yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-07-31 04:46:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update patterns.py (#391)

Browse Source
This commit is contained in:
cragwolfe 2023-03-21 23:58:18 -07:00 committed by GitHub
parent 6b17cb228e
commit 3467a2786d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
unstructured/nlp/patterns.py
View File

@ -66,8 +66,9 @@ EMAIL_HEAD_PATTERN = (
)
EMAIL_HEAD_RE = re.compile(EMAIL_HEAD_PATTERN)
# Helps split text by paragraphs
PARAGRAPH_PATTERN = "\n\n\n|\n\n|\r\n|\r|\n" # noqa: W605 NOTE(harrell)
# Helps split text by paragraphs. There must be one newline, with potential whitespace
# (incluing \r and \n chars) on either side
PARAGRAPH_PATTERN = r"\s*\n\s*" # noqa: W605 NOTE(harrell)
# IP Address examples: ba23::58b5:2236:45g2:88h2 or 10.0.2.01
IP_ADDRESS_PATTERN = (