add explicit casts for clang

[pknowles]

Summary by CodeRabbit

• Bug Fixes
  • Improved type handling and alignment calculations in Linux memory-mapped file operations. This reduces rare alignment-related failures during file resizing and memory synchronization, improves arithmetic consistency across platforms, and enhances overall stability and reliability of file-backed memory usage.

[coderabbitai]

Warning

Rate limit exceeded

@pknowles has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 18 minutes and 37 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

Walkthrough

Refined type casts in Linux memory-mapped file code: ftruncate size is cast to off_t; page-size values are cast to size_t for alignment masks in MemoryMap::sync; and resizing arithmetic in ResizableMappedMemory uses size_t casts.

Changes

Cohort / File(s)	Summary
Type safety & alignment fixes include/decodeless/detail/mappedfile_linux.hpp	Cast ftruncate size argument to off_t; cast (pageSize() - 1) and page-size usages to size_t for bitmask/alignment and resize calculations.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Possibly related PRs

• Fix compilation on Linux, macOS and Windows. #10: Also changes mapping-related code in include/decodeless/detail/mappedfile_linux.hpp, focusing on MemoryMap and resizable mapping behavior.

Poem

🐰 I nibble at casts, tidy and spry,

off_t for truncate, page masks comply.
Size_t aligns where bits once slipped,
Mappings snug now, no misfit crypt.
A little hop — safe syscalls fly! 🥕

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'add explicit casts for clang' accurately describes the main change—adding explicit type casts to improve clang compiler compatibility.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch pknowles/casts_for_clang

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 3

🤖 Fix all issues with AI agents

In `@include/decodeless/detail/mappedfile_linux.hpp`:
- Around line 297-298: Change the C-style cast to a C++ cast by replacing
size_t(pageSize()) with static_cast<size_t>(pageSize()), and replace the
division/multiplication alignment used to compute newMappedSize with a
power-of-two bitmask rounding approach (round up to the next multiple of ps
using a mask based on ps-1 since pageSize() is power-of-two) so the alignment
idiom matches the one used elsewhere in this file.
- Line 136: The expression that computes alignedOffset uses a functional-style
cast; change it to use an explicit C++ cast by replacing size_t(pageSize() - 1)
with static_cast<size_t>(pageSize() - 1) in the alignedOffset calculation (the
variables/functions involved: alignedOffset, offset, pageSize()); optionally
consider aligning pageSize()'s return type to size_t on Linux to remove the need
for casts across mappedfile_linux.hpp.
- Line 77: Replace the C-style functional cast off_t(size) in the ftruncate call
with an explicit static_cast: use static_cast<off_t>(size) when calling
ftruncate(m_fd, ...), and add a pre-check that the unsigned/integral variable
size does not exceed std::numeric_limits<off_t>::max() (handle the error path if
it does) to avoid signed overflow/UB; update the code around the ftruncate
invocation in mappedfile_linux.hpp where m_fd and size are used to perform this
bounds check before casting and truncating.

[coderabbitai]

🧹 Nitpick | 🔵 Trivial

Prefer static_cast<off_t>(size) over functional-style cast.

off_t(size) is a C-style (functional notation) cast. In C++ codebases, static_cast<off_t>(size) is preferred as it's more explicit and grep-friendly, and it won't silently degrade to a reinterpret_cast if types change in the future.

Also, if size exceeds std::numeric_limits<off_t>::max(), this is signed integer overflow (UB). Consider a bounds check before truncating.

Suggested fix

-        if (ftruncate(m_fd, off_t(size)) == -1)
+        if (ftruncate(m_fd, static_cast<off_t>(size)) == -1)

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	if (ftruncate(m_fd, off_t(size)) == -1)
	if (ftruncate(m_fd, static_cast<off_t>(size)) == -1)

🤖 Prompt for AI Agents

In `@include/decodeless/detail/mappedfile_linux.hpp` at line 77, Replace the
C-style functional cast off_t(size) in the ftruncate call with an explicit
static_cast: use static_cast<off_t>(size) when calling ftruncate(m_fd, ...), and
add a pre-check that the unsigned/integral variable size does not exceed
std::numeric_limits<off_t>::max() (handle the error path if it does) to avoid
signed overflow/UB; update the code around the ftruncate invocation in
mappedfile_linux.hpp where m_fd and size are used to perform this bounds check
before casting and truncating.