示例#1
0
    def testSilly(self):
        if not self.can_run:
            return
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x: tuple(x) if utils.containerish(x) else (x, )
        for t in ("a", "b"):
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] = (), []
        schema6 = sillyMeSchema()
        schema6["d"] = [["dField"], ()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x)
                                        for x in (schema2, schema3, schema4,
                                                  schema5, schema6))
        tdf5.set_generator_tables(("a", "c"))
        tdf5 = tdf5.clone()
        filePath = os.path.join(_scratchDir, "silly.db")
        tdf.sql.write_db_data(ticDat, filePath)
        self.assertFalse(tdf.sql.find_duplicates(filePath))

        ticDat2 = tdf2.sql.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.sql.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.sql.create_tic_dat(filePath)
        for t in ["a", "b"]:
            for k, v in getattr(ticDat4, t).items():
                for _k, _v in v.items():
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]):
                    self.assertTrue(t == "b")
                else:
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.sql.create_tic_dat(filePath)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(
            callable(ticDat5.a) and callable(ticDat5.c)
            and not callable(ticDat5.b))

        self.assertTrue("table d" in self.firesException(
            lambda: tdf6.sql.create_tic_dat(filePath)))

        ticDat.a["theboger"] = (1, None, 12)
        tdf.sql.write_db_data(ticDat, makeCleanPath(filePath))
        ticDatNone = tdf.sql.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)
示例#2
0
    def testSilly(self):
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
        for t in ("a", "b") :
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] =  (),  []
        schema6 = sillyMeSchema()
        schema6["d"] =  [["dField"],()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x) for x in (schema2, schema3, schema4, schema5, schema6))
        tdf5.set_generator_tables(("a","c"))
        filePath = os.path.join(_scratchDir, "silly.db")
        tdf.sql.write_db_data(ticDat, filePath)

        ticDat2 = tdf2.sql.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.sql.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.sql.create_tic_dat(filePath)
        for t in ["a","b"]:
            for k,v in getattr(ticDat4, t).items() :
                for _k, _v in v.items() :
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]) :
                    self.assertTrue(t == "b")
                else :
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.sql.create_tic_dat(filePath)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

        self.assertTrue("table d" in self.firesException(lambda  : tdf6.sql.create_tic_dat(filePath)))

        ticDat.a["theboger"] = (1, None, 12)
        tdf.sql.write_db_data(ticDat, makeCleanPath(filePath))
        ticDatNone = tdf.sql.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)
示例#3
0
    def testSilly(self):
        if not self.can_run:
            return
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x: tuple(x) if utils.containerish(x) else (x, )
        for t in ("a", "b"):
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] = (), []
        schema6 = sillyMeSchema()
        schema6["d"] = [["dField"], ()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x)
                                        for x in (schema2, schema3, schema4,
                                                  schema5, schema6))
        tdf5.set_generator_tables(("a", "c"))
        filePath = os.path.join(_scratchDir, "silly.xls")
        tdf.xls.write_file(ticDat, filePath)

        ticDat2 = tdf2.xls.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.xls.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.xls.create_tic_dat(filePath)
        for t in ["a", "b"]:
            for k, v in getattr(ticDat4, t).items():
                for _k, _v in v.items():
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]):
                    self.assertTrue(t == "b")
                else:
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.xls.create_tic_dat(filePath,
                                          treat_inf_as_infinity=False)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(
            callable(ticDat5.a) and callable(ticDat5.c)
            and not callable(ticDat5.b))

        ticDat6 = tdf6.xls.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat6))
        self.assertTrue(
            firesException(lambda: tdf6._same_data(ticDat, ticDat6)))
        self.assertTrue(hasattr(ticDat6, "d") and utils.dictish(ticDat6.d))

