StringExtras.h | Explore in Territory

//===- llvm/ADT/StringExtras.h - Useful string functions --------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file contains some functions that are useful when dealing with strings.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_ADT_STRINGEXTRAS_H
#define LLVM_ADT_STRINGEXTRAS_H

#include "llvm/ADT/APSInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <cstdlib>
#include <cstring>
#include <iterator>
#include <string>
#include <utility>

namespace llvm {

class raw_ostream;

/// hexdigit - Return the hexadecimal character for the
/// given number \p X (which should be less than 16).
inline char hexdigit(unsigned X, bool LowerCase = false) { … }

/// Given an array of c-style strings terminated by a null pointer, construct
/// a vector of StringRefs representing the same strings without the terminating
/// null string.
inline std::vector<StringRef> toStringRefArray(const char *const *Strings) { … }

/// Construct a string ref from a boolean.
inline StringRef toStringRef(bool B) { … }

/// Construct a string ref from an array ref of unsigned chars.
inline StringRef toStringRef(ArrayRef<uint8_t> Input) { … }
inline StringRef toStringRef(ArrayRef<char> Input) { … }

/// Construct a string ref from an array ref of unsigned chars.
template <class CharT = uint8_t>
inline ArrayRef<CharT> arrayRefFromStringRef(StringRef Input) { … }

/// Interpret the given character \p C as a hexadecimal digit and return its
/// value.
///
/// If \p C is not a valid hex digit, -1U is returned.
inline unsigned hexDigitValue(char C) { … }

/// Checks if character \p C is one of the 10 decimal digits.
inline bool isDigit(char C) { … }

/// Checks if character \p C is a hexadecimal numeric character.
inline bool isHexDigit(char C) { … }

/// Checks if character \p C is a lowercase letter as classified by "C" locale.
inline bool isLower(char C) { … }

/// Checks if character \p C is a uppercase letter as classified by "C" locale.
inline bool isUpper(char C) { … }

/// Checks if character \p C is a valid letter as classified by "C" locale.
inline bool isAlpha(char C) { … }

/// Checks whether character \p C is either a decimal digit or an uppercase or
/// lowercase letter as classified by "C" locale.
inline bool isAlnum(char C) { … }

/// Checks whether character \p C is valid ASCII (high bit is zero).
inline bool isASCII(char C) { … }

/// Checks whether all characters in S are ASCII.
inline bool isASCII(llvm::StringRef S) { … }

/// Checks whether character \p C is printable.
///
/// Locale-independent version of the C standard library isprint whose results
/// may differ on different platforms.
inline bool isPrint(char C) { … }

/// Checks whether character \p C is a punctuation character.
///
/// Locale-independent version of the C standard library ispunct. The list of
/// punctuation characters can be found in the documentation of std::ispunct:
/// https://en.cppreference.com/w/cpp/string/byte/ispunct.
inline bool isPunct(char C) { … }

/// Checks whether character \p C is whitespace in the "C" locale.
///
/// Locale-independent version of the C standard library isspace.
inline bool isSpace(char C) { … }

/// Returns the corresponding lowercase character if \p x is uppercase.
inline char toLower(char x) { … }

/// Returns the corresponding uppercase character if \p x is lowercase.
inline char toUpper(char x) { … }

inline std::string utohexstr(uint64_t X, bool LowerCase = false,
                             unsigned Width = 0) { … }

/// Convert buffer \p Input to its hexadecimal representation.
/// The returned string is double the size of \p Input.
inline void toHex(ArrayRef<uint8_t> Input, bool LowerCase,
                  SmallVectorImpl<char> &Output) { … }

inline std::string toHex(ArrayRef<uint8_t> Input, bool LowerCase = false) { … }

inline std::string toHex(StringRef Input, bool LowerCase = false) { … }

/// Store the binary representation of the two provided values, \p MSB and
/// \p LSB, that make up the nibbles of a hexadecimal digit. If \p MSB or \p LSB
/// do not correspond to proper nibbles of a hexadecimal digit, this method
/// returns false. Otherwise, returns true.
inline bool tryGetHexFromNibbles(char MSB, char LSB, uint8_t &Hex) { … }

/// Return the binary representation of the two provided values, \p MSB and
/// \p LSB, that make up the nibbles of a hexadecimal digit.
inline uint8_t hexFromNibbles(char MSB, char LSB) { … }

/// Convert hexadecimal string \p Input to its binary representation and store
/// the result in \p Output. Returns true if the binary representation could be
/// converted from the hexadecimal string. Returns false if \p Input contains
/// non-hexadecimal digits. The output string is half the size of \p Input.
inline bool tryGetFromHex(StringRef Input, std::string &Output) { … }

/// Convert hexadecimal string \p Input to its binary representation.
/// The return string is half the size of \p Input.
inline std::string fromHex(StringRef Input) { … }

