Normalize URIs

brickschema/brickify/src/handlers/Handler/RACHandler/RACHandler.py

@@ -1,8 +1,7 @@
-from pathlib import Path
-from typing import Optional, List
-
 import typer
+from pathlib import Path
 from tabulate import tabulate
+from typing import Optional, List
 
 from brickschema.brickify.src.handlers.Handler.TableHandler import TableHandler
 from brickschema.brickify.util import (
@@ -72,6 +71,12 @@ def ingest_data(self):
                     )
                 )
 
+        replace_dict = {"headers": {}, "values": {}, "ignore_columns": {}}
+        if "replace_dict" in self.config:
+            for key in replace_dict.keys():
+                if key in self.config["replace_dict"]:
+                    replace_dict[key] = self.config["replace_dict"][key]
+
         for index, sheet in enumerate(sheets):
             if index not in sheet_ids:
                 continue
@@ -81,9 +86,7 @@ def ingest_data(self):
             if not header_row:
                 continue
             header = sheet.row_values(header_row)
-            header = cleaned_value(
-                value=header, replace_dict=self.config["replace_dict"]["headers"]
-            )
+            header = cleaned_value(value=header, replace_dict=replace_dict["headers"])
             header_dict = {idx: value for idx, value in enumerate(header)}
             for row_number in range(header_row + 1, sheet.nrows):
                 row = sheet.row_values(row_number)
@@ -108,8 +111,9 @@ def ingest_data(self):
                         row_object = {
                             key: cleaned_value(
                                 value,
-                                replace_dict=self.config["replace_dict"]["values"],
+                                replace_dict=replace_dict["values"],
                             )
                             for key, value in row_object.items()
+                            if key not in replace_dict["ignore_columns"]
                         }
                         self.data.append(row_object)

brickschema/brickify/src/handlers/Handler/TableHandler.py

@@ -1,11 +1,10 @@
 import csv
 import re
 import traceback
-from pathlib import Path
-from typing import Optional, List
-
 from jinja2 import Template
+from pathlib import Path
 from typer import progressbar
+from typing import Optional, List
 
 from brickschema.brickify.src.handlers.Handler.Handler import Handler
 from brickschema.brickify.util import cleaned_value
@@ -43,21 +42,22 @@ def ingest_data(self):
         Ingests tabular data into a key-value based data model where the key is the column header, and value is
         the cleaned cell value.
         """
+        replace_dict = {"headers": {}, "values": {}, "ignore_columns": {}}
+        if "replace_dict" in self.config:
+            for key in replace_dict.keys():
+                if key in self.config["replace_dict"]:
+                    replace_dict[key] = self.config["replace_dict"][key]
+
         with open(self.source, newline="") as csv_file:
             reader = csv.DictReader(csv_file, dialect=self.dialect)
             for row in reader:
-                replace_dict = (
-                    self.config["replace_dict"]["values"]
-                    if "replace_dict" in self.config
-                    and "values" in self.config["replace_dict"]
-                    else {}
-                )
                 item = {
                     key.strip(): cleaned_value(
                         value,
-                        replace_dict=replace_dict,
+                        replace_dict=replace_dict["values"],
                     )
                     for key, value in row.items()
+                    if key not in replace_dict["ignore_columns"]
                 }
                 self.data.append(item)
 

brickschema/brickify/util.py

@@ -2,18 +2,31 @@
 The util module provides helper functions used by brickify.
 """
 
+import click_spinner
 import json
 import re
-from pathlib import Path
-from typing import Optional, Dict
-
-import click_spinner
 import typer
+import urllib.parse
 import yaml
+from pathlib import Path
 from rdflib import Namespace, OWL, RDF, RDFS, Graph
+from typing import Optional, Dict, Union
+from unicodedata import normalize
 from xlrd import open_workbook
 
 
+def decode(value: Union[str, bytes]):
+    """
+    Returns a UTF-8 string produced for the given value.
+
+    :param value: string|bytes
+    :returns: UTF-8 decoded string
+    """
+    if type(value) is bytes:
+        return value.decode("UTF-8")
+    return value
+
+
 def cleaned_value(value, replace_dict: Optional[Dict] = {}):
     """
     Returns a cleaned value produced by doing regex replacements and elimination
@@ -39,9 +52,11 @@ def cleaned_value(value, replace_dict: Optional[Dict] = {}):
             return True
         if value in ["FALSE", "false", "False", "off", "OFF"]:
             return False
+        clean_value = clean_value.strip()
         for replacement in replace_dict.items():
-            clean_value = re.sub(*replacement, clean_value)
-        return clean_value.strip()
+            clean_value = re.sub(*replacement, clean_value).strip()
+        clean_value = urllib.parse.quote_plus(clean_value.encode("UTF-8"))
+        return clean_value
     return clean_value
 
 

brickschema/web.py

@@ -48,7 +48,12 @@ def home(self):
 
     def bindings(self):
         return jsonify(
-            {prefix: namespace for prefix, namespace in self.graph.namespaces() if prefix not in self.ignore_prefixes})
+            {
+                prefix: namespace
+                for prefix, namespace in self.graph.namespaces()
+                if prefix not in self.ignore_prefixes
+            }
+        )
 
     def apply_reasoning(self, profile):
         self.graph.expand(profile)