lsp: handle line-endings appropriately (#3318)

Author: xTVaser

CMakePresets.json

@@ -108,6 +108,16 @@
       "description": "Build with Clang with Debug Symbols",
       "inherits": ["base-windows-debug", "base-clang"]
     },
+    {
+      "name": "Debug-windows-clang-static",
+      "displayName": "Windows Static Debug (clang)",
+      "description": "Build with Clang as Debug but statically linked",
+      "inherits": ["base-windows-debug", "base-clang"],
+      "cacheVariables": {
+        "STATICALLY_LINK": "true",
+        "ZYDIS_BUILD_SHARED_LIB": "OFF"
+      }
+    },
     {
       "name": "RelWithDebInfo-windows-clang",
       "displayName": "Windows RelWithDebInfo (clang)",

common/util/FileUtil.cpp

@@ -706,4 +706,24 @@ std::string make_screenshot_filepath(const GameVersion game_version, const std::
   return file_path;
 }
 
+std::string get_majority_file_line_endings(const std::string& file_contents) {
+  size_t lf_count = 0;
+  size_t crlf_count = 0;
+
+  for (size_t i = 0; i < file_contents.size(); ++i) {
+    if (file_contents[i] == '\n') {
+      if (i > 0 && file_contents[i - 1] == '\r') {
+        crlf_count++;
+      } else {
+        lf_count++;
+      }
+    }
+  }
+
+  if (crlf_count > lf_count) {
+    return "\r\n";
+  }
+  return "\n";
+}
+
 }  // namespace file_util

common/util/FileUtil.h

@@ -69,4 +69,5 @@ std::vector<fs::path> sort_filepaths(const std::vector<fs::path>& paths, const b
 /// Will overwrite the destination if it exists
 void copy_file(const fs::path& src, const fs::path& dst);
 std::string make_screenshot_filepath(const GameVersion game_version, const std::string& name = "");
+std::string get_majority_file_line_endings(const std::string& file_contents);
 }  // namespace file_util

common/util/string_util.cpp

@@ -102,6 +102,22 @@ std::vector<std::string> split(const ::std::string& str, char delimiter) {
   return google_diff::split_string(str, delimiter);
 }
 
+std::vector<std::string> split_string(const std::string& str, const std::string& delimiter) {
+  std::vector<std::string> parsed;
+  std::string::size_type pos = 0;
+  while (true) {
+    const std::string::size_type found = str.find(delimiter, pos);
+    if (found == std::string::npos) {
+      parsed.push_back(str.substr(pos));
+      break;
+    } else {
+      parsed.push_back(str.substr(pos, found - pos));
+      pos = found + delimiter.length();
+    }
+  }
+  return parsed;
+}
+
 std::vector<std::string> regex_get_capture_groups(const std::string& str,
                                                   const std::string& regex) {
   std::vector<std::string> groups;

common/util/string_util.h

@@ -18,7 +18,9 @@ int line_count(const std::string& str);
 bool valid_regex(const std::string& regex);
 std::string diff(const std::string& lhs, const std::string& rhs);
 /// Default splits on \n characters
+/// DEPRECATED - stop using it, limited as it only takes a char
 std::vector<std::string> split(const ::std::string& str, char delimiter = '\n');
+std::vector<std::string> split_string(const std::string& str, const std::string& delimiter = "\n");
 std::string join(const std::vector<std::string>& strs, const std::string& join_with);
 std::vector<std::string> regex_get_capture_groups(const std::string& str, const std::string& regex);
 bool replace(std::string& str, const std::string& from, const std::string& to);

lsp/state/workspace.cpp

@@ -295,7 +295,8 @@ void Workspace::stop_tracking_file(const LSPSpec::DocumentUri& file_uri) {
 
 WorkspaceOGFile::WorkspaceOGFile(const std::string& content, const GameVersion& game_version)
     : m_content(content), m_game_version(game_version) {
-  m_lines = str_util::split(content);
+  const auto line_ending = file_util::get_majority_file_line_endings(content);
+  m_lines = str_util::split_string(content, line_ending);
   lg::info("Added new OG file. {} lines with {} symbols and {} diagnostics", m_lines.size(),
            m_symbols.size(), m_diagnostics.size());
 }
@@ -322,24 +323,17 @@ std::optional<std::string> WorkspaceOGFile::get_symbol_at_position(
 }
 
 WorkspaceIRFile::WorkspaceIRFile(const std::string& content) {
-  // Get all lines of file
-  std::string::size_type pos = 0;
-  std::string::size_type prev = 0;
-
-  // TODO - i hate this assignment inside a conditional, get rid of it
-  while ((pos = content.find("\r\n", prev)) != std::string::npos) {
-    std::string line = content.substr(prev, pos - prev);
-    m_lines.push_back(line);
-    // Run any checks on that line
-    find_all_types_path(line);
-    find_function_symbol(m_lines.size() - 1, line);
-    identify_diagnostics(m_lines.size() - 1, line);
-    prev = pos + 1;
+  const auto line_ending = file_util::get_majority_file_line_endings(content);
+  m_lines = str_util::split_string(content, line_ending);
+
+  for (int i = 0; i < m_lines.size(); i++) {
+    const auto& line = m_lines.at(i);
+    if (m_all_types_uri == "") {
+      find_all_types_path(line);
+    }
+    find_function_symbol(i, line);
+    identify_diagnostics(i, line);
   }
-  std::string line = content.substr(prev);
-  m_lines.push_back(line);
-  find_function_symbol(m_lines.size() - 1, line);
-  identify_diagnostics(m_lines.size() - 1, line);
 
   lg::info("Added new IR file. {} lines with {} symbols and {} diagnostics", m_lines.size(),
            m_symbols.size(), m_diagnostics.size());