a real client construct. Counts unescaped quotes before ``idx``.
+    """
+    quote_count = 0
+    i = 0
+    while i < idx and i < len(line):
+        ch = line[i]
+        if ch == "\\":
+            i += 2
+            continue
+        if ch == '"':
+            quote_count += 1
+        i += 1
+    return quote_count % 2 == 1
+
+
+def _classify_naming_factory(text: str) -> Optional[str]:
+    """Classify a javax.naming.directory usage by its INITIAL_CONTEXT_FACTORY.
+
+    Returns ``"dns"``, ``"ldap"``, or ``None`` (factory not statically resolvable).
+    See BUG #2 — DirContext alone does not imply LDAP.
+    """
+    if _DNS_FACTORY_RE.search(text):
+        return "dns"
+    if _LDAP_FACTORY_RE.search(text):
+        return "ldap"
+    return None
+
+
 def detect_integrations(file_paths: "list[str]", root: Path) -> dict:
     """Detect outbound integrations across ``file_paths`` (relative to ``root``).
 
@@ -93,18 +150,31 @@ def detect_integrations(file_paths: "list[str]", root: Path) -> dict:
     seen: "set[tuple[str, str, Optional[str], str]]" = set()
     records: "list[dict]" = []
 
-    def _add(kind: str, client: str, target: Optional[str], rel: str, line: int) -> None:
+    def _add(
+        kind: str,
+        client: str,
+        target: Optional[str],
+        rel: str,
+        line: int,
+        confidence: Optional[str] = None,
+    ) -> None:
         evidence = f"{rel}:{line}"
         key = (kind, client, target, evidence)
         if key in seen:
             return
         seen.add(key)
-        records.append({
+        rec = {
             "kind": kind,
             "client": client,
             "target": target,
             "evidence": evidence,
-        })
+        }
+        # Per-record confidence is emitted only when the classification is uncertain
+        # (e.g. a JNDI DirContext whose factory could not be resolved). Confident hits
+        # stay schema-clean without the field.
+        if confidence is not None:
+            rec["confidence"] = confidence
+        records.append(rec)
 
     for rel in file_paths:
         try:
@@ -126,6 +196,10 @@ def detect_integrations(file_paths: "list[str]", root: Path) -> dict:
             )
             _add("http", "feign", target, rel, _line_of(text, m.start()))
 
+        # Per-file context used to disambiguate / gate uncertain tokens (BUG #1/#2).
+        has_mail_import = bool(_MAIL_IMPORT_RE.search(text))
+        naming_factory = _classify_naming_factory(text)
+
         # Token clients — per line, skipping imports/package/comment noise.
         # First pass records the declaration site and any variable name bound to
         # the client, so a later call site (where the URL literal usually lives)
@@ -146,7 +220,28 @@ def detect_integrations(file_paths: "list[str]", root: Path) -> dict:
                 m = token_re.search(line)
                 if not m:
                     continue
-                _add(kind, client, _extract_target(line), rel, lineno)
+                # BUG #1: a token matched inside a string literal (log message, doc
+                # comment text) is never a real client construct — skip it.
+                if _in_string_literal(line, m.start()):
+                    continue
+                confidence: Optional[str] = None
+                # BUG #1: SMTP tokens require a JavaMail/Jakarta-Mail import to be
+                # trusted — "Transport" / "MimeMessage" are too generic otherwise.
+                if kind == "smtp" and not has_mail_import:
+                    continue
+                # BUG #2: javax.naming.directory.{Dir,Initial}Context is protocol-
+                # agnostic. Reclassify by the configured context factory; default to
+                # an explicit low-confidence "unknown" rather than assuming LDAP.
+                if client == "jndi-ldap" and "Dir" in token_re.pattern:
+                    if naming_factory == "dns":
+                        kind, client = "dns", "jndi-dns"
+                    elif naming_factory == "ldap":
+                        kind, client = "ldap", "jndi-ldap"
+                    else:
+                        kind, client, confidence = (
+                            "naming-directory-unknown", "jndi-dircontext", "low",
+                        )
+                _add(kind, client, _extract_target(line), rel, lineno, confidence)
                 tok = m.group(0)
                 # `Type name` (field/local decl) and `name = new Type(` forms.
                 decl = re.search(re.escape(tok) + r"\s+(\w+)\b", line)
@@ -186,9 +281,13 @@ def detect_integrations(file_paths: "list[str]", root: Path) -> dict:
         "confidence": confidence,
         "coverage_note": (
             "Detects HTTP (RestTemplate/WebClient/JDK/Apache/OkHttp), LDAP (Spring "
-            "+ JNDI), SMTP (JavaMail), and JMS client constructs by source-text "
-            "matching. A count of 0 means no such construct was found, not that the "
-            "system has no outbound integrations — runtime/DI-wired clients are not "
-            "statically visible."
+            "+ JNDI), DNS (JNDI DirContext w/ DnsContextFactory), SMTP (JavaMail, "
+            "import-gated), and JMS client constructs by source-text matching. JNDI "
+            "DirContext usage is classified by its INITIAL_CONTEXT_FACTORY (dns vs "
+            "ldap); when the factory is not statically resolvable the kind is "
+            "'naming-directory-unknown' with confidence='low', never assumed LDAP. A "
+            "count of 0 means no such construct was found, not that the system has no "
+            "outbound integrations — runtime/DI-wired clients are not statically "
+            "visible."
         ),
     }

