[PATCH 3 of 3] templater: make strings in template expressions be "string-escape"-ed correctly
FUJIWARA Katsunori
foozy at lares.dti.ne.jp
Sun Mar 9 11:09:25 CDT 2014
# HG changeset patch
# User FUJIWARA Katsunori <foozy at lares.dti.ne.jp>
# Date 1394380903 -32400
# Mon Mar 10 01:01:43 2014 +0900
# Branch stable
# Node ID 5ab28a2e9962f78f90cf3e38483af1bd24035e1a
# Parent a54c0d830499da186d56bf071c3e698eb818de0c
templater: make strings in template expressions be "string-escape"-ed correctly
Changeset 64b4f0cd7336 (released with 2.8.1) fixed "recursively
evaluate string literals as templates" problem (issue4102) by moving
the location of "string-escape"-ing from "tokenizer()" to
"compiletemplate()".
But some parts in template expressions below are not processed by
"compiletemplate()", and it may cause unexpected result.
- 'expr' of 'if(expr, then, else)'
- 'expr's of 'ifeq(expr, expr, then, else)'
- 'sep' of 'join(list, sep)'
- 'text' and 'style' of 'rstdoc(text, style)'
- 'text' and 'chars' of 'strip(text, chars)'
- 'pat' and 'repl' of 'sub(pat, repl, expr)'
For example, '\n' of "{join(extras, '\n')}" is not "string-escape"-ed
and treated as a literal '\n'. This breaks "Display the contents of
the 'extra' field, one per line" example in "hg help templates".
Just "string-escape"-ing on each parts above may not work correctly,
because inside expression of nested ones already applies
"string-escape" on string literals. For example:
- "{join(files, '\n')}" doesn't return "string-escape"-ed string, but
- "{join(files, if(branch, '\n', '\n'))}" does
To fix this problem, this patch does:
- introduce "rawstring" token and "runrawstring" method to handle
strings not to be "string-escape"-ed correctly, and
- make "runstring" method return "string-escape"-ed string, and
delay "string-escape"-ing until evaluation
This patch invokes "compiletemplate()" with "strtoken=exp[0]" in
"gettemplate()", because "exp[1]" is not yet evaluated. This code path
is tested via mapping ("expr % '{template}'").
In the other hand, this patch invokes it with "strtoken='rawstring'"
in "_evalifliteral()", because "t" is the result of "arg" evaluation
and it should be "string-escape"-ed if "arg" is "string" expression.
This patch doesn't test "string-escape"-ing on 'expr' of 'if(expr,
then, else)', because it doesn't affect the result.
diff --git a/mercurial/templater.py b/mercurial/templater.py
--- a/mercurial/templater.py
+++ b/mercurial/templater.py
@@ -21,6 +21,7 @@
")": (0, None, None),
"symbol": (0, ("symbol",), None),
"string": (0, ("string",), None),
+ "rawstring": (0, ("rawstring",), None),
"end": (0, None, None),
}
@@ -50,7 +51,7 @@
continue
if d == c:
if not decode:
- yield ('string', program[s:pos].replace('\\', r'\\'), s)
+ yield ('rawstring', program[s:pos], s)
break
yield ('string', program[s:pos], s)
break
@@ -76,23 +77,22 @@
pos += 1
yield ('end', None, pos)
-def compiletemplate(tmpl, context):
+def compiletemplate(tmpl, context, strtoken="string"):
parsed = []
pos, stop = 0, len(tmpl)
p = parser.parser(tokenizer, elements)
while pos < stop:
n = tmpl.find('{', pos)
if n < 0:
- parsed.append(("string", tmpl[pos:].decode("string-escape")))
+ parsed.append((strtoken, tmpl[pos:]))
break
if n > 0 and tmpl[n - 1] == '\\':
# escaped
- parsed.append(("string",
- (tmpl[pos:n - 1] + "{").decode("string-escape")))
+ parsed.append((strtoken, (tmpl[pos:n - 1] + "{")))
pos = n + 1
continue
if n > pos:
- parsed.append(("string", tmpl[pos:n].decode("string-escape")))
+ parsed.append((strtoken, tmpl[pos:n]))
pd = [tmpl, n + 1, stop]
parseres, pos = p.parse(pd)
@@ -127,13 +127,16 @@
return context._filters[f]
def gettemplate(exp, context):
- if exp[0] == 'string':
- return compiletemplate(exp[1], context)
+ if exp[0] == 'string' or exp[0] == 'rawstring':
+ return compiletemplate(exp[1], context, strtoken=exp[0])
if exp[0] == 'symbol':
return context._load(exp[1])
