[lldb] [llvm] [lldb-dap][NFC] Add Breakpoint struct to share common logic. (PR #80753)

Zequan Wu via llvm-commits llvm-commits at lists.llvm.org
Wed Feb 7 11:08:33 PST 2024


https://github.com/ZequanWu updated https://github.com/llvm/llvm-project/pull/80753

>From c4b767909a9ffc2a3015dc9021e4c265da0d877d Mon Sep 17 00:00:00 2001
From: Zequan Wu <zequanwu at google.com>
Date: Mon, 5 Feb 2024 17:26:48 -0500
Subject: [PATCH 1/3] [lldb-dap][NFC] Add Breakpoint struct to share common
 logic.

---
 lldb/tools/lldb-dap/Breakpoint.cpp            | 182 ++++++++++++++++++
 lldb/tools/lldb-dap/Breakpoint.h              |  34 ++++
 lldb/tools/lldb-dap/BreakpointBase.cpp        | 113 -----------
 lldb/tools/lldb-dap/BreakpointBase.h          |  12 +-
 lldb/tools/lldb-dap/CMakeLists.txt            |   1 +
 lldb/tools/lldb-dap/FunctionBreakpoint.cpp    |  12 +-
 lldb/tools/lldb-dap/FunctionBreakpoint.h      |   4 +-
 lldb/tools/lldb-dap/JSONUtils.cpp             |  46 +----
 lldb/tools/lldb-dap/JSONUtils.h               |   5 +-
 lldb/tools/lldb-dap/SourceBreakpoint.cpp      |  12 +-
 lldb/tools/lldb-dap/SourceBreakpoint.h        |   6 +-
 lldb/tools/lldb-dap/lldb-dap.cpp              |  17 +-
 .../gn/secondary/lldb/tools/lldb-dap/BUILD.gn |   1 +
 13 files changed, 248 insertions(+), 197 deletions(-)
 create mode 100644 lldb/tools/lldb-dap/Breakpoint.cpp
 create mode 100644 lldb/tools/lldb-dap/Breakpoint.h

diff --git a/lldb/tools/lldb-dap/Breakpoint.cpp b/lldb/tools/lldb-dap/Breakpoint.cpp
new file mode 100644
index 0000000000000..4ccf353b06ccc
--- /dev/null
+++ b/lldb/tools/lldb-dap/Breakpoint.cpp
@@ -0,0 +1,182 @@
+//===-- Breakpoint.cpp ------------------------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "Breakpoint.h"
+#include "DAP.h"
+#include "JSONUtils.h"
+#include "llvm/ADT/StringExtras.h"
+
+using namespace lldb_dap;
+
+void Breakpoint::SetCondition() { bp.SetCondition(condition.c_str()); }
+
+void Breakpoint::SetHitCondition() {
+  uint64_t hitCount = 0;
+  if (llvm::to_integer(hitCondition, hitCount))
+    bp.SetIgnoreCount(hitCount - 1);
+}
+
+// logMessage will be divided into array of LogMessagePart as two kinds:
+// 1. raw print text message, and
+// 2. interpolated expression for evaluation which is inside matching curly
+//    braces.
+//
+// The function tries to parse logMessage into a list of LogMessageParts
+// for easy later access in BreakpointHitCallback.
+void Breakpoint::SetLogMessage() {
+  logMessageParts.clear();
+
+  // Contains unmatched open curly braces indices.
+  std::vector<int> unmatched_curly_braces;
+
+  // Contains all matched curly braces in logMessage.
+  // Loop invariant: matched_curly_braces_ranges are sorted by start index in
+  // ascending order without any overlap between them.
+  std::vector<std::pair<int, int>> matched_curly_braces_ranges;
+
+  lldb::SBError error;
+  // Part1 - parse matched_curly_braces_ranges.
+  // locating all curly braced expression ranges in logMessage.
+  // The algorithm takes care of nested and imbalanced curly braces.
+  for (size_t i = 0; i < logMessage.size(); ++i) {
+    if (logMessage[i] == '{') {
+      unmatched_curly_braces.push_back(i);
+    } else if (logMessage[i] == '}') {
+      if (unmatched_curly_braces.empty())
+        // Nothing to match.
+        continue;
+
+      int last_unmatched_index = unmatched_curly_braces.back();
+      unmatched_curly_braces.pop_back();
+
+      // Erase any matched ranges included in the new match.
+      while (!matched_curly_braces_ranges.empty()) {
+        assert(matched_curly_braces_ranges.back().first !=
+                   last_unmatched_index &&
+               "How can a curley brace be matched twice?");
+        if (matched_curly_braces_ranges.back().first < last_unmatched_index)
+          break;
+
+        // This is a nested range let's earse it.
+        assert((size_t)matched_curly_braces_ranges.back().second < i);
+        matched_curly_braces_ranges.pop_back();
+      }
+
+      // Assert invariant.
+      assert(matched_curly_braces_ranges.empty() ||
+             matched_curly_braces_ranges.back().first < last_unmatched_index);
+      matched_curly_braces_ranges.emplace_back(last_unmatched_index, i);
+    }
+  }
+
+  // Part2 - parse raw text and expresions parts.
+  // All expression ranges have been parsed in matched_curly_braces_ranges.
+  // The code below uses matched_curly_braces_ranges to divide logMessage
+  // into raw text parts and expression parts.
+  int last_raw_text_start = 0;
+  for (const std::pair<int, int> &curly_braces_range :
+       matched_curly_braces_ranges) {
+    // Raw text before open curly brace.
+    assert(curly_braces_range.first >= last_raw_text_start);
+    size_t raw_text_len = curly_braces_range.first - last_raw_text_start;
+    if (raw_text_len > 0) {
+      error = AppendLogMessagePart(
+          llvm::StringRef(logMessage.c_str() + last_raw_text_start,
+                          raw_text_len),
+          /*is_expr=*/false);
+      if (error.Fail()) {
+        NotifyLogMessageError(error.GetCString());
+        return;
+      }
+    }
+
+    // Expression between curly braces.
+    assert(curly_braces_range.second > curly_braces_range.first);
+    size_t expr_len = curly_braces_range.second - curly_braces_range.first - 1;
+    error = AppendLogMessagePart(
+        llvm::StringRef(logMessage.c_str() + curly_braces_range.first + 1,
+                        expr_len),
+        /*is_expr=*/true);
+    if (error.Fail()) {
+      NotifyLogMessageError(error.GetCString());
+      return;
+    }
+
+    last_raw_text_start = curly_braces_range.second + 1;
+  }
+  // Trailing raw text after close curly brace.
+  assert(last_raw_text_start >= 0);
+  if (logMessage.size() > (size_t)last_raw_text_start) {
+    error = AppendLogMessagePart(
+        llvm::StringRef(logMessage.c_str() + last_raw_text_start,
+                        logMessage.size() - last_raw_text_start),
+        /*is_expr=*/false);
+    if (error.Fail()) {
+      NotifyLogMessageError(error.GetCString());
+      return;
+    }
+  }
+
+  bp.SetCallback(BreakpointBase::BreakpointHitCallback, this);
+}
+
+void Breakpoint::CreateJsonObject(llvm::json::Object &object) {
+  // Each breakpoint location is treated as a separate breakpoint for VS code.
+  // They don't have the notion of a single breakpoint with multiple locations.
+  if (!bp.IsValid())
+    return;
+  object.try_emplace("verified", bp.GetNumResolvedLocations() > 0);
+  object.try_emplace("id", bp.GetID());
+  // VS Code DAP doesn't currently allow one breakpoint to have multiple
+  // locations so we just report the first one. If we report all locations
+  // then the IDE starts showing the wrong line numbers and locations for
+  // other source file and line breakpoints in the same file.
+
+  // Below we search for the first resolved location in a breakpoint and report
+  // this as the breakpoint location since it will have a complete location
+  // that is at least loaded in the current process.
+  lldb::SBBreakpointLocation bp_loc;
+  const auto num_locs = bp.GetNumLocations();
+  for (size_t i = 0; i < num_locs; ++i) {
+    bp_loc = bp.GetLocationAtIndex(i);
+    if (bp_loc.IsResolved())
+      break;
+  }
+  // If not locations are resolved, use the first location.
+  if (!bp_loc.IsResolved())
+    bp_loc = bp.GetLocationAtIndex(0);
+  auto bp_addr = bp_loc.GetAddress();
+
+  if (bp_addr.IsValid()) {
+    std::string formatted_addr =
+        "0x" + llvm::utohexstr(bp_addr.GetLoadAddress(g_dap.target));
+    object.try_emplace("instructionReference", formatted_addr);
+    auto line_entry = bp_addr.GetLineEntry();
+    const auto line = line_entry.GetLine();
+    if (line != UINT32_MAX)
+      object.try_emplace("line", line);
+    const auto column = line_entry.GetColumn();
+    if (column != 0)
+      object.try_emplace("column", column);
+    object.try_emplace("source", CreateSource(line_entry));
+  }
+}
+
+bool Breakpoint::MatchesName(const char *name) { return bp.MatchesName(name); }
+
+void Breakpoint::SetBreakpoint() {
+  // See comments in BreakpointBase::GetBreakpointLabel() for details of why
+  // we add a label to our breakpoints.
+  bp.AddName(GetBreakpointLabel());
+  if (!condition.empty())
+    SetCondition();
+  if (!hitCondition.empty())
+    SetHitCondition();
+  if (!logMessage.empty())
+    SetLogMessage();
+}
diff --git a/lldb/tools/lldb-dap/Breakpoint.h b/lldb/tools/lldb-dap/Breakpoint.h
new file mode 100644
index 0000000000000..a668e29f3d1e8
--- /dev/null
+++ b/lldb/tools/lldb-dap/Breakpoint.h
@@ -0,0 +1,34 @@
+//===-- Breakpoint.h --------------------------------------------*- 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 LLDB_TOOLS_LLDB_DAP_BREAKPOINT_H
+#define LLDB_TOOLS_LLDB_DAP_BREAKPOINT_H
+
+#include "BreakpointBase.h"
+
+namespace lldb_dap {
+
+struct Breakpoint : public BreakpointBase {
+  // The LLDB breakpoint associated wit this source breakpoint
+  lldb::SBBreakpoint bp;
+
+  Breakpoint() = default;
+  Breakpoint(const llvm::json::Object &obj) : BreakpointBase(obj){};
+  Breakpoint(lldb::SBBreakpoint bp): bp(bp) {}
+
+  void SetCondition() override;
+  void SetHitCondition() override;
+  void SetLogMessage() override;
+  void CreateJsonObject(llvm::json::Object &object) override;
+
+  bool MatchesName(const char *name);
+  void SetBreakpoint();
+};
+} // namespace lldb_dap
+
+#endif
diff --git a/lldb/tools/lldb-dap/BreakpointBase.cpp b/lldb/tools/lldb-dap/BreakpointBase.cpp
index fb4b27fbe315f..088ccc6b27f8e 100644
--- a/lldb/tools/lldb-dap/BreakpointBase.cpp
+++ b/lldb/tools/lldb-dap/BreakpointBase.cpp
@@ -8,7 +8,6 @@
 
