chore: add new pattern for dash bullet (#109)

* add new pattern for dash bullet
Unstructured-IO · Dec 21, 2022 · 6f4d9ad · 6f4d9ad
1 parent 962c9dc
commit 6f4d9ad
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,8 @@
+## 0.3.5-dev0
+
+* Add new pattern to recognize plain text dash bullets
+* Add test for bullet patterns
+
 ## 0.3.4
 
 * Python-3.7 compat

diff --git a/test_unstructured/partition/test_text_type.py b/test_unstructured/partition/test_text_type.py
@@ -88,6 +88,7 @@ def test_is_possible_title(text, expected, monkeypatch):
         ("⦿ This is a fine point!", True),
         ("  This is a fine point!", True),
         ("* This is a fine point!", True),
+        ("- This is a fine point!", True),
         ("This is NOT a fine point!", False),  # No bullet point
         ("I love morse code! ● ● ● --- ● ● ●", False),  # Not at the beginning
     ],

diff --git a/unstructured/__version__.py b/unstructured/__version__.py
@@ -1 +1 @@
-__version__ = "0.3.4"  # pragma: no cover
+__version__ = "0.3.5-dev0"  # pragma: no cover
diff --git a/unstructured/nlp/patterns.py b/unstructured/nlp/patterns.py
@@ -26,6 +26,7 @@
     "\u2767",
     "\u29BE",
     "\u29BF",
+    "\u002D",
     "",
     "\*",  # noqa: W605 NOTE(robinson) - skipping qa because we need the escape for the regex
     "\x95",
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		__version__ = "0.3.4" # pragma: no cover
		__version__ = "0.3.5-dev0" # pragma: no cover