WIP use custom warnings

OpenDataServices · Jul 31, 2024 · f3e4367 · f3e4367
1 parent 1f0b320
commit f3e4367
Show file tree

Hide file tree

Showing 6 changed files with 69 additions and 23 deletions.
diff --git a/flattentool/exceptions.py b/flattentool/exceptions.py
@@ -1,4 +1,13 @@
-class DataErrorWarning(UserWarning):
+class FlattenToolWarning(UserWarning):
+    """
+    A warning generated directly by flatten-tool.
+
+    """
+
+    pass
+
+
+class DataErrorWarning(FlattenToolWarning):
     """
     A warnings that indicates an error in the data, rather than the schema.
 

diff --git a/flattentool/input.py b/flattentool/input.py
@@ -142,7 +142,10 @@ def convert_type(type_string, value, timezone=pytz.timezone("UTC"), convert_flag
             feature = geojson.Feature(geometry=geom, properties={})
             return feature.geometry
         else:
-            warn("Install flattentool's optional geo dependencies to use geo features.")
+            warn(
+                "Install flattentool's optional geo dependencies to use geo features.",
+                FlattenToolWarning,
+            )
             return str(value)
     elif type_string == "":
         if type(value) == datetime.datetime:
@@ -156,7 +159,10 @@ def convert_type(type_string, value, timezone=pytz.timezone("UTC"), convert_flag
 
 def warnings_for_ignored_columns(v, extra_message):
     if isinstance(v, Cell):
-        warn("Column {} has been ignored, {}".format(v.cell_location[3], extra_message))
+        warn(
+            "Column {} has been ignored, {}".format(v.cell_location[3], extra_message),
+            DataErrorWarning,
+        )
     elif isinstance(v, dict):
         for x in v.values():
             warnings_for_ignored_columns(x, extra_message)

diff --git a/flattentool/json_input.py b/flattentool/json_input.py
@@ -28,7 +28,7 @@
 import zc.zlibstorage
 import ZODB.FileStorage
 
-from flattentool.exceptions import DataErrorWarning
+from flattentool.exceptions import DataErrorWarning, FlattenToolWarning
 from flattentool.i18n import _
 from flattentool.input import path_search
 from flattentool.schema import make_sub_sheet_name
@@ -195,7 +195,10 @@ def __init__(
                 if isinstance(rollup, (list,)) and (
                     len(rollup) > 1 or (len(rollup) == 1 and rollup[0] is not True)
                 ):
-                    warn(_("Using rollUp values from schema, ignoring direct input."))
+                    warn(
+                        _("Using rollUp values from schema, ignoring direct input."),
+                        FlattenToolWarning,
+                    )
             elif isinstance(rollup, (list,)):
                 if len(rollup) == 1 and os.path.isfile(rollup[0]):
                     # Parse file, one json path per line.
@@ -209,15 +212,17 @@ def __init__(
                 elif len(rollup) == 1 and rollup[0] is True:
                     warn(
                         _(
-                            "No fields to rollup found (pass json path directly, as a list in a file, or via a schema)"
+                            "No fields to rollup found (pass json path directly, as a list in a file, or via a schema)",
+                            FlattenToolWarning,
                         )
                     )
                 else:
                     self.rollup = set(rollup)
             else:
                 warn(
                     _(
-                        "Invalid value passed for rollup (pass json path directly, as a list in a file, or via a schema)"
+                        "Invalid value passed for rollup (pass json path directly, as a list in a file, or via a schema)",
+                        FlattenToolWarning,
                     )
                 )
 
@@ -276,7 +281,8 @@ def __init__(
                 warn(
                     _(
                         "You wanted to preserve the following fields which are not present in the supplied schema: {}"
-                    ).format(list(input_not_in_schema))
+                    ).format(list(input_not_in_schema)),
+                    FlattenToolWarning,
                 )
             except AttributeError:
                 # no schema
@@ -344,7 +350,8 @@ def parse(self):
                 warn(
                     _(
                         "You wanted to preserve the following fields which are not present in the input data: {}"
-                    ).format(nonexistent_input_paths)
+                    ).format(nonexistent_input_paths),
+                    FlattenToolWarning,
                 )
 
     def parse_json_dict(
@@ -383,13 +390,17 @@ def parse_json_dict(
                 try:
                     geom = shapely.geometry.shape(json_dict)
                 except (shapely.errors.GeometryTypeError, TypeError, ValueError) as e:
-                    warn(_("Invalid GeoJSON: {parser_msg}").format(parser_msg=repr(e)))
+                    warn(
+                        _("Invalid GeoJSON: {parser_msg}").format(parser_msg=repr(e)),
+                        DataErrorWarning,
+                    )
                     return
                 flattened_dict[_sheet_key] = geom.wkt
                 skip_type_and_coordinates = True
             else:
                 warn(
-                    "Install flattentool's optional geo dependencies to use geo features."
+                    "Install flattentool's optional geo dependencies to use geo features.",
+                    FlattenToolWarning,
                 )
 
         parent_id_fields = copy.copy(parent_id_fields) or OrderedDict()
@@ -482,7 +493,8 @@ def parse_json_dict(
                         if self.use_titles and not self.schema_parser:
                             warn(
                                 _(
-                                    "Warning: No schema was provided so column headings are JSON keys, not titles."
+                                    "Warning: No schema was provided so column headings are JSON keys, not titles.",
+                                    FlattenToolWarning,
                                 )
                             )
 