        def writeData(data, write_header="same"):
            assert filePath.endswith(".xls")
            assert not write_header or write_header in ("lower", "same",
                                                        "duped")
            import xlwt
            book = xlwt.Workbook()
            for t in tdf.all_tables:
                sheet = book.add_sheet(t)
                if write_header:
                    all_fields = tdf.primary_key_fields.get(
                        t, ()) + tdf.data_fields.get(t, ())
                    for i, f in enumerate(
                        (2 if write_header == "duped" else 1) * all_fields):
                        sheet.write(
                            0, i,
                            f.lower() if write_header == "lower"
                            or i >= len(all_fields) else f)
                for rowInd, row in enumerate(data):
                    for fieldInd, cellValue in enumerate(
                        (2 if write_header == "duped" else 1) * row):
                        sheet.write(rowInd + (1 if write_header else 0),
                                    fieldInd, cellValue)
            if os.path.exists(filePath):
                os.remove(filePath)
            book.save(filePath)
            if write_header in [
                    "lower", "same"
            ]:  # will use pandas to generate the xlsx file version
                file_path_x = filePath + "x"
                if os.path.exists(file_path_x):
                    os.remove(file_path_x)
                writer = utils.pd.ExcelWriter(file_path_x)
                for t, (pks, dfs) in tdf.schema().items():
                    fields = pks + dfs
                    if write_header == "lower":
                        fields = [_.lower() for _ in fields]
                    d = {f: [] for f in fields}
                    for row in data:
                        for f, c in zip(fields, row):
                            d[f].append(c)
                    utils.pd.DataFrame(d).to_excel(writer, t, index=False)
                writer.save()

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)],
                  write_header="duped")
        self.assertTrue(
            self.firesException(
                lambda: tdf.xls.create_tic_dat(filePath, freeze_it=True)))

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)])
        ticDatMan = tdf.xls.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
        self.assertTrue(ticDatMan.b[1, 20, 30]["bData"] == 40)
        for f in [filePath, filePath + "x"]:
            rowCount = tdf.xls.find_duplicates(f)
            self.assertTrue(
                set(rowCount) == {'a'} and set(rowCount["a"]) == {1}
                and rowCount["a"][1] == 2)

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)],
                  write_header="lower")
        ticDatMan = tdf.xls.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
        self.assertTrue(ticDatMan.b[1, 20, 30]["bData"] == 40)
        for f in [filePath, filePath + "x"]:
            rowCount = tdf.xls.find_duplicates(f)
            self.assertTrue(
                set(rowCount) == {'a'} and set(rowCount["a"]) == {1}
                and rowCount["a"][1] == 2)

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)],
                  write_header=False)
        self.assertTrue(
            self.firesException(
                lambda: tdf.xls.create_tic_dat(filePath, freeze_it=True)))
        ticDatMan = tdf.xls.create_tic_dat(filePath,
                                           freeze_it=True,
                                           headers_present=False)
        self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
        self.assertTrue(ticDatMan.b[1, 20, 30]["bData"] == 40)
        rowCount = tdf.xls.find_duplicates(filePath, headers_present=False)
        self.assertTrue(
            set(rowCount) == {'a'} and set(rowCount["a"]) == {1}
            and rowCount["a"][1] == 2)

        ticDat.a["theboger"] = (1, None, 12)
        tdf.xls.write_file(ticDat, filePath, allow_overwrite=True)
        ticDatNone = tdf.xls.create_tic_dat(filePath, freeze_it=True)
        # THIS IS A FLAW - but a minor one. None's are hard to represent. It is turning into the empty string here.
        # not sure how to handle this, but documenting for now.
        self.assertFalse(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == "")
        # the workaround for this flaw is to set the data type to be nullabe but not allow the empty string
        tdfwa = TicDatFactory(**sillyMeSchema())
        tdfwa.set_data_type("a", "aData2", nullable=True)
        ticDatNone = tdfwa.xls.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)

        # checking the same thing with .xlsx - using openpyxl, None is indeed recovered even without tdfwa munging!
        tdf.xls.write_file(ticDat, filePath + "x", allow_overwrite=True)
        ticDatNone = tdf.xls.create_tic_dat(filePath + "x", freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)
        ticDatNone = tdfwa.xls.create_tic_dat(filePath + "x", freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40),
                   (1, 20, 30, 12)])
        for f in [filePath, filePath + "x"]:
            rowCount = tdf.xls.find_duplicates(f)
            self.assertTrue(
                set(rowCount) == {'a', 'b'} and set(rowCount["a"]) == {1}
                and rowCount["a"][1] == 3)
            self.assertTrue(
                set(rowCount["b"]) == {(1, 20, 30)}
                and rowCount["b"][1, 20, 30] == 2)
示例#4
0
    def testSilly(self):
        if not _can_accdb_unit_test:
            return
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        filePath = os.path.join(_scratchDir, "silly.accdb")
        self.assertTrue(firesException(lambda : tdf.mdb.write_file(ticDat, makeCleanPath(filePath))))
        def sillyMeCleanData() :
            return {
                "a" : {"1" : (1, 2, "3"), "b" : (12, 12.2, "twelve"), "c" : (11, 12, "thirt")},
                "b" : {(1, 2, "3") : 1, (3, 4, "b") : 12},
                "c" : ((1, "2", 3, 4), (0.2, "b", 0.3, 0.4), (1.2, "b", 12, 24) )
            }
        ticDat = tdf.TicDat(**sillyMeCleanData())
        self.assertTrue(firesException(lambda : tdf.mdb.write_file(ticDat, makeCleanPath(filePath))))
        def makeCleanSchema() :
            tdf.mdb.write_schema(makeCleanPath(filePath), a={"aData3" : "text"},
                        b = {"bField1" : "int", "bField2" : "int"}, c={"cData2" : "text"})
            return filePath
        tdf.mdb.write_file(ticDat, makeCleanSchema())
        self.assertFalse(tdf.mdb.find_duplicates(filePath))
        accdbTicDat = tdf.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, accdbTicDat))