 #include "BreakpointBase.h"
 #include "DAP.h"
-#include "JSONUtils.h"
 #include "llvm/ADT/StringExtras.h"
 
 using namespace lldb_dap;
@@ -18,14 +17,6 @@ BreakpointBase::BreakpointBase(const llvm::json::Object &obj)
       hitCondition(std::string(GetString(obj, "hitCondition"))),
       logMessage(std::string(GetString(obj, "logMessage"))) {}
 
-void BreakpointBase::SetCondition() { bp.SetCondition(condition.c_str()); }
-
-void BreakpointBase::SetHitCondition() {
-  uint64_t hitCount = 0;
-  if (llvm::to_integer(hitCondition, hitCount))
-    bp.SetIgnoreCount(hitCount - 1);
-}
-
 lldb::SBError BreakpointBase::AppendLogMessagePart(llvm::StringRef part,
                                                    bool is_expr) {
   if (is_expr) {
@@ -164,110 +155,6 @@ lldb::SBError BreakpointBase::FormatLogText(llvm::StringRef text,
   return error;
 }
 
-// logMessage will be divided into array of LogMessagePart as two kinds:
-// 1. raw print text message, and
-// 2. interpolated expression for evaluation which is inside matching curly
-//    braces.
-//
-// The function tries to parse logMessage into a list of LogMessageParts
-// for easy later access in BreakpointHitCallback.
-void BreakpointBase::SetLogMessage() {
-  logMessageParts.clear();
-
-  // Contains unmatched open curly braces indices.
-  std::vector<int> unmatched_curly_braces;
-
-  // Contains all matched curly braces in logMessage.
-  // Loop invariant: matched_curly_braces_ranges are sorted by start index in
-  // ascending order without any overlap between them.
-  std::vector<std::pair<int, int>> matched_curly_braces_ranges;
-
-  lldb::SBError error;
-  // Part1 - parse matched_curly_braces_ranges.
-  // locating all curly braced expression ranges in logMessage.
-  // The algorithm takes care of nested and imbalanced curly braces.
-  for (size_t i = 0; i < logMessage.size(); ++i) {
-    if (logMessage[i] == '{') {
-      unmatched_curly_braces.push_back(i);
-    } else if (logMessage[i] == '}') {
-      if (unmatched_curly_braces.empty())
-        // Nothing to match.
-        continue;
-
-      int last_unmatched_index = unmatched_curly_braces.back();
-      unmatched_curly_braces.pop_back();
-
-      // Erase any matched ranges included in the new match.
-      while (!matched_curly_braces_ranges.empty()) {
-        assert(matched_curly_braces_ranges.back().first !=
-                   last_unmatched_index &&
-               "How can a curley brace be matched twice?");
-        if (matched_curly_braces_ranges.back().first < last_unmatched_index)
-          break;
-
-        // This is a nested range let's earse it.
-        assert((size_t)matched_curly_braces_ranges.back().second < i);
-        matched_curly_braces_ranges.pop_back();
-      }
-
-      // Assert invariant.
-      assert(matched_curly_braces_ranges.empty() ||
-             matched_curly_braces_ranges.back().first < last_unmatched_index);
-      matched_curly_braces_ranges.emplace_back(last_unmatched_index, i);
-    }
-  }
-
-  // Part2 - parse raw text and expresions parts.
-  // All expression ranges have been parsed in matched_curly_braces_ranges.
-  // The code below uses matched_curly_braces_ranges to divide logMessage
-  // into raw text parts and expression parts.
-  int last_raw_text_start = 0;
-  for (const std::pair<int, int> &curly_braces_range :
-       matched_curly_braces_ranges) {
-    // Raw text before open curly brace.
-    assert(curly_braces_range.first >= last_raw_text_start);
-    size_t raw_text_len = curly_braces_range.first - last_raw_text_start;
-    if (raw_text_len > 0) {
-      error = AppendLogMessagePart(
-          llvm::StringRef(logMessage.c_str() + last_raw_text_start,
-                          raw_text_len),
-          /*is_expr=*/false);
-      if (error.Fail()) {
-        NotifyLogMessageError(error.GetCString());
-        return;
-      }
-    }
-
-    // Expression between curly braces.
-    assert(curly_braces_range.second > curly_braces_range.first);
-    size_t expr_len = curly_braces_range.second - curly_braces_range.first - 1;
-    error = AppendLogMessagePart(
-        llvm::StringRef(logMessage.c_str() + curly_braces_range.first + 1,
-                        expr_len),
-        /*is_expr=*/true);
-    if (error.Fail()) {
-      NotifyLogMessageError(error.GetCString());
-      return;
-    }
-
-    last_raw_text_start = curly_braces_range.second + 1;
-  }
-  // Trailing raw text after close curly brace.
-  assert(last_raw_text_start >= 0);
-  if (logMessage.size() > (size_t)last_raw_text_start) {
-    error = AppendLogMessagePart(
-        llvm::StringRef(logMessage.c_str() + last_raw_text_start,
-                        logMessage.size() - last_raw_text_start),
-        /*is_expr=*/false);
-    if (error.Fail()) {
-      NotifyLogMessageError(error.GetCString());
-      return;
-    }
-  }
-
-  bp.SetCallback(BreakpointBase::BreakpointHitCallback, this);
-}
-
 void BreakpointBase::NotifyLogMessageError(llvm::StringRef error) {
   std::string message = "Log message has error: ";
   message += error;
diff --git a/lldb/tools/lldb-dap/BreakpointBase.h b/lldb/tools/lldb-dap/BreakpointBase.h
index 41787f7861021..a4184bfe65d27 100644
--- a/lldb/tools/lldb-dap/BreakpointBase.h
+++ b/lldb/tools/lldb-dap/BreakpointBase.h
@@ -9,7 +9,6 @@
 #ifndef LLDB_TOOLS_LLDB_DAP_BREAKPOINTBASE_H
 #define LLDB_TOOLS_LLDB_DAP_BREAKPOINTBASE_H
 
