llvm/lib/Support/StringExtras.cpp

   1 //===-- StringExtras.cpp - Implement the StringExtras header --------------===//
   2 //
   3 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
   4 // See https://llvm.org/LICENSE.txt for license information.
   5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
   6 //
   7 //===----------------------------------------------------------------------===//
   8 //
   9 // This file implements the StringExtras.h header
  10 //
  11 //===----------------------------------------------------------------------===//
  12
  13 #include "llvm/ADT/StringExtras.h"
  14 #include "llvm/ADT/SmallVector.h"
  15 #include "llvm/Support/raw_ostream.h"
  16 #include <cctype>
  17
  18 using namespace llvm;
  19
  20 /// StrInStrNoCase - Portable version of strcasestr.  Locates the first
  21 /// occurrence of string 's1' in string 's2', ignoring case.  Returns
  22 /// the offset of s2 in s1 or npos if s2 cannot be found.
  23 StringRef::size_type llvm::StrInStrNoCase(StringRef s1, StringRef s2) {
  24   size_t N = s2.size(), M = s1.size();
  25   if (N > M)
  26     return StringRef::npos;
  27   for (size_t i = 0, e = M - N + 1; i != e; ++i)
  28     if (s1.substr(i, N).equals_insensitive(s2))
  29       return i;
  30   return StringRef::npos;
  31 }
  32
  33 /// getToken - This function extracts one token from source, ignoring any
  34 /// leading characters that appear in the Delimiters string, and ending the
  35 /// token at any of the characters that appear in the Delimiters string.  If
  36 /// there are no tokens in the source string, an empty string is returned.
  37 /// The function returns a pair containing the extracted token and the
  38 /// remaining tail string.
  39 std::pair<StringRef, StringRef> llvm::getToken(StringRef Source,
  40                                                StringRef Delimiters) {
  41   // Figure out where the token starts.
  42   StringRef::size_type Start = Source.find_first_not_of(Delimiters);
  43
  44   // Find the next occurrence of the delimiter.
  45   StringRef::size_type End = Source.find_first_of(Delimiters, Start);
  46
  47   return std::make_pair(Source.slice(Start, End), Source.substr(End));
  48 }
  49
  50 /// SplitString - Split up the specified string according to the specified
  51 /// delimiters, appending the result fragments to the output list.
  52 void llvm::SplitString(StringRef Source,
  53                        SmallVectorImpl<StringRef> &OutFragments,
  54                        StringRef Delimiters) {
  55   std::pair<StringRef, StringRef> S = getToken(Source, Delimiters);
  56   while (!S.first.empty()) {
  57     OutFragments.push_back(S.first);
  58     S = getToken(S.second, Delimiters);
  59   }
  60 }
  61
  62 void llvm::printEscapedString(StringRef Name, raw_ostream &Out) {
  63   for (unsigned char C : Name) {
  64     if (C == '\\')
  65       Out << '\\' << C;
  66     else if (isPrint(C) && C != '"')
  67       Out << C;
  68     else
  69       Out << '\\' << hexdigit(C >> 4) << hexdigit(C & 0x0F);
  70   }
  71 }
  72
  73 void llvm::printHTMLEscaped(StringRef String, raw_ostream &Out) {
  74   for (char C : String) {
  75     if (C == '&')
  76       Out << "&amp;";
  77     else if (C == '<')
  78       Out << "&lt;";
  79     else if (C == '>')
  80       Out << "&gt;";
  81     else if (C == '\"')
  82       Out << "&quot;";
  83     else if (C == '\'')
  84       Out << "&apos;";
  85     else
  86       Out << C;
  87   }
  88 }
  89
  90 void llvm::printLowerCase(StringRef String, raw_ostream &Out) {
  91   for (const char C : String)
  92     Out << toLower(C);
  93 }
  94
  95 std::string llvm::convertToSnakeFromCamelCase(StringRef input) {
  96   if (input.empty())
  97     return "";
  98
  99   std::string snakeCase;
 100   snakeCase.reserve(input.size());
 101   auto check = [&input](size_t j, function_ref<bool(int)> predicate) {
 102     return j < input.size() && predicate(input[j]);
 103   };
 104   for (size_t i = 0; i < input.size(); ++i) {
 105     snakeCase.push_back(tolower(input[i]));
 106     // Handles "runs" of capitals, such as in OPName -> op_name.
 107     if (check(i, isupper) && check(i + 1, isupper) && check(i + 2, islower))
 108       snakeCase.push_back('_');
 109     if ((check(i, islower) || check(i, isdigit)) && check(i + 1, isupper))
 110       snakeCase.push_back('_');
 111   }
 112   return snakeCase;
 113 }
 114
 115 std::string llvm::convertToCamelFromSnakeCase(StringRef input,
 116                                               bool capitalizeFirst) {
 117   if (input.empty())
 118     return "";
 119
 120   std::string output;
 121   output.reserve(input.size());
 122
 123   // Push the first character, capatilizing if necessary.
 124   if (capitalizeFirst && std::islower(input.front()))
 125     output.push_back(llvm::toUpper(input.front()));
 126   else
 127     output.push_back(input.front());
 128
 129   // Walk the input converting any `*_[a-z]` snake case into `*[A-Z]` camelCase.
 130   for (size_t pos = 1, e = input.size(); pos < e; ++pos) {
 131     if (input[pos] == '_' && pos != (e - 1) && std::islower(input[pos + 1]))
 132       output.push_back(llvm::toUpper(input[++pos]));
 133     else
 134       output.push_back(input[pos]);
 135   }
 136   return output;
 137 }