Future/bison
1
0
Fork 0
mirror of https://git.savannah.gnu.org/git/bison.git synced 2026-03-14 06:43:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

parser: keep string aliases as the user wrote it

Browse Source 
Currently our scanner decodes all the escapes in the strings, and we
later reescape the strings when we emit them.

This is troublesome, as we do not respect the user input.  For
instance, when the user writes in UTF-8, we destroy her string when we
write it back.  And this shows everywhere: in the reports we show the
escaped string instead of the actual alias:

    0 $accept: . exp $end
    1 exp: . exp "\342\212\225" exp
    2    | . exp "+" exp
    3    | . exp "+" exp
    4    | . "number"
    5    | . "\303\221\303\271\341\271\203\303\251\342\204\235\303\264"

    "number"                                                    shift, and go to state 1
    "\303\221\303\271\341\271\203\303\251\342\204\235\303\264"  shift, and go to state 2

This commit preserves the user's exact spelling of the string aliases,
instead of interpreting the escapes and then reescaping.  The report
now shows:

    0 $accept: . exp $end
    1 exp: . exp "⊕" exp
    2    | . exp "+" exp
    3    | . exp "+" exp
    4    | . "number"
    5    | . "Ñùṃéℝô"

    "number"          shift, and go to state 1
    "Ñùṃéℝô"  shift, and go to state 2

Likewise, the XML (and therefore HTML) outputs are fixed.

* src/scan-gram.l (STRING, TSTRING): Do not interpret the escapes in
the resulting string.
* src/parse-gram.y (unquote, parser_init, parser_free, unquote_free)
(handle_defines, handle_language, obstack_for_unquote): New.
Use them to unquote where needed.
* tests/regression.at, tests/report.at: Update.
This commit is contained in:
Akim Demaille
2020-06-13 08:46:58 +02:00
parent 5d5e1df1dc
commit 5855da4722
7 changed files with 266 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/scan-gram.l
View File

@@ -88,16 +88,15 @@ static boundary scanner_cursor;
do { \
verify (UCHAR_MAX < ULONG_MAX); \
long c = Char; \
if (0 < c && c <= UCHAR_MAX) \
STRING_1GROW (c); \
bool valid = 0 < c && c <= UCHAR_MAX; \
if (!valid) \
complain (loc, complaint, \
_("invalid number after \\-escape: %s"), \
yytext + 1); \
if (YY_START == SC_ESCAPED_CHARACTER) \
STRING_1GROW (valid ? c : '?'); \
else \
{ \
complain (loc, complaint, \
_("invalid number after \\-escape: %s"), \
yytext + 1); \
/* Avoid additional errors about empty char literal. */ \
STRING_1GROW ('?'); \
} \
STRING_GROW (); \
} while (0)
@@ -337,8 +336,8 @@ eqopt ({sp}=)?
"'" token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;
/* Strings. */
"\"" token_start = loc->start; BEGIN SC_ESCAPED_STRING;
"_(\"" token_start = loc->start; BEGIN SC_ESCAPED_TSTRING;
"\"" token_start = loc->start; STRING_1GROW ('"'); BEGIN SC_ESCAPED_STRING;
"_(\"" token_start = loc->start; STRING_1GROW ('"'); BEGIN SC_ESCAPED_TSTRING;
/* Prologue. */
"%{" code_start = loc->start; BEGIN SC_PROLOGUE;
@@ -559,6 +558,7 @@ eqopt ({sp}=)?
<SC_ESCAPED_STRING>
{
"\"" {
STRING_1GROW ('"');
STRING_FINISH ();
BEGIN INITIAL;
loc->start = token_start;
@@ -571,6 +571,7 @@ eqopt ({sp}=)?
<SC_ESCAPED_TSTRING>
{
"\")" {
STRING_1GROW ('"');
STRING_FINISH ();
BEGIN INITIAL;
loc->start = token_start;
@@ -664,16 +665,16 @@ eqopt ({sp}=)?
STRING_GROW_ESCAPE (strtol (yytext + 2, NULL, 16));
}
\\a STRING_1GROW ('\a');
\\b STRING_1GROW ('\b');
\\f STRING_1GROW ('\f');
\\n STRING_1GROW ('\n');
\\r STRING_1GROW ('\r');
\\t STRING_1GROW ('\t');
\\v STRING_1GROW ('\v');
\\a STRING_GROW_ESCAPE ('\a');
\\b STRING_GROW_ESCAPE ('\b');
\\f STRING_GROW_ESCAPE ('\f');
\\n STRING_GROW_ESCAPE ('\n');
\\r STRING_GROW_ESCAPE ('\r');
\\t STRING_GROW_ESCAPE ('\t');
\\v STRING_GROW_ESCAPE ('\v');
/* \\[\"\'?\\] would be shorter, but it confuses xgettext. */
\\("\""|"'"|"?"|"\\") STRING_1GROW (yytext[1]);
\\("\""|"'"|"?"|"\\") STRING_GROW_ESCAPE (yytext[1]);
\\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} {
STRING_GROW_ESCAPE (convert_ucn_to_byte (yytext));
@@ -1024,7 +1025,7 @@ gram_scanner_open (const char *gram)
void
gram_scanner_close ()
gram_scanner_close (void)
{
xfclose (gram_in);
/* Reclaim Flex's buffers. */
@@ -1032,7 +1033,6 @@ gram_scanner_close ()
}
void
gram_scanner_free (void)
{