Skip to content

[SUGGESTION][FIX] Add support for raw string literals in mixed mode #69

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Dec 15, 2022
Merged

[SUGGESTION][FIX] Add support for raw string literals in mixed mode #69

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
245fa46
Add support for raw string literals in mixed mode
filipsajdak Oct 11, 2022
e95b547
Add support for raw string d_char_sequence
filipsajdak Oct 11, 2022
e870980
Correct formating
filipsajdak Oct 11, 2022
1bce5b4
Simplifying search for closing sequence
filipsajdak Oct 12, 2022
cd3160a
Rename the variable for closing sequence
filipsajdak Oct 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion source/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ struct source_line
{
std::string text;

enum class category { empty, preprocessor, comment, import, cpp1, cpp2 }
enum class category { empty, preprocessor, comment, import, cpp1, cpp2, rawstring }
cat = category::empty;

auto prefix() const -> std::string
Expand All @@ -58,6 +58,7 @@ struct source_line
break;case category::import: return "/* i */ ";
break;case category::cpp1: return "/* 1 */ ";
break;case category::cpp2: return "/* 2 */ ";
break;case category::rawstring: return "/* R */ ";
break;default: assert(!"illegal category"); abort();
}
}
Expand Down
58 changes: 44 additions & 14 deletions source/load.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,27 +196,30 @@ auto starts_with_identifier_colon(std::string const& line) -> bool
struct process_line_ret {
bool all_comment_line;
bool empty_line;
bool all_rawstring_line;
};
auto process_cpp_line(
std::string const& line,
bool& in_comment,
bool& in_string_literal,
bool& in_raw_string_literal,
std::string& raw_string_closing_seq,
std::vector<int>& brace_depth,
lineno_t lineno,
std::vector<error>& errors
)
-> process_line_ret
{
if (!in_comment && !in_string_literal && starts_with_whitespace_slash_slash(line)) {
return { true, false };
if (!in_comment && !in_string_literal && !in_raw_string_literal && starts_with_whitespace_slash_slash(line)) {
return { true, false, false };
}

if (!in_comment && !in_string_literal && starts_with_whitespace_slash_star_and_no_star_slash(line)) {
if (!in_comment && !in_string_literal && !in_raw_string_literal && starts_with_whitespace_slash_star_and_no_star_slash(line)) {
in_comment = true;
return { true, false };
return { true, false, false };
}

struct process_line_ret r { in_comment, true };
struct process_line_ret r { in_comment, true , in_raw_string_literal};

auto prev = ' ';
for (auto i = colno_t{0}; i < ssize(line); ++i)
Expand All @@ -225,27 +228,46 @@ auto process_cpp_line(
// Note: in_literal is for { and } and so doesn't have to work for escaped ' characters
//
auto peek = [&](int num) { return (i+num < std::ssize(line)) ? line[i+num] : '\0'; };
auto in_literal = [&]() { return in_string_literal || (prev == '\'' && peek(1) == '\''); };
auto in_literal = [&]() { return in_string_literal || in_raw_string_literal || (prev == '\'' && peek(1) == '\''); };

// Process this source character
//
if (!std::isspace(line[i])) {
r.empty_line = false;
}

if (in_comment && !in_string_literal) {
if (in_comment && !in_string_literal && !in_raw_string_literal) {
switch (line[i]) {
break;case '/': if (prev == '*') { in_comment = false; }
break;default: ;
}
}

else if (in_raw_string_literal) {
auto end_pos = line.find(raw_string_closing_seq, i);
if (end_pos == std::string::npos) {
return r;
}
in_raw_string_literal = false;
i = end_pos+raw_string_closing_seq.size()-1;
}
else {
r.all_comment_line = false;
r.all_rawstring_line = false;
switch (line[i]) {
break;case 'R':
if (!in_comment && !in_string_literal && !in_raw_string_literal && peek(1) == '"') {
i+=2;
if (i < ssize(line) - 1) {
if (auto paren_pos = line.find("(", i); paren_pos != std::string::npos) {
raw_string_closing_seq = ")"+line.substr(i, paren_pos-i)+"\"";
in_raw_string_literal = true;
}
}
}

break;case '\"':
// If this isn't an escaped quote, toggle string literal state
if (!in_comment && prev != '\\' && (in_string_literal || prev != '\'')) {
if (!in_comment && prev != '\\' && (in_string_literal || prev != '\'') && !in_raw_string_literal) {
in_string_literal = !in_string_literal;
}

Expand All @@ -270,10 +292,10 @@ auto process_cpp_line(
}

break;case '*':
if (!in_string_literal && prev == '/') { in_comment = true; }
if (!in_string_literal && !in_raw_string_literal && prev == '/') { in_comment = true; }

break;case '/':
if (!in_string_literal && prev == '/') { in_comment = false; return r; }
if (!in_string_literal && !in_raw_string_literal && prev == '/') { in_comment = false; return r; }

break;default: ;
}
Expand Down Expand Up @@ -436,8 +458,11 @@ class source
return false;
}

auto in_comment = false;
auto in_string_literal = false;
auto in_comment = false;
auto in_string_literal = false;
auto in_raw_string_literal = false;
std::string raw_string_closing_seq;

auto brace_depth = std::vector<int>();

while (in.getline(&buf[0], max_line_len)) {
Expand All @@ -462,7 +487,7 @@ class source
// Switch to cpp2 mode if we're not in a comment, not inside nested { },
// and the line starts with "nonwhitespace :" but not "::"
//
if (!in_comment && std::ssize(brace_depth) == 0 && starts_with_identifier_colon(lines.back().text))
if (!in_comment && !in_raw_string_literal && std::ssize(brace_depth) == 0 && starts_with_identifier_colon(lines.back().text))
{
cpp2_found= true;

Expand Down Expand Up @@ -506,13 +531,18 @@ class source
lines.back().text,
in_comment,
in_string_literal,
in_raw_string_literal,
raw_string_closing_seq,
brace_depth,
std::ssize(lines) - 1,
errors
);
if (stats.all_comment_line) {
lines.back().cat = source_line::category::comment;
}
else if (stats.all_rawstring_line) {
lines.back().cat = source_line::category::rawstring;
}
else if (stats.empty_line) {
lines.back().cat = source_line::category::empty;
}
Expand Down