sourcecode/jdk_exports.py

@@ -0,0 +1,26 @@
+"""GENERATED FILE — do not edit by hand.
+
+Allowlist of sun.* / com.sun.* packages exported UNCONDITIONALLY by the
+JDK (no `--add-exports` / `--add-opens` required on classpath or module
+path). Consumed by migrate-check MIG-011 to suppress false positives.
+
+Regenerate with:  python scripts/generate_jdk_exports.py > src/sourcecode/jdk_exports.py
+Generated from:   java version "21.0.10" 2026-01-20 LTS
+"""
+from __future__ import annotations
+
+
+JDK_UNCONDITIONAL_EXPORTS: frozenset[str] = frozenset(
+    {
+        "com.sun.java.accessibility.util",
+        "com.sun.management",
+        "com.sun.net.httpserver",
+        "com.sun.net.httpserver.spi",
+        "com.sun.nio.sctp",
+        "com.sun.security.auth",
+        "com.sun.security.auth.callback",
+        "com.sun.security.auth.login",
+        "com.sun.security.auth.module",
+        "com.sun.security.jgss",
+    }
+)

sourcecode/migrate_check.py

@@ -23,6 +23,7 @@ from pathlib import Path
 from typing import Optional, TYPE_CHECKING
 
 from sourcecode.path_filters import is_test_or_fixture_path
+from sourcecode.jdk_exports import JDK_UNCONDITIONAL_EXPORTS
 
 if TYPE_CHECKING:
     from sourcecode.hibernate_strat import HibernateStratification
@@ -381,15 +382,22 @@ _JAVA_9_RULES: list[_Rule] = [
         severity="high",
         title="JDK internal API imports (sun.* / com.sun.net.*) — strong encapsulation since Java 9",
         explanation=(
-            "Imports from sun.* and com.sun.net.* reference JDK-internal APIs that are "
-            "not part of the public specification. Since Java 9 (JPMS), these packages are "
-            "strongly encapsulated and require --add-exports / --add-opens JVM flags, "
-            "which are cumbersome and may be removed in future Java releases."
+            "Imports from sun.* and com.sun.* (tools/jdi/source internals) reference "
+            "JDK-internal APIs that are not part of the public specification. Since Java 9 "
+            "(JPMS), these packages are strongly encapsulated and require --add-exports / "
+            "--add-opens JVM flags, which are cumbersome and may be removed in future Java "
+            "releases. Packages the JDK exports UNCONDITIONALLY (e.g. com.sun.net.httpserver "
+            "in jdk.httpserver, com.sun.management in jdk.management) are NOT flagged: they "
+            "need no JVM flags on any classpath or module path."
         ),
         fix_hint=(
             "Replace internal API usage with public equivalents. "
-            "For com.sun.net.httpserver, migrate to java.net.http.HttpServer or a framework. "
-            "Add '--add-exports java.base/sun.misc=ALL-UNNAMED' only as a last resort."
+            "For sun.misc.Unsafe migrate to java.lang.invoke.VarHandle; for com.sun.tools.* "
+            "use the public javax.tools / java.compiler API. "
+            "Add '--add-exports java.base/sun.misc=ALL-UNNAMED' only as a last resort. "
+            "Note: unconditionally-exported packages (com.sun.net.httpserver, "
+            "com.sun.management, com.sun.security.auth, ...) are auto-excluded — they are "
+            "public, stable, and require no migration."
         ),
         migration_target="java_9_plus",
         openrewrite_recipe=None,
@@ -585,6 +593,45 @@ def _is_no_migrate_javax(fqn: str) -> bool:
     return any(fqn.startswith(p) for p in _JAKARTA_NO_MIGRATE_PREFIXES)
 
 
+# BUG #1 (JobRunr field test): MIG-011 flags `sun.*` / `com.sun.*` imports as
+# strongly-encapsulated JDK internals on a pure PREFIX heuristic. That is wrong
+# for packages the JDK exports UNCONDITIONALLY (no `to` clause) — e.g.
+# `com.sun.net.httpserver` (module jdk.httpserver, public since Java 6, the basis
+# of JEP 408) or `com.sun.management` (jdk.management, JMX/diagnostics). These
+# need NO `--add-exports` / `--add-opens` on any classpath or module path, so they
+# must not be flagged `high` / `manual_migration`. The allowlist is generated from
+# the running JDK by scripts/generate_jdk_exports.py (see sourcecode/jdk_exports.py),
+# never hand-maintained. Genuinely-internal packages (sun.misc.Unsafe, com.sun.tools.*,
+# com.sun.jdi.*, com.sun.source.*) are NOT in the allowlist and keep `high` severity.
+
+
+def _import_package(fqn: str) -> str:
+    """Extract the Java package of an import FQN.
+
+    Packages are lowercase by convention and types are Capitalized, so the
+    package is the maximal prefix of non-type segments. Handles wildcard
+    (`a.b.*`) and `static` imports. Conservative: an unrecognized shape yields
+    the leading lowercase run, never a broader prefix — so a sub-package like
+    `com.sun.management.internal` is never confused with `com.sun.management`.
+    """
+    fqn = fqn.strip().rstrip(";").strip()
+    if fqn.startswith("static "):
+        fqn = fqn[len("static "):].strip()
+    if fqn.endswith(".*"):
+        return fqn[:-2]
+    pkg_parts: list[str] = []
+    for seg in fqn.split("."):
+        if seg[:1].isupper():  # first type segment — package ends here
+            break
+        pkg_parts.append(seg)
+    return ".".join(pkg_parts)
+
+
+def _is_jdk_unconditional_export(fqn: str) -> bool:
+    """True if an import targets a package the JDK exports unconditionally."""
+    return _import_package(fqn) in JDK_UNCONDITIONAL_EXPORTS
+
+
 # BUG #8: autogenerated source markers — path fragments and the JSR-250 marker.
 _GENERATED_PATH_FRAGMENTS: tuple[str, ...] = (
     "/generated-sources/", "/generated/", "/target/generated",
@@ -1631,6 +1678,53 @@ def _refine_mig006(matched_imports: list[str]) -> tuple[str, str]:
     )
 
 
+# ---------------------------------------------------------------------------
+# BUG #3 (v1.68.0): framework-gated narrative.
+# MIG-* explanations are written assuming a Spring Boot 2→3 upgrade because that is
+# the overwhelmingly common Jakarta-migration context. On a repo where the tool has
+# already determined spring_present=False (plain Jakarta EE, JAX-RS/Jersey, Quarkus,
+# Guice, ...), the underlying javax→jakarta finding is still valid, but prose that
+# says "Spring Boot 3 requires ..." is factually wrong for that repo and misleads any
+# reader who trusts the narrative over the structured spring_present field.
+#
+# Treat the narrative as a pure function of the structured data: when spring_present
+# is False, rewrite Spring-specific framing into framework-neutral Jakarta-EE /
+# servlet-container framing. Ordered phrase map first (keeps nice sentences for the
+# common phrasings), then a catch-all so no "Spring Boot" string can survive.
+# ---------------------------------------------------------------------------
+_NON_SPRING_EXPLANATION_SUBS: tuple[tuple[str, str], ...] = (
+    ("Spring Boot 3 bundles Jakarta Servlet 6.0.",
+     "Modern servlet containers (Jetty 12+, Tomcat 11+) require Jakarta Servlet 6.0."),
+    ("Spring Boot 3 requires Jakarta Servlet 5.0+",
+     "Jakarta EE 9+ servlet containers require Jakarta Servlet 5.0+"),
+    ("Spring Boot 3 uses Jakarta EE 9 which moved",
+     "Jakarta EE 9 moved"),
+    ("Spring Boot 3 uses Hibernate Validator 8.x which implements jakarta.validation.",
+     "Jakarta EE 9+ uses Hibernate Validator 8.x which implements jakarta.validation."),
+    ("Spring Boot 3 depends on Jakarta Transactions (jakarta.transaction).",
+     "Jakarta EE 9+ uses Jakarta Transactions (jakarta.transaction)."),
+    ("Spring Boot 3 requires Hibernate 6",
+     "Jakarta Persistence (JPA 3.x) requires Hibernate 6"),
+    ("Spring Boot 3 cache abstraction. Spring Boot 3 requires EhCache 3.x",
+     "Jakarta-EE cache abstraction. The modern JCache provider requires EhCache 3.x"),
+    # Catch-all: any remaining Spring-Boot framing → generic Jakarta EE 9+.
+    ("Spring Boot 3", "Jakarta EE 9+"),
+    ("Spring Boot 2", "the pre-Jakarta (javax) baseline"),
+)
+
+
+def _neutralize_non_spring_explanation(text: str) -> str:
+    """Rewrite Spring-specific migration prose into framework-neutral Jakarta framing.
+
+    Applied only when the report's spring_present is False. Deterministic phrase
+    substitution — no model, no guess. Guarantees the returned text contains no
+    "Spring Boot" framing that the structured data does not support.
+    """
+    for needle, repl in _NON_SPRING_EXPLANATION_SUBS:
+        text = text.replace(needle, repl)
+    return text
+
+
 def _scan_file(
     source: str,
     rel_path: str,
@@ -1651,6 +1745,16 @@ def _scan_file(
             # javax.annotation.processing.*, ...). These do NOT migrate to jakarta.
             if matches and rule.migration_target == "jakarta":
                 matches = [m for m in matches if not _is_no_migrate_javax(m.group(1).strip())]
+            # BUG #1: MIG-011 prefix heuristic must not flag sun.*/com.sun.* packages
+            # the JDK exports unconditionally (no --add-exports/--add-opens needed).
+            # Drop those imports; if none remain, the file produces no MIG-011 finding
+            # (so it never inflates blocking_count / effort). Genuinely-internal
+            # packages are absent from the allowlist and survive as `high`.
+            if matches and rule.id == "MIG-011":
+                matches = [
+                    m for m in matches
+                    if not _is_jdk_unconditional_export(m.group(1).strip())
+                ]
             if matches:
                 import_first_line = source[: matches[0].start()].count("\n") + 1
                 matched_imports = [m.group(1) for m in matches]
@@ -1822,6 +1926,15 @@ def run_migrate_check(
     for f in all_findings:
         f.code_context = _classify_code_context(f)
 
