Coverage for C: \ Users \ peaco \ OneDrive \ Documents \ GitHub \ mt_metadata \ mt_metadata \ transfer_functions \ io \ emtfxml \ metadata \ site.py: 98%
83 statements
« prev ^ index » next coverage.py v7.13.1, created at 2026-01-10 00:11 -0800
1# =====================================================
2# Imports
3# =====================================================
4from typing import Annotated
5from xml.etree import cElementTree as et
7import numpy as np
8import pandas as pd
9from pydantic import Field, field_validator
11from mt_metadata.base import MetadataBase
12from mt_metadata.common import BasicLocationNoDatum, Comment
13from mt_metadata.common.mttime import MTime
14from mt_metadata.transfer_functions.io.emtfxml.metadata import helpers
16from . import DataQualityNotes, DataQualityWarnings, Orientation
19# =====================================================
20class Site(MetadataBase):
21 project: Annotated[
22 str,
23 Field(
24 default="",
25 description="Name of the project",
26 alias=None,
27 pattern="^[a-zA-Z0-9-_]*$",
28 json_schema_extra={
29 "units": None,
30 "required": True,
31 "examples": ["USMTArray"],
32 },
33 ),
34 ]
36 survey: Annotated[
37 str,
38 Field(
39 default="",
40 description="Name of the survey",
41 alias=None,
42 json_schema_extra={
43 "units": None,
44 "required": True,
45 "examples": ["MT 2020"],
46 },
47 ),
48 ]
50 year_collected: Annotated[
51 MTime | str | float | int | np.datetime64 | pd.Timestamp,
52 Field(
53 default=None,
54 description="Year data collected",
55 alias=None,
56 json_schema_extra={
57 "units": None,
58 "required": True,
59 "examples": ["2020"],
60 },
61 ),
62 ]
64 country: Annotated[
65 str,
66 Field(
67 default="",
68 description="Country where data was collected",
69 alias=None,
70 json_schema_extra={
71 "units": None,
72 "required": False,
73 "examples": ["USA"],
74 },
75 ),
76 ]
78 id: Annotated[
79 str,
80 Field(
81 default="",
82 description="Station ID name. This should be an alpha numeric name that is typically 5-6 characters long. Commonly the project name in 2 or 3 letters and the station number.",
83 alias=None,
84 pattern="^[a-zA-Z0-9]*$",
85 json_schema_extra={
86 "units": None,
87 "required": True,
88 "examples": ["MT001"],
89 },
90 ),
91 ]
93 name: Annotated[
94 str,
95 Field(
96 default="",
97 description="closest geographic name to the station",
98 alias=None,
99 json_schema_extra={
100 "units": None,
101 "required": True,
102 "examples": ['"Whitehorse, YK"'],
103 },
104 ),
105 ]
107 acquired_by: Annotated[
108 str,
109 Field(
110 default="",
111 description="Person or group who collected the data",
112 alias=None,
113 json_schema_extra={
114 "units": None,
115 "required": True,
116 "examples": ["MT Group"],
117 },
118 ),
119 ]
121 start: Annotated[
122 MTime | str | float | int | np.datetime64 | pd.Timestamp,
123 Field(
124 default_factory=lambda: MTime(time_stamp=None),
125 description="Date time when the data collection started",
126 alias=None,
127 json_schema_extra={
128 "units": None,
129 "required": True,
130 "examples": ["2020-01-01T12:00:00"],
131 },
132 ),
133 ]
135 end: Annotated[
136 MTime | str | float | int | np.datetime64 | pd.Timestamp,
137 Field(
138 default_factory=lambda: MTime(time_stamp=None),
139 description="Date time when the data collection ended",
140 alias=None,
141 json_schema_extra={
142 "units": None,
143 "required": True,
144 "examples": ["2020-05-01T12:00:00"],
145 },
146 ),
147 ]
149 run_list: Annotated[
150 list[str] | None,
151 Field(
152 default_factory=list,
153 description="list of runs recorded by the station. Should be a summary of all runs recorded",
154 alias=None,
155 json_schema_extra={
156 "units": None,
157 "required": True,
158 "examples": ['"[ mt001a, mt001b, mt001c ]"'],
159 },
160 ),
161 ]
163 data_quality_notes: Annotated[
164 DataQualityNotes,
165 Field(
166 default_factory=DataQualityNotes, # type: ignore
167 description="Notes on the data quality",
168 alias=None,
169 json_schema_extra={
170 "units": None,
171 "required": False,
172 "examples": ["Data quality is good"],
173 },
174 ),
175 ]
177 data_quality_warnings: Annotated[
178 DataQualityWarnings,
179 Field(
180 default_factory=DataQualityWarnings, # type: ignore
181 description="Warnings about the data quality",
182 alias=None,
183 json_schema_extra={
184 "units": None,
185 "required": False,
186 "examples": ["Data quality is questionable"],
187 },
188 ),
189 ]
190 orientation: Annotated[
191 Orientation,
192 Field(
