datamarket 0.9.50__tar.gz → 0.9.51__tar.gz

{datamarket-0.9.50 → datamarket-0.9.51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: datamarket
-Version: 0.9.50
+Version: 0.9.51
 Summary: Utilities that integrate advanced scraping knowledge into just one library.
 License: GPL-3.0-or-later
 Author: DataMarket

{datamarket-0.9.50 → datamarket-0.9.51}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "datamarket"
-version = "0.9.50"
+version = "0.9.51"
 description = "Utilities that integrate advanced scraping knowledge into just one library."
 authors = ["DataMarket <techsupport@datamarket.es>"]
 license = "GPL-3.0-or-later"

{datamarket-0.9.50 → datamarket-0.9.51}/src/datamarket/utils/strings/normalization.py

@@ -137,8 +137,13 @@ def normalize(
     # Parameter mapping
     if isinstance(mode, str):
         mode = NormalizationMode[mode.upper()]
+    if not isinstance(mode, NormalizationMode):
+        raise TypeError("mode must be NormalizationMode or str")
+
     if isinstance(naming, str):
         naming = NamingConvention[naming.upper()]
+    if not isinstance(naming, NamingConvention):
+        raise TypeError("naming must be NamingConvention or str")
 
     _allowed_symbols_set: Set[str] = set(allowed_symbols) if allowed_symbols else set()
 
@@ -148,7 +153,11 @@ def normalize(
     elif not isinstance(s, str):
         return str(s)
     else:
-        text = prettify(strip_html(str(s), True))
+        raw_text = str(s)
+        if naming is NamingConvention.NONE:
+            text = raw_text
+        else:
+            text = prettify(strip_html(raw_text, True))
 
         if mode is NormalizationMode.NONE:
             normalized = text
@@ -170,9 +179,7 @@ def normalize(
 
             for c in intermediate_text:
                 cat = unicodedata.category(c)
-                if c in _allowed_symbols_set:  # Allowed symbols are part of tokens
-                    current_token_chars.append(c)
-                elif c.isalnum():
+                if c in _allowed_symbols_set or c.isalnum():  # Allowed symbols are part of tokens
                     current_token_chars.append(c)
                 elif mode is NormalizationMode.FULL and cat.startswith("S"):
                     # Transliterate S* category symbols not in allowed_symbols