+    # BUG #3 (v1.68.0): on a non-Spring repo, rewrite Spring-Boot-specific framing in
+    # every finding's explanation into framework-neutral Jakarta-EE framing. The
+    # finding itself (javax→jakarta) stays; only the prose is corrected so it matches
+    # the structured spring_present=False signal in the same report.
+    if not spring_present:
+        for f in all_findings:
+            if f.explanation:
+                f.explanation = _neutralize_non_spring_explanation(f.explanation)
+
     # Hibernate 5→6 stratification (independent of min_severity — it is its own
     # risk model, not a severity-filtered finding stream).
     from sourcecode.hibernate_strat import analyze_hibernate

sourcecode/repository_ir.py

@@ -20,7 +20,7 @@ import subprocess
 from collections import deque
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Any, Optional
+from typing import Any, Iterable, Optional
 
 from sourcecode.fqn_utils import normalize_owner_fqn as _normalize_owner_fqn
 from sourcecode.path_filters import is_test_path as _is_test_path
@@ -3366,9 +3366,20 @@ def build_repo_ir(
                 and not _INHERIT_PRESCAN_RE.search(source):
             pkg_m = _PKG_RE.search(source)
             _pkg = pkg_m.group(1) if pkg_m else ""
-            # Minimal class-name symbols for same-package map (no methods/fields)
+            # Minimal class-name symbols for same-package map (no methods/fields).
+            # BUG #2 (JobRunr field test): this fast-path regex previously ran over RAW
+            # source, so prose inside Javadoc/comments and string literals (e.g.
+            # "This class provides the entry point", "...the interface is Serializable
+            # ...instead.") was tokenized into phantom type symbols like
+            # `org.jobrunr.configuration.provides`. Those leaked into the symbol graph
+            # and every consumer of it (modernize statically_unreferenced /
+            # framework_dispatched, impact, export --c4). Strip comments AND string
+            # literals before scanning so only real declarations are captured. The name
+            # must also start uppercase ([A-Z]) — Java type convention, matching the
+            # precision of the full _CLASS_DECL_RE used on annotated files.
+            _decl_source = _STRING_LITERAL_RE.sub('', _strip_java_comments(source))
             _min_syms: list[SymbolRecord] = []
-            for _cm in re.finditer(r'(?:class|interface|enum)\s+(\w+)', source):
+            for _cm in re.finditer(r'\b(?:class|interface|enum)\s+([A-Z]\w*)', _decl_source):
                 _cls_name = _cm.group(1)
                 _fqn = f"{_pkg}.{_cls_name}" if _pkg else _cls_name
                 _min_syms.append(SymbolRecord(
@@ -4023,6 +4034,27 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
     _SERVLET_RE = _re.compile(r"\bextends\s+\w*HttpServlet\b")
     _nonspring: dict[str, int] = {"webscripts": 0, "jax_rs": 0, "servlets": 0}
 
+    # BUG #3 (JobRunr field test): imperative router-DSL routes. Lightweight HTTP
+    # frameworks that deliberately avoid Spring/JAX-RS (JobRunr's own dashboard
+    # handler, Javalin, Spark Java, hand-rolled routers) register routes as method
+    # calls `get("/path", handler)` / `post(...)` instead of annotations, so the
+    # annotation surface above never sees them and `endpoints` returns 0 — a silent
+    # total false negative that also disables the `validation` command downstream.
+    # Detection is by SYNTACTIC SHAPE (no framework knowledge): an HTTP-verb method
+    # name, a first argument that is a string literal looking like a path (starts
+    # with "/", may contain :param / {param}), AND a second argument (the trailing
+    # comma) — the comma is what distinguishes a route registration from a 1-arg
+    # getter such as Map.get("/k"). Matches both bare `get(...)` (static-import /
+    # Spark style) and `app.get(...)` (Javalin style); the lookbehind only rejects
+    # an identifier char so `forget(` is not mistaken for `get(`. Reported at
+    # confidence "medium" — an occasional flagged false positive beats a total
+    # silent false negative.
+    _DSL_ROUTE_RE = _re.compile(
+        r'(?<![A-Za-z0-9_])(get|post|put|delete|patch|head|options)\s*\(\s*'
+        r'"(/[^"\s]*)"\s*,'
+    )
+    _dsl_routes: list[dict] = []
+
     for jf in java_files:
         try:
             source = jf.read_text(encoding="utf-8", errors="replace")
@@ -4051,6 +4083,27 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
                 if m:
                     extends_map[sym.symbol] = m.group(1)
 
