sourcecode 1.31.22__py3-none-any.whl → 1.31.23__py3-none-any.whl

sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.31.22"
+__version__ = "1.31.23"

sourcecode/cli.py

@@ -423,7 +423,7 @@ def main(
             "High-signal summary (typically 1000–3000 tokens depending on repo size): "
             "stacks, entry points, dependency summary, confidence, and gaps. "
             "Includes security_surface (when @M3FiltroSeguridad detected), mybatis (when MyBatis framework detected), and transactional_boundaries for Java projects. "
-            "Use --agent for maximum signal or --slim (when available) for minimal token footprint."
+            "Use --agent for maximum signal."
         ),
     ),
     dependencies: bool = typer.Option(

sourcecode/repository_ir.py

@@ -1093,7 +1093,18 @@ def _resolve_jaxrs_prefixes(
 
     for parent_simple, locator_path in locator_map[cls_simple]:
         parent_full = _resolve_jaxrs_prefixes(parent_simple, class_info, locator_map, new_visited)
-        for pp in parent_full:
+        # Skip implementation/unrooted parents: if the parent resolves to only empty
+        # prefixes AND has no class-level @Path annotation, it is a concrete impl class
+        # (e.g. DefaultClientsApi implements ClientsApi) that duplicates a locator method
+        # from its interface. Including it would produce spurious short paths like /{id}
+        # alongside the correctly-resolved full path. The interface version is already
+        # in the locator_map and will produce the correct full path.
+        _parent_has_path_ann = class_info.get(parent_simple, {}).get("has_path_ann", False)
+        _non_empty_parent = [p for p in parent_full if p]
+        if not _non_empty_parent and not _parent_has_path_ann:
+            continue
+        use_parent_paths = _non_empty_parent if _non_empty_parent else parent_full
+        for pp in use_parent_paths:
             for op in own_prefixes:
                 combined = _join_path_segments(pp, locator_path, op)
                 full_prefixes.append(combined)
@@ -2833,6 +2844,18 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
                 entry["required_permission"] = security_info["required_permission"]
         endpoints.append(entry)
 
+    # Filter out endpoints whose path looks like a Java FQN (e.g. dynamic admin routing
+    # in frameworks like Broadleaf Commerce where @AdminSection registers entity class
+    # FQNs as URL segments). These are not real REST paths — they are resolved at
+    # runtime by the framework. Including them pollutes the endpoint surface with 20+
+    # garbage entries that confuse agents and break endpoint count accuracy.
+    # Pattern: path segment that matches a Java package hierarchy (org.foo.Bar).
+    import re as _re_fqn
+    _FQN_PATH_RE = _re_fqn.compile(
+        r"/(org|com|net|io|edu)\.[a-z][a-z0-9]*\.[a-zA-Z]",
+    )
+    endpoints = [e for e in endpoints if not _FQN_PATH_RE.search(e.get("path", ""))]
+
     # "no_security_signal" = no recognized security annotation at method OR class level.
     # Note: repos may use framework-level security (e.g. Keycloak itself) with no
     # per-endpoint annotations — this count reflects annotation-based coverage only.

sourcecode/serializer.py

@@ -1771,24 +1771,47 @@ def _angular_analysis(sm: "SourceMap") -> "Optional[dict[str, Any]]":
                 if val and val not in route_paths:
                     route_paths.append(val)
 