        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
        for t in ("a", "b") :
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] =  (),  []
        schema6 = sillyMeSchema()
        schema6["d"] =  [["dField"],()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x) for x in (schema2, schema3, schema4, schema5, schema6))
        tdf5.set_generator_tables(("a","c"))

        ticDat2 = tdf2.mdb.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.mdb.create_tic_dat(filePath)
        for t in ["a","b"]:
            for k,v in getattr(ticDat4, t).items() :
                for _k, _v in v.items() :
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]) :
                    self.assertTrue(t == "b")
                else :
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

        self.assertTrue("table d" in self.firesException(lambda  : tdf6.mdb.create_tic_dat(filePath)))

        ticDat.a["theboger"] = (1, None, "twelve")
        tdf.mdb.write_file(ticDat, makeCleanSchema())
        ticDatNone = tdf.mdb.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)
示例#5
0
    def testSilly(self):
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
        for t in ("a", "b") :
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] =  (),  []
        schema6 = sillyMeSchema()
        schema6["d"] =  [["dField"],()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x) for x in (schema2, schema3, schema4, schema5, schema6))
        tdf5.set_generator_tables(("a","c"))
        filePath = os.path.join(_scratchDir, "silly.xls")
        tdf.xls.write_file(ticDat, filePath)

        ticDat2 = tdf2.xls.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.xls.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.xls.create_tic_dat(filePath)
        for t in ["a","b"]:
            for k,v in getattr(ticDat4, t).items() :
                for _k, _v in v.items() :
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]) :
                    self.assertTrue(t == "b")
                else :
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.xls.create_tic_dat(filePath)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

        ticDat6 = tdf6.xls.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat6))
        self.assertTrue(firesException(lambda : tdf6._same_data(ticDat, ticDat6)))
        self.assertTrue(hasattr(ticDat6, "d") and utils.dictish(ticDat6.d))

        def writeData(data, write_header = True):
            import xlwt
            book = xlwt.Workbook()
            for t in tdf.all_tables :
                sheet = book.add_sheet(t)
                if write_header :
                    for i,f in enumerate(tdf.primary_key_fields.get(t, ()) + tdf.data_fields.get(t, ())) :
                        sheet.write(0, i, f)
                for rowInd, row in enumerate(data) :
                    for fieldInd, cellValue in enumerate(row):
                        sheet.write(rowInd+ (1 if write_header else 0), fieldInd, cellValue)
            if os.path.exists(filePath):
                os.remove(filePath)
            book.save(filePath)

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)])
        ticDatMan = tdf.xls.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
        self.assertTrue(ticDatMan.b[1, 20, 30]["bData"] == 40)
        rowCount = tdf.xls.get_duplicates(filePath)
        self.assertTrue(set(rowCount) == {'a'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==2)

