Files
carbon-lang/common/string_helpers.cpp
T
8d0f3364d8 Initial implementation of raw string literals (#1304)
* test cases for raw string literals

* raw string literal implementation

* match as block string if starting with triple ", and better error message for simple string

except for *#"""#*

* fix broken test case

block string  literal cannot be one line

* test cases for raw string literals

* raw string literal implementation

* match as block string if starting with triple ", and better error message for simple string

except for *#"""#*

* fix broken test case

block string  literal cannot be one line

* removed unused initial value

* rename flag to indicate multi-line string and remove comment

* use * to get value from std::optional

* clean-ups

* removed skip_scan flag and directly return in case of a single line string starting with #+\'\'\'

* Updated error message: simple string -> single-line string.

Co-authored-by: josh11b <josh11b@users.noreply.github.com>

* Updated test cases according to changes in error message

* Removed counting_hashtag flag.

* Implemented ScanHelper class to handle scanning

* Fixed explanation of ReadHashTags.

* Addressed PR comment.

* Clarify that scan_helper holds the source text.

* Addressed PR comments.

* Updated error messages in test cases.

* Added const keyword to return type of GetCurrentStr().

* addressed PR comments.

1. Moved ScanHelper class to lex_scan_helper.h and lex_scan_helper.cpp.
2. Moved ReadHashTags and Process* functions to lex_scan_helper.cpp. Moved YY_USER_ACTION, SIMPLE_TOKEN and ARG_TOKEN to lex_helper.h. Added a wrapper function YyinputWrapper to call static function yyinput in lexer.lpp.
3. Renamed ScanHelper with StringLexHelper.
4. Modified BUILD accordingly.
5. Renamed data members and functions.

* Addressed PR comments.

1. Adjusted order to keep ret usage close.
2. Used resize to construct the string to avoid creation of temp string.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Removed the multi_line flag and skip_read field to improve readability.

* Copied default parameter value to definition of UnescapeStringLiteral.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Copied default parameter value to definition of ParseBlockStringLiteral.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Prefix CARBON_ to SIMPLE_TOKEN and ARG_TOKEN macros.

* Rollback redefinition of arguments.

* Updated comment on the flex macro.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Updated wording.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Moved the EOF error out of the loop.

* Removed duplicated declaration.

* Changed type of `hashtag_num` and `leading_quotes` to int.

* Minor fix: string copy.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Added comment on YyinputWrapper.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Garmmar in comment.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

* Added check of eof before readling next char.

* Minor updates based on PR comments.

* Minor changes to address PR comments.

* Used a clearer way to calculate `hashtag_num` and `leading_quotes`. Switched back to indicate muti-line string with a flag.

* Directly copy StringRef for compilation error message.

* Make str_with_quote const as we don't change it.

Co-authored-by: josh11b <josh11b@users.noreply.github.com>

* Added TODO for unsupported cases.

* Fixed a typo.

Co-authored-by: Jon Ross-Perkins <jperkins@google.com>

Co-authored-by: josh11b <josh11b@users.noreply.github.com>
Co-authored-by: Jon Ross-Perkins <jperkins@google.com>
2022-06-22 15:38:47 -07:00

