This is an archive of the discontinued Mercurial Phabricator instance.

Differential D5815

global: use raw strings for regular expressions with escapes
ClosedPublic

Authored by indygreg on Feb 4 2019, 12:18 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHGbd3f03d8cc9f: global: use raw strings for regular expressions with escapes
Summary

Escape sequences like \w, \s, and \d are technically invalid
in str/bytes. This became a deprecation warning in Python 3.6
(https://bugs.python.org/issue27364). Python 3.8 bumps it to
a SyntaxWarning (https://bugs.python.org/issue32912), which is
non-silent by default.

This commit changes a number of regular expressions to use
br'' so regular expression special sequences don't need \\
literals. This fixes roughly half of the SyntaxWarning we
see in the code base with Python 3.8.

Diff Detail

Repository
rHG Mercurial
Lint
Lint Skipped
Unit
Unit Tests Skipped

Event Timeline

indygreg created this revision.Feb 4 2019, 12:18 PM
Closed by commit rHGbd3f03d8cc9f: global: use raw strings for regular expressions with escapes (authored by indygreg). · Explain WhyFeb 4 2019, 6:35 PM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mhgext/blackbox.py (2 lines)
Mhgext/commitextras.py (2 lines)
Mhgext/convert/cvsps.py (2 lines)
Mhgext/mq.py (2 lines)
Mhgext/phabricator.py (4 lines)
Mhgext/releasenotes.py (2 lines)
Mmercurial/color.py (2 lines)
Mmercurial/patch.py (6 lines)

Diff 13742

hgext/blackbox.py

count = 0 count = 0
output = [] output = []
for line in reversed(lines): for line in reversed(lines):
if count >= limit: if count >= limit:
break break
# count the commands by matching lines like: 2013/01/23 19:13:36 root> # count the commands by matching lines like: 2013/01/23 19:13:36 root>
if re.match('^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line): if re.match(br'^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
count += 1 count += 1
output.append(line) output.append(line)
ui.status('\n'.join(reversed(output))) ui.status('\n'.join(reversed(output)))

hgext/commitextras.py

if '=' not in raw: if '=' not in raw:
msg = _("unable to parse '%s', should follow " msg = _("unable to parse '%s', should follow "
"KEY=VALUE format") "KEY=VALUE format")
raise error.Abort(msg % raw) raise error.Abort(msg % raw)
k, v = raw.split('=', 1) k, v = raw.split('=', 1)
if not k: if not k:
msg = _("unable to parse '%s', keys can't be empty") msg = _("unable to parse '%s', keys can't be empty")
raise error.Abort(msg % raw) raise error.Abort(msg % raw)
if re.search('[^\w-]', k): if re.search(br'[^\w-]', k):
msg = _("keys can only contain ascii letters, digits," msg = _("keys can only contain ascii letters, digits,"
" '_' and '-'") " '_' and '-'")
raise error.Abort(msg) raise error.Abort(msg)
if k in usedinternally: if k in usedinternally:
msg = _("key '%s' is used internally, can't be set " msg = _("key '%s' is used internally, can't be set "
"manually") "manually")
raise error.Abort(msg % k) raise error.Abort(msg % k)
inneropts[r'extra'][k] = v inneropts[r'extra'][k] = v
return super(repoextra, self).commit(*innerpats, **inneropts) return super(repoextra, self).commit(*innerpats, **inneropts)
repo.__class__ = repoextra repo.__class__ = repoextra
return orig(ui, repo, *pats, **opts) return orig(ui, repo, *pats, **opts)

hgext/convert/cvsps.py

re_03 = re.compile(b"(Cannot access.+CVSROOT)|" re_03 = re.compile(b"(Cannot access.+CVSROOT)|"
b"(can't create temporary directory.+)$") b"(can't create temporary directory.+)$")
re_10 = re.compile(b'Working file: (.+)$') re_10 = re.compile(b'Working file: (.+)$')
re_20 = re.compile(b'symbolic names:') re_20 = re.compile(b'symbolic names:')
re_30 = re.compile(b'\t(.+): ([\\d.]+)$') re_30 = re.compile(b'\t(.+): ([\\d.]+)$')
re_31 = re.compile(b'----------------------------$') re_31 = re.compile(b'----------------------------$')
re_32 = re.compile(b'=======================================' re_32 = re.compile(b'======================================='
b'======================================$') b'======================================$')
re_50 = re.compile(b'revision ([\\d.]+)(\s+locked by:\s+.+;)?$') re_50 = re.compile(br'revision ([\d.]+)(\s+locked by:\s+.+;)?$')
re_60 = re.compile(br'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);' re_60 = re.compile(br'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
br'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?' br'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
br'(\s+commitid:\s+([^;]+);)?' br'(\s+commitid:\s+([^;]+);)?'
br'(.*mergepoint:\s+([^;]+);)?') br'(.*mergepoint:\s+([^;]+);)?')
re_70 = re.compile(b'branches: (.+);$') re_70 = re.compile(b'branches: (.+);$')
file_added_re = re.compile(br'file [^/]+ was (initially )?added on branch') file_added_re = re.compile(br'file [^/]+ was (initially )?added on branch')

hgext/mq.py

raise error.Abort(_('"%s" already exists as a directory') raise error.Abort(_('"%s" already exists as a directory')
% name) % name)
else: else:
raise error.Abort(_('patch "%s" already exists') % name) raise error.Abort(_('patch "%s" already exists') % name)
def makepatchname(self, title, fallbackname): def makepatchname(self, title, fallbackname):
"""Return a suitable filename for title, adding a suffix to make """Return a suitable filename for title, adding a suffix to make
it unique in the existing list""" it unique in the existing list"""
namebase = re.sub('[\s\W_]+', '_', title.lower()).strip('_') namebase = re.sub(br'[\s\W_]+', b'_', title.lower()).strip(b'_')
namebase = namebase[:75] # avoid too long name (issue5117) namebase = namebase[:75] # avoid too long name (issue5117)
if namebase: if namebase:
try: try:
self.checkreservedname(namebase) self.checkreservedname(namebase)
except error.Abort: except error.Abort:
namebase = fallbackname namebase = fallbackname
else: else:
namebase = fallbackname namebase = fallbackname

hgext/phabricator.py

query = callconduit(repo, b'diffusion.repository.search', query = callconduit(repo, b'diffusion.repository.search',
{b'constraints': {b'callsigns': [callsign]}}) {b'constraints': {b'callsigns': [callsign]}})
if len(query[r'data']) == 0: if len(query[r'data']) == 0:
return None return None
repophid = encoding.strtolocal(query[r'data'][0][r'phid']) repophid = encoding.strtolocal(query[r'data'][0][r'phid'])
repo.ui.setconfig(b'phabricator', b'repophid', repophid) repo.ui.setconfig(b'phabricator', b'repophid', repophid)
return repophid return repophid
_differentialrevisiontagre = re.compile(b'\AD([1-9][0-9]*)\Z') _differentialrevisiontagre = re.compile(br'\AD([1-9][0-9]*)\Z')
_differentialrevisiondescre = re.compile( _differentialrevisiondescre = re.compile(
b'^Differential Revision:\s*(?P<url>(?:.*)D(?P<id>[1-9][0-9]*))$', re.M) br'^Differential Revision:\s*(?P<url>(?:.*)D(?P<id>[1-9][0-9]*))$', re.M)
def getoldnodedrevmap(repo, nodelist): def getoldnodedrevmap(repo, nodelist):
"""find previous nodes that has been sent to Phabricator """find previous nodes that has been sent to Phabricator
return {node: (oldnode, Differential diff, Differential Revision ID)} return {node: (oldnode, Differential diff, Differential Revision ID)}
for node in nodelist with known previous sent versions, or associated for node in nodelist with known previous sent versions, or associated
Differential Revision IDs. ``oldnode`` and ``Differential diff`` could Differential Revision IDs. ``oldnode`` and ``Differential diff`` could
be ``None``. be ``None``.

