sourcecode 1.4.0__py3-none-any.whl → 1.6.0__py3-none-any.whl

sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.4.0"
+__version__ = "1.6.0"

sourcecode/architecture_analyzer.py

@@ -182,8 +182,19 @@ class ArchitectureAnalyzer:
         ddd_result = self._detect_ddd(sm.file_paths)
         if ddd_result is not None:
             ddd_pattern, ddd_layers, ddd_contexts, ddd_layer_names = ddd_result
-            domains_for_ddd = self._cluster_domains(filtered) if len(filtered) >= 2 else []
             module_files = self._build_ddd_module_files(sm.file_paths, ddd_contexts)
+            # Use DDD bounded context names as domains so --architecture shows each
+            # context as a distinct domain instead of collapsing all files under
+            # the Maven path segment (e.g. "java").
+            domains_for_ddd = [
+                ArchitectureDomain(
+                    name=n,
+                    files=module_files.get(n, []),
+                    role="DDD bounded context",
+                    confidence="high",
+                )
+                for n in ddd_contexts
+            ]
             bc_list = [
                 BoundedContext(name=n, modules=module_files.get(n, []), confidence="high")
                 for n in ddd_contexts

sourcecode/ast_extractor.py

@@ -1172,6 +1172,51 @@ def _detect_role(path: str, contract: FileContract) -> str:
     return "util"
 
 
+# ---------------------------------------------------------------------------
+# MyBatis XML mapper extractor
+# ---------------------------------------------------------------------------
+
+def _extract_mybatis_xml(rel_path: str, source: str) -> FileContract:
+    """Extract namespace and SQL operations from a MyBatis *Mapper.xml file."""
+    import re as _re
+    from xml.etree import ElementTree
+
+    _NS_STRIP = _re.compile(r"\{[^}]+\}")
+    _SQL_OPS = frozenset({"select", "insert", "update", "delete"})
+
+    exports: list[ExportRecord] = []
+    namespace: str | None = None
+
+    try:
+        root_elem = ElementTree.fromstring(source.encode("utf-8"))
+        namespace = root_elem.get("namespace") or None
+        for elem in root_elem:
+            tag = _NS_STRIP.sub("", elem.tag).lower()
+            if tag in _SQL_OPS:
+                op_id = (elem.get("id") or "").strip()
+                if op_id:
+                    # type_ref carries select/insert/update/delete for the serializer
+                    exports.append(ExportRecord(kind="query", name=op_id, type_ref=tag))
+    except Exception:
+        return FileContract(
+            path=rel_path,
+            language="mybatis-xml",
+            role="mybatis-mapper",
+            extraction_method="heuristic",
+            limitations=["xml_parse_error: failed to parse mapper XML"],
+        )
+
+    deps = [f"namespace:{namespace}"] if namespace else []
+    return FileContract(
+        path=rel_path,
+        language="mybatis-xml",
+        role="mybatis-mapper",
+        exports=exports,
+        dependencies=deps,
+        extraction_method="heuristic",
+    )
+
+
 # ---------------------------------------------------------------------------
 # AstExtractor public class
 # ---------------------------------------------------------------------------
@@ -1191,6 +1236,16 @@ class AstExtractor:
         return self._ts_ok
 
     def extract(self, path: Path, root: Optional[Path] = None) -> Optional[FileContract]:
+        # MyBatis mapper XML — handled before the language map lookup so .xml
+        # files are only processed when they match the mapper naming convention.
+        if path.suffix.lower() == ".xml" and path.name.endswith("Mapper.xml"):
+            try:
+                source = path.read_text(encoding="utf-8", errors="replace")
+            except OSError:
+                return None
+            rel_path = str(path.relative_to(root)).replace("\\", "/") if root else path.name
+            return _extract_mybatis_xml(rel_path, source)
+
         ext = path.suffix.lower()
         language = _LANGUAGE_MAP.get(ext)
         if language is None:

sourcecode/cli.py

@@ -1399,12 +1399,6 @@ def main(
                         ))
         sm = _replace(sm, pipeline_trace=_trace.build_trace())
 
