disdrodb 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/SPAIN/LIAISE.py

@@ -0,0 +1,137 @@
+#!/usr/bin/env python3
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2023 DISDRODB developers
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# -----------------------------------------------------------------------------.
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+    # - Skip first row as columns names
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin"  # "ISO-8859-1"
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+    # - Define reader engine
+    #   - C engine is faster
+    #   - Python engine is more feature-complete
+    reader_kwargs["engine"] = "python"
+    # - Define on-the-fly decompression of on-disk data
+    #   - Available: gzip, bz2, zip
+    reader_kwargs["compression"] = "infer"
+    # - Strings to recognize as NA/NaN and replace with standard NA flags
+    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+    reader_kwargs["na_values"] = ["na", "", "error"]
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Define time
+    df = df["TO_PARSE"].str.split(",", n=2, expand=True)
+    df.columns = ["date", "time", "TO_PARSE"]
+    datetime_str = df["date"] + " " + df["time"]
+    df["time"] = pd.to_datetime(datetime_str, format="%d.%m.%Y %H:%M:%S", errors="coerce")
+
+    # Identify rows with integral variables
+    df_vars = df[df["TO_PARSE"].str.len() == 61]
+
+    # Split and assign column names
+    df_data = df_vars["TO_PARSE"].str.split(",", expand=True)
+    var_names = [
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+    ]
+    df_data.columns = var_names
+    df_data["time"] = df_vars["time"]
+
+    # Initialize empty arrays
+    # --> 0 values array produced in L0B
+    df_data["raw_drop_concentration"] = ""
+    df_data["raw_drop_average_velocity"] = ""
+    df_data["raw_drop_number"] = ""
+
+    # Identify raw spectrum
+    df_raw_spectrum = df[df["TO_PARSE"].str.len() == 4545]
+
+    # Derive raw drop arrays
+    def split_string(s):
+        vals = [v.strip() for v in s.split(",")]
+        c1 = ",".join(vals[:32])
+        c2 = ",".join(vals[32:64])
+        c3 = ",".join(vals[64].replace("r", "").split("/"))
+        series = pd.Series(
+            {
+                "raw_drop_concentration": c1,
+                "raw_drop_average_velocity": c2,
+                "raw_drop_number": c3,
+            },
+        )
+        return series
+
+    splitted_string = df_raw_spectrum["TO_PARSE"].apply(split_string)
+    df_raw_spectrum["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
+    df_raw_spectrum["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
+    df_raw_spectrum["raw_drop_number"] = splitted_string["raw_drop_number"]
+    df_raw_spectrum = df_raw_spectrum.drop(columns=["date", "TO_PARSE"])
+
+    # Add raw array
+    df = df_data.set_index("time")
+    df_raw_spectrum = df_raw_spectrum.set_index("time")
+
+    df.update(df_raw_spectrum)
+
+    # Set back time as column
+    df = df.reset_index()
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/USA/C3WE.py

@@ -0,0 +1,146 @@
+#!/usr/bin/env python3
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2023 DISDRODB developers
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# -----------------------------------------------------------------------------.
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+    # - Define reader engine
+    #   - C engine is faster
+    #   - Python engine is more feature-complete
+    reader_kwargs["engine"] = "python"
+    # - Define on-the-fly decompression of on-disk data
+    #   - Available: gzip, bz2, zip
+    reader_kwargs["compression"] = "infer"
+    # - Strings to recognize as NA/NaN and replace with standard NA flags
+    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+    reader_kwargs["na_values"] = ["na", "", "error", "NA", "-.-"]
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Define 'time' datetime
+
+    # Split the columns
+    df["TO_PARSE"].iloc[0:5].str.split(";", n=16, expand=True).iloc[0]
+
+    df = df["TO_PARSE"].str.split(";", n=16, expand=True)
+
+    # Assign column names
+    names = [
+        "sensor_serial_number",
+        "sensor_status",
+        "laser_amplitude",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "dummy_date",
+        "sensor_time",
+        "sensor_date",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "reflectivity_32bit",
+        "rainfall_accumulated_16bit",
+        "mor_visibility",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "TO_SPLIT",
+    ]
+    df.columns = names
+
+    # Derive raw drop arrays
+    def split_string(s):
+        vals = [v.strip() for v in s.split(";")]
+        c1 = ";".join(vals[:32])
+        c2 = ";".join(vals[32:64])
+        c3 = ";".join(vals[64:1088])
+        c4 = vals[1088]
+        c5 = vals[1089]
+        series = pd.Series(
+            {
+                "raw_drop_concentration": c1,
+                "raw_drop_average_velocity": c2,
+                "raw_drop_number": c3,
+                "rain_kinetic_energy": c4,
+                "CHECK_EMPTY": c5,
+            },
+        )
+        return series
+
+    splitted_string = df["TO_SPLIT"].apply(split_string)
+    df["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
+    df["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
+    df["raw_drop_number"] = splitted_string["raw_drop_number"]
+    df["rain_kinetic_energy"] = splitted_string["rain_kinetic_energy"]
+    df["CHECK_EMPTY"] = splitted_string["CHECK_EMPTY"]
+
+    # Ensure valid observation
+    df = df[df["CHECK_EMPTY"] == ""]
+
+    # Add the time column
+    time_str = df["sensor_date"] + "-" + df["sensor_time"]
+    df["time"] = pd.to_datetime(time_str, format="%d.%m.%Y-%H:%M:%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "dummy_date",
+        "sensor_date",
+        "sensor_time",
+        "sensor_serial_number",
+        "rainfall_accumulated_16bit",  # unexpected format
+        "CHECK_EMPTY",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PWS100/FRANCE/ENPC_PWS100.py

@@ -17,12 +17,112 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
 """DISDRODB reader for ENPC PWS100 raw text data."""
-import zipfile
-
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
-from disdrodb.utils.logger import log_error, log_warning
+from disdrodb.utils.logger import log_error  # , log_warning
+
+
+def read_txt_file(file, filename, logger):
+    r"""Parse a single txt file within the daily zip file.
+
+    The file starts with \\x020 and ends with \\x03\\r\\n.
+    """
+    # Read file
+    try:
+        txt = file.readline().decode("utf-8")
+    except Exception:
+        log_error(logger=logger, msg=f"{filename} is corrupted", verbose=False)
+        return None
+
+    # Check file is not empty
+    if txt == "":
+        log_error(logger=logger, msg=f"{filename} is empty", verbose=False)
+        return None
+
+    # Remove everything before \x020
+    # - At start it can appear: \x013 0 \x02PSU voltage too low 13.3\x03\r\n\
+    txt = txt.split("x020 ", 1)[-1]
+
+    # Remove everything after \\x03
+    txt = txt.split("x03", 1)[0]
+
+    # if "PSU voltage too low" in txt or "volt" in txt:
+    #     log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
+    #     return None
+
+    # if "Error - message" in txt:
+    #     log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
+    #     return None
+
+    # Clean up the line
+    txt = txt.replace(" 00 ", " 0 0 ")
+    txt = txt.replace("  ", " 0 ")
+
+    # Split the cleaned line
+    buf = txt.split(" ")
+
+    # Helper to convert list of floats to comma-separated string
+    def int_list_to_str(lst):
+        return ",".join(f"{int(i)}" for i in lst)
