Merge pull request #63733 from akien-mga/file-get_as_text-skip-CR

File: Re-add support to skip CR (`\r`) in `File::get_as_text`

6 files changed, 17 insertions, 9 deletions

diff --git a/core/core_bind.cpp b/core/core_bind.cpp
index 65cc3b4c42..79c80cf7d1 100644
--- a/core/core_bind.cpp
+++ b/core/core_bind.cpp
@@ -1238,13 +1238,13 @@ Vector<uint8_t> File::get_buffer(int64_t p_length) const {
 	return data;
 }
 
-String File::get_as_text() const {
+String File::get_as_text(bool p_skip_cr) const {
 	ERR_FAIL_COND_V_MSG(f.is_null(), String(), "File must be opened before use, or is lacking read-write permission.");
 
 	uint64_t original_pos = f->get_position();
 	const_cast<FileAccess *>(*f)->seek(0);
 
-	String text = f->get_as_utf8_string();
+	String text = f->get_as_utf8_string(p_skip_cr);
 
 	const_cast<FileAccess *>(*f)->seek(original_pos);
 
@@ -1441,7 +1441,7 @@ void File::_bind_methods() {
 	ClassDB::bind_method(D_METHOD("get_buffer", "length"), &File::get_buffer);
 	ClassDB::bind_method(D_METHOD("get_line"), &File::get_line);
 	ClassDB::bind_method(D_METHOD("get_csv_line", "delim"), &File::get_csv_line, DEFVAL(","));
-	ClassDB::bind_method(D_METHOD("get_as_text"), &File::get_as_text);
+	ClassDB::bind_method(D_METHOD("get_as_text", "skip_cr"), &File::get_as_text, DEFVAL(false));
 	ClassDB::bind_method(D_METHOD("get_md5", "path"), &File::get_md5);
 	ClassDB::bind_method(D_METHOD("get_sha256", "path"), &File::get_sha256);
 	ClassDB::bind_method(D_METHOD("is_big_endian"), &File::is_big_endian);
diff --git a/core/core_bind.h b/core/core_bind.h
index 8f66dc03ce..45b4091ce2 100644
--- a/core/core_bind.h
+++ b/core/core_bind.h
@@ -412,7 +412,7 @@ public:
 	Vector<uint8_t> get_buffer(int64_t p_length) const; // Get an array of bytes.
 	String get_line() const;
 	Vector<String> get_csv_line(const String &p_delim = ",") const;
-	String get_as_text() const;
+	String get_as_text(bool p_skip_cr = false) const;
 	String get_md5(const String &p_path) const;
 	String get_sha256(const String &p_path) const;
 
diff --git a/core/io/file_access.cpp b/core/io/file_access.cpp
index da25f23917..8ed3d40c22 100644
--- a/core/io/file_access.cpp
+++ b/core/io/file_access.cpp
@@ -377,7 +377,7 @@ uint64_t FileAccess::get_buffer(uint8_t *p_dst, uint64_t p_length) const {
 	return i;
 }
 
-String FileAccess::get_as_utf8_string() const {
+String FileAccess::get_as_utf8_string(bool p_skip_cr) const {
 	Vector<uint8_t> sourcef;
 	uint64_t len = get_length();
 	sourcef.resize(len + 1);
@@ -388,7 +388,7 @@ String FileAccess::get_as_utf8_string() const {
 	w[len] = 0;
 
 	String s;
-	s.parse_utf8((const char *)w);
+	s.parse_utf8((const char *)w, -1, p_skip_cr);
 	return s;
 }
 
diff --git a/core/io/file_access.h b/core/io/file_access.h
index e2c11142d7..3386800686 100644
--- a/core/io/file_access.h
+++ b/core/io/file_access.h
@@ -113,7 +113,7 @@ public:
 	virtual String get_line() const;
 	virtual String get_token() const;
 	virtual Vector<String> get_csv_line(const String &p_delim = ",") const;
-	virtual String get_as_utf8_string() const;
+	virtual String get_as_utf8_string(bool p_skip_cr = false) const;
 
 	/**
 	 * Use this for files WRITTEN in _big_ endian machines (ie, amiga/mac)
diff --git a/core/string/ustring.cpp b/core/string/ustring.cpp
index beefe54faf..e93375bff7 100644
--- a/core/string/ustring.cpp
+++ b/core/string/ustring.cpp
@@ -1656,7 +1656,7 @@ String String::utf8(const char *p_utf8, int p_len) {
 	return ret;
 }
 
-Error String::parse_utf8(const char *p_utf8, int p_len) {
+Error String::parse_utf8(const char *p_utf8, int p_len, bool p_skip_cr) {
 	if (!p_utf8) {
 		return ERR_INVALID_DATA;
 	}
@@ -1689,6 +1689,10 @@ Error String::parse_utf8(const char *p_utf8, int p_len) {
 			uint8_t c = *ptrtmp >= 0 ? *ptrtmp : uint8_t(256 + *ptrtmp);
 
 			if (skip == 0) {
+				if (p_skip_cr && c == '\r') {
+					ptrtmp++;
+					continue;
+				}
 				/* Determine the number of characters in sequence */
 				if ((c & 0x80) == 0) {
 					skip = 0;
@@ -1753,6 +1757,10 @@ Error String::parse_utf8(const char *p_utf8, int p_len) {
 		uint8_t c = *p_utf8 >= 0 ? *p_utf8 : uint8_t(256 + *p_utf8);
 
 		if (skip == 0) {
+			if (p_skip_cr && c == '\r') {
+				p_utf8++;
+				continue;
+			}
 			/* Determine the number of characters in sequence */
 			if ((c & 0x80) == 0) {
 				*(dst++) = c;
diff --git a/core/string/ustring.h b/core/string/ustring.h
index 7672663964..6c3169f136 100644
--- a/core/string/ustring.h
+++ b/core/string/ustring.h
@@ -377,7 +377,7 @@ public:
 
 	CharString ascii(bool p_allow_extended = false) const;
 	CharString utf8() const;
-	Error parse_utf8(const char *p_utf8, int p_len = -1);
+	Error parse_utf8(const char *p_utf8, int p_len = -1, bool p_skip_cr = false);
 	static String utf8(const char *p_utf8, int p_len = -1);
 
 	Char16String utf16() const;