+        # BUG #3: scan for imperative router-DSL route registrations. Strip comments
+        # first so commented-out / example routes don't leak in. The enclosing class
+        # is the first class/interface symbol in the file (route DSLs live in one
+        # handler class); fall back to the file stem when none was extracted.
+        _dsl_src = _strip_java_comments(source)
+        _dsl_matches = list(_DSL_ROUTE_RE.finditer(_dsl_src))
+        if _dsl_matches:
+            _cls_fqn = next(
+                (s.symbol for s in symbols if s.type in ("class", "interface")), None
+            )
+            _cls_simple = (
+                _cls_fqn.split(".")[-1] if _cls_fqn else Path(rel).stem
+            )
+            for _m in _dsl_matches:
+                _dsl_routes.append({
+                    "method": _m.group(1).upper(),
+                    "path": _m.group(2),
+                    "controller": _cls_simple,
+                    "effective_class": _cls_fqn or _cls_simple,
+                })
+
     routes = _build_route_surface(
         all_symbols, route_diffs=None, extends_map=extends_map,
         custom_security=_custom_sec_tuple,
@@ -4226,6 +4279,32 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
             if e.get("security", {}).get("policy") == "none_detected"
         )
 
+    # BUG #3: merge imperative router-DSL endpoints. Dedup against the annotation
+    # surface (method+path) in case a handler is both annotated and DSL-registered.
+    # These carry confidence "medium" (no unambiguous annotation) and explicit
+    # provenance so a consumer can tell shape-detected routes from annotated ones.
+    if _dsl_routes:
+        _seen_mp = {(e.get("method"), e.get("path")) for e in endpoints}
+        for _r in _dsl_routes:
+            _key = (_r["method"], _r["path"])
+            if _key in _seen_mp:
+                continue
+            _seen_mp.add(_key)
+            endpoints.append({
+                "method": _r["method"],
+                "path": _r["path"],
+                "controller": _r["controller"],
+                "handler": _r["controller"],
+                "return_type": "unknown",
+                "security": {"policy": "none_detected"},
+                "confidence": "medium",
+                "source": "router_dsl",
+            })
+        no_security_signal = sum(
+            1 for e in endpoints
+            if e.get("security", {}).get("policy") == "none_detected"
+        )
+
     # Append spec-recovered endpoints AFTER the security-model heuristics (which
     # are about annotation/filter/XML coverage of scanned source) so spec-sourced
     # entries don't skew those signals. They carry their own source provenance.
@@ -4700,9 +4779,16 @@ def compute_blast_radius(
         )
         if is_mapper and fqn not in _seen_mapper_fqns:
             _seen_mapper_fqns.add(fqn)
+            # BUG #5 (v1.68.0): distinguish a CONFIRMED persistence mapper (a
+            # @Repository/DAO role or a MyBatis @Mapper interface) from a class that
+            # only matched the name pattern (e.g. AzToRegionMapper — an AWS topology
+            # mapper with no data layer). Only confirmed entries may be described as
+            # "persistence" in the narrative.
+            _is_persistence = role in _MAPPER_ROLES or symbol_kind == "mapper_interface"
             _mapper_entry: dict = {
                 "fqn": fqn,
                 "role": role or ("mapper" if symbol_kind == "mapper_interface" else "repository"),
+                "mapper_kind": "persistence" if _is_persistence else "name_heuristic",
                 "source_file": node_dict.get("source_file") or "",
             }
             if canonical != fqn:
@@ -4841,18 +4927,33 @@ def compute_blast_radius(
         _parts.append(f"{n_ep} endpoint{'s' if n_ep != 1 else ''} exposed")
     if n_txn:
         _parts.append(f"{n_txn} transactional boundary{'s' if n_txn != 1 else ''} touched")
-    if n_mappers:
-        _parts.append(f"{n_mappers} persistence path{'s' if n_mappers != 1 else ''} in blast cone")
+    # BUG #5 (v1.68.0): only confirmed persistence mappers earn the word "persistence".
+    # Name-heuristic matches (e.g. *Mapper utility classes with no data layer) are
+    # surfaced as neutral "data-mapping class(es)" so the prose never invents a
+    # persistence tier the repo does not have.
+    _n_persist = sum(1 for m in mappers_affected if m.get("mapper_kind") == "persistence")
+    _n_heur = n_mappers - _n_persist
+    if _n_persist:
+        _parts.append(f"{_n_persist} persistence path{'s' if _n_persist != 1 else ''} in blast cone")
+    if _n_heur:
+        _parts.append(f"{_n_heur} data-mapping class{'es' if _n_heur != 1 else ''} in blast cone")
     if n_sec:
         _parts.append(f"{n_sec} security-gated endpoint{'s' if n_sec != 1 else ''} affected")
     if n_modules > 1:
         _parts.append(f"impact crosses {n_modules} modules")
 