-#include "JSONUtils.h"
 #include "lldb/API/SBBreakpoint.h"
 #include "llvm/Support/JSON.h"
 #include <string>
@@ -35,15 +34,16 @@ struct BreakpointBase {
   // interpolated.
   std::string logMessage;
   std::vector<LogMessagePart> logMessageParts;
-  // The LLDB breakpoint associated wit this source breakpoint
-  lldb::SBBreakpoint bp;
 
   BreakpointBase() = default;
   BreakpointBase(const llvm::json::Object &obj);
+  virtual ~BreakpointBase() = default;
+
+  virtual void SetCondition() = 0;
+  virtual void SetHitCondition() = 0;
+  virtual void SetLogMessage() = 0;
+  virtual void CreateJsonObject(llvm::json::Object &object) = 0;
 
-  void SetCondition();
-  void SetHitCondition();
-  void SetLogMessage();
   void UpdateBreakpoint(const BreakpointBase &request_bp);
 
   // Format \param text and return formatted text in \param formatted.
diff --git a/lldb/tools/lldb-dap/CMakeLists.txt b/lldb/tools/lldb-dap/CMakeLists.txt
index 554567eb3b0e2..f8c0e4ecf36c2 100644
--- a/lldb/tools/lldb-dap/CMakeLists.txt
+++ b/lldb/tools/lldb-dap/CMakeLists.txt
@@ -24,6 +24,7 @@ tablegen(LLVM Options.inc -gen-opt-parser-defs)
 add_public_tablegen_target(LLDBDAPOptionsTableGen)
 add_lldb_tool(lldb-dap
   lldb-dap.cpp
+  Breakpoint.cpp
   BreakpointBase.cpp
   ExceptionBreakpoint.cpp
   FifoFiles.cpp
diff --git a/lldb/tools/lldb-dap/FunctionBreakpoint.cpp b/lldb/tools/lldb-dap/FunctionBreakpoint.cpp
index d4bdb976500ec..21743bf908706 100644
--- a/lldb/tools/lldb-dap/FunctionBreakpoint.cpp
+++ b/lldb/tools/lldb-dap/FunctionBreakpoint.cpp
@@ -12,21 +12,13 @@
 namespace lldb_dap {
 
 FunctionBreakpoint::FunctionBreakpoint(const llvm::json::Object &obj)
-    : BreakpointBase(obj), functionName(std::string(GetString(obj, "name"))) {}
+    : Breakpoint(obj), functionName(std::string(GetString(obj, "name"))) {}
 
 void FunctionBreakpoint::SetBreakpoint() {
   if (functionName.empty())
     return;
   bp = g_dap.target.BreakpointCreateByName(functionName.c_str());
-  // See comments in BreakpointBase::GetBreakpointLabel() for details of why
-  // we add a label to our breakpoints.
-  bp.AddName(GetBreakpointLabel());
-  if (!condition.empty())
-    SetCondition();
-  if (!hitCondition.empty())
-    SetHitCondition();
-  if (!logMessage.empty())
-    SetLogMessage();
+  Breakpoint::SetBreakpoint();
 }
 
 } // namespace lldb_dap
diff --git a/lldb/tools/lldb-dap/FunctionBreakpoint.h b/lldb/tools/lldb-dap/FunctionBreakpoint.h
index fc23e94e12876..b15ff1931a6b2 100644
--- a/lldb/tools/lldb-dap/FunctionBreakpoint.h
+++ b/lldb/tools/lldb-dap/FunctionBreakpoint.h
@@ -9,11 +9,11 @@
 #ifndef LLDB_TOOLS_LLDB_DAP_FUNCTIONBREAKPOINT_H
 #define LLDB_TOOLS_LLDB_DAP_FUNCTIONBREAKPOINT_H
 
-#include "BreakpointBase.h"
+#include "Breakpoint.h"
 
 namespace lldb_dap {
 
-struct FunctionBreakpoint : public BreakpointBase {
+struct FunctionBreakpoint : public Breakpoint {
   std::string functionName;
 
   FunctionBreakpoint() = default;
diff --git a/lldb/tools/lldb-dap/JSONUtils.cpp b/lldb/tools/lldb-dap/JSONUtils.cpp
index a8b438d9d6df3..878449a91aa66 100644
--- a/lldb/tools/lldb-dap/JSONUtils.cpp
+++ b/lldb/tools/lldb-dap/JSONUtils.cpp
@@ -364,54 +364,14 @@ llvm::json::Value CreateScope(const llvm::StringRef name,
 //   },
 //   "required": [ "verified" ]
 // }
-llvm::json::Value CreateBreakpoint(lldb::SBBreakpoint &bp,
+llvm::json::Value CreateBreakpoint(BreakpointBase *bp,
                                    std::optional<llvm::StringRef> request_path,
                                    std::optional<uint32_t> request_line,
                                    std::optional<uint32_t> request_column) {
-  // Each breakpoint location is treated as a separate breakpoint for VS code.
-  // They don't have the notion of a single breakpoint with multiple locations.
   llvm::json::Object object;
-  if (!bp.IsValid())
-    return llvm::json::Value(std::move(object));
-
-  object.try_emplace("verified", bp.GetNumResolvedLocations() > 0);
-  object.try_emplace("id", bp.GetID());
-  // VS Code DAP doesn't currently allow one breakpoint to have multiple
-  // locations so we just report the first one. If we report all locations
-  // then the IDE starts showing the wrong line numbers and locations for
-  // other source file and line breakpoints in the same file.
-
-  // Below we search for the first resolved location in a breakpoint and report
-  // this as the breakpoint location since it will have a complete location
-  // that is at least loaded in the current process.
-  lldb::SBBreakpointLocation bp_loc;
-  const auto num_locs = bp.GetNumLocations();
-  for (size_t i = 0; i < num_locs; ++i) {
-    bp_loc = bp.GetLocationAtIndex(i);
-    if (bp_loc.IsResolved())
-      break;
-  }
-  // If not locations are resolved, use the first location.
-  if (!bp_loc.IsResolved())
-    bp_loc = bp.GetLocationAtIndex(0);
-  auto bp_addr = bp_loc.GetAddress();
-
   if (request_path)
     object.try_emplace("source", CreateSource(*request_path));
-
-  if (bp_addr.IsValid()) {
-    std::string formatted_addr =
-        "0x" + llvm::utohexstr(bp_addr.GetLoadAddress(g_dap.target));
-    object.try_emplace("instructionReference", formatted_addr);
-    auto line_entry = bp_addr.GetLineEntry();
-    const auto line = line_entry.GetLine();
-    if (line != UINT32_MAX)
-      object.try_emplace("line", line);
-    const auto column = line_entry.GetColumn();
-    if (column != 0)
-      object.try_emplace("column", column);
-    object.try_emplace("source", CreateSource(line_entry));
-  }
+  bp->CreateJsonObject(object);
   // We try to add request_line as a fallback
   if (request_line)
     object.try_emplace("line", *request_line);
@@ -506,7 +466,7 @@ llvm::json::Value CreateModule(lldb::SBModule &module) {
   return llvm::json::Value(std::move(object));
 }
 
-void AppendBreakpoint(lldb::SBBreakpoint &bp, llvm::json::Array &breakpoints,
+void AppendBreakpoint(BreakpointBase *bp, llvm::json::Array &breakpoints,
                       std::optional<llvm::StringRef> request_path,
                       std::optional<uint32_t> request_line) {
   breakpoints.emplace_back(CreateBreakpoint(bp, request_path, request_line));
diff --git a/lldb/tools/lldb-dap/JSONUtils.h b/lldb/tools/lldb-dap/JSONUtils.h
index 62338548890c0..1515f5ba2e5f4 100644
--- a/lldb/tools/lldb-dap/JSONUtils.h
+++ b/lldb/tools/lldb-dap/JSONUtils.h
@@ -9,6 +9,7 @@
 #ifndef LLDB_TOOLS_LLDB_DAP_JSONUTILS_H
 #define LLDB_TOOLS_LLDB_DAP_JSONUTILS_H
 
+#include "BreakpointBase.h"
 #include "DAPForward.h"
 #include "lldb/API/SBModule.h"
 #include "llvm/ADT/StringRef.h"
@@ -191,7 +192,7 @@ void FillResponse(const llvm::json::Object &request,
 ///     provided by the setBreakpoints request are returned to the IDE as a
 ///     fallback.
 void AppendBreakpoint(
-    lldb::SBBreakpoint &bp, llvm::json::Array &breakpoints,
+    BreakpointBase *bp, llvm::json::Array &breakpoints,
     std::optional<llvm::StringRef> request_path = std::nullopt,
     std::optional<uint32_t> request_line = std::nullopt);
 
@@ -223,7 +224,7 @@ void AppendBreakpoint(
 ///     A "Breakpoint" JSON object with that follows the formal JSON
 ///     definition outlined by Microsoft.
 llvm::json::Value
-CreateBreakpoint(lldb::SBBreakpoint &bp,
+CreateBreakpoint(BreakpointBase *bp,
                  std::optional<llvm::StringRef> request_path = std::nullopt,
                  std::optional<uint32_t> request_line = std::nullopt,
                  std::optional<uint32_t> request_column = std::nullopt);
diff --git a/lldb/tools/lldb-dap/SourceBreakpoint.cpp b/lldb/tools/lldb-dap/SourceBreakpoint.cpp
index 3bd83c0a6874d..87e5c7177ca65 100644
--- a/lldb/tools/lldb-dap/SourceBreakpoint.cpp
+++ b/lldb/tools/lldb-dap/SourceBreakpoint.cpp
@@ -12,22 +12,14 @@
 namespace lldb_dap {
 
 SourceBreakpoint::SourceBreakpoint(const llvm::json::Object &obj)
-    : BreakpointBase(obj), line(GetUnsigned(obj, "line", 0)),
+    : Breakpoint(obj), line(GetUnsigned(obj, "line", 0)),
       column(GetUnsigned(obj, "column", 0)) {}
 
 void SourceBreakpoint::SetBreakpoint(const llvm::StringRef source_path) {
   lldb::SBFileSpecList module_list;
   bp = g_dap.target.BreakpointCreateByLocation(source_path.str().c_str(), line,
                                                column, 0, module_list);
-  // See comments in BreakpointBase::GetBreakpointLabel() for details of why
-  // we add a label to our breakpoints.
-  bp.AddName(GetBreakpointLabel());
-  if (!condition.empty())
-    SetCondition();
-  if (!hitCondition.empty())
-    SetHitCondition();
-  if (!logMessage.empty())
-    SetLogMessage();
+  Breakpoint::SetBreakpoint();
 }
 
 } // namespace lldb_dap
diff --git a/lldb/tools/lldb-dap/SourceBreakpoint.h b/lldb/tools/lldb-dap/SourceBreakpoint.h
index f4b54a44fc687..0b26048b53acf 100644
--- a/lldb/tools/lldb-dap/SourceBreakpoint.h
+++ b/lldb/tools/lldb-dap/SourceBreakpoint.h
@@ -9,17 +9,17 @@
 #ifndef LLDB_TOOLS_LLDB_DAP_SOURCEBREAKPOINT_H
 #define LLDB_TOOLS_LLDB_DAP_SOURCEBREAKPOINT_H
 
-#include "BreakpointBase.h"
+#include "Breakpoint.h"
 #include "llvm/ADT/StringRef.h"
 
 namespace lldb_dap {
 
-struct SourceBreakpoint : public BreakpointBase {
+struct SourceBreakpoint : public Breakpoint {
 
   uint32_t line;   ///< The source line of the breakpoint or logpoint
   uint32_t column; ///< An optional source column of the breakpoint
 
-  SourceBreakpoint() : BreakpointBase(), line(0), column(0) {}
+  SourceBreakpoint() : Breakpoint(), line(0), column(0) {}
   SourceBreakpoint(const llvm::json::Object &obj);
 
   // Set this breakpoint in LLDB as a new breakpoint
diff --git a/lldb/tools/lldb-dap/lldb-dap.cpp b/lldb/tools/lldb-dap/lldb-dap.cpp
index 01494dcc7da00..67022347e6d62 100644
--- a/lldb/tools/lldb-dap/lldb-dap.cpp
+++ b/lldb/tools/lldb-dap/lldb-dap.cpp
@@ -525,7 +525,8 @@ void EventThreadFunction() {
         if (event_mask & lldb::SBTarget::eBroadcastBitBreakpointChanged) {
           auto event_type =
               lldb::SBBreakpoint::GetBreakpointEventTypeFromEvent(event);
-          auto bp = lldb::SBBreakpoint::GetBreakpointFromEvent(event);
+          auto bp =
+              Breakpoint(lldb::SBBreakpoint::GetBreakpointFromEvent(event));
           // If the breakpoint was originated from the IDE, it will have the
           // BreakpointBase::GetBreakpointLabel() label attached. Regardless
           // of wether the locations were added or removed, the breakpoint
@@ -541,7 +542,7 @@ void EventThreadFunction() {
             // mapped. Note that CreateBreakpoint doesn't apply source mapping.
             // Besides, the current implementation of VSCode ignores the
             // "source" element of breakpoint events.
-            llvm::json::Value source_bp = CreateBreakpoint(bp);
+            llvm::json::Value source_bp = CreateBreakpoint(&bp);
             source_bp.getAsObject()->erase("source");
 
             body.try_emplace("breakpoint", source_bp);
@@ -2345,7 +2346,7 @@ void request_setBreakpoints(const llvm::json::Object &request) {
               existing_source_bps->second.find(src_bp.line);
           if (existing_bp != existing_source_bps->second.end()) {
             existing_bp->second.UpdateBreakpoint(src_bp);
-            AppendBreakpoint(existing_bp->second.bp, response_breakpoints, path,
+            AppendBreakpoint(&existing_bp->second, response_breakpoints, path,
                              src_bp.line);
             continue;
           }
@@ -2354,7 +2355,7 @@ void request_setBreakpoints(const llvm::json::Object &request) {
         g_dap.source_breakpoints[path][src_bp.line] = src_bp;
         SourceBreakpoint &new_bp = g_dap.source_breakpoints[path][src_bp.line];
         new_bp.SetBreakpoint(path.data());
-        AppendBreakpoint(new_bp.bp, response_breakpoints, path, new_bp.line);
+        AppendBreakpoint(&new_bp, response_breakpoints, path, new_bp.line);
       }
     }
   }
@@ -2567,7 +2568,7 @@ void request_setFunctionBreakpoints(const llvm::json::Object &request) {
       // handled it here and we don't need to set a new breakpoint below.
       request_bps.erase(request_pos);
       // Add this breakpoint info to the response
-      AppendBreakpoint(pair.second.bp, response_breakpoints);
+      AppendBreakpoint(&pair.second, response_breakpoints);
     }
   }
   // Remove any breakpoints that are no longer in our list
@@ -2581,7 +2582,7 @@ void request_setFunctionBreakpoints(const llvm::json::Object &request) {
     g_dap.function_breakpoints[pair.first()] = std::move(pair.second);
     FunctionBreakpoint &new_bp = g_dap.function_breakpoints[pair.first()];
     new_bp.SetBreakpoint();
-    AppendBreakpoint(new_bp.bp, response_breakpoints);
+    AppendBreakpoint(&new_bp, response_breakpoints);
   }
 
