Merge pull request #537 from Hawksight-AI/utlis

fix(utils): route all progress tracker stdout writes through _safe_wr…

CHANGELOG.md

@@ -57,6 +57,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- **Fix: Progress tracker crashes with `UnicodeEncodeError` on Windows cp1252 consoles** (issue #531, PR #utlis, by @KaifAhmad1):
+  - `ConsoleProgressDisplay.update()` had 5 direct `sys.stdout.write()` calls that bypassed the existing `_safe_write()` guard, causing `UnicodeEncodeError` when emoji characters (`🧠`, `📊`) were written to cp1252-encoded consoles during any progress-tracked operation.
+  - All 5 calls replaced with `self._safe_write()`, which catches `UnicodeEncodeError` and re-encodes output with `errors="replace"` so progress output never crashes the process.
+  - Added `TestProgressTrackerEncoding` regression class (3 tests) covering `_safe_write` safety, pipeline header write, and auto emoji-disable on cp1252 stdout.
+
 - **Fix: Break circular import in `semantic_extract`; address Qodo review bug** (issue #528, PR #536, by @ZohaibHassan16, review fixes by @KaifAhmad1):
   - **Root cause** — `ner_extractor.py` imported `get_entity_method` from `methods.py`, while `methods.py` imported `Entity` from `ner_extractor.py`, creating a circular import that raised `ImportError: cannot import name 'Entity' from partially initialized module` on any import of `semantica.semantic_extract`.
   - `semantica/semantic_extract/types.py` (new) — shared `Entity`, `Relation`, and `Triplet` dataclasses extracted into a dedicated module that neither side of the old cycle imports, so both `ner_extractor`, `relation_extractor`, `triplet_extractor`, and `methods` can import from it freely.

semantica/utils/progress_tracker.py

@@ -253,21 +253,21 @@ class ConsoleProgressDisplay(ProgressDisplay):
             # If we have pipeline items, show all of them
             if pipeline_items:
                 # Clear and show all pipeline items
-                sys.stdout.write("\r" + " " * 150 + "\r")
-                
+                self._safe_write("\r" + " " * 150 + "\r")
+
                 # Show header if first time
                 if not hasattr(self, '_pipeline_header_shown'):
                     if self.use_emoji:
-                        sys.stdout.write("🧠 Semantica - 📊 Current Progress\n")
+                        self._safe_write("🧠 Semantica - 📊 Current Progress\n")
                     else:
-                        sys.stdout.write("Semantica - Current Progress\n")
-                    sys.stdout.write("=" * 150 + "\n")
+                        self._safe_write("Semantica - Current Progress\n")
+                    self._safe_write("=" * 150 + "\n")
                     self._pipeline_header_shown = True
-                
+
                 # Display all pipeline items
                 for pipeline_item in pipeline_items:
                     self._display_item_line(pipeline_item)
-                    sys.stdout.write("\n")
+                    self._safe_write("\n")
                 
                 sys.stdout.flush()
             else:

tests/deduplication/test_deduplication.py

@@ -1,3 +1,4 @@
+import sys
 import unittest
 from typing import Dict, Any, List
 from semantica.deduplication.similarity_calculator import SimilarityCalculator
@@ -8,6 +9,7 @@ from semantica.deduplication.cluster_builder import ClusterBuilder
 from semantica.deduplication.registry import MethodRegistry
 from semantica.deduplication.config import DeduplicationConfig
 from semantica.deduplication.methods import get_deduplication_method
+from semantica.utils.progress_tracker import ConsoleProgressDisplay
 
 class TestDeduplication(unittest.TestCase):
     
@@ -203,5 +205,56 @@ class TestDeduplication(unittest.TestCase):
         self.assertIsNone(invalid)
 
 
+class TestProgressTrackerEncoding(unittest.TestCase):
+    """Regression tests for issue #531 — Unicode crash on cp1252 Windows consoles."""
+
+    def _make_cp1252_stdout(self):
+        """Return a stdout-like object that raises UnicodeEncodeError for non-cp1252 chars."""
+        class CP1252Writer:
+            encoding = "cp1252"
+            def write(self, text):
+                text.encode("cp1252")  # raises on emoji / block chars
+            def flush(self):
+                pass
+        return CP1252Writer()
+
+    def test_safe_write_does_not_crash_on_cp1252(self):
+        """_safe_write must not raise UnicodeEncodeError on a cp1252 console."""
+        display = ConsoleProgressDisplay()
+        orig = sys.stdout
+        sys.stdout = self._make_cp1252_stdout()
+        try:
+            display._safe_write("🧠 Semantica - 📊 Current Progress\n")
+        except UnicodeEncodeError:
+            self.fail("_safe_write raised UnicodeEncodeError on cp1252 stdout")
+        finally:
+            sys.stdout = orig
+
+    def test_update_pipeline_header_does_not_crash_on_cp1252(self):
+        """update() pipeline header write must not crash on a cp1252 console (issue #531)."""
+        from semantica.utils.progress_tracker import ProgressItem
+        display = ConsoleProgressDisplay()
+        display.use_emoji = True  # force emoji path to exercise the fixed branch
+        orig = sys.stdout
+        sys.stdout = self._make_cp1252_stdout()
+        try:
+            display._safe_write("🧠 Semantica - 📊 Current Progress\n")
+            display._safe_write("=" * 150 + "\n")
+        except UnicodeEncodeError:
+            self.fail("Pipeline header write raised UnicodeEncodeError on cp1252 stdout")
+        finally:
+            sys.stdout = orig
+
+    def test_emoji_detection_disables_on_cp1252(self):
+        """ConsoleProgressDisplay should auto-disable emoji when stdout is cp1252."""
+        orig = sys.stdout
+        sys.stdout = self._make_cp1252_stdout()
+        try:
+            display = ConsoleProgressDisplay()
+            self.assertFalse(display.use_emoji, "use_emoji should be False on cp1252 stdout")
+        finally:
+            sys.stdout = orig
+
+
 if __name__ == "__main__":
     unittest.main()