+
+    # Try to get the drop_size distribution:
+    try:
+        drop_size_distribution = int_list_to_str(buf[29:329])  # Drop size distribution (message field 42)
+    except Exception:
+        log_error(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
+        return None
+
+    # Try to get peak_to_pedestal_hist
+    try:
+        peak_to_pedestal_hist = int_list_to_str(buf[1498:1548])
+    except Exception:
+        log_error(
+            logger,
+            msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
+            verbose=False,
+        )
+        return None
+
+    # Parse fields
+    data = {
+        "mor_visibility": float(buf[1]),  # Visibility Range (message field 20)
+        "weather_code_synop_4680": float(buf[2]),  # Present Weather Code (WMO)  (message field 21)
+        "weather_code_metar_4678": buf[3],  # Present Weather Code (METAR)  (message field 22)
+        "weather_code_nws": buf[4],  # Present Weather Code (NWS)  (message field 23)
+        "alarms": int_list_to_str(buf[5:21]),  # Alarms (message field (24))
+        "sensor_status": buf[21],  # Fault status of PWS100 (message field 25)
+        "air_temperature": float(buf[22]),  # Temperature (°C) (message field 30)
+        "relative_humidity": float(buf[23]),  # Sampled relative humidity (%) (message field 30)
+        "wetbulb_temperature": float(buf[24]),  # Average wetbulb temperature (°C)(message field 30)
+        "air_temperature_max": float(buf[25]),  # Maximum temperature (°C)(message field 31)
+        "air_temperature_min": float(buf[26]),  # Minimum temperature (°C)(message field 31)
+        "rainfall_rate": float(buf[27]),  # Precipitation rate (mm/h)(message field 40)
+        "rainfall_accumulated": float(buf[28]),  # Precipitation accumulation (mm/h)(message field 41)
+        "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
+        "average_drop_velocity": float(buf[329]),  # Average velocity (mm/s)(message field 43)
+        "average_drop_size": float(buf[330]),  # Average size (mm/h)(message field 43)
+        "type_distribution": int_list_to_str(buf[331:342]),  # Type distribution (message field 44)
+        "raw_drop_number": int_list_to_str(buf[342:1498]),  # Size/velocity spectrum (34*34) (message field 47)
+        "peak_to_pedestal_hist": (
+            peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
+        ),
+    }
+
+    # Convert to single-row DataFrame
+    df = pd.DataFrame([data])
+
+    # Define datetime "time" column from filename
+    datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+    df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+    # # Drop columns not agreeing with DISDRODB L0 standards
+    # columns_to_drop = [
+    #      "peak_to_pedestal_hist",
+    #      "type_distribution",
+    # ]
+    # df = df.drop(columns=columns_to_drop)
+    return df
 
 
 @is_documented_by(reader_generic_docstring)
@@ -31,102 +131,9 @@ def reader(
     logger=None,
 ):
     """Reader."""
+    import zipfile
 
-    ##------------------------------------------------------------------------.
-    #### Define function to read each txt file inside each daily zip file
-    def read_txt_file(file, filename, logger):  # noqa PLR0911
-        """Parse a single txt file within the daily zip file."""
-        # Read file
-        try:
-            txt = file.readline().decode("utf-8")
-        except Exception:
-            log_warning(logger=logger, msg=f"{filename} is corrupted", verbose=False)
-            return None
-
-        # Check file is not empty
-        if txt == "":
-            log_warning(logger=logger, msg=f"{filename} is empty", verbose=False)
-            return None
-
-        if "PSU voltage too low" in txt or "volt" in txt:
-            log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
-            return None
-
-        if "Error - message" in txt:
-            log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
-            return None
-
-        # Clean up the line
-        txt = txt.replace(" 00 ", " 0 0 ")
-        txt = txt.replace("  ", " 0 ")
-        txt = txt[1:-8]
-
-        # Split the cleaned line
-        buf = txt.split(" ")
-
-        # Helper to convert list of floats to comma-separated string
-        def int_list_to_str(lst):
-            return ",".join(f"{int(i)}" for i in lst)
-
-        # Try to get the drop_size distribution:
-        try:
-            drop_size_distribution = int_list_to_str(buf[30:330])  # Drop size distribution (message field 42)
-        except Exception:
-            log_warning(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
-            return None
-
-        # Try to get peak_to_pedestal_hist
-        try:
-            peak_to_pedestal_hist = int_list_to_str(buf[1499:1549])
-        except Exception:
-            log_warning(
-                logger,
-                msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
-                verbose=False,
-            )
-            return None
-        # Parse fields
-        data = {
-            "mor_visibility": float(buf[2]),  # Visibility Range (message field 20)
-            "weather_code_synop_4680": float(buf[3]),  # Present Weather Code (WMO)  (message field 21)
-            "weather_code_metar_4678": buf[4],  # Present Weather Code (METAR)  (message field 22)
-            "weather_code_nws": buf[5],  # Present Weather Code (NWS)  (message field 23)
-            "alarms": int_list_to_str(buf[6:22]),  # Alarms (message field (24))
-            "sensor_status": buf[22],  # Fault status of PWS100 (message field 25)
-            "air_temperature": float(buf[23]),  # Temperature (°C) (message field 30)
-            "relative_humidity": float(buf[24]),  # Sampled relative humidity (%) (message field 30)
-            "wetbulb_temperature": float(buf[25]),  # Average wetbulb temperature (°C)(message field 30)
-            "air_temperature_max": float(buf[26]),  # Maximum temperature (°C)(message field 31)
-            "air_temperature_min": float(buf[27]),  # Minimum temperature (°C)(message field 31)
-            "rainfall_rate": float(buf[28]),  # Precipitation rate (mm/h)(message field 40)
-            "rainfall_accumulated": float(buf[29]),  # Precipitation accumulation (mm/h)(message field 41)
-            "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
-            "average_drop_velocity": float(buf[330]),  # Average velocity (mm/s)(message field 43)
-            "average_drop_size": float(buf[331]),  # Average size (mm/h)(message field 43)
-            "type_distribution": int_list_to_str(buf[332:343]),  # Type distribution (message field 44)
-            "raw_drop_number": int_list_to_str(buf[343:1499]),  # Size/velocity spectrum (34*34) (message field 47)
-            "peak_to_pedestal_hist": (
-                peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
-            ),
-        }
-
-        # Convert to single-row DataFrame
-        df = pd.DataFrame([data])
-
-        # Define datetime "time" column from filename
-        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
-        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
-
-        # # Drop columns not agreeing with DISDRODB L0 standards
-        # columns_to_drop = [
-        #      "peak_to_pedestal_hist",
-        #      "type_distribution",
-        # ]
-        # df = df.drop(columns=columns_to_drop)
-        return df
-
-    # ---------------------------------------------------------------------.
-    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # Iterate over all files (aka timesteps) in the daily zip archive
     # - Each file contain a single timestep !
     list_df = []
     with zipfile.ZipFile(filepath, "r") as zip_ref:
@@ -146,5 +153,4 @@ def reader(
     # Concatenate all dataframes into a single one
     df = pd.concat(list_df)
 
-    # ---------------------------------------------------------------------.
     return df

disdrodb/l0/readers/PWS100/FRANCE/ENPC_PWS100_SIRTA.py

@@ -0,0 +1,151 @@
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2023 DISDRODB developers
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# -----------------------------------------------------------------------------.
+"""DISDRODB reader for ENPC PWS100 raw text data."""
+import zipfile
+
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.utils.logger import log_error  # , log_warning
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+
+    ##------------------------------------------------------------------------.
+    #### Define function to read each txt file inside each daily zip file
+    def read_txt_file(file, filename, logger):
+        r"""Parse a single txt file within the daily zip file.
+
+        The file starts with \x020 and ends with \x03\r\r\n.