   llvm::json::Object body;
@@ -3582,8 +3583,8 @@ void request__testGetTargetBreakpoints(const llvm::json::Object &request) {
   FillResponse(request, response);
   llvm::json::Array response_breakpoints;
   for (uint32_t i = 0; g_dap.target.GetBreakpointAtIndex(i).IsValid(); ++i) {
-    auto bp = g_dap.target.GetBreakpointAtIndex(i);
-    AppendBreakpoint(bp, response_breakpoints);
+    auto bp = Breakpoint(g_dap.target.GetBreakpointAtIndex(i));
+    AppendBreakpoint(&bp, response_breakpoints);
   }
   llvm::json::Object body;
   body.try_emplace("breakpoints", std::move(response_breakpoints));
diff --git a/llvm/utils/gn/secondary/lldb/tools/lldb-dap/BUILD.gn b/llvm/utils/gn/secondary/lldb/tools/lldb-dap/BUILD.gn
index d8292df8c0e74..98c2068f6da29 100644
--- a/llvm/utils/gn/secondary/lldb/tools/lldb-dap/BUILD.gn
+++ b/llvm/utils/gn/secondary/lldb/tools/lldb-dap/BUILD.gn
@@ -38,6 +38,7 @@ executable("lldb-dap") {
   # FIXME: rpath/install_name stuff on macOS for framework on macOS
 
   sources = [
+    "Breakpoint.cpp",
     "BreakpointBase.cpp",
     "DAP.cpp",
     "ExceptionBreakpoint.cpp",

>From 82da694cc85ea0462fb639aa9506541fbf375496 Mon Sep 17 00:00:00 2001
From: Zequan Wu <zequanwu at google.com>
Date: Tue, 6 Feb 2024 16:12:43 -0500
Subject: [PATCH 2/3] Move logging from Breakpoint to SourceBreakpoint as
 `logMessage` may only show up in `SourceBreakpoint` json object.

---
 lldb/tools/lldb-dap/Breakpoint.cpp       | 106 --------
 lldb/tools/lldb-dap/Breakpoint.h         |   3 +-
 lldb/tools/lldb-dap/BreakpointBase.cpp   | 186 +-------------
 lldb/tools/lldb-dap/BreakpointBase.h     |  23 +-
 lldb/tools/lldb-dap/SourceBreakpoint.cpp | 298 ++++++++++++++++++++++-
 lldb/tools/lldb-dap/SourceBreakpoint.h   |  24 ++
 6 files changed, 323 insertions(+), 317 deletions(-)

diff --git a/lldb/tools/lldb-dap/Breakpoint.cpp b/lldb/tools/lldb-dap/Breakpoint.cpp
index 4ccf353b06ccc..d8401c175c979 100644
--- a/lldb/tools/lldb-dap/Breakpoint.cpp
+++ b/lldb/tools/lldb-dap/Breakpoint.cpp
@@ -21,110 +21,6 @@ void Breakpoint::SetHitCondition() {
     bp.SetIgnoreCount(hitCount - 1);
 }
 
-// logMessage will be divided into array of LogMessagePart as two kinds:
-// 1. raw print text message, and
-// 2. interpolated expression for evaluation which is inside matching curly
-//    braces.
-//
-// The function tries to parse logMessage into a list of LogMessageParts
-// for easy later access in BreakpointHitCallback.
-void Breakpoint::SetLogMessage() {
-  logMessageParts.clear();
-
-  // Contains unmatched open curly braces indices.
-  std::vector<int> unmatched_curly_braces;
-
-  // Contains all matched curly braces in logMessage.
-  // Loop invariant: matched_curly_braces_ranges are sorted by start index in
-  // ascending order without any overlap between them.
-  std::vector<std::pair<int, int>> matched_curly_braces_ranges;
-
-  lldb::SBError error;
-  // Part1 - parse matched_curly_braces_ranges.
-  // locating all curly braced expression ranges in logMessage.
-  // The algorithm takes care of nested and imbalanced curly braces.
-  for (size_t i = 0; i < logMessage.size(); ++i) {
-    if (logMessage[i] == '{') {
-      unmatched_curly_braces.push_back(i);
-    } else if (logMessage[i] == '}') {
-      if (unmatched_curly_braces.empty())
-        // Nothing to match.
-        continue;
-
-      int last_unmatched_index = unmatched_curly_braces.back();
-      unmatched_curly_braces.pop_back();
-
-      // Erase any matched ranges included in the new match.
-      while (!matched_curly_braces_ranges.empty()) {
-        assert(matched_curly_braces_ranges.back().first !=
-                   last_unmatched_index &&
-               "How can a curley brace be matched twice?");
-        if (matched_curly_braces_ranges.back().first < last_unmatched_index)
-          break;
-
-        // This is a nested range let's earse it.
-        assert((size_t)matched_curly_braces_ranges.back().second < i);
-        matched_curly_braces_ranges.pop_back();
-      }
-
-      // Assert invariant.
-      assert(matched_curly_braces_ranges.empty() ||
-             matched_curly_braces_ranges.back().first < last_unmatched_index);
-      matched_curly_braces_ranges.emplace_back(last_unmatched_index, i);
-    }
-  }
-
-  // Part2 - parse raw text and expresions parts.
-  // All expression ranges have been parsed in matched_curly_braces_ranges.
-  // The code below uses matched_curly_braces_ranges to divide logMessage
-  // into raw text parts and expression parts.
-  int last_raw_text_start = 0;
-  for (const std::pair<int, int> &curly_braces_range :
-       matched_curly_braces_ranges) {
-    // Raw text before open curly brace.
-    assert(curly_braces_range.first >= last_raw_text_start);
-    size_t raw_text_len = curly_braces_range.first - last_raw_text_start;
-    if (raw_text_len > 0) {
-      error = AppendLogMessagePart(
-          llvm::StringRef(logMessage.c_str() + last_raw_text_start,
-                          raw_text_len),
-          /*is_expr=*/false);
-      if (error.Fail()) {
-        NotifyLogMessageError(error.GetCString());
-        return;
-      }
-    }
-
-    // Expression between curly braces.
-    assert(curly_braces_range.second > curly_braces_range.first);
-    size_t expr_len = curly_braces_range.second - curly_braces_range.first - 1;
-    error = AppendLogMessagePart(
-        llvm::StringRef(logMessage.c_str() + curly_braces_range.first + 1,
-                        expr_len),
-        /*is_expr=*/true);
-    if (error.Fail()) {
-      NotifyLogMessageError(error.GetCString());
-      return;
-    }
-
-    last_raw_text_start = curly_braces_range.second + 1;
-  }
-  // Trailing raw text after close curly brace.
-  assert(last_raw_text_start >= 0);
-  if (logMessage.size() > (size_t)last_raw_text_start) {
-    error = AppendLogMessagePart(
-        llvm::StringRef(logMessage.c_str() + last_raw_text_start,
-                        logMessage.size() - last_raw_text_start),
-        /*is_expr=*/false);
-    if (error.Fail()) {
-      NotifyLogMessageError(error.GetCString());
-      return;
-    }
-  }
-
-  bp.SetCallback(BreakpointBase::BreakpointHitCallback, this);
-}
-
 void Breakpoint::CreateJsonObject(llvm::json::Object &object) {
   // Each breakpoint location is treated as a separate breakpoint for VS code.
   // They don't have the notion of a single breakpoint with multiple locations.
@@ -177,6 +73,4 @@ void Breakpoint::SetBreakpoint() {
     SetCondition();
   if (!hitCondition.empty())
     SetHitCondition();
-  if (!logMessage.empty())
-    SetLogMessage();
 }
diff --git a/lldb/tools/lldb-dap/Breakpoint.h b/lldb/tools/lldb-dap/Breakpoint.h
index a668e29f3d1e8..47a9d9c59ae2b 100644
--- a/lldb/tools/lldb-dap/Breakpoint.h
+++ b/lldb/tools/lldb-dap/Breakpoint.h
@@ -19,11 +19,10 @@ struct Breakpoint : public BreakpointBase {
 