/// Convert the string \p S to an integer of the specified type using
/// the radix \p Base.  If \p Base is 0, auto-detects the radix.
/// Returns true if the number was successfully converted, false otherwise.
template <typename N> bool to_integer(StringRef S, N &Num, unsigned Base = 0) { … }

namespace detail {
template <typename N>
inline bool to_float(const Twine &T, N &Num, N (*StrTo)(const char *, char **)) { … }
}

inline bool to_float(const Twine &T, float &Num) { … }

inline bool to_float(const Twine &T, double &Num) { … }

inline bool to_float(const Twine &T, long double &Num) { … }

inline std::string utostr(uint64_t X, bool isNeg = false) { … }

inline std::string itostr(int64_t X) { … }

inline std::string toString(const APInt &I, unsigned Radix, bool Signed,
                            bool formatAsCLiteral = false,
                            bool UpperCase = true,
                            bool InsertSeparators = false) { … }

inline std::string toString(const APSInt &I, unsigned Radix) { … }

/// StrInStrNoCase - Portable version of strcasestr.  Locates the first
/// occurrence of string 's1' in string 's2', ignoring case.  Returns
/// the offset of s2 in s1 or npos if s2 cannot be found.
StringRef::size_type StrInStrNoCase(StringRef s1, StringRef s2);

/// getToken - This function extracts one token from source, ignoring any
/// leading characters that appear in the Delimiters string, and ending the
/// token at any of the characters that appear in the Delimiters string.  If
/// there are no tokens in the source string, an empty string is returned.
/// The function returns a pair containing the extracted token and the
/// remaining tail string.
std::pair<StringRef, StringRef> getToken(StringRef Source,
                                         StringRef Delimiters = " \t\n\v\f\r");

/// SplitString - Split up the specified string according to the specified
/// delimiters, appending the result fragments to the output list.
void SplitString(StringRef Source,
                 SmallVectorImpl<StringRef> &OutFragments,
                 StringRef Delimiters = " \t\n\v\f\r");

/// Returns the English suffix for an ordinal integer (-st, -nd, -rd, -th).
inline StringRef getOrdinalSuffix(unsigned Val) { … }

/// Print each character of the specified string, escaping it if it is not
/// printable or if it is an escape char.
void printEscapedString(StringRef Name, raw_ostream &Out);

/// Print each character of the specified string, escaping HTML special
/// characters.
void printHTMLEscaped(StringRef String, raw_ostream &Out);

/// printLowerCase - Print each character as lowercase if it is uppercase.
void printLowerCase(StringRef String, raw_ostream &Out);

/// Converts a string from camel-case to snake-case by replacing all uppercase
/// letters with '_' followed by the letter in lowercase, except if the
/// uppercase letter is the first character of the string.
std::string convertToSnakeFromCamelCase(StringRef input);

/// Converts a string from snake-case to camel-case by replacing all occurrences
/// of '_' followed by a lowercase letter with the letter in uppercase.
/// Optionally allow capitalization of the first letter (if it is a lowercase
/// letter)
std::string convertToCamelFromSnakeCase(StringRef input,
                                        bool capitalizeFirst = false);

namespace detail {

template <typename IteratorT>
inline std::string join_impl(IteratorT Begin, IteratorT End,
                             StringRef Separator, std::input_iterator_tag) { … }

template <typename IteratorT>
inline std::string join_impl(IteratorT Begin, IteratorT End,
                             StringRef Separator, std::forward_iterator_tag) { … }

template <typename Sep>
inline void join_items_impl(std::string &Result, Sep Separator) { … }

template <typename Sep, typename Arg>
inline void join_items_impl(std::string &Result, Sep Separator,
                            const Arg &Item) { … }

template <typename Sep, typename Arg1, typename... Args>
inline void join_items_impl(std::string &Result, Sep Separator, const Arg1 &A1,
                            Args &&... Items) { … }

inline size_t join_one_item_size(char) { … }
inline size_t join_one_item_size(const char *S) { … }

template <typename T> inline size_t join_one_item_size(const T &Str) { … }

template <typename... Args> inline size_t join_items_size(Args &&...Items) { … }

} // end namespace detail

/// Joins the strings in the range [Begin, End), adding Separator between
/// the elements.
template <typename IteratorT>
inline std::string join(IteratorT Begin, IteratorT End, StringRef Separator) { … }

/// Joins the strings in the range [R.begin(), R.end()), adding Separator
/// between the elements.
template <typename Range>
inline std::string join(Range &&R, StringRef Separator) { … }

/// Joins the strings in the parameter pack \p Items, adding \p Separator
/// between the elements.  All arguments must be implicitly convertible to
/// std::string, or there should be an overload of std::string::operator+=()
/// that accepts the argument explicitly.
template <typename Sep, typename... Args>
inline std::string join_items(Sep Separator, Args &&... Items) { … }

/// A helper class to return the specified delimiter string after the first
/// invocation of operator StringRef().  Used to generate a comma-separated
/// list from a loop like so:
///
/// \code
///   ListSeparator LS;
///   for (auto &I : C)
///     OS << LS << I.getName();
/// \end
class ListSeparator { … };

/// A forward iterator over partitions of string over a separator.
class SplittingIterator
    : public iterator_facade_base<SplittingIterator, std::forward_iterator_tag,
                                  StringRef> { … };

/// Split the specified string over a separator and return a range-compatible
/// iterable over its partitions.  Used to permit conveniently iterating
/// over separated strings like so:
///
/// \code
///   for (StringRef x : llvm::split("foo,bar,baz", ","))
///     ...;
/// \end
///
/// Note that the passed string must remain valid throuhgout lifetime
/// of the iterators.
inline iterator_range<SplittingIterator> split(StringRef Str, StringRef Separator) { … }

inline iterator_range<SplittingIterator> split(StringRef Str, char Separator) { … }

} // end namespace llvm

#endif // LLVM_ADT_STRINGEXTRAS_H
llvm/llvm/include/llvm/ADT/StringExtras.h