-    # Angular version from package.json
+    # Angular version from package.json — check root first, then subdirectories.
+    # In monorepos (Java + Angular), the Angular package.json is in a subdirectory
+    # like frontend/ and not at the repo root. We probe candidate locations.
     angular_version: Optional[str] = None
-    pkg_json = root / "package.json"
-    if pkg_json.exists():
+
+    def _read_angular_version_from_pkg(pkg_path: Path) -> Optional[str]:
+        """Extract @angular/core version from a package.json file."""
         try:
-            pkg = _json.loads(pkg_json.read_text(encoding="utf-8", errors="replace"))
-            # Use `or {}` so explicit `null` values in package.json don't
-            # raise TypeError when unpacking (BUG-4).
+            pkg = _json.loads(pkg_path.read_text(encoding="utf-8", errors="replace"))
             deps = {
                 **(pkg.get("dependencies") or {}),
                 **(pkg.get("devDependencies") or {}),
                 **(pkg.get("peerDependencies") or {}),
             }
             av = deps.get("@angular/core")
-            if av:
-                angular_version = av.lstrip("^~>=")
+            if av and isinstance(av, str):
+                return av.lstrip("^~>=")
         except Exception:
             pass
+        return None
+
+    # 1. Try root package.json first (fastest, most common for pure Angular projects)
+    _root_pkg = root / "package.json"
+    if _root_pkg.exists():
+        angular_version = _read_angular_version_from_pkg(_root_pkg)
+
+    # 2. If not found at root, search subdirectory package.json files.
+    # Limit to ts_files-derived subdirs to avoid scanning the whole repo.
+    if angular_version is None and ts_files:
+        _candidate_dirs: set[str] = set()
+        for ts_rel in ts_files[:200]:  # sample first 200 ts files
+            parts = ts_rel.replace("\\", "/").split("/")
+            if len(parts) >= 2:
+                _candidate_dirs.add(parts[0])  # top-level subdir (e.g. "frontend")
+        for subdir in sorted(_candidate_dirs):
+            _sub_pkg = root / subdir / "package.json"
+            if _sub_pkg.exists():
+                _v = _read_angular_version_from_pkg(_sub_pkg)
+                if _v:
+                    angular_version = _v
+                    break
 
     # Also check angular.json for entry point
     entry_point: Optional[str] = None

sourcecode/summarizer.py

@@ -203,34 +203,78 @@ class ProjectSummarizer:
         __import__("re").IGNORECASE,
     )
 
+    # Patterns that indicate license notices or user-facing marketing text.
+    # These describe what the product does FOR users or its licensing terms,
+    # not the codebase architecture.
+    _LICENSE_MARKETING_RE = __import__("re").compile(
+        r"\bfair[- ]use\b"                        # Fair Use license
+        r"|\bcommunity edition\b"                 # product tier labels
+        r"|\benterprise edition\b"
+        r"|\bcommercial licen[sc]e\b"
+        r"|\bsource.available\b"
+        r"|\bavailable to companies\b"            # license restriction
+        r"|\bunder \$\d+[MK]\b"                   # revenue threshold
+        r"|\bimportant:\s"                        # WARNING/IMPORTANT caveats
+        r"|\badd authentication to\b"             # user-facing "add X to Y" marketing
+        r"|\bno need to deal with\b"