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)], write_header=False)
        self.assertTrue(self.firesException(lambda  : tdf.xls.create_tic_dat(filePath, freeze_it=True)))
        ticDatMan = tdf.xls.create_tic_dat(filePath, freeze_it=True, headers_present=False)
        self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
        self.assertTrue(ticDatMan.b[1, 20, 30]["bData"] == 40)
        rowCount = tdf.xls.get_duplicates(filePath, headers_present=False)
        self.assertTrue(set(rowCount) == {'a'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==2)

        ticDat.a["theboger"] = (1, None, 12)
        tdf.xls.write_file(ticDat, filePath, allow_overwrite=True)
        ticDatNone = tdf.xls.create_tic_dat(filePath, freeze_it=True)
        # THIS IS A FLAW - but a minor one. None's are hard to represent. It is turning into the empty string here.
        # not sure how to handle this, but documenting for now.
        self.assertFalse(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == "")

        writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40), (1,20,30,12)])
        rowCount = tdf.xls.get_duplicates(filePath)
        self.assertTrue(set(rowCount) == {'a', 'b'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==3)
        self.assertTrue(set(rowCount["b"]) == {(1,20,30)} and rowCount["b"][1,20,30]==2)
示例#6
0
        def doTest(headersPresent) :
            tdf = TicDatFactory(**sillyMeSchema())
            ticDat = tdf.TicDat(**sillyMeData())
            schema2 = sillyMeSchema()
            schema2["b"][0] = ("bField2", "bField1", "bField3")
            schema3 = sillyMeSchema()
            schema3["a"][1] = ("aData2", "aData3", "aData1")
            schema4 = sillyMeSchema()
            schema4["a"][1] = ("aData1", "aData3")
            schema5 = sillyMeSchema()
            _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
            for t in ("a", "b") :
                schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
            schema5["a"][0], schema5["b"][0] = (), []
            schema5b = sillyMeSchema()
            for t in ("a", "b") :
                schema5b[t][1] = _tuple(schema5b[t][0]) + _tuple(schema5b[t][1])
            schema5b["a"][0], schema5b["b"][0] = (), []
            schema6 = sillyMeSchema()
            schema6["d"] = [("dField",),[]]

            tdf2, tdf3, tdf4, tdf5, tdf5b, tdf6 = (TicDatFactory(**x) for x in
                            (schema2, schema3, schema4, schema5, schema5b, schema6))
            tdf5.set_generator_tables(["a", "c"])
            tdf5b.set_generator_tables(("a", "c"))


            dirPath = makeCleanDir(os.path.join(_scratchDir, "silly"))
            tdf.csv.write_directory(ticDat, dirPath, write_header=headersPresent)

            ticDat2 = tdf2.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertFalse if headersPresent else self.assertTrue)(tdf._same_data(ticDat, ticDat2))

            ticDat3 = tdf3.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertTrue if headersPresent else self.assertFalse)(tdf._same_data(ticDat, ticDat3))

            if headersPresent :
                ticDat4 = tdf4.csv.create_tic_dat(dirPath, headers_present=headersPresent)
                for t in ("a", "b") :
                    for k,v in getattr(ticDat4, t).items() :
                        for _k, _v in v.items() :
                            self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                        if set(v) == set(getattr(ticDat, t)[k]) :
                            self.assertTrue(t == "b")
                        else :
                            self.assertTrue(t == "a")
            else :
                self.assertTrue(self.firesException(lambda :
                                    tdf4.csv.create_tic_dat(dirPath, headers_present=headersPresent)))

            ticDat5 = tdf5.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertTrue if headersPresent else self.assertFalse)(
                                                    tdf5._same_data(tdf._keyless(ticDat), ticDat5))
            self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

            ticDat5b = tdf5b.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            self.assertTrue(tdf5b._same_data(tdf._keyless(ticDat), ticDat5b))
            self.assertTrue(callable(ticDat5b.a) and callable(ticDat5b.c) and not callable(ticDat5b.b))


            ticDat6 = tdf6.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            self.assertTrue(tdf._same_data(ticDat, ticDat6))
            self.assertTrue(firesException(lambda : tdf6._same_data(ticDat, ticDat6)))
            self.assertTrue(hasattr(ticDat6, "d") and utils.dictish(ticDat6.d))
            allDataTdf = TicDatFactory(**{t:[[], tdf.primary_key_fields.get(t, ()) + tdf.data_fields.get(t, ())]
                             for t in tdf.all_tables})

            def writeData(data):
                td = allDataTdf.TicDat(a = data, b=data, c=data)
                allDataTdf.csv.write_directory(td, dirPath, allow_overwrite=True, write_header=headersPresent)

            writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)])
            ticDatMan = tdf.csv.create_tic_dat(dirPath, headers_present=headersPresent, freeze_it=True)
            self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
            self.assertTrue(ticDatMan.b[(1, 20, 30)]["bData"] == 40)
            rowCount = tdf.csv.find_duplicates(dirPath, headers_present= headersPresent)
            self.assertTrue(set(rowCount) == {'a'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==2)


            writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40), (1,20,30,12)])
            rowCount = tdf.csv.find_duplicates(dirPath, headers_present=headersPresent)
            self.assertTrue(set(rowCount) == {'a', 'b'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==3)
            self.assertTrue(set(rowCount["b"]) == {(1,20,30)} and rowCount["b"][1,20,30]==2)
示例#7
0
        def doTest(headersPresent) :
            tdf = TicDatFactory(**sillyMeSchema())
            ticDat = tdf.TicDat(**sillyMeData())
            schema2 = sillyMeSchema()
            schema2["b"][0] = ("bField2", "bField1", "bField3")
            schema3 = sillyMeSchema()
            schema3["a"][1] = ("aData2", "aData3", "aData1")
            schema4 = sillyMeSchema()
            schema4["a"][1] = ("aData1", "aData3")
            schema5 = sillyMeSchema()
            _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
            for t in ("a", "b") :
                schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
            schema5["a"][0], schema5["b"][0] = (), []
            schema5b = sillyMeSchema()
            for t in ("a", "b") :
                schema5b[t][1] = _tuple(schema5b[t][0]) + _tuple(schema5b[t][1])
            schema5b["a"][0], schema5b["b"][0] = (), []
            schema6 = sillyMeSchema()
            schema6["d"] = [("dField",),[]]

            tdf2, tdf3, tdf4, tdf5, tdf5b, tdf6 = (TicDatFactory(**x) for x in
                            (schema2, schema3, schema4, schema5, schema5b, schema6))
            tdf5.set_generator_tables(["a", "c"])
            tdf5b.set_generator_tables(("a", "c"))


            dirPath = makeCleanDir(os.path.join(_scratchDir, "silly"))
            tdf.csv.write_directory(ticDat, dirPath, write_header=headersPresent)

            ticDat2 = tdf2.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertFalse if headersPresent else self.assertTrue)(tdf._same_data(ticDat, ticDat2))

            ticDat3 = tdf3.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertTrue if headersPresent else self.assertFalse)(tdf._same_data(ticDat, ticDat3))

            if headersPresent :
                ticDat4 = tdf4.csv.create_tic_dat(dirPath, headers_present=headersPresent)
                for t in ("a", "b") :
                    for k,v in getattr(ticDat4, t).items() :
                        for _k, _v in v.items() :
                            self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                        if set(v) == set(getattr(ticDat, t)[k]) :
                            self.assertTrue(t == "b")
                        else :
                            self.assertTrue(t == "a")
            else :
                self.assertTrue(self.firesException(lambda :
                                    tdf4.csv.create_tic_dat(dirPath, headers_present=headersPresent)))

            ticDat5 = tdf5.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            (self.assertTrue if headersPresent else self.assertFalse)(
                                                    tdf5._same_data(tdf._keyless(ticDat), ticDat5))
            self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

            ticDat5b = tdf5b.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            self.assertTrue(tdf5b._same_data(tdf._keyless(ticDat), ticDat5b))
            self.assertTrue(callable(ticDat5b.a) and callable(ticDat5b.c) and not callable(ticDat5b.b))


            ticDat6 = tdf6.csv.create_tic_dat(dirPath, headers_present=headersPresent)
            self.assertTrue(tdf._same_data(ticDat, ticDat6))
            self.assertTrue(firesException(lambda : tdf6._same_data(ticDat, ticDat6)))
            self.assertTrue(hasattr(ticDat6, "d") and utils.dictish(ticDat6.d))
            allDataTdf = TicDatFactory(**{t:[[], tdf.primary_key_fields.get(t, ()) + tdf.data_fields.get(t, ())]
                             for t in tdf.all_tables})

            def writeData(data):
                td = allDataTdf.TicDat(a = data, b=data, c=data)
                allDataTdf.csv.write_directory(td, dirPath, allow_overwrite=True, write_header=headersPresent)

            writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40)])
            ticDatMan = tdf.csv.create_tic_dat(dirPath, headers_present=headersPresent, freeze_it=True)
            self.assertTrue(len(ticDatMan.a) == 2 and len(ticDatMan.b) == 3)
            self.assertTrue(ticDatMan.b[(1, 20, 30)]["bData"] == 40)
            rowCount = tdf.csv.get_duplicates(dirPath, headers_present= headersPresent)
            self.assertTrue(set(rowCount) == {'a'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==2)


