diff --git a/parser.py b/parser.py index c9363dc..dcdab52 100644 --- a/parser.py +++ b/parser.py @@ -7,7 +7,7 @@ def is_blank(l: str) -> bool: def parse(): - fp = open("dados.txt") + fp = open("test_data.txt") data = [l for l in fp.read().split("\n")] chunks = boundaries(data) @@ -34,9 +34,8 @@ def boundaries(data: list[str]): def parse_chunk(chunk_lines: list[str]): header = None for (idx, l) in enumerate(chunk_lines): - print(l[-1]) - if l[-1] == " ": - header = idx-1 + if l[-1] == "7": + header = idx break parse_header(chunk_lines[:header]) @@ -60,6 +59,8 @@ def parse_header(hLines: list[str]): aux["E"].append(line) case "I": aux["I"].append(line) + case "F": + aux["F"].append(line) case _: raise NotImplemented @@ -70,6 +71,19 @@ def parse_header(hLines: list[str]): pprint(headerDict) +def parse_mag(line: str): + magnitudes = [] + base = 55 + while base < 79: + print(base) + m = line[base:base+4] + mt = line[base+4] + if not is_blank(m): + magnitudes.append({"M": m, "T": mt}) + base += 8 + return magnitudes + + def parse_type_1(data: list[str]): aux = data[0] y = int(aux[1:5]) @@ -92,34 +106,28 @@ def parse_type_1(data: list[str]): for l in data: hypo["Magnitudes"] = hypo["Magnitudes"] + parse_mag(l) - + return hypo -def parse_mag(line: str): - magnitudes = [] - base = 55 - while base < 80: - m = line[base:base+4] - mt = line[base+4] - if is_blank(m): - break - magnitudes.append({"M": m, "T": mt}) - base += 8 - return magnitudes - - def parse_type_2(data: list[str]): return {} def parse_type_3(data: list[str]): - return {} + comments = [] + for line in data: + comments.append(line[:-2].strip()) + return {"Comments": comments} def parse_type_5(data: list[str]): return {} def parse_type_6(data: list[str]): - return {} + waves = [] + for l in data: + waves.append(l.strip().split(" ")[0]) + + return {"Wave": waves} def parse_type_e(data: list[str]): aux = data[0] @@ -131,7 +139,9 @@ def parse_type_f(data: list[str]): return {} def parse_type_i(data: list[str]): - return {} + aux = data[0] + dt = datetime.strptime(aux[12:26], "%y-%m-%d %H:%M") + return {"Action": aux[8:11], "Action Extra": {"Date": dt.isoformat(), "OP": aux[30:35].strip(), "Status": aux[42:57].strip(), "ID":int(aux[60:74])}} FUNCS = {1: parse_type_1, 2: parse_type_2, 3: parse_type_3, 5: parse_type_5, 6: parse_type_6, "E": parse_type_e, "F": parse_type_f, "I": parse_type_i} diff --git a/test_data.txt b/test_data.txt new file mode 100644 index 0000000..1befe10 --- /dev/null +++ b/test_data.txt @@ -0,0 +1,31 @@ + 1996 6 7 1325 29.2 L 59.846 5.130 12.0F TES 12 .60 1.9LTES 2.2CTES 2.0LNAO1 + GAP=177 2.78 4.5 12.80.000 0.2239E+02 0.6258E+03 -0.2817E+03E + 1996 6 7 1325 30.5 L 59.763 5.396 29.2 NAO 2 1.0 2.0LNAO1 + 8.3 41.0 74.7 1 F + 1996-06-07-1324-51S.TEST__009 6 + ACTION:SPL 14-12-11 12:04 OP:jh STATUS: ID:19960607132529 L I + STAT COM NTLO IPHASE W HHMM SS.SSS PAR1 PAR2 AGA OPE AIN RES W DIS CAZ7 + EGD HHZ NS IP 4 1325 35.950 C BER jh 120.0-1.131047.70 6 + EGD HHZ NS END 1325 35.950 111.0 BER jh 0.0 47.70 6 + EGD HHZ NS AMP 1325 35.950 11.1 33.3 BER jh 47.70 6 + EGD HHN NS ES 1325 42.030 BER jh 70.0-.8901047.70 6 + BER BHZ NS00 IP 1325 38.120 C kkk AUT -.9801061.00 11 + BER BHZ NS00 END 1325 38.120 55.0 BER jh 4.8 61.00 11 + BER BHN NS00 ES 1325 45.440 BER jh 70.0-.9901061.00 11 + BER BHZ NS00 IAML A1325 46.710 31.7 0.20 BER jh 0.4 61.00 11 + KMY BHZ NS10 IP 1325 40.260 C PPP Ajh 70.0 .3301070.90 175 + KMY BHZ NS10 END 1325 40.260 62.0 BER jh 70.90 175 + KMY BHN NS10 ES 1325 48.740 BER jh 70.0.3001070.90 175 + KMY BHZ NS10 IAML 1325 48.920 83.6 0.20 BER jh 70.90 175 + ASK SHZ NS EP 2 1325 39.590 D -1.031071.10 3 + ASK SHZ NS END 1325 39.590 68.0 71.10 3 + ASK SHZ NS ES 1325 48.070 -1.021071.10 3 + ASK SHZ NS AMP 1325 48.070 333.3 2.20 71.10 3 + ASK SHZ NS IAML 1325 50.900 111.0 0.30 71.10 3 + NRA0 S Z Pn A1326 19.090 50.0-.05010368.0 72 + NRA0 S Z END 1326 19.090 333.0 368.0 72 + NRA0 S Z BAZ-P 1326 19.090 256.9 6.9 0. 368.0 72 + NRA0 S Z Pg 1326 27.940 -.64010368.0 72 + NRA0 S Z BAZ 1326 27.940 253.0 7.3 -3. 368.0 72 + NRA0 S Z Lg 1327 10.540 -.89010368.0 72 + NRA0 S Z BAZ 1327 10.540 266.6 4.1 9. 368.0 72 diff --git a/tests.py b/tests.py new file mode 100644 index 0000000..8e7aeff --- /dev/null +++ b/tests.py @@ -0,0 +1,50 @@ +import pytest +import parser + +def test_type_1(): + test_data =[" 1996 6 7 1325 29.2 L 59.846 5.130 12.0F TES 12 .60 1.9LTES 2.2CTES 2.0LNAO1", + " 1996 6 7 1325 30.5 L 59.763 5.396 29.2 NAO 2 1.0 2.0LNAO1"] + expected = {"DateTime": "1996-06-07T13:25:29.200000", "Distance Indicator": "L", "Event ID": " ", 'Lat': 59.846, 'Long': 5.13,'Depth': 12.0, 'Agency': 'TES', 'Magnitudes': [{'M': ' 1.9', 'T': 'L'},{'M': ' 2.2', 'T': 'C'},{'M': ' 2.0', 'T': 'L'},{'M': ' 2.0', 'T': 'L'}]} + + _ret = parser.parse_type_1(test_data) + for (k,v) in _ret.items(): + assert _ret[k] == expected[k] + +def test_type_3(): + test_data = [" OP: CVUA-RM/RC 3", +" STATUS: OK SENTIDO 3", +" SENTIDO: II/III -Pico: S. Caetano 3", +" PUB: NAO 3", +" WEB: SIM 3", +" OBS: Por ordem do CT nao foi emitido novo comunicado 3", +" OBS: Sismo sobreposto 3", +" REGIAO: Pico,VZ14,SZ06,FE95 405 3"] + + _ret = parser.parse_type_3(test_data) + assert len(_ret["Comments"]) == 8 + +def test_type_6(): + test_data = [" 1996-06-03-2002-18S.TEST__012 6", + " 1996-06-03-1917-52S.TEST__002 6"] + expected = {"Wave": ["1996-06-03-2002-18S.TEST__012", "1996-06-03-1917-52S.TEST__002"]} + + _ret = parser.parse_type_6(test_data) + for (k,v) in _ret.items(): + assert _ret[k] == expected[k] + +def test_type_i(): + test_data = [" ACTION:SPL 08-10-02 10:19 OP:jh STATUS: ID:19960603195540 I"] + expected = {"Action": "SPL", "Action Extra": {"Date": '2008-10-02T10:19:00', "OP": "jh", "Status": "", "ID":19960603195540}} + + _ret = parser.parse_type_i(test_data) + for (k,v) in _ret.items(): + assert _ret[k] == expected[k] + +def test_type_e(): + test_data =[" GAP=348 2.88 999.9 999.9999.9 -0.1404E+08 -0.3810E+08 0.1205E+09E"] + expected = {"Gap": 348, "Origin": 2.88, "Error_lat": 999.9, "Error_long": 999.9, "Error_depth": 999.9, "Cov_xy": -14040000.0, "Cov_xz": -38100000.0, "Cov_yz": 120500000.0} + + _ret = parser.parse_type_e(test_data) + for (k,v) in _ret.items(): + assert _ret[k] == expected[k] +