+    # BUG #4 (v1.68.0): derive the DI-framework label ONCE from caller evidence and
+    # reuse it for both the short explanation and the long via_interface_note, so the
+    # two never disagree (the old code hardcoded "Spring/CDI" in one and "Spring/CDI/
+    # Guice" in the other). When the actual framework is identifiable from the caller
+    # FQNs (e.g. *.guice.* packages on a Guice repo), name it specifically instead of
+    # a generic guess.
+    _di_label = _detect_di_framework_label(direct_callers)
     if _iface_bridging:
         _iface_names = [b["interface"].split(".")[-1] for b in _iface_bridging]
         _parts.append(
             f"callers resolved via interface{'s' if len(_iface_names) > 1 else ''} "
-            f"({', '.join(_iface_names)}) — Spring/CDI DI pattern"
+            f"({', '.join(_iface_names)}) — {_di_label} DI pattern"
         )
 
     # Transparency: hub-class BFS truncation must appear in explanation so the
@@ -4924,9 +5025,9 @@ def compute_blast_radius(
     if _iface_bridging:
         out["via_interface_resolution"] = _iface_bridging
         out["via_interface_note"] = (
-            "Target is a concrete class injected via interface(s) in DI frameworks "
-            "(Spring/CDI/Guice). direct_callers includes callers of the implemented "
-            "interface(s) — these are the real production dependents."
+            "Target is a concrete class injected via interface(s) in a "
+            f"{_di_label} DI framework. direct_callers includes callers of the "
+            "implemented interface(s) — these are the real production dependents."
         )
     if _bfs_truncated:
         out["bfs_truncation_reason"] = "hub_class_depth_cap"
@@ -5106,3 +5207,31 @@ def _all_callers_from_rg(fqn: str, reverse_graph: dict[str, dict[str, list[str]]
 def _simple_name(fqn: str) -> str:
     """Extract the simple class name from a fully-qualified name."""
     return fqn.split(".")[-1].split("#")[0]
+
+
+def _detect_di_framework_label(caller_fqns: "Iterable[str]") -> str:
+    """Name the DI framework(s) evidenced by the caller FQNs (BUG #4, v1.68.0).
+
+    Returns a "/"-joined label of the frameworks actually identifiable from the
+    callers' package names (e.g. "Guice" when callers live under a ``*.guice.*``
+    package, "Spring" under ``org.springframework``). When nothing is identifiable
+    the label degrades to the generic "Spring/CDI/Guice" rather than asserting a
+    framework the evidence does not support. The same label feeds both the short
+    explanation and the long via_interface_note so they cannot disagree.
+    """
+    frameworks: set[str] = set()
+    for fqn in caller_fqns:
+        low = fqn.lower()
+        if "guice" in low or "com.google.inject" in low:
+            frameworks.add("Guice")
+        if "springframework" in low or ".spring." in low:
+            frameworks.add("Spring")
+        if "jakarta.enterprise" in low or "javax.enterprise" in low or ".cdi." in low:
+            frameworks.add("CDI")
+        if "micronaut" in low:
+            frameworks.add("Micronaut")
+        if "dagger" in low:
+            frameworks.add("Dagger")
+    if frameworks:
+        return "/".join(sorted(frameworks))
+    return "Spring/CDI/Guice"

{sourcecode-1.67.0.dist-info → sourcecode-1.69.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.67.0
+Version: 1.69.0
 Summary: Persistent structural context and ultra-fast repeated analysis for AI coding agents
 License-File: LICENSE
 Keywords: agents,ai,codebase,context,developer-tools,llm