   Breakpoint() = default;
   Breakpoint(const llvm::json::Object &obj) : BreakpointBase(obj){};
-  Breakpoint(lldb::SBBreakpoint bp): bp(bp) {}
+  Breakpoint(lldb::SBBreakpoint bp) : bp(bp) {}
 
   void SetCondition() override;
   void SetHitCondition() override;
-  void SetLogMessage() override;
   void CreateJsonObject(llvm::json::Object &object) override;
 
   bool MatchesName(const char *name);
diff --git a/lldb/tools/lldb-dap/BreakpointBase.cpp b/lldb/tools/lldb-dap/BreakpointBase.cpp
index 088ccc6b27f8e..519729f5519ff 100644
--- a/lldb/tools/lldb-dap/BreakpointBase.cpp
+++ b/lldb/tools/lldb-dap/BreakpointBase.cpp
@@ -14,187 +14,7 @@ using namespace lldb_dap;
 
 BreakpointBase::BreakpointBase(const llvm::json::Object &obj)
     : condition(std::string(GetString(obj, "condition"))),
-      hitCondition(std::string(GetString(obj, "hitCondition"))),
-      logMessage(std::string(GetString(obj, "logMessage"))) {}
-
-lldb::SBError BreakpointBase::AppendLogMessagePart(llvm::StringRef part,
-                                                   bool is_expr) {
-  if (is_expr) {
-    logMessageParts.emplace_back(part, is_expr);
-  } else {
-    std::string formatted;
-    lldb::SBError error = FormatLogText(part, formatted);
-    if (error.Fail())
-      return error;
-    logMessageParts.emplace_back(formatted, is_expr);
-  }
-  return lldb::SBError();
-}
-
-// TODO: consolidate this code with the implementation in
-// FormatEntity::ParseInternal().
-lldb::SBError BreakpointBase::FormatLogText(llvm::StringRef text,
-                                            std::string &formatted) {
-  lldb::SBError error;
-  while (!text.empty()) {
-    size_t backslash_pos = text.find_first_of('\\');
-    if (backslash_pos == std::string::npos) {
-      formatted += text.str();
-      return error;
-    }
-
-    formatted += text.substr(0, backslash_pos).str();
-    // Skip the characters before and including '\'.
-    text = text.drop_front(backslash_pos + 1);
-
-    if (text.empty()) {
-      error.SetErrorString(
-          "'\\' character was not followed by another character");
-      return error;
-    }
-
-    const char desens_char = text[0];
-    text = text.drop_front(); // Skip the desensitized char character
-    switch (desens_char) {
-    case 'a':
-      formatted.push_back('\a');
-      break;
-    case 'b':
-      formatted.push_back('\b');
-      break;
-    case 'f':
-      formatted.push_back('\f');
-      break;
-    case 'n':
-      formatted.push_back('\n');
-      break;
-    case 'r':
-      formatted.push_back('\r');
-      break;
-    case 't':
-      formatted.push_back('\t');
-      break;
-    case 'v':
-      formatted.push_back('\v');
-      break;
-    case '\'':
-      formatted.push_back('\'');
-      break;
-    case '\\':
-      formatted.push_back('\\');
-      break;
-    case '0':
-      // 1 to 3 octal chars
-      {
-        if (text.empty()) {
-          error.SetErrorString("missing octal number following '\\0'");
-          return error;
-        }
-
-        // Make a string that can hold onto the initial zero char, up to 3
-        // octal digits, and a terminating NULL.
-        char oct_str[5] = {0, 0, 0, 0, 0};
-
-        size_t i;
-        for (i = 0;
-             i < text.size() && i < 4 && (text[i] >= '0' && text[i] <= '7');
-             ++i) {
-          oct_str[i] = text[i];
-        }
-
-        text = text.drop_front(i);
-        unsigned long octal_value = ::strtoul(oct_str, nullptr, 8);
-        if (octal_value <= UINT8_MAX) {
-          formatted.push_back((char)octal_value);
-        } else {
-          error.SetErrorString("octal number is larger than a single byte");
-          return error;
-        }
-      }
-      break;
-
-    case 'x': {
-      if (text.empty()) {
-        error.SetErrorString("missing hex number following '\\x'");
-        return error;
-      }
-      // hex number in the text
-      if (isxdigit(text[0])) {
-        // Make a string that can hold onto two hex chars plus a
-        // NULL terminator
-        char hex_str[3] = {0, 0, 0};
-        hex_str[0] = text[0];
-
-        text = text.drop_front();
-
-        if (!text.empty() && isxdigit(text[0])) {
-          hex_str[1] = text[0];
-          text = text.drop_front();
-        }
-
-        unsigned long hex_value = strtoul(hex_str, nullptr, 16);
-        if (hex_value <= UINT8_MAX) {
-          formatted.push_back((char)hex_value);
-        } else {
-          error.SetErrorString("hex number is larger than a single byte");
-          return error;
-        }
-      } else {
-        formatted.push_back(desens_char);
-      }
-      break;
-    }
-
-    default:
-      // Just desensitize any other character by just printing what came
-      // after the '\'
-      formatted.push_back(desens_char);
-      break;
-    }
-  }
-  return error;
-}
-
-void BreakpointBase::NotifyLogMessageError(llvm::StringRef error) {
-  std::string message = "Log message has error: ";
-  message += error;
-  g_dap.SendOutput(OutputType::Console, message);
-}
-
-/*static*/
-bool BreakpointBase::BreakpointHitCallback(
-    void *baton, lldb::SBProcess &process, lldb::SBThread &thread,
-    lldb::SBBreakpointLocation &location) {
-  if (!baton)
-    return true;
-
-  BreakpointBase *bp = (BreakpointBase *)baton;
-  lldb::SBFrame frame = thread.GetSelectedFrame();
-
-  std::string output;
-  for (const BreakpointBase::LogMessagePart &messagePart :
-       bp->logMessageParts) {
-    if (messagePart.is_expr) {
-      // Try local frame variables first before fall back to expression
-      // evaluation
-      const std::string &expr_str = messagePart.text;
-      const char *expr = expr_str.c_str();
-      lldb::SBValue value =
-          frame.GetValueForVariablePath(expr, lldb::eDynamicDontRunTarget);
-      if (value.GetError().Fail())
-        value = frame.EvaluateExpression(expr);
-      output += VariableDescription(value).display_value;
-    } else {
-      output += messagePart.text;
-    }
-  }
-  if (!output.empty() && output.back() != '\n')
-    output.push_back('\n'); // Ensure log message has line break.
-  g_dap.SendOutput(OutputType::Console, output.c_str());
-
-  // Do not stop.
-  return false;
-}
+      hitCondition(std::string(GetString(obj, "hitCondition"))) {}
 
 void BreakpointBase::UpdateBreakpoint(const BreakpointBase &request_bp) {
   if (condition != request_bp.condition) {
@@ -205,10 +25,6 @@ void BreakpointBase::UpdateBreakpoint(const BreakpointBase &request_bp) {
     hitCondition = request_bp.hitCondition;
     SetHitCondition();
   }
-  if (logMessage != request_bp.logMessage) {
-    logMessage = request_bp.logMessage;
-    SetLogMessage();
-  }
 }
 
 const char *BreakpointBase::GetBreakpointLabel() {
diff --git a/lldb/tools/lldb-dap/BreakpointBase.h b/lldb/tools/lldb-dap/BreakpointBase.h
index a4184bfe65d27..5a04bb201615f 100644
--- a/lldb/tools/lldb-dap/BreakpointBase.h
+++ b/lldb/tools/lldb-dap/BreakpointBase.h
@@ -17,23 +17,12 @@
 namespace lldb_dap {
 
 struct BreakpointBase {
-  // logMessage part can be either a raw text or an expression.
-  struct LogMessagePart {
-    LogMessagePart(llvm::StringRef text, bool is_expr)
-        : text(text), is_expr(is_expr) {}
-    std::string text;
-    bool is_expr;
-  };
+
   // An optional expression for conditional breakpoints.
   std::string condition;
   // An optional expression that controls how many hits of the breakpoint are
   // ignored. The backend is expected to interpret the expression as needed
   std::string hitCondition;
-  // If this attribute exists and is non-empty, the backend must not 'break'
-  // (stop) but log the message instead. Expressions within {} are
-  // interpolated.
-  std::string logMessage;
-  std::vector<LogMessagePart> logMessageParts;
 
