Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix deprecation warnings due to invalid escape sequences. #820

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix deprecation warnings due to invalid escape sequences. #820

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions jieba/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,9 +41,9 @@
# \r\n|\s : whitespace characters. Will not be handled.
# re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%]+)", re.U)
# Adding "-" symbol in re_han_default
re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%\-]+)", re.U)
re_han_default = re.compile(r"([\u4E00-\u9FD5a-zA-Z0-9+#&\._%\-]+)", re.U)

re_skip_default = re.compile("(\r\n|\s)", re.U)
re_skip_default = re.compile(r"(\r\n|\s)", re.U)


def setLogLevel(log_level):
Expand Down
2 changes: 1 addition & 1 deletion jieba/finalseg/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ def __cut(sentence):
yield sentence[nexti:]

re_han = re.compile("([\u4E00-\u9FD5]+)")
re_skip = re.compile("([a-zA-Z0-9]+(?:\.\d+)?%?)")
re_skip = re.compile(r"([a-zA-Z0-9]+(?:\.\d+)?%?)")


def add_force_split(word):
Expand Down
8 changes: 4 additions & 4 deletions jieba/posseg/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,12 @@
CHAR_STATE_TAB_P = "char_state_tab.p"

re_han_detail = re.compile("([\u4E00-\u9FD5]+)")
re_skip_detail = re.compile("([\.0-9]+|[a-zA-Z0-9]+)")
re_han_internal = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._]+)")
re_skip_internal = re.compile("(\r\n|\s)")
re_skip_detail = re.compile(r"([\.0-9]+|[a-zA-Z0-9]+)")
re_han_internal = re.compile(r"([\u4E00-\u9FD5a-zA-Z0-9+#&\._]+)")
re_skip_internal = re.compile(r"(\r\n|\s)")

re_eng = re.compile("[a-zA-Z0-9]+")
re_num = re.compile("[\.0-9]+")
re_num = re.compile(r"[\.0-9]+")

re_eng1 = re.compile('^[a-zA-Z0-9]$', re.U)

Expand Down