193 default_factory=Orientation, # type: ignore
194 description="Orientation of the site",
195 alias=None,
196 json_schema_extra={
197 "units": None,
198 "required": False,
199 "examples": [
200 "Orientation('layout=orthogonal, angle_to_geographic_north=0.0')"
201 ],
202 },
203 ),
204 ]
206 location: Annotated[
207 BasicLocationNoDatum,
208 Field(
209 default_factory=BasicLocationNoDatum, # type: ignore
210 description="Location of the site",
211 alias=None,
212 json_schema_extra={
213 "units": None,
214 "required": False,
215 "examples": ["BasicLocation('latitude=60.0, longitude=-135.0')"],
216 },
217 ),
218 ]
220 comments: Annotated[
221 Comment | str | None,
222 Field(
223 default_factory=Comment, # type: ignore
224 description="Comments about the site",
225 alias=None,
226 json_schema_extra={
227 "units": None,
228 "required": False,
229 "examples": ["Comment('This is a comment about the site')"],
230 },
231 ),
232 ]
234 @field_validator("start", "end", mode="before")
235 @classmethod
236 def validate_start(
237 cls, field_value: MTime | float | int | np.datetime64 | pd.Timestamp | str
238 ):
239 if isinstance(field_value, MTime):
240 return field_value
241 return MTime(time_stamp=field_value)
243 @field_validator("year_collected", mode="before")
244 @classmethod
245 def validate_year_collected(
246 cls, field_value: MTime | float | int | np.datetime64 | pd.Timestamp | str
247 ):
248 if isinstance(field_value, str):
249 if field_value.count("-") == 1:
250 field_value = field_value.split("-")[0]
251 if isinstance(field_value, MTime):
252 return field_value.year
253 if isinstance(field_value, int):
254 # If it's already an integer year, return as-is
255 return field_value
256 return MTime(time_stamp=field_value).year
258 @field_validator("id", "project", "survey", "name", "acquired_by", mode="before")
259 @classmethod
260 def validate_string_fields(cls, field_value: str | None) -> str:
261 """
262 Validate string fields, converting None to empty string.
263 """
264 if field_value is None:
265 return ""
266 return str(field_value)
268 @field_validator("comments", mode="before")
269 @classmethod
270 def validate_comments(cls, value) -> Comment:
271 """
272 Validate that the value is a valid string.
273 """
274 if isinstance(value, str):
275 return Comment(value=value) # type: ignore[return-value]
276 return value
278 @field_validator("run_list", mode="before")
279 @classmethod
280 def validate_run_list(cls, value: str | list[str] | None) -> list[str] | None:
281 """
282 Validate that the value is a list of strings.
283 """
284 if value is None:
285 return None
286 if isinstance(value, str):
287 if value.count("[") > 0 and value.count("]") > 0:
288 # Handle string representation of a list
289 value = value.strip("[]")
291 if value.count(",") > 0:
292 return value.split(",")
293 elif value.count(" ") > 0:
294 # Split by space if no commas are present
295 return value.split(" ")
296 if value == "":
297 return []
298 return [value] # Return as a single-item list if no commas or spaces
300 elif isinstance(value, list) and all(isinstance(item, str) for item in value):
301 return value
302 raise ValueError("run_list must be a list of strings.")
304 def read_dict(self, input_dict: dict) -> None:
305 """
306 Read the input dictionary and update the object's attributes.
308 Parameters
309 ----------
310 input_dict : dict
311 The input dictionary containing the data to read.
312 """
313 for element in input_dict["site"].keys():
314 attr = getattr(self, element)
315 if hasattr(attr, "read_dict"):
316 attr.read_dict(input_dict["site"])
317 else:
318 helpers._read_single(self, input_dict["site"], element)
320 def to_xml(self, string: bool = False, required: bool = True) -> str | et.Element:
321 """
322 Convert the object to XML format.
324 Parameters
325 ----------
326 string : bool, optional
327 Whether to return the XML as a string, by default False
328 required : bool, optional
329 Whether the XML is required, by default True
331 Returns
332 -------
333 str | et.Element
334 The XML representation of the object.
335 """
337 if self.end < self.start: # type: ignore
338 self.end = self.start
340 return helpers.to_xml(
341 self,
342 string=string,
343 required=required,
344 order=[
345 "project",
346 "survey",
347 "year_collected",
348 "country",
349 "id",
350 "name",
351 "location",
352 "orientation",
353 "acquired_by",
354 "start",
355 "end",
356 "run_list",
357 "data_quality_notes",
358 "data_quality_warnings",
359 ],
360 )