   BreakpointBase() = default;
   BreakpointBase(const llvm::json::Object &obj);
@@ -41,21 +30,11 @@ struct BreakpointBase {
 
   virtual void SetCondition() = 0;
   virtual void SetHitCondition() = 0;
-  virtual void SetLogMessage() = 0;
   virtual void CreateJsonObject(llvm::json::Object &object) = 0;
 
   void UpdateBreakpoint(const BreakpointBase &request_bp);
 
-  // Format \param text and return formatted text in \param formatted.
-  // \return any formatting failures.
-  lldb::SBError FormatLogText(llvm::StringRef text, std::string &formatted);
-  lldb::SBError AppendLogMessagePart(llvm::StringRef part, bool is_expr);
-  void NotifyLogMessageError(llvm::StringRef error);
-
   static const char *GetBreakpointLabel();
-  static bool BreakpointHitCallback(void *baton, lldb::SBProcess &process,
-                                    lldb::SBThread &thread,
-                                    lldb::SBBreakpointLocation &location);
 };
 
 } // namespace lldb_dap
diff --git a/lldb/tools/lldb-dap/SourceBreakpoint.cpp b/lldb/tools/lldb-dap/SourceBreakpoint.cpp
index 87e5c7177ca65..f5dd1346cb9e5 100644
--- a/lldb/tools/lldb-dap/SourceBreakpoint.cpp
+++ b/lldb/tools/lldb-dap/SourceBreakpoint.cpp
@@ -12,14 +12,308 @@
 namespace lldb_dap {
 
 SourceBreakpoint::SourceBreakpoint(const llvm::json::Object &obj)
-    : Breakpoint(obj), line(GetUnsigned(obj, "line", 0)),
-      column(GetUnsigned(obj, "column", 0)) {}
+    : Breakpoint(obj), logMessage(std::string(GetString(obj, "logMessage"))),
+      line(GetUnsigned(obj, "line", 0)), column(GetUnsigned(obj, "column", 0)) {
+}
 
 void SourceBreakpoint::SetBreakpoint(const llvm::StringRef source_path) {
   lldb::SBFileSpecList module_list;
   bp = g_dap.target.BreakpointCreateByLocation(source_path.str().c_str(), line,
                                                column, 0, module_list);
+  if (!logMessage.empty())
+    SetLogMessage();
   Breakpoint::SetBreakpoint();
 }
 