raise error.ParseError(_("expected template specifier"))
def runstring(context, mapping, data):
+ return data.decode("string-escape")
+
+def runrawstring(context, mapping, data):
return data
def runsymbol(context, mapping, key):
@@ -256,8 +259,9 @@
def _evalifliteral(arg, context, mapping):
t = stringify(arg[0](context, mapping, arg[1]))
- if arg[0] == runstring:
- yield runtemplate(context, mapping, compiletemplate(t, context))
+ if arg[0] == runstring or arg[0] == runrawstring:
+ yield runtemplate(context, mapping,
+ compiletemplate(t, context, strtoken='rawstring'))
else:
yield t
@@ -346,6 +350,7 @@
methods = {
"string": lambda e, c: (runstring, e[1]),
+ "rawstring": lambda e, c: (runrawstring, e[1]),
"symbol": lambda e, c: (runsymbol, e[1]),
"group": lambda e, c: compileexp(e[1], c),
# ".": buildmember,
diff --git a/tests/test-command-template.t b/tests/test-command-template.t
--- a/tests/test-command-template.t
+++ b/tests/test-command-template.t
@@ -1610,6 +1610,92 @@
<>\n<]>
<>\n<
+"string-escape"-ed "\x5c\x786e" becomes r"\x6e" (once) or r"n" (twice)
+
+ $ hg log -R a -r 0 --template '{if("1", "\x5c\x786e", "NG")}\n'
+ \x6e
+ $ hg log -R a -r 0 --template '{if("1", r"\x5c\x786e", "NG")}\n'
+ \x5c\x786e
+ $ hg log -R a -r 0 --template '{if("", "NG", "\x5c\x786e")}\n'
+ \x6e
+ $ hg log -R a -r 0 --template '{if("", "NG", r"\x5c\x786e")}\n'
+ \x5c\x786e
+
+ $ hg log -R a -r 2 --template '{ifeq("no perso\x6e", desc, "\x5c\x786e", "NG")}\n'
+ \x6e
+ $ hg log -R a -r 2 --template '{ifeq(r"no perso\x6e", desc, "NG", r"\x5c\x786e")}\n'
+ \x5c\x786e
+ $ hg log -R a -r 2 --template '{ifeq(desc, "no perso\x6e", "\x5c\x786e", "NG")}\n'
+ \x6e
+ $ hg log -R a -r 2 --template '{ifeq(desc, r"no perso\x6e", "NG", r"\x5c\x786e")}\n'
+ \x5c\x786e
+
+ $ hg log -R a -r 8 --template '{join(files, "\n")}\n'
+ fourth
+ second
+ third
+ $ hg log -R a -r 8 --template '{join(files, r"\n")}\n'
+ fourth\nsecond\nthird
+
+ $ hg log -R a -r 2 --template '{rstdoc("1st\n\n2nd", "htm\x6c")}'
+ <p>
+ 1st
+ </p>
+ <p>
+ 2nd
+ </p>
+ $ hg log -R a -r 2 --template '{rstdoc(r"1st\n\n2nd", "html")}'
+ <p>
+ 1st\n\n2nd
+ </p>
+ $ hg log -R a -r 2 --template '{rstdoc("1st\n\n2nd", r"htm\x6c")}'
+ 1st
+
+ 2nd
+
+ $ hg log -R a -r 2 --template '{strip(desc, "\x6e")}\n'
+ o perso
+ $ hg log -R a -r 2 --template '{strip(desc, r"\x6e")}\n'
+ no person
+ $ hg log -R a -r 2 --template '{strip("no perso\x6e", "\x6e")}\n'
+ o perso
+ $ hg log -R a -r 2 --template '{strip(r"no perso\x6e", r"\x6e")}\n'
+ no perso
+
+ $ hg log -R a -r 2 --template '{sub("\\x6e", "\x2d", desc)}\n'
+ -o perso-
+ $ hg log -R a -r 2 --template '{sub(r"\\x6e", "-", desc)}\n'
+ no person
+ $ hg log -R a -r 2 --template '{sub("n", r"\x2d", desc)}\n'
+ \x2do perso\x2d
+ $ hg log -R a -r 2 --template '{sub("n", "\x2d", "no perso\x6e")}\n'
+ -o perso-
+ $ hg log -R a -r 2 --template '{sub("n", r"\x2d", r"no perso\x6e")}\n'
+ \x2do perso\x6e
+
+ $ hg log -R a -r 8 --template '{files % "{file}\n"}'
+ fourth
+ second
+ third
+ $ hg log -R a -r 8 --template '{files % r"{file}\n"}\n'
+ fourth\nsecond\nthird\n
+
+Test string escapeing in nested expression:
+
+ $ hg log -R a -r 8 --template '{ifeq(r"\x6e", if("1", "\x5c\x786e"), join(files, "\x5c\x786e"))}\n'
+ fourth\x6esecond\x6ethird
+ $ hg log -R a -r 8 --template '{ifeq(if("1", r"\x6e"), "\x5c\x786e", join(files, "\x5c\x786e"))}\n'
+ fourth\x6esecond\x6ethird
+
+ $ hg log -R a -r 8 --template '{join(files, ifeq(branch, "default", "\x5c\x786e"))}\n'
+ fourth\x6esecond\x6ethird
+ $ hg log -R a -r 8 --template '{join(files, ifeq(branch, "default", r"\x5c\x786e"))}\n'
+ fourth\x5c\x786esecond\x5c\x786ethird
+
+ $ hg log -R a -r 3:4 --template '{rev}:{sub(if("1", "\x6e"), ifeq(branch, "foo", r"\x5c\x786e", "\x5c\x786e"), desc)}\n'
+ 3:\x6eo user, \x6eo domai\x6e
+ 4:\x5c\x786eew bra\x5c\x786ech
+
Test recursive evaluation:
$ hg init r
More information about the Mercurial-devel
mailing list