hgext/releasenotes.py

DEFAULT_SECTIONS = [ DEFAULT_SECTIONS = [
('feature', _('New Features')), ('feature', _('New Features')),
('bc', _('Backwards Compatibility Changes')), ('bc', _('Backwards Compatibility Changes')),
('fix', _('Bug Fixes')), ('fix', _('Bug Fixes')),
('perf', _('Performance Improvements')), ('perf', _('Performance Improvements')),
('api', _('API Changes')), ('api', _('API Changes')),
] ]
RE_DIRECTIVE = re.compile('^\.\. ([a-zA-Z0-9_]+)::\s*([^$]+)?$') RE_DIRECTIVE = re.compile(br'^\.\. ([a-zA-Z0-9_]+)::\s*([^$]+)?$')
RE_ISSUE = br'\bissue ?[0-9]{4,6}(?![0-9])\b' RE_ISSUE = br'\bissue ?[0-9]{4,6}(?![0-9])\b'
BULLET_SECTION = _('Other Changes') BULLET_SECTION = _('Other Changes')
class parsedreleasenotes(object): class parsedreleasenotes(object):
def __init__(self): def __init__(self):
self.sections = {} self.sections = {}

mercurial/color.py

csbi = _CONSOLE_SCREEN_BUFFER_INFO() csbi = _CONSOLE_SCREEN_BUFFER_INFO()
if not _kernel32.GetConsoleScreenBufferInfo( if not _kernel32.GetConsoleScreenBufferInfo(
stdout, ctypes.byref(csbi)): stdout, ctypes.byref(csbi)):
# stdout may not support GetConsoleScreenBufferInfo() # stdout may not support GetConsoleScreenBufferInfo()
# when called from subprocess or redirected # when called from subprocess or redirected
w32effects = None w32effects = None
else: else:
origattr = csbi.wAttributes origattr = csbi.wAttributes
ansire = re.compile(b'\033\[([^m]*)m([^\033]*)(.*)', ansire = re.compile(br'\033\[([^m]*)m([^\033]*)(.*)',
re.MULTILINE | re.DOTALL) re.MULTILINE | re.DOTALL)
def win32print(ui, writefunc, text, **opts): def win32print(ui, writefunc, text, **opts):
label = opts.get(r'label', '') label = opts.get(r'label', '')
attr = origattr attr = origattr
def mapcolor(val, attr): def mapcolor(val, attr):
if val == -1: if val == -1:

mercurial/patch.py

def exists(self, fname): def exists(self, fname):
return fname in self.ctx return fname in self.ctx
def close(self): def close(self):
return self.changed | self.removed return self.changed | self.removed
# @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@') unidesc = re.compile(br'@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)') contextdesc = re.compile(br'(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
eolmodes = ['strict', 'crlf', 'lf', 'auto'] eolmodes = ['strict', 'crlf', 'lf', 'auto']
class patchfile(object): class patchfile(object):
def __init__(self, ui, gp, backend, store, eolmode='strict'): def __init__(self, ui, gp, backend, store, eolmode='strict'):
self.fname = gp.path self.fname = gp.path
self.eolmode = eolmode self.eolmode = eolmode
self.eol = None self.eol = None
self.backend = backend self.backend = backend
maxtotal = max(maxtotal, a + r) maxtotal = max(maxtotal, a + r)
addtotal += a addtotal += a
removetotal += r removetotal += r
binary = binary or b binary = binary or b
return maxfile, maxtotal, addtotal, removetotal, binary return maxfile, maxtotal, addtotal, removetotal, binary
def diffstatdata(lines): def diffstatdata(lines):
diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$') diffre = re.compile(br'^diff .*-r [a-z0-9]+\s(.*)$')
results = [] results = []
filename, adds, removes, isbinary = None, 0, 0, False filename, adds, removes, isbinary = None, 0, 0, False
def addresult(): def addresult():
if filename: if filename:
results.append((filename, adds, removes, isbinary)) results.append((filename, adds, removes, isbinary))