totph created this revision.
totph added reviewers: jkorous, arphaman, ributzka.
Herald added a subscriber: mgrang.
Herald added a project: All.
totph requested review of this revision.
Herald added subscribers: cfe-commits, MaskRay.
Herald added a project: clang.
[clang] Deterministic `-gen-cdb-fragment-path` filenames
The files written into the given target directory follow the pattern
`ab.c.X.json`.
Instead of X being 4 randomly generated hexadecimal chars, it is now
a deterministic hash of the input and output filenames encoded in
10 base64 chars.
This means the output directory no longer fills up with duplicates,
and concatenating the `*.json` files continues to generates a useful
compilation database even after the first full project build.
The output file is also hashed so that these compiler calls can be
distinguished:
`clang -c ab.c -o ab.o`
`clang -c ab.c -D_BAR_ -o bar.o`
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D156142
Files:
clang/lib/Driver/ToolChains/Clang.cpp
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -45,6 +45,8 @@
#include "llvm/ADT/StringExtras.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Option/ArgList.h"
+#include "llvm/Support/BLAKE3.h"
+#include "llvm/Support/Base64.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Compression.h"
@@ -2479,13 +2481,38 @@
return;
}
- llvm::sys::path::append(
- Path,
- Twine(llvm::sys::path::filename(Input.getFilename())) + ".%%%%.json");
+ // Append the Input basename and a .XXXXXXXXXX.json suffix, where
+ // X is base64-ish and derived from the Input and Output filenames.
+ auto AppendBasenameAndHash = [](SmallString<256> &Path,
+ const InputInfo &Input,
+ const InputInfo &Output) {
+ llvm::TruncatedBLAKE3<8> Hash;
+ llvm::BLAKE3Result<8> HashResult;
+ Hash.update(llvm::StringRef(Input.getFilename()));
+ // Simpler value separation than that of HashBuilder, so external tools
+ // can deduce the filename easier:
+ Hash.update('\0');
+ Hash.update(llvm::StringRef(Output.getFilename()));
+ Hash.final(HashResult);
+
+ std::string Base64Hash = llvm::encodeBase64(HashResult);
+ // Base64: 8 * 1.33 (encoding efficiency) > 10
+ Base64Hash.resize(10);
+ // Make the base64 string filesystem and url safe by mapping + to -
+ // and / to _, see RFC 4648#section-5
+ for (char &c : Base64Hash) {
+ c = (c == '+') ? '-' : ((c == '/') ? '_' : c);
+ }
+ llvm::sys::path::append(
+ Path, Twine(llvm::sys::path::filename(Input.getFilename())) + "." +
+ StringRef(Base64Hash) + ".json");
+ };
+
+ AppendBasenameAndHash(Path, Input, Output);
+
int FD;
- SmallString<256> TempPath;
- Err = llvm::sys::fs::createUniqueFile(Path, FD, TempPath,
- llvm::sys::fs::OF_Text);
+ Err = llvm::sys::fs::openFileForWrite(
+ Path, FD, llvm::sys::fs::CD_CreateAlways, llvm::sys::fs::OF_Text);
if (Err) {
Driver.Diag(diag::err_drv_compilationdatabase) << Path << Err.message();
return;
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -45,6 +45,8 @@
#include "llvm/ADT/StringExtras.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Option/ArgList.h"
+#include "llvm/Support/BLAKE3.h"
+#include "llvm/Support/Base64.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Compression.h"
@@ -2479,13 +2481,38 @@
return;
}
- llvm::sys::path::append(
- Path,
- Twine(llvm::sys::path::filename(Input.getFilename())) + ".%%%%.json");
+ // Append the Input basename and a .XXXXXXXXXX.json suffix, where
+ // X is base64-ish and derived from the Input and Output filenames.
+ auto AppendBasenameAndHash = [](SmallString<256> &Path,
+ const InputInfo &Input,
+ const InputInfo &Output) {
+ llvm::TruncatedBLAKE3<8> Hash;
+ llvm::BLAKE3Result<8> HashResult;
+ Hash.update(llvm::StringRef(Input.getFilename()));
+ // Simpler value separation than that of HashBuilder, so external tools
+ // can deduce the filename easier:
+ Hash.update('\0');
+ Hash.update(llvm::StringRef(Output.getFilename()));
+ Hash.final(HashResult);
+
+ std::string Base64Hash = llvm::encodeBase64(HashResult);
+ // Base64: 8 * 1.33 (encoding efficiency) > 10
+ Base64Hash.resize(10);
+ // Make the base64 string filesystem and url safe by mapping + to -
+ // and / to _, see RFC 4648#section-5
+ for (char &c : Base64Hash) {
+ c = (c == '+') ? '-' : ((c == '/') ? '_' : c);
+ }
+ llvm::sys::path::append(
+ Path, Twine(llvm::sys::path::filename(Input.getFilename())) + "." +
+ StringRef(Base64Hash) + ".json");
+ };
+
+ AppendBasenameAndHash(Path, Input, Output);
+
int FD;
- SmallString<256> TempPath;
- Err = llvm::sys::fs::createUniqueFile(Path, FD, TempPath,
- llvm::sys::fs::OF_Text);
+ Err = llvm::sys::fs::openFileForWrite(
+ Path, FD, llvm::sys::fs::CD_CreateAlways, llvm::sys::fs::OF_Text);
if (Err) {
Driver.Diag(diag::err_drv_compilationdatabase) << Path << Err.message();
return;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