-    # P3-B: Auto-switch to centrality ranking when DDD layout detected
-    if (rank_by == "relevance"
-            and sm.architecture is not None
-            and sm.architecture.pattern == "ddd"):
-        rank_by = "centrality"
-
     # Contract pipeline — runs for mode=contract|standard|deep|hybrid (skip for raw)
     _is_contract_mode = mode in ("contract", "standard")
     _pipeline_error = False

sourcecode/contract_pipeline.py

@@ -219,9 +219,18 @@ class ContractPipeline:
             fname = Path(pn).name
             return any(fname.startswith(pat) or f".{pat.strip('.')}" in fname for pat in _TEST_PATTERNS)
 
+        def _is_extractable(p: str) -> bool:
+            suf = Path(p).suffix.lower()
+            if suf in _SRC_EXTENSIONS:
+                return True
+            # MyBatis mapper XML files — only *Mapper.xml, not all XML
+            if suf == ".xml" and p.endswith("Mapper.xml"):
+                return True
+            return False
+
         src_paths = [
             p for p in file_paths
-            if Path(p).suffix.lower() in _SRC_EXTENSIONS
+            if _is_extractable(p)
             and not scorer.is_noise(p)
             and (symbol is not None or changed_only or not _is_test(p))
         ]
@@ -231,10 +240,18 @@ class ContractPipeline:
 
         # Apply max_files cap — bypass when symbol search to ensure defining files are found.
         # A symbol query over a large repo needs all files; result set is small after filtering.
+        # MyBatis Mapper.xml contracts rank below Java files on path score alone (.xml has no
+        # suffix boost). Give them the same priority slot as entry_points so they survive the cap.
+        def _is_priority(p: str) -> bool:
+            if p in entry_paths:
+                return True
+            name = p.rsplit("/", 1)[-1]
+            return name.lower().endswith("mapper.xml")
+
         if symbol is None and len(src_paths) > self.max_files:
             src_paths = sorted(
                 src_paths,
-                key=lambda p: (p in entry_paths, scorer.score(p)),
+                key=lambda p: (_is_priority(p), scorer.score(p)),
                 reverse=True,
             )[:self.max_files]
 
@@ -353,7 +370,9 @@ class ContractPipeline:
 
     def _rank(self, contracts: list[FileContract], rank_by: RankStrategy) -> list[FileContract]:
         if rank_by == "centrality":
-            return sorted(contracts, key=lambda c: (-(c.fan_in + c.fan_out), c.path))
+            # Entrypoints (REST controllers, main classes) surface first even in centrality mode:
+            # they have low fan_in (not imported) but are the primary API surface.
+            return sorted(contracts, key=lambda c: (-c.is_entrypoint, -(c.fan_in + c.fan_out), c.path))
         if rank_by == "git-churn":
             return sorted(contracts, key=lambda c: (-c.is_changed, -c.relevance_score, c.path))
         # Default: relevance — path breaks ties deterministically

sourcecode/dependency_analyzer.py

@@ -1191,6 +1191,18 @@ class DependencyAnalyzer:
         limitations: list[str] = []
         if not records:
             limitations.append("java: pom.xml sin dependencias parseables (puede usar BOM o propiedades)")
+
+        # Warn when Spring Boot BOM manages transitive deps — they can't be resolved statically.
+        parent_artifact_local = (
+            root_elem.findtext(f"{ns}parent/{ns}artifactId") or ""
+        ).strip() if parent_elem is not None else ""
+        if parent_artifact_local == "spring-boot-starter-parent" and parent_version:
+            limitations.append(
+                f"spring_boot_bom_detected: transitive deps managed by Spring Boot BOM "
+                f"v{parent_version}, not resolved statically. "
+                "Run 'mvn dependency:tree' for the full transitive tree."
+            )
+
         return records, limitations
 
     def _analyze_gradle(self, root: Path) -> tuple[list[DependencyRecord], list[str]]:

sourcecode/detectors/java.py

@@ -18,7 +18,7 @@ _NS_TAG_RE = re.compile(r"\{[^}]+\}")
 