            writeData([(1, 2, 3, 4), (1, 20, 30, 40), (10, 20, 30, 40), (1,20,30,12)])
            rowCount = tdf.csv.get_duplicates(dirPath, headers_present=headersPresent)
            self.assertTrue(set(rowCount) == {'a', 'b'} and set(rowCount["a"]) == {1} and rowCount["a"][1]==3)
            self.assertTrue(set(rowCount["b"]) == {(1,20,30)} and rowCount["b"][1,20,30]==2)
示例#8
0
    def testSilly(self):
        tdf = TicDatFactory(**sillyMeSchema())
        ticDat = tdf.TicDat(**sillyMeData())
        filePath = os.path.join(_scratchDir, "silly.mdb")
        self.assertTrue(firesException(lambda : tdf.mdb.write_file(ticDat, makeCleanPath(filePath))))
        def sillyMeCleanData() :
            return {
                "a" : {"1" : (1, 2, "3"), "b" : (12, 12.2, "twelve"), "c" : (11, 12, "thirt")},
                "b" : {(1, 2, "3") : 1, (3, 4, "b") : 12},
                "c" : ((1, "2", 3, 4), (0.2, "b", 0.3, 0.4), (1.2, "b", 12, 24) )
            }
        ticDat = tdf.TicDat(**sillyMeCleanData())
        self.assertTrue(firesException(lambda : tdf.mdb.write_file(ticDat, makeCleanPath(filePath))))
        def makeCleanSchema() :
            tdf.mdb.write_schema(makeCleanPath(filePath), a={"aData3" : "text"},
                        b = {"bField1" : "int", "bField2" : "int"}, c={"cData2" : "text"})
            return filePath
        tdf.mdb.write_file(ticDat, makeCleanSchema())
        mdbTicDat = tdf.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, mdbTicDat))

        schema2 = sillyMeSchema()
        schema2["b"][0] = ("bField2", "bField1", "bField3")
        schema3 = sillyMeSchema()
        schema3["a"][1] = ("aData2", "aData3", "aData1")
        schema4 = sillyMeSchema()
        schema4["a"][1] = ("aData1", "aData3")
        schema5 = sillyMeSchema()
        _tuple = lambda x : tuple(x) if utils.containerish(x) else (x,)
        for t in ("a", "b") :
            schema5[t][1] = _tuple(schema5[t][1]) + _tuple(schema5[t][0])
        schema5["a"][0], schema5["b"][0] =  (),  []
        schema6 = sillyMeSchema()
        schema6["d"] =  [["dField"],()]

        tdf2, tdf3, tdf4, tdf5, tdf6 = (TicDatFactory(**x) for x in (schema2, schema3, schema4, schema5, schema6))
        tdf5.set_generator_tables(("a","c"))

        ticDat2 = tdf2.mdb.create_tic_dat(filePath)
        self.assertFalse(tdf._same_data(ticDat, ticDat2))

        ticDat3 = tdf3.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf._same_data(ticDat, ticDat3))

        ticDat4 = tdf4.mdb.create_tic_dat(filePath)
        for t in ["a","b"]:
            for k,v in getattr(ticDat4, t).items() :
                for _k, _v in v.items() :
                    self.assertTrue(getattr(ticDat, t)[k][_k] == _v)
                if set(v) == set(getattr(ticDat, t)[k]) :
                    self.assertTrue(t == "b")
                else :
                    self.assertTrue(t == "a")

        ticDat5 = tdf5.mdb.create_tic_dat(filePath)
        self.assertTrue(tdf5._same_data(tdf._keyless(ticDat), ticDat5))
        self.assertTrue(callable(ticDat5.a) and callable(ticDat5.c) and not callable(ticDat5.b))

        self.assertTrue("table d" in self.firesException(lambda  : tdf6.mdb.create_tic_dat(filePath)))

        ticDat.a["theboger"] = (1, None, "twelve")
        tdf.mdb.write_file(ticDat, makeCleanSchema())
        ticDatNone = tdf.mdb.create_tic_dat(filePath, freeze_it=True)
        self.assertTrue(tdf._same_data(ticDat, ticDatNone))
        self.assertTrue(ticDatNone.a["theboger"]["aData2"] == None)