dafab-client 2.2.3__tar.gz → 2.2.4__tar.gz

{dafab_client-2.2.3 → dafab_client-2.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dafab_client
-Version: 2.2.3
+Version: 2.2.4
 Summary: DaFab helper client built on top of Rucio client modules.
 Author: DaFab
 License-Expression: Apache-2.0

{dafab_client-2.2.3 → dafab_client-2.2.4}/dafab_client/example_notebooks/dafab_dasi_workflows.ipynb

@@ -73,13 +73,16 @@
     "STAC_COLLECTION_ID = \"sentinel_2_l2a\"\n",
     "\n",
     "# Input JSON file for original-item validation.\n",
-    "ORIGINAL_ITEM_FILE = \"docs/notebooks/demo-data/uploads/items/sentinel-2-l2a/S2A_45RYJ_20221205_0_L2A_(bootstrap).json\"\n",
+    "ORIGINAL_ITEM_FILE = \"../../docs/notebooks/demo-data/uploads/items/sentinel-2-l2a/S2C_MSIL2A_20260218T105111_N0512_R051_T30TYN_20260218T145711.json\"\n",
     "\n",
-    "# JSON schema file used to validate the original-item payload.\n",
-    "ORIGINAL_ITEM_SCHEMA = \"docs/notebooks/demo-data/uploads/items/Schema_Copernicus_with_dafab.json\"\n",
+    "# JSON schema used before the item is normalized into DaFab STAC state.\n",
+    "ORIGINAL_ITEM_SOURCE_SCHEMA = \"../../dafab_client/helpers/resources/schemas/dasi-original-item.schema.json\"\n",
+    "\n",
+    "# JSON schema used after DaFab navigation fields are synchronized.\n",
+    "ORIGINAL_ITEM_SCHEMA = \"../../dafab_client/helpers/resources/schemas/Schema_Copernicus_with_dafab.json\"\n",
     "\n",
     "# Original Sentinel-2 item ID reused across DASI publication steps.\n",
-    "ORIGINAL_ITEM_ID = \"S2A_45RYJ_20221205_0_L2A\""
+    "ORIGINAL_ITEM_ID = \"S2C_MSIL2A_20260218T105111_N0512_R051_T30TYN_20260218T145711\"\n"
    ],
    "id": "51b980534fbae32f",
    "outputs": [],
@@ -133,12 +136,12 @@
    "metadata": {},
    "source": [
     "## 4. Validate Original Item Contract (Pre-Publish Mode)\n",
-    "- Load the local JSON payload and validate it against the Copernicus+DaFab schema before insertion.\n",
+    "- Load the local JSON payload and validate it against the DASI original-item schema before insertion.\n",
     "- Check required STAC fields and object type (`Feature`, `id`, `collection`, `properties`, `geometry`, `bbox`, `links`, `assets`).\n",
-    "- Validate pre-publish link contract (`self`, `canonical`, `derived_from`) and href/id consistency.\n",
+    "- Validate the source `self` link and href/id consistency.\n",
     "- Validate coordinate-box structure and ordering.\n",
     "- Validate temporal fields (`datetime`, optional `created`/`updated` ordering).\n",
-    "- Validate Sentinel item-id semantics and sequence consistency.\n",
+    "- Validate Sentinel SAFE-style product ID semantics.\n",
     "- Validate collection-name compatibility against the expected collection ID (hyphen/underscore normalization).\n"
    ],
    "id": "c3d5740b3ef24780"
@@ -151,12 +154,12 @@
     "    scope=STAC_SCOPE,\n",
     "    source=\"local\",\n",
     "    item_path=ORIGINAL_ITEM_FILE,\n",
-    "    schema_path=ORIGINAL_ITEM_SCHEMA,\n",
+    "    schema_path=ORIGINAL_ITEM_SOURCE_SCHEMA,\n",
     "    expected_item_id=ORIGINAL_ITEM_ID,\n",
     "    expected_collection_id=STAC_COLLECTION_ID,\n",
     "    check_catalog_state=False,\n",
     ")\n",
-    "print(dc.as_json(original_item_pre_publish_validation))"
+    "print(dc.as_json(original_item_pre_publish_validation))\n"
    ],
    "id": "8f988f1e6d08439a",
    "outputs": [],
@@ -180,7 +183,7 @@
     "    metadata_path=ORIGINAL_ITEM_FILE,\n",
     "    scope=STAC_SCOPE,\n",
     "    op=\"upsert\",\n",
-    ")"
+    ")\n"
    ],
    "id": "6e822f1f67784d8f",
    "outputs": [],

{dafab_client-2.2.3 → dafab_client-2.2.4}/dafab_client/helpers/metadata_management/Preflight/validate_original_item_file.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import argparse
 import copy
 import json
+import re
 from datetime import datetime
 from pathlib import Path
 from typing import Any, Literal, Optional
@@ -37,6 +38,9 @@ STATE_ERROR_PREFIXES = (
     "collection_metadata:",
     "catalog_state:",
 )
+SENTINEL_SAFE_ITEM_ID_RE = re.compile(
+    r"^S2[ABC]_MSIL(?:1C|2A)_\d{8}T\d{6}_N\d{4}_R\d{3}_T\d{2}[A-Z]{3}_\d{8}T\d{6}$"
+)
 
 
 def _resolve_validation_phase(
@@ -178,33 +182,15 @@ def _validate_bbox(bbox: Any) -> tuple[Optional[bool], Optional[str]]:
     return True, None
 
