paulmataruso/zulip
1
0
Fork 0
mirror of https://github.com/zulip/zulip.git synced 2025-11-05 06:23:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

python: Normalize quotes with Black.

Browse Source 
Signed-off-by: Anders Kaseorg <anders@zulip.com>
This commit is contained in:
Anders Kaseorg
2021-02-11 23:20:45 -08:00
committed by Tim Abbott
parent 11741543da
commit 6e4c3e41dc
989 changed files with 32792 additions and 32792 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
tools/lib/capitalization.py
View File

@@ -43,11 +43,11 @@ IGNORED_PHRASES = [
r"Play Store",
r"PM",
r"PMs",
r'REMOTE_USER',
r'Slack',
r"REMOTE_USER",
r"Slack",
r"SSO",
r'Terms of Service',
r'Tuesday',
r"Terms of Service",
r"Tuesday",
r"URL",
r"Ubuntu",
r"Updown",
@@ -94,13 +94,13 @@ IGNORED_PHRASES = [
r"streamname",
r"user@example.com",
# Fragments of larger strings
(r'your subscriptions on your Streams page'),
(r"your subscriptions on your Streams page"),
(
r'Change notification settings for individual streams on your '
r"Change notification settings for individual streams on your "
'<a href="/#streams">Streams page</a>.'
),
(
r'Looking for our '
r"Looking for our "
'<a href="/integrations" target="_blank">Integrations</a> or '
'<a href="/api" target="_blank">API</a> documentation?'
),
@@ -128,10 +128,10 @@ IGNORED_PHRASES = [
r"in 20 minutes",
r"in 3 hours",
# We should probably just delete this string from translations
r'activation key',
r"activation key",
# these are used as topics
r'^new streams$',
r'^stream events$',
r"^new streams$",
r"^stream events$",
# These are used as example short names (e.g. an uncapitalized context):
r"^marketing$",
r"^cookie$",
@@ -167,22 +167,22 @@ IGNORED_PHRASES.sort(key=lambda regex: len(regex), reverse=True)
# text using BeautifulSoup and then removes extra whitespaces from
# it. This step enables us to add HTML in our regexes directly.
COMPILED_IGNORED_PHRASES = [
re.compile(' '.join(BeautifulSoup(regex, 'lxml').text.split())) for regex in IGNORED_PHRASES
re.compile(" ".join(BeautifulSoup(regex, "lxml").text.split())) for regex in IGNORED_PHRASES
]
SPLIT_BOUNDARY = '?.!' # Used to split string into sentences.
SPLIT_BOUNDARY_REGEX = re.compile(fr'[{SPLIT_BOUNDARY}]')
SPLIT_BOUNDARY = "?.!" # Used to split string into sentences.
SPLIT_BOUNDARY_REGEX = re.compile(fr"[{SPLIT_BOUNDARY}]")
# Regexes which check capitalization in sentences.
DISALLOWED = [
r'^[a-z](?!\})', # Checks if the sentence starts with a lower case character.
r'^[A-Z][a-z]+[\sa-z0-9]+[A-Z]', # Checks if an upper case character exists
r"^[a-z](?!\})", # Checks if the sentence starts with a lower case character.
r"^[A-Z][a-z]+[\sa-z0-9]+[A-Z]", # Checks if an upper case character exists
# after a lower case character when the first character is in upper case.
]
DISALLOWED_REGEX = re.compile(r"|".join(DISALLOWED))
BANNED_WORDS = {
'realm': 'The term realm should not appear in user-facing strings. Use organization instead.',
"realm": "The term realm should not appear in user-facing strings. Use organization instead.",
}
@@ -192,7 +192,7 @@ def get_safe_phrase(phrase: str) -> str:
conflict with split boundaries. All conflicting characters are replaced
with low dash (_).
"""
phrase = SPLIT_BOUNDARY_REGEX.sub('_', phrase)
phrase = SPLIT_BOUNDARY_REGEX.sub("_", phrase)
return phrase.lower()
@@ -226,8 +226,8 @@ def get_safe_text(text: str) -> str:
This returns text which is rendered by BeautifulSoup and is in the
form that can be split easily and has all IGNORED_PHRASES processed.
"""
soup = BeautifulSoup(text, 'lxml')
text = ' '.join(soup.text.split()) # Remove extra whitespaces.
soup = BeautifulSoup(text, "lxml")
text = " ".join(soup.text.split()) # Remove extra whitespaces.
for phrase_regex in COMPILED_IGNORED_PHRASES:
text = phrase_regex.sub(replace_with_safe_phrase, text)
@@ -246,7 +246,7 @@ def check_banned_words(text: str) -> List[str]:
if word in lower_cased_text:
# Hack: Should move this into BANNED_WORDS framework; for
# now, just hand-code the skips:
if 'realm_name' in lower_cased_text:
if "realm_name" in lower_cased_text:
continue
kwargs = dict(word=word, text=text, reason=reason)
msg = "{word} found in '{text}'. {reason}".format(**kwargs)
@@ -260,7 +260,7 @@ def check_capitalization(strings: List[str]) -> Tuple[List[str], List[str], List
ignored = []
banned_word_errors = []
for text in strings:
text = ' '.join(text.split()) # Remove extra whitespaces.
text = " ".join(text.split()) # Remove extra whitespaces.
safe_text = get_safe_text(text)
has_ignored_phrase = text != safe_text
capitalized = is_capitalized(safe_text)