+        r"|\bwith minimum effort\b"
+        r"|\bsign up\b.*\bevaluation\b"
+        r"|\bcontact us\b.*\bmore information\b",
+        __import__("re").IGNORECASE,
+    )
+
     def _extract_first_useful_paragraph(self, content: str) -> str | None:
+        """Extract the first paragraph that describes the project architecture, not its license or marketing."""
         import re as _re
         _BADGE_RE = _re.compile(r"^\[?!\[")  # [![badge](...)] or ![img](...)
         _LINK_ONLY_RE = _re.compile(r"^\[.*?\]\(.*?\)$")  # pure link line
-        lines: list[str] = []
+
+        paragraphs: list[str] = []
+        current_lines: list[str] = []
         in_code_block = False
+
         for raw_line in content.splitlines():
             line = raw_line.strip()
             if line.startswith("```"):
                 in_code_block = not in_code_block
                 continue
-            if in_code_block or not line or line.startswith(("#", "<!--", ">")):
-                if lines:
-                    break
+            if in_code_block:
                 continue
-            # Skip badge-only lines and pure-link lines — they are metadata, not descriptions
-            if _BADGE_RE.match(line) or (not lines and _LINK_ONLY_RE.match(line)):
+            if not line or line.startswith(("#", "<!--", ">")):
+                if current_lines:
+                    paragraphs.append(" ".join(current_lines).strip())
+                    current_lines = []
                 continue
-            lines.append(line)
-        if not lines:
-            return None
-        paragraph = " ".join(lines).strip()
-        # Reject paragraphs that are startup/setup snippets, not domain descriptions.
-        # Count how many startup signals appear; >1 means the paragraph is instructions.
-        _startup_hits = len(self._STARTUP_RE.findall(paragraph))
-        if _startup_hits >= 2:
-            return None
-        return paragraph
+            if _BADGE_RE.match(line) or _LINK_ONLY_RE.match(line):
+                if current_lines:
+                    paragraphs.append(" ".join(current_lines).strip())
+                    current_lines = []
+                continue
+            current_lines.append(line)
+        if current_lines:
+            paragraphs.append(" ".join(current_lines).strip())
+
+        _MD_LINK_RE = _re.compile(r"\[.+?\]\(.+?\)")
+        for paragraph in paragraphs[:6]:  # Check up to 6 paragraphs
+            if not paragraph:
+                continue
+            # Reject very short fragments (< 30 chars) — likely just a section title
+            if len(paragraph) < 30:
+                continue
+            # Reject startup/setup snippets
+            _startup_hits = len(self._STARTUP_RE.findall(paragraph))
+            if _startup_hits >= 2:
+                continue
+            # Reject license notices and user-facing marketing text
+            if self._LICENSE_MARKETING_RE.search(paragraph):
+                continue
+            # Reject link-list paragraphs (docs/navigation sections):
+            # if more than 2 markdown links dominate the paragraph, it's a nav section
+            _link_count = len(_MD_LINK_RE.findall(paragraph))
+            if _link_count > 2 and _link_count * 30 > len(paragraph):
+                continue
+            return paragraph
+        return None
 
