various gps parsers support

wizard/parsers/helpers.py

@@ -5,6 +5,13 @@ def stream_starts_with(stream, text):
     return chunk == text
 
 
+def stream_chunk_contains(stream, length, text):
+    position = stream.tell()
+    chunk = stream.read(length)
+    stream.seek(position)
+    return text in chunk
+
+
 def read_csv(data, separator=",", newline="\n", trailing=""):
     for line in data.split(newline):
         if not line:

wizard/parsers/parser.py

@@ -2,15 +2,13 @@
 import logging
 
 from .parser_base import Parser
-from .parser_gps import GPSParser, GPSCSVParser
+from .parser_gps import PARSERS as GPS_PARSERS
 from .parser_pathtrack import PathtrackParser, PathtrackParserNoUnknown
 
 available_parsers = [
-    GPSParser,
-    GPSCSVParser,
     PathtrackParser,
     PathtrackParserNoUnknown,
-]
+] + GPS_PARSERS
 
 
 def detect(stream) -> Parser:

wizard/parsers/parser_base.py

@@ -37,16 +37,17 @@ class CSVParser(Parser):
     DATATYPE = "generic_csv"
     FIELDS = []
     SEPARATOR = ','
+    SKIP_INITIAL_SPACE = True
 
     def __init__(self, stream):
         super().__init__(stream)
         if not self.stream.seekable():
             self._raise_not_supported('Stream not seekable')
 
-        reader = csv.reader(self.stream, delimiter=self.SEPARATOR)
+        reader = csv.reader(self.stream, delimiter=self.SEPARATOR, skipinitialspace=self.SKIP_INITIAL_SPACE)
         header = next(reader)
-        if len(header) != len(self.FIELDS):
-            self._raise_not_supported(f"Stream have a number of fields different than expected, {len(header)} != {len(self.FIELDS)}")
+        if header != self.FIELDS:
+            self._raise_not_supported(f"Stream have a header different than expected, {header} != {self.FIELDS}")
 
         self.stream.seek(0)
-        self.data = pd.read_csv(self.stream, sep=self.SEPARATOR)
+        self.data = pd.read_csv(self.stream, header=1, names=self.FIELDS, sep=self.SEPARATOR)

wizard/parsers/parser_gps.py

@@ -1,4 +1,9 @@
+import pandas as pd
+import csv
+import io
+import logging
 from .parser_base import CSVParser
+from .helpers import stream_starts_with, stream_chunk_contains
 
 
 class GPSParser(CSVParser):
@@ -31,8 +36,138 @@ class GPSParser(CSVParser):
         ]
 
 
-class GPSCSVParser(CSVParser):
-    DATATYPE = "gps_csv"
+class IGotU_GT_Parser(CSVParser):
+    '''
+    Parser for IGotU_GT X version Logger
+    '''
+    DATATYPE = "gps_igotugl"
     FIELDS = [
             "Date", "Time", "Latitude", "Longitude", "Altitude", "Speed", "Course", "Type", "Distance", "Essential"
         ]
+
+
+class IGotU_GT_TabSeparatedParser(IGotU_GT_Parser):
+    '''
+    Parser for Earth&Ocean Logger separated by tabs
+    '''
+    SEPARATOR = '\t'
+
+
+class GPSUnknownFormatParser(CSVParser):
+    '''
+    Parser for a format, its a GPS CSV like format
+    with the following fields
+    '''
+    DATATYPE = "gps_unknown"
+    SEPARATOR = '\t'
+    FIELDS = [
+            "DataID", "ID","Ring_nr","Date","Time","Altitude","Speed","Course","HDOP","Latitude","Longitude","TripNr"]
+
+
+class GPSUnknownFormatParserWithEmptyColumns(GPSUnknownFormatParser):
+    '''
+    Parser for a format, its a GPS CSV like format
+    with the following fields
+    '''
+
+    def __init__(self, stream):
+        self.stream = stream
+        self.data = []
+
+        if not self.stream.seekable():
+            self._raise_not_supported('Stream not seekable')
+
+        reader = csv.reader(self.stream, delimiter=self.SEPARATOR, skipinitialspace=self.SKIP_INITIAL_SPACE)
+        header = next(reader)
+
+        # Filter empty columns
+        header = [c for c in header if c != ""]
+
+        if header != self.FIELDS:
+            self._raise_not_supported(f"Stream have a header different than expected, {header} != {self.FIELDS}")
+
+        self.stream.seek(0)
+        self.data = pd.read_csv(self.stream, header=1, names=self.FIELDS, sep=self.SEPARATOR)
+
+
+class GPSCatTrackParser(CSVParser):
+    '''
+    Parser for a format, its a GPS CSV like format
+    with the following fields
+    '''
+    DATATYPE = "gps_cattrack"
+    DIVIDER = "--------\n"
+    FIELDS = [
+"Date", "Time", "Latitude", "Longitude", "Altitude", "Satellites", "HDOP", "PDOP", "Temperature [C]", "Speed [km/h]", "TTFF", "SNR", "tbd"]
+
+    def __init__(self, stream):
+        self.stream = stream
+        self.data = []
+
+        if not self.stream.seekable():
+            self._raise_not_supported('Stream not seekable')
+
+        if not stream_starts_with(self.stream, "Name:CatLog"):
+            self._raise_not_supported(f"Stream must start with Name:CatLog")
+
+        _intro, data = self.stream.read().split(self.DIVIDER)
+        content = io.StringIO(data)
+
+        reader = csv.reader(content, delimiter=self.SEPARATOR, skipinitialspace=self.SKIP_INITIAL_SPACE)
+        header = next(reader)
+        if header != self.FIELDS:
+            self._raise_not_supported(f"Stream have fields different than expected, {header} != {self.FIELDS}")
+
+        self.data = pd.read_csv(content, header=0, names=self.FIELDS, sep=self.SEPARATOR)
+
+
+class GPS2JMParser(CSVParser):
+    '''
+    Parser for 2Jm format
+    '''
+    DATATYPE = "gps_2jm"
+    # TODO: define fields
+    FIELDS = [str(x) for x in range(0,13)]
+    SEPARATOR = " "
+    ENDINGS = [
+        "[EOF]",
+        "---- End of data ----",
+    ]
+
+    def __init__(self, stream):
+        self.stream = stream
+        self.data = []
+
+        if not self.stream.seekable():
+            self._raise_not_supported('Stream not seekable')
+
+        if not stream_chunk_contains(self.stream, 30, "2JmGPS-LOG"):
+            self._raise_not_supported(f"Stream must start with 2JmGPS-LOG")
+
+        groups = self.stream.read().split('\n\n')[1:]
+        data = None
+        for group in groups:
+            if group in self.ENDINGS:
+                break
+            data = group
+
+        content = io.StringIO(data)
+
+        reader = csv.reader(content, delimiter=self.SEPARATOR, skipinitialspace=self.SKIP_INITIAL_SPACE)
+        header = next(reader)
+        if len(header) != len(self.FIELDS):
+            self._raise_not_supported(f"Stream have fields different than expected, {len(header)} != {len(self.FIELDS)}")
+
+        self.data = pd.read_csv(content, header=0, names=self.FIELDS, sep=self.SEPARATOR)
+
+
+
+PARSERS = [
+    GPSParser,
+    GPSUnknownFormatParser,
+    GPSUnknownFormatParserWithEmptyColumns,
+    GPSCatTrackParser,
+    IGotU_GT_Parser,
+    IGotU_GT_TabSeparatedParser,
+    GPS2JMParser,
+]