@@ -583,7 +595,8 @@ def parse_json_dict(
                                     warn(
                                         _(
                                             'More than one value supplied for "{}". Could not provide rollup, so adding a warning to the relevant cell(s) in the spreadsheet.'
-                                        ).format(parent_name + key)
+                                        ).format(parent_name + key),
+                                        FlattenToolWarning,
                                     )
                                     flattened_dict[
                                         sheet_key(sheet, parent_name + key + "/0/" + k)
@@ -594,7 +607,8 @@ def parse_json_dict(
                                     warn(
                                         _(
                                             'More than one value supplied for "{}". Could not provide rollup, so adding a warning to the relevant cell(s) in the spreadsheet.'
-                                        ).format(parent_name + key)
+                                        ).format(parent_name + key),
+                                        FlattenToolWarning,
                                     )
                                     flattened_dict[
                                         sheet_key(sheet, parent_name + key + "/0/" + k)

diff --git a/flattentool/schema.py b/flattentool/schema.py
@@ -10,6 +10,7 @@
 
 import jsonref
 
+from flattentool.exceptions import FlattenToolWarning
 from flattentool.i18n import _
 from flattentool.sheet import Sheet
 
@@ -187,7 +188,10 @@ def parse(self):
         for field, title in fields:
             if self.use_titles:
                 if not title:
-                    warn(_("Field {} does not have a title, skipping.").format(field))
+                    warn(
+                        _("Field {} does not have a title, skipping.").format(field),
+                        FlattenToolWarning,
+                    )
                 else:
                     self.main_sheet.append(title)
                     self.main_sheet.titles[field] = title
@@ -367,13 +371,15 @@ def parse_schema_dict(
                                     warn(
                                         _(
                                             "Field {}{}/0/{} is missing a title, skipping."
-                                        ).format(parent_path, property_name, field)
+                                        ).format(parent_path, property_name, field),
+                                        FlattenToolWarning,
                                     )
                                 elif not title:
                                     warn(
                                         _(
                                             "Field {}{} does not have a title, skipping it and all its children."
-                                        ).format(parent_path, property_name)
+                                        ).format(parent_path, property_name),
+                                        FlattenToolWarning,
                                     )
                                 else:
                                     # This code only works for arrays that are at 0 or 1 layer of nesting
@@ -406,7 +412,8 @@ def parse_schema_dict(
                                 warn(
                                     "{} in rollUp but not in schema".format(
                                         ", ".join(missedRollUp)
-                                    )
+                                    ),
+                                    FlattenToolWarning,
                                 )
 
                     else:
@@ -447,12 +454,14 @@ def parse_schema_dict(
                         _(
                             'Unrecognised types {} for property "{}" with context "{}",'
                             "so this property has been ignored."
-                        ).format(repr(property_type_set), property_name, parent_path)
+                        ).format(repr(property_type_set), property_name, parent_path),
+                        FlattenToolWarning,
                     )
 
         else:
             warn(
                 _('Skipping field "{}", because it has no properties.').format(
                     parent_path
-                )
+                ),
+                FlattenToolWarning,
             )
diff --git a/flattentool/sort_xml.py b/flattentool/sort_xml.py
@@ -27,6 +27,8 @@
 from collections import OrderedDict
 from warnings import warn
 
+from flattentool.exceptions import FlattenToolWarning
+
 try:
     import lxml.etree as ET
 
@@ -36,7 +38,10 @@
 except ImportError:
     import xml.etree.ElementTree as ET
 
-    warn("Using stdlib etree may work, but is not supported. Please install lxml.")
+    warn(
+        "Using stdlib etree may work, but is not supported. Please install lxml.",
+        FlattenToolWarning,
+    )
 
 # Namespaces necessary for opening schema files
 namespaces = {"xsd": "http://www.w3.org/2001/XMLSchema"}

diff --git a/flattentool/xml_output.py b/flattentool/xml_output.py
@@ -1,7 +1,7 @@
 from collections import OrderedDict
 from warnings import warn
 
-from flattentool.exceptions import DataErrorWarning
+from flattentool.exceptions import DataErrorWarning, FlattenToolWarning
 from flattentool.sort_xml import XMLSchemaWalker, sort_element
 
 try:
@@ -17,7 +17,10 @@
     import xml.etree.ElementTree as ET
 
     USING_LXML = False
-    warn("Using stdlib etree may work, but is not supported. Please install lxml.")
+    warn(
+        "Using stdlib etree may work, but is not supported. Please install lxml.",
+        FlattenToolWarning,
+    )
 
 
 def sort_attributes(data):