{sourcecode-1.67.0.dist-info → sourcecode-1.69.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sourcecode/__init__.py,sha256=PwGPkSaAcBTadA2mRPMQcETHoR9cW1WtQrx9s5Clpqw,103
+sourcecode/__init__.py,sha256=mxqKQ416I6lEnKsI6lwjPPRQY5VpPWrIc3-FB4IRfK8,103
 sourcecode/adaptive_scanner.py,sha256=XffluXKzJUXrMtjEiAOnSNPZnztdIcts17T9ouHeID0,10521
 sourcecode/architecture_analyzer.py,sha256=liCwQmLgb5vplohy8arjYxs_HOIv5C9MjLh_gY6bc5Q,44115
 sourcecode/architecture_summary.py,sha256=z34_6v7cSwy98cof2UVciGho7SCrZ93tiqMmq5WNzRQ,20405
@@ -6,8 +6,8 @@ sourcecode/ast_extractor.py,sha256=sa6CmLpn-k5G3_Hzxn8hAlZ5-TS-EVzXDD0Gvxd2jzs,5
 sourcecode/cache.py,sha256=1V3vsaODAa2UBJAC0xpvxpmRdriCezQx5Q8JCcfgziE,31892
 sourcecode/canonical_ir.py,sha256=DEwucOPJguLsVtg5cV8mWXNi112l5jmBhv73KGGebVk,24849
 sourcecode/cir_graphs.py,sha256=9G0HHj1kw2325IDyzo2OpX73BNswEckecf4MZUXB4JM,12078
-sourcecode/classifier.py,sha256=hKzg-nQ47htqqIUzSGvYxv15cXrA3KgICTwJmdqal0o,8095
-sourcecode/cli.py,sha256=lVkoLKPfPPJT5YGr1_IskcAKfQ0Qvfc-zRF5xF8WTjc,281985
+sourcecode/classifier.py,sha256=YTTCoRdcLEFRVcql9Ow1dE7eYQj0jq2rgx32bRDnb1k,13852
+sourcecode/cli.py,sha256=VqAiGRauTO-s8yBJh2JMldha3VKx0jTXC0tOvRpWQkI,283297
 sourcecode/code_notes_analyzer.py,sha256=EJemNCNc9Dn-1RZYu-aNbK0ELzmsyC4s6FdHi3XyNEI,9392
 sourcecode/confidence_analyzer.py,sha256=_jckZSxksV-OU38vbkxfVNBnWCtlCq8Vwfg23x1uspA,19054
 sourcecode/context_scorer.py,sha256=QpChSpsmaAYz91rXA4Ue5xzQmNz_ZboZN09YOHScq1U,14679
@@ -20,7 +20,7 @@ sourcecode/doc_analyzer.py,sha256=05bjTUbDbmnbajD_cgRnACzS8T7xxBKVX4CjkJlhZg8,24
 sourcecode/entrypoint_classifier.py,sha256=jhTYlyqDJH2AtdEcLVaRU3lYRTJuF8DkxVzl4-W3zWE,5322
 sourcecode/env_analyzer.py,sha256=aNTyYgQk5noJDfJU6FmasmESOHfiomyJw5EvZqjy6qc,22213
 sourcecode/error_schema.py,sha256=uwosfNaSujtYm11_732Hu92z5ITV040fQDaIyefSvR4,1683
-sourcecode/explain.py,sha256=dVG35YBlpRmbtOXSmspEhoIwDMVApPmLISBy3iigUSc,16913
+sourcecode/explain.py,sha256=GbcruAyzlmseV3o2rjeyxGQxToCfSYHJjKG3N05NVbQ,19897
 sourcecode/file_chunker.py,sha256=3vkM3mDQ5eE_yTPvUgjyjpGFBIjkW6_mrBmIbrylnA8,16444
 sourcecode/file_classifier.py,sha256=A0fEABqtfVu1MfoaxnPAvGpZgneGgVXlJDhT74NYXxE,15314
 sourcecode/flow_analyzer.py,sha256=dSiuY4w49k29jW_EPXUOND9B5uVbuCA7kjnuHi-pIWA,28781
@@ -29,11 +29,12 @@ sourcecode/fqn_utils.py,sha256=XLU7zDkNBXz_RZkIUNfpPmp1nekWtqP-fxV92tDV1vg,2158
 sourcecode/git_analyzer.py,sha256=JStxTQXNjBWi_wLdwhsZs9mT-v50cSJIz4Agzn6Kh9I,13362
 sourcecode/graph_analyzer.py,sha256=DHR8fY69oU_Pi4SYaWboX6EoEFrctQKB9dsjpqwGMzw,62403
 sourcecode/hibernate_strat.py,sha256=ZyI0sikxh7IemU8uqn1Z73z-tHeFeCJuYhJnyQL8pzU,57765
-sourcecode/integration_detector.py,sha256=mQulsXN1P-4V_3ueh3xy_N9x3Aqlvm7GQ-3YGqlBEYM,8223
+sourcecode/integration_detector.py,sha256=ygZwXHJXJ4QM6oiqKb5S6WIfElByDYdz9moyuFlZpYI,12997
+sourcecode/jdk_exports.py,sha256=fCrlwNAXUT9gge_joq6kMnY3zJxYB2pxqy-0w3o3MJI,874
 sourcecode/license.py,sha256=wckiLuiwaE35KMCStUf1gYzleJuFe6qsSyxUQJvit3s,23500
 sourcecode/mcp_nudge.py,sha256=5ELU_ixzh6uA83NXLOZT8h00OhL53okfQdji3jyKOjg,2917
 sourcecode/metrics_analyzer.py,sha256=m0ENgtqKeBL17kUIK3fmGkgo7UfXBNHxCMj0H_Y5K7c,22750
