[PATCH 1/3] [GSOC] quote: add *.quote_buf_with_size functions

From: ZheNing Hu via GitGitGadget <gitgitgadget@gmail.com>
Date: May 23, 2021, 09:53 UTC
Message-ID: <f7121bdc4d8d8ac0071e6410960fd8787b0c36ae.1621763612.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.959.git.1621763612.gitgitgadget@gmail.com>

From: ZheNing Hu <adlternative@gmail.com>

With the original functions `*._quote_buf()`, there may be '\0' in our source string, only the content before the first '\0' will be processed and added to the buffer.

Add `perl_quote_buf_with_size()`, `python_quote_buf_with_size()`, `tcl_quote_buf_with_size`,`sq_quote_buf_with_size()` to `quote.c`, they will process the source string with specified length characters. With them, the content after '\0' will not be truncated.

This will help us add binary data containing '\0' to `quote_formatting()` in `ref-filter.c`.

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 quote.c | 116 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 quote.h |   4 ++
 2 files changed, 120 insertions(+)

diff --git a/quote.c b/quote.c
index 8a3a5e39eb12..9a1d9dde1fdb 100644
--- a/quote.c
+++ b/quote.c
@@ -43,6 +43,39 @@ void sq_quote_buf(struct strbuf *dst, const char *src)
 	free(to_free);
 }
 
+void sq_quote_buf_with_size(struct strbuf *dst, const char *src, size_t size)
+{
+	char *to_free = NULL;
+	size_t cur_size = 0;
+
+	if (dst->buf == src)
+		to_free = strbuf_detach(dst, NULL);
+
+	strbuf_addch(dst, '\'');
+	while (cur_size < size) {
+		size_t len = strcspn(src, "'!");
+		if (!len) {
+			strbuf_add(dst, src, 1);
+			src++;
+			cur_size++;
+		} else {
+			strbuf_add(dst, src, len);
+			src += len;
+			cur_size += len;
+		}
+		if (cur_size >= size)
+			break;
+		while (need_bs_quote(*src)) {
+			strbuf_addstr(dst, "'\\");
+			strbuf_addch(dst, *src++);
+			cur_size++;
+			strbuf_addch(dst, '\'');
+		}
+	}
+	strbuf_addch(dst, '\'');
+	free(to_free);
+}
+
 void sq_quote_buf_pretty(struct strbuf *dst, const char *src)
 {
 	static const char ok_punct[] = "+,-./:=@_^";
@@ -471,6 +504,25 @@ void perl_quote_buf(struct strbuf *sb, const char *src)
 	strbuf_addch(sb, sq);
 }
 
+void perl_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	char c;
+	size_t cur_size = 0;
+
+	strbuf_addch(sb, sq);
+	while (cur_size < size) {
+		c = *src++;
+		cur_size++;
+
+		if (c == sq || c == bq)
+			strbuf_addch(sb, bq);
+		strbuf_addch(sb, c);
+	}
+	strbuf_addch(sb, sq);
+}
+
 void python_quote_buf(struct strbuf *sb, const char *src)
 {
 	const char sq = '\'';
@@ -492,6 +544,31 @@ void python_quote_buf(struct strbuf *sb, const char *src)
 	strbuf_addch(sb, sq);
 }
 
+void python_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	const char nl = '\n';
+	char c;
+	size_t cur_size = 0;
+
+	strbuf_addch(sb, sq);
+	while (cur_size < size) {
+		c = *src++;
+		cur_size++;
+
+		if (c == nl) {
+			strbuf_addch(sb, bq);
+			strbuf_addch(sb, 'n');
+			continue;
+		}
+		if (c == sq || c == bq)
+			strbuf_addch(sb, bq);
+		strbuf_addch(sb, c);
+	}
+	strbuf_addch(sb, sq);
+}
+
 void tcl_quote_buf(struct strbuf *sb, const char *src)
 {
 	char c;
@@ -527,6 +604,45 @@ void tcl_quote_buf(struct strbuf *sb, const char *src)
 	strbuf_addch(sb, '"');
 }
 
+void tcl_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size)
+{
+	char c;
+	size_t cur_size = 0;
+
+	strbuf_addch(sb, '"');
+	while (cur_size < size) {
+		c = *src++;
+		cur_size++;
+
+		switch (c) {
+		case '[': case ']':
+		case '{': case '}':
+		case '$': case '\\': case '"':
+			strbuf_addch(sb, '\\');
+			/* fallthrough */
+		default:
+			strbuf_addch(sb, c);
+			break;
+		case '\f':
+			strbuf_addstr(sb, "\\f");
+			break;
+		case '\r':
+			strbuf_addstr(sb, "\\r");
+			break;
+		case '\n':
+			strbuf_addstr(sb, "\\n");
+			break;
+		case '\t':
+			strbuf_addstr(sb, "\\t");
+			break;
+		case '\v':
+			strbuf_addstr(sb, "\\v");
+			break;
+		}
+	}
+	strbuf_addch(sb, '"');
+}
+
 void basic_regex_quote_buf(struct strbuf *sb, const char *src)
 {
 	char c;
diff --git a/quote.h b/quote.h
index 768cc6338e27..e894507329cc 100644
--- a/quote.h
+++ b/quote.h
@@ -30,6 +30,7 @@ struct strbuf;
  */
 
 void sq_quote_buf(struct strbuf *, const char *src);
+void sq_quote_buf_with_size(struct strbuf *, const char *src, size_t size);
 void sq_quote_argv(struct strbuf *, const char **argv);
 void sq_quotef(struct strbuf *, const char *fmt, ...);
 
@@ -94,8 +95,11 @@ char *quote_path(const char *in, const char *prefix, struct strbuf *out, unsigne
 
 /* quoting as a string literal for other languages */
 void perl_quote_buf(struct strbuf *sb, const char *src);
+void perl_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size);
 void python_quote_buf(struct strbuf *sb, const char *src);
+void python_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size);
 void tcl_quote_buf(struct strbuf *sb, const char *src);
+void tcl_quote_buf_with_size(struct strbuf *sb, const char *src, size_t size);
 void basic_regex_quote_buf(struct strbuf *sb, const char *src);
 
 #endif

-- 
gitgitgadget