diff mbox series

[v4,03/14,GSOC] ref-filter: --format=%(raw) re-support --perl

Message ID b54dbc431e043c3ea2530fa8d1b4ba7e743b3d61.1624332054.git.gitgitgadget@gmail.com (mailing list archive)
State Superseded
Headers show
Series cat-file: reuse ref-filter logic | expand

Commit Message

ZheNing Hu June 22, 2021, 3:20 a.m. UTC
From: ZheNing Hu <adlternative@gmail.com>

Because the perl language can handle binary data correctly,
add the function perl_quote_buf_with_len(), which can specify
the length of the data and prevent the data from being truncated
at '\0' to help `--format="%(raw)"` re-support `--perl`.

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 Documentation/git-for-each-ref.txt |  2 +-
 quote.c                            | 17 +++++++++++++++++
 quote.h                            |  1 +
 ref-filter.c                       | 15 +++++++++++----
 t/t6300-for-each-ref.sh            | 19 +++++++++++++++++--
 5 files changed, 47 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/Documentation/git-for-each-ref.txt b/Documentation/git-for-each-ref.txt
index 7f1f0a1ca3b6..ea9b438c16f6 100644
--- a/Documentation/git-for-each-ref.txt
+++ b/Documentation/git-for-each-ref.txt
@@ -241,7 +241,7 @@  raw:size::
 	The raw data size of the object.
 
 Note that `--format=%(raw)` can not be used with `--python`, `--shell`, `--tcl`,
-`--perl` because the host language may not support arbitrary binary data in the
+because the host language may not support arbitrary binary data in the
 variables of its string type.
 
 The message in a commit or a tag object is `contents`, from which
diff --git a/quote.c b/quote.c
index 8a3a5e39eb12..26719d21d1e7 100644
--- a/quote.c
+++ b/quote.c
@@ -471,6 +471,23 @@  void perl_quote_buf(struct strbuf *sb, const char *src)
 	strbuf_addch(sb, sq);
 }
 
+void perl_quote_buf_with_len(struct strbuf *sb, const char *src, size_t len)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	const char *c = src;
+	const char *end = src + len;
+
+	strbuf_addch(sb, sq);
+	while (c != end) {
+		if (*c == sq || *c == bq)
+			strbuf_addch(sb, bq);
+		strbuf_addch(sb, *c);
+		c++;
+	}
+	strbuf_addch(sb, sq);
+}
+
 void python_quote_buf(struct strbuf *sb, const char *src)
 {
 	const char sq = '\'';
diff --git a/quote.h b/quote.h
index 768cc6338e27..0fe69e264b0e 100644
--- a/quote.h
+++ b/quote.h
@@ -94,6 +94,7 @@  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_len(struct strbuf *sb, const char *src, size_t len);
 void python_quote_buf(struct strbuf *sb, const char *src);
 void tcl_quote_buf(struct strbuf *sb, const char *src);
 void basic_regex_quote_buf(struct strbuf *sb, const char *src);
diff --git a/ref-filter.c b/ref-filter.c
index 7822be903071..797b20ffa612 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -742,7 +742,10 @@  static void quote_formatting(struct strbuf *s, const char *str, size_t len, int
 		sq_quote_buf(s, str);
 		break;
 	case QUOTE_PERL:
-		perl_quote_buf(s, str);
+		if (len != ATOM_VALUE_S_SIZE_INIT)
+			perl_quote_buf_with_len(s, str, len);
+		else
+			perl_quote_buf(s, str);
 		break;
 	case QUOTE_PYTHON:
 		python_quote_buf(s, str);
@@ -1006,10 +1009,14 @@  int verify_ref_format(struct ref_format *format)
 		at = parse_ref_filter_atom(format, sp + 2, ep, &err);
 		if (at < 0)
 			die("%s", err.buf);
-		if (format->quote_style && used_atom[at].atom_type == ATOM_RAW &&
-		    used_atom[at].u.raw_data.option == RAW_BARE)
+
+		if ((format->quote_style == QUOTE_PYTHON ||
+		     format->quote_style == QUOTE_SHELL ||
+		     format->quote_style == QUOTE_TCL) &&
+		     used_atom[at].atom_type == ATOM_RAW &&
+		     used_atom[at].u.raw_data.option == RAW_BARE)
 			die(_("--format=%.*s cannot be used with"
-			      "--python, --shell, --tcl, --perl"), (int)(ep - sp - 2), sp + 2);
+			      "--python, --shell, --tcl"), (int)(ep - sp - 2), sp + 2);
 		cp = ep + 1;
 
 		if (skip_prefix(used_atom[at].name, "color:", &color))
diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh
index 9c5379e2f56f..5556063c347d 100755
--- a/t/t6300-for-each-ref.sh
+++ b/t/t6300-for-each-ref.sh
@@ -915,8 +915,23 @@  test_expect_success '%(raw) with --tcl must fail' '
 	test_must_fail git for-each-ref --format="%(raw)" --tcl
 '
 
-test_expect_success '%(raw) with --perl must fail' '
-	test_must_fail git for-each-ref --format="%(raw)" --perl
+test_expect_success '%(raw) with --perl' '
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob1 --perl | perl > actual &&
+	cmp blob1 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob3 --perl | perl > actual &&
+	cmp blob3 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob8 --perl | perl > actual &&
+	cmp blob8 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/first --perl | perl > actual &&
+	cmp one actual &&
+	git cat-file tree refs/mytrees/first > expected &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/mytrees/first --perl | perl > actual &&
+	cmp expected actual
 '
 
 test_expect_success '%(raw) with --shell must fail' '