[libc] Wchar Stringconverter

libc/src/__support/wchar/CMakeLists.txt

@@ -6,6 +6,19 @@ add_header_library(
     libc.hdr.types.char32_t    
 )
 
+add_header_library(
+  string_converter
+  HDRS
+    string_converter.h
+  DEPENDS
+    libc.hdr.types.char8_t
+    libc.hdr.types.char32_t
+    libc.hdr.types.size_t
+    libc.src.__support.error_or
+    .mbstate
+    .character_converter 
+)
+
 add_object_library(
   character_converter
   HDRS

libc/src/__support/wchar/character_converter.cpp

@@ -14,6 +14,7 @@
 #include "src/__support/error_or.h"
 #include "src/__support/math_extras.h"
 #include "src/__support/wchar/mbstate.h"
+#include <stddef.h>
 
 #include "character_converter.h"
 
@@ -92,6 +93,7 @@ int CharacterConverter::push(char8_t utf8_byte) {
     state->bytes_stored++;
     return 0;
   }
+
   // Invalid byte -> reset the state
   clear();
   return EILSEQ;
@@ -130,6 +132,12 @@ ErrorOr<char32_t> CharacterConverter::pop_utf32() {
   return utf32;
 }
 
+size_t CharacterConverter::sizeAsUTF32() {
+  return 1; // a single utf-32 value can fit an entire character
+}
+
+size_t CharacterConverter::sizeAsUTF8() { return state->total_bytes; }
+
 ErrorOr<char8_t> CharacterConverter::pop_utf8() {
   if (isEmpty())
     return Error(-1);
@@ -156,6 +164,9 @@ ErrorOr<char8_t> CharacterConverter::pop_utf8() {
   }
 
   state->bytes_stored--;
+  if (state->bytes_stored == 0)
+    clear();
+
   return static_cast<char8_t>(output);
 }
 

libc/src/__support/wchar/character_converter.h

@@ -14,6 +14,7 @@
 #include "src/__support/common.h"
 #include "src/__support/error_or.h"
 #include "src/__support/wchar/mbstate.h"
+#include <stddef.h>
 
 namespace LIBC_NAMESPACE_DECL {
 namespace internal {
@@ -30,6 +31,9 @@ class CharacterConverter {
   bool isEmpty();
   bool isValidState();
 
+  size_t sizeAsUTF32();
+  size_t sizeAsUTF8();
+
   int push(char8_t utf8_byte);
   int push(char32_t utf32);
 

libc/src/__support/wchar/string_converter.h

@@ -0,0 +1,113 @@
+//===-- Definition of a class for mbstate_t and conversion -----*-- 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_SRC___SUPPORT_STRING_CONVERTER_H
+#define LLVM_LIBC_SRC___SUPPORT_STRING_CONVERTER_H
+
+#include "hdr/types/char32_t.h"
+#include "hdr/types/char8_t.h"
+#include "hdr/types/size_t.h"
+#include "src/__support/common.h"
+#include "src/__support/error_or.h"
+#include "src/__support/wchar/character_converter.h"
+#include "src/__support/wchar/mbstate.h"
+
+namespace LIBC_NAMESPACE_DECL {
+namespace internal {
+
+template <typename T> class StringConverter {
+private:
+  CharacterConverter cr;
+  const T *src;
+  size_t src_len;
+  size_t src_idx;
+  size_t bytes_pushed;
+  size_t num_to_write;
+
+  int pushFullCharacter() {
+    for (bytes_pushed = 0; !cr.isFull() && src_idx + bytes_pushed < src_len;
+         ++bytes_pushed) {
+      int err = cr.push(src[src_idx + bytes_pushed]);
+      if (err != 0)
+        return err;
+    }
+
+    // if we aren't able to read a full character from the source string
+    if (src_idx + bytes_pushed == src_len && !cr.isFull()) {
+      src_idx += bytes_pushed;
+      return -1;
+    }
+
+    return 0;
+  }
+
+public:
+  StringConverter(const T *s, size_t srclen, size_t dstlen, mbstate *ps)
+      : cr(ps), src(s), src_len(srclen), src_idx(0), bytes_pushed(0),
+        num_to_write(dstlen) {
+    pushFullCharacter();
+  }
+
+  StringConverter(const T *s, size_t dstlen, mbstate *ps)
+      : StringConverter(s, SIZE_MAX, dstlen, ps) {}
+
+  ErrorOr<char32_t> popUTF32() {
+    if (cr.isEmpty()) {
+      int err = pushFullCharacter();
+      if (err != 0)
+        return Error(err);
+
+      if (cr.sizeAsUTF32() > num_to_write) {
+        cr.clear();
+        return Error(-1);
+      }
+    }
+
+    auto out = cr.pop_utf32();
+    if (cr.isEmpty())
+      src_idx += bytes_pushed;
+
+    if (out.has_value() && out.value() == L'\0')
+      src_len = src_idx;
+
+    num_to_write--;
+
+    return out;
+  }
+
+  ErrorOr<char8_t> popUTF8() {
+    if (cr.isEmpty()) {
+      int err = pushFullCharacter();
+      if (err != 0)
+        return Error(err);
+
+      if (cr.sizeAsUTF8() > num_to_write) {
+        cr.clear();
+        return Error(-1);
+      }
+    }
+
+    auto out = cr.pop_utf8();
+    if (cr.isEmpty())
+      src_idx += bytes_pushed;
+
+    if (out.has_value() && out.value() == '\0')
+      src_len = src_idx;
+
+    num_to_write--;
+
+    return out;
+  }
+
+  size_t getSourceIndex() { return src_idx; }
+};
+
+} // namespace internal
+} // namespace LIBC_NAMESPACE_DECL
+
+#endif // LLVM_LIBC_SRC___SUPPORT_STRING_CONVERTER_H

libc/test/src/__support/wchar/CMakeLists.txt

@@ -19,3 +19,17 @@ add_libc_test(
   DEPENDS
     libc.src.__support.wchar.character_converter
 )
+
+add_libc_test(
+  string_converter_test.cpp
+  SUITE
+    libc-support-tests
+  SRCS
+    string_converter_test.cpp
+  DEPENDS
+    libc.src.__support.wchar.string_converter
+    libc.src.__support.wchar.mbstate
+    libc.src.__support.error_or
+    libc.hdr.errno_macros
+    libc.hdr.types.char32_t
+)