     _TYPE_LABELS: dict[str, str] = {
         "cli": "CLI",

{sourcecode-1.31.22.dist-info → sourcecode-1.31.23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.31.22
+Version: 1.31.23
 Summary: Deterministic codebase context for AI coding agents
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -225,7 +225,7 @@ Description-Content-Type: text/markdown
 
 **AI-ready change intelligence for Java/Spring enterprise monoliths.**
 
-![Version](https://img.shields.io/badge/version-1.31.22-blue)
+![Version](https://img.shields.io/badge/version-1.31.23-blue)
 ![Python](https://img.shields.io/badge/python-3.10%2B-green)
 
 ---
@@ -263,7 +263,7 @@ pipx install sourcecode
 
 ```bash
 sourcecode version
-# sourcecode 1.31.22
+# sourcecode 1.31.23
 ```
 
 ---

{sourcecode-1.31.22.dist-info → sourcecode-1.31.23.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sourcecode/__init__.py,sha256=Wsav7BZkVmw8XZqjz_WUnhLQyGjtZVwjYnyc_N4sraE,104
+sourcecode/__init__.py,sha256=u-AGXNvPNCuCZnA6MlEhddkQlAKa1tp7BeXtzkz6TpU,104
 sourcecode/adaptive_scanner.py,sha256=XffluXKzJUXrMtjEiAOnSNPZnztdIcts17T9ouHeID0,10521
 sourcecode/architecture_analyzer.py,sha256=4R13Yb02OrPeB4IH3z6V_g7HWhmGcRHbI8CobCVnRrc,39111
 sourcecode/architecture_summary.py,sha256=z34_6v7cSwy98cof2UVciGho7SCrZ93tiqMmq5WNzRQ,20405
@@ -6,7 +6,7 @@ sourcecode/ast_extractor.py,sha256=_btmeOJIe3t-NicF94D5ZAesa2YIJ0_QNExGnbHxGFE,5
 sourcecode/cache.py,sha256=TiYa3ECjBKtvlfCk7GvQ9v6gZkAITpH3ow9PubA7sUo,22946
 sourcecode/canonical_ir.py,sha256=NZu0XICv__hkQGKzW2LNQLRqb1L28K2p_WQCQKS5Zlk,23141
 sourcecode/classifier.py,sha256=yWeq6agTjkFa3zuNa-gdVIHtjoBoPoVlJnX-b7tdVJs,7851
-sourcecode/cli.py,sha256=qMn-4zD8v03dmkn-AZsf2TSplyhjbq9ZPMAcWl_Lrxg,147576
+sourcecode/cli.py,sha256=juaaKE6QgifwFGSRdIxxB7XoQhp51m_AuG3U7zLNQ4Y,147521
 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
@@ -32,13 +32,13 @@ sourcecode/ranking_engine.py,sha256=ZAucq_YX2KkWUuAZf4P0lhtQ_38vEFnUhuGtSZd1S0E,
 sourcecode/redactor.py,sha256=xuGcadGEHaPw4qZXlMDvzMCsr4VOkdp3oBQptHyJk8c,2884
 sourcecode/relevance_scorer.py,sha256=MYF4FFkveAQps9SmTeTlh6ODiBz2F--_hWNeHMLtUHQ,8405
 sourcecode/repo_classifier.py,sha256=FG1vaWKdWXsWdl-S8hjVMiTqcwgaRXkDyvK4rPcOGtQ,22681
-sourcecode/repository_ir.py,sha256=NooCrMJYqycKSYTEroVWTYR8X83hHaAYKTsgYxvlz-I,140221
+sourcecode/repository_ir.py,sha256=vdgJwzfoY2qpQtzcGX7k0E5jWe9fcuyFdkqnF4K6UBs,141767
 sourcecode/runtime_classifier.py,sha256=uTAD6BDCiBLUZEDRfqk718kM4RTT_vAbfkcOI2_Xx58,18432
 sourcecode/scanner.py,sha256=WdOQ78mMzjR1NjmKTlbxdgwinnCTfAhxCVLBEFQiFHU,8899
 sourcecode/schema.py,sha256=aHNXDf8LGyUC8ZDE_VS9kiskC2-Oswhi_WnpdGy6HDw,24897
 sourcecode/semantic_analyzer.py,sha256=TDuC3wzZR2DPm1mgrAg1YSLk2QzJoueS3TZAmyGGpCU,89417
-sourcecode/serializer.py,sha256=V8ZV3Y1j4T6rkpO09-PvpVORioWWWbSnOvDjZ2hmQ2U,122144
-sourcecode/summarizer.py,sha256=lPlKhMh28nueXkPo2xKeD3DUFYVGRlJMIdY-8TSM-ls,17486
+sourcecode/serializer.py,sha256=zzhWyaseWSAqSIe77QwJkyehVI_1DJBkGM7KqbDQtXo,123313
+sourcecode/summarizer.py,sha256=KAtU2mvXT1GLJJQ50Rup42BFsJXij5hmklCwMvcxVx4,19514
 sourcecode/tree_utils.py,sha256=8GAkIfQAsvtEudIeW1l4ooH_oRtrWR8cpJQJsEa_Pfw,2093
 sourcecode/workspace.py,sha256=X_6NmNnitvT3_38V-JDChydo_sR68s249hLFlrQskU0,8271
 sourcecode/detectors/__init__.py,sha256=A0AACJFF6HWf_RgatNtWu3PUzstcKtIGM9f1PoFcJug,1987
@@ -76,8 +76,8 @@ 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-1.31.22.dist-info/METADATA,sha256=zjEDrWUQ-08LOjvIfXTDUgQ4UTPkneyr4CFGZc5yaOo,31103
-sourcecode-1.31.22.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-sourcecode-1.31.22.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
-sourcecode-1.31.22.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
-sourcecode-1.31.22.dist-info/RECORD,,
+sourcecode-1.31.23.dist-info/METADATA,sha256=3-xJut96GlWt6KcUJCKPO4trdkPbNuSR9cxUo9O6FlI,31103
+sourcecode-1.31.23.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+sourcecode-1.31.23.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
+sourcecode-1.31.23.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
+sourcecode-1.31.23.dist-info/RECORD,,