+        """
+        # Read file
+        try:
+            txt = file.readline().decode("utf-8")
+        except Exception:
+            log_error(logger=logger, msg=f"{filename} is corrupted", verbose=False)
+            return None
+
+        # Check file is not empty
+        if txt == "":
+            log_error(logger=logger, msg=f"{filename} is empty", verbose=False)
+            return None
+
+        # if "PSU voltage too low" in txt or "volt" in txt:
+        #     log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
+        #     return None
+
+        # if "Error - message" in txt:
+        #     log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
+        #     return None
+
+        # Clean up the line
+        txt = txt.replace(" 00 ", " 0 0 ")
+        txt = txt.replace("  ", " 0 ")
+        txt = txt[1:-8]
+
+        # Split the cleaned line
+        buf = txt.split(" ")
+
+        # Helper to convert list of floats to comma-separated string
+        def int_list_to_str(lst):
+            return ",".join(f"{int(i)}" for i in lst)
+
+        # Try to get the drop_size distribution:
+        try:
+            drop_size_distribution = int_list_to_str(buf[30:330])  # Drop size distribution (message field 42)
+        except Exception:
+            log_error(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
+            return None
+
+        # Try to get peak_to_pedestal_hist
+        try:
+            peak_to_pedestal_hist = int_list_to_str(buf[1499:1549])
+        except Exception:
+            log_error(
+                logger,
+                msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
+                verbose=False,
+            )
+            return None
+        # Parse fields
+        data = {
+            "mor_visibility": float(buf[2]),  # Visibility Range (message field 20)
+            "weather_code_synop_4680": float(buf[3]),  # Present Weather Code (WMO)  (message field 21)
+            "weather_code_metar_4678": buf[4],  # Present Weather Code (METAR)  (message field 22)
+            "weather_code_nws": buf[5],  # Present Weather Code (NWS)  (message field 23)
+            "alarms": int_list_to_str(buf[6:22]),  # Alarms (message field (24))
+            "sensor_status": buf[22],  # Fault status of PWS100 (message field 25)
+            "air_temperature": float(buf[23]),  # Temperature (°C) (message field 30)
+            "relative_humidity": float(buf[24]),  # Sampled relative humidity (%) (message field 30)
+            "wetbulb_temperature": float(buf[25]),  # Average wetbulb temperature (°C)(message field 30)
+            "air_temperature_max": float(buf[26]),  # Maximum temperature (°C)(message field 31)
+            "air_temperature_min": float(buf[27]),  # Minimum temperature (°C)(message field 31)
+            "rainfall_rate": float(buf[28]),  # Precipitation rate (mm/h)(message field 40)
+            "rainfall_accumulated": float(buf[29]),  # Precipitation accumulation (mm/h)(message field 41)
+            "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
+            "average_drop_velocity": float(buf[330]),  # Average velocity (mm/s)(message field 43)
+            "average_drop_size": float(buf[331]),  # Average size (mm/h)(message field 43)
+            "type_distribution": int_list_to_str(buf[332:343]),  # Type distribution (message field 44)
+            "raw_drop_number": int_list_to_str(buf[343:1499]),  # Size/velocity spectrum (34*34) (message field 47)
+            "peak_to_pedestal_hist": (
+                peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
+            ),
+        }
+
+        # Convert to single-row DataFrame
+        df = pd.DataFrame([data])
+
+        # Define datetime "time" column from filename
+        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+        # # Drop columns not agreeing with DISDRODB L0 standards
+        # columns_to_drop = [
+        #      "peak_to_pedestal_hist",
+        #      "type_distribution",
+        # ]
+        # df = df.drop(columns=columns_to_drop)
+        return df
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    list_df = []
+    with zipfile.ZipFile(filepath, "r") as zip_ref:
+        filenames = sorted(zip_ref.namelist())
+        for filename in filenames:
+            if filename.endswith(".txt"):
+                # Open file
+                with zip_ref.open(filename) as f:
+                    try:
+                        df = read_txt_file(file=f, filename=filename, logger=logger)
+                        if df is not None:
+                            list_df.append(df)
+                    except Exception as e:
+                        msg = f"An error occurred while reading {filename}. The error is: {e}."
+                        log_error(logger=logger, msg=msg, verbose=True)
+
+    # Concatenate all dataframes into a single one
+    df = pd.concat(list_df)
+
+    # ---------------------------------------------------------------------.
+    return df