grep/icase: avoid kwsset when -F is specified

Similar to the previous commit, we can't use kws on icase search
outside ascii range. But we can't simply pass the pattern to
regcomp/pcre like the previous commit because it may contain regex
special characters, so we need to quote the regex first.

To avoid misquote traps that could lead to undefined behavior, we
always stick to basic regex engine in this case. We don't need fancy
features for grepping a literal string anyway.

basic_regex_quote_buf() assumes that if the pattern is in a multibyte
encoding, ascii chars must be unambiguously encoded as single
bytes. This is true at least for UTF-8. For others, let's wait until
people yell up. Chances are nobody uses multibyte, non utf-8 charsets
anymore.

Noticed-by: Plamen Totev <[email protected]>
Helped-by: René Scharfe <[email protected]>
Helped-by: Eric Sunshine <[email protected]>
Signed-off-by: Nguyễn Thái Ngọc Duy <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pclouds

grep.c

@@ -5,6 +5,7 @@
 #include "diff.h"
 #include "diffcore.h"
 #include "commit.h"
+#include "quote.h"
 
 static int grep_source_load(struct grep_source *gs);
 static int grep_source_is_binary(struct grep_source *gs);
@@ -397,6 +398,28 @@ static int is_fixed(const char *s, size_t len)
 	return 1;
 }
 
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int err;
+	int regflags;
+
+	basic_regex_quote_buf(&sb, p->pattern);
+	regflags = opt->regflags & ~REG_EXTENDED;
+	if (opt->ignore_case)
+		regflags |= REG_ICASE;
+	err = regcomp(&p->regexp, sb.buf, regflags);
+	if (opt->debug)
+		fprintf(stderr, "fixed %s\n", sb.buf);
+	strbuf_release(&sb);
+	if (err) {
+		char errbuf[1024];
+		regerror(err, &p->regexp, errbuf, sizeof(errbuf));
+		regfree(&p->regexp);
+		compile_regexp_failed(p, errbuf);
+	}
+}
+
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
 	int icase, ascii_only;
@@ -407,8 +430,20 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 	icase	       = opt->regflags & REG_ICASE || p->ignore_case;
 	ascii_only     = !has_non_ascii(p->pattern);
 
+	/*
+	 * Even when -F (fixed) asks us to do a non-regexp search, we
+	 * may not be able to correctly case-fold when -i
+	 * (ignore-case) is asked (in which case, we'll synthesize a
+	 * regexp to match the pattern that matches regexp special
+	 * characters literally, while ignoring case differences).  On
+	 * the other hand, even without -F, if the pattern does not
+	 * have any regexp special characters and there is no need for
+	 * case-folding search, we can internally turn it into a
+	 * simple string match using kws.  p->fixed tells us if we
+	 * want to use kws.
+	 */
 	if (opt->fixed)
-		p->fixed = 1;
+		p->fixed = !icase || ascii_only;
 	else if ((!icase || ascii_only) &&
 		 is_fixed(p->pattern, p->patternlen))
 		p->fixed = 1;
@@ -423,6 +458,14 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 		kwsincr(p->kws, p->pattern, p->patternlen);
 		kwsprep(p->kws);
 		return;
+	} else if (opt->fixed) {
+		/*
+		 * We come here when the pattern has the non-ascii
+		 * characters we cannot case-fold, and asked to
+		 * ignore-case.
+		 */
+		compile_fixed_regexp(p, opt);
+		return;
 	}
 
 	if (opt->pcre) {

quote.c

@@ -440,3 +440,40 @@ void tcl_quote_buf(struct strbuf *sb, const char *src)
 	}
 	strbuf_addch(sb, '"');
 }
+
+void basic_regex_quote_buf(struct strbuf *sb, const char *src)
+{
+	char c;
+
+	if (*src == '^') {
+		/* only beginning '^' is special and needs quoting */
+		strbuf_addch(sb, '\\');
+		strbuf_addch(sb, *src++);
+	}
+	if (*src == '*')
+		/* beginning '*' is not special, no quoting */
+		strbuf_addch(sb, *src++);
+
+	while ((c = *src++)) {
+		switch (c) {
+		case '[':
+		case '.':
+		case '\\':
+		case '*':
+			strbuf_addch(sb, '\\');
+			strbuf_addch(sb, c);
+			break;
+
+		case '$':
+			/* only the end '$' is special and needs quoting */
+			if (*src == '\0')
+				strbuf_addch(sb, '\\');
+			strbuf_addch(sb, c);
+			break;
+
+		default:
+			strbuf_addch(sb, c);
+			break;
+		}
+	}
+}

quote.h

@@ -67,5 +67,6 @@ extern char *quote_path_relative(const char *in, const char *prefix,
 extern void perl_quote_buf(struct strbuf *sb, const char *src);
 extern void python_quote_buf(struct strbuf *sb, const char *src);
 extern void tcl_quote_buf(struct strbuf *sb, const char *src);
+extern void basic_regex_quote_buf(struct strbuf *sb, const char *src);
 
 #endif

t/t7812-grep-icase-non-ascii.sh

@@ -20,4 +20,30 @@ test_expect_success REGEX_LOCALE 'grep literal string, no -F' '
 	git grep -i "TILRAUN: HALLÓ HEIMUR!"
 '
 
+test_expect_success REGEX_LOCALE 'grep literal string, with -F' '
+	git grep --debug -i -F "TILRAUN: Halló Heimur!"  2>&1 >/dev/null |
+		 grep fixed >debug1 &&
+	test_write_lines "fixed TILRAUN: Halló Heimur!" >expect1 &&
+	test_cmp expect1 debug1 &&
+
+	git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!"  2>&1 >/dev/null |
+		 grep fixed >debug2 &&
+	test_write_lines "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 &&
+	test_cmp expect2 debug2
+'
+
+test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
+	test_write_lines "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file &&
+
+	git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null |
+		 grep fixed >debug1 &&
+	test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 &&
+	test_cmp expect1 debug1 &&
+
+	git grep --debug -i -F "^*TILR^AUN:.* \\HALLÓ \$HE[]IMUR!\$"  2>&1 >/dev/null |
+		 grep fixed >debug2 &&
+	test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
+	test_cmp expect2 debug2
+'
+
 test_done