 _MAX_FILE_SIZE = 256 * 1024  # 256 KB
 _MAX_JAVA_ENTRY_SCAN = 1000
-_MAX_ANNOTATION_ENTRY_POINTS = 500
+_MAX_ANNOTATION_ENTRY_POINTS = 1000
 
 _REST_CONTROLLER_RE = re.compile(r'@RestController\b')
 _MVC_CONTROLLER_RE = re.compile(r'@Controller\b')
@@ -225,6 +225,12 @@ class JavaDetector(AbstractDetector):
         all_paths = flatten_file_tree(context.file_tree)
         all_java = [p for p in all_paths if p.endswith(".java")]
 
+        # Augment with a direct scan of standard Java source roots for Controller-named
+        # files that the depth-limited file_tree scanner may have missed.
+        # DDD layouts place REST controllers at depth 10+ (e.g.
+        # src/main/java/com/org/app/ddd/domain/infraestructure/rest/XxxRestController.java).
+        self._augment_deep_java_controllers(context, all_java)
+
         # 1. @SpringBootApplication entry: Application.java / Main.java by name
         app_candidates = [
             p for p in all_java
@@ -236,10 +242,12 @@ class JavaDetector(AbstractDetector):
         ]
 
         # 2. Annotation-based scan: @RestController, @WebFilter, FilterRegistrationBean
-        scan_candidates = [
-            p for p in all_java
-            if "/test/" not in p and "/tests/" not in p
-        ][:_MAX_JAVA_ENTRY_SCAN]
+        # Prioritize Controller-named files so all REST controllers are detected
+        # even in large codebases where total files > _MAX_JAVA_ENTRY_SCAN.
+        _non_test = [p for p in all_java if "/test/" not in p and "/tests/" not in p]
+        _ctrl_files = [p for p in _non_test if "Controller" in p]
+        _other_files = [p for p in _non_test if "Controller" not in p]
+        scan_candidates = _ctrl_files + _other_files[:max(0, _MAX_JAVA_ENTRY_SCAN - len(_ctrl_files))]
 
         annotation_eps: list[EntryPoint] = []
         for rel_path in scan_candidates:
@@ -268,6 +276,40 @@ class JavaDetector(AbstractDetector):
                 unique_eps.append(ep)
         return unique_eps
 
+    def _augment_deep_java_controllers(self, context: DetectionContext, all_java: list[str]) -> None:
+        """Scan standard Java source roots for *Controller*.java files not in all_java.
+
+        The depth-limited file_tree scanner misses files at depth >= max_depth.
+        DDD layouts place REST controllers deep (e.g. depth 10+), so we supplement
+        with a direct filesystem walk scoped to the standard Maven/Gradle source root.
+        """
+        import os as _os
+        existing = set(all_java)
+        # Standard Java source root candidates (Maven first, then Gradle/other)
+        _SRC_ROOTS = ("src/main/java", "src/main/kotlin", "src/java", "src")
+        for src_root_name in _SRC_ROOTS:
+            src_root = context.root / src_root_name
+            if not src_root.is_dir():
+                continue
+            try:
+                for dirpath, _dirs, filenames in _os.walk(str(src_root)):
+                    for fname in filenames:
+                        if "Controller" not in fname or not fname.endswith(".java"):
+                            continue
+                        full = Path(dirpath) / fname
+                        if full.is_symlink():
+                            continue
+                        try:
+                            rel = str(full.relative_to(context.root)).replace("\\", "/")
+                            if rel not in existing:
+                                all_java.append(rel)
+                                existing.add(rel)
+                        except ValueError:
+                            pass
+            except OSError:
+                pass
+            return  # use only first matching source root
+
     def _scan_java_file_for_entry_points(self, abs_path: Path, rel_path: str) -> list[EntryPoint]:
         try:
             if abs_path.stat().st_size > _MAX_FILE_SIZE:

sourcecode/serializer.py

@@ -1110,6 +1110,10 @@ def standard_view(sm: SourceMap, *, include_tree: bool = False) -> dict[str, Any
 
     if sm.semantic_summary is not None and sm.semantic_summary.requested:
         result["semantic_summary"] = asdict(sm.semantic_summary)
+        # Backward compat: also emit hotspots at top level (moved to semantic_summary in v1.5.0).
+        # Consumers reading d["hotspots"] directly still work.
+        if sm.semantic_summary.hotspots:
+            result["hotspots"] = sm.semantic_summary.hotspots[:10]
         # Defensive filter: never emit objects with null required fields.
         # A null entry in these arrays is worse than a shorter array — it causes
         # agents to misinterpret the analysis as valid when it is not.
@@ -1439,10 +1443,31 @@ def _serialize_contract_java(c: Any) -> dict[str, Any]:
     return item
 
 
+def _serialize_contract_mybatis_xml(c: Any) -> dict[str, Any]:
+    """Serialize a MyBatis *Mapper.xml contract."""
+    item: dict[str, Any] = {"path": c.path, "language": "mybatis-xml"}
+    # Extract namespace stored as "namespace:<fqn>" in dependencies
+    for dep in (c.dependencies or []):
+        if dep.startswith("namespace:"):
+            item["namespace"] = dep[len("namespace:"):]
+            break
+    exports_out: list[dict] = []
+    for e in c.exports:
+        entry: dict = {"kind": e.kind, "name": e.name}
+        if getattr(e, "type_ref", None):
+            entry["type"] = e.type_ref
+        exports_out.append(entry)
+    if exports_out:
+        item["exports"] = exports_out
+    return item
+
+
 def _serialize_contract_minimal(c: Any) -> dict[str, Any]:
     """Serialize one FileContract to minimal format."""
     if getattr(c, "language", None) == "java":
         return _serialize_contract_java(c)
+    if getattr(c, "language", None) == "mybatis-xml":
+        return _serialize_contract_mybatis_xml(c)
     item: dict[str, Any] = {"path": c.path, "role": c.role}
 
     if c.is_changed:
@@ -1560,6 +1585,11 @@ def _contract_view_standard(
     if contracts:
         serialized: list[dict[str, Any]] = []
         for c in contracts:
+            if getattr(c, "language", None) == "mybatis-xml":
+                item = _serialize_contract_mybatis_xml(c)
+                item["relevance_score"] = round(c.relevance_score, 3)
+                serialized.append(item)
+                continue
             item: dict[str, Any] = {
                 "path": c.path,
                 "language": c.language,
@@ -1609,7 +1639,7 @@ def _contract_view_standard(
                     item["ranking_reasons"] = non_trivial
             item["method"] = c.extraction_method
             serialized.append(item)
-        result["file_contracts"] = serialized
+        result["contracts"] = serialized
 
     # Optional analysis sections (deep mode or when analyzers ran)
     if include_optional:

{sourcecode-1.4.0.dist-info → sourcecode-1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.4.0
+Version: 1.6.0
 Summary: Deterministic codebase context for AI coding agents
 License:                                  Apache License
                                    Version 2.0, January 2004