+void SourceBreakpoint::UpdateBreakpoint(const SourceBreakpoint &request_bp) {
+  if (logMessage != request_bp.logMessage) {
+    logMessage = request_bp.logMessage;
+    SetLogMessage();
+  }
+  BreakpointBase::UpdateBreakpoint(request_bp);
+}
+
+lldb::SBError SourceBreakpoint::AppendLogMessagePart(llvm::StringRef part,
+                                                     bool is_expr) {
+  if (is_expr) {
+    logMessageParts.emplace_back(part, is_expr);
+  } else {
+    std::string formatted;
+    lldb::SBError error = FormatLogText(part, formatted);
+    if (error.Fail())
+      return error;
+    logMessageParts.emplace_back(formatted, is_expr);
+  }
+  return lldb::SBError();
+}
+
+// TODO: consolidate this code with the implementation in
+// FormatEntity::ParseInternal().
+lldb::SBError SourceBreakpoint::FormatLogText(llvm::StringRef text,
+                                              std::string &formatted) {
+  lldb::SBError error;
+  while (!text.empty()) {
+    size_t backslash_pos = text.find_first_of('\\');
+    if (backslash_pos == std::string::npos) {
+      formatted += text.str();
+      return error;
+    }
+
+    formatted += text.substr(0, backslash_pos).str();
+    // Skip the characters before and including '\'.
+    text = text.drop_front(backslash_pos + 1);
+
+    if (text.empty()) {
+      error.SetErrorString(
+          "'\\' character was not followed by another character");
+      return error;
+    }
+
+    const char desens_char = text[0];
+    text = text.drop_front(); // Skip the desensitized char character
+    switch (desens_char) {
+    case 'a':
+      formatted.push_back('\a');
+      break;
+    case 'b':
+      formatted.push_back('\b');
+      break;
+    case 'f':
+      formatted.push_back('\f');
+      break;
+    case 'n':
+      formatted.push_back('\n');
+      break;
+    case 'r':
+      formatted.push_back('\r');
+      break;
+    case 't':
+      formatted.push_back('\t');
+      break;
+    case 'v':
+      formatted.push_back('\v');
+      break;
+    case '\'':
+      formatted.push_back('\'');
+      break;
+    case '\\':
+      formatted.push_back('\\');
+      break;
+    case '0':
+      // 1 to 3 octal chars
+      {
+        if (text.empty()) {
+          error.SetErrorString("missing octal number following '\\0'");
+          return error;
+        }
+
+        // Make a string that can hold onto the initial zero char, up to 3
+        // octal digits, and a terminating NULL.
+        char oct_str[5] = {0, 0, 0, 0, 0};
+
+        size_t i;
+        for (i = 0;
+             i < text.size() && i < 4 && (text[i] >= '0' && text[i] <= '7');
+             ++i) {
+          oct_str[i] = text[i];
+        }
+
+        text = text.drop_front(i);
+        unsigned long octal_value = ::strtoul(oct_str, nullptr, 8);
+        if (octal_value <= UINT8_MAX) {
+          formatted.push_back((char)octal_value);
+        } else {
+          error.SetErrorString("octal number is larger than a single byte");
+          return error;
+        }
+      }
+      break;
+
+    case 'x': {
+      if (text.empty()) {
+        error.SetErrorString("missing hex number following '\\x'");
+        return error;
+      }
+      // hex number in the text
+      if (isxdigit(text[0])) {
+        // Make a string that can hold onto two hex chars plus a
+        // NULL terminator
+        char hex_str[3] = {0, 0, 0};
+        hex_str[0] = text[0];
+
+        text = text.drop_front();
+
+        if (!text.empty() && isxdigit(text[0])) {
+          hex_str[1] = text[0];
+          text = text.drop_front();
+        }
+
+        unsigned long hex_value = strtoul(hex_str, nullptr, 16);
+        if (hex_value <= UINT8_MAX) {
+          formatted.push_back((char)hex_value);
+        } else {
+          error.SetErrorString("hex number is larger than a single byte");
+          return error;
+        }
+      } else {
+        formatted.push_back(desens_char);
+      }
+      break;
+    }
+
+    default:
+      // Just desensitize any other character by just printing what came
+      // after the '\'
+      formatted.push_back(desens_char);
+      break;
+    }
+  }
+  return error;
+}
+
+// logMessage will be divided into array of LogMessagePart as two kinds:
+// 1. raw print text message, and
+// 2. interpolated expression for evaluation which is inside matching curly
+//    braces.
+//
+// The function tries to parse logMessage into a list of LogMessageParts
+// for easy later access in BreakpointHitCallback.
+void SourceBreakpoint::SetLogMessage() {
+  logMessageParts.clear();
+
+  // Contains unmatched open curly braces indices.
+  std::vector<int> unmatched_curly_braces;
+
+  // Contains all matched curly braces in logMessage.
+  // Loop invariant: matched_curly_braces_ranges are sorted by start index in
+  // ascending order without any overlap between them.
+  std::vector<std::pair<int, int>> matched_curly_braces_ranges;
+
+  lldb::SBError error;
+  // Part1 - parse matched_curly_braces_ranges.
+  // locating all curly braced expression ranges in logMessage.
+  // The algorithm takes care of nested and imbalanced curly braces.
+  for (size_t i = 0; i < logMessage.size(); ++i) {
+    if (logMessage[i] == '{') {
+      unmatched_curly_braces.push_back(i);
+    } else if (logMessage[i] == '}') {
+      if (unmatched_curly_braces.empty())
+        // Nothing to match.
+        continue;
+
+      int last_unmatched_index = unmatched_curly_braces.back();
+      unmatched_curly_braces.pop_back();
+
+      // Erase any matched ranges included in the new match.
+      while (!matched_curly_braces_ranges.empty()) {
+        assert(matched_curly_braces_ranges.back().first !=
+                   last_unmatched_index &&
+               "How can a curley brace be matched twice?");
+        if (matched_curly_braces_ranges.back().first < last_unmatched_index)
+          break;
+
+        // This is a nested range let's earse it.
+        assert((size_t)matched_curly_braces_ranges.back().second < i);
+        matched_curly_braces_ranges.pop_back();
+      }
+
+      // Assert invariant.
+      assert(matched_curly_braces_ranges.empty() ||
+             matched_curly_braces_ranges.back().first < last_unmatched_index);
+      matched_curly_braces_ranges.emplace_back(last_unmatched_index, i);
+    }
+  }
+
+  // Part2 - parse raw text and expresions parts.
+  // All expression ranges have been parsed in matched_curly_braces_ranges.
+  // The code below uses matched_curly_braces_ranges to divide logMessage
+  // into raw text parts and expression parts.
+  int last_raw_text_start = 0;
+  for (const std::pair<int, int> &curly_braces_range :
+       matched_curly_braces_ranges) {
+    // Raw text before open curly brace.
+    assert(curly_braces_range.first >= last_raw_text_start);
+    size_t raw_text_len = curly_braces_range.first - last_raw_text_start;
+    if (raw_text_len > 0) {
+      error = AppendLogMessagePart(
+          llvm::StringRef(logMessage.c_str() + last_raw_text_start,
+                          raw_text_len),
+          /*is_expr=*/false);
+      if (error.Fail()) {
+        NotifyLogMessageError(error.GetCString());
+        return;
+      }
+    }
+
+    // Expression between curly braces.
+    assert(curly_braces_range.second > curly_braces_range.first);
+    size_t expr_len = curly_braces_range.second - curly_braces_range.first - 1;
+    error = AppendLogMessagePart(
+        llvm::StringRef(logMessage.c_str() + curly_braces_range.first + 1,
+                        expr_len),
+        /*is_expr=*/true);
+    if (error.Fail()) {
+      NotifyLogMessageError(error.GetCString());
+      return;
+    }
+
+    last_raw_text_start = curly_braces_range.second + 1;
+  }
+  // Trailing raw text after close curly brace.
+  assert(last_raw_text_start >= 0);
+  if (logMessage.size() > (size_t)last_raw_text_start) {
+    error = AppendLogMessagePart(
+        llvm::StringRef(logMessage.c_str() + last_raw_text_start,
+                        logMessage.size() - last_raw_text_start),
+        /*is_expr=*/false);
+    if (error.Fail()) {
+      NotifyLogMessageError(error.GetCString());
+      return;
+    }
+  }
+
+  bp.SetCallback(BreakpointHitCallback, this);
+}
+
+void SourceBreakpoint::NotifyLogMessageError(llvm::StringRef error) {
+  std::string message = "Log message has error: ";
+  message += error;
+  g_dap.SendOutput(OutputType::Console, message);
+}
+
+/*static*/
+bool SourceBreakpoint::BreakpointHitCallback(
+    void *baton, lldb::SBProcess &process, lldb::SBThread &thread,
+    lldb::SBBreakpointLocation &location) {
+  if (!baton)
+    return true;
+
+  SourceBreakpoint *bp = (SourceBreakpoint *)baton;
+  lldb::SBFrame frame = thread.GetSelectedFrame();
+
+  std::string output;
+  for (const SourceBreakpoint::LogMessagePart &messagePart :
+       bp->logMessageParts) {
+    if (messagePart.is_expr) {
+      // Try local frame variables first before fall back to expression
+      // evaluation
+      const std::string &expr_str = messagePart.text;
+      const char *expr = expr_str.c_str();
+      lldb::SBValue value =
+          frame.GetValueForVariablePath(expr, lldb::eDynamicDontRunTarget);
+      if (value.GetError().Fail())
+        value = frame.EvaluateExpression(expr);
+      output += VariableDescription(value).display_value;
+    } else {
+      output += messagePart.text;
+    }
+  }
+  if (!output.empty() && output.back() != '\n')
+    output.push_back('\n'); // Ensure log message has line break.
+  g_dap.SendOutput(OutputType::Console, output.c_str());
+
+  // Do not stop.
+  return false;
+}
+
 } // namespace lldb_dap
diff --git a/lldb/tools/lldb-dap/SourceBreakpoint.h b/lldb/tools/lldb-dap/SourceBreakpoint.h
index 0b26048b53acf..aa3fbe6d0f96d 100644
--- a/lldb/tools/lldb-dap/SourceBreakpoint.h
+++ b/lldb/tools/lldb-dap/SourceBreakpoint.h
@@ -15,6 +15,18 @@
 namespace lldb_dap {
 
 struct SourceBreakpoint : public Breakpoint {
+  // logMessage part can be either a raw text or an expression.
+  struct LogMessagePart {
+    LogMessagePart(llvm::StringRef text, bool is_expr)
+        : text(text), is_expr(is_expr) {}
+    std::string text;
+    bool is_expr;
+  };
+  // If this attribute exists and is non-empty, the backend must not 'break'
+  // (stop) but log the message instead. Expressions within {} are
+  // interpolated.
+  std::string logMessage;
+  std::vector<LogMessagePart> logMessageParts;
 
   uint32_t line;   ///< The source line of the breakpoint or logpoint
   uint32_t column; ///< An optional source column of the breakpoint
@@ -24,6 +36,18 @@ struct SourceBreakpoint : public Breakpoint {
 
   // Set this breakpoint in LLDB as a new breakpoint
   void SetBreakpoint(const llvm::StringRef source_path);
+  void UpdateBreakpoint(const SourceBreakpoint &request_bp);
+
+  void SetLogMessage();
+  // Format \param text and return formatted text in \param formatted.
+  // \return any formatting failures.
+  lldb::SBError FormatLogText(llvm::StringRef text, std::string &formatted);
+  lldb::SBError AppendLogMessagePart(llvm::StringRef part, bool is_expr);
+  void NotifyLogMessageError(llvm::StringRef error);
+
+  static bool BreakpointHitCallback(void *baton, lldb::SBProcess &process,
+                                    lldb::SBThread &thread,
+                                    lldb::SBBreakpointLocation &location);
 };
 
 inline bool operator<(const SourceBreakpoint &lhs,

>From 3bfc9f943eb07f81b098aebb1efe35eb88568ef8 Mon Sep 17 00:00:00 2001
From: Zequan Wu <zequanwu at google.com>
Date: Wed, 7 Feb 2024 14:07:53 -0500
Subject: [PATCH 3/3] remove `*- C++ -*` from Breakpoint.cpp comment

---
 lldb/tools/lldb-dap/Breakpoint.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lldb/tools/lldb-dap/Breakpoint.cpp b/lldb/tools/lldb-dap/Breakpoint.cpp
index d8401c175c979..0c33d4b114d76 100644
--- a/lldb/tools/lldb-dap/Breakpoint.cpp
+++ b/lldb/tools/lldb-dap/Breakpoint.cpp
@@ -1,4 +1,4 @@
-//===-- Breakpoint.cpp ------------------------------------------*- C++ -*-===//
+//===-- Breakpoint.cpp ----------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.



More information about the llvm-commits mailing list