172 lines
5.2 KiB
C++

// Part of the Carbon Language project, under the Apache License v2.0 with LLVM
// Exceptions. See /LICENSE for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#include "common/string_helpers.h"
#include <algorithm>
#include <optional>
#include "common/check.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringRef.h"
namespace Carbon {
static constexpr llvm::StringRef TripleQuotes = R"(""")";
static constexpr llvm::StringRef HorizontalWhitespaceChars = " \t";
// Carbon only takes uppercase hex input.
static auto FromHex(char c) -> std::optional<char> {
if (c >= '0' && c <= '9') {
return c - '0';
}
if (c >= 'A' && c <= 'F') {
return 10 + c - 'A';
}
return std::nullopt;
}
auto UnescapeStringLiteral(llvm::StringRef source, const int hashtag_num,
bool is_block_string) -> std::optional<std::string> {
std::string ret;
ret.reserve(source.size());
std::string escape = "\\";
escape.resize(hashtag_num + 1, '#');
size_t i = 0;
while (i < source.size()) {
char c = source[i];
if (i + hashtag_num < source.size() &&
source.slice(i, i + hashtag_num + 1).equals(escape)) {
i += hashtag_num + 1;
if (i == source.size()) {
return std::nullopt;
}
switch (source[i]) {
case 'n':
ret.push_back('\n');
break;
case 'r':
ret.push_back('\r');
break;
case 't':
ret.push_back('\t');
break;
case '0':
if (i + 1 < source.size() && llvm::isDigit(source[i + 1])) {
// \0[0-9] is reserved.
return std::nullopt;
}
ret.push_back('\0');
break;
case '"':
ret.push_back('"');
break;
case '\'':
ret.push_back('\'');
break;
case '\\':
ret.push_back('\\');
break;
case 'x': {
i += 2;
if (i >= source.size()) {
return std::nullopt;
}
std::optional<char> c1 = FromHex(source[i - 1]);
std::optional<char> c2 = FromHex(source[i]);
if (c1 == std::nullopt || c2 == std::nullopt) {
return std::nullopt;
}
ret.push_back(16 * *c1 + *c2);
break;
}
case 'u':
CARBON_FATAL() << "\\u is not yet supported in string literals";
case '\n':
if (!is_block_string) {
return std::nullopt;
}
break;
default:
// Unsupported.
return std::nullopt;
}
} else if (c == '\t') {
// Disallow non-` ` horizontal whitespace:
// https://github.com/carbon-language/carbon-lang/blob/trunk/docs/design/lexical_conventions/whitespace.md
// TODO: This doesn't handle unicode whitespace.
return std::nullopt;
} else {
ret.push_back(c);
}
++i;
}
return ret;
}
auto ParseBlockStringLiteral(llvm::StringRef source, const int hashtag_num)
-> ErrorOr<std::string> {
llvm::SmallVector<llvm::StringRef> lines;
source.split(lines, '\n', /*MaxSplit=*/-1, /*KeepEmpty=*/true);
if (lines.size() < 2) {
return Error("Too few lines");
}
llvm::StringRef first = lines[0];
if (!first.consume_front(TripleQuotes)) {
return Error("Should start with triple quotes: " + first);
}
first = first.rtrim(HorizontalWhitespaceChars);
// Remaining chars, if any, are a file type indicator.
if (first.find_first_of("\"#") != llvm::StringRef::npos ||
first.find_first_of(HorizontalWhitespaceChars) != llvm::StringRef::npos) {
return Error("Invalid characters in file type indicator: " + first);
}
llvm::StringRef last = lines[lines.size() - 1];
const size_t last_length = last.size();
last = last.ltrim(HorizontalWhitespaceChars);
const size_t indent = last_length - last.size();
if (last != TripleQuotes) {
return Error("Should end with triple quotes: " + last);
}
std::string parsed;
for (size_t i = 1; i < lines.size() - 1; ++i) {
llvm::StringRef line = lines[i];
const size_t first_non_ws =
line.find_first_not_of(HorizontalWhitespaceChars);
if (first_non_ws == llvm::StringRef::npos) {
// Empty or whitespace-only line.
line = "";
} else {
if (first_non_ws < indent) {
return Error("Wrong indent for line: " + line + ", expected " +
llvm::Twine(indent));
}
line = line.drop_front(indent).rtrim(HorizontalWhitespaceChars);
}
// Unescaping with \n appended to handle things like \\<newline>.
llvm::SmallVector<char> buffer;
std::optional<std::string> unescaped =
UnescapeStringLiteral((line + "\n").toStringRef(buffer), hashtag_num,
/*is_block_string=*/true);
if (!unescaped.has_value()) {
return Error("Invalid escaping in " + line);
}
// A \<newline> string collapses into nothing.
if (!unescaped->empty()) {
parsed.append(*unescaped);
}
}
return parsed;
}
auto StringRefContainsPointer(llvm::StringRef ref, const char* ptr) -> bool {
auto le = std::less_equal<const char*>();
return le(ref.begin(), ptr) && le(ptr, ref.end());
}
} // namespace Carbon