Convert Asana tickets to GitHub issues (#96)

records_mover/db/mysql/load_options.py

@@ -248,7 +248,7 @@ def mysql_load_options(unhandled_hints: Set[str],
     # to a compatible locale.  This is true for a number of the
     # database drivers; the backlog item to address is here:
     #
-    # https://app.asana.com/0/1128138765527694/1173779659264666
+    # https://github.com/bluelabsio/records-mover/issues/75
     #
     # To address, we'll want to look into "set trade_date" per
     # https://stackoverflow.com/questions/44171283/load-data-local-infile-with-sqlalchemy-and-pymysql

records_mover/records/delimited/conversions.py

@@ -38,7 +38,7 @@
 # This is a Union because the date formats currently don't really
 # account for MM/DD time.
 #
-# https://app.asana.com/0/1128138765527694/1173779659264666
+# https://github.com/bluelabsio/records-mover/issues/75
 #
 python_date_format_from_hints: Dict[Union[HintDateFormat, Literal['DD/MM/YY']], str] = {
     'YYYY-MM-DD': '%Y-%m-%d',

records_mover/records/delimited/sniff.py

@@ -190,7 +190,7 @@ def sniff_compression_hint(fileobj: IO[bytes]) -> HintCompression:
 def sniff_hints_from_fileobjs(fileobjs: List[IO[bytes]],
                               initial_hints: PartialRecordsHints) -> PartialRecordsHints:
     if len(fileobjs) != 1:
-        # https://app.asana.com/0/53283930106309/1131698268455054
+        # https://github.com/bluelabsio/records-mover/issues/84
         raise NotImplementedError('Cannot currently sniff hints from mulitple '
                                   'files--please provide hints')
     fileobj = fileobjs[0]

records_mover/records/pandas/to_csv_options.py

@@ -84,7 +84,7 @@ def pandas_to_csv_options(records_format: DelimitedRecordsFormat,
             # '2000-01-02 12:34:56.789012'
             # >>>
             #
-            # https://app.asana.com/0/1128138765527694/1159958019131681
+            # https://github.com/bluelabsio/records-mover/issues/95
             pandas_options['date_format'] = '%Y-%m-%d %H:%M:%S.%f'
         else:
             pandas_options['date_format'] = '%Y-%m-%d %H:%M:%S.%f%z'

records_mover/records/schema/field/numpy.py

@@ -19,7 +19,7 @@ def details_from_numpy_dtype(dtype: numpy.dtype,
             if has_tz:
                 # See: 'Represent pandas datetime64 with timezone in records schema'
                 #
-                # https://app.asana.com/0/53283930106309/1132706099772565
+                # https://github.com/bluelabsio/records-mover/issues/89
                 field_type = 'datetimetz'
             else:
                 field_type = 'datetime'

records_mover/records/schema/field/sqlalchemy.py

@@ -36,7 +36,7 @@ def field_from_sqlalchemy_column(column: Column,
     # constraints out of database tables, so set this to null,
     # which means "we don't know":
     #
-    # https://app.asana.com/0/1128138765527694/1131416227825120
+    # https://github.com/bluelabsio/records-mover/issues/90
     unique = None
 
     if isinstance(type_, sqlalchemy.sql.sqltypes.Integer):
@@ -114,7 +114,7 @@ def field_from_sqlalchemy_column(column: Column,
     # We don't currently gather statistics from databases - which
     # can bite us when exporting from BigQuery, for instance:
     #
-    # https://app.asana.com/0/53283930106309/1131698268455053
+    # https://github.com/bluelabsio/records-mover/issues/91
     statistics = None
 
     return RecordsSchemaField(name=name,

records_mover/records/schema/schema/__init__.py

@@ -109,7 +109,7 @@ def from_fileobjs(fileobjs: List[IO[bytes]],
         from records_mover.pandas import purge_unnamed_unused_columns
 
         if len(fileobjs) != 1:
-            # https://app.asana.com/0/53283930106309/1131698268455054
+            # https://github.com/bluelabsio/records-mover/issues/84
             raise NotImplementedError('Cannot currently sniff schema from mulitple '
                                       'files--please provide explicit schema JSON')
         fileobj = fileobjs[0]
@@ -171,7 +171,7 @@ def assign_dataframe_names(self,
             index_name = field_names[0]
             # RecordsMover supports only single indexes for the moment.
             #
-            # https://app.asana.com/0/1128138765527694/1161071033650873
+            # https://github.com/bluelabsio/records-mover/issues/92
             index_mapping = {0: index_name}
 
             # remove first name, which applies to index

records_mover/records/sources/dataframes.py

@@ -86,7 +86,7 @@ def serialize_dfs(self,
                     # initial_records_schema was based on only the
                     # first chunk.
                     #
-                    # https://app.asana.com/0/1128138765527694/1161074649542801
+                    # https://github.com/bluelabsio/records-mover/issues/93
                     logger.warning("Only checking first chunk for type inference")
                 i = i + 1
 
@@ -156,7 +156,7 @@ def save_df(df: 'DataFrame', output_filename: str) -> None:
             def save_df(df: 'DataFrame', output_filename: str) -> None:
                 logger.info(f"Writing Parquet file to {output_filename}")
                 # Note that this doesn't specify partitioning as of yet -
-                # https://app.asana.com/0/1128138765527694/1126615025514407
+                # https://github.com/bluelabsio/records-mover/issues/94
                 df.to_parquet(fname=output_filename,
                               engine='pyarrow',
                               index=self.include_index,

records_mover/records/targets/spectrum.py

@@ -106,11 +106,11 @@ def post_load_hook(self, num_rows_loaded: Optional[int]) -> None:
         columns = [f.to_sqlalchemy_column(self.driver) for f in records_schema.fields]
         for column in columns:
             if isinstance(column.type, sqlalchemy.sql.sqltypes.Numeric) and column.type.asdecimal:
-                # https://app.asana.com/0/1128138765527694/1139365728890234
+                # https://github.com/bluelabsio/records-mover/issues/85
                 raise NotImplementedError("Teach me how to write a NUMERIC to Redshift Spectrum "
                                           f"(column name: {column})")
             if isinstance(column.type, sqlalchemy.sql.sqltypes.DateTime) and column.type.timezone:
-                # https://app.asana.com/0/53283930106309/1136051640283464
+                # https://github.com/bluelabsio/records-mover/issues/86
                 raise NotImplementedError("Teach me how to write a datetimetz to Redshift Spectrum "
                                           f"({column})")
 
@@ -129,7 +129,7 @@ def post_load_hook(self, num_rows_loaded: Optional[int]) -> None:
             #
             # https://docs.aws.amazon.com/redshift/latest/dg/r_ALTER_TABLE_external-table.html
             #
-            # https://app.asana.com/0/53283930106309/1140172717234001
+            # https://github.com/bluelabsio/records-mover/issues/87
             pass
         storage_clause = "STORED AS PARQUET\n"
         location_clause = f"LOCATION '{self.output_loc.url}_manifest'\n"

records_mover/records/targets/table/target.py

@@ -57,7 +57,7 @@ def __init__(self,
         # advertise what format we prefer to be given for mover paths
         # that don't yet support full records negotiation.
         #
-        # https://app.asana.com/0/1128138765527694/1130105834872106
+        # https://github.com/bluelabsio/records-mover/issues/88
         self.records_format = next(iter(self.known_supported_records_formats()), None)
 
     def move_from_records_directory(self,

tests/integration/records/directory_validator.py

@@ -76,7 +76,7 @@ def validate_records_schema(self) -> None:
                     # inference to determine if the data in question will
                     # fit into it.
                     #
-                    # https://app.asana.com/0/1128138765527694/1166526213569051
+                    # https://github.com/bluelabsio/records-mover/issues/82
                     # https://stackoverflow.com/questions/31761047/what-difference-between-the-date-time-datetime-and-timestamp-types/56138746
                     'mysql': [
                         'integer', 'string', 'string', 'string',

tests/integration/records/expected_column_types.py

@@ -75,7 +75,7 @@
     # databases like Redshift.  We could collect and use
     # statistics to get a better read on this:
     #
-    # https://app.asana.com/0/1128138765527694/1152727792219521
+    # https://github.com/bluelabsio/records-mover/issues/79
     #
     #
     #
@@ -87,8 +87,8 @@
     # types from numeric statistics it pulls from the source
     # tables.
     #
-    # https://app.asana.com/0/1128138765527694/1152727792219523
-    # https://app.asana.com/0/1128138765527694/1152727792219521
+    # https://github.com/bluelabsio/records-mover/issues/78
+    # https://github.com/bluelabsio/records-mover/issues/79
     #
     #
     #

tests/integration/records/single_db/test_records_load.py

@@ -11,8 +11,8 @@
 class RecordsLoadIntegrationTest(BaseRecordsIntegrationTest):
     def load_and_verify(self, format_type, variant, hints={}, broken=False, sourcefn=None):
         if self.engine.name == 'bigquery' and variant == 'csv':
-            # https://app.asana.com/0/53283930106309/1130065227225218
-            # https://app.asana.com/0/53283930106309/1130065227225219
+            # https://github.com/bluelabsio/records-mover/issues/80
+            # https://github.com/bluelabsio/records-mover/issues/81
             logger.warning("This test won't pass until we can use hints to "
                            "infer date/time/etc columns, or we use records schema "
                            "from target to set types on the source, so skipping.")
@@ -118,7 +118,7 @@ def sourcefn(filename, records_format, records_schema):
         # CSV type inference is not smart enough to identify the
         # date/time columns as anything but strings yet.
         #
-        # https://app.asana.com/0/1128138765527694/1130065227225218
+        # https://github.com/bluelabsio/records-mover/issues/80
         #
         # Once that's fixed, we can stop passing in a records schema
         # here when we have a header row for the names and let the

tests/integration/resources/README.md

@@ -46,7 +46,7 @@ timezones in timestamps are expressed.
   times, just datetimes, so dates and times come out in
   default Pandas __str__() format.
 
-  See details on [Pandas limitations](https://app.asana.com/0/53283930106309/1133167860965681)
+  See details on [Pandas limitations](https://github.com/bluelabsio/records-mover/issues/83)
 
 ### utc
 

tests/unit/records/pandas/test_prep_for_csv.py

@@ -39,11 +39,11 @@ def test_prep_df_for_csv_output_no_include_index(self):
             # instance, specifying how it's turned into a CSV is not
             # currently part of the records spec:
             #
-            #   https://app.asana.com/0/1128138765527694/1169941483931186
+            #   https://github.com/bluelabsio/records-mover/issues/76
             #
             # In addition, Vertica suffers from a driver limitation:
             #
-            #   https://app.asana.com/0/search/1169941483931185/1126315736470782
+            #   https://github.com/bluelabsio/records-mover/issues/77
             #
             # 'timetz': [
             #     us_eastern.localize(pd.Timestamp(year=1970, month=1, day=1,
@@ -95,11 +95,11 @@ def test_prep_df_for_csv_output_include_index(self):
             # instance, specifying how it's turned into a CSV is not
             # currently part of the records spec:
             #
-            #   https://app.asana.com/0/1128138765527694/1169941483931186
+            #   https://github.com/bluelabsio/records-mover/issues/76
             #
             # In addition, Vertica suffers from a driver limitation:
             #
-            #   https://app.asana.com/0/search/1169941483931185/1126315736470782
+            #   https://github.com/bluelabsio/records-mover/issues/77
             #
             # 'timetz': [
             #     us_eastern.localize(pd.Timestamp(year=1970, month=1, day=1,

tests/unit/records/test_pandas_read_csv_options.py

@@ -57,7 +57,7 @@ def test_pandas_read_csv_options_bluelabs(self):
         self.assertEqual(expected, actual)
         self.assertFalse(unhandled_hints)
 
-    # MM-DD not yet fully supported - see https://app.asana.com/0/1128138765527694/1173779659264666
+    # MM-DD not yet fully supported - see https://github.com/bluelabsio/records-mover/issues/75
     #
     # def test_pandas_read_csv_options_bleulabs(self):
     #     expected = {

tests/unit/records/test_pandas_to_csv_options_dateformats.py

@@ -63,7 +63,7 @@ class TestPandasToCsvOptionsDateformats(unittest.TestCase):
     #     self.assertFalse(unhandled_hints)
 
     # DD-MM format not yet fully supported - see
-    # https://app.asana.com/0/1128138765527694/1173779659264666
+    # https://github.com/bluelabsio/records-mover/issues/75
     #
     # def test_pandas_dateformat_DD_MM_YYYY_no_tz(self):
     #     expected = {