yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-11-11 16:07:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* add new pattern for dash bullet
This commit is contained in:
Mallori Harrell 2022-12-21 10:23:51 -06:00 committed by GitHub
parent 962c9dccca
commit 6f4d9ad06c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
CHANGELOG.md
View File

@ -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 ## 0.3.4
* Python-3.7 compat * Python-3.7 compat

1
test_unstructured/partition/test_text_type.py
View File

@ -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 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 ("This is NOT a fine point!", False), # No bullet point
("I love morse code! ● ● ● --- ● ● ●", False), # Not at the beginning ("I love morse code! ● ● ● --- ● ● ●", False), # Not at the beginning
], ],

2
unstructured/__version__.py
View File

@ -1 +1 @@
__version__ = "0.3.4" # pragma: no cover __version__ = "0.3.5-dev0" # pragma: no cover

1
unstructured/nlp/patterns.py
View File

@ -26,6 +26,7 @@ UNICODE_BULLETS: Final[List[str]] = [
"\u2767", "\u2767",
"\u29BE", "\u29BE",
"\u29BF", "\u29BF",
"\u002D",
"", "",
"\*", # noqa: W605 NOTE(robinson) - skipping qa because we need the escape for the regex "\*", # noqa: W605 NOTE(robinson) - skipping qa because we need the escape for the regex
"\x95", "\x95",