{sourcecode-1.4.0.dist-info → sourcecode-1.6.0.dist-info}/RECORD

@@ -1,18 +1,18 @@
-sourcecode/__init__.py,sha256=7vIUDLA50NqbZpGWjbWgBBlC-d6NEDyVgAmqGi5Qy1I,102
+sourcecode/__init__.py,sha256=s3ubr020DVq1rHjxHihNLq1cecOGqF6x7czXl3I96Sk,102
 sourcecode/adaptive_scanner.py,sha256=6dh34C2qZXyRbw-8xBhbEwDdXanM6CRFRWayVoYITnA,10190
-sourcecode/architecture_analyzer.py,sha256=qzDW3_lQv__czQ-qs6AqEEoMvTfhfp7M7kNslPuQy7A,32128
+sourcecode/architecture_analyzer.py,sha256=oPmGPf9_p6y8Z7SIGHEu57nVYwxycIovDzBvlHl-l5k,32557
 sourcecode/architecture_summary.py,sha256=J9yoLgh8wXwIRrT6q6JooB6PekivbOEYpJz4BUXdalk,20545
-sourcecode/ast_extractor.py,sha256=L_MbLz22TdF_P21-nSSxSG9hZcMdtUjRKmPTWFx5NmU,47732
+sourcecode/ast_extractor.py,sha256=XgrZg2DcWcUm9r87cRG3KGO7IK2TIL_N-CvhSbUmmh4,49901
 sourcecode/classifier.py,sha256=GKTMN8qKZX7ponSwDJfN08RrasI4CVpq1_gFBgEopps,7093
-sourcecode/cli.py,sha256=_oYoP4_AAFGw0gg-FBGn_DKh7y49xmwuL6D_Bafl2w4,74497
+sourcecode/cli.py,sha256=91GUbfLS86RMTurkhoMWFUPqby30AEgzkLDIvJui9Fc,74262
 sourcecode/code_notes_analyzer.py,sha256=rRd8bFYV0krjlxxQV0wenwE9K7pVpUQSR7KvSvUQKw4,9226
 sourcecode/confidence_analyzer.py,sha256=HcaewB2pZaZ_hfKrZWtr_yPMY2-CxS1zzTUD7c4argc,13188
 sourcecode/context_scorer.py,sha256=QpChSpsmaAYz91rXA4Ue5xzQmNz_ZboZN09YOHScq1U,14679
 sourcecode/context_summarizer.py,sha256=CiQrfBEzun949bWvmLabWoj2HhPn6Lw62ofqnsy0FlQ,6503
 sourcecode/contract_model.py,sha256=nRxJKPMs1VHwFTa8AVXhGmaLjti3Lr2sjHDpWgv1bfE,3917
-sourcecode/contract_pipeline.py,sha256=mjI1MgFebZW6uQAei0aheW7VPmZntH5eVXiyqkE2N9w,26332
+sourcecode/contract_pipeline.py,sha256=GX-AyUxULywnGHYpmVlMDGsiHEsdegGUHfLVn7Ffvis,27238
 sourcecode/coverage_parser.py,sha256=q0LeZJaX1bnntLu-ImksdBsMlpsVmk_iUfSaB4eaJGo,19702
-sourcecode/dependency_analyzer.py,sha256=LGEcpbpPl7cO4-TjPO02XAJRwiAhE1ad0QQDIjAqmEA,55595
+sourcecode/dependency_analyzer.py,sha256=p4ljXhkcGBbFlhaZuPrsjOVjDXaKLTg0Gor2p4qFPP0,56208
 sourcecode/doc_analyzer.py,sha256=a1CIClCNmfYM3ku4bdgwHQpmb6Js4wdJZ1V5EYLo04I,24345
 sourcecode/entrypoint_classifier.py,sha256=gvKgl0f5T8ol1r4JMmkeqGHuZTfZJiOwFOWdc7EYwYw,4061
 sourcecode/env_analyzer.py,sha256=GxCidahAAIptTdDFIlVB6URd4HBnBlIX_SqUov3MBRQ,22076
@@ -29,7 +29,7 @@ sourcecode/runtime_classifier.py,sha256=zWX3r3HCKHc-qtIobErOa8aKMmaoPYREtJKvPcBG
 sourcecode/scanner.py,sha256=aM3h9-DCQ3xKpeHpHYdo2vX6T5P95HA_YwZbkAVNwmo,8288
