reencode_string: use size_t for string lengths

peff · gitster · commit c7d017d7e1cc · 2018-07-24T10:19:29.000-07:00
The iconv interface takes a size_t, which is the appropriate
type for an in-memory buffer. But our reencode_string_*
functions use integers, meaning we may get confusing results
when the sizes exceed INT_MAX. Let's use size_t
consistently.

Signed-off-by: Jeff King &lt;peff@peff.net&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/convert.c b/convert.c
@@ -389,7 +389,7 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 			 struct strbuf *buf, const char *enc, int conv_flags)
 {
 	char *dst;
-	int dst_len;
+	size_t dst_len;
 	int die_on_error = conv_flags & CONV_WRITE_OBJECT;
 
 	/*
@@ -452,7 +452,7 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	 */
 	if (die_on_error && check_roundtrip(enc)) {
 		char *re_src;
-		int re_src_len;
+		size_t re_src_len;
 
 		re_src = reencode_string_len(dst, dst_len,
 					     enc, default_encoding,
@@ -480,7 +480,7 @@ static int encode_to_worktree(const char *path, const char *src, size_t src_len,
 			      struct strbuf *buf, const char *enc)
 {
 	char *dst;
-	int dst_len;
+	size_t dst_len;
 
 	/*
 	 * No encoding is specified or there is nothing to encode.
diff --git a/pretty.c b/pretty.c
@@ -1538,7 +1538,7 @@ void format_commit_message(const struct commit *commit,
 	}
 
 	if (output_enc) {
-		int outsz;
+		size_t outsz;
 		char *out = reencode_string_len(sb->buf, sb->len,
 						output_enc, utf8, &outsz);
 		if (out)
diff --git a/strbuf.c b/strbuf.c
@@ -134,7 +134,7 @@ void strbuf_ltrim(struct strbuf *sb)
 int strbuf_reencode(struct strbuf *sb, const char *from, const char *to)
 {
 	char *out;
-	int len;
+	size_t len;
 
 	if (same_encoding(from, to))
 		return 0;
diff --git a/utf8.c b/utf8.c
@@ -470,7 +470,7 @@ int utf8_fprintf(FILE *stream, const char *format, ...)
 #else
 	typedef char * iconv_ibp;
 #endif
-char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p)
+char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, size_t *outsz_p)
 {
 	size_t outsz, outalloc;
 	char *out, *outpos;
@@ -534,9 +534,9 @@ static const char *fallback_encoding(const char *name)
 	return name;
 }
 
-char *reencode_string_len(const char *in, int insz,
+char *reencode_string_len(const char *in, size_t insz,
 			  const char *out_encoding, const char *in_encoding,
-			  int *outsz)
+			  size_t *outsz)
 {
 	iconv_t conv;
 	char *out;
diff --git a/utf8.h b/utf8.h
@@ -25,14 +25,14 @@ void strbuf_utf8_replace(struct strbuf *sb, int pos, int width,
 
 #ifndef NO_ICONV
 char *reencode_string_iconv(const char *in, size_t insz,
-			    iconv_t conv, int *outsz);
-char *reencode_string_len(const char *in, int insz,
+			    iconv_t conv, size_t *outsz);
+char *reencode_string_len(const char *in, size_t insz,
 			  const char *out_encoding,
 			  const char *in_encoding,
-			  int *outsz);
+			  size_t *outsz);
 #else
-static inline char *reencode_string_len(const char *a, int b,
-					const char *c, const char *d, int *e)
+static inline char *reencode_string_len(const char *a, size_t b,
+					const char *c, const char *d, size_t *e)
 { if (e) *e = 0; return NULL; }
 #endif
 

Original file line number	Diff line number	Diff line change
`@@ -1538,7 +1538,7 @@ void format_commit_message(const struct commit *commit,`
`1538`	`1538`	`}`
`1539`	`1539`
`1540`	`1540`	`if (output_enc) {`
`1541`		`- int outsz;`
	`1541`	`+ size_t outsz;`
`1542`	`1542`	`char *out = reencode_string_len(sb->buf, sb->len,`
`1543`	`1543`	`output_enc, utf8, &outsz);`
`1544`	`1544`	`if (out)`
Original file line number	Diff line number	Diff line change
`@@ -134,7 +134,7 @@ void strbuf_ltrim(struct strbuf *sb)`
`134`	`134`	`int strbuf_reencode(struct strbuf sb, const char from, const char *to)`
`135`	`135`	`{`
`136`	`136`	`char *out;`
`137`		`- int len;`
	`137`	`+ size_t len;`
`138`	`138`
`139`	`139`	`if (same_encoding(from, to))`
`140`	`140`	`return 0;`
Original file line number	Diff line number	Diff line change
`@@ -470,7 +470,7 @@ int utf8_fprintf(FILE stream, const char format, ...)`
`470`	`470`	`#else`
`471`	`471`	`typedef char * iconv_ibp;`
`472`	`472`	`#endif`
`473`		`-char reencode_string_iconv(const char in, size_t insz, iconv_t conv, int *outsz_p)`
	`473`	`+char reencode_string_iconv(const char in, size_t insz, iconv_t conv, size_t *outsz_p)`
`474`	`474`	`{`
`475`	`475`	`size_t outsz, outalloc;`
`476`	`476`	`char out, outpos;`
`@@ -534,9 +534,9 @@ static const char fallback_encoding(const char name)`
`534`	`534`	`return name;`
`535`	`535`	`}`
`536`	`536`
`537`		`-char reencode_string_len(const char in, int insz,`
	`537`	`+char reencode_string_len(const char in, size_t insz,`
`538`	`538`	`const char out_encoding, const char in_encoding,`
`539`		`- int *outsz)`
	`539`	`+ size_t *outsz)`
`540`	`540`	`{`
`541`	`541`	`iconv_t conv;`
`542`	`542`	`char *out;`