 
-def _validate_item_id_semantics(item_id: Any, sequence: Any) -> tuple[Optional[bool], list[str]]:
-    issues: list[str] = []
+def _validate_item_id_semantics(item_id: Any, sequence: Any) -> tuple[Optional[bool], list[str]]:  # noqa: ARG001
     if not isinstance(item_id, str) or not item_id.strip():
         return False, ["item id is missing or empty."]
-
-    parts = item_id.split("_")
-    if len(parts) < 5:
-        issues.append("item id does not match expected Sentinel token layout '<platform>_<tile>_<date>_<sequence>_<level>'.")
-        return False, issues
-
-    platform_token = parts[0]
-    sequence_token = parts[-2]
-    level_token = parts[-1]
-
-    if not platform_token.startswith("S2"):
-        issues.append(f"item id platform token '{platform_token}' does not look like Sentinel-2.")
-    if not sequence_token.isdigit():
-        issues.append(f"item id sequence token '{sequence_token}' is not numeric.")
-    if level_token not in {"L1C", "L2A"}:
-        issues.append(f"item id level token '{level_token}' is not one of expected values (L1C/L2A).")
-
-    if sequence is not None and str(sequence) != sequence_token:
-        issues.append(
-            f"properties['s2:sequence'] ('{sequence}') does not match item id sequence token '{sequence_token}'."
-        )
-
-    return len(issues) == 0, issues
+    if SENTINEL_SAFE_ITEM_ID_RE.fullmatch(item_id):
+        return True, []
+    return False, [
+        "item id does not match expected Sentinel SAFE-style product id "
+        "'<platform>_MSIL<level>_<sensing_time>_N<baseline>_R<relative_orbit>_T<mgrs_tile>_<generation_time>'."
+    ]
 
 
 def _extract_document(payload: Any) -> dict[str, Any]:
@@ -428,8 +414,6 @@ def _evaluate_original_item_payload(
     links = core_fields["links"]
     hrefs_by_rel = _collect_hrefs_by_rel(links)
     self_links = hrefs_by_rel.get("self", [])
-    canonical_links = hrefs_by_rel.get("canonical", [])
-    derived_from_links = hrefs_by_rel.get("derived_from", [])
     root_links = hrefs_by_rel.get("root", [])
     collection_links = hrefs_by_rel.get("collection", [])
 
@@ -438,40 +422,21 @@ def _evaluate_original_item_payload(
         if len(self_links) != 1:
             link_structure_valid = False
             errors.append(f"links: expected exactly one 'self' link, found {len(self_links)}")
-        if len(canonical_links) != 1:
-            link_structure_valid = False
-            errors.append(f"links: expected exactly one 'canonical' link, found {len(canonical_links)}")
-        if len(derived_from_links) < 1:
-            link_structure_valid = False
-            errors.append("links: expected at least one 'derived_from' link.")
-
-        if root_links:
-            root_valid = all(link == root_href for link in root_links)
-            report["checks"]["root_link_valid"] = root_valid
-            if not root_valid:
-                errors.append(f"root_link: expected all root hrefs to be '{root_href}', found {root_links}")
 
         link_id_consistency_valid = False
         if isinstance(item_id, str):
-            for rel_name, rel_links in {"self": self_links, "canonical": canonical_links}.items():
-                for href in rel_links:
-                    parsed_id = _item_id_from_href(href)
-                    if parsed_id is None:
-                        errors.append(f"links:{rel_name}: could not extract item id from href '{href}'")
-                        continue
-                    if parsed_id != item_id:
-                        errors.append(
-                            f"links:{rel_name}: href-derived id '{parsed_id}' does not match payload id '{item_id}'"
-                        )
-            if len(self_links) == 1 and len(canonical_links) == 1:
+            for href in self_links:
+                parsed_self_id = _item_id_from_href(href)
+                if parsed_self_id is None:
+                    errors.append(f"links:self: could not extract item id from href '{href}'")
+                    continue
+                if parsed_self_id != item_id:
+                    errors.append(
+                        f"links:self: href-derived id '{parsed_self_id}' does not match payload id '{item_id}'"
+                    )
+            if len(self_links) == 1:
                 parsed_self_id = _item_id_from_href(self_links[0])
-                parsed_canonical_id = _item_id_from_href(canonical_links[0])
-                link_id_consistency_valid = (
-                    parsed_self_id is not None
-                    and parsed_canonical_id is not None
-                    and parsed_self_id == item_id
-                    and parsed_canonical_id == item_id
-                )
+                link_id_consistency_valid = parsed_self_id is not None and parsed_self_id == item_id
         report["checks"]["link_id_consistency_valid"] = link_id_consistency_valid
 
     if validation_phase == "post_publish":