 sourcecode/schema.py,sha256=rNxpDUgOfvJDzz6DKitL-5_0UAh0YomNwTsSSe8PafY,24066
 sourcecode/semantic_analyzer.py,sha256=12TwXYkYbDcBdu0heX_EmfPM2EkO8a_r5osf0SaeQbs,88956
-sourcecode/serializer.py,sha256=qqqH84ensw31P6ElqivPUwmYtb6AR7KTENM2nFJSde4,68403
+sourcecode/serializer.py,sha256=6dHvWc-iqqCjpu9-FcAXqtpKEO4mO3AZVzWT7Tphajo,69736
 sourcecode/summarizer.py,sha256=ZuzIdm3t8A-d5MuQL0TSNLrd-L0IQIuguIxeNXMNJf8,16070
 sourcecode/tree_utils.py,sha256=Fj9OIuUksBvgibNd3feog0sMDjVypJzPexp5lvMoYWI,1424
 sourcecode/workspace.py,sha256=X_6NmNnitvT3_38V-JDChydo_sR68s249hLFlrQskU0,8271
@@ -42,7 +42,7 @@ sourcecode/detectors/elixir.py,sha256=jCpvt5Yi6jvplc80ovRtWh17q-11ZGo9qX7o8b57TJ
 sourcecode/detectors/go.py,sha256=2r66uRQfeTWsqxr4HDhT6vExZErby0t46QXLHVBRv9w,2782
 sourcecode/detectors/heuristic.py,sha256=bCqqgbHavl4Sse3dqT8mwmo1wAdgeJr7VyXOmfClLKo,3387
 sourcecode/detectors/hybrid.py,sha256=IGFRUVsAZ1ooRlFdznCeJAV6vy1yVDx-VyghvLtddXc,9101
-sourcecode/detectors/java.py,sha256=acRCelw-SdxaPsJsBJEGybFTqe1esPpgqKibB9xbJoI,16277
+sourcecode/detectors/java.py,sha256=XAnVOmq7yXgO_4UGlIFIVgNRtyWZQEVsDDu3sa5mTsk,18669
 sourcecode/detectors/jvm_ext.py,sha256=EgHJ5W8EE-ZTN9V607mVzohyKgZE8Mc2jCi-DF8RAZU,2616
 sourcecode/detectors/nodejs.py,sha256=7fsyAmrGkkguX6U80HUQpIe9MRaYyi_A7zbaRtmFmGc,13097
 sourcecode/detectors/parsers.py,sha256=ugPg8yNUf0Ai1gA7Fnn6wAkYGFjTxRodSP3IeViYJJ4,2290
@@ -60,8 +60,8 @@ sourcecode/telemetry/consent.py,sha256=wLMvGNJeSSyZoNkQXpoUioY6mMv4Qdvuw7S9jAEWn
 sourcecode/telemetry/events.py,sha256=oEvvulfsv5GIDWG2174gSS6tNB95w38AIYiYeifGKlE,2294
 sourcecode/telemetry/filters.py,sha256=Asa71oRl7q3Wt_FMwuufIZJFzSYdgRNKS8LHCIyFeYE,4805
 sourcecode/telemetry/transport.py,sha256=KJeIPCPWMdmbCP3ySGs2iUlia34U6vWne2dZsUezesw,1560
-sourcecode-1.4.0.dist-info/METADATA,sha256=vVglc6X8WawZuI4yHs6aWszUHNLtVowyFpCRRSA4INM,20411
-sourcecode-1.4.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-sourcecode-1.4.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
-sourcecode-1.4.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
-sourcecode-1.4.0.dist-info/RECORD,,
+sourcecode-1.6.0.dist-info/METADATA,sha256=hB2-2Dm1fOj4fkPULr9PEH3aSLhD7ni4cPDxGAjmgB0,20411
+sourcecode-1.6.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+sourcecode-1.6.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
+sourcecode-1.6.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
+sourcecode-1.6.0.dist-info/RECORD,,