-sourcecode/migrate_check.py,sha256=psBbL8P7vz8LUtWr0ykoKfUhDb9ss8_J3SB6UUHbMHo,88702
+sourcecode/migrate_check.py,sha256=QNyFmrEqYUSqmi0iIQ1P6oI63g8prOluSvYA5fUJ7Ow,95040
 sourcecode/openapi_surface.py,sha256=BTt0K-woZbkbWTN77IkqeBm_Okag9owR0848fmot8sk,16207
 sourcecode/output_budget.py,sha256=Js9yUlfQtPhqBl9R6wn_9UHVjjJc3GtLcqyfjf5t50Q,9869
 sourcecode/path_filters.py,sha256=VnaD9jxZVNzluackNSTCdIddwzAqIseuSCs_A-gpCDM,6898
@@ -46,7 +47,7 @@ sourcecode/redactor.py,sha256=SB4hwIvg8h-hvcqKcDWaZvA-aSyn-at-BIRwa0tUv5E,3227
 sourcecode/relevance_scorer.py,sha256=0AgEt4KrV73nioMqBgjhGjtY7L2C7L7cSyKtj3IKcrw,9408
 sourcecode/rename_refactor.py,sha256=h6dNFlB9aZ_3q6heeHBkgXQeXaT03nvPSsYH6P8qxFg,12965
 sourcecode/repo_classifier.py,sha256=FG1vaWKdWXsWdl-S8hjVMiTqcwgaRXkDyvK4rPcOGtQ,22681
-sourcecode/repository_ir.py,sha256=iwSE9JewlBkLuAFNDF5GgBPMKXPvf_hAxnLQrgeQX9Y,222027
+sourcecode/repository_ir.py,sha256=tP9L8v9K2xg-xb93N1aELJP-pHHxww8537GZ7Sf0_94,229324
 sourcecode/ris.py,sha256=RcqLVwC-doFcKKViYDkCjZLBqf_wzLES7-F6vHEeWzE,20419
 sourcecode/runtime_classifier.py,sha256=uTAD6BDCiBLUZEDRfqk718kM4RTT_vAbfkcOI2_Xx58,18432
 sourcecode/scanner.py,sha256=WdOQ78mMzjR1NjmKTlbxdgwinnCTfAhxCVLBEFQiFHU,8899
@@ -75,7 +76,7 @@ sourcecode/detectors/elixir.py,sha256=jCpvt5Yi6jvplc80ovRtWh17q-11ZGo9qX7o8b57TJ
 sourcecode/detectors/go.py,sha256=2r66uRQfeTWsqxr4HDhT6vExZErby0t46QXLHVBRv9w,2782
 sourcecode/detectors/heuristic.py,sha256=7cRxrip4yIaggYzZJB6ef8yHKh-gHgiH_pXMFcjlyFU,3723
 sourcecode/detectors/hybrid.py,sha256=IGFRUVsAZ1ooRlFdznCeJAV6vy1yVDx-VyghvLtddXc,9101
-sourcecode/detectors/java.py,sha256=HZcK94A3FzhTMXveicKSSDJBvRbgeqnflEP_mPgaOpo,30438
+sourcecode/detectors/java.py,sha256=V9Eb2EMqEdonIhoegvFN2-z95R4Nu9q2y9G54baWShc,32298
 sourcecode/detectors/jvm_ext.py,sha256=EgHJ5W8EE-ZTN9V607mVzohyKgZE8Mc2jCi-DF8RAZU,2616
 sourcecode/detectors/nodejs.py,sha256=Hg3Gmr7yIMJFiLoDwOTk2wtu00wxIs6kZf-oQujTFUA,13187
 sourcecode/detectors/parsers.py,sha256=ugPg8yNUf0Ai1gA7Fnn6wAkYGFjTxRodSP3IeViYJJ4,2290
@@ -103,8 +104,8 @@ sourcecode/telemetry/consent.py,sha256=H5z2Wu63pZqbaKucRPoJQJ0zCo4cke9ZlBrJC-MaW
 sourcecode/telemetry/events.py,sha256=LtzYfaX9Ilckj5PTvAcTpDa9mLqDsYPDUiDkRa58piY,2580
 sourcecode/telemetry/filters.py,sha256=NHa5T-6DaZduQPFuC34jOqHWQgSizM-Ygq8aZ4j19ng,5834
 sourcecode/telemetry/transport.py,sha256=4gGHsq0WeY9VywEZXA3vUxykfiYnw9uuqfjAAec7F8o,1681
-sourcecode-1.67.0.dist-info/METADATA,sha256=2UUp86qduBBVjyFuifvdUOmahDSseKPyZ8rsy7j2P8g,47341
-sourcecode-1.67.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-sourcecode-1.67.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
-sourcecode-1.67.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
-sourcecode-1.67.0.dist-info/RECORD,,
+sourcecode-1.69.0.dist-info/METADATA,sha256=s7Ko18CIs4SrMOMsNrqCkc-nFZLcxTnC0M_r0zxXycU,47341
+sourcecode-1.69.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+sourcecode-1.69.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
+sourcecode-1.69.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
+sourcecode-1.69.0.dist-info/RECORD,,