utils: better nsl handling

.pre-commit-config.yaml

@@ -2,15 +2,15 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-added-large-files
       - id: mixed-line-ending
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.3.2
+    rev: v0.4.4
     hooks:
       - id: ruff
       - id: ruff-format

README.md

@@ -20,10 +20,13 @@ Key features are of the earthquake detection and localisation framework are:
   * 1D Layered velocity model
   * 3D fast-marching velocity model (NonLinLoc compatible)
 * Extraction of earthquake event features:
-    * Local magnitudes
-    * Ground motion attributes
+  * Moment Magnitudes (MW) based on modelled peak ground motions
+  * Local magnitudes (ML), different models
+  * Ground motion attributes (e.g. PGA, PGV, ...)
 * Automatic extraction of modelled and picked travel times
-* Calculation and application of station corrections / station delay times
+* Station Corrections
+  * station specific corrections (SST)
+  * source specific station corrections (SSST)
 
 Qseek is built on top of [Pyrocko](https://pyrocko.org).
 

src/qseek/utils.py

@@ -116,7 +116,7 @@ def match(self, other: NSL) -> bool:
         return self.network == other.network
 
     @classmethod
-    def parse(cls, nsl: str | NSL | list[str]) -> NSL:
+    def parse(cls, nsl: str | NSL | list[str] | tuple[str, str, str]) -> NSL:
         """Parse the given NSL string and return an NSL object.
 
         Args:
@@ -132,22 +132,49 @@ def parse(cls, nsl: str | NSL | list[str]) -> NSL:
             raise ValueError("invalid empty NSL")
         if type(nsl) is _NSL:
             return nsl
-        if isinstance(nsl, list):
+        if isinstance(nsl, (list, tuple)):
             return cls(*nsl)
         if not isinstance(nsl, str):
             raise ValueError(f"invalid NSL {nsl}")
+
         parts = nsl.split(".")
         n_parts = len(parts)
         if n_parts >= 3:
             return cls(*parts[:3])
         if n_parts == 2:
             return cls(parts[0], parts[1], "")
-        if n_parts == 1:
-            return cls(parts[0], "", "")
-        raise ValueError(f"invalid NSL {nsl}")
+        raise ValueError(
+            f"invalid NSL `{nsl}`, expecting `<net>.<sta>.<loc>`, "
+            "e.g. `6A.STA130.00`, `6A.STA130` or `.STA130`"
+        )
+
+    def _check(self) -> None:
+        """Check if the current NSL object matches another NSL object.
+
+        Args:
+            nsl (NSL): The NSL object to compare with.
+
+        Returns:
+            bool: True if the objects match, False otherwise.
+        """
+        if len(self.network) > 2:
+            raise ValueError(
+                f"invalid network {self.network} for {self.pretty},"
+                " expected 0-2 characters for network code"
+            )
+        if len(self.station) > 5 or len(self.station) < 1:
+            raise ValueError(
+                f"invalid station {self.station} for {self.pretty},"
+                " expected 1-5 characters for station code"
+            )
+        if len(self.location) > 2:
+            raise ValueError(
+                f"invalid location {self.location} for {self.pretty},"
+                " expected 0-2 characters for location code"
+            )
 
 
-NSL = Annotated[_NSL, BeforeValidator(_NSL.parse)]
+NSL = Annotated[_NSL, BeforeValidator(_NSL.parse), AfterValidator(_NSL._check)]
 
 
 class _Range(NamedTuple):

test/test_utils.py

@@ -1,3 +1,4 @@
+import pytest
 from pydantic import BaseModel
 from qseek.utils import NSL
 
@@ -23,3 +24,24 @@ class Model(BaseModel):
     }
     """
     Model.model_validate_json(json)
+
+    json = """
+    {
+        "nsl": "6E.TE234.",
+        "nsl_list": [".TE232"]
+    }
+    """
+    Model.model_validate_json(json)
+
+    json_tpl = """
+    {{
+        "nsl": "{code}",
+        "nsl_list": []
+    }}
+    """
+
+    invalid_codes = ["6E", "6E5.", "6E.", "6E.TE123112"]
+
+    for code in invalid_codes:
+        with pytest.raises(ValueError):
+            Model.model_validate_json(json_tpl.format(code=code))