templater: take any string literals as template, but not for rawstring (BC)
This patch series is intended to unify the interpretation of string literals.
It is breaking change that boldly assumes
a. string literal "..." never contains template-like fragment or it is
intended to be a template
b. we tend to use raw string literal r"..." for regexp pattern in which "{"
should have different meaning
Currently, we don't have a comprehensible rule how string literals are
evaluated in template functions. For example, fill() takes "initialindent"
and "hangindent" as templates, but not for "text", whereas "text" is a
template in pad() function.
date(date, fmt)
diff(includepattern, excludepattern)
fill(text, width, initialident: T, hangindent: T)
get(dict, key)
if(expr, then: T, else: T)
ifcontains(search, thing, then: T, else: T)
ifeq(expr1, expr2, then: T, else: T)
indent(text, indentchars, firstline)
join(list, sep)
label(label: T, expr: T)
pad(text: T, width, fillchar, right)
revset(query, formatargs...])
rstdoc(text, style)
shortest(node, minlength)
startswith(pattern, text)
strip(text, chars)
sub(pattern, replacement, expression: T)
word(number, text, separator)
expr % template: T
T: interpret "string" or r"rawstring" as template
This patch series adjusts the rule as follows:
a. string literal, '' or "", starts template processing (BC)
b. raw string literal, r'' or r"", disables both \-escape and template
processing (BC, done by subsequent patches)
c. fragment not surrounded by {} is non-templated string
"ccc{'aaa'}{r'bbb'}"
------------------ *: template
--- c: string
--- a: template
--- b: rawstring
Because this can eliminate the compilation of template arguments from the
evaluation phase, "hg log -Tdefault" gets faster.
% cd mozilla-central
% LANG=C HGRCPATH=/dev/null hg log -Tdefault -r0:10000 --time > /dev/null
before: real 4.870 secs (user 4.860+0.000 sys 0.010+0.000)
after: real 3.480 secs (user 3.440+0.000 sys 0.030+0.000)
Also, this will allow us to parse nested templates at once for better error
indication.
#!/usr/bin/env python
#
# check-translation.py - check Mercurial specific translation problems
import polib
import re
checkers = []
def levelchecker(level, msgidpat):
def decorator(func):
if msgidpat:
match = re.compile(msgidpat).search
else:
match = lambda msgid: True
checkers.append((func, level))
func.match = match
return func
return decorator
def match(checker, pe):
"""Examine whether POEntry "pe" is target of specified checker or not
"""
if not checker.match(pe.msgid):
return
# examine suppression by translator comment
nochecker = 'no-%s-check' % checker.__name__
for tc in pe.tcomment.split():
if nochecker == tc:
return
return True
####################
def fatalchecker(msgidpat=None):
return levelchecker('fatal', msgidpat)
@fatalchecker(r'\$\$')
def promptchoice(pe):
"""Check translation of the string given to "ui.promptchoice()"
>>> pe = polib.POEntry(
... msgid ='prompt$$missing &sep$$missing &$$followed by &none',
... msgstr='prompt missing &sep$$missing amp$$followed by none&')
>>> match(promptchoice, pe)
True
>>> for e in promptchoice(pe): print e
number of choices differs between msgid and msgstr
msgstr has invalid choice missing '&'
msgstr has invalid '&' followed by none
"""
idchoices = [c.rstrip(' ') for c in pe.msgid.split('$$')[1:]]
strchoices = [c.rstrip(' ') for c in pe.msgstr.split('$$')[1:]]
if len(idchoices) != len(strchoices):
yield "number of choices differs between msgid and msgstr"
indices = [(c, c.find('&')) for c in strchoices]
if [c for c, i in indices if i == -1]:
yield "msgstr has invalid choice missing '&'"
if [c for c, i in indices if len(c) == i + 1]:
yield "msgstr has invalid '&' followed by none"
####################
def warningchecker(msgidpat=None):
return levelchecker('warning', msgidpat)
@warningchecker()
def taildoublecolons(pe):
"""Check equality of tail '::'-ness between msgid and msgstr
>>> pe = polib.POEntry(
... msgid ='ends with ::',
... msgstr='ends with ::')
>>> for e in taildoublecolons(pe): print e
>>> pe = polib.POEntry(
... msgid ='ends with ::',
... msgstr='ends without double-colons')
>>> for e in taildoublecolons(pe): print e
tail '::'-ness differs between msgid and msgstr
>>> pe = polib.POEntry(
... msgid ='ends without double-colons',
... msgstr='ends with ::')
>>> for e in taildoublecolons(pe): print e
tail '::'-ness differs between msgid and msgstr
"""
if pe.msgid.endswith('::') != pe.msgstr.endswith('::'):
yield "tail '::'-ness differs between msgid and msgstr"
@warningchecker()
def indentation(pe):
"""Check equality of initial indentation between msgid and msgstr
This may report unexpected warning, because this doesn't aware
the syntax of rst document and the context of msgstr.
>>> pe = polib.POEntry(
... msgid =' indented text',
... msgstr=' narrowed indentation')
>>> for e in indentation(pe): print e
initial indentation width differs betweeen msgid and msgstr
"""
idindent = len(pe.msgid) - len(pe.msgid.lstrip())
strindent = len(pe.msgstr) - len(pe.msgstr.lstrip())
if idindent != strindent:
yield "initial indentation width differs betweeen msgid and msgstr"
####################
def check(pofile, fatal=True, warning=False):
targetlevel = { 'fatal': fatal, 'warning': warning }
targetcheckers = [(checker, level)
for checker, level in checkers
if targetlevel[level]]
if not targetcheckers:
return []
detected = []
for pe in pofile.translated_entries():
errors = []
for checker, level in targetcheckers:
if match(checker, pe):
errors.extend((level, checker.__name__, error)
for error in checker(pe))
if errors:
detected.append((pe, errors))
return detected
########################################
if __name__ == "__main__":
import sys
import optparse
optparser = optparse.OptionParser("""%prog [options] pofile ...
This checks Mercurial specific translation problems in specified
'*.po' files.
Each detected problems are shown in the format below::
filename:linenum:type(checker): problem detail .....
"type" is "fatal" or "warning". "checker" is the name of the function
detecting corresponded error.
Checking by checker "foo" on the specific msgstr can be suppressed by
the "translator comment" like below. Multiple "no-xxxx-check" should
be separated by whitespaces::
# no-foo-check
msgid = "....."
msgstr = "....."
""")
optparser.add_option("", "--warning",
help="show also warning level problems",
action="store_true")
optparser.add_option("", "--doctest",
help="run doctest of this tool, instead of check",
action="store_true")
(options, args) = optparser.parse_args()
if options.doctest:
import os
if 'TERM' in os.environ:
del os.environ['TERM']
import doctest
failures, tests = doctest.testmod()
sys.exit(failures and 1 or 0)
# replace polib._POFileParser to show linenum of problematic msgstr
class ExtPOFileParser(polib._POFileParser):
def process(self, symbol, linenum):
super(ExtPOFileParser, self).process(symbol, linenum)
if symbol == 'MS': # msgstr
self.current_entry.linenum = linenum
polib._POFileParser = ExtPOFileParser
detected = []
warning = options.warning
for f in args:
detected.extend((f, pe, errors)
for pe, errors in check(polib.pofile(f),
warning=warning))
if detected:
for f, pe, errors in detected:
for level, checker, error in errors:
sys.stderr.write('%s:%d:%s(%s): %s\n'
% (f, pe.linenum, level, checker, error))
sys.exit(1)