Pull wmain -> main code from qpdf.cc into QUtil.cc

Jay Berkenbilt
1 parent ab4061f1
Showing 6 changed files with 67 additions and 30 deletions
ChangeLog
include/qpdf/QUtil.hh
libqpdf/QUtil.cc
libtests/qtest/qutil/qutil.out
libtests/qutil.cc
qpdf/qpdf.cc
+2020-01-14  Jay Berkenbilt  <ejb@ql.org>
+
+	* Add QUtil::call_main_from_wmain, a helper function that can be
+	called in the body of wmain to convert UTF-16 arguments to UTF-8
+	arguments and then call another main function.
+
 2020-01-13  Jay Berkenbilt  <ejb@ql.org>
  
 	* QUtil::read_lines_from_file: add new versions that use FILE*,
@@ -362,6 +362,13 @@ namespace QUtil
     // command-line tool. May throw std::runtime_error.
     QPDF_DLL
     std::vector<int> parse_numrange(char const* range, int max);
+
+    // Take an argv array consisting of wchar_t, as when wmain is
+    // invoked, convert all UTF-16 encoded strings to UTF-8, and call
+    // another main.
+    QPDF_DLL
+    int call_main_from_wmain(int argc, wchar_t* argv[],
+                             std::function<int(int, char*[])> realmain);
 };
  
 #endif // QUTIL_HH
@@ -23,6 +23,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <fcntl.h>
+#include <memory>
 #ifdef _WIN32
 #include <windows.h>
 #include <direct.h>
@@ -2361,3 +2362,38 @@ QUtil::possible_repaired_encodings(std::string supplied)
     }
     return t;
 }
+
+int
+QUtil::call_main_from_wmain(int argc, wchar_t* argv[], std::function<int(int, char*[])> realmain)
+{
+    // argv contains UTF-16-encoded strings with a 16-bit wchar_t.
+    // Convert this to UTF-8-encoded strings for compatibility with
+    // other systems. That way the rest of qpdf.cc can just act like
+    // arguments are UTF-8.
+
+    std::vector<std::shared_ptr<char>> utf8_argv;
+    for (int i = 0; i < argc; ++i)
+    {
+        std::string utf16;
+        for (size_t j = 0; j < wcslen(argv[i]); ++j)
+        {
+            unsigned short codepoint = static_cast<unsigned short>(argv[i][j]);
+            utf16.append(1, static_cast<char>(
+                             QIntC::to_uchar(codepoint >> 8)));
+            utf16.append(1, static_cast<char>(
+                             QIntC::to_uchar(codepoint & 0xff)));
+        }
+        std::string utf8 = QUtil::utf16_to_utf8(utf16);
+        utf8_argv.push_back(std::shared_ptr<char>(QUtil::copy_string(utf8.c_str()), std::default_delete<char[]>()));
+    }
+    auto utf8_argv_sp =
+        std::shared_ptr<char*>(new char*[1+utf8_argv.size()], std::default_delete<char*[]>());
+    char** new_argv = utf8_argv_sp.get();
+    for (size_t i = 0; i < utf8_argv.size(); ++i)
+    {
+        new_argv[i] = utf8_argv.at(i).get();
+    }
+    argc = QIntC::to_int(utf8_argv.size());
+    new_argv[argc] = 0;
+    return realmain(argc, new_argv);
+}
@@ -105,3 +105,7 @@ rename file
 create file
 rename over existing
 delete file
+---- wmain
+ascii
+10 ÷ 2 = 5
+qwww÷π
@@ -543,6 +543,17 @@ void rename_delete_test()
     assert_no_file("old\xcf\x80.~tmp");
 }
  
+void wmain_test()
+{
+    auto realmain = [](int argc, char* argv[]) {
+                        for (int i = 0; i < argc; ++i) { std::cout << argv[i] << std::endl; } return 0; };
+    wchar_t* argv[3];
+    argv[0] = const_cast<wchar_t*>(L"ascii");
+    argv[1] = const_cast<wchar_t*>(L"10 \xf7 2 = 5");
+    argv[2] = const_cast<wchar_t*>(L"qwww\xf7\x03c0");
+    QUtil::call_main_from_wmain(3, argv, realmain);
+}
+
 int main(int argc, char* argv[])
 {
     try
@@ -573,6 +584,8 @@ int main(int argc, char* argv[])
 	hex_encode_decode_test();
 	std::cout << "---- rename/delete" << std::endl;
 	rename_delete_test();
+	std::cout << "---- wmain" << std::endl;
+	wmain_test();
     }
     catch (std::exception& e)
     {
@@ -5304,36 +5304,7 @@ int realmain(int argc, char* argv[])
 extern "C"
 int wmain(int argc, wchar_t* argv[])
 {
-    // If wmain is supported, argv contains UTF-16-encoded strings
-    // with a 16-bit wchar_t. Convert this to UTF-8-encoded strings
-    // for compatibility with other systems. That way the rest of
-    // qpdf.cc can just act like arguments are UTF-8.
-    std::vector<PointerHolder<char> > utf8_argv;
-    for (int i = 0; i < argc; ++i)
-    {
-        std::string utf16;
-        for (size_t j = 0; j < wcslen(argv[i]); ++j)
-        {
-            unsigned short codepoint = static_cast<unsigned short>(argv[i][j]);
-            utf16.append(1, static_cast<char>(
-                             QIntC::to_uchar(codepoint >> 8)));
-            utf16.append(1, static_cast<char>(
-                             QIntC::to_uchar(codepoint & 0xff)));
-        }
-        std::string utf8 = QUtil::utf16_to_utf8(utf16);
-        utf8_argv.push_back(
-            PointerHolder<char>(true, QUtil::copy_string(utf8.c_str())));
-    }
-    PointerHolder<char*> utf8_argv_ph =
-        PointerHolder<char*>(true, new char*[1+utf8_argv.size()]);
-    char** new_argv = utf8_argv_ph.getPointer();
-    for (size_t i = 0; i < utf8_argv.size(); ++i)
-    {
-        new_argv[i] = utf8_argv.at(i).getPointer();
-    }
-    argc = QIntC::to_int(utf8_argv.size());
-    new_argv[argc] = 0;
-    return realmain(argc, new_argv);
+    return QUtil::call_main_from_wmain(argc, argv, realmain);
 }
  
 #else