seabirdfilehandler 0.4.2__py3-none-any.whl → 0.5.0__py3-none-any.whl

seabirdfilehandler/seabirdfiles.py

@@ -1,210 +0,0 @@
-from pathlib import Path
-from dataclasses import dataclass
-from datetime import datetime, timezone
-import xmltodict
-import logging
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class SeaBirdFile:
-    """Base class to describe any kind of file generated by the Seasoft
-    software. Such a file should be given as input to this class and the
-    information it contains should subsequently be extracted and structured
-    automatically. Various classes inherit from this one for a more file
-    specific behaviour
-
-    Parameters
-    ----------
-
-    Returns
-    -------
-
-    """
-
-    def __init__(
-        self,
-        path_to_file: Path | str,
-        only_header: bool = False,
-    ):
-        self.path_to_file = Path(path_to_file)
-        self.file_name = self.path_to_file.stem
-        self.file_dir = self.path_to_file.parent
-        self.timestamp = datetime.now(timezone.utc)
-        self.raw_file_data = []  # the text file input
-        self.header = []  # the full file header
-        self.sbe9_data = []  # device specific information
-        self.metadata = {}  # non-SeaBird metadata
-        self.metadata_list = []  # unstructured metadata for easier export
-        self.data_table_description = []  # the column names and other info
-        self.data_table_stats = {}
-        self.data_table_names_and_spans = []
-        self.data_table_misc = {}
-        self.sensor_data = []
-        self.sensors = {}  # xml-parsed sensor data
-        self.processing_info = []  # everything after the sensor data
-        self.data = []  # the data table
-        self.file_data = self.raw_file_data  # variable file information
-        with self.path_to_file.open("r", encoding="latin-1") as file:
-            for line in file:
-                self.raw_file_data.append(line)
-                if only_header and line.startswith("*END*"):
-                    break
-        self.extract_file_information(only_header)
-        if len(self.sensor_data) > 0:
-            self.sensors = self.sensor_xml_to_flattened_dict(
-                "".join(self.sensor_data)
-            )
-
-    def __str__(self) -> str:
-        return "/n".join(self.file_data)
-
-    def __repr__(self) -> str:
-        return str(self.path_to_file.absolute())
-
-    def __eq__(self, other) -> bool:
-        return self.file_data == other.file_data
-
-    def extract_file_information(self, only_header: bool = False):
-        """Reads and structures all the different information present in the
-        file. Lists and Dictionaries are the data structures of choice. Uses
-        basic prefix checking to distinguish different header information.
-
-        Parameters
-        ----------
-
-        Returns
-        -------
-
-        """
-        self.metadata_list = []
-        past_sensors = False
-        for line in self.raw_file_data:
-            line_prefix = line[:2]
-            if line_prefix == "* ":
-                self.header.append(line)
-                self.sbe9_data.append(line[2:])
-            elif line_prefix == "**":
-                self.header.append(line)
-                self.metadata_list.append(line[3:])
-            elif line_prefix == "# ":
-                self.header.append(line)
-                if line[2:].strip()[0] == "<":
-                    self.sensor_data.append(line[2:])
-                    past_sensors = True
-                else:
-                    if past_sensors:
-                        self.processing_info.append(line[2:])
-                    else:
-                        self.data_table_description.append(line[2:])
-            elif line_prefix == "*E":
-                self.header.append(line)
-                if only_header:
-                    break
-            else:
-                self.data.append(line)
-
-        self.metadata = self.structure_metadata(self.metadata_list)
-        self.differentiate_table_description()
-
-    def differentiate_table_description(self):
-        past_spans = False
-        pre = []
-        column_names = []
-        column_value_spans = []
-        post = []
-        for line in self.data_table_description:
-            if line.startswith("name"):
-                # TODO: cuts off lines containing multiple '=' symbols
-                column_names.append(line.split("=")[1].strip())
-            elif line.startswith("span"):
-                past_spans = True
-                column_value_spans.append(line.split("=")[1].strip())
-            else:
-                if not past_spans:
-                    pre.append(line)
-                else:
-                    post.append(line)
-        assert len(column_names) == len(column_value_spans)
-        self.data_table_stats = {
-            line.split("=")[0].strip(): line.split("=")[1].strip()
-            for line in pre
-        }
-        self.data_table_names_and_spans = [
-            (name, span)
-            for name, span in zip(column_names, column_value_spans)
-        ]
-        self.data_table_misc = {
-            line.split("=")[0].strip(): line.split("=")[1].strip()
-            for line in post
-        }
-
-    def sensor_xml_to_flattened_dict(
-        self, sensor_data: str
-    ) -> list[dict] | dict:
-        """Reads the pure xml sensor input and creates a multilevel dictionary,
-        dropping the first two dictionaries, as they are single entry only
-
-        Parameters
-        ----------
-
-        Returns
-        -------
-
-        """
-        full_sensor_dict = xmltodict.parse(sensor_data, process_comments=True)
-        try:
-            sensors = full_sensor_dict["Sensors"]["sensor"]
-        except KeyError as error:
-            logger.error(f"XML is not formatted as expected: {error}")
-            return full_sensor_dict
-        else:
-            # create a tidied version of the xml-parsed sensor dict
-            tidied_sensor_list = []
-            for entry in sensors:
-                # use comment value as type descriptor
-                comment = entry["#comment"]
-                split_comment = comment.split(",")
-                new_entry = split_comment[1].strip()
-                if split_comment[-1] == " 2":
-                    new_entry += " 2"
-                # remove second-level dict
-                calibration_info = list(entry.values())[-1]
-                try:
-                    new_dict = {
-                        "Channel": entry["@Channel"],
-                        "SensorName": new_entry,
-                        **calibration_info,
-                    }
-                except TypeError:
-                    new_dict = {
-                        "Channel": entry["@Channel"],
-                        "SensorName": new_entry,
-                        "Info": calibration_info,
-                    }
-                tidied_sensor_list.append(new_dict)
-            return tidied_sensor_list
-
-    def structure_metadata(self, metadata_list: list) -> dict:
-        """Creates a dictionary to store the metadata that is added by using
-        werums dship API.
-
-        Parameters
-        ----------
-        metadata_list: list :
-            a list of the individual lines of metadata found in the file
-
-        Returns
-        -------
-        a dictionary of the lines of metadata divided into key-value pairs
-        """
-        out_dict = {}
-        for line in metadata_list:
-            try:
-                (key, val) = line.split("=")
-            except ValueError:
-                out_dict["text"] = line
-            else:
-                out_dict[key.strip()] = val.strip()
-        return out_dict

seabirdfilehandler-0.4.2.dist-info/RECORD

@@ -1,13 +0,0 @@
-seabirdfilehandler/__init__.py,sha256=8Vk2TURWXv2_NG_U_fR0fIVDFymkFkBipvmlS5ucB3M,147
-seabirdfilehandler/dataframe_meta_accessor.py,sha256=x4mSEN49us6Ezzjdt41fl5Ry8IJR09ORrZ1roOIJbyc,6439
-seabirdfilehandler/datatablefiles.py,sha256=LwHAh_2dUSERHvs-ql_wBl2a5jcHabOAD5i33fASfs0,31618
-seabirdfilehandler/file_collection.py,sha256=eFJqKnKMwAGC37D27FsPUi7ceTU3iUC0Y_wG2HzxwmU,7518
-seabirdfilehandler/logging.yaml,sha256=mXxbhJPio3OGaukTpc3rLGA8Ywq1DNqp0Vn5YCbH6jY,459
-seabirdfilehandler/parameter.py,sha256=UyKb_HGQ57pETdhSfR5FbJ60aOj8_d3_Tgw_akth0TY,13283
-seabirdfilehandler/seabirdfiles.py,sha256=BKLyk5gUMkt1CG4ljDXlCqcr5zej0-9PjPS0sX2E4n8,7449
-seabirdfilehandler/validation_modules.py,sha256=eZ6x0giftUtlxnRMOnK_vCkgccdwUXPrDjajFa-E6n0,4698
-seabirdfilehandler/xmlfiles.py,sha256=Es0pUCoB0af-meCH-75h-s-r0mEfrthl-8QDjqNBWPk,2441
-seabirdfilehandler-0.4.2.dist-info/LICENSE,sha256=Ifd1VPmYv32oJd2QVh3wIQP9X05vYJlcY6kONz360ws,34603
-seabirdfilehandler-0.4.2.dist-info/METADATA,sha256=9HcKSVWHN90OnsS86UftA7plWh6ho_BUV1sbf5eHESo,1289
-seabirdfilehandler-0.4.2.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-seabirdfilehandler-0.4.2.dist-info/RECORD,,