From f5191b8affff08a66baadde175f0b1152896491d Mon Sep 17 00:00:00 2001
From: ohadmata <ohad@pecan.ai>
Date: Tue, 30 Jan 2024 14:12:24 +0200
Subject: [PATCH] float casting issue

---
 assets/coverage.svg        |  4 ++--
 src/shmessy/types/float.py | 23 +++++++++++++++++++++--
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/assets/coverage.svg b/assets/coverage.svg
index 3438732..ee07d4c 100644
--- a/assets/coverage.svg
+++ b/assets/coverage.svg
@@ -15,7 +15,7 @@
     <g fill="#fff" text-anchor="middle" font-family="DejaVu Sans,Verdana,Geneva,sans-serif" font-size="11">
         <text x="31.5" y="15" fill="#010101" fill-opacity=".3">coverage</text>
         <text x="31.5" y="14">coverage</text>
-        <text x="80" y="15" fill="#010101" fill-opacity=".3">97%</text>
-        <text x="80" y="14">97%</text>
+        <text x="80" y="15" fill="#010101" fill-opacity=".3">96%</text>
+        <text x="80" y="14">96%</text>
     </g>
 </svg>
diff --git a/src/shmessy/types/float.py b/src/shmessy/types/float.py
index f82fe8c..f567573 100644
--- a/src/shmessy/types/float.py
+++ b/src/shmessy/types/float.py
@@ -1,11 +1,12 @@
 import locale
 import logging
-from typing import Optional
+from typing import Any, Optional, Tuple
 
 from numpy import ndarray
 from pandas import Series, to_numeric
 from pandas.api.types import is_numeric_dtype
 
+from ..exceptions import FieldCastingException
 from ..schema import InferredField
 from .base import BaseType
 
@@ -30,7 +31,25 @@ def validate(self, data: ndarray) -> Optional[InferredField]:
     def fix(self, column: Series, inferred_field: InferredField) -> Series:
         if is_numeric_dtype(column):
             return column
-        return to_numeric(column.apply(locale.atof))
+        try:
+            return to_numeric(column.apply(locale.atof))
+        except Exception as e:
+            logger.debug(f"Couldn't cast column to type {self.name}: {e}")
+            line_number, bad_value = self._extract_bad_value(column)
+            raise FieldCastingException(
+                type_=self.name, line_number=line_number, bad_value=bad_value
+            )
+
+    @staticmethod
+    def _extract_bad_value(column: Series) -> Tuple[int, Any]:
+        for idx, row in enumerate(column):
+            try:
+                float(row)  # noqa
+            except Exception:  # noqa
+                return idx, row
+
+        # If we reached this piece of code - The dtype is probably an object - do nothing!
+        raise NotImplementedError